fix(ci): delta-assert reporter leak test + raise shard timeout to 22min

The signal-handler test asserted an absolute liveReporters===0 on a
module-global set, so any other test file in the shard holding a live
reporter flaked it — it red-flagged ~12 unrelated PR runs and one master
push in two days, purely as a function of shard composition. The delta
form pins the same claim (50 reporter lifecycles leak nothing).

The 15-minute shard timeout cancelled 13 fully-passing runs under
parallel PR load (PGLite WASM cold-starts stretch shards); the
test-status gate then reported the cancellations as failures.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

.github/workflows/osv-scanner.yml

@@ -0,0 +1,33 @@
+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

.github/workflows/release.yml

@@ -19,6 +19,10 @@ jobs:
             target: bun-linux-x64
             artifact: gbrain-linux-x64
     runs-on: ${{ matrix.os }}
+    permissions:
+      contents: read
+      id-token: write      # for attest-build-provenance (Sigstore OIDC)
+      attestations: write  # for attest-build-provenance
     steps:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
@@ -28,6 +32,10 @@ jobs:
       - run: bun test
       - run: bun run verify
       - run: bun build --compile --target=${{ 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 }}

.github/workflows/semgrep.yml

@@ -0,0 +1,36 @@
+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

.github/workflows/test.yml

@@ -206,7 +206,11 @@ jobs:
     needs: cache-check
     if: needs.cache-check.outputs.hit != 'true'
     runs-on: ubuntu-latest
-    timeout-minutes: 15
+    # 22, not 15: under parallel PR load the PGLite WASM cold-starts stretch a
+    # shard past 15 min while every test is still passing — the timeout then
+    # cancels the job and the test-status gate reads it as a failure. 13 runs
+    # died this way on 2026-07-21/22 alone.
+    timeout-minutes: 22
     strategy:
       fail-fast: false
       matrix:

CHANGELOG.md

@@ -2,6 +2,88 @@
 
 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.**

README.md

@@ -71,8 +71,8 @@ GBrain is designed to be installed and operated by an AI agent. The fastest path
 
 If you don't already have an AI agent platform running, start with one of these. Both are designed to read GBrain's install protocol and execute it:
 
-- **[OpenClaw](https://github.com/openclawagents/openclaw)** — deploy [AlphaClaw on Render](https://render.com/deploy?repo=https://github.com/chrysb/alphaclaw) (one click, 8GB+ RAM)
-- **[Hermes](https://github.com/openclawagents/hermes)** — deploy on [Railway](https://github.com/praveen-ks-2001/hermes-agent-template) (one click)
+- **[OpenClaw](https://github.com/openclaw/openclaw)** — deploy [AlphaClaw on Render](https://render.com/deploy?repo=https://github.com/chrysb/alphaclaw) (one click, 8GB+ RAM)
+- **[Hermes](https://github.com/NousResearch/hermes-agent)** — deploy on [Railway](https://github.com/praveen-ks-2001/hermes-agent-template) (one click)
 
 Then paste this into your agent:
 
@@ -258,6 +258,24 @@ 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).

VERSION

@@ -1 +1 @@
-0.42.61.0
+0.42.64.0

admin/bun.lock

@@ -13,48 +13,52 @@
         "@types/react-dom": "^19.1.2",
         "@vitejs/plugin-react": "^4.4.1",
         "typescript": "^5.8.3",
-        "vite": "^6.3.3",
+        "vite": "^6.4.3",
       },
     },
   },
+  "overrides": {
+    "@babel/core": "^7.29.6",
+    "postcss": "^8.5.10",
+  },
   "packages": {
-    "@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/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/compat-data": ["@babel/compat-data@7.29.0", "", {}, "sha512-T1NCJqT/j9+cn8fvkt7jtwbLBfLC/1y1c7NtCeXFRgzGTsafi68MRv8yzkYSapBnFA6L3U2VSc02ciDzoAJhJg=="],
+    "@babel/compat-data": ["@babel/compat-data@7.29.7", "", {}, "sha512-locTkQyKvwIEgBzVrn8693ebc97F2U8ZHjbXwDXJ5Fn2TCpNwTlKcaKLkdHop5c/icOFE7qt7Q9JC5hnKNa6Gg=="],
 
-    "@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/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/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/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/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-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-globals": ["@babel/helper-globals@7.28.0", "", {}, "sha512-+W6cISkXFa1jXsDEdYA8HeevQT/FULhxzR99pxphltZcVaugps53THCeiWA8SguxxpSp3gKPiuYfSWopkLQ4hw=="],
+    "@babel/helper-globals": ["@babel/helper-globals@7.29.7", "", {}, "sha512-3nQVUAtvkKH9zahfWgw96Jc/uFOmjACE1kQz82E2lqWmHBgjzbNlsC22nuQTfahmWeQtTq5nQ/4Nnd2A1wj4zA=="],
 
-    "@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-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-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-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-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@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
+    "@babel/helper-string-parser": ["@babel/helper-string-parser@7.29.7", "", {}, "sha512-Pb5ijPrZ89GDH8223L4UP8i6QApWxs04RbPQJTeWDV0/keR2E36MeKnyr6LYmUUvqRRI+Iv87SuF1W6ErINzYw=="],
 
-    "@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
+    "@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.29.7", "", {}, "sha512-qehxGkRj55h/ff8EMaJ+cYhyaKlHIxqYDn682wQD7RNp9UujOQsHog2uS0r2vzr4pW+sXf90NeeayjcNaX3fFg=="],
 
-    "@babel/helper-validator-option": ["@babel/helper-validator-option@7.27.1", "", {}, "sha512-YvjJow9FxbhFFKDSuFnVCe2WxXk1zWc22fFePVNEaWJEu8IrZVlda6N0uHwzZrUM1il7NC9Mlp4MaJYbYd9JSg=="],
+    "@babel/helper-validator-option": ["@babel/helper-validator-option@7.29.7", "", {}, "sha512-N9ZErrD+yW5geCDtBqnOoxmR8+tNKiGuxKlDpuJxfsqpa2dFcexaziGAE/qoHLiDDreVNMupxGmSoNlyvsA3gw=="],
 
-    "@babel/helpers": ["@babel/helpers@7.29.2", "", { "dependencies": { "@babel/template": "^7.28.6", "@babel/types": "^7.29.0" } }, "sha512-HoGuUs4sCZNezVEKdVcwqmZN8GoHirLUcLaYVNBK2J0DadGtdcqgr3BCbvH8+XUo4NGjNl3VOtSjEKNzqfFgKw=="],
+    "@babel/helpers": ["@babel/helpers@7.29.7", "", { "dependencies": { "@babel/template": "^7.29.7", "@babel/types": "^7.29.7" } }, "sha512-1k2lAGRMfHTcwuNYcCNUmaUffmQv8KWMfh2iJUUeRlwlwH4FdNG7mfPI10NPfLHJFThE4Tyr4mv7kTNZOiPuBg=="],
 
-    "@babel/parser": ["@babel/parser@7.29.2", "", { "dependencies": { "@babel/types": "^7.29.0" }, "bin": "./bin/babel-parser.js" }, "sha512-4GgRzy/+fsBa72/RZVJmGKPmZu9Byn8o4MoLpmNe1m8ZfYnz5emHLQz3U4gLud6Zwl0RZIcgiLD7Uq7ySFuDLA=="],
+    "@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/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@7.28.6", "", { "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/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/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/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/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
+    "@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=="],
 
     "@esbuild/aix-ppc64": ["@esbuild/aix-ppc64@0.25.12", "", { "os": "aix", "cpu": "ppc64" }, "sha512-Hhmwd6CInZ3dwpuGTF8fJG6yoWmsToE+vYgD4nytZVxcu1ulHpUQRAB1UJ8+N1Am3Mz4+xOByoQoSZf4D+CpkA=="],
 
@@ -220,7 +224,7 @@
 
     "ms": ["ms@2.1.3", "", {}, "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="],
 
-    "nanoid": ["nanoid@3.3.11", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w=="],
+    "nanoid": ["nanoid@3.3.16", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-bzlKTyNJ7+LdGIIwy8ijFpIqEQIvafahV7eYykJ8Cvh42EdJeODoJ6gUJXpQJvej1BddH8OqTXZNE/KfbWAu8Q=="],
 
     "node-releases": ["node-releases@2.0.37", "", {}, "sha512-1h5gKZCF+pO/o3Iqt5Jp7wc9rH3eJJ0+nh/CIoiRwjRxde/hAHyLPXYN4V3CqKAbiZPSeJFSWHmJsbkicta0Eg=="],
 
@@ -228,7 +232,7 @@
 
     "picomatch": ["picomatch@4.0.4", "", {}, "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A=="],
 
-    "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=="],
+    "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=="],
 
     "react": ["react@19.2.5", "", {}, "sha512-llUJLzz1zTUBrskt2pwZgLq59AemifIftw4aB7JxOqf1HY2FDaGDxgwpAPVzHU1kdWabH7FauP4i1oEeer2WCA=="],
 
@@ -250,8 +254,36 @@
 
     "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@6.4.2", "", { "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=="],
+    "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=="],
 
     "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=="],
   }
 }

admin/dist/index.html

@@ -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-DqP-zmqH.js"></script>
+  <script type="module" crossorigin src="/admin/assets/index-CoGEje3-.js"></script>
   <link rel="stylesheet" crossorigin href="/admin/assets/index-GxkWX7v3.css">
 </head>
 <body>

admin/package.json

@@ -15,7 +15,11 @@
     "@types/react": "^19.1.2",
     "@types/react-dom": "^19.1.2",
     "@vitejs/plugin-react": "^4.4.1",
-    "vite": "^6.3.3",
+    "vite": "^6.4.3",
     "typescript": "^5.8.3"
+  },
+  "overrides": {
+    "@babel/core": "^7.29.6",
+    "postcss": "^8.5.10"
   }
 }

admin/src/pages/Dashboard.tsx

@@ -21,7 +21,7 @@ export function DashboardPage() {
     api.stats().then(setStats).catch(() => {});
     api.health().then(setHealth).catch(() => {});
 
-    const es = new EventSource('/admin/events');
+    const es = new EventSource('/admin/events', { withCredentials: true });
     eventSourceRef.current = es;
     es.onopen = () => setSseStatus('connected');
     es.onmessage = (e) => {

bun.lock

@@ -26,8 +26,8 @@
         "express-rate-limit": "^7.5.0",
         "gray-matter": "^4.0.3",
         "heic-decode": "^2.1.0",
-        "js-yaml": "^3.14.2",
-        "marked": "^18.0.0",
+        "js-yaml": "^3.15.0",
+        "marked": "^18.0.2",
         "openai": "^4.0.0",
         "pgvector": "^0.2.0",
         "postgres": "^3.4.0",
@@ -50,6 +50,17 @@
   "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=="],
 
@@ -151,7 +162,7 @@
 
     "@electric-sql/pglite": ["@electric-sql/pglite@0.4.3", "", {}, "sha512-ichuWTgtd4mOM1G4SpyGJa5trT03lWbMypDV0fUXUCXg5hiHqVAz/bZyV68NqmkLB7WcYmj1RMJVSp8HV/v/ZQ=="],
 
-    "@hono/node-server": ["@hono/node-server@1.19.12", "", { "peerDependencies": { "hono": "^4" } }, "sha512-txsUW4SQ1iilgE0l9/e9VQWmELXifEFvmdA1j6WFh/aFPj99hIntrSsq/if0UWyGVkmrRPKA1wCeP+UCr1B9Uw=="],
+    "@hono/node-server": ["@hono/node-server@1.19.14", "", { "peerDependencies": { "hono": "^4" } }, "sha512-GwtvgtXxnWsucXvbQXkRgqksiH2Qed37H9xHZocE5sA3N8O8O8/8FA3uclQXxXVzc9XBZuEOMK7+r02FmSpHtw=="],
 
     "@jsquash/avif": ["@jsquash/avif@2.1.1", "", { "dependencies": { "wasm-feature-detect": "^1.2.11" } }, "sha512-LMRxd0fMgfCLtobDh0/sFYJMMiRJTNYSEEWvRDKXlAeZ08t3gI5V+1thIT0XjXJ+SVG7Zug9B0XPyx0Ti5VRNA=="],
 
@@ -159,6 +170,8 @@
 
     "@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=="],
@@ -307,6 +320,8 @@
 
     "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=="],
@@ -385,15 +400,15 @@
 
     "fast-deep-equal": ["fast-deep-equal@3.1.3", "", {}, "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q=="],
 
-    "fast-uri": ["fast-uri@3.1.0", "", {}, "sha512-iPeeDKJSWf4IEOasVVrknXpaBV0IApz/gp7S2bb7Z4Lljbl2MGJRqInZiUrQwV16cpzw/D3S5j5Julj/gT52AA=="],
+    "fast-uri": ["fast-uri@3.1.3", "", {}, "sha512-i70LwGWUduXqzicKXWshooq+sWL1K3WUU5rKZNG/0i3a1OSoX3HqhH5WbWwTmqWfor4urUakGPiRQcleRZTwOg=="],
 
-    "fast-xml-builder": ["fast-xml-builder@1.1.4", "", { "dependencies": { "path-expression-matcher": "^1.1.3" } }, "sha512-f2jhpN4Eccy0/Uz9csxh3Nu6q4ErKxf0XIsasomfOihuSUa3/xw6w8dnOtCDgEItQFJG8KyXPzQXzcODDrrbOg=="],
+    "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-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=="],
+    "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=="],
 
     "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@4.0.5", "", { "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": ["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-encoder": ["form-data-encoder@1.7.2", "", {}, "sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A=="],
 
@@ -417,11 +432,11 @@
 
     "has-tostringtag": ["has-tostringtag@1.0.2", "", { "dependencies": { "has-symbols": "^1.0.3" } }, "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw=="],
 
-    "hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
+    "hasown": ["hasown@2.0.4", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-T2UbfbBEF32wiepXIsMlTW9+dDYC6wMh/t/vYA4tuOMKqWz/n3vr1NFSxQiyP+zk2mXsoMA/i/7qV6LKut1t1A=="],
 
     "heic-decode": ["heic-decode@2.1.0", "", { "dependencies": { "libheif-js": "^1.19.8" } }, "sha512-0fB3O3WMk38+PScbHLVp66jcNhsZ/ErtQ6u2lMYu/YxXgbBtl+oKOhGQHa4RpvE68k8IzbWkABzHnyAIjR758A=="],
 
