mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-14 17:02:19 +00:00
Compare commits
4
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Garry Tan
|
f23c24dc82 | ||
|
Garry TanandClaude Opus 4.8
|
6be5095ef9 | ||
|
Garry TanandClaude Opus 4.8
|
d2599ba89b | ||
|
Garry Tan
|
c559931f1e |
@@ -1,32 +0,0 @@
|
||||
name: Actionlint
|
||||
|
||||
# Lints the GitHub Actions workflow YAML on every change so a malformed
|
||||
# workflow / bad action ref / missing-permission bug is caught before it ships
|
||||
# a broken pipeline. gbrain edits .github/workflows/* often (sharding, cache,
|
||||
# timeouts); this is the cheap guard that keeps those edits honest.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [master]
|
||||
paths:
|
||||
- '.github/workflows/**'
|
||||
pull_request:
|
||||
branches: [master]
|
||||
paths:
|
||||
- '.github/workflows/**'
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
actionlint:
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 5
|
||||
steps:
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
- uses: rhysd/actionlint@393031adb9afb225ee52ae2ccd7a5af5525e03e8 # v1.7.11
|
||||
@@ -12,61 +12,10 @@ on:
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
# Cancel a superseded run when a newer commit lands on the same PR/branch.
|
||||
# PR number for pull_request events (fork-safe), github.ref fallback for
|
||||
# push/scheduled runs.
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
jsonb-parity:
|
||||
# Dedicated required guard for the JSONB double-encode bug-class (#2339).
|
||||
# PGLite parses a double-encoded jsonb string silently, so this assertion can
|
||||
# ONLY be made on real Postgres — a normal gated e2e file would skip without
|
||||
# DATABASE_URL and let the bug ship green (as #2339 did). This job provisions
|
||||
# Postgres and HARD-FAILS if DATABASE_URL is missing, so the guard can never
|
||||
# silently skip.
|
||||
name: JSONB parity (#2339 regression guard)
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 15
|
||||
services:
|
||||
postgres:
|
||||
image: pgvector/pgvector:pg16
|
||||
env:
|
||||
POSTGRES_USER: postgres
|
||||
POSTGRES_PASSWORD: postgres
|
||||
POSTGRES_DB: gbrain_test
|
||||
ports:
|
||||
- 5432:5432
|
||||
options: >-
|
||||
--health-cmd pg_isready
|
||||
--health-interval 10s
|
||||
--health-timeout 5s
|
||||
--health-retries 5
|
||||
steps:
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
|
||||
with:
|
||||
bun-version: 1.3.13
|
||||
- run: bun install
|
||||
- name: Require DATABASE_URL (no silent skip)
|
||||
env:
|
||||
DATABASE_URL: postgresql://postgres:postgres@localhost:5432/gbrain_test
|
||||
run: |
|
||||
if [ -z "$DATABASE_URL" ]; then
|
||||
echo "::error::DATABASE_URL must be set for the jsonb-parity job — the #2339 guard would silently skip (the exact failure PGLite hides). Failing the job." >&2
|
||||
exit 1
|
||||
fi
|
||||
- name: Run JSONB double-encode parity tests on real Postgres
|
||||
env:
|
||||
DATABASE_URL: postgresql://postgres:postgres@localhost:5432/gbrain_test
|
||||
run: bun test test/e2e/op-checkpoint-jsonb-parity.test.ts test/e2e/jsonb-roundtrip.test.ts
|
||||
|
||||
tier1:
|
||||
name: Tier 1 (Mechanical)
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 20
|
||||
services:
|
||||
postgres:
|
||||
image: pgvector/pgvector:pg16
|
||||
@@ -100,7 +49,6 @@ jobs:
|
||||
# from repo/org secrets. Nightly + manual triggers still supported via
|
||||
# the workflow-level `on:` list.
|
||||
needs: tier1
|
||||
timeout-minutes: 30
|
||||
services:
|
||||
postgres:
|
||||
image: pgvector/pgvector:pg16
|
||||
@@ -122,22 +70,7 @@ jobs:
|
||||
bun-version: 1.3.13
|
||||
- run: bun install
|
||||
- name: Install OpenClaw
|
||||
# Bound + retry the install: a transient npm/registry stall here used to
|
||||
# hang unbounded and (since the v0.42.50.0 job timeout) burn the entire
|
||||
# 30m Tier 2 budget before failing — even though the install normally
|
||||
# finishes in well under a minute. `timeout` kills a hung attempt fast;
|
||||
# up to 3 attempts ride out a flaky registry. Step cap is a backstop.
|
||||
timeout-minutes: 8
|
||||
run: |
|
||||
for attempt in 1 2 3; do
|
||||
if timeout 120 npm install -g openclaw@2026.4.9; then
|
||||
exit 0
|
||||
fi
|
||||
echo "::warning::openclaw install attempt $attempt failed or timed out; retrying in 10s" >&2
|
||||
sleep 10
|
||||
done
|
||||
echo "::error::openclaw install failed after 3 attempts" >&2
|
||||
exit 1
|
||||
run: npm install -g openclaw@2026.4.9
|
||||
- name: Configure OpenClaw MCP
|
||||
run: |
|
||||
mkdir -p ~/.openclaw
|
||||
|
||||
@@ -1,33 +0,0 @@
|
||||
name: OSV-Scanner
|
||||
|
||||
# Dependency vulnerability scan (#2182) via Google's official reusable
|
||||
# workflow. Runs weekly and on any PR that touches the dependency manifests.
|
||||
# Tokenless: needs zero secrets. Findings are reported in the job log and as
|
||||
# a SARIF artifact on the run; code-scanning upload is deliberately disabled
|
||||
# so the workflow stays read-only (no security-events: write).
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
branches: [master]
|
||||
paths:
|
||||
- 'bun.lock'
|
||||
- 'package.json'
|
||||
schedule:
|
||||
- cron: '30 6 * * 1' # weekly, Monday 06:30 UTC
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
osv-scan:
|
||||
permissions:
|
||||
actions: read
|
||||
contents: read
|
||||
# Required by the reusable workflow's own top-level permissions block —
|
||||
# GitHub validates the caller grants a superset AT STARTUP, even with
|
||||
# upload-sarif: false (nothing is actually uploaded; see #2117 upstream).
|
||||
security-events: write
|
||||
uses: google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@9a498708959aeaef5ef730655706c5a1df1edbc2 # v2.3.8
|
||||
with:
|
||||
upload-sarif: false
|
||||
@@ -19,10 +19,6 @@ jobs:
|
||||
target: bun-linux-x64
|
||||
artifact: gbrain-linux-x64
|
||||
runs-on: ${{ matrix.os }}
|
||||
permissions:
|
||||
contents: read
|
||||
id-token: write # for attest-build-provenance (Sigstore OIDC)
|
||||
attestations: write # for attest-build-provenance
|
||||
steps:
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
|
||||
@@ -30,12 +26,7 @@ jobs:
|
||||
bun-version: 1.3.13
|
||||
- run: bun install
|
||||
- run: bun test
|
||||
- run: bun run verify
|
||||
- run: bun build --compile --target=${{ matrix.target }} --outfile bin/${{ matrix.artifact }} src/cli.ts
|
||||
- name: Attest build provenance
|
||||
uses: actions/attest-build-provenance@0f67c3f4856b2e3261c31976d6725780e5e4c373 # v4.1.1
|
||||
with:
|
||||
subject-path: bin/${{ matrix.artifact }}
|
||||
- uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
|
||||
with:
|
||||
name: ${{ matrix.artifact }}
|
||||
|
||||
@@ -1,36 +0,0 @@
|
||||
name: Semgrep
|
||||
|
||||
# Static analysis (SAST) with Semgrep Community Edition (#2272). Tokenless:
|
||||
# uses the public registry rulesets, needs zero secrets. Findings print in
|
||||
# the job log; no code-scanning/SARIF upload by design (keeps permissions
|
||||
# read-only, no security-events: write).
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
branches: [master]
|
||||
schedule:
|
||||
- cron: '30 7 * * 1' # weekly, Monday 07:30 UTC
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
semgrep:
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 20
|
||||
container:
|
||||
image: semgrep/semgrep:1.170.0@sha256:c98f8829eea377274ee4b10656458b078b88232469b2ff913f091c2317347c9d
|
||||
steps:
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
# Non-blocking initially (continue-on-error): the first runs establish a
|
||||
# baseline without failing unrelated PRs. Graduation path: once the
|
||||
# baseline findings are triaged (fixed or `# nosemgrep`'d), remove
|
||||
# continue-on-error so new findings block PRs.
|
||||
- name: Semgrep scan (report-only)
|
||||
run: semgrep scan --config p/default --config p/typescript --error
|
||||
continue-on-error: true
|
||||
@@ -14,15 +14,6 @@ on:
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
# Cancel a superseded run when a newer commit lands on the same PR/branch.
|
||||
# Keyed on the PR number for pull_request events (unique per PR, so two PRs
|
||||
# from forks sharing a branch name don't cancel each other) and falls back to
|
||||
# github.ref for push/scheduled runs. Mirrors heavy-tests.yml; frees runners
|
||||
# and stops a stale-SHA run from reporting a flaky failure on an obsolete commit.
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
# cache-check: runs first, computes the content hash of every tracked
|
||||
@@ -38,7 +29,6 @@ jobs:
|
||||
# ──────────────────────────────────────────────────────────────────────
|
||||
cache-check:
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 10
|
||||
outputs:
|
||||
hit: ${{ steps.lookup.outputs.cache-hit }}
|
||||
hash: ${{ steps.compute.outputs.hash }}
|
||||
@@ -82,7 +72,6 @@ jobs:
|
||||
needs: cache-check
|
||||
if: needs.cache-check.outputs.hit != 'true'
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 10
|
||||
steps:
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
with:
|
||||
@@ -101,7 +90,6 @@ jobs:
|
||||
needs: cache-check
|
||||
if: needs.cache-check.outputs.hit != 'true'
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 12
|
||||
steps:
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
|
||||
@@ -122,7 +110,6 @@ jobs:
|
||||
needs: cache-check
|
||||
if: needs.cache-check.outputs.hit != 'true'
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 15
|
||||
steps:
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
|
||||
@@ -147,7 +134,6 @@ jobs:
|
||||
needs: cache-check
|
||||
if: needs.cache-check.outputs.hit != 'true'
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 12
|
||||
steps:
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
|
||||
@@ -170,7 +156,6 @@ jobs:
|
||||
needs: cache-check
|
||||
if: needs.cache-check.outputs.hit != 'true'
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 12
|
||||
steps:
|
||||
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
||||
- uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
|
||||
@@ -206,7 +191,6 @@ jobs:
|
||||
needs: cache-check
|
||||
if: needs.cache-check.outputs.hit != 'true'
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 15
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
@@ -236,7 +220,6 @@ jobs:
|
||||
needs: [cache-check, gitleaks, verify, serial-tests, slow-eval-longmemeval, slow-entity-resolve-perf, test]
|
||||
if: success() && needs.cache-check.outputs.hit != 'true'
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 5
|
||||
steps:
|
||||
- name: Create cache marker
|
||||
run: |
|
||||
@@ -259,7 +242,6 @@ jobs:
|
||||
needs: [cache-check, gitleaks, verify, serial-tests, slow-eval-longmemeval, slow-entity-resolve-perf, test]
|
||||
if: always()
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 5
|
||||
steps:
|
||||
- name: Aggregate result
|
||||
run: |
|
||||
|
||||
@@ -104,9 +104,8 @@ writing or reviewing an operation, consult `src/core/operations.ts` for the cont
|
||||
## Before shipping
|
||||
|
||||
Easiest path: `bun run ci:local` runs the full CI gate inside Docker (gitleaks,
|
||||
guards + typecheck, then 4-shard parallel unit + E2E against four pgvector
|
||||
containers plus a transaction-mode PgBouncer; unit phase keeps `DATABASE_URL`
|
||||
unset) and tears down. Use `bun run ci:local:diff` for the
|
||||
unit tests with `DATABASE_URL` unset, then all 29 E2E files sequentially against a
|
||||
fresh pgvector container) and tears down. Use `bun run ci:local:diff` for the
|
||||
diff-aware subset during fast iteration on a focused branch. Requires Docker
|
||||
(Docker Desktop / OrbStack / Colima) and `gitleaks` (`brew install gitleaks`).
|
||||
|
||||
|
||||
+4
-616
@@ -2,620 +2,6 @@
|
||||
|
||||
All notable changes to GBrain will be documented in this file.
|
||||
|
||||
## [0.42.64.0] - 2026-07-20
|
||||
|
||||
### Fixed
|
||||
|
||||
- Confidential OAuth clients can now revoke access tokens through the standard revocation endpoint when client secrets are stored as hashes. Invalid credentials fail closed, malformed or mixed authentication is rejected, backend failures remain retryable, and discovery metadata accurately advertises supported authentication methods.
|
||||
|
||||
No schema migrations.
|
||||
## [0.42.63.0] - 2026-07-20
|
||||
|
||||
**Schema commands now open the local brain you actually configured.**
|
||||
|
||||
If your PGLite brain lives at a custom path, commands such as `gbrain schema stats` previously ignored that path and could inspect the default brain instead. That made a healthy configured brain look empty or report the wrong schema counts. Schema commands now use the same complete database configuration as the rest of GBrain. PostgreSQL behavior is unchanged, and no migration is required.
|
||||
|
||||
### How to use it
|
||||
|
||||
Upgrade, then run the schema command normally:
|
||||
|
||||
```bash
|
||||
gbrain upgrade
|
||||
gbrain schema stats --json
|
||||
```
|
||||
|
||||
The reported page and type counts now come from the `database_path` in `~/.gbrain/config.json` when the engine is PGLite.
|
||||
|
||||
### Itemized changes
|
||||
|
||||
#### Fixed
|
||||
- **Schema CLI commands preserve configured PGLite paths.** Engine construction and connection now receive the canonical complete engine configuration, including both `database_path` and `database_url` where applicable.
|
||||
- **CLI tests are isolated from ambient database URLs.** Schema subprocess tests explicitly clear inherited PostgreSQL URL variables, and a persistent-PGLite regression test proves `schema stats` reads the configured database rather than the default brain.
|
||||
|
||||
## [0.42.62.0] - 2026-07-17
|
||||
|
||||
**If your brain holds more than one source, everything now lands in the right one. Link extraction, timeline extraction, background cycles, and webhook captures used to quietly file some of their output under the default source; all of those paths now carry the correct source identity. Background agent jobs got tougher too: a failed database reconnect can no longer wedge the engine, and workers recover from dropped connections instead of crash-looping. If you run the admin dashboard behind a reverse proxy, the live activity panel finally connects. Long agent conversations cost less because repeated context is reused between turns on Anthropic calls. Local LiteLLM proxies work out of the box. Nested sources scan correctly again instead of reporting zero files. And the project's automated checks now include dependency vulnerability scanning, static code-security analysis, and signed provenance for release builds. Thirty merged changes in all, the largest batch to date, each one reviewed and verified against the live codebase before landing.**
|
||||
|
||||
## To take advantage of v0.42.62.0
|
||||
|
||||
`gbrain upgrade`. No new schema migrations.
|
||||
|
||||
1. **Multi-source brains:** run `gbrain extract all` once (or let the next cycle do it) so previously mis-scoped link and timeline rows are regenerated under the right source.
|
||||
2. **If you serve the admin dashboard behind a reverse proxy,** hard-refresh it once after upgrading; Live Activity should connect.
|
||||
3. **Verify:**
|
||||
```bash
|
||||
gbrain doctor
|
||||
gbrain stats
|
||||
```
|
||||
4. **If any step fails,** please file an issue at https://github.com/garrytan/gbrain/issues with the output of `gbrain doctor`.
|
||||
|
||||
### Itemized changes
|
||||
|
||||
#### Fixed
|
||||
- **Source identity threaded through write paths.** Filesystem link/timeline extraction (`src/commands/extract.ts`), the cycle extract phase, and ingest capture now stamp the resolved source id instead of defaulting to `default`, with fail-closed validation on externally supplied ids. (#1522, #1747, #1503 via #2920; absorbs #1719, contributed by @seungsu)
|
||||
- **`reconnect()` is build-then-swap.** The new pool is validated before replacing the old one, so a failed rebuild restores the previous connection instead of leaving `_sql` null. (#1593 follow-up via #1906, contributed by @rayers)
|
||||
- **Minion worker reconnects after promote-time connection loss** instead of crash-looping. (#1491 class via #2025, contributed by @maxpetrusenkoagent)
|
||||
- **Admin Live Activity works behind reverse proxies.** The EventSource now sends credentials so strict-cookie sessions survive the proxy hop. (#912 via #1560, contributed by @flamerged)
|
||||
- **Stats exclude soft-deleted pages** from visible counts on both engines; destructive-removal counts stay all-inclusive. (#2235, contributed by @xd-Neji)
|
||||
- **LiteLLM recipes declare chat and expansion touchpoints,** so the subagent loop no longer swaps to Anthropic and fails without an Anthropic key. (#2207 via #2208, contributed by @brettdavies)
|
||||
- **Rolling prompt-cache on the direct SDK path.** Growing conversations place rolling cache breakpoints (two, within the four-marker budget), cutting repeat-token cost on multi-turn Anthropic tool loops. (#2740 via #2771, contributed by @Masashi-Ono0611)
|
||||
- **Nested sources scan again.** `sources audit` had one inverted prune check (descending into node_modules while reporting 0 files). (#2678, contributed by @ikamal97)
|
||||
- **Import and sync agree on metafiles.** The import walker now skips the same structural metafiles sync skips. (#345 via #2315, contributed by @ElliotDrel)
|
||||
- **Frontmatter scans respect git excludes** via a shared git-visible-files helper. (#2462, contributed by @kubi-dev)
|
||||
- **Sync renames are crash-safe** (per-file failures recorded instead of aborting the run) and **zero-change syncs still bump `last_sync_at`** so freshness reporting stops lying. (#2402, contributed by @supportswift; #2335, contributed by @lost9999)
|
||||
- **Facts survive one-shot CLI runs.** Facts-absorb work is enqueued as durable minion jobs instead of dying with the process exit drain; fence paths are source-scoped. (#2104, contributed by @reghar-bot)
|
||||
- **Takes reads are source-scoped, `gbrain calibration` is reachable, outputs are BigInt-safe.** (#2035 and the takes slice of #2200 via #2892, takeover of #2452, contributed by @spinsirr)
|
||||
- **CLI answers honestly.** `config get` reads both config planes with provenance, `sources archive` is idempotent, help text matches real subcommands, doctor recommendations name commands that exist. (#2120, #2792, #1175, #1123, #2451 via #2918)
|
||||
- **PGLite init failures name plausible causes for your platform** instead of blaming a macOS-specific bug everywhere, and non-Error crashes print their message instead of `[object Object]`. (#2674 class via #2891)
|
||||
- **YAML comments inside frontmatter parse.** `#` lines inside a closed fence are comments, not headings; no more false MISSING_CLOSE. (#2152 via #2153, contributed by @brettdavies)
|
||||
- **Conversation facts read the raw transcript sidecar** and recognize plain `Speaker A:` lines. (#1897 via #1898, contributed by @ElliotDrel)
|
||||
- **`get_timeline` exposes date-window filters** (#2604 via #2694, contributed by @RerankerGuo) and **`query` since/until filter on effective date,** not updated_at (#1520 via #1706, contributed by @mvanhorn).
|
||||
- **Windows serve watchdog works** via a signal-0 liveness probe instead of a POSIX-only process listing. (#2049, contributed by @abyss-node)
|
||||
- **Doctor probes route through the active engine** (no false pgvector/jsonb warnings on PGLite; #1513 via #1183, contributed by @duncanclaw) and **a disabled retrieval reflex reads as intentional** (#2459, contributed by @eloe).
|
||||
- **Cross-platform installs.** The postinstall hook is a real bun script, not POSIX shell that failed on Windows. (#1486 via #1554, contributed by @Sanjays2402)
|
||||
- **Agent-bound auth clients.** `auth register-client` gains the `--bound-*` flags the submit_agent gate requires. (#1945, #1971 via #1976, contributed by @mzkarami)
|
||||
|
||||
#### Added
|
||||
- **Security automation in the project's checks:** scheduled OSV dependency scanning, Semgrep static analysis on every PR (non-blocking initially), and build-provenance attestations wired into the release workflow. (#2182, #2142, #2272 via #2917)
|
||||
- **`provider_chat_options` config passthrough** to the gateway, e.g. disabling thinking mode per provider or model. (#2577 via #2857)
|
||||
- **Docs:** macOS 26.x PGLite workaround and native Postgres setup guide. (#1671, contributed by @roysaurav)
|
||||
|
||||
#### Internal
|
||||
- release.yml runs `verify` before building. (#2222 via #2243, contributed by @mzkarami)
|
||||
- Regenerated llms bundle after the docs merge. (#2893)
|
||||
|
||||
## [0.42.61.0] - 2026-07-16
|
||||
|
||||
**If gbrain's background daemon dies hard, a restart now takes over right away instead of waiting minutes for a stale lock to expire. Re-processing the same content no longer piles up near-duplicate knowledge atoms. On large brains, the takes bootstrap finally works through the whole corpus instead of re-scanning the same newest pages every run. And `gbrain schema use` can now activate the schema packs gbrain actually ships — including the install default — instead of just one hardcoded name. Cost tracking also learns the newest Claude models, so spend on them is metered instead of invisible.**
|
||||
|
||||
### Itemized changes
|
||||
|
||||
#### Fixed
|
||||
- **Autopilot recovers immediately from a crashed daemon.** The stale-lock check verifies whether the lock-holding process is still alive instead of relying on a fixed age window — a hard-killed autopilot no longer delays restarts, and the age check alone can no longer displace a busy, live one. (#477, contributed by @vinsew)
|
||||
- **Atom extraction stops minting duplicate atoms across runs.** Atom slugs are now deterministic (source-dated, canonical slugging, content-hashed suffix), so re-extracting the same content upserts instead of creating a near-duplicate under a new run-date path, and titles that truncate mid-word no longer produce trailing-dash slug variants. Pre-existing duplicates are not re-created but remain until cleaned up (an `atoms consolidate` command is tracked as a follow-up). (#2482, contributed by @joelwp)
|
||||
- **Takes bootstrap works through the whole corpus.** Bootstrap runs skip pages that already have takes, so brains larger than the per-run page cap make forward progress instead of rescanning the newest slice and re-spending extraction budget. `--include-covered` restores the old behavior. (#2638, contributed by @p3ob7o)
|
||||
- **`gbrain schema use` can activate the core bundled packs.** The command resolved only one hardcoded pack name; it now resolves through the bundled-pack registry, so the recommended and v2 base packs (including the install default) can be selected. (#1707, contributed by @mvanhorn)
|
||||
- **Budget tracking prices Sonnet 5 and Fable 5.** The canonical chat-pricing table adds the newest Claude models at standard list rates (time-limited introductory discounts are deliberately not modeled, so early Sonnet 5 spend reads slightly conservative), removing the no-pricing blind spot in cost telemetry and budget metering. (#2799, contributed by @p3ob7o)
|
||||
|
||||
#### Added
|
||||
- **Inline `[Source: ..., YYYY-MM-DD]` citations become timeline entries.** Both the filesystem extract path and the auto-timeline write path recognize the citation convention gbrain’s own quality guidance recommends, with idempotent re-extraction. (#2524, contributed by @pabloglzg)
|
||||
- **Schema packs extend atom-extraction page discovery.** For packs that declare the `extract_atoms` phase, the manifest’s `extractable` flag now unions with the legacy page-type list (synthesis outputs stay excluded, so concepts never feed back into atom extraction). (#2615, contributed by @p3ob7o)
|
||||
- **Book-mirror two-column pages are generated as HTML tables** with top alignment instead of markdown pipe tables, which broke on multi-paragraph cells in most renderers. (#2270)
|
||||
|
||||
#### Internal
|
||||
- Gateway tool-schema conversion extracted into a tested helper so the regression test exercises the exact code path production uses. (#2063, contributed by @maxpetrusenkoagent)
|
||||
- Reference docs synced for the v0.42.59.0 fixes (engine/testing entries). (#2798, contributed by @time-attack)
|
||||
|
||||
### To take advantage of v0.42.61.0
|
||||
|
||||
`gbrain upgrade`. No new schema migrations.
|
||||
|
||||
1. **Heads-up on extraction scope:** if your active schema pack declares the `extract_atoms` phase, page types the pack marks `extractable` now feed atom extraction alongside the legacy list — the first cycle after upgrading may process page types (notes, emails, slack) it previously skipped. Per-run page and budget caps still apply; check `gbrain search stats` / budget output if you watch spend closely.
|
||||
2. **If takes bootstrap seemed stuck** on a large brain, re-run it — each run now covers new pages.
|
||||
3. **Verify:**
|
||||
```bash
|
||||
gbrain doctor
|
||||
gbrain stats
|
||||
```
|
||||
4. **If any step fails,** please file an issue at https://github.com/garrytan/gbrain/issues with the output of `gbrain doctor`.
|
||||
|
||||
## [0.42.60.0] - 2026-07-16
|
||||
|
||||
**Eleven verified community fixes: Windows brains no longer risk losing subdirectory pages on a full sync, agent tool loops on non-Anthropic providers survive interruption instead of dead-lettering, multi-source brains get two source-isolation gaps closed, and the search cache stops leaking results across exclude policies. Every fix was reproduced and reviewed against master before landing.**
|
||||
|
||||
### Fixed
|
||||
- **Windows: `sync --full` no longer deletes subdirectory pages.** A path-separator mismatch made every subdirectory page look stale during full-sync reconcile, so a routine full sync could delete them. Paths are now normalized before comparison, and a mass-delete safety valve blocks any reconcile that would remove most of a source's pages. (#2828, #2836, contributed by @1alessio)
|
||||
- **Gateway tool loops on non-Anthropic providers are reliable across resume.** Tool-result turns are persisted as they happen, interrupted jobs reconcile dangling tool calls on resume instead of dead-lettering with unbalanced-transcript errors, `Date` values in tool outputs no longer crash serialization, DeepSeek reasoning-only replies are read correctly instead of as empty, and `openrouter_api_key` in config reaches the gateway. (#2820, consolidating community fixes #2062, #2065, #2257, #2274, #2336, #2487, #2491, #2572, #2614, #2617, #2806; contributed by @time-attack and the original PR authors)
|
||||
- **Claude 5 models get output-token headroom.** Thinking-default models no longer have long answers silently truncated by the old 4096-token default output cap; Claude 5 chat calls now default to 32000 output tokens (16000 for `think`). Other providers keep their existing caps, so smaller-limit providers are unaffected. (#2820)
|
||||
- **Bulk import survives huge fence-less files.** The markdown lexer is skipped when a page contains no code fences, removing an out-of-memory crash on large tables and notes during bulk import. (#2437, #2440, contributed by @irresi)
|
||||
- **`file_list` no longer crashes on Postgres brains over MCP.** BIGINT file sizes are normalized before JSON serialization; the CLI files listing gets the same fix. (#472, contributed by @vinsew)
|
||||
- **`gbrain config set auto_chronicle true` works as documented.** The Life Chronicle config keys (and `takes.bootstrap_enabled`) are registered, so the documented enable commands stop being rejected as unknown keys. (#2632, contributed by @p3ob7o)
|
||||
- **Orphan reports skip generated corpus roots.** `raw/`, `atoms/`, and `skills/` no longer inflate the orphan ratio by default; `--include-pseudo` still shows everything. (#2068, contributed by @mgunnin)
|
||||
|
||||
### Security
|
||||
- **The search cache honors your hard-exclude policy.** Cached search results are now keyed on the effective hard-exclude/include slug-prefix policy, so a process with `GBRAIN_SEARCH_EXCLUDE` set can never be served cached rows written under a different policy — and vice versa. (#2825, #2885)
|
||||
- **Take-writes are source-scoped.** When a source resolves (via `--source`, `GBRAIN_SOURCE`, or the dotfile chain), CLI take commands look pages up within that source instead of first-match-by-slug, closing a cross-source write path on brains where the same slug exists in multiple sources. Brains without a resolvable source keep the previous lookup. (#2684, #2698, contributed by @RerankerGuo)
|
||||
- **Image pages land in the right source.** Imported images are stamped with the syncing source (and their auto-links stay within it) instead of always landing in `default`. (#2706, #2718, contributed by @RerankerGuo)
|
||||
- **The admin bootstrap token no longer prints to a non-terminal stream.** The one-time token is withheld when its output stream is a pipe, log, or CI capture instead of an interactive terminal. (#2625, contributed by @irresi)
|
||||
|
||||
### Internal
|
||||
- Pinned embedding dimensions in a doctor test to eliminate a shard-order flake in CI. (#2801, contributed by @p3ob7o)
|
||||
|
||||
### To take advantage of v0.42.60.0
|
||||
|
||||
`gbrain upgrade`. No new schema migrations.
|
||||
|
||||
1. **Windows users with git-synced sources:** re-run `gbrain sync --full` once after upgrading — if a pre-upgrade sync deleted subdirectory pages, they re-import from the repo.
|
||||
2. **Your first search after upgrading may be a cache miss** (the cache key now includes the exclude policy). Speeds return to normal as the cache refills within its TTL.
|
||||
3. **If agent jobs previously dead-lettered** with unbalanced tool-call transcript errors on OpenAI-compatible providers, retry them with `gbrain jobs retry <id>` — resume now reconciles the transcript.
|
||||
4. **Verify:**
|
||||
```bash
|
||||
gbrain doctor
|
||||
gbrain stats
|
||||
```
|
||||
5. **If any step fails,** please file an issue at https://github.com/garrytan/gbrain/issues with the output of `gbrain doctor`.
|
||||
|
||||
## [0.42.59.0] - 2026-07-13
|
||||
|
||||
**Five community-reported fixes, each reproduced and verified before/after on both engines (PGLite + real Postgres): an upgrade wedge that locked pre-v121 brains out of migrations, two data-integrity holes in engine migration, silent deletion of facts containing pipe characters, confidently-wrong entity attribution on ambiguous names, and tightened source-scope enforcement in `think`.**
|
||||
|
||||
### Fixed
|
||||
- **Existing brains below schema v121 can upgrade again.** Brains created before v0.42.56.0 could get stuck in a loop where every command (including `apply-migrations`) failed with `column "event_page_id" does not exist` — the migration that adds the column could never run. The startup bootstrap now adds the forward-referenced column first; migration v121 still owns the FK and indexes. Re-running is idempotent, and already-wedged brains heal on the next command. (#2724, #2735, contributed by @time-attack)
|
||||
- **`gbrain migrate --to` no longer fails on multi-source brains.** The source catalog is copied before pages, so the first page no longer dies on a foreign-key violation. Source rows migrate with full fidelity (paths, sync state, config). (#2677, #2736, contributed by @time-attack)
|
||||
- **Migration resume checkpoints are target-aware.** An interrupted migration to one target no longer convinces a later migration to a *different* target that most pages are "already done" (which silently shorted the new target). A checkpoint for another destination is discarded and the run starts fresh; no connection strings or credentials are written to manifests or logs. (#2677, #2736, contributed by @time-attack)
|
||||
- **Facts containing `|` characters survive reconciliation.** The facts fence rendered literal pipes escaped but re-parsed rows by splitting on every pipe, so any fact whose text contained a `|` was silently deleted from the DB on the next extract-facts cycle. Render→parse is now symmetric (pipes, backslashes, and empty cells verified round-trip). The takes fence shares the parser and gets the same fix. (#2726, #2738, contributed by @time-attack)
|
||||
- **Ambiguous entity names quarantine instead of guessing.** A bare first name shared by two people, or a company name sharing a generic token (e.g. "… Capital") with another company, used to resolve confidently to the wrong entity — misattributed facts are invisible and expensive to repair. Bare names now resolve only when exactly one canonical candidate exists; low-specificity fuzzy matches fall through to the guarded holding path (a held fact is recoverable; a misattributed one isn't). Explicit slugs, full names, unique bare names, and close typos still resolve. Trade-off: heavier typos on short names may now hold instead of resolving. (#2723, #2737, contributed by @time-attack)
|
||||
|
||||
### Security
|
||||
- **`think` now applies the caller's source scope across all of its internal retrieval.** Hybrid page retrieval, takes keyword/vector retrieval, and graph traversal all honor scalar and federated source scope, matching the isolation the rest of the read surface already enforces. Part of the #2200 tracking work. (#2739, contributed by @time-attack)
|
||||
|
||||
### To take advantage of v0.42.59.0
|
||||
|
||||
`gbrain upgrade` should do this automatically. No new schema migrations ship in this release (v121/v122 shipped with v0.42.56.0).
|
||||
|
||||
1. **If your brain was stuck below schema v121** (every command printed a schema-probe warning), just upgrade and run any command — the brain heals and migrates to current on first connect. If `gbrain doctor` still complains:
|
||||
```bash
|
||||
gbrain apply-migrations --yes
|
||||
```
|
||||
2. **Verify:**
|
||||
```bash
|
||||
gbrain doctor
|
||||
gbrain stats
|
||||
```
|
||||
3. **If a previously-resolving shorthand name now files under a holding page**, that's the new ambiguity quarantine working as intended — add an alias or use the full name/slug for entities you want bare shorthand to hit.
|
||||
4. **If any step fails,** please file an issue at https://github.com/garrytan/gbrain/issues with the output of `gbrain doctor` and `~/.gbrain/upgrade-errors.jsonl` if it exists.
|
||||
|
||||
## [0.42.58.0] - 2026-07-06
|
||||
|
||||
**gbrain now runs cleanly on the stack you already have — a local Ollama box, a self-hosted LiteLLM proxy, llama.cpp's llama-server, or gbrain running as a Claude Code MCP subprocess — instead of silently degrading or hard-failing when you're not on a raw OpenAI/Anthropic key.** A provider-agnostic plumbing pass across the AI gateway: environment handling, base-URL normalization, and embedding-dimension validation all stop tripping on the non-frontier-vendor setups that used to fail without a clear signal.
|
||||
|
||||
### Fixed
|
||||
- **Running gbrain as a Claude Code MCP subprocess no longer breaks every AI call.** Some hosts inject an empty `ANTHROPIC_API_KEY` into the subprocess environment; that empty value used to override a real key set in your `~/.gbrain/config.json`, so every gateway call failed with a missing-key error. Empty environment values no longer clobber a configured key. (#1249)
|
||||
- **A custom Anthropic or OpenAI base URL without a `/v1` suffix no longer 404s.** When the base URL comes from the environment as a bare host, gbrain normalizes it before the call instead of posting to a path the provider doesn't serve. Unset base URLs are untouched, so the default hosted endpoints are unaffected. (#1250)
|
||||
- **Vector search stops silently going dark on a LiteLLM or llama-server embedding model.** A model-availability check was rejecting user-provided embedding recipes even when a model was configured, quietly disabling vector search so results looked empty. The check now validates what actually matters — that a dimension is set — and reports a clear, actionable message when it isn't. (#1292, #2295)
|
||||
- **Local embedding models with non-standard dimensions are accepted.** Ollama, llama-server, and LiteLLM models (e.g. modern 1024- or 4096-dimension embedders) no longer get hard-rejected by the dimension validator; you declare the dimension and gbrain trusts it. Hosted fixed-dimension providers stay strictly validated. Modern Ollama embed models are recognized. (#2271)
|
||||
|
||||
### Changed
|
||||
- **LiteLLM setup guidance now names the `/v1` path convention** so OpenAI-shaped proxies that only serve the `/v1` route don't fail authentication with no hint. (#2209)
|
||||
|
||||
### To take advantage of v0.42.58.0
|
||||
`gbrain upgrade`. If you run on Ollama, a LiteLLM proxy, llama-server, or as a Claude Code MCP subprocess, the fixes apply automatically — no migration, no config change. If you use a user-provided embedding recipe (LiteLLM / llama-server) and see a "no default embedding dimension" message, set it with `gbrain init --embedding-dimensions <N>`.
|
||||
|
||||
## [0.42.57.0] - 2026-07-02
|
||||
|
||||
**PGLite incident fix: a busy `gbrain dream` (or `embed`) could have its data-directory lock stolen and get its brain corrupted beyond in-place repair. The lock will no longer be taken from a process that is alive, and an already-corrupted store now tells you exactly how to recover.**
|
||||
|
||||
### Fixed
|
||||
- **A live PGLite holder is never stolen.** The data-directory lock used to be reaped if the holder's heartbeat went stale past a grace window. But the heartbeat runs on the JS event loop, which is blocked during long synchronous WASM imports/checkpoints, so a genuinely working `gbrain dream`/`embed` could look stale while fully alive. Reaping it let a second process open the same store and corrupt the catalog + pgvector extension (surfacing later as `relation "content_chunks" does not exist` / `type "vector" does not exist`, only recoverable by wipe-and-restore). The lock is now reaped only when the holder process is actually dead; a wedged-but-alive or PID-reused holder makes the acquire time out with a clear message naming the PID, instead of risking corruption.
|
||||
- **A corrupted PGLite store now explains how to recover.** When the store's catalog or pgvector extension can no longer load, the error names the cause and points at `gbrain reinit-pglite --embedding-model <id> --embedding-dimensions <N>` (or restoring a backup), instead of the unrelated "macOS WASM bug" hint. It also notes that deleting the lock dir or `postmaster.pid` does not fix it.
|
||||
|
||||
### To take advantage of v0.42.57.0
|
||||
`gbrain upgrade`. No migration. New corruption is prevented going forward. A brain already corrupted by a prior concurrent open cannot be repaired in place; the upgraded error message walks you through `gbrain reinit-pglite` or restoring a backup.
|
||||
|
||||
## [0.42.56.0] - 2026-07-02
|
||||
|
||||
**Life Chronicle: gbrain gains a temporal spine. Meetings and transcripts project into a queryable timeline, entities carry a bi-temporal ontology (sourced, confidence-weighted properties that supersede over time), and a low-friction diary captures interiority — so an agent can reconstruct "what happened the week of X", answer "when did I last interact with Y", and see how an entity's role or stance changed, instead of re-deriving chronology from scratch every session.** Built entirely on existing primitives (pages, the `facts` table, `timeline_entries`) — no new datastore. Auto-emission is off by default; opt in per below.
|
||||
|
||||
### Added
|
||||
- **Timeline events + reads.** Meetings/transcripts auto-emit `type:event` atoms (when·where·who·what) that project into a date index and backlink to the depth page. Query them with `gbrain day <date> [--week] [--narrative]`, `gbrain since <date> [--kind]`, `gbrain last-seen <entity>`, and `gbrain on-this-day`. Intra-day ordering, read-time hiding of deleted events, and source isolation throughout.
|
||||
- **Bi-temporal per-entity ontology.** An open-world, sourced, confidence-weighted property bag rides the existing `facts` table (new `dimension`/`value` columns). A new value supersedes the prior across a validity window, so `gbrain ontology <entity> [--asof <date>]` can time-travel; genuine two-source disagreement surfaces via `gbrain ontology-contradictions`; `gbrain ontology-dimensions` shows what the brain tracks about entities. Novel LLM-proposed dimensions quarantine until confirmed.
|
||||
- **Diary capture + agent orientation.** `gbrain capture --type diary` (and `--type event` with `--who/--what/--where/--kind`) for low-friction entries; `gbrain orient` hands an agent the recent timeline plus resolved-entity ontology in one zero-LLM payload. `gbrain chronicle-backfill` sweeps existing meetings into the timeline.
|
||||
- **Ambient temporal recall + proactive surfacing.** Temporal queries lift chronicle pages in search; `gbrain advisor` flags unresolved ontology conflicts and recent meetings missing from the timeline. A deterministic `gbrain eval chronicle` gates the feature (day-order, last-seen, supersession, contradiction, source isolation).
|
||||
- **Migrations v121 (event-projection column) + v122 (facts ontology columns).** Additive; legacy rows unchanged.
|
||||
|
||||
### Security
|
||||
- **Interiority stays local.** Diary content and diary-sourced ontology are redacted from untrusted (remote/MCP) readers across reads, search, advisor, and orientation. Auto-emission runs only for trusted local writes.
|
||||
|
||||
### To take advantage of v0.42.56.0
|
||||
`gbrain upgrade`, then `gbrain apply-migrations --yes` (or any command that opens the brain) to pick up v121/v122. Auto-emission is OFF by default: turn it on with `gbrain config set auto_chronicle true`, then `gbrain chronicle-backfill` to populate the timeline from existing meetings. Manual capture (`gbrain capture --type event/diary`) and every read surface work immediately. Closes #2390 (duplicate #2388).
|
||||
|
||||
## [0.42.55.0] - 2026-06-24
|
||||
|
||||
**A security-hardening pass: routing dotfiles, the skills directory, page slugs, and large-file transcription are confined against multi-user-host and untrusted-input edge cases; dynamic OAuth client registration defaults to a consent-bearing grant; and a schema-lint migration brings existing brains to the fresh-install posture.** Several of these close community-reported gaps. Fresh installs were already covered; existing brains are brought to the same bar automatically on upgrade. If `gbrain doctor` flags anything afterward, its message names the object and the exact fix.
|
||||
|
||||
### Fixed
|
||||
- **Walk-up routing dotfiles are trust-gated.** On a shared multi-user host, a `.gbrain-source` / `.gbrain-mount` found by the ancestor-directory walk is accepted only when it's owned by you (or root) and is neither a symlink nor world-writable — otherwise it's skipped, fail-closed. The working-directory match that routes by registered path now resolves symlinks on both sides, so a redirected directory can't misattribute your source or brain. (#418, contributed by @garagon)
|
||||
- **The skills directory is confined to its workspace.** Every skills-dir resolution tier now requires the resolved directory to stay within the declared workspace, so a redirected `skills` entry can't point the loader outside it. (#419, contributed by @garagon)
|
||||
- **Page slugs reject unsafe characters at the write boundary.** The shared slug validator now rejects control bytes, bidirectional/RTL overrides, backslashes, and URL-encoded path separators on top of the existing traversal check, and the file-write path confirms the target stays inside the source's working tree. Ordinary slugs — including non-Latin and CJK — are unaffected.
|
||||
- **Large-file transcription no longer builds shell command strings.** The segmentation path invokes `ffprobe`/`ffmpeg` with argument arrays and removes its temp directory through the filesystem API, so a media path is never parsed by a shell. (#245, contributed by @aliceagent)
|
||||
- **Superuser-connected fresh installs no longer abort during migration.** The RLS preflight in the schema migrations recognizes superuser and inherited-role privileges, not just the role's own flag. (#1385)
|
||||
|
||||
### Changed
|
||||
- **Dynamic client registration defaults to the consent-bearing grant.** With Dynamic Client Registration enabled, a self-registered client now defaults to `authorization_code` (which goes through the approval screen) instead of `client_credentials`. Operators who need the machine-to-machine grant opt in with the new `--enable-dcr-insecure` flag, and a startup warning prints whenever registration is open. Registering clients via the CLI or admin API is unchanged. (#1353)
|
||||
|
||||
### Added
|
||||
- **Migration v120 — schema-lint hardening.** Brings existing brains to the fresh-install posture: the `page_links` view runs with the caller's privileges on Postgres, and the gbrain-owned trigger/event functions pin their schema search path on both engines. A new CI guard keeps new trigger functions from regressing. (#1647, #171)
|
||||
|
||||
### To take advantage of v0.42.55.0
|
||||
`gbrain upgrade`, then `gbrain apply-migrations --yes` (or any command that opens the brain) to pick up migration v120 — no manual step, all on by default. Fresh installs already carry every change. The hardening applies automatically; `--enable-dcr-insecure` is the explicit escape hatch if you genuinely need the machine-to-machine OAuth grant.
|
||||
|
||||
## [0.42.53.0] - 2026-06-23
|
||||
|
||||
**`gbrain sync` works again on managed Postgres brains: the durable-checkpoint pin write was encoding its value the wrong way, so every multi-source sync aborted at the very first checkpoint. Fixed, plus a repo-wide sweep of the same JSONB footgun and a new CI guard so it can't come back.** A recent release added a structural check on the sync checkpoint table; the pin write that runs before every drain bound its value as a string rather than a real array, so the check rejected it and the run bailed before importing anything. The bug was invisible on the embedded engine (its driver parses the value either way) and only bit managed Postgres.
|
||||
|
||||
### Fixed
|
||||
- **Multi-source sync no longer aborts at the first checkpoint.** The sync-target pin write now binds its value so Postgres stores a genuine JSONB array instead of a double-encoded string scalar. A dedicated Postgres CI job exercises this on a real database, because the embedded test engine masks the failure — which is exactly why it shipped.
|
||||
- **The same JSONB double-encode footgun is swept across the codebase.** Every raw write that serialized a value into a JSONB column the bug-prone way is corrected to the safe form (search cache, source config, calibration profiles, subagent tool records, eval receipts, code-intel cache, symbol resolver, and others). Readers were already defensive, so existing rows self-heal as each is rewritten.
|
||||
- **`gbrain eval suspected-contradictions` no longer crashes on an exact-alias query.** An alias-matched result was missing its page id, which aborted the whole probe on Postgres; the id is now carried through, with a finite-id filter as a defensive backstop.
|
||||
|
||||
### Added
|
||||
- **A CI guard for the positional JSONB double-encode pattern.** The existing guard caught only the template-string spelling; a new static check (`scripts/check-jsonb-params.mjs`) catches the positional-parameter form — the one behind this wave — across the codebase, with its own self-test. The embedded engine's native path is intentionally not flagged, since the bug can't occur there.
|
||||
|
||||
### To take advantage of v0.42.53.0
|
||||
`gbrain upgrade`. Multi-source Postgres brains that had stopped syncing resume on the next `gbrain sync` — no migration, no manual step. Rows written in the double-encoded form before the fix self-heal as each is rewritten; re-running the affected write (or a sync) repairs them eagerly if you'd rather not wait.
|
||||
|
||||
## [0.42.52.0] - 2026-06-18
|
||||
|
||||
**Autopilot stops manufacturing dead jobs and wedging its own queue, plus four operational rough edges get fixed: minion attempt-accounting, `agent run` flag parsing, honest `sources status`, and a budgeted `gbrain status`.** On a multi-source Postgres brain, autopilot could fan out a continuous stream of dead `autopilot-cycle` jobs while the supervisor periodically wedged the very queue it exists to keep alive. The root cause was one disease with several interacting parts; this wave addresses all of them, then cleans up four smaller reliability bugs found alongside.
|
||||
|
||||
### Changed
|
||||
- **Autopilot runs one brain-wide maintenance pass, not one per source.** The cycle is split: per-source jobs run only source-scoped phases, and a single `autopilot-global-maintenance` job runs the brain-wide phases once per window. This removes the per-cycle memory blow-up that was the shared root cause of the dead-job storm and the queue wedge. Per-source filesystem phases bind to the source's own path, so the freshness stamp and the work agree on which source ran.
|
||||
- **The supervisor self-heals instead of giving up.** A transient database blip no longer trips the crash-budget breaker into a permanent stop; the supervisor degrades to capped-backoff retry and recovers, with a hard ceiling as the backstop. It detects a live sibling supervisor through the queue's database lock (not a `$HOME`-derived pidfile), so two supervisors under a split home directory can't both claim the queue.
|
||||
- **`gbrain sources status` tells a running sync apart from an idle source.** A source holding a live sync lock now reads as actively syncing instead of "idle," matching the honest-freshness signal `gbrain doctor` already shows.
|
||||
|
||||
### Added
|
||||
- **Per-source failure cooldown + fan-out clamp.** A source that fails backs off (bounded exponential) instead of being re-dispatched every tick; per-tick fan-out is clamped to the worker concurrency, with a `gbrain doctor` check that warns on a mismatch.
|
||||
- **`gbrain status --deadline-ms` / `--fast`.** A budgeted status snapshot returns whatever sections completed within the budget (marked partial) instead of hanging a poller; the JSON envelope also carries the CLI `version`.
|
||||
- **A sync stall watchdog.** If the import drain makes no forward progress for `GBRAIN_SYNC_STALL_ABORT_SECONDS` (default 900), the run aborts and releases its per-source lock so the next `gbrain sync` resumes from the checkpoint — no manual `pkill`. It keys off import progress (not the lock heartbeat) and reports a distinct `stall_timeout` reason. (Limit: a hang inside a single file's import is observed between files, not mid-file; the wall-clock deadline remains the backstop there.)
|
||||
|
||||
### Fixed
|
||||
- **A timed-out minion run counts as a spent attempt.** Wall-clock dead-lettering already did; the per-job timeout path didn't, so long-lane jobs (subagent / embed-backfill / autopilot-cycle) could read `attempts: 0/N (started: N)`. Accounting is now honest across all dead-letter paths.
|
||||
- **`gbrain agent run` no longer swallows flags after the prompt.** A trailing `--detach` / `--follow` is recognized instead of being captured into the prompt string; a `--word` inside the prompt stays verbatim, and an explicit `--` ends flag parsing anywhere.
|
||||
|
||||
### To take advantage of v0.42.52.0
|
||||
`gbrain upgrade`. Existing brains pick up the cycle split, supervisor backoff, and per-source cooldown on the next autopilot tick (one catch-up global-maintenance pass on the first tick) — no migration, all on by default. Tune the sync stall watchdog with `GBRAIN_SYNC_STALL_ABORT_SECONDS` if 900s doesn't fit your largest files; budget a status poller with `gbrain status --fast` or `--deadline-ms=<n>`.
|
||||
|
||||
## [0.42.51.0] - 2026-06-17
|
||||
|
||||
**`gbrain sync` stops bottlenecking all its workers on a single database row, a malformed checkpoint can no longer wedge a source, and `gbrain doctor` tells an actively-running sync apart from a stuck one.** A slow source that fell behind HEAD could read as permanently stale even while it imported every cycle: sync was single-core-bound at the database layer, so handing it more workers didn't help, and the freshness check couldn't see that a sync was in fact running.
|
||||
|
||||
The root cause was the page-generation clock that backs the search cache. Every page write bumped a single locked counter row, so concurrent sync workers serialized on one another's commits no matter how many you ran. It is now a contention-free sequence: the cache invalidation contract is unchanged (it still over-invalidates rather than ever serving stale), but writers no longer wait in line. The other fixes harden checkpoint state and make the freshness signal honest.
|
||||
|
||||
### Changed
|
||||
- **Sync writes scale across cores.** The page-generation clock moved from a single locked counter row to a contention-free sequence, so parallel sync workers stop serializing on each other. A large `gbrain sync` now uses the workers you give it instead of collapsing to roughly one.
|
||||
- **`gbrain doctor` distinguishes in-progress from stale.** A source holding a live sync lock is reported as actively syncing (naming the running process), not flagged stale. A genuinely stuck, blocked, or never-completed sync still reports stale — the signal is the live lock, so a stopped sync is never masked.
|
||||
|
||||
### Fixed
|
||||
- **A malformed checkpoint record can no longer wedge a source.** Checkpoint state is structurally constrained, repaired automatically on upgrade, and the loader survives a bad record instead of discarding all banked progress for that source.
|
||||
- **`gbrain sync --force-break-lock` is honest when there is no lock.** It now says plainly that nothing was held and points at how to inspect a genuinely wedged sync, instead of a terse no-op that read like a successful unwedge.
|
||||
|
||||
### To take advantage of v0.42.51.0
|
||||
`gbrain upgrade`, then `gbrain doctor`. Existing brains pick up the contention-free clock and the checkpoint integrity constraint automatically on the next migration; the search cache rebuilds itself on first query. Nothing to configure.
|
||||
## [0.42.50.0] - 2026-06-17
|
||||
|
||||
**CI reliability hardening — a wedged job can no longer run for six hours, a superseded run no longer reports a stale flaky failure, and broken workflow YAML is caught before it ships.** gbrain's CI already had the deep machinery (content-hash run-skip cache, weight-aware shard balancing, test-isolation guards, hermetic E2E). What it lacked was the cheap GitHub-Actions hygiene that was already wired into `heavy-tests.yml` but never into the two hot-path workflows. This pass closes that gap, porting the patterns from the sibling GStack project's CI-reliability work.
|
||||
|
||||
### Changed
|
||||
- **`test.yml` and `e2e.yml` cancel a superseded run** when a newer commit lands on the same PR (`concurrency` keyed on the PR number — fork-safe — with a `github.ref` fallback so push and scheduled runs always complete). Frees runners and stops a run against an obsolete commit from reporting a flaky failure.
|
||||
- **Every job in `test.yml`/`e2e.yml` now has a `timeout-minutes` bound** (test matrix 15, verify 12, serial 15, slow jobs 12, E2E tier 1 20 / tier 2 30, trivial jobs 5-10). A wedged job is converted from a six-hour zombie (GitHub's default) into a fast, legible failure.
|
||||
- **`scripts/run-e2e.sh` scrubs operator/agent environment before E2E.** A dev or Conductor shell exporting `CONDUCTOR_*` / `MCP_*` / `GBRAIN_*` config overrides no longer bleeds into E2E child processes (which made "hermetic" E2E non-hermetic and its failures unreproducible across machines). Denylist scrub — `PATH`/`HOME`/`TMPDIR`/`DATABASE_URL` survive; `GBRAIN_HOME` is preserved for the existing HOME isolation.
|
||||
|
||||
### Added
|
||||
- **`actionlint` workflow** (`rhysd/actionlint`, SHA-pinned) lints all workflow YAML on `.github/workflows/**` changes, catching a malformed workflow / bad action ref / missing-permission bug before it ships a broken pipeline.
|
||||
|
||||
### To take advantage of v0.42.50.0
|
||||
Nothing to do — these are CI/test-infra changes that take effect automatically on the next push. Contributors running the suite locally get the same hermetic-E2E env scrub via `bash scripts/run-e2e.sh` (or `bun run ci:local`).
|
||||
|
||||
## [0.42.49.0] - 2026-06-16
|
||||
|
||||
**Big embed backfills and syncs now throttle themselves when the database gets busy, so clearing a backlog can't starve the job queue — no more external babysitter scripts.** A naive `gbrain embed --stale` or large `gbrain sync` against a PgBouncer transaction-mode pooler could saturate it and starve the minion supervisor's lock renewals, cascading `lock-renewal-failed` into dead jobs. The field workaround was an external wrapper that SIGSTOP/SIGCONT'd the process off a side-pool latency probe. That approach was blind (the side pool read low latency while the pool that mattered starved), unsafe (SIGSTOP can freeze a process mid-transaction holding locks), and couldn't touch peak pressure. gbrain now does this natively, and better.
|
||||
|
||||
Pacing is **opt-in** (default `off`) and built on one composable primitive: it caps simultaneous in-flight DB writes (the real lever against pooler-slot starvation), measures the work's own query latency in-band (so it can never be blind), and sleeps cooperatively between safe points (never mid-transaction, so the lock heartbeat keeps firing). Turn it on per-run with `gbrain embed --stale --pace`, or set `pace.mode` in config to pace every embed path plus the production embed-backfill job automatically. `GBRAIN_PACE_*` env vars override config as an incident escape hatch.
|
||||
|
||||
### Added
|
||||
- **`--pace[=mode]` for `gbrain embed`** — `off`/`gentle`/`balanced`/`aggressive` bundles (bare `--pace` = balanced), plus `--pace-max-concurrency=N`. `--background` carries the explicit override into the queued `embed` job; the handler re-resolves env > config > bundle at execution.
|
||||
- **`pace.mode` config + `GBRAIN_PACE_*` env** — config paces every `runEmbedCore` caller (cycle embed, catch-up, sync-auto-embed) and the prod `embed-backfill` job automatically; env beats config for incident response.
|
||||
- **Composable `db-pacer` primitive** (`src/core/db-pacer.ts`) + named bundles (`src/core/pace-mode.ts`) — concurrency permit + in-band EWMA + jittered cooperative sleep, abort-throwing, fail-open. `sync` uses the shared permit across its parallel worker engines.
|
||||
- **Pacing telemetry** — `EmbedResult.pacing` (cap, samples, EWMA latency, slept ms) in `--json`, plus a one-line stderr summary.
|
||||
|
||||
### Changed
|
||||
- **`gbrain embed --stale` now single-flights per source** using the same lock the `embed-backfill` job holds, so a hand-run backfill and a queued job can't grind the same source concurrently. Paced runs add a bounded end-of-run rescan (catches rows that landed behind the cursor during a longer run), and the embed time budget excludes paced-sleep time so a contended DB still converges instead of exiting early.
|
||||
|
||||
### To take advantage of v0.42.49.0
|
||||
`gbrain upgrade`. Pacing is off by default — nothing changes until you opt in. To clear a big embed backlog safely on a busy pooler: `gbrain embed --stale --pace` (or `--pace=gentle` to be extra conservative). To pace the background embed-backfill job and every embed path automatically: `gbrain config set pace.mode balanced`. During an incident you can override without a redeploy: `GBRAIN_PACE_MODE=gentle` or `GBRAIN_PACE_MAX_CONCURRENCY=4`.
|
||||
## [0.42.48.0] - 2026-06-16
|
||||
|
||||
**Brain repos harden themselves for durability the moment gbrain is given a PAT and a GitHub URL.** Fresh agents kept drifting out of sync with their knowledge-wiki git repos: writes sat local-only and never pushed, long-lived sessions edited a stale tree, and scratch output landed outside the repo and vanished. Now `gbrain sources add --url <repo> --pat-file <p>` auto-hardens the managed clone, and `gbrain sources harden <id>` runs the same audit idempotently against any source. Hardening is six always-on guarantees: it pulls current state (divergence-safe rebase that skips a dirty tree and never leaves a half-rebase), installs a local auto-push safety net, ships a committed `scripts/brain-commit-push.sh` that refuses to report success without a confirmed push, writes always-on durability rules into the agent's context file (deterministic filing from the canonical taxonomy, commit-and-push-never-deferred, pull-before-each-write-batch), registers a 30-minute background pull so an idle session can't go stale, and verifies push access up front.
|
||||
|
||||
This is gbrain's first push path and first credential storage, built secure by default. The push automation is installed locally per machine rather than committed into the repo, the GitHub token is wired per-repo (least-privilege; an existing credential helper is reused when present rather than writing a new one), and the token never enters the repo, the tracked remote URL, logs, or the run report. Hardening proves push works with a dry-run probe before declaring done, so a read-only token or a protected branch surfaces immediately instead of silently dropping writes later. `gbrain sources unharden <id>` cleanly removes everything it installed and runs automatically before `sources remove`.
|
||||
|
||||
### Added
|
||||
- `gbrain sources harden <id|--all> [--pat-file <p>] [--branch <b>] [--no-cron] [--no-verify] [--dry-run] [--json]` — idempotent brain-repo durability hardening.
|
||||
- `gbrain sources pull <id> | --path <dir> [--branch <b>]` — divergence-safe rebase-pull; `--path` runs DB-free so the 30-minute cron never contends for the local engine lock.
|
||||
- `gbrain sources unharden <id>` — remove the durability cron, hook, and credential wiring.
|
||||
- `--pat-file` / `--no-harden` on `gbrain sources add`; managed clones added with a PAT auto-harden.
|
||||
- `git-remote.ts`: `divergenceSafePull`, `detectDefaultBranch`, `pushProbe`, and an env-gated `GBRAIN_GIT_ALLOW_FILE_TRANSPORT` escape hatch for self-hosted filesystem remotes.
|
||||
|
||||
### To take advantage of v0.42.48.0
|
||||
`gbrain upgrade`. Add a brain repo with `gbrain sources add <id> --url <https-repo> --pat-file <path-to-token>` and it hardens automatically; or run `gbrain sources harden <id> --pat-file <path>` on an existing source. Use a fine-grained PAT scoped to just that repo. Existing brains are untouched until you opt in.
|
||||
|
||||
## [0.42.47.0] - 2026-06-16
|
||||
|
||||
**A brain now travels with its own operating manual, and gbrain finally tells you how to run it better (gbrain#2180).** Two long-standing gaps closed. First: a brain repo can carry its own skillpack — skills authored for and versioned with that specific brain — and any harness that connects is offered it. Connect a fresh Claude Code or a thin client to a mature brain and it learns, on the spot, which meeting-ingestion or diligence protocol the brain expects, instead of starting blind. Second: gbrain stops being purely passive. `gbrain advisor` reads the brain's own state and hands back a ranked, read-only list of high-leverage actions — pending migrations, version drift, stalled backfills, low embedding coverage, setup smells — each with the exact command to fix it. It never acts on its own; it shows you and asks.
|
||||
|
||||
Discovery works on both connection topologies. Add a federated source that ships a brain-resident pack and gbrain prints what's in it and how to install it (with bounded, escalate-then-suppress nagging while it stays uninstalled — it never nags off a cron or an MCP call, only a real CLI prompt). Over MCP, a connecting agent calls `list_brain_skillpack` (source-scoped, so a multi-source brain attributes each pack to its source) and `get_skill --source_id` to fetch a specific pack skill. The advisor is also available over MCP behind its own gate, read-only, so a thin client can coach you in its own voice without ever exposing a fix it could run itself.
|
||||
|
||||
Nothing here forks the manifest, the installer, or the trust model — brain packs go through the same TOFU gate and SSRF allowlist as any third-party pack. Thin-client *binary* install (download-and-unpack) remains the separate, still-deferred PR2 work; today a thin client resolves a pack from its git source on its own machine.
|
||||
|
||||
### Added
|
||||
- **Brain-resident skillpacks** — optional `brain_resident` + `schema_pack` fields on the v1 manifest (additive, forward-compatible); `gbrain skillpack init-brain-pack` scaffolds one (with a machine-parseable README a connecting harness can scan) pinned to the exact serving version so a pack can't install on a binary that lacks its ops.
|
||||
- **Connect-time discovery** — `gbrain sources add` surfaces a brain-resident pack and offers to install it; a new `list_brain_skillpack` MCP tool (source-scoped, `mcp.publish_skills`-gated) plus `get_skill --source_id` let a thin client discover and fetch per-source pack skills. `gbrain connect` now teaches agents to call it.
|
||||
- **`gbrain advisor`** — ranked, read-only "what to do next" for this brain (version drift, pending migrations, schema-pack issues, stalled jobs/sync, embedding coverage, setup smells, uninstalled skills). `--json` with severity-based exit codes for CI/cron; `--apply <id>` runs one fix locally behind an explicit confirm (structured argv, never a shell). Exposed over MCP behind `mcp.publish_advisor` (default off, read-only).
|
||||
- **`gbrain-advisor` bundled skill + weekly cron recipe** — teaches a harness to run the advisor on a cadence and ping you with what's new since last run.
|
||||
- **Brain-pack version-skew lint** — `init-brain-pack` validates each pack skill's declared `tools:` against the serving op set, so a pack fails loud on drift instead of silently half-working.
|
||||
|
||||
### Changed
|
||||
- **The post-install/upgrade advisory is now state-aware and current.** It reads a single current-state recommended set (not a version-pinned constant) and the install ledger, and it speaks `gbrain skillpack scaffold` (the removed `install` verb is gone from the copy).
|
||||
|
||||
### To take advantage of v0.42.47.0
|
||||
`gbrain upgrade`, then run `gbrain advisor` to see the top things worth doing on your brain right now. To publish a brain's skills to anyone who connects, run `gbrain skillpack init-brain-pack <name>` in the brain repo, fill in the README's five sections, and commit it. To let connecting agents discover packs over MCP, `gbrain config set mcp.publish_skills true`; to let a thin client run the advisor, `gbrain config set mcp.publish_advisor true` (both default off). Install the `gbrain-advisor` skill and its weekly cron recipe for a standing brain checkup.
|
||||
## [0.42.46.0] - 2026-06-16
|
||||
|
||||
**Federated read scope now reaches every by-slug read, not just search and query (gbrain#2200).** A client that mounts several sources (a `federated_read` grant) could find a page through search and query, but the by-slug reads — `get_page`'s tags, plus `get_tags`, `get_links`, `get_backlinks`, and `get_timeline` — didn't honor the same grant. For a page living outside the default source that meant two wrong outcomes: the read came back empty for content the client was authorized to see, or it resolved against the wrong source. This release routes all of those reads through the same source-scope ladder that already governs search/query, so a federated client reads exactly the sources it's granted — no more, no less. Thanks to @mlobo2012 for the report and the proposed fix.
|
||||
|
||||
Link reads are scoped on every endpoint. A link connects up to three pages (the source page, the target, and the page that authored the edge); a federated read now constrains all three to the grant, so a link that crosses out of your granted sources doesn't surface a foreign page's slug. Untrusted remote callers carrying a single-source token get the same all-endpoint scoping; trusted local CLI keeps its cross-source view for link reconciliation and validators.
|
||||
|
||||
The semantic query cache was already corrected in v0.42.34.0 (cache rows key on the full source set, so a federated result can't be served to a caller with a different scope); this release closes the read-path half of the same theme.
|
||||
|
||||
### Fixed
|
||||
- **By-slug reads honor the federated read grant.** `get_page` resolves a page's tags against that page's own source, and `get_tags` / `get_links` / `get_backlinks` / `get_timeline` route through the federated source scope. A multi-source client reads tags, links, backlinks, and timeline across exactly its granted sources (union), instead of falling back to a single source.
|
||||
- **Link reads are scoped on all three endpoints** (source, target, and authoring page) under a federated grant, and untrusted remote single-source callers are scoped the same way — so a cross-source link can't disclose a foreign slug. Trusted local reads keep the full cross-source view.
|
||||
|
||||
### Changed
|
||||
- The engine's `getTags` / `getLinks` / `getBacklinks` / `getTimeline` and `TimelineOpts` accept a `sourceIds[]` federated scope (precedence over the scalar source), mirroring `getPage` from v0.42.37.0. Write-side operations are unchanged — a read grant never widens writes.
|
||||
|
||||
### To take advantage of v0.42.46.0
|
||||
`gbrain upgrade`. No configuration needed — federated clients immediately read tags, links, backlinks, and timeline across their full granted source set, and cross-source link reads stop surfacing foreign slugs. Single-source brains are unaffected.
|
||||
|
||||
## [0.42.45.0] - 2026-06-13
|
||||
|
||||
**The daily sync cron stops wedging on cost, and the embedding-spend estimate finally matches what a sync actually does (gbrain#2139).** On an active brain the inline-embed cost gate priced the *entire* corpus every time the working tree was dirty — which is always, since agents and crons write to it constantly — so a routine daily sync estimated ~158M tokens / ~$8 when the real delta was a few hundred files / ~$0.04, then blocked the cron with a confirmation it could never answer. Embeds silently stalled until someone noticed. The estimate now mirrors execution: it fetches first and prices only the files this run will pull and import, through the same diff machinery the sync itself uses. A brain whose commits are caught up but whose tree is dirty estimates $0, because an attached-HEAD sync imports only the committed diff.
|
||||
|
||||
When the gate does fire in a non-interactive session, it no longer exits with an error — it imports now and defers embedding to capped background jobs (which drain via the jobs worker or `gbrain embed --stale`), so a cron is never wedged again. Operators who have decided cost isn't the constraint get one switch — `gbrain config set spend.posture tokenmax` — that makes every cost gate informational across sync, reindex, enrich, and onboard (spend is still recorded; the switch removes the ceiling, not the accounting). The USD knobs accept `off` / `unlimited`, and every gate message now carries paste-ready commands so the controls are discoverable at the moment they fire.
|
||||
|
||||
This release also lifts the rule that blocked `--skip-failed` / `--retry-failed` under parallel sync — failure recovery no longer has to drop to `--serial` (which is what armed the inline gate in the first place).
|
||||
|
||||
### Added
|
||||
- **`spend.posture` config** — `tokenmax` makes every embedding-cost gate informational (print the estimate, proceed, keep the ledger); `gated` (default) enforces as before. Documented end-to-end in `docs/operations/spend-controls.md`.
|
||||
- **First-class off switches** — `sync.cost_gate_min_usd`, `embed.backfill_max_usd_per_source_24h`, `embed.backfill_max_usd`, and `reindex --max-cost` / `enrich --max-usd` accept `off` / `unlimited` / `none`. No more sentinel values like `100000`.
|
||||
- **Single-source `gbrain sync` cost preview** — plain `gbrain sync` previously embedded inline with no preview; it now carries the same gate as `sync --all` (auto-defers in non-TTY sessions, never blocks).
|
||||
- **Self-describing gate messages** — every cost-gate / FYI line ends with the exact `gbrain config set` commands to widen, disable, or switch posture, plus a docs pointer.
|
||||
|
||||
### Changed
|
||||
- **`gbrain sync --all` is no longer blocked by the cost gate in cron/agent contexts.** Above the floor in a non-interactive session it auto-defers embeds (exit 0) instead of emitting a `cost_preview_requires_yes` envelope and exiting 2. Cron wrappers that branched on exit 2 now see exit 0 with `status: "auto_deferred"`. A TTY still prompts `[y/N]`; `--yes` still embeds inline.
|
||||
- **`--skip-failed` / `--retry-failed` now work under parallel sync.** The failure ledger is per-source and lock-serialized, so the previous "not supported under parallel — re-run with --serial" refusal is retired.
|
||||
- **The six spend-control config keys are now first-class** (`gbrain config set` accepts them without `--force`).
|
||||
|
||||
### To take advantage of v0.42.45.0
|
||||
`gbrain upgrade`. Nothing to configure for the headline fix — the daily sync cron stops wedging and the estimate is accurate out of the box. If you run a high-volume brain where cost genuinely isn't the constraint, `gbrain config set spend.posture tokenmax` makes every gate informational. To widen or disable a specific gate instead, see the table in `docs/operations/spend-controls.md` (e.g. `gbrain config set sync.cost_gate_min_usd off`). Failure-recovery syncs can now stay parallel: `gbrain sync --all --skip-failed` no longer forces `--serial`.
|
||||
|
||||
## [0.42.44.0] - 2026-06-13
|
||||
|
||||
### Fixed
|
||||
|
||||
- **Personal-brain tutorial points at the correct AlphaClaw site.** Step 4 of `docs/tutorials/personal-brain.md` ("Deploy via AlphaClaw on Render") linked to the wrong top-level domain, sending readers to a site that isn't the official AlphaClaw. The link now resolves to the right destination, so the deploy step works as written (gbrain#2165).
|
||||
|
||||
## [0.42.43.0] - 2026-06-12
|
||||
|
||||
**The brain now volunteers relevant pages instead of waiting to be asked (gbrain#2095).** Retrieval used to be pull-only: a deep session could run for hours with zero brain contributions — not because the brain had nothing, but because nothing prompted the agent to ask, and pages stored under coined names were missed by literal-string queries. Push-based context inverts that, on three channels sharing one zero-LLM, confidence-gated core: the ambient retrieval reflex now reads the last few conversation turns (an entity your assistant introduced two turns ago resolves on the "what did she invest in?" follow-up), a new `volunteer_context` operation gives any agent a per-turn volunteer surface over CLI stdin or MCP, and `gbrain watch` streams volunteered pages as a transcript flows through it.
|
||||
|
||||
Every volunteered page carries an honest confidence (alias match 0.9, exact title 0.8, slug-suffix 0.6, small boosts for repeated or newest-turn mentions; default gate 0.7) and a one-line rationale. A feedback loop closes the tuning circle: volunteered pages are logged, "used" is derived from whether the page actually got retrieved afterwards, and `gbrain volunteer-context --stats` reports per-arm precision (labeled approximate, because the retrieval signal is throttled). Suppression learned the difference between a page that was actually surfaced and one merely mentioned — under windowing only a surfaced page is held back, so prior-turn mentions can't silence themselves.
|
||||
|
||||
This release also lands on top of v0.42.42.0's exit-contract work as a strict superset: the transaction-mode pooler topology behind three consecutive teardown waves is now reproduced in the local CI gate (a real pooler service + an end-to-end teardown test), the exit-verdict sweep is completed across every command surface (notably `gbrain doctor`, whose FAIL verdict could still report exit 0), and a structural guard makes the next raw exit-code write fail in CI instead of silently reporting success on failure.
|
||||
|
||||
### Added
|
||||
- **`volunteer_context` operation** (CLI: `gbrain volunteer-context`, MCP tool) — pipe recent turns in (`user:` / `assistant:` prefixed lines, or plain text), get confidence-gated page pointers with rationales and synopses out. `--stats` returns the volunteered-vs-used precision summary. Per-call knobs: `max_pages`, `min_confidence`, `session_id`/`turn` attribution.
|
||||
- **`gbrain watch`** — the streaming push transport: feed a transcript on stdin, volunteered pages stream out (`--json` for JSONL), each slug at most once per session. Piped input exits cleanly at end-of-input; interactive sessions run until Ctrl-C.
|
||||
- **Rolling-window retrieval reflex** — the ambient channel extracts entities from the last 4 turns (configurable via `retrieval_reflex_window_turns` / `GBRAIN_RETRIEVAL_REFLEX_WINDOW_TURNS`; 1 restores the previous single-turn behavior). Assistant-introduced entities and named-antecedent follow-ups now surface pointers with zero agent-initiated queries.
|
||||
- **Volunteered-context feedback log** — volunteered pages are recorded best-effort (channel, arm, confidence, optional session/turn) with 90-day retention handled by the nightly cycle; rationales are deterministic templates, never raw conversation text. Synopses always strip the takes/facts privacy fences before reaching a prompt.
|
||||
- **Transaction-mode pooler in the local CI gate** — `bun run ci:local` now runs a real transaction-pooling service in front of Postgres with an end-to-end teardown test, so the bug class behind gbrain#1972/#2015/#2084 is reproducible before it ships, not after.
|
||||
|
||||
### Fixed
|
||||
- **`gbrain doctor` exits 1 on FAIL again on every engine.** Its verdict write predated the v0.42.42.0 exit-verdict channel and was being silently zeroed; swept, plus a structural test that fails CI on the next raw exit-code write anywhere in the CLI.
|
||||
- **Reflex pointer suppression under multi-turn windows** distinguishes "page already surfaced" from "entity merely mentioned earlier" — without this, window extraction would have suppressed every prior-turn entity by construction.
|
||||
|
||||
### To take advantage of v0.42.43.0
|
||||
`gbrain upgrade` (applies the new feedback-log migration automatically). The wider reflex window is on by default for context-engine hosts — set `retrieval_reflex_window_turns: 1` in `~/.gbrain/config.json` to restore single-turn behavior. Agents without the context engine: call `volunteer_context` per turn (window in, pointers out), or pipe a transcript through `gbrain watch --json`. After a few days, `gbrain volunteer-context --stats` shows which resolution arms are earning their keep; raise or lower `min_confidence` accordingly.
|
||||
## [0.42.42.0] - 2026-06-12
|
||||
|
||||
**`gbrain query` no longer pays a flat 10-second exit tax on managed Postgres behind a transaction-mode pooler — and CLI exit codes finally tell the truth on PGLite.** On deployments where the pooler holds sockets open past the bounded pool drain (gbrain#2084, a residual of gbrain#1972), every query printed its results and then sat for 10 seconds until the force-exit banner fired. The cause was two-layered: the hard-deadline timer was armed *before* the operation handler, so a multi-second search on a large brain burned the teardown budget (and any operation slower than 10 seconds was silently killed mid-run with exit 0 and truncated output); and the CLI never exited explicitly on success — it waited for Bun's event loop to drain, which a stuck pooler socket can hold open forever.
|
||||
|
||||
The teardown contract now lives in one place: every cli.ts disconnect site runs a bounded background-work drain and a bounded disconnect under a backstop whose deadline is computed from the bounds it guards (so it fires only when something violated its own bound), then the process exits explicitly — after fencing stdout/stderr and holding a short aliveness window so piped output is delivered (Bun queues pipe writes in a native buffer that only drains while the process is alive). The most-used command in the CLI now exits in milliseconds-to-a-couple-seconds instead of ten.
|
||||
|
||||
Along the way the wave fixed a deeper, silent bug: PGLite's WASM runtime writes its own status into `process.exitCode` at arbitrary points mid-run, which meant **every error exit on PGLite-engine brains has been reporting success (exit 0)** — scripts and agents keying on exit codes never saw failures. The CLI verdict now lives in a gbrain-owned channel that the WASM runtime cannot touch.
|
||||
|
||||
### Fixed
|
||||
- **The flat 10s teardown tax + force-exit banner on transaction-mode poolers (gbrain#2084).** Queries exit promptly; the banner now appears only when a teardown component genuinely violated its own bound.
|
||||
- **Slow operations are no longer killed mid-run with a false success.** The teardown deadline starts at teardown, never before the operation handler — a 30-second sync or a deep query runs to completion.
|
||||
- **Error exits on PGLite report exit 1, not 0.** Failed operations (e.g. `gbrain get <missing-page>`) now exit non-zero on every engine; the exit code reports the operation, not the cleanup.
|
||||
- **Piped output survives the exit.** Output is fenced and given a delivery window before the process exits, on every routed exit path including the backstop (the truncation class from gbrain#1959).
|
||||
- **`gbrain doctor` no longer leaks its connection pool when DB checks throw**, and `dream`, `doctor`, `ze-switch`, and the search dashboards route their dispatcher teardown through the same bounded path (closing a long-standing drain gap on the overnight-cron path).
|
||||
- **Daemon safety with space-separated global flags.** `gbrain --timeout 30s serve` is recognized as the daemon it is — the exit gate resolves the command exactly the way dispatch does.
|
||||
|
||||
### Added
|
||||
- **`GBRAIN_TEARDOWN_DEADLINE_MS`** — env override for the teardown backstop deadline (incident escape hatch; the default is computed from the drain and pool bounds).
|
||||
- **`GBRAIN_FLUSH_GRACE_MS`** — env override for the pre-exit output-delivery window (default 250ms on pipes, 0 on TTYs). Raise it when piping very large payloads into slow consumers; lower it for high-frequency scripted invocations that capture to files.
|
||||
|
||||
### To take advantage of v0.42.42.0
|
||||
`gbrain upgrade`. No configuration needed. If your `gbrain query` has been printing results and then hanging ~10 seconds before a `force-exiting` banner, this release removes both the wait and the banner. If your scripts check gbrain exit codes on a PGLite brain, they will start seeing real failures — previously masked as exit 0 — so a wrapper that suddenly reports errors is the fix working, not a regression.
|
||||
## [0.42.41.0] - 2026-06-11
|
||||
|
||||
**A correctness-and-reliability wave: your conversation facts survive a cycle, write-through stops polluting other repos, autopilot rides out a DB blip instead of crash-looping, and concurrent PGLite processes stop corrupting each other.** A triage of open reports surfaced six bugs with no fix yet plus a batch of community PRs; this ships them together, each with a regression test.
|
||||
|
||||
The headline is data durability. The `extract_facts` cycle phase reconciles a page's facts from its `## Facts` fence by deleting then reinserting — but conversation facts (written by `extract-conversation-facts`) live on pages that have no fence, so a cycle could delete them and reinsert nothing. A failed sync made it worse by escalating the phase to a full-brain walk. Both are fixed: the reconcile now protects non-fence (`cli:`-origin) facts, the destructive phase no longer inherits the failed-sync full-walk, and a reconcile that removes far more than it adds now reports `warn` instead of a silent `ok`.
|
||||
|
||||
Three more silent failures, each found in production and now self-healing or loud:
|
||||
- **Timeline writes that silently stopped.** A migration renumbered during a merge could be recorded as applied without its index change ever running, so every timeline insert failed its `ON CONFLICT`. `gbrain` now repairs the index shape on every migrate pass (dedupe-then-rebuild, even when nothing is pending), `gbrain doctor` reports the drift, and the meetings extractor no longer swallows batch errors.
|
||||
- **Autopilot crash-loop on transient DB errors.** The health-probe recovery called `connect()` without its config, so every reconnect threw and the process exited on any blip. It now uses `reconnect()`, which restores the captured config; `reconnect()` is a first-class method on both engines.
|
||||
- **WAL corruption from concurrent PGLite processes.** A live, working process holding the data-dir lock could have it stolen after five minutes. The lock now heartbeats while held and is only reclaimed from a dead or genuinely stalled holder.
|
||||
|
||||
### Added
|
||||
- **`timeline_dedup_index` doctor check + always-run repair (#2038).** Detects and heals a stale `idx_timeline_dedup` shape; `gbrain apply-migrations --force-schema` triggers the repair on demand. Reported by @jbarol.
|
||||
- **`BrainEngine.reconnect()` on both engines (#2034).** Config-restoring reconnect, replacing the `disconnect()`+bare-`connect()` pattern.
|
||||
|
||||
### Fixed
|
||||
- **Conversation facts survive a fence reconcile (#1928).** The cycle's per-page wipe now excludes non-fence (`cli:`) facts, the destructive phase no longer full-walks on a failed sync, and net-negative reconciles surface as `warn`.
|
||||
- **`put_page` write-through no longer leaks into an unrelated source's repo (#2018).** It mirrors to the assigned source's own `local_path`; a source without one is skipped rather than written into the global repo path.
|
||||
- **Autopilot survives transient DB errors instead of crash-looping (#2034).**
|
||||
- **Concurrent PGLite processes no longer corrupt the WAL (#2058).** Heartbeat + steal-grace replaces the age-only stale-lock check.
|
||||
- **Timeline migration drift self-heals; the extractor stops swallowing errors (#2038, #2057).** A Date-typed batch date round-trips correctly (verified by test).
|
||||
- **A cwd `.env` `DATABASE_URL` no longer silently retargets the brain (#2064, closes #427).** Reported by @bomliu.
|
||||
- **`gbrain sync --strategy code` honors `.gitignore` and skips `vendor`/`dist`/`build`/`venv` (#2052, #2020).** Reported by @aphaiboon and @dMac716.
|
||||
- **Asymmetric embedding `input_type` reaches the wire across every openai-compatible recipe (#2033, supersedes #1400).** Query vectors are no longer document-typed. By @pabloglzg; original diagnosis by @billy-armstrong.
|
||||
- **`updateSourceConfig` JSONB merge is atomic (#2074).** Eliminates a concurrent-writer lost-update race. Reported by @pai-scaffolde.
|
||||
- **`gbrain doctor` correctness pass (#2075):** stale-lock hints, content sanity, graph coverage, exit code, gateway guard. Reported by @pai-scaffolde.
|
||||
- **`gbrain search` returns results instead of exiting 0 empty on slow poolers; scoped `code-callers`/`code-callees` find their edges (#2073).** Migration v116 backfills NULL edge `source_id` and indexes `from_symbol_qualified`. Reported by @jbarol.
|
||||
- **OAuth scope handling (#2009, #2072):** an omitted authorize scope now defaults to the client's registered grant (clamped to it, so no widening) instead of an empty grant that never self-heals; legacy token source grants are honored through a single shared scope parser. By @austinrarnett and @maxpetrusenkoagent.
|
||||
|
||||
### To take advantage of v0.42.41.0
|
||||
|
||||
`gbrain upgrade`. The timeline-index repair and migration v116 run automatically on the next migrate pass — if `gbrain doctor` flagged a timeline or call-graph problem before, re-run it after upgrade. No config changes required; the facts, write-through, autopilot, and lock fixes apply on restart.
|
||||
|
||||
## [0.42.40.0] - 2026-06-09
|
||||
|
||||
**`gbrain extract --stale` no longer aborts partway through a brain that contains emoji or other non-BMP characters.** On a large brain, link/timeline extraction could die with `invalid input syntax for type json` and commit nothing — and because the staleness bookmark only advances on a clean finish, every retry re-hit the same point and extraction stayed wedged. The cause: the link-context excerpt was sliced by raw UTF-16 index, so a window boundary landing inside an emoji's surrogate pair left an unpaired surrogate half in the text, which Postgres rejects when the batch is serialized to JSONB — taking down the whole batch, not just the one row. (PGLite is more permissive here, so this primarily bit the managed-Postgres engine.)
|
||||
|
||||
The fix well-forms free text before it is serialized: any unpaired surrogate half is replaced with the Unicode replacement character before it reaches the database. It is applied at the slicer and, as defense in depth, centrally at the batch-insert boundary for every free-text field — link context, timeline summary/detail/source, take claim/source — across both the batch and single-row write paths and both engines. Identity fields (slugs, source ids, holders) are deliberately left untouched, so a malformed identifier still fails loudly instead of being silently rewritten. The same well-forming helper now also backs the brainstorm prompt path, replacing a hand-rolled version that left back-to-back malformed characters half-cleaned.
|
||||
|
||||
### Fixed
|
||||
- **`extract --stale` runs to completion on brains with emoji / non-BMP text (gbrain#2011).** The link-context slicer no longer leaves an unpaired UTF-16 surrogate that Postgres rejects at the JSONB cast and aborts the whole batch. A 192K-page brain that died at ~1,550 pages now sweeps clean.
|
||||
- **Defense in depth at the batch-insert boundary.** Every free-text field written to JSONB (link context; timeline summary/detail/source; take claim/source) is now NUL- and surrogate-sanitized centrally, in both the batch and single-row paths and on both engines, so no future slicer can re-trigger this class of crash. Identity/security fields stay un-sanitized and fail closed.
|
||||
|
||||
### Changed
|
||||
- **One shared well-forming primitive.** The brainstorm cross-prompt path now uses the same surrogate-cleaning helper, which also fixes a case where consecutive malformed characters were only half-cleaned.
|
||||
|
||||
### To take advantage of v0.42.40.0
|
||||
`gbrain upgrade`. No configuration needed. If a `gbrain extract` run had been stalling at the same page count every time, this is the release that unsticks it — the next run resumes and completes.
|
||||
## [0.42.39.0] - 2026-06-09
|
||||
|
||||
**Your agent now learns a brain page exists the moment you name someone — instead of talking about a close contact for four messages without ever opening their page.** gbrain was great at *storing* knowledge and at injecting deterministic per-turn context, but it never taught the agent the *policy* of retrieval: when to look something up, and what to pull. That lived in each user's hand-rolled instructions and failed silently. The Retrieval Reflex makes it a property of having a brain.
|
||||
|
||||
Two layers, on by default. A **deterministic pointer layer** in the context engine scans each turn's message for salient, resolvable entities (capitalized names, `@handles`) and injects a compact pointer — name → slug → one-line summary → "open the page before relying on details." Zero-LLM, fail-open, capped, and judgment-gated: it points, it never auto-dumps the page body, and it stays silent on trivial mentions or entities already in context. A **policy skill** (installed into your agent's resolver via `gbrain integrations install retrieval-reflex`) encodes the trigger policy and the pointer → full-page → graph-neighbors escalation ladder so the agent knows what to do with the pointer.
|
||||
|
||||
It works on every engine without leaking a second database connection. PGLite holds a single connection (your `gbrain serve` owns it), so the context engine resolves *through* the live holder over a local socket rather than opening its own — and on Postgres it uses a cached direct connection. Synopses run through the same privacy boundary `get_page` applies, so private facts never reach the prompt. `gbrain doctor` reports whether the reflex is actually firing.
|
||||
|
||||
### Added
|
||||
- **Retrieval Reflex deterministic pointer layer (gbrain#1981).** The context engine injects compact, privacy-safe entity pointers per turn — on by default, zero-LLM, fail-open, capped. Disable with `GBRAIN_RETRIEVAL_REFLEX=false` or `retrieval_reflex: false` in `~/.gbrain/config.json` (file/env plane).
|
||||
- **`retrieval-reflex` recipe + policy skill.** Installs the when/what-to-retrieve policy into your agent's resolver: `gbrain integrations install retrieval-reflex --target <host-repo>`.
|
||||
- **`retrieval_reflex_health` doctor check.** Reports the deterministic layer's real runtime status (observed firing, resolve path, policy-skill install state).
|
||||
|
||||
### Fixed
|
||||
- **Resolver-row install fence is now keyed by recipe id.** Installing a second `copy-into-host-repo` recipe previously wrote a block mislabeled with the first recipe's name; `--refresh`/uninstall now find their own rows.
|
||||
|
||||
### To take advantage of v0.42.39.0
|
||||
|
||||
`gbrain upgrade`. The deterministic pointer layer is on automatically — no config needed. To give the agent the matching policy skill, run `gbrain integrations install retrieval-reflex --target <your-agent-repo>`, then `gbrain doctor` to confirm `retrieval_reflex_health` is green.
|
||||
|
||||
## [0.42.38.0] - 2026-06-09
|
||||
|
||||
**Three independent job-layer bugs that left autopilot wedged or swallowed a command's output are fixed, each traced to source.** A triage of the job/lock/teardown layer (gbrain#1972) pulled them into one wave.
|
||||
|
||||
A crashed sync (OOM, a recycle, a kill) used to strand its lock row: the source looked "syncing" forever because reclaim only happened when something else came along and contended for the same lock. There was no background sweep, so a low-traffic source could sit falsely locked for a long time. Now every cycle reaps locks whose holder process is provably dead on this host — scoped to the sync/cycle lock namespaces, never to elections or the worker supervisor, and guarded against PID reuse so a recycled PID can never clear a live lock. `gbrain doctor --fix` runs the same reaper for brains that don't run autopilot.
|
||||
|
||||
Short one-shot CLI calls also got their full latency and output back. Database teardown could block for the full force-exit deadline against a transaction-mode pooler and then exit hard mid-write, which truncated the command's real output — the reason a relational query could come back empty even though the query itself worked. Teardown is now bounded by gbrain's own deadline instead of the connection driver's, so a short command returns in milliseconds with its output intact.
|
||||
|
||||
And the cooperative-abort work started in v0.42.29 (which only covered the embed phase) now covers every long phase a cycle runs — extract, fact extraction, and consolidation all check for cancellation between batches, so a cancelled cycle relinquishes its worker promptly instead of being force-evicted. A cancelled cycle also no longer records itself as a completed full run.
|
||||
|
||||
### Fixed
|
||||
- **Stale dead-holder locks are reaped automatically (gbrain#1972, adjacent to #1470).** A background, host-scoped sweep at cycle start deletes `gbrain-sync:*` / `gbrain-cycle*` locks whose holder PID is dead, with a snapshot-matched delete that's safe against PID reuse and a 60s grace window. Other lock namespaces (elections, supervisor, reindex) keep their existing TTL behavior, untouched. `gbrain doctor --fix` reaps too, for no-autopilot brains.
|
||||
- **One-shot CLI calls no longer hang on teardown or lose their output (gbrain#1959).** Pool disconnect is bounded by a gbrain-owned deadline (both pools closed concurrently) instead of blocking until the hard force-exit fired and truncated stdout. A short command returns promptly with intact output.
|
||||
- **Cooperative abort now covers every long cycle phase (gbrain#1737 follow-up).** `extract` (incremental + full-walk), `extract_facts` (including its per-page embed and the phantom-redirect lock-retry), and `consolidate` check the abort signal between batches; `lint` yields periodically so it can be cancelled too. A cycle aborted mid-phase no longer stamps `last_full_cycle_at` as a completed run, and a new per-phase duration warning names any phase that overruns the worker's force-evict deadline.
|
||||
|
||||
### To take advantage of v0.42.38.0
|
||||
|
||||
`gbrain upgrade`. No configuration needed — the lock reaper, bounded teardown, and abort coverage are all on by default. If a source has looked stuck "syncing" with no live process, the next cycle (or `gbrain doctor --fix`) clears it automatically.
|
||||
|
||||
## [0.42.37.0] - 2026-06-08
|
||||
|
||||
**Cross-source reads now honor the caller's grant everywhere, a single bad frontmatter value no longer wedges a whole `lint`/`sync` run, and a handful of long-standing papercuts are gone.** A triage of the open issue backlog pulled the highest-impact bugs into one wave.
|
||||
|
||||
The headline is a source-isolation hardening pass. Every read that can be scoped to a source now resolves through one shared, fail-closed trust+grant check, so a remote client only ever sees the sources it was granted — whether it asks for one source, all sources, or reads a page by exact slug. Reads route the same way across query, the code-intel traversals, image search, and `get_page`. Legacy bearer tokens now carry the source grant an operator already stored on them, instead of being pinned to `default`.
|
||||
|
||||
On ingestion, a non-string frontmatter value (a bare number or date in `title:`, `slug:`, or `type:`) used to throw partway through and abort the entire run — so one malformed file could stop a whole brain from linting or syncing. Now those values are coerced to a usable string (a bare date `2024-06-01` becomes a real slug, not a crash), and `gbrain lint` flags the un-quoted field by name so you can clean it up.
|
||||
|
||||
Plus: `gbrain embed --catch-up` runs to completion instead of stopping after the first batch (and tells you when chunks genuinely can't be embedded); the frontmatter pre-commit hook actually matches `.md`/`.mdx` files now instead of silently doing nothing; the skill catalog shows the real description for skills that write it as a YAML block scalar; and `getConfig` retries through a transient connection blip instead of silently falling back to defaults.
|
||||
|
||||
### Fixed
|
||||
- **Source-scoped reads honor the caller's grant across every read op (gbrain#1924, #1371, #1393).** One shared resolver replaces the per-op scope logic: a remote caller's "all sources" request is bounded to its grant, an out-of-grant source is refused, and `get_page`'s exact-slug path is scoped like every other read (both engines).
|
||||
- **Legacy bearer tokens carry their stored source grant (gbrain#1336).** Tokens with an operator-set source grant read across exactly those sources instead of being limited to `default`.
|
||||
- **Non-string frontmatter no longer aborts `lint`/`sync` (gbrain#1883, #1658, #1556, #1948).** Title/slug/type are coerced to usable strings instead of throwing mid-run, and `gbrain lint` reports the un-quoted field by name.
|
||||
- **`embed --catch-up` runs to completion (gbrain#1946).** The mode no longer stops after one batch, and surfaces chunks that can't be embedded instead of looking like a clean finish.
|
||||
- **Frontmatter pre-commit hook matches `.md`/`.mdx` files (gbrain#1840).** The installed hook was a silent no-op; it now validates staged markdown on commit.
|
||||
- **Skill catalog shows block-scalar descriptions (gbrain#1711).** Skills written with `description: |` show their real text instead of a stray indicator.
|
||||
- **`getConfig` retries on a transient connection blip (gbrain#1603)** instead of silently falling through to defaults (which surfaced as the wrong search mode / empty output on remote Postgres).
|
||||
|
||||
### To take advantage of v0.42.37.0
|
||||
|
||||
`gbrain upgrade`. No configuration needed. If `gbrain lint` now flags a `frontmatter-non-string-field` on a page, quote the value in that page's frontmatter (e.g. `title: "123"`). Reinstall the pre-commit hook with `gbrain frontmatter install-hook` to pick up the fixed matcher.