-    "hono": ["hono@4.12.10", "", {}, "sha512-mx/p18PLy5og9ufies2GOSUqep98Td9q4i/EF6X7yJgAiIopxqdfIO3jbqsi3jRgTgw88jMDEzVKi+V2EF+27w=="],
+    "hono": ["hono@4.12.30", "", {}, "sha512-emn+JoJjrN9YTpRDS5it/UI2SO9BAE37T6I3d963RxcZ81G9A4pr2SZTEiiaiKbzx+NKRg5BZ89fCL7gCJCUog=="],
 
     "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=="],
 
@@ -431,7 +446,7 @@
 
     "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
 
-    "ip-address": ["ip-address@10.1.0", "", {}, "sha512-XXADHxXmvT9+CRxhXg56LJovE+bmWnEWB78LB83VZTprKTmaC5QfruXocxzTZ2Kl0DNwKuBdlIhjL8LeY8Sf8Q=="],
+    "ip-address": ["ip-address@10.2.0", "", {}, "sha512-/+S6j4E9AHvW9SWMSEY9Xfy66O5PWvVEJ08O0y5JGyEKQpojb0K0GKpz/v5HJ/G0vi3D2sjGK78119oXZeE0qA=="],
 
     "ipaddr.js": ["ipaddr.js@1.9.1", "", {}, "sha512-0KI/607xoxSToH7GjN1FfSbLoU0+btTicjsQSWQlh/hZykN8KpmMf7uYwPW3R+akZ6R/w18ZlXSHBYXiYUPO3g=="],
 
@@ -439,11 +454,13 @@
 
     "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@3.14.2", "", { "dependencies": { "argparse": "^1.0.7", "esprima": "^4.0.0" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-PMSmkqxr106Xa156c2M265Z+FTrPl+oxd/rgOQy2tijQeK5TxQ43psO1ZCwhVOSdnn+RzkzlRz/eY4BgJBYVpg=="],
+    "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=="],
 
     "json-schema": ["json-schema@0.4.0", "", {}, "sha512-es94M3nTIfsEPisRafak+HDLfHXnKBhV3vU5eqPcS3flIWqcxJWgXHXiey3YrpaNsanY5ei1VoYEbOzijuq9BA=="],
 
@@ -455,7 +472,7 @@
 
     "libheif-js": ["libheif-js@1.19.8", "", {}, "sha512-vQJWusIxO7wavpON1dusciL8Go9jsIQ+EUrckauFYAiSTjcmLAsuJh3SszLpvkwPci3JcL41ek2n+LUZGFpPIQ=="],
 
-    "marked": ["marked@18.0.0", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-2e7Qiv/HJSXj8rDEpgTvGKsP8yYtI9xXHKDnrftrmnrJPaFNM7VRb2YCzWaX4BP1iCJ/XPduzDJZMFoqTCcIMA=="],
+    "marked": ["marked@18.0.6", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-MrV5puXBfuiy6wl6DLaq3BtIJQAJToAd5zt/ZKhRfGRAuFPALE7/4Y7jnxRQoEgK/pBgurGqLyAuRgZ2xOjr6w=="],
 
     "math-intrinsics": ["math-intrinsics@1.1.0", "", {}, "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g=="],
 
@@ -487,7 +504,7 @@
 
     "parseurl": ["parseurl@1.3.3", "", {}, "sha512-CiyeOxFT/JZyN5m0z9PfXw4SCBJ6Sygz1Dpl0wqjlhDEGGBP1GnsUVEL0p63hoG1fcj3fHynXi9NYO4nWOL+qQ=="],
 
-    "path-expression-matcher": ["path-expression-matcher@1.5.0", "", {}, "sha512-cbrerZV+6rvdQrrD+iGMcZFEiiSrbv9Tfdkvnusy6y0x0GKBXREFg/Y65GhIfm0tnLntThhzCnfKwp1WRjeCyQ=="],
+    "path-expression-matcher": ["path-expression-matcher@1.6.2", "", {}, "sha512-enSlaiat05iasnzmgNxRj8reFdj3puY2QpNgP1aPIaVfT6nn9ICuPoFlKHk8EN22HcwewshO+mN2DGbkCEOtqQ=="],
 
     "path-key": ["path-key@3.1.1", "", {}, "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q=="],
 
@@ -503,7 +520,7 @@
 
     "pure-rand": ["pure-rand@8.4.0", "", {}, "sha512-IoM8YF/jY0hiugFo/wOWqfmarlE6J0wc6fDK1PhftMk7MGhVZl88sZimmqBBFomLOCSmcCCpsfj7wXASCpvK9A=="],
 
-    "qs": ["qs@6.15.0", "", { "dependencies": { "side-channel": "^1.1.0" } }, "sha512-mAZTtNCeetKMH+pSjrb76NAM8V9a05I9aBZOHztWy/UqcJdQYNsf59vrRKWnojAT9Y+GbIvoTBC++CPHqpDBhQ=="],
+    "qs": ["qs@6.15.3", "", { "dependencies": { "es-define-property": "^1.0.1", "side-channel": "^1.1.1" } }, "sha512-O9gl3zCl5h5blw1KGUzQKhA5oUXSl8rwUIM5o0S3nCXMliSvy5Dzx7/DJcI+SwgICv+IneSZwhBh1oSyEHA71A=="],
 
     "range-parser": ["range-parser@1.2.1", "", {}, "sha512-Hrgsx+orqoygnmhFbKaHE6c296J+HTAQXoxEF6gNupROmmGJRoyzfG3ccAveqCBrwr/2yxQ5BVd/GTl5agOwSg=="],
 
@@ -529,9 +546,9 @@
 
     "shebang-regex": ["shebang-regex@3.0.0", "", {}, "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A=="],
 
-    "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": ["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-list": ["side-channel-list@1.0.0", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.3" } }, "sha512-FCLHtRD/gnpCiCHEiJLOwdmFP+wzCmDEkc9y7NsYxeF4u7Btsn1ZuwgwJGxImImHicJArLP4R0yX4c2KCrMrTA=="],
+    "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-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=="],
 
@@ -543,7 +560,7 @@
 
     "strip-bom-string": ["strip-bom-string@1.0.0", "", {}, "sha512-uCC2VHvQRYu+lMh4My/sFNmF2klFymLX1wHJeXnbEJERpV/ZsVuonzerjfrGpIGF7LBVa1O7i9kjiWvJiFck8g=="],
 
-    "strnum": ["strnum@2.2.3", "", {}, "sha512-oKx6RUCuHfT3oyVjtnrmn19H1SiCqgJSg+54XqURKp5aCMbrXrhLjRN9TjuwMjiYstZ0MzDrHqkGZ5dFTKd+zg=="],
+    "strnum": ["strnum@2.4.1", "", { "dependencies": { "anynum": "^1.0.1" } }, "sha512-M9eUSMT2dCB2cTNPG7UYj6KuK7RJR2SN2+yCV/fTW3xzTCS6EaGZ5pSMgDIjB7r8zSfTGk+dvvn9rTjpVS9Mwg=="],
 
     "toidentifier": ["toidentifier@1.0.1", "", {}, "sha512-o5sSPKEkg/DIQNmH43V0/uerLrpzVedkUh8tGNvaeXpfpuwjKenlSox/2O/BTlZUtEe+JG7s5YhEz608PlAHRA=="],
 
@@ -577,6 +594,8 @@
 
     "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=="],
@@ -595,12 +614,16 @@
 
     "@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=="],

bunfig.toml

@@ -13,4 +13,9 @@ 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.
-preload = ["./test/helpers/legacy-embedding-preload.ts"]
+#
+# #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"]

docs/ENGINES.md

@@ -148,6 +148,51 @@ 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+)

docs/TESTING.md

@@ -3,6 +3,8 @@
 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:

docs/guides/live-sync.md

@@ -131,6 +131,16 @@ 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,

docs/guides/multi-language-fts.md

@@ -0,0 +1,97 @@
+# 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.

docs/guides/multi-source-brains.md

@@ -114,8 +114,11 @@ Flip later with `gbrain sources federate <id>` / `unfederate <id>`.
 Full subcommand reference:
 
 ```
-gbrain sources add <id> --path <p> [--name <n>] [--federated|--no-federated]
+gbrain sources add <id> --path <p> [--name <n>] [--federated|--no-federated] [--force]
                                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).
@@ -128,6 +131,47 @@ 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

docs/guides/skillpacks-as-scaffolding.md

@@ -131,7 +131,9 @@ into gbrain so other clients can scaffold it. Default behavior:
   `~/.gbrain/harvest-private-patterns.txt` plus built-in defaults
   (canonical private fork name, common email regex, Slack channel pattern). Any
   match → rollback (delete the harvested files) and exit non-zero.
-- `openclaw.plugin.json` updated with the new slug, sorted.
+- `openclaw.plugin.json` updated with the new slug, sorted. Harvest must preserve
+  the top-level OpenClaw-native plugin fields (`id`, `configSchema`, `contracts`)
+  because OpenClaw validates those before it can install the package.
 - `--no-lint` bypasses the linter (after a manual editorial scrub).
 
 Use the `skillpack-harvest` skill (its companion editorial workflow)

docs/tutorials/improving-skills-with-skillopt.md

@@ -233,13 +233,14 @@ keep it or `git checkout` to throw it away. Nothing is committed for you.
 
 **For a skill that ships with gbrain** (anything under the gbrain repo's own
 `skills/`): SkillOpt refuses to overwrite it by default and writes the winner to
-`skills/<name>/skillopt/best.md` instead, so an optimization pass can never
-silently mutate a skill other people depend on. Two ways to handle that:
+`skills/<name>/skillopt/proposed.md` instead (while keeping `best.md` as the
+optimizer's current-best pointer), so an optimization pass can never silently
+mutate a skill other people depend on. Two ways to handle that:
 
 ```bash
 # See the proposed improvement without touching SKILL.md (works for ANY skill):
 gbrain skillopt meeting-prep --split 1:1:1 --no-mutate
-# → writes skills/meeting-prep/skillopt/best.md (the proposed rewrite), prints its path. Copy what you want.
+# → writes skills/meeting-prep/skillopt/proposed.md, updates best.md, and prints the proposal path.
 
 # Actually rewrite a bundled skill (explicit opt-in + an independent held-out set):
 gbrain skillopt brain-ops --split 1:1:1 --allow-mutate-bundled \

llms-full.txt

@@ -1565,8 +1565,8 @@ GBrain is designed to be installed and operated by an AI agent. The fastest path
 
 If you don't already have an AI agent platform running, start with one of these. Both are designed to read GBrain's install protocol and execute it:
 
-- **[OpenClaw](https://github.com/openclawagents/openclaw)** — deploy [AlphaClaw on Render](https://render.com/deploy?repo=https://github.com/chrysb/alphaclaw) (one click, 8GB+ RAM)
-- **[Hermes](https://github.com/openclawagents/hermes)** — deploy on [Railway](https://github.com/praveen-ks-2001/hermes-agent-template) (one click)
+- **[OpenClaw](https://github.com/openclaw/openclaw)** — deploy [AlphaClaw on Render](https://render.com/deploy?repo=https://github.com/chrysb/alphaclaw) (one click, 8GB+ RAM)
+- **[Hermes](https://github.com/NousResearch/hermes-agent)** — deploy on [Railway](https://github.com/praveen-ks-2001/hermes-agent-template) (one click)
 
 Then paste this into your agent:
 
@@ -1752,6 +1752,24 @@ 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).
@@ -2095,6 +2113,51 @@ 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+)
@@ -2767,6 +2830,16 @@ 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,

openclaw.plugin.json

@@ -1,4 +1,5 @@
 {
+  "id": "gbrain-context-engine",
   "name": "gbrain",
   "version": "0.32.3.0",
   "description": "Personal knowledge brain with Postgres + pgvector hybrid search",

package.json

@@ -118,8 +118,8 @@
     "express-rate-limit": "^7.5.0",
     "gray-matter": "^4.0.3",
     "heic-decode": "^2.1.0",
-    "js-yaml": "^3.14.2",
-    "marked": "^18.0.0",
+    "js-yaml": "^3.15.0",
+    "marked": "^18.0.2",
     "openai": "^4.0.0",
     "pgvector": "^0.2.0",
     "postgres": "^3.4.0",
@@ -144,5 +144,16 @@
     "bun": ">=1.3.10"
   },
   "license": "MIT",
-  "version": "0.42.61.0"
+  "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"
+  }
 }

skills/skillpack-harvest/SKILL.md

@@ -266,4 +266,5 @@ editorial pass.
   (e.g. `src/commands/<slug>.ts` if the host SKILL.md declares it
   in frontmatter)
 - gbrain's `openclaw.plugin.json` — adds the slug to `skills:`
-  array, sorted alphabetically
+  array, sorted alphabetically, without removing OpenClaw-native plugin fields
+  like `id`, `configSchema`, or `contracts`

skills/testing/SKILL.md

@@ -57,6 +57,8 @@ This mode guarantees:
 - `skills/manifest.json` lists every skill directory
 - `skills/RESOLVER.md` references every skill in the manifest
 - `openclaw.plugin.json` `skills[]` round-trips with both
+- `openclaw.plugin.json` keeps OpenClaw install-required native plugin fields
+  (`id`, object `configSchema`, and `contracts.contextEngines` when applicable)
 - No MECE violations (duplicate triggers across skills)
 
 ### Phases
@@ -72,7 +74,7 @@ This mode guarantees:
 ### Automation
 
 ```bash
-bun test test/skills-conformance.test.ts test/resolver.test.ts
+bun test test/skills-conformance.test.ts test/resolver.test.ts test/openclaw-plugin-manifest.test.ts
 ```
 
 The CI-gated check is the package.json `test` script.

src/admin-embedded.ts

@@ -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 2026-05-24.
+// Source: admin/dist/ at 2026-05-27.
 //
 // 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_DqP_zmqH_js from '../admin/dist/assets/index-DqP-zmqH.js' with { type: 'file' };
+import A_0_assets_index_CoGEje3__js from '../admin/dist/assets/index-CoGEje3-.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-DqP-zmqH.js": { path: A_0_assets_index_DqP_zmqH_js as unknown as string, mime: "application/javascript; charset=utf-8" },
+  "/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-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" },
 };

src/cli.ts

@@ -54,7 +54,7 @@ export function bigintToStringReplacer(_key: string, value: unknown): unknown {
 }
 