|
||||
|
||||
## [0.42.36.0] - 2026-06-08
|
||||
|
||||
**A huge `gbrain sync` that keeps getting killed now converges instead of restarting from zero.** On a high-write source — hundreds of thousands of files, a generator committing faster than each sync can drain — a full sync that ran past its launching session's timeout (SIGTERM) would lose 100% of its progress and re-import the entire backlog on the next run, forever. The bookmark never advanced, the source went quietly stale for hours while the importer burned CPU the whole time, and competing hourly launches stole each other's lock and raced. This release makes a large sync **resumable, durable, and single-flight** so it banks what it imports and picks up where it left off.
|
||||
|
||||
Progress is now banked into an append-only checkpoint as files drain, written through a direct session connection so it survives connection-pool exhaustion (the exact condition that used to silently drop every checkpoint write). The write is a delta — one row per drained file — instead of rewriting the whole completed-set each flush, so banking stays cheap even at hundreds of thousands of files. The bookmark still only advances on true completion, so a killed run resumes from the checkpoint rather than re-walking from zero. And the per-source lock now heartbeats through the direct pool and refuses to steal a holder that's alive and actively refreshing — so a long sync that overruns into the next scheduled run is skipped, not break-locked into a thrashing race.
|
||||
|
||||
### Fixed
|
||||
- **Resumable sync survives pool exhaustion (gbrain#1794).** Checkpoint reads/writes route through the direct session pool with bounded retry; `EMAXCONNSESSION` / `too_many_connections` are now classified retryable. A killed run banks its progress and the next run skips already-drained files.
|
||||
- **Guaranteed final flush on every exit path.** A cooperative timeout, an external SIGTERM (one-shot no-retry flush via the cleanup registry, ordered before lock release), and a clean finish all bank the in-flight delta. The bookmark is never advanced on a partial.
|
||||
- **Fail-loud instead of burning CPU.** If checkpoint persistence fails repeatedly (pool genuinely dead), the run aborts with a `checkpoint_unavailable` partial rather than importing work it can never bank. Every partial/blocked exit now logs how many files were banked, so a killed run is never misread as total loss.
|
||||
- **Lock thrash eliminated.** The import loop yields the event loop so the lock-refresh heartbeat fires mid-import; takeover refuses to steal a recently-refreshed (alive-but-starved) holder; a bare `gbrain sync` (no `--source`) now uses the refreshing lock too; and a cron sync that collides with a running one is reported as a skip, not a phase failure.
|
||||
|
||||
### Added
|
||||
- **Append-only checkpoint storage** (`op_checkpoint_paths`, migration v115): one row per drained path; O(delta) writes instead of O(N²) full-set rewrites over a large sync.
|
||||
|
||||
### To take advantage of v0.42.36.0
|
||||
- Nothing to do. `gbrain sync` is resumable by default — a killed sync now banks its progress and the next run converges. Five env knobs tune cadence, fail-loud threshold, event-loop yield, and lock-steal grace if you need them at incident time; see the "Sync resumability + lock tuning" section in CLAUDE.md.
|
||||
|
||||
## [0.42.35.0] - 2026-06-07
|
||||
|
||||
**A bookmark left pointing at a rewritten-away commit no longer freezes your brain in an endless full re-walk.** When a source's history is rewritten — a force-push, a `master`→`main` consolidation, a squash — the commit gbrain recorded as "last synced" can fall outside the branch's current history. The old guard treated that the same as a missing commit and fell back to re-importing the entire repository on every run. On a large brain with a cross-region database that full walk never finishes inside the sync timeout, so the bookmark never advanced and the source went quietly stale with no error surfaced.
|
||||
|
||||
The fix is a smaller, exact diff. `git diff A..B` compares two trees and does not require A to be an ancestor of B, so when the recorded commit's object is still on disk (the common case right after a rewrite) gbrain now diffs directly against it and imports only the real delta — the changed files, not the whole tree. A clear `[sync] last_commit … history rewritten` line marks the recovery. Only when the commit object is genuinely gone does sync fall back to a full reconcile, and that reconcile now also purges pages whose source files were removed — so a full sync is finally authoritative for deletes, not just imports (manually authored `put_page` pages and metafiles are never swept). Sibling of the v0.42.32.0 silent-staleness fix (gbrain#1939); closes gbrain#1970.
|
||||
|
||||
### Fixed
|
||||
- **Sync recovers from an unreachable `last_commit` instead of full-walking forever (gbrain#1970).** A bookmark orphaned by a history rewrite is now diffed tree-to-tree directly when its object is still present, importing only the changed files; an oversized or failed diff degrades to a full reconcile instead of throwing. Only a truly-absent (gc'd) object forces a full reconcile.
|
||||
- **A full sync now purges deleted files.** `performFullSync` reconciles deletions — pages whose backing file is gone are removed (gated to file-backed pages via `source_path`; manual `put_page` pages and metafiles are spared). This makes both the object-absent recovery path and every `--full` sync authoritative for deletes, not just imports.
|
||||
- **Rename to an unsyncable path deletes the stale page.** A syncable file renamed to a non-syncable destination (which git reports as a rename, not a delete) now removes the old page instead of leaving it orphaned.
|
||||
|
||||
### To take advantage of v0.42.35.0
|
||||
- Nothing to do. The next `gbrain sync` after upgrading self-heals a stuck bookmark automatically; watch for the one-line `[sync] last_commit … history rewritten` recovery message. If a source has been stale since a force-push or branch consolidation, this is the release that unsticks it.
|
||||
## [0.42.34.0] - 2026-06-07
|
||||
|
||||
**Relationship questions now get relationship answers.** Ask "who invested in widget-co", "who introduced me to alice-example", or "what connects fund-a and fund-b" and gbrain resolves the named entity and walks its typed-edge graph (`invested_in`, `works_at`, `founded`, `attended`, `advises`, …) to surface the answer — even when no single page mentions both sides. Until now the graph only re-ranked results that keyword/vector search had already found; a relationship that lived purely in the edges (an investor whose page never names the company) was invisible. It now enters retrieval as a first-class candidate.
|
||||
|
||||
This is on by default in the `balanced` and `tokenmax` search modes, a pure no-op for non-relational questions and for brains with no typed edges, and off in `conservative`. On a benchmark of relationship queries whose answers are unreachable by content similarity, recall@10 goes from near-zero to over 75%. The traversal is deterministic (same query + brain → same answer), stays within a single source (it never crosses a mounted-brain boundary), excludes noisy body-text "mentions" edges by default, and is depth- and fan-out-bounded so a popular hub entity can't blow up a query.
|
||||
|
||||
### Added
|
||||
- **Typed-edge relational retrieval** (`search.relational_retrieval`, on for balanced/tokenmax). Relational questions resolve their seed entity and traverse the typed-edge graph, injecting edge-derived answers as a fourth fusion arm alongside keyword + vector. Relation vocabulary is schema-pack-extensible: a pack that defines its own link types can declare the query phrases that retrieve them. The `query` operation gains a `relational` flag (omit for the smart default; pass `false` to force lexical/vector-only). Results carry `--explain` attribution ("surfaced via invested_in from widget-co") and, for "what connects A and B", the connecting path.
|
||||
- **`relationalFanout` engine method** (PGLite + Postgres, in lockstep). Seed-array typed-edge fan-out aggregating to ranked nodes (shortest hop, edge richness, connecting path, canonical chunk), source-scoped and deterministic.
|
||||
- **`gbrain eval retrieval-quality --ab-relational`**: A/Bs the arm off vs on over a question set and reports the recall@10 lift + latency. The retrieval-quality harness gains recall@k / recall@10 metrics.
|
||||
|
||||
### Fixed
|
||||
- **Cross-source result collapse.** The search fusion/dedup key now carries `source_id`, so two pages that share a slug across mounted brains no longer merge into one result. The semantic query cache is likewise scoped per source-set, so a federated search can't be served a single-source cached result.
|
||||
|
||||
### To take advantage of v0.42.34.0
|
||||
- Just ask relationship questions in natural language — the arm is on by default in balanced/tokenmax. To turn it off: `gbrain config set search.relational_retrieval false`.
|
||||
- One-time cache note: this release advances the search-cache key version (a relational-on result must not be served to a relational-off lookup), so the first query after upgrade re-runs instead of hitting a stale cache row. No action needed; it self-heals on first use.
|
||||
## [0.42.33.0] - 2026-06-07
|
||||
|
||||
**`gbrain sync` will never delete a repo it didn't create.** If a source was registered with a `remote_url` but its `local_path` pointed at a working tree you manage yourself (not a gbrain-managed clone), a failed or degraded code sync could remove that directory and re-clone over it. Sync now re-clones **only** clones gbrain actually created — identified by an ownership marker, or by gbrain's own clone location for clones made before this release. Anything else, including your live working tree, is treated as read-only: indexed, never deleted. On an unowned path, sync aborts loudly **before touching the filesystem** and tells you how to fix the source registration. Thanks to @zaqwery for the report.
|
||||
@@ -16878,7 +16264,8 @@ The OAuth provider in `src/core/oauth-provider.ts` got a parallel hardening pass
|
||||
Smaller hardening: admin cookies set `Secure` when behind HTTPS or a public-URL proxy (F9), magic-link nonces are bounded by an LRU cap (F10), `/mcp` wraps `transport.handleRequest` in try/catch so SDK throws hit a JSON-RPC 500 instead of express's default HTML error page (F14), and OperationError + unexpected exceptions both route through the unified `buildError`/`serializeError` envelope (F15). DCR disable became a constructor option on the provider rather than a serve-http monkey-patch (F12 — cleanup, not security).
|
||||
|
||||
To take advantage of v0.26.9
|
||||
=====================
|
||||
============================
|
||||
|
||||
`gbrain upgrade` is a one-step upgrade. There is no migration; all changes are application-layer.
|
||||
|
||||
1. **Upgrade.** `gbrain upgrade`. Confirm `gbrain --version` shows `0.26.9`.
|
||||
@@ -17012,7 +16399,8 @@ Both run at `--max-concurrency=1` after the parallel pass, same as the existing
|
||||
Wallclock observed: 74s on a Mac dev box (running `bun run test` with the new quarantines). Already at the v0.26.9 informational target. The full intra-file marker flip (with codemod + per-file `test.concurrent()`) lands in v0.26.9 and aims for the same ≤60s with pinned config.
|
||||
|
||||
To take advantage of v0.26.7
|
||||
=====================
|
||||
============================
|
||||
|
||||
`gbrain upgrade` does nothing functional in this release — it ships test infrastructure, not user-facing code. But if you contribute tests:
|
||||
|
||||
1. **Run `bun run verify` before pushing.** The new `check-test-isolation.sh` runs alongside the privacy + jsonb + progress checks. Catches new env-mutation, mock.module, and PGLite-pattern violations before CI does.
|
||||
|
||||
@@ -38,7 +38,7 @@ mount, CEO-class with multiple team brains) and
|
||||
|
||||
## Architecture
|
||||
|
||||
Contract-first: `src/core/operations.ts` defines ~90 shared operations (v0.29 adds `get_recent_salience`, `find_anomalies`, `get_recent_transcripts`; v0.42.43.0 adds `volunteer_context` — push-based context, see `docs/guides/push-context.md`). CLI and MCP
|
||||
Contract-first: `src/core/operations.ts` defines ~47 shared operations (v0.29 adds `get_recent_salience`, `find_anomalies`, `get_recent_transcripts`). CLI and MCP
|
||||
server are both generated from this single source. Engine factory (`src/core/engine-factory.ts`)
|
||||
dynamically imports the configured engine (`'pglite'` or `'postgres'`). Skills are fat
|
||||
markdown files (tool-agnostic, work with both CLI and plugin contexts).
|
||||
@@ -59,14 +59,9 @@ Per-file detail is in `docs/architecture/KEY_FILES.md`.
|
||||
- **Source isolation.** Every read-side op routes through `sourceScopeOpts(ctx)`; precedence
|
||||
is federated array (`ctx.auth.allowedSources`) > scalar (`ctx.sourceId`) > nothing. Don't
|
||||
hand-roll source filtering — a missed thread is a cross-source data leak.
|
||||
- **JSONB: never `JSON.stringify` into a `::jsonb` cast.** postgres.js double-encodes it (a jsonb
|
||||
string scalar); PGLite hides the bug. This bites BOTH spellings — the template form
|
||||
(`${JSON.stringify(x)}::jsonb`) AND the positional form (`executeRaw(\`…$N::jsonb\`, [JSON.stringify(x)])`,
|
||||
the #2339 class that aborted every sync). Fix: pass a raw object to `engine.executeRaw` / use
|
||||
`executeRawJsonb` / `sql.json()`; or for the positional path bind through `$N::text::jsonb` (binds as
|
||||
text, the cast parses it). Guarded by `scripts/check-jsonb-pattern.sh` (template grep) +
|
||||
`scripts/check-jsonb-params.mjs` (positional AST scanner); the real backstop is the DATABASE_URL-gated
|
||||
e2e parity tests, since PGLite can't surface the bug. Full rule in `docs/ENGINES.md`.
|
||||
- **JSONB: never `JSON.stringify` into a `::jsonb` cast.** postgres.js double-encodes it;
|
||||
PGLite hides the bug. Pass raw objects to `engine.executeRaw`, or use `executeRawJsonb`.
|
||||
Guarded by `scripts/check-jsonb-pattern.sh`.
|
||||
- **Engine parity.** `src/core/postgres-engine.ts` and `src/core/pglite-engine.ts` move in
|
||||
lockstep — a new method/SQL shape lands in BOTH, pinned by `test/e2e/engine-parity.test.ts`.
|
||||
Forward-referenced columns/indexes go in the bootstrap probe set (guarded by
|
||||
@@ -102,8 +97,6 @@ detail on demand.)
|
||||
| any file in `src/` (what it does + its invariants) | `docs/architecture/KEY_FILES.md` — find the file's entry |
|
||||
| search / ranking / hybrid / retrieval | `docs/architecture/RETRIEVAL.md` + the `search/*` entries in `KEY_FILES.md` |
|
||||
| search modes / cost knobs | `docs/guides/search-modes.md` |
|
||||
| embedding spend gates / cost gate / `spend.posture` / off switches | `docs/operations/spend-controls.md` |
|
||||
| push-based context (volunteer/watch/reflex window) | `docs/guides/push-context.md` |
|
||||
| schema packs / page types / extraction | `docs/architecture/schema-packs.md`, `type-taxonomy.md`, `lens-packs.md` |
|
||||
| thin-client / remote MCP / cross-modal | `docs/architecture/thin-client.md` |
|
||||
| the CLI surface (commands + flags) | `gbrain --help` / `gbrain --tools-json`, plus the relevant `KEY_FILES.md` entry |
|
||||
@@ -156,7 +149,6 @@ project resolves through `src/core/search/mode.ts`.
|
||||
| `intentWeighting` | true | true | true |
|
||||
| `tokenBudget` | **4000** | **12000** | **off** |
|
||||
| `expansion` (LLM multi-query) | false | false | **true** |
|
||||
| `relationalRetrieval` | false | **true** | **true** |
|
||||
| `searchLimit` default | 10 | 25 | 50 |
|
||||
|
||||
**Cost anchors (downstream agent input cost — gbrain itself is rounding error).**
|
||||
@@ -215,19 +207,6 @@ written against `embedding` (1536d OpenAI). Existing v=2 rows become
|
||||
unreachable on first re-query (one-time miss spike on upgrade);
|
||||
`mode.ts:KNOBS_HASH_VERSION` is the single source of truth.
|
||||
|
||||
**v0.42.34.0 knobs_hash v=9 → v=10.** Folds the `relationalRetrieval` knob +
|
||||
depth into the cache key so a relational-on result set can't be served to a
|
||||
relational-off lookup (same contamination class as graph_signals). One-time
|
||||
miss spike on upgrade.
|
||||
|
||||
**Relational retrieval (v0.42.34.0).** `relationalRetrieval` (on for
|
||||
balanced/tokenmax) adds a fourth recall arm: a relational query ("who invested
|
||||
in X", "what connects A and B") resolves its seed entity and walks the typed-edge
|
||||
graph (`src/core/search/relational-recall.ts` + `relational-intent.ts`,
|
||||
`engine.relationalFanout`), injecting edge-derived answers into RRF. Within-source,
|
||||
deterministic, mentions-excluded by default, pure no-op for non-relational queries.
|
||||
The `query` op's `relational` flag forces it on/off per call.
|
||||
|
||||
**Three CLI surfaces:**
|
||||
|
||||
gbrain search modes # what is running, with per-knob attribution
|
||||
@@ -259,7 +238,7 @@ audit trail lives in the source repo's git history.
|
||||
|
||||
## Skills
|
||||
|
||||
Read the skill files in `skills/` before doing brain operations. GBrain ships 30 skills
|
||||
Read the skill files in `skills/` before doing brain operations. GBrain ships 29 skills
|
||||
organized by `skills/RESOLVER.md` (`AGENTS.md` is also accepted as of v0.19):
|
||||
|
||||
**Original 8 (conformance-migrated):** ingest (thin router), query, maintain, enrich,
|
||||
@@ -278,17 +257,6 @@ routing is narrowed to what the skill actually covers.
|
||||
**Skillify loop (v0.19):** skillify (the markdown orchestration), skillpack-check
|
||||
(agent-readable health report).
|
||||
|
||||
**Brain-resident skillpacks + advisor (v0.42.47.0, #2180):** A brain repo can carry its
|
||||
own publishable skillpack (`brain_resident: true` in `skillpack.json` + `schema_pack`);
|
||||
`gbrain skillpack init-brain-pack` scaffolds one with a 5-section machine-parseable README.
|
||||
Connecting harnesses discover it on `gbrain sources add` (Topology A advisory, bounded nag
|
||||
via `nag-state.ts`) and over MCP via the source-scoped `list_brain_skillpack` op +
|
||||
`get_skill --source_id` (gated by `mcp.publish_skills`). The bundled `gbrain-advisor` skill
|
||||
+ `gbrain advisor` op compute a ranked, read-only list of high-leverage actions from brain
|
||||
state (8 collectors in `src/core/advisor/`); `--json`+exit codes for CI/cron, local-only
|
||||
`--apply <id>` behind confirm, exposed over MCP behind `mcp.publish_advisor` (default off,
|
||||
read-only on remote). Thin-client binary install stays deferred to PR2 `build_skillpack`.
|
||||
|
||||
**Routing-table compression (v0.32.3.0):** `skills/functional-area-resolver/` —
|
||||
two-layer dispatch pattern for shrinking large AGENTS.md / RESOLVER.md files
|
||||
(>=12KB) without losing routing accuracy. Replaces one row per skill with one
|
||||
@@ -388,76 +356,6 @@ For background tasks (`run_in_background: true`), the harness captures the exit
|
||||
file separately — use it via the bg task's `<id>.exit` file, not the streamed
|
||||
output.
|
||||
|
||||
## Sync resumability + lock tuning (v0.42.x, #1794)
|
||||
|
||||
`gbrain sync` is resumable and converges under pool exhaustion + repeated kills.
|
||||
Progress banks into the append-only `op_checkpoint_paths` table (one row per drained
|
||||
path, written via the direct session pool so it survives `EMAXCONNSESSION`); a killed
|
||||
run resumes from the checkpoint and `last_commit` only advances on true completion. The
|
||||
per-source lock heartbeats through the direct pool and refuses to steal a live,
|
||||
recently-refreshed holder. Six env knobs tune it (all env-only, incident-time escape
|
||||
hatches — no config-dashboard surface by design):
|
||||
|
||||
| Env var | Default | What it does |
|
||||
|---|---|---|
|
||||
| `GBRAIN_SYNC_CHECKPOINT_EVERY` | 1000 | Flush the checkpoint every N drained files. |
|
||||
| `GBRAIN_SYNC_CHECKPOINT_SECONDS` | 10 | Also flush every N seconds (whichever comes first) — bounds worst-case loss regardless of throughput. Flush also fires after the first file. |
|
||||
| `GBRAIN_SYNC_MAX_CHECKPOINT_FAILURES` | 3 | Consecutive failed flushes (each already retried ~12s) before the run aborts with `reason: 'checkpoint_unavailable'` instead of importing work it can never bank. |
|
||||
| `GBRAIN_SYNC_YIELD_EVERY` | 64 | Yield the event loop (`setTimeout(0)`, NOT `setImmediate` — Bun starves the timers phase under a tight setImmediate loop) every N files so the lock-refresh `setInterval` heartbeat fires mid-import. |
|
||||
| `GBRAIN_LOCK_STEAL_GRACE_SECONDS` | derived (~600 at 30min TTL) | A holder that refreshed within this window is NOT stolen even if its TTL lapsed (starved-but-alive). Dead holders stop refreshing, age past the grace, and become stealable; TTL stays the backstop. |
|
||||
| `GBRAIN_SYNC_STALL_ABORT_SECONDS` | 900 | Progress-aware stall watchdog (#1950): if the import drain makes no forward progress (keyed on file-import progress, NOT the lock heartbeat) for N seconds, abort the run and release the per-source lock so the next `gbrain sync` resumes from the checkpoint. Reports `reason: 'stall_timeout'`. Observed BETWEEN files; a hang inside one file's import isn't interrupted until it returns (the wall-clock hard deadline is that backstop). 0 disables. |
|
||||
|
||||
## Pace Mode (DB-contention-aware backfill pacing)
|
||||
|
||||
A naive `gbrain embed --stale` / large `sync` can saturate a PgBouncer
|
||||
transaction-mode pooler and starve the minion supervisor's lock renewals
|
||||
(`lock-renewal-failed` → dead jobs). Pacing is the native, composable fix — it
|
||||
replaces external SIGSTOP/SIGCONT wrapper scripts. **Opt-in: default mode `off`.**
|
||||
|
||||
The composable primitive is `src/core/db-pacer.ts` (`createDbPacer`):
|
||||
- **Concurrency cap is the real lever** (caps simultaneous in-flight DB writes =
|
||||
pooler slots held). Embed paths set their worker count to `maxConcurrency`
|
||||
(single pool, no permit); `sync` uses the shared `acquire()` **permit** because
|
||||
each parallel worker owns a separate engine (one budget must span pools).
|
||||
- **In-band signal** (`observe(ms)` EWMA from the work's own queries — never
|
||||
blind the way an out-of-band probe pool was). **No probe loop, no
|
||||
`probeLatency` engine method.**
|
||||
- **Cooperative `pace()` sleep** on `setTimeout` (keeps the lock heartbeat
|
||||
firing), jittered to avoid a thundering-herd resume. `acquire()`/`pace()` throw
|
||||
`AbortError` on cancel; everything else is fail-open (a pacer bug never kills a
|
||||
backfill, never throws an unhandledRejection).
|
||||
|
||||
Named bundles resolve through `src/core/pace-mode.ts` (`resolvePaceMode`), mirror
|
||||
of the search-mode pattern but with **env ABOVE config** (incident escape hatch):
|
||||
|
||||
per-call flag → GBRAIN_PACE_* env → config (pace.*) → PACE_BUNDLES[mode] → off
|
||||
|
||||
| Knob | off | gentle | balanced | aggressive |
|
||||
|---|---|---|---|---|
|
||||
| `maxConcurrency` | (off) | 4 | 8 | 16 |
|
||||
| `paceAtMs` (EWMA → sleep) | — | 250 | 500 | 1000 |
|
||||
| `maxSleepMs` (jittered cap) | — | 2000 | 1500 | 1000 |
|
||||
|
||||
**Surfaces.** `gbrain embed --stale --pace[=mode]` (bare `--pace` = balanced),
|
||||
`--pace-max-concurrency=N`. `--background` carries explicit pace OVERRIDES (not
|
||||
the resolved bundle) into the `embed` job payload; the handler re-resolves
|
||||
env>config>bundle at execution so `GBRAIN_PACE_*` still wins (CX5). Config-level
|
||||
`pace.mode` paces EVERY `runEmbedCore` caller (cycle embed, embed-catch-up,
|
||||
sync-auto-embed) and the prod `embed-backfill` job automatically. `sync` reads
|
||||
env/config. PGLite / mode `off` → no-op pacer.
|
||||
|
||||
**Correctness fixes pacing bundles** (longer paced runs widen these): CLI
|
||||
`embed --stale` single-flights via the SAME per-source lock key as the
|
||||
`embed-backfill` handler (`src/core/embed-backfill-lock.ts`; all-source runs lock
|
||||
every source in sorted order) so a hand-run backfill and a queued job can't race
|
||||
the NULL→non-NULL upsert (`TODOS:2299`); a **bounded** end-of-run keyset re-entry
|
||||
(max 3 + forward-progress, paced runs only) catches rows inserted behind the
|
||||
cursor (`TODOS:2301`); and the embed wall-clock budget timer is re-armed around
|
||||
`pace()` sleeps so paced time doesn't burn the work budget.
|
||||
|
||||
`EmbedResult.pacing` carries the end-of-run telemetry (cap, samples, EWMA, slept
|
||||
ms, max waiters) for `--json`; a one-line summary prints to stderr.
|
||||
|
||||
## Build
|
||||
|
||||
`bun build --compile --outfile bin/gbrain src/cli.ts`
|
||||
|
||||
@@ -258,24 +258,6 @@ The whole loop is described in [`docs/architecture/topologies.md`](docs/architec
|
||||
|
||||
**Job queue (Minions).** BullMQ-shaped, Postgres-native job queue. Durable subagents (LLM tool loops that survive crashes via two-phase pending→done persistence), shell jobs with audit, child jobs with cascading timeouts, rate leases for outbound providers, attachments via S3/Supabase storage. Replaces "spawn subagent as fire-and-forget Promise" with something that recovers from anything.
|
||||
|
||||
**Non-English brains (FTS language config).** The Postgres full-text search tokenizer is configurable via `GBRAIN_FTS_LANGUAGE`. Defaults to `english`. Set it to any text-search configuration that exists in your Postgres instance:
|
||||
|
||||
```bash
|
||||
export GBRAIN_FTS_LANGUAGE=portuguese # uses built-in portuguese stemmer
|
||||
export GBRAIN_FTS_LANGUAGE=spanish # built-in spanish stemmer
|
||||
export GBRAIN_FTS_LANGUAGE=pt_br # custom config (e.g. unaccent + portuguese)
|
||||
```
|
||||
|
||||
List available configs: `psql -c "SELECT cfgname FROM pg_ts_config"`. Both the **query side** (`websearch_to_tsquery`) and the **write side** (the trigger functions that populate `pages.search_vector` and `content_chunks.search_vector`) honor `GBRAIN_FTS_LANGUAGE`. On first install (or upgrade), the `configurable_fts_language` schema migration reads the env var and creates trigger functions in the configured language; subsequent inserts/updates tokenize using that setting. To change language on a brain that has already run the migration, use the dedicated CLI command:
|
||||
|
||||
```bash
|
||||
export GBRAIN_FTS_LANGUAGE=portuguese
|
||||
gbrain reindex-search-vector --dry-run # preview row counts
|
||||
gbrain reindex-search-vector --yes # recreate triggers + backfill
|
||||
```
|
||||
|
||||
The command is idempotent (re-running with the same language is a no-op for vector content) and uses the same recreate-and-backfill primitives as the migration. For accent-insensitive Portuguese (`pt_br`), see [docs/guides/multi-language-fts.md](docs/guides/multi-language-fts.md) for the `unaccent` + portuguese stemmer recipe.
|
||||
|
||||
**43 curated skills.** Routing lives in [`skills/RESOLVER.md`](skills/RESOLVER.md). Covers signal capture, ingest (idea / media / meeting), enrichment, querying, brain ops, citation fixing, daily task management, cron scheduling, reports, voice, soul audit, skill creation, eval framework, and migrations. Skills are markdown files (tool-agnostic), packaged as a single skillpack the installer drops into your agent workspace.
|
||||
|
||||
**Eval framework.** `gbrain eval longmemeval` runs the public [LongMemEval](https://huggingface.co/datasets/xiaowu0162/longmemeval) benchmark against your hybrid retrieval. `gbrain eval export` + `gbrain eval replay` capture real queries and replay them against code changes (set `GBRAIN_CONTRIBUTOR_MODE=1`). `gbrain eval cross-modal` cross-checks an output against the task using three different-provider frontier models. `gbrain eval retrieval-quality` runs NamedThingBench, which hard-gates the named-thing retrieval families (title-substring, alias-synonym, generic-to-named, multi-chunk-dilution) so a regression in "find the page this query names" fails CI loudly. Full methodology in [`docs/eval/SEARCH_MODE_METHODOLOGY.md`](docs/eval/SEARCH_MODE_METHODOLOGY.md).
|
||||
@@ -307,8 +289,6 @@ Data flowing into the brain. Each integration is a recipe — markdown + setup h
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
**`gbrain init --pglite` crashes on macOS 26.x (Tahoe)?** PGLite's embedded WASM engine is incompatible with macOS 26.x on Apple Silicon. The fix is to use native Homebrew PostgreSQL + pgvector instead. Full step-by-step setup in [`docs/INSTALL.md` — Troubleshooting: PGLite crashes on macOS 26.x](docs/INSTALL.md#pglite-crashes-on-macos-26x-tahoe).
|
||||
|
||||
**`gbrain import` fails with `expected N dimensions, not M`?** Run `gbrain doctor`. It will print the exact `gbrain config set ...` or `gbrain retrieval-upgrade` command to repair the mismatch. You should not need to delete `~/.gbrain`. Fresh `gbrain init --pglite` auto-detects your embedding provider from API keys in your environment: set `OPENAI_API_KEY` (or `ZEROENTROPY_API_KEY` / `VOYAGE_API_KEY`) before running init, or pass `--embedding-model <provider>:<model>` explicitly. With multiple keys set, init fires an interactive picker. In non-TTY contexts (CI, Docker) with no keys, init exits 1 with a paste-ready setup hint; pass `--no-embedding` to defer setup until runtime. See [`docs/integrations/embedding-providers.md`](docs/integrations/embedding-providers.md) for the full provider matrix and [`docs/operations/headless-install.md`](docs/operations/headless-install.md) for Docker/CI sequencing.
|
||||
|
||||
**Hourly cron sync keeps timing out on a federated brain?** v0.41.13.0 ships
|
||||
|
||||
-12
@@ -87,18 +87,6 @@ and the DCR `POST /register` path. Pre-v0.41.3 the CLI hard-coded
|
||||
operators to UPDATE `oauth_clients` rows by hand to make claude.ai work
|
||||
without `--enable-dcr`. That footgun is gone.
|
||||
|
||||
### DCR consent default (v0.42.55+)
|
||||
|
||||
The "disable `client_credentials`, only allow `authorization_code`" guidance
|
||||
above is now the built-in default for the DCR path, not just advice for custom
|
||||
wrappers. With `--enable-dcr` on, a self-registered client defaults to the
|
||||
`authorization_code` (browser-approval) grant, and an explicit
|
||||
`client_credentials` request is rejected with `invalid_client_metadata`.
|
||||
Operators who genuinely need the machine-to-machine grant on the registration
|
||||
endpoint opt in with `--enable-dcr-insecure` (which implies `--enable-dcr`); a
|
||||
startup WARNING prints whenever DCR is enabled, and a second when the insecure
|
||||
grant is allowed. Pre-registering clients via the CLI / admin API is unchanged.
|
||||
|
||||
### Token Management
|
||||
|
||||
```bash
|
||||
|
||||
@@ -1,397 +1,5 @@
|
||||
# TODOS
|
||||
|
||||
## community fix-wave follow-ups (filed v0.42.60.0)
|
||||
|
||||
- [ ] **P1 — take-writes source scoping fails open when source resolution errors (#2684 residual).**
|
||||
`resolveTakesSourceId` (src/commands/takes.ts) swallows resolution errors and returns
|
||||
`undefined`, which falls back to the unscoped slug-only page lookup — so an invalid
|
||||
`GBRAIN_SOURCE` (or a broken dotfile chain) silently restores the pre-#2698 cross-source
|
||||
write behavior on multi-source brains. Decide fail-closed semantics: error out when a
|
||||
source was explicitly requested but doesn't resolve; keep the unscoped fallback only for
|
||||
brains with no source configuration at all. Add a regression test for the invalid-source
|
||||
path. Found by cross-model adversarial review during the v0.42.60.0 release ship.
|
||||
- [ ] **P2 — cherry-pick #2112's uncovered doctor.ts hunk.** Fix-wave A (#2820) superseded
|
||||
most of #2112 but not its `checkSubagentCapability` fix (check explicit `models.subagent`
|
||||
before `models.tier.subagent`). Refile or cherry-pick; the rest of that PR is covered.
|
||||
|
||||
## v0.42.59.0 follow-ups (five-fix rollup #2735–#2739)
|
||||
|
||||
Filed as follow-ups from v0.42.59.0 (bootstrap probe for
|
||||
`timeline_entries.event_page_id`, migrate-engine source catalog + target-aware
|
||||
resume, entity-resolution quarantine, escape-aware fence cells, think gather
|
||||
source scope).
|
||||
|
||||
- [ ] **P2 — schema-bootstrap-coverage strip block never exercises `timeline_entries.event_page_id`.**
|
||||
The guard's pre-migration-brain simulation (the strip DDL in
|
||||
`test/schema-bootstrap-coverage.test.ts`) has no
|
||||
`ALTER TABLE timeline_entries DROP COLUMN IF EXISTS event_page_id` (or FK drop), so the
|
||||
coverage entry added for the v121 forward reference is vacuous — the probe never fires
|
||||
under that harness. The real regression guard lives in `test/bootstrap.test.ts` (which
|
||||
does drop → re-bootstrap → assert). Add the DROP statements to the strip block so the
|
||||
coverage test genuinely exercises its own entry.
|
||||
- [ ] **P2 — extract-facts reconcile still wipes-then-reinserts when the parse emitted MALFORMED warnings.**
|
||||
`runExtractFacts` (`src/core/cycle/extract-facts.ts`) deletes a page's facts and
|
||||
reinserts from the parsed fence even when `parseFactsFence` surfaced
|
||||
`FACTS_TABLE_MALFORMED` warnings — any future parse defect becomes a deletion vector
|
||||
(rows the parser failed to read get wiped with nothing to reinsert). Consider
|
||||
skip-wipe-on-warnings: treat a warning-bearing parse as non-authoritative for that page
|
||||
(skip the wipe, surface a warn), mirroring the empty-fence legacy-row guard's posture.
|
||||
- [ ] **P3 — bare-name resolution quarantines even on an exact unique match when prefix siblings exist.**
|
||||
With pages `companies/acme` + `companies/acme-labs`, a bare `"Acme"` yields two
|
||||
`findPrefixCandidates` rows, so `tryUnambiguousPrefixExpansion` declines — even though
|
||||
`companies/acme` is an exact `dir/token` slug match (and may be a unique exact title
|
||||
match). That's an unambiguity signal being wasted. Consider promoting an exact
|
||||
`dir/token` (or exact-title) hit above the sibling-count check in
|
||||
`src/core/entities/resolve.ts`.
|
||||
- [ ] **P2 — `scripts/run-verify-parallel.sh` no-gtimeout fallback reports the watchdog's exit code, not the check's.**
|
||||
In the fallback branch, `rc=$?` is captured after `wait "$cap_pid"` (the killed
|
||||
sleep-watchdog, rc=143) rather than after `wait "$pid"` (the actual check) — on a Mac
|
||||
without coreutils every check false-fails with rc=143. Capture `rc` from `wait "$pid"`
|
||||
first, then reap the watchdog.
|
||||
- [ ] **P3 — same-target migrate resume with `--force` still skips checkpointed pages after the wipe.**
|
||||
`gbrain migrate --to <engine> --force` wipes the target's pages, but the resume
|
||||
manifest's `completed_slugs` filter still applies, so previously-checkpointed pages are
|
||||
skipped against the now-empty target (pre-existing behavior; the v0.42.59.0 verification
|
||||
warns about it). `--force` should clear the manifest when it matches the same target.
|
||||
Where: `src/commands/migrate-engine.ts`.
|
||||
- [ ] **P2 — think residual scope gaps.** Two spots in `src/core/think/index.ts` don't yet
|
||||
inherit the caller's source scope the way the gather stage now does:
|
||||
`persistCitations` resolves citation slugs with an unscoped
|
||||
`SELECT id FROM pages WHERE slug = $1 LIMIT 1` (cross-source slug ambiguity can attach
|
||||
saved evidence to the wrong same-slug page), and the trajectory entity-resolution scalar
|
||||
is `opts.sourceId ?? 'default'` (a federated caller with `allowedSources` but no scalar
|
||||
resolves entities against `default` instead of its grant). Mirror the gather-stage
|
||||
precedence (federated array > scalar > default) at both sites.
|
||||
|
||||
## provider-agnostic follow-ups (filed v0.42.58.0)
|
||||
|
||||
Deferred from the provider-agnostic plumbing wave (#1249/#1250/#1292/#2271/#2209).
|
||||
Plan + review trail at `~/.claude/plans/system-instruction-you-are-working-keen-newell.md`.
|
||||
The eng-review + Codex outside-voice narrowed the wave to these deferrals:
|
||||
|
||||
- [ ] **P2 — Capability-aware query expansion on OpenAI-compat providers (#2372).**
|
||||
Expansion only runs for recipes that declare an `expansion` touchpoint, and only the
|
||||
native providers (anthropic/openai/google) do. To make expansion work on
|
||||
litellm/openrouter/groq/together/deepseek you must ADD expansion touchpoints to those
|
||||
chat-capable recipes AND add a `generateObject`→`generateText` capability fallback for
|
||||
backends without strict structured outputs. Feature-shaped; overlaps the general
|
||||
OpenAI-compat proxy story (`docs/designs/COMMUNITY_IDEAS.md`). Community PR #2373 is a
|
||||
starting point. Where: `src/core/ai/gateway.ts:expand`, recipe files, `types.ts` (ExpansionTouchpoint).
|
||||
- [ ] **P2 — LiteLLM as a chat/expansion backend.** `litellm-proxy` declares ONLY an
|
||||
embedding touchpoint, so `think`/chat on LiteLLM is dead. Add chat (and expansion) so a
|
||||
LiteLLM proxy is a full LLM backend, not embedding-only. The general OpenAI-compat proxy story.
|
||||
- [ ] **P3 — Per-model embedding dims metadata on `EmbeddingTouchpoint`.** `default_dims`
|
||||
is recipe-wide, so a recipe (ollama) can't carry different native dims per model. This
|
||||
wave added the modern ollama model NAMES + a `trust_custom_dims` passthrough (user supplies
|
||||
`--embedding-dimensions`); per-model dims would let gbrain pick the right default. Then
|
||||
ollama could fail-closed at preflight like litellm/llama-server instead of at first embed.
|
||||
- [ ] **P3 — Google native baseURL normalization (#1250 follow-up).** `resolveNativeBaseUrl`
|
||||
covers anthropic + openai; Google was deferred because Gemini's native suffix is unproven
|
||||
(its OpenAI-compat route is `/v1beta/openai`). Verify the correct `@ai-sdk/google` suffix,
|
||||
then add `google` to the helper. Where: `src/core/ai/gateway.ts:resolveNativeBaseUrl`.
|
||||
- [ ] **P3 — Fold Voyage/Google/LiteLLM/OpenRouter API keys into `buildGatewayConfig`.**
|
||||
It folds only OPENAI/ANTHROPIC/ZEROENTROPY file-plane keys today, so `config.json`-set keys
|
||||
for other providers only work if also in `process.env`. Extend the mapping. Where:
|
||||
`src/core/ai/build-gateway-config.ts`.
|
||||
- [ ] **P3 — OpenRouter per-model custom-dim handling.** OpenRouter declares recipe-wide
|
||||
`dims_options` and mixes fixed-dim + arbitrary models, so it's excluded from `trust_custom_dims`.
|
||||
A per-model story would let OpenRouter accept custom dims for models that support them.
|
||||
- [ ] **P1 — Gateway subagent-loop tool-result persistence + Date normalization (#2273/#2256).**
|
||||
Confirmed crash-block: non-Anthropic subagent jobs dead-letter after any interruption
|
||||
(tool-result user turns aren't persisted; raw Date values fail the AI SDK's strict JSON
|
||||
check). Larger self-contained change with 6 competing community PRs
|
||||
(#2274/#2257/#1934/#2065/#2112/#2336) — pick one canonical impl, preserve authorship.
|
||||
This is the immediate fast-follow to the provider-agnostic wave. Where:
|
||||
`src/core/ai/gateway.ts:toolLoop`/`toModelMessages`, `src/core/minions/handlers/subagent.ts`.
|
||||
|
||||
## Life Chronicle follow-ups (filed v0.42.56.0, #2390)
|
||||
|
||||
Deferred from the Life Chronicle wave (CEO Scope-Expansion + eng review CLEARED,
|
||||
3 codex rounds absorbed, PR #2533). Every item was an explicit review decision,
|
||||
not an oversight; each names its decision provenance.
|
||||
|
||||
- [ ] **P1 — Eval-gated auto-emit default-flip (D5.5 fast-follow).** Auto-emission
|
||||
ships OFF (`auto_chronicle=false`) per spend/consent posture. The headline
|
||||
fast-follow: run `gbrain eval chronicle` + a live-LLM OFF-vs-ON agent arm on a
|
||||
real brain, and if the lift holds, flip the default ON in the next minor with
|
||||
an upgrade notice. Where: `src/core/chronicle/config.ts`, upgrade banner in
|
||||
`src/commands/upgrade.ts`.
|
||||
- [ ] **P2 — Live-LLM OFF-vs-ON eval arm + LongMemEval temporal slice.** The
|
||||
shipped `gbrain eval chronicle` is the deterministic CI bar (6 gold tasks).
|
||||
The full North-Star proof adds (a) a live agent reconstructing a day with the
|
||||
chronicle ops ON vs OFF, and (b) the LongMemEval `question_type:
|
||||
temporal-reasoning` slice as secondary corroboration — verify the adapter can
|
||||
filter by question type first. Where: `src/eval/chronicle/harness.ts`,
|
||||
`src/commands/eval-longmemeval.ts`.
|
||||
- [ ] **P2 — Passive diary capture + consent model (D3.5/E5).** Active-only in v1
|
||||
by explicit decision (highest consent-risk surface). Passive detection of
|
||||
first-person interiority in transcripts requires a dedicated consent design:
|
||||
an explicit `chronicle.diary.passive` opt-in, a consent prompt, and
|
||||
provenance-aware redaction (the facts `visibility` lane is already in place).
|
||||
- [ ] **P2 — Ontology interval-splitting for backdated conflicts (G4).** A
|
||||
backdated observation whose validity window overlaps an existing row is
|
||||
flagged (not rewritten) in v1. Real interval algebra (split the prior window
|
||||
around the backdated fact) is deliberate follow-up scope; the conflict lane
|
||||
(`findOntologyConflicts`) is the holding surface. Where: both engines'
|
||||
`mergeOntologyFact`.
|
||||
- [ ] **P3 — Cross-brain federated timeline (D3.6/E6).** v1 holds source
|
||||
isolation (scoped-default, `--all-sources` opt-in within the host brain).
|
||||
Unifying across mounted team brains is its own epic with an access-policy
|
||||
surface.
|
||||
- [ ] **P3 — Place-as-entity (`gbrain where <venue>`).** `event.where` is
|
||||
captured as free text; resolving venues to entity pages + geo-adjacency
|
||||
queries is a follow-up.
|
||||
- [ ] **P3 — Richer meta-ontology dashboard.** `gbrain ontology-dimensions` is
|
||||
the v1 surface; a full dashboard (per-dimension drill-down, quarantine review
|
||||
queue for novel dimensions) is deferred until usage shows demand.
|
||||
- [ ] **P3 — Materialized daily timeline pages / emotional-arc view.** The
|
||||
query-time aggregator won D5.6; embeddable `life/timeline/YYYY/MM/DD.md`
|
||||
narrative pages (a single `materialize_timeline` cycle phase) revisit after
|
||||
the eval shows `reflect`-style recall needs them.
|
||||
|
||||
## reliability fix-wave follow-ups (filed v0.42.52.0)
|
||||
|
||||
Deferred from the autopilot/supervisor + sync/status/minion reliability wave
|
||||
(plan-eng-review + codex + adversarial diff review CLEARED). Both surfaced by the
|
||||
ship-stage pre-landing review; neither blocks the wave.
|
||||
|
||||
- [ ] **P2 — Thread a cancellation signal through `importFile` (#1950).** The sync
|
||||
stall watchdog aborts `opts.signal`, but the per-iteration abort checks observe
|
||||
it BETWEEN files — a hang inside one `importFile` call (e.g. a stuck embed
|
||||
network request) isn't interrupted until that call returns. Thread an
|
||||
`AbortSignal` into `importFromContent`/`importFromFile` and check it at the async
|
||||
phase boundaries (post-parse, pre-embed, pre-DB-write) so an in-flight wedge is
|
||||
reaped too. Core hot path (engine-parity + downstream-client surface) — scope it
|
||||
on its own. Where: `src/core/import-file.ts`, `src/commands/sync.ts`.
|
||||
- [ ] **P3 — Centralize live-sync liveness onto `liveSyncStatus` (#1950).**
|
||||
`gbrain sources status` now uses the shared `liveSyncStatus(engine, sourceId)`
|
||||
helper; retrofit `gbrain doctor` (its own inline lock probe) and `gbrain status`
|
||||
onto the same helper so there's one source of truth for "is this source
|
||||
syncing." Where: `src/core/db-lock.ts`, `src/commands/doctor.ts`,
|
||||
`src/commands/status.ts`.
|
||||
|
||||
## Pace Mode follow-ups (filed v0.42.49.0)
|
||||
|
||||
Deferred from the paced-backfill wave (CEO + eng review CLEARED). Core shipped:
|
||||
`db-pacer` + `pace-mode` wired into embed (CLI + shared core + `embed-backfill`
|
||||
job) and sync. See CLAUDE.md "Pace Mode".
|
||||
|
||||
- [ ] **P2 — `doctor` pacing check (E2).** Detect a txn-mode pooler (port 6543)
|
||||
running unpaced bulk and recommend `--pace`; optionally correlate recent
|
||||
`minion_jobs` deaths with backfill windows. Where: `src/commands/doctor.ts`.
|
||||
- [ ] **P2 — `--pace=auto` autotuned thresholds (E3).** Derive `paceAtMs`/cap from
|
||||
observed baseline latency (rolling median) instead of fixed bundle values,
|
||||
mirroring `gbrain search tune`. Needs a baseline window + cold-start default +
|
||||
config persistence — not a small add. Where: `src/core/pace-mode.ts` +
|
||||
`src/core/db-pacer.ts`.
|
||||
- [ ] **P3 — First-class pacing in more minion job handlers (E5).** `embed-backfill`
|
||||
is paced; extend to `extract`/`embed-catch-up`/contextual-reindex handlers with
|
||||
supervisor-detection downgrade. Today these inherit config/env pacing only when
|
||||
they call `runEmbedCore`.
|
||||
- [ ] **P1-companion — Supervisor concurrency 3→2 + job-kind slot fairness (E7).**
|
||||
The daemon-side root cause the external wrapper's probe was blind to:
|
||||
`embed-backfill`/`autopilot-cycle` jobs can occupy all supervisor slots
|
||||
(`:215` below). Pacing makes backfills safe; this fixes the residual death rate.
|
||||
Where: `src/core/minions/supervisor.ts` + queue slot accounting.
|
||||
- [ ] **P3 — `gbrain sync --pace` CLI flag.** Sync reads env/config pacing today;
|
||||
add a per-run `--pace[=mode]` flag for symmetry with `embed`. Where:
|
||||
`src/commands/sync.ts` arg parsing.
|
||||
- [ ] **P3 — Real-PG e2e for pacing.** Gated on `DATABASE_URL`: paced
|
||||
`embed --stale --pace --progress-json` caps concurrency + emits telemetry;
|
||||
single-flight rejects a 2nd concurrent run; lock heartbeat advances during a
|
||||
paced sleep (short-TTL). Unit coverage (`db-pacer`/`pace-mode`) already ships.
|
||||
## brain-repo durability follow-ups (filed v0.42.48.0)
|
||||
|
||||
- [ ] **P3 — gbrain write-path calls commit-push synchronously when durability is on.**
|
||||
v0.42.48.0 ships the synchronous `brain-commit-push.sh` as the guarantee and a local
|
||||
post-commit hook as a best-effort fallback. The strongest durability (codex outside-voice
|
||||
D13-C) is to have gbrain's own write-through path call the commit-push helper synchronously
|
||||
when a source is hardened — that also covers writes that never get committed by an agent.
|
||||
Deferred because it touches the write path; the hook + mandated helper cover the
|
||||
agent-driven case today.
|
||||
- **Where to start:** `src/core/write-through.ts:writePageThrough` + a per-source "hardened"
|
||||
flag to gate the synchronous push.
|
||||
|
||||
- [ ] **P3 — Unify the durability pull cron with autopilot's OS-scheduler.**
|
||||
v0.42.48.0 ships a minimal launchd/crontab installer inside `brain-repo-durability.ts`
|
||||
(D12: minimal-now to keep the diff off the load-bearing autopilot feature). Extract a shared
|
||||
`os-scheduler.ts` (`installPeriodic`/`removePeriodic`) and have both autopilot and brain-pull
|
||||
call it, so there's one OS-cron path.
|
||||
- **Where to start:** `src/commands/autopilot.ts` (`installLaunchd`/`installSystemd`/
|
||||
`installCrontab`/`writeWrapperScript`) + `brain-repo-durability.ts:installDurabilityCron`.
|
||||
|
||||
## gbrain#2200 federated-read follow-ups (filed v0.42.46.0)
|
||||
|
||||
- [ ] **P1 — Close the federated-read scope on the remaining same-class by-slug read ops.**
|
||||
v0.42.46.0 (#2200) routed `get_page` tags + `get_tags` / `get_links` / `get_backlinks` /
|
||||
`get_timeline` through the federated source scope and taught the engine methods to honor
|
||||
`sourceIds[]`. The adversarial review (Codex + Claude) flagged sibling read ops in the
|
||||
SAME class that still use scalar-only `ctx.sourceId ? {sourceId} : {}` and never thread
|
||||
`ctx.auth.allowedSources`: `get_chunks`, `get_raw_data`, `get_versions`, `resolve_slugs`
|
||||
(the standalone op — `resolve_slugs` passes NO scope at all), plus (per the v0.42.55.0
|
||||
eng-review codex pass) `takes_search` (`operations.ts:1727` — holder-allowlist only, no
|
||||
`sourceScopeOpts`) and `code_def` (`operations.ts:4155` — brain-wide raw SQL over
|
||||
`content_chunks`; confirm whether brain-wide is intentional before scoping). A remote
|
||||
federated client (grant set, dispatch-default `ctx.sourceId='default'`) reads these against
|
||||
`default` or unscoped, not its grant.
|
||||
- **Why:** same cross-source correctness/isolation class #2200 targets; a federated client
|
||||
can't read chunks/raw-data/versions for an authorized non-default source, `resolve_slugs`
|
||||
can fuzzy-resolve across all sources, and `takes_search`/`code_def` query without the grant.
|
||||
The #2399 close-list deliberately did NOT blanket-close #1371/#2200 because of these residual
|
||||
surfaces — close those issues only after this TODO lands.
|
||||
- **How to start:** mirror the #2200 pattern — route each handler through `sourceScopeOpts(ctx)`
|
||||
(or `linkReadScopeOpts` if a far endpoint exists), add `sourceIds?: string[]` to the engine
|
||||
methods (`getChunks` / `getRawData` / `getVersions` / `resolveSlugs` / the takes-search +
|
||||
code-def queries) with `source_id = ANY($::text[])` precedence, and add federated/isolation
|
||||
tests + engine-parity arms.
|
||||
- **Depends on:** nothing; #2200 established the pattern and the `linkReadScopeOpts` helper.
|
||||
|
||||
## Spend-controls wave follow-ups (filed v0.42.45.0, #2139)
|
||||
|
||||
Deferred from the #2139 delta-estimator wave. See plan + GSTACK REVIEW REPORT at
|
||||
`~/.claude/plans/system-instruction-you-are-working-lovely-balloon.md`.
|
||||
|
||||
- [ ] **P3 — Measured post-import chunk-count gating (#2139 proposal 2b).**
|
||||
**What:** Gate the inline cost decision on the actual chunk count sync produced
|
||||
(known after import, before embedding) instead of the pre-sync token estimate.
|
||||
**Why:** A fully execution-accurate gate with zero estimate error. **Context:**
|
||||
After v0.42.42.0 the estimator already mirrors execution (fetch-first delta via the
|
||||
shared `computeSyncDelta`, `--full`=delta+stale, dirty-tree→$0). This is the
|
||||
belt-and-suspenders fallback if a future case still drifts. **Trigger:** only if the
|
||||
delta estimator proves insufficient in practice. **Start:** the gate call site in
|
||||
`src/commands/sync.ts` (`runInlineCostGate`), gate on post-import `chunksCreated`.
|
||||
- [ ] **P3 — Per-source defer granularity (#2139, D8A road-not-taken).**
|
||||
**What:** When the aggregate inline gate trips in a non-TTY session, defer embeds
|
||||
only for sources above a per-source floor; let cheap sources keep embedding inline.
|
||||
**Why:** Cheap sources would get embeddings minutes sooner instead of waiting for a
|
||||
backfill-worker drain. **Context:** v0.42.42.0 chose GLOBAL defer (one flag, strictly
|
||||
dominates the exit-2 it replaced). This is the granularity upgrade. **Trigger:** a
|
||||
filed embedding-latency-by-minutes complaint. **Start:** thread per-source estimates
|
||||
through `runOne` (`src/commands/sync.ts`); design worked out at D8A in the plan.
|
||||
|
||||
## gbrain#2095 push-based context follow-ups (v0.43+)
|
||||
|
||||
Filed from the #2095 wave (volunteer_context op + reflex window + `gbrain watch`).
|
||||
Deliberately scoped OUT of v1 per the eng-review scope decision (success criteria
|
||||
are the bar). Plan + GSTACK REVIEW REPORT at
|
||||
`~/.claude/plans/system-instruction-you-are-working-cheerful-elephant.md`.
|
||||
|
||||
- [ ] **P3 — SSE/HTTP push channel via serve-http.** The op + `gbrain watch` cover
|
||||
pull-per-turn and stdin streaming; a serve-http SSE feed would push volunteered
|
||||
pages to remote agents without a local CLI. **Why:** thin-client/remote-MCP
|
||||
deployments get push too. **Cons:** async plumbing + auth scoping; no consumer
|
||||
wired today. **Where:** `src/commands/serve-http.ts` + `src/core/context/volunteer.ts`.
|
||||
**Blocked by:** a real consumer (revisit when one exists).
|
||||
- [ ] **P3 — policy skill + doctor check for push-context.** The ambient reflex
|
||||
needed doctor visibility because silent failure was invisible; volunteer is
|
||||
invoked-on-demand so v1 skipped it. If `volunteer-context --stats` adoption shows
|
||||
agents not discovering the surface, ship a `push-context` recipe (mirror
|
||||
`recipes/retrieval-reflex/`) + a doctor check reading the events table.
|
||||
**Where:** `recipes/`, `src/commands/doctor.ts`.
|
||||
- [ ] **P3 — structured `messages[]` param for volunteer_context.** v1 takes a
|
||||
string window (`user:`/`assistant:` prefixes) to avoid a dual-shape contract.
|
||||
If MCP callers accumulate parsing bugs, add a structured array param beside it.
|
||||
**Where:** `src/core/operations.ts:volunteer_context` + `src/core/context/volunteer.ts:parseWindow`.
|
||||
- [ ] **P3 — index shapes for the per-turn resolver query.** The arm-2 resolver
|
||||
(`retrieval-reflex.ts`: `lower(title) = ANY() OR slug = ANY() OR slug LIKE
|
||||
ANY('%/...')`) predates #2095 but now runs per turn on three channels
|
||||
(reflex window, volunteer_context, watch) federated across sources. Neither
|
||||
the leading-wildcard suffix arm nor `lower(title)` is index-served. If
|
||||
per-turn latency telemetry on large brains comes back hot: add
|
||||
`(source_id, lower(title))` btree + a reverse(slug) text_pattern_ops (or
|
||||
gin_trgm) index, or split the OR into three index-friendly queries.
|
||||
**Where:** `src/core/context/retrieval-reflex.ts`, migration.
|
||||
- [ ] **P3 — batch the volunteer-events pruner's first run after a long gap.**
|
||||
`purgeStaleVolunteerEvents` is one unbatched DELETE with a bare
|
||||
`volunteered_at` predicate (full scan; fine for a TTL-bounded table). Edge:
|
||||
a brain whose dream cycle was off for months could hit the pooler's ~2min
|
||||
statement_timeout on the first prune, get swallowed by the catch, and never
|
||||
make progress. If observed: id-batched chunks (`DELETE ... WHERE id IN
|
||||
(SELECT ... LIMIT 10000)` looped). **Where:**
|
||||
`src/core/context/volunteer-events.ts:purgeStaleVolunteerEvents`.
|
||||
- [ ] **P3 — route `gbrain watch` through the serve resolve-IPC on PGLite.**
|
||||
`watch` connects directly, so on a PGLite brain it monopolizes the single
|
||||
connection for its whole (potentially hours-long) session — a concurrent
|
||||
`gbrain serve` or any write path blocks on the lock until watch exits.
|
||||
WATCH_HELP documents the monopoly; the fix is an IPC rung in watch's
|
||||
resolver (reuse `resolveViaIpc` like the ambient reflex's ladder) so a
|
||||
running serve answers and watch never takes the lock. **Why:** watch +
|
||||
serve concurrently is the natural agent topology. **Where:**
|
||||
`src/commands/watch.ts`, `src/core/context/resolve-ipc.ts` (red-team RT2).
|
||||
- [ ] **P3 — capability/version gate for host-injected reflex resolvers.**
|
||||
Windowing switched the orchestrator's suppression request to 'slug-only';
|
||||
a host resolver built against the pre-window contract that still applies
|
||||
title-whole-word suppression silently self-suppresses every windowed
|
||||
entity. The contract is documented at `ResolveEntitiesFn` (reflex.ts), but
|
||||
nothing detects a stale host. Add a capability handshake (e.g. resolver
|
||||
advertises `supportsSuppressionModes`) and fall back to
|
||||
`window_turns: 1` semantics when absent. **Where:**
|
||||
`src/core/context/reflex.ts:ResolveEntitiesFn` + the OpenClaw plugin
|
||||
contract (red-team RT4).
|
||||
|
||||
## gbrain triage wave follow-ups (filed v0.42.41.0)
|
||||
|
||||
Deferred from the v0.42.41.0 fix wave (eng-reviewed as separate scope, not hotfixes).
|
||||
See plan + GSTACK REVIEW REPORT at
|
||||
`~/.claude/plans/system-instruction-you-are-working-zany-thacker.md`.
|
||||
|
||||
- [ ] **P1 — supervisor: retry-with-backoff instead of hard stop on transient DB outages (#1994).**
|
||||
`max_crashes_exceeded` gives up permanently; a transient pooler blip that trips the
|
||||
counter wedges the supervisor until manual restart. **Why:** the #2034 reconnect fix
|
||||
makes the engine recover, but the supervisor still hard-stops. **Where:**
|
||||
`src/core/minions/supervisor.ts` crash-count loop — add exponential backoff with a
|
||||
much higher (or no) permanent-give-up threshold for recoverable errors.
|
||||
- [ ] **P2 — PGLite `reindex-frontmatter` / backfill statement_timeout boost (#1963).**
|
||||
Community RCA: `SET LOCAL statement_timeout` is gated on `engine.kind === 'postgres'`,
|
||||
so PGLite inherits the 30s session default and trips on non-trivial batches; the CLI
|
||||
then swallows the error and exits 0. **Where:** `src/core/backfill-effective-date.ts`
|
||||
(boost on PGLite too, or per-row updates) + the cli.ts catch that hides it.
|
||||
- [ ] **P2 — autopilot drain-worker concurrency self-deadlock (#2050).** Drain-worker
|
||||
runs at concurrency=1, so any cycle phase that spawns a subagent (patterns, synthesize)
|
||||
deadlocks waiting on a worker slot it can't get. **Where:** autopilot drain-worker
|
||||
dispatch — raise concurrency or exempt subagent-spawning phases.
|
||||
- [ ] **P3 — name-keyed migration ledger (#2038 structural follow-up).** The always-run
|
||||
index drift probe heals the one known case; the general fix is keying applied-migration
|
||||
tracking by stable name rather than version integer so a renumber can't strand a
|
||||
migration as recorded-but-not-executed. **Where:** `src/core/migrate.ts` ledger.
|
||||
|
||||
## gbrain#1981 Retrieval Reflex follow-ups (v0.43+)
|
||||
|
||||
Filed from the #1981 ship (v0.42.39.0). Deliberately scoped OUT — the v1 extractor
|
||||
is deterministic + precision-biased. See plan + GSTACK REVIEW REPORT at
|
||||
`~/.claude/plans/system-instruction-you-are-working-wild-yeti.md`.
|
||||
|
||||
- [ ] **P3 — broaden entity detection beyond proper-case ASCII.** The extractor
|
||||
(`src/core/context/entity-salience.ts`) misses lowercase names and many non-Latin
|
||||
scripts; these need an LLM pass or script-aware heuristics. **Why:** higher recall
|
||||
on the read side. **Where:** `entity-salience.ts`. *(Partially done by the #2095
|
||||
wave: `extractCandidatesFromWindow` now covers assistant-introduced entities and
|
||||
pronoun follow-ups whose antecedent was NAMED in the rolling window; true pronoun
|
||||
coreference for never-named antecedents remains with the LLM-pass idea.)*
|
||||
- [ ] **P3 — recall knob: optional fuzzy/prefix-expansion resolution.** The resolver
|
||||
(`src/core/context/retrieval-reflex.ts`) is exact-only (alias + title + slug-suffix)
|
||||
for precision. Revisit adding `resolveEntitySlug`'s trgm-fuzzy / prefix-expansion
|
||||
arm, gated on an unambiguous single hit, if recall telemetry comes back weak.
|
||||
|
||||
## gbrain#1972 job-layer follow-up (v0.43+)
|
||||
|
||||
Filed from the #1972 fix (stale-lock reaper + bounded disconnect + complete
|
||||
cooperative-abort). One item was deliberately gated, not deferred blindly. See plan +
|
||||
GSTACK REVIEW REPORT at `~/.claude/plans/system-instruction-you-are-working-curious-pike.md`.
|
||||
|
||||
- [ ] **P2 — `findBacklinkGaps` sync→async refactor (gated on telemetry).** The backlinks
|
||||
phase does its heavy work in a single synchronous call (`findBacklinkGaps`,
|
||||
`src/commands/backlinks.ts:71` — nested `readdirSync` double-walk, no `await` seam), so it
|
||||
cannot be cooperatively aborted: a >30s run on a huge brain blocks the event loop and gets
|
||||
force-evicted. lint was made yield-able this wave (it was already async); backlinks needs
|
||||
`findBacklinkGaps` converted to async-with-periodic-yields, threaded through
|
||||
`runBacklinksCore` + `runPhaseBacklinks`. **Why gated:** the trigger is UNCONFIRMED — we
|
||||
don't know backlinks ever exceeds 30s. This wave added the phase-duration force-evict
|
||||
attribution log (`FORCE_EVICT_DEADLINE_MS` in `src/core/cycle.ts`), which names any phase
|
||||
that crosses the deadline. Do this refactor only if a production 24h pull shows backlinks
|
||||
crossing it; otherwise it's a hot-loop rewrite for a non-occurring case. **Where:**
|
||||
`src/commands/backlinks.ts`, `src/core/cycle.ts` (runPhaseBacklinks signal threading).
|
||||
|
||||
## gbrain#1881 sync reclone ownership follow-ups (v0.43+)
|
||||
|
||||
Filed from the #1881 fix (`gbrain sync --strategy code` deleted a user's working
|
||||
@@ -481,9 +89,8 @@ context). Deliberately scoped OUT of that PR. See plan + GSTACK REVIEW REPORT at
|
||||
batch error, retry the batch element-by-element so one bad row can't abort a
|
||||
353K-page `extract --stale` sweep, logging the offending `(from_slug, context)`
|
||||
instead of dying. The durable JSONB fix removed the known crash class (malformed
|
||||
array literal), NUL-stripping removed a second jsonb-parse failure, and
|
||||
v0.42.40.0 lone-surrogate well-forming (#2011) removed a third, so there is no
|
||||
remaining *known* data-dependent crash for this to catch *today* — it's
|
||||
array literal) and NUL-stripping removed the other known jsonb-parse failure, so
|
||||
there is no remaining data-dependent crash for this to catch *today* — it's
|
||||
belt-and-suspenders against unknown future per-row failures. Wire it in
|
||||
`addLinksBatch`/`addTimelineEntriesBatch`/`addTakesBatch` (or in `batchRetry` as
|
||||
a post-classification fallback). Issue #1861 option 2.
|
||||
@@ -570,41 +177,17 @@ GSTACK REVIEW REPORT at
|
||||
can't desync per-engine, bounded against CLI-hang by a top-level forced
|
||||
cleanup. Do this BEFORE introducing any concurrent module-engine connect path.
|
||||
|
||||
- [x] **P3 — `dream` + CLI_ONLY fall-through paths don't drain the facts /
|
||||
last-retrieved queues before the owner disconnect.** DONE in the #2084 fix:
|
||||
`finishCliTeardown` (`src/core/cli-force-exit.ts`) is exactly the shared
|
||||
drain-before-disconnect helper this item asked for, and ALL NINE cli.ts
|
||||
disconnect sites route through it (op-dispatch, fall-through, dream, doctor
|
||||
×3, ze-switch, search dashboard, read-only timeout path). Structural guard:
|
||||
no bare `await engine.disconnect()` remains in cli.ts
|
||||
(`test/fix-wave-structural.test.ts` `#2084` describe).
|
||||
|
||||
- [ ] **P2 — command-module `process.exit` sites bypass the #2084 teardown
|
||||
contract.** Several CLI_ONLY command modules exit directly on their normal
|
||||
paths (`doctor.ts` ~10 sites incl. its verdict exit, `dream.ts` ~23,
|
||||
`ze-switch.ts` ~9, plus friction/claw-test/eval verdict exits in cli.ts) —
|
||||
those exits preempt the call-site `finally`, so the background-work drain,
|
||||
bounded disconnect, and `flushThenExit` grace are all skipped on those paths
|
||||
(pre-existing class, NOT introduced by #2084; pre-fix the same exits skipped
|
||||
the inline drains too). Consequences: `gbrain doctor --json | <slow reader>`
|
||||
keeps the #1959 truncation exposure; a dream path that exits mid-cycle
|
||||
discards in-flight facts/search-cache writes. Fix shape: convert in-command
|
||||
`process.exit(n)` to `setCliExitVerdict(n)` + return (the central seam
|
||||
exits), or route them through a shared `exitCommand(n)` helper that runs
|
||||
teardown first. Surfaced by the #2084 cross-model adversarial review (F2).
|
||||
|
||||
- [ ] **P3 — opt-in whole-command wallclock cap (`GBRAIN_COMMAND_DEADLINE_MS`),
|
||||
build ONLY on a real wedged-handler incident.** The #2084 fix deliberately
|
||||
removed the blanket pre-handler 10s force-exit (it killed slow-legit ops with
|
||||
exit 0 and truncated output); per-op deadlines (query-embed deadline,
|
||||
`withTimeout` on read-only commands) own handler wallclock now, and
|
||||
`connectEngine` hangs — the historically observed zombie class — were never
|
||||
covered by the old timer anyway. If production ever shows a genuinely wedged
|
||||
handler (trigger: a non-`serve` command alive >30min with no progress
|
||||
output), add an opt-in env cap that exits NON-ZERO with a truthful banner.
|
||||
Attach point: the `GBRAIN_TEARDOWN_DEADLINE_MS` / `computeTeardownDeadlineMs`
|
||||
plumbing in `src/core/cli-force-exit.ts`. Do not build speculatively —
|
||||
follow-up from the #2084 eng review (decision D2/D14).
|
||||
- [ ] **P3 — `dream` + CLI_ONLY fall-through paths don't drain the facts /
|
||||
last-retrieved queues before the owner disconnect.** The op-dispatch path
|
||||
(`cli.ts:~282-314`) drains `getFactsQueue().drainPending()` +
|
||||
`awaitPendingLastRetrievedWrites()` before `engine.disconnect()`; the `dream`
|
||||
owner-disconnect (`cli.ts:~1164`) and the fall-through owner-disconnect
|
||||
(`cli.ts:~1785`) do not. If the dream cycle ever enqueues a facts:absorb /
|
||||
last-retrieved write that's still in flight at disconnect, the owner nulls the
|
||||
singleton and the write throws "No database connection". Pre-existing (not
|
||||
introduced by the #1471 ownership fix), surfaced by the Claude adversarial
|
||||
review (F5). Fix: hoist the same drain-before-disconnect block the op-dispatch
|
||||
path uses into a shared helper and call it on all three owner-disconnect sites.
|
||||
## v0.42.x AI SDK v6 tool-schema fix follow-ups (#1782/#1764)
|
||||
|
||||
Surfaced by the codex outside-voice pass during `/plan-eng-review` and
|
||||
@@ -922,19 +505,6 @@ PR1 shipped the read-only catalog; PR2 is the download-and-install surface,
|
||||
deferred per the plan's D1 + D8 because it stands up new HTTP/binary/token
|
||||
infra and reaches into third-party packs that live outside the host skills dir.
|
||||
|
||||
> **#2180 update (v0.43+ brain-resident skillpacks + advisor):** brain-resident
|
||||
> pack DISCOVERY over MCP shipped as a dedicated, source-scoped
|
||||
> `list_brain_skillpack` op (NOT folded into `list_skills` — the host catalog is
|
||||
> host-global and ignores `ctx.sourceId`, so per-source packs needed their own
|
||||
> tenancy-correct surface). `get_skill` gained an optional `source_id` for
|
||||
> per-source fetch disambiguation. The `tools:` version-skew lint below is now
|
||||
> implemented (`src/core/skillpack/brain-pack-lint.ts`, run by
|
||||
> `gbrain skillpack init-brain-pack`). STILL DEFERRED to this PR2: thin-client
|
||||
> BINARY install (`build_skillpack` download) — a thin client today gets the
|
||||
> pack's git scaffold spec and `resolveSource`s it on its own machine. The
|
||||
> `include_skillpacks` host-global merge below is intentionally still open
|
||||
> (separate concern from per-source brain packs).
|
||||
|
||||
- [ ] **v0.41.37+: `build_skillpack` op + `GET /skillpack/download/:token` endpoint.** Build a deterministic `.tgz` on demand (named skillpack, ad-hoc skill subset, or whole repo) and deliver it both base64-inline (universal/stdio) and via an authenticated short-lived download URL when running under `gbrain serve --http`. **What:** new admin-or-write-scoped op + a token-store + cache-dir GC; reuse `packTarball` from `src/core/skillpack/tarball.ts` (already deterministic + symlink-rejecting + size-capped) and the magic-link nonce pattern in `serve-http.ts`. The tarball ships source CODE, so it needs its own trust decision separate from PR1's prose-only catalog. **Why:** lets a thin client install a skillpack into its own setup, not just follow one live. **Depends on:** PR1 (landed in v0.41.36.0). Priority: P2.
|
||||
- [ ] **v0.41.37+: `include_skillpacks` merge in `list_skills`.** Fold pinned third-party packs (from `~/.gbrain/skillpack-state.json`) into the catalog. Deferred from PR1 (D8) because packs live OUTSIDE the host skills dir and need (a) a per-pack trusted-root realpath confinement and (b) `{name, skillpack_name?}` disambiguation when a pack skill and a host skill share a name. Lands naturally with PR2's pack machinery. Priority: P2.
|
||||
- [ ] **v0.41.37+: TTL+mtime cache for the skill-catalog walk.** PR1 reads fresh every call (cold path, ~ms). If telemetry shows repeated `list_skills` calls, add a TTL+mtime-keyed cache shared by `list_skills` + `get_skill`. Priority: P3 (do-nothing was the deliberate PR1 call).
|
||||
@@ -2194,6 +1764,11 @@ Three items deferred:
|
||||
self-heals via stale-reclaim). The common sync SUCCESS path already drains via
|
||||
handleCliOnly's finally. Convert for graceful drain on sync error exits.
|
||||
|
||||
- [ ] **(v0.42.20.0 follow-up) Decouple the op-dispatch force-exit timer** so it
|
||||
wraps `engine.disconnect()` only (it's armed before the handler today, doubling
|
||||
as a blanket handler watchdog) and fix its misleading "engine.disconnect() did
|
||||
not return…" message that fires even when the handler (not disconnect) was slow.
|
||||
|
||||
- [ ] **(v0.42.20.0 follow-up) Gateway idle-timeout (vs absolute) for streaming
|
||||
chat.** `withDefaultTimeout` uses an absolute `AbortSignal.timeout`; a streaming
|
||||
generation actively producing tokens past the chat default (300s) would abort.
|
||||
@@ -3963,18 +3538,6 @@ keeping both skills' triggers intact for chaining.
|
||||
|
||||
## Completed
|
||||
|
||||
### ~~(v0.42.20.0 follow-up) Decouple the op-dispatch force-exit timer~~
|
||||
**Completed:** v0.42.39.0 (2026-06-10)
|
||||
|
||||
The timer now arms at teardown entry (inside the op-dispatch finally, before
|
||||
drain + disconnect) so it bounds ONLY disconnect — no longer doubling as a
|
||||
blanket handler watchdog that killed slow-but-healthy ops at 10s with exit 0
|
||||
and empty stdout. Its "engine.disconnect() did not return…" message is now
|
||||
accurate by construction (it can only fire during teardown). Read-scope
|
||||
handlers + context build got their own explicit wallclock bound (180s default,
|
||||
`--timeout=Ns`, exit 124, hard-exit after teardown) in the same wave. Pinned by
|
||||
`test/cli-force-exit-teardown-arming.test.ts`.