 // 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', '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']);
+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', 'maintain', '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']);
 // 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.
@@ -78,6 +78,8 @@ const CLI_ONLY_SELF_HELP = new Set([
   'capture',
   // v0.42 self-upgrade ships its own usage (flags + the agent-skill story).
   'self-upgrade',
+  // maintain (#3015) prints its own usage block (modes + not-auto-applied list).
+  'maintain',
   // 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
@@ -998,6 +1000,13 @@ 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',
 ]);
 
 /**
@@ -1035,6 +1044,9 @@ 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.',
 };
 
 /**
@@ -1593,6 +1605,27 @@ 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 {
@@ -1726,6 +1759,11 @@ async function handleCliOnly(command: string, args: string[]) {
         await runOrphans(engine, args);
         break;
       }
+      case 'maintain': {
+        const { runMaintain } = await import('./commands/maintain.ts');
+        await runMaintain(engine, args);
+        break;
+      }
       // v0.32.7 CJK wave — post-upgrade markdown re-chunk sweep.
       // v0.36 Phase 3 wave — `gbrain reindex --multimodal` re-embeds content_chunks
       // into the unified Voyage multimodal-3 column.
@@ -2001,6 +2039,15 @@ 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
@@ -2249,7 +2296,7 @@ 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)
-  sync --install-cron                Install persistent sync daemon
+                                     See also: autopilot --install (continuous 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
@@ -2315,7 +2362,14 @@ 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
+  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, ...)
   sync --all                         Sync all sources with a local_path
   sync --source <id>                 Sync one specific source
   repos ...                          DEPRECATED alias for 'sources' (v0.19.0)
@@ -2329,6 +2383,9 @@ 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)

src/commands/auth.ts

@@ -346,6 +346,12 @@ 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 {
@@ -356,6 +362,12 @@ 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;
@@ -389,6 +401,34 @@ 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}`);
     }
@@ -405,7 +445,7 @@ 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]');
+    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]');
     process.exit(1);
   }
   let parsed: RegisterClientArgs;
@@ -413,17 +453,28 @@ 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]');
+    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]');
     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,
+        name, grantTypes, scopes, redirectUris, sourceId, federatedRead, tokenEndpointAuthMethod, agentBindings,
       );
       const effectiveFederated = federatedRead && federatedRead.length > 0 ? federatedRead : [sourceId];
       const effectiveAuthMethod = tokenEndpointAuthMethod || 'client_secret_post';
@@ -441,7 +492,16 @@ async function registerClient(name: string, args: string[]) {
         console.log(`  Redirect URIs:       ${redirectUris.join(', ')}`);
       }
       console.log(`  Write source:        ${sourceId}`);
-      console.log(`  Federated reads:     ${effectiveFederated.join(', ')}\n`);
+      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('');
       if (clientSecret) {
         console.log('Save the client secret — it will not be shown again.');
       } else {
@@ -527,6 +587,12 @@ 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
 `);

src/commands/autopilot.ts

@@ -17,7 +17,7 @@
  *   gbrain autopilot --status [--json]
  */
 
-import { existsSync, readFileSync, writeFileSync, mkdirSync, appendFileSync, utimesSync, unlinkSync } from 'fs';
+import { existsSync, readFileSync, writeFileSync, mkdirSync, appendFileSync, utimesSync, unlinkSync, chmodSync } from 'fs';
 import { setCliExitVerdict } from '../core/cli-force-exit.ts';
 import { join } from 'path';
 import { execSync } from 'child_process';
@@ -109,7 +109,21 @@ function logError(phase: string, e: unknown) {
  */
 export function resolveGbrainCliPath(): string {
   try {
-    const which = execSync('which gbrain', { encoding: 'utf-8', stdio: ['ignore', 'pipe', 'ignore'] }).trim();
+    // #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();
     if (which) return which;
   } catch { /* not on $PATH — fall through */ }
 
@@ -123,7 +137,14 @@ export function resolveGbrainCliPath(): string {
     return 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.');
+  // #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)}`,
+  );
 }
 
 export function shouldSpawnAutopilotWorker(args: string[]): boolean {
@@ -1242,7 +1263,14 @@ function installLaunchd(wrapperPath: string, home: string, repoPath: string) {
   try {
     const agentsDir = join(home, 'Library', 'LaunchAgents');
     mkdirSync(agentsDir, { recursive: true });
-    writeFileSync(plistPath(), plist);
+    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);
     execSync(`launchctl load "${plistPath()}"`, { stdio: 'pipe' });
     console.log('Installed launchd service: com.gbrain.autopilot');
     console.log(`  Repo: ${repoPath}`);
@@ -1332,7 +1360,11 @@ export function migrateSystemdUnitToRestartAlways(): { rewritten: boolean; reaso
     return { rewritten: false, reason: 'hand-edited' };
   }
   try {
-    writeFileSync(unitPath, generateSystemdUnit(execMatch![1]));
+    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);
     try {
       execSync('systemctl --user daemon-reload', { stdio: 'pipe', timeout: 10_000 });
     } catch {
@@ -1349,7 +1381,10 @@ function installSystemd(wrapperPath: string, repoPath: string) {
   try {
     const unitPath = systemdUnitPath();
     mkdirSync(join(process.env.HOME || '', '.config', 'systemd', 'user'), { recursive: true });
-    writeFileSync(unitPath, unit);
+    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);
     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');

src/commands/config.ts

@@ -98,9 +98,25 @@ export async function runConfig(engine: BrainEngine, args: string[]) {
   const value = args[2];
 
   if (action === 'get' && key) {
-    const val = await engine.getConfig(key);
-    if (val !== null) {
-      console.log(val);
+    // #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`);
+      }
     } else {
       console.error(`Config key not found: ${key}`);
       process.exit(1);

src/commands/doctor.ts

@@ -3056,7 +3056,7 @@ export async function computeConversationFactsBacklogCheck(
     const typesRaw = await engine.getConfig(
       'cycle.conversation_facts_backfill.types',
     );
-    let types = ['conversation', 'meeting', 'slack', 'email'];
+    let types = ['conversation', 'meeting', 'slack', 'email', 'imessage', 'imessage-daily'];
     if (typesRaw) {
       try {
         const parsed = JSON.parse(typesRaw);
@@ -4345,7 +4345,7 @@ export async function buildChecks(
 
   // 2. Skill conformance (SKILL group — gated)
   if (scope === 'all' && skillsDir) {
-    const conformanceResult = checkSkillConformance(skillsDir);
+    const conformanceResult = skillConformanceCheck(skillsDir);
     checks.push(conformanceResult);
   }
 
@@ -4927,8 +4927,8 @@ export async function buildChecks(
     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'] as const;
-      // PageFilters supports singular `type` only; iterate the 4 types
+      const allowedTypes = ['conversation', 'meeting', 'slack', 'email', 'imessage', 'imessage-daily'] as const;
+      // PageFilters supports singular `type` only; iterate the allowed types
       // and cap at ~50/each to land at ~200 total max.
       const sample: import('../core/types.ts').Page[] = [];
       for (const t of allowedTypes) {
@@ -5138,13 +5138,7 @@ export async function buildChecks(
         checks.push({
           name: 'multi_source_drift',
           status: 'warn',
-          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.)`,
+          message: multiSourceDriftAdvice(result.count, sampleStr),
         });
       } else {
         checks.push({
@@ -7184,9 +7178,17 @@ 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(r.storage_path);
+          fs.statSync(abs);
         } catch {
           vanished++;
           if (vanishedPaths.length < 5) vanishedPaths.push(r.storage_path);
@@ -7430,15 +7432,13 @@ function printAutoFixReport(report: AutoFixReport, dryRun: boolean, jsonOutput:
 
 
 /** Quick skill conformance check — frontmatter + required sections */
-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' };
-  }
-
+export function skillConformanceCheck(skillsDir: string): Check {
   try {
-    const manifest = JSON.parse(readFileSync(manifestPath, 'utf-8'));
-    const skills = manifest.skills || [];
+    // 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;
     let passing = 0;
     const failing: string[] = [];
 
@@ -7458,7 +7458,8 @@ function checkSkillConformance(skillsDir: string): Check {
     }
 
     if (failing.length === 0) {
-      return { name: 'skill_conformance', status: 'ok', message: `${passing}/${skills.length} skills pass` };
+      const derivedNote = manifest.derived ? ' (derived from SKILL.md files)' : '';
+      return { name: 'skill_conformance', status: 'ok', message: `${passing}/${skills.length} skills pass${derivedNote}` };
     }
     return {
       name: 'skill_conformance',
@@ -7466,7 +7467,7 @@ function checkSkillConformance(skillsDir: string): Check {
       message: `${passing}/${skills.length} pass. Failing: ${failing.join(', ')}`,
     };
   } catch {
-    return { name: 'skill_conformance', status: 'warn', message: 'Could not parse manifest.json' };
+    return { name: 'skill_conformance', status: 'warn', message: 'Could not load or derive skills manifest' };
   }
 }
 
@@ -8074,3 +8075,24 @@ 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.`
+  );
+}

src/commands/dream.ts

@@ -76,6 +76,18 @@ 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}$/;
@@ -105,6 +117,14 @@ 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)
@@ -214,6 +234,35 @@ 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'),
@@ -229,6 +278,7 @@ function parseArgs(args: string[]): DreamArgs {
     source,
     drain,
     windowSeconds,
+    once,
   };
 }
 
@@ -310,6 +360,17 @@ 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
@@ -353,6 +414,7 @@ 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
@@ -594,6 +656,9 @@ 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) {

src/commands/embed.ts

@@ -581,7 +581,7 @@ async function embedPage(
   for (let j = 0; j < toEmbed.length; j++) {
     embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
   }
-  const updated: ChunkInput[] = chunks.map(c => ({
+  const updated: ChunkInput[] = chunks.map(c => preserveCodeMetadata(c, {
     chunk_index: c.chunk_index,
     chunk_text: c.chunk_text,
     chunk_source: c.chunk_source,
@@ -605,6 +605,31 @@ async function embedPage(
   slog(`${slug}: embedded ${toEmbed.length} chunks`);
 }
 
+/**
+ * Carry code-chunk metadata (language, symbol_name, symbol_type, line range,
+ * parent scope, doc comment, qualified name) from a loaded Chunk back into a
+ * ChunkInput destined for upsertChunks.
+ *
+ * Issue #769: every re-embed used to strip these fields, and upsertChunks
+ * overwrites (does not COALESCE) the metadata columns from EXCLUDED, so
+ * each pass clobbered code-def's primary index to NULL. Pulling the
+ * preservation into one helper keeps the three re-embed call sites
+ * (embedPage, embedAll non-stale, embedAllStale) in lock-step.
+ */
+function preserveCodeMetadata(loaded: any, base: ChunkInput): ChunkInput {
+  return {
+    ...base,
+    language: loaded.language ?? undefined,
+    symbol_name: loaded.symbol_name ?? undefined,
+    symbol_type: loaded.symbol_type ?? undefined,
+    start_line: loaded.start_line ?? undefined,
+    end_line: loaded.end_line ?? undefined,
+    parent_symbol_path: loaded.parent_symbol_path ?? undefined,
+    doc_comment: loaded.doc_comment ?? undefined,
+    symbol_name_qualified: loaded.symbol_name_qualified ?? undefined,
+  };
+}
+
 async function embedAll(
   engine: BrainEngine,
   staleOnly: boolean,
@@ -717,8 +742,10 @@ async function embedAll(
       for (let j = 0; j < toEmbed.length; j++) {
         embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
       }
-      // Preserve ALL chunks, only update embeddings for stale ones
-      const updated: ChunkInput[] = chunks.map(c => ({
+      // Preserve ALL chunks, only update embeddings for stale ones.
+      // preserveCodeMetadata threads code-chunk metadata (#769) so re-embed
+      // doesn't clobber language/symbol_name/symbol_type to NULL.
+      const updated: ChunkInput[] = chunks.map(c => preserveCodeMetadata(c, {
         chunk_index: c.chunk_index,
         chunk_text: c.chunk_text,
         chunk_source: c.chunk_source,
@@ -1012,7 +1039,10 @@ async function embedAllStale(
           for (let j = 0; j < stale.length; j++) {
             staleIdxToEmbedding.set(stale[j].chunk_index, embeddings[j]);
           }
-          const merged: ChunkInput[] = existing.map(c => ({
+          // preserveCodeMetadata threads code-chunk metadata (#769) so the
+          // autopilot --stale path doesn't clobber language/symbol_name/etc
+          // to NULL on every cycle.
+          const merged: ChunkInput[] = existing.map(c => preserveCodeMetadata(c, {
             chunk_index: c.chunk_index,
             chunk_text: c.chunk_text,
             chunk_source: c.chunk_source,

src/commands/enrich.ts

@@ -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 { isAvailable, chat, getChatModel, withBudgetTracker } from '../core/ai/gateway.ts';
+import { configureGatewayIfUninitialized, 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';
@@ -807,7 +807,9 @@ export async function runEnrich(engine: BrainEngine, args: string[]): Promise<vo
     process.exit(1);
   }
 
-  // Chat gateway required for non-dry-run.
+  // Chat gateway is required for non-dry-run. Recover a cold singleton before
+  // reporting an availability error (#2590).
+  if (!parsed.dryRun && !isAvailable('chat')) configureGatewayIfUninitialized();
   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);

src/commands/extract-conversation-facts.ts

@@ -71,7 +71,7 @@ import {
   extractFactsFromTurn,
   isFactsExtractionEnabled,
 } from '../core/facts/extract.ts';
-import { isAvailable, withBudgetTracker } from '../core/ai/gateway.ts';
+import { configureGatewayIfUninitialized, isAvailable, withBudgetTracker } from '../core/ai/gateway.ts';
 import { BudgetTracker, BudgetExhausted } from '../core/budget/budget-tracker.ts';
 import { listSources } from '../core/sources-ops.ts';
 import {
@@ -81,7 +81,6 @@ 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
@@ -141,7 +140,14 @@ 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'] as const;
+export const ALLOWED_TYPES = [
+  'conversation',
+  'meeting',
+  'slack',
+  'email',
+  'imessage',
+  'imessage-daily',
+] as const;
 export type AllowedType = (typeof ALLOWED_TYPES)[number];
 
 /**
@@ -757,6 +763,12 @@ 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}`,
       }));
@@ -1069,7 +1081,8 @@ export async function runExtractConversationFactsCore(
       }
       // Fall through to receipt+rollup write so the partial run is
       // still observable in extract_health doctor + extracts/ pages.
-      await writeRunReceiptAndRollup(engine, sourceId, result, /* halted */ true);
+      // ...but not under --dry-run: a preview must not persist cache state.
+      if (!dryRun) await writeRunReceiptAndRollup(engine, sourceId, result, /* halted */ true);
       // Return partial result — caller (CLI / Minion) decides how to
       // surface. NOT a thrown failure.
       return result;
@@ -1081,7 +1094,9 @@ 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.
-  await writeRunReceiptAndRollup(engine, sourceId, result, /* halted */ false);
+  // --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);
 
   return result;
 }
@@ -1351,7 +1366,9 @@ export async function runExtractConversationFacts(
     process.exit(1);
   }
 
-  // Chat gateway is required for non-dry-run.
+  // Chat gateway is required for non-dry-run. Recover a cold singleton before
+  // reporting an availability error (#2590).
+  if (!parsed.dryRun && !isAvailable('chat')) configureGatewayIfUninitialized();
   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);

src/commands/extract.ts

@@ -188,7 +188,7 @@ 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/`, `ops/`, README.md, etc.). Now: pruneDir skips entire vendor
+  // (`.raw/`, 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 }[] = [];
@@ -568,6 +568,20 @@ export interface ExtractOpts {
    * 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;
 }
 
 /**
@@ -606,7 +620,7 @@ 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);
+    const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers, opts.signal, opts.sourceId);
     result.links_created = r.links_created;
     result.timeline_entries_created = r.timeline_created;
     result.pages_processed = r.pages;
@@ -615,12 +629,12 @@ 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);
+    const r = await extractLinksFromDir(engine, opts.dir, dryRun, jsonMode, workers, opts.signal, opts.sourceId);
     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);
+    const r = await extractTimelineFromDir(engine, opts.dir, dryRun, jsonMode, workers, opts.signal, opts.sourceId);
     result.timeline_entries_created = r.created;
     result.pages_processed = Math.max(result.pages_processed, r.pages);
   }
@@ -941,11 +955,21 @@ 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,
       });
     }
@@ -985,6 +1009,8 @@ async function extractForSlugs(
   // 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);
@@ -1065,7 +1091,9 @@ async function extractForSlugs(
               if (!jsonMode) console.log(`  ${link.from_slug} → ${link.to_slug} (${link.link_type})`);
               linksCreated++;
             } else {
-              linkBatch.push(link);
+              linkBatch.push(sourceId
+                ? { ...link, from_source_id: sourceId, to_source_id: sourceId, origin_source_id: sourceId }
+                : link);
               if (linkBatch.length >= BATCH_SIZE) await flushLinks();
             }
           }
@@ -1078,7 +1106,7 @@ 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 });
+              timelineBatch.push({ slug: entry.slug, date: entry.date, source: entry.source, summary: entry.summary, detail: entry.detail, ...(sourceId ? { source_id: sourceId } : {}) });
               if (timelineBatch.length >= BATCH_SIZE) await flushTimeline();
             }
           }
@@ -1107,6 +1135,9 @@ async function extractLinksFromDir(
   // 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)));
@@ -1163,7 +1194,9 @@ async function extractLinksFromDir(
             if (!jsonMode) console.log(`  ${link.from_slug} → ${link.to_slug} (${link.link_type})`);
             created++;
           } else {
-            batch.push(link);
+            batch.push(sourceId
+              ? { ...link, from_source_id: sourceId, to_source_id: sourceId, origin_source_id: sourceId }
+              : link);
             if (batch.length >= BATCH_SIZE) await flush();
           }
         }
@@ -1186,6 +1219,9 @@ async function extractTimelineFromDir(
   // 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);
 
@@ -1232,7 +1268,7 @@ 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 });
+            batch.push({ slug: entry.slug, date: entry.date, source: entry.source, summary: entry.summary, detail: entry.detail, ...(sourceId ? { source_id: sourceId } : {}) });
             if (batch.length >= BATCH_SIZE) await flush();
           }
         }
@@ -1615,7 +1651,7 @@ async function extractTimelineFromDB(
  * make re-extraction idempotent). EVERY processed page is stamped, including
  * zero-link pages — they WERE processed.
  */
-async function extractStaleFromDB(
+export async function extractStaleFromDB(
   engine: BrainEngine,
   opts: {
     dryRun: boolean;

src/commands/frontmatter.ts

@@ -30,6 +30,7 @@ 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> {
@@ -272,6 +273,13 @@ 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);

src/commands/import.ts

@@ -11,7 +11,9 @@ 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';
@@ -19,6 +21,7 @@ import {
   loadCheckpoint,
   saveCheckpoint,
   clearCheckpoint,
+  resolveImportTargetDir,
   resumeFilter,
 } from '../core/import-checkpoint.ts';
 
@@ -45,7 +48,25 @@ export interface RunImportResult {
 export async function runImport(
   engine: BrainEngine,
   args: string[],
-  opts: { commit?: string; strategy?: SyncStrategy; sourceId?: string; managedBookmark?: boolean } = {},
+  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;
+  } = {},
 ): Promise<RunImportResult> {
   const noEmbed = args.includes('--no-embed');
   const fresh = args.includes('--fresh');
@@ -167,7 +188,19 @@ export async function runImport(
     console.error('Usage: gbrain import <dir> [--no-embed] [--workers N] [--fresh] [--source-id <id>] [--json]');
     process.exit(1);
   }
-  const dir: string = dirArg;  // narrowed; survives closure capture
+  // #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);
+  }
 
   // v0.31.2: collect under the right strategy. Pre-fix this called
   // collectMarkdownFiles unconditionally — code-strategy first sync
@@ -176,13 +209,30 @@ 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}`);
-  const allFiles = collectSyncableFiles(dir, { strategy });
+  let 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';
-  console.log(`Found ${allFiles.length} ${fileTypeLabel} files`);
+  // #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`);
+  }
 
   // Sort newest-first so date-prefixed brain paths get embedded before older ones.
   // See src/core/sort-newest-first.ts for the policy.
@@ -228,6 +278,11 @@ 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.
@@ -238,8 +293,8 @@ 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, relativePath, { noEmbed, sourceId })
-        : await importFile(eng, filePath, relativePath, { noEmbed, sourceId, activePack: importActivePack });
+        ? await importImageFile(eng, filePath, importRelPath, { noEmbed, sourceId })
+        : await importFile(eng, filePath, importRelPath, { noEmbed, sourceId, activePack: importActivePack });
       const _fileMs = Date.now() - _fileT0;
       if (_fileMs > 5000) {
         console.error(`[gbrain phase] import.process_file slow ${_fileMs}ms ${relativePath}`);
@@ -255,7 +310,9 @@ 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.
-          failures.push({ path: relativePath, error: result.error });
+          // #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 });
         } else {
           // 'unchanged' or no-error skip: content_hash matched a prior
           // successful import, so this file IS done for checkpoint purposes.
@@ -273,7 +330,7 @@ export async function runImport(
       }
       errors++;
       skipped++;
-      failures.push({ path: relativePath, error: msg });
+      failures.push({ path: importRelPath, error: msg });
     }
     processed++;
     tickProgress();
@@ -287,6 +344,9 @@ 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(),
@@ -493,12 +553,39 @@ 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);

src/commands/jobs.ts

@@ -7,7 +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 { MinionJob, MinionJobStatus } from '../core/minions/types.ts';
+import type { MinionHandler, MinionJob, MinionJobStatus } from '../core/minions/types.ts';
 import type { PaceKeyOverrides } from '../core/pace-mode.ts';
 import { loadConfig, isThinClient } from '../core/config.ts';
 import { callRemoteTool, unpackToolResult } from '../core/mcp-client.ts';
@@ -22,6 +22,49 @@ 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.
@@ -132,9 +175,23 @@ function formatJobDetail(job: MinionJob): string {
   return lines.join('\n');
 }
 
-export async function runJobs(engine: BrainEngine, args: string[]): Promise<void> {
+export async function runJobs(engineOrNull: BrainEngine | null, 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
 
@@ -217,6 +274,8 @@ 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) {
@@ -1423,7 +1482,7 @@ export async function registerBuiltinHandlers(
     return { ...result, embed_job_id: embedJobId, embed_skip_reason: embedSkipReason };
   });
 
-  worker.register('embed', async (job) => {
+  registerBuiltinJob(worker, engine, '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
@@ -1470,7 +1529,7 @@ 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.
-  worker.register('extract-conversation-facts', async (job) => {
+  registerBuiltinJob(worker, engine, '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) {
@@ -1481,7 +1540,7 @@ export async function registerBuiltinHandlers(
     }
     const types = Array.isArray(job.data.types)
       ? (job.data.types as string[]).filter((t) =>
-          ['conversation', 'meeting', 'slack', 'email'].includes(t),
+          ['conversation', 'meeting', 'slack', 'email', 'imessage', 'imessage-daily'].includes(t),
         )
       : undefined;
     const result = await runExtractConversationFactsCore(engine, {
@@ -1529,7 +1588,7 @@ export async function registerBuiltinHandlers(
   // 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.
-  worker.register('enrich', async (job) => {
+  registerBuiltinJob(worker, engine, 'enrich', async (job) => {
     const { runEnrichCore } = await import('./enrich.ts');
     const sourceId = typeof job.data.sourceId === 'string' ? job.data.sourceId : undefined;
     if (!sourceId) {
@@ -1669,13 +1728,13 @@ export async function registerBuiltinHandlers(
     const { makeContextualReindexHandler } = await import(
       '../core/minions/handlers/contextual-reindex-per-chunk.ts'
     );
-    worker.register('contextual_reindex_per_chunk', makeContextualReindexHandler({ engine }));
+    registerBuiltinJob(worker, engine, '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.
-  worker.register('autopilot-cycle', async (job) => {
+  registerBuiltinJob(worker, engine, '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
@@ -1780,6 +1839,7 @@ export async function registerBuiltinHandlers(
       brainDir: effectiveBrainDir,
       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 () => {
@@ -1817,6 +1877,7 @@ export async function registerBuiltinHandlers(
       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)); },
     });
@@ -1962,17 +2023,18 @@ 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
-  worker.register('synthesize', makePhaseHandler('synthesize'));
-  worker.register('patterns', makePhaseHandler('patterns'));
-  worker.register('consolidate', makePhaseHandler('consolidate'));
+  registerBuiltinJob(worker, engine, 'synthesize', makePhaseHandler('synthesize'));
+  registerBuiltinJob(worker, engine, 'patterns', makePhaseHandler('patterns'));
+  registerBuiltinJob(worker, engine, 'consolidate', makePhaseHandler('consolidate'));
 
   // Open — DB writes only, no LLM spend
-  worker.register('extract_facts', makePhaseHandler('extract_facts'));
+  registerBuiltinJob(worker, engine, 'extract_facts', makePhaseHandler('extract_facts'));
   worker.register('resolve_symbol_edges', makePhaseHandler('resolve_symbol_edges'));
   worker.register('recompute_emotional_weight', makePhaseHandler('recompute_emotional_weight'));
 
@@ -1982,7 +2044,7 @@ 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).
-  worker.register('extract-atoms-drain', async (job) => {
+  registerBuiltinJob(worker, engine, '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;
@@ -2010,7 +2072,7 @@ 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.
-  worker.register('embed-backfill', async (job) => {
+  registerBuiltinJob(worker, engine, 'embed-backfill', async (job) => {
     const { makeEmbedBackfillHandler } = await import('../core/minions/handlers/embed-backfill.ts');
     return await makeEmbedBackfillHandler(engine)(job);
   });
@@ -2031,7 +2093,7 @@ 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.
-  worker.register('extract-takes-from-pages', async (job) => {
+  registerBuiltinJob(worker, engine, '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');
@@ -2058,7 +2120,7 @@ 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).
-  worker.register('embed-catch-up', async (job) => {
+  registerBuiltinJob(worker, engine, 'embed-catch-up', async (job) => {
     const { runEmbedCore } = await import('./embed.ts');
     const data = (job.data ?? {}) as {
       sourceId?: string;