|
||||
|
||||
### ~~Checks 5 + 6 for check-resolvable~~
|
||||
**Completed:** v0.19.0 (2026-04-22)
|
||||
|
||||
|
||||
+20
-52
@@ -13,52 +13,48 @@
|
||||
"@types/react-dom": "^19.1.2",
|
||||
"@vitejs/plugin-react": "^4.4.1",
|
||||
"typescript": "^5.8.3",
|
||||
"vite": "^6.4.3",
|
||||
"vite": "^6.3.3",
|
||||
},
|
||||
},
|
||||
},
|
||||
"overrides": {
|
||||
"@babel/core": "^7.29.6",
|
||||
"postcss": "^8.5.10",
|
||||
},
|
||||
"packages": {
|
||||
"@babel/code-frame": ["@babel/code-frame@7.29.7", "", { "dependencies": { "@babel/helper-validator-identifier": "^7.29.7", "js-tokens": "^4.0.0", "picocolors": "^1.1.1" } }, "sha512-Aup7aUOfpbAUg2ROOJN6Iw5f9DMBlzu0mIkm/malLQFN/YQgO48wCj0Kxa3sEHJvPVFg7siR+qRInwXd2qhQKw=="],
|
||||
"@babel/code-frame": ["@babel/code-frame@7.29.0", "", { "dependencies": { "@babel/helper-validator-identifier": "^7.28.5", "js-tokens": "^4.0.0", "picocolors": "^1.1.1" } }, "sha512-9NhCeYjq9+3uxgdtp20LSiJXJvN0FeCtNGpJxuMFZ1Kv3cWUNb6DOhJwUvcVCzKGR66cw4njwM6hrJLqgOwbcw=="],
|
||||
|
||||
"@babel/compat-data": ["@babel/compat-data@7.29.7", "", {}, "sha512-locTkQyKvwIEgBzVrn8693ebc97F2U8ZHjbXwDXJ5Fn2TCpNwTlKcaKLkdHop5c/icOFE7qt7Q9JC5hnKNa6Gg=="],
|
||||
"@babel/compat-data": ["@babel/compat-data@7.29.0", "", {}, "sha512-T1NCJqT/j9+cn8fvkt7jtwbLBfLC/1y1c7NtCeXFRgzGTsafi68MRv8yzkYSapBnFA6L3U2VSc02ciDzoAJhJg=="],
|
||||
|
||||
"@babel/core": ["@babel/core@7.29.7", "", { "dependencies": { "@babel/code-frame": "^7.29.7", "@babel/generator": "^7.29.7", "@babel/helper-compilation-targets": "^7.29.7", "@babel/helper-module-transforms": "^7.29.7", "@babel/helpers": "^7.29.7", "@babel/parser": "^7.29.7", "@babel/template": "^7.29.7", "@babel/traverse": "^7.29.7", "@babel/types": "^7.29.7", "@jridgewell/remapping": "^2.3.5", "convert-source-map": "^2.0.0", "debug": "^4.1.0", "gensync": "^1.0.0-beta.2", "json5": "^2.2.3", "semver": "^6.3.1" } }, "sha512-RgHBCvtjbOK2gXSNBNIkNoEc9qoVEtau3hj8gEqKQuL3HZAibKarWFEI3Lfm6EYKkLalOh8eSrj9b+ch9H/VBA=="],
|
||||
"@babel/core": ["@babel/core@7.29.0", "", { "dependencies": { "@babel/code-frame": "^7.29.0", "@babel/generator": "^7.29.0", "@babel/helper-compilation-targets": "^7.28.6", "@babel/helper-module-transforms": "^7.28.6", "@babel/helpers": "^7.28.6", "@babel/parser": "^7.29.0", "@babel/template": "^7.28.6", "@babel/traverse": "^7.29.0", "@babel/types": "^7.29.0", "@jridgewell/remapping": "^2.3.5", "convert-source-map": "^2.0.0", "debug": "^4.1.0", "gensync": "^1.0.0-beta.2", "json5": "^2.2.3", "semver": "^6.3.1" } }, "sha512-CGOfOJqWjg2qW/Mb6zNsDm+u5vFQ8DxXfbM09z69p5Z6+mE1ikP2jUXw+j42Pf1XTYED2Rni5f95npYeuwMDQA=="],
|
||||
|
||||
"@babel/generator": ["@babel/generator@7.29.7", "", { "dependencies": { "@babel/parser": "^7.29.7", "@babel/types": "^7.29.7", "@jridgewell/gen-mapping": "^0.3.12", "@jridgewell/trace-mapping": "^0.3.28", "jsesc": "^3.0.2" } }, "sha512-DkXD5OJQaAQIdZ1bt3UZdEnHAn9Imd3IVBdX03UFe+ony9Ojw5pzr9YVKGDY1jt+Gcn/FnGkNf8r+Vj5NOJWtQ=="],
|
||||
"@babel/generator": ["@babel/generator@7.29.1", "", { "dependencies": { "@babel/parser": "^7.29.0", "@babel/types": "^7.29.0", "@jridgewell/gen-mapping": "^0.3.12", "@jridgewell/trace-mapping": "^0.3.28", "jsesc": "^3.0.2" } }, "sha512-qsaF+9Qcm2Qv8SRIMMscAvG4O3lJ0F1GuMo5HR/Bp02LopNgnZBC/EkbevHFeGs4ls/oPz9v+Bsmzbkbe+0dUw=="],
|
||||
|
||||
"@babel/helper-compilation-targets": ["@babel/helper-compilation-targets@7.29.7", "", { "dependencies": { "@babel/compat-data": "^7.29.7", "@babel/helper-validator-option": "^7.29.7", "browserslist": "^4.24.0", "lru-cache": "^5.1.1", "semver": "^6.3.1" } }, "sha512-wem6WaBj4NaVYVdNhLPPVacES6ZJ+KBBfSkTMD3YZxbP3rm3Di85tJU5ljaUNhaOynt+Aj0xruhYuzQBt8n71g=="],
|
||||
"@babel/helper-compilation-targets": ["@babel/helper-compilation-targets@7.28.6", "", { "dependencies": { "@babel/compat-data": "^7.28.6", "@babel/helper-validator-option": "^7.27.1", "browserslist": "^4.24.0", "lru-cache": "^5.1.1", "semver": "^6.3.1" } }, "sha512-JYtls3hqi15fcx5GaSNL7SCTJ2MNmjrkHXg4FSpOA/grxK8KwyZ5bubHsCq8FXCkua6xhuaaBit+3b7+VZRfcA=="],
|
||||
|
||||
"@babel/helper-globals": ["@babel/helper-globals@7.29.7", "", {}, "sha512-3nQVUAtvkKH9zahfWgw96Jc/uFOmjACE1kQz82E2lqWmHBgjzbNlsC22nuQTfahmWeQtTq5nQ/4Nnd2A1wj4zA=="],
|
||||
"@babel/helper-globals": ["@babel/helper-globals@7.28.0", "", {}, "sha512-+W6cISkXFa1jXsDEdYA8HeevQT/FULhxzR99pxphltZcVaugps53THCeiWA8SguxxpSp3gKPiuYfSWopkLQ4hw=="],
|
||||
|
||||
"@babel/helper-module-imports": ["@babel/helper-module-imports@7.29.7", "", { "dependencies": { "@babel/traverse": "^7.29.7", "@babel/types": "^7.29.7" } }, "sha512-ejHwrQQYcm9xnTivShn2IDOlIzInN34AXskvq9QicvCtEzq1Vzclu/tKF8Jq1Cg8JG2GL6/EmjgsCT7lXepE3g=="],
|
||||
"@babel/helper-module-imports": ["@babel/helper-module-imports@7.28.6", "", { "dependencies": { "@babel/traverse": "^7.28.6", "@babel/types": "^7.28.6" } }, "sha512-l5XkZK7r7wa9LucGw9LwZyyCUscb4x37JWTPz7swwFE/0FMQAGpiWUZn8u9DzkSBWEcK25jmvubfpw2dnAMdbw=="],
|
||||
|
||||
"@babel/helper-module-transforms": ["@babel/helper-module-transforms@7.29.7", "", { "dependencies": { "@babel/helper-module-imports": "^7.29.7", "@babel/helper-validator-identifier": "^7.29.7", "@babel/traverse": "^7.29.7" }, "peerDependencies": { "@babel/core": "^7.0.0" } }, "sha512-UPUVSyXbOh627KiCIGQSgwWzGeBKLkaJ9PJEdrngIwMSzxLR4jS4+f1f1jb7VzBbg8nFLaYotvVPFCTqdrmTAg=="],
|
||||
"@babel/helper-module-transforms": ["@babel/helper-module-transforms@7.28.6", "", { "dependencies": { "@babel/helper-module-imports": "^7.28.6", "@babel/helper-validator-identifier": "^7.28.5", "@babel/traverse": "^7.28.6" }, "peerDependencies": { "@babel/core": "^7.0.0" } }, "sha512-67oXFAYr2cDLDVGLXTEABjdBJZ6drElUSI7WKp70NrpyISso3plG9SAGEF6y7zbha/wOzUByWWTJvEDVNIUGcA=="],
|
||||
|
||||
"@babel/helper-plugin-utils": ["@babel/helper-plugin-utils@7.28.6", "", {}, "sha512-S9gzZ/bz83GRysI7gAD4wPT/AI3uCnY+9xn+Mx/KPs2JwHJIz1W8PZkg2cqyt3RNOBM8ejcXhV6y8Og7ly/Dug=="],
|
||||
|
||||
"@babel/helper-string-parser": ["@babel/helper-string-parser@7.29.7", "", {}, "sha512-Pb5ijPrZ89GDH8223L4UP8i6QApWxs04RbPQJTeWDV0/keR2E36MeKnyr6LYmUUvqRRI+Iv87SuF1W6ErINzYw=="],
|
||||
"@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
|
||||
|
||||
"@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.29.7", "", {}, "sha512-qehxGkRj55h/ff8EMaJ+cYhyaKlHIxqYDn682wQD7RNp9UujOQsHog2uS0r2vzr4pW+sXf90NeeayjcNaX3fFg=="],
|
||||
"@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
|
||||
|
||||
"@babel/helper-validator-option": ["@babel/helper-validator-option@7.29.7", "", {}, "sha512-N9ZErrD+yW5geCDtBqnOoxmR8+tNKiGuxKlDpuJxfsqpa2dFcexaziGAE/qoHLiDDreVNMupxGmSoNlyvsA3gw=="],
|
||||
"@babel/helper-validator-option": ["@babel/helper-validator-option@7.27.1", "", {}, "sha512-YvjJow9FxbhFFKDSuFnVCe2WxXk1zWc22fFePVNEaWJEu8IrZVlda6N0uHwzZrUM1il7NC9Mlp4MaJYbYd9JSg=="],
|
||||
|
||||
"@babel/helpers": ["@babel/helpers@7.29.7", "", { "dependencies": { "@babel/template": "^7.29.7", "@babel/types": "^7.29.7" } }, "sha512-1k2lAGRMfHTcwuNYcCNUmaUffmQv8KWMfh2iJUUeRlwlwH4FdNG7mfPI10NPfLHJFThE4Tyr4mv7kTNZOiPuBg=="],
|
||||
"@babel/helpers": ["@babel/helpers@7.29.2", "", { "dependencies": { "@babel/template": "^7.28.6", "@babel/types": "^7.29.0" } }, "sha512-HoGuUs4sCZNezVEKdVcwqmZN8GoHirLUcLaYVNBK2J0DadGtdcqgr3BCbvH8+XUo4NGjNl3VOtSjEKNzqfFgKw=="],
|
||||
|
||||
"@babel/parser": ["@babel/parser@7.29.7", "", { "dependencies": { "@babel/types": "^7.29.7" }, "bin": "./bin/babel-parser.js" }, "sha512-hnORnjP/1P/zFEndoeX+n+t1RwWRJiJpM/jO7FW32Kn9r5+sJB2JWOdYo4L6k78j15eCwY3Gm/7364B1EMwtNg=="],
|
||||
"@babel/parser": ["@babel/parser@7.29.2", "", { "dependencies": { "@babel/types": "^7.29.0" }, "bin": "./bin/babel-parser.js" }, "sha512-4GgRzy/+fsBa72/RZVJmGKPmZu9Byn8o4MoLpmNe1m8ZfYnz5emHLQz3U4gLud6Zwl0RZIcgiLD7Uq7ySFuDLA=="],
|
||||
|
||||
"@babel/plugin-transform-react-jsx-self": ["@babel/plugin-transform-react-jsx-self@7.27.1", "", { "dependencies": { "@babel/helper-plugin-utils": "^7.27.1" }, "peerDependencies": { "@babel/core": "^7.0.0-0" } }, "sha512-6UzkCs+ejGdZ5mFFC/OCUrv028ab2fp1znZmCZjAOBKiBK2jXD1O+BPSfX8X2qjJ75fZBMSnQn3Rq2mrBJK2mw=="],
|
||||
|
||||
"@babel/plugin-transform-react-jsx-source": ["@babel/plugin-transform-react-jsx-source@7.27.1", "", { "dependencies": { "@babel/helper-plugin-utils": "^7.27.1" }, "peerDependencies": { "@babel/core": "^7.0.0-0" } }, "sha512-zbwoTsBruTeKB9hSq73ha66iFeJHuaFkUbwvqElnygoNbj/jHRsSeokowZFN3CZ64IvEqcmmkVe89OPXc7ldAw=="],
|
||||
|
||||
"@babel/template": ["@babel/template@7.29.7", "", { "dependencies": { "@babel/code-frame": "^7.29.7", "@babel/parser": "^7.29.7", "@babel/types": "^7.29.7" } }, "sha512-puq+Gf35oI24FeN11LkoUQFqv9uwNeWpxXZi/Ji3rRIoKAzKnxRaZ+Gkj0vKS9ZCiTESfng1N9LyOyXvo+m+Gg=="],
|
||||
"@babel/template": ["@babel/template@7.28.6", "", { "dependencies": { "@babel/code-frame": "^7.28.6", "@babel/parser": "^7.28.6", "@babel/types": "^7.28.6" } }, "sha512-YA6Ma2KsCdGb+WC6UpBVFJGXL58MDA6oyONbjyF/+5sBgxY/dwkhLogbMT2GXXyU84/IhRw/2D1Os1B/giz+BQ=="],
|
||||
|
||||
"@babel/traverse": ["@babel/traverse@7.29.7", "", { "dependencies": { "@babel/code-frame": "^7.29.7", "@babel/generator": "^7.29.7", "@babel/helper-globals": "^7.29.7", "@babel/parser": "^7.29.7", "@babel/template": "^7.29.7", "@babel/types": "^7.29.7", "debug": "^4.3.1" } }, "sha512-EhlfNQtZ+NK22w5BM61ciuiq1m58ed33Wr1Xan//ZRTy6hgjnwyCffRYwzsGXdASJSUJ1guZILsErh1eQcl+zw=="],
|
||||
"@babel/traverse": ["@babel/traverse@7.29.0", "", { "dependencies": { "@babel/code-frame": "^7.29.0", "@babel/generator": "^7.29.0", "@babel/helper-globals": "^7.28.0", "@babel/parser": "^7.29.0", "@babel/template": "^7.28.6", "@babel/types": "^7.29.0", "debug": "^4.3.1" } }, "sha512-4HPiQr0X7+waHfyXPZpWPfWL/J7dcN1mx9gL6WdQVMbPnF3+ZhSMs8tCxN7oHddJE9fhNE7+lxdnlyemKfJRuA=="],
|
||||
|
||||
"@babel/types": ["@babel/types@7.29.7", "", { "dependencies": { "@babel/helper-string-parser": "^7.29.7", "@babel/helper-validator-identifier": "^7.29.7" } }, "sha512-4zBIxpPzowiZpusoFkyGVwakdRJUyuH5PxQ/PrqghfdFWWasvnCdPfQXHrenDai+gyLARulZjZowCOj6fjT4pA=="],
|
||||
"@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
|
||||
|
||||
"@esbuild/aix-ppc64": ["@esbuild/aix-ppc64@0.25.12", "", { "os": "aix", "cpu": "ppc64" }, "sha512-Hhmwd6CInZ3dwpuGTF8fJG6yoWmsToE+vYgD4nytZVxcu1ulHpUQRAB1UJ8+N1Am3Mz4+xOByoQoSZf4D+CpkA=="],
|
||||
|
||||
@@ -224,7 +220,7 @@
|
||||
|
||||
"ms": ["ms@2.1.3", "", {}, "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="],
|
||||
|
||||
"nanoid": ["nanoid@3.3.16", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-bzlKTyNJ7+LdGIIwy8ijFpIqEQIvafahV7eYykJ8Cvh42EdJeODoJ6gUJXpQJvej1BddH8OqTXZNE/KfbWAu8Q=="],
|
||||
"nanoid": ["nanoid@3.3.11", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w=="],
|
||||
|
||||
"node-releases": ["node-releases@2.0.37", "", {}, "sha512-1h5gKZCF+pO/o3Iqt5Jp7wc9rH3eJJ0+nh/CIoiRwjRxde/hAHyLPXYN4V3CqKAbiZPSeJFSWHmJsbkicta0Eg=="],
|
||||
|
||||
@@ -232,7 +228,7 @@
|
||||
|
||||
"picomatch": ["picomatch@4.0.4", "", {}, "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A=="],
|
||||
|
||||
"postcss": ["postcss@8.5.19", "", { "dependencies": { "nanoid": "^3.3.12", "picocolors": "^1.1.1", "source-map-js": "^1.2.1" } }, "sha512-Mz8SaolMd8nB+G13WkORcxQKHZ/NE4xXevtkJHVuG+guo9/wYKlIMTKAqGdEmYOXR2ijPjTYNHssizdaVSUNdQ=="],
|
||||
"postcss": ["postcss@8.5.9", "", { "dependencies": { "nanoid": "^3.3.11", "picocolors": "^1.1.1", "source-map-js": "^1.2.1" } }, "sha512-7a70Nsot+EMX9fFU3064K/kdHWZqGVY+BADLyXc8Dfv+mTLLVl6JzJpPaCZ2kQL9gIJvKXSLMHhqdRRjwQeFtw=="],
|
||||
|
||||
"react": ["react@19.2.5", "", {}, "sha512-llUJLzz1zTUBrskt2pwZgLq59AemifIftw4aB7JxOqf1HY2FDaGDxgwpAPVzHU1kdWabH7FauP4i1oEeer2WCA=="],
|
||||
|
||||
@@ -254,36 +250,8 @@
|
||||
|
||||
"update-browserslist-db": ["update-browserslist-db@1.2.3", "", { "dependencies": { "escalade": "^3.2.0", "picocolors": "^1.1.1" }, "peerDependencies": { "browserslist": ">= 4.21.0" }, "bin": { "update-browserslist-db": "cli.js" } }, "sha512-Js0m9cx+qOgDxo0eMiFGEueWztz+d4+M3rGlmKPT+T4IS/jP4ylw3Nwpu6cpTTP8R1MAC1kF4VbdLt3ARf209w=="],
|
||||
|
||||
"vite": ["vite@6.4.3", "", { "dependencies": { "esbuild": "^0.25.0", "fdir": "^6.4.4", "picomatch": "^4.0.2", "postcss": "^8.5.3", "rollup": "^4.34.9", "tinyglobby": "^0.2.13" }, "optionalDependencies": { "fsevents": "~2.3.3" }, "peerDependencies": { "@types/node": "^18.0.0 || ^20.0.0 || >=22.0.0", "jiti": ">=1.21.0", "less": "*", "lightningcss": "^1.21.0", "sass": "*", "sass-embedded": "*", "stylus": "*", "sugarss": "*", "terser": "^5.16.0", "tsx": "^4.8.1", "yaml": "^2.4.2" }, "optionalPeers": ["@types/node", "jiti", "less", "lightningcss", "sass", "sass-embedded", "stylus", "sugarss", "terser", "tsx", "yaml"], "bin": { "vite": "bin/vite.js" } }, "sha512-NTKlcQjlAK7MlQoyb6LgaqHc8sso/pVyUJYWMws3jg21uTJw/LddqIFPcPqP6PzpgbIcZyKI85sFE4HBrQDA8A=="],
|
||||
"vite": ["vite@6.4.2", "", { "dependencies": { "esbuild": "^0.25.0", "fdir": "^6.4.4", "picomatch": "^4.0.2", "postcss": "^8.5.3", "rollup": "^4.34.9", "tinyglobby": "^0.2.13" }, "optionalDependencies": { "fsevents": "~2.3.3" }, "peerDependencies": { "@types/node": "^18.0.0 || ^20.0.0 || >=22.0.0", "jiti": ">=1.21.0", "less": "*", "lightningcss": "^1.21.0", "sass": "*", "sass-embedded": "*", "stylus": "*", "sugarss": "*", "terser": "^5.16.0", "tsx": "^4.8.1", "yaml": "^2.4.2" }, "optionalPeers": ["@types/node", "jiti", "less", "lightningcss", "sass", "sass-embedded", "stylus", "sugarss", "terser", "tsx", "yaml"], "bin": { "vite": "bin/vite.js" } }, "sha512-2N/55r4JDJ4gdrCvGgINMy+HH3iRpNIz8K6SFwVsA+JbQScLiC+clmAxBgwiSPgcG9U15QmvqCGWzMbqda5zGQ=="],
|
||||
|
||||
"yallist": ["yallist@3.1.1", "", {}, "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g=="],
|
||||
|
||||
"@types/babel__core/@babel/parser": ["@babel/parser@7.29.2", "", { "dependencies": { "@babel/types": "^7.29.0" }, "bin": "./bin/babel-parser.js" }, "sha512-4GgRzy/+fsBa72/RZVJmGKPmZu9Byn8o4MoLpmNe1m8ZfYnz5emHLQz3U4gLud6Zwl0RZIcgiLD7Uq7ySFuDLA=="],
|
||||
|
||||
"@types/babel__core/@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
|
||||
|
||||
"@types/babel__generator/@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
|
||||
|
||||
"@types/babel__template/@babel/parser": ["@babel/parser@7.29.2", "", { "dependencies": { "@babel/types": "^7.29.0" }, "bin": "./bin/babel-parser.js" }, "sha512-4GgRzy/+fsBa72/RZVJmGKPmZu9Byn8o4MoLpmNe1m8ZfYnz5emHLQz3U4gLud6Zwl0RZIcgiLD7Uq7ySFuDLA=="],
|
||||
|
||||
"@types/babel__template/@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
|
||||
|
||||
"@types/babel__traverse/@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
|
||||
|
||||
"@types/babel__core/@babel/types/@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
|
||||
|
||||
"@types/babel__core/@babel/types/@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
|
||||
|
||||
"@types/babel__generator/@babel/types/@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
|
||||
|
||||
"@types/babel__generator/@babel/types/@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
|
||||
|
||||
"@types/babel__template/@babel/types/@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
|
||||
|
||||
"@types/babel__template/@babel/types/@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
|
||||
|
||||
"@types/babel__traverse/@babel/types/@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
|
||||
|
||||
"@types/babel__traverse/@babel/types/@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
|
||||
}
|
||||
}
|
||||
|
||||
File diff suppressed because one or more lines are too long
Vendored
+1
-1
@@ -7,7 +7,7 @@
|
||||
<link rel="preconnect" href="https://fonts.googleapis.com" />
|
||||
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
|
||||
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet" />
|
||||
<script type="module" crossorigin src="/admin/assets/index-CoGEje3-.js"></script>
|
||||
<script type="module" crossorigin src="/admin/assets/index-DqP-zmqH.js"></script>
|
||||
<link rel="stylesheet" crossorigin href="/admin/assets/index-GxkWX7v3.css">
|
||||
</head>
|
||||
<body>
|
||||
|
||||
+1
-5
@@ -15,11 +15,7 @@
|
||||
"@types/react": "^19.1.2",
|
||||
"@types/react-dom": "^19.1.2",
|
||||
"@vitejs/plugin-react": "^4.4.1",
|
||||
"vite": "^6.4.3",
|
||||
"vite": "^6.3.3",
|
||||
"typescript": "^5.8.3"
|
||||
},
|
||||
"overrides": {
|
||||
"@babel/core": "^7.29.6",
|
||||
"postcss": "^8.5.10"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -21,7 +21,7 @@ export function DashboardPage() {
|
||||
api.stats().then(setStats).catch(() => {});
|
||||
api.health().then(setHealth).catch(() => {});
|
||||
|
||||
const es = new EventSource('/admin/events', { withCredentials: true });
|
||||
const es = new EventSource('/admin/events');
|
||||
eventSourceRef.current = es;
|
||||
es.onopen = () => setSseStatus('connected');
|
||||
es.onmessage = (e) => {
|
||||
|
||||
@@ -26,8 +26,8 @@
|
||||
"express-rate-limit": "^7.5.0",
|
||||
"gray-matter": "^4.0.3",
|
||||
"heic-decode": "^2.1.0",
|
||||
"js-yaml": "^3.15.0",
|
||||
"marked": "^18.0.2",
|
||||
"js-yaml": "^3.14.2",
|
||||
"marked": "^18.0.0",
|
||||
"openai": "^4.0.0",
|
||||
"pgvector": "^0.2.0",
|
||||
"postgres": "^3.4.0",
|
||||
@@ -50,17 +50,6 @@
|
||||
"trustedDependencies": [
|
||||
"@electric-sql/pglite",
|
||||
],
|
||||
"overrides": {
|
||||
"@hono/node-server": "^1.19.13",
|
||||
"fast-uri": "^3.1.2",
|
||||
"fast-xml-builder": "^1.1.7",
|
||||
"fast-xml-parser": "^5.7.0",
|
||||
"form-data": "^4.0.6",
|
||||
"hono": "^4.12.25",
|
||||
"ip-address": "^10.1.1",
|
||||
"js-yaml": "^3.15.0",
|
||||
"qs": "^6.15.2",
|
||||
},
|
||||
"packages": {
|
||||
"@ai-sdk/anthropic": ["@ai-sdk/anthropic@3.0.74", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@ai-sdk/provider-utils": "4.0.26" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-Xew9rfz9WWhDSyF8rNhjT/XWOWelNfJrMlmG0Ahw210hStisRpQZ1s+7VeI9JTJOZ5y5tXqBi5kfPwYnCfyRTA=="],
|
||||
|
||||
@@ -162,7 +151,7 @@
|
||||
|
||||
"@electric-sql/pglite": ["@electric-sql/pglite@0.4.3", "", {}, "sha512-ichuWTgtd4mOM1G4SpyGJa5trT03lWbMypDV0fUXUCXg5hiHqVAz/bZyV68NqmkLB7WcYmj1RMJVSp8HV/v/ZQ=="],
|
||||
|
||||
"@hono/node-server": ["@hono/node-server@1.19.14", "", { "peerDependencies": { "hono": "^4" } }, "sha512-GwtvgtXxnWsucXvbQXkRgqksiH2Qed37H9xHZocE5sA3N8O8O8/8FA3uclQXxXVzc9XBZuEOMK7+r02FmSpHtw=="],
|
||||
"@hono/node-server": ["@hono/node-server@1.19.12", "", { "peerDependencies": { "hono": "^4" } }, "sha512-txsUW4SQ1iilgE0l9/e9VQWmELXifEFvmdA1j6WFh/aFPj99hIntrSsq/if0UWyGVkmrRPKA1wCeP+UCr1B9Uw=="],
|
||||
|
||||
"@jsquash/avif": ["@jsquash/avif@2.1.1", "", { "dependencies": { "wasm-feature-detect": "^1.2.11" } }, "sha512-LMRxd0fMgfCLtobDh0/sFYJMMiRJTNYSEEWvRDKXlAeZ08t3gI5V+1thIT0XjXJ+SVG7Zug9B0XPyx0Ti5VRNA=="],
|
||||
|
||||
@@ -170,8 +159,6 @@
|
||||
|
||||
"@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.29.0", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.2.1", "express-rate-limit": "^8.2.1", "hono": "^4.11.4", "jose": "^6.1.3", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.1" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-zo37mZA9hJWpULgkRpowewez1y6ML5GsXJPY8FI0tBBCd77HEvza4jDqRKOXgHNn867PVGCyTdzqpz0izu5ZjQ=="],
|
||||
|
||||
"@nodable/entities": ["@nodable/entities@3.0.0", "", {}, "sha512-8L9xFeTYKhm49xfIypoe2W5wV1m/3Z58kT+7kR9A8OyFxcPduI4VmxaUMQyKYrRjUoLLSXv6EKKID5Tvj9cUVw=="],
|
||||
|
||||
"@opentelemetry/api": ["@opentelemetry/api@1.9.0", "", {}, "sha512-3giAOQvZiH5F9bMlMiv8+GSPMeqg0dbaeo58/0SlA9sxSqZhnUtxzX9/2FzyhS9sWQf5S0GJE0AKBrFqjpeYcg=="],
|
||||
|
||||
"@smithy/chunked-blob-reader": ["@smithy/chunked-blob-reader@5.2.2", "", { "dependencies": { "tslib": "^2.6.2" } }, "sha512-St+kVicSyayWQca+I1rGitaOEH6uKgE8IUWoYnnEX26SWdWQcL6LvMSD19Lg+vYHKdT9B2Zuu7rd3i6Wnyb/iw=="],
|
||||
@@ -320,8 +307,6 @@
|
||||
|
||||
"ajv-formats": ["ajv-formats@3.0.1", "", { "dependencies": { "ajv": "^8.0.0" } }, "sha512-8iUql50EUR+uUcdRQ3HDqa6EVyo3docL8g5WJ3FNcWmu62IbkGUue/pEyLBW8VGKKucTPgqeks4fIU1DA4yowQ=="],
|
||||
|
||||
"anynum": ["anynum@1.0.1", "", {}, "sha512-N6//FLET/tXYNM/F6ABca1oH6fWB+KlTt909Le28WMDBk8oaT4vY17DCrwg2MvmuqUKt3Ni4N5dGJ/EoBgcO6A=="],
|
||||
|
||||
"argparse": ["argparse@1.0.10", "", { "dependencies": { "sprintf-js": "~1.0.2" } }, "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg=="],
|
||||
|
||||
"asynckit": ["asynckit@0.4.0", "", {}, "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="],
|
||||
@@ -400,15 +385,15 @@
|
||||
|
||||
"fast-deep-equal": ["fast-deep-equal@3.1.3", "", {}, "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q=="],
|
||||
|
||||
"fast-uri": ["fast-uri@3.1.3", "", {}, "sha512-i70LwGWUduXqzicKXWshooq+sWL1K3WUU5rKZNG/0i3a1OSoX3HqhH5WbWwTmqWfor4urUakGPiRQcleRZTwOg=="],
|
||||
"fast-uri": ["fast-uri@3.1.0", "", {}, "sha512-iPeeDKJSWf4IEOasVVrknXpaBV0IApz/gp7S2bb7Z4Lljbl2MGJRqInZiUrQwV16cpzw/D3S5j5Julj/gT52AA=="],
|
||||
|
||||
"fast-xml-builder": ["fast-xml-builder@1.3.0", "", { "dependencies": { "path-expression-matcher": "^1.6.2", "xml-naming": "^0.3.0" } }, "sha512-F74cZEdCvuw9P41GAC3rod4X04jjWGM1JPEv/GWSqFTWLsdyMSBMBMlm9Hk3GLBgLBbdBNY8yee0pQh2RBVESQ=="],
|
||||
"fast-xml-builder": ["fast-xml-builder@1.1.4", "", { "dependencies": { "path-expression-matcher": "^1.1.3" } }, "sha512-f2jhpN4Eccy0/Uz9csxh3Nu6q4ErKxf0XIsasomfOihuSUa3/xw6w8dnOtCDgEItQFJG8KyXPzQXzcODDrrbOg=="],
|
||||
|
||||
"fast-xml-parser": ["fast-xml-parser@5.10.1", "", { "dependencies": { "@nodable/entities": "^3.0.0", "fast-xml-builder": "^1.2.0", "is-unsafe": "^2.0.0", "path-expression-matcher": "^1.6.2", "strnum": "^2.4.1", "xml-naming": "^0.3.0" }, "bin": { "fxparser": "src/cli/cli.js" } }, "sha512-IEMIf7298kXuZSRFoGfMYrl7is8LpavODgbNz1cwIudv7KwVFnuU+UsMporfq6PD6aXSlawZlARiA3UywCTfMw=="],
|
||||
"fast-xml-parser": ["fast-xml-parser@5.5.8", "", { "dependencies": { "fast-xml-builder": "^1.1.4", "path-expression-matcher": "^1.2.0", "strnum": "^2.2.0" }, "bin": { "fxparser": "src/cli/cli.js" } }, "sha512-Z7Fh2nVQSb2d+poDViM063ix2ZGt9jmY1nWhPfHBOK2Hgnb/OW3P4Et3P/81SEej0J7QbWtJqxO05h8QYfK7LQ=="],
|
||||
|
||||
"finalhandler": ["finalhandler@2.1.1", "", { "dependencies": { "debug": "^4.4.0", "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "on-finished": "^2.4.1", "parseurl": "^1.3.3", "statuses": "^2.0.1" } }, "sha512-S8KoZgRZN+a5rNwqTxlZZePjT/4cnm0ROV70LedRHZ0p8u9fRID0hJUZQpkKLzro8LfmC8sx23bY6tVNxv8pQA=="],
|
||||
|
||||
"form-data": ["form-data@4.0.6", "", { "dependencies": { "asynckit": "^0.4.0", "combined-stream": "^1.0.8", "es-set-tostringtag": "^2.1.0", "hasown": "^2.0.4", "mime-types": "^2.1.35" } }, "sha512-vKatAh4SlVfgbv+YtmhiRjhEMJsYpsG1Y2rMQtR+SVSbytsSD1YGzDIcrAJmdFec88u/+VoGmxnl+80gL1tRCQ=="],
|
||||
"form-data": ["form-data@4.0.5", "", { "dependencies": { "asynckit": "^0.4.0", "combined-stream": "^1.0.8", "es-set-tostringtag": "^2.1.0", "hasown": "^2.0.2", "mime-types": "^2.1.12" } }, "sha512-8RipRLol37bNs2bhoV67fiTEvdTrbMUYcFTiy3+wuuOnUog2QBHCZWXDRijWQfAkhBj2Uf5UnVaiWwA5vdd82w=="],
|
||||
|
||||
"form-data-encoder": ["form-data-encoder@1.7.2", "", {}, "sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A=="],
|
||||
|
||||
@@ -432,11 +417,11 @@
|
||||
|
||||
"has-tostringtag": ["has-tostringtag@1.0.2", "", { "dependencies": { "has-symbols": "^1.0.3" } }, "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw=="],
|
||||
|
||||
"hasown": ["hasown@2.0.4", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-T2UbfbBEF32wiepXIsMlTW9+dDYC6wMh/t/vYA4tuOMKqWz/n3vr1NFSxQiyP+zk2mXsoMA/i/7qV6LKut1t1A=="],
|
||||
"hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
|
||||
|
||||
"heic-decode": ["heic-decode@2.1.0", "", { "dependencies": { "libheif-js": "^1.19.8" } }, "sha512-0fB3O3WMk38+PScbHLVp66jcNhsZ/ErtQ6u2lMYu/YxXgbBtl+oKOhGQHa4RpvE68k8IzbWkABzHnyAIjR758A=="],
|
||||
|
||||
"hono": ["hono@4.12.30", "", {}, "sha512-emn+JoJjrN9YTpRDS5it/UI2SO9BAE37T6I3d963RxcZ81G9A4pr2SZTEiiaiKbzx+NKRg5BZ89fCL7gCJCUog=="],
|
||||
"hono": ["hono@4.12.10", "", {}, "sha512-mx/p18PLy5og9ufies2GOSUqep98Td9q4i/EF6X7yJgAiIopxqdfIO3jbqsi3jRgTgw88jMDEzVKi+V2EF+27w=="],
|
||||
|
||||
"http-errors": ["http-errors@2.0.1", "", { "dependencies": { "depd": "~2.0.0", "inherits": "~2.0.4", "setprototypeof": "~1.2.0", "statuses": "~2.0.2", "toidentifier": "~1.0.1" } }, "sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ=="],
|
||||
|
||||
@@ -446,7 +431,7 @@
|
||||
|
||||
"inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
|
||||
|
||||
"ip-address": ["ip-address@10.2.0", "", {}, "sha512-/+S6j4E9AHvW9SWMSEY9Xfy66O5PWvVEJ08O0y5JGyEKQpojb0K0GKpz/v5HJ/G0vi3D2sjGK78119oXZeE0qA=="],
|
||||
"ip-address": ["ip-address@10.1.0", "", {}, "sha512-XXADHxXmvT9+CRxhXg56LJovE+bmWnEWB78LB83VZTprKTmaC5QfruXocxzTZ2Kl0DNwKuBdlIhjL8LeY8Sf8Q=="],
|
||||
|
||||
"ipaddr.js": ["ipaddr.js@1.9.1", "", {}, "sha512-0KI/607xoxSToH7GjN1FfSbLoU0+btTicjsQSWQlh/hZykN8KpmMf7uYwPW3R+akZ6R/w18ZlXSHBYXiYUPO3g=="],
|
||||
|
||||
@@ -454,13 +439,11 @@
|
||||
|
||||
"is-promise": ["is-promise@4.0.0", "", {}, "sha512-hvpoI6korhJMnej285dSg6nu1+e6uxs7zG3BYAm5byqDsgJNWwxzM6z6iZiAgQR4TJ30JmBTOwqZUw3WlyH3AQ=="],
|
||||
|
||||
"is-unsafe": ["is-unsafe@2.0.0", "", {}, "sha512-2LdV822R+wmI86unXA93WCFpL6g+av8ynWk0nrHyJqGop5VoocYsSLFgN8jrfalT6iGeLNM4KXuVSsULP53kEA=="],
|
||||
|
||||
"isexe": ["isexe@2.0.0", "", {}, "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw=="],
|
||||
|
||||
"jose": ["jose@6.2.2", "", {}, "sha512-d7kPDd34KO/YnzaDOlikGpOurfF0ByC2sEV4cANCtdqLlTfBlw2p14O/5d/zv40gJPbIQxfES3nSx1/oYNyuZQ=="],
|
||||
|
||||
"js-yaml": ["js-yaml@3.15.0", "", { "dependencies": { "argparse": "^1.0.7", "esprima": "^4.0.0" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-ttBQIIQPDeLjpPOohtUdXuXUVoA2uIB6fEH9HyJ7234s5mBJ5wTx20njxplLZQgLaOfpmPQA7X2t5AX6tIPbog=="],
|
||||
"js-yaml": ["js-yaml@3.14.2", "", { "dependencies": { "argparse": "^1.0.7", "esprima": "^4.0.0" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-PMSmkqxr106Xa156c2M265Z+FTrPl+oxd/rgOQy2tijQeK5TxQ43psO1ZCwhVOSdnn+RzkzlRz/eY4BgJBYVpg=="],
|
||||
|
||||
"json-schema": ["json-schema@0.4.0", "", {}, "sha512-es94M3nTIfsEPisRafak+HDLfHXnKBhV3vU5eqPcS3flIWqcxJWgXHXiey3YrpaNsanY5ei1VoYEbOzijuq9BA=="],
|
||||
|
||||
@@ -472,7 +455,7 @@
|
||||
|
||||
"libheif-js": ["libheif-js@1.19.8", "", {}, "sha512-vQJWusIxO7wavpON1dusciL8Go9jsIQ+EUrckauFYAiSTjcmLAsuJh3SszLpvkwPci3JcL41ek2n+LUZGFpPIQ=="],
|
||||
|
||||
"marked": ["marked@18.0.6", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-MrV5puXBfuiy6wl6DLaq3BtIJQAJToAd5zt/ZKhRfGRAuFPALE7/4Y7jnxRQoEgK/pBgurGqLyAuRgZ2xOjr6w=="],
|
||||
"marked": ["marked@18.0.0", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-2e7Qiv/HJSXj8rDEpgTvGKsP8yYtI9xXHKDnrftrmnrJPaFNM7VRb2YCzWaX4BP1iCJ/XPduzDJZMFoqTCcIMA=="],
|
||||
|
||||
"math-intrinsics": ["math-intrinsics@1.1.0", "", {}, "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g=="],
|
||||
|
||||
@@ -504,7 +487,7 @@
|
||||
|
||||
"parseurl": ["parseurl@1.3.3", "", {}, "sha512-CiyeOxFT/JZyN5m0z9PfXw4SCBJ6Sygz1Dpl0wqjlhDEGGBP1GnsUVEL0p63hoG1fcj3fHynXi9NYO4nWOL+qQ=="],
|
||||
|
||||
"path-expression-matcher": ["path-expression-matcher@1.6.2", "", {}, "sha512-enSlaiat05iasnzmgNxRj8reFdj3puY2QpNgP1aPIaVfT6nn9ICuPoFlKHk8EN22HcwewshO+mN2DGbkCEOtqQ=="],
|
||||
"path-expression-matcher": ["path-expression-matcher@1.5.0", "", {}, "sha512-cbrerZV+6rvdQrrD+iGMcZFEiiSrbv9Tfdkvnusy6y0x0GKBXREFg/Y65GhIfm0tnLntThhzCnfKwp1WRjeCyQ=="],
|
||||
|
||||
"path-key": ["path-key@3.1.1", "", {}, "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q=="],
|
||||
|
||||
@@ -520,7 +503,7 @@
|
||||
|
||||
"pure-rand": ["pure-rand@8.4.0", "", {}, "sha512-IoM8YF/jY0hiugFo/wOWqfmarlE6J0wc6fDK1PhftMk7MGhVZl88sZimmqBBFomLOCSmcCCpsfj7wXASCpvK9A=="],
|
||||
|
||||
"qs": ["qs@6.15.3", "", { "dependencies": { "es-define-property": "^1.0.1", "side-channel": "^1.1.1" } }, "sha512-O9gl3zCl5h5blw1KGUzQKhA5oUXSl8rwUIM5o0S3nCXMliSvy5Dzx7/DJcI+SwgICv+IneSZwhBh1oSyEHA71A=="],
|
||||
"qs": ["qs@6.15.0", "", { "dependencies": { "side-channel": "^1.1.0" } }, "sha512-mAZTtNCeetKMH+pSjrb76NAM8V9a05I9aBZOHztWy/UqcJdQYNsf59vrRKWnojAT9Y+GbIvoTBC++CPHqpDBhQ=="],
|
||||
|
||||
"range-parser": ["range-parser@1.2.1", "", {}, "sha512-Hrgsx+orqoygnmhFbKaHE6c296J+HTAQXoxEF6gNupROmmGJRoyzfG3ccAveqCBrwr/2yxQ5BVd/GTl5agOwSg=="],
|
||||
|
||||
@@ -546,9 +529,9 @@
|
||||
|
||||
"shebang-regex": ["shebang-regex@3.0.0", "", {}, "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A=="],
|
||||
|
||||
"side-channel": ["side-channel@1.1.1", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.4", "side-channel-list": "^1.0.1", "side-channel-map": "^1.0.1", "side-channel-weakmap": "^1.0.2" } }, "sha512-6x6dK6zJdpTzF4sQeNYxwtvBzf6Eg4GtlesS94HOvTudUeyK2WXAaIfmDgsyslYrRBeFIlsi54AYsFGUuhmvrQ=="],
|
||||
"side-channel": ["side-channel@1.1.0", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.3", "side-channel-list": "^1.0.0", "side-channel-map": "^1.0.1", "side-channel-weakmap": "^1.0.2" } }, "sha512-ZX99e6tRweoUXqR+VBrslhda51Nh5MTQwou5tnUDgbtyM0dBgmhEDtWGP/xbKn6hqfPRHujUNwz5fy/wbbhnpw=="],
|
||||
|
||||
"side-channel-list": ["side-channel-list@1.0.1", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.4" } }, "sha512-mjn/0bi/oUURjc5Xl7IaWi/OJJJumuoJFQJfDDyO46+hBWsfaVM65TBHq2eoZBhzl9EchxOijpkbRC8SVBQU0w=="],
|
||||
"side-channel-list": ["side-channel-list@1.0.0", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.3" } }, "sha512-FCLHtRD/gnpCiCHEiJLOwdmFP+wzCmDEkc9y7NsYxeF4u7Btsn1ZuwgwJGxImImHicJArLP4R0yX4c2KCrMrTA=="],
|
||||
|
||||
"side-channel-map": ["side-channel-map@1.0.1", "", { "dependencies": { "call-bound": "^1.0.2", "es-errors": "^1.3.0", "get-intrinsic": "^1.2.5", "object-inspect": "^1.13.3" } }, "sha512-VCjCNfgMsby3tTdo02nbjtM/ewra6jPHmpThenkTYh8pG9ucZ/1P8So4u4FGBek/BjpOVsDCMoLA/iuBKIFXRA=="],
|
||||
|
||||
@@ -560,7 +543,7 @@
|
||||
|
||||
"strip-bom-string": ["strip-bom-string@1.0.0", "", {}, "sha512-uCC2VHvQRYu+lMh4My/sFNmF2klFymLX1wHJeXnbEJERpV/ZsVuonzerjfrGpIGF7LBVa1O7i9kjiWvJiFck8g=="],
|
||||
|
||||
"strnum": ["strnum@2.4.1", "", { "dependencies": { "anynum": "^1.0.1" } }, "sha512-M9eUSMT2dCB2cTNPG7UYj6KuK7RJR2SN2+yCV/fTW3xzTCS6EaGZ5pSMgDIjB7r8zSfTGk+dvvn9rTjpVS9Mwg=="],
|
||||
"strnum": ["strnum@2.2.3", "", {}, "sha512-oKx6RUCuHfT3oyVjtnrmn19H1SiCqgJSg+54XqURKp5aCMbrXrhLjRN9TjuwMjiYstZ0MzDrHqkGZ5dFTKd+zg=="],
|
||||
|
||||
"toidentifier": ["toidentifier@1.0.1", "", {}, "sha512-o5sSPKEkg/DIQNmH43V0/uerLrpzVedkUh8tGNvaeXpfpuwjKenlSox/2O/BTlZUtEe+JG7s5YhEz608PlAHRA=="],
|
||||
|
||||
@@ -594,8 +577,6 @@
|
||||
|
||||
"wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
|
||||
|
||||
"xml-naming": ["xml-naming@0.3.0", "", {}, "sha512-ghig2TBE/H11aOVgmahA3MhimvkBr6JIYknH/Dhdk10nXwdbIqBJsbfMxpvFPG8bAw77gN29aQWvKpmVoPlvPQ=="],
|
||||
|
||||
"zod": ["zod@4.3.6", "", {}, "sha512-rftlrkhHZOcjDwkGlnUtZZkvaPHCsDATp4pGpuOOMDaTdDDXF91wuVDJoWoPsKX/3YPQ5fHuF3STjcYyKr+Qhg=="],
|
||||
|
||||
"zod-to-json-schema": ["zod-to-json-schema@3.25.2", "", { "peerDependencies": { "zod": "^3.25.28 || ^4" } }, "sha512-O/PgfnpT1xKSDeQYSCfRI5Gy3hPf91mKVDuYLUHZJMiDFptvP41MSnWofm8dnCm0256ZNfZIM7DSzuSMAFnjHA=="],
|
||||
@@ -614,16 +595,12 @@
|
||||
|
||||
"@types/bun/bun-types": ["bun-types@1.3.11", "", { "dependencies": { "@types/node": "*" } }, "sha512-1KGPpoxQWl9f6wcZh57LvrPIInQMn2TQ7jsgxqpRzg+l0QPOFvJVH7HmvHo/AiPgwXy+/Thf6Ov3EdVn1vOabg=="],
|
||||
|
||||
"es-set-tostringtag/hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
|
||||
|
||||
"eventsource/eventsource-parser": ["eventsource-parser@3.0.6", "", {}, "sha512-Vo1ab+QXPzZ4tCa8SwIHJFaSzy4R6SHf7BY79rFBDf0idraZWAkYrDjDj8uWaSm3S2TK+hJ7/t1CEmZ7jXw+pg=="],
|
||||
|
||||
"express/cookie-signature": ["cookie-signature@1.2.2", "", {}, "sha512-D76uU73ulSXrD1UXF4KE2TMxVVwhsnCgfAyTg9k8P6KGZjlXKrOLe4dJQKI3Bxi5wjesZoFXJWElNWBjPZMbhg=="],
|
||||
|
||||
"form-data/mime-types": ["mime-types@2.1.35", "", { "dependencies": { "mime-db": "1.52.0" } }, "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw=="],
|
||||
|
||||
"get-intrinsic/hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
|
||||
|
||||
"openai/@types/node": ["@types/node@18.19.130", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-GRaXQx6jGfL8sKfaIDD6OupbIHBr9jv7Jnaml9tB7l4v068PAOXqfcujMMo5PhbIs6ggR1XODELqahT2R8v0fg=="],
|
||||
|
||||
"@anthropic-ai/sdk/@types/node/undici-types": ["undici-types@5.26.5", "", {}, "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA=="],
|
||||
|
||||
+1
-6
@@ -13,9 +13,4 @@ timeout = 60_000
|
||||
# fixtures still match the schema. v0.37's production default is ZE/1280;
|
||||
# tests that want the new default call configureGateway() explicitly in
|
||||
# their own beforeAll.
|
||||
#
|
||||
# #2823: redirect GBRAIN_AUDIT_DIR to a per-run scratch dir BEFORE any test
|
||||
# runs, so audit-emitting code paths (content-sanity, shell-audit, etc.)
|
||||
# can't leak fixture events into the operator's real ~/.gbrain/audit/. See
|
||||
# test/helpers/audit-dir-preload.ts for the full rationale.
|
||||
preload = ["./test/helpers/legacy-embedding-preload.ts", "./test/helpers/audit-dir-preload.ts"]
|
||||
preload = ["./test/helpers/legacy-embedding-preload.ts"]
|
||||
|
||||
@@ -85,40 +85,6 @@ services:
|
||||
volumes:
|
||||
- gbrain-ci-pg-data-4:/var/lib/postgresql/data
|
||||
|
||||
# v0.43 (#2084 / eng-review TD1): PgBouncer in TRANSACTION pooling mode
|
||||
# fronting postgres-1 — the production topology (Supabase direct :5432 +
|
||||
# pooled :6543) behind three consecutive pooler-teardown waves
|
||||
# (#1972 → #2015 → #2084) that CI could never reproduce.
|
||||
# test/e2e/pgbouncer-teardown.test.ts uses a DEDICATED database
|
||||
# (gbrain_pgbouncer) on postgres-1 so it never races shard 1's
|
||||
# TRUNCATE-based fixtures; pgbouncer's wildcard [databases] section
|
||||
# forwards any dbname to DB_HOST.
|
||||
pgbouncer:
|
||||
image: edoburu/pgbouncer:latest
|
||||
environment:
|
||||
DB_HOST: postgres-1
|
||||
DB_PORT: "5432"
|
||||
DB_USER: postgres
|
||||
DB_PASSWORD: postgres
|
||||
POOL_MODE: transaction
|
||||
# plain (CI-only): pg16 stores SCRAM verifiers, and pgbouncer can only
|
||||
# answer the server's SCRAM challenge when its userlist holds the
|
||||
# PLAINTEXT password — an md5-hashed userlist fails with
|
||||
# "server login failed: wrong password type".
|
||||
AUTH_TYPE: plain
|
||||
MAX_CLIENT_CONN: "200"
|
||||
DEFAULT_POOL_SIZE: "10"
|
||||
# gbrain's client sets statement_timeout + idle_in_transaction_session_timeout
|
||||
# as startup parameters (db.ts buildConnectionParams); the Supabase pooler
|
||||
# whitelists them, so this pooler must too or every connection is refused
|
||||
# before the teardown path is even reached.
|
||||
IGNORE_STARTUP_PARAMETERS: extra_float_digits,statement_timeout,idle_in_transaction_session_timeout,search_path
|
||||
ports:
|
||||
- "${GBRAIN_CI_PGBOUNCER_PORT:-6543}:5432"
|
||||
depends_on:
|
||||
postgres-1:
|
||||
condition: service_healthy
|
||||
|
||||
runner:
|
||||
image: oven/bun:1
|
||||
working_dir: /app
|
||||
@@ -131,8 +97,6 @@ services:
|
||||
condition: service_healthy
|
||||
postgres-4:
|
||||
condition: service_healthy
|
||||
pgbouncer:
|
||||
condition: service_started
|
||||
# No global DATABASE_URL — scripts/ci-local.sh sets per-shard URL via -e.
|
||||
# Unit phase explicitly unsets DATABASE_URL so test/e2e/* gracefully skip.
|
||||
volumes:
|
||||
|
||||
+1
-79
@@ -94,7 +94,7 @@ export interface BrainEngine {
|
||||
|
||||
**Slug-based API, not ID-based.** Every method takes slugs, not numeric IDs. The engine resolves slugs to IDs internally. This keeps the interface portable... slugs are strings, IDs are database-specific.
|
||||
|
||||
**Embedding is NOT in the engine.** The engine stores embeddings and searches by vector, but it doesn't generate embeddings. `src/core/embedding.ts` handles that (a thin delegation to the provider-agnostic AI gateway in `src/core/ai/gateway.ts`). This is intentional: embedding is an external API call (OpenAI, Voyage, a local Ollama — whichever provider you configured), not a storage concern. All engines share the same embedding service.
|
||||
**Embedding is NOT in the engine.** The engine stores embeddings and searches by vector, but it doesn't generate embeddings. `src/core/embedding.ts` handles that. This is intentional: embedding is an external API call (OpenAI), not a storage concern. All engines share the same embedding service.
|
||||
|
||||
**Chunking is NOT in the engine.** Same logic. `src/core/chunkers/` handles chunking. The engine stores and retrieves chunks. All engines share the same chunkers.
|
||||
|
||||
@@ -148,51 +148,6 @@ RRF fusion, multi-query expansion, and 4-layer dedup are engine-agnostic. They o
|
||||
|
||||
**Why not self-hosted for v0:** The brain should be infrastructure agents use, not something you maintain. Self-hosted Postgres with Docker is a welcome community PR, but v0 optimizes for zero ops.
|
||||
|
||||
### Opt-in RLS source-scope binding (`GBRAIN_RLS_SCOPE_BINDING`)
|
||||
|
||||
Defense-in-depth layer for Postgres deployments that want the database itself
|
||||
to enforce source isolation, in addition to the mandatory app-layer filters
|
||||
(`sourceScopeOpts` — layer 1, always on).
|
||||
|
||||
**Mechanism.** With `GBRAIN_RLS_SCOPE_BINDING=1` (or `true`), the engine's
|
||||
source-scoped read methods wrap their queries in a transaction that first runs
|
||||
`SELECT set_config('app.scopes', $1, true)` — the value is a bound parameter
|
||||
(federated `sourceIds` CSV > scalar `sourceId` > `'*'` for unscoped internal
|
||||
reads), transaction-local (equivalent to `SET LOCAL`, which itself can't take
|
||||
bound params). An RLS policy can then filter rows by
|
||||
`current_setting('app.scopes', true)`.
|
||||
|
||||
**Default off.** With the env var unset, reads call through on the shared pool
|
||||
exactly as before — no per-read transaction, no pool-slot hold (the search
|
||||
methods keep the transaction they always had for their `SET LOCAL
|
||||
statement_timeout`). Existing operators see zero behavior change.
|
||||
|
||||
**Enabling it** (operator-managed SQL; gbrain ships no DDL for this):
|
||||
|
||||
```sql
|
||||
ALTER TABLE pages ENABLE ROW LEVEL SECURITY;
|
||||
CREATE POLICY pages_scope_filter ON pages
|
||||
USING (current_setting('app.scopes', true) = '*'
|
||||
OR source_id = ANY(string_to_array(current_setting('app.scopes', true), ',')));
|
||||
|
||||
-- Required: connections that don't run through the scoped read helper
|
||||
-- (admin, autopilot, cycle, writes) must default to unscoped, or they
|
||||
-- see zero rows once the policy exists:
|
||||
ALTER ROLE <runtime-role> SET app.scopes = '*';
|
||||
|
||||
-- If the runtime role OWNS the table, RLS is skipped for it unless forced:
|
||||
ALTER TABLE pages FORCE ROW LEVEL SECURITY;
|
||||
```
|
||||
|
||||
Safe to enable in either order: the env var without a policy is a no-op
|
||||
setting; a policy without the env var is enforced only via the role default.
|
||||
|
||||
**Honest caveat:** only read paths routed through the scoped helper carry a
|
||||
per-request scope binding — unwrapped paths (writes, admin/maintenance reads)
|
||||
run under the role default and are not backstopped per caller. This is layer 2;
|
||||
the app-layer source filters remain layer 1 and stay mandatory. Behavioral pins
|
||||
live in `test/postgres-engine-rls-scope.test.ts`.
|
||||
|
||||
## PGLiteEngine (v0.7, ships)
|
||||
|
||||
**Dependencies:** `@electric-sql/pglite` (v0.4.4+)
|
||||
@@ -221,39 +176,6 @@ live in `test/postgres-engine-rls-scope.test.ts`.
|
||||
|
||||
**Migration:** `gbrain migrate --to supabase` exports everything (pages, chunks, embeddings, links, tags, timeline) and imports into Supabase. `gbrain migrate --to pglite` goes the other direction. Bidirectional, lossless.
|
||||
|
||||
## JSONB writes: never double-encode (the #2339 trap)
|
||||
|
||||
Writing a JS value into a `jsonb` column has exactly two correct forms. Get this
|
||||
wrong and the write succeeds on PGLite but stores a **jsonb string scalar** on
|
||||
real Postgres — `col ->> 'k'` returns NULL, `jsonb_array_elements` throws, and a
|
||||
`jsonb_typeof = 'array'` CHECK rejects the row (this aborted every sync in #2339).
|
||||
|
||||
| Form | Verdict |
|
||||
|---|---|
|
||||
| Template tag: `` sql`... ${sql.json(obj)}` `` (postgres-engine only) | ✅ native jsonb serialization |
|
||||
| Positional raw call, raw object: `executeRawJsonb(engine, sql, scalars, [obj])` | ✅ object reaches the wire as jsonb |
|
||||
| Positional raw call, stringified: `executeRaw(\`... $N::text::jsonb\`, [JSON.stringify(x)])` | ✅ binds as text, the cast parses it |
|
||||
| Positional raw call, BARE cast: `executeRaw(\`... $N::jsonb\`, [JSON.stringify(x)])` | ❌ **double-encodes** under postgres.js `.unsafe()` |
|
||||
| Template literal interpolation: `` `... ${JSON.stringify(x)}::jsonb` `` | ❌ double-encodes |
|
||||
|
||||
**Why:** postgres.js `.unsafe(sql, params)` (the path behind `executeRaw` /
|
||||
`executeRawDirect`) binds a JS **string** as a text param. A bare `$N::jsonb`
|
||||
cast then wraps that already-JSON string into a jsonb scalar string instead of
|
||||
parsing it. Casting through `$N::text::jsonb` forces a text→jsonb parse.
|
||||
**PGLite's `db.query` parses text→jsonb natively, so it hides the bug** — which is
|
||||
why a regression only shows up on Postgres (and why the parity test must run there).
|
||||
|
||||
**Two CI guards enforce this, both wired into `scripts/check-jsonb-pattern.sh`:**
|
||||
- the template-tag grep (`${JSON.stringify(x)}::jsonb`), and
|
||||
- `scripts/check-jsonb-params.mjs`, an AST-lite scanner for the positional
|
||||
`$N::jsonb` + `JSON.stringify` form the grep misses. Sanctioned escapes:
|
||||
`$N::text::jsonb`, `$N::text[]`, `executeRawJsonb`, `sql.json`, or an inline
|
||||
`jsonb-guard-ok` comment.
|
||||
|
||||
The real backstop is `test/e2e/op-checkpoint-jsonb-parity.test.ts` +
|
||||
`test/e2e/jsonb-roundtrip.test.ts`, which round-trip writes through real Postgres
|
||||
and assert `jsonb_typeof` — the assertion PGLite cannot make.
|
||||
|
||||
## Adding a new engine
|
||||
|
||||
1. Create `src/core/<name>-engine.ts` implementing `BrainEngine`
|
||||
|
||||
@@ -111,38 +111,3 @@ gbrain models doctor # 1-token probe per configured model
|
||||
```
|
||||
|
||||
If anything's yellow, `gbrain doctor` names the fix command in the message. Most issues are missing API keys or stale schema (`gbrain upgrade --force-schema`).
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### PGLite crashes on macOS 26.x (Tahoe)
|
||||
|
||||
PGLite's embedded WASM engine is incompatible with macOS 26.x (Tahoe) on Apple Silicon. If `gbrain init --pglite` crashes during engine initialization, switch to native Homebrew PostgreSQL:
|
||||
|
||||
```bash
|
||||
# Install PostgreSQL + pgvector
|
||||
brew install postgresql@17
|
||||
brew services start postgresql@17
|
||||
createdb gbrain
|
||||
|
||||
# Build pgvector from source (required for vector search)
|
||||
cd /tmp && git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
|
||||
cd pgvector && make && make install
|
||||
psql gbrain -c "CREATE EXTENSION IF NOT EXISTS vector;"
|
||||
|
||||
# Point gbrain at your local Postgres
|
||||
cat > ~/.gbrain/config.json << 'EOF'
|
||||
{
|
||||
"engine": "postgres",
|
||||
"database_url": "postgresql://localhost:5432/gbrain",
|
||||
"schema_pack": "gbrain-base-v2"
|
||||
}
|
||||
EOF
|
||||
|
||||
# Run migrations and verify
|
||||
gbrain apply-migrations --yes
|
||||
gbrain doctor
|
||||
```
|
||||
|
||||
All 102 migrations run on first try. Once `gbrain doctor` shows green, the brain works identically to PGLite — same commands, same skills, same data model. The only difference is the storage backend.
|
||||
|
||||
> **Note:** This workaround is temporary. When the upstream WASM runtime fix ships (likely via a Bun update), `--pglite` will work on Tahoe again.
|
||||
|
||||
+8
-10
@@ -12,17 +12,15 @@ Before shipping (/ship) or reviewing (/review), always run the full test suite.
|
||||
Two equivalent paths:
|
||||
|
||||
**Path A — local CI gate (recommended, v0.23.1+):**
|
||||
- `bun run ci:local` runs the entire stack inside Docker: gitleaks (host),
|
||||
guards + typecheck, then 4-shard parallel unit + E2E against four pgvector
|
||||
containers plus a transaction-mode PgBouncer service (unit phase keeps
|
||||
`DATABASE_URL` unset; `--no-shard` for the legacy sequential flow). Stronger
|
||||
than PR CI's 2-file Tier 1 set; closer to what nightly Tier 1 catches. Spins
|
||||
up + tears down postgres automatically via `docker-compose.ci.yml`. Override
|
||||
the host port with `GBRAIN_CI_PG_PORT=5435 bun run ci:local` if 5434 collides.
|
||||
- `bun run ci:local` runs the entire stack inside Docker: gitleaks (host), unit
|
||||
tests with `DATABASE_URL` unset, and all 29 E2E files sequentially against a
|
||||
fresh pgvector container. Stronger than PR CI's 2-file Tier 1 set; closer to
|
||||
what nightly Tier 1 catches. Spins up + tears down postgres automatically via
|
||||
`docker-compose.ci.yml`. Override the host port with
|
||||
`GBRAIN_CI_PG_PORT=5435 bun run ci:local` if 5434 collides.
|
||||
- `bun run ci:local:diff` runs only the E2E files matched by the diff selector
|
||||
(`scripts/select-e2e.ts`), falling back to ALL E2E files on unmapped src/
|
||||
paths or schema/skills/package.json changes. Fast iteration during a focused
|
||||
branch.
|
||||
(`scripts/select-e2e.ts`), falling back to all 29 on unmapped src/ paths or
|
||||
schema/skills/package.json changes. Fast iteration during a focused branch.
|
||||
|
||||
**Path B — manual lifecycle (still supported):**
|
||||
- `bun test` — unit tests (no database required)
|
||||
|
||||
+10
-27
@@ -3,8 +3,6 @@
|
||||
On-demand reference (see CLAUDE.md Reference map). Current behavior + invariants
|
||||
only.
|
||||
|
||||
`test/e2e/serve-http-oauth.test.ts` additionally pins confidential POST/Basic revocation, public-client SDK fallthrough, malformed/mixed authentication rejection, cross-client isolation, unknown-token opacity, metadata auth methods, no-store responses, strict post-revoke `401`, and retryable backend `503` semantics.
|
||||
|
||||
### Test command tiers
|
||||
|
||||
Seven test command tiers, each with a clear scope:
|
||||
@@ -12,16 +10,16 @@ Seven test command tiers, each with a clear scope:
|
||||
| Command | What it runs | Wallclock | When to use |
|
||||
|---|---|---|---|
|
||||
| `bun run test` | Parallel unit-test fast loop. 8-shard fan-out via `scripts/run-unit-parallel.sh`, then a serial pass over `*.serial.test.ts`. Excludes `*.slow.test.ts` and `test/e2e/*`. No pre-checks, no typecheck. | ~85s on a Mac dev box (3650+ tests) | Inner edit loop. Default. |
|
||||
| `bun run verify` | CI's authoritative pre-test gate set, fanned out in parallel by `scripts/run-verify-parallel.sh`: the full `check:*` battery (~30 checks — privacy, jsonb, progress, source-id, test-isolation, wasm, …) plus `bun run typecheck`. The `CHECKS` array in that script is the single source of truth — CI literally calls `bun run verify` in a dedicated job. | ~16s (parallel; typecheck dominates) | Before pushing; before `/ship`. |
|
||||
| `bun run verify` | CI's authoritative pre-test gate set: `check:privacy && check:jsonb && check:progress && check:wasm && bun run typecheck`. The 4 checks `.github/workflows/test.yml` runs on shard 1 + typecheck. Single source of truth — CI literally calls `bun run verify`. | ~12s (wasm-compile dominates) | Before pushing; before `/ship`. |
|
||||
| `bun run test:full` | `verify && bun run test && bun run test:slow && [smart e2e]`. The local equivalent of "everything CI runs." Smart e2e: runs e2e only when `DATABASE_URL` is set; else loud skip notice to stderr. | ~3-5min depending on slow + e2e | Pre-merge sanity, before opening a PR. |
|
||||
| `bun run test:slow` | Just the `*.slow.test.ts` set (intentional cold-path correctness checks). | seconds-to-minutes | When touching slow-path code. |
|
||||
| `bun run test:serial` | Just the `*.serial.test.ts` set (cross-file-contention quarantine; one bun process per file for true module-registry isolation). | ~1s per quarantined file | Debugging a specific quarantined file. |
|
||||
| `bun run test:serial` | Just the `*.serial.test.ts` set (cross-file-contention quarantine; runs at `--max-concurrency=1`). | ~1s per quarantined file | Debugging a specific quarantined file. |
|
||||
| `bun run test:e2e` | Real Postgres E2E. Requires Docker + `DATABASE_URL`. Sequential. | ~5-10min | Pre-ship; nightly. |
|
||||
| `bun run check:all` | The historical pre-check scripts (22, chained sequentially in package.json). Overlaps `verify` heavily but is NOT a superset — `verify`'s `CHECKS` array in `scripts/run-verify-parallel.sh` (~30 entries incl. typecheck) is the authoritative gate; `check:all` keeps a few local-only extras (trailing-newline, exports-count, no-legacy-getconnection). | ~10s | Local-only sweep for the extras. |
|
||||
| `bun run check:all` | All 7 historical pre-checks (privacy + jsonb + progress + no-legacy-getconnection + trailing-newline + wasm + exports-count). Superset of `verify`. | ~10s | Local-only sweep. The 4 not in `verify` are nice-to-haves. |
|
||||
|
||||
### CI vs local: intentionally divergent file sets
|
||||
|
||||
- **CI matrix** (`.github/workflows/test.yml`) runs `scripts/test-shard.sh` across 10 matrix shards partitioned by weight-aware LPT bin-packing (`scripts/sharding.ts`) and INCLUDES `*.slow.test.ts` (the two outlier slow files run as dedicated jobs alongside the matrix). CI EXCLUDES `*.serial.test.ts` from the shards and runs them in a dedicated job via `bun run test:serial`, one bun process per file — keeping serial files out of the shard processes is what preserves the `mock.module` quarantine (a top-level mock in one file leaks into every other file sharing its process). `bun run verify` gets its own job too. CI is the ground truth for "did everything pass."
|
||||
- **CI matrix** (`.github/workflows/test.yml`) runs `scripts/test-shard.sh` 4-way, which uses FNV-1a hash bucketing and INCLUDES `*.slow.test.ts`. CI EXCLUDES `*.serial.test.ts` from the hash buckets and runs them on shard 1 via `bun run test:serial` at `--max-concurrency=1` — keeping serial files out of the hash buckets is what preserves the `mock.module` quarantine (top-level mocks in serial files would otherwise leak into the parallel files they share a shard process with). CI is the ground truth for "did everything pass."
|
||||
- **Local fast loop** (`scripts/run-unit-shard.sh` via the parallel wrapper) uses round-robin-by-index sharding and EXCLUDES `*.slow.test.ts` AND `*.serial.test.ts`. Local trades coverage for inner-loop speed; CI catches what local skips.
|
||||
|
||||
This divergence is intentional. Don't try to make them equal — the two scripts deliberately solve different problems. The regression test at `test/scripts/run-unit-shard.test.ts` pins what the local fast loop should and shouldn't include.
|
||||
@@ -41,7 +39,7 @@ If a shard wedges (per-shard `GBRAIN_TEST_SHARD_TIMEOUT` cap, default 600s), the
|
||||
|
||||
- `*.test.ts` → fast loop (parallel 8-shard fan-out).
|
||||
- `*.slow.test.ts` → run via `bun run test:slow` only (intentional cold-path tests; would dominate the fast loop's wallclock).
|
||||
- `*.serial.test.ts` → run via `bun run test:serial` after the parallel pass completes; one bun process per file (`--max-concurrency=1` within a shared process is not enough — the module registry still leaks `mock.module`). Quarantine for tests that share file-wide state and race when run alongside other files in the same `bun test` process. Several dozen files, discovered by the `*.serial.test.ts` glob — no list to maintain. Typical residents: `mock.module(...)` users (top-level mocks leak across files in a shard process, e.g. `test/embed.serial.test.ts`), env-coupled files (e.g. `test/brain-registry.serial.test.ts`), and process-lifecycle suites that assert on `process.exitCode` (e.g. `test/pglite-engine-disconnect.serial.test.ts`). **Do not put the parallelism back on a serial file unless you've fixed the contention root cause** (it just re-introduces the flake).
|
||||
- `*.serial.test.ts` → run via `bun run test:serial` after the parallel pass completes; uses `--max-concurrency=1`. Quarantine for tests that share file-wide state and race when run alongside other files in the same `bun test` process. Currently: `test/brain-registry.serial.test.ts`, `test/reconcile-links.serial.test.ts`, `test/core/cycle.serial.test.ts`, `test/embed.serial.test.ts` (the latter two use `mock.module(...)` which leaks across files in the shard process). **Do not put the parallelism back on a serial file unless you've fixed the contention root cause** (it just re-introduces the flake).
|
||||
- `test/e2e/*.test.ts` → real-Postgres E2E. Skipped when `DATABASE_URL` is unset.
|
||||
- `tests/heavy/*.sh` → ops-shape shell scripts. Cost minutes per run; NOT in default `bun test`. Run via `bun run test:heavy` or scheduled nightly via `.github/workflows/heavy-tests.yml`. Examples: pg_upgrade matrix (boot legacy brain → walk to head), RSS budget gate (measure peak worker RSS vs committed baseline), read-latency-under-sync (p50/p95/p99 under concurrent writer load), sync lock regression (N concurrent syncs assert 1 winner + N-1 lock-busy + zero leaked `gbrain_cycle_locks` rows). See `tests/heavy/README.md` for when to add a script here vs `*.slow.test.ts`. Files prefixed with `_` (e.g. `tests/heavy/_build_legacy_fixtures.sh`) are helpers/libs invoked by sibling tests — the runner skips them.
|
||||
- `test/fuzz/*.test.ts` → property-based fuzz harness. Pure-validator targets in `pure-validators.test.ts` are guarded by `scripts/check-fuzz-purity.sh` (in `bun run verify`), which `bun build --target=bun` bundles each target and greps the resulting bundle for banned transitive imports (`node:fs`, `node:child_process`, engine modules). Anything that fails the guard moves to `mixed-validators.test.ts` (still property-tested, but no purity guarantee) or `filesystem-validators.test.ts` (fs-backed, uses temp dirs). Fuzz tests run in the default `bun test` loop because they're fast (~3s for ~12 properties × 1000 runs each).
|
||||
@@ -113,7 +111,7 @@ Rename to `*.serial.test.ts` when:
|
||||
- The file is genuinely env-coupled (e.g. `gbrain-home-isolation.test.ts`, `claw-test-cli.test.ts`) — module-load env readers + ESM caching defeat dynamic-import-after-env tricks.
|
||||
- The file's tests intentionally share state across `it()` boundaries.
|
||||
|
||||
The quarantine has grown to dozens of files — treat it as debt: every addition needs a reason from the list above, and prefer fixing the contention root cause when one exists.
|
||||
Quarantine count cap: 10 (informational). Beyond that, push back on the design.
|
||||
|
||||
### Unit test inventory
|
||||
|
||||
@@ -125,15 +123,6 @@ Unit tests and what they cover:
|
||||
- `test/chunkers/recursive.test.ts` — chunking.
|
||||
- `test/parity.test.ts` — operations contract parity.
|
||||
- `test/cli.test.ts` — CLI structure.
|
||||
- `test/cli-finish-teardown.test.ts` — the #2084 teardown contract: `computeTeardownDeadlineMs` formula/floor/live-registry scaling + `GBRAIN_TEARDOWN_DEADLINE_MS` override (garbage/zero/negative values fall back to the formula); `finishCliTeardown` clean path (drain BEFORE disconnect, no exit, no warn), backstop on hung drain or disconnect (honors an errored op's exit code), throwing drain/disconnect warned + swallowed; the gbrain-owned verdict channel is immune to PGLite WASM `process.exitCode` writes; `flushThenExit` unit coverage with mocked streams (exits once after both stream callbacks, non-TTY aliveness grace, blocked-pipe guard, EPIPE-safe, `GBRAIN_FLUSH_GRACE_MS` override).
|
||||
- `test/flush-then-exit-harness.test.ts` — real spawned-Bun pipe semantics for `flushThenExit` (fixture: `test/fixtures/flush-then-exit-harness.ts`): a 4MB piped stdout payload arrives byte-complete with the exit code even with a late reader, small output survives exit with a concurrent reader, and the fence resolves promptly (wall time well under the guard + grace ceiling).
|
||||
- `test/cli-should-force-exit.test.ts` — `shouldForceExitAfterMain` daemon-survival gate: `serve` (stdio and `--http`) never force-exits, including with preceding global flags; op commands / empty / flag-only argv do; the #2084 case that space-separated global-flag VALUES can't fake a command (`--timeout 30s serve` resolves to the `serve` daemon, not a `30s` command).
|
||||
- `test/cli-exit-verdict-pin.test.ts` — #2084 structural class pin: greps `src/` so the NEXT raw `process.exitCode =` write fails CI (a raw write bypasses the gbrain-owned verdict channel and gets silently zeroed by the deliberate flush-exit — the bug that made doctor's FAIL path exit 0). Runtime variants live in `test/cli-finish-teardown.test.ts`; this is the review-time guard.
|
||||
- `test/cli-pipe-truncation.test.ts` — real-CLI pipe completeness (the #1959 incident class), implementation-agnostic: the actual CLI run the way agents run it (piped stdout) produces complete, parseable, byte-stable `--tools-json` output and exits deliberately, well under the teardown backstop. Synthetic flush-mechanism coverage stays in `test/flush-then-exit-harness.test.ts`.
|
||||
- `test/volunteer-context.test.ts` — push-based context core (#2095), hermetic in-memory PGLite: `parseWindow` lenient `user:`/`assistant:` parsing, multi-turn window extraction, confidence-gated volunteering (arm confidences, multi-turn/newest-turn boosts, `min_confidence` gate, max-pages cap), slug-only suppression, privacy (rationales are deterministic templates; synopses pass the takes/facts fence), and the approximate usage-stats join.
|
||||
- `test/watch-command.test.ts` — `gbrain watch` push transport (#2095): streaming loop, rolling window, session dedupe, `--json` JSONL shape, `channel: 'watch'` event logging, clean EOF return. Hermetic PGLite + injected line/write deps (no subprocess, no real stdin).
|
||||
- `test/watch-sigint.serial.test.ts` — `gbrain watch` SIGINT lifecycle against a real spawned CLI subprocess with a tmpdir brain. SERIAL: parallel unit shards flake on concurrent subprocess spawns (same rationale as `apply-migrations-pglite-spawn.serial.test.ts`).
|
||||
- `test/cli-format-volunteer.test.ts` — `formatResult`'s `volunteer_context` human rendering: pointer lines with confidence/arm/rationale, the empty-result message, the approximate stats summary.
|
||||
- `test/config.test.ts` — config redaction.
|
||||
- `test/files.test.ts` — MIME/hash.
|
||||
- `test/import-file.test.ts` — import pipeline.
|
||||
@@ -141,7 +130,7 @@ Unit tests and what they cover:
|
||||
- `test/file-migration.test.ts` — file migration.
|
||||
- `test/file-resolver.test.ts` — file resolution.
|
||||
- `test/import-resume.test.ts` — import checkpoints.
|
||||
- `test/migrate.test.ts` — migration: v8/v9 helper-btree-index SQL structural assertions; 1000-row wall-clock fixtures guarding the O(n²)→O(n log n) fix; v12/v13 SQL shape; `sqlFor` + `transaction:false` runner semantics; the `max_stalled DEFAULT 1` regression guard; v24 `sqlFor.pglite: ''` no-op assertion; v117 `context_volunteer_events` (named + idempotent entry, documented columns + both source-scoped indexes after `initSchema`, insert + 90-day `purgeStaleVolunteerEvents` round-trip).
|
||||
- `test/migrate.test.ts` — migration: v8/v9 helper-btree-index SQL structural assertions; 1000-row wall-clock fixtures guarding the O(n²)→O(n log n) fix; v12/v13 SQL shape; `sqlFor` + `transaction:false` runner semantics; the `max_stalled DEFAULT 1` regression guard; v24 `sqlFor.pglite: ''` no-op assertion.
|
||||
- `test/bootstrap.test.ts` — bootstrap contract: no-op on fresh install, idempotent across two `initSchema()` calls, no-op on modern brain that already has every probed column, full bootstrap path on a simulated legacy brain, fresh-install regression guard, legacy `links` shape coverage.
|
||||
- `test/schema-bootstrap-coverage.test.ts` — CI guard. `REQUIRED_BOOTSTRAP_COVERAGE` lists every forward reference in `PGLITE_SCHEMA_SQL`; the test fails loudly if `applyForwardReferenceBootstrap` skips one (extend both arrays when adding a column-with-index to the embedded schema blob). Also parses `src/core/migrate.ts` source text for every `ALTER TABLE ... ADD COLUMN` (top-level `sql:`, `sqlFor.{postgres,pglite}` overrides, AND handler-body `engine.runMigration(N, \`ALTER TABLE ...\`)`) and asserts each (table, column) pair is covered by the bootstrap OR by the schema blob's CREATE TABLE bodies — catching the column-only forward-reference class (e.g. `sources.archived`, `oauth_clients.source_id`) that a CREATE INDEX parser alone can't see. `parseBaseTableColumns` strips SQL line + block comments before identifying column names so commented-out lines don't hide adjacent columns.
|
||||
- `test/helpers/schema-diff.ts` + `test/helpers/schema-diff.test.ts` + `test/e2e/schema-drift.test.ts` — cross-engine schema parity gate. Helper exports pure `snapshotSchema(query)` / `diffSnapshots(pg, pglite, opts)` / `formatDiffForFailure(diff)` / `isCleanDiff(diff)` over a four-tuple per column (`data_type`, `udt_name`, `is_nullable`, `column_default`). E2E test spins up fresh PGLite + Postgres, runs `engine.initSchema()` on each, snapshots `information_schema.columns`, then diffs. 2-table allowlist (`files`, `file_migration_ledger`) — every other Postgres table must reach PGLite via `PGLITE_SCHEMA_SQL` or a migration's `sqlFor.pglite` branch. Sentinels for `oauth_clients`, `mcp_request_log`, `access_tokens`, `eval_candidates` give tighter blame messages. Skips without `DATABASE_URL`. Wired into `scripts/e2e-test-map.ts` so changes to `src/schema.sql`, `src/core/pglite-schema.ts`, or `src/core/migrate.ts` trigger it. The failure message names every drift with a paste-ready hint pointing at `src/core/pglite-schema.ts`.
|
||||
@@ -152,7 +141,7 @@ Unit tests and what they cover:
|
||||
- `test/yaml-lite.test.ts` — YAML parsing.
|
||||
- `test/check-update.test.ts` — version check + update CLI.
|
||||
- `test/pglite-engine.test.ts` — PGLite engine, all BrainEngine methods including `addLinksBatch` / `addTimelineEntriesBatch` (empty batch, missing optionals, within-batch dedup via ON CONFLICT, missing-slug rows dropped by JOIN, half-existing batch, batch of 100) plus `connect()` error-wrap assertion (original error nested, #223 link in message, lock released).
|
||||
- `test/links-timeline-jsonb-poison.test.ts` — gbrain#1861 PGLite half (always-on, no `DATABASE_URL`). Locks the `jsonb_to_recordset` batch-insert path for links/timeline/takes against free-text "poison" payloads (commas, quotes, backslashes, braces, em-dashes) and asserts NUL is stripped from free-text body fields but rejected in identity fields. gbrain#2011 adds lone-UTF-16-surrogate cases: every free-text field (link context; timeline summary/detail/source; take claim/source) well-forms to U+FFFD across batch + scalar write paths, while a surrogate in an identity field (slug) still fail-closed rejects the batch. The Postgres lane (`test/e2e/jsonb-batch-poison-postgres.test.ts`) is the one that actually reproduced the original crash.
|
||||
- `test/links-timeline-jsonb-poison.test.ts` — gbrain#1861 PGLite half (always-on, no `DATABASE_URL`). Locks the `jsonb_to_recordset` batch-insert path for links/timeline/takes against free-text "poison" payloads (commas, quotes, backslashes, braces, em-dashes) and asserts NUL is stripped from free-text body fields but rejected in identity fields. The Postgres lane (`test/e2e/jsonb-batch-poison-postgres.test.ts`) is the one that actually reproduced the original crash.
|
||||
- `test/engine-factory.test.ts` — engine factory + dynamic imports.
|
||||
- `test/integrations.test.ts` — recipe parsing, CLI routing, recipe validation.
|
||||
- `test/publish.test.ts` — content stripping, encryption, password generation, HTML output.
|
||||
@@ -223,16 +212,13 @@ E2E tests live in `test/e2e/` and run against real Postgres+pgvector (require `D
|
||||
- `bun run test:e2e` runs Tier 1 (mechanical, all operations, no API keys). Includes dedicated cases for the postgres-engine `addLinksBatch` / `addTimelineEntriesBatch` bind path — postgres-js's JSONB bind (`jsonb_to_recordset(($1::jsonb)->'rows')`) differs from PGLite's and gets its own coverage.
|
||||
- `test/e2e/search-quality.test.ts` — search quality against PGLite (no API keys, in-memory).
|
||||
- `test/e2e/graph-quality.test.ts` — knowledge graph pipeline (auto-link via put_page, reconciliation, traversePaths) against PGLite in-memory.
|
||||
- `test/e2e/jsonb-batch-poison-postgres.test.ts` — gbrain#1861 regression, the engine that actually crashed. Seeds free-text "poison" context (Zoom URL with `?pwd=`, commas, quotes, Windows backslash path, braces, em-dash) and asserts the links/timeline/takes batch writers no longer error with "malformed array literal"; also asserts NUL is stripped from free-text bodies (`context`/`summary`/`detail`/`claim`) and still rejected in identity fields. gbrain#2011 adds the lone-surrogate crash lock: a lone UTF-16 surrogate in free text (the value that aborted `extract --stale` with `22P02` on Supabase) well-forms to U+FFFD across batch + scalar paths (incl. timeline + take `source`), while a surrogate in an identity field still rejects the batch. `DATABASE_URL`-gated.
|
||||
- `test/e2e/jsonb-batch-poison-postgres.test.ts` — gbrain#1861 regression, the engine that actually crashed. Seeds free-text "poison" context (Zoom URL with `?pwd=`, commas, quotes, Windows backslash path, braces, em-dash) and asserts the links/timeline/takes batch writers no longer error with "malformed array literal"; also asserts NUL is stripped from free-text bodies (`context`/`summary`/`detail`/`claim`) and still rejected in identity fields. `DATABASE_URL`-gated.
|
||||
- `test/e2e/postgres-jsonb.test.ts` — round-trips all 5 JSONB write sites (`pages.frontmatter`, `raw_data.data`, `ingest_log.pages_updated`, `files.metadata`, `page_versions.frontmatter`) against real Postgres and asserts `jsonb_typeof='object'` plus `->>'key'` returns the expected scalar. Guards against the double-encode bug.
|
||||
- `test/e2e/integrity-batch.test.ts` — parity for `scanIntegrity`'s batch-load fast path vs sequential. Cases (dedup, hits, validate, topPages) seed a fixture and assert both paths return identical results. Dedup case uses raw SQL via `getConn().unsafe()` to seed a `(test-source-2, people/alice)` row alongside the default-source row, since `engine.putPage` doesn't take a `source_id`. Pins multi-source overcounting; the "multi-source duplicate slugs scan once" case expects both batch + sequential paths to report 2.
|
||||
- `test/e2e/jsonb-roundtrip.test.ts` — companion regression against the 4 doctor-scanned JSONB sites. Assertion-level overlap with `postgres-jsonb.test.ts` is intentional defense-in-depth: if doctor's scan surface drifts from the actual write surface, one of these tests catches it.
|
||||
- `test/e2e/sync.test.ts` — `--skip-failed` failure-loop test alongside happy-path tests: broken file → `performSync` returns `blocked_by_failures` with grouped breakdown → `performSync({skipFailed: true})` advances bookmark and returns `AcknowledgeResult` with code summary → second broken file → second cycle. Saves and restores the user's real `~/.gbrain/sync-failures.jsonl` so the test is hermetic. Asserts bookmark gating, JSONL state, dedup across paths, summary aggregation, and the literal doctor-rendering string format.
|
||||
- `test/e2e/upgrade.test.ts` — check-update against real GitHub API (network required).
|
||||
- `test/e2e/minions-shell-pglite.test.ts` — PGLite `--follow` inline shell-job path (in-memory, no `DATABASE_URL` required) — the path the minion-orchestrator skill documents for dev use.
|
||||
- `test/e2e/pglite-cli-exit.serial.test.ts` — real spawned-CLI exit behavior on PGLite (in-memory, no `DATABASE_URL`): read commands (`search`/`get`/`query`) exit 0 promptly; CLI_ONLY `capture` exits clean and frees the single-writer lock; the `#2084` describes pin every swept disconnect site — a failed op exits 1 with the error on stderr, and the dashboard, read-only-timeout, doctor, and `dream --dry-run` paths all exit with no force-exit banner.
|
||||
- `test/e2e/pgbouncer-teardown.test.ts` — PgBouncer TRANSACTION-mode teardown (#2084 / the #1972→#2015→#2084 class). Pins the bug CLASS, not timings: a CLI op against a txn-mode pooled URL exits 0 with intact stdout and does NOT ride the 10s hard-deadline backstop (the `engine.disconnect() did not return` banner is the smoking gun — pre-#2084 it printed on 100% of query-shaped ops). Gated by `GBRAIN_PGBOUNCER_URL` + `GBRAIN_PGBOUNCER_DIRECT_URL` (NOT `DATABASE_URL`) — set automatically by `bun run ci:local`'s `pgbouncer` compose service; skips gracefully elsewhere. Uses a DEDICATED `gbrain_pgbouncer` database so it never races the `gbrain_test` TRUNCATE fixtures.
|
||||
- `test/e2e/volunteer-context-postgres.test.ts` — `volunteer_context` on REAL Postgres (#2095; engine parity beyond the hermetic PGLite unit suite): resolution arms through the actual op handler, the fire-and-forget volunteer-event sink landing rows, the stats join, and the RLS pin that `context_volunteer_events` has ROW LEVEL SECURITY enabled (keeps the v35 auto-RLS event trigger honest for migration-created tables). `DATABASE_URL`-gated.
|
||||
- `test/e2e/openclaw-reference-compat.test.ts` — `check-resolvable` + `skillpack install` against a minimal AGENTS.md workspace fixture (`test/fixtures/openclaw-reference-minimal/`), regression guard for the OpenClaw deployment shape.
|
||||
- `test/e2e/search-swamp.test.ts` — reproduces the source-swamp case. Seeds a curated `originals/talks/article-outline-fat-code` page against two `<fork>/chat/` pages stuffed with the same multi-word phrase. Asserts the article wins keyword AND vector ranking, that `detail=high` lets the chat swamp re-surface, and that `source_id` passes through the two-stage CTE intact. PGLite in-memory.
|
||||
- `test/e2e/search-exclude.test.ts` — `test/` + `archive/` pages hidden by default, `include_slug_prefixes` opts back in, caller-supplied `exclude_slug_prefixes` adds to defaults. Both keyword and vector search paths.
|
||||
@@ -241,11 +227,8 @@ E2E tests live in `test/e2e/` and run against real Postgres+pgvector (require `D
|
||||
- `test/e2e/http-transport.test.ts` — `gbrain serve --http` end-to-end against real Postgres: bearer auth round-trip, `last_used_at` SQL-level debounce, `mcp_request_log` row insertion on success and auth_failed paths, `/health` DB-down → 503 (DB-probing health check), and the dispatch round-trip with a real operation. Skips without `DATABASE_URL`.
|
||||
- `test/e2e/serve-http-oauth.test.ts` — real-Postgres E2E against `gbrain serve --http` with full OAuth 2.1. Spawns a subprocess server, registers a client via the CLI, mints `client_credentials` tokens, exercises the `/mcp` JSON-RPC pipeline. Real DCR `/register` HTTP-level response-shape test (asserts `typeof body.client_id_issued_at === 'number'` over the wire, RFC 7591 §3.2.1); real CLI subprocess test for `revoke-client` (registers → mints token → revokes via `execSync` → asserts token rejected at `/mcp` → asserts re-run exits 1); server fixture flips on `--enable-dcr` so `/register` is reachable. **bun execSync env-inheritance contract:** bun's `execSync` does NOT inherit env mutations done via `process.env.X = ...`, only OS-level env from before bun started. helpers.ts loads `.env.testing` and sets `DATABASE_URL` via `process.env` mutation, which is invisible to subprocesses unless `env: { ...process.env }` is passed explicitly — every subprocess call in this file passes `env: { ...process.env }`. Reference fix for the same failure mode in sibling sync/cycle/dream/claw-test E2Es. `afterAll` cleanup is guarded on `clientId` (won't throw if `beforeAll` failed before registration); cleanup errors surface to stderr without throwing so real test failures aren't masked. Also covers the trust-boundary fix: an HTTP MCP `submit_job` for `name: "shell"` MUST reject with a permission error (request handler sets `remote: true` and `submit_job`'s protected-name guard fires), and the same guard rejects subagent submission. Skips without `DATABASE_URL`.
|
||||
- `test/e2e/sync-parallel.test.ts` — `DATABASE_URL`-gated. 60-file Postgres sync at concurrency=4 imports all + no connection leak (probes `pg_stat_activity` before/after to confirm worker engines disconnected). 120-file serial-vs-parallel benchmark prints `SYNC_PARALLEL_BENCH N files | serial=Xms | parallel(4)=Yms | speedup=Zx`. Asserts parallel ≤ serial × 1.5 (CI-noise tolerant; not a strict speedup gate).
|
||||
- `test/e2e/multi-source-bug-class.test.ts` — PGLite in-memory regression suite pinning every multi-source bug site: `listAllPageRefs` ordering by `(source_id, slug)`, `getPage` with sourceId picks the right `(source, slug)` row, `extract-takes` processes both overlapping `people/alice` rows independently, `listPages` filters correctly with `PageFilters.sourceId`, `addLinksBatch` with `from/to_source_id` targets the right rows, `validateSourceId` rejects path traversal, reverse-write disk layout uses `brainDir/.sources/<id>/<slug>.md` for non-default sources, `copyMigrationSources` lands source metadata before overlapping-slug pages. No `DATABASE_URL` needed. Wired into `scripts/e2e-test-map.ts` so changes to extract-takes / patterns / synthesize / embed / extract / migrate-engine auto-trigger it.
|
||||
- `test/e2e/migrate-engine-sources-postgres.test.ts` — `DATABASE_URL`-gated companion for `gbrain migrate --to`: migrates a PGLite brain carrying two non-default sources with overlapping slugs into real Postgres and asserts `copyMigrationSources` created every `sources` FK parent (config JSONB intact, not double-encoded) before any page write. Unit-level manifest identity (crash manifest resumes only against the SAME target; legacy engine-only manifests start fresh) is `test/migrate-engine-resume.test.ts`.
|
||||
- `test/e2e/facts-fence-reconcile-postgres.test.ts` — `DATABASE_URL`-gated round-trip for the escape-aware fence parser: renders a `## Facts` fence whose cells carry literal pipes, backslashes (Windows paths), and empty cells via `renderFactsTable`, runs the wipe-and-reinsert reconcile (`runExtractFacts`) on real Postgres, and asserts every cell survives byte-identically with no column shift.
|
||||
- `test/e2e/multi-source-bug-class.test.ts` — PGLite in-memory regression suite pinning every multi-source bug site: `listAllPageRefs` ordering by `(source_id, slug)`, `getPage` with sourceId picks the right `(source, slug)` row, `extract-takes` processes both overlapping `people/alice` rows independently, `listPages` filters correctly with `PageFilters.sourceId`, `addLinksBatch` with `from/to_source_id` targets the right rows, `validateSourceId` rejects path traversal, reverse-write disk layout uses `brainDir/.sources/<id>/<slug>.md` for non-default sources. No `DATABASE_URL` needed. Wired into `scripts/e2e-test-map.ts` so changes to extract-takes / patterns / synthesize / embed / extract / migrate-engine auto-trigger it.
|
||||
- `test/e2e/source-isolation-pglite.test.ts` — PGLite in-memory regression suite pinning the source-isolation seal at two layers. Engine layer: `searchKeyword` / `searchVector` / `searchKeywordChunks` / `listPages` / `getPage` / `traverseGraph` / `traversePaths` apply `sourceId` (scalar fast path) and `sourceIds` (array path) correctly across both engines. Op-handler layer: routes through `sourceScopeOpts(ctx)` so a `read+write`-scoped OAuth client bound to `--source dept-x` cannot see rows from neighboring sources via `search`, `query`, `list_pages`, `get_page`, or `find_experts`. Covers both `ctx.sourceId` (single-source clients) and `ctx.auth.allowedSources` (federated_read clients) precedence; federated array wins over scalar wins over nothing. No `DATABASE_URL` needed.
|
||||
- `test/e2e/think-source-isolation-pglite.test.ts` — PGLite in-memory suite pinning the `think` gather stage's source scope: seeds three sources with cross-source links and embedded takes, then asserts `runGather` under a federated `sourceIds` grant (and under a scalar `sourceId`) keeps every stream — hybrid retrieval, takes keyword + vector (`searchTakes`/`searchTakesVector`), and the `traversePaths` graph walk — inside the grant while still reaching authorized neighboring sources. No `DATABASE_URL` needed.
|
||||
- `test/e2e/skill-brain-first.test.ts` — doctor reports `skill_brain_first` check with structured issues; `--fix --dry-run` previews insertion without writing; `--fix` applies the canonical Convention callout idempotently; `brain_first: exempt` frontmatter resolves the warn; `brain_first_typo` surfaces a paste-ready hint; audit JSONL records `detected` / `resolved` / `fixed` transitions; stable brain emits 0 audit lines/run.
|
||||
- Tier 2 (`test/e2e/skills.test.ts`) requires OpenClaw + API keys, runs nightly in CI.
|
||||
- If `.env.testing` doesn't exist in this directory, check sibling worktrees: `find ../ -maxdepth 2 -name .env.testing -print -quit` and copy it here if found.
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -123,7 +123,6 @@ expansion (if enabled)
|
||||
hybrid search:
|
||||
├── vector (HNSW on chunk embeddings)
|
||||
├── keyword (BM25 via tsvector)
|
||||
├── relational (v0.42.34.0: typed-edge recall arm — relational queries only)
|
||||
├── source-aware re-rank (CASE in SQL)
|
||||
└── RRF fusion → top 30
|
||||
│
|
||||
|
||||
@@ -1,367 +0,0 @@
|
||||
# Community Ideas Ledger
|
||||
|
||||
> A diary of the **valuable ideas** surfaced by the community-PR wave, kept so that
|
||||
> good thinking survives even when the PR that carried it is closed. gbrain moves
|
||||
> fast and the maintainer's "cathedral" rewrites supersede most individual PRs —
|
||||
> but the *idea* behind a closed PR is often still worth something.
|
||||
>
|
||||
> **Bar for this file:** an idea only earns a line if it is (a) still live on
|
||||
> master and (b) genuinely valuable to gbrain users. **Graduating an idea to
|
||||
> `TODOS.md` is a higher bar still** — it must serve the North Star (next-Postgres-
|
||||
> for-memory: widest coverage, best-for-the-most-at-the-least) and be worth a
|
||||
> maintainer-owned implementation. Most lines here will never graduate. That's fine.
|
||||
>
|
||||
> Status legend: **OPEN** = PR still open as a real merge candidate · **CLOSED** =
|
||||
> PR closed, idea captured here · **HELD** = strategic, awaiting maintainer call.
|
||||
> Provenance is credited to the contributor; scrub real private-network names per
|
||||
> the repo privacy rule when anything here graduates to a public artifact.
|
||||
|
||||
_Generated from a full triage of the open-PR backlog (436 community PRs), 2026-06-07._
|
||||
|
||||
---
|
||||
|
||||
## 1. Internationalization — non-English brains are second-class
|
||||
|
||||
The single biggest coverage gap for "serve a billion people." Several independent
|
||||
contributors hit the same walls.
|
||||
|
||||
- **Configurable FTS language** (#580/#581/#582, @rafaelreis-r) — **OPEN, high.**
|
||||
Every `to_tsvector`/`tsquery` is hardcoded `'english'` (query side, trigger side,
|
||||
and no reindex path), so non-English brains run every search through the English
|
||||
stemmer. A coherent 3-PR set: `GBRAIN_FTS_LANGUAGE` config → migration recreating
|
||||
triggers with the chosen language → `gbrain reindex-search-vector` to change it
|
||||
post-install. **Strongest i18n candidate to graduate.**
|
||||
- **Full-Unicode slugs** (#782, @tamagodo-fu; #514 zh, @JimmyJiang67) — **HELD, high.**
|
||||
CJK slugs already work (`CJK_SLUG_CHARS`); generalize to all scripts (Cyrillic,
|
||||
Devanagari, Hangul, …) and widen the remaining ASCII-only validators so non-ASCII
|
||||
slugs flow end-to-end instead of being generated then rejected. #514 also carries a
|
||||
corpus-driven `relationships-zh.json` verb dictionary for `inferLinkType` — a
|
||||
reusable artifact for Chinese relationship typing.
|
||||
- **CJK entity extraction** (#1637, @alkalide) — **OPEN, high.** Mention extraction is
|
||||
ASCII-only (`TOKEN_RE`, `MIN_NAME_LENGTH=4`), so 2–3 char Chinese/Japanese/Korean
|
||||
names are invisible to the gazetteer (there's an in-code TODO acknowledging it).
|
||||
CJK detection + lower min-length + single-token pure-CJK titles + substring pass.
|
||||
|
||||
## 2. Reliability — the daily-driver failure modes
|
||||
|
||||
Recurring, production-observed failures. Many are tiny fixes with outsized impact;
|
||||
these are the densest source of real bugs in the whole backlog.
|
||||
|
||||
- **Embedding egress waste** (#347/#460, @notjbg) — **OPEN, high.** `getChunks` does
|
||||
`SELECT cc.*`, shipping the ~6KB pgvector embedding that `rowToChunk` immediately
|
||||
discards — ~19–22 GB/day egress on a busy Supabase brain. Enumerate the columns;
|
||||
add a CI guard. (#460 dup of #347.)
|
||||
- **Body-keyed embedding reuse** (#1424, @defenestrate2) — **OPEN, high.** Markdown
|
||||
import re-embeds byte-identical chunks that merely shifted position, turning a
|
||||
cosmetic edit into ~99K wasted re-embeds. Reuse by chunk-text hash like the code
|
||||
path already does; add `--force` + a no-hash sentinel.
|
||||
- **`embed --stale` full re-pull** (#775, @kyledeanjackson) — **CLOSED (partial on
|
||||
master), high.** Re-pulled all chunks every cycle (~3TB/mo egress); steady-state
|
||||
brains should do near-zero work. Master added a `countStaleChunks` early-exit;
|
||||
verify it fully closes this.
|
||||
- **Config round-trip storm** (#1694, @Omerbahari) — **OPEN, high.** A single query
|
||||
fires ~85 serial single-key config `SELECT`s — invisible on PGLite, ~85 network
|
||||
RTTs on a remote pooler. Batch + cache `getConfig` (`getConfigMany`).
|
||||
- **cgroup-aware worker sizing** (#1244, @tyler3k1) — **OPEN, high.** `defaultWorkers()`
|
||||
sizes from `os.totalmem()` (host RAM), so containerized installs (Railway/Fly/Render/
|
||||
Cloud Run/ECS) oversize the pool and get OOM-killed mid-import. Use
|
||||
`process.constrainedMemory()`.
|
||||
- **Linux memory-pressure throttle** (#556, @chengzehsu) — **OPEN, high.** `os.freemem()`
|
||||
is `MemFree` (excludes reclaimable cache), so healthy containers reject every batch
|
||||
job. Read `MemAvailable` from `/proc/meminfo`.
|
||||
- **propose_takes never caches empties** (#1218 @AdityaRajeshGadgil / #1760 @notjbg) —
|
||||
**OPEN, high.** A valid `[]` extractor result writes no cache row, so unchanged pages
|
||||
re-spend extractor tokens every ~5min cycle (57,885 calls/11 days observed). Sentinel
|
||||
row keyed on `(source_id, page_slug, content_hash, prompt_version)`.
|
||||
- **Prompt-cache opt-in on hot paths** (#1761, @notjbg) — **OPEN, high.** Only ~4.9% of
|
||||
input tokens hit the Anthropic prompt cache because the highest-volume cycle/extraction
|
||||
call sites don't set `cacheSystem:true` despite gateway support. One-line opt-ins.
|
||||
- **Autopilot reliability cluster** (#232 @ianderse, #464/#465 @notjbg, #289 @RyanAlberts,
|
||||
#477 @vinsew, #1935/#1936 @mdcruz88, #1906/#1891 @rayers/@jalagrange) — **OPEN, high.**
|
||||
A family of distinct live bugs: argless `engine.connect()` wipes saved config and
|
||||
crash-loops under launchd; `cwd=/` wrappers miss `brain/.env`; mtime-only lock probing
|
||||
blocks respawn for 10min after OOM; no backoff on the 5-failure suicide cap;
|
||||
disconnect-before-connect `reconnect()` bricks the engine on a transient blip; config
|
||||
accessors lack the retry wrapper. **Pick the best fix per layer and land as a wave.**
|
||||
- **lint `--fix` corrupts mid-doc fences** (#1417 @trinh-macbook, #1597 @chungty) —
|
||||
**OPEN, high.** Detector/fixer regex disagree, so `lint --fix` strips the closing fence
|
||||
of mid-document ```` ```markdown ```` blocks and autopilot re-corrupts the page every
|
||||
cycle. Only unwrap whole-page fences.
|
||||
- **backlinks worker defaults to `fix`** (#1853 @choomz; #1027 @sliday; #495 @23salus) —
|
||||
**OPEN, high.** Empty-payload backlinks jobs default to `action='fix'`, silently
|
||||
rewriting tracked markdown ("Referenced in" bullets) on every sync→embed→backlinks
|
||||
chain (129 files/day in the wild). Default to `check`; require explicit opt-in. Also
|
||||
fixes a duplicate-line accumulation bug.
|
||||
- **`DATABASE_URL` hijack** (#1884, @awilkinson) — **OPEN, high.** A co-located app's
|
||||
generic `DATABASE_URL` silently overrides the configured brain (wrong DB, or
|
||||
auto-migrates it). Fix precedence: `GBRAIN_DATABASE_URL` > config.json > `DATABASE_URL`.
|
||||
- **Engine-switch strips config** (#1088, @samchaudhary) — **OPEN, high.** `migrate --to`
|
||||
rewrites config to just `{engine,url}`, dropping `embedding_model`/`dimensions`/keys;
|
||||
migration "succeeds" but new embeds break.
|
||||
- **Re-init silently corrupts the brain** (#1060, @vincedk-alt) — **OPEN, high.** Flag-less
|
||||
re-init ignores persisted `embedding_model`/`dimensions` and writes a wrong-shape
|
||||
OpenAI-1536 brain before the dim-check catches it.
|
||||
- **IPv6-only direct URL** (#1006, @diazMelgarejo) — **OPEN, high.** `deriveDirectUrl`
|
||||
turns a Session-Pooler URL into an IPv6-only host, ECONNREFUSED on IPv4-only networks
|
||||
(the majority). Return null for pooler URLs.
|
||||
- **HOME-isolation in tests** (#205/#517/#534 @orendi84, #434 @lloydarmbrust) — **OPEN,
|
||||
high.** The E2E suite spawns `gbrain init/import` against the developer's real
|
||||
`~/.gbrain/config.json`, clobbering their live DB URL+keys. Isolate HOME to a tmpdir.
|
||||
*(A footgun that bites contributors of this very repo.)*
|
||||
- **dim-aware embed write target** (#1263, @DmitryBMsk) — **OPEN, high.** `upsertChunks`
|
||||
always writes the legacy `embedding vector(1536)` column, so brains on an alternate
|
||||
column (`embedding_ze halfvec(2560)`) fail with dim-mismatch on every write.
|
||||
- **Oversized chunks silently unembedded** (#1675, @lubos-buracinsky) — **OPEN, high.**
|
||||
The code chunker emits giant literals/template strings whole; the embedder rejects
|
||||
them and they vanish from semantic search. Cap chunk size so they stay embeddable.
|
||||
- **Token-vs-char truncation** (#557 @chengzehsu, #990 @mgunnin, #1180 @kkroo,
|
||||
#1281 @mmekkaoui, #1947 @100menotu001) — **OPEN, high.** The embed path truncates by
|
||||
chars (`MAX_CHARS`) not tokens, so dense pages still exceed the 8192/300K-token ceiling
|
||||
and loop forever on HTTP 400 with `embedded_at` never cleared; `isTokenLimitError`
|
||||
misses OpenAI's real error string; llama-server's 32-input limit isn't capped; and
|
||||
`--catch-up`'s unbounded budget overflows the 32-bit `setTimeout` and aborts after one
|
||||
batch. A "make embedding backfills never silently wedge" cluster.
|
||||
|
||||
## 3. Search & retrieval quality
|
||||
|
||||
- **Keyword search ignores page titles** (#1646, @jeades) — **OPEN, high.** `searchKeyword`
|
||||
ranks only chunk `search_vector`, never `pages.search_vector` (weight-A titles), so an
|
||||
exact-title `gbrain search` returns nothing while `query` finds it. High-impact, tiny.
|
||||
- **`code-def` misses most OO symbols** (#1628, @rayers) — **OPEN, high.** `DEF_TYPES`
|
||||
omits method/constructor/field/struct/protocol, so `code-def` returns 0 for most
|
||||
object-oriented code. Root-cause fix in `normalizeSymbolType` + `DEF_TYPES`.
|
||||
(Prefer over #1701's fallback-only approach.)
|
||||
- **doc-comment column is wired but dead** (#520, @Evode-Manirahari) — **OPEN, high.** FTS
|
||||
weights `content_chunks.doc_comment` above chunk text but the column is never populated.
|
||||
Extract JSDoc/docstrings per symbol via AST and thread through import.
|
||||
- **autocut weak-top collapse** (#1863, @rayers) — **OPEN, high.** The fresh autocut
|
||||
feature (#1682) normalizes the rerank gap by the top score, so a weak top (0.317→1.0)
|
||||
looks like a confident cliff and rare cross-source queries collapse to 1 result. Add a
|
||||
`minTopScore` floor.
|
||||
- **Graph-hop wikilink rerank** (#717, @gwanghoon91) — **HELD, high.** Zero-token
|
||||
score-shapers (graph-hop wikilink rerank + query-token disambiguation) claimed
|
||||
+2.6/+2.8pt P@5/R@5 on BrainBench. Worth re-evaluating against the new retrieval
|
||||
cathedral's ranker rather than merging the old diff.
|
||||
- **Effective-date time filters** (#1706, @mvanhorn) — **OPEN, med.** `since`/`until`
|
||||
filter on `updated_at`, so content dated to the past but edited recently is mis-filtered;
|
||||
filter on `COALESCE(effective_date, updated_at, created_at)`.
|
||||
|
||||
## 4. Extraction & the knowledge graph
|
||||
|
||||
- **Obsidian wikilink → typed graph edges** (#87 @franmaranchello; alias/title/basename
|
||||
fallback #1188 @rwbaker) — **OPEN/HELD, high.** `[[wikilinks]]`/`![[embeds]]` are
|
||||
invisible to the graph. Materialize them as typed edges with alias (frontmatter
|
||||
`aliases:`), first-H1-title, and basename fallback resolution (path-equality-only gives
|
||||
~5.5% edge recall on real vaults). Master shipped global-basename (#1388); the alias/
|
||||
title fallbacks are the still-novel part.
|
||||
- **Schema-pack-aware link extraction** (#1547, @billy-armstrong) — **OPEN, high.** The
|
||||
link extractor's `DIR_PATTERN` is a frozen 16-prefix const that ignores pack-declared
|
||||
`path_prefixes`, so default-pack installs silently lose wikilinks to `person/`,
|
||||
`writing/`, `wiki/*`. Resolve prefixes from the active pack.
|
||||
- **DB-source extraction** (#1539, @afshaker) — **OPEN, high.** The cycle's extract phase
|
||||
only walks the filesystem, so DB-resident pages (imported transcripts, remote-DB brains)
|
||||
never get links/timeline and `brain_score` is capped. Thread `source:'db'`.
|
||||
- **source_id threaded through fs-walk extract** (#1719, @seungsu-kr) — **OPEN, high.**
|
||||
fs-walk extractors omit `source_id`, defaulting to `'default'`, so the `pages` INNER JOIN
|
||||
drops every row on non-default-source brains — silent 0 inserted.
|
||||
- **extract `--stale` permanent-lag loop** (#1791, @Nazim22) — **OPEN, high.** Pages last
|
||||
edited before the link-extractor version bump get stamped below the version threshold and
|
||||
re-flag every run (~97% pages permanently "stale"). Stamp `GREATEST(updated_at, versionTs)`.
|
||||
- **Plain-text NER for auto-link** (#1565, @donogeme) — **HELD, med.** Plain mentions of
|
||||
people (no `[[wikilink]]`) never become edges. The opt-in idea is right; the shipped
|
||||
implementation (capitalized-bigram regex, Western-names-only) is too crude — needs a
|
||||
real NER pass to clear the graph-integrity bar.
|
||||
|
||||
## 5. Providers & the gateway
|
||||
|
||||
The AI-gateway + recipes + `user_provided_models` system already absorbed ~40
|
||||
per-vendor embedding PRs (Ollama, Gemini, Azure, DashScope, DeepSeek, Zhipu, E5,
|
||||
bge-m3, Copilot, Composio, Kimi, LM Studio, Mistral, Hunyuan, MiniMax…). The
|
||||
*residue* worth keeping:
|
||||
|
||||
- **litellm proxy unusable for chat** (#1953 @miroslavb, #1938 @BKF-Gitty) — **OPEN, high.**
|
||||
The `litellm-proxy` recipe declares only an embedding touchpoint (no chat), so
|
||||
`chat_model=litellm:*` fails validation and `think` degrades to a misleading "set
|
||||
ANTHROPIC_API_KEY"; and `build-gateway-config` never folds `litellm/openrouter/together`
|
||||
keys, so configured proxy auth goes out unauthenticated. Plus user-provided custom-dim
|
||||
embeddings are double-false-rejected in preflight. **The general-OpenAI-compat-proxy
|
||||
story.**
|
||||
- **Matryoshka dims threading** (#1072 @mgandal, #1240 @mike7seven) — **OPEN, high.**
|
||||
Qwen3-Embedding returns its native dim (2560/4096) not the requested one because
|
||||
`dimensions:N` isn't threaded for the openai-compat path, hard-failing a 1536-dim brain.
|
||||
- **"Freeze provider at init, clear vectors on dim change"** (#100/#172, @niallobrien/
|
||||
@nbzy1995) — **CLOSED, med.** A safety insight worth keeping even though the provider
|
||||
PRs are superseded: persist+freeze the brain's provider/dim at init so a later env change
|
||||
can't silently corrupt the vector space; clear stale embeddings on an intentional change.
|
||||
- **China-region provider coverage** (#59 @Magicray1217, #1071 @AzeWZ) — **CLOSED, med.**
|
||||
Make DashScope/DeepSeek/Zhipu first-class recipes that honor `provider_base_urls` (the
|
||||
China-region endpoints) and provider batch limits — on-mission for global coverage.
|
||||
- **Amazon Bedrock native** (#1826, @naterchrdsn) / **Jina asymmetric retrieval**
|
||||
(#1930, @Whamp) — **HELD, high/med.** The maintainer pattern prefers the universal
|
||||
litellm-proxy over per-vendor native recipes, but Bedrock (AWS IAM credential chain) and
|
||||
Jina's asymmetric `input_type=document|query` are distinct enough to warrant a call.
|
||||
- **Local-first chat parity** (#1854/#1855/#1858 @starm2010, #1423 @pabloglzg,
|
||||
#1618 @punksterlabs) — **OPEN, high.** `FREE_LOCAL_CHAT_PROVIDERS` doesn't exist (only
|
||||
embed), brainstorm/cycle/takes hardcode `anthropic:claude-sonnet-4-6`, and the
|
||||
openai-compat `generateObject` path silently fails on providers that reject
|
||||
`json_schema`. The "run gbrain fully local" cluster.
|
||||
- **OpenRouter config key** (#1714 @tmchow), **OAuth bearer for AI providers**
|
||||
(#1312 @pabloglzg), **API-key files** (#570 @shawnduggan) — **OPEN, med.** Credential
|
||||
ergonomics: config-file key (not just env), externally-minted bearer tokens, and
|
||||
`OPENAI_API_KEY_FILE` so OAuth harnesses don't inherit a raw key in `process.env`.