src/commands/maintain.ts

@@ -0,0 +1,224 @@
+/**
+ * gbrain maintain — conservative self-healing maintenance.
+ *
+ * This command automates the safe parts of the operator runbook:
+ *   - stale link/timeline extraction
+ *   - stale per-source dream cycles when doctor reports cycle_freshness
+ *
+ * It deliberately does NOT mutate source files, apply schema-pack upgrades, or
+ * invent semantic hub links. Those need review or a separate command with an
+ * auditable proposal surface.
+ */
+
+import { existsSync } from 'fs';
+import type { BrainEngine } from '../core/engine.ts';
+import type { BrainHealth } from '../core/types.ts';
+import { buildChecks, computeDoctorReport, type DoctorReport, type Check } from './doctor.ts';
+import { extractStaleFromDB } from './extract.ts';
+import { runCycle, type CycleReport } from '../core/cycle.ts';
+
+type ActionStatus = 'ok' | 'would_apply' | 'applied' | 'blocked' | 'skipped';
+
+export interface MaintenanceAction {
+  name: string;
+  status: ActionStatus;
+  message: string;
+  details?: Record<string, unknown>;
+}
+
+export interface MaintainOptions {
+  json: boolean;
+  safe: boolean;
+  dryRun: boolean;
+  help: boolean;
+}
+
+export interface MaintainReport {
+  mode: 'dry-run' | 'safe';
+  before: {
+    health: BrainHealth;
+    doctor: DoctorReport;
+  };
+  actions: MaintenanceAction[];
+  after: {
+    health: BrainHealth;
+    doctor: DoctorReport;
+  };
+}
+
+export function parseMaintainArgs(args: string[]): MaintainOptions {
+  const safe = args.includes('--safe');
+  return {
+    json: args.includes('--json'),
+    safe,
+    dryRun: args.includes('--dry-run') || !safe,
+    help: args.includes('--help') || args.includes('-h'),
+  };
+}
+
+export function extractCycleFreshnessSourceIds(checks: Check[]): string[] {
+  const ids = new Set<string>();
+  for (const check of checks) {
+    if (check.name !== 'cycle_freshness' || check.status === 'ok') continue;
+    const re = /Source '([^']+)' last cycled/g;
+    for (const match of check.message.matchAll(re)) {
+      const id = match[1]?.trim();
+      if (id) ids.add(id);
+    }
+  }
+  return [...ids].sort();
+}
+
+async function buildDoctorReport(engine: BrainEngine): Promise<DoctorReport> {
+  const checks = await buildChecks(engine, ['--json', '--scope=brain']);
+  return computeDoctorReport(checks);
+}
+
+async function runStaleExtraction(
+  engine: BrainEngine,
+  beforeHealth: BrainHealth,
+  dryRun: boolean,
+): Promise<MaintenanceAction> {
+  if (beforeHealth.stale_pages <= 0) {
+    return { name: 'extract_stale', status: 'ok', message: 'No stale pages.' };
+  }
+
+  if (dryRun) {
+    return {
+      name: 'extract_stale',
+      status: 'would_apply',
+      message: `Would run DB-backed stale extraction for ${beforeHealth.stale_pages} page(s).`,
+      details: { stale_pages: beforeHealth.stale_pages },
+    };
+  }
+
+  const result = await extractStaleFromDB(engine, {
+    dryRun: false,
+    jsonMode: false,
+    includeFrontmatter: false,
+    catchUp: false,
+  });
+
+  return {
+    name: 'extract_stale',
+    status: 'applied',
+    message: `Processed ${result.pagesProcessed} stale page(s); ${result.staleRemaining} remain.`,
+    details: {
+      links_created: result.linksCreated,
+      timeline_created: result.timelineCreated,
+      pages_processed: result.pagesProcessed,
+      stale_remaining: result.staleRemaining,
+    },
+  };
+}
+
+async function runCycleFreshnessMaintenance(
+  engine: BrainEngine,
+  beforeDoctor: DoctorReport,
+  dryRun: boolean,
+): Promise<MaintenanceAction[]> {
+  const sourceIds = extractCycleFreshnessSourceIds(beforeDoctor.checks);
+  if (sourceIds.length === 0) {
+    return [{ name: 'cycle_freshness', status: 'ok', message: 'All sources cycled recently.' }];
+  }
+
+  if (dryRun) {
+    return sourceIds.map((sourceId) => ({
+      name: 'cycle_freshness',
+      status: 'would_apply',
+      message: `Would run source-scoped dream cycle for ${sourceId}.`,
+      details: { source_id: sourceId },
+    }));
+  }
+
+  const sources = await engine.listAllSources();
+  const actions: MaintenanceAction[] = [];
+
+  for (const sourceId of sourceIds) {
+    const source = sources.find((s) => s.id === sourceId);
+    const localPath = source?.local_path ?? null;
+    const brainDir = localPath && existsSync(localPath) ? localPath : null;
+    const report: CycleReport = await runCycle(engine, {
+      brainDir,
+      dryRun: false,
+      pull: false,
+      sourceId,
+    });
+    actions.push({
+      name: 'cycle_freshness',
+      status: report.status === 'failed' ? 'blocked' : 'applied',
+      message: `Ran source-scoped dream cycle for ${sourceId}: ${report.status}.`,
+      details: {
+        source_id: sourceId,
+        brain_dir: brainDir,
+        cycle_status: report.status,
+        phases: report.phases.map((p) => ({ phase: p.phase, status: p.status })),
+      },
+    });
+  }
+
+  return actions;
+}
+
+export async function runMaintain(engine: BrainEngine, args: string[]): Promise<MaintainReport | void> {
+  const opts = parseMaintainArgs(args);
+  if (opts.help) {
+    console.log(`Usage: gbrain maintain [--safe] [--dry-run] [--json]
+
+Conservative self-healing maintenance.
+
+Modes:
+  --dry-run   Preview safe actions without writes. Default when --safe is absent.
+  --safe      Apply safe actions: stale extraction and source cycle freshness.
+  --json      Emit a structured before/action/after report.
+
+Not auto-applied:
+  source-file frontmatter fixes, schema-pack upgrades, atom-pack changes,
+  semantic hub-link guesses, and destructive cleanup.
+`);
+    return;
+  }
+
+  const beforeHealth = await engine.getHealth();
+  const beforeDoctor = await buildDoctorReport(engine);
+  const actions: MaintenanceAction[] = [];
+
+  actions.push(await runStaleExtraction(engine, beforeHealth, opts.dryRun));
+  actions.push(...await runCycleFreshnessMaintenance(engine, beforeDoctor, opts.dryRun));
+
+  const afterHealth = await engine.getHealth();
+  const afterDoctor = await buildDoctorReport(engine);
+  const report: MaintainReport = {
+    mode: opts.dryRun ? 'dry-run' : 'safe',
+    before: { health: beforeHealth, doctor: beforeDoctor },
+    actions,
+    after: { health: afterHealth, doctor: afterDoctor },
+  };
+
+  if (opts.json) {
+    console.log(JSON.stringify(report, null, 2));
+  } else {
+    printMaintainReport(report);
+  }
+  return report;
+}
+
+function printMaintainReport(report: MaintainReport): void {
+  console.log(`GBrain maintain (${report.mode})`);
+  console.log(
+    `Before: brain_score=${Math.round(report.before.health.brain_score)}/100 ` +
+    `stale=${report.before.health.stale_pages} islands=${report.before.health.orphan_pages} ` +
+    `doctor=${report.before.doctor.status}`,
+  );
+  for (const action of report.actions) {
+    console.log(`  ${action.status}: ${action.name} — ${action.message}`);
+  }
+  console.log(
+    `After:  brain_score=${Math.round(report.after.health.brain_score)}/100 ` +
+    `stale=${report.after.health.stale_pages} islands=${report.after.health.orphan_pages} ` +
+    `doctor=${report.after.doctor.status}`,
+  );
+  if (report.mode === 'dry-run') {
+    console.log('Run `gbrain maintain --safe` to apply safe actions.');
+  }
+}

src/commands/orphans.ts

@@ -15,6 +15,11 @@
 import type { BrainEngine } from '../core/engine.ts';
 import { createProgress, startHeartbeat } from '../core/progress.ts';
 import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
+import {
+  shouldExcludeFromOrphanReporting,
+  loadOrphanPolicyOverrides,
+  type OrphanPolicyOverrides,
+} from '../core/orphan-policy.ts';
 
 // --- Types ---
 
@@ -32,65 +37,14 @@ export interface OrphanResult {
   excluded: number;
 }
 
-// --- Filter constants ---
-
-/** Slug suffixes that are always auto-generated root files */
-const AUTO_SUFFIX_PATTERNS = ['/_index', '/log'];
-
-/** Page slugs that are pseudo-pages by convention */
-const PSEUDO_SLUGS = new Set(['_atlas', '_index', '_stats', '_orphans', '_scratch', 'claude']);
-
-/** Slug segment that marks raw sources */
-const RAW_SEGMENT = '/raw/';
-
-/** Slug prefixes where no inbound links is expected */
-const DENY_PREFIXES = [
-  'output/',
-  'dashboards/',
-  'scripts/',
-  'templates/',
-  'openclaw/config/',
-];
-
-/** First slug segments where no inbound links is expected */
-const FIRST_SEGMENT_EXCLUSIONS = new Set([
-  'scratch',
-  'thoughts',
-  'catalog',
-  'entities',
-  'raw',
-  'atoms',
-  'skills',
-]);
-
 // --- Filter logic ---
 
 /**
  * Returns true if a slug should be excluded from orphan reporting by default.
  * These are pages where having no inbound links is expected / not a content problem.
  */
-export function shouldExclude(slug: string): boolean {
-  // Pseudo-pages (exact match)
-  if (PSEUDO_SLUGS.has(slug)) return true;
-
-  // Auto-generated suffix patterns
-  for (const suffix of AUTO_SUFFIX_PATTERNS) {
-    if (slug.endsWith(suffix)) return true;
-  }
-
-  // Raw source slugs
-  if (slug.includes(RAW_SEGMENT)) return true;
-
-  // Deny-prefix slugs
-  for (const prefix of DENY_PREFIXES) {
-    if (slug.startsWith(prefix)) return true;
-  }
-
-  // First-segment exclusions
-  const firstSegment = slug.split('/')[0];
-  if (FIRST_SEGMENT_EXCLUSIONS.has(firstSegment)) return true;
-
-  return false;
+export function shouldExclude(slug: string, overrides?: OrphanPolicyOverrides): boolean {
+  return shouldExcludeFromOrphanReporting(slug, overrides);
 }
 
 /**
@@ -156,6 +110,7 @@ export async function findOrphans(
   let allOrphans: { slug: string; title: string; domain: string | null }[];
   let total: number;
   let excludedAll: number;
+  const overrides = includePseudo ? undefined : await loadOrphanPolicyOverrides(engine);
   try {
     allOrphans = await engine.findOrphanPages(
       sourceIds ? { sourceIds } : sourceId ? { sourceId } : undefined,
@@ -184,7 +139,7 @@ export async function findOrphans(
     total = liveRows.length;
     excludedAll = includePseudo
       ? 0
-      : liveRows.reduce((n, r) => n + (shouldExclude(r.slug) ? 1 : 0), 0);
+      : liveRows.reduce((n, r) => n + (shouldExclude(r.slug, overrides) ? 1 : 0), 0);
   } finally {
     stopHb();
     progress.finish();
@@ -192,7 +147,7 @@ export async function findOrphans(
 
   const filtered = includePseudo
     ? allOrphans
-    : allOrphans.filter(row => !shouldExclude(row.slug));
+    : allOrphans.filter(row => !shouldExclude(row.slug, overrides));
 
   const orphans: OrphanPage[] = filtered.map(row => ({
     slug: row.slug,

src/commands/providers.ts

@@ -7,6 +7,7 @@
 
 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';
@@ -33,16 +34,19 @@ interface ProviderOption {
 
 function configureFromEnv(): void {
   const config = loadConfig();
-  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,
-    provider_chat_options: config?.provider_chat_options,
-    env: { ...process.env },
-  });
+  // 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 } });
 }
 
 export function envReady(recipe: Recipe, env: NodeJS.ProcessEnv = process.env): boolean {
@@ -137,7 +141,12 @@ EXAMPLES
 }
 
 function runList(_args: string[]): void {
-  console.log(formatRecipeTable(listRecipes()));
+  // 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));
 }
 
 async function runTest(args: string[]): Promise<void> {
@@ -164,8 +173,18 @@ 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 {
-      const cfg = loadConfig();
+      cfg = loadConfig();
       const configuredModel = tpArg === 'embedding' ? cfg?.embedding_model : cfg?.chat_model;
       if (!configuredModel) {
         console.error(
@@ -181,17 +200,27 @@ 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

src/commands/reindex-search-vector.ts

@@ -0,0 +1,282 @@
+/**
+ * `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 });
+}

src/commands/remote.ts

@@ -105,13 +105,19 @@ function printHelp(): void {
 async function runRemotePing(config: NonNullable<ReturnType<typeof loadConfig>>, args: string[]): Promise<void> {
   const { json, timeoutMs } = parseFlags(args);
 
-  let submitted: { id: number; name: string; state: string };
+  // 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 };
   try {
     const res = await callRemoteTool(config, 'submit_job', {
       name: 'autopilot-cycle',
       data: { phases: ['sync', 'extract', 'embed'] },
     });
-    submitted = unpackToolResult<{ id: number; name: string; state: string }>(res);
+    submitted = unpackToolResult<{ id: number; name: string; status: string }>(res);
   } catch (e) {
     return failPing(e, json);
   }
@@ -122,43 +128,43 @@ async function runRemotePing(config: NonNullable<ReturnType<typeof loadConfig>>,
 
   const startMs = Date.now();
   let attempt = 0;
-  let lastState = submitted.state;
+  let lastState = submitted.status;
   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; state: string; failed_reason?: string };
+    let job: { id: number; status: string; failed_reason?: string };
     try {
       const res = await callRemoteTool(config, 'get_job', { id: submitted.id });
-      job = unpackToolResult<{ id: number; state: string; failed_reason?: string }>(res);
+      job = unpackToolResult<{ id: number; status: 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.state !== lastState) {
-      lastState = job.state;
-      if (!json) console.error(`  job #${submitted.id} → ${job.state}`);
+    if (job.status !== lastState) {
+      lastState = job.status;
+      if (!json) console.error(`  job #${submitted.id} → ${job.status}`);
     }
 
     const terminal = ['completed', 'failed', 'dead', 'cancelled'];
-    if (terminal.includes(job.state)) {
-      const ok = job.state === 'completed';
+    if (terminal.includes(job.status)) {
+      const ok = job.status === 'completed';
       if (json) {
         console.log(JSON.stringify({
           status: ok ? 'success' : 'error',
           job_id: submitted.id,
-          state: job.state,
+          state: job.status,
           ...(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 ${job.state}${job.failed_reason ? `: ${job.failed_reason}` : ''}.`);
+          : `\nautopilot-cycle ended ${job.status}${job.failed_reason ? `: ${job.failed_reason}` : ''}.`);
       }
       process.exit(ok ? 0 : 1);
     }

src/commands/schema.ts

@@ -48,7 +48,7 @@ import {
 } from '../core/schema-pack/index.ts';
 import type { SchemaPackManifest, PackPrimitive } from '../core/schema-pack/manifest-v1.ts';
 import { PACK_PRIMITIVES } from '../core/schema-pack/manifest-v1.ts';
-import { gbrainPath, loadConfig, configPath } from '../core/config.ts';
+import { gbrainPath, loadConfig, configPath, toEngineConfig } from '../core/config.ts';
 
 export async function runSchema(args: string[]): Promise<void> {
   const sub = args[0];
@@ -434,16 +434,12 @@ function parseFlags(args: string[]): ParsedFlags {
 
 async function withConnectedEngine<T>(fn: (engine: import('../core/engine.ts').BrainEngine) => Promise<T>): Promise<T> {
   const { createEngine } = await import('../core/engine-factory.ts');
-  const cfg = loadConfig() ?? {};
-  const engineKind = (cfg as { engine?: string }).engine === 'postgres' ? 'postgres' : 'pglite';
+  const cfg = loadConfig() ?? { engine: 'pglite' as const };
   // PR #1321 (closed) defensive fix retained: build the EngineConfig once and
   // pass it to BOTH createEngine and engine.connect. The factory captures
   // config at construction; explicit re-pass at connect() is defense in depth
   // against future engine implementations that read URL from connect-time.
-  const connectConfig: import('../core/types.ts').EngineConfig = {
-    engine: engineKind,
-    database_url: (cfg as { database_url?: string }).database_url,
-  };
+  const connectConfig = toEngineConfig(cfg);
   const engine = await createEngine(connectConfig);
   await engine.connect(connectConfig);
   try {

src/commands/serve-http.ts

@@ -22,6 +22,7 @@ import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/
 import { ListToolsRequestSchema, CallToolRequestSchema } from '@modelcontextprotocol/sdk/types.js';
 import { mcpAuthRouter } from '@modelcontextprotocol/sdk/server/auth/router.js';
 import { requireBearerAuth } from '@modelcontextprotocol/sdk/server/auth/middleware/bearerAuth.js';
+import { OAuthTokenRevocationRequestSchema } from '@modelcontextprotocol/sdk/shared/auth.js';
 import type { BrainEngine } from '../core/engine.ts';
 import { operations, OperationError } from '../core/operations.ts';
 import type { OperationContext, AuthInfo } from '../core/operations.ts';
@@ -37,6 +38,7 @@ import { VERSION } from '../version.ts';
 import * as db from '../core/db.ts';
 import { sqlQueryForEngine, executeRawJsonb } from '../core/sql-query.ts';
 import { MinionQueue } from '../core/minions/queue.ts';
+import { isRetryableError } from '../core/retry-matcher.ts';
 import {
   computeContentHash,
   validateIngestionEvent,
@@ -745,6 +747,93 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
     }
   });
 
+  // The SDK's /revoke handler compares the presented secret with
+  // client.client_secret as plaintext. GBrain stores only a SHA-256 hash, so
+  // confidential clients need the same hash-aware validation used above for
+  // authorization_code and refresh_token exchanges. Public clients present no
+  // secret and continue through to the SDK's PKCE-compatible handler.
+  app.post('/revoke', ccRateLimiter, express.urlencoded({ extended: false }), async (req, res, next) => {
+    res.setHeader('Cache-Control', 'no-store');
+
+    const rawClientId: unknown = req.body?.client_id;
+    const rawBodySecret: unknown = req.body?.client_secret;
+    const authHeader = (req.headers.authorization ?? '').toString();
+
+    // RFC 6749 §2.3: one client-authentication method per request. Reject
+    // duplicates/arrays from express.urlencoded rather than letting them reach
+    // hashToken() as non-strings and become a misleading invalid_client error.
+    const hasBasicAuth = /^Basic\b/i.test(authHeader);
+    if (
+      (rawClientId !== undefined && typeof rawClientId !== 'string') ||
+      (rawBodySecret !== undefined && typeof rawBodySecret !== 'string') ||
+      (hasBasicAuth && (rawClientId !== undefined || rawBodySecret !== undefined))
+    ) {
+      res.status(400).json({ error: 'invalid_request', error_description: 'Malformed or mixed client authentication' });
+      return;
+    }
+
+    let clientId = typeof rawClientId === 'string' ? rawClientId : undefined;
+    let presentedSecret = typeof rawBodySecret === 'string' && rawBodySecret.length > 0
+      ? rawBodySecret
+      : undefined;
+    if (hasBasicAuth) {
+      try {
+        const match = authHeader.match(/^Basic\s+([^\s]+)$/i);
+        if (!match) throw new Error('Malformed Basic authentication');
+        const decoded = Buffer.from(match[1], 'base64').toString('utf8');
+        const idx = decoded.indexOf(':');
+        if (idx < 1) throw new Error('Malformed Basic authentication');
+        clientId = decodeURIComponent(decoded.slice(0, idx).replace(/\+/g, ' '));
+        presentedSecret = decodeURIComponent(decoded.slice(idx + 1).replace(/\+/g, ' '));
+        if (!presentedSecret) throw new Error('Malformed Basic authentication');
+      } catch {
+        res.setHeader('WWW-Authenticate', 'Basic realm="gbrain"');
+        res.status(401).json({ error: 'invalid_client', error_description: 'Invalid client' });
+        return;
+      }
+    }
+    if (!clientId || !presentedSecret) return next();
+
+    const parsedRequest = OAuthTokenRevocationRequestSchema.safeParse(req.body);
+    if (!parsedRequest.success || parsedRequest.data.token.length === 0) {
+      res.status(400).json({ error: 'invalid_request', error_description: 'Valid token required' });
+      return;
+    }
+
+    let client;
+    try {
+      client = await oauthProvider.verifyConfidentialClientSecret(clientId, presentedSecret);
+    } catch (e) {
+      const msg = e instanceof Error ? e.message : '';
+      if (msg === 'Invalid client' || msg === 'Client has been revoked') {
+        if (hasBasicAuth) res.setHeader('WWW-Authenticate', 'Basic realm="gbrain"');
+        res.status(401).json({ error: 'invalid_client', error_description: 'Invalid client' });
+        return;
+      }
+      console.error('[serve-http] revoke client verification failed:', msg || 'Unknown error');
+      const retryable = isRetryableError(e);
+      res.status(retryable ? 503 : 500).json({
+        error: retryable ? 'temporarily_unavailable' : 'server_error',
+        error_description: retryable ? 'Token revocation temporarily unavailable' : 'Token revocation failed',
+      });
+      return;
+    }
+
+    try {
+      await oauthProvider.revokeToken(client, parsedRequest.data);
+      // RFC 7009 §2.2: successful revocation, including an unknown token, is 200.
+      res.status(200).end();
+    } catch (e) {
+      const msg = e instanceof Error ? e.message : 'Unknown error';
+      console.error('[serve-http] token revocation failed:', msg);
+      const retryable = isRetryableError(e);
+      res.status(retryable ? 503 : 500).json({
+        error: retryable ? 'temporarily_unavailable' : 'server_error',
+        error_description: retryable ? 'Token revocation temporarily unavailable' : 'Token revocation failed',
+      });
+    }
+  });
+
   // ---------------------------------------------------------------------------
   // MCP SDK Auth Router (OAuth endpoints)
   // ---------------------------------------------------------------------------
@@ -796,6 +885,16 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
         if (body?.grant_types_supported && !body.grant_types_supported.includes('client_credentials')) {
           body.grant_types_supported.push('client_credentials');
         }
+        if (body?.token_endpoint_auth_methods_supported) {
+          for (const method of ['client_secret_basic', 'none']) {
+            if (!body.token_endpoint_auth_methods_supported.includes(method)) {
+              body.token_endpoint_auth_methods_supported.push(method);
+            }
+          }
+        }
+        if (body?.revocation_endpoint_auth_methods_supported && !body.revocation_endpoint_auth_methods_supported.includes('client_secret_basic')) {
+          body.revocation_endpoint_auth_methods_supported.push('client_secret_basic');
+        }
         return origJson(body);
       };
     }

src/commands/sources.ts

@@ -7,7 +7,9 @@
  * full story.
  *
  * Subcommands:
- *   gbrain sources add <id> --path <path> [--name <display>] [--federated|--no-federated]
+ *   gbrain sources add <id> --path <path> [--name <display>] [--federated|--no-federated] [--force]
+ *                               --path must be a git-initialized repo (files committed,
+ *                               not just present) — #2707. --force skips the check.
  *   gbrain sources list [--json]
  *   gbrain sources remove <id> [--yes] [--dry-run] [--keep-storage]
  *   gbrain sources rename <id> <new-name>
@@ -107,7 +109,7 @@ async function fetchSource(engine: BrainEngine, id: string): Promise<SourceRow |
 
 async function countPages(engine: BrainEngine, sourceId: string): Promise<number> {
   const rows = await engine.executeRaw<{ n: number }>(
-    `SELECT COUNT(*)::int AS n FROM pages WHERE source_id = $1`,
+    `SELECT COUNT(*)::int AS n FROM pages WHERE source_id = $1 AND deleted_at IS NULL`,
     [sourceId],
   );
   return rows[0]?.n ?? 0;
@@ -120,7 +122,7 @@ async function runAdd(engine: BrainEngine, args: string[]): Promise<void> {
   if (!id) {
     console.error(
       'Usage: gbrain sources add <id> [--path <path> | --url <https-url>] ' +
-        '[--name <display>] [--federated|--no-federated] [--clone-dir <path>]',
+        '[--name <display>] [--federated|--no-federated] [--clone-dir <path>] [--force]',
     );
     process.exit(2);
   }
@@ -132,6 +134,7 @@ async function runAdd(engine: BrainEngine, args: string[]): Promise<void> {
   let cloneDir: string | undefined;
   let patFile: string | undefined;
   let noHarden = false;
+  let force = false;
 
   for (let i = 1; i < args.length; i++) {
     const a = args[i];
@@ -143,6 +146,7 @@ async function runAdd(engine: BrainEngine, args: string[]): Promise<void> {
     if (a === '--clone-dir') { cloneDir = args[++i]; continue; }
     if (a === '--pat-file') { patFile = args[++i]; continue; }
     if (a === '--no-harden') { noHarden = true; continue; }
+    if (a === '--force') { force = true; continue; }
     console.error(`Unknown flag: ${a}`);
     process.exit(2);
   }
@@ -162,6 +166,7 @@ async function runAdd(engine: BrainEngine, args: string[]): Promise<void> {
     remoteUrl,
     federated,
     cloneDir,
+    force,
   });
 
   // Topology A discovery: if the just-added source carries a brain-resident
@@ -502,6 +507,19 @@ async function runArchive(engine: BrainEngine, args: string[]): Promise<void> {
 
   const result = await softDeleteSource(engine, id);
   if (!result) {
+    // #2792: softDeleteSource returns null both for "not found" (handled by
+    // the impact check above) and for "already archived" (UPDATE matched no
+    // `archived = false` row). Distinguish them: already-archived is a
+    // friendly idempotent no-op, not a reasonless failure.
+    const rows = await engine.executeRaw<{ archived: boolean }>(
+      `SELECT archived FROM sources WHERE id = $1`,
+      [id],
+    );
+    if (rows[0]?.archived) {
+      console.log(`Source "${id}" is already archived — nothing to do.`);
+      console.log(`  'gbrain sources archived' shows its purge expiry; 'gbrain sources restore ${id}' un-archives it.`);
+      return;
+    }
     console.error(`Failed to archive source "${id}".`);
     process.exit(4);
   }
@@ -1134,7 +1152,8 @@ async function runAudit(engine: BrainEngine, args: string[]): Promise<void> {
         continue;
       }
       if (stat.isDirectory()) {
-        if (pruneDir(entry, dir)) continue;
+        // pruneDir returns true = descend, false = prune (see core/sync.ts).
+        if (!pruneDir(entry, dir)) continue;
         walk(full);
       } else if (entry.endsWith('.md')) {
         files.push(full);
@@ -1164,7 +1183,14 @@ async function runAudit(engine: BrainEngine, args: string[]): Promise<void> {
   // frontmatter.type and estimates per-page segment count from body
   // bytes. Estimated per-segment Sonnet cost is a rough heuristic
   // (~2000 in + 500 out tokens at $3/MTok in + $15/MTok out ≈ $0.013).
-  const FACTS_BACKFILL_ALLOWED = ['conversation', 'meeting', 'slack', 'email'];
+  const FACTS_BACKFILL_ALLOWED = [
+    'conversation',
+    'meeting',
+    'slack',
+    'email',
+    'imessage',
+    'imessage-daily',
+  ];
   const FACTS_BACKFILL_CHARS_PER_SEGMENT = 6500; // matches SEGMENT_TEXT_CHAR_LIMIT
   const FACTS_BACKFILL_USD_PER_SEGMENT = 0.013;
   let factsBackfillPages = 0;
@@ -1354,8 +1380,9 @@ function printHelp(): void {
   console.log(`gbrain sources — manage multi-source brain configuration (v0.26.5)
 
 Subcommands:
-  add <id> --path <p> [--name <n>] [--federated|--no-federated]
-                                    Register a new source.
+  add <id> --path <p> [--name <n>] [--federated|--no-federated] [--force]
+                                    Register a new source. --path must be a git repo
+                                    with committed files; --force skips that check.
   list [--json]                     List registered sources with page counts.
   remove <id> [--confirm-destructive] [--dry-run]
                                     Permanently delete a source and all its data.

src/commands/takes.ts

@@ -101,12 +101,18 @@ async function getPageId(engine: BrainEngine, slug: string, sourceId?: string):
   return rows[0].id;
 }
 
-async function resolveTakesSourceId(engine: BrainEngine): Promise<string | undefined> {
-  try {
-    return await resolveSourceId(engine, null);
-  } catch {
-    return undefined;
-  }
+// Fail-closed (#2698 residual, TODOS.md): `resolveSourceId` only ever
+// throws when a source WAS explicitly in play — an invalid or
+// unregistered `GBRAIN_SOURCE`, a `.gbrain-source` dotfile pointing at a
+// source that doesn't exist, or a genuine DB error — never for "nothing
+// configured" (that path resolves cleanly to the seeded `'default'`
+// source, tier 6 of resolveSourceId). Swallowing those errors here used
+// to fall back to the unscoped slug-only page lookup, silently
+// reintroducing the pre-#2698 cross-source write bug whenever resolution
+// merely errored instead of resolving cleanly. Let it propagate so the
+// write is blocked instead of silently unscoped.
+async function resolveTakesSourceId(engine: BrainEngine): Promise<string> {
+  return resolveSourceId(engine, null);
 }
 
 function readBodyOrEmpty(path: string): string {

src/core/ai/dims.ts

@@ -90,6 +90,38 @@ export function isValidOpenAITextEmbedding3Dim(modelId: string, dims: number): b
   return Number.isInteger(dims) && dims >= 1 && dims <= max;
 }
 