|
||||
|
||||
## 6. Auth, federation & access control (security-adjacent)
|
||||
|
||||
These cluster into a real theme: **runtime access control for remote/multi-tenant MCP
|
||||
beyond prompt discipline.** Several are live security gaps (see the security list in the
|
||||
triage report) and should be treated as a coordinated design, not piecemeal merges.
|
||||
|
||||
- **Clamp remote source overrides** (#1372, @jlfetter1) — **OPEN, high, SECURITY.** A
|
||||
remote MCP caller can pass `source_id` (or `__all__`) to `query`/`get_page` to read
|
||||
sources outside their OAuth `allowedSources` — the param bypasses `sourceScopeOpts`
|
||||
(CWE-285). Clamp to token claims, fail-closed. **#1394 (get_page source_id) must land
|
||||
*with* this clamp, not before it.**
|
||||
- **Read-side prefix/federation enforcement** (#1860 @choomz, #1790 @colin-atlas,
|
||||
#470 @AdityaRajeshGadgil, #1508 @tim404x) — **OPEN, high.** `bound_slug_prefixes` is
|
||||
enforced on write but not read; exact `get_page` uses scalar `ctx.sourceId` while fuzzy
|
||||
uses the federation ladder; unqualified search can scan isolated `--no-federated` sources.
|
||||
Unify on one fail-closed visibility predicate across every read surface.
|
||||
- **Per-OIDC-user access tiers** (#789, @0x471) — **HELD, high, SECURITY.** Map verified
|
||||
OIDC end-users to `oauth_clients.access_tier` dispatch gates + shape filters — real
|
||||
runtime access control. Pairs with multi-agent MCP hardening (#1316, @chipoto69, HELD).
|
||||
- **Federated-read management CLI + admin UI** (#1592/#1601 @bitak1, #1558 @flamerged) —
|
||||
**OPEN, high.** No CLI/UI to inspect or change a client's `federated_read` scope (raw
|
||||
SQL only today). Atomic `array_append`/`array_remove` SQL to avoid read-modify-write
|
||||
races, plus an admin Sources tab.
|
||||
- **Pre-registration flow flags** (#894, @panda850819) — **OPEN, high, SECURITY.**
|
||||
`register-client` hardcodes `redirect_uris=[]`, making the SECURITY.md-recommended
|
||||
pre-registration (DCR-off) flow unusable for Claude.ai/ChatGPT connectors.
|
||||
- **RFC 9728 `resource_metadata`** (#1410, @rayers) — **OPEN, high.** HTTP MCP 401s omit
|
||||
the `resource_metadata` param the MCP auth spec + RFC 9728 require, so claude.ai/Cursor
|
||||
can't discover the auth server and never start OAuth.
|
||||
- **Server-enforced memory groups** (#1497, @oldmate99) — **HELD, med.** Audience-based
|
||||
read/write via `memory_groups` + client-to-group assignment — strategic for hosted
|
||||
multi-tenant, but overlaps the existing source-isolation model; a design call.
|
||||
|
||||
## 7. Security hardening (must not be lost)
|
||||
|
||||
- **Command injection in transcription** (#245, @aliceagent) — **OPEN, high, SECURITY.**
|
||||
`transcription.ts` shell-interpolates an agent-controlled `audioPath` into `execSync`
|
||||
ffprobe/ffmpeg/`rm -rf`. **Confirmed still present on master.** Switch to
|
||||
`execFileSync` arg arrays + `fs.rmSync`.
|
||||
- **Dotfile / skills-dir confinement** (#418/#419, @garagon) — **OPEN, high, SECURITY.**
|
||||
`.gbrain-source` walk-up trusts any ancestor dotfile (source hijack on shared hosts);
|
||||
`resolveWorkspaceSkillsDir` never canonicalizes (symlink escape). `lstat` ownership/
|
||||
symlink/world-writable checks + realpath containment.
|
||||
- **Destructive reclone gate** (#1705, @mvanhorn) — **OPEN, high, SECURITY.**
|
||||
`recloneIfMissing` does `rm`+rename over `src.local_path` without verifying it's
|
||||
gbrain-managed, so a re-pointed source can wipe a user's working tree. Gate behind
|
||||
`isManagedRecloneTarget()` + reject `..`. *(The maintainer's own #1960 is the canonical
|
||||
landing for this class — cross-check.)*
|
||||
- **CORS preflight asymmetry** (#983, @yashkot007) — **OPEN, high, SECURITY.** Preflight
|
||||
returns the full method/header surface unconditionally while the actual-request path
|
||||
gates on the allowlist — leaks allowed surface to non-allowlisted origins.
|
||||
- **jsonb double-encode corruption** (#1584 @warkcod, #597 @vinsew) — **OPEN, high,
|
||||
SECURITY/integrity.** Source-config and subagent writers `JSON.stringify` into a
|
||||
`::jsonb` cast — the exact postgres.js trap CLAUDE.md forbids; corrupts source config
|
||||
(freshness/autopilot) and breaks dream synthesize slug-collection on real Postgres.
|
||||
|
||||
## 8. Developer experience & platform reach
|
||||
|
||||
- **Windows / CRLF portability** (#1294 @xwang4-svg, #1149 @samporter-31, #1554 @Sanjays2402,
|
||||
#1396 @xuezhaolan) — **OPEN, high.** CRLF breaks frontmatter + skill-trigger parsing
|
||||
(CI is Ubuntu-only so it never surfaces), `/dev/stdin` doesn't exist, a POSIX postinstall
|
||||
one-liner hard-fails `bun install`, backslash bundle keys. A coordinated "first-class
|
||||
Windows" pass. *(A working Windows binary + CI target #180/#181 is the prerequisite for
|
||||
the full story.)*
|
||||
- **`.gbrainignore` / per-repo exclusion** (#1483 @eepaul; repo-local code filters
|
||||
#1011 @AndrewLauder; `--respect-gitignore` #1159 @jetsetterfl) — **OPEN, high.** Sync
|
||||
indexes every file with no ignore mechanism (`data/`, `*.parquet`, fixtures, vendored
|
||||
trees), bloating DB + embedding cost. gitignore-parity `.gbrainignore` + per-source
|
||||
`excludePatterns`. *(See also the maintainer's walker-prune work; #1942 prunes
|
||||
vendor/dist/build.)*
|
||||
- **Monorepo sub-path sources** (#774, @jeremyknows) — **HELD, high.** `--src-subpath`
|
||||
(split repo into git-root + logical-source axes) + `--exclude` so one repo can hold N
|
||||
sources at subdirs.
|
||||
- **MCP tool filtering** (#747, @joelwp) — **OPEN, high.** MCP advertises all ~51 ops to
|
||||
every consumer (~10K tokens of schemas, tool confusion); `GBRAIN_EXPOSED_TOOLS` filters
|
||||
the advertised surface.
|
||||
- **Install-method detection for upgrade** (#538, @brucek) — **OPEN, high.** The README's
|
||||
own recommended git-clone+bun-link install detects as `unknown`, so `gbrain upgrade`
|
||||
offers three dead ends including a wrong npm package.
|
||||
- **Runtime subagent defs** (#1282, @dcarolan1) — **OPEN, high.** The plugin loader
|
||||
validates `SubagentDefinition[]` at startup but the handler never reads
|
||||
`data.subagent_def`, so the persisted field is dead at runtime — callers must re-embed
|
||||
the full system body in every job.
|
||||
- **macOS Tahoe PGLite workaround** (#1671, @roysaurav) — **HELD, med.** PGLite's WASM
|
||||
engine crashes on macOS 26 (Apple Silicon); document the native Homebrew Postgres+pgvector
|
||||
fallback. Reader-valuable until the WASM crash is fixed upstream.
|
||||
|
||||
## 9. Capabilities & integrations (strategic — maintainer call)
|
||||
|
||||
These are net-new surfaces held for a product decision, not auto-closed.
|
||||
|
||||
- **Alternative engines** — SQLite/`bun:sqlite`+FTS5 single-file backend (#291, @mvanhorn)
|
||||
and Neo4j GraphBrain REST backend (#594, @pkyanam). Both conflict with the two-engine
|
||||
lockstep invariant and the Postgres-for-memory North Star, but the *zero-WASM single-file*
|
||||
install story (SQLite) is strategically interesting. **HELD.**
|
||||
- **Page versioning / soft-delete / read audit** (#573, @cropsgg) — **HELD, high.** Snapshots
|
||||
with provenance, soft-delete tombstones + hard purge, read-path audit treating edits as
|
||||
derivative works. Ambitious cathedral-scope; maintainer-owned territory.
|
||||
- **Configurable embedding dimension** (#1051, @vincedk-alt) — **HELD, high.** `schema.sql`
|
||||
hardcodes `vector(1536)`; read `embedding_dimensions` from config (default 1536). The
|
||||
canonical fix that dozens of local-provider PRs hack around. *(Pairs with #1263.)*
|
||||
- **Transcribe skill** (#1449, @RyanAlberts) — **OPEN, high.** Implements the empty
|
||||
video/audio branch of `media-ingest` (YouTube captions fast path + yt-dlp/whisper
|
||||
fallback), $0 by default. A genuine capability gap.
|
||||
- **iPhone backup importer** (#1733, @H4RR1SON) — **HELD, med.** Local-CLI-only importer
|
||||
for decrypted iPhone backups (contacts→person pages, iMessage→conversation pages); zero
|
||||
network, thin-client refused.
|
||||
- **Compounding dream phase** (#509, @durang) — **HELD, high.** An LLM "7th phase" that
|
||||
*creates* structure (orphan-mention people, knowledge gaps, concept-dup at cosine>0.92,
|
||||
decay, incomplete pages) vs the deterministic phases. Overlaps `enrich --thin`.
|
||||
- **Codex-OAuth for dream** (#977, @barronlroth) / **dream gateway + `migrate-embedding-dim`**
|
||||
(#1013, @cxbitz) — **HELD, high.** OAuth-backed chat for synthesis; a command to resize
|
||||
the vector schema + clear incompatible embeddings.
|
||||
- **Voice-extraction skill** (#300, @harjclaw) — **CLOSED, med.** Mine the user's outbound-
|
||||
email corpus already in the brain to build a queryable writing-voice profile so agents
|
||||
draft in the user's voice. Overlaps soul-audit.
|
||||
- **MCP put_page parity + DB→markdown reconciliation** (#438, @rayzhux) — **HELD, high.**
|
||||
A frontmatter-only safe auto-link mode for remote callers + `GBRAIN_BRAIN_ROOT` to render
|
||||
remote writes back to markdown so MCP writes reach the git source-of-truth. Touches the
|
||||
remote trust boundary — a design proposal, not a merge.
|
||||
- **Recipe discovery convention** (#1279, @ialmeida-jera) — **OPEN, med.** `~/.gbrain/recipes/`
|
||||
auto-discovery + `--external-dir`, loaded untrusted to keep the command-spawn boundary.
|
||||
- **Destructive-op audit trail + audit-factory** (#1069/#1070, @vincedk-alt) — **HELD, med.**
|
||||
Rotating JSONL forensic trail for hard-deletes + a shared `createAuditLogger` factory.
|
||||
|
||||
## 10. Doctor & brain-health observability
|
||||
|
||||
- **Queue dead-job visibility** (#1185, @ethanbeard) — **OPEN, high.** A collector can
|
||||
heartbeat green while all its jobs die in the worker (3561 dead in the wild) and doctor
|
||||
has zero view into the minions queue. Add a cross-cutting `[queue]` dead-jobs check.
|
||||
- **Orphan-metric alignment** (#1107 @colin477, #915 @xaviroblessarries, #1202 @rwbaker) —
|
||||
**OPEN, high.** `get_health` counts ingestion-by-design (`daily/`, briefings), soft-deleted,
|
||||
and hub pages as orphans, distorting `brain_score`; CLI `find_orphans` uses a *different*
|
||||
predicate than `getHealth`. Unify on one islanded predicate with sensible exclusions.
|
||||
- **doctor check-name registry drift** (#1839, @mvanhorn) — **OPEN, med.** Several emitted
|
||||
checks aren't registered in `doctor-categories`, printing `unknown check name` every run;
|
||||
the drift guard only scanned `doctor.ts`, missing `onboard/checks.ts` emitters.
|
||||
- **Honest stale-lock hint** (#1553, @Sanjays2402) — **OPEN, med.** doctor always says
|
||||
`gbrain sync --break-lock`, which silently no-ops on `gbrain-cycle` locks.
|
||||
|
||||
---
|
||||
|
||||
## Cross-cutting observations for the maintainer
|
||||
|
||||
- **The same bug was filed many times.** `extract_facts.entity_hints` missing an `items`
|
||||
schema came in ≥5 times (#812/#832/#847/#863/…, already fixed); the Postgres-singleton
|
||||
disconnect class a dozen+ times; sync no-op freshness, slug-casing, and the embedding-
|
||||
preflight false-reject each 5–15 times. A short "already fixed / known" note in the
|
||||
release notes or a CONTRIBUTING "before you file" list would cut the re-file rate.
|
||||
- **The recipe system is working as a pressure valve** — it correctly absorbed ~40 vendor
|
||||
PRs into config rather than code. The remaining provider asks are about *capabilities*
|
||||
the recipe schema doesn't yet express (asymmetric `input_type`, Matryoshka dims, per-item
|
||||
RPM caps, alternative credential groups), not new vendors.
|
||||
- **i18n (§1) and local-first chat (§5) are the two biggest "serve a billion" coverage
|
||||
gaps** the community is repeatedly hitting and the best candidates to graduate to TODOs.
|
||||
@@ -43,8 +43,8 @@ genuinely has to change.
|
||||
Switching dimensions requires:
|
||||
|
||||
1. Dropping the HNSW vector index (pgvector won't survive an `ALTER COLUMN TYPE`).
|
||||
2. Wiping every existing embedding (the old vectors are unusable in the new space — and pgvector refuses to cast them across dimensions, so this must happen before the alter).
|
||||
3. Altering the column type (Postgres only — PGLite cannot do this).
|
||||
2. Altering the column type (Postgres only — PGLite cannot do this).
|
||||
3. Wiping every existing embedding (the old vectors are unusable in the new space).
|
||||
4. Re-embedding the entire corpus (can take hours on a 50K-page brain and costs $1-100 in API calls depending on model).
|
||||
5. Conditionally recreating the index (HNSW supports up to 2000 dimensions per pgvector; above that you must use exact scans).
|
||||
|
||||
@@ -115,17 +115,12 @@ BEGIN;
|
||||
-- 1. Drop the HNSW index. It can't survive the column type change.
|
||||
DROP INDEX IF EXISTS idx_chunks_embedding;
|
||||
|
||||
-- 2. Clear stale embeddings FIRST. This must happen BEFORE the column
|
||||
-- alter: pgvector refuses to cast existing vectors across dimensions
|
||||
-- ("expected <NEW_DIMS> dimensions, not <OLD_DIMS>"), so altering a
|
||||
-- column that still holds old-width vectors aborts the transaction.
|
||||
-- NULLs cast fine. (The old vectors are unusable in the new space
|
||||
-- anyway — this is the wipe step from the rationale above.)
|
||||
UPDATE content_chunks SET embedding = NULL, embedded_at = NULL;
|
||||
|
||||
-- 3. Alter the column type (all rows are NULL now, so the cast succeeds).
|
||||
-- 2. Alter the column type.
|
||||
ALTER TABLE content_chunks ALTER COLUMN embedding TYPE vector(<NEW_DIMS>);
|
||||
|
||||
-- 3. Clear stale embeddings so they don't survive into the new space.
|
||||
UPDATE content_chunks SET embedding = NULL, embedded_at = NULL;
|
||||
|
||||
-- 4. Recreate the HNSW index ONLY IF dims <= 2000. Above that, leave it
|
||||
-- indexless and rely on exact scans (gbrain searchVector handles this
|
||||
-- automatically — search just gets slower, not broken).
|
||||
|
||||
@@ -131,16 +131,6 @@ hashes match. If both a cron and `--watch` fire simultaneously, no conflict.
|
||||
history rewrite still hard-blocks even with `--skip-failed`. Run
|
||||
`gbrain sync --skip-failed` to acknowledge a known-bad set yourself.
|
||||
|
||||
5. **Import checkpoints name the import target, not the caller's CWD.**
|
||||
Interrupted `gbrain import <dir>` runs may leave
|
||||
`~/.gbrain/import-checkpoint.json` so the next import can resume. The
|
||||
checkpoint `dir` is the absolute, resolved import target captured when
|
||||
import starts. It is not a cleanup instruction and it must not be
|
||||
re-derived from the process working directory. Checkpoints written by
|
||||
gbrain include `schema_version: 1`, `owner: "gbrain"`, and
|
||||
`kind: "import"` so downstream tools can validate the contract before
|
||||
deciding whether to resume.
|
||||
|
||||
## How to Verify
|
||||
|
||||
1. **Edit a file and search for the change.** Edit a brain markdown file,
|
||||
|
||||
@@ -1,97 +0,0 @@
|
||||
# Multi-language full-text search
|
||||
|
||||
GBrain's keyword search arm uses Postgres full-text search (tsvector/tsquery).
|
||||
The tokenizer language is configurable via the `GBRAIN_FTS_LANGUAGE`
|
||||
environment variable. Default: `english`.
|
||||
|
||||
## How it works
|
||||
|
||||
Postgres text-search configurations control stemming and stop-word removal.
|
||||
`GBRAIN_FTS_LANGUAGE` is read by `src/core/fts-language.ts` and applied on
|
||||
both sides of the search:
|
||||
|
||||
- **Query side** — `websearch_to_tsquery('<lang>', $query)` in both engines
|
||||
(Postgres and PGLite).
|
||||
- **Write side** — the `update_page_search_vector` and
|
||||
`update_chunk_search_vector` trigger functions that populate
|
||||
`pages.search_vector` and `content_chunks.search_vector`.
|
||||
|
||||
The value is validated against `/^[a-z][a-z0-9_]*$/` before it is ever
|
||||
interpolated into SQL (tsvector functions don't accept parameterized config
|
||||
names). Invalid values fall back to `english` with a warning.
|
||||
|
||||
## Built-in languages
|
||||
|
||||
Set the env var to any configuration your Postgres instance ships:
|
||||
|
||||
```bash
|
||||
export GBRAIN_FTS_LANGUAGE=portuguese
|
||||
export GBRAIN_FTS_LANGUAGE=spanish
|
||||
export GBRAIN_FTS_LANGUAGE=german
|
||||
```
|
||||
|
||||
List what's available:
|
||||
|
||||
```sql
|
||||
SELECT cfgname FROM pg_ts_config;
|
||||
```
|
||||
|
||||
PGLite (the embedded default engine) ships the same built-in snowball
|
||||
configurations as stock Postgres.
|
||||
|
||||
## First install vs. changing language later
|
||||
|
||||
On first install (or upgrade), the `configurable_fts_language` schema
|
||||
migration reads `GBRAIN_FTS_LANGUAGE` and stamps the trigger functions with
|
||||
that language. After the migration has run, changing the env var alone does
|
||||
NOT retokenize existing rows — the migration shows as applied and is skipped.
|
||||
Use the explicit command:
|
||||
|
||||
```bash
|
||||
export GBRAIN_FTS_LANGUAGE=portuguese
|
||||
gbrain reindex-search-vector --dry-run # preview: language + row counts
|
||||
gbrain reindex-search-vector --yes # recreate triggers + backfill
|
||||
```
|
||||
|
||||
The command recreates both trigger functions under the new language and
|
||||
backfills every existing `pages` and `content_chunks` row in batches,
|
||||
streaming progress to stderr. It is idempotent: re-running with the same
|
||||
language produces identical vectors. `--json` prints a machine-readable
|
||||
result envelope but still requires `--yes` (or an interactive confirm).
|
||||
|
||||
## Recipe: accent-insensitive Portuguese (`pt_br`)
|
||||
|
||||
Brazilian Portuguese content often mixes accented and unaccented spellings
|
||||
("São Paulo" vs "Sao Paulo"). Build a custom config that folds accents via
|
||||
the `unaccent` extension, then stems with the portuguese snowball dictionary:
|
||||
|
||||
```sql
|
||||
CREATE EXTENSION IF NOT EXISTS unaccent;
|
||||
|
||||
CREATE TEXT SEARCH CONFIGURATION pt_br (COPY = portuguese);
|
||||
|
||||
ALTER TEXT SEARCH CONFIGURATION pt_br
|
||||
ALTER MAPPING FOR hword, hword_part, word
|
||||
WITH unaccent, portuguese_stem;
|
||||
```
|
||||
|
||||
Then point GBrain at it:
|
||||
|
||||
```bash
|
||||
export GBRAIN_FTS_LANGUAGE=pt_br
|
||||
gbrain reindex-search-vector --yes
|
||||
```
|
||||
|
||||
Note: custom configurations require a real Postgres instance (e.g. the
|
||||
Supabase engine). The config must exist BEFORE the migration or the reindex
|
||||
command runs, or Postgres will reject the trigger recreation with
|
||||
`text search configuration "pt_br" does not exist`.
|
||||
|
||||
## Caveats
|
||||
|
||||
- One language per brain: the setting is global to the database, not
|
||||
per-source. Mixed-language brains should pick the dominant language (the
|
||||
vector-search arm is language-agnostic and covers the rest).
|
||||
- Keep `GBRAIN_FTS_LANGUAGE` set consistently in every environment that
|
||||
writes to the brain (CLI shells, MCP server, cron jobs) — a writer without
|
||||
the env var tokenizes new rows in `english` until the next reindex.
|
||||
@@ -114,11 +114,8 @@ Flip later with `gbrain sources federate <id>` / `unfederate <id>`.
|
||||
Full subcommand reference:
|
||||
|
||||
```
|
||||
gbrain sources add <id> --path <p> [--name <n>] [--federated|--no-federated] [--force]
|
||||
gbrain sources add <id> --path <p> [--name <n>] [--federated|--no-federated]
|
||||
Register a source. id: [a-z0-9](?:[a-z0-9-]{0,30}[a-z0-9])?
|
||||
--path must be a git repo (or a subdirectory of one) — see
|
||||
"The git requirement for --path sources" below. --force
|
||||
skips that check to register before git-init exists.
|
||||
gbrain sources list [--json] List all sources with page counts + federation state.
|
||||
gbrain sources remove <id> [--yes] [--dry-run] [--keep-storage]
|
||||
Cascade-delete a source (pages, chunks, timeline).
|
||||
@@ -131,47 +128,6 @@ gbrain sources federate <id>
|
||||
gbrain sources unfederate <id>
|
||||
```
|
||||
|
||||
## The git requirement for --path sources
|
||||
|
||||
Every `--path` source must be a git repository (or live inside one — a
|
||||
subdirectory of a git repo works too) with at least one committed, tracked
|
||||
file under that path. `gbrain sources add` validates this at registration
|
||||
time and refuses a directory that doesn't qualify — no `.git` at all, a
|
||||
`git init` with no commit yet, or a commit made before `git add` — with an
|
||||
actionable error instead of silently registering a source that will fail
|
||||
(or worse, "succeed" while importing nothing) on its first `gbrain sync`.
|
||||
Fix it with:
|
||||
|
||||
```bash
|
||||
git -C <path> init
|
||||
git -C <path> add -A
|
||||
git -C <path> commit -m "initial import"
|
||||
gbrain sources add <id> --path <path>
|
||||
```
|
||||
|
||||
Two details that are easy to miss:
|
||||
|
||||
- **Files must actually be committed, not just present.** The sync walker
|
||||
reads files through git objects, so `git init` alone — even followed by an
|
||||
empty commit (`git commit --allow-empty`) — isn't enough. Registration
|
||||
checks for real tracked content (`git ls-tree HEAD` scoped to the path),
|
||||
not just a resolvable `HEAD`, so this footgun is caught immediately
|
||||
instead of surfacing later as a sync that imports nothing.
|
||||
- **`--force` registers the source anyway**, skipping the check. Use this if
|
||||
you're registering a path before an automated pipeline gets around to
|
||||
`git init`-ing it. GBrain never auto-`git init`s a `--path` source for
|
||||
you — it's your directory, not a gbrain-managed clone (same consent
|
||||
boundary as sync-time self-heal, which also never mutates a `--path`
|
||||
source without an explicit ask).
|
||||
|
||||
**If sync ever reports a problem with the sync anchor** (`last_commit`) —
|
||||
after a force-push, a history rewrite, or a from-scratch `git init` on a
|
||||
directory that was synced before — you do not need to reset anything by
|
||||
hand. `gbrain sync` detects an unreachable or non-ancestor anchor
|
||||
automatically and recovers: either a full reimport (anchor object missing)
|
||||
or a direct tree-to-tree diff against the orphaned bookmark (anchor present
|
||||
but rewritten), advancing the anchor to the new HEAD when it completes.
|
||||
|
||||
## Citation format for agents
|
||||
|
||||
When agents receive multi-source results they MUST cite pages in
|
||||
@@ -199,58 +155,6 @@ Reads span federated sources by default. Writes require a resolved
|
||||
source (explicit, inferred, or default). The resolver never picks a
|
||||
source silently when ambiguous — it errors with a clear fix.
|
||||
|
||||
## Durability: keep a brain repo in sync (auto-harden)
|
||||
|
||||
A long-lived agent that writes to a knowledge-wiki git repo needs three
|
||||
things to never lose work: pull before it edits, push every write, and not
|
||||
go stale while it sits idle. `gbrain sources harden` installs all of that,
|
||||
idempotently. The moment you add a brain repo with a token, it runs
|
||||
automatically:
|
||||
|
||||
```bash
|
||||
# Clone + register a GitHub repo, then auto-harden it for durability.
|
||||
# Use a fine-grained PAT scoped to just this repo.
|
||||
gbrain sources add wiki --url https://github.com/you/brain-wiki.git --pat-file ~/.secrets/wiki-pat
|
||||
# → clones, then installs: local auto-push hook, scripts/brain-commit-push.sh,
|
||||
# always-on durability rules in AGENTS.md/RESOLVER.md, a 30-min pull cron,
|
||||
# and a repo-scoped credential. Verifies push works before declaring done.
|
||||
|
||||
# Run the same audit on an existing source any time (idempotent):
|
||||
gbrain sources harden wiki --pat-file ~/.secrets/wiki-pat
|
||||
|
||||
# Pull on demand (the cron calls the --path form, which never opens the DB):
|
||||
gbrain sources pull wiki
|
||||
|
||||
# Remove the durability scaffolding (also runs automatically on `sources remove`):
|
||||
gbrain sources unharden wiki
|
||||
```
|
||||
|
||||
What hardening guarantees:
|
||||
|
||||
- **Pull-first, conflict-safe.** Every pull is a divergence-safe rebase. A
|
||||
dirty working tree is skipped (your in-progress edits are never touched); a
|
||||
rebase conflict is aborted cleanly and flagged for attention, never left
|
||||
half-applied.
|
||||
- **Push is never deferred.** `scripts/brain-commit-push.sh "<msg>" <path>`
|
||||
commits and pushes atomically and refuses to report success without a
|
||||
confirmed push. The post-commit hook is a best-effort background fallback;
|
||||
the helper is the guarantee.
|
||||
- **No silent staleness.** A 30-minute background pull keeps an idle session
|
||||
current. It runs DB-free, so it never contends with a live brain for the
|
||||
PGLite single-writer lock.
|
||||
|
||||
Flags: `--no-cron` skips the scheduled pull, `--no-verify` skips the push
|
||||
probe, `--dry-run` reports what would change, `--json` emits a machine
|
||||
report, `--all` hardens every source with a remote (same-account only).
|
||||
`--no-harden` on `sources add` opts out of auto-harden.
|
||||
|
||||
Security: the push automation is installed locally per machine (never
|
||||
committed into the repo), the token is wired per-repo (an existing
|
||||
credential helper is reused when present), and it never appears in the repo,
|
||||
the remote URL, logs, or the JSON report. For a self-hosted git server
|
||||
reachable only over a filesystem path, set `GBRAIN_GIT_ALLOW_FILE_TRANSPORT=1`
|
||||
(default is HTTPS-only).
|
||||
|
||||
## Upgrading an existing brain
|
||||
|
||||
`gbrain upgrade` runs the v16 + v17 migrations automatically. Your
|
||||
|
||||
@@ -1,79 +0,0 @@
|
||||
# Push-based context (#2095, v0.42.43.0)
|
||||
|
||||
Retrieval used to be pull-only: the agent had to *know to ask* before the brain
|
||||
contributed anything. Push-based context inverts that — the brain volunteers
|
||||
relevant pages from the recent conversation, confidence-gated so push noise
|
||||
never becomes worse than pull silence.
|
||||
|
||||
Three channels share one zero-LLM core (`src/core/context/volunteer.ts`):
|
||||
|
||||
| Channel | Surface | When to use |
|
||||
|---|---|---|
|
||||
| `reflex` | automatic, inside the context engine | default-on for plugin hosts; nothing to call |
|
||||
| `op` | `gbrain volunteer-context` / MCP `volunteer_context` | agents without the plugin; one call per turn |
|
||||
| `watch` | `gbrain watch` | stream a transcript in, volunteered pages stream out |
|
||||
|
||||
## How it decides
|
||||
|
||||
1. **Extract** entities across the last N turns (capitalized runs, `@handles`),
|
||||
merged with recency / frequency / user-role salience. Assistant-introduced
|
||||
entities and "what did she invest in?" follow-ups whose antecedent was named
|
||||
in the window now resolve.
|
||||
2. **Resolve** through the alias table, exact titles, and slug suffixes — each
|
||||
arm carries an honest confidence: alias 0.9, exact title 0.8, slug-suffix 0.6,
|
||||
+0.05 when mentioned in ≥2 turns or the newest turn.
|
||||
3. **Gate** at `min_confidence` (default 0.7 — slug-suffix matches need an
|
||||
explicit lower gate), suppress pages already surfaced (slug-presence only),
|
||||
cap at 3 pages (hard cap 5).
|
||||
|
||||
## CLI
|
||||
|
||||
```bash
|
||||
# one-shot: pipe recent turns (oldest → newest)
|
||||
printf 'user: ask alice-example about the deal\nassistant: noted\nuser: what did she say?\n' \
|
||||
| gbrain volunteer-context
|
||||
|
||||
# streaming: volunteered pages print as the transcript flows
|
||||
some-transcript-feed | gbrain watch --json
|
||||
|
||||
# the feedback loop: how often were volunteered pages actually opened?
|
||||
gbrain volunteer-context --stats
|
||||
```
|
||||
|
||||
Stats are **approximate** by design: "used" means `pages.last_retrieved_at >
|
||||
volunteered_at` — the 5-minute last-retrieved throttle causes false negatives
|
||||
and unrelated reads of the same page cause false positives. Use the per-arm
|
||||
precision to tune `min_confidence`, not as an exact metric.
|
||||
|
||||
**PGLite + `gbrain watch`:** PGLite is single-connection, and watch holds its
|
||||
connection for the whole session — a concurrent `gbrain serve` or any write
|
||||
path blocks until watch exits. On a PGLite brain, run watch in bursts (piped
|
||||
input exits at EOF) or use the ambient reflex channel instead, which routes
|
||||
through a running serve's resolve socket rather than taking the lock. Routing
|
||||
watch through that same socket is a filed follow-up (TODOS.md). Postgres
|
||||
brains are unaffected.
|
||||
|
||||
## Config
|
||||
|
||||
| Key | Default | What it does |
|
||||
|---|---|---|
|
||||
| `retrieval_reflex_window_turns` | 4 | turns the ambient reflex extracts from; 1 = legacy current-turn-only (file/env plane: `GBRAIN_RETRIEVAL_REFLEX_WINDOW_TURNS`) |
|
||||
| `retrieval_reflex` | true | the ambient channel's master switch |
|
||||
| `retrieval_reflex_max_pointers` | 3 | pointer cap per turn |
|
||||
|
||||
Per-call knobs: `max_pages` + `min_confidence` on both the op and `gbrain watch`
|
||||
(`--max-pages` / `--min-confidence`, plus `--window-turns` / `--source` on watch);
|
||||
on the op only: `prior_context` (text whose already-surfaced slugs are suppressed),
|
||||
`session_id` / `turn` attribution params (watch stamps its own per-session id and
|
||||
turn numbers in the feedback log), and `days` to size the `--stats` window.
|
||||
|
||||
## Storage + privacy
|
||||
|
||||
Volunteered pages log to `context_volunteer_events` (migration v117): slug,
|
||||
arm, confidence, channel, optional session/turn — the rationale is a
|
||||
deterministic template string, never raw conversation text. Event writes are
|
||||
best-effort (fire-and-forget, drained at CLI exit) — the log is a tuning signal,
|
||||
not an audit trail. Rows are pruned after 90 days by the dream cycle's purge
|
||||
phase. Synopses always strip the takes/facts fences — the same strip `get_page`
|
||||
applies to untrusted callers, applied unconditionally here so private fence rows
|
||||
never reach a prompt regardless of caller trust.
|
||||
@@ -208,10 +208,9 @@ architectural rounds shipped in the budget-cathedral wave that followed:
|
||||
- **P3 (judge chunking):** `runJudge` in `src/core/brainstorm/judges.ts`
|
||||
auto-chunks at 100 ideas/call. Context-window overflow is structurally
|
||||
prevented.
|
||||
- **P4 (unicode sanitization):** `ensureWellFormed` (in `src/core/text-safe.ts`,
|
||||
used by `src/core/brainstorm/orchestrator.ts`) replaces unpaired surrogates
|
||||
with U+FFFD before serialization. (Consolidated from the original hand-rolled
|
||||
`sanitizeUnicode` in v0.42.40.0 / #2011.)
|
||||
- **P4 (unicode sanitization):** `sanitizeUnicode` in
|
||||
`src/core/brainstorm/orchestrator.ts` strips unpaired surrogates before
|
||||
serialization.
|
||||
- **P5 (BudgetTracker at the gateway layer):** new
|
||||
`src/core/budget/budget-tracker.ts` is the canonical primitive. The
|
||||
gateway's `withBudgetTracker(tracker, fn)` composes via
|
||||
|
||||
@@ -34,7 +34,7 @@ The resolved provider + dimensions get persisted to `~/.gbrain/config.json` atom
|
||||
| `zhipu` | `ZHIPUAI_API_KEY` | 1024 | varies | no | no |
|
||||
| `ollama` | (none — runs locally) | 768 | 0 | yes | no |
|
||||
| `llama-server` | (none — runs locally) | user-set | 0 | yes | no |
|
||||
| `litellm` | `LITELLM_API_KEY` (optional) | user-set | varies | yes (proxy) | yes (backend permitting) |
|
||||
| `litellm` | `LITELLM_API_KEY` (optional) | user-set | varies | yes (proxy) | no |
|
||||
| `together` | `TOGETHER_API_KEY` | 768 | varies | no | no |
|
||||
| `anthropic` | (no embedding model — chat only) | — | — | — | — |
|
||||
| `deepseek` | (no embedding model — chat only) | — | — | — | — |
|
||||
@@ -77,8 +77,6 @@ The doctor distinguishes two repair paths:
|
||||
|
||||
Default. Set `OPENAI_API_KEY`. Models: `text-embedding-3-large` (3072 max, 1536 default), `text-embedding-3-small` (1536). Matryoshka via the `dimensions` field — gbrain pins it from `embedding_dimensions` config so existing 1536-dim brains stay aligned across SDK upgrades.
|
||||
|
||||
Optional `OPENAI_BASE_URL` — point the native OpenAI provider at an OpenAI-compatible gateway. A bare host is normalized to carry the `/v1` suffix automatically (so `https://gw.example.com` and `https://gw.example.com/v1` both work); when unset, the SDK's default endpoint is untouched. `ANTHROPIC_BASE_URL` gets the same normalization for Anthropic chat/expansion calls.
|
||||
|
||||
### Voyage AI
|
||||
|
||||
Best-in-class quality on the Voyage 4 family (Jan 2026 release). Set `VOYAGE_API_KEY`. Models: `voyage-4-large`, `voyage-4`, `voyage-4-lite`, `voyage-4-nano`, `voyage-3.5`, `voyage-code-3` (code-tuned), `voyage-finance-2`, `voyage-law-2`, `voyage-multimodal-3` (text + image).
|
||||
@@ -143,15 +141,13 @@ Set `ZHIPUAI_API_KEY`. Models: `embedding-3` (current; Matryoshka 256-2048 dims)
|
||||
|
||||
No env required — Ollama runs unauthenticated locally. Optional `OLLAMA_BASE_URL` (default `http://localhost:11434/v1`) and `OLLAMA_API_KEY` (for auth-enabled deployments).
|
||||
|
||||
Recipe ships with `nomic-embed-text` (768d, recommended), `mxbai-embed-large` (1024d), `all-minilm` (384d), plus the larger modern embedders `qwen3-embed-8b` (4096d) and `snowflake-arctic-embed-l-v2` (1024d). `gbrain providers test --model ollama:nomic-embed-text` smoke-tests the local install.
|
||||
|
||||
The recipe default is `nomic-embed-text`'s 768 dims. If you run one of the larger models, declare its native dimension with `--embedding-dimensions <N>` at init — gbrain trusts the value you declare for local recipes instead of rejecting a non-768 width.
|
||||
Recipe ships with `nomic-embed-text` (768d, recommended), `mxbai-embed-large` (1024d), `all-minilm` (384d). `gbrain providers test --model ollama:nomic-embed-text` smoke-tests the local install.
|
||||
|
||||
### llama-server (local, llama.cpp)
|
||||
|
||||
`llama.cpp`'s `llama-server --embeddings` endpoint. No env required. Optional `LLAMA_SERVER_BASE_URL` (default `http://localhost:8080/v1`) and `LLAMA_SERVER_API_KEY`.
|
||||
|
||||
User-driven models: launch llama-server with `--model <gguf-path> --embeddings`, then run `gbrain init --embedding-model llama-server:<your-id> --embedding-dimensions <N>`. gbrain trusts the dimension you declare (you know the GGUF you launched); the recipe refuses the implicit shorthand `--model llama-server` because there's no canonical first model.
|
||||
User-driven models: launch llama-server with `--model <gguf-path> --embeddings`, then run `gbrain init --embedding-model llama-server:<your-id> --embedding-dimensions <N>`. The recipe refuses the implicit shorthand `--model llama-server` because there's no canonical first model.
|
||||
|
||||
### LiteLLM proxy (universal escape hatch)
|
||||
|
||||
@@ -159,8 +155,6 @@ Run [LiteLLM](https://docs.litellm.ai/docs/proxy/quick_start) in front of any pr
|
||||
|
||||
This is the catch-all for "my provider isn't in the list above." Set up LiteLLM, then `gbrain init --embedding-model litellm:<your-model-id> --embedding-dimensions <N>`.
|
||||
|
||||
**Include the `/v1` suffix in `LITELLM_BASE_URL` if your proxy serves the OpenAI route there** (e.g. `http://localhost:4000/v1`). Many LiteLLM deployments expose the OpenAI-compatible API only under `/v1`; pointing gbrain at the bare host 404s or fails authentication with no hint. gbrain trusts the dimension you declare for the proxy-backed model — the proxy's backend, not gbrain, decides the true width — so `--embedding-dimensions <N>` is required and accepted as-is.
|
||||
|
||||
## Choosing dimensions
|
||||
|
||||
Three numbers matter:
|
||||
@@ -189,3 +183,5 @@ The supported paths:
|
||||
- **Postgres (Supabase / self-hosted):** follow the SQL recipe in `docs/embedding-migrations.md` (drop the HNSW index, ALTER COLUMN TYPE, clear stale embeddings, recreate the index conditionally, then `gbrain init --supabase --embedding-model X --embedding-dimensions N` to update the file plane and re-embed).
|
||||
|
||||
`gbrain doctor` 8c "alternative_providers" surfaces unconfigured providers whose env is already set — useful when you've configured OpenAI but also have e.g. `VOYAGE_API_KEY` exported and want to know you can switch without extra setup.
|
||||
|
||||
`gbrain doctor` 8c "alternative_providers" surfaces unconfigured providers whose env is already set — useful when you've configured OpenAI but also have e.g. `VOYAGE_API_KEY` exported and want to know you can switch without extra setup.
|
||||
|
||||
@@ -7,7 +7,7 @@ brain source's repo that runs `gbrain frontmatter validate` against staged
|
||||
|
||||
## What the hook catches
|
||||
|
||||
The same eight validation classes the `frontmatter-guard` skill and
|
||||
The same seven validation classes the `frontmatter-guard` skill and
|
||||
`gbrain doctor`'s `frontmatter_integrity` subcheck report:
|
||||
|
||||
| Code | What it catches |
|
||||
@@ -18,7 +18,6 @@ The same eight validation classes the `frontmatter-guard` skill and
|
||||
| `SLUG_MISMATCH` | `slug:` in frontmatter doesn't match path-derived slug |
|
||||
| `NULL_BYTES` | Binary corruption (`\x00`) anywhere in the content |
|
||||
| `NESTED_QUOTES` | `title: "outer "inner" outer"` shape that breaks YAML |
|
||||
| `NON_STRING_FIELD` | `title`/`type`/`slug` is an unquoted non-string scalar (`title: 123`) |
|
||||
| `EMPTY_FRONTMATTER` | `---` ... `---` with nothing meaningful between |
|
||||
|
||||
## Install
|
||||
|
||||
+1
-8
@@ -74,20 +74,13 @@ to the HTTP server, so no migration is required.
|
||||
gbrain serve --http --port 3131
|
||||
```
|
||||
|
||||
On first start in an interactive terminal, the server prints an **admin
|
||||
bootstrap token** to stderr:
|
||||
On first start, the server prints an **admin bootstrap token** to stderr:
|
||||
|
||||
```
|
||||
Admin bootstrap token: 3a1f9c...
|
||||
Open http://localhost:3131/admin and paste it to log in.
|
||||
```
|
||||
|
||||
On a non-TTY start (systemd, Docker, any piped or captured logs) the generated
|
||||
token is hidden so it never lands in log storage. For headless deploys either
|
||||
set `GBRAIN_ADMIN_BOOTSTRAP_TOKEN` to a value you control before starting, or
|
||||
run `gbrain serve --http --print-admin-token` once on a trusted terminal to
|
||||
force printing.
|
||||
|
||||
Save this token. Open `http://localhost:3131/admin` and paste it to access the
|
||||
dashboard. The dashboard shows live activity, registered clients, request logs,
|
||||
and per-client config export.
|
||||
|
||||
@@ -1,111 +0,0 @@
|
||||
# Spend controls
|
||||
|
||||
GBrain's embedding-spend gates in one place: every gate, its config key, default,
|
||||
whether it blocks or just informs, how to widen or disable it, and how the
|
||||
`spend.posture` switch governs all of them.
|
||||
|
||||
The orienting idea: **GBrain itself is rounding error; the spend that matters is
|
||||
downstream embedding.** These gates exist so a routine sync or enrich can't run up
|
||||
an unexpected embedding bill, while never wedging an unattended cron.
|
||||
|
||||
## `spend.posture` — one switch for "cost is not my constraint"
|
||||
|
||||
```bash
|
||||
gbrain config set spend.posture tokenmax # all cost gates become informational
|
||||
gbrain config set spend.posture gated # default — gates enforce
|
||||
```
|
||||
|
||||
| Value | Effect |
|
||||
|-------|--------|
|
||||
| `gated` (default) | Every cost gate enforces its limit as documented below. |
|
||||
| `tokenmax` | Every cost gate prints its estimate and **proceeds** — informational only. Spend is still recorded to the ledger; posture removes the *ceiling*, not the *accounting*. |
|
||||
|
||||
`spend.posture` is deliberately separate from `search.mode=tokenmax` (which governs
|
||||
retrieval payload size, not embedding spend). When a gate fires and
|
||||
`search.mode=tokenmax` but `spend.posture` is unset, the gate prints a one-line hint
|
||||
pointing at this switch.
|
||||
|
||||
**Precedence:** an explicit per-call cap (`--max-usd N`, `--max-cost N`) always wins
|
||||
over posture. `tokenmax` only governs the default/absent case — it never overrides a
|
||||
number you typed on the command line.
|
||||
|
||||
## Off switches (`off` / `unlimited` / `none`)
|
||||
|
||||
The USD-limit knobs accept `off`, `unlimited`, or `none` (case-insensitive) to mean
|
||||
"no limit" — no more setting sentinel values like `100000`.
|
||||
|
||||
- `0` is **not** "off". On `sync.cost_gate_min_usd`, `0` means "block on any nonzero
|
||||
spend" (a real choice). On the backfill caps, `0` falls back to the default.
|
||||
- Internally "no limit" is the string `unlimited` in any printed/JSON output and "no
|
||||
cap" inside the budget tracker — never a raw `Infinity` (which would serialize to
|
||||
`null` in ledger rows).
|
||||
|
||||
## The gates
|
||||
|
||||
| Gate | Config key | Default | Blocks? | Off switch | tokenmax |
|
||||
|------|-----------|---------|---------|-----------|----------|
|
||||
| Sync inline-embed cost gate | `sync.cost_gate_min_usd` | `0.50` | TTY prompt / non-TTY auto-defer | `off` (or `0` = block-on-any) | informational |
|
||||
| Backfill 24h per-source spend cap | `embed.backfill_max_usd_per_source_24h` | `25` | refuses submission | `off` (`0` → default) | bypassed (still ledgered) |
|
||||
| Backfill per-job budget | `embed.backfill_max_usd` | `10` | caps the job's tracker | `off` (`0` → default) | uncapped (still ledgered) |
|
||||
| Backfill cooldown | `embed.backfill_cooldown_min` | `10` | skips re-submission inside window | — (latency knob, not spend) | **not** bypassed |
|
||||
| `reindex-code` cost gate | — (preview before re-embed) | — | TTY prompt / non-TTY refuse + exit 2 | `--max-cost off` | informational |
|
||||
| `enrich` / `onboard --auto` | `--max-usd` (per-call) | — | refuse without a cap (non-TTY) | `--max-usd off` | runs uncapped (still ledgered) |
|
||||
|
||||
### Sync inline-embed cost gate
|
||||
|
||||
Fires only when sync embeds **inline** (federated_v2 off, or `--serial` without
|
||||
`--no-embed`). Under federated_v2 + parallel, embedding is deferred to capped backfill
|
||||
jobs and the gate is informational. The estimate prices the **delta** — the files this
|
||||
sync will actually import (fetched-first, so it sees commits the run is about to pull) —
|
||||
not the whole tree. A busy brain with a dirty working tree but caught-up commits
|
||||
estimates `$0`, because an attached-HEAD sync imports only the committed diff.
|
||||
|
||||
Behavior above the floor:
|
||||
- **TTY:** prompts `[y/N]`.
|
||||
- **Non-interactive (cron/agent):** **auto-defers** embeds to capped backfill jobs and
|
||||
exits 0 — it never wedges the pipeline. The backlog drains via the jobs worker or
|
||||
`gbrain embed --stale`. Pass `--yes` to embed inline instead.
|
||||
|
||||
Output format splits on the explicit `--json` flag: `--json` emits a structured
|
||||
envelope; otherwise human text. Every gate message carries paste-ready knobs.
|
||||
|
||||
`--full` re-embeds the stale backlog inline (full sync sweeps it), so a `--full`
|
||||
estimate is `delta + stale backlog`, labeled as such.
|
||||
|
||||
### Estimate labels
|
||||
|
||||
- `~N tokens (delta: changed files since last sync)` — the precise estimate.
|
||||
- `<=N tokens (full-tree ceiling for K source(s): <reasons> …)` — a conservative
|
||||
over-count used only when a precise delta can't be computed: a first sync, a chunker
|
||||
version drift (forces a full re-chunk), or git being unavailable. Unchanged files
|
||||
still skip via `content_hash` at execution, so the ceiling over-states real spend.
|
||||
|
||||
## Notes & limits
|
||||
|
||||
- **Pre-pull window:** the gate fetches before estimating, so it prices what the run
|
||||
will pull. If a fetch fails (offline), it estimates against local HEAD and labels the
|
||||
result; the bounded residual is priced on the next run.
|
||||
- **Single-source `gbrain sync`** carries the same gate as `sync --all` (it previously
|
||||
embedded inline with no preview).
|
||||
- **Recovery under parallel:** `--skip-failed` / `--retry-failed` work under parallel
|
||||
sync (the failure ledger is per-source and lock-serialized) — you no longer have to
|
||||
drop to `--serial`, which is what used to arm the inline gate.
|
||||
|
||||
## Escape hatches at a glance
|
||||
|
||||
```bash
|
||||
# Never gate this brain on cost:
|
||||
gbrain config set spend.posture tokenmax
|
||||
|
||||
# Widen the sync inline floor to $5:
|
||||
gbrain config set sync.cost_gate_min_usd 5
|
||||
|
||||
# Disable the sync inline floor entirely:
|
||||
gbrain config set sync.cost_gate_min_usd off
|
||||
|
||||
# Lift the backfill 24h spend cap:
|
||||
gbrain config set embed.backfill_max_usd_per_source_24h off
|
||||
|
||||
# Run enrich uncapped non-interactively:
|
||||
gbrain enrich --max-usd off # or: gbrain config set spend.posture tokenmax
|
||||
```
|
||||
@@ -158,7 +158,7 @@ gbrain serve --http --port 3131 --bind 0.0.0.0
|
||||
|
||||
The `--bind 0.0.0.0` is important. By default the server binds to localhost only, which is correct for a personal install but blocks remote teammates. Setting `0.0.0.0` accepts connections from any interface.
|
||||
|
||||
The server prints an admin bootstrap token to stderr on first start when run in an interactive terminal. Save it. You'll use it once for the admin dashboard. On a non-TTY start (systemd, Docker, piped logs) the token is hidden from logs — set `GBRAIN_ADMIN_BOOTSTRAP_TOKEN` yourself or pass `--print-admin-token` on a trusted terminal instead.
|
||||
The server prints an admin bootstrap token to stderr on first start. Save it. You'll use it once for the admin dashboard.
|
||||
|
||||
For development, tunnel the local server out via ngrok:
|
||||
|
||||
|
||||
@@ -86,7 +86,7 @@ Save this token. You'll need it for the AlphaClaw setup.
|
||||
|
||||
AlphaClaw is the setup harness that manages OpenClaw deployment.
|
||||
|
||||
1. Go to [alphaclaw.md](https://alphaclaw.md)
|
||||
1. Go to [alphaclaw.com](https://alphaclaw.com)
|
||||
2. Enter your **workspace repo** (not the brain repo): `your-org/myagent`
|
||||
3. Select "Use existing" if the repo already exists
|
||||
4. Enter your GitHub PAT from Step 2
|
||||
|
||||
@@ -415,7 +415,6 @@ export async function main(argv: string[]): Promise<number> {
|
||||
chat_model: config?.chat_model ?? modelFull,
|
||||
chat_fallback_chain: config?.chat_fallback_chain,
|
||||
base_urls: config?.provider_base_urls,
|
||||
provider_chat_options: config?.provider_chat_options,
|
||||
env: { ...process.env } as Record<string, string>,
|
||||
});
|
||||
|
||||
|
||||
+9
-314
@@ -117,9 +117,8 @@ writing or reviewing an operation, consult `src/core/operations.ts` for the cont
|
||||
## Before shipping
|
||||
|
||||
Easiest path: `bun run ci:local` runs the full CI gate inside Docker (gitleaks,
|
||||
guards + typecheck, then 4-shard parallel unit + E2E against four pgvector
|
||||
containers plus a transaction-mode PgBouncer; unit phase keeps `DATABASE_URL`
|
||||
unset) and tears down. Use `bun run ci:local:diff` for the
|
||||
unit tests with `DATABASE_URL` unset, then all 29 E2E files sequentially against a
|
||||
fresh pgvector container) and tears down. Use `bun run ci:local:diff` for the
|
||||
diff-aware subset during fast iteration on a focused branch. Requires Docker
|
||||
(Docker Desktop / OrbStack / Colima) and `gitleaks` (`brew install gitleaks`).
|
||||
|
||||
@@ -187,7 +186,7 @@ mount, CEO-class with multiple team brains) and
|
||||
|
||||
## Architecture
|
||||
|
||||
Contract-first: `src/core/operations.ts` defines ~90 shared operations (v0.29 adds `get_recent_salience`, `find_anomalies`, `get_recent_transcripts`; v0.42.43.0 adds `volunteer_context` — push-based context, see `docs/guides/push-context.md`). CLI and MCP
|
||||
Contract-first: `src/core/operations.ts` defines ~47 shared operations (v0.29 adds `get_recent_salience`, `find_anomalies`, `get_recent_transcripts`). CLI and MCP
|
||||
server are both generated from this single source. Engine factory (`src/core/engine-factory.ts`)
|
||||
dynamically imports the configured engine (`'pglite'` or `'postgres'`). Skills are fat
|
||||
markdown files (tool-agnostic, work with both CLI and plugin contexts).
|
||||
@@ -208,14 +207,9 @@ Per-file detail is in `docs/architecture/KEY_FILES.md`.
|
||||
- **Source isolation.** Every read-side op routes through `sourceScopeOpts(ctx)`; precedence
|
||||
is federated array (`ctx.auth.allowedSources`) > scalar (`ctx.sourceId`) > nothing. Don't
|
||||
hand-roll source filtering — a missed thread is a cross-source data leak.
|
||||
- **JSONB: never `JSON.stringify` into a `::jsonb` cast.** postgres.js double-encodes it (a jsonb
|
||||
string scalar); PGLite hides the bug. This bites BOTH spellings — the template form
|
||||
(`${JSON.stringify(x)}::jsonb`) AND the positional form (`executeRaw(\`…$N::jsonb\`, [JSON.stringify(x)])`,
|
||||
the #2339 class that aborted every sync). Fix: pass a raw object to `engine.executeRaw` / use
|
||||
`executeRawJsonb` / `sql.json()`; or for the positional path bind through `$N::text::jsonb` (binds as
|
||||
text, the cast parses it). Guarded by `scripts/check-jsonb-pattern.sh` (template grep) +
|
||||
`scripts/check-jsonb-params.mjs` (positional AST scanner); the real backstop is the DATABASE_URL-gated
|
||||
e2e parity tests, since PGLite can't surface the bug. Full rule in `docs/ENGINES.md`.
|
||||
- **JSONB: never `JSON.stringify` into a `::jsonb` cast.** postgres.js double-encodes it;
|
||||
PGLite hides the bug. Pass raw objects to `engine.executeRaw`, or use `executeRawJsonb`.
|
||||
Guarded by `scripts/check-jsonb-pattern.sh`.
|
||||
- **Engine parity.** `src/core/postgres-engine.ts` and `src/core/pglite-engine.ts` move in
|
||||
lockstep — a new method/SQL shape lands in BOTH, pinned by `test/e2e/engine-parity.test.ts`.
|
||||
Forward-referenced columns/indexes go in the bootstrap probe set (guarded by
|
||||
@@ -251,8 +245,6 @@ detail on demand.)
|
||||
| any file in `src/` (what it does + its invariants) | `docs/architecture/KEY_FILES.md` — find the file's entry |
|
||||
| search / ranking / hybrid / retrieval | `docs/architecture/RETRIEVAL.md` + the `search/*` entries in `KEY_FILES.md` |
|
||||
| search modes / cost knobs | `docs/guides/search-modes.md` |
|
||||
| embedding spend gates / cost gate / `spend.posture` / off switches | `docs/operations/spend-controls.md` |
|
||||
| push-based context (volunteer/watch/reflex window) | `docs/guides/push-context.md` |
|
||||
| schema packs / page types / extraction | `docs/architecture/schema-packs.md`, `type-taxonomy.md`, `lens-packs.md` |
|
||||
| thin-client / remote MCP / cross-modal | `docs/architecture/thin-client.md` |
|
||||
| the CLI surface (commands + flags) | `gbrain --help` / `gbrain --tools-json`, plus the relevant `KEY_FILES.md` entry |
|
||||
@@ -305,7 +297,6 @@ project resolves through `src/core/search/mode.ts`.
|
||||
| `intentWeighting` | true | true | true |
|
||||
| `tokenBudget` | **4000** | **12000** | **off** |
|
||||
| `expansion` (LLM multi-query) | false | false | **true** |
|
||||
| `relationalRetrieval` | false | **true** | **true** |
|
||||
| `searchLimit` default | 10 | 25 | 50 |
|
||||
|
||||
**Cost anchors (downstream agent input cost — gbrain itself is rounding error).**
|
||||
@@ -364,19 +355,6 @@ written against `embedding` (1536d OpenAI). Existing v=2 rows become
|
||||
unreachable on first re-query (one-time miss spike on upgrade);
|
||||
`mode.ts:KNOBS_HASH_VERSION` is the single source of truth.
|
||||
|
||||
**v0.42.34.0 knobs_hash v=9 → v=10.** Folds the `relationalRetrieval` knob +
|
||||
depth into the cache key so a relational-on result set can't be served to a
|
||||
relational-off lookup (same contamination class as graph_signals). One-time
|
||||
miss spike on upgrade.
|
||||
|
||||
**Relational retrieval (v0.42.34.0).** `relationalRetrieval` (on for
|
||||
balanced/tokenmax) adds a fourth recall arm: a relational query ("who invested
|
||||
in X", "what connects A and B") resolves its seed entity and walks the typed-edge
|
||||
graph (`src/core/search/relational-recall.ts` + `relational-intent.ts`,
|
||||
`engine.relationalFanout`), injecting edge-derived answers into RRF. Within-source,
|
||||
deterministic, mentions-excluded by default, pure no-op for non-relational queries.
|
||||
The `query` op's `relational` flag forces it on/off per call.
|
||||
|
||||
**Three CLI surfaces:**
|
||||
|
||||
gbrain search modes # what is running, with per-knob attribution
|
||||
@@ -408,7 +386,7 @@ audit trail lives in the source repo's git history.
|
||||
|
||||
## Skills
|
||||
|
||||
Read the skill files in `skills/` before doing brain operations. GBrain ships 30 skills
|
||||
Read the skill files in `skills/` before doing brain operations. GBrain ships 29 skills
|
||||
organized by `skills/RESOLVER.md` (`AGENTS.md` is also accepted as of v0.19):
|
||||
|
||||
**Original 8 (conformance-migrated):** ingest (thin router), query, maintain, enrich,
|
||||
@@ -427,17 +405,6 @@ routing is narrowed to what the skill actually covers.
|
||||
**Skillify loop (v0.19):** skillify (the markdown orchestration), skillpack-check
|
||||
(agent-readable health report).
|
||||
|
||||
**Brain-resident skillpacks + advisor (v0.42.47.0, #2180):** A brain repo can carry its
|
||||
own publishable skillpack (`brain_resident: true` in `skillpack.json` + `schema_pack`);
|
||||
`gbrain skillpack init-brain-pack` scaffolds one with a 5-section machine-parseable README.
|
||||
Connecting harnesses discover it on `gbrain sources add` (Topology A advisory, bounded nag
|
||||
via `nag-state.ts`) and over MCP via the source-scoped `list_brain_skillpack` op +
|
||||
`get_skill --source_id` (gated by `mcp.publish_skills`). The bundled `gbrain-advisor` skill
|
||||
+ `gbrain advisor` op compute a ranked, read-only list of high-leverage actions from brain
|
||||
state (8 collectors in `src/core/advisor/`); `--json`+exit codes for CI/cron, local-only
|
||||
`--apply <id>` behind confirm, exposed over MCP behind `mcp.publish_advisor` (default off,
|
||||
read-only on remote). Thin-client binary install stays deferred to PR2 `build_skillpack`.
|
||||
|
||||
**Routing-table compression (v0.32.3.0):** `skills/functional-area-resolver/` —
|
||||
two-layer dispatch pattern for shrinking large AGENTS.md / RESOLVER.md files
|
||||
(>=12KB) without losing routing accuracy. Replaces one row per skill with one
|
||||
@@ -537,76 +504,6 @@ For background tasks (`run_in_background: true`), the harness captures the exit
|
||||
file separately — use it via the bg task's `<id>.exit` file, not the streamed
|
||||
output.
|
||||
|
||||
## Sync resumability + lock tuning (v0.42.x, #1794)
|
||||
|
||||
`gbrain sync` is resumable and converges under pool exhaustion + repeated kills.
|
||||
Progress banks into the append-only `op_checkpoint_paths` table (one row per drained
|
||||
path, written via the direct session pool so it survives `EMAXCONNSESSION`); a killed
|
||||
run resumes from the checkpoint and `last_commit` only advances on true completion. The
|
||||
per-source lock heartbeats through the direct pool and refuses to steal a live,
|
||||
recently-refreshed holder. Six env knobs tune it (all env-only, incident-time escape
|
||||
hatches — no config-dashboard surface by design):
|
||||
|
||||
| Env var | Default | What it does |
|
||||
|---|---|---|
|
||||
| `GBRAIN_SYNC_CHECKPOINT_EVERY` | 1000 | Flush the checkpoint every N drained files. |
|
||||
| `GBRAIN_SYNC_CHECKPOINT_SECONDS` | 10 | Also flush every N seconds (whichever comes first) — bounds worst-case loss regardless of throughput. Flush also fires after the first file. |
|
||||
| `GBRAIN_SYNC_MAX_CHECKPOINT_FAILURES` | 3 | Consecutive failed flushes (each already retried ~12s) before the run aborts with `reason: 'checkpoint_unavailable'` instead of importing work it can never bank. |
|
||||
| `GBRAIN_SYNC_YIELD_EVERY` | 64 | Yield the event loop (`setTimeout(0)`, NOT `setImmediate` — Bun starves the timers phase under a tight setImmediate loop) every N files so the lock-refresh `setInterval` heartbeat fires mid-import. |
|
||||
| `GBRAIN_LOCK_STEAL_GRACE_SECONDS` | derived (~600 at 30min TTL) | A holder that refreshed within this window is NOT stolen even if its TTL lapsed (starved-but-alive). Dead holders stop refreshing, age past the grace, and become stealable; TTL stays the backstop. |
|
||||
| `GBRAIN_SYNC_STALL_ABORT_SECONDS` | 900 | Progress-aware stall watchdog (#1950): if the import drain makes no forward progress (keyed on file-import progress, NOT the lock heartbeat) for N seconds, abort the run and release the per-source lock so the next `gbrain sync` resumes from the checkpoint. Reports `reason: 'stall_timeout'`. Observed BETWEEN files; a hang inside one file's import isn't interrupted until it returns (the wall-clock hard deadline is that backstop). 0 disables. |
|
||||
|
||||
## Pace Mode (DB-contention-aware backfill pacing)
|
||||
|
||||
A naive `gbrain embed --stale` / large `sync` can saturate a PgBouncer
|
||||
transaction-mode pooler and starve the minion supervisor's lock renewals
|
||||
(`lock-renewal-failed` → dead jobs). Pacing is the native, composable fix — it
|
||||
replaces external SIGSTOP/SIGCONT wrapper scripts. **Opt-in: default mode `off`.**
|
||||
|
||||
The composable primitive is `src/core/db-pacer.ts` (`createDbPacer`):
|
||||
- **Concurrency cap is the real lever** (caps simultaneous in-flight DB writes =
|
||||
pooler slots held). Embed paths set their worker count to `maxConcurrency`
|
||||
(single pool, no permit); `sync` uses the shared `acquire()` **permit** because
|
||||
each parallel worker owns a separate engine (one budget must span pools).
|
||||
- **In-band signal** (`observe(ms)` EWMA from the work's own queries — never
|
||||
blind the way an out-of-band probe pool was). **No probe loop, no
|
||||
`probeLatency` engine method.**
|
||||
- **Cooperative `pace()` sleep** on `setTimeout` (keeps the lock heartbeat
|
||||
firing), jittered to avoid a thundering-herd resume. `acquire()`/`pace()` throw
|
||||
`AbortError` on cancel; everything else is fail-open (a pacer bug never kills a
|
||||
backfill, never throws an unhandledRejection).
|
||||
|
||||
Named bundles resolve through `src/core/pace-mode.ts` (`resolvePaceMode`), mirror
|
||||
of the search-mode pattern but with **env ABOVE config** (incident escape hatch):
|
||||
|
||||
per-call flag → GBRAIN_PACE_* env → config (pace.*) → PACE_BUNDLES[mode] → off
|
||||
|
||||
| Knob | off | gentle | balanced | aggressive |
|
||||
|---|---|---|---|---|
|
||||
| `maxConcurrency` | (off) | 4 | 8 | 16 |
|
||||
| `paceAtMs` (EWMA → sleep) | — | 250 | 500 | 1000 |
|
||||
| `maxSleepMs` (jittered cap) | — | 2000 | 1500 | 1000 |
|
||||
|
||||
**Surfaces.** `gbrain embed --stale --pace[=mode]` (bare `--pace` = balanced),
|
||||
`--pace-max-concurrency=N`. `--background` carries explicit pace OVERRIDES (not
|
||||
the resolved bundle) into the `embed` job payload; the handler re-resolves
|
||||
env>config>bundle at execution so `GBRAIN_PACE_*` still wins (CX5). Config-level
|
||||
`pace.mode` paces EVERY `runEmbedCore` caller (cycle embed, embed-catch-up,
|
||||
sync-auto-embed) and the prod `embed-backfill` job automatically. `sync` reads
|
||||
env/config. PGLite / mode `off` → no-op pacer.
|
||||
|
||||
**Correctness fixes pacing bundles** (longer paced runs widen these): CLI
|
||||
`embed --stale` single-flights via the SAME per-source lock key as the
|
||||
`embed-backfill` handler (`src/core/embed-backfill-lock.ts`; all-source runs lock
|
||||
every source in sorted order) so a hand-run backfill and a queued job can't race
|
||||
the NULL→non-NULL upsert (`TODOS:2299`); a **bounded** end-of-run keyset re-entry
|
||||
(max 3 + forward-progress, paced runs only) catches rows inserted behind the
|
||||
cursor (`TODOS:2301`); and the embed wall-clock budget timer is re-armed around
|
||||
`pace()` sleeps so paced time doesn't burn the work budget.
|
||||
|
||||
`EmbedResult.pacing` carries the end-of-run telemetry (cap, samples, EWMA, slept
|
||||
ms, max waiters) for `--json`; a one-line summary prints to stderr.
|
||||
|
||||
## Build
|
||||
|
||||
`bun build --compile --outfile bin/gbrain src/cli.ts`
|
||||
@@ -1408,7 +1305,6 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
|
||||
| Morning prep, meeting context, day planning | `skills/daily-task-prep/SKILL.md` |
|
||||
| Daily briefing, "what's happening today" | `skills/briefing/SKILL.md` |
|
||||
| Cron scheduling, quiet hours, job staggering | `skills/cron-scheduler/SKILL.md` |
|
||||
| "get more out of gbrain", "is my brain set up right", "weekly brain checkup", "advise me on my brain", "gbrain advisor" | `skills/gbrain-advisor/SKILL.md` |
|
||||
| Save or load reports | `skills/reports/SKILL.md` |
|
||||
| "Create a skill", "improve this skill" | `skills/skill-creator/SKILL.md` |
|
||||
| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/SKILL.md` |
|
||||
@@ -1752,24 +1648,6 @@ The whole loop is described in [`docs/architecture/topologies.md`](docs/architec
|
||||
|
||||
**Job queue (Minions).** BullMQ-shaped, Postgres-native job queue. Durable subagents (LLM tool loops that survive crashes via two-phase pending→done persistence), shell jobs with audit, child jobs with cascading timeouts, rate leases for outbound providers, attachments via S3/Supabase storage. Replaces "spawn subagent as fire-and-forget Promise" with something that recovers from anything.
|
||||
|
||||
**Non-English brains (FTS language config).** The Postgres full-text search tokenizer is configurable via `GBRAIN_FTS_LANGUAGE`. Defaults to `english`. Set it to any text-search configuration that exists in your Postgres instance:
|
||||
|
||||
```bash
|
||||
export GBRAIN_FTS_LANGUAGE=portuguese # uses built-in portuguese stemmer
|
||||
export GBRAIN_FTS_LANGUAGE=spanish # built-in spanish stemmer
|
||||
export GBRAIN_FTS_LANGUAGE=pt_br # custom config (e.g. unaccent + portuguese)
|
||||
```
|
||||
|
||||
List available configs: `psql -c "SELECT cfgname FROM pg_ts_config"`. Both the **query side** (`websearch_to_tsquery`) and the **write side** (the trigger functions that populate `pages.search_vector` and `content_chunks.search_vector`) honor `GBRAIN_FTS_LANGUAGE`. On first install (or upgrade), the `configurable_fts_language` schema migration reads the env var and creates trigger functions in the configured language; subsequent inserts/updates tokenize using that setting. To change language on a brain that has already run the migration, use the dedicated CLI command:
|
||||
|
||||
```bash
|
||||
export GBRAIN_FTS_LANGUAGE=portuguese
|
||||
gbrain reindex-search-vector --dry-run # preview row counts
|
||||
gbrain reindex-search-vector --yes # recreate triggers + backfill
|
||||
```
|
||||
|
||||
The command is idempotent (re-running with the same language is a no-op for vector content) and uses the same recreate-and-backfill primitives as the migration. For accent-insensitive Portuguese (`pt_br`), see [docs/guides/multi-language-fts.md](docs/guides/multi-language-fts.md) for the `unaccent` + portuguese stemmer recipe.
|
||||
|
||||
**43 curated skills.** Routing lives in [`skills/RESOLVER.md`](skills/RESOLVER.md). Covers signal capture, ingest (idea / media / meeting), enrichment, querying, brain ops, citation fixing, daily task management, cron scheduling, reports, voice, soul audit, skill creation, eval framework, and migrations. Skills are markdown files (tool-agnostic), packaged as a single skillpack the installer drops into your agent workspace.
|
||||
|
||||
**Eval framework.** `gbrain eval longmemeval` runs the public [LongMemEval](https://huggingface.co/datasets/xiaowu0162/longmemeval) benchmark against your hybrid retrieval. `gbrain eval export` + `gbrain eval replay` capture real queries and replay them against code changes (set `GBRAIN_CONTRIBUTOR_MODE=1`). `gbrain eval cross-modal` cross-checks an output against the task using three different-provider frontier models. `gbrain eval retrieval-quality` runs NamedThingBench, which hard-gates the named-thing retrieval families (title-substring, alias-synonym, generic-to-named, multi-chunk-dilution) so a regression in "find the page this query names" fails CI loudly. Full methodology in [`docs/eval/SEARCH_MODE_METHODOLOGY.md`](docs/eval/SEARCH_MODE_METHODOLOGY.md).
|
||||
@@ -1801,8 +1679,6 @@ Data flowing into the brain. Each integration is a recipe — markdown + setup h
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
**`gbrain init --pglite` crashes on macOS 26.x (Tahoe)?** PGLite's embedded WASM engine is incompatible with macOS 26.x on Apple Silicon. The fix is to use native Homebrew PostgreSQL + pgvector instead. Full step-by-step setup in [`docs/INSTALL.md` — Troubleshooting: PGLite crashes on macOS 26.x](docs/INSTALL.md#pglite-crashes-on-macos-26x-tahoe).
|
||||
|
||||
**`gbrain import` fails with `expected N dimensions, not M`?** Run `gbrain doctor`. It will print the exact `gbrain config set ...` or `gbrain retrieval-upgrade` command to repair the mismatch. You should not need to delete `~/.gbrain`. Fresh `gbrain init --pglite` auto-detects your embedding provider from API keys in your environment: set `OPENAI_API_KEY` (or `ZEROENTROPY_API_KEY` / `VOYAGE_API_KEY`) before running init, or pass `--embedding-model <provider>:<model>` explicitly. With multiple keys set, init fires an interactive picker. In non-TTY contexts (CI, Docker) with no keys, init exits 1 with a paste-ready setup hint; pass `--no-embedding` to defer setup until runtime. See [`docs/integrations/embedding-providers.md`](docs/integrations/embedding-providers.md) for the full provider matrix and [`docs/operations/headless-install.md`](docs/operations/headless-install.md) for Docker/CI sequencing.
|
||||
|
||||
**Hourly cron sync keeps timing out on a federated brain?** v0.41.13.0 ships
|
||||
@@ -2059,7 +1935,7 @@ export interface BrainEngine {
|
||||
|
||||
**Slug-based API, not ID-based.** Every method takes slugs, not numeric IDs. The engine resolves slugs to IDs internally. This keeps the interface portable... slugs are strings, IDs are database-specific.
|
||||
|
||||
**Embedding is NOT in the engine.** The engine stores embeddings and searches by vector, but it doesn't generate embeddings. `src/core/embedding.ts` handles that (a thin delegation to the provider-agnostic AI gateway in `src/core/ai/gateway.ts`). This is intentional: embedding is an external API call (OpenAI, Voyage, a local Ollama — whichever provider you configured), not a storage concern. All engines share the same embedding service.
|
||||
**Embedding is NOT in the engine.** The engine stores embeddings and searches by vector, but it doesn't generate embeddings. `src/core/embedding.ts` handles that. This is intentional: embedding is an external API call (OpenAI), not a storage concern. All engines share the same embedding service.
|
||||
|
||||
**Chunking is NOT in the engine.** Same logic. `src/core/chunkers/` handles chunking. The engine stores and retrieves chunks. All engines share the same chunkers.
|
||||
|
||||
@@ -2113,51 +1989,6 @@ RRF fusion, multi-query expansion, and 4-layer dedup are engine-agnostic. They o
|
||||
|
||||
**Why not self-hosted for v0:** The brain should be infrastructure agents use, not something you maintain. Self-hosted Postgres with Docker is a welcome community PR, but v0 optimizes for zero ops.
|
||||
|
||||
### Opt-in RLS source-scope binding (`GBRAIN_RLS_SCOPE_BINDING`)
|
||||
|
||||
Defense-in-depth layer for Postgres deployments that want the database itself
|
||||
to enforce source isolation, in addition to the mandatory app-layer filters
|
||||
(`sourceScopeOpts` — layer 1, always on).
|
||||
|
||||
**Mechanism.** With `GBRAIN_RLS_SCOPE_BINDING=1` (or `true`), the engine's
|
||||
source-scoped read methods wrap their queries in a transaction that first runs
|
||||
`SELECT set_config('app.scopes', $1, true)` — the value is a bound parameter
|
||||
(federated `sourceIds` CSV > scalar `sourceId` > `'*'` for unscoped internal
|
||||
reads), transaction-local (equivalent to `SET LOCAL`, which itself can't take
|
||||
bound params). An RLS policy can then filter rows by
|
||||
`current_setting('app.scopes', true)`.
|
||||
|
||||
**Default off.** With the env var unset, reads call through on the shared pool
|
||||
exactly as before — no per-read transaction, no pool-slot hold (the search
|
||||
methods keep the transaction they always had for their `SET LOCAL
|
||||
statement_timeout`). Existing operators see zero behavior change.
|
||||
|
||||
**Enabling it** (operator-managed SQL; gbrain ships no DDL for this):
|
||||
|
||||
```sql
|
||||
ALTER TABLE pages ENABLE ROW LEVEL SECURITY;
|
||||
CREATE POLICY pages_scope_filter ON pages
|
||||
USING (current_setting('app.scopes', true) = '*'
|
||||
OR source_id = ANY(string_to_array(current_setting('app.scopes', true), ',')));
|
||||
|
||||
-- Required: connections that don't run through the scoped read helper
|
||||
-- (admin, autopilot, cycle, writes) must default to unscoped, or they
|
||||
-- see zero rows once the policy exists:
|
||||
ALTER ROLE <runtime-role> SET app.scopes = '*';
|
||||
|
||||
-- If the runtime role OWNS the table, RLS is skipped for it unless forced:
|
||||
ALTER TABLE pages FORCE ROW LEVEL SECURITY;
|
||||
```
|
||||
|
||||
Safe to enable in either order: the env var without a policy is a no-op
|
||||
setting; a policy without the env var is enforced only via the role default.
|
||||
|
||||
**Honest caveat:** only read paths routed through the scoped helper carry a
|
||||
per-request scope binding — unwrapped paths (writes, admin/maintenance reads)
|
||||
run under the role default and are not backstopped per caller. This is layer 2;
|
||||
the app-layer source filters remain layer 1 and stay mandatory. Behavioral pins
|
||||
live in `test/postgres-engine-rls-scope.test.ts`.
|
||||
|
||||
## PGLiteEngine (v0.7, ships)
|
||||
|
||||
**Dependencies:** `@electric-sql/pglite` (v0.4.4+)
|
||||
@@ -2186,39 +2017,6 @@ live in `test/postgres-engine-rls-scope.test.ts`.
|
||||
|
||||
**Migration:** `gbrain migrate --to supabase` exports everything (pages, chunks, embeddings, links, tags, timeline) and imports into Supabase. `gbrain migrate --to pglite` goes the other direction. Bidirectional, lossless.
|
||||
|
||||
## JSONB writes: never double-encode (the #2339 trap)
|
||||
|
||||
Writing a JS value into a `jsonb` column has exactly two correct forms. Get this
|
||||
wrong and the write succeeds on PGLite but stores a **jsonb string scalar** on
|
||||
real Postgres — `col ->> 'k'` returns NULL, `jsonb_array_elements` throws, and a
|
||||
`jsonb_typeof = 'array'` CHECK rejects the row (this aborted every sync in #2339).
|
||||
|
||||
| Form | Verdict |
|
||||
|---|---|
|
||||
| Template tag: `` sql`... ${sql.json(obj)}` `` (postgres-engine only) | ✅ native jsonb serialization |
|
||||
| Positional raw call, raw object: `executeRawJsonb(engine, sql, scalars, [obj])` | ✅ object reaches the wire as jsonb |
|
||||
| Positional raw call, stringified: `executeRaw(\`... $N::text::jsonb\`, [JSON.stringify(x)])` | ✅ binds as text, the cast parses it |
|
||||
| Positional raw call, BARE cast: `executeRaw(\`... $N::jsonb\`, [JSON.stringify(x)])` | ❌ **double-encodes** under postgres.js `.unsafe()` |
|
||||
| Template literal interpolation: `` `... ${JSON.stringify(x)}::jsonb` `` | ❌ double-encodes |
|
||||
|
||||
**Why:** postgres.js `.unsafe(sql, params)` (the path behind `executeRaw` /
|
||||
`executeRawDirect`) binds a JS **string** as a text param. A bare `$N::jsonb`
|
||||
cast then wraps that already-JSON string into a jsonb scalar string instead of
|
||||
parsing it. Casting through `$N::text::jsonb` forces a text→jsonb parse.
|
||||
**PGLite's `db.query` parses text→jsonb natively, so it hides the bug** — which is
|
||||
why a regression only shows up on Postgres (and why the parity test must run there).
|
||||
|
||||
**Two CI guards enforce this, both wired into `scripts/check-jsonb-pattern.sh`:**
|
||||
- the template-tag grep (`${JSON.stringify(x)}::jsonb`), and
|
||||
- `scripts/check-jsonb-params.mjs`, an AST-lite scanner for the positional
|
||||
`$N::jsonb` + `JSON.stringify` form the grep misses. Sanctioned escapes:
|
||||
`$N::text::jsonb`, `$N::text[]`, `executeRawJsonb`, `sql.json`, or an inline
|
||||
`jsonb-guard-ok` comment.
|
||||
|
||||
The real backstop is `test/e2e/op-checkpoint-jsonb-parity.test.ts` +
|
||||
`test/e2e/jsonb-roundtrip.test.ts`, which round-trip writes through real Postgres
|
||||
and assert `jsonb_typeof` — the assertion PGLite cannot make.
|
||||
|
||||
## Adding a new engine
|
||||
|
||||
1. Create `src/core/<name>-engine.ts` implementing `BrainEngine`
|
||||
@@ -2830,16 +2628,6 @@ hashes match. If both a cron and `--watch` fire simultaneously, no conflict.
|
||||
history rewrite still hard-blocks even with `--skip-failed`. Run
|
||||
`gbrain sync --skip-failed` to acknowledge a known-bad set yourself.
|
||||
|
||||
5. **Import checkpoints name the import target, not the caller's CWD.**
|
||||
Interrupted `gbrain import <dir>` runs may leave
|
||||
`~/.gbrain/import-checkpoint.json` so the next import can resume. The
|
||||
checkpoint `dir` is the absolute, resolved import target captured when
|
||||
import starts. It is not a cleanup instruction and it must not be
|
||||
re-derived from the process working directory. Checkpoints written by
|
||||
gbrain include `schema_version: 1`, `owner: "gbrain"`, and
|
||||
`kind: "import"` so downstream tools can validate the contract before
|
||||
deciding whether to resume.
|
||||
|
||||
## How to Verify
|
||||
|
||||
1. **Edit a file and search for the change.** Edit a brain markdown file,
|
||||
@@ -3552,92 +3340,6 @@ the bundled resolver lives at [`skills/RESOLVER.md`](../../skills/RESOLVER.md).
|
||||
|
||||
---
|
||||
|
||||
## docs/guides/push-context.md
|
||||
|
||||
Source: https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/push-context.md
|
||||
|
||||
# Push-based context (#2095, v0.42.43.0)
|
||||
|
||||
Retrieval used to be pull-only: the agent had to *know to ask* before the brain
|
||||
contributed anything. Push-based context inverts that — the brain volunteers
|
||||
relevant pages from the recent conversation, confidence-gated so push noise
|
||||
never becomes worse than pull silence.
|
||||
|
||||
Three channels share one zero-LLM core (`src/core/context/volunteer.ts`):
|
||||
|
||||
| Channel | Surface | When to use |
|
||||
|---|---|---|
|
||||
| `reflex` | automatic, inside the context engine | default-on for plugin hosts; nothing to call |
|
||||
| `op` | `gbrain volunteer-context` / MCP `volunteer_context` | agents without the plugin; one call per turn |
|
||||
| `watch` | `gbrain watch` | stream a transcript in, volunteered pages stream out |
|
||||
|
||||
## How it decides
|
||||
|
||||
1. **Extract** entities across the last N turns (capitalized runs, `@handles`),
|
||||
merged with recency / frequency / user-role salience. Assistant-introduced
|
||||
entities and "what did she invest in?" follow-ups whose antecedent was named
|
||||
in the window now resolve.
|
||||
2. **Resolve** through the alias table, exact titles, and slug suffixes — each
|
||||
arm carries an honest confidence: alias 0.9, exact title 0.8, slug-suffix 0.6,
|
||||
+0.05 when mentioned in ≥2 turns or the newest turn.
|
||||
3. **Gate** at `min_confidence` (default 0.7 — slug-suffix matches need an
|
||||
explicit lower gate), suppress pages already surfaced (slug-presence only),
|
||||
cap at 3 pages (hard cap 5).
|
||||
|
||||
## CLI
|
||||
|
||||
```bash
|
||||
# one-shot: pipe recent turns (oldest → newest)
|
||||
printf 'user: ask alice-example about the deal\nassistant: noted\nuser: what did she say?\n' \
|
||||
| gbrain volunteer-context
|
||||
|
||||
# streaming: volunteered pages print as the transcript flows
|
||||
some-transcript-feed | gbrain watch --json
|
||||
|
||||
# the feedback loop: how often were volunteered pages actually opened?
|
||||
gbrain volunteer-context --stats
|
||||
```
|
||||
|
||||
Stats are **approximate** by design: "used" means `pages.last_retrieved_at >
|
||||
volunteered_at` — the 5-minute last-retrieved throttle causes false negatives
|
||||
and unrelated reads of the same page cause false positives. Use the per-arm
|
||||
precision to tune `min_confidence`, not as an exact metric.
|
||||
|
||||
**PGLite + `gbrain watch`:** PGLite is single-connection, and watch holds its
|
||||
connection for the whole session — a concurrent `gbrain serve` or any write
|
||||
path blocks until watch exits. On a PGLite brain, run watch in bursts (piped
|
||||
input exits at EOF) or use the ambient reflex channel instead, which routes
|
||||
through a running serve's resolve socket rather than taking the lock. Routing
|
||||
watch through that same socket is a filed follow-up (TODOS.md). Postgres
|
||||
brains are unaffected.
|
||||
|
||||
## Config
|
||||
|
||||
| Key | Default | What it does |
|
||||
|---|---|---|
|
||||
| `retrieval_reflex_window_turns` | 4 | turns the ambient reflex extracts from; 1 = legacy current-turn-only (file/env plane: `GBRAIN_RETRIEVAL_REFLEX_WINDOW_TURNS`) |
|
||||
| `retrieval_reflex` | true | the ambient channel's master switch |
|
||||
| `retrieval_reflex_max_pointers` | 3 | pointer cap per turn |
|
||||
|
||||
Per-call knobs: `max_pages` + `min_confidence` on both the op and `gbrain watch`
|
||||
(`--max-pages` / `--min-confidence`, plus `--window-turns` / `--source` on watch);
|
||||
on the op only: `prior_context` (text whose already-surfaced slugs are suppressed),
|
||||
`session_id` / `turn` attribution params (watch stamps its own per-session id and
|
||||
turn numbers in the feedback log), and `days` to size the `--stats` window.
|
||||
|
||||
## Storage + privacy
|
||||
|
||||
Volunteered pages log to `context_volunteer_events` (migration v117): slug,
|
||||
arm, confidence, channel, optional session/turn — the rationale is a
|
||||
deterministic template string, never raw conversation text. Event writes are
|
||||
best-effort (fire-and-forget, drained at CLI exit) — the log is a tuning signal,
|
||||
not an audit trail. Rows are pruned after 90 days by the dream cycle's purge
|
||||
phase. Synopses always strip the takes/facts fences — the same strip `get_page`
|
||||
applies to untrusted callers, applied unconditionally here so private fence rows
|
||||
never reach a prompt regardless of caller trust.
|
||||
|
||||
---
|
||||
|
||||
## docs/mcp/DEPLOY.md
|
||||
|
||||
Source: https://raw.githubusercontent.com/garrytan/gbrain/master/docs/mcp/DEPLOY.md
|
||||
@@ -3718,20 +3420,13 @@ to the HTTP server, so no migration is required.
|
||||
gbrain serve --http --port 3131
|
||||
```
|
||||
|
||||
On first start in an interactive terminal, the server prints an **admin
|
||||
bootstrap token** to stderr:
|
||||
On first start, the server prints an **admin bootstrap token** to stderr:
|
||||
|
||||
```
|
||||
Admin bootstrap token: 3a1f9c...
|
||||
Open http://localhost:3131/admin and paste it to log in.
|
||||
```
|
||||
|
||||
On a non-TTY start (systemd, Docker, any piped or captured logs) the generated
|
||||
token is hidden so it never lands in log storage. For headless deploys either
|
||||
set `GBRAIN_ADMIN_BOOTSTRAP_TOKEN` to a value you control before starting, or
|
||||
run `gbrain serve --http --print-admin-token` once on a trusted terminal to
|
||||
force printing.
|
||||
|
||||
Save this token. Open `http://localhost:3131/admin` and paste it to access the
|
||||
dashboard. The dashboard shows live activity, registered clients, request logs,
|
||||
and per-client config export.
|
||||
|
||||
@@ -25,7 +25,6 @@ Repo: https://github.com/garrytan/gbrain
|
||||
- [docs/guides/minions-deployment.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/minions-deployment.md): Deploying the gbrain jobs worker: crontab + watchdog, inline --follow, systemd/Procfile/fly.toml, upgrade checklist.
|
||||
- [docs/guides/quiet-hours.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/quiet-hours.md): Notification hold + timezone-aware delivery.
|
||||
- [docs/guides/scaling-skills.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/scaling-skills.md): Three-tier architecture for agents with 300+ skills: always-loaded, resolver-routed, and dormant. Per-turn token math, the v0.41.7.0 compact list-format resolver, and the `gbrain doctor` safety net. 306 skills, ~21K tokens freed per turn, zero capability loss.
|
||||
- [docs/guides/push-context.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/push-context.md): Push-based context: the brain volunteers confidence-gated pages from the rolling conversation window. Three channels (ambient reflex, volunteer_context op, gbrain watch), config knobs, and the volunteered-vs-used feedback loop.
|
||||
- [docs/mcp/DEPLOY.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/mcp/DEPLOY.md): MCP server deployment.
|
||||
|
||||
## AI providers
|
||||
|
||||
@@ -46,7 +46,6 @@
|
||||
"skills/data-research",
|
||||
"skills/enrich",
|
||||
"skills/functional-area-resolver",
|
||||
"skills/gbrain-advisor",
|
||||
"skills/idea-ingest",
|
||||
"skills/idea-lineage",
|
||||
"skills/ingest",
|
||||
|
||||
+4
-16
@@ -65,7 +65,6 @@
|
||||
"ci:select-e2e": "bun run scripts/select-e2e.ts",
|
||||
"typecheck": "tsc --noEmit",
|
||||
"check:jsonb": "scripts/check-jsonb-pattern.sh",
|
||||
"check:search-path": "scripts/check-search-path.sh",
|
||||
"check:no-double-retry": "scripts/check-no-double-retry.sh",
|
||||
"check:batch-audit-site": "scripts/check-batch-audit-site.sh",
|
||||
"check:worker-lock-renewal-shape": "scripts/check-worker-lock-renewal-shape.sh",
|
||||
@@ -84,7 +83,7 @@
|
||||
"check:fixture-privacy": "scripts/check-fixture-privacy.sh",
|
||||
"check:conversation-parser": "bun src/cli.ts eval conversation-parser test/fixtures/conversation-formats/all.jsonl --no-llm",
|
||||
"check:source-scope-onboard": "scripts/check-source-scope-onboard.sh",
|
||||
"postinstall": "bun run scripts/postinstall.ts",
|
||||
"postinstall": "command -v gbrain >/dev/null 2>&1 && gbrain apply-migrations --yes --non-interactive || echo '[gbrain] postinstall skipped. If installed via bun install -g github:...: run `gbrain doctor` and `gbrain apply-migrations --yes` manually. See https://github.com/garrytan/gbrain/issues/218' 1>&2",
|
||||
"prepublish:clawhub": "bun run build:all",
|
||||
"publish:clawhub": "clawhub package publish . --family bundle-plugin"
|
||||
},
|
||||
@@ -118,8 +117,8 @@
|
||||
"express-rate-limit": "^7.5.0",
|
||||
"gray-matter": "^4.0.3",
|
||||
"heic-decode": "^2.1.0",
|
||||
"js-yaml": "^3.15.0",
|
||||
"marked": "^18.0.2",
|
||||
"js-yaml": "^3.14.2",
|
||||
"marked": "^18.0.0",
|
||||
"openai": "^4.0.0",
|
||||
"pgvector": "^0.2.0",
|
||||
"postgres": "^3.4.0",
|
||||
@@ -144,16 +143,5 @@
|
||||
"bun": ">=1.3.10"
|
||||
},
|
||||
"license": "MIT",
|
||||
"version": "0.42.64.0",
|
||||
"overrides": {
|
||||
"@hono/node-server": "^1.19.13",
|
||||
"fast-uri": "^3.1.2",
|
||||
"fast-xml-builder": "^1.1.7",
|
||||
"fast-xml-parser": "^5.7.0",
|
||||
"form-data": "^4.0.6",
|
||||
"hono": "^4.12.25",
|
||||
"ip-address": "^10.1.1",
|
||||
"qs": "^6.15.2",
|
||||
"js-yaml": "^3.15.0"
|
||||
}
|
||||
"version": "0.42.33.0"
|
||||
}
|
||||
|
||||
@@ -1,54 +0,0 @@
|
||||
---
|
||||
id: retrieval-reflex
|
||||
name: Retrieval Reflex
|
||||
version: 0.1.0
|
||||
description: Teaches the host agent WHEN to look something up and WHAT to pull. Ships a policy skill (trigger + retrieval spec) into the host resolver; pairs with the deterministic pointer layer in the context engine.
|
||||
category: reflex
|
||||
install_kind: copy-into-host-repo
|
||||
requires: []
|
||||
secrets: []
|
||||
health_checks:
|
||||
- type: command
|
||||
argv: [gbrain, doctor, --json]
|
||||
label: Retrieval reflex wiring (see retrieval_reflex_health)
|
||||
setup_time: 2 min
|
||||
cost_estimate: "$0 — zero-LLM deterministic layer + a prose policy skill"
|
||||
---
|
||||
|
||||
# Retrieval Reflex: teach the agent *when* and *what* to retrieve
|
||||
|
||||
gbrain is great at **storing** knowledge and at **injecting deterministic
|
||||
context** every turn. It does not, by itself, teach the host agent the *policy*
|
||||
of retrieval: **when** to look something up and **what** to pull. Without it,
|
||||
the agent can discuss a person who has a rich brain page for several messages
|
||||
without ever opening it — then answer generically about facts the brain already
|
||||
knew.
|
||||
|
||||
This reflex has two halves:
|
||||
|
||||
1. **Deterministic pointer layer (automatic, on by default).** The
|
||||
`gbrain-context` engine scans each turn's user message for salient,
|
||||
resolvable entities and injects a compact pointer (name → slug → one-line
|
||||
summary) so the agent *knows the page exists*. Zero-LLM, fail-open. Nothing
|
||||
to install — it's on unless `retrieval_reflex` is disabled in
|
||||
`~/.gbrain/config.json` or `GBRAIN_RETRIEVAL_REFLEX=false`.
|
||||
|
||||
2. **Policy skill (this recipe installs it).** A SKILL fragment in the host
|
||||
resolver that encodes the trigger policy and retrieval spec the agent
|
||||
follows when a pointer appears or an entity becomes the subject.
|
||||
|
||||
## IMPORTANT: Instructions for the Agent
|
||||
|
||||
**You are the installer.** Run these steps on behalf of the user.
|
||||
|
||||
1. Confirm the deterministic layer isn't disabled:
|
||||
`gbrain doctor --json | jq '.checks[] | select(.name=="retrieval_reflex_health")'`
|
||||
2. Install the policy skill into the host repo (the OpenClaw/agent repo that
|
||||
holds `skills/RESOLVER.md` or `AGENTS.md`):
|
||||
`gbrain integrations install retrieval-reflex --target <host-repo>`
|
||||
3. Verify: re-run `gbrain doctor` and confirm `retrieval_reflex_health` is `ok`.
|
||||
|
||||
The deterministic layer needs no install. On a PGLite brain it resolves through
|
||||
the running `gbrain serve` (or a host-provided capability); if neither is
|
||||
available it stays disabled and this policy skill carries the behavior — the
|
||||
doctor check reports which.
|
||||
@@ -1,16 +0,0 @@
|
||||
{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"recipe": "retrieval-reflex",
|
||||
"version": "0.1.0",
|
||||
"install_kind": "copy-into-host-repo",
|
||||
"description": "src → target mapping consumed by `gbrain integrations install retrieval-reflex`. Policy-only recipe: ships one SKILL.md into the host resolver and appends a resolver row. The deterministic pointer layer lives in the gbrain context engine and needs no install.",
|
||||
"target_root_relative_to_host_repo": "skills/retrieval-reflex",
|
||||
"skills_target_root_relative_to_host_repo": "skills",
|
||||
"files": [],
|
||||
"skills": [
|
||||
{ "src": "skills/retrieval-reflex/SKILL.md", "target": "skills/retrieval-reflex/SKILL.md", "mode": "0644" }
|
||||
],
|
||||
"resolver_rows_to_append": [
|
||||
"retrieval-reflex | a named person/company/project/place becomes the subject; a brain-page pointer appears in context; \"who is\", \"what do we know about\", \"tell me about\"; about to assert a non-trivial detail about a named entity"
|
||||
]
|
||||
}
|
||||
@@ -1,59 +0,0 @@
|
||||
---
|
||||
name: retrieval-reflex
|
||||
version: 0.1.0
|
||||
description: When/what to retrieve — open the brain page for a salient entity before answering from memory.
|
||||
triggers:
|
||||
- "who is"
|
||||
- "what do we know about"
|
||||
- "tell me about"
|
||||
mutating: false
|
||||
writes_pages: false
|
||||
writes_to: []
|
||||
tools: [get_page, query, graph, backlinks]
|
||||
---
|
||||
|
||||
# Retrieval Reflex — retrieve on demand, when an entity is salient
|
||||
|
||||
A person doesn't bulk-load their whole address book into working memory. They
|
||||
retrieve **on demand**, when an entity becomes **salient**, use it, and drop it.
|
||||
Encode that reflex. The brain probably has the data — if a name is salient and
|
||||
you haven't opened its page, open it before you answer.
|
||||
|
||||
## Trigger policy — WHEN to retrieve
|
||||
|
||||
Retrieve when ANY of these holds AND the page isn't already loaded in context:
|
||||
|
||||
- An entity (person / company / project / deal / place) is the **subject** of
|
||||
the message, or a decision/judgment about it is being made, or the exchange is
|
||||
substantive / relational / emotional about it.
|
||||
- A **brain-page pointer** appeared in context this turn (the deterministic
|
||||
layer told you the page exists) — open it before relying on details.
|
||||
- A name or term appears that you **don't recognize** and that looks notable →
|
||||
do a quick resolve (the human reflex).
|
||||
- You're about to **assert a non-trivial detail** about an entity (attribution,
|
||||
status, history) → verify against the brain first. Say "let me check", not a guess.
|
||||
|
||||
**Skip** trivial passing mentions, logistics pings, and anything already loaded.
|
||||
Judgment first — retrieve when it changes the quality of the reply, not reflexively.
|
||||
|
||||
## Retrieval spec — WHAT to pull, and when to stop
|
||||
|
||||
Escalate only as far as the task needs:
|
||||
|
||||
1. **Pointer / metadata.** If a pointer is already in context (slug + one-line
|
||||
summary), and the task only needs identity, stop there.
|
||||
2. **Full page.** When the entity is the subject or details matter, open it:
|
||||
`get_page <slug>` (MCP) — read the page before relying on specifics.
|
||||
3. **Linked neighbors.** Only when relationship context is needed, pull
|
||||
`graph` / `backlinks` for the slug.
|
||||
|
||||
**Resolve only the name(s) the current task needs, use them, drop them.** No
|
||||
bulk-loading the inner circle.
|
||||
|
||||
## The failure this prevents
|
||||
|
||||
If you've discussed a named person for more than a message without opening their
|
||||
page, open it now. The write side captures everything; the read side only helps
|
||||
if you actually look.
|
||||
|
||||
See also: `skills/query/SKILL.md` (search the brain), `skills/brain-ops/SKILL.md`.
|
||||
@@ -1,128 +0,0 @@
|
||||
#!/usr/bin/env node
|
||||
/**
|
||||
* CI guard for the POSITIONAL jsonb double-encode footgun (#2339 / #2324 class).
|
||||
*
|
||||
* The legacy scripts/check-jsonb-pattern.sh only catches the template-tag form
|
||||
* (`${JSON.stringify(x)}::jsonb`). It MISSES the positional-param form:
|
||||
*
|
||||
* engine.executeRaw(`... $3::jsonb ...`, [a, b, JSON.stringify(x)])
|
||||
*
|
||||
* Under postgres.js `.unsafe(sql, params)` a JS STRING bound to a `$N::jsonb`
|
||||
* param double-encodes — the text→jsonb cast wraps the already-JSON string into a
|
||||
* jsonb *string scalar*. PGLite parses it silently, so the bug is invisible in
|
||||
* unit tests and only bites on real Postgres (it aborted every sync in #2339).
|
||||
*
|
||||
* This scanner flags any executeRaw / executeRawDirect / .unsafe(...) call whose
|
||||
* balanced argument span contains BOTH a positional `$N::jsonb` cast
|
||||
* (NOT `$N::text::jsonb`, NOT `$N::text[]`) AND a `JSON.stringify(` — the exact
|
||||
* double-encode shape. It is heuristic by design (whole-span correlation); the
|
||||
* real backstop is the DATABASE_URL-gated e2e parity test. Keep both.
|
||||
*
|
||||
* Allowed forms (NOT flagged):
|
||||
* - `$N::text::jsonb` + JSON.stringify (the fix: binds as text, cast parses it)
|
||||
* - `$N::text[]` (the unnest path — arrays bind fine)
|
||||
* - executeRawJsonb(...) (passes raw objects, not strings)
|
||||
* - sql.json(x) (postgres.js native jsonb serializer)
|
||||
* - a `jsonb-guard-ok` comment anywhere in the call span (explicit opt-out)
|
||||
*
|
||||
* Exit 0 = clean, 1 = violations found. Runs under node or bun.
|
||||
*/
|
||||
import { readdirSync, readFileSync, statSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
|
||||
// Default scan roots; overridable via argv so the guard's own test can point it
|
||||
// at a fixture dir (e.g. `node check-jsonb-params.mjs /tmp/fixtures`).
|
||||
const ROOTS = process.argv.slice(2).length > 0 ? process.argv.slice(2) : ['src', 'scripts'];
|
||||
// executeRawDirect must precede executeRaw in the alternation so the longer name
|
||||
// wins; executeRawJsonb is deliberately excluded (it passes objects). The
|
||||
// optional `<...>` handles generic type args, e.g. `executeRaw<{ id: string }>(`.
|
||||
//
|
||||
// Only the postgres.js raw path is scanned (executeRaw/executeRawDirect/.unsafe).
|
||||
// PGLite's native `this.db.query(...)` is intentionally NOT matched: its driver
|
||||
// parses a text→jsonb cast natively, so the double-encode that bites postgres.js
|
||||
// `.unsafe()` does not occur there (the `pglite-masks` invariant). The engine
|
||||
// parity test pins that the resulting jsonb_typeof agrees across both engines.
|
||||
const CALL_RE = /\b(executeRawDirect|executeRaw|unsafe)\s*(?:<[^>;]*>)?\s*\(/g;
|
||||
|
||||
/** Walk from the '(' at openIdx and return [start,end) of the balanced span,
|
||||
* respecting strings, template literals, and comments. */
|
||||
function findSpan(src, openIdx) {
|
||||
let depth = 0;
|
||||
let mode = 'code'; // code | line | block | sq | dq | tpl
|
||||
for (let i = openIdx; i < src.length; i++) {
|
||||
const c = src[i];
|
||||
const n = src[i + 1];
|
||||
if (mode === 'line') { if (c === '\n') mode = 'code'; continue; }
|
||||
if (mode === 'block') { if (c === '*' && n === '/') { mode = 'code'; i++; } continue; }
|
||||
if (mode === 'sq') { if (c === '\\') { i++; continue; } if (c === "'") mode = 'code'; continue; }
|
||||
if (mode === 'dq') { if (c === '\\') { i++; continue; } if (c === '"') mode = 'code'; continue; }
|
||||
if (mode === 'tpl') { if (c === '\\') { i++; continue; } if (c === '`') mode = 'code'; continue; }
|
||||
// mode === 'code'
|
||||
if (c === '/' && n === '/') { mode = 'line'; i++; continue; }
|
||||
if (c === '/' && n === '*') { mode = 'block'; i++; continue; }
|
||||
if (c === "'") { mode = 'sq'; continue; }
|
||||
if (c === '"') { mode = 'dq'; continue; }
|
||||
if (c === '`') { mode = 'tpl'; continue; }
|
||||
if (c === '(') depth++;
|
||||
else if (c === ')') { depth--; if (depth === 0) return [openIdx + 1, i]; }
|
||||
}
|
||||
return [openIdx + 1, src.length];
|
||||
}
|
||||
|
||||
/** Blank out comments so a commented-out example doesn't trip the JSON.stringify probe. */
|
||||
function stripComments(s) {
|
||||
return s.replace(/\/\/[^\n]*/g, '').replace(/\/\*[\s\S]*?\*\//g, '');
|
||||
}
|
||||
|
||||
const violations = [];
|
||||
|
||||
function scanFile(file) {
|
||||
const src = readFileSync(file, 'utf8');
|
||||
CALL_RE.lastIndex = 0;
|
||||
let m;
|
||||
while ((m = CALL_RE.exec(src))) {
|
||||
const method = m[1];
|
||||
const openIdx = m.index + m[0].length - 1; // index of the '('
|
||||
const [s, e] = findSpan(src, openIdx);
|
||||
const span = src.slice(s, e);
|
||||
if (/jsonb-guard-ok/.test(span)) continue;
|
||||
if (!/JSON\.stringify\s*\(/.test(stripComments(span))) continue;
|
||||
// A positional `$N::jsonb` that is NOT `$N::text::jsonb`.
|
||||
const jsonbRe = /\$\d+\s*::\s*jsonb\b/g;
|
||||
let j;
|
||||
let badText = '';
|
||||
while ((j = jsonbRe.exec(span))) {
|
||||
const pre = span.slice(Math.max(0, j.index - 12), j.index);
|
||||
if (/::\s*text\s*$/.test(pre)) continue; // $N::text::jsonb is the fix — allowed
|
||||
badText = j[0].replace(/\s+/g, '');
|
||||
break;
|
||||
}
|
||||
if (!badText) continue;
|
||||
const line = src.slice(0, s).split('\n').length;
|
||||
violations.push(
|
||||
`${file}:${line} ${method}(...) binds JSON.stringify into ${badText} — use $N::text::jsonb or pass a raw object (executeRawJsonb / sql.json)`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
function walk(dir) {
|
||||
let ents;
|
||||
try { ents = readdirSync(dir); } catch { return; }
|
||||
for (const ent of ents) {
|
||||
if (ent === 'node_modules') continue;
|
||||
const p = join(dir, ent);
|
||||
const st = statSync(p);
|
||||
if (st.isDirectory()) walk(p);
|
||||
else if (p.endsWith('.ts') && !p.endsWith('.test.ts')) scanFile(p);
|
||||
}
|
||||
}
|
||||
|
||||
for (const root of ROOTS) walk(root);
|
||||
|
||||
if (violations.length) {
|
||||
console.error('JSONB positional double-encode violations (#2339 class):\n');
|
||||
for (const v of violations) console.error(' ' + v);
|
||||
console.error(`\n${violations.length} violation(s). Fix: bind through $N::text::jsonb (keeping JSON.stringify), or pass a raw object via executeRawJsonb / sql.json. See docs/ENGINES.md.`);
|
||||
process.exit(1);
|
||||
}
|
||||
console.log('check-jsonb-params: clean (no positional $N::jsonb + JSON.stringify double-encodes)');
|
||||
@@ -44,17 +44,3 @@ if grep -rEn "$MAX_STALLED_PATTERN" src/schema.sql src/core/migrate.ts src/core/
|
||||
fi
|
||||
|
||||
echo "OK: max_stalled defaults are 5 in all schema sources"
|
||||
|
||||
# v0.42.x (#2339 / #2324): positional `$N::jsonb` + JSON.stringify double-encode.
|
||||
# The template-string grep above only catches `${JSON.stringify(x)}::jsonb`. It
|
||||
# MISSES the positional-param form — executeRaw(`... $N::jsonb ...`,
|
||||
# [JSON.stringify(x)]) — which is the exact shape that double-encoded the
|
||||
# op_checkpoints pin and aborted every sync in #2339. The AST-lite scanner below
|
||||
# catches it. `set -e` propagates its non-zero exit.
|
||||
if command -v node >/dev/null 2>&1; then
|
||||
node scripts/check-jsonb-params.mjs
|
||||
elif command -v bun >/dev/null 2>&1; then
|
||||
bun scripts/check-jsonb-params.mjs
|
||||
else
|
||||
echo "WARN: neither node nor bun on PATH; skipping check-jsonb-params.mjs" >&2
|
||||
fi
|
||||
|
||||
@@ -1,41 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# CI guard (#1647 / #171): every trigger function in the canonical schema base
|
||||
# files MUST pin `SET search_path`. Without it, an unqualified reference inside
|
||||
# the function body resolves through the caller's search_path, so a same-named
|
||||
# object in a user-controlled schema could shadow it. Migration v120 ALTERs
|
||||
# existing brains; this guard keeps fresh-install function definitions correct
|
||||
# so a NEW trigger function can't reintroduce the gap. Mirrors the
|
||||
# check-jsonb-pattern.sh guard philosophy (a written rule caused the disease;
|
||||
# a guard cures it).
|
||||
#
|
||||
# Scope: schema base files only (src/schema.sql, src/core/pglite-schema.ts).
|
||||
# Historical migration bodies in migrate.ts are append-only and not rescanned;
|
||||
# the runtime doctor probe (pg_proc.proconfig) covers the live post-migration
|
||||
# state on real brains.
|
||||
#
|
||||
# Usage: scripts/check-search-path.sh
|
||||
# Exit: 0 when all trigger functions pin search_path, 1 otherwise.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
|
||||
cd "$ROOT"
|
||||
|
||||
FILES="src/schema.sql src/core/pglite-schema.ts src/core/schema-embedded.ts"
|
||||
|
||||
# A hardened header reads `... RETURNS trigger SET search_path = ... AS $tag$`.
|
||||
# An UNHARDENED one reads `... RETURNS trigger AS $tag$` — match that form and
|
||||
# (belt-and-suspenders) drop any line that already mentions search_path.
|
||||
BAD="$(grep -nEi 'CREATE OR REPLACE FUNCTION [a-z_]+\(\) RETURNS trigger AS ' $FILES 2>/dev/null | grep -vi 'search_path' || true)"
|
||||
|
||||
if [ -n "$BAD" ]; then
|
||||
echo "ERROR: trigger function(s) missing SET search_path in schema base files:"
|
||||
echo "$BAD"
|
||||
echo
|
||||
echo "Add 'SET search_path = pg_catalog, public' to the function header, e.g.:"
|
||||
echo " CREATE OR REPLACE FUNCTION foo() RETURNS trigger SET search_path = pg_catalog, public AS \$\$"
|
||||
echo "See #1647 / #171."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "OK: all trigger functions in schema base files pin search_path"
|
||||
+2
-12
@@ -196,10 +196,7 @@ SELECTED=$(bun run scripts/select-e2e.ts)
|
||||
if [ -z "$SELECTED" ]; then
|
||||
echo "[runner] selector emitted nothing (doc-only diff); skipping E2E."
|
||||
else
|
||||
DATABASE_URL=postgresql://postgres:postgres@postgres-1:5432/gbrain_test \
|
||||
GBRAIN_PGBOUNCER_URL=postgresql://postgres:postgres@pgbouncer:5432/gbrain_pgbouncer \
|
||||
GBRAIN_PGBOUNCER_DIRECT_URL=postgresql://postgres:postgres@postgres-1:5432/gbrain_test \
|
||||
echo "$SELECTED" | xargs bash scripts/run-e2e.sh
|
||||
DATABASE_URL=postgresql://postgres:postgres@postgres-1:5432/gbrain_test echo "$SELECTED" | xargs bash scripts/run-e2e.sh
|
||||
fi'
|
||||
else
|
||||
RUN_PHASES_CMD='echo "[runner] guards + typecheck"
|
||||
@@ -211,10 +208,7 @@ bun run typecheck
|
||||
echo "[runner] unit (unsharded, DATABASE_URL unset)"
|
||||
env -u DATABASE_URL bash scripts/run-unit-shard.sh
|
||||
echo "[runner] e2e (unsharded)"
|
||||
DATABASE_URL=postgresql://postgres:postgres@postgres-1:5432/gbrain_test \
|
||||
GBRAIN_PGBOUNCER_URL=postgresql://postgres:postgres@pgbouncer:5432/gbrain_pgbouncer \
|
||||
GBRAIN_PGBOUNCER_DIRECT_URL=postgresql://postgres:postgres@postgres-1:5432/gbrain_test \
|
||||
bash scripts/run-e2e.sh'
|
||||
DATABASE_URL=postgresql://postgres:postgres@postgres-1:5432/gbrain_test bash scripts/run-e2e.sh'
|
||||
fi
|
||||
else
|
||||
# Tier 1 sharded path. Each shard runs unit+E2E sequentially against its
|
||||
@@ -263,14 +257,10 @@ printf '%s\\n' 1 2 3 4 | xargs -P4 -I{} sh -c '
|
||||
if [ -s /tmp/e2e-selected.txt ]; then
|
||||
SHARD=\${shard}/4 \\
|
||||
DATABASE_URL=postgresql://postgres:postgres@postgres-\${shard}:5432/gbrain_test \\
|
||||
GBRAIN_PGBOUNCER_URL=postgresql://postgres:postgres@pgbouncer:5432/gbrain_pgbouncer \\
|
||||
GBRAIN_PGBOUNCER_DIRECT_URL=postgresql://postgres:postgres@postgres-1:5432/gbrain_test \\
|
||||
xargs -a /tmp/e2e-selected.txt bash scripts/run-e2e.sh >> \$log 2>&1
|
||||
else
|
||||
SHARD=\${shard}/4 \\
|
||||
DATABASE_URL=postgresql://postgres:postgres@postgres-\${shard}:5432/gbrain_test \\
|
||||
GBRAIN_PGBOUNCER_URL=postgresql://postgres:postgres@pgbouncer:5432/gbrain_pgbouncer \\
|
||||
GBRAIN_PGBOUNCER_DIRECT_URL=postgresql://postgres:postgres@postgres-1:5432/gbrain_test \\
|
||||
bash scripts/run-e2e.sh >> \$log 2>&1
|
||||
fi
|
||||
e2e_exit=\$?
|
||||
|
||||
@@ -151,12 +151,6 @@ export const SECTIONS: DocSection[] = [
|
||||
"Three-tier architecture for agents with 300+ skills: always-loaded, resolver-routed, and dormant. Per-turn token math, the v0.41.7.0 compact list-format resolver, and the `gbrain doctor` safety net. 306 skills, ~21K tokens freed per turn, zero capability loss.",
|
||||
path: "docs/guides/scaling-skills.md",
|
||||
},
|
||||
{
|
||||
title: "docs/guides/push-context.md",
|
||||
description:
|
||||
"Push-based context: the brain volunteers confidence-gated pages from the rolling conversation window. Three channels (ambient reflex, volunteer_context op, gbrain watch), config knobs, and the volunteered-vs-used feedback loop.",
|
||||
path: "docs/guides/push-context.md",
|
||||
},
|
||||
{
|
||||
title: "docs/mcp/DEPLOY.md",
|
||||
description: "MCP server deployment.",
|
||||
|
||||
@@ -1,49 +0,0 @@
|
||||
#!/usr/bin/env bun
|
||||
// scripts/postinstall.ts
|
||||
//
|
||||
// Postinstall hook: after `bun install`, apply any pending schema migrations so
|
||||
// a freshly-installed gbrain is immediately usable. Wired via package.json
|
||||
// ("postinstall": "bun run scripts/postinstall.ts") as a real Bun script rather
|
||||
// than an inline `node -e` one-liner.
|
||||
//
|
||||
// Why a script file and not an inline command:
|
||||
// Embedding a program inside the package.json postinstall string lets the
|
||||
// lifecycle shell mangle it. Bun's Windows script-runner expands `\n` in the
|
||||
// hint string into a REAL newline before node sees it, producing
|
||||
// `SyntaxError: Invalid or unexpected token` and aborting the whole install.
|
||||
// `node` is also not guaranteed present under a Bun install (bun is the
|
||||
// guaranteed runtime), and `shell: win32` re-opens a quoting surface. A
|
||||
// checked-in .ts run by `bun run` sidesteps all three.
|
||||
//
|
||||
// Uses Bun APIs only — `which()` for Windows-aware PATH resolution (finds
|
||||
// gbrain.exe / gbrain.cmd) and an argv-array `Bun.spawnSync` (no shell, nothing
|
||||
// to quote). It NEVER fails the install: every path exits 0.
|
||||
|
||||
import { which } from 'bun';
|
||||
|
||||
const HINT =
|
||||
'[gbrain] postinstall skipped. If installed via bun install -g github:...: ' +
|
||||
'run `gbrain doctor` and `gbrain apply-migrations --yes` manually. ' +
|
||||
'See https://github.com/garrytan/gbrain/issues/218';
|
||||
|
||||
// Windows-aware PATH resolution — finds gbrain, gbrain.exe or gbrain.cmd.
|
||||
const bin = which('gbrain');
|
||||
|
||||
if (!bin) {
|
||||
// Fresh clone / global install where gbrain isn't on PATH yet: skip cleanly.
|
||||
console.error(HINT);
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
try {
|
||||
const r = Bun.spawnSync({
|
||||
cmd: [bin, 'apply-migrations', '--yes', '--non-interactive'],
|
||||
stdout: 'inherit',
|
||||
stderr: 'inherit',
|
||||
});
|
||||
if (r.exitCode !== 0) console.error(HINT);
|
||||
} catch {
|
||||
console.error(HINT);
|
||||
}
|
||||
|
||||
process.exit(0); // never abort the install
|
||||
@@ -66,24 +66,6 @@ export HOME="$E2E_TMP_HOME"
|
||||
export GBRAIN_HOME="$E2E_TMP_HOME"
|
||||
mkdir -p "$E2E_TMP_HOME/.gbrain"
|
||||
|
||||
# --- Hermetic env scrub: operator/agent context must not bleed into E2E ---
|
||||
# A dev shell or a Conductor workspace exports CONDUCTOR_*, MCP_*, OPENCLAW_*,
|
||||
# and GBRAIN_* config overrides (e.g. a stray GBRAIN_BRAIN_ID, GBRAIN_SOURCE,
|
||||
# GBRAIN_*_THRESHOLD, GBRAIN_SUPERVISOR_PID_FILE) that would silently change
|
||||
# test behavior — making "hermetic" E2E non-hermetic and its failures
|
||||
# unreproducible across machines. Drop them before bun starts. This is a
|
||||
# DENYLIST of operator-context prefixes (not an allowlist rebuild), so PATH,
|
||||
# HOME, TMPDIR, CI, DATABASE_URL, and bun internals survive untouched. We keep
|
||||
# GBRAIN_HOME (just set above for HOME isolation); everything else GBRAIN_* is
|
||||
# an operator override the suite must not inherit. Adapts GStack's
|
||||
# buildHermeticEnv() allowlist to gbrain's shell E2E runner.
|
||||
for _e2e_var in $(env | grep -oE '^(CONDUCTOR_|MCP_|OPENCLAW_|GBRAIN_)[A-Za-z0-9_]*' | sort -u); do
|
||||
case "$_e2e_var" in
|
||||
GBRAIN_HOME) ;; # required for HOME isolation (set above) — keep
|
||||
*) unset "$_e2e_var" || true ;;
|
||||
esac
|
||||
done
|
||||
|
||||
# --dry-run-list: print the resolved file list (one per line) and exit. Used
|
||||
# by scripts/ci-local.sh to smoke-test the argv branching at startup.
|
||||
DRY_RUN_LIST=0
|
||||
|
||||
@@ -38,7 +38,6 @@ CHECKS=(
|
||||
"check:proposal-pii"
|
||||
"check:test-names"
|
||||
"check:jsonb"
|
||||
"check:search-path"
|
||||
"check:source-id-projection"
|
||||
"check:source-config-leak"
|
||||
"check:progress"
|
||||
|
||||
@@ -57,7 +57,6 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
|
||||
| Morning prep, meeting context, day planning | `skills/daily-task-prep/SKILL.md` |
|
||||
| Daily briefing, "what's happening today" | `skills/briefing/SKILL.md` |
|
||||
| Cron scheduling, quiet hours, job staggering | `skills/cron-scheduler/SKILL.md` |
|
||||
| "get more out of gbrain", "is my brain set up right", "weekly brain checkup", "advise me on my brain", "gbrain advisor" | `skills/gbrain-advisor/SKILL.md` |
|
||||
| Save or load reports | `skills/reports/SKILL.md` |
|
||||
| "Create a skill", "improve this skill" | `skills/skill-creator/SKILL.md` |
|
||||
| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/SKILL.md` |
|
||||
|
||||
@@ -24,7 +24,7 @@ mutating: true
|
||||
## Contract
|
||||
|
||||
This skill guarantees:
|
||||
- Every brain page is scanned against the eight canonical frontmatter validation classes
|
||||
- Every brain page is scanned against the seven canonical frontmatter validation classes
|
||||
- Mechanical errors (nested quotes, missing closing `---`, null bytes, slug mismatch) are auto-repairable on demand with `.bak` backups
|
||||
- Validation logic is shared with `gbrain doctor`'s `frontmatter_integrity` subcheck — single source of truth
|
||||
- Reports per source (gbrain is multi-source since v0.18.0); never silently audits the wrong root
|
||||
@@ -50,7 +50,6 @@ Without a guard, these accumulate silently until `gbrain sync` chokes or search
|
||||
| `SLUG_MISMATCH` | Frontmatter `slug:` differs from path-derived slug | Yes (removes the field) |
|
||||
| `NULL_BYTES` | Binary corruption (`\x00`) | Yes |
|
||||
| `NESTED_QUOTES` | `title: "outer "inner" outer"` shape | Yes |
|
||||
| `NON_STRING_FIELD` | `title`/`type`/`slug` is an unquoted non-string scalar (e.g. `title: 123`, `slug: 2024-06-01`) | No (quote the value) |
|
||||
| `EMPTY_FRONTMATTER` | Open + close present but nothing between | No (needs human) |
|
||||
|
||||
## Phases
|
||||
|
||||
@@ -1,117 +0,0 @@
|
||||
---
|
||||
name: gbrain-advisor
|
||||
version: 1.0.0
|
||||
description: |
|
||||
Proactive "make the most of gbrain" coaching. Runs `gbrain advisor` on a
|
||||
cadence and pings the user with the top high-leverage actions for their brain:
|
||||
version drift, pending migrations, stalled jobs, low embed coverage, setup
|
||||
smells, and uninstalled brain skills. Read-only; always asks before fixing.
|
||||
triggers:
|
||||
- "what should I do to get more out of gbrain"
|
||||
- "is my brain set up right"
|
||||
- "gbrain advisor"
|
||||
- "advise me on my brain"
|
||||
- "weekly brain checkup"
|
||||
tools:
|
||||
- advisor
|
||||
mutating: false
|
||||
---
|
||||
|
||||
# gbrain Advisor
|
||||
|
||||
> **Convention:** See `skills/conventions/brain-first.md`. This skill is the
|
||||
> proactive voice of the brain — it tells the owner how to run it better.
|
||||
|
||||
## Contract
|
||||
|
||||
This skill guarantees:
|
||||
- **Read-only.** `gbrain advisor` never mutates. It computes a ranked list of
|
||||
actions from existing brain state.
|
||||
- **Print, never execute.** You SHOW the user the findings and ASK before running
|
||||
any fix. The user owns every decision.
|
||||
- **Bounded nagging.** On a cadence, surface only what changed or what's
|
||||
critical; don't repeat an ignored low-severity item every run.
|
||||
|
||||
## When to run
|
||||
|
||||
- On demand when the user asks "how do I get more out of this brain?"
|
||||
- On a **weekly** cadence via the cron recipe below (even idle brains get a
|
||||
"here's how to run this better" ping).
|
||||
|
||||
## How to run it
|
||||
|
||||
```bash
|
||||
gbrain advisor --json
|
||||
```
|
||||
|
||||
Exit code is the severity gate (E2): `0` clean, `1` warn, `2` critical. The JSON
|
||||
payload is `{ version, generated_at, worst, findings: [...] }`. Each finding has:
|
||||
|
||||
- `severity` — `critical` | `warn` | `info`
|
||||
- `title` — one-line why-it-matters
|
||||
- `fix.command_argv` — the exact command to fix it (a structured argv)
|
||||
- `fix.dispatch_id` — present when the fix is safe to run via `--apply`
|
||||
|
||||
## What to do with the findings
|
||||
|
||||
1. Read the findings, highest severity first.
|
||||
2. Summarize the top 1-3 to the user in their own channel/voice. Lead with any
|
||||
`critical` item (e.g. pending migrations).
|
||||
3. For each, show the `fix.command_argv` and **ask** whether to run it.
|
||||
4. If they say yes and the finding has a `fix.dispatch_id`, you may run it
|
||||
locally with an explicit confirm:
|
||||
|
||||
```bash
|
||||
gbrain advisor --apply <dispatch_id>
|
||||
```
|
||||
|
||||
`--apply` is local-only, runs the fix as a structured argv (no shell), and
|
||||
confirms first. Findings without a `dispatch_id` are not auto-runnable — run
|
||||
their `fix.command_argv` yourself after the user agrees.
|
||||
5. Never run a fix the user didn't approve.
|
||||
|
||||
## Cron recipe (weekly checkup)
|
||||
|
||||
Install a weekly job via the `cron-scheduler` skill. Keep the prompt THIN — the
|
||||
job just reads this skill and runs the advisor:
|
||||
|
||||
- **Schedule:** weekly, one quiet-hours-respecting slot (e.g. Monday 09:00 local).
|
||||
- **Job prompt:** `Read skills/gbrain-advisor/SKILL.md and run gbrain advisor --json. If anything is critical or new since last run, ping me with the top items and the exact fix commands. Ask before fixing.`
|
||||
- **Idempotent:** the advisor is read-only, so a double-fire is harmless.
|
||||
|
||||
The advisor records a local run history, so on each fire you can tell the user
|
||||
what is **new since last run** rather than re-listing everything.
|
||||
|
||||
## Output Format
|
||||
|
||||
When you surface advisor findings to the user, lead with severity and keep it
|
||||
scannable:
|
||||
|
||||
```
|
||||
🧠 gbrain checkup — 2 things worth your attention
|
||||
|
||||
CRITICAL Schema migrations are pending.
|
||||
Fix: gbrain apply-migrations --yes (want me to run it?)
|
||||
|
||||
WARN gbrain 0.44 is available (you're on 0.43).
|
||||
Fix: gbrain upgrade
|
||||
```
|
||||
|
||||
- One block per finding, highest severity first.
|
||||
- Always show the exact `fix` command and ASK before running it.
|
||||
- If nothing is pressing, say so in one line ("brain looks healthy") — don't
|
||||
manufacture work.
|
||||
|
||||
## Anti-Patterns
|
||||
|
||||
- **Running a fix without asking.** The advisor is read-only by contract. Never
|
||||
run `--apply` (or any `fix` command) without the user's explicit yes.
|
||||
- **Dumping the raw JSON at the user.** Translate findings into their voice; lead
|
||||
with what matters.
|
||||
- **Re-nagging ignored low-severity items every run.** Use the "new since last
|
||||
run" delta; respect the user's prior non-action.
|
||||
- **Treating `info` like `critical`.** Only block/insist on `critical` findings
|
||||
(pending migrations). `info` is a gentle nudge.
|
||||
- **Calling the MCP `advisor` op for workspace install state.** Over MCP the
|
||||
advisor returns brain-state signals only; uninstalled-skill findings are a
|
||||
local-CLI concern.
|
||||
@@ -239,11 +239,6 @@
|
||||
"path": "functional-area-resolver/SKILL.md",
|
||||
"description": "Compress an agent's routing file (RESOLVER.md or AGENTS.md) by replacing skill-per-row tables with functional-area dispatcher entries. Two-layer dispatch keeps every sub-skill reachable at ~50% of the file size."
|
||||
},
|
||||
{
|
||||
"name": "gbrain-advisor",
|
||||
"path": "gbrain-advisor/SKILL.md",
|
||||
"description": "Proactive 'make the most of gbrain' coaching. Runs gbrain advisor on a cadence and pings the user with the top high-leverage actions for their brain. Read-only; always asks before fixing."
|
||||
},
|
||||
{
|
||||
"name": "brain-taxonomist",
|
||||
"path": "brain-taxonomist/SKILL.md",
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
// AUTO-GENERATED — do not edit by hand.
|
||||
// Run `bun run scripts/build-admin-embedded.ts` to regenerate.
|
||||
// Source: admin/dist/ at 2026-05-27.
|
||||
// Source: admin/dist/ at 2026-05-24.
|
||||
//
|
||||
// Bun resolves the file: imports to a path that works at runtime even
|
||||
// inside a compiled binary (`bun build --compile`). The manifest maps
|
||||
// the request path the express handler sees to (resolved-path, mime).
|
||||
|
||||
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
|
||||
import A_0_assets_index_CoGEje3__js from '../admin/dist/assets/index-CoGEje3-.js' with { type: 'file' };
|
||||
import A_0_assets_index_DqP_zmqH_js from '../admin/dist/assets/index-DqP-zmqH.js' with { type: 'file' };
|
||||
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
|
||||
import A_1_assets_index_GxkWX7v3_css from '../admin/dist/assets/index-GxkWX7v3.css' with { type: 'file' };
|
||||
// @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
|
||||
@@ -19,7 +19,7 @@ export interface AdminAsset {
|
||||
}
|
||||
|
||||
export const ADMIN_ASSETS: Record<string, AdminAsset> = {
|
||||
"/admin/assets/index-CoGEje3-.js": { path: A_0_assets_index_CoGEje3__js as unknown as string, mime: "application/javascript; charset=utf-8" },
|
||||
"/admin/assets/index-DqP-zmqH.js": { path: A_0_assets_index_DqP_zmqH_js as unknown as string, mime: "application/javascript; charset=utf-8" },
|
||||
"/admin/assets/index-GxkWX7v3.css": { path: A_1_assets_index_GxkWX7v3_css as unknown as string, mime: "text/css; charset=utf-8" },
|
||||
"/admin/index.html": { path: A_2_index_html as unknown as string, mime: "text/html; charset=utf-8" },
|
||||
};
|
||||
|
||||
+101
-290
@@ -24,9 +24,9 @@ import type { GBrainConfig } from './core/config.ts';
|
||||
import type { AIGatewayConfig } from './core/ai/types.ts';
|
||||
import type { BrainEngine } from './core/engine.ts';
|
||||
import { operations, OperationError } from './core/operations.ts';
|
||||
import { formatVolunteeredPage } from './core/context/volunteer.ts';
|
||||
import type { Operation, OperationContext } from './core/operations.ts';
|
||||
import { shouldForceExitAfterMain, finishCliTeardown, flushThenExit, currentExitCode, setCliExitVerdict } from './core/cli-force-exit.ts';
|
||||
import { drainAllBackgroundWorkForCliExit } from './core/background-work.ts';
|
||||
import { shouldForceExitAfterMain } from './core/cli-force-exit.ts';
|
||||
import { serializeMarkdown } from './core/markdown.ts';
|
||||
import { parseGlobalFlags, setCliOptions, getCliOptions } from './core/cli-options.ts';
|
||||
import type { CliOptions } from './core/cli-options.ts';
|
||||
@@ -43,18 +43,8 @@ for (const op of operations) {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* JSON replacer: `bigint` → string, matching the postgres.js wire shape (int8
|
||||
* comes back as a string on the routed path). Lets the local-engine output
|
||||
* normalizer round-trip bigint columns (e.g. a `BIGSERIAL` `id`) instead of
|
||||
* throwing `TypeError: Do not know how to serialize a BigInt`.
|
||||
*/
|
||||
export function bigintToStringReplacer(_key: string, value: unknown): unknown {
|
||||
return typeof value === 'bigint' ? value.toString() : value;
|
||||
}
|
||||
|
||||
// CLI-only commands that bypass the operation layer
|
||||
export const CLI_ONLY = new Set(['init', 'reinit-pglite', 'upgrade', 'post-upgrade', 'check-update', 'integrations', 'publish', 'check-backlinks', 'lint', 'report', 'import', 'export', 'files', 'embed', 'serve', 'call', 'config', 'doctor', 'migrate', 'eval', 'sync', 'extract', 'extract-conversation-facts', 'enrich', 'features', 'autopilot', 'graph-query', 'jobs', 'agent', 'apply-migrations', 'skillpack-check', 'skillpack', 'resolvers', 'integrity', 'repair-jsonb', 'orphans', 'sources', 'mounts', 'dream', 'check-resolvable', 'routing-eval', 'skillify', 'smoke-test', 'providers', 'storage', 'repos', 'code-def', 'code-refs', 'reindex', 'reindex-code', 'reindex-frontmatter', 'code-callers', 'code-callees', 'reconcile-links', 'frontmatter', 'auth', 'friction', 'claw-test', 'book-mirror', 'takes', 'think', 'salience', 'anomalies', 'calibration', 'transcripts', 'models', 'remote', 'recall', 'forget', 'edges-backfill', 'cache', 'ze-switch', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector']);
|
||||
const CLI_ONLY = new Set(['init', 'reinit-pglite', 'upgrade', 'post-upgrade', 'check-update', 'integrations', 'publish', 'check-backlinks', 'lint', 'report', 'import', 'export', 'files', 'embed', 'serve', 'call', 'config', 'doctor', 'migrate', 'eval', 'sync', 'extract', 'extract-conversation-facts', 'enrich', 'features', 'autopilot', 'graph-query', 'jobs', 'agent', 'apply-migrations', 'skillpack-check', 'skillpack', 'resolvers', 'integrity', 'repair-jsonb', 'orphans', 'sources', 'mounts', 'dream', 'check-resolvable', 'routing-eval', 'skillify', 'smoke-test', 'providers', 'storage', 'repos', 'code-def', 'code-refs', 'reindex', 'reindex-code', 'reindex-frontmatter', 'code-callers', 'code-callees', 'frontmatter', 'auth', 'friction', 'claw-test', 'book-mirror', 'takes', 'think', 'salience', 'anomalies', 'transcripts', 'models', 'remote', 'recall', 'forget', 'edges-backfill', 'cache', 'ze-switch', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade']);
|
||||
// CLI-only commands whose handlers print their own --help text. These are
|
||||
// excluded from the generic short-circuit so detailed per-command and
|
||||
// per-subcommand usage stays reachable.
|
||||
@@ -78,8 +68,6 @@ const CLI_ONLY_SELF_HELP = new Set([
|
||||
'capture',
|
||||
// v0.42 self-upgrade ships its own usage (flags + the agent-skill story).
|
||||
'self-upgrade',
|
||||
// v0.43 (#2095): watch ships WATCH_HELP (flags + the stdin-turn protocol).
|
||||
'watch',
|
||||
// v0.37 fix wave (Lane D.4 + CDX2-12): sync's --no-embed flag was
|
||||
// unreachable via help because the dispatcher's generic CLI-only
|
||||
// short-circuit fired before runSync could print its own usage block.
|
||||
@@ -245,17 +233,6 @@ async function main() {
|
||||
command = 'query';
|
||||
}
|
||||
|
||||
// Local patch 2026-06-11 — mark one-shot CLI processes so the facts
|
||||
// backstop routes absorb work to the durable jobs worker instead of the
|
||||
// in-process queue that the exit teardown drains-then-aborts after ~1-2s
|
||||
// (the `pipeline_error: [chat(...)] The operation was aborted.` class in
|
||||
// ingest_log). Daemons keep the in-process queue: their event loop
|
||||
// outlives the work. See src/core/facts/cli-process-mode.ts.
|
||||
if (!['serve', 'jobs', 'autopilot'].includes(command)) {
|
||||
const { markShortLivedCliProcess } = await import('./core/facts/cli-process-mode.ts');
|
||||
markShortLivedCliProcess();
|
||||
}
|
||||
|
||||
// T5 — `gbrain search modes|stats|tune` is the read-only config dashboard,
|
||||
// NOT a free-text search for the literal word "modes". Free-text
|
||||
// `gbrain search "<query>"` falls through to the cheap-hybrid `search` op
|
||||
@@ -283,11 +260,7 @@ async function main() {
|
||||
await withTimeout(runSearch(engine, subArgs), timeoutMs, label);
|
||||
}
|
||||
} finally {
|
||||
// #2084: `search diagnose` runs real hybrid retrieval (arms search-cache
|
||||
// writes) — route through the shared bounded teardown like every other
|
||||
// one-shot path. The connect-timeout process.exit(124) above is reviewed
|
||||
// and intentionally unchanged: no engine exists at that point.
|
||||
await finishCliTeardown({ engine });
|
||||
await engine.disconnect();
|
||||
}
|
||||
return;
|
||||
}
|
||||
@@ -305,17 +278,6 @@ async function main() {
|
||||
}
|
||||
}
|
||||
|
||||
// DB-free durability pull (v0.42.44 D2): the harden cron calls
|
||||
// `gbrain sources pull --path <dir>` every ~30 min. It must NOT open PGLite
|
||||
// (a live long-lived session holds the single-writer lock), so handle it
|
||||
// BEFORE connectEngine. The `sources pull <id>` form (no --path) still routes
|
||||
// through handleCliOnly → runSources with an engine.
|
||||
if (command === 'sources' && subArgs[0] === 'pull' && subArgs.includes('--path')) {
|
||||
const { runPull } = await import('./commands/sources-harden.ts');
|
||||
await runPull(null, subArgs.slice(1));
|
||||
return;
|
||||
}
|
||||
|
||||
// CLI-only commands
|
||||
if (CLI_ONLY.has(command)) {
|
||||
await handleCliOnly(command, subArgs);
|
||||
@@ -388,82 +350,45 @@ async function main() {
|
||||
|
||||
// Local engine path (unchanged behavior for local installs).
|
||||
const engine = await connectEngine();
|
||||
// #2084: the teardown contract (bounded drain of every background-work sink,
|
||||
// bounded disconnect, computed-deadline backstop) lives in finishCliTeardown
|
||||
// — see src/core/cli-force-exit.ts for the full design. The hard-deadline
|
||||
// timer arms at TEARDOWN start inside the helper, never before the handler:
|
||||
// the pre-#2084 placement here measured handler + teardown combined, so a
|
||||
// slow-but-healthy query burned the teardown budget (the flat-10s-banner
|
||||
// bug) and any >10s op was force-killed mid-run with exit 0. The explicit
|
||||
// process exit happens once, in the import.meta.main seam at the bottom of
|
||||
// this file — NOT here.
|
||||
|
||||
// v0.42.41.0 (merged): wallclock bound for READ-scope op handlers. With the
|
||||
// teardown backstop correctly scoped to teardown, a genuinely WEDGED read
|
||||
// handler (hung pooler connection mid-query) would otherwise hang the CLI
|
||||
// forever — the #1633 zombie class the old pre-try timer accidentally
|
||||
// bounded at 10s. 180s sits far above any healthy slow-pooler run
|
||||
// (6-10s/connection); --timeout=Ns overrides. Writes/admin stay unbounded:
|
||||
// a long import/embed must never be killed by a default deadline. On
|
||||
// timeout the abandoned handler may hold ref'd sockets — harmless here,
|
||||
// because the import.meta.main seam exits explicitly on every one-shot path.
|
||||
const READ_OP_TIMEOUT_MS = 180_000;
|
||||
// v0.41.8.0 (#1247, #1269, #1290): the search / query / get_page
|
||||
// op handlers fire-and-forget `bumpLastRetrievedAt` after returning
|
||||
// results. On PGLite that IIFE keeps Bun's event loop alive past
|
||||
// engine.disconnect(), hanging the CLI at ~95-98% CPU until SIGKILL.
|
||||
// Drain the fire-and-forget set BEFORE disconnect; force-exit only
|
||||
// if the drain itself times out (preserves stderr diagnostic signal
|
||||
// AND guarantees the CLI doesn't re-hang at the disconnect layer).
|
||||
//
|
||||
// Defense-in-depth (adversarial-review C13): `engine.disconnect()` itself
|
||||
// can hang on PGLite (db.close() or releaseLock racing OS-level FS state).
|
||||
// Install an unref'd setTimeout hard-exit fallback BEFORE entering the
|
||||
// try/catch/finally so a hung disconnect cannot defeat the force-exit
|
||||
// contract. Daemons (`serve`) are excluded so they stay alive.
|
||||
const DISCONNECT_HARD_DEADLINE_MS = 10_000;
|
||||
let forceExitTimer: ReturnType<typeof setTimeout> | undefined;
|
||||
if (shouldForceExitAfterMain()) {
|
||||
forceExitTimer = setTimeout(() => {
|
||||
console.warn(
|
||||
`[cli] engine.disconnect() did not return within ${DISCONNECT_HARD_DEADLINE_MS}ms — force-exiting`,
|
||||
);
|
||||
// v0.42.20.0 (codex): honor an exit code an errored op already set —
|
||||
// a bare process.exit(0) here would mask a failed op as success if the
|
||||
// drain/disconnect then hangs.
|
||||
process.exit(process.exitCode ?? 0);
|
||||
}, DISCONNECT_HARD_DEADLINE_MS);
|
||||
// unref so the timer itself doesn't keep the event loop alive — only
|
||||
// the actual pending work (PGLite WASM handle) does. Without unref,
|
||||
// we'd block a clean exit by 10s on every successful CLI run.
|
||||
forceExitTimer.unref?.();
|
||||
}
|
||||
|
||||
try {
|
||||
const { withTimeout, OperationTimeoutError } = await import('./core/timeout.ts');
|
||||
const wallclockMs = getCliOptions().timeoutMs ?? READ_OP_TIMEOUT_MS;
|
||||
const onWallclockTimeout = (e: InstanceType<typeof OperationTimeoutError>) => {
|
||||
const hint = getCliOptions().timeoutMs
|
||||
? ''
|
||||
: ` (default ${e.ms}ms; pass --timeout=Ns to override)`;
|
||||
console.error(`${e.label} timed out${hint}.`);
|
||||
// 124 = timeout convention (matches the read-only dispatch path). Set
|
||||
// through the verdict channel — a raw process.exitCode write is invisible
|
||||
// to the exit seam and PGLite's WASM runtime can scribble over it.
|
||||
setCliExitVerdict(124);
|
||||
};
|
||||
|
||||
// Context build does DB I/O (resolveSourceId) and runs for EVERY op —
|
||||
// a wedged pooler connection here would otherwise hang reads, writes,
|
||||
// and admin alike with no bound at all (adversarial review finding).
|
||||
let ctx: Awaited<ReturnType<typeof makeContext>>;
|
||||
try {
|
||||
ctx = await withTimeout(
|
||||
makeContext(engine, params),
|
||||
wallclockMs,
|
||||
`gbrain ${command}: context`,
|
||||
);
|
||||
} catch (e: unknown) {
|
||||
if (e instanceof OperationTimeoutError) {
|
||||
onWallclockTimeout(e);
|
||||
return; // the finally drains + disconnects; the import.meta.main seam exits
|
||||
}
|
||||
throw e;
|
||||
}
|
||||
|
||||
let rawResult: unknown;
|
||||
if (op.scope === 'read') {
|
||||
try {
|
||||
rawResult = await withTimeout(
|
||||
op.handler(ctx, params),
|
||||
wallclockMs,
|
||||
`gbrain ${command}`,
|
||||
);
|
||||
} catch (e: unknown) {
|
||||
if (e instanceof OperationTimeoutError) {
|
||||
onWallclockTimeout(e);
|
||||
return; // the finally drains + disconnects; the import.meta.main seam exits
|
||||
}
|
||||
throw e;
|
||||
}
|
||||
} else {
|
||||
rawResult = await op.handler(ctx, params);
|
||||
}
|
||||
const ctx = await makeContext(engine, params);
|
||||
const rawResult = await op.handler(ctx, params);
|
||||
// ENG-2 (renderer parity by data shape): JSON-round-trip the local-engine
|
||||
// path's return value so renderers see the same shape they'd see on the
|
||||
// routed path. Date → ISO string; bigint → string (postgres.js shape);
|
||||
// Buffer → object. Microsecond-cost; eliminates a whole drift bug class.
|
||||
const result = JSON.parse(JSON.stringify(rawResult, bigintToStringReplacer));
|
||||
const result = JSON.parse(JSON.stringify(rawResult));
|
||||
const output = formatResult(op.name, result);
|
||||
if (output) process.stdout.write(output);
|
||||
} catch (e: unknown) {
|
||||
@@ -471,20 +396,27 @@ async function main() {
|
||||
// STILL runs (drains every background-work sink + disconnects). A bare
|
||||
// process.exit(1) here would skip the finally → skip the drain + disconnect
|
||||
// (leaves facts/cache/eval-capture writes racing teardown). The finally's
|
||||
// drain bounds teardown; the hard-deadline timer armed at teardown entry
|
||||
// bounds a hung one.
|
||||
// drain bounds teardown; the outer hard-deadline timer bounds a hung one.
|
||||
if (e instanceof OperationError) {
|
||||
console.error(`Error [${e.code}]: ${e.message}`);
|
||||
if (e.suggestion) console.error(` Fix: ${e.suggestion}`);
|
||||
} else {
|
||||
console.error(e instanceof Error ? e.message : String(e));
|
||||
}
|
||||
setCliExitVerdict(1);
|
||||
process.exitCode = 1;
|
||||
} finally {
|
||||
// 1s per-sink drain budget: read paths with no pending work pay the ~0ms
|
||||
// fast path; capture/import that DO enqueue pay up to 1s (+ facts shutdown
|
||||
// grace) while in-flight Haiku finishes (#1762 drain-before-disconnect).
|
||||
await finishCliTeardown({ engine, drainTimeoutMs: 1000 });
|
||||
// v0.42.20.0 — drain ALL fire-and-forget sinks (facts, last-retrieved,
|
||||
// search-cache, eval-capture) via the background-work registry BEFORE
|
||||
// disconnect, so a PGLite db.close() can't race in-flight work into the
|
||||
// re-pump busy-loop (#1762). facts drains first (order 0) so its abort-path
|
||||
// DB logIngest gets the freshest live-engine window. 1s per-sink timeout:
|
||||
// read paths with no pending work pay the ~0ms fast path; capture/import
|
||||
// that DO enqueue pay up to 1s (+ facts shutdown grace) while in-flight
|
||||
// Haiku finishes. The unref'd hard-deadline timer above is the backstop if
|
||||
// disconnect or a lingering socket keeps Bun's loop alive.
|
||||
await drainAllBackgroundWorkForCliExit({ timeoutMs: 1000 });
|
||||
await engine.disconnect();
|
||||
if (forceExitTimer) clearTimeout(forceExitTimer);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -837,27 +769,8 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
|
||||
};
|
||||
}
|
||||
|
||||
// Exported for tests (same import-safety contract as cliAliases/printOpHelp).
|
||||
export function formatResult(opName: string, result: unknown): string {
|
||||
function formatResult(opName: string, result: unknown): string {
|
||||
switch (opName) {
|
||||
case 'volunteer_context': {
|
||||
const r = result as any;
|
||||
// Stats mode (the feedback loop).
|
||||
if (r && r.approximate === true && Array.isArray(r.by_arm)) {
|
||||
const lines = [
|
||||
`volunteered-context precision — last ${r.days} day(s) (${r.note})`,
|
||||
`total: ${r.total_volunteered} volunteered, ${r.total_used} used`,
|
||||
];
|
||||
for (const a of r.by_arm) {
|
||||
lines.push(` ${a.match_arm}/${a.channel}: ${a.used}/${a.volunteered} used (precision ${a.precision})`);
|
||||
}
|
||||
if (!r.by_arm.length) lines.push(' (no volunteer events in the window)');
|
||||
return lines.join('\n') + '\n';
|
||||
}
|
||||
const pages = (r?.pages ?? []) as any[];
|
||||
if (!pages.length) return 'Nothing volunteered (no entity cleared the confidence gate).\n';
|
||||
return pages.map((p) => formatVolunteeredPage(p)).join('\n') + '\n';
|
||||
}
|
||||
case 'get_page': {
|
||||
const r = result as any;
|
||||
if (r.error === 'ambiguous_slug') {
|
||||
@@ -979,9 +892,6 @@ export function formatResult(opName: string, result: unknown): string {
|
||||
const THIN_CLIENT_REFUSED_COMMANDS = new Set([
|
||||
'sync', 'embed', 'extract', 'extract-conversation-facts', 'enrich', 'migrate', 'apply-migrations',
|
||||
'repair-jsonb', 'orphans', 'integrity', 'serve',
|
||||
// v0.43 (#2095): watch streams against a LOCAL engine; thin clients get
|
||||
// the volunteer_context MCP op instead.
|
||||
'watch',
|
||||
// v0.31.1 (CDX-2 op coverage matrix): more local-only commands
|
||||
'dream', 'transcripts', 'storage',
|
||||
// v0.31.1 CDX-2 audit: takes/sources have multiple subcommands; some
|
||||
@@ -998,13 +908,6 @@ const THIN_CLIENT_REFUSED_COMMANDS = new Set([
|
||||
// - `code-def`/`code-refs`/`code-callers`/`code-callees` have NO MCP ops
|
||||
// in operations.ts:2630-2671; cannot be "fixed by routing" yet
|
||||
'pages', 'files', 'eval', 'code-def', 'code-refs', 'code-callers', 'code-callees',
|
||||
// scratch-DB audit: `config` get/set operate on the host brain's config
|
||||
// plane (DB rows / host file-plane). On a thin client they fabricated an
|
||||
// ephemeral local PGLite (full migration replay per call) and read/wrote
|
||||
// config nobody would ever see. NOTE: `jobs` is deliberately NOT here —
|
||||
// it gets a partial dispatch (list/get route over MCP engine-free, the
|
||||
// rest refuse) in the main dispatch before connectEngine().
|
||||
'config',
|
||||
]);
|
||||
|
||||
/**
|
||||
@@ -1042,9 +945,6 @@ const THIN_CLIENT_REFUSE_HINTS: Record<string, string> = {
|
||||
'code-refs': '`code-refs` has no MCP op yet. Run on the host.',
|
||||
'code-callers': '`code-callers` has no MCP op yet. Run on the host.',
|
||||
'code-callees': '`code-callees` has no MCP op yet. Run on the host.',
|
||||
// scratch-DB audit additions
|
||||
config: "config reads/writes the host brain's config plane. Edit the host's .gbrain/config.json (file-plane keys) or run on the host with GBRAIN_HOME set.",
|
||||
jobs: '`jobs list` and `jobs get <id>` are thin-client routable; this subcommand runs against the host queue. Use the submit_job / list_jobs / get_job MCP tools from your agent, or run on the host with GBRAIN_HOME set.',
|
||||
};
|
||||
|
||||
/**
|
||||
@@ -1223,14 +1123,11 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
}
|
||||
if (command === 'friction') {
|
||||
const { runFriction } = await import('./commands/friction.ts');
|
||||
// #2084 inner-exit sweep: verdict + return so teardown + the flush seam run.
|
||||
setCliExitVerdict(runFriction(args));
|
||||
return;
|
||||
process.exit(runFriction(args));
|
||||
}
|
||||
if (command === 'claw-test') {
|
||||
const { runClawTest } = await import('./commands/claw-test.ts');
|
||||
setCliExitVerdict(await runClawTest(args));
|
||||
return;
|
||||
process.exit(await runClawTest(args));
|
||||
}
|
||||
if (command === 'report') {
|
||||
const { runReport } = await import('./commands/report.ts');
|
||||
@@ -1276,13 +1173,13 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
if (args.includes('--remediation-plan')) {
|
||||
const { runRemediationPlan } = await import('./commands/doctor.ts');
|
||||
const eng = await connectEngine();
|
||||
try { await runRemediationPlan(eng, args); } finally { await finishCliTeardown({ engine: eng }); }
|
||||
try { await runRemediationPlan(eng, args); } finally { await eng.disconnect(); }
|
||||
return;
|
||||
}
|
||||
if (args.includes('--remediate')) {
|
||||
const { runRemediate } = await import('./commands/doctor.ts');
|
||||
const eng = await connectEngine();
|
||||
try { await runRemediate(eng, args); } finally { await finishCliTeardown({ engine: eng }); }
|
||||
try { await runRemediate(eng, args); } finally { await eng.disconnect(); }
|
||||
return;
|
||||
}
|
||||
|
||||
@@ -1295,21 +1192,13 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
// "user chose --fast while config is present".
|
||||
await runDoctor(null, args, getDbUrlSource());
|
||||
} else {
|
||||
// #2084: both failure kinds (connect throw, runDoctor(eng) throw) still
|
||||
// fall back to filesystem-only checks — identical to the prior shape.
|
||||
// The finally closes the gap where a runDoctor(eng) throw used to skip
|
||||
// the in-try disconnect. NOTE: runDoctor normally calls process.exit
|
||||
// itself, which preempts this finally — in-command exit sites bypassing
|
||||
// teardown are a pre-existing class, tracked as a TODOS.md follow-up.
|
||||
let eng: BrainEngine | null = null;
|
||||
try {
|
||||
eng = await connectEngine();
|
||||
const eng = await connectEngine();
|
||||
await runDoctor(eng, args);
|
||||
await eng.disconnect();
|
||||
} catch {
|
||||
// DB unavailable — still run filesystem checks
|
||||
await runDoctor(null, args, getDbUrlSource());
|
||||
} finally {
|
||||
if (eng) await finishCliTeardown({ engine: eng });
|
||||
}
|
||||
}
|
||||
return;
|
||||
@@ -1323,7 +1212,7 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
try {
|
||||
await runZeSwitch(args, eng);
|
||||
} finally {
|
||||
await finishCliTeardown({ engine: eng });
|
||||
await eng.disconnect();
|
||||
}
|
||||
return;
|
||||
}
|
||||
@@ -1339,7 +1228,7 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
execSync(`bash "${scriptPath}"`, { stdio: 'inherit', env: { ...process.env } });
|
||||
} catch (e: any) {
|
||||
// Non-zero exit = some tests failed (exit code = failure count)
|
||||
setCliExitVerdict(e.status ?? 1);
|
||||
process.exit(e.status ?? 1);
|
||||
}
|
||||
return;
|
||||
}
|
||||
@@ -1368,15 +1257,12 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
await runDream(eng, args);
|
||||
} finally {
|
||||
// #1471 invariant tripwire (the dream-cycle owner): `eng` created the
|
||||
// module singleton (first module connector) and is torn down LAST,
|
||||
// module singleton (first module connector) and is disconnected LAST,
|
||||
// here, after the whole cycle. The ownership fix relies on this owner's
|
||||
// lifetime strictly dominating every borrower (lint/doctor probe engines
|
||||
// created mid-cycle). Do NOT tear down `eng` before runDream returns, or
|
||||
// created mid-cycle). Do NOT disconnect `eng` before runDream returns, or
|
||||
// a borrower could outlive the owner and lose the shared singleton.
|
||||
// #2084: routed through the shared bounded teardown — dream runs as an
|
||||
// overnight cron, where a lingering-socket hang is a silent zombie
|
||||
// (closes the TODOS.md drain-before-owner-disconnect item).
|
||||
if (eng) await finishCliTeardown({ engine: eng });
|
||||
if (eng) await eng.disconnect();
|
||||
}
|
||||
return;
|
||||
}
|
||||
@@ -1388,8 +1274,7 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
// The handler self-configures the AI gateway from loadConfig() + process.env.
|
||||
if (command === 'eval' && args[0] === 'cross-modal') {
|
||||
const { runEvalCrossModal } = await import('./commands/eval-cross-modal.ts');
|
||||
setCliExitVerdict(await runEvalCrossModal(args.slice(1)));
|
||||
return;
|
||||
process.exit(await runEvalCrossModal(args.slice(1)));
|
||||
}
|
||||
|
||||
// v0.32 EXP-5 (codex review #10): `eval takes-quality replay <receipt>`
|
||||
@@ -1400,8 +1285,7 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
// engine-required path below.
|
||||
if (command === 'eval' && args[0] === 'takes-quality' && args[1] === 'replay') {
|
||||
const { runReplayNoBrain } = await import('./commands/eval-takes-quality.ts');
|
||||
setCliExitVerdict(await runReplayNoBrain(args.slice(2)));
|
||||
return;
|
||||
process.exit(await runReplayNoBrain(args.slice(2)));
|
||||
}
|
||||
|
||||
// v0.28.8: longmemeval brings its own in-memory PGLite. Bypassing
|
||||
@@ -1427,22 +1311,13 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
return;
|
||||
}
|
||||
|
||||
// v0.42.x (#2390): `gbrain eval chronicle` is deterministic — brings its own
|
||||
// in-memory PGLite, no DB/gateway. CI fixture gate runs anywhere.
|
||||
if (command === 'eval' && args[0] === 'chronicle') {
|
||||
const { runEvalChronicle } = await import('./commands/eval-chronicle.ts');
|
||||
setCliExitVerdict(await runEvalChronicle(args.slice(1)));
|
||||
return;
|
||||
}
|
||||
|
||||
// v0.41.13.0: `gbrain eval conversation-parser` is pure-function
|
||||
// (parses fixture JSONL, runs parseConversation, scores results).
|
||||
// No DB access; bypass connectEngine entirely so the CI fixture
|
||||
// gate runs on machines with no `~/.gbrain/config.json`.
|
||||
if (command === 'eval' && args[0] === 'conversation-parser') {
|
||||
const { runEvalConversationParser } = await import('./commands/eval-conversation-parser.ts');
|
||||
setCliExitVerdict(await runEvalConversationParser(args.slice(1)));
|
||||
return;
|
||||
process.exit(await runEvalConversationParser(args.slice(1)));
|
||||
}
|
||||
|
||||
// v0.41.13.0: `gbrain conversation-parser list-builtins | validate
|
||||
@@ -1470,8 +1345,7 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
const cfgPre = loadConfig();
|
||||
if (isThinClient(cfgPre)) {
|
||||
const { runEvalWhoknows } = await import('./commands/eval-whoknows.ts');
|
||||
setCliExitVerdict(await runEvalWhoknows(null, args.slice(1)));
|
||||
return;
|
||||
process.exit(await runEvalWhoknows(null, args.slice(1)));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1485,8 +1359,7 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
if (cfgPre && isThinClient(cfgPre)) {
|
||||
const { runStatus } = await import('./commands/status.ts');
|
||||
const result = await runStatus(null, args);
|
||||
setCliExitVerdict(result.exitCode);
|
||||
return;
|
||||
process.exit(result.exitCode);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1565,7 +1438,7 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
}
|
||||
throw e;
|
||||
} finally {
|
||||
await finishCliTeardown({ engine });
|
||||
try { await engine.disconnect(); } catch { /* best-effort */ }
|
||||
}
|
||||
return;
|
||||
}
|
||||
@@ -1603,27 +1476,6 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
}
|
||||
}
|
||||
|
||||
// Thin-client `jobs` dispatch: `list` and `get` route over MCP (v0.32
|
||||
// routing branches in commands/jobs.ts) and never touch a local engine —
|
||||
// but falling through to connectEngine() below fabricates an empty
|
||||
// scratch PGLite in the thin-client GBRAIN_HOME and replays the entire
|
||||
// migration chain on every invocation before the remote call even runs.
|
||||
// Dispatch them engine-free here; every other jobs subcommand is
|
||||
// host-queue-bound, so refuse with a pinpoint hint instead of building
|
||||
// the scratch store.
|
||||
if (command === 'jobs') {
|
||||
const cfgJobs = loadConfig();
|
||||
if (isThinClient(cfgJobs)) {
|
||||
const jobsSub = args[0];
|
||||
if (jobsSub === 'list' || jobsSub === 'get') {
|
||||
const { runJobs } = await import('./commands/jobs.ts');
|
||||
await runJobs(null, args);
|
||||
return;
|
||||
}
|
||||
refuseThinClient('jobs', cfgJobs!.remote_mcp!.mcp_url);
|
||||
}
|
||||
}
|
||||
|
||||
// All remaining CLI-only commands need a DB connection
|
||||
const engine = await connectEngine();
|
||||
try {
|
||||
@@ -1638,7 +1490,7 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
// so wrappers (sync, CI scripts, `&& gbrain doctor`) propagate.
|
||||
const importResult = await runImport(engine, args);
|
||||
if (importResult.errors > 0) {
|
||||
setCliExitVerdict(1);
|
||||
process.exitCode = 1;
|
||||
}
|
||||
break;
|
||||
}
|
||||
@@ -1820,15 +1672,6 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
case 'status': {
|
||||
const { runStatus } = await import('./commands/status.ts');
|
||||
const result = await runStatus(engine, args);
|
||||
// #2084 inner-exit sweep: a mid-switch exit skips the finally teardown.
|
||||
setCliExitVerdict(result.exitCode);
|
||||
break;
|
||||
}
|
||||
// v0.43 (#2180) — `gbrain advisor`: ranked, read-only "what to do next".
|
||||
// CLI surface; the same signals are exposed over MCP via the `advisor` op.
|
||||
case 'advisor': {
|
||||
const { runAdvisorCli } = await import('./commands/advisor.ts');
|
||||
const result = await runAdvisorCli(engine, args);
|
||||
process.exit(result.exitCode);
|
||||
// eslint-disable-next-line no-unreachable
|
||||
break;
|
||||
@@ -2000,15 +1843,6 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
await runQuarantine(engine, args);
|
||||
break;
|
||||
}
|
||||
case 'watch': {
|
||||
// v0.43 (#2095): push-based context transport. Blocks in the stdin
|
||||
// iteration (interactive stays alive; piped exits at EOF), then the
|
||||
// finally below runs finishCliTeardown (volunteer events drain with
|
||||
// every other sink) and the import.meta.main seam flush-exits.
|
||||
const { runWatch } = await import('./commands/watch.ts');
|
||||
await runWatch(engine, args);
|
||||
break;
|
||||
}
|
||||
case 'storage': {
|
||||
const { runStorage } = await import('./commands/storage.ts');
|
||||
await runStorage(engine, args);
|
||||
@@ -2032,15 +1866,6 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
await runReindexCodeCli(engine, args);
|
||||
break;
|
||||
}
|
||||
case 'reindex-search-vector': {
|
||||
// Explicit recreate of FTS trigger functions + batched backfill,
|
||||
// honoring GBRAIN_FTS_LANGUAGE. Use after changing the language
|
||||
// env var on a brain that already ran the configurable_fts_language
|
||||
// migration.
|
||||
const { runReindexSearchVectorCli } = await import('./commands/reindex-search-vector.ts');
|
||||
await runReindexSearchVectorCli(engine, args);
|
||||
break;
|
||||
}
|
||||
case 'reindex-frontmatter': {
|
||||
// v0.29.1: recovery / explicit-rebuild path for pages.effective_date.
|
||||
// Mirror of reindex-code shape. Wraps the shared library function in
|
||||
@@ -2088,16 +1913,31 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
}
|
||||
} finally {
|
||||
syncWatchdog?.dispose(); // #1633: tear down the hard-deadline watchdog on clean exit
|
||||
// #2084 — the CLI_ONLY fall-through teardown (drain every background-work
|
||||
// sink, THEN disconnect, under a computed-deadline backstop) lives in
|
||||
// finishCliTeardown. `gbrain capture`'s fire-and-forget facts:absorb job
|
||||
// gets its drain window before PGLite's db.close() can race it into the
|
||||
// re-pump busy-loop (#1762). #1471: this is also the fall-through
|
||||
// OWNER-disconnect — the owner is torn down LAST (after the drain), so
|
||||
// module-singleton borrowers never outlive it. `serve` skips teardown
|
||||
// entirely: the daemon owns its lifecycle.
|
||||
// v0.42.20.0 (#1762) — the CLI_ONLY path (which owns `gbrain capture`)
|
||||
// lacked the op-dispatch drain-before-disconnect contract. `put_page` fires
|
||||
// a fire-and-forget facts:absorb job AFTER printing the receipt; on a
|
||||
// multi-chunk page that job is in flight when this finally tears the engine
|
||||
// down, and `engine.disconnect()` nulling PGLite's _db mid-job spins
|
||||
// db.close() into a 100%-CPU busy-loop that pins the single-writer lock.
|
||||
// Drain every background-work sink first (facts shutdown() abort cancels a
|
||||
// hung Haiku), THEN disconnect. The drain-before-disconnect is the causal
|
||||
// fix; the force-exit defense below is secondary (it CANNOT preempt a WASM
|
||||
// busy-loop on a pinned JS thread — that's exactly why the drain matters).
|
||||
// #1471: this is also the fall-through OWNER-disconnect — the owner is torn
|
||||
// down LAST (after the drain), so module-singleton borrowers never outlive it.
|
||||
if (command !== 'serve') {
|
||||
await finishCliTeardown({ engine });
|
||||
const forceExit = shouldForceExitAfterMain();
|
||||
let hardExitTimer: ReturnType<typeof setTimeout> | undefined;
|
||||
if (forceExit) {
|
||||
hardExitTimer = setTimeout(() => {
|
||||
console.warn('[cli] engine.disconnect() did not return within 10000ms — force-exiting');
|
||||
process.exit(process.exitCode ?? 0);
|
||||
}, 10_000);
|
||||
hardExitTimer.unref?.();
|
||||
}
|
||||
await drainAllBackgroundWorkForCliExit();
|
||||
await engine.disconnect();
|
||||
if (hardExitTimer) clearTimeout(hardExitTimer);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -2289,7 +2129,7 @@ IMPORT/EXPORT
|
||||
import <dir> [--no-embed] Import markdown directory
|
||||
sync [--repo <path>] [flags] Git-to-brain incremental sync
|
||||
sync --watch [--interval N] Continuous sync (loops until stopped)
|
||||
See also: autopilot --install (continuous daemon).
|
||||
sync --install-cron Install persistent sync daemon
|
||||
export [--dir ./out/] Export to markdown
|
||||
export --restore-only [--repo <p>] Restore missing supabase-only files
|
||||
[--type T] [--slug-prefix S] With optional filters
|
||||
@@ -2355,14 +2195,7 @@ BRAIN (capture / ideate / explore — v0.37/v0.38)
|
||||
SOURCES (multi-repo / multi-brain)
|
||||
sources list Show registered sources
|
||||
sources add <id> --path <p> Register a source (id = short name, e.g. 'wiki')
|
||||
sources remove <id> Remove a source + its pages (--confirm-destructive)
|
||||
sources archive <id> Soft-delete: hide from search, recoverable for 72h
|
||||
sources restore <id> Un-archive a soft-deleted source
|
||||
sources archived List soft-deleted sources and their purge expiry
|
||||
sources purge [<id>] Permanently delete archived sources
|
||||
sources status Per-source dashboard (sync lag, embed coverage)
|
||||
sources --help Full subcommand list (rename, default, attach,
|
||||
current, federate, set-cr-mode, webhook, harden, ...)
|
||||
sources remove <id> Remove a source + its pages
|
||||
sync --all Sync all sources with a local_path
|
||||
sync --source <id> Sync one specific source
|
||||
repos ... DEPRECATED alias for 'sources' (v0.19.0)
|
||||
@@ -2376,9 +2209,6 @@ CODE INDEXING (v0.19.0 / v0.20.0 Cathedral II)
|
||||
query <q> --symbol-kind <k> Filter to symbol type (function|class|method|...) (v0.20.0)
|
||||
reconcile-links [--dry-run] Batch-recompute doc↔impl edges (v0.20.0)
|
||||
reindex-code [--source id] [--yes] Explicit code-page reindex (v0.20.0)
|
||||
reindex-search-vector [--dry-run] [--yes] [--json]
|
||||
Recreate FTS triggers + backfill under
|
||||
$GBRAIN_FTS_LANGUAGE (default 'english')
|
||||
sync --strategy code Sync code files into the brain
|
||||
|
||||
JOBS (Minions)
|
||||
@@ -2404,13 +2234,10 @@ ADMIN
|
||||
serve MCP server (stdio)
|
||||
serve --http [--port N] HTTP MCP server with OAuth 2.1
|
||||
--token-ttl N Access token TTL in seconds (default: 3600)
|
||||
--enable-dcr Enable Dynamic Client Registration (DCR clients default to authorization_code)
|
||||
--enable-dcr-insecure Also allow the consent-bypassing client_credentials grant on DCR (implies --enable-dcr)
|
||||
--enable-dcr Enable Dynamic Client Registration
|
||||
--public-url URL Public issuer URL (required behind proxy/tunnel)
|
||||
connect <mcp-url> --token <t> Wire Claude Code to a remote gbrain (bearer token)
|
||||
[--install] [--json] Print the paste-ready command, or --install to run it
|
||||
watch [--json] Push-based context: pipe conversation turns in,
|
||||
volunteered brain pages stream out (#2095)
|
||||
call <tool> '<json>' Raw tool invocation
|
||||
version Version info
|
||||
--tools-json Tool discovery (JSON)
|
||||
@@ -2422,25 +2249,9 @@ Run gbrain <command> --help for command-specific help.
|
||||
// Only auto-run when invoked as the entry point (the compiled binary or
|
||||
// `bun src/cli.ts`). Guarded so tests can import cliAliases / printOpHelp
|
||||
// without triggering argv parsing + main(). v114 (#1941).
|
||||
//
|
||||
// #2084 — the ONE process-exit seam for one-shot commands. Every teardown site
|
||||
// routes through finishCliTeardown (which returns); the exit itself happens
|
||||
// here, after main() settles, so the CLI never waits on Bun's event loop to
|
||||
// drain (stuck PgBouncer sockets kept it alive — endPoolBounded races PAST a
|
||||
// stuck pool.end() by design). flushThenExit fences stdout/stderr and holds a
|
||||
// short aliveness grace so piped output is delivered before exit (#1959).
|
||||
// Daemons (`serve`) are excluded by shouldForceExitAfterMain and keep the
|
||||
// pre-#2084 behavior: main() resolves and the server's own work keeps the
|
||||
// process alive. A fatal error still exits 1 for every command, daemons
|
||||
// included (matches the prior unconditional process.exit(1) on rejection).
|
||||
if (import.meta.main) {
|
||||
main().then(
|
||||
() => {
|
||||
if (shouldForceExitAfterMain()) flushThenExit(currentExitCode());
|
||||
},
|
||||
(e) => {
|
||||
console.error(e.message || e);
|
||||
flushThenExit(1);
|
||||
},
|
||||
);
|
||||
main().catch(e => {
|
||||
console.error(e.message || e);
|
||||
process.exit(1);
|
||||
});
|
||||
}
|
||||
|
||||
@@ -1,140 +0,0 @@
|
||||
/**
|
||||
* commands/advisor.ts — `gbrain advisor` CLI surface.
|
||||
*
|
||||
* gbrain advisor # ranked, agent-readable action list (human render)
|
||||
* gbrain advisor --json # structured findings; exit non-zero on critical (E2)
|
||||
* gbrain advisor --apply ID # run ONE finding's fix, local-only, after confirm (E5)
|
||||
*
|
||||
* The advisor itself never mutates. `--apply` is the only path that runs a fix,
|
||||
* and it: refuses over MCP (CLI is always local), only acts on allowlisted
|
||||
* findings (those carrying a dispatch_id), executes the fix as STRUCTURED ARGV
|
||||
* via a child process (never a shell — no injection), and confirms first.
|
||||
*/
|
||||
|
||||
import { spawnSync } from 'child_process';
|
||||
import { createInterface } from 'readline';
|
||||
import { resolve as resolvePath } from 'path';
|
||||
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { VERSION } from '../version.ts';
|
||||
import { loadConfig } from '../core/config.ts';
|
||||
import { autoDetectSkillsDir } from '../core/repo-root.ts';
|
||||
import { runAdvisor } from '../core/advisor/run.ts';
|
||||
import { renderAdvisorReport } from '../core/advisor/render.ts';
|
||||
import { appendAdvisorRun, summarizeDeltas } from '../core/advisor/history.ts';
|
||||
import { resolveApplyTarget } from '../core/advisor/apply.ts';
|
||||
import type { AdvisorContext, AdvisorReport } from '../core/advisor/types.ts';
|
||||
|
||||
export interface AdvisorCliResult {
|
||||
exitCode: 0 | 1 | 2;
|
||||
}
|
||||
|
||||
function buildContext(engine: BrainEngine): AdvisorContext {
|
||||
const det = autoDetectSkillsDir();
|
||||
const skillsDir = det.dir;
|
||||
const workspace = skillsDir ? resolvePath(skillsDir, '..') : null;
|
||||
return {
|
||||
engine,
|
||||
config: loadConfig() ?? ({} as AdvisorContext['config']),
|
||||
version: VERSION,
|
||||
workspace,
|
||||
skillsDir,
|
||||
now: new Date(),
|
||||
remote: false, // CLI is always the trusted local owner
|
||||
};
|
||||
}
|
||||
|
||||
/** Exit-code contract (E2): 0 clean / 1 warn / 2 critical. */
|
||||
function exitFor(report: AdvisorReport): 0 | 1 | 2 {
|
||||
if (report.worst === 'critical') return 2;
|
||||
if (report.worst === 'warn') return 1;
|
||||
return 0;
|
||||
}
|
||||
|
||||
export async function runAdvisorCli(engine: BrainEngine, args: string[]): Promise<AdvisorCliResult> {
|
||||
if (args.includes('--help') || args.includes('-h')) {
|
||||
console.log(
|
||||
'gbrain advisor [--json] [--apply <finding-id>]\n\n' +
|
||||
' (no flags) Ranked, agent-readable list of high-leverage actions for this brain.\n' +
|
||||
' --json Structured findings. Exit code: 0 clean / 1 warn / 2 critical.\n' +
|
||||
' --apply <id> Run ONE finding\'s fix (local-only, confirms first). Only findings\n' +
|
||||
' that report an apply id are runnable.\n\n' +
|
||||
'Read-only by default; never mutates without --apply + your confirmation.',
|
||||
);
|
||||
return { exitCode: 0 };
|
||||
}
|
||||
|
||||
const json = args.includes('--json');
|
||||
const applyIdx = args.indexOf('--apply');
|
||||
const applyId = applyIdx >= 0 ? args[applyIdx + 1] : undefined;
|
||||
|
||||
const ctx = buildContext(engine);
|
||||
const report = await runAdvisor(ctx);
|
||||
|
||||
if (applyId) {
|
||||
return applyFinding(report, applyId);
|
||||
}
|
||||
|
||||
// Record run history (local-only) for "since last run" deltas.
|
||||
let deltaNote = '';
|
||||
try {
|
||||
const prior = appendAdvisorRun(report);
|
||||
deltaNote = summarizeDeltas(prior, report);
|
||||
} catch {
|
||||
/* history is best-effort; never block the report */
|
||||
}
|
||||
|
||||
if (json) {
|
||||
process.stdout.write(JSON.stringify(report, null, 2) + '\n');
|
||||
} else {
|
||||
process.stdout.write(renderAdvisorReport(report));
|
||||
if (deltaNote) process.stdout.write(deltaNote + '\n');
|
||||
}
|
||||
return { exitCode: exitFor(report) };
|
||||
}
|
||||
|
||||
/**
|
||||
* E5: run a single finding's fix. Allowlist = findings carrying a dispatch_id.
|
||||
* Local-only (refused over MCP by construction — this is the CLI path). Executes
|
||||
* the structured argv via a child process with NO shell.
|
||||
*/
|
||||
function applyFinding(report: AdvisorReport, id: string): AdvisorCliResult {
|
||||
const target = resolveApplyTarget(report, id);
|
||||
if (!target.ok) {
|
||||
console.error(
|
||||
target.error +
|
||||
(target.runnable.length ? ` Runnable now: ${target.runnable.join(', ')}.` : ' Nothing is runnable right now.'),
|
||||
);
|
||||
return { exitCode: 2 };
|
||||
}
|
||||
|
||||
console.error(`About to run: ${target.display}`);
|
||||
if (!confirmTty('Proceed? [y/N]: ')) {
|
||||
console.error('Aborted. Nothing was run.');
|
||||
return { exitCode: 1 };
|
||||
}
|
||||
|
||||
const [cmd, ...rest] = target.argv;
|
||||
const res = spawnSync(cmd!, rest, { stdio: 'inherit', shell: false });
|
||||
return { exitCode: (res.status ?? 1) === 0 ? 0 : 2 };
|
||||
}
|
||||
|
||||
/** Synchronous y/N TTY confirm. Non-TTY → false (never auto-run). */
|
||||
function confirmTty(prompt: string): boolean {
|
||||
if (!process.stdin.isTTY) return false;
|
||||
// Bun supports a synchronous prompt via readline only async; use a tiny
|
||||
// blocking read on the TTY fd instead.
|
||||
process.stderr.write(prompt);
|
||||
const buf = Buffer.alloc(8);
|
||||
try {
|
||||
const fs = require('fs') as typeof import('fs');
|
||||
const n = fs.readSync(0, buf, 0, 8, null);
|
||||
const ans = buf.toString('utf8', 0, n).trim().toLowerCase();
|
||||
return ans === 'y' || ans === 'yes';
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// readline imported for type-compat with other commands; not used directly.
|
||||
void createInterface;
|
||||
+19
-78
@@ -74,12 +74,8 @@ SUBMITTING
|
||||
--follow Tail status until terminal (default on TTY)
|
||||
--detach Submit + print job id, exit immediately
|
||||
|
||||
Flags before the prompt are parsed normally. The no-value switches
|
||||
--detach, --follow and --no-follow are ALSO recognized when they trail
|
||||
the prompt, so \`gbrain agent run "do X" --detach\` detaches. Any other
|
||||
--word is treated as prompt text (no error). Use \`--\` to end flag
|
||||
parsing and pass the rest verbatim:
|
||||
gbrain agent run -- "literally --detach this, with --flags"
|
||||
Flags after \`run\` up to the first unrecognized token are parsed; the
|
||||
remainder is the prompt. Use \`--\` to explicitly terminate flag parsing.
|
||||
|
||||
VIEWING
|
||||
gbrain agent logs <job_id>
|
||||
@@ -106,86 +102,31 @@ interface RunFlags {
|
||||
detach: boolean;
|
||||
}
|
||||
|
||||
/** No-value switches that may also trail the prompt and get hoisted out (#1738). */
|
||||
const BOOLEAN_TAIL_FLAGS = new Set(['--follow', '--no-follow', '--detach']);
|
||||
|
||||
function applyBooleanFlag(flags: RunFlags, a: string): void {
|
||||
if (a === '--follow') flags.follow = true;
|
||||
else if (a === '--no-follow') flags.follow = false;
|
||||
else { flags.detach = true; flags.follow = false; } // --detach
|
||||
}
|
||||
|
||||
/** Read the value for a value-flag, rejecting a missing or flag-shaped value. */
|
||||
function requireFlagValue(args: string[], i: number, flag: string): string {
|
||||
const v = args[i];
|
||||
if (v === undefined || v.startsWith('--')) {
|
||||
throw new Error(`gbrain agent run: ${flag} requires a value. Run \`gbrain agent run --help\`.`);
|
||||
}
|
||||
return v;
|
||||
}
|
||||
|
||||
function parseIntFlagValue(v: string, flag: string): number {
|
||||
const n = parseInt(v, 10);
|
||||
if (Number.isNaN(n)) {
|
||||
throw new Error(`gbrain agent run: ${flag} expects a number, got "${v}".`);
|
||||
}
|
||||
return n;
|
||||
}
|
||||
|
||||
/**
|
||||
* Parse `agent run` args into flags + prompt (#1738).
|
||||
*
|
||||
* args ──► [ leading flag zone ] [ ── ? ] [ prompt … (trailing booleans) ]
|
||||
*
|
||||
* Leading zone: known flags (value + boolean) are consumed left-to-right until
|
||||
* the first positional token, an UNKNOWN --flag, or an explicit `--`. An
|
||||
* unknown --flag is NOT an error — it begins the freeform prompt, so
|
||||
* `agent run "--note: do X"` works without `--`. Value-flags missing their
|
||||
* value throw a usage error instead of silently capturing `undefined`/`NaN`.
|
||||
*
|
||||
* Prompt zone: a trailing run of the no-value switches (--detach/--follow/
|
||||
* --no-follow) is hoisted out so `agent run "do X" --detach` detaches. Only
|
||||
* trailing switches are hoisted; a `--word` elsewhere in the prompt stays
|
||||
* verbatim. After an explicit `--`, nothing is hoisted.
|
||||
*/
|
||||
function parseRunFlags(args: string[]): { flags: RunFlags; rest: string[] } {
|
||||
const flags: RunFlags = {
|
||||
follow: process.stdout.isTTY === true,
|
||||
detach: false,
|
||||
};
|
||||
let i = 0;
|
||||
let escaped = false;
|
||||
for (; i < args.length; i++) {
|
||||
const a = args[i]!;
|
||||
if (a === '--') { i++; escaped = true; break; }
|
||||
if (!a.startsWith('--')) break;
|
||||
let known = true;
|
||||
while (i < args.length) {
|
||||
const a = args[i];
|
||||
if (a === '--') { i++; break; }
|
||||
if (!isKnownFlag(a!)) break;
|
||||
switch (a) {
|
||||
case '--subagent-def': flags.subagentDef = requireFlagValue(args, ++i, a); break;
|
||||
case '--model': flags.model = requireFlagValue(args, ++i, a); break;
|
||||
case '--max-turns': flags.maxTurns = parseIntFlagValue(requireFlagValue(args, ++i, a), a); break;
|
||||
case '--tools': flags.tools = requireFlagValue(args, ++i, a).split(',').map(s => s.trim()).filter(Boolean); break;
|
||||
case '--timeout-ms': flags.timeoutMs = parseIntFlagValue(requireFlagValue(args, ++i, a), a); break;
|
||||
case '--fanout-manifest': flags.fanoutManifest = requireFlagValue(args, ++i, a); break;
|
||||
case '--follow': flags.follow = true; break;
|
||||
case '--no-follow': flags.follow = false; break;
|
||||
case '--detach': flags.detach = true; flags.follow = false; break;
|
||||
default: known = false; break;
|
||||
}
|
||||
if (!known) break; // unknown --flag → first token of the (freeform) prompt
|
||||
}
|
||||
const rest = args.slice(i);
|
||||
// An explicit `--` terminates flag parsing wherever it appears — leading
|
||||
// zone (escaped) OR after a positional (the leading loop breaks before it,
|
||||
// so `escaped` stays false). Honor both: when the prompt carries a literal
|
||||
// `--`, hoist nothing, so `agent run note -- --detach` keeps `--detach`
|
||||
// verbatim instead of silently flipping detach mode.
|
||||
if (!escaped && !rest.includes('--')) {
|
||||
while (rest.length > 0 && BOOLEAN_TAIL_FLAGS.has(rest[rest.length - 1]!)) {
|
||||
applyBooleanFlag(flags, rest.pop()!);
|
||||
case '--subagent-def': flags.subagentDef = args[++i]; i++; break;
|
||||
case '--model': flags.model = args[++i]; i++; break;
|
||||
case '--max-turns': flags.maxTurns = parseInt(args[++i] ?? '', 10); i++; break;
|
||||
case '--tools': flags.tools = (args[++i] ?? '').split(',').map(s => s.trim()).filter(Boolean); i++; break;
|
||||
case '--timeout-ms': flags.timeoutMs = parseInt(args[++i] ?? '', 10); i++; break;
|
||||
case '--fanout-manifest': flags.fanoutManifest = args[++i]; i++; break;
|
||||
case '--follow': flags.follow = true; i++; break;
|
||||
case '--no-follow': flags.follow = false; i++; break;
|
||||
case '--detach': flags.detach = true; flags.follow = false; i++; break;
|
||||
default:
|
||||
throw new Error(`unknown flag: ${a}. Run \`gbrain agent run --help\` for usage.`);
|
||||
}
|
||||
}
|
||||
return { flags, rest };
|
||||
return { flags, rest: args.slice(i) };
|
||||
}
|
||||
|
||||
export async function runAgentRun(engine: BrainEngine, args: string[]): Promise<void> {
|
||||
@@ -310,7 +251,7 @@ async function runFanout(engine: BrainEngine, queue: MinionQueue, flags: RunFlag
|
||||
// do this after submission because each add() returns the committed
|
||||
// row's id; the aggregator's seed started with an empty array.
|
||||
await engine.executeRaw(
|
||||
`UPDATE minion_jobs SET data = jsonb_set(data, '{children_ids}', $1::text::jsonb) WHERE id = $2`,
|
||||
`UPDATE minion_jobs SET data = jsonb_set(data, '{children_ids}', $1::jsonb) WHERE id = $2`,
|
||||
[JSON.stringify(childIds), aggregator.id],
|
||||
);
|
||||
|
||||
|
||||
+4
-70
@@ -346,12 +346,6 @@ interface RegisterClientArgs {
|
||||
federatedRead: string[] | undefined;
|
||||
redirectUris: string[];
|
||||
tokenEndpointAuthMethod: string | undefined;
|
||||
boundTools: string[] | undefined;
|
||||
boundSourceId: string | undefined;
|
||||
boundBrainId: string | undefined;
|
||||
boundSlugPrefixes: string[] | undefined;
|
||||
boundMaxConcurrent: number | undefined;
|
||||
budgetUsdPerDay: string | undefined;
|
||||
}
|
||||
|
||||
export function parseRegisterClientArgs(args: string[]): RegisterClientArgs {
|
||||
@@ -362,12 +356,6 @@ export function parseRegisterClientArgs(args: string[]): RegisterClientArgs {
|
||||
federatedRead: undefined,
|
||||
redirectUris: [],
|
||||
tokenEndpointAuthMethod: undefined,
|
||||
boundTools: undefined,
|
||||
boundSourceId: undefined,
|
||||
boundBrainId: undefined,
|
||||
boundSlugPrefixes: undefined,
|
||||
boundMaxConcurrent: undefined,
|
||||
budgetUsdPerDay: undefined,
|
||||
};
|
||||
let i = 0;
|
||||
let grantTypesSet = false;
|
||||
@@ -401,34 +389,6 @@ export function parseRegisterClientArgs(args: string[]): RegisterClientArgs {
|
||||
case '--token-endpoint-auth-method':
|
||||
out.tokenEndpointAuthMethod = requireValue();
|
||||
i += 2; break;
|
||||
case '--bound-tools': {
|
||||
const v = requireValue();
|
||||
out.boundTools = v.split(',').map(s => s.trim()).filter(Boolean);
|
||||
i += 2; break;
|
||||
}
|
||||
case '--bound-source': out.boundSourceId = requireValue(); i += 2; break;
|
||||
case '--bound-brain': out.boundBrainId = requireValue(); i += 2; break;
|
||||
case '--bound-slug-prefixes': {
|
||||
const v = requireValue();
|
||||
out.boundSlugPrefixes = v.split(',').map(s => s.trim()).filter(Boolean);
|
||||
i += 2; break;
|
||||
}
|
||||
case '--bound-max-concurrent': {
|
||||
const v = Number(requireValue());
|
||||
if (!Number.isInteger(v) || v < 1) {
|
||||
throw new Error('--bound-max-concurrent must be a positive integer');
|
||||
}
|
||||
out.boundMaxConcurrent = v;
|
||||
i += 2; break;
|
||||
}
|
||||
case '--budget-usd-per-day': {
|
||||
const v = requireValue();
|
||||
if (!/^\d+(?:\.\d{1,2})?$/.test(v)) {
|
||||
throw new Error('--budget-usd-per-day must be a non-negative decimal with at most 2 decimal places');
|
||||
}
|
||||
out.budgetUsdPerDay = v;
|
||||
i += 2; break;
|
||||
}
|
||||
default:
|
||||
throw new Error(`Unknown flag: ${flag}`);
|
||||
}
|
||||
@@ -445,7 +405,7 @@ export function parseRegisterClientArgs(args: string[]): RegisterClientArgs {
|
||||
|
||||
async function registerClient(name: string, args: string[]) {
|
||||
if (!name) {
|
||||
console.error('Usage: auth register-client <name> [--grant-types G] [--scopes S] [--source SOURCE] [--federated-read SRC1,SRC2,...] [--redirect-uri URI ...] [--token-endpoint-auth-method client_secret_post|client_secret_basic|none] [--bound-tools T1,T2] [--bound-source SOURCE] [--bound-brain BRAIN] [--bound-slug-prefixes P1,P2] [--bound-max-concurrent N] [--budget-usd-per-day USD]');
|
||||
console.error('Usage: auth register-client <name> [--grant-types G] [--scopes S] [--source SOURCE] [--federated-read SRC1,SRC2,...] [--redirect-uri URI ...] [--token-endpoint-auth-method client_secret_post|client_secret_basic|none]');
|
||||
process.exit(1);
|
||||
}
|
||||
let parsed: RegisterClientArgs;
|
||||
@@ -453,28 +413,17 @@ async function registerClient(name: string, args: string[]) {
|
||||
parsed = parseRegisterClientArgs(args);
|
||||
} catch (e: any) {
|
||||
console.error(`Error: ${e.message}`);
|
||||
console.error('Usage: auth register-client <name> [--grant-types G] [--scopes S] [--source SOURCE] [--federated-read SRC1,SRC2,...] [--redirect-uri URI ...] [--token-endpoint-auth-method client_secret_post|client_secret_basic|none] [--bound-tools T1,T2] [--bound-source SOURCE] [--bound-brain BRAIN] [--bound-slug-prefixes P1,P2] [--bound-max-concurrent N] [--budget-usd-per-day USD]');
|
||||
console.error('Usage: auth register-client <name> [--grant-types G] [--scopes S] [--source SOURCE] [--federated-read SRC1,SRC2,...] [--redirect-uri URI ...] [--token-endpoint-auth-method client_secret_post|client_secret_basic|none]');
|
||||
process.exit(1);
|
||||
}
|
||||
const { grantTypes, scopes, sourceId, federatedRead, redirectUris, tokenEndpointAuthMethod } = parsed;
|
||||
const agentBindings = parsed.boundTools || parsed.boundSourceId || parsed.boundBrainId ||
|
||||
parsed.boundSlugPrefixes || parsed.boundMaxConcurrent !== undefined || parsed.budgetUsdPerDay !== undefined
|
||||
? {
|
||||
boundTools: parsed.boundTools,
|
||||
boundSourceId: parsed.boundSourceId,
|
||||
boundBrainId: parsed.boundBrainId,
|
||||
boundSlugPrefixes: parsed.boundSlugPrefixes,
|
||||
boundMaxConcurrent: parsed.boundMaxConcurrent,
|
||||
budgetUsdPerDay: parsed.budgetUsdPerDay,
|
||||
}
|
||||
: undefined;
|
||||
|
||||
try {
|
||||
await withConfiguredSql(async (sql) => {
|
||||
const { GBrainOAuthProvider } = await import('../core/oauth-provider.ts');
|
||||
const provider = new GBrainOAuthProvider({ sql });
|
||||
const { clientId, clientSecret } = await provider.registerClientManual(
|
||||
name, grantTypes, scopes, redirectUris, sourceId, federatedRead, tokenEndpointAuthMethod, agentBindings,
|
||||
name, grantTypes, scopes, redirectUris, sourceId, federatedRead, tokenEndpointAuthMethod,
|
||||
);
|
||||
const effectiveFederated = federatedRead && federatedRead.length > 0 ? federatedRead : [sourceId];
|
||||
const effectiveAuthMethod = tokenEndpointAuthMethod || 'client_secret_post';
|
||||
@@ -492,16 +441,7 @@ async function registerClient(name: string, args: string[]) {
|
||||
console.log(` Redirect URIs: ${redirectUris.join(', ')}`);
|
||||
}
|
||||
console.log(` Write source: ${sourceId}`);
|
||||
console.log(` Federated reads: ${effectiveFederated.join(', ')}`);
|
||||
if (agentBindings) {
|
||||
console.log(` Bound tools: ${(parsed.boundTools ?? []).join(', ') || '<none>'}`);
|
||||
console.log(` Bound source: ${parsed.boundSourceId ?? '<none>'}`);
|
||||
console.log(` Bound brain: ${parsed.boundBrainId ?? '<none>'}`);
|
||||
console.log(` Bound slug prefixes:${parsed.boundSlugPrefixes ? ' ' + parsed.boundSlugPrefixes.join(', ') : ' <none>'}`);
|
||||
console.log(` Max concurrency: ${parsed.boundMaxConcurrent ?? 1}`);
|
||||
console.log(` Daily budget USD: ${parsed.budgetUsdPerDay ?? '<none>'}`);
|
||||
}
|
||||
console.log('');
|
||||
console.log(` Federated reads: ${effectiveFederated.join(', ')}\n`);
|
||||
if (clientSecret) {
|
||||
console.log('Save the client secret — it will not be shown again.');
|
||||
} else {
|
||||
@@ -587,12 +527,6 @@ Usage:
|
||||
--redirect-uri <https://...> (v0.41.3+; repeatable; required for authorization_code)
|
||||
--token-endpoint-auth-method <method> (v0.41.3+; client_secret_post | client_secret_basic | none;
|
||||
'none' = public PKCE-only client, no secret minted)
|
||||
--bound-tools <tool1,tool2> Bind submit_agent to an allow-list of tools
|
||||
--bound-source <id> Bind submit_agent jobs to a source id
|
||||
--bound-brain <id> Bind submit_agent jobs to a brain id
|
||||
--bound-slug-prefixes <prefix1,prefix2> Bind submit_agent writes to slug prefixes
|
||||
--bound-max-concurrent <n> Bound submit_agent concurrency (default: 1)
|
||||
--budget-usd-per-day <usd> Bound submit_agent daily spend cap
|
||||
gbrain auth revoke-client <client_id> Hard-delete an OAuth 2.1 client (cascades to tokens + codes)
|
||||
gbrain auth test <url> --token <token> Smoke-test a remote MCP server
|
||||
`);
|
||||
|
||||
@@ -32,26 +32,9 @@
|
||||
|
||||
import type { BrainEngine, SourceRow } from '../core/engine.ts';
|
||||
import type { MinionQueue } from '../core/minions/queue.ts';
|
||||
import { NON_GLOBAL_PHASES, GLOBAL_PHASES, LAST_GLOBAL_AT_KEY } from '../core/cycle.ts';
|
||||
|
||||
const FULL_CYCLE_FLOOR_MIN = 60;
|
||||
|
||||
// #2194 fix #2: failure cooldown. A source whose autopilot-cycle keeps
|
||||
// failing/timing-out re-dispatches every tick today (only SUCCESS gates
|
||||
// dispatch), so the same handful of sources fail and re-fan-out forever — the
|
||||
// self-perpetuating dead-job storm. Back a failed source off with bounded
|
||||
// exponential cooldown so a chronically-slow source can't re-dispatch every
|
||||
// tick. Disabled with autopilot.failure_cooldown_min=0.