+// NVIDIA NIM hosted embedding models use asymmetric input_type values. Most
+// emit fixed natural dimensions, but llama-nemotron-embed-1b-v2 accepts
+// Matryoshka-style dimension overrides (e.g. matching an existing 1280d
+// brain column without re-embedding through another provider).
+const NVIDIA_EMBEDDING_DIMS: Record<string, number> = {
+  'nvidia/nv-embedqa-e5-v5': 1024,
+  'nvidia/llama-nemotron-embed-1b-v2': 2048,
+  'nvidia/nv-embed-v1': 4096,
+  'nvidia/nv-embedcode-7b-v1': 4096,
+};
+
+const NVIDIA_EMBEDDING_DIM_OPTIONS: Record<string, number[]> = {
+  'nvidia/llama-nemotron-embed-1b-v2': [1024, 1280, 1536, 2048],
+};
+
+export function isNvidiaEmbeddingModel(modelId: string): boolean {
+  return modelId in NVIDIA_EMBEDDING_DIMS;
+}
+
+export function nvidiaEmbeddingDim(modelId: string): number | undefined {
+  return NVIDIA_EMBEDDING_DIMS[modelId];
+}
+
+export function nvidiaEmbeddingDimOptions(modelId: string): number[] | undefined {
+  return NVIDIA_EMBEDDING_DIM_OPTIONS[modelId];
+}
+
+export function supportsNvidiaEmbeddingDimension(modelId: string, dims: number): boolean {
+  const options = nvidiaEmbeddingDimOptions(modelId);
+  return !!options && options.includes(dims);
+}
+
 /**
  * Build the providerOptions blob for embedMany() that pins output dimensions.
  *
@@ -194,6 +226,17 @@ export function dimsProviderOptions(
           },
         };
       }
+      // NVIDIA NIM hosted embeddings are OpenAI-compatible but require
+      // asymmetric input_type. Use passage for indexing/document-side vectors
+      // and query for search-side vectors. Only llama-nemotron-embed-1b-v2
+      // supports a dimensions override; fixed-dim models reject it.
+      if (isNvidiaEmbeddingModel(modelId)) {
+        const opts: Record<string, any> = {
+          input_type: inputType === 'query' ? 'query' : 'passage',
+        };
+        if (supportsNvidiaEmbeddingDimension(modelId, dims)) opts.dimensions = dims;
+        return { openaiCompatible: opts };
+      }
       // OpenAI text-embedding-3 family on the openai-compatible adapter
       // (Azure OpenAI hosts these via its OpenAI-compatible /embeddings
       // endpoint). The provider defaults to the model's native size (3072
@@ -220,6 +263,15 @@ export function dimsProviderOptions(
       if (modelId === 'text-embedding-v3' || modelId === 'embedding-3') {
         return { openaiCompatible: { dimensions: dims } };
       }
+      // Qwen3-Embedding family on Ollama (and any other openai-compatible
+      // provider serving it) supports Matryoshka truncation via `dimensions`.
+      // Native sizes: 0.6B=1024, 4B=2560, 8B=4096. Without `dimensions`,
+      // Ollama returns the native size and brains configured for narrower
+      // widths hard-fail with a dim-mismatch error. Pattern match the bare
+      // model name + any `:tag` (e.g. `qwen3-embedding:4b`, `qwen3-embedding:0.6b`).
+      if (modelId === 'qwen3-embedding' || modelId.startsWith('qwen3-embedding:')) {
+        return { openaiCompatible: { dimensions: dims } };
+      }
       // MiniMax embo-01 takes a `type: 'db' | 'query'` field for asymmetric
       // retrieval. Today still hardcoded to 'db' for back-compat — opting
       // into the new inputType seam is a follow-up (see plan's deferred

src/core/ai/gateway.ts

@@ -23,6 +23,7 @@
 
 import { embed as aiEmbed, embedMany, generateObject, generateText, jsonSchema } from 'ai';
 import { AsyncLocalStorage } from 'node:async_hooks';
+import { createHash } from 'node:crypto';
 import { listRecipes } from './recipes/index.ts';
 import { createOpenAI } from '@ai-sdk/openai';
 import { createGoogleGenerativeAI } from '@ai-sdk/google';
@@ -52,6 +53,8 @@ import { dimsProviderOptions } from './dims.ts';
 import { hasAnthropicKey } from './anthropic-key.ts';
 import { AIConfigError, AITransientError, normalizeAIError } from './errors.ts';
 import { runGuardrails, hasGuardrails, type GuardrailHook } from '../guardrails.ts';
+import { loadConfig } from '../config.ts';
+import { buildGatewayConfig } from './build-gateway-config.ts';
 
 // ---- Gateway-wide AI-HTTP timeout (v0.42.20.0, #1762/#1775) ----
 //
@@ -116,6 +119,18 @@ const DEFAULT_RERANKER_MODEL = 'zeroentropyai:zerank-2';
 let _config: AIGatewayConfig | null = null;
 const _modelCache = new Map<string, any>();
 
+/**
+ * Recover the process-global gateway for foreground command entrypoints that
+ * were reached without cli.ts's normal engine-connect initialization (#2590).
+ * Existing configured gateways, including their DB-resolved model overrides,
+ * are deliberately left unchanged.
+ */
+export function configureGatewayIfUninitialized(): void {
+  if (_config) return;
+  const config = loadConfig();
+  if (config) configureGateway(buildGatewayConfig(config));
+}
+
 /**
  * v0.31.12 recipe-models merge: per-gateway-instance set of model ids the
  * user opted into via config. Keyed by provider id (`anthropic`, `openai`,
@@ -506,6 +521,20 @@ export async function reconfigureGatewayWithEngine(engine: BrainEngine): Promise
   const expansionFull = newExpansion.includes(':') ? newExpansion : prefixWithProviderFrom(cfg.expansion_model ?? DEFAULT_EXPANSION_MODEL, newExpansion);
   const chatFull = newChat.includes(':') ? newChat : prefixWithProviderFrom(cfg.chat_model ?? DEFAULT_CHAT_MODEL, newChat);
 
+  // ALSO resolve the four tier models and register them as extended models.
+  // assertTouchpoint's contract (model-resolver.ts) says config-chosen models —
+  // `models.default` and `models.tier.*` included — bypass the native recipe
+  // allowlist, but pre-fix only chat/expansion/embedding/reranker were
+  // registered. A model reachable ONLY through a tier (e.g. `models.tier.deep`
+  // set to an Opus newer than the recipe list) failed `probeChatModel` at call
+  // time and silently degraded think/auto_think to the gather-only stub.
+  // Resolving per-tier also honors `models.default` (it sits above tiers in
+  // the resolveModel chain).
+  const tierModels: string[] = [];
+  for (const tier of ['utility', 'reasoning', 'deep', 'subagent'] as const) {
+    tierModels.push(await resolveModel(engine, { tier, fallback: TIER_DEFAULTS[tier] }));
+  }
+
   _config = { ...cfg, expansion_model: expansionFull, chat_model: chatFull };
   _modelCache.clear();
   _shrinkState.clear();
@@ -517,6 +546,7 @@ export async function reconfigureGatewayWithEngine(engine: BrainEngine): Promise
     _config.chat_model,
     _config.reranker_model,
     ...(_config.chat_fallback_chain ?? []),
+    ...tierModels,
   ]) {
     if (m) registerExtendedModel(m);
   }
@@ -1044,6 +1074,30 @@ const voyageCompatFetch = (async (input: RequestInfo | URL, init?: RequestInit)
  * float[] (not base64), so the Layer 2 cap compares against the JSON
  * payload size of each embedding rather than a base64 string length.
  */
+/**
+ * NVIDIA NIM compatibility shim. NVIDIA uses the OpenAI embeddings wire
+ * shape but requires asymmetric input_type values: query for retrieval and
+ * passage for indexed documents. The generic gateway store carries
+ * query/document across the AI SDK boundary; map document to passage here.
+ */
+const nvidiaCompatFetch = (async (input: RequestInfo | URL, init?: RequestInit) => {
+  let baseInit: RequestInit = init ?? {};
+  if (baseInit.body && typeof baseInit.body === 'string') {
+    try {
+      const parsed = JSON.parse(baseInit.body);
+      if (parsed && typeof parsed === 'object' && parsed.input_type === undefined) {
+        parsed.input_type = __embedInputTypeStore.getStore() === 'query' ? 'query' : 'passage';
+        const headers = new Headers(baseInit.headers ?? {});
+        headers.delete('content-length');
+        baseInit = { ...baseInit, body: JSON.stringify(parsed), headers };
+      }
+    } catch {
+      // Preserve the provider response when the SDK body is unexpectedly non-JSON.
+    }
+  }
+  return fetch(input as any, baseInit);
+}) as unknown as typeof fetch;
+
 const zeroEntropyCompatFetch = (async (input: RequestInfo | URL, init?: RequestInit) => {
   // OUTBOUND: normalize URL, rewrite path /embeddings → /models/embed, then
   // rewrite body. fetch accepts RequestInfo (string | Request) | URL; we
@@ -1304,6 +1358,8 @@ function instantiateEmbedding(recipe: Recipe, modelId: string, cfg: AIGatewayCon
           ? voyageCompatFetch
           : recipe.id === 'zeroentropyai'
           ? zeroEntropyCompatFetch
+          : recipe.id === 'nvidia'
+          ? nvidiaCompatFetch
           : openAICompatAsymmetricFetch);
       const client = createOpenAICompatible({
         name: recipe.id,
@@ -2849,6 +2905,30 @@ async function classifyGatewayGuardrail(input: {
   }
 }
 
+/**
+ * Derive OpenAI's `prompt_cache_key` (the AI SDK's `providerOptions.openai.
+ * promptCacheKey`). It's a ROUTING hint, not a cache breakpoint: OpenAI caches
+ * prefixes automatically, and a stable key makes requests sharing a prefix
+ * land on the same engine, raising the hit rate (OpenAI cites 60%→87%).
+ *
+ * Hash the system prompt + sorted tool names — that's the stable prefix
+ * gbrain's repeated loops (enrich, page-summary, skillopt, subagent) actually
+ * share. Returns undefined when there's no system prompt (nothing stable to
+ * key on), so one-off requests don't get pinned to a single engine. An
+ * explicit key can still be set per provider/model via
+ * `provider_chat_options` config, which overrides the derived key.
+ *
+ * @internal exported for tests; not part of the public gateway API.
+ */
+export function openAIPromptCacheKey(args: {
+  system?: string;
+  toolNames?: string[];
+}): string | undefined {
+  if (!args.system) return undefined;
+  const basis = `${args.system} ${(args.toolNames ?? []).slice().sort().join(',')}`;
+  return `gbrain:${createHash('sha256').update(basis).digest('hex').slice(0, 32)}`;
+}
+
 export function toAISDKTools(tools: ChatToolDef[] | undefined): Record<string, any> | undefined {
   if (!tools || tools.length === 0) return undefined;
   return tools.reduce((acc, t) => {
@@ -2957,10 +3037,68 @@ export async function chat(opts: ChatOpts): Promise<ChatResult> {
 
   const providerOptions: Record<string, any> = {};
   if (useCache) {
+    // Call-level `providerOptions.anthropic.cacheControl` is NOT a no-op:
+    // @ai-sdk/anthropic 3.0.47+ passes it through as a top-level
+    // `cache_control` field on the Anthropic request body, which the
+    // Messages API resolves as its documented "auto-cache the last
+    // cacheable block in the request" shorthand (see Anthropic's
+    // prompt-caching docs — "top-level auto-caching ... is the simplest
+    // option when you don't need fine-grained placement"). Keep it: it's
+    // what gives a growing multi-turn conversation (toolLoop()) a rolling
+    // cache breakpoint on each turn's tail for free, without us having to
+    // hand-roll the marker-walking logic subagent.ts's raw-SDK path uses.
+    //
+    // But "last cacheable block" is the wrong block for gbrain#2490's
+    // actual callers (page-summary, skillopt, enrich): those are
+    // single-turn calls with a STABLE system prompt and a DIFFERENT user
+    // message every time, so the auto-marker lands on the ever-varying
+    // tail — every call WRITES a fresh cache entry and never READS a prior
+    // one (cache_read_input_tokens stays 0 forever). Caching the stable
+    // prefix needs an EXPLICIT breakpoint on the system block itself,
+    // which is applied below via a `SystemModelMessage` (round-trips its
+    // own `providerOptions`) instead of a bare string.
     providerOptions.anthropic = { cacheControl: { type: 'ephemeral' } };
   }
+  // OpenAI prompt_cache_key (native-openai only): a stable per-prefix routing
+  // hint that keeps requests sharing a system prompt + tool set on the same
+  // inference engine, lifting OpenAI's automatic prefix-cache hit rate. The
+  // openai-compatible path (litellm/azure/groq/...) ignores
+  // providerOptions.openai, so it gets nothing. Applied BEFORE the configured
+  // provider options so `provider_chat_options.openai.promptCacheKey` from
+  // config still overrides the derived key.
+  if (recipe.implementation === 'native-openai') {
+    const promptCacheKey = openAIPromptCacheKey({
+      system: opts.system,
+      toolNames: (opts.tools ?? []).map(t => t.name),
+    });
+    if (promptCacheKey) providerOptions.openai = { promptCacheKey };
+  }
   applyConfiguredChatProviderOptions(providerOptions, cfg, recipe.id, modelId);
 
+  // Derive ONE canonical cache-control value AFTER config merging and reuse
+  // it for every breakpoint (system block, last tool def, call-level). If
+  // `provider_chat_options.anthropic.cacheControl` overrides the TTL (e.g.
+  // `{ type: 'ephemeral', ttl: '1h' }`), that override lands in
+  // `providerOptions.anthropic.cacheControl` via the deep-merge above —
+  // reusing it here (instead of hardcoding `{ type: 'ephemeral' }` per
+  // breakpoint) keeps every marker in the request on the same TTL.
+  const cacheControlValue: { type: 'ephemeral'; ttl?: '5m' | '1h' } | undefined = useCache
+    ? (providerOptions.anthropic?.cacheControl ?? { type: 'ephemeral' })
+    : undefined;
+
+  // Anthropic-only secondary breakpoint: mark the LAST tool def too (mirrors
+  // subagent.ts's raw-SDK path — Anthropic caches everything up to and
+  // including the last `cache_control` block it sees in the request, so
+  // marking the last tool extends the cached prefix through the whole tool
+  // list). `tool.providerOptions.anthropic.cacheControl` is the shape
+  // @ai-sdk/anthropic 3.x reads for tool-def breakpoints.
+  if (cacheControlValue && opts.tools && opts.tools.length > 0 && tools) {
+    const lastTool = tools[opts.tools[opts.tools.length - 1]!.name];
+    if (lastTool) {
+      lastTool.providerOptions = { anthropic: { cacheControl: cacheControlValue } };
+    }
+  }
+
   let _budgetRecorded = false;
   const _recordBudget = (modelLabel: string, inputTokens: number, outputTokens: number): void => {
     if (!tracker || _budgetRecorded) return;
@@ -2977,10 +3115,28 @@ export async function chat(opts: ChatOpts): Promise<ChatResult> {
     }
   };
 