|
||||
const FAILURE_COOLDOWN_BASE_MIN = 10;
|
||||
const FAILURE_COOLDOWN_CAP_MIN = 120;
|
||||
const FAILURE_COOLDOWN_EXP_CAP = 4; // 2^4 = 16× base before the cap clamps
|
||||
|
||||
/** Recent-failure record for one source (from minion_jobs dead/failed rows). */
|
||||
export interface SourceFailure { count: number; lastFailedAt: Date; }
|
||||
|
||||
/** Resolved cooldown knobs. baseMin <= 0 means the cooldown is disabled. */
|
||||
export interface CooldownOpts { baseMin: number; capMin: number; }
|
||||
|
||||
export interface FanoutOpts {
|
||||
repoPath: string;
|
||||
slot: string;
|
||||
@@ -75,8 +58,6 @@ export interface FanoutResult {
|
||||
skipped_fresh: string[];
|
||||
/** Source ids beyond the fanoutMax cap (will retry next tick). */
|
||||
skipped_cap: string[];
|
||||
/** Source ids skipped because they're in failure cooldown (#2194 fix #2). */
|
||||
skipped_cooldown: string[];
|
||||
/** True when this tick fell back to the legacy single-job path
|
||||
* (no sources rows / engine empty). */
|
||||
legacy_fallback: boolean;
|
||||
@@ -102,62 +83,6 @@ export async function resolveFanoutMax(engine: BrainEngine): Promise<number> {
|
||||
return engine.kind === 'pglite' ? 1 : 4;
|
||||
}
|
||||
|
||||
/**
|
||||
* Read the worker concurrency the supervisor most recently STARTED with, from
|
||||
* its `started` audit event (the lowest-coupling source — no extra lock-row
|
||||
* column). Filesystem read; returns null when no supervisor has ever started
|
||||
* (or the event lacks concurrency). Filtered by queue so a `shell`-queue
|
||||
* supervisor's concurrency doesn't leak into the `default`-queue decision.
|
||||
*
|
||||
* ADVISORY use only (doctor warning). Behavior-changing callers (the fanout
|
||||
* clamp) must additionally gate on a LIVE supervisor — see
|
||||
* resolveEffectiveFanoutMax — because a stale `started` row can otherwise
|
||||
* shrink fan-out for a supervisor that isn't running that config (codex #9/D5).
|
||||
*/
|
||||
export async function readSupervisorConcurrency(queue = 'default'): Promise<number | null> {
|
||||
try {
|
||||
const { readSupervisorEvents } = await import('../core/minions/handlers/supervisor-audit.ts');
|
||||
const events = readSupervisorEvents({ sinceMs: 24 * 60 * 60 * 1000 });
|
||||
const started = events
|
||||
.filter((e) => e.event === 'started' && (e.queue === undefined || e.queue === queue))
|
||||
.pop();
|
||||
const c = started?.concurrency;
|
||||
return typeof c === 'number' && Number.isFinite(c) ? c : null;
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolve fanoutMax CLAMPED to the worker's effective concurrency (#2194 fix #1).
|
||||
*
|
||||
* Fanning out more cycles than the worker can run guarantees waiters that then
|
||||
* race the stalled-sweeper. Clamp to `max(1, concurrency - 1)` — reserving ≥1
|
||||
* slot for targeted sync/embed jobs that share the `default` queue.
|
||||
*
|
||||
* codex #9 / D5: the clamp is BEHAVIOR-changing, so it trusts only a
|
||||
* proven-alive supervisor (live DB-lock holder, `ttl_expires_at`-gated). With
|
||||
* no live holder the concurrency is UNKNOWN and we fall back to the unclamped
|
||||
* default (4 pg / 1 pglite) — the safe direction (never starve on stale data).
|
||||
* Operators can disable the clamp via `autopilot.fanout_clamp_to_concurrency`.
|
||||
*/
|
||||
export async function resolveEffectiveFanoutMax(engine: BrainEngine, queue = 'default'): Promise<number> {
|
||||
const base = await resolveFanoutMax(engine);
|
||||
const clampCfg = await engine.getConfig('autopilot.fanout_clamp_to_concurrency');
|
||||
if (clampCfg === 'false' || clampCfg === '0') return base; // operator opt-out
|
||||
try {
|
||||
const { inspectLock, isLockHolderLive } = await import('../core/db-lock.ts');
|
||||
const { supervisorLockId, SUPERVISOR_LOCK_TTL_MIN } = await import('../core/minions/supervisor.ts');
|
||||
const snap = await inspectLock(engine, supervisorLockId(queue));
|
||||
if (!snap || !isLockHolderLive(snap, SUPERVISOR_LOCK_TTL_MIN)) return base; // no live holder → unknown → no clamp
|
||||
const concurrency = await readSupervisorConcurrency(queue);
|
||||
if (concurrency === null) return base;
|
||||
return Math.max(1, Math.min(base, concurrency - 1));
|
||||
} catch {
|
||||
return base;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Read `last_full_cycle_at` ISO string from a source's config JSONB.
|
||||
* Returns null when missing or unparseable. Pure function over the row
|
||||
@@ -186,133 +111,6 @@ export function isSourceStale(src: SourceRow, now = Date.now(), floorMin = FULL_
|
||||
return ageMin >= floorMin;
|
||||
}
|
||||
|
||||
/**
|
||||
* Most recent SUCCESSFUL cycle for a source. Prefers `last_source_cycle_at`
|
||||
* (per-source phases, written by the split cycle) and falls back to the legacy
|
||||
* `last_full_cycle_at`, so this works before AND after the cycle split.
|
||||
*/
|
||||
export function readLastSuccessAt(src: SourceRow): Date | null {
|
||||
const c = src.config ?? {};
|
||||
const raw = (typeof c.last_source_cycle_at === 'string' && c.last_source_cycle_at)
|
||||
|| (typeof c.last_full_cycle_at === 'string' && c.last_full_cycle_at)
|
||||
|| null;
|
||||
if (!raw) return null;
|
||||
const d = new Date(raw);
|
||||
return Number.isFinite(d.getTime()) ? d : null;
|
||||
}
|
||||
|
||||
/** Bounded exponential cooldown window (minutes) for a given failure count. */
|
||||
export function cooldownMinForCount(count: number, opts: CooldownOpts): number {
|
||||
if (count <= 0 || opts.baseMin <= 0) return 0;
|
||||
const mult = Math.pow(2, Math.min(count - 1, FAILURE_COOLDOWN_EXP_CAP));
|
||||
return Math.min(opts.baseMin * mult, opts.capMin);
|
||||
}
|
||||
|
||||
/**
|
||||
* Is a source currently in failure cooldown? Pure — drives both the dispatch
|
||||
* gate and the claim-time guard. A SUCCESS at-or-after the most recent failure
|
||||
* clears the cooldown (codex #7: operator repair / manual cycle re-eligibility),
|
||||
* so a recovered source is never suppressed by stale failure history.
|
||||
*/
|
||||
export function isInFailureCooldown(
|
||||
failure: SourceFailure | undefined,
|
||||
lastSuccessAt: Date | null,
|
||||
now: number,
|
||||
opts: CooldownOpts,
|
||||
): boolean {
|
||||
if (opts.baseMin <= 0) return false; // disabled
|
||||
if (!failure || failure.count <= 0) return false;
|
||||
if (lastSuccessAt && lastSuccessAt.getTime() >= failure.lastFailedAt.getTime()) return false;
|
||||
const cooldownMs = cooldownMinForCount(failure.count, opts) * 60_000;
|
||||
return (now - failure.lastFailedAt.getTime()) < cooldownMs;
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolve cooldown knobs from config. `autopilot.failure_cooldown_min` overrides
|
||||
* the base (0 = disable entirely — exactly today's behavior);
|
||||
* `autopilot.failure_cooldown_cap_min` overrides the ceiling.
|
||||
*/
|
||||
export async function resolveFailureCooldownOpts(engine: BrainEngine): Promise<CooldownOpts> {
|
||||
let baseMin = FAILURE_COOLDOWN_BASE_MIN;
|
||||
let capMin = FAILURE_COOLDOWN_CAP_MIN;
|
||||
const baseCfg = await engine.getConfig('autopilot.failure_cooldown_min');
|
||||
if (baseCfg !== null && baseCfg !== undefined && baseCfg !== '') {
|
||||
const n = parseInt(baseCfg, 10);
|
||||
if (Number.isFinite(n) && n >= 0) baseMin = n;
|
||||
}
|
||||
const capCfg = await engine.getConfig('autopilot.failure_cooldown_cap_min');
|
||||
if (capCfg) {
|
||||
const n = parseInt(capCfg, 10);
|
||||
if (Number.isFinite(n) && n >= 1) capMin = n;
|
||||
}
|
||||
return { baseMin, capMin };
|
||||
}
|
||||
|
||||
/**
|
||||
* Read recent dead/failed autopilot-cycle jobs grouped by source. Read-at-
|
||||
* dispatch (NOT a write hook) because timeouts/RSS-kills/stalls dead-letter via
|
||||
* SQL in queue.ts and never run handler code — a write-only cooldown would miss
|
||||
* the exact failures that drive the storm. Engine-parity-safe via executeRaw
|
||||
* (one query, both engines); cutoff is precomputed in JS to avoid INTERVAL
|
||||
* portability concerns. codex #6: rows with a null source_id are excluded.
|
||||
*/
|
||||
export async function readRecentSourceFailures(
|
||||
engine: BrainEngine,
|
||||
opts: { sinceMin?: number; sourceId?: string } = {},
|
||||
): Promise<Map<string, SourceFailure>> {
|
||||
const sinceMin = opts.sinceMin ?? FAILURE_COOLDOWN_CAP_MIN;
|
||||
const cutoff = new Date(Date.now() - sinceMin * 60_000).toISOString();
|
||||
const map = new Map<string, SourceFailure>();
|
||||
try {
|
||||
const params: unknown[] = [cutoff];
|
||||
let sql =
|
||||
`SELECT data->>'source_id' AS source_id,
|
||||
count(*)::int AS fail_count,
|
||||
max(finished_at) AS last_failed_at
|
||||
FROM minion_jobs
|
||||
WHERE name = 'autopilot-cycle'
|
||||
AND status IN ('dead','failed')
|
||||
AND data->>'source_id' IS NOT NULL
|
||||
AND finished_at IS NOT NULL
|
||||
AND finished_at > $1`;
|
||||
if (opts.sourceId) { params.push(opts.sourceId); sql += ` AND data->>'source_id' = $${params.length}`; }
|
||||
sql += ` GROUP BY data->>'source_id'`;
|
||||
const rows = await engine.executeRaw<{ source_id: string | null; fail_count: number; last_failed_at: string | Date }>(sql, params);
|
||||
for (const r of rows) {
|
||||
if (!r.source_id) continue; // codex #6 null-source guard (defensive)
|
||||
const last = r.last_failed_at instanceof Date ? r.last_failed_at : new Date(r.last_failed_at);
|
||||
if (!Number.isFinite(last.getTime())) continue;
|
||||
map.set(r.source_id, { count: Number(r.fail_count) || 0, lastFailedAt: last });
|
||||
}
|
||||
} catch {
|
||||
// Pre-migration / transient DB error → no cooldown data (fail open: dispatch).
|
||||
}
|
||||
return map;
|
||||
}
|
||||
|
||||
/**
|
||||
* Claim-time cooldown guard (codex #5 / D4): a job already queued or retrying
|
||||
* (max_attempts:2) can reach the worker after the dispatch gate decided. The
|
||||
* handler calls this immediately before runCycle; an in-cooldown claim becomes
|
||||
* a no-op skip (NOT a failure — it must not re-arm the cooldown). Shares the
|
||||
* exact cooldown math with the dispatch gate (DRY).
|
||||
*/
|
||||
export async function isSourceInCooldown(engine: BrainEngine, sourceId: string, now = Date.now()): Promise<boolean> {
|
||||
const opts = await resolveFailureCooldownOpts(engine);
|
||||
if (opts.baseMin <= 0) return false;
|
||||
const failures = await readRecentSourceFailures(engine, { sinceMin: opts.capMin, sourceId });
|
||||
const failure = failures.get(sourceId);
|
||||
if (!failure) return false;
|
||||
let lastSuccessAt: Date | null = null;
|
||||
try {
|
||||
const rows = await engine.executeRaw<{ config: Record<string, unknown> | null }>(
|
||||
`SELECT config FROM sources WHERE id = $1`, [sourceId],
|
||||
);
|
||||
if (rows[0]) lastSuccessAt = readLastSuccessAt({ config: rows[0].config ?? {} } as SourceRow);
|
||||
} catch { /* treat as no success */ }
|
||||
return isInFailureCooldown(failure, lastSuccessAt, now, opts);
|
||||
}
|
||||
|
||||
/**
|
||||
* Decide which sources to dispatch this tick. Pure function so tests can
|
||||
* exercise the freshness gate + cap math without an engine.
|
||||
@@ -328,21 +126,11 @@ export function selectSourcesForDispatch(
|
||||
fanoutMax: number,
|
||||
now = Date.now(),
|
||||
floorMin = FULL_CYCLE_FLOOR_MIN,
|
||||
recentFailures: Map<string, SourceFailure> = new Map(),
|
||||
cooldownOpts: CooldownOpts = { baseMin: FAILURE_COOLDOWN_BASE_MIN, capMin: FAILURE_COOLDOWN_CAP_MIN },
|
||||
): { dispatch: SourceRow[]; skippedFresh: SourceRow[]; skippedCap: SourceRow[]; skippedCooldown: SourceRow[] } {
|
||||
): { dispatch: SourceRow[]; skippedFresh: SourceRow[]; skippedCap: SourceRow[] } {
|
||||
const stale: SourceRow[] = [];
|
||||
const fresh: SourceRow[] = [];
|
||||
const cooldown: SourceRow[] = [];
|
||||
for (const s of sources) {
|
||||
if (!isSourceStale(s, now, floorMin)) { fresh.push(s); continue; }
|
||||
// #2194 fix #2: a stale source that recently failed is held in cooldown so
|
||||
// it can't re-dispatch every tick (the storm). Success clears it.
|
||||
if (isInFailureCooldown(recentFailures.get(s.id), readLastSuccessAt(s), now, cooldownOpts)) {
|
||||
cooldown.push(s);
|
||||
continue;
|
||||
}
|
||||
stale.push(s);
|
||||
(isSourceStale(s, now, floorMin) ? stale : fresh).push(s);
|
||||
}
|
||||
// Oldest-first ordering: NULL last_full_cycle_at sorts before any timestamp.
|
||||
stale.sort((a, b) => {
|
||||
@@ -353,7 +141,7 @@ export function selectSourcesForDispatch(
|
||||
});
|
||||
const dispatch = stale.slice(0, fanoutMax);
|
||||
const skippedCap = stale.slice(fanoutMax);
|
||||
return { dispatch, skippedFresh: fresh, skippedCap, skippedCooldown: cooldown };
|
||||
return { dispatch, skippedFresh: fresh, skippedCap };
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -405,27 +193,10 @@ export async function dispatchPerSource(
|
||||
} else {
|
||||
log(`[dispatch] job #${job.id} autopilot-cycle (legacy single-source)`);
|
||||
}
|
||||
return { dispatched: [], skipped_fresh: [], skipped_cap: [], skipped_cooldown: [], legacy_fallback: true };
|
||||
return { dispatched: [], skipped_fresh: [], skipped_cap: [], legacy_fallback: true };
|
||||
}
|
||||
|
||||
// #2194 fix #2: load recent per-source failures + cooldown knobs so a
|
||||
// chronically-failing source is backed off instead of re-dispatched every
|
||||
// tick. Fail-open: cooldown is an optimization, not a correctness gate — if
|
||||
// config/job-history reads fail (or the engine lacks them), dispatch proceeds
|
||||
// with no cooldown rather than blocking.
|
||||
let cooldownOpts: CooldownOpts = { baseMin: 0, capMin: FAILURE_COOLDOWN_CAP_MIN };
|
||||
let recentFailures = new Map<string, SourceFailure>();
|
||||
try {
|
||||
cooldownOpts = await resolveFailureCooldownOpts(engine);
|
||||
if (cooldownOpts.baseMin > 0) {
|
||||
recentFailures = await readRecentSourceFailures(engine, { sinceMin: cooldownOpts.capMin });
|
||||
}
|
||||
} catch {
|
||||
cooldownOpts = { baseMin: 0, capMin: FAILURE_COOLDOWN_CAP_MIN };
|
||||
}
|
||||
|
||||
const { dispatch, skippedFresh, skippedCap, skippedCooldown } =
|
||||
selectSourcesForDispatch(sources, opts.fanoutMax, Date.now(), FULL_CYCLE_FLOOR_MIN, recentFailures, cooldownOpts);
|
||||
const { dispatch, skippedFresh, skippedCap } = selectSourcesForDispatch(sources, opts.fanoutMax);
|
||||
|
||||
const dispatched: string[] = [];
|
||||
for (const src of dispatch) {
|
||||
@@ -437,11 +208,6 @@ export async function dispatchPerSource(
|
||||
repoPath: opts.repoPath,
|
||||
source_id: src.id,
|
||||
pull: !!remoteUrl,
|
||||
// #2194 fix #3 (cycle split): per-source cycles run ONLY source-scoped
|
||||
// (+ mixed) phases. The brain-wide global phases (embed, orphans,
|
||||
// purge, …) run once in autopilot-global-maintenance, not N times
|
||||
// concurrently here — the fix for the 4→10GB RSS blowout.
|
||||
phases: NON_GLOBAL_PHASES,
|
||||
},
|
||||
{
|
||||
queue: 'default',
|
||||
@@ -495,77 +261,10 @@ export async function dispatchPerSource(
|
||||
}));
|
||||
}
|
||||
|
||||
if (skippedCooldown.length > 0 && opts.jsonMode) {
|
||||
emit(JSON.stringify({
|
||||
event: 'fanout_cooldown_skipped',
|
||||
sources: skippedCooldown.map(s => s.id),
|
||||
}));
|
||||
}
|
||||
|
||||
return {
|
||||
dispatched,
|
||||
skipped_fresh: skippedFresh.map(s => s.id),
|
||||
skipped_cap: skippedCap.map(s => s.id),
|
||||
skipped_cooldown: skippedCooldown.map(s => s.id),
|
||||
legacy_fallback: false,
|
||||
};
|
||||
}
|
||||
|
||||
const GLOBAL_FLOOR_MIN = 60;
|
||||
|
||||
/** Is the brain-wide maintenance overdue? Null/unparseable → overdue. */
|
||||
export function isGlobalMaintenanceStale(lastGlobalAtIso: string | null, now = Date.now(), floorMin = GLOBAL_FLOOR_MIN): boolean {
|
||||
if (!lastGlobalAtIso) return true;
|
||||
const d = new Date(lastGlobalAtIso);
|
||||
if (!Number.isFinite(d.getTime())) return true;
|
||||
return (now - d.getTime()) / 60_000 >= floorMin;
|
||||
}
|
||||
|
||||
/**
|
||||
* #2194 fix #3 / #2227 bug #3 — dispatch the single brain-wide maintenance job
|
||||
* that runs the `global` cycle phases (embed, orphans, purge, …) ONCE per
|
||||
* window, instead of N per-source cycles each running them concurrently (the
|
||||
* RSS blowout). Single-flight is structural: one `idempotency_key` +
|
||||
* `maxWaiting:1`, so a slow run never stacks. Gated on `autopilot.last_global_at`
|
||||
* (stamped by the handler on success). Postgres-only fan-out concern; on PGLite
|
||||
* the file lock already serializes, but the job is still correct there.
|
||||
*/
|
||||
export async function dispatchGlobalMaintenance(
|
||||
engine: BrainEngine,
|
||||
queue: MinionQueue,
|
||||
opts: { repoPath: string; slot: string; timeoutMs: number; jsonMode: boolean; emit?: (l: string) => void; log?: (l: string) => void },
|
||||
): Promise<{ dispatched: boolean; reason: 'stale' | 'fresh' }> {
|
||||
const emit = opts.emit ?? ((line) => process.stderr.write(line + '\n'));
|
||||
const log = opts.log ?? ((line) => console.log(line));
|
||||
|
||||
let floorMin = GLOBAL_FLOOR_MIN;
|
||||
const floorCfg = await engine.getConfig('autopilot.global_floor_min');
|
||||
if (floorCfg) {
|
||||
const n = parseInt(floorCfg, 10);
|
||||
if (Number.isFinite(n) && n >= 1) floorMin = n;
|
||||
}
|
||||
const lastGlobalAt = await engine.getConfig(LAST_GLOBAL_AT_KEY);
|
||||
if (!isGlobalMaintenanceStale(lastGlobalAt, Date.now(), floorMin)) {
|
||||
return { dispatched: false, reason: 'fresh' };
|
||||
}
|
||||
|
||||
const job = await queue.add(
|
||||
'autopilot-global-maintenance',
|
||||
{ repoPath: opts.repoPath, phases: GLOBAL_PHASES },
|
||||
{
|
||||
queue: 'default',
|
||||
// Structural single-flight: one global job per slot; maxWaiting:1 coalesces
|
||||
// any surplus so a slow brain-wide pass never stacks duplicates.
|
||||
idempotency_key: `autopilot-global:${opts.slot}`,
|
||||
max_attempts: 2,
|
||||
timeout_ms: opts.timeoutMs,
|
||||
maxWaiting: 1,
|
||||
},
|
||||
);
|
||||
if (opts.jsonMode) {
|
||||
emit(JSON.stringify({ event: 'dispatched', job_id: job.id, mode: 'global_maintenance', slot: opts.slot }));
|
||||
} else {
|
||||
log(`[dispatch] job #${job.id} autopilot-global-maintenance (brain-wide phases)`);
|
||||
}
|
||||
return { dispatched: true, reason: 'stale' };
|
||||
}
|
||||
|
||||
+21
-110
@@ -17,8 +17,7 @@
|
||||
* gbrain autopilot --status [--json]
|
||||
*/
|
||||
|
||||
import { existsSync, readFileSync, writeFileSync, mkdirSync, appendFileSync, utimesSync, unlinkSync, chmodSync } from 'fs';
|
||||
import { setCliExitVerdict } from '../core/cli-force-exit.ts';
|
||||
import { existsSync, readFileSync, writeFileSync, mkdirSync, appendFileSync, utimesSync, unlinkSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
import { execSync } from 'child_process';
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
@@ -109,21 +108,7 @@ function logError(phase: string, e: unknown) {
|
||||
*/
|
||||
export function resolveGbrainCliPath(): string {
|
||||
try {
|
||||
// #2747: `env: process.env` is required under Bun. Bun's execSync
|
||||
// snapshots process.env at Bun's OWN startup, not at call time — a
|
||||
// runtime PATH mutation (dotenv/config loading, shell-profile sourcing
|
||||
// in a wrapper, etc.) happening between Bun boot and this call is
|
||||
// invisible to `which` without explicitly forwarding the current env.
|
||||
// This is why "which gbrain" succeeds when run standalone (fresh Bun
|
||||
// process, no prior mutation) but can fail from inside autopilot's own
|
||||
// process at this exact call site. Same fix already applied to
|
||||
// detectTini() in spawn-helpers.ts (see its comment) — this call site
|
||||
// was missed.
|
||||
const which = execSync('which gbrain', {
|
||||
encoding: 'utf-8',
|
||||
stdio: ['ignore', 'pipe', 'ignore'],
|
||||
env: process.env,
|
||||
}).trim();
|
||||
const which = execSync('which gbrain', { encoding: 'utf-8', stdio: ['ignore', 'pipe', 'ignore'] }).trim();
|
||||
if (which) return which;
|
||||
} catch { /* not on $PATH — fall through */ }
|
||||
|
||||
@@ -137,51 +122,13 @@ export function resolveGbrainCliPath(): string {
|
||||
return arg1;
|
||||
}
|
||||
|
||||
// #2747: include what we actually saw so an operator (or a future bug
|
||||
// report) doesn't have to guess whether PATH/execPath/argv[1] looked
|
||||
// sane at the moment of failure.
|
||||
throw new Error(
|
||||
'Could not resolve the gbrain CLI path. Install gbrain so it is on $PATH ' +
|
||||
'(e.g. /usr/local/bin/gbrain), or run autopilot from the compiled binary directly. ' +
|
||||
`Debug: PATH=${JSON.stringify(process.env.PATH ?? '')} execPath=${JSON.stringify(exec)} argv1=${JSON.stringify(arg1)}`,
|
||||
);
|
||||
throw new Error('Could not resolve the gbrain CLI path. Install gbrain so it is on $PATH (e.g. /usr/local/bin/gbrain), or run autopilot from the compiled binary directly.');
|
||||
}
|
||||
|
||||
export function shouldSpawnAutopilotWorker(args: string[]): boolean {
|
||||
return !args.includes('--no-worker');
|
||||
}
|
||||
|
||||
export function isPidAlive(pid: number): boolean {
|
||||
if (!Number.isFinite(pid) || pid <= 0) return false;
|
||||
try {
|
||||
process.kill(pid, 0);
|
||||
return true;
|
||||
} catch (error: unknown) {
|
||||
return (error as NodeJS.ErrnoException).code === 'EPERM';
|
||||
}
|
||||
}
|
||||
|
||||
export function decideLockAcquisition(
|
||||
lockPath: string,
|
||||
currentPid: number,
|
||||
): { action: 'acquire' } | { action: 'exit'; holderPid: number } | { action: 'takeover'; reason: string } {
|
||||
if (!existsSync(lockPath)) return { action: 'acquire' };
|
||||
|
||||
let raw = '';
|
||||
try {
|
||||
raw = readFileSync(lockPath, 'utf-8').trim();
|
||||
} catch {
|
||||
// An unreadable lock cannot prove another process is alive.
|
||||
}
|
||||
|
||||
const holderPid = Number.parseInt(raw, 10);
|
||||
const sameProcess = Number.isFinite(holderPid) && holderPid === currentPid;
|
||||
const alive = !sameProcess && isPidAlive(holderPid);
|
||||
|
||||
if (alive) return { action: 'exit', holderPid };
|
||||
return { action: 'takeover', reason: `dead pid ${raw || '<empty>'}` };
|
||||
}
|
||||
|
||||
// ── Self-upgrade silent channel (v0.42; opt-in, supervisor-relaunch) ─────────
|
||||
|
||||
/**
|
||||
@@ -403,13 +350,14 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
const lockPath = gbrainHomePath('autopilot.lock');
|
||||
try {
|
||||
mkdirSync(gbrainHomePath(), { recursive: true });
|
||||
const decision = decideLockAcquisition(lockPath, process.pid);
|
||||
if (decision.action === 'exit') {
|
||||
console.error(`Another autopilot instance is running (pid ${decision.holderPid}). Exiting.`);
|
||||
process.exit(0);
|
||||
}
|
||||
if (decision.action === 'takeover') {
|
||||
console.log(`Stale autopilot lock found (${decision.reason}). Taking over.`);
|
||||
if (existsSync(lockPath)) {
|
||||
const stat = require('fs').statSync(lockPath);
|
||||
const ageMinutes = (Date.now() - stat.mtimeMs) / 60000;
|
||||
if (ageMinutes < 10) {
|
||||
console.error('Another autopilot instance is running (lock file is fresh). Exiting.');
|
||||
process.exit(0);
|
||||
}
|
||||
console.log('Stale lock file found (>10 min). Taking over.');
|
||||
}
|
||||
writeFileSync(lockPath, String(process.pid));
|
||||
} catch { /* best-effort */ }
|
||||
@@ -581,13 +529,8 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
autopilotReconnectFails = 0; // reset on success
|
||||
} catch (probeErr) {
|
||||
try {
|
||||
// #2034: use reconnect() — it restores the config captured at connect()
|
||||
// and avoids the null-connection window. The previous
|
||||
// `disconnect()` + bare `connect()` lost the config (throwing
|
||||
// `database_url undefined` on every retry → FATAL restart-loop on any
|
||||
// transient DB blip) AND tore down the pool postgres.js can otherwise
|
||||
// self-heal.
|
||||
await engine.reconnect({ error: probeErr });
|
||||
await engine.disconnect();
|
||||
await (engine as any).connect?.();
|
||||
autopilotReconnectFails = 0;
|
||||
} catch (e) {
|
||||
logError('reconnect', e);
|
||||
@@ -599,7 +542,7 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
`Exiting so launchd ThrottleInterval can apply backoff.`,
|
||||
);
|
||||
stopping = true;
|
||||
setCliExitVerdict(1);
|
||||
process.exitCode = 1;
|
||||
break;
|
||||
}
|
||||
if (autopilotReconnectFails >= AUTOPILOT_MAX_RECONNECT_FAILS) {
|
||||
@@ -608,7 +551,7 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
`Last error: ${(e as Error).message ?? 'unknown'}. Exiting.`,
|
||||
);
|
||||
stopping = true;
|
||||
setCliExitVerdict(1);
|
||||
process.exitCode = 1;
|
||||
break;
|
||||
}
|
||||
}
|
||||
@@ -922,12 +865,8 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
// codex P1-3). Fresh-install brains with no sources rows fall
|
||||
// back to the legacy single autopilot-cycle so existing
|
||||
// behavior is preserved.
|
||||
const { dispatchPerSource, dispatchGlobalMaintenance, resolveEffectiveFanoutMax } = await import('./autopilot-fanout.ts');
|
||||
// #2194 fix #1: clamp fan-out to the worker's effective concurrency
|
||||
// (reserve ≥1 slot), gated on a LIVE supervisor so a stale audit row
|
||||
// can't shrink throughput (codex #9/D5). autopilot-cycle jobs run on
|
||||
// the 'default' queue, so that's the concurrency we compare against.
|
||||
const fanoutMax = await resolveEffectiveFanoutMax(engine, 'default');
|
||||
const { dispatchPerSource, resolveFanoutMax } = await import('./autopilot-fanout.ts');
|
||||
const fanoutMax = await resolveFanoutMax(engine);
|
||||
const result = await dispatchPerSource(engine, queue, {
|
||||
repoPath,
|
||||
slot,
|
||||
@@ -935,18 +874,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
fanoutMax,
|
||||
jsonMode,
|
||||
});
|
||||
// #2194 fix #3 / #2227 bug #3: dispatch the single brain-wide
|
||||
// maintenance job (embed/orphans/purge/…) once per window — the per-
|
||||
// source cycles above no longer run global phases, so this is where
|
||||
// the brain-wide work happens (single-flight, no RSS blowout). Only on
|
||||
// the per-source path (legacy single-source still runs everything).
|
||||
if (!result.legacy_fallback) {
|
||||
try {
|
||||
await dispatchGlobalMaintenance(engine, queue, { repoPath, slot, timeoutMs, jsonMode });
|
||||
} catch (e) {
|
||||
if (jsonMode) process.stderr.write(JSON.stringify({ event: 'global_maintenance_dispatch_failed', error: e instanceof Error ? e.message : String(e) }) + '\n');
|
||||
}
|
||||
}
|
||||
if (result.dispatched.length > 0 || result.legacy_fallback) {
|
||||
lastFullCycleAt = Date.now();
|
||||
}
|
||||
@@ -956,7 +883,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
dispatched: result.dispatched,
|
||||
skipped_fresh: result.skipped_fresh,
|
||||
skipped_cap: result.skipped_cap,
|
||||
skipped_cooldown: result.skipped_cooldown,
|
||||
legacy_fallback: result.legacy_fallback,
|
||||
fanout_max: fanoutMax,
|
||||
score,
|
||||
@@ -964,8 +890,7 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
} else if (!result.legacy_fallback) {
|
||||
console.log(
|
||||
`[dispatch] fanout: ${result.dispatched.length} dispatched, ` +
|
||||
`${result.skipped_fresh.length} fresh, ${result.skipped_cap.length} capped, ` +
|
||||
`${result.skipped_cooldown.length} cooldown ` +
|
||||
`${result.skipped_fresh.length} fresh, ${result.skipped_cap.length} capped ` +
|
||||
`(score=${score}, max=${fanoutMax})`,
|
||||
);
|
||||
}
|
||||
@@ -1263,14 +1188,7 @@ function installLaunchd(wrapperPath: string, home: string, repoPath: string) {
|
||||
try {
|
||||
const agentsDir = join(home, 'Library', 'LaunchAgents');
|
||||
mkdirSync(agentsDir, { recursive: true });
|
||||
writeFileSync(plistPath(), plist, { mode: 0o644 });
|
||||
// launchd rejects group/world-writable agent plists: bootstrap/load fails
|
||||
// with the opaque "Bootstrap failed: 5: Input/output error" and the login
|
||||
// scan skips the file silently. writeFileSync's mode only applies on
|
||||
// create — a reinstall over an existing plist keeps the old bits (a 0666
|
||||
// plist written under an umask-0 parent stays 0666 forever) — so
|
||||
// normalize unconditionally.
|
||||
chmodSync(plistPath(), 0o644);
|
||||
writeFileSync(plistPath(), plist);
|
||||
execSync(`launchctl load "${plistPath()}"`, { stdio: 'pipe' });
|
||||
console.log('Installed launchd service: com.gbrain.autopilot');
|
||||
console.log(` Repo: ${repoPath}`);
|
||||
@@ -1360,11 +1278,7 @@ export function migrateSystemdUnitToRestartAlways(): { rewritten: boolean; reaso
|
||||
return { rewritten: false, reason: 'hand-edited' };
|
||||
}
|
||||
try {
|
||||
writeFileSync(unitPath, generateSystemdUnit(execMatch![1]), { mode: 0o644 });
|
||||
// This path always rewrites an EXISTING unit, so writeFileSync's mode
|
||||
// never applies — chmod is the only thing that normalizes a unit born
|
||||
// 0666 under a umask-0 parent (systemd warns on world-writable units).
|
||||
chmodSync(unitPath, 0o644);
|
||||
writeFileSync(unitPath, generateSystemdUnit(execMatch![1]));
|
||||
try {
|
||||
execSync('systemctl --user daemon-reload', { stdio: 'pipe', timeout: 10_000 });
|
||||
} catch {
|
||||
@@ -1381,10 +1295,7 @@ function installSystemd(wrapperPath: string, repoPath: string) {
|
||||
try {
|
||||
const unitPath = systemdUnitPath();
|
||||
mkdirSync(join(process.env.HOME || '', '.config', 'systemd', 'user'), { recursive: true });
|
||||
writeFileSync(unitPath, unit, { mode: 0o644 });
|
||||
// Same umask-0 hardening as the launchd path (systemd warns on
|
||||
// world-writable units); mode only applies on create, so normalize.
|
||||
chmodSync(unitPath, 0o644);
|
||||
writeFileSync(unitPath, unit);
|
||||
execSync('systemctl --user daemon-reload', { stdio: 'pipe', timeout: 10_000 });
|
||||
execSync('systemctl --user enable --now gbrain-autopilot.service', { stdio: 'pipe', timeout: 15_000 });
|
||||
console.log('Installed systemd user service: gbrain-autopilot.service');
|
||||
|
||||
@@ -257,9 +257,7 @@ function buildChapterPrompt(
|
||||
|
||||
return `You are analyzing one chapter of "${bookTitle}"${authorLine} for the user.
|
||||
|
||||
Your output is a two-column HTML table where the LEFT column preserves the chapter's actual content (stories, frameworks, statistics, named examples) and the RIGHT column maps each idea to the user's actual life using their words, situations, and patterns from the brain.
|
||||
|
||||
CRITICAL: Use an HTML <table> with valign="top" on EVERY cell — NOT a markdown pipe table. Markdown pipe tables have no way to set vertical alignment, so every renderer except GitHub middle-aligns the rows, which is unreadable when the two columns have different lengths. The HTML <table valign="top"> form top-aligns everywhere (GitHub, PDF, Obsidian).
|
||||
Your output is a markdown two-column table where the LEFT column preserves the chapter's actual content (stories, frameworks, statistics, named examples) and the RIGHT column maps each idea to the user's actual life using their words, situations, and patterns from the brain.
|
||||
|
||||
This is chapter ${chapter.index} of ${totalChapters}.
|
||||
|
||||
@@ -278,12 +276,11 @@ Return ONLY a single markdown section in this exact shape:
|
||||
### Key Ideas
|
||||
[2-4 sentence thesis of the chapter — what the author is actually arguing.]
|
||||
|
||||
<table>
|
||||
<tr><th align="left">What the Author Says</th><th align="left">How This Applies to You</th></tr>
|
||||
<tr><td valign="top">[Detailed paragraph: a section/argument from the chapter, preserving stories, stats, frameworks, named examples. Use \`<br><br>\` for paragraph breaks within the cell.]</td><td valign="top">[Specific personal connection: name dates, people, exact quotes from the user, real situations. Same \`<br><br>\` for breaks.]</td></tr>
|
||||
<tr><td valign="top">[Next section]</td><td valign="top">[Next mirror]</td></tr>
|
||||
[4-10 rows depending on chapter density]
|
||||
</table>
|
||||
| What the Author Says | How This Applies to You |
|
||||
|---|---|
|
||||
| [Detailed paragraph: a section/argument from the chapter, preserving stories, stats, frameworks, named examples. Use \`<br><br>\` for paragraph breaks within the cell.] | [Specific personal connection: name dates, people, exact quotes from the user, real situations. Same \`<br><br>\` for breaks.] |
|
||||
| [Next section] | [Next mirror] |
|
||||
| [4-10 rows depending on chapter density] | |
|
||||
\`\`\`
|
||||
|
||||
## RULES
|
||||
@@ -293,7 +290,6 @@ Return ONLY a single markdown section in this exact shape:
|
||||
- 4-10 rows per chapter. If a section honestly doesn't apply, write \`*This section is less directly relevant because [specific reason].*\` Don't force connections.
|
||||
- Never generic ("This might apply if you've ever felt..."). Never sycophantic. Never preach.
|
||||
- Use \`<br><br>\` for paragraph breaks inside table cells, not literal newlines.
|
||||
- EVERY <td> MUST carry valign="top". Never emit a markdown pipe table (| ... | ... |) — always the HTML <table> form above.
|
||||
|
||||
You have ${DEFAULT_MAX_TURNS} turns and read-only tools (get_page, search). You CANNOT call put_page — your output is the markdown text in your final message. The CLI assembles all chapters and writes the brain page.
|
||||
|
||||
@@ -318,7 +314,7 @@ title: "${opts.title} — Personalized"
|
||||
type: book-analysis${authorLine}
|
||||
date: ${today}
|
||||
context: "${contextSummary.replace(/"/g, '\\"')}"
|
||||
tags: [book, personalized, two-column-htmltable-valign-top]
|
||||
tags: [book, personalized, two-column]
|
||||
---`;
|
||||
|
||||
const intro = `# ${opts.title} — Personalized
|
||||
|
||||
@@ -13,7 +13,6 @@
|
||||
*/
|
||||
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { setCliExitVerdict } from '../core/cli-force-exit.ts';
|
||||
import {
|
||||
runBrainstorm,
|
||||
formatBrainstormMarkdown,
|
||||
@@ -323,7 +322,7 @@ async function runBrainstormCli(
|
||||
const msg = formatSaveOutcome(outcome, { profileLabel: profile.label, slug });
|
||||
if (msg.stdout) console.log(msg.stdout);
|
||||
for (const line of msg.stderr) console.error(line);
|
||||
if (msg.exitCode) setCliExitVerdict(msg.exitCode);
|
||||
if (msg.exitCode) process.exitCode = msg.exitCode;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -19,15 +19,13 @@
|
||||
*/
|
||||
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { resolveCalibrationHolder, runPhaseCalibrationProfile } from '../core/cycle/calibration-profile.ts';
|
||||
import { runPhaseCalibrationProfile } from '../core/cycle/calibration-profile.ts';
|
||||
import { sourceScopeOpts, type OperationContext } from '../core/operations.ts';
|
||||
import type { GBrainConfig } from '../core/config.ts';
|
||||
import { GBrainError } from '../core/types.ts';
|
||||
|
||||
export interface CalibrationProfileRow {
|
||||
/** BIGSERIAL → string (postgres.js int8 wire shape; never Number() — int8
|
||||
* exceeds 2^53). No consumer does arithmetic on it; it's audit/serialize only. */
|
||||
id: string;
|
||||
id: number;
|
||||
source_id: string;
|
||||
holder: string;
|
||||
wave_version: string;
|
||||
@@ -69,12 +67,7 @@ export async function getLatestProfile(
|
||||
sql += ` ORDER BY generated_at DESC LIMIT 1`;
|
||||
|
||||
const rows = await engine.executeRaw<CalibrationProfileRow>(sql, params);
|
||||
if (!rows[0]) return null;
|
||||
// `id` is BIGSERIAL → the pg driver returns it as a JS bigint, which crashes
|
||||
// JSON.stringify on the --json / MCP output paths once a row exists. Coerce to
|
||||
// string — matches the postgres.js int8 wire shape (and cli.ts's ENG-2
|
||||
// "bigint → string" contract); String() has no 2^53 ceiling, unlike Number().
|
||||
return { ...rows[0], id: String(rows[0].id) };
|
||||
return rows[0] ?? null;
|
||||
}
|
||||
|
||||
/** Human format the profile for terminal output. */
|
||||
@@ -132,7 +125,6 @@ export interface RunCalibrationArgs {
|
||||
regenerate?: boolean;
|
||||
undoWave?: string;
|
||||
abReport?: boolean;
|
||||
source?: string;
|
||||
}
|
||||
|
||||
function parseArgs(args: string[]): { sub?: string; opts: RunCalibrationArgs } {
|
||||
@@ -152,7 +144,6 @@ function parseArgs(args: string[]): { sub?: string; opts: RunCalibrationArgs } {
|
||||
else if (a === '--json') opts.json = true;
|
||||
else if (a === '--regenerate') opts.regenerate = true;
|
||||
else if (a === '--undo-wave') opts.undoWave = args[++i];
|
||||
else if (a === '--source') opts.source = args[++i];
|
||||
}
|
||||
return { sub, opts };
|
||||
}
|
||||
@@ -167,12 +158,8 @@ export async function runCalibration(
|
||||
config: GBrainConfig,
|
||||
): Promise<void> {
|
||||
const { opts } = parseArgs(args);
|
||||
const holder = await resolveCalibrationHolder(engine, opts.holder);
|
||||
// Resolve --source / GBRAIN_SOURCE / .gbrain-source so the (now reachable, #2035)
|
||||
// calibration command targets the right source in a multi-source brain instead
|
||||
// of always reading `default`. No signal → 'default' (prior behavior).
|
||||
const { resolveSourceId } = await import('../core/source-resolver.ts');
|
||||
const sourceId = await resolveSourceId(engine, opts.source ?? null);
|
||||
const holder = opts.holder ?? 'garry';
|
||||
const sourceId = 'default';
|
||||
|
||||
if (opts.undoWave) {
|
||||
// T17 / D18 CDX-3 — reverse the wave's mutations on canonical state.
|
||||
@@ -253,14 +240,14 @@ export async function getCalibrationProfileOp(
|
||||
ctx: OperationContext,
|
||||
params: { holder?: string },
|
||||
): Promise<CalibrationProfileRow | null> {
|
||||
if (params.holder !== undefined && (typeof params.holder !== 'string' || params.holder.length === 0)) {
|
||||
const holder = params.holder ?? 'garry';
|
||||
if (typeof holder !== 'string' || holder.length === 0) {
|
||||
throw new GBrainError(
|
||||
'INVALID_HOLDER',
|
||||
'get_calibration_profile.holder must be a non-empty string',
|
||||
'pass holder="<slug>" or omit to default to the calibration.user_holder config (then "garry")',
|
||||
'pass holder="<slug>" or omit to default to "garry"',
|
||||
);
|
||||
}
|
||||
const holder = await resolveCalibrationHolder(ctx.engine, params.holder);
|
||||
const scope = sourceScopeOpts(ctx);
|
||||
return getLatestProfile(ctx.engine, { holder, ...scope });
|
||||
}
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { handleToolCall } from '../mcp/server.ts';
|
||||
import { resolveSourceId } from '../core/source-resolver.ts';
|
||||
import { bigintToStringReplacer } from '../cli.ts';
|
||||
|
||||
/**
|
||||
* `gbrain call <tool> <json>` — trusted local op-dispatch surface.
|
||||
@@ -50,8 +49,5 @@ export async function runCall(engine: BrainEngine, args: string[]) {
|
||||
// an explicit/env/dotfile id refers to a non-registered source.
|
||||
const sourceId = await resolveSourceId(engine, explicitSource);
|
||||
const result = await handleToolCall(engine, tool, params, { sourceId });
|
||||
// `gbrain call` bypasses cli.ts's op-output normalizer entirely, so this
|
||||
// exit needs its own bigint-safe replacer — any op returning an int8 column
|
||||
// (BIGSERIAL id) would otherwise crash plain JSON.stringify (#2450).
|
||||
console.log(JSON.stringify(result, bigintToStringReplacer, 2));
|
||||
console.log(JSON.stringify(result, null, 2));
|
||||
}
|
||||
|
||||
+3
-47
@@ -49,12 +49,6 @@ interface RunOpts {
|
||||
source?: string;
|
||||
quiet?: boolean;
|
||||
json?: boolean;
|
||||
// v0.42.x — Life Chronicle (#2390): manual `--type event` frontmatter sugar.
|
||||
who?: string; // comma-separated entity slugs
|
||||
what?: string;
|
||||
where?: string;
|
||||
kind?: string;
|
||||
depth?: string; // the depth page this event backlinks
|
||||
}
|
||||
|
||||
function parseArgs(args: string[]): RunOpts | { help: true; positional: string | undefined } {
|
||||
@@ -86,12 +80,6 @@ function parseArgs(args: string[]): RunOpts | { help: true; positional: string |
|
||||
if (v) opts.source = v;
|
||||
continue;
|
||||
}
|
||||
// v0.42.x — Life Chronicle event sugar.
|
||||
if (a === '--who') { const v = args[++i]; if (v) opts.who = v; continue; }
|
||||
if (a === '--what') { const v = args[++i]; if (v) opts.what = v; continue; }
|
||||
if (a === '--where') { const v = args[++i]; if (v) opts.where = v; continue; }
|
||||
if (a === '--kind') { const v = args[++i]; if (v) opts.kind = v; continue; }
|
||||
if (a === '--depth') { const v = args[++i]; if (v) opts.depth = v; continue; }
|
||||
if (a.startsWith('--')) continue; // unknown flag, ignore
|
||||
positional.push(a);
|
||||
}
|
||||
@@ -144,21 +132,12 @@ Examples:
|
||||
JOB=$(gbrain capture "..." --quiet)
|
||||
`;
|
||||
|
||||
// v0.42.x — Life Chronicle (#2390): route the default slug prefix by type so
|
||||
// `gbrain capture --type diary` lands under life/diary/ and `--type event`
|
||||
// under life/events/ (matching the chronicle path-prefix inference). Everything
|
||||
// else keeps the inbox/ default.
|
||||
function slugPrefixForType(type?: string): string {
|
||||
if (type === 'diary') return 'life/diary';
|
||||
if (type === 'event') return 'life/events';
|
||||
return 'inbox';
|
||||
}
|
||||
function defaultSlug(content: string, now: Date = new Date(), type?: string): string {
|
||||
function defaultSlug(content: string, now: Date = new Date()): string {
|
||||
const y = now.getUTCFullYear();
|
||||
const m = String(now.getUTCMonth() + 1).padStart(2, '0');
|
||||
const d = String(now.getUTCDate()).padStart(2, '0');
|
||||
const hashPrefix = computeContentHash(content).slice(0, 8);
|
||||
return `${slugPrefixForType(type)}/${y}-${m}-${d}-${hashPrefix}`;
|
||||
return `inbox/${y}-${m}-${d}-${hashPrefix}`;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -266,22 +245,6 @@ function deriveTitle(rawBody: string): string {
|
||||
* stamps a fresh frontmatter block, and if the body doesn't already look
|
||||
* like markdown (no `#` heading), wraps it under a `# {title}` heading.
|
||||
*/
|
||||
// v0.42.x — Life Chronicle (#2390): assemble the `event:` frontmatter block
|
||||
// from the --who/--what/--where/--kind/--depth flags (only for --type event).
|
||||
// Returns undefined when no event flags are set so non-event captures are
|
||||
// untouched.
|
||||
function buildEventBlock(opts: RunOpts): Record<string, unknown> | undefined {
|
||||
if (opts.type !== 'event') return undefined;
|
||||
const who = opts.who ? opts.who.split(',').map((s) => s.trim()).filter(Boolean) : [];
|
||||
const block: Record<string, unknown> = {};
|
||||
if (opts.what) block.what = opts.what;
|
||||
if (who.length) block.who = who;
|
||||
if (opts.where) block.where = opts.where;
|
||||
if (opts.kind) block.kind = opts.kind;
|
||||
if (opts.depth) block.depth = opts.depth;
|
||||
return Object.keys(block).length ? block : undefined;
|
||||
}
|
||||
|
||||
export function mergeCaptureFrontmatter(rawBody: string, opts: RunOpts): string {
|
||||
const nowIso = new Date().toISOString();
|
||||
// Detect frontmatter: leading `---\n` or `---\r\n`, tolerating leading BOM/whitespace.
|
||||
@@ -300,8 +263,6 @@ export function mergeCaptureFrontmatter(rawBody: string, opts: RunOpts): string
|
||||
captured_via: opts.source ?? 'capture-cli',
|
||||
captured_at: nowIso,
|
||||
};
|
||||
const ev = buildEventBlock(opts);
|
||||
if (ev) fm.event = ev;
|
||||
const looksMarkdown = /^#{1,6}\s/.test(rawBody.trimStart());
|
||||
const body = looksMarkdown ? rawBody : `# ${title}\n\n${rawBody}`;
|
||||
return matter.stringify(body, fm);
|
||||
@@ -329,11 +290,6 @@ export function mergeCaptureFrontmatter(rawBody: string, opts: RunOpts): string
|
||||
captured_via: userFm.captured_via ?? opts.source ?? 'capture-cli',
|
||||
captured_at: userFm.captured_at ?? nowIso,
|
||||
};
|
||||
// v0.42.x — merge the event block (user-declared keys win per-key).
|
||||
const ev = buildEventBlock(opts);
|
||||
if (ev || userFm.event) {
|
||||
merged.event = { ...(ev ?? {}), ...((userFm.event as Record<string, unknown>) ?? {}) };
|
||||
}
|
||||
return matter.stringify(parsed.content, merged);
|
||||
}
|
||||
|
||||
@@ -483,7 +439,7 @@ export async function runCapture(engine: BrainEngine | null, args: string[]): Pr
|
||||
// The daemon's 24h LRU dedup keys on this hash; identical captures must
|
||||
// produce identical hashes. The DB content_hash (importFromContent at
|
||||
// src/core/import-file.ts) gets the same treatment in Phase 3d.
|
||||
const slug = parsed.slug ?? defaultSlug(normalizedBody, new Date(), parsed.type);
|
||||
const slug = parsed.slug ?? defaultSlug(normalizedBody);
|
||||
const fullContent = buildContent(rawBody, parsed);
|
||||
const capturedAt = new Date().toISOString();
|
||||
const contentHash = computeContentHash(normalizedBody);
|
||||
|
||||
+3
-33
@@ -98,25 +98,9 @@ export async function runConfig(engine: BrainEngine, args: string[]) {
|
||||
const value = args[2];
|
||||
|
||||
if (action === 'get' && key) {
|
||||
// #2120: `get` used to read only the DB plane, so a runtime-effective key
|
||||
// in ~/.gbrain/config.json (or env) reported not-found. Resolve the way
|
||||
// the runtime does — env/file plane wins over DB (loadConfig() already
|
||||
// overlays env onto the file) — and report which plane answered on
|
||||
// stderr, keeping stdout a bare value for scripts.
|
||||
const filePlane = loadConfig() as Record<string, unknown> | null;
|
||||
const fileVal = filePlane?.[key];
|
||||
const dbVal = await engine.getConfig(key);
|
||||
const val = fileVal !== undefined && fileVal !== null ? fileVal : dbVal;
|
||||
if (val !== null && val !== undefined) {
|
||||
console.log(typeof val === 'string' ? val : JSON.stringify(val));
|
||||
if (fileVal !== undefined && fileVal !== null) {
|
||||
const shadow = dbVal !== null && dbVal !== undefined
|
||||
? ' — a DB-plane value also exists and is shadowed at runtime'
|
||||
: '';
|
||||
console.error(`[config] source: file/env plane (~/.gbrain/config.json or env)${shadow}`);
|
||||
} else {
|
||||
console.error(`[config] source: db plane`);
|
||||
}
|
||||
const val = await engine.getConfig(key);
|
||||
if (val !== null) {
|
||||
console.log(val);
|
||||
} else {
|
||||
console.error(`Config key not found: ${key}`);
|
||||
process.exit(1);
|
||||
@@ -197,20 +181,6 @@ export async function runConfig(engine: BrainEngine, args: string[]) {
|
||||
const coverageOverride =
|
||||
args.includes('--coverage-override') || args.includes('--yes');
|
||||
|
||||
// v0.42.42.0 (#2139): validate spend.posture at set time so a typo
|
||||
// ('tokenMax', 'max') doesn't silently fall back to gated.
|
||||
if (key === 'spend.posture') {
|
||||
const { isValidSpendPosture } = await import('../core/spend-posture.ts');
|
||||
if (!isValidSpendPosture(value)) {
|
||||
console.error(
|
||||
`[config] spend.posture must be 'gated' or 'tokenmax' (got '${value}').\n` +
|
||||
`[config] gbrain config set spend.posture tokenmax # cost gates become informational\n` +
|
||||
`[config] gbrain config set spend.posture gated # default — gates enforce`,
|
||||
);
|
||||
process.exit(1);
|
||||
}
|
||||
}
|
||||
|
||||
if (key === 'embedding_columns') {
|
||||
try {
|
||||
const parsed = JSON.parse(value);
|
||||
|
||||
@@ -73,9 +73,7 @@ export const LEARN_INSTRUCTION =
|
||||
'Once connected, call the `get_brain_identity` tool (whose brain this is), then ' +
|
||||
'`list_skills` (everything it can do; if it errors, the host has not enabled skill ' +
|
||||
'publishing — these core tools still work: search, query, get_page, put_page, ' +
|
||||
'think, find_experts). Then call `list_brain_skillpack`: if this brain ships a ' +
|
||||
'skillpack, ask the user whether to install it (gbrain skillpack scaffold <spec>). ' +
|
||||
'Always search the brain before answering or writing.';
|
||||
'think, find_experts). Always search the brain before answering or writing.';
|
||||
|
||||
const SECRET_NOTE =
|
||||
'Note: that bearer token is a long-lived, full-access secret — keep it private and ' +
|
||||
|
||||
@@ -16,7 +16,6 @@
|
||||
|
||||
import { readFileSync, existsSync } from 'node:fs';
|
||||
import { BUILTIN_PATTERNS } from '../core/conversation-parser/builtins.ts';
|
||||
import { readConversationBodyForParsing } from '../core/conversation-parser/body.ts';
|
||||
import { parseConversation } from '../core/conversation-parser/parse.ts';
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
|
||||
@@ -171,7 +170,8 @@ async function runScan(
|
||||
process.exit(2);
|
||||
}
|
||||
|
||||
const body = await readConversationBodyForParsing(engine, page);
|
||||
// Concatenate compiled_truth + timeline (matches the real parser's body shape).
|
||||
const body = `${page.compiled_truth ?? ''}\n${page.timeline ?? ''}`.trim();
|
||||
|
||||
const result = parseConversation(body, { page, diagnostic: true });
|
||||
|
||||
|
||||
+89
-487
@@ -1,5 +1,4 @@
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { setCliExitVerdict } from '../core/cli-force-exit.ts';
|
||||
import * as db from '../core/db.ts';
|
||||
import { LATEST_VERSION, getIdleBlockers } from '../core/migrate.ts';
|
||||
import { checkResolvable } from '../core/check-resolvable.ts';
|
||||
@@ -25,10 +24,7 @@ import { categorizeCheck, type CheckCategory } from '../core/doctor-categories.t
|
||||
import { rankIssues, type RankedIssue } from '../core/doctor-cause-rank.ts';
|
||||
import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
|
||||
import type { DbUrlSource } from '../core/config.ts';
|
||||
import { gbrainPath, loadConfig } from '../core/config.ts';
|
||||
import { reflexEnabled } from '../core/context/reflex.ts';
|
||||
import { resolveSocketPath } from '../core/context/resolve-ipc.ts';
|
||||
import { homedir } from 'os';
|
||||
import { gbrainPath } from '../core/config.ts';
|
||||
import { dirname, isAbsolute, join, resolve as resolvePath } from 'path';
|
||||
import { fileURLToPath } from 'url';
|
||||
import { existsSync, readFileSync, readdirSync, statSync } from 'fs';
|
||||
@@ -326,70 +322,6 @@ export async function whoknowsHealthCheck(_engine: BrainEngine): Promise<Check>
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Doctor check: pgvector availability.
|
||||
*
|
||||
* Use the active engine instead of the module-level Postgres singleton.
|
||||
* PGLite exposes pg_extension through its engine connection, but does not
|
||||
* connect db.ts's Postgres singleton; using db.getConnection() here turns a
|
||||
* healthy PGLite brain into a false warning.
|
||||
*/
|
||||
export async function pgvectorCheck(engine: BrainEngine): Promise<Check> {
|
||||
try {
|
||||
const ext = await engine.executeRaw<{ extname: string }>(
|
||||
`SELECT extname FROM pg_extension WHERE extname = 'vector'`,
|
||||
);
|
||||
if (ext.length > 0) {
|
||||
return { name: 'pgvector', status: 'ok', message: 'Extension installed' };
|
||||
}
|
||||
return { name: 'pgvector', status: 'fail', message: 'Extension not found. Run: CREATE EXTENSION vector;' };
|
||||
} catch {
|
||||
return { name: 'pgvector', status: 'warn', message: 'Could not check pgvector extension' };
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Doctor check: JSONB columns are not double-encoded as strings.
|
||||
*
|
||||
* This check is valid on both Postgres and PGLite. Route through
|
||||
* engine.executeRaw() so embedded PGLite brains are checked through their
|
||||
* actual connection instead of the unrelated Postgres singleton.
|
||||
*/
|
||||
export async function jsonbIntegrityCheck(
|
||||
engine: BrainEngine,
|
||||
progress?: Pick<ProgressReporter, 'heartbeat'>,
|
||||
): Promise<Check> {
|
||||
try {
|
||||
const targets: Array<{ table: string; col: string; expected: 'object' | 'array' }> = [
|
||||
{ table: 'pages', col: 'frontmatter', expected: 'object' },
|
||||
{ table: 'raw_data', col: 'data', expected: 'object' },
|
||||
{ table: 'ingest_log', col: 'pages_updated', expected: 'array' },
|
||||
{ table: 'files', col: 'metadata', expected: 'object' },
|
||||
{ table: 'page_versions', col: 'frontmatter', expected: 'object' },
|
||||
];
|
||||
let totalBad = 0;
|
||||
const breakdown: string[] = [];
|
||||
for (const { table, col } of targets) {
|
||||
progress?.heartbeat(`jsonb_integrity.${table}.${col}`);
|
||||
const rows = await engine.executeRaw<{ n: number }>(
|
||||
`SELECT count(*)::int AS n FROM ${table} WHERE jsonb_typeof(${col}) = 'string'`,
|
||||
);
|
||||
const n = Number(rows[0]?.n ?? 0);
|
||||
if (n > 0) { totalBad += n; breakdown.push(`${table}.${col}=${n}`); }
|
||||
}
|
||||
if (totalBad === 0) {
|
||||
return { name: 'jsonb_integrity', status: 'ok', message: 'All JSONB columns store objects/arrays' };
|
||||
}
|
||||
return {
|
||||
name: 'jsonb_integrity',
|
||||
status: 'warn',
|
||||
message: `${totalBad} row(s) double-encoded (${breakdown.join(', ')}). Fix: gbrain repair-jsonb`,
|
||||
};
|
||||
} catch {
|
||||
return { name: 'jsonb_integrity', status: 'warn', message: 'Could not check JSONB integrity' };
|
||||
}
|
||||
}
|
||||
|
||||
export async function takesWeightGridCheck(engine: BrainEngine): Promise<Check> {
|
||||
try {
|
||||
const rows = await engine.executeRaw<{ off_grid: string | number; total: string | number }>(
|
||||
@@ -575,60 +507,6 @@ export async function doctorReportRemote(engine: BrainEngine): Promise<DoctorRep
|
||||
checks.push({ name: 'schema_version', status: 'warn', message: 'Could not check schema version' });
|
||||
}
|
||||
|
||||
// 2b. #2038: idx_timeline_dedup shape. A renumbered-during-merge migration
|
||||
// (v102) can be recorded-as-applied without its DDL running, leaving the
|
||||
// 3-column index in place — every timeline write then fails the 4-column
|
||||
// ON CONFLICT. The version counter can't see this, so check the index SHAPE.
|
||||
try {
|
||||
const { checkTimelineDedupIndex } = await import('../core/timeline-dedup-repair.ts');
|
||||
const idx = await checkTimelineDedupIndex(engine);
|
||||
if (!idx.tablePresent || !idx.needsRepair) {
|
||||
checks.push({
|
||||
name: 'timeline_dedup_index',
|
||||
status: 'ok',
|
||||
message: idx.tablePresent ? 'idx_timeline_dedup has the 4-column shape' : 'no timeline_entries table yet',
|
||||
});
|
||||
} else {
|
||||
checks.push({
|
||||
name: 'timeline_dedup_index',
|
||||
status: 'fail',
|
||||
message:
|
||||
`idx_timeline_dedup is ${idx.indexPresent ? `(${idx.columns.join(', ')})` : 'absent'}, ` +
|
||||
`expected (page_id, date, summary, source) — timeline writes are failing (#2038). ` +
|
||||
`Run \`gbrain apply-migrations --force-schema\` to heal it.`,
|
||||
});
|
||||
}
|
||||
} catch {
|
||||
checks.push({ name: 'timeline_dedup_index', status: 'warn', message: 'Could not check idx_timeline_dedup shape' });
|
||||
}
|
||||
|
||||
// v0.42.x — Life Chronicle (#2390): orphaned event projections. Reads already
|
||||
// hide projections whose event page is soft-deleted (read-time correctness);
|
||||
// this always-run probe surfaces the cleanup backlog. Keyed off the real
|
||||
// schema (event_page_id), NOT a migration verify-hook, per
|
||||
// migration-verify-hook-never-runs-on-stamped-brains.
|
||||
try {
|
||||
const orphans = await engine.executeRaw<{ n: number }>(
|
||||
`SELECT count(*)::int AS n FROM timeline_entries te
|
||||
JOIN pages ep ON ep.id = te.event_page_id
|
||||
WHERE te.event_page_id IS NOT NULL AND ep.deleted_at IS NOT NULL`,
|
||||
);
|
||||
const n = Number(orphans[0]?.n ?? 0);
|
||||
checks.push(
|
||||
n === 0
|
||||
? { name: 'chronicle_projection_health', status: 'ok', message: 'No orphaned event projections' }
|
||||
: {
|
||||
name: 'chronicle_projection_health',
|
||||
status: 'warn',
|
||||
message:
|
||||
`${n} timeline projection(s) point to soft-deleted event pages ` +
|
||||
'(hidden at read time; clean up with `gbrain integrity auto`).',
|
||||
},
|
||||
);
|
||||
} catch {
|
||||
checks.push({ name: 'chronicle_projection_health', status: 'ok', message: 'no event projections yet' });
|
||||
}
|
||||
|
||||
// 3. Brain score
|
||||
try {
|
||||
const health = await engine.getHealth();
|
||||
@@ -786,9 +664,6 @@ export async function doctorReportRemote(engine: BrainEngine): Promise<DoctorRep
|
||||
// issue #1801 — wedged_queue (cross-surface parity with buildChecks).
|
||||
checks.push(await computeWedgedQueueCheck(engine));
|
||||
|
||||
// #2194 fix #5 — warn when autopilot fan-out exceeds worker concurrency.
|
||||
checks.push(await computeAutopilotFanoutConcurrencyCheck(engine));
|
||||
|
||||
// v0.41 Bug 2 / Eng D8 — subagent_health surfaces rate-lease pressure to the operator.
|
||||
checks.push(await checkSubagentHealth(engine));
|
||||
|
||||
@@ -1657,49 +1532,6 @@ export async function computeWedgedQueueCheck(engine: BrainEngine): Promise<Chec
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* #2194 fix #5: warn when autopilot's per-tick fan-out exceeds the worker's
|
||||
* effective concurrency. Fanning out more cycles than there are worker slots
|
||||
* guarantees waiters that race the stalled-sweeper — a silent misconfig today.
|
||||
* Advisory (started-event concurrency is fine here; the behavior-changing clamp
|
||||
* in resolveEffectiveFanoutMax is the one that gates on liveness). Surfaces only
|
||||
* when a supervisor has actually started (no noise on never-supervised brains).
|
||||
*/
|
||||
export async function computeAutopilotFanoutConcurrencyCheck(engine: BrainEngine): Promise<Check> {
|
||||
if (engine.kind !== 'postgres') {
|
||||
return { name: 'autopilot_fanout_concurrency', status: 'ok', message: 'PGLite — single-writer, fan-out is 1' };
|
||||
}
|
||||
try {
|
||||
const { resolveFanoutMax, readSupervisorConcurrency } = await import('./autopilot-fanout.ts');
|
||||
const concurrency = await readSupervisorConcurrency('default');
|
||||
if (concurrency === null) {
|
||||
return { name: 'autopilot_fanout_concurrency', status: 'ok', message: 'No supervisor observed — skipping fan-out/concurrency check' };
|
||||
}
|
||||
const fanoutMax = await resolveFanoutMax(engine);
|
||||
const effectiveSlots = Math.max(1, concurrency - 1);
|
||||
if (fanoutMax > effectiveSlots) {
|
||||
return {
|
||||
name: 'autopilot_fanout_concurrency',
|
||||
status: 'warn',
|
||||
message:
|
||||
`autopilot fan-out (${fanoutMax}/tick) exceeds worker concurrency (${concurrency}). ` +
|
||||
`Surplus cycles queue behind the worker and race the stalled-sweeper. ` +
|
||||
`Lower fan-out: \`gbrain config set autopilot.fanout_max_per_tick ${effectiveSlots}\`, ` +
|
||||
`or raise the supervisor's \`--concurrency\` to ${fanoutMax + 1}. ` +
|
||||
`(The clamp in autopilot does this automatically unless disabled.)`,
|
||||
details: { fanout_max: fanoutMax, concurrency, effective_slots: effectiveSlots },
|
||||
};
|
||||
}
|
||||
return {
|
||||
name: 'autopilot_fanout_concurrency',
|
||||
status: 'ok',
|
||||
message: `fan-out ${fanoutMax}/tick within worker concurrency ${concurrency}`,
|
||||
};
|
||||
} catch (e) {
|
||||
return { name: 'autopilot_fanout_concurrency', status: 'ok', message: `Skipped (${e instanceof Error ? e.message : String(e)})` };
|
||||
}
|
||||
}
|
||||
|
||||
export async function checkBatchRetryHealth(_engine: BrainEngine): Promise<Check> {
|
||||
try {
|
||||
// Codex M-10: surface bad env config at doctor time.
|
||||
@@ -2514,62 +2346,25 @@ export function checkAutopilotLockScope(): Check {
|
||||
* but the main work is blocked. Requires explicit heartbeat probe;
|
||||
* speculation until production data shows the case.
|
||||
*/
|
||||
export async function checkStaleLocks(
|
||||
engine: BrainEngine,
|
||||
opts: { fix?: boolean; dryRun?: boolean } = {},
|
||||
): Promise<Check> {
|
||||
export async function checkStaleLocks(engine: BrainEngine): Promise<Check> {
|
||||
try {
|
||||
const { listStaleLocks, reapDeadHolderLocks } = await import('../core/db-lock.ts');
|
||||
|
||||
// #1972: under `gbrain doctor --fix`, reap dead-holder sync/cycle locks
|
||||
// using the SAME namespace-scoped, host-scoped, snapshot-matched reaper the
|
||||
// cycle runs at start. This is the self-heal path for no-autopilot brains: a
|
||||
// brain that never runs `gbrain dream` never hits the cycle-start sweep, so
|
||||
// doctor --fix is how its crashed-sync locks get cleared. DB-only, so it's
|
||||
// orthogonal to (and unaffected by) the skills-dir --fix safety gate above.
|
||||
// Best-effort: a reap failure falls through to the warn path below.
|
||||
let reapedIds: string[] = [];
|
||||
if (opts.fix && !opts.dryRun) {
|
||||
try {
|
||||
reapedIds = (await reapDeadHolderLocks(engine)).reapedIds;
|
||||
} catch { /* fall through; listStaleLocks still surfaces remaining locks */ }
|
||||
}
|
||||
const reapedNote = reapedIds.length > 0
|
||||
? `Reaped ${reapedIds.length} dead-holder lock(s): ${reapedIds.join(', ')}.`
|
||||
: null;
|
||||
|
||||
const { listStaleLocks } = await import('../core/db-lock.ts');
|
||||
const stale = await listStaleLocks(engine);
|
||||
if (stale.length === 0) {
|
||||
return {
|
||||
name: 'stale_locks',
|
||||
status: 'ok',
|
||||
message: reapedNote
|
||||
? `${reapedNote} No stale locks remain.`
|
||||
: 'No stale locks (no rows with ttl_expires_at < NOW())',
|
||||
};
|
||||
return { name: 'stale_locks', status: 'ok', message: 'No stale locks (no rows with ttl_expires_at < NOW())' };
|
||||
}
|
||||
const lines = stale.slice(0, 10).map(s => {
|
||||
const ageH = Math.floor(s.age_ms / 3600_000);
|
||||
let breakHint = 'gbrain doctor';
|
||||
if (s.id.startsWith('gbrain-sync:')) {
|
||||
breakHint = `gbrain sync --break-lock --source ${s.id.slice('gbrain-sync:'.length)}`;
|
||||
} else if (s.id.startsWith('gbrain-cycle:')) {
|
||||
breakHint = `gbrain dream --break-lock --source ${s.id.slice('gbrain-cycle:'.length)}`;
|
||||
} else if (s.id === 'gbrain-cycle') {
|
||||
breakHint = 'gbrain dream --break-lock';
|
||||
}
|
||||
const source = s.id.startsWith('gbrain-sync:') ? s.id.slice('gbrain-sync:'.length) : null;
|
||||
const breakHint = source ? `gbrain sync --break-lock --source ${source}` : `gbrain sync --break-lock`;
|
||||
return ` ${s.id} (pid ${s.holder_pid} on ${s.holder_host}, age ${ageH}h) → ${breakHint}`;
|
||||
});
|
||||
const tail = stale.length > 10 ? ` ... and ${stale.length - 10} more.` : null;
|
||||
const header = opts.fix
|
||||
? `${stale.length} stale lock(s) remain that could not be auto-reaped (live holder, cross-host, or within the PID-reuse grace):`
|
||||
: `${stale.length} stale lock(s) detected (ttl_expires_at < NOW()):`;
|
||||
return {
|
||||
name: 'stale_locks',
|
||||
status: 'warn',
|
||||
message: [
|
||||
reapedNote,
|
||||
header,
|
||||
`${stale.length} stale lock(s) detected (ttl_expires_at < NOW()):`,
|
||||
...lines,
|
||||
tail,
|
||||
].filter(Boolean).join('\n'),
|
||||
@@ -2785,7 +2580,7 @@ async function checkEmbeddingEnvOverride(engine: BrainEngine): Promise<Check> {
|
||||
};
|
||||
}
|
||||
|
||||
export async function checkSubagentCapability(engine: BrainEngine): Promise<Check> {
|
||||
async function checkSubagentCapability(engine: BrainEngine): Promise<Check> {
|
||||
try {
|
||||
const { classifyCapabilities } = await import('../core/ai/capabilities.ts');
|
||||
const tierSubagent = await engine.getConfig('models.tier.subagent');
|
||||
@@ -2846,11 +2641,8 @@ export async function checkSubagentCapability(engine: BrainEngine): Promise<Chec
|
||||
const { loadConfig } = await import('../core/config.ts');
|
||||
const cfg = loadConfig();
|
||||
const chatModel = cfg?.chat_model;
|
||||
const gatewayLoopRaw = await engine.getConfig('agent.use_gateway_loop').catch(() => null);
|
||||
const gatewayLoopEnabled = typeof gatewayLoopRaw === 'string'
|
||||
&& ['true', '1', 'yes', 'on'].includes(gatewayLoopRaw.trim().toLowerCase());
|
||||
const { isAnthropicProvider } = await import('../core/model-config.ts');
|
||||
if (chatModel && !isAnthropicProvider(chatModel) && !process.env.ANTHROPIC_API_KEY && !gatewayLoopEnabled) {
|
||||
if (chatModel && !isAnthropicProvider(chatModel) && !process.env.ANTHROPIC_API_KEY) {
|
||||
return {
|
||||
name: 'subagent_capability',
|
||||
status: 'warn',
|
||||
@@ -3056,7 +2848,7 @@ export async function computeConversationFactsBacklogCheck(
|
||||
const typesRaw = await engine.getConfig(
|
||||
'cycle.conversation_facts_backfill.types',
|
||||
);
|
||||
let types = ['conversation', 'meeting', 'slack', 'email', 'imessage', 'imessage-daily'];
|
||||
let types = ['conversation', 'meeting', 'slack', 'email'];
|
||||
if (typesRaw) {
|
||||
try {
|
||||
const parsed = JSON.parse(typesRaw);
|
||||
@@ -3531,40 +3323,6 @@ export async function checkSyncFreshness(
|
||||
let hasWarnings = false;
|
||||
let hasFailures = false;
|
||||
|
||||
// BUG 4 (v0.42.x): a source with a LIVE, non-expired per-source sync lock is
|
||||
// actively syncing RIGHT NOW — it must not read as stale or never-synced.
|
||||
// The live lock is the only honest "in progress" signal. Checkpoint banking
|
||||
// is NOT usable: a blocked sync banks the good files then writes no anchor
|
||||
// (test/sync-resumable-import.serial.test.ts), so banking can't tell
|
||||
// in-progress from wedged. A blocked/failed sync's process has exited (no
|
||||
// lock row) and a wedged holder stops refreshing (TTL lapses), so either
|
||||
// correctly falls through to the stale path and is NEVER masked. Same
|
||||
// dynamic import as the stale_locks check; any throw (stub engine in unit
|
||||
// tests, pre-lock-table brain) is swallowed to false, so this can only ADD
|
||||
// an in-progress verdict, never suppress a real stale one.
|
||||
// Notes for sources caught actively syncing (surfaced in the result
|
||||
// message so the operator sees "in progress", not just a silent healthy
|
||||
// bucket). Empty when nothing is syncing — keeps the steady-state messages
|
||||
// byte-for-byte unchanged.
|
||||
const inProgress: string[] = [];
|
||||
let liveSyncSnap: (sourceId: string) => Promise<{ holder_pid: number; holder_host: string } | null> =
|
||||
async () => null;
|
||||
try {
|
||||
const { inspectLock, syncLockId } = await import('../core/db-lock.ts');
|
||||
liveSyncSnap = async (sourceId: string) => {
|
||||
try {
|
||||
const snap = await inspectLock(engine, syncLockId(sourceId));
|
||||
return snap && !snap.ttl_expired
|
||||
? { holder_pid: snap.holder_pid, holder_host: snap.holder_host }
|
||||
: null;
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
};
|
||||
} catch {
|
||||
/* db-lock unavailable — skip in-progress detection, staleness stands. */
|
||||
}
|
||||
|
||||
for (const source of sources) {
|
||||
// Embed source.id in user-visible messages so `gbrain sync --source <id>`
|
||||
// matches what the user copy-pastes. Show display name in parens when set.
|
||||
@@ -3572,15 +3330,6 @@ export async function checkSyncFreshness(
|
||||
? `'${source.id}' (${source.name})`
|
||||
: `'${source.id}'`;
|
||||
|
||||
// BUG 4: actively syncing (live lock) → healthy, count as synced_recently
|
||||
// and skip the staleness checks. Keeps the 3-bucket invariant intact.
|
||||
const liveSnap = await liveSyncSnap(source.id);
|
||||
if (liveSnap) {
|
||||
inProgress.push(`${display} sync in progress (pid ${liveSnap.holder_pid} on ${liveSnap.holder_host})`);
|
||||
synced_recently_count++;
|
||||
continue;
|
||||
}
|
||||
|
||||
if (!source.last_sync_at) {
|
||||
issues.push(`Source ${display} has never been synced`);
|
||||
hasFailures = true;
|
||||
@@ -3666,15 +3415,12 @@ export async function checkSyncFreshness(
|
||||
|
||||
// D6 invariant: every source incremented exactly one bucket.
|
||||
const details = { unchanged_count, synced_recently_count, stale_count };
|
||||
// BUG 4: append in-progress context when any source is actively syncing.
|
||||
// Empty otherwise, so steady-state messages are byte-for-byte unchanged.
|
||||
const inProgressNote = inProgress.length ? `. ${inProgress.join('; ')}` : '';
|
||||
|
||||
if (hasFailures) {
|
||||
return {
|
||||
name: 'sync_freshness',
|
||||
status: 'fail',
|
||||
message: `${issues.join('; ')}. Run \`gbrain sync --source <id>\` for each stale source${inProgressNote}`,
|
||||
message: `${issues.join('; ')}. Run \`gbrain sync --source <id>\` for each stale source`,
|
||||
details,
|
||||
};
|
||||
}
|
||||
@@ -3682,7 +3428,7 @@ export async function checkSyncFreshness(
|
||||
return {
|
||||
name: 'sync_freshness',
|
||||
status: 'warn',
|
||||
message: `${issues.join('; ')}. Run \`gbrain sync --source <id>\` to refresh${inProgressNote}`,
|
||||
message: `${issues.join('; ')}. Run \`gbrain sync --source <id>\` to refresh`,
|
||||
details,
|
||||
};
|
||||
}
|
||||
@@ -3693,7 +3439,7 @@ export async function checkSyncFreshness(
|
||||
return {
|
||||
name: 'sync_freshness',
|
||||
status: 'ok',
|
||||
message: `All ${sources.length} federated source(s) up to date (no new commits since last sync)${inProgressNote}`,
|
||||
message: `All ${sources.length} federated source(s) up to date (no new commits since last sync)`,
|
||||
details,
|
||||
};
|
||||
}
|
||||
@@ -3701,14 +3447,14 @@ export async function checkSyncFreshness(
|
||||
return {
|
||||
name: 'sync_freshness',
|
||||
status: 'ok',
|
||||
message: `${sources.length} federated source(s): ${synced_recently_count} synced recently, ${unchanged_count} unchanged since last sync${inProgressNote}`,
|
||||
message: `${sources.length} federated source(s): ${synced_recently_count} synced recently, ${unchanged_count} unchanged since last sync`,
|
||||
details,
|
||||
};
|
||||
}
|
||||
return {
|
||||
name: 'sync_freshness',
|
||||
status: 'ok',
|
||||
message: `All ${sources.length} federated source(s) synced recently${inProgressNote}`,
|
||||
message: `All ${sources.length} federated source(s) synced recently`,
|
||||
details,
|
||||
};
|
||||
} catch (e) {
|
||||
@@ -4135,93 +3881,6 @@ export async function computePoolReapHealthCheck(
|
||||
return null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Retrieval Reflex health (#1981). Read-only, fail-open. The deterministic
|
||||
* pointer layer is on by default; this reports the TRUTH, not an aspiration:
|
||||
* - config/env disabled → warn (pointer layer off)
|
||||
* - heartbeat fired recently → ok, "active" (it's demonstrably working,
|
||||
* whatever path — Postgres/IPC/host)
|
||||
* - enabled, no recent heartbeat → ok if a viable path looks present
|
||||
* (postgres, or pglite serve socket),
|
||||
* else warn (likely inactive — policy
|
||||
* skill carries). Never claims a host
|
||||
* capability it can't observe.
|
||||
* Policy-skill install state is reported in details (it ships into the HOST
|
||||
* repo, so absence in gbrain's own skills dir is expected, not a failure).
|
||||
*/
|
||||
export function buildRetrievalReflexCheck(skillsDir: string | null): Check {
|
||||
const name = 'retrieval_reflex_health';
|
||||
try {
|
||||
const cfg = loadConfig();
|
||||
const enabled = reflexEnabled(cfg);
|
||||
const engineKind = cfg?.engine ?? 'unknown';
|
||||
const skillInstalled = !!skillsDir && existsSync(join(skillsDir, 'retrieval-reflex', 'SKILL.md'));
|
||||
|
||||
if (!enabled) {
|
||||
return {
|
||||
name,
|
||||
status: 'ok',
|
||||
message: 'retrieval reflex intentionally disabled (config/env) — entity pointer layer off',
|
||||
details: { enabled: false, engine: engineKind, policy_skill_installed: skillInstalled },
|
||||
};
|
||||
}
|
||||
|
||||
// Heartbeat is the authority for "is it firing".
|
||||
const hbPath = join(homedir(), '.gbrain', 'integrations', 'retrieval-reflex', 'heartbeat.jsonl');
|
||||
let lastFired: string | null = null;
|
||||
try {
|
||||
if (existsSync(hbPath)) {
|
||||
const lines = readFileSync(hbPath, 'utf8').trim().split('\n').filter(Boolean);
|
||||
const last = lines.length ? JSON.parse(lines[lines.length - 1]) : null;
|
||||
if (last && typeof last.ts === 'string') lastFired = last.ts;
|
||||
}
|
||||
} catch { /* heartbeat unreadable — treat as never fired */ }
|
||||
const firedRecently =
|
||||
!!lastFired && Date.now() - new Date(lastFired).getTime() < 7 * 24 * 60 * 60 * 1000;
|
||||
|
||||
// Detect a viable resolve path the doctor CAN see (host ctx.brainQuery is invisible).
|
||||
let pathDesc: string;
|
||||
let viablePathVisible: boolean;
|
||||
if (engineKind === 'postgres') {
|
||||
pathDesc = 'postgres direct';
|
||||
viablePathVisible = true;
|
||||
} else if (engineKind === 'pglite' && cfg?.database_path) {
|
||||
const socket = resolveSocketPath(cfg.database_path);
|
||||
viablePathVisible = existsSync(socket);
|
||||
pathDesc = viablePathVisible ? 'pglite via serve IPC' : 'pglite — serve IPC socket not present';
|
||||
} else {
|
||||
pathDesc = `engine ${engineKind}`;
|
||||
viablePathVisible = false;
|
||||
}
|
||||
|
||||
const runtimeMsg = firedRecently
|
||||
? `active (last fired ${lastFired})`
|
||||
: viablePathVisible
|
||||
? 'enabled; not observed firing yet'
|
||||
: 'enabled but no observed activity and no visible resolve path (host capability may still supply it; policy skill carries otherwise)';
|
||||
|
||||
const status: Check['status'] = firedRecently || viablePathVisible ? 'ok' : 'warn';
|
||||
const skillHint = skillInstalled
|
||||
? ''
|
||||
: ' — policy skill not installed; run `gbrain integrations install retrieval-reflex --target <host-repo>`';
|
||||
return {
|
||||
name,
|
||||
status,
|
||||
message: `${pathDesc}; ${runtimeMsg}${skillHint}`,
|
||||
details: {
|
||||
enabled: true,
|
||||
engine: engineKind,
|
||||
path: pathDesc,
|
||||
fired_recently: firedRecently,
|
||||
last_fired: lastFired,
|
||||
policy_skill_installed: skillInstalled,
|
||||
},
|
||||
};
|
||||
} catch (e) {
|
||||
return { name, status: 'warn', message: `could not check: ${(e as Error).message}` };
|
||||
}
|
||||
}
|
||||
|
||||
export async function buildChecks(
|
||||
engine: BrainEngine | null,
|
||||
args: string[],
|
||||
@@ -4334,18 +3993,9 @@ export async function buildChecks(
|
||||
checks.push({ name: 'resolver_health', status: 'warn', message: 'Could not find skills directory' });
|
||||
}
|
||||
|
||||
// 1b. Retrieval Reflex health (#1981, SKILL group — gated). Truthful runtime
|
||||
// status: the deterministic pointer layer is on by default; the heartbeat file
|
||||
// (written by the context engine when it actually injects) is the authority for
|
||||
// "is it firing". The doctor cannot see the OpenClaw host capability directly,
|
||||
// so it never claims "enabled via host"; it reports observed activity instead.
|
||||
if (scope === 'all') {
|
||||
checks.push(buildRetrievalReflexCheck(skillsDir));
|
||||
}
|
||||
|
||||
// 2. Skill conformance (SKILL group — gated)
|
||||
if (scope === 'all' && skillsDir) {
|
||||
const conformanceResult = skillConformanceCheck(skillsDir);
|
||||
const conformanceResult = checkSkillConformance(skillsDir);
|
||||
checks.push(conformanceResult);
|
||||
}
|
||||
|
||||
@@ -4485,22 +4135,7 @@ export async function buildChecks(
|
||||
|
||||
const pidStatus = readSupervisorPid(DEFAULT_PID_FILE);
|
||||
const supervisorPid = pidStatus.pid;
|
||||
const pidfileRunning = pidStatus.running;
|
||||
|
||||
// issue #2227 fix #1/#3: DEFAULT_PID_FILE is HOME-derived, so a supervisor
|
||||
// started under a different $HOME reads as "not running" even when healthy.
|
||||
// Consult the queue-scoped DB singleton lock (#1849, HOME-independent) before
|
||||
// warning. PID-reuse-safe (isLockHolderLive keys on lock freshness).
|
||||
let detectedViaDbLock = false;
|
||||
if (!pidfileRunning && engine) {
|
||||
try {
|
||||
const { inspectLock, isLockHolderLive } = await import('../core/db-lock.ts');
|
||||
const { supervisorLockId, SUPERVISOR_LOCK_TTL_MIN } = await import('../core/minions/supervisor.ts');
|
||||
const snap = await inspectLock(engine, supervisorLockId('default'));
|
||||
if (snap && isLockHolderLive(snap, SUPERVISOR_LOCK_TTL_MIN)) detectedViaDbLock = true;
|
||||
} catch { /* pre-migration / transient: pidfile-only */ }
|
||||
}
|
||||
const running = pidfileRunning || detectedViaDbLock;
|
||||
const running = pidStatus.running;
|
||||
|
||||
const events = readSupervisorEvents({ sinceMs: 24 * 60 * 60 * 1000 });
|
||||
const lastStart = events.filter(e => e.event === 'started').pop()?.ts ?? null;
|
||||
@@ -4548,7 +4183,7 @@ export async function buildChecks(
|
||||
checks.push({
|
||||
name: 'supervisor',
|
||||
status: 'ok',
|
||||
message: `running=true${detectedViaDbLock ? ' (detected via DB lock; pidfile not at the HOME-derived path)' : ` pid=${supervisorPid}`} last_start=${lastStart ?? 'unknown'} crashes_24h=${crashes24h} clean_exits_24h=${summary.clean_exits}`,
|
||||
message: `running=true pid=${supervisorPid} last_start=${lastStart ?? 'unknown'} crashes_24h=${crashes24h} clean_exits_24h=${summary.clean_exits}`,
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -4925,10 +4560,9 @@ export async function buildChecks(
|
||||
// triage the misses interactively.
|
||||
if (engine) {
|
||||
try {
|
||||
const { readConversationBodyForParsing } = await import('../core/conversation-parser/body.ts');
|
||||
const { parseConversation } = await import('../core/conversation-parser/parse.ts');
|
||||
const allowedTypes = ['conversation', 'meeting', 'slack', 'email', 'imessage', 'imessage-daily'] as const;
|
||||
// PageFilters supports singular `type` only; iterate the allowed types
|
||||
const allowedTypes = ['conversation', 'meeting', 'slack', 'email'] as const;
|
||||
// PageFilters supports singular `type` only; iterate the 4 types
|
||||
// and cap at ~50/each to land at ~200 total max.
|
||||
const sample: import('../core/types.ts').Page[] = [];
|
||||
for (const t of allowedTypes) {
|
||||
@@ -4945,7 +4579,7 @@ export async function buildChecks(
|
||||
const hitsByPattern: Record<string, number> = {};
|
||||
let unmatched = 0;
|
||||
for (const page of sample) {
|
||||
const body = await readConversationBodyForParsing(engine, page);
|
||||
const body = `${page.compiled_truth ?? ''}\n${page.timeline ?? ''}`.trim();
|
||||
const result = parseConversation(body, { page, noPolish: true, noFallback: true });
|
||||
const id = result.matched_pattern_id ?? '_no_match';
|
||||
hitsByPattern[id] = (hitsByPattern[id] ?? 0) + 1;
|
||||
@@ -5138,7 +4772,13 @@ export async function buildChecks(
|
||||
checks.push({
|
||||
name: 'multi_source_drift',
|
||||
status: 'warn',
|
||||
message: multiSourceDriftAdvice(result.count, sampleStr),
|
||||
message:
|
||||
`${result.count} page slug(s) appear at 'default' but NOT at the intended source ` +
|
||||
`(e.g., ${sampleStr}). Two possible causes: (1) pre-v0.30.3 putPage misroutes; ` +
|
||||
`(2) source X never completed initial sync and the default page is unrelated. ` +
|
||||
`Verify with 'gbrain sources status', then either re-sync with ` +
|
||||
`'gbrain sync --source <id> --full' or 'gbrain delete <slug>' if the default-source ` +
|
||||
`row is the misroute. (A 'gbrain sources rehome' cleanup command is tracked for v0.32.0.)`,
|
||||
});
|
||||
} else {
|
||||
checks.push({
|
||||
@@ -5247,7 +4887,17 @@ export async function buildChecks(
|
||||
|
||||
// 4. pgvector extension
|
||||
progress.heartbeat('pgvector');
|
||||
checks.push(await pgvectorCheck(engine));
|
||||
try {
|
||||
const sql = db.getConnection();
|
||||
const ext = await sql`SELECT extname FROM pg_extension WHERE extname = 'vector'`;
|
||||
if (ext.length > 0) {
|
||||
checks.push({ name: 'pgvector', status: 'ok', message: 'Extension installed' });
|
||||
} else {
|
||||
checks.push({ name: 'pgvector', status: 'fail', message: 'Extension not found. Run: CREATE EXTENSION vector;' });
|
||||
}
|
||||
} catch {
|
||||
checks.push({ name: 'pgvector', status: 'warn', message: 'Could not check pgvector extension' });
|
||||
}
|
||||
|
||||
// 4b. PgBouncer / prepared-statement compatibility.
|
||||
// URL-only inspection — no DB roundtrip — so this is cheap and works
|
||||
@@ -5830,29 +5480,8 @@ export async function buildChecks(
|
||||
"SELECT COUNT(*)::int AS count FROM pages WHERE type IN ('entity', 'person', 'company', 'organization')",
|
||||
))[0]?.count ?? 0;
|
||||
|
||||
// Compute coverage against eligible entities only — exclude test fixtures
|
||||
// (`tools/gbrain/test/*`) and template stubs (`templates/new-person`) so
|
||||
// that brains seeded only with code sources don't get spurious warnings
|
||||
// about missing link/timeline coverage on pages that are test fixtures, not
|
||||
// real knowledge entities.
|
||||
const eligibleStats = (await engine.executeRaw<{ entities: number; linked_from: number; timeline: number }>(
|
||||
`WITH eligible AS (
|
||||
SELECT id FROM pages
|
||||
WHERE type IN ('entity','person','company','organization')
|
||||
AND slug NOT LIKE 'tools/gbrain/test/%'
|
||||
AND slug <> 'templates/new-person'
|
||||
)
|
||||
SELECT
|
||||
(SELECT count(*)::int FROM eligible) AS entities,
|
||||
(SELECT count(DISTINCT from_page_id)::int FROM links WHERE from_page_id IN (SELECT id FROM eligible)) AS linked_from,
|
||||
(SELECT count(DISTINCT page_id)::int FROM timeline_entries WHERE page_id IN (SELECT id FROM eligible)) AS timeline`,
|
||||
))[0] ?? { entities: entityCount, linked_from: 0, timeline: 0 };
|
||||
|
||||
const eligibleEntityCount = Number(eligibleStats.entities ?? entityCount);
|
||||
const linkCoverage = eligibleEntityCount > 0 ? Number(eligibleStats.linked_from ?? 0) / eligibleEntityCount : 0;
|
||||
const timelineCoverage = eligibleEntityCount > 0 ? Number(eligibleStats.timeline ?? 0) / eligibleEntityCount : 0;
|
||||
const linkPct = (linkCoverage * 100).toFixed(0);
|
||||
const timelinePct = (timelineCoverage * 100).toFixed(0);
|
||||
const linkPct = ((health.link_coverage ?? 0) * 100).toFixed(0);
|
||||
const timelinePct = ((health.timeline_coverage ?? 0) * 100).toFixed(0);
|
||||
if (entityCount === 0) {
|
||||
// Markdown-only / journal / wiki brain — no entity pages to compute
|
||||
// coverage against. Coverage formula is structurally inapplicable.
|
||||
@@ -5861,19 +5490,13 @@ export async function buildChecks(
|
||||
status: 'ok',
|
||||
message: 'No entity pages — graph_coverage not applicable (markdown-only brain)',
|
||||
});
|
||||
} else if (eligibleEntityCount === 0) {
|
||||
checks.push({
|
||||
name: 'graph_coverage',
|
||||
status: 'ok',
|
||||
message: `Only code/test fixture entity pages found (${entityCount}); graph_coverage not applicable`,
|
||||
});
|
||||
} else if (linkCoverage >= 0.5 && timelineCoverage >= 0.5) {
|
||||
} else if ((health.link_coverage ?? 0) >= 0.5 && (health.timeline_coverage ?? 0) >= 0.5) {
|
||||
checks.push({ name: 'graph_coverage', status: 'ok', message: `Entity link coverage ${linkPct}%, timeline ${timelinePct}%` });
|
||||
} else {
|
||||
checks.push({
|
||||
name: 'graph_coverage',
|
||||
status: 'warn',
|
||||
message: `Entity link coverage ${linkPct}%, timeline ${timelinePct}% (${eligibleEntityCount} entity pages). Run: gbrain extract all`,
|
||||
message: `Entity link coverage ${linkPct}%, timeline ${timelinePct}% (${entityCount} entity pages). Run: gbrain extract all`,
|
||||
});
|
||||
}
|
||||
|
||||
@@ -6033,7 +5656,37 @@ export async function buildChecks(
|
||||
// surface matches `repair-jsonb` (the previous 4-target scan missed a
|
||||
// repair target, per #254/Codex review).
|
||||
progress.heartbeat('jsonb_integrity');
|
||||
checks.push(await jsonbIntegrityCheck(engine, progress));
|
||||
try {
|
||||
const sql = db.getConnection();
|
||||
const targets: Array<{ table: string; col: string; expected: 'object' | 'array' }> = [
|
||||
{ table: 'pages', col: 'frontmatter', expected: 'object' },
|
||||
{ table: 'raw_data', col: 'data', expected: 'object' },
|
||||
{ table: 'ingest_log', col: 'pages_updated', expected: 'array' },
|
||||
{ table: 'files', col: 'metadata', expected: 'object' },
|
||||
{ table: 'page_versions', col: 'frontmatter', expected: 'object' },
|
||||
];
|
||||
let totalBad = 0;
|
||||
const breakdown: string[] = [];
|
||||
for (const { table, col } of targets) {
|
||||
progress.heartbeat(`jsonb_integrity.${table}.${col}`);
|
||||
const rows = await sql.unsafe(
|
||||
`SELECT count(*)::int AS n FROM ${table} WHERE jsonb_typeof(${col}) = 'string'`,
|
||||
);
|
||||
const n = Number((rows as any)[0]?.n ?? 0);
|
||||
if (n > 0) { totalBad += n; breakdown.push(`${table}.${col}=${n}`); }
|
||||
}
|
||||
if (totalBad === 0) {
|
||||
checks.push({ name: 'jsonb_integrity', status: 'ok', message: 'All JSONB columns store objects/arrays' });
|
||||
} else {
|
||||
checks.push({
|
||||
name: 'jsonb_integrity',
|
||||
status: 'warn',
|
||||
message: `${totalBad} row(s) double-encoded (${breakdown.join(', ')}). Fix: gbrain repair-jsonb`,
|
||||
});
|
||||
}
|
||||
} catch {
|
||||
checks.push({ name: 'jsonb_integrity', status: 'warn', message: 'Could not check JSONB integrity' });
|
||||
}
|
||||
|
||||
// 10b. Takes weight grid integrity (v0.32 — EXP-2).
|
||||
//
|
||||
@@ -6379,29 +6032,12 @@ export async function buildChecks(
|
||||
.slice(0, 3)
|
||||
.map(([s, n]) => `${s}=${n}`)
|
||||
.join(', ');
|
||||
// Audit events are evidence, not automatically breakage. A large code
|
||||
// source can legitimately emit many WARN events (oversize/markup-heavy)
|
||||
// while remaining searchable and intentionally flagged. Fail on hard
|
||||
// dispositions (content actually blocked or hidden); warn on soft
|
||||
// dispositions or volume. This keeps doctor from treating expected
|
||||
// code-corpus telemetry as an unhealthy brain.
|
||||
//
|
||||
// v0.42 renamed the hard path: a rejected page emits `reject` and a
|
||||
// quarantined (hidden) junk page emits `quarantine`; `hard_block` is now
|
||||
// only the pre-v0.42 legacy alias. Counting `hard_block` alone let fresh
|
||||
// junk-ingest evidence (`reject`/`quarantine`) clear as `ok` whenever
|
||||
// fewer than 10 events landed. `flag` is a warn disposition (still
|
||||
// searchable, agent warned on retrieval), so it joins `soft_block`.
|
||||
const hardBlocked =
|
||||
summary.by_type.hard_block + summary.by_type.reject + summary.by_type.quarantine;
|
||||
const softBlocked = summary.by_type.soft_block + summary.by_type.flag;
|
||||
const status: 'ok' | 'warn' | 'fail' =
|
||||
hardBlocked > 0 ? 'fail' :
|
||||
(softBlocked > 0 || events.length >= 10) ? 'warn' : 'ok';
|
||||
events.length >= 100 ? 'fail' : events.length >= 10 ? 'warn' : 'ok';
|
||||
checks.push({
|
||||
name: 'content_sanity_audit_recent',
|
||||
status,
|
||||
message: `${events.length} events (hard=${hardBlocked} [hard_block=${summary.by_type.hard_block} reject=${summary.by_type.reject} quarantine=${summary.by_type.quarantine}] soft=${softBlocked} [soft_block=${summary.by_type.soft_block} flag=${summary.by_type.flag}] warn=${summary.by_type.warn})${topPatterns ? ', patterns: ' + topPatterns : ''}${topSources ? ', sources: ' + topSources : ''}. (Local audit only — multi-host operators set GBRAIN_AUDIT_DIR.)`,
|
||||
message: `${events.length} events (hard=${summary.by_type.hard_block} soft=${summary.by_type.soft_block} warn=${summary.by_type.warn})${topPatterns ? ', patterns: ' + topPatterns : ''}${topSources ? ', sources: ' + topSources : ''}. (Local audit only — multi-host operators set GBRAIN_AUDIT_DIR.)`,
|
||||
});
|
||||
}
|
||||
} catch (err) {
|
||||
@@ -7178,17 +6814,9 @@ export async function buildChecks(
|
||||
let vanished = 0;
|
||||
const vanishedPaths: string[] = [];
|
||||
const fs = await import('node:fs');
|
||||
const nodePath = await import('node:path');
|
||||
// storage_path is repo-relative for sync-ingested assets. Resolving
|
||||
// against cwd made this check a false-positive WARN whenever doctor
|
||||
// ran outside the brain repo.
|
||||
const repoRoot = (await engine.getConfig('sync.repo_path')) ?? process.cwd();
|
||||
for (const r of rows) {
|
||||
const abs = nodePath.isAbsolute(r.storage_path)
|
||||
? r.storage_path
|
||||
: nodePath.join(repoRoot, r.storage_path);
|
||||
try {
|
||||
fs.statSync(abs);
|
||||
fs.statSync(r.storage_path);
|
||||
} catch {
|
||||
vanished++;
|
||||
if (vanishedPaths.length < 5) vanishedPaths.push(r.storage_path);
|
||||
@@ -7286,9 +6914,6 @@ export async function buildChecks(
|
||||
// waiting, zero live-lock active, stale completions) as a health error.
|
||||
progress.heartbeat('wedged_queue');
|
||||
checks.push(await computeWedgedQueueCheck(engine));
|
||||
// #2194 fix #5 — autopilot fan-out vs worker concurrency mismatch.
|
||||
progress.heartbeat('autopilot_fanout_concurrency');
|
||||
checks.push(await computeAutopilotFanoutConcurrencyCheck(engine));
|
||||
// v0.40.4 graph_signals_coverage — global inbound-link density when
|
||||
// graph_signals is enabled in the active mode bundle.
|
||||
progress.heartbeat('graph_signals_coverage');
|
||||
@@ -7326,7 +6951,7 @@ export async function buildChecks(
|
||||
checks.push(checkAutopilotLockScope());
|
||||
// v0.41.6.0 D3 — stale_locks (gbrain_cycle_locks rows with ttl_expires_at < NOW())
|
||||
progress.heartbeat('stale_locks');
|
||||
checks.push(await checkStaleLocks(engine, { fix: doFix, dryRun }));
|
||||
checks.push(await checkStaleLocks(engine));
|
||||
// v0.38 — cycle_phase_scope (informational; no DB cost)
|
||||
progress.heartbeat('cycle_phase_scope');
|
||||
checks.push(checkCyclePhaseScope());
|
||||
@@ -7390,10 +7015,7 @@ export async function runDoctor(
|
||||
} catch { /* best-effort */ }
|
||||
}
|
||||
|
||||
// Use process.exitCode instead of process.exit() so cleanup handlers
|
||||
// (e.g. Bun unload events, open database connections) still run before
|
||||
// the process terminates. process.exit() is a hard kill that bypasses them.
|
||||
setCliExitVerdict(hasFail ? 1 : 0);
|
||||
process.exit(hasFail ? 1 : 0);
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
@@ -7432,13 +7054,15 @@ function printAutoFixReport(report: AutoFixReport, dryRun: boolean, jsonOutput:
|
||||
|
||||
|
||||
/** Quick skill conformance check — frontmatter + required sections */
|
||||
export function skillConformanceCheck(skillsDir: string): Check {
|
||||
function checkSkillConformance(skillsDir: string): Check {
|
||||
const manifestPath = join(skillsDir, 'manifest.json');
|
||||
if (!existsSync(manifestPath)) {
|
||||
return { name: 'skill_conformance', status: 'warn', message: 'manifest.json not found' };
|
||||
}
|
||||
|
||||
try {
|
||||
// Host workspaces are allowed to omit a gbrain-specific manifest. Keep
|
||||
// conformance aligned with resolver_health and skill_brain_first by using
|
||||
// the canonical fallback that derives entries from direct SKILL.md files.
|
||||
const manifest = loadOrDeriveManifest(skillsDir);
|
||||
const skills = manifest.skills;
|
||||
const manifest = JSON.parse(readFileSync(manifestPath, 'utf-8'));
|
||||
const skills = manifest.skills || [];
|
||||
let passing = 0;
|
||||
const failing: string[] = [];
|
||||
|
||||
@@ -7458,8 +7082,7 @@ export function skillConformanceCheck(skillsDir: string): Check {
|
||||
}
|
||||
|
||||
if (failing.length === 0) {
|
||||
const derivedNote = manifest.derived ? ' (derived from SKILL.md files)' : '';
|
||||
return { name: 'skill_conformance', status: 'ok', message: `${passing}/${skills.length} skills pass${derivedNote}` };
|
||||
return { name: 'skill_conformance', status: 'ok', message: `${passing}/${skills.length} skills pass` };
|
||||
}
|
||||
return {
|
||||
name: 'skill_conformance',
|
||||
@@ -7467,7 +7090,7 @@ export function skillConformanceCheck(skillsDir: string): Check {
|
||||
message: `${passing}/${skills.length} pass. Failing: ${failing.join(', ')}`,
|
||||
};
|
||||
} catch {
|
||||
return { name: 'skill_conformance', status: 'warn', message: 'Could not load or derive skills manifest' };
|
||||
return { name: 'skill_conformance', status: 'warn', message: 'Could not parse manifest.json' };
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8075,24 +7698,3 @@ async function checkSchemaPackSourceDrift(engine: BrainEngine): Promise<Check> {
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* #1123 — multi_source_drift remediation advice. Exported so the regression
|
||||
* test can pin that it only references CLI surfaces that actually exist
|
||||
* (the pre-fix text pointed at 'gbrain sources rehome', which was never
|
||||
* built, and at 'gbrain delete <slug>' without explaining that delete
|
||||
* targets the ACTIVE source — following it literally on a multi-source
|
||||
* brain deletes the correctly-routed row).
|
||||
*/
|
||||
export function multiSourceDriftAdvice(count: number, sampleStr: string): string {
|
||||
return (
|
||||
`${count} page slug(s) appear at 'default' but NOT at the intended source ` +
|
||||
`(e.g., ${sampleStr}). Two possible causes: (1) pre-v0.30.3 putPage misroutes; ` +
|
||||
`(2) the intended source never completed initial sync and the default page is unrelated. ` +
|
||||
`Verify with 'gbrain sources status', then re-sync with ` +
|
||||
`'gbrain sync --source <id> --full' (reconciles drift without deleting data). ` +
|
||||
`If a misrouted default-source row remains after re-sync, remove it with ` +
|
||||
`'GBRAIN_SOURCE=default gbrain delete <slug>' — delete targets the active source, ` +
|
||||
`so pin it to 'default' explicitly.`
|
||||
);
|
||||
}
|
||||
|
||||
@@ -76,18 +76,6 @@ interface DreamArgs {
|
||||
drain: boolean;
|
||||
/** Drain wallclock budget in seconds. Default 300 (5 min). */
|
||||
windowSeconds: number;
|
||||
/**
|
||||
* issue #2860 — `--once`. One-shot bypass of the named `--phase`'s own
|
||||
* `dream.<phase>.enabled` / `cycle.<phase>.enabled` config gate, for this
|
||||
* invocation only. Never reads or writes config — unlike the old
|
||||
* "toggle enabled true, run, toggle back to false" workaround, a crash
|
||||
* mid-run can't leave any global state stuck. Requires an explicit
|
||||
* `--phase <name>`; bare `--once` is a usage error (there'd be no single
|
||||
* phase to target). Applies only to phases with a config `.enabled` gate
|
||||
* (patterns, synthesize, conversation_facts_backfill, enrich_thin,
|
||||
* skillopt) — a no-op for phases that always run when named directly.
|
||||
*/
|
||||
once: boolean;
|
||||
}
|
||||
|
||||
const ISO_DATE_RE = /^\d{4}-\d{2}-\d{2}$/;
|
||||
@@ -117,14 +105,6 @@ function collectFlagValues(args: string[], flag: string): string[] | null {
|
||||
|
||||
function parseArgs(args: string[]): DreamArgs {
|
||||
const phaseIdx = args.indexOf('--phase');
|
||||
// issue #2860 (Codex P3): captured BEFORE --input/--drain get a chance to
|
||||
// implicitly default `phase` below, so --once's validation can require
|
||||
// the user actually TYPED --phase, not merely that some phase ended up
|
||||
// resolved. Without this, `--input <f> --once` and `--drain --once`
|
||||
// slip past the "explicit --phase required" contract (the derived
|
||||
// `phase` value is already non-null by the time that check runs) and
|
||||
// --once becomes silently ineffective for both.
|
||||
const phaseWasExplicit = phaseIdx !== -1;
|
||||
const rawPhase = phaseIdx !== -1 ? args[phaseIdx + 1] : null;
|
||||
let phase = rawPhase && (ALL_PHASES as string[]).includes(rawPhase)
|
||||
? (rawPhase as CyclePhase)
|
||||
@@ -234,35 +214,6 @@ function parseArgs(args: string[]): DreamArgs {
|
||||
}
|
||||
}
|
||||
|
||||
// issue #2860: --once requires an EXPLICIT single --phase target (typed
|
||||
// by the user, not merely implied by --input/--drain — see
|
||||
// `phaseWasExplicit` above). Bare `--once` (full/default cycle) has no
|
||||
// single phase to bypass the gate for, and force-enabling EVERY
|
||||
// currently-disabled phase at once would be exactly the kind of
|
||||
// surprise-spend risk the flag exists to prevent. An implicit phase
|
||||
// (from --input or --drain) is rejected too: --drain returns before
|
||||
// onceForPhase is ever read, and --input already bypasses the
|
||||
// synthesize gate on its own, so --once would silently do nothing in
|
||||
// either case — reject loudly instead of pretending it worked (Codex
|
||||
// review finding).
|
||||
//
|
||||
// Codex review finding: `--help` must short-circuit BEFORE this exits(2),
|
||||
// matching the "IRON RULE" pinned by test/dream.test.ts's
|
||||
// "--help --source whatever prints help and exits 0" case — `gbrain
|
||||
// dream --help --once` (no --phase) must show help, not a usage error.
|
||||
const once = args.includes('--once');
|
||||
const wantsHelp = args.includes('--help') || args.includes('-h');
|
||||
if (once && !phaseWasExplicit && !wantsHelp) {
|
||||
console.error(
|
||||
'--once requires an explicit --phase <name> (bypasses that one ' +
|
||||
'phase\'s dream.<phase>.enabled / cycle.<phase>.enabled gate for ' +
|
||||
'this run only; never touches config). A phase implied by --input ' +
|
||||
'or --drain does not count — --once would silently do nothing for ' +
|
||||
'those. Usage: gbrain dream --phase <name> --once',
|
||||
);
|
||||
process.exit(2);
|
||||
}
|
||||
|
||||
return {
|
||||
json: args.includes('--json'),
|
||||
dryRun: args.includes('--dry-run'),
|
||||
@@ -278,7 +229,6 @@ function parseArgs(args: string[]): DreamArgs {
|
||||
source,
|
||||
drain,
|
||||
windowSeconds,
|
||||
once,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -360,17 +310,6 @@ Options:
|
||||
"--dry-run" does NOT mean "zero LLM calls."
|
||||
--json Emit the CycleReport as JSON (agent-readable)
|
||||
--phase <name> Run a single phase: ${ALL_PHASES.join(' | ')}
|
||||
--once With --phase <name>: run that phase once even if its
|
||||
own dream.<phase>.enabled / cycle.<phase>.enabled
|
||||
config gate is false. Never reads or writes config —
|
||||
unlike toggling the flag on/off around the run, a
|
||||
crash mid-invocation can't leave it stuck. Applies to
|
||||
patterns, synthesize, conversation_facts_backfill,
|
||||
enrich_thin, skillopt; no-op on phases with no such
|
||||
gate. Requires an EXPLICIT --phase <name> — a phase
|
||||
implied by --input or --drain does not count (bare
|
||||
--once, or --once with --input/--drain and no
|
||||
explicit --phase, is a usage error).
|
||||
--pull git pull the brain repo before syncing (default: no pull)
|
||||
--dir <path> Brain directory (default: configured brain). On a
|
||||
postgres/remote brain with no local checkout, the
|
||||
@@ -414,7 +353,6 @@ Examples:
|
||||
gbrain dream
|
||||
gbrain dream --dry-run --json
|
||||
gbrain dream --phase lint
|
||||
gbrain dream --phase patterns --once # run once, ignore dream.patterns.enabled=false
|
||||
gbrain dream --phase synthesize --input ~/transcripts/2026-04-25.txt
|
||||
gbrain dream --phase synthesize --from 2026-04-01 --to 2026-04-25
|
||||
0 2 * * * gbrain dream --json # nightly via cron
|
||||
@@ -656,9 +594,6 @@ export async function runDream(engine: BrainEngine | null, args: string[]): Prom
|
||||
synthFrom: opts.from ?? undefined,
|
||||
synthTo: opts.to ?? undefined,
|
||||
synthBypassDreamGuard: opts.bypassDreamGuard,
|
||||
// issue #2860: opts.phase is guaranteed non-null here when opts.once is
|
||||
// set (parseArgs enforces --once requires --phase).
|
||||
onceForPhase: opts.once ? opts.phase! : undefined,
|
||||
});
|
||||
|
||||
if (opts.json) {
|
||||
|
||||
+34
-354
@@ -9,16 +9,7 @@ import { loadConfig } from '../core/config.ts';
|
||||
import { slog, serr } from '../core/console-prefix.ts';
|
||||
import { filterOutEmbedSkipped } from '../core/embed-skip.ts';
|
||||
import { runSlidingPool } from '../core/worker-pool.ts';
|
||||
import { isAborted, anySignal, AbortError } from '../core/abort-check.ts';
|
||||
import { type DbPacer, createDbPacer, createNoopPacer, observed } from '../core/db-pacer.ts';
|
||||
import {
|
||||
resolvePaceMode,
|
||||
loadPaceModeConfig,
|
||||
readPaceEnv,
|
||||
type PaceKeyOverrides,
|
||||
} from '../core/pace-mode.ts';
|
||||
import { tryAcquireDbLock, type DbLockHandle } from '../core/db-lock.ts';
|
||||
import { embedBackfillLockId } from '../core/embed-backfill-lock.ts';
|
||||
import { isAborted, anySignal } from '../core/abort-check.ts';
|
||||
|
||||
export interface EmbedOpts {
|
||||
/** Embed ALL pages (every chunk). */
|
||||
@@ -80,33 +71,6 @@ export interface EmbedOpts {
|
||||
* with the internal wall-clock budget timer via `anySignal`.
|
||||
*/
|
||||
signal?: AbortSignal;
|
||||
/**
|
||||
* DB-contention pacing (paced-backfill). Raw inputs resolved in
|
||||
* runEmbedCore via env > config > bundle (env beats config = incident
|
||||
* escape hatch). `perCallMode` is from `--pace[=mode]`; `perCall` from
|
||||
* `--pace-max-concurrency` etc. Absent ⇒ resolves from env/config (so a
|
||||
* queued job paced by config alone still throttles). Mode `off` ⇒ no-op.
|
||||
*/
|
||||
pace?: {
|
||||
perCallMode?: string;
|
||||
perCall?: PaceKeyOverrides;
|
||||
};
|
||||
/**
|
||||
* When the pace overrides were SERIALIZED from a background-job payload (not
|
||||
* typed at an interactive CLI), resolve them at the config tier so
|
||||
* `GBRAIN_PACE_*` on the worker still overrides at execution (Codex P2). Set
|
||||
* by the `embed` job handler; unset for interactive CLI runs.
|
||||
*/
|
||||
paceFromBackground?: boolean;
|
||||
/**
|
||||
* E-2 (paced-backfill): single-flight the stale run by taking the SAME
|
||||
* per-source lock the `embed-backfill` minion handler uses, so a hand-run CLI
|
||||
* backfill and a queued job can't grind the same source at once (closing the
|
||||
* NULL→non-NULL upsert race window that paced — longer — runs widen). Set
|
||||
* ONLY by the CLI (`runEmbed`); the minion path already locks. All-source
|
||||
* runs lock every source in sorted order. dryRun skips it.
|
||||
*/
|
||||
singleFlight?: boolean;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -130,24 +94,6 @@ export interface EmbedResult {
|
||||
pages_processed: number;
|
||||
/** True if this run was a dry-run. */
|
||||
dryRun: boolean;
|
||||
/**
|
||||
* E1 (paced-backfill): end-of-run pacing telemetry. Present ONLY when pacing
|
||||
* was active (enabled bundle). The number the operator could not get from an
|
||||
* external wrapper ("zero pauses" ≠ "queue safe").
|
||||
*/
|
||||
pacing?: {
|
||||
maxConcurrency: number;
|
||||
/** In-band latency samples folded into the EWMA. */
|
||||
samples: number;
|
||||
/** Final EWMA of observed DB-op latency (ms), or null if no samples. */
|
||||
ewmaMs: number | null;
|
||||
/** Cumulative cooperative-sleep time (ms). */
|
||||
totalSleptMs: number;
|
||||
/** Number of cooperative sleeps. */
|
||||
sleeps: number;
|
||||
/** High-water mark of acquirers blocked on the permit (sync path). */
|
||||
maxWaiters: number;
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -261,118 +207,11 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
|
||||
return result;
|
||||
}
|
||||
if (opts.all || opts.stale) {
|
||||
// E-2 (paced-backfill): CLI single-flight. Take the SAME per-source lock as
|
||||
// the embed-backfill minion handler so a hand-run backfill and a queued job
|
||||
// are mutually exclusive per source. All-source runs lock every source in
|
||||
// sorted (deterministic) order to avoid acquire-order deadlock. Released in
|
||||
// the finally below. Skipped for dryRun and when the caller didn't opt in
|
||||
// (cycle / catch-up / sync-auto-embed callers never single-flight).
|
||||
const sfLocks: DbLockHandle[] = [];
|
||||
if (opts.singleFlight && opts.stale && !opts.dryRun) {
|
||||
let lockSourceIds: string[];
|
||||
if (opts.sourceId) {
|
||||
lockSourceIds = [opts.sourceId];
|
||||
} else {
|
||||
try {
|
||||
const rows = await engine.listAllSources();
|
||||
lockSourceIds = rows.map((r) => r.id).sort();
|
||||
} catch {
|
||||
lockSourceIds = [];
|
||||
}
|
||||
}
|
||||
for (const sid of lockSourceIds) {
|
||||
let lock: DbLockHandle | null = null;
|
||||
try {
|
||||
lock = await tryAcquireDbLock(engine, embedBackfillLockId(sid), 60);
|
||||
} catch {
|
||||
// Fail-open: a lock-subsystem error must not crash a backfill. Drop
|
||||
// single-flight for this run (release what we took) and proceed.
|
||||
for (const h of sfLocks) {
|
||||
try { await h.release(); } catch { /* best-effort */ }
|
||||
}
|
||||
sfLocks.length = 0;
|
||||
break;
|
||||
}
|
||||
if (!lock) {
|
||||
// Another backfill (CLI or job) holds this source. Release what we
|
||||
// took and bail cleanly rather than racing the upsert path.
|
||||
for (const h of sfLocks) {
|
||||
try { await h.release(); } catch { /* best-effort */ }
|
||||
}
|
||||
serr(` [embed] another backfill is already running for source "${sid}"; skipping (single-flight).`);
|
||||
return result;
|
||||
}
|
||||
sfLocks.push(lock);
|
||||
}
|
||||
}
|
||||
|
||||
// Resolve DB-contention pacing (env > config > bundle; env is the
|
||||
// incident escape hatch). dryRun skips it — no writes to pace. A
|
||||
// disabled bundle yields a no-op pacer (zero overhead on the hot path).
|
||||
let pacer: DbPacer = createNoopPacer();
|
||||
let paceMaxConcurrency: number | undefined;
|
||||
if (!opts.dryRun) {
|
||||
try {
|
||||
const cfg = await loadPaceModeConfig(engine);
|
||||
const { envMode, envOverrides } = readPaceEnv();
|
||||
// Codex P2: an interactive CLI flag (--pace) is the most immediate
|
||||
// intent and sits at the per-call tier (beats env). But a flag
|
||||
// SERIALIZED into a background job payload must sit at the CONFIG tier
|
||||
// so GBRAIN_PACE_* on the worker can still override it at execution
|
||||
// (incident escape hatch). paceFromBackground distinguishes the two.
|
||||
const fromBg = !!opts.paceFromBackground;
|
||||
const knobs = resolvePaceMode({
|
||||
mode: fromBg ? (opts.pace?.perCallMode ?? cfg.mode) : cfg.mode,
|
||||
configOverrides: fromBg
|
||||
? { ...cfg.configOverrides, ...(opts.pace?.perCall ?? {}) }
|
||||
: cfg.configOverrides,
|
||||
envMode,
|
||||
envOverrides,
|
||||
perCallMode: fromBg ? undefined : opts.pace?.perCallMode,
|
||||
perCall: fromBg ? undefined : opts.pace?.perCall,
|
||||
});
|
||||
if (knobs.enabled) {
|
||||
pacer = createDbPacer({ bundle: knobs });
|
||||
paceMaxConcurrency = knobs.maxConcurrency;
|
||||
}
|
||||
} catch {
|
||||
// Fail-open: pacing must never break a backfill.
|
||||
pacer = createNoopPacer();
|
||||
}
|
||||
}
|
||||
try {
|
||||
await embedAll(engine, !!opts.stale, !!opts.dryRun, result, opts.onProgress, opts.sourceId, {
|
||||
batchSize: opts.batchSize,
|
||||
priority: opts.priority,
|
||||
catchUp: opts.catchUp,
|
||||
pacer,
|
||||
paceMaxConcurrency,
|
||||
}, opts.signal);
|
||||
} finally {
|
||||
// E1: surface pacing telemetry (human + structured) when pacing was on.
|
||||
const snap = pacer.snapshot();
|
||||
if (snap.enabled) {
|
||||
result.pacing = {
|
||||
maxConcurrency: snap.maxConcurrency,
|
||||
samples: snap.sampleCount,
|
||||
ewmaMs: snap.ewmaMs,
|
||||
totalSleptMs: snap.totalSleptMs,
|
||||
sleeps: snap.sleepCount,
|
||||
maxWaiters: snap.maxWaiters,
|
||||
};
|
||||
serr(
|
||||
` [embed] pacing: cap=${snap.maxConcurrency} samples=${snap.sampleCount} ` +
|
||||
`ewma=${snap.ewmaMs === null ? 'n/a' : Math.round(snap.ewmaMs) + 'ms'} ` +
|
||||
`slept=${snap.totalSleptMs}ms/${snap.sleepCount}`,
|
||||
);
|
||||
}
|
||||
pacer.dispose();
|
||||
// E-2: release single-flight locks (reverse order). Best-effort; the
|
||||
// lock TTL is the backstop if a release fails.
|
||||
for (const h of sfLocks.reverse()) {
|
||||
try { await h.release(); } catch { /* best-effort; TTL covers it */ }
|
||||
}
|
||||
}
|
||||
await embedAll(engine, !!opts.stale, !!opts.dryRun, result, opts.onProgress, opts.sourceId, {
|
||||
batchSize: opts.batchSize,
|
||||
priority: opts.priority,
|
||||
catchUp: opts.catchUp,
|
||||
}, opts.signal);
|
||||
return result;
|
||||
}
|
||||
if (opts.slug) {
|
||||
@@ -382,39 +221,6 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
|
||||
throw new Error('No embed target specified. Pass { slug }, { slugs }, { all }, or { stale }.');
|
||||
}
|
||||
|
||||
/**
|
||||
* Parse the `--pace` family from a CLI arg list. Returns ONLY the explicit
|
||||
* overrides (CX5: never the full resolved bundle) so they can be serialized
|
||||
* into a background-job payload and re-resolved (env > config > bundle) at
|
||||
* execution. Returns undefined when no pace flag is present.
|
||||
*
|
||||
* Recognized: `--pace` (bare ⇒ balanced), `--pace=<mode>`,
|
||||
* `--pace-max-concurrency=<n>` / `--pace-max-concurrency <n>`.
|
||||
*/
|
||||
export function parsePaceArgs(
|
||||
args: string[],
|
||||
): { perCallMode?: string; perCall?: PaceKeyOverrides } | undefined {
|
||||
let perCallMode: string | undefined;
|
||||
let perCall: PaceKeyOverrides | undefined;
|
||||
for (let i = 0; i < args.length; i++) {
|
||||
const a = args[i];
|
||||
if (a === '--pace') {
|
||||
perCallMode = 'balanced';
|
||||
} else if (a.startsWith('--pace=')) {
|
||||
perCallMode = a.slice('--pace='.length) || 'balanced';
|
||||
} else if (a.startsWith('--pace-max-concurrency=')) {
|
||||
const n = parseInt(a.slice('--pace-max-concurrency='.length), 10);
|
||||
if (Number.isFinite(n) && n >= 1) (perCall ??= {}).maxConcurrency = n;
|
||||
} else if (a === '--pace-max-concurrency') {
|
||||
const n = parseInt(args[i + 1] ?? '', 10);
|
||||
if (Number.isFinite(n) && n >= 1) (perCall ??= {}).maxConcurrency = n;
|
||||
i++; // consume the value token so positional parsing can't read it as a slug (Codex P2)
|
||||
}
|
||||
}
|
||||
if (perCallMode === undefined && perCall === undefined) return undefined;
|
||||
return { ...(perCallMode !== undefined && { perCallMode }), ...(perCall && { perCall }) };
|
||||
}
|
||||
|
||||
export async function runEmbed(engine: BrainEngine, args: string[]): Promise<EmbedResult | undefined> {
|
||||
// v0.36+ T7: --background submits via Minion queue, returns job_id to
|
||||
// stdout, exits. Same semantics in TTY and cron (D9).
|
||||
@@ -433,10 +239,6 @@ export async function runEmbed(engine: BrainEngine, args: string[]): Promise<Emb
|
||||
dryRun: cleanArgs.includes('--dry-run'),
|
||||
slugs: slugsI >= 0 ? cleanArgs.slice(slugsI + 1).filter(a => !a.startsWith('--')) : undefined,
|
||||
sourceId: srcI >= 0 ? cleanArgs[srcI + 1] : undefined,
|
||||
// CX1+CX5: carry explicit pace overrides into the `embed` job payload
|
||||
// (the job name CLI --background actually submits). The handler
|
||||
// re-resolves env > config > bundle at execution.
|
||||
...(parsePaceArgs(cleanArgs) && { pace: parsePaceArgs(cleanArgs) }),
|
||||
};
|
||||
},
|
||||
source: 'cli',
|
||||
@@ -460,14 +262,12 @@ export async function runEmbed(engine: BrainEngine, args: string[]): Promise<Emb
|
||||
const priorityRaw = priorityIdx >= 0 ? args[priorityIdx + 1] : undefined;
|
||||
const priority = priorityRaw === 'recent' ? 'recent' as const : undefined;
|
||||
const catchUp = args.includes('--catch-up');
|
||||
const pace = parsePaceArgs(args);
|
||||
|
||||
let opts: EmbedOpts;
|
||||
if (slugsIdx >= 0) {
|
||||
opts = { slugs: args.slice(slugsIdx + 1).filter(a => !a.startsWith('--')), dryRun, sourceId, batchSize, priority, catchUp };
|
||||
} else if (all || stale) {
|
||||
// E-2: CLI-only single-flight for stale runs (the minion path locks itself).
|
||||
opts = { all, stale, dryRun, sourceId, batchSize, priority, catchUp, ...(pace && { pace }), ...(stale && { singleFlight: true }) };
|
||||
opts = { all, stale, dryRun, sourceId, batchSize, priority, catchUp };
|
||||
} else {
|
||||
const slug = args.find(a => !a.startsWith('--'));
|
||||
if (!slug) {
|
||||
@@ -616,10 +416,6 @@ async function embedAll(
|
||||
batchSize?: number;
|
||||
priority?: 'recent';
|
||||
catchUp?: boolean;
|
||||
/** DB-contention pacer (paced-backfill); no-op when pacing is off. */
|
||||
pacer?: DbPacer;
|
||||
/** Resolved concurrency cap (E-1: the worker count, no separate permit). */
|
||||
paceMaxConcurrency?: number;
|
||||
},
|
||||
signal?: AbortSignal,
|
||||
) {
|
||||
@@ -647,10 +443,6 @@ async function embedAll(
|
||||
return await embedAllStale(engine, sourceId, dryRun, result, onProgress, staleOpts, signature, signal);
|
||||
}
|
||||
|
||||
// --all path: pacer (no-op when off). E-1: lower the worker count to the
|
||||
// resolved cap instead of adding a separate permit.
|
||||
const pacer = staleOpts?.pacer ?? createNoopPacer();
|
||||
|
||||
// v0.31.12: when sourceId is set, scope listPages to that source.
|
||||
// v0.41 (D8 + Codex r2 #11): apply embed-skip filter via the shared
|
||||
// helper so the `--all` path honors `frontmatter.embed_skip` the same
|
||||
@@ -674,13 +466,7 @@ async function embedAll(
|
||||
// (3000+/min for tier 1 = 50+/sec, 20 parallel is safely below) and
|
||||
// avoids overwhelming postgres connection pools. Users can tune via
|
||||
// GBRAIN_EMBED_CONCURRENCY env var based on their tier/infra.
|
||||
// Paced runs lower this to the resolved cap (the real lever vs pooler-slot
|
||||
// starvation); unpaced keeps the env/default 20. Codex P2: only ever LOWER —
|
||||
// never raise above an operator's existing env cap.
|
||||
const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
|
||||
const CONCURRENCY = staleOpts?.paceMaxConcurrency
|
||||
? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
|
||||
: BASE_CONCURRENCY;
|
||||
const CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
|
||||
|
||||
async function embedOnePage(page: typeof pages[number]) {
|
||||
// #1737: bail before doing any work for this page if the run was aborted.
|
||||
@@ -689,7 +475,7 @@ async function embedAll(
|
||||
// target the correct (source_id, slug) row, not the 'default' source.
|
||||
const pageSourceId = page.source_id;
|
||||
const pageOpts = pageSourceId ? { sourceId: pageSourceId } : undefined;
|
||||
const chunks = await observed(pacer, () => engine.getChunks(page.slug, pageOpts));
|
||||
const chunks = await engine.getChunks(page.slug, pageOpts);
|
||||
const toEmbed = chunks; // staleOnly path handled above via embedAllStale
|
||||
|
||||
result.total_chunks += chunks.length;
|
||||
@@ -725,12 +511,10 @@ async function embedAll(
|
||||
embedding: embeddingMap.get(c.chunk_index) ?? undefined,
|
||||
token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
|
||||
}));
|
||||
await observed(pacer, () => engine.upsertChunks(page.slug, updated, pageOpts));
|
||||
await engine.upsertChunks(page.slug, updated, pageOpts);
|
||||
// v0.41.31: stamp embedding provenance so a later model swap is
|
||||
// detectable as stale.
|
||||
await observed(pacer, () =>
|
||||
engine.setPageEmbeddingSignature(page.slug, { sourceId: pageSourceId, signature }),
|
||||
);
|
||||
await engine.setPageEmbeddingSignature(page.slug, { sourceId: pageSourceId, signature });
|
||||
result.embedded += toEmbed.length;
|
||||
} catch (e: unknown) {
|
||||
serr(`\n Error embedding ${page.slug}: ${e instanceof Error ? e.message : e}`);
|
||||
@@ -739,12 +523,6 @@ async function embedAll(
|
||||
processed++;
|
||||
result.pages_processed++;
|
||||
onProgress?.(processed, pages.length, result.embedded);
|
||||
// Cooperative DB-contention pace between pages (no-op when unpaced).
|
||||
try {
|
||||
await pacer.pace(signal);
|
||||
} catch (e) {
|
||||
if (!(e instanceof AbortError)) throw e;
|
||||
}
|
||||
}
|
||||
|
||||
// v0.41.15.0: sliding worker pool extracted into src/core/worker-pool.ts.
|
||||
@@ -798,10 +576,6 @@ async function embedAllStale(
|
||||
batchSize?: number;
|
||||
priority?: 'recent';
|
||||
catchUp?: boolean;
|
||||
/** DB-contention pacer (paced-backfill); no-op when pacing is off. */
|
||||
pacer?: DbPacer;
|
||||
/** Resolved concurrency cap (E-1: the worker count, no separate permit). */
|
||||
paceMaxConcurrency?: number;
|
||||
},
|
||||
signature?: string,
|
||||
externalSignal?: AbortSignal,
|
||||
@@ -852,43 +626,18 @@ async function embedAllStale(
|
||||
// (page_id, chunk_index). Each query finishes in <1s.
|
||||
// v0.41.18.0 (A13): --batch-size N CLI flag overrides hardcoded 2000 default.
|
||||
const PAGE_SIZE = staleOpts?.batchSize ?? 2000;
|
||||
// Paced runs lower concurrency to the resolved cap (E-1: worker count IS the
|
||||
// lever on this single pool, no separate permit). Codex P2: pacing only ever
|
||||
// LOWERS concurrency — never raise above an operator's existing env cap.
|
||||
const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
|
||||
const CONCURRENCY = staleOpts?.paceMaxConcurrency
|
||||
? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
|
||||
: BASE_CONCURRENCY;
|
||||
const pacer = staleOpts?.pacer ?? createNoopPacer();
|
||||
const CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
|
||||
|
||||
// D3 + D3a + D8: wall-clock budget. 30 min default; env override.
|
||||
// #1946: --catch-up removes the wall-clock cap. The prior code set BUDGET_MS =
|
||||
// Number.MAX_SAFE_INTEGER and passed it to setTimeout — but setTimeout's delay
|
||||
// is a 32-bit signed int, so MAX_SAFE_INTEGER (9e15) overflows and the timer
|
||||
// fires almost immediately, aborting catch-up after a single batch. The fix is
|
||||
// to NOT arm the timer in catch-up at all: the keyset pass below terminates on
|
||||
// its own (the (page_id, chunk_index) cursor advances monotonically), and
|
||||
// SIGINT / worker-abort still propagate via externalSignal.
|
||||
const BUDGET_MS: number | null = staleOpts?.catchUp
|
||||
? null
|
||||
// v0.41.18.0 (A13): --catch-up removes the wall-clock cap entirely so the
|
||||
// handler runs until countStaleChunks() returns 0. Use Number.MAX_SAFE_INTEGER
|
||||
// (effectively unbounded) instead of the 30-min default. The AbortController
|
||||
// still wraps for SIGINT propagation; just the timer never fires.
|
||||
const BUDGET_MS = staleOpts?.catchUp
|
||||
? Number.MAX_SAFE_INTEGER
|
||||
: parseInt(process.env.GBRAIN_EMBED_TIME_BUDGET_MS || `${30 * 60 * 1000}`, 10);
|
||||
const budgetController = new AbortController();
|
||||
const budgetStart = Date.now();
|
||||
let budgetTimer = BUDGET_MS != null
|
||||
? setTimeout(() => budgetController.abort(), BUDGET_MS)
|
||||
: undefined;
|
||||
// E-4 (paced-backfill): the budget measures WORK, not waiting. After each
|
||||
// batch, re-arm the timer to fire at start + BUDGET + total-paced-sleep, so a
|
||||
// contended DB that spends time in pace() sleeps converges instead of exiting
|
||||
// having embedded little. No-op when unpaced (totalSleptMs stays 0) or in
|
||||
// catch-up (no budget timer).
|
||||
const rearmBudgetForPacing = (): void => {
|
||||
if (BUDGET_MS == null) return;
|
||||
const slept = pacer.snapshot().totalSleptMs;
|
||||
if (budgetTimer) clearTimeout(budgetTimer);
|
||||
const fireInMs = budgetStart + BUDGET_MS + slept - Date.now();
|
||||
budgetTimer = setTimeout(() => budgetController.abort(), Math.max(0, fireInMs));
|
||||
};
|
||||
const budgetTimer = setTimeout(() => budgetController.abort(), BUDGET_MS);
|
||||
const budgetSignal = budgetController.signal;
|
||||
// #1737: the effective signal fires when EITHER the internal wall-clock
|
||||
// budget OR the caller's abort (worker timeout / lock loss / SIGTERM) fires.
|
||||
@@ -911,37 +660,6 @@ async function embedAllStale(
|
||||
let afterUpdatedAt: string | null = null;
|
||||
let totalChunksLoaded = 0;
|
||||
let budgetExitNotified = false;
|
||||
// #1946 (OV2a): track chunks that errored out so a catch-up pass that finishes
|
||||
// with stale chunks still remaining (un-embeddable for a non-transient reason)
|
||||
// surfaces that loudly instead of looking like a clean run.
|
||||
let embedFailures = 0;
|
||||
|
||||
// E-3 (paced-backfill): bounded end-of-run re-entry. A longer paced run gives
|
||||
// a live writer (sync / put_page) more time to insert NEW stale rows BEHIND
|
||||
// the keyset cursor (TODOS:2301). When the cursor exhausts, re-scan from the
|
||||
// start — capped at MAX_REENTRIES AND requiring forward progress (a pass that
|
||||
// embeds 0 while count>0 stops) so a writer outrunning embed can't spin
|
||||
// forever.
|
||||
const MAX_REENTRIES = 3;
|
||||
let reentries = 0;
|
||||
let lastReentryEmbedded = 0;
|
||||
const maybeReenter = async (): Promise<boolean> => {
|
||||
// Scoped to PACED runs: pacing lengthens the run, which is what widens the
|
||||
// behind-cursor window. Unpaced runs keep prior (single-pass) behavior.
|
||||
if (!pacer.snapshot().enabled) return false;
|
||||
if (effectiveSignal.aborted) return false;
|
||||
if (reentries >= MAX_REENTRIES) return false;
|
||||
const remaining = await engine.countStaleChunks(sourceOpt);
|
||||
if (remaining === 0) return false;
|
||||
if (result.embedded === lastReentryEmbedded) return false; // no forward progress
|
||||
lastReentryEmbedded = result.embedded;
|
||||
reentries++;
|
||||
afterPageId = 0;
|
||||
afterChunkIndex = -1;
|
||||
afterUpdatedAt = null;
|
||||
serr(`\n [embed] re-entry ${reentries}/${MAX_REENTRIES}: ${remaining} stale chunk(s) appeared during the run; rescanning from start.`);
|
||||
return true;
|
||||
};
|
||||
|
||||
try {
|
||||
// eslint-disable-next-line no-constant-condition
|
||||
@@ -957,22 +675,17 @@ async function embedAllStale(
|
||||
break;
|
||||
}
|
||||
|
||||
const batch = await observed(pacer, () =>
|
||||
engine.listStaleChunks({
|
||||
batchSize: PAGE_SIZE,
|
||||
afterPageId,
|
||||
afterChunkIndex,
|
||||
...(orderBy === 'updated_desc' && {
|
||||
orderBy,
|
||||
afterUpdatedAt,
|
||||
}),
|
||||
...(sourceId && { sourceId }),
|
||||
const batch = await engine.listStaleChunks({
|
||||
batchSize: PAGE_SIZE,
|
||||
afterPageId,
|
||||
afterChunkIndex,
|
||||
...(orderBy === 'updated_desc' && {
|
||||
orderBy,
|
||||
afterUpdatedAt,
|
||||
}),
|
||||
);
|
||||
if (batch.length === 0) {
|
||||
if (await maybeReenter()) continue;
|
||||
break;
|
||||
}
|
||||
...(sourceId && { sourceId }),
|
||||
});
|
||||
if (batch.length === 0) break;
|
||||
totalChunksLoaded += batch.length;
|
||||
|
||||
// Advance cursor to last row in this batch.
|
||||
@@ -1007,7 +720,7 @@ async function embedAllStale(
|
||||
try {
|
||||
const embeddings = await embedBatchWithBackoff(stale.map(c => c.chunk_text), { abortSignal: effectiveSignal });
|
||||
// Re-fetch existing chunks and merge to avoid deleting non-stale chunks.
|
||||
const existing = await observed(pacer, () => engine.getChunks(slug, { sourceId: keySourceId }));
|
||||
const existing = await engine.getChunks(slug, { sourceId: keySourceId });
|
||||
const staleIdxToEmbedding = new Map<number, Float32Array>();
|
||||
for (let j = 0; j < stale.length; j++) {
|
||||
staleIdxToEmbedding.set(stale[j].chunk_index, embeddings[j]);
|
||||
@@ -1019,23 +732,20 @@ async function embedAllStale(
|
||||
embedding: staleIdxToEmbedding.get(c.chunk_index) ?? undefined,
|
||||
token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
|
||||
}));
|
||||
await observed(pacer, () => engine.upsertChunks(slug, merged, { sourceId: keySourceId }));
|
||||
await engine.upsertChunks(slug, merged, { sourceId: keySourceId });
|
||||
// v0.41.31: stamp provenance after the page's chunks are embedded —
|
||||
// but only when EVERY chunk was stale (fully re-embedded this pass).
|
||||
// A partially-stale page keeps preserved chunks of unknown/old
|
||||
// provenance, so don't claim it's current. (After invalidate, a
|
||||
// signature-drifted page IS fully stale → this stamps it.)
|
||||
if (signature && stale.length === existing.length) {
|
||||
await observed(pacer, () =>
|
||||
engine.setPageEmbeddingSignature(slug, { sourceId: keySourceId, signature }),
|
||||
);
|
||||
await engine.setPageEmbeddingSignature(slug, { sourceId: keySourceId, signature });
|
||||
}
|
||||
result.embedded += stale.length;
|
||||
} catch (e: unknown) {
|
||||
// Budget/abort-fired cancellations are expected on the way out; don't
|
||||
// spam per-page "Error embedding" lines when we're shutting down.
|
||||
if (effectiveSignal.aborted) return;
|
||||
embedFailures++;
|
||||
serr(`\n Error embedding ${slug}: ${e instanceof Error ? e.message : e}`);
|
||||
}
|
||||
totalProcessedPages++;
|
||||
@@ -1043,17 +753,6 @@ async function embedAllStale(
|
||||
// Use staleCount as the estimated total for progress (not exact after
|
||||
// pagination starts, but directionally correct).
|
||||
onProgress?.(totalProcessedPages, Math.ceil(staleCount / PAGE_SIZE) * keys.length, result.embedded);
|
||||
// Cooperative DB-contention pace between keys (no-op when unpaced).
|
||||
// E-4 (Codex P1): pace() is subject to the EXTERNAL abort only, NOT the
|
||||
// wall-clock budget — a contended DB's sleep must not be cut by the
|
||||
// budget timer before its time is credited. Re-arm the budget right
|
||||
// after each sleep so accrued sleep never eats into work time.
|
||||
try {
|
||||
await pacer.pace(externalSignal);
|
||||
rearmBudgetForPacing();
|
||||
} catch (e) {
|
||||
if (!(e instanceof AbortError)) throw e;
|
||||
}
|
||||
}
|
||||
|
||||
// v0.41.15.0: migrated to shared runSlidingPool. The pool checks
|
||||
@@ -1069,33 +768,14 @@ async function embedAllStale(
|
||||
failureLabel: (key) => key,
|
||||
});
|
||||
|
||||
// E-4: extend the work budget by any paced-sleep time accrued this batch.
|
||||
rearmBudgetForPacing();
|
||||
|
||||
// If we got fewer rows than PAGE_SIZE, we've reached the end.
|
||||
if (batch.length < PAGE_SIZE) {
|
||||
if (await maybeReenter()) continue;
|
||||
break;
|
||||
}
|
||||
if (batch.length < PAGE_SIZE) break;
|
||||
}
|
||||
} finally {
|
||||
if (budgetTimer) clearTimeout(budgetTimer);
|
||||
clearTimeout(budgetTimer);
|
||||
}
|
||||
|
||||
slog(`Embedded ${result.embedded} chunks across ${totalProcessedPages} pages`);
|
||||
|
||||
// #1946 (OV2a): a catch-up pass that completed without being aborted but left
|
||||
// chunks unembedded means those chunks are stuck (a non-transient embed
|
||||
// failure), not that we ran out of time. Surface it loudly so it doesn't read
|
||||
// as a clean run — re-running won't help until the underlying failure is fixed.
|
||||
if (staleOpts?.catchUp && !effectiveSignal.aborted && embedFailures > 0) {
|
||||
const remaining = await engine.countStaleChunks(
|
||||
signature ? { signature, ...(sourceId ? { sourceId } : {}) } : (sourceId ? { sourceId } : undefined),
|
||||
);
|
||||
if (remaining > 0) {
|
||||
serr(`\n [embed] catch-up finished but ${remaining} chunk(s) remain stale after ${embedFailures} embed failure(s). These are not embeddable as-is; re-running won't clear them until the underlying error is resolved.`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
+9
-40
@@ -33,7 +33,7 @@ import type { BrainEngine } from '../core/engine.ts';
|
||||
import type { EnrichCandidate, PageType } from '../core/types.ts';
|
||||
import { operations } from '../core/operations.ts';
|
||||
import type { OperationContext } from '../core/operations.ts';
|
||||
import { configureGatewayIfUninitialized, isAvailable, chat, getChatModel, withBudgetTracker } from '../core/ai/gateway.ts';
|
||||
import { isAvailable, chat, getChatModel, withBudgetTracker } from '../core/ai/gateway.ts';
|
||||
import { BudgetTracker, BudgetExhausted } from '../core/budget/budget-tracker.ts';
|
||||
import { hybridSearch } from '../core/search/hybrid.ts';
|
||||
import { serializeMarkdown } from '../core/markdown.ts';
|
||||
@@ -508,13 +508,8 @@ export async function runEnrichCore(
|
||||
// One tracker reference for both the run and the post-hoc overage check.
|
||||
// External tracker (cycle phase): used as-is, no withBudgetTracker wrap (that
|
||||
// would REPLACE not stack). Internal: capped at maxCostUsd ?? DEFAULT.
|
||||
// v0.42.42.0 (#2139): Infinity = explicit "uncapped" (off / tokenmax) → pass
|
||||
// `undefined` so BudgetTracker runs without a ceiling (NOT raw Infinity, which
|
||||
// would serialize to null in audit rows). undefined-when-unset still → DEFAULT.
|
||||
const resolvedCap =
|
||||
opts.maxCostUsd === Infinity ? undefined : (opts.maxCostUsd ?? DEFAULT_MAX_COST_USD);
|
||||
const tracker = opts.budgetTracker ?? new BudgetTracker({
|
||||
maxCostUsd: resolvedCap,
|
||||
maxCostUsd: opts.maxCostUsd ?? DEFAULT_MAX_COST_USD,
|
||||
label: `enrich:${sourceId}`,
|
||||
});
|
||||
try {
|
||||
@@ -627,15 +622,8 @@ export function parseArgs(args: string[]): ParsedArgs {
|
||||
continue;
|
||||
}
|
||||
if (a === '--max-usd' || a === '--max-cost-usd') {
|
||||
const raw = args[++i] ?? '';
|
||||
// v0.42.42.0 (#2139): off/unlimited/none → run uncapped (Infinity sentinel;
|
||||
// mapped to "no BudgetTracker ceiling" in runEnrichCore). Spend still ledgered.
|
||||
if (['off', 'unlimited', 'none'].includes(raw.trim().toLowerCase())) {
|
||||
out.maxCostUsd = Infinity;
|
||||
} else {
|
||||
const n = parseFloat(raw);
|
||||
if (Number.isFinite(n) && n > 0) out.maxCostUsd = n;
|
||||
}
|
||||
const n = parseFloat(args[++i] ?? '');
|
||||
if (Number.isFinite(n) && n > 0) out.maxCostUsd = n;
|
||||
continue;
|
||||
}
|
||||
if (a === '--min-context') {
|
||||
@@ -807,32 +795,15 @@ export async function runEnrich(engine: BrainEngine, args: string[]): Promise<vo
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Chat gateway is required for non-dry-run. Recover a cold singleton before
|
||||
// reporting an availability error (#2590).
|
||||
if (!parsed.dryRun && !isAvailable('chat')) configureGatewayIfUninitialized();
|
||||
// Chat gateway required for non-dry-run.
|
||||
if (!parsed.dryRun && !isAvailable('chat')) {
|
||||
console.error('Chat gateway unavailable. Configure a chat model (e.g. `gbrain config set chat_model anthropic:claude-haiku-4-5`), or pass --dry-run to preview candidates.');
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// v0.42.42.0 (#2139, D15A): enrich runs UNCAPPED when the operator says cost
|
||||
// isn't the constraint — either explicit `--max-usd off` (parsed to Infinity)
|
||||
// or `spend.posture=tokenmax` with no per-call cap. Uncapped → the missing-cap
|
||||
// refusals lift AND runEnrichCore passes no ceiling to the BudgetTracker (spend
|
||||
// still ledgered; posture removes the ceiling, not the accounting). An explicit
|
||||
// finite --max-usd always wins (precedence: per-call > posture).
|
||||
const explicitOff = parsed.maxCostUsd === Infinity;
|
||||
const { resolveSpendPosture } = await import('../core/spend-posture.ts');
|
||||
const posture = parsed.dryRun ? 'gated' : await resolveSpendPosture(engine);
|
||||
const uncapped =
|
||||
!parsed.dryRun && (explicitOff || (parsed.maxCostUsd === undefined && posture === 'tokenmax'));
|
||||
if (uncapped) {
|
||||
console.error(`${explicitOff ? '--max-usd off' : 'spend.posture=tokenmax'}: running uncapped, spend ledgered. docs: docs/operations/spend-controls.md`);
|
||||
}
|
||||
|
||||
// Non-TTY execute without --max-usd or --yes is refused (cost guardrail).
|
||||
if (!parsed.dryRun && parsed.maxCostUsd === undefined && !parsed.yes && !process.stdout.isTTY && !uncapped) {
|
||||
console.error('Refusing to spend without a cap in a non-interactive context. Pass --max-usd <FLOAT> (or `off`), --yes, or set spend.posture=tokenmax.');
|
||||
if (!parsed.dryRun && parsed.maxCostUsd === undefined && !parsed.yes && !process.stdout.isTTY) {
|
||||
console.error('Refusing to spend without a cap in a non-interactive context. Pass --max-usd <FLOAT> or --yes.');
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
@@ -841,7 +812,7 @@ export async function runEnrich(engine: BrainEngine, args: string[]): Promise<vo
|
||||
: (await listSources(engine)).map((s) => s.id);
|
||||
|
||||
// Dry-run cost preview (TTY) before spending.
|
||||
if (!parsed.dryRun && process.stdout.isTTY && !parsed.yes && parsed.maxCostUsd === undefined && !uncapped) {
|
||||
if (!parsed.dryRun && process.stdout.isTTY && !parsed.yes && parsed.maxCostUsd === undefined) {
|
||||
const limit = parsed.limit ?? DEFAULT_LIMIT;
|
||||
const est = (limit * sourceIds.length * COST_ESTIMATE_PER_PAGE_USD).toFixed(2);
|
||||
console.error(`About to enrich up to ${limit} page(s) per source across ${sourceIds.length} source(s), est. ~$${est}. Re-run with --max-usd or --yes to confirm.`);
|
||||
@@ -863,9 +834,7 @@ export async function runEnrich(engine: BrainEngine, args: string[]): Promise<vo
|
||||
limit: parsed.limit,
|
||||
workers: parsed.workers,
|
||||
model: parsed.model,
|
||||
// uncapped (off / tokenmax) → Infinity sentinel; runEnrichCore maps it
|
||||
// to "no BudgetTracker ceiling".
|
||||
maxCostUsd: uncapped ? Infinity : parsed.maxCostUsd,
|
||||
maxCostUsd: parsed.maxCostUsd,
|
||||
minContextChars: parsed.minContextChars,
|
||||
thinThreshold: parsed.thinThreshold,
|
||||
reenrichAfterMs: parsed.reenrichAfterMs,
|
||||
|
||||
@@ -1,44 +0,0 @@
|
||||
// v0.42.x — Life Chronicle (#2390) `gbrain eval chronicle` (Phase A.9).
|
||||
// Deterministic, brings its own in-memory PGLite (no DB, no gateway), so the
|
||||
// CI fixture gate runs anywhere. Exit 0 only on a perfect score.
|
||||
import { PGLiteEngine } from '../core/pglite-engine.ts';
|
||||
import { runChronicleEval } from '../eval/chronicle/harness.ts';
|
||||
|
||||
const HELP = `Usage: gbrain eval chronicle [--json]
|
||||
|
||||
Deterministic Life Chronicle (#2390) feature eval. Builds a synthetic month
|
||||
corpus with a known gold chronology + a planted ontology supersession + a
|
||||
planted conflict, then scores the chronicle layer on: day reconstruction
|
||||
(intra-day order), last-seen exact date, ontology supersession + --asof
|
||||
time-travel, contradiction surfacing, and source isolation.
|
||||
|
||||
Exit code 0 iff every task passes.
|
||||
`;
|
||||
|
||||
export async function runEvalChronicle(args: string[]): Promise<number> {
|
||||
if (args.includes('--help') || args.includes('-h')) {
|
||||
process.stdout.write(HELP);
|
||||
return 0;
|
||||
}
|
||||
const json = args.includes('--json');
|
||||
const engine = new PGLiteEngine();
|
||||
await engine.connect({ database_url: '' });
|
||||
await engine.initSchema();
|
||||
try {
|
||||
const result = await runChronicleEval(engine);
|
||||
if (json) {
|
||||
process.stdout.write(`${JSON.stringify(result, null, 2)}\n`);
|
||||
} else {
|
||||
process.stderr.write(
|
||||
`[eval chronicle] ${result.passed}/${result.total} tasks passed ` +
|
||||
`(score ${(result.score * 100).toFixed(0)}%)\n`,
|
||||
);
|
||||
for (const t of result.tasks) {
|
||||
process.stderr.write(` ${t.passed ? 'PASS' : 'FAIL'} ${t.id} — ${t.detail}\n`);
|
||||
}
|
||||
}
|
||||
return result.score === 1 ? 0 : 1;
|
||||
} finally {
|
||||
await engine.disconnect();
|
||||
}
|
||||
}
|
||||
@@ -275,7 +275,6 @@ function configureGatewayForCli(): boolean {
|
||||
chat_model: undefined,
|
||||
chat_fallback_chain: undefined,
|
||||
base_urls: undefined,
|
||||
provider_chat_options: undefined,
|
||||
env: { ...process.env },
|
||||
});
|
||||
return true;
|
||||
@@ -287,7 +286,6 @@ function configureGatewayForCli(): boolean {
|
||||
chat_model: config.chat_model,
|
||||
chat_fallback_chain: config.chat_fallback_chain,
|
||||
base_urls: config.provider_base_urls,
|
||||
provider_chat_options: config.provider_chat_options,
|
||||
env: { ...process.env },
|
||||
});
|
||||
return true;
|
||||
|
||||
@@ -20,13 +20,12 @@ import {
|
||||
|
||||
export async function runEvalRetrievalQuality(engine: BrainEngine, args: string[]): Promise<void> {
|
||||
const json = args.includes('--json');
|
||||
const abRelational = args.includes('--ab-relational');
|
||||
const sourceIdx = args.indexOf('--source');
|
||||
const sourceId = sourceIdx >= 0 ? args[sourceIdx + 1] : undefined;
|
||||
const fixture = args.find(a => !a.startsWith('--') && a !== sourceId);
|
||||
|
||||
if (!fixture) {
|
||||
console.error('Usage: gbrain eval retrieval-quality <fixture.jsonl> [--json] [--source <id>] [--ab-relational]');
|
||||
console.error('Usage: gbrain eval retrieval-quality <fixture.jsonl> [--json] [--source <id>]');
|
||||
process.exit(2);
|
||||
}
|
||||
|
||||
@@ -48,48 +47,6 @@ export async function runEvalRetrievalQuality(engine: BrainEngine, args: string[
|
||||
return results.map(r => r.slug);
|
||||
};
|
||||
|
||||
// v0.43 — A/B the relational recall arm (off vs on) over the same questions
|
||||
// in a fixed mode (expansion off, skipCache-equivalent via bare hybridSearch)
|
||||
// so the delta is purely the arm. Headline: graph-relationship recall@10 lift.
|
||||
if (abRelational) {
|
||||
const mk = (relationalRetrieval: boolean): SearchFn => async (q) => {
|
||||
const results = await hybridSearch(engine, q, {
|
||||
limit: 10, relationalRetrieval, expansion: false,
|
||||
...(sourceId ? { sourceId } : {}),
|
||||
});
|
||||
return results.map(r => r.slug);
|
||||
};
|
||||
const t0 = Date.now();
|
||||
const off = await runRetrievalQuality(questions, mk(false));
|
||||
const tMid = Date.now();
|
||||
const on = await runRetrievalQuality(questions, mk(true));
|
||||
const tEnd = Date.now();
|
||||
const fam = (r: typeof off, f: string) => r.families.find(x => x.family === f);
|
||||
const rel = { off: fam(off, 'graph-relationship'), on: fam(on, 'graph-relationship') };
|
||||
const payload = {
|
||||
schema_version: 1 as const,
|
||||
ab: 'relational',
|
||||
graph_relationship: {
|
||||
n: rel.on?.n ?? 0,
|
||||
recall_at_10: { off: rel.off?.recall_at_10 ?? 0, on: rel.on?.recall_at_10 ?? 0,
|
||||
delta: (rel.on?.recall_at_10 ?? 0) - (rel.off?.recall_at_10 ?? 0) },
|
||||
hit_at_3: { off: rel.off?.hit_at_3 ?? 0, on: rel.on?.hit_at_3 ?? 0 },
|
||||
},
|
||||
latency_ms: { off_total: tMid - t0, on_total: tEnd - tMid },
|
||||
families: { off: off.families, on: on.families },
|
||||
};
|
||||
if (json) {
|
||||
console.log(JSON.stringify(payload, null, 2));
|
||||
} else {
|
||||
console.log(`Relational A/B — graph-relationship n=${payload.graph_relationship.n}`);
|
||||
const g = payload.graph_relationship;
|
||||
console.log(` recall@10: off=${(g.recall_at_10.off * 100).toFixed(0)}% on=${(g.recall_at_10.on * 100).toFixed(0)}% Δ=+${(g.recall_at_10.delta * 100).toFixed(0)}pp`);
|
||||
console.log(` Hit@3: off=${(g.hit_at_3.off * 100).toFixed(0)}% on=${(g.hit_at_3.on * 100).toFixed(0)}%`);
|
||||
console.log(` latency: off=${payload.latency_ms.off_total}ms on=${payload.latency_ms.on_total}ms (arm adds ${payload.latency_ms.on_total - payload.latency_ms.off_total}ms over ${payload.graph_relationship.n} queries)`);
|
||||
}
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
const report = await runRetrievalQuality(questions, searchFn);
|
||||
const gate = evaluateGate(report);
|
||||
|
||||
|
||||
@@ -35,10 +35,9 @@
|
||||
* `listPages({type, sourceId, limit: PAGE_LIST_BATCH})` so worst
|
||||
* case is BATCH × 25MB per batch (currently 10 × 25MB = 250MB
|
||||
* bounded). Per-page body cap drops oversize before parsing.
|
||||
* - Body read prefers frontmatter.raw_transcript when present, then
|
||||
* falls back to compiled_truth + timeline. Meeting pages often
|
||||
* store the real turn-by-turn transcript in a sidecar file while
|
||||
* compiled_truth is just the human summary.
|
||||
* - Body read covers compiled_truth + timeline. parseMarkdown splits
|
||||
* conversation imports across both columns; reading only
|
||||
* compiled_truth silently drops half on iMessage/Slack imports.
|
||||
* - Page-global row_num accumulator. facts table unique index is
|
||||
* (source_id, source_markdown_slug, row_num); per-segment row_num
|
||||
* would collide on segment 2. Per-page counter increments across
|
||||
@@ -71,7 +70,7 @@ import {
|
||||
extractFactsFromTurn,
|
||||
isFactsExtractionEnabled,
|
||||
} from '../core/facts/extract.ts';
|
||||
import { configureGatewayIfUninitialized, isAvailable, withBudgetTracker } from '../core/ai/gateway.ts';
|
||||
import { isAvailable, withBudgetTracker } from '../core/ai/gateway.ts';
|
||||
import { BudgetTracker, BudgetExhausted } from '../core/budget/budget-tracker.ts';
|
||||
import { listSources } from '../core/sources-ops.ts';
|
||||
import {
|
||||
@@ -81,6 +80,7 @@ import {
|
||||
} from '../core/op-checkpoint.ts';
|
||||
import { createProgress } from '../core/progress.ts';
|
||||
import { getCliOptions, cliOptsToProgressOptions, maybeBackground } from '../core/cli-options.ts';
|
||||
import { loadConfig } from '../core/config.ts';
|
||||
import { createHash } from 'crypto';
|
||||
// v0.41.15.0 (T5): worker-pool primitive + per-source-clamp wrapper +
|
||||
// per-page advisory lock + delete-orphans-first replay safety. See plan
|
||||
@@ -140,14 +140,7 @@ export const DEFAULT_MAX_COST_USD = 5.0;
|
||||
* `--types` flag is an explicit per-run override; cycle config is
|
||||
* the single source of truth.
|
||||
*/
|
||||
export const ALLOWED_TYPES = [
|
||||
'conversation',
|
||||
'meeting',
|
||||
'slack',
|
||||
'email',
|
||||
'imessage',
|
||||
'imessage-daily',
|
||||
] as const;
|
||||
export const ALLOWED_TYPES = ['conversation', 'meeting', 'slack', 'email'] as const;
|
||||
export type AllowedType = (typeof ALLOWED_TYPES)[number];
|
||||
|
||||
/**
|
||||
@@ -293,7 +286,6 @@ import {
|
||||
parseConversation,
|
||||
type ParseConversationOpts as OrchestratorParseOpts,
|
||||
} from '../core/conversation-parser/parse.ts';
|
||||
import { readConversationBodyForParsing } from '../core/conversation-parser/body.ts';
|
||||
|
||||
/**
|
||||
* v0.41.13.0 — back-compat shape for direct callers + the existing
|
||||
@@ -482,6 +474,16 @@ function pageBodyBytes(page: Page): number {
|
||||
return Buffer.byteLength(compiled, 'utf8') + Buffer.byteLength(timeline, 'utf8');
|
||||
}
|
||||
|
||||
function readPageBody(page: Page): string {
|
||||
// F1: read BOTH compiled_truth AND timeline; iMessage importers
|
||||
// place chronological message stream in timeline.
|
||||
const compiled = page.compiled_truth ?? '';
|
||||
const timeline = page.timeline ?? '';
|
||||
if (!compiled) return timeline;
|
||||
if (!timeline) return compiled;
|
||||
return `${compiled}\n\n${timeline}`;
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Types config resolver (Eng-v2 A2 — unified single source of truth).
|
||||
// ---------------------------------------------------------------------------
|
||||
@@ -680,7 +682,7 @@ async function processPage(
|
||||
return { newEndIso: null };
|
||||
}
|
||||
|
||||
const body = await readConversationBodyForParsing(state.engine, page);
|
||||
const body = readPageBody(page);
|
||||
// v0.41.13.0: thread the full Page through the orchestrator so D8
|
||||
// date-derivation chain (frontmatter.date > effective_date >
|
||||
// '1970-01-01') AND timezone_policy warnings apply. The historical
|
||||
@@ -763,12 +765,6 @@ async function processPage(
|
||||
source_markdown_slug: page.slug,
|
||||
source: PER_SEGMENT_SOURCE_PREFIX,
|
||||
source_session: sessionId,
|
||||
// Preserve the conversation's valid time instead of defaulting every
|
||||
// extracted fact to extraction time. Epoch-anchored parses have no
|
||||
// trustworthy date, so they retain the existing now() fallback.
|
||||
...(seg.startIso && !seg.startIso.startsWith('1970-')
|
||||
? { valid_from: new Date(seg.startIso) }
|
||||
: {}),
|
||||
context:
|
||||
fact.context ?? `from ${page.slug} segment ${seg.startIso}..${seg.endIso}`,
|
||||
}));
|
||||
@@ -1081,8 +1077,7 @@ export async function runExtractConversationFactsCore(
|
||||
}
|
||||
// Fall through to receipt+rollup write so the partial run is
|
||||
// still observable in extract_health doctor + extracts/ pages.
|
||||
// ...but not under --dry-run: a preview must not persist cache state.
|
||||
if (!dryRun) await writeRunReceiptAndRollup(engine, sourceId, result, /* halted */ true);
|
||||
await writeRunReceiptAndRollup(engine, sourceId, result, /* halted */ true);
|
||||
// Return partial result — caller (CLI / Minion) decides how to
|
||||
// surface. NOT a thrown failure.
|
||||
return result;
|
||||
@@ -1094,9 +1089,7 @@ export async function runExtractConversationFactsCore(
|
||||
// (queryable + citable per D-EXTRACT-17/19) AND UPSERTs the per-day
|
||||
// rollup row (best-effort cache per F-OUT-19). Both are best-effort —
|
||||
// failures stderr-warn but never fail the parent operation.
|
||||
// --dry-run must not persist cache/knowledge state: skip the rollup UPSERT +
|
||||
// receipt-page write so a preview leaves no extract cache row behind.
|
||||
if (!dryRun) await writeRunReceiptAndRollup(engine, sourceId, result, /* halted */ false);
|
||||
await writeRunReceiptAndRollup(engine, sourceId, result, /* halted */ false);
|
||||
|
||||
return result;
|
||||
}
|
||||
@@ -1366,9 +1359,7 @@ export async function runExtractConversationFacts(
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Chat gateway is required for non-dry-run. Recover a cold singleton before
|
||||
// reporting an availability error (#2590).
|
||||
if (!parsed.dryRun && !isAvailable('chat')) configureGatewayIfUninitialized();
|
||||
// Chat gateway is required for non-dry-run.
|
||||
if (!parsed.dryRun && !isAvailable('chat')) {
|
||||
console.error('Chat gateway unavailable. Configure an Anthropic or compatible chat model, or pass --dry-run to preview segmentation.');
|
||||
process.exit(1);
|
||||
|
||||
+8
-110
@@ -29,7 +29,6 @@
|
||||
*/
|
||||
|
||||
import { readFileSync, readdirSync, lstatSync, existsSync } from 'fs';
|
||||
import { setCliExitVerdict } from '../core/cli-force-exit.ts';
|
||||
import { join, relative, dirname } from 'path';
|
||||
import type { BrainEngine, LinkBatchInput, TimelineBatchInput } from '../core/engine.ts';
|
||||
import type { PageType } from '../core/types.ts';
|
||||
@@ -61,7 +60,6 @@ import { createHash } from 'crypto';
|
||||
// v0.41.15.0 (T7, D9): --workers N for the fs-walk inner loops via the
|
||||
// shared sliding-pool helper + PGLite-clamp wrapper.
|
||||
import { runSlidingPool } from '../core/worker-pool.ts';
|
||||
import { isAborted } from '../core/abort-check.ts';
|
||||
import { parseWorkers, resolveWorkersWithClamp } from '../core/sync-concurrency.ts';
|
||||
|
||||
// Batch size for addLinksBatch / addTimelineEntriesBatch.
|
||||
@@ -188,7 +186,7 @@ export function walkMarkdownFiles(dir: string): { path: string; relPath: string
|
||||
// Pre-fix, this walker had only an ad-hoc dot-prefix exclusion and didn't
|
||||
// call isSyncable at all — so it descended into `node_modules/`, emitted
|
||||
// markdown files from there, AND ignored the canonical exclusion list
|
||||
// (`.raw/`, README.md, etc.). Now: pruneDir skips entire vendor
|
||||
// (`.raw/`, `ops/`, README.md, etc.). Now: pruneDir skips entire vendor
|
||||
// subtrees before recursion (saving IO), and isSyncable filters the emit
|
||||
// set against the canonical markdown-strategy rules.
|
||||
const files: { path: string; relPath: string }[] = [];
|
||||
@@ -494,38 +492,6 @@ export function extractTimelineFromContent(content: string, slug: string): Extra
|
||||
entries.push({ slug, date: match[1], source: 'markdown', summary: match[2].trim(), detail: detail || undefined });
|
||||
}
|
||||
|
||||
// Format 3: Inline citation — [Source: <source>, YYYY-MM-DD]
|
||||
//
|
||||
// This is the citation convention gbrain's own quality rules require on
|
||||
// every brain write (skills/conventions/quality.md), so dated evidence is
|
||||
// pervasive in curated pages — but until now the extractor could not see
|
||||
// it, and a page whose dates all live in citations scored zero timeline
|
||||
// coverage. The entry's summary is the sentence the citation annotates
|
||||
// (the surrounding line with citation markers stripped).
|
||||
//
|
||||
// Lines already captured by Format 1 are skipped: a timeline bullet often
|
||||
// carries its own [Source: ...] citation, and re-extracting it would file
|
||||
// a duplicate entry under a different (source, summary) shape that the
|
||||
// DB-level uniqueness cannot collapse.
|
||||
const citationPattern = /\[Source:\s*([^\]]+?),\s*(\d{4}-\d{2}-\d{2})\s*\]/g;
|
||||
const bulletLinePattern = /^-\s+\*\*\d{4}-\d{2}-\d{2}\*\*\s*\|/;
|
||||
for (const line of content.split(/\r?\n/)) {
|
||||
if (bulletLinePattern.test(line)) continue;
|
||||
const lineMatches = [...line.matchAll(citationPattern)];
|
||||
if (lineMatches.length === 0) continue;
|
||||
// Strip every citation marker from the line to leave the annotated text.
|
||||
const summary = line
|
||||
.replace(/\[Source:[^\]]*\]/g, '')
|
||||
.replace(/^[-*>#\s]+/, '')
|
||||
.replace(/\s+/g, ' ')
|
||||
.trim()
|
||||
.slice(0, 300);
|
||||
if (!summary) continue; // a bare citation with no surrounding text is not an event
|
||||
for (const m of lineMatches) {
|
||||
entries.push({ slug, date: m[2], source: m[1].trim().slice(0, 200), summary });
|
||||
}
|
||||
}
|
||||
|
||||
return entries;
|
||||
}
|
||||
|
||||
@@ -560,28 +526,6 @@ export interface ExtractOpts {
|
||||
* own pagination and stay serial in v0.41.15.0.
|
||||
*/
|
||||
workers?: number;
|
||||
/**
|
||||
* #1972: cooperative-abort signal. Forwarded into the sliding pool (which
|
||||
* propagates it to every worker) and checked at the top of each onItem, so a
|
||||
* cancelled cycle's extract (incremental OR full-walk) relinquishes its
|
||||
* worker slot well under the 30s force-evict. Honored by the cycle-reachable
|
||||
* paths: extractForSlugs, extractLinksFromDir, extractTimelineFromDir.
|
||||
*/
|
||||
signal?: AbortSignal;
|
||||
/**
|
||||
* Brain source id to stamp on extracted fs-walk rows (#1747 / #1503).
|
||||
*
|
||||
* The fs-walk extractors build LinkBatchInput / TimelineBatchInput rows
|
||||
* with no source_id, so addLinksBatch / addTimelineEntriesBatch map
|
||||
* missing → literal 'default'. On a brain whose content lives in a
|
||||
* non-'default' source (e.g. 'wiki'), the batch INSERT's
|
||||
* `JOIN pages ON (slug, source_id='default')` drops EVERY row → 0
|
||||
* inserted, no error (the "created 0 from N pages" silent no-op).
|
||||
* Threading the resolved source id here stamps from/to/origin_source_id
|
||||
* so the JOIN matches. When undefined, rows fall back to 'default' as
|
||||
* before (single-'default'-source brains unaffected).
|
||||
*/
|
||||
sourceId?: string;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -620,7 +564,7 @@ export async function runExtractCore(engine: BrainEngine, opts: ExtractOpts): Pr
|
||||
// Nothing changed — skip entirely.
|
||||
return result;
|
||||
}
|
||||
const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers, opts.signal, opts.sourceId);
|
||||
const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers);
|
||||
result.links_created = r.links_created;
|
||||
result.timeline_entries_created = r.timeline_created;
|
||||
result.pages_processed = r.pages;
|
||||
@@ -629,12 +573,12 @@ export async function runExtractCore(engine: BrainEngine, opts: ExtractOpts): Pr
|
||||
|
||||
// Full walk path: CLI `gbrain extract` or first-run.
|
||||
if (opts.mode === 'links' || opts.mode === 'all') {
|
||||
const r = await extractLinksFromDir(engine, opts.dir, dryRun, jsonMode, workers, opts.signal, opts.sourceId);
|
||||
const r = await extractLinksFromDir(engine, opts.dir, dryRun, jsonMode, workers);
|
||||
result.links_created = r.created;
|
||||
result.pages_processed = r.pages;
|
||||
}
|
||||
if (opts.mode === 'timeline' || opts.mode === 'all') {
|
||||
const r = await extractTimelineFromDir(engine, opts.dir, dryRun, jsonMode, workers, opts.signal, opts.sourceId);
|
||||
const r = await extractTimelineFromDir(engine, opts.dir, dryRun, jsonMode, workers);
|
||||
result.timeline_entries_created = r.created;
|
||||
result.pages_processed = Math.max(result.pages_processed, r.pages);
|
||||
}
|
||||
@@ -902,17 +846,6 @@ Status (v0.42):
|
||||
if (!jsonMode) {
|
||||
console.log(`Timeline from meetings: ${r.entries_created} entries on ${r.entities_touched} entity pages from ${r.meetings_scanned} meetings`);
|
||||
}
|
||||
// #2057 (codex): batch failures are no longer swallowed silently — make
|
||||
// them visible at the command surface (and non-zero exit) instead of
|
||||
// printing a clean "N entries" success over failed inserts.
|
||||
if (r.batch_errors > 0) {
|
||||
console.error(
|
||||
`[extract timeline] ${r.batch_errors} batch(es) failed to insert` +
|
||||
(r.first_batch_error ? ` (first error: ${r.first_batch_error})` : '') +
|
||||
` — timeline is incomplete.`,
|
||||
);
|
||||
setCliExitVerdict(1);
|
||||
}
|
||||
} else if (byMention || ner) {
|
||||
// v0.41.18.0 (T7): combined --by-mention + --ner walk shares one
|
||||
// gazetteer; saves an entire pass on big brains. When only one
|
||||
@@ -955,21 +888,11 @@ Status (v0.42):
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// #1747: resolve the brain source id and thread it into the fs-walk
|
||||
// extractors so batch rows carry from/to_source_id. Without this they
|
||||
// default to 'default' and addLinksBatch's JOIN drops every row on a
|
||||
// non-'default' brain → silent "created 0 from N pages". Resolution
|
||||
// honors --source-id, then GBRAIN_SOURCE / .gbrain-source /
|
||||
// registered-path / sole-non-default, mirroring the source-aware
|
||||
// inline hooks (extractLinksForSlugs) that #1204 confirmed correct.
|
||||
const { resolveSourceId } = await import('../core/source-resolver.ts');
|
||||
const resolvedSourceId = await resolveSourceId(engine, sourceIdFilter, brainDir);
|
||||
result = await runExtractCore(engine, {
|
||||
mode: subcommand as 'links' | 'timeline' | 'all',
|
||||
dir: brainDir,
|
||||
dryRun,
|
||||
jsonMode,
|
||||
sourceId: resolvedSourceId,
|
||||
workers,
|
||||
});
|
||||
}
|
||||
@@ -1008,9 +931,6 @@ async function extractForSlugs(
|
||||
// shared flush primitive; JS single-threaded event loop makes the
|
||||
// shared counter increments atomic.
|
||||
workers: number = 1,
|
||||
signal?: AbortSignal,
|
||||
// #1747/#1503: stamp resolved brain source id on batch rows (see ExtractOpts.sourceId).
|
||||
sourceId?: string,
|
||||
): Promise<{ links_created: number; timeline_created: number; pages: number }> {
|
||||
// Build the full slug set for link resolution (fast: just readdir, no file reads)
|
||||
const allFiles = walkMarkdownFiles(brainDir);
|
||||
@@ -1072,12 +992,8 @@ async function extractForSlugs(
|
||||
await runSlidingPool({
|
||||
items: slugs,
|
||||
workers,
|
||||
signal,
|
||||
failureLabel: (slug) => slug,
|
||||
onItem: async (slug) => {
|
||||
// #1972: bail before doing any work for this slug on abort. Trailing
|
||||
// flushLinks/flushTimeline still commit accumulated rows — no torn write.
|
||||
if (isAborted(signal)) return;
|
||||
const relPath = slug + '.md';
|
||||
const fullPath = join(brainDir, relPath);
|
||||
try {
|
||||
@@ -1091,9 +1007,7 @@ async function extractForSlugs(
|
||||
if (!jsonMode) console.log(` ${link.from_slug} → ${link.to_slug} (${link.link_type})`);
|
||||
linksCreated++;
|
||||
} else {
|
||||
linkBatch.push(sourceId
|
||||
? { ...link, from_source_id: sourceId, to_source_id: sourceId, origin_source_id: sourceId }
|
||||
: link);
|
||||
linkBatch.push(link);
|
||||
if (linkBatch.length >= BATCH_SIZE) await flushLinks();
|
||||
}
|
||||
}
|
||||
@@ -1106,7 +1020,7 @@ async function extractForSlugs(
|
||||
if (!jsonMode) console.log(` ${entry.slug}: ${entry.date} — ${entry.summary}`);
|
||||
timelineCreated++;
|
||||
} else {
|
||||
timelineBatch.push({ slug: entry.slug, date: entry.date, source: entry.source, summary: entry.summary, detail: entry.detail, ...(sourceId ? { source_id: sourceId } : {}) });
|
||||
timelineBatch.push({ slug: entry.slug, date: entry.date, source: entry.source, summary: entry.summary, detail: entry.detail });
|
||||
if (timelineBatch.length >= BATCH_SIZE) await flushTimeline();
|
||||
}
|
||||
}
|
||||
@@ -1134,10 +1048,6 @@ async function extractLinksFromDir(
|
||||
engine: BrainEngine, brainDir: string, dryRun: boolean, jsonMode: boolean,
|
||||
// v0.41.15.0 (T7): in-process worker count. Default 1.
|
||||
workers: number = 1,
|
||||
signal?: AbortSignal,
|
||||
// #1747/#1503: stamp resolved brain source id on batch rows so the
|
||||
// addLinksBatch JOIN matches non-'default' source pages.
|
||||
sourceId?: string,
|
||||
): Promise<{ created: number; pages: number }> {
|
||||
const files = walkMarkdownFiles(brainDir);
|
||||
const allSlugs = new Set(files.map(f => pathToSlug(f.relPath)));
|
||||
@@ -1178,11 +1088,8 @@ async function extractLinksFromDir(
|
||||
await runSlidingPool({
|
||||
items: files,
|
||||
workers,
|
||||
signal,
|
||||
failureLabel: (f) => f.relPath,
|
||||
onItem: async (file) => {
|
||||
// #1972: bail before this file on abort; trailing flush() commits the batch.
|
||||
if (isAborted(signal)) return;
|
||||
try {
|
||||
const content = readFileSync(file.path, 'utf-8');
|
||||
const links = await extractLinksFromFile(content, file.relPath, allSlugs, { globalBasename });
|
||||
@@ -1194,9 +1101,7 @@ async function extractLinksFromDir(
|
||||
if (!jsonMode) console.log(` ${link.from_slug} → ${link.to_slug} (${link.link_type})`);
|
||||
created++;
|
||||
} else {
|
||||
batch.push(sourceId
|
||||
? { ...link, from_source_id: sourceId, to_source_id: sourceId, origin_source_id: sourceId }
|
||||
: link);
|
||||
batch.push(link);
|
||||
if (batch.length >= BATCH_SIZE) await flush();
|
||||
}
|
||||
}
|
||||
@@ -1218,10 +1123,6 @@ async function extractTimelineFromDir(
|
||||
engine: BrainEngine, brainDir: string, dryRun: boolean, jsonMode: boolean,
|
||||
// v0.41.15.0 (T7): in-process worker count. Default 1.
|
||||
workers: number = 1,
|
||||
signal?: AbortSignal,
|
||||
// #1747/#1503: stamp resolved brain source id so addTimelineEntriesBatch
|
||||
// matches non-'default' source pages.
|
||||
sourceId?: string,
|
||||
): Promise<{ created: number; pages: number }> {
|
||||
const files = walkMarkdownFiles(brainDir);
|
||||
|
||||
@@ -1252,11 +1153,8 @@ async function extractTimelineFromDir(
|
||||
await runSlidingPool({
|
||||
items: files,
|
||||
workers,
|
||||
signal,
|
||||
failureLabel: (f) => f.relPath,
|
||||
onItem: async (file) => {
|
||||
// #1972: bail before this file on abort; trailing flush() commits the batch.
|
||||
if (isAborted(signal)) return;
|
||||
try {
|
||||
const content = readFileSync(file.path, 'utf-8');
|
||||
const slug = pathToSlug(file.relPath);
|
||||
@@ -1268,7 +1166,7 @@ async function extractTimelineFromDir(
|
||||
if (!jsonMode) console.log(` ${entry.slug}: ${entry.date} — ${entry.summary}`);
|
||||
created++;
|
||||
} else {
|
||||
batch.push({ slug: entry.slug, date: entry.date, source: entry.source, summary: entry.summary, detail: entry.detail, ...(sourceId ? { source_id: sourceId } : {}) });
|
||||
batch.push({ slug: entry.slug, date: entry.date, source: entry.source, summary: entry.summary, detail: entry.detail });
|
||||
if (batch.length >= BATCH_SIZE) await flush();
|
||||
}
|
||||
}
|
||||
|
||||
@@ -116,7 +116,8 @@ async function listFiles(engine: BrainEngine, slug?: string) {
|
||||
|
||||
console.log(`${rows.length} file(s):`);
|
||||
for (const row of rows) {
|
||||
const size = row.size_bytes ? `${Math.round(Number(row.size_bytes) / 1024)}KB` : '?';
|
||||
const sizeBytes = row.size_bytes as number | null;
|
||||
const size = sizeBytes ? `${Math.round(sizeBytes / 1024)}KB` : '?';
|
||||
console.log(` ${row.page_slug || '(unlinked)'} / ${row.filename} [${size}, ${row.mime_type || '?'}]`);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -39,7 +39,7 @@ if ! command -v gbrain >/dev/null 2>&1; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
staged=$(git diff --cached --name-only --diff-filter=ACM | grep -E '\\.mdx?$' || true)
|
||||
staged=$(git diff --cached --name-only --diff-filter=ACM | grep -E '\\\\.mdx?$' || true)
|
||||
[ -z "$staged" ] && exit 0
|
||||
|
||||
failed=0
|
||||
|
||||
@@ -16,7 +16,6 @@
|
||||
*/
|
||||
|
||||
import { readFileSync, writeFileSync, existsSync, lstatSync, readdirSync } from 'fs';
|
||||
import { setCliExitVerdict } from '../core/cli-force-exit.ts';
|
||||
import { join, relative, resolve } from 'path';
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { loadConfig, toEngineConfig } from '../core/config.ts';
|
||||
@@ -30,7 +29,6 @@ import {
|
||||
type AuditReport,
|
||||
type AuditFix,
|
||||
} from '../core/brain-writer.ts';
|
||||
import { collectGitVisibleFiles } from '../core/git-visible-files.ts';
|
||||
import { isSyncable, pruneDir, slugifyPath } from '../core/sync.ts';
|
||||
|
||||
export async function runFrontmatter(args: string[]): Promise<void> {
|
||||
@@ -65,7 +63,7 @@ export async function runFrontmatter(args: string[]): Promise<void> {
|
||||
}
|
||||
console.error(`Unknown frontmatter subcommand: ${sub}\n`);
|
||||
printHelp();
|
||||
setCliExitVerdict(1);
|
||||
process.exitCode = 1;
|
||||
}
|
||||
|
||||
async function connectEngineForAudit(): Promise<BrainEngine> {
|
||||
@@ -166,14 +164,14 @@ async function runValidate(rest: string[]): Promise<void> {
|
||||
}
|
||||
if (!target) {
|
||||
console.error('error: gbrain frontmatter validate requires a <path> argument');
|
||||
setCliExitVerdict(1);
|
||||
process.exitCode = 1;
|
||||
return;
|
||||
}
|
||||
|
||||
const resolved = resolve(target);
|
||||
if (!existsSync(resolved)) {
|
||||
console.error(`error: path not found: ${target}`);
|
||||
setCliExitVerdict(1);
|
||||
process.exitCode = 1;
|
||||
return;
|
||||
}
|
||||
|
||||
@@ -244,7 +242,7 @@ async function runValidate(rest: string[]): Promise<void> {
|
||||
}
|
||||
}
|
||||
|
||||
setCliExitVerdict(totalErrors > 0 && !flags.fix ? 1 : 0);
|
||||
process.exitCode = totalErrors > 0 && !flags.fix ? 1 : 0;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -273,13 +271,6 @@ export function collectFiles(
|
||||
if (st.isFile()) {
|
||||
return [target];
|
||||
}
|
||||
|
||||
const gitFiles = collectGitVisibleFiles(target, (rel) => isSyncable(rel, { strategy: 'markdown' }));
|
||||
if (gitFiles) {
|
||||
if (visitDir) visitDir(target);
|
||||
return gitFiles;
|
||||
}
|
||||
|
||||
const out: string[] = [];
|
||||
const stack = [target];
|
||||
if (visitDir) visitDir(target);
|
||||
@@ -387,7 +378,7 @@ async function runGenerate(args: string[]): Promise<void> {
|
||||
if (!targetPath) {
|
||||
console.error('error: gbrain frontmatter generate requires a <path> argument');
|
||||
console.error('usage: gbrain frontmatter generate <path> [--fix] [--dry-run] [--json]');
|
||||
setCliExitVerdict(1);
|
||||
process.exitCode = 1;
|
||||
return;
|
||||
}
|
||||
|
||||
|
||||
+13
-159
@@ -11,9 +11,6 @@ import {
|
||||
isCodeFilePath,
|
||||
isMarkdownFilePath,
|
||||
isImageFilePath as isImageFilePathFromSync,
|
||||
matchesAnyGlob,
|
||||
pruneDir,
|
||||
SYNC_SKIP_FILES,
|
||||
type SyncStrategy,
|
||||
} from '../core/sync.ts';
|
||||
import { sortNewestFirst } from '../core/sort-newest-first.ts';
|
||||
@@ -21,7 +18,6 @@ import {
|
||||
loadCheckpoint,
|
||||
saveCheckpoint,
|
||||
clearCheckpoint,
|
||||
resolveImportTargetDir,
|
||||
resumeFilter,
|
||||
} from '../core/import-checkpoint.ts';
|
||||
|
||||
@@ -48,25 +44,7 @@ export interface RunImportResult {
|
||||
export async function runImport(
|
||||
engine: BrainEngine,
|
||||
args: string[],
|
||||
opts: {
|
||||
commit?: string;
|
||||
strategy?: SyncStrategy;
|
||||
sourceId?: string;
|
||||
managedBookmark?: boolean;
|
||||
/**
|
||||
* #753/#774: glob patterns to exclude from the import (same semantics as
|
||||
* `isSyncable`'s `exclude` — matched against the dir-relative path).
|
||||
* Threaded by performFullSync for `gbrain sync --exclude`.
|
||||
*/
|
||||
exclude?: string[];
|
||||
/**
|
||||
* #753/#774 monorepo subdir-source support: when set, slugs and
|
||||
* `source_path` are computed relative to this root (the git repo root)
|
||||
* instead of `dir` (the sync scope), so `wiki/page1.md` lands as slug
|
||||
* `wiki/page1` consistently across full and incremental sync.
|
||||
*/
|
||||
slugRoot?: string;
|
||||
} = {},
|
||||
opts: { commit?: string; strategy?: SyncStrategy; sourceId?: string; managedBookmark?: boolean } = {},
|
||||
): Promise<RunImportResult> {
|
||||
const noEmbed = args.includes('--no-embed');
|
||||
const fresh = args.includes('--fresh');
|
||||
@@ -188,19 +166,7 @@ export async function runImport(
|
||||
console.error('Usage: gbrain import <dir> [--no-embed] [--workers N] [--fresh] [--source-id <id>] [--json]');
|
||||
process.exit(1);
|
||||
}
|
||||
// #1728: capture the import target ONCE as an absolute real path. Every
|
||||
// downstream consumer of `dir` (collection, checkpoint load/save, resume
|
||||
// filtering) sees the same canonical identity — never the caller's `.`/
|
||||
// relative spelling, which would make the persisted checkpoint `dir`
|
||||
// resolve against whatever CWD a later process happens to run from.
|
||||
let dir: string;
|
||||
try {
|
||||
dir = resolveImportTargetDir(dirArg);
|
||||
} catch (e) {
|
||||
const msg = e instanceof Error ? e.message : String(e);
|
||||
console.error(`Import target is not readable: ${dirArg} (${msg})`);
|
||||
process.exit(1);
|
||||
}
|
||||
const dir: string = dirArg; // narrowed; survives closure capture
|
||||
|
||||
// v0.31.2: collect under the right strategy. Pre-fix this called
|
||||
// collectMarkdownFiles unconditionally — code-strategy first sync
|
||||
@@ -209,30 +175,13 @@ export async function runImport(
|
||||
const strategy: SyncStrategy = opts.strategy ?? 'markdown';
|
||||
const _walkT0 = Date.now();
|
||||
console.error(`[gbrain phase] import.collect_files start dir=${dir} strategy=${strategy}`);
|
||||
let allFiles = collectSyncableFiles(dir, { strategy });
|
||||
const allFiles = collectSyncableFiles(dir, { strategy });
|
||||
console.error(
|
||||
`[gbrain phase] import.collect_files done ${Date.now() - _walkT0}ms files=${allFiles.length}`,
|
||||
);
|
||||
const fileTypeLabel = strategy === 'code' ? 'code'
|
||||
: strategy === 'auto' ? 'syncable' : 'markdown';
|
||||
// #753/#774: apply --exclude glob patterns (threaded by performFullSync).
|
||||
if (opts.exclude && opts.exclude.length > 0) {
|
||||
const beforeExclude = allFiles.length;
|
||||
allFiles = allFiles.filter(abs => !matchesAnyGlob(relative(dir, abs), opts.exclude));
|
||||
console.log(
|
||||
`Found ${allFiles.length} ${fileTypeLabel} files ` +
|
||||
`(${beforeExclude - allFiles.length} excluded by --exclude patterns)`,
|
||||
);
|
||||
// NAV-4: everything excluded is almost always a mistyped pattern — warn.
|
||||
if (beforeExclude > 0 && allFiles.length === 0) {
|
||||
console.warn(
|
||||
`[gbrain sync] No files matched after applying ${opts.exclude.length} --exclude pattern(s). ` +
|
||||
`Check your --exclude flags. Patterns: ${JSON.stringify(opts.exclude)}`,
|
||||
);
|
||||
}
|
||||
} else {
|
||||
console.log(`Found ${allFiles.length} ${fileTypeLabel} files`);
|
||||
}
|
||||
console.log(`Found ${allFiles.length} ${fileTypeLabel} files`);
|
||||
|
||||
// Sort newest-first so date-prefixed brain paths get embedded before older ones.
|
||||
// See src/core/sort-newest-first.ts for the policy.
|
||||
@@ -278,11 +227,6 @@ export async function runImport(
|
||||
|
||||
async function processFile(eng: BrainEngine, filePath: string) {
|
||||
const relativePath = relative(dir, filePath);
|
||||
// #753/#774: slug + source_path base. When performFullSync syncs a
|
||||
// monorepo subdir, slugRoot is the git root so slugs stay git-root-
|
||||
// relative (matching the incremental path's git-diff paths). The
|
||||
// checkpoint (`completed`) stays dir-relative — resumeFilter's contract.
|
||||
const importRelPath = opts.slugRoot ? relative(opts.slugRoot, filePath) : relativePath;
|
||||
// v0.31.2 (D5): per-file slow-path log. Fires only when a single
|
||||
// file takes >5s. The user's hang surfaces as one file taking
|
||||
// forever — without this, the agent can't see which file.
|
||||
@@ -293,8 +237,8 @@ export async function runImport(
|
||||
// up images when GBRAIN_EMBEDDING_MULTIMODAL=true so this branch is
|
||||
// unreachable when the gate is off; defense-in-depth check anyway.
|
||||
const result = isImageFilePath(relativePath) && process.env.GBRAIN_EMBEDDING_MULTIMODAL === 'true'
|
||||
? await importImageFile(eng, filePath, importRelPath, { noEmbed, sourceId })
|
||||
: await importFile(eng, filePath, importRelPath, { noEmbed, sourceId, activePack: importActivePack });
|
||||
? await importImageFile(eng, filePath, relativePath, { noEmbed, sourceId })
|
||||
: await importFile(eng, filePath, relativePath, { noEmbed, sourceId, activePack: importActivePack });
|
||||
const _fileMs = Date.now() - _fileT0;
|
||||
if (_fileMs > 5000) {
|
||||
console.error(`[gbrain phase] import.process_file slow ${_fileMs}ms ${relativePath}`);
|
||||
@@ -310,9 +254,7 @@ export async function runImport(
|
||||
if (result.error && result.error !== 'unchanged') {
|
||||
console.error(` Skipped ${relativePath}: ${result.error}`);
|
||||
// Bug 9 — non-"unchanged" skips carry a real error reason.
|
||||
// #774: ledger paths use the slug base so an incremental sync's
|
||||
// success at the same (git-root-relative) path clears the row.
|
||||
failures.push({ path: importRelPath, error: result.error });
|
||||
failures.push({ path: relativePath, error: result.error });
|
||||
} else {
|
||||
// 'unchanged' or no-error skip: content_hash matched a prior
|
||||
// successful import, so this file IS done for checkpoint purposes.
|
||||
@@ -330,7 +272,7 @@ export async function runImport(
|
||||
}
|
||||
errors++;
|
||||
skipped++;
|
||||
failures.push({ path: importRelPath, error: msg });
|
||||
failures.push({ path: relativePath, error: msg });
|
||||
}
|
||||
processed++;
|
||||
tickProgress();
|
||||
@@ -344,9 +286,6 @@ export async function runImport(
|
||||
catch { /* non-fatal */ }
|
||||
}
|
||||
saveCheckpoint(checkpointPath, {
|
||||
schema_version: 1,
|
||||
owner: 'gbrain',
|
||||
kind: 'import',
|
||||
dir,
|
||||
completedPaths: Array.from(completed),
|
||||
timestamp: new Date().toISOString(),
|
||||
@@ -553,39 +492,12 @@ interface CollectOpts {
|
||||
* The first-sync walker historically admitted them on markdown too when
|
||||
* `GBRAIN_EMBEDDING_MULTIMODAL=true`. Codex (C5) flagged the contradiction
|
||||
* — preserve the walker semantic explicitly.
|
||||
*
|
||||
* Closes #345: exclude `SYNC_SKIP_FILES` metafiles
|
||||
* (`README.md` / `index.md` / `log.md` / `schema.md` / `RESOLVER.md`).
|
||||
* Incremental `sync` skips these via `isSyncable`, but the bulk-import
|
||||
* walker only filtered by extension — so a directory import imported every
|
||||
* directory README as a page, titled by its folder ("People", "Companies",
|
||||
* …). Those index-titled pages then trigram-corrupt fuzzy entity resolution
|
||||
* (any `people/X` slug matches the "People" page) and inflate orphan count.
|
||||
* Funnel both admission paths through the same metafile exclusion so import
|
||||
* and sync agree on what is a page.
|
||||
*/
|
||||
function isCollectibleForWalker(
|
||||
path: string,
|
||||
strategy: SyncStrategy,
|
||||
multimodalOn: boolean,
|
||||
): boolean {
|
||||
// #2607: apply the SAME segment-level prune gate as incremental sync's
|
||||
// `classifySync` (core/sync.ts). The FS walk below prunes at descent time,
|
||||
// but the git fast path enumerates via `git ls-files` and historically
|
||||
// filtered only by extension — so `sync --full` imported (and resurrected
|
||||
// previously-deleted) pages under dot-dirs / vendored trees that incremental
|
||||
// sync excludes. Full and incremental must agree on the exclusion set.
|
||||
// (In the FS-walk route `path` is a basename, so this is the same dot-file
|
||||
// check pruneDir already applied there — no behavior change on that route.)
|
||||
const segments = path.split('/');
|
||||
if (segments.some((seg) => !pruneDir(seg))) return false;
|
||||
|
||||
// Metafiles are directory scaffolding (READMEs / index / log / schema /
|
||||
// resolver), not typed brain pages — same exclusion `sync`'s `isSyncable`
|
||||
// applies. Guards both the FS-walk and the git-fast-path collection routes.
|
||||
const basename = segments[segments.length - 1] || '';
|
||||
if ((SYNC_SKIP_FILES as readonly string[]).includes(basename)) return false;
|
||||
|
||||
switch (strategy) {
|
||||
case 'code':
|
||||
return isCodeFilePath(path);
|
||||
@@ -600,51 +512,6 @@ function isCollectibleForWalker(
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Git-aware fast path for `collectSyncableFiles`. Returns the strategy-filtered
|
||||
* list of syncable files when `dir` is inside a git work tree (paths absolute,
|
||||
* sorted), or `null` when `dir` is not a git repo / git is unavailable — in
|
||||
* which case the caller falls back to the recursive FS walk.
|
||||
*
|
||||
* Honors `.gitignore` (the whole point): `git ls-files --cached --others
|
||||
* --exclude-standard` lists tracked + untracked-not-ignored files, so vendored
|
||||
* / build / generated trees never reach the importer. `-z` (NUL-delimited)
|
||||
* survives paths with spaces/newlines. Each path is lstat-checked to preserve
|
||||
* the walker's no-symlink policy and to drop submodule gitlinks (which surface
|
||||
* as a single non-regular entry).
|
||||
*/
|
||||
function gitListSyncableFiles(
|
||||
dir: string,
|
||||
strategy: SyncStrategy,
|
||||
multimodalOn: boolean,
|
||||
): string[] | null {
|
||||
let stdout: string;
|
||||
try {
|
||||
stdout = execFileSync(
|
||||
'git',
|
||||
['-C', dir, 'ls-files', '--cached', '--others', '--exclude-standard', '-z'],
|
||||
{ encoding: 'utf8', maxBuffer: 512 * 1024 * 1024, stdio: ['ignore', 'pipe', 'ignore'] },
|
||||
);
|
||||
} catch {
|
||||
return null; // not a git work tree, or git not on PATH → FS-walk fallback
|
||||
}
|
||||
const files: string[] = [];
|
||||
for (const rel of stdout.split('\0')) {
|
||||
if (!rel) continue;
|
||||
if (!isCollectibleForWalker(rel, strategy, multimodalOn)) continue;
|
||||
const full = join(dir, rel);
|
||||
let st;
|
||||
try {
|
||||
st = lstatSync(full);
|
||||
} catch {
|
||||
continue; // ls-files raced a deletion, or unreadable
|
||||
}
|
||||
if (st.isSymbolicLink() || !st.isFile()) continue;
|
||||
files.push(full);
|
||||
}
|
||||
return files.sort();
|
||||
}
|
||||
|
||||
/**
|
||||
* v0.31.2 (codex C4 + C5 + C8): unified walker with five hardenings:
|
||||
*
|
||||
@@ -665,19 +532,6 @@ function gitListSyncableFiles(
|
||||
export function collectSyncableFiles(dir: string, opts: CollectOpts = {}): string[] {
|
||||
const strategy: SyncStrategy = opts.strategy ?? 'markdown';
|
||||
const multimodalOn = process.env.GBRAIN_EMBEDDING_MULTIMODAL === 'true';
|
||||
|
||||
// v0.42.x (#1159 --respect-gitignore / #1483 .gbrainignore): when `dir` is a
|
||||
// git work tree, enumerate via `git ls-files` so the walk honors
|
||||
// `.gitignore`. Pre-fix the recursive FS walk below descended into every
|
||||
// git-ignored tree — `vendor/` (PHP Composer), `storage/`, `public/build/`,
|
||||
// etc. — so a Laravel/PHP repo's `--strategy code` sync tried to import ~50k
|
||||
// dependency/build files (and bloated DB + embedding cost on any repo with
|
||||
// vendored data/fixtures). `--cached --others --exclude-standard` = tracked
|
||||
// PLUS untracked-not-ignored, so uncommitted source is still indexed. Non-git
|
||||
// dirs (or git unavailable) fall through to the FS walk below.
|
||||
const gitFiles = gitListSyncableFiles(dir, strategy, multimodalOn);
|
||||
if (gitFiles) return gitFiles;
|
||||
|
||||
const maxDepth = resolveMaxWalkDepth();
|
||||
const visitedInodes = new Map<string, true>();
|
||||
const files: string[] = [];
|
||||
@@ -694,11 +548,11 @@ export function collectSyncableFiles(dir: string, opts: CollectOpts = {}): strin
|
||||
return;
|
||||
}
|
||||
for (const entry of entries) {
|
||||
// Descent-time prune through the canonical gate (single source of truth
|
||||
// in core/sync.ts) instead of a hand-maintained inline list that drifted
|
||||
// from it. Skips hidden dirs (`.git`, `.raw`, etc.), `node_modules`,
|
||||
// `vendor`, `dist`, `build`, `venv` (#2020), `ops`, and git submodules.
|
||||
if (!pruneDir(entry, d)) continue;
|
||||
// Skip hidden dirs (.git, .claude, .raw, etc.) and `node_modules`/`ops`.
|
||||
// Same set the legacy walkers honored, surfaced once at the top of
|
||||
// every iteration.
|
||||
if (entry.startsWith('.')) continue;
|
||||
if (entry === 'node_modules' || entry === 'ops') continue;
|
||||
|
||||
const full = join(d, entry);
|
||||
let stat;
|
||||
|
||||
+2
-12
@@ -6,7 +6,7 @@ import { homedir } from 'os';
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = dirname(__filename);
|
||||
import { saveConfig, loadConfig, loadConfigFileOnly, toEngineConfig, gbrainPath, configPath, isThinClient, effectiveEnvDatabaseUrl, type GBrainConfig } from '../core/config.ts';
|
||||
import { saveConfig, loadConfig, loadConfigFileOnly, toEngineConfig, gbrainPath, configPath, isThinClient, type GBrainConfig } from '../core/config.ts';
|
||||
import { createEngine } from '../core/engine-factory.ts';
|
||||
import { discoverOAuth, mintClientCredentialsToken, smokeTestMcp } from '../core/remote-mcp-probe.ts';
|
||||
import { runInitEmbedCheck } from '../core/init-embed-check.ts';
|
||||
@@ -133,11 +133,7 @@ export async function runInit(args: string[]) {
|
||||
if (manualUrl) {
|
||||
databaseUrl = manualUrl;
|
||||
} else if (isNonInteractive) {
|
||||
// effectiveEnvDatabaseUrl applies the #427 guard: a DATABASE_URL that Bun
|
||||
// auto-loaded from a .env in cwd must not seed a brain config — that is
|
||||
// the "init inside a web-app checkout writes the app's DB into
|
||||
// ~/.gbrain/config.json" failure mode.
|
||||
const envUrl = effectiveEnvDatabaseUrl();
|
||||
const envUrl = process.env.GBRAIN_DATABASE_URL || process.env.DATABASE_URL;
|
||||
if (envUrl) {
|
||||
databaseUrl = envUrl;
|
||||
} else {
|
||||
@@ -1456,12 +1452,6 @@ export function reportModStatus(): void {
|
||||
}
|
||||
console.log('Resolver: skills/RESOLVER.md');
|
||||
console.log('Soul audit: run `gbrain soul-audit` to customize agent identity');
|
||||
// Retrieval Reflex (#1981): the deterministic pointer layer is ON by default
|
||||
// (no action needed). The policy skill is installed into the HOST repo on
|
||||
// request — we PRINT the command rather than silently mutating the host repo.
|
||||
console.log('Retrieval reflex: on by default (entity pointers injected per turn)');
|
||||
console.log(' Install the policy skill into your agent repo:');
|
||||
console.log(' gbrain integrations install retrieval-reflex --target <host-repo>');
|
||||
console.log('');
|
||||
}
|
||||
|
||||
|
||||
@@ -1438,15 +1438,9 @@ export async function installRecipeIntoHostRepo(
|
||||
} catch { /* not present */ }
|
||||
}
|
||||
if (resolverPath) {
|
||||
// Fence the appended rows by the RECIPE id, not a hardcoded recipe name.
|
||||
// The pre-v0.42 fence was literally `gbrain:agent-voice:resolver-rows`,
|
||||
// so any second copy-into-host-repo recipe (e.g. retrieval-reflex) wrote
|
||||
// an agent-voice-labeled block — and `--refresh`/uninstall keyed on the
|
||||
// recipe id would never find it. Derive the fence from manifest.recipe.
|
||||
const fenceId = manifest.recipe || 'gbrain';
|
||||
const rowsBlock = `\n\n<!-- gbrain:${fenceId}:resolver-rows -->\n` +
|
||||
const rowsBlock = `\n\n<!-- gbrain:agent-voice:resolver-rows -->\n` +
|
||||
manifest.resolver_rows_to_append.map((r) => `- ${r}`).join('\n') +
|
||||
`\n<!-- /gbrain:${fenceId}:resolver-rows -->\n`;
|
||||
'\n<!-- /gbrain:agent-voice:resolver-rows -->\n';
|
||||
fsAppendFileSync(resolverPath, rowsBlock);
|
||||
} else {
|
||||
console.warn(
|
||||
|
||||
+25
-266
@@ -7,8 +7,7 @@ import type { BrainEngine } from '../core/engine.ts';
|
||||
import { MinionQueue } from '../core/minions/queue.ts';
|
||||
import { MinionWorker } from '../core/minions/worker.ts';
|
||||
import { WORKER_EXIT_RSS_WATCHDOG } from '../core/minions/worker-exit-codes.ts';
|
||||
import type { MinionHandler, MinionJob, MinionJobStatus } from '../core/minions/types.ts';
|
||||
import type { PaceKeyOverrides } from '../core/pace-mode.ts';
|
||||
import type { MinionJob, MinionJobStatus } from '../core/minions/types.ts';
|
||||
import { loadConfig, isThinClient } from '../core/config.ts';
|
||||
import { callRemoteTool, unpackToolResult } from '../core/mcp-client.ts';
|
||||
import { parseNiceValue, applyNiceness, getEffectiveNiceness, formatNice } from '../core/minions/niceness.ts';
|
||||
@@ -22,49 +21,6 @@ function hasFlag(args: string[], flag: string): boolean {
|
||||
return args.includes(flag);
|
||||
}
|
||||
|
||||
/**
|
||||
* Long-lived workers outlive operator config changes. Re-stamp the AI gateway
|
||||
* from DB-backed model config immediately before queued jobs enter gateway-backed
|
||||
* paths, so a stale process-level default cannot route new work to the wrong
|
||||
* provider.
|
||||
*/
|
||||
async function refreshGatewayForJob(engine: BrainEngine): Promise<void> {
|
||||
const { reconfigureGatewayWithEngine } = await import('../core/ai/gateway.ts');
|
||||
await reconfigureGatewayWithEngine(engine);
|
||||
}
|
||||
|
||||
const GATEWAY_REFRESH_JOB_NAMES = new Set([
|
||||
'embed',
|
||||
'extract-conversation-facts',
|
||||
'enrich',
|
||||
'contextual_reindex_per_chunk',
|
||||
'autopilot-cycle',
|
||||
'synthesize',
|
||||
'patterns',
|
||||
'consolidate',
|
||||
'extract_facts',
|
||||
'extract-atoms-drain',
|
||||
'embed-backfill',
|
||||
'extract-takes-from-pages',
|
||||
'embed-catch-up',
|
||||
]);
|
||||
|
||||
function registerBuiltinJob(
|
||||
worker: MinionWorker,
|
||||
engine: BrainEngine,
|
||||
name: string,
|
||||
handler: MinionHandler,
|
||||
): void {
|
||||
if (!GATEWAY_REFRESH_JOB_NAMES.has(name)) {
|
||||
worker.register(name, handler);
|
||||
return;
|
||||
}
|
||||
worker.register(name, async (job) => {
|
||||
await refreshGatewayForJob(engine);
|
||||
return await handler(job);
|
||||
});
|
||||
}
|
||||
|
||||
/** Parse `--max-waiting N` from CLI args. Returns undefined if absent.
|
||||
* Throws on malformed input (caller should surface the error and exit).
|
||||
* Clamps to [1, 100] to match the queue-layer clamp in MinionQueue.add.
|
||||
@@ -175,23 +131,9 @@ function formatJobDetail(job: MinionJob): string {
|
||||
return lines.join('\n');
|
||||
}
|
||||
|
||||
export async function runJobs(engineOrNull: BrainEngine | null, args: string[]): Promise<void> {
|
||||
export async function runJobs(engine: BrainEngine, args: string[]): Promise<void> {
|
||||
const sub = args[0];
|
||||
|
||||
// Thin-client dispatch (cli.ts) passes engine=null for the subcommands
|
||||
// with remote MCP routing (`list`, `get`) so no scratch local engine is
|
||||
// ever built. Any other subcommand arriving with a null engine is a
|
||||
// routing bug upstream of this function — refuse instead of crashing
|
||||
// inside MinionQueue.
|
||||
if (!engineOrNull && sub !== 'list' && sub !== 'get') {
|
||||
console.error(`\`gbrain jobs ${sub ?? ''}\` needs a local engine and cannot run on a thin client.`);
|
||||
process.exit(1);
|
||||
}
|
||||
// Null only ever reaches the MCP-routed `list`/`get` branches, which
|
||||
// never touch the engine — narrowed once here so the host-only cases
|
||||
// below typecheck unchanged.
|
||||
const engine = engineOrNull as BrainEngine;
|
||||
|
||||
if (!sub || sub === '--help' || sub === '-h') {
|
||||
console.log(`gbrain jobs — Minions job queue
|
||||
|
||||
@@ -274,8 +216,6 @@ HANDLER TYPES (built in)
|
||||
return;
|
||||
}
|
||||
|
||||
// The constructor just stores the reference; on the null (thin-client
|
||||
// list/get) paths no queue method is ever reached.
|
||||
const queue = new MinionQueue(engine);
|
||||
|
||||
switch (sub) {
|
||||
@@ -1079,38 +1019,10 @@ HANDLER TYPES (built in)
|
||||
|
||||
const pidStatus = readSupervisorPid(pidFile);
|
||||
const supervisorPid = pidStatus.pid;
|
||||
const pidfileRunning = pidStatus.running;
|
||||
const running = pidStatus.running;
|
||||
|
||||
const events = readSupervisorEvents({ sinceMs: 24 * 60 * 60 * 1000 });
|
||||
const lastStart = events.filter(e => e.event === 'started').pop()?.ts ?? null;
|
||||
|
||||
// issue #2227 fix #1/#3: the pidfile is HOME-derived, so a supervisor
|
||||
// started under a different $HOME (keeper=/root vs ops=/data) reads as
|
||||
// "not running" here even when it is healthy — the false signal that
|
||||
// makes an operator spawn a duplicate. Fall back to the queue-scoped DB
|
||||
// singleton lock (#1849), the HOME-independent authority. PID-reuse-safe:
|
||||
// isLockHolderLive keys on lock freshness, never process.kill.
|
||||
const supQueue = parseFlag(args, '--queue') ?? 'default';
|
||||
let detectedViaDbLock = false;
|
||||
let dbLockHolder: { holder_pid: number; holder_host: string } | null = null;
|
||||
if (!pidfileRunning) {
|
||||
try {
|
||||
const { inspectLock, isLockHolderLive } = await import('../core/db-lock.ts');
|
||||
const { supervisorLockId, SUPERVISOR_LOCK_TTL_MIN } = await import('../core/minions/supervisor.ts');
|
||||
const snap = await inspectLock(engine, supervisorLockId(supQueue));
|
||||
if (snap && isLockHolderLive(snap, SUPERVISOR_LOCK_TTL_MIN)) {
|
||||
detectedViaDbLock = true;
|
||||
dbLockHolder = { holder_pid: snap.holder_pid, holder_host: snap.holder_host };
|
||||
}
|
||||
} catch {
|
||||
// Pre-migration brains / transient DB errors: fall back to pidfile-only.
|
||||
}
|
||||
}
|
||||
const running = pidfileRunning || detectedViaDbLock;
|
||||
// Surface the supervisor's recorded config from the latest `started`
|
||||
// event (concurrency + effective --max-rss) so split-$HOME deployments
|
||||
// see what the live-but-pidfile-invisible supervisor is running.
|
||||
const startedEvt = events.filter(e => e.event === 'started').pop() ?? null;
|
||||
// Shared classifier — same code path runs in `gbrain doctor` so the
|
||||
// two surfaces cannot drift on what counts as a crash. Supersedes
|
||||
// v0.35.4.0's binary `classifyWorkerExit({code})` on this surface;
|
||||
@@ -1125,20 +1037,15 @@ HANDLER TYPES (built in)
|
||||
nice_requested: w.nice_requested,
|
||||
nice: w.nice_now,
|
||||
}));
|
||||
const supervisorNice = pidfileRunning && supervisorPid !== null
|
||||
const supervisorNice = running && supervisorPid !== null
|
||||
? getEffectiveNiceness(supervisorPid)
|
||||
: null;
|
||||
|
||||
const status = {
|
||||
running,
|
||||
detected_via: detectedViaDbLock ? 'db_lock' : (pidfileRunning ? 'pidfile' : null),
|
||||
supervisor_pid: supervisorPid ?? dbLockHolder?.holder_pid ?? null,
|
||||
db_lock_holder: dbLockHolder,
|
||||
supervisor_pid: supervisorPid,
|
||||
pid_file: pidFile,
|
||||
queue: supQueue,
|
||||
last_start: lastStart,
|
||||
concurrency: typeof startedEvt?.concurrency === 'number' ? startedEvt.concurrency : null,
|
||||
max_rss_mb: typeof startedEvt?.max_rss_mb === 'number' ? startedEvt.max_rss_mb : null,
|
||||
crashes_24h: summary.total,
|
||||
clean_exits_24h: summary.clean_exits,
|
||||
crashes_by_cause: summary.by_cause,
|
||||
@@ -1150,11 +1057,9 @@ HANDLER TYPES (built in)
|
||||
if (jsonMode) {
|
||||
console.log(JSON.stringify(status, null, 2));
|
||||
} else {
|
||||
const via = detectedViaDbLock ? ' (detected via DB lock; pidfile not found at the configured path)' : '';
|
||||
console.log(`Supervisor: ${running ? 'running' : 'not running'}${via}`);
|
||||
if (status.supervisor_pid) console.log(` PID: ${status.supervisor_pid}${detectedViaDbLock ? ` @ ${dbLockHolder?.holder_host}` : ''}`);
|
||||
console.log(`Supervisor: ${running ? 'running' : 'not running'}`);
|
||||
if (supervisorPid) console.log(` PID: ${supervisorPid}`);
|
||||
console.log(` PID file: ${pidFile}`);
|
||||
if (detectedViaDbLock && status.concurrency !== null) console.log(` Concurrency: ${status.concurrency}${status.max_rss_mb !== null ? ` (max-rss ${status.max_rss_mb}MB)` : ''}`);
|
||||
if (lastStart) console.log(` Last start: ${lastStart}`);
|
||||
console.log(` Crashes (24h): ${summary.total} (runtime=${summary.by_cause.runtime_error} oom=${summary.by_cause.oom_or_external_kill} unknown=${summary.by_cause.unknown} legacy=${summary.by_cause.legacy})`);
|
||||
console.log(` Clean exits (24h): ${summary.clean_exits}`);
|
||||
@@ -1482,7 +1387,7 @@ export async function registerBuiltinHandlers(
|
||||
return { ...result, embed_job_id: embedJobId, embed_skip_reason: embedSkipReason };
|
||||
});
|
||||
|
||||
registerBuiltinJob(worker, engine, 'embed', async (job) => {
|
||||
worker.register('embed', async (job) => {
|
||||
const { runEmbedCore } = await import('./embed.ts');
|
||||
// Primary Minion progress channel is job.updateProgress (DB-backed,
|
||||
// readable via `gbrain jobs get <id>`). Stderr from the worker daemon
|
||||
@@ -1493,18 +1398,6 @@ export async function registerBuiltinHandlers(
|
||||
slugs: Array.isArray(job.data.slugs) ? (job.data.slugs as string[]) : undefined,
|
||||
all: !!job.data.all,
|
||||
stale: job.data.all ? false : (job.data.stale !== false),
|
||||
sourceId: typeof job.data.sourceId === 'string' ? job.data.sourceId : undefined,
|
||||
// CX1+CX5: pace overrides ride in the job payload as explicit overrides
|
||||
// only; runEmbedCore re-resolves env > config > bundle at execution so
|
||||
// GBRAIN_PACE_* still wins during an incident.
|
||||
...(job.data.pace && typeof job.data.pace === 'object'
|
||||
? {
|
||||
pace: job.data.pace as { perCallMode?: string; perCall?: PaceKeyOverrides },
|
||||
// Serialized from the queued payload → config tier so GBRAIN_PACE_*
|
||||
// on the worker still wins at execution (Codex P2 escape hatch).
|
||||
paceFromBackground: true,
|
||||
}
|
||||
: {}),
|
||||
onProgress: (done, total, embedded) => {
|
||||
// Fire-and-forget: progress updates are best-effort and must not
|
||||
// block the worker loop.
|
||||
@@ -1529,7 +1422,7 @@ export async function registerBuiltinHandlers(
|
||||
// BudgetTracker inside its own process. BudgetExhausted is caught at
|
||||
// the core level and returned as `result.budget_exhausted: true` (NOT
|
||||
// a job failure) so the user can resume with a higher cap.
|
||||
registerBuiltinJob(worker, engine, 'extract-conversation-facts', async (job) => {
|
||||
worker.register('extract-conversation-facts', async (job) => {
|
||||
const { runExtractConversationFactsCore } = await import('./extract-conversation-facts.ts');
|
||||
const sourceId = typeof job.data.sourceId === 'string' ? job.data.sourceId : undefined;
|
||||
if (!sourceId) {
|
||||
@@ -1540,7 +1433,7 @@ export async function registerBuiltinHandlers(
|
||||
}
|
||||
const types = Array.isArray(job.data.types)
|
||||
? (job.data.types as string[]).filter((t) =>
|
||||
['conversation', 'meeting', 'slack', 'email', 'imessage', 'imessage-daily'].includes(t),
|
||||
['conversation', 'meeting', 'slack', 'email'].includes(t),
|
||||
)
|
||||
: undefined;
|
||||
const result = await runExtractConversationFactsCore(engine, {
|
||||
@@ -1563,32 +1456,13 @@ export async function registerBuiltinHandlers(
|
||||
return result;
|
||||
});
|
||||
|
||||
// v0.42.x (#2390) — Life Chronicle event extraction. NOT protected (bounded
|
||||
// LLM spend per page; no shell). Enqueued by the put_page chronicle backstop
|
||||
// and by `gbrain chronicle backfill`. Idempotent (content-addressed event
|
||||
// slugs + projection upsert), so a retry re-runs to the same state.
|
||||
worker.register('chronicle_extract', async (job) => {
|
||||
const slug = typeof job.data.slug === 'string' ? job.data.slug : undefined;
|
||||
if (!slug) throw new Error('chronicle_extract job requires data.slug');
|
||||
const sourceId = typeof job.data.sourceId === 'string' ? job.data.sourceId : undefined;
|
||||
const { runChronicleExtract } = await import('../core/chronicle/extract-events.ts');
|
||||
const { chronicleTz } = await import('../core/chronicle/config.ts');
|
||||
const tz = await chronicleTz(engine);
|
||||
return await runChronicleExtract(engine, {
|
||||
slug,
|
||||
sourceId,
|
||||
tz,
|
||||
signal: (job as { signal?: AbortSignal }).signal,
|
||||
});
|
||||
});
|
||||
|
||||
// v0.41.39 (#1700) — enrich. NOT in PROTECTED_JOB_NAMES: per-call cost is
|
||||
// bounded by data.maxCostUsd (default DEFAULT_MAX_COST_USD) and the handler
|
||||
// re-creates the BudgetTracker in its own process. BudgetExhausted is caught
|
||||
// at the core level and returned as result.budget_exhausted (NOT a failure).
|
||||
// Strict per-source: the CLI fans out one job per source when --source is
|
||||
// omitted, so a job ALWAYS carries data.sourceId.
|
||||
registerBuiltinJob(worker, engine, 'enrich', async (job) => {
|
||||
worker.register('enrich', async (job) => {
|
||||
const { runEnrichCore } = await import('./enrich.ts');
|
||||
const sourceId = typeof job.data.sourceId === 'string' ? job.data.sourceId : undefined;
|
||||
if (!sourceId) {
|
||||
@@ -1671,43 +1545,6 @@ export async function registerBuiltinHandlers(
|
||||
return await runBacklinksCore({ action, dir, dryRun: !!job.data.dryRun });
|
||||
});
|
||||
|
||||
// Local patch 2026-06-11: durable facts:absorb. One-shot CLI processes
|
||||
// (capture/put/sync) can't finish the extraction chat before their exit
|
||||
// drain aborts it, so backstop.ts submits this job instead and the
|
||||
// long-lived worker does the LLM work here. Inline mode: errors throw,
|
||||
// so minion retry/backoff handles transient gateway failures and real
|
||||
// failures stay visible in `gbrain jobs list --status failed`.
|
||||
worker.register('facts-absorb', async (job) => {
|
||||
const slug = typeof job.data.slug === 'string' ? job.data.slug : '';
|
||||
if (!slug) throw new Error('facts-absorb job requires data.slug');
|
||||
const sourceId = typeof job.data.sourceId === 'string' ? job.data.sourceId : 'default';
|
||||
const page = await engine.getPage(slug, { sourceId });
|
||||
if (!page) return { skipped: 'page_missing', slug, sourceId };
|
||||
const { runFactsBackstop } = await import('../core/facts/backstop.ts');
|
||||
const KNOWN_SOURCES = ['sync:import', 'mcp:put_page', 'mcp:extract_facts', 'file_upload', 'code_import'] as const;
|
||||
const source = (KNOWN_SOURCES as readonly string[]).includes(job.data.source as string)
|
||||
? (job.data.source as typeof KNOWN_SOURCES[number])
|
||||
: 'mcp:put_page';
|
||||
return await runFactsBackstop(
|
||||
{
|
||||
slug: page.slug,
|
||||
type: page.type,
|
||||
compiled_truth: page.compiled_truth,
|
||||
frontmatter: (page.frontmatter ?? {}) as Record<string, unknown>,
|
||||
},
|
||||
{
|
||||
engine,
|
||||
sourceId,
|
||||
sessionId: typeof job.data.sessionId === 'string' ? job.data.sessionId : null,
|
||||
source,
|
||||
mode: 'inline',
|
||||
notabilityFilter: job.data.notabilityFilter === 'high-only' ? 'high-only' : 'all',
|
||||
visibility: job.data.visibility === 'world' ? 'world' : 'private',
|
||||
...(typeof job.data.model === 'string' && job.data.model ? { model: job.data.model } : {}),
|
||||
},
|
||||
);
|
||||
});
|
||||
|
||||
// Autopilot-cycle handler: delegates to runCycle. Shares the exact same
|
||||
// phase set and ordering as `gbrain dream` and autopilot's inline path —
|
||||
// one source of truth for what the brain does overnight.
|
||||
@@ -1728,13 +1565,13 @@ export async function registerBuiltinHandlers(
|
||||
const { makeContextualReindexHandler } = await import(
|
||||
'../core/minions/handlers/contextual-reindex-per-chunk.ts'
|
||||
);
|
||||
registerBuiltinJob(worker, engine, 'contextual_reindex_per_chunk', makeContextualReindexHandler({ engine }));
|
||||
worker.register('contextual_reindex_per_chunk', makeContextualReindexHandler({ engine }));
|
||||
}
|
||||
|
||||
// derivation); the handler returns { partial, status, report } so
|
||||
// `gbrain jobs get <id>` shows the full structured report. Does NOT
|
||||
// throw on partial: a flaky phase must not block every future cycle.
|
||||
registerBuiltinJob(worker, engine, 'autopilot-cycle', async (job) => {
|
||||
worker.register('autopilot-cycle', async (job) => {
|
||||
const { runCycle } = await import('../core/cycle.ts');
|
||||
// v0.41.30 (T2): fall back to null (NOT cwd '.') when no repo is configured.
|
||||
// The queued cycle is the same primitive `gbrain dream` uses; a checkout-less
|
||||
@@ -1757,13 +1594,6 @@ export async function registerBuiltinHandlers(
|
||||
// archived between fan-out and worker claim, skip cleanly.
|
||||
const rawSourceId = job.data.source_id;
|
||||
let sourceId: string | undefined;
|
||||
// issue #2227/#2194 (TODOS:634, codex #8): a per-source cycle must run its
|
||||
// FILESYSTEM phases (sync/lint/extract) against the SOURCE's own checkout,
|
||||
// not the global brain's. Pre-fix it inherited `repoPath` (the default
|
||||
// checkout) while writing DB freshness for `source_id` — mixed scope that
|
||||
// made cooldown/freshness attribute to the wrong source. We resolve the
|
||||
// source's `local_path` here and use it as the cycle's brainDir below.
|
||||
let sourceLocalPath: string | null = null;
|
||||
if (rawSourceId !== undefined && rawSourceId !== null) {
|
||||
if (typeof rawSourceId !== 'string') {
|
||||
throw new Error(`autopilot-cycle: invalid source_id (not a string): ${JSON.stringify(rawSourceId)}`);
|
||||
@@ -1777,10 +1607,9 @@ export async function registerBuiltinHandlers(
|
||||
}
|
||||
// Archive recheck (codex r1 P1-5): cheap pre-cycle lookup. Returns
|
||||
// immediately if source is gone or archived; runCycle never even
|
||||
// acquires a lock. Also fetches local_path so FS phases bind to the
|
||||
// source's own checkout (the #2227/#2194 mixed-scope fix).
|
||||
const rows = await engine.executeRaw<{ archived: boolean | null; local_path: string | null }>(
|
||||
`SELECT archived, local_path FROM sources WHERE id = $1`,
|
||||
// acquires a lock.
|
||||
const rows = await engine.executeRaw<{ archived: boolean | null }>(
|
||||
`SELECT archived FROM sources WHERE id = $1`,
|
||||
[rawSourceId],
|
||||
);
|
||||
if (rows.length === 0) {
|
||||
@@ -1798,17 +1627,8 @@ export async function registerBuiltinHandlers(
|
||||
};
|
||||
}
|
||||
sourceId = rawSourceId;
|
||||
sourceLocalPath = typeof rows[0].local_path === 'string' && rows[0].local_path.length > 0
|
||||
? rows[0].local_path
|
||||
: null;
|
||||
}
|
||||
|
||||
// Effective checkout for FS phases. For a per-source cycle, bind to the
|
||||
// SOURCE's local_path (or null → skip FS phases for a pure-DB source);
|
||||
// NEVER fall through to the global repoPath, which would run sync/lint
|
||||
// against the wrong tree. Legacy (no source_id) keeps the global repoPath.
|
||||
const effectiveBrainDir: string | null = sourceId ? sourceLocalPath : repoPath;
|
||||
|
||||
// Allow callers to select phases via job data (e.g. skip embed for
|
||||
// fast cycles). Validates against ALL_PHASES to prevent injection.
|
||||
const { ALL_PHASES } = await import('../core/cycle.ts');
|
||||
@@ -1820,26 +1640,10 @@ export async function registerBuiltinHandlers(
|
||||
// Pull default: legacy `true` for back-compat; explicit boolean wins.
|
||||
const pull = typeof job.data.pull === 'boolean' ? job.data.pull : true;
|
||||
|
||||
// #2194 fix #2 / codex #5 (D4): claim-time cooldown guard. A job already
|
||||
// queued or retrying (max_attempts:2) can reach the worker after the
|
||||
// dispatch gate decided to back this source off. Skip it here as a NO-OP
|
||||
// (status 'skipped', NOT a failure — a failure would re-arm the cooldown).
|
||||
if (sourceId) {
|
||||
const { isSourceInCooldown } = await import('./autopilot-fanout.ts');
|
||||
if (await isSourceInCooldown(engine, sourceId)) {
|
||||
return {
|
||||
partial: false,
|
||||
status: 'skipped',
|
||||
report: { reason: 'source_in_cooldown', source_id: sourceId },
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
const report = await runCycle(engine, {
|
||||
brainDir: effectiveBrainDir,
|
||||
brainDir: repoPath,
|
||||
pull,
|
||||
signal: job.signal, // propagate abort so cycle bails on timeout/cancel
|
||||
deadlineAtMs: job.deadlineAtMs, // #2781: phases budget sub-work from remaining time
|
||||
...(sourceId ? { sourceId } : {}),
|
||||
...(requestedPhases && requestedPhases.length > 0 ? { phases: requestedPhases as any } : {}),
|
||||
yieldBetweenPhases: async () => {
|
||||
@@ -1855,50 +1659,6 @@ export async function registerBuiltinHandlers(
|
||||
};
|
||||
});
|
||||
|
||||
// #2194 fix #3 / #2227 bug #3 — brain-wide maintenance. Runs the `global`
|
||||
// cycle phases (embed, orphans, purge, resolve_symbol_edges, grade_takes,
|
||||
// calibration_profile, synthesize_concepts, skillopt) ONCE per window instead
|
||||
// of N times concurrently across per-source cycles (the 4→10GB RSS blowout).
|
||||
// No source_id → uses the legacy global cycle lock; stamps autopilot.last_global_at
|
||||
// on success so the dispatch gate backs off.
|
||||
worker.register('autopilot-global-maintenance', async (job) => {
|
||||
const { runCycle, GLOBAL_PHASES, LAST_GLOBAL_AT_KEY, ALL_PHASES } = await import('../core/cycle.ts');
|
||||
const repoPath: string | null = typeof job.data.repoPath === 'string'
|
||||
? job.data.repoPath
|
||||
: (await engine.getConfig('sync.repo_path')) ?? null;
|
||||
|
||||
const validPhases = new Set(ALL_PHASES);
|
||||
const requested = Array.isArray(job.data.phases)
|
||||
? (job.data.phases as string[]).filter((p) => validPhases.has(p as never))
|
||||
: GLOBAL_PHASES;
|
||||
const phases = (requested.length > 0 ? requested : GLOBAL_PHASES) as typeof GLOBAL_PHASES;
|
||||
|
||||
const report = await runCycle(engine, {
|
||||
brainDir: repoPath,
|
||||
pull: false, // brain-wide DB/maintenance work never git-pulls
|
||||
signal: job.signal,
|
||||
deadlineAtMs: job.deadlineAtMs, // #2781: phases budget sub-work from remaining time
|
||||
phases,
|
||||
yieldBetweenPhases: async () => { await new Promise<void>((r) => setImmediate(r)); },
|
||||
});
|
||||
|
||||
// Stamp last_global_at only on a non-failed run so a failed pass stays stale
|
||||
// and re-dispatches next tick (self-healing retry).
|
||||
if (report.status === 'ok' || report.status === 'clean' || report.status === 'partial') {
|
||||
try {
|
||||
await engine.setConfig(LAST_GLOBAL_AT_KEY, new Date().toISOString());
|
||||
} catch (e) {
|
||||
console.warn(`[autopilot-global-maintenance] failed to stamp last_global_at: ${e instanceof Error ? e.message : String(e)}`);
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
partial: report.status === 'partial' || report.status === 'failed',
|
||||
status: report.status,
|
||||
report,
|
||||
};
|
||||
});
|
||||
|
||||
// Shell handler is always registered. Runtime env guard lives inside the
|
||||
// handler so claimed jobs emit a clear rejection log on workers missing
|
||||
// GBRAIN_ALLOW_SHELL_JOBS=1.
|
||||
@@ -2023,18 +1783,17 @@ export async function registerBuiltinHandlers(
|
||||
brainDir: repoPath,
|
||||
phases: [phase as any],
|
||||
signal: job.signal,
|
||||
deadlineAtMs: job.deadlineAtMs, // #2781: phases budget sub-work from remaining time
|
||||
});
|
||||
return { phase, status: report.status, report };
|
||||
};
|
||||
|
||||
// PROTECTED — internally spawn subagent children
|
||||
registerBuiltinJob(worker, engine, 'synthesize', makePhaseHandler('synthesize'));
|
||||
registerBuiltinJob(worker, engine, 'patterns', makePhaseHandler('patterns'));
|
||||
registerBuiltinJob(worker, engine, 'consolidate', makePhaseHandler('consolidate'));
|
||||
worker.register('synthesize', makePhaseHandler('synthesize'));
|
||||
worker.register('patterns', makePhaseHandler('patterns'));
|
||||
worker.register('consolidate', makePhaseHandler('consolidate'));
|
||||
|
||||
// Open — DB writes only, no LLM spend
|
||||
registerBuiltinJob(worker, engine, 'extract_facts', makePhaseHandler('extract_facts'));
|
||||
worker.register('extract_facts', makePhaseHandler('extract_facts'));
|
||||
worker.register('resolve_symbol_edges', makePhaseHandler('resolve_symbol_edges'));
|
||||
worker.register('recompute_emotional_weight', makePhaseHandler('recompute_emotional_weight'));
|
||||
|
||||
@@ -2044,7 +1803,7 @@ export async function registerBuiltinHandlers(
|
||||
// window / defer behavior. On LockUnavailableError (the routine cycle holds
|
||||
// the per-source lock) the job completes `{ deferred: true }` and retries
|
||||
// next tick instead of failing — cooperative interleave (CODEX accepted).
|
||||
registerBuiltinJob(worker, engine, 'extract-atoms-drain', async (job) => {
|
||||
worker.register('extract-atoms-drain', async (job) => {
|
||||
const { runExtractAtomsDrainForSource } = await import('../core/cycle/extract-atoms-drain.ts');
|
||||
const { LockUnavailableError } = await import('../core/db-lock.ts');
|
||||
const sourceId = typeof job.data.sourceId === 'string' ? job.data.sourceId : undefined;
|
||||
@@ -2072,7 +1831,7 @@ export async function registerBuiltinHandlers(
|
||||
// Cost-bounded via D6 ($10/job BudgetTracker) + D19 (source-level cooldown
|
||||
// + 24h rolling cap, gated at submit time). NOT in PROTECTED_JOB_NAMES —
|
||||
// embedding-only spend, no API-by-the-minute risk like subagent.
|
||||
registerBuiltinJob(worker, engine, 'embed-backfill', async (job) => {
|
||||
worker.register('embed-backfill', async (job) => {
|
||||
const { makeEmbedBackfillHandler } = await import('../core/minions/handlers/embed-backfill.ts');
|
||||
return await makeEmbedBackfillHandler(engine)(job);
|
||||
});
|
||||
@@ -2093,7 +1852,7 @@ export async function registerBuiltinHandlers(
|
||||
// (LLM-bearing). Two-gate consent enforced at the handler boundary:
|
||||
// refuses to run unless takes.bootstrap_enabled config is true, even
|
||||
// when allowProtectedSubmit was set at queue.add time.
|
||||
registerBuiltinJob(worker, engine, 'extract-takes-from-pages', async (job) => {
|
||||
worker.register('extract-takes-from-pages', async (job) => {
|
||||
const { extractTakesFromPages } = await import('../core/extract-takes-from-pages.ts');
|
||||
const data = (job.data ?? {}) as { sourceId?: string; maxPages?: number };
|
||||
const bootstrapCfg = await engine.getConfig('takes.bootstrap_enabled');
|
||||
@@ -2120,7 +1879,7 @@ export async function registerBuiltinHandlers(
|
||||
// remediation pipeline. Wraps runEmbedCore with stale + catchUp + the
|
||||
// priority/batchSize the recommendation supplies. NOT in
|
||||
// PROTECTED_JOB_NAMES (embedding spend only).
|
||||
registerBuiltinJob(worker, engine, 'embed-catch-up', async (job) => {
|
||||
worker.register('embed-catch-up', async (job) => {
|
||||
const { runEmbedCore } = await import('./embed.ts');
|
||||
const data = (job.data ?? {}) as {
|
||||
sourceId?: string;
|
||||
|
||||
+1
-19
@@ -18,7 +18,6 @@
|
||||
|
||||
import { readFileSync, writeFileSync, readdirSync, statSync, lstatSync, existsSync } from 'fs';
|
||||
import { join, relative } from 'path';
|
||||
import { isAborted } from '../core/abort-check.ts';
|
||||
import { parseMarkdown, type ParseValidationCode } from '../core/markdown.ts';
|
||||
import {
|
||||
assessContentSanity,
|
||||
@@ -46,7 +45,6 @@ const FRONTMATTER_RULE_NAMES: Record<ParseValidationCode, string> = {
|
||||
SLUG_MISMATCH: 'frontmatter-slug-mismatch',
|
||||
NULL_BYTES: 'frontmatter-null-bytes',
|
||||
NESTED_QUOTES: 'frontmatter-nested-quotes',
|
||||
NON_STRING_FIELD: 'frontmatter-non-string-field',
|
||||
EMPTY_FRONTMATTER: 'frontmatter-empty',
|
||||
};
|
||||
|
||||
@@ -407,13 +405,6 @@ export interface LintOpts {
|
||||
* create + disconnect a competing module-style engine that nulls the
|
||||
* shared db singleton mid-cycle. */
|
||||
engine?: BrainEngine;
|
||||
/**
|
||||
* #1972: cooperative-abort signal. lint's per-page work is synchronous, so
|
||||
* without a periodic yield the event loop can't deliver an abort and a
|
||||
* very large lint would block past the worker's 30s force-evict. The loop
|
||||
* yields + checks this every 200 pages.
|
||||
*/
|
||||
signal?: AbortSignal;
|
||||
}
|
||||
|
||||
export interface LintResult {
|
||||
@@ -452,16 +443,7 @@ export async function runLintCore(opts: LintOpts): Promise<LintResult> {
|
||||
let totalFixed = 0;
|
||||
let pagesWithIssues = 0;
|
||||
|
||||
for (let idx = 0; idx < pages.length; idx++) {
|
||||
const page = pages[idx];
|
||||
// #1972: every 200 pages, yield to the event loop and honor abort. The
|
||||
// yield is what lets the abort signal actually fire (the rest of the loop
|
||||
// is synchronous); the break returns a valid partial LintResult since each
|
||||
// page is independently read + written.
|
||||
if (idx > 0 && idx % 200 === 0) {
|
||||
if (isAborted(opts.signal)) break;
|
||||
await new Promise<void>((resolve) => setImmediate(resolve));
|
||||
}
|
||||
for (const page of pages) {
|
||||
const content = readFileSync(page, 'utf-8');
|
||||
const issues = lintContent(content, isSingleFile ? page : relative(opts.target, page), lintOpts);
|
||||
if (issues.length === 0) continue;
|
||||
|
||||
@@ -8,12 +8,10 @@
|
||||
*/
|
||||
|
||||
import { createEngine } from '../core/engine-factory.ts';
|
||||
import { loadConfig, saveConfig, toEngineConfig, gbrainPath, effectiveEnvDatabaseUrl, type GBrainConfig } from '../core/config.ts';
|
||||
import { loadConfig, saveConfig, toEngineConfig, gbrainPath, type GBrainConfig } from '../core/config.ts';
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import type { EngineConfig } from '../core/types.ts';
|
||||
import { writeFileSync, readFileSync, existsSync, unlinkSync } from 'fs';
|
||||
import { createHash } from 'crypto';
|
||||
import { resolve } from 'path';
|
||||
import { createProgress } from '../core/progress.ts';
|
||||
import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
|
||||
|
||||
@@ -51,27 +49,12 @@ function getManifestPath(): string {
|
||||
return gbrainPath('migrate-manifest.json');
|
||||
}
|
||||
|
||||
export interface MigrateManifest {
|
||||
interface MigrateManifest {
|
||||
completed_slugs: string[];
|
||||
target_engine: string;
|
||||
target_id?: string;
|
||||
schema_version?: number;
|
||||
started_at: string;
|
||||
}
|
||||
|
||||
export function migrationTargetId(config: EngineConfig): string {
|
||||
const locator = config.engine === 'postgres'
|
||||
? config.database_url ?? ''
|
||||
: resolve(config.database_path ?? gbrainPath('brain.pglite'));
|
||||
return createHash('sha256')
|
||||
.update(JSON.stringify([config.engine, locator]))
|
||||
.digest('hex');
|
||||
}
|
||||
|
||||
export function manifestMatchesTarget(manifest: MigrateManifest, targetId: string): boolean {
|
||||
return manifest.schema_version === 2 && manifest.target_id === targetId;
|
||||
}
|
||||
|
||||
function loadManifest(): MigrateManifest | null {
|
||||
const path = getManifestPath();
|
||||
if (!existsSync(path)) return null;
|
||||
@@ -91,58 +74,6 @@ function clearManifest(): void {
|
||||
if (existsSync(path)) unlinkSync(path);
|
||||
}
|
||||
|
||||
interface MigratedSourceRow {
|
||||
id: string;
|
||||
name: string;
|
||||
local_path: string | null;
|
||||
last_commit: string | null;
|
||||
last_sync_at: Date | string | null;
|
||||
config_json: string;
|
||||
archived: boolean;
|
||||
archived_at: Date | string | null;
|
||||
archive_expires_at: Date | string | null;
|
||||
contextual_retrieval_mode: string | null;
|
||||
trust_frontmatter_overrides: boolean;
|
||||
newest_content_at: Date | string | null;
|
||||
created_at: Date | string;
|
||||
}
|
||||
|
||||
export async function copyMigrationSources(source: BrainEngine, target: BrainEngine): Promise<void> {
|
||||
const sources = await source.executeRaw<MigratedSourceRow>(`
|
||||
SELECT id, name, local_path, last_commit, last_sync_at, config::text AS config_json, archived,
|
||||
archived_at, archive_expires_at, contextual_retrieval_mode,
|
||||
trust_frontmatter_overrides, newest_content_at, created_at
|
||||
FROM sources
|
||||
ORDER BY (id = 'default') DESC, id`);
|
||||
|
||||
for (const row of sources) {
|
||||
await target.executeRaw(`
|
||||
INSERT INTO sources
|
||||
(id, name, local_path, last_commit, last_sync_at, config, archived,
|
||||
archived_at, archive_expires_at, contextual_retrieval_mode,
|
||||
trust_frontmatter_overrides, newest_content_at, created_at)
|
||||
VALUES ($1, $2, $3, $4, $5, $6::text::jsonb, $7, $8, $9, $10, $11, $12, $13)
|
||||
ON CONFLICT (id) DO UPDATE SET
|
||||
name = EXCLUDED.name,
|
||||
local_path = EXCLUDED.local_path,
|
||||
last_commit = EXCLUDED.last_commit,
|
||||
last_sync_at = EXCLUDED.last_sync_at,
|
||||
config = EXCLUDED.config,
|
||||
archived = EXCLUDED.archived,
|
||||
archived_at = EXCLUDED.archived_at,
|
||||
archive_expires_at = EXCLUDED.archive_expires_at,
|
||||
contextual_retrieval_mode = EXCLUDED.contextual_retrieval_mode,
|
||||
trust_frontmatter_overrides = EXCLUDED.trust_frontmatter_overrides,
|
||||
newest_content_at = EXCLUDED.newest_content_at,
|
||||
created_at = EXCLUDED.created_at`, [
|
||||
row.id, row.name, row.local_path, row.last_commit, row.last_sync_at,
|
||||
row.config_json, row.archived, row.archived_at, row.archive_expires_at,
|
||||
row.contextual_retrieval_mode, row.trust_frontmatter_overrides,
|
||||
row.newest_content_at, row.created_at,
|
||||
]);
|
||||
}
|
||||
}
|
||||
|
||||
export async function runMigrateEngine(sourceEngine: BrainEngine, args: string[]): Promise<void> {
|
||||
const opts = parseArgs(args);
|
||||
const config = loadConfig();
|
||||
@@ -160,8 +91,7 @@ export async function runMigrateEngine(sourceEngine: BrainEngine, args: string[]
|
||||
// Build target config
|
||||
const targetConfig: EngineConfig = { engine: opts.targetEngine };
|
||||
if (opts.targetEngine === 'postgres') {
|
||||
// #427 guard: don't let a cwd-.env DATABASE_URL become a migration target.
|
||||
targetConfig.database_url = opts.targetUrl || effectiveEnvDatabaseUrl();
|
||||
targetConfig.database_url = opts.targetUrl || process.env.GBRAIN_DATABASE_URL || process.env.DATABASE_URL;
|
||||
if (!targetConfig.database_url) {
|
||||
console.error('Target is Supabase but no connection string provided. Use: --url <connection_string>');
|
||||
process.exit(1);
|
||||
@@ -169,7 +99,6 @@ export async function runMigrateEngine(sourceEngine: BrainEngine, args: string[]
|
||||
} else {
|
||||
targetConfig.database_path = opts.targetPath || gbrainPath('brain.pglite');
|
||||
}
|
||||
const targetId = migrationTargetId(targetConfig);
|
||||
|
||||
// Connect to target
|
||||
console.log(`Connecting to target (${opts.targetEngine})...`);
|
||||
@@ -199,7 +128,7 @@ export async function runMigrateEngine(sourceEngine: BrainEngine, args: string[]
|
||||
|
||||
// Load or create manifest for resume
|
||||
let manifest = loadManifest();
|
||||
if (manifest && !manifestMatchesTarget(manifest, targetId)) {
|
||||
if (manifest && manifest.target_engine !== opts.targetEngine) {
|
||||
console.log('Previous migration was to a different target. Starting fresh.');
|
||||
manifest = null;
|
||||
}
|
||||
@@ -214,17 +143,10 @@ export async function runMigrateEngine(sourceEngine: BrainEngine, args: string[]
|
||||
manifest = {
|
||||
completed_slugs: [],
|
||||
target_engine: opts.targetEngine,
|
||||
target_id: targetId,
|
||||
schema_version: 2,
|
||||
started_at: new Date().toISOString(),
|
||||
};
|
||||
}
|
||||
|
||||
// Pages.source_id is a foreign key. Copy the complete source catalog first,
|
||||
// including archived rows and sync/routing metadata, so every page write has
|
||||
// a valid parent and the target preserves source behavior.
|
||||
await copyMigrationSources(sourceEngine, targetEngine);
|
||||
|
||||
// Get all source pages
|
||||
const sourceStats = await sourceEngine.getStats();
|
||||
const allPages = await sourceEngine.listPages({ limit: 100000 });
|
||||
|
||||
+6
-23
@@ -45,13 +45,6 @@ export async function runOnboard(engine: BrainEngine, args: string[]): Promise<v
|
||||
// No-op without a pack_upgrade_available finding.
|
||||
const explain = args.includes('--explain');
|
||||
const targetScore = parseInt10(args, '--target-score') ?? 90;
|
||||
// v0.42.42.0 (#2139): `--max-usd off`/`unlimited`/`none` → run uncapped. maxUsd
|
||||
// stays undefined, which runRemediation already treats as no ceiling (skips the
|
||||
// est-cost refusal + BudgetTracker runs uncapped); `maxUsdOff` lifts the
|
||||
// missing-cap refusal below. Spend is still ledgered.
|
||||
const maxUsdIdx = args.indexOf('--max-usd');
|
||||
const maxUsdVal = maxUsdIdx >= 0 ? (args[maxUsdIdx + 1] ?? '').trim().toLowerCase() : '';
|
||||
const maxUsdOff = ['off', 'unlimited', 'none'].includes(maxUsdVal);
|
||||
const maxUsdRaw = parseFloat10(args, '--max-usd');
|
||||
const maxUsd = maxUsdRaw === null ? undefined : maxUsdRaw;
|
||||
|
||||
@@ -98,23 +91,13 @@ export async function runOnboard(engine: BrainEngine, args: string[]): Promise<v
|
||||
}
|
||||
|
||||
// --auto refuses without --max-usd (cron-safety per A12 + A20).
|
||||
// v0.42.42.0 (#2139, D15A): spend.posture=tokenmax lifts the refusal —
|
||||
// --auto runs UNCAPPED (maxUsd stays undefined), spend still ledgered by the
|
||||
// remediation budget tracker. An explicit --max-usd always wins.
|
||||
if (auto && maxUsd === undefined) {
|
||||
const { resolveSpendPosture } = await import('../core/spend-posture.ts');
|
||||
const tokenmax = (await resolveSpendPosture(engine)) === 'tokenmax';
|
||||
if (maxUsdOff || tokenmax) {
|
||||
process.stderr.write(`${maxUsdOff ? '--max-usd off' : 'spend.posture=tokenmax'}: onboard --auto running uncapped, spend ledgered. docs: docs/operations/spend-controls.md\n`);
|
||||
} else {
|
||||
process.stderr.write(
|
||||
`gbrain onboard --auto refuses without --max-usd N.\n` +
|
||||
`Set a cap to avoid surprise spend:\n` +
|
||||
` gbrain onboard --auto --max-usd 5\n` +
|
||||
`Or pass --max-usd off / set spend.posture=tokenmax to run uncapped. docs: docs/operations/spend-controls.md\n`,
|
||||
);
|
||||
process.exit(2);
|
||||
}
|
||||
process.stderr.write(
|
||||
`gbrain onboard --auto refuses without --max-usd N.\n` +
|
||||
`Set a cap to avoid surprise spend:\n` +
|
||||
` gbrain onboard --auto --max-usd 5\n`,
|
||||
);
|
||||
process.exit(2);
|
||||
}
|
||||
|
||||
// Build the plan: T4 checks supply extra remediations on top of T3's
|
||||
|
||||
@@ -53,15 +53,7 @@ const DENY_PREFIXES = [
|
||||
];
|
||||
|
||||
/** First slug segments where no inbound links is expected */
|
||||
const FIRST_SEGMENT_EXCLUSIONS = new Set([
|
||||
'scratch',
|
||||
'thoughts',
|
||||
'catalog',
|
||||
'entities',
|
||||
'raw',
|
||||
'atoms',
|
||||
'skills',
|
||||
]);
|
||||
const FIRST_SEGMENT_EXCLUSIONS = new Set(['scratch', 'thoughts', 'catalog', 'entities']);
|
||||
|
||||
// --- Filter logic ---
|
||||
|
||||
|
||||
+13
-43
@@ -7,7 +7,6 @@
|
||||
|
||||
import { listRecipes, getRecipe } from '../core/ai/recipes/index.ts';
|
||||
import { configureGateway, embedOne, isAvailable as gwIsAvailable, chat as gwChat } from '../core/ai/gateway.ts';
|
||||
import { buildGatewayConfig } from '../core/ai/build-gateway-config.ts';
|
||||
import { probeOllama, probeLMStudio } from '../core/ai/probes.ts';
|
||||
import { loadConfig } from '../core/config.ts';
|
||||
import { AIConfigError, AITransientError } from '../core/ai/errors.ts';
|
||||
@@ -34,19 +33,15 @@ interface ProviderOption {
|
||||
|
||||
function configureFromEnv(): void {
|
||||
const config = loadConfig();
|
||||
// Route through buildGatewayConfig — the single ownership seam that folds
|
||||
// file-plane API keys (openrouter_api_key, zeroentropy_api_key, ...) into
|
||||
// the gateway env — instead of hand-assembling AIGatewayConfig field by
|
||||
// field. Hand-building it here let this diagnostic report a provider as
|
||||
// missing env even when ~/.gbrain/config.json had it and the real gateway
|
||||
// path resolved it fine (#2728). Pre-init (no file-plane config yet) falls
|
||||
// back to a bare env passthrough so the command still works before
|
||||
// `gbrain init`.
|
||||
if (config) {
|
||||
configureGateway(buildGatewayConfig(config));
|
||||
return;
|
||||
}
|
||||
configureGateway({ env: { ...process.env } });
|
||||
configureGateway({
|
||||
embedding_model: config?.embedding_model,
|
||||
embedding_dimensions: config?.embedding_dimensions,
|
||||
expansion_model: config?.expansion_model,
|
||||
chat_model: config?.chat_model,
|
||||
chat_fallback_chain: config?.chat_fallback_chain,
|
||||
base_urls: config?.provider_base_urls,
|
||||
env: { ...process.env },
|
||||
});
|
||||
}
|
||||
|
||||
export function envReady(recipe: Recipe, env: NodeJS.ProcessEnv = process.env): boolean {
|
||||
@@ -141,12 +136,7 @@ EXAMPLES
|
||||
}
|
||||
|
||||
function runList(_args: string[]): void {
|
||||
// Same env the gateway actually sees (file-plane keys folded in), not bare
|
||||
// process.env — keeps this table's STATUS column honest with what
|
||||
// `providers test` (and the real init/gateway path) would report.
|
||||
const cfg = loadConfig();
|
||||
const env = cfg ? buildGatewayConfig(cfg).env : process.env;
|
||||
console.log(formatRecipeTable(listRecipes(), env));
|
||||
console.log(formatRecipeTable(listRecipes()));
|
||||
}
|
||||
|
||||
async function runTest(args: string[]): Promise<void> {
|
||||
@@ -173,18 +163,8 @@ async function runTest(args: string[]): Promise<void> {
|
||||
// the divergence at the top of the test so the recovery experience
|
||||
// doesn't repeat the bug-reporter's "providers test ✓ but import still
|
||||
// broken" trap.
|
||||
//
|
||||
// #2863: `cfg` is lifted out of the try block (not just used for the
|
||||
// warning) so the configureGateway calls below can reuse it. Before this
|
||||
// fix, the --model override only forwarded embedding_model/chat_model +
|
||||
// env, dropping config.provider_base_urls entirely — a probe against a
|
||||
// custom endpoint (e.g. a regional DashScope base URL) would silently
|
||||
// fall back to the recipe's hardcoded default endpoint and fail with a
|
||||
// misleading "Incorrect API key" error even though the key was valid for
|
||||
// the configured endpoint.
|
||||
let cfg: ReturnType<typeof loadConfig> | null = null;
|
||||
try {
|
||||
cfg = loadConfig();
|
||||
const cfg = loadConfig();
|
||||
const configuredModel = tpArg === 'embedding' ? cfg?.embedding_model : cfg?.chat_model;
|
||||
if (!configuredModel) {
|
||||
console.error(
|
||||
@@ -200,27 +180,17 @@ async function runTest(args: string[]): Promise<void> {
|
||||
}
|
||||
} catch { /* loadConfig throws when no brain configured — first-time install path; the no-config branch above handles it. */ }
|
||||
|
||||
// Reuse the SAME resolver the production path uses (buildGatewayConfig —
|
||||
// also used by cli.ts#connectEngine and init-embed-check.ts) so the probe
|
||||
// sees the identical base_urls / provider_chat_options / folded API keys
|
||||
// that a real `gbrain import`/`gbrain query` call would. Only the
|
||||
// touchpoint's model (+ embedding dims) is overridden on top, so an
|
||||
// isolated `--model` probe still targets exactly the requested model —
|
||||
// it just resolves that model's endpoint the way the brain actually
|
||||
// would. Falls back to bare env when no brain is configured yet (cfg is
|
||||
// null on first-time install, matching the old behavior for that case).
|
||||
const baseGatewayConfig = cfg ? buildGatewayConfig(cfg) : { env: { ...process.env } };
|
||||
if (tpArg === 'embedding') {
|
||||
const dims = recipe?.touchpoints.embedding?.default_dims ?? 1536;
|
||||
configureGateway({
|
||||
...baseGatewayConfig,
|
||||
embedding_model: modelArg,
|
||||
embedding_dimensions: dims,
|
||||
env: { ...process.env },
|
||||
});
|
||||
} else {
|
||||
configureGateway({
|
||||
...baseGatewayConfig,
|
||||
chat_model: modelArg,
|
||||
env: { ...process.env },
|
||||
});
|
||||
}
|
||||
void modelId; // intentionally unused but preserved for readability
|
||||
|
||||
@@ -444,24 +444,14 @@ export async function runReindexCodeCli(engine: BrainEngine, args: string[]): Pr
|
||||
}
|
||||
|
||||
// F3: --max-cost / --max-cost-usd both accepted for symmetry with brainstorm.
|
||||
// v0.42.42.0 (#2139): `off`/`unlimited`/`none` → no runtime cap AND an explicit
|
||||
// "cost isn't the constraint" decision that proceeds past the confirmation gate
|
||||
// (like --yes). Numeric must be positive; `0`/garbage is rejected.
|
||||
let maxCostUsd: number | undefined;
|
||||
let maxCostOff = false;
|
||||
for (const flag of ['--max-cost', '--max-cost-usd']) {
|
||||
const idx = args.indexOf(flag);
|
||||
if (idx >= 0) {
|
||||
const v = args[idx + 1];
|
||||
const t = (v ?? '').trim().toLowerCase();
|
||||
if (['off', 'unlimited', 'none'].includes(t)) {
|
||||
maxCostUsd = undefined; // no runtime cap (reindex skips the tracker when unset)
|
||||
maxCostOff = true;
|
||||
break;
|
||||
}
|
||||
const n = v ? parseFloat(v) : NaN;
|
||||
if (!Number.isFinite(n) || n <= 0) {
|
||||
console.error(`gbrain reindex --code: ${flag} requires a positive number in USD, or off/unlimited (got ${v ?? '(missing)'})`);
|
||||
console.error(`gbrain reindex --code: ${flag} requires a positive number in USD (got ${v ?? '(missing)'})`);
|
||||
process.exit(2);
|
||||
}
|
||||
maxCostUsd = n;
|
||||
@@ -503,36 +493,20 @@ export async function runReindexCodeCli(engine: BrainEngine, args: string[]): Pr
|
||||
}
|
||||
|
||||
if (!yes) {
|
||||
// v0.42.42.0 (#2139): spend.posture=tokenmax makes the gate informational
|
||||
// — print the estimate and proceed (the operator declared cost isn't the
|
||||
// constraint). The spend is still ledgered by the runtime BudgetTracker.
|
||||
const { resolveSpendPosture } = await import('../core/spend-posture.ts');
|
||||
const posture = await resolveSpendPosture(engine);
|
||||
// An explicit `--max-cost off` is the same "cost isn't the constraint"
|
||||
// signal as spend.posture=tokenmax — proceed past the confirmation gate.
|
||||
if (posture === 'tokenmax' || maxCostOff) {
|
||||
const gate = maxCostOff ? 'max_cost_off' : 'posture_tokenmax';
|
||||
if (json) {
|
||||
console.log(JSON.stringify({ status: 'proceeding', gate, codePages: preview.totalPages, totalTokens: preview.totalTokens, costUsd, model: getEmbeddingModelName() }));
|
||||
} else {
|
||||
console.log(`${previewMsg} ${maxCostOff ? '--max-cost off' : 'spend.posture=tokenmax'}: proceeding (informational). docs: docs/operations/spend-controls.md`);
|
||||
}
|
||||
} else {
|
||||
const isTTY = Boolean(process.stdout.isTTY) && Boolean(process.stdin.isTTY);
|
||||
if (!isTTY || json) {
|
||||
// Guardrail unchanged: refuse + exit 2, no spend. Only the FORMAT splits
|
||||
// on --json now (human refusal on stderr otherwise) — #1784.
|
||||
const refusal = buildCostRefusal({ json, previewMsg, preview, costUsd, model: getEmbeddingModelName() });
|
||||
if (refusal.stdout) console.log(refusal.stdout);
|
||||
if (refusal.stderr) console.error(refusal.stderr);
|
||||
process.exit(2);
|
||||
}
|
||||
console.log(previewMsg);
|
||||
const answer = await promptYesNo('Proceed? [y/N] ');
|
||||
if (!answer) {
|
||||
console.log('Cancelled.');
|
||||
return;
|
||||
}
|
||||
const isTTY = Boolean(process.stdout.isTTY) && Boolean(process.stdin.isTTY);
|
||||
if (!isTTY || json) {
|
||||
// Guardrail unchanged: refuse + exit 2, no spend. Only the FORMAT splits
|
||||
// on --json now (human refusal on stderr otherwise) — #1784.
|
||||
const refusal = buildCostRefusal({ json, previewMsg, preview, costUsd, model: getEmbeddingModelName() });
|
||||
if (refusal.stdout) console.log(refusal.stdout);
|
||||
if (refusal.stderr) console.error(refusal.stderr);
|
||||
process.exit(2);
|
||||
}
|
||||
console.log(previewMsg);
|
||||
const answer = await promptYesNo('Proceed? [y/N] ');
|
||||
if (!answer) {
|
||||
console.log('Cancelled.');
|
||||
return;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,282 +0,0 @@
|
||||
/**
|
||||
* `gbrain reindex-search-vector` — recreate FTS trigger functions and
|
||||
* backfill existing rows under the language configured via
|
||||
* GBRAIN_FTS_LANGUAGE.
|
||||
*
|
||||
* Why this command exists: schema migration v123 (configurable_fts_language)
|
||||
* stamps the trigger functions with the configured language at first apply.
|
||||
* After that, changing the env var has no effect on the write side because
|
||||
* v123 already shows as "applied" — the migrations runner will skip it.
|
||||
* This command is the documented escape hatch: it re-runs the same
|
||||
* recreate-and-backfill logic v123 uses, gated on an explicit user
|
||||
* action so the operation is intentional and visible (writes touch
|
||||
* every row in pages and content_chunks).
|
||||
*
|
||||
* Idempotent: running twice with the same GBRAIN_FTS_LANGUAGE produces
|
||||
* the same trigger function bodies and the same tokenized vectors.
|
||||
*
|
||||
* Flags:
|
||||
* --dry-run Show what would happen, exit 0 without touching DB.
|
||||
* --yes Skip interactive [y/N]. Required for non-TTY (including --json).
|
||||
* --json Machine-readable result envelope. Does NOT imply --yes.
|
||||
*
|
||||
* Backfill runs in id-keyset batches (BACKFILL_BATCH_SIZE rows per UPDATE)
|
||||
* so a large brain never holds one giant row lock, and streams progress
|
||||
* through the shared reporter (stderr; stdout stays clean for --json).
|
||||
*
|
||||
* Cost: trigger recreate is sub-millisecond. Backfill is one tsvector
|
||||
* rebuild per page + per chunk. On a 20K-page brain with 80K chunks,
|
||||
* expect ~5-15s depending on Postgres CPU and content size.
|
||||
*/
|
||||
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { getFtsLanguage } from '../core/fts-language.ts';
|
||||
import { createInterface } from 'readline';
|
||||
import { createProgress } from '../core/progress.ts';
|
||||
import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
|
||||
|
||||
export interface ReindexSearchVectorOpts {
|
||||
dryRun?: boolean;
|
||||
yes?: boolean;
|
||||
json?: boolean;
|
||||
}
|
||||
|
||||
export interface ReindexSearchVectorResult {
|
||||
status: 'ok' | 'dry_run' | 'cancelled';
|
||||
language: string;
|
||||
pagesUpdated: number;
|
||||
chunksUpdated: number;
|
||||
triggersRecreated: number;
|
||||
durationMs: number;
|
||||
}
|
||||
|
||||
interface CountRow {
|
||||
pages: number;
|
||||
chunks: number;
|
||||
}
|
||||
|
||||
/** Rows per backfill UPDATE. Keyset-batched so one statement never locks the whole table. */
|
||||
export const BACKFILL_BATCH_SIZE = 5000;
|
||||
|
||||
/**
|
||||
* Keyset-batched UPDATE: applies `setClause` to `table` rows where
|
||||
* search_vector IS NOT NULL, BACKFILL_BATCH_SIZE ids at a time, ticking
|
||||
* the shared progress reporter after each batch. Terminates when a batch
|
||||
* returns fewer rows than the batch size (or none).
|
||||
*/
|
||||
async function batchedBackfill(
|
||||
engine: BrainEngine,
|
||||
table: 'pages' | 'content_chunks',
|
||||
setClause: string,
|
||||
tick: (n: number) => void
|
||||
): Promise<void> {
|
||||
let cursor = 0;
|
||||
for (;;) {
|
||||
const rows = await engine.executeRaw<{ id: number }>(`
|
||||
UPDATE ${table} SET ${setClause}
|
||||
WHERE id IN (
|
||||
SELECT id FROM ${table}
|
||||
WHERE search_vector IS NOT NULL AND id > ${cursor}
|
||||
ORDER BY id
|
||||
LIMIT ${BACKFILL_BATCH_SIZE}
|
||||
)
|
||||
RETURNING id
|
||||
`);
|
||||
if (rows.length === 0) break;
|
||||
tick(rows.length);
|
||||
cursor = rows.reduce((m, r) => Math.max(m, Number(r.id)), cursor);
|
||||
if (rows.length < BACKFILL_BATCH_SIZE) break;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Programmatic entrypoint — takes a typed opts object. Used by tests and
|
||||
* future internal callers. The CLI wrapper is `runReindexSearchVectorCli`
|
||||
* defined at the bottom of this file.
|
||||
*/
|
||||
export async function runReindexSearchVector(
|
||||
engine: BrainEngine,
|
||||
opts: ReindexSearchVectorOpts
|
||||
): Promise<ReindexSearchVectorResult> {
|
||||
const lang = getFtsLanguage();
|
||||
const startedAt = Date.now();
|
||||
|
||||
// Inventory: how many rows will the backfill touch?
|
||||
const counts = await engine.executeRaw<CountRow>(
|
||||
`SELECT
|
||||
(SELECT COUNT(*)::int FROM pages WHERE search_vector IS NOT NULL) AS pages,
|
||||
(SELECT COUNT(*)::int FROM content_chunks WHERE search_vector IS NOT NULL) AS chunks`
|
||||
);
|
||||
const pagesCount = counts[0]?.pages ?? 0;
|
||||
const chunksCount = counts[0]?.chunks ?? 0;
|
||||
|
||||
if (opts.dryRun) {
|
||||
const result: ReindexSearchVectorResult = {
|
||||
status: 'dry_run',
|
||||
language: lang,
|
||||
pagesUpdated: pagesCount,
|
||||
chunksUpdated: chunksCount,
|
||||
triggersRecreated: 0,
|
||||
durationMs: Date.now() - startedAt,
|
||||
};
|
||||
if (opts.json) {
|
||||
console.log(JSON.stringify(result, null, 2));
|
||||
} else {
|
||||
console.log(`[dry-run] Would recreate 2 trigger functions with language='${lang}'`);
|
||||
console.log(`[dry-run] Would backfill ${pagesCount} pages + ${chunksCount} chunks`);
|
||||
console.log(`[dry-run] Skipping all DB writes. Pass --yes to apply.`);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
// Confirm unless --yes. --json does NOT bypass the gate — a machine
|
||||
// caller must pass --yes explicitly (mirrors reindex-code, #1784).
|
||||
if (!opts.yes) {
|
||||
if (!process.stdin.isTTY) {
|
||||
if (opts.json) {
|
||||
console.log(JSON.stringify({
|
||||
error: {
|
||||
class: 'ConfirmationRequired',
|
||||
code: 'reindex_requires_yes',
|
||||
message: `Refusing to recreate FTS triggers + backfill ${pagesCount} pages + ${chunksCount} chunks without --yes in a non-TTY environment.`,
|
||||
hint: 'Pass --yes to proceed, or --dry-run to preview.',
|
||||
},
|
||||
language: lang,
|
||||
pages: pagesCount,
|
||||
chunks: chunksCount,
|
||||
}));
|
||||
} else {
|
||||
console.error('Refusing to run without --yes in non-TTY environment.');
|
||||
}
|
||||
process.exit(2);
|
||||
}
|
||||
|
||||
const rl = createInterface({ input: process.stdin, output: process.stdout });
|
||||
const answer = await new Promise<string>(resolve => {
|
||||
rl.question(
|
||||
`Recreate FTS triggers with language='${lang}' and backfill ${pagesCount} pages + ${chunksCount} chunks? [y/N]: `,
|
||||
resolve
|
||||
);
|
||||
});
|
||||
rl.close();
|
||||
|
||||
if (!/^y(es)?$/i.test(answer.trim())) {
|
||||
const result: ReindexSearchVectorResult = {
|
||||
status: 'cancelled',
|
||||
language: lang,
|
||||
pagesUpdated: 0,
|
||||
chunksUpdated: 0,
|
||||
triggersRecreated: 0,
|
||||
durationMs: Date.now() - startedAt,
|
||||
};
|
||||
if (opts.json) {
|
||||
console.log(JSON.stringify(result, null, 2));
|
||||
} else {
|
||||
console.log('Cancelled.');
|
||||
}
|
||||
return result;
|
||||
}
|
||||
}
|
||||
|
||||
// Recreate trigger functions. The strings are intentionally identical to
|
||||
// the v124 migration body — keeping them in lockstep is the contract.
|
||||
// `SET search_path = pg_catalog, public` mirrors the v120/#1647 hardening:
|
||||
// CREATE OR REPLACE resets proconfig, so omitting it here would strip the
|
||||
// hardening from every brain that runs this command.
|
||||
//
|
||||
// #2704: compiled_truth (the unbounded whole-page body) is deliberately
|
||||
// NOT indexed here — it overflows Postgres's 1MB tsvector cap on large
|
||||
// pages, and content_chunks.search_vector (populated separately, chunk-
|
||||
// grain, well under the cap) is what searchKeyword() actually queries.
|
||||
// See migrate.ts's v124 for the full rationale; keep this copy in sync.
|
||||
const recreatePagesFn = `
|
||||
CREATE OR REPLACE FUNCTION update_page_search_vector() RETURNS trigger SET search_path = pg_catalog, public AS $fn$
|
||||
DECLARE
|
||||
timeline_text TEXT;
|
||||
BEGIN
|
||||
SELECT coalesce(string_agg(summary || ' ' || detail, ' '), '')
|
||||
INTO timeline_text
|
||||
FROM timeline_entries
|
||||
WHERE page_id = NEW.id;
|
||||
|
||||
NEW.search_vector :=
|
||||
setweight(to_tsvector('${lang}', coalesce(NEW.title, '')), 'A') ||
|
||||
setweight(to_tsvector('${lang}', coalesce(NEW.timeline, '')), 'C') ||
|
||||
setweight(to_tsvector('${lang}', coalesce(timeline_text, '')), 'C');
|
||||
|
||||
RETURN NEW;
|
||||
END;
|
||||
$fn$ LANGUAGE plpgsql;
|
||||
`;
|
||||
|
||||
const recreateChunksFn = `
|
||||
CREATE OR REPLACE FUNCTION update_chunk_search_vector() RETURNS TRIGGER SET search_path = pg_catalog, public AS $fn$
|
||||
BEGIN
|
||||
NEW.search_vector :=
|
||||
setweight(to_tsvector('${lang}', COALESCE(NEW.doc_comment, '')), 'A') ||
|
||||
setweight(to_tsvector('${lang}', COALESCE(NEW.symbol_name_qualified, '')), 'A') ||
|
||||
setweight(to_tsvector('${lang}', COALESCE(NEW.chunk_text, '')), 'B');
|
||||
RETURN NEW;
|
||||
END;
|
||||
$fn$ LANGUAGE plpgsql;
|
||||
`;
|
||||
|
||||
await engine.executeRaw(recreatePagesFn);
|
||||
await engine.executeRaw(recreateChunksFn);
|
||||
|
||||
const progress = createProgress(cliOptsToProgressOptions(getCliOptions()));
|
||||
|
||||
// Backfill: UPDATE-to-self forces the pages trigger to re-fire
|
||||
// (Postgres re-fires on UPDATE-to-same-value); content_chunks gets a
|
||||
// direct vector compute since the column itself is what we want.
|
||||
progress.start('reindex_search_vector.pages', pagesCount);
|
||||
await batchedBackfill(engine, 'pages', 'id = id', n => progress.tick(n));
|
||||
progress.finish();
|
||||
|
||||
progress.start('reindex_search_vector.chunks', chunksCount);
|
||||
await batchedBackfill(
|
||||
engine,
|
||||
'content_chunks',
|
||||
`search_vector =
|
||||
setweight(to_tsvector('${lang}', COALESCE(doc_comment, '')), 'A') ||
|
||||
setweight(to_tsvector('${lang}', COALESCE(symbol_name_qualified, '')), 'A') ||
|
||||
setweight(to_tsvector('${lang}', COALESCE(chunk_text, '')), 'B')`,
|
||||
n => progress.tick(n)
|
||||
);
|
||||
progress.finish();
|
||||
|
||||
const result: ReindexSearchVectorResult = {
|
||||
status: 'ok',
|
||||
language: lang,
|
||||
pagesUpdated: pagesCount,
|
||||
chunksUpdated: chunksCount,
|
||||
triggersRecreated: 2,
|
||||
durationMs: Date.now() - startedAt,
|
||||
};
|
||||
|
||||
if (opts.json) {
|
||||
console.log(JSON.stringify(result, null, 2));
|
||||
} else {
|
||||
console.log(`✅ Recreated 2 trigger functions with language='${lang}'`);
|
||||
console.log(`✅ Backfilled ${pagesCount} pages + ${chunksCount} chunks (${result.durationMs}ms)`);
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
/**
|
||||
* CLI entrypoint. Parses argv flags and dispatches to runReindexSearchVector.
|
||||
* Matches the style of `reindex-code`: --dry-run, --yes/-y, --json.
|
||||
*
|
||||
* Exit codes: 0 success/dry-run/cancelled, 2 if non-TTY without --yes.
|
||||
*/
|
||||
export async function runReindexSearchVectorCli(
|
||||
engine: BrainEngine,
|
||||
args: string[]
|
||||
): Promise<void> {
|
||||
const dryRun = args.includes('--dry-run');
|
||||
const yes = args.includes('--yes') || args.includes('-y');
|
||||
const json = args.includes('--json');
|
||||
|
||||
await runReindexSearchVector(engine, { dryRun, yes, json });
|
||||
}
|
||||
@@ -22,7 +22,6 @@
|
||||
*/
|
||||
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { setCliExitVerdict } from '../core/cli-force-exit.ts';
|
||||
import { MARKDOWN_CHUNKER_VERSION } from '../core/chunkers/recursive.ts';
|
||||
import { importFromContent, importFromFile } from '../core/import-file.ts';
|
||||
import { serializeMarkdown } from '../core/markdown.ts';
|
||||
@@ -151,7 +150,7 @@ export async function runReindex(engine: BrainEngine, args: string[]): Promise<R
|
||||
} else {
|
||||
process.stderr.write('Usage: gbrain reindex --markdown [--limit N] [--dry-run] [--json] [--repo PATH]\n');
|
||||
}
|
||||
setCliExitVerdict(2);
|
||||
process.exitCode = 2;
|
||||
return { pending: 0, reindexed: 0, skipped: 0, failed: 0, dryRun: !!opts.dryRun, chunkerVersion: MARKDOWN_CHUNKER_VERSION };
|
||||
}
|
||||
|
||||
|
||||
+12
-18
@@ -105,19 +105,13 @@ function printHelp(): void {
|
||||
async function runRemotePing(config: NonNullable<ReturnType<typeof loadConfig>>, args: string[]): Promise<void> {
|
||||
const { json, timeoutMs } = parseFlags(args);
|
||||
|
||||
// submit_job / get_job return the MinionJob row verbatim — the lifecycle
|
||||
// field is `status` (src/core/minions/types.ts), not `state`. Reading
|
||||
// `state` here made every poll see `undefined`, so the terminal check
|
||||
// never matched and ping always exhausted its timeout (exit 1) even when
|
||||
// the cycle completed. The ping's own JSON *output* keys (`state`,
|
||||
// `last_state`) are kept as-is for consumers.
|
||||
let submitted: { id: number; name: string; status: string };
|
||||
let submitted: { id: number; name: string; state: string };
|
||||
try {
|
||||
const res = await callRemoteTool(config, 'submit_job', {
|
||||
name: 'autopilot-cycle',
|
||||
data: { phases: ['sync', 'extract', 'embed'] },
|
||||
});
|
||||
submitted = unpackToolResult<{ id: number; name: string; status: string }>(res);
|
||||
submitted = unpackToolResult<{ id: number; name: string; state: string }>(res);
|
||||
} catch (e) {
|
||||
return failPing(e, json);
|
||||
}
|
||||
@@ -128,43 +122,43 @@ async function runRemotePing(config: NonNullable<ReturnType<typeof loadConfig>>,
|
||||
|
||||
const startMs = Date.now();
|
||||
let attempt = 0;
|
||||
let lastState = submitted.status;
|
||||
let lastState = submitted.state;
|
||||
while (Date.now() - startMs < timeoutMs) {
|
||||
const elapsed = Date.now() - startMs;
|
||||
const intervalMs = elapsed < 30_000 ? 1_000 : elapsed < 5 * 60_000 + 30_000 ? 5_000 : 10_000;
|
||||
await sleep(intervalMs);
|
||||
attempt++;
|
||||
|
||||
let job: { id: number; status: string; failed_reason?: string };
|
||||
let job: { id: number; state: string; failed_reason?: string };
|
||||
try {
|
||||
const res = await callRemoteTool(config, 'get_job', { id: submitted.id });
|
||||
job = unpackToolResult<{ id: number; status: string; failed_reason?: string }>(res);
|
||||
job = unpackToolResult<{ id: number; state: string; failed_reason?: string }>(res);
|
||||
} catch (e) {
|
||||
// Network blip mid-poll: log and keep going. Surface only if persistent.
|
||||
if (!json) console.error(` poll #${attempt} failed (${e instanceof Error ? e.message : String(e)}); continuing...`);
|
||||
continue;
|
||||
}
|
||||
|
||||
if (job.status !== lastState) {
|
||||
lastState = job.status;
|
||||
if (!json) console.error(` job #${submitted.id} → ${job.status}`);
|
||||
if (job.state !== lastState) {
|
||||
lastState = job.state;
|
||||
if (!json) console.error(` job #${submitted.id} → ${job.state}`);
|
||||
}
|
||||
|
||||
const terminal = ['completed', 'failed', 'dead', 'cancelled'];
|
||||
if (terminal.includes(job.status)) {
|
||||
const ok = job.status === 'completed';
|
||||
if (terminal.includes(job.state)) {
|
||||
const ok = job.state === 'completed';
|
||||
if (json) {
|
||||
console.log(JSON.stringify({
|
||||
status: ok ? 'success' : 'error',
|
||||
job_id: submitted.id,
|
||||
state: job.status,
|
||||
state: job.state,
|
||||
...(job.failed_reason ? { failed_reason: job.failed_reason } : {}),
|
||||
elapsed_ms: Date.now() - startMs,
|
||||
}));
|
||||
} else {
|
||||
console.log(ok
|
||||
? `\nautopilot-cycle complete (${Math.round((Date.now() - startMs) / 1000)}s).`
|
||||
: `\nautopilot-cycle ended ${job.status}${job.failed_reason ? `: ${job.failed_reason}` : ''}.`);
|
||||
: `\nautopilot-cycle ended ${job.state}${job.failed_reason ? `: ${job.failed_reason}` : ''}.`);
|
||||
}
|
||||
process.exit(ok ? 0 : 1);
|
||||
}
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user