+  // The actual Anthropic system-prompt cache breakpoint. A bare string
+  // `system` produces `{ role: 'system', content }` with no `providerOptions`
+  // field (ai@6's convertToLanguageModelPrompt), so @ai-sdk/anthropic's
+  // getCacheControl(providerOptions) on that block always resolves to
+  // nothing. Passing a `SystemModelMessage` object instead — the shape `ai`
+  // documents specifically for "additional provider options (e.g. for
+  // caching)" — round-trips `providerOptions` onto that block. Byte-identical
+  // to the old bare-string form when useCache is false. Reuses
+  // `cacheControlValue` (the config-merged value) so this breakpoint's TTL
+  // always matches the last-tool and call-level breakpoints.
+  const systemParam = cacheControlValue && opts.system
+    ? {
+        role: 'system' as const,
+        content: opts.system,
+        providerOptions: { anthropic: { cacheControl: cacheControlValue } },
+      }
+    : opts.system;
+
   try {
     const result = await _generateTextTransport({
       model,
-      system: opts.system,
+      system: systemParam,
       messages: toModelMessages(repairToolPairing(opts.messages)) as any,
       tools: opts.tools && opts.tools.length > 0 ? tools : undefined,
       maxOutputTokens: opts.maxTokens ?? defaultMaxOutputTokens(modelStr),

src/core/ai/recipes/anthropic.ts

@@ -17,13 +17,16 @@ export const anthropic: Recipe = {
   touchpoints: {
     // No embedding model available.
     expansion: {
-      models: ['claude-haiku-4-5-20251001', 'claude-sonnet-4-6'],
+      models: ['claude-haiku-4-5-20251001', 'claude-sonnet-5', 'claude-sonnet-4-6'],
       cost_per_1m_tokens_usd: 0.25,
       price_last_verified: '2026-05-10',
     },
     chat: {
       models: [
+        'claude-fable-5',
+        'claude-opus-4-8',
         'claude-opus-4-7',
+        'claude-sonnet-5',
         'claude-sonnet-4-6',
         'claude-haiku-4-5-20251001',
       ],

src/core/ai/recipes/index.ts

@@ -23,6 +23,9 @@ import { zhipu } from './zhipu.ts';
 import { azureOpenAI } from './azure-openai.ts';
 import { zeroentropyai } from './zeroentropyai.ts';
 import { llamaServerReranker } from './llama-server-reranker.ts';
+import { moonshot } from './moonshot.ts';
+import { mistral } from './mistral.ts';
+import { nvidia } from './nvidia.ts';
 
 const ALL: Recipe[] = [
   openai,
@@ -42,6 +45,9 @@ const ALL: Recipe[] = [
   zhipu,
   azureOpenAI,
   zeroentropyai,
+  moonshot,
+  mistral,
+  nvidia,
 ];
 
 /** Map from `provider:id` key to recipe. */

src/core/ai/recipes/litellm-proxy.ts

@@ -41,6 +41,21 @@ export const litellmProxy: Recipe = {
       // mismatched-dim responses pre-storage).
       supports_multimodal: true,
     },
+    expansion: {
+      models: [],
+      cost_per_1m_tokens_usd: undefined,
+      price_last_verified: '2026-06-14',
+    },
+    chat: {
+      models: [],
+      supports_tools: true,
+      supports_subagent_loop: true,
+      supports_prompt_cache: false,
+      max_context_tokens: 200_000,
+      cost_per_1m_input_usd: undefined,
+      cost_per_1m_output_usd: undefined,
+      price_last_verified: '2026-06-14',
+    },
   },
   setup_hint: 'Run LiteLLM (https://docs.litellm.ai) in front of any provider; set LITELLM_BASE_URL (include the /v1 suffix if your proxy serves the OpenAI route there, e.g. http://localhost:4000/v1) + pass --embedding-model litellm:<model> and --embedding-dimensions <N>.',
 };

src/core/ai/recipes/mistral.ts

@@ -0,0 +1,84 @@
+import type { Recipe } from '../types.ts';
+
+/**
+ * Mistral AI exposes an OpenAI-compatible API at https://api.mistral.ai/v1
+ * (/embeddings + /chat/completions). EU-hosted — the reason this recipe
+ * exists: a brain that must stay inside EU jurisdiction can run embed +
+ * expansion + chat on a single provider without a US hop.
+ *
+ * Verified against the live API on 2026-07-19 (model catalog, embedding
+ * dimensions, dimension-parameter rejection, and the batch ceiling — see
+ * the notes on each field below).
+ *
+ * DIMENSIONS — mistral-embed is FIXED 1024 and accepts NO dimension
+ * parameter at all. Both spellings are rejected upstream:
+ *   {"dimensions": 512}        -> 400 extra_forbidden (not in the API schema)
+ *   {"output_dimension": 512}  -> 400 "This model does not support output_dimension"
+ * The generic `openai-compatible` branch of dims.ts:dimsProviderOptions()
+ * already falls through to `return undefined` for these model ids, so no
+ * dimension field is emitted. Do NOT add mistral-embed to any of the
+ * flexible-dim allowlists there — it would 400 every embed call. Same
+ * contract as voyage-4-nano, for the same reason.
+ *
+ * codestral-embed / codestral-embed-2505 are deliberately NOT listed: they
+ * return 1536 dims, and a touchpoint carries a single `default_dims`.
+ * Mixing them under a 1024 declaration is the mixed-dim footgun
+ * embedding-dim-check.ts exists to catch. They are code-retrieval models
+ * anyway; a prose brain wants mistral-embed.
+ */
+export const mistral: Recipe = {
+  id: 'mistral',
+  name: 'Mistral AI',
+  tier: 'openai-compat',
+  implementation: 'openai-compatible',
+  base_url_default: 'https://api.mistral.ai/v1',
+  auth_env: {
+    required: ['MISTRAL_API_KEY'],
+    setup_url: 'https://console.mistral.ai/api-keys',
+  },
+  touchpoints: {
+    embedding: {
+      models: ['mistral-embed', 'mistral-embed-2312'],
+      default_dims: 1024,
+      // Mistral's published list price. Advisory only — canonical embedding
+      // spend accounting lives in src/core/embedding-pricing.ts.
+      cost_per_1m_tokens_usd: 0.1,
+      price_last_verified: '2026-07-19',
+      // Measured ceiling, not a doc guess: the /embeddings endpoint accepts a
+      // 65,286-token batch and rejects 66,960 with
+      //   400 code 3210 "Too many tokens overall, split into more batches."
+      // -> the real cap is 65,536 (64K) tokens per request.
+      max_batch_tokens: 65_536,
+      // chars_per_token is a DIVISOR in splitByTokenBudget()
+      // (estTokens = text.length / charsPerToken), so a LOWER value is the
+      // conservative direction. The module default of 4 is an English-prose
+      // assumption; German prose measured 3.58 here, and code/JSON/CJK runs
+      // denser still. 2 keeps the estimate above the real token count for
+      // every content shape we see.
+      chars_per_token: 2,
+      // With safety_factor 0.5 the pre-split budget is 32,768 estimated
+      // tokens = 65,536 chars. Worst realistic density (~1.5 chars/token)
+      // puts that at ~43.7K real tokens — still clear of the 64K ceiling.
+      safety_factor: 0.5,
+    },
+    expansion: {
+      models: ['ministral-3b-latest', 'mistral-small-latest'],
+      price_last_verified: '2026-07-19',
+    },
+    chat: {
+      models: [
+        'mistral-small-latest', 'mistral-medium-latest', 'mistral-large-latest',
+        'ministral-3b-latest', 'ministral-8b-latest', 'magistral-small-latest',
+      ],
+      supports_tools: true,
+      // Same call as the Moonshot recipe: ordinary tool calls are fine, but
+      // gbrain's subagent loop stays Anthropic-pinned for stable tool_use_id
+      // behavior across crashes/replays.
+      supports_subagent_loop: false,
+      supports_prompt_cache: false,
+      max_context_tokens: 262144,
+      price_last_verified: '2026-07-19',
+    },
+  },
+  setup_hint: 'Get an API key at https://console.mistral.ai/api-keys, then `export MISTRAL_API_KEY=...` and use `mistral:mistral-embed` (1024 dims) for embeddings.',
+};

src/core/ai/recipes/moonshot.ts

@@ -0,0 +1,42 @@
+import type { Recipe } from '../types.ts';
+
+/**
+ * Moonshot AI / Kimi Open Platform. Kimi exposes an OpenAI-compatible
+ * /v1/chat/completions API at https://api.moonshot.ai/v1.
+ *
+ * Verified against Kimi API docs and live /v1/models on 2026-06-23.
+ * The recipe is local-production glue until upstream GBrain carries a native
+ * Moonshot recipe; keep it registered in the local patch registry.
+ */
+export const moonshot: Recipe = {
+  id: 'moonshot',
+  name: 'Moonshot AI / Kimi',
+  tier: 'openai-compat',
+  implementation: 'openai-compatible',
+  base_url_default: 'https://api.moonshot.ai/v1',
+  auth_env: {
+    required: ['MOONSHOT_API_KEY'],
+    setup_url: 'https://platform.kimi.ai/console/api-keys',
+  },
+  touchpoints: {
+    expansion: {
+      models: ['kimi-k2.7-code', 'kimi-k2.7-code-highspeed', 'kimi-k2.6', 'kimi-k2.5'],
+      // Kimi pricing varies by current promotional/account terms; do not use
+      // this advisory field for budget enforcement. Canonical budget pricing
+      // belongs in src/core/model-pricing.ts when verified for the account.
+      price_last_verified: '2026-06-23',
+    },
+    chat: {
+      models: ['kimi-k2.7-code', 'kimi-k2.7-code-highspeed', 'kimi-k2.6', 'kimi-k2.5'],
+      supports_tools: true,
+      // Kimi tool calling is enough for ordinary chat/tool calls. GBrain's
+      // subagent loop remains Anthropic-pinned because upstream requires stable
+      // Anthropic-style tool_use_id behavior across crashes/replays.
+      supports_subagent_loop: false,
+      supports_prompt_cache: false,
+      max_context_tokens: 256000,
+      price_last_verified: '2026-06-23',
+    },
+  },
+  setup_hint: 'Get an API key at https://platform.kimi.ai/console/api-keys, then `export MOONSHOT_API_KEY=...` and use `moonshot:kimi-k2.7-code`.',
+};

src/core/ai/recipes/nvidia.ts

@@ -0,0 +1,71 @@
+import type { Recipe } from '../types.ts';
+
+/**
+ * NVIDIA NIM / API Catalog exposes OpenAI-compatible /v1/chat/completions
+ * and /v1/embeddings APIs.
+ *
+ * Retrieval models use asymmetric encoding. The gateway maps gbrain's
+ * document/query distinction to NVIDIA's wire values:
+ *   document -> input_type: passage
+ *   query    -> input_type: query
+ *
+ * The model ids below intentionally keep NVIDIA's full catalog ids because
+ * the hosted endpoint expects values like `nvidia/nv-embedqa-e5-v5` in the
+ * request body. Short aliases are provided for CLI ergonomics.
+ */
+export const nvidia: Recipe = {
+  id: 'nvidia',
+  name: 'NVIDIA NIM',
+  tier: 'openai-compat',
+  implementation: 'openai-compatible',
+  base_url_default: 'https://integrate.api.nvidia.com/v1',
+  auth_env: {
+    required: ['NVIDIA_API_KEY'],
+    setup_url: 'https://build.nvidia.com',
+  },
+  aliases: {
+    'nv-embedqa-e5-v5': 'nvidia/nv-embedqa-e5-v5',
+    'llama-nemotron-embed-1b-v2': 'nvidia/llama-nemotron-embed-1b-v2',
+    'nemotron-3-super': 'nvidia/nemotron-3-super-120b-a12b',
+    'nemotron-3-super-120b-a12b': 'nvidia/nemotron-3-super-120b-a12b',
+    'nv-embed-v1': 'nvidia/nv-embed-v1',
+    'nv-embedcode-7b-v1': 'nvidia/nv-embedcode-7b-v1',
+  },
+  // No resolveAuth override: NVIDIA is plain `Authorization: Bearer <key>`,
+  // which defaultResolveAuth derives from auth_env.required. IRON RULE
+  // (test/ai/recipes-existing-regression.test.ts): only Azure overrides
+  // resolveAuth.
+  touchpoints: {
+    chat: {
+      models: [
+        'nvidia/nemotron-3-super-120b-a12b',
+      ],
+      supports_tools: false,
+      supports_subagent_loop: false,
+      // Do not treat Nemotron as a Minions subagent driver until tool-calling
+      // and replay stability are proven through a separate adapter test.
+      max_context_tokens: 128000,
+      price_last_verified: '2026-05-24',
+    },
+    embedding: {
+      models: [
+        'nvidia/nv-embedqa-e5-v5',
+        'nvidia/llama-nemotron-embed-1b-v2',
+        'nvidia/nv-embed-v1',
+        'nvidia/nv-embedcode-7b-v1',
+      ],
+      // Default to the lightest tested hosted model. Larger NVIDIA models are
+      // supported via explicit embedding_dimensions (2048 or 4096).
+      default_dims: 1024,
+      dims_options: [1024, 2048, 4096],
+      // Conservative split; hosted NVIDIA embedding endpoints require
+      // input_type and may reject large payloads before tokenizing.
+      max_batch_tokens: 8192,
+      chars_per_token: 4,
+      safety_factor: 0.75,
+      cost_per_1m_tokens_usd: undefined,
+      price_last_verified: '2026-05-24',
+    },
+  },
+  setup_hint: 'Get an API key at https://build.nvidia.com, then `export NVIDIA_API_KEY=...`.',
+};

src/core/brain-repo-durability.ts

@@ -100,7 +100,15 @@ function gbrainHome(): string {
  *  core→commands import). which gbrain → process.execPath → argv[1] → "gbrain". */
 function resolveGbrainCliPath(): string {
   try {
-    const which = execSync('which gbrain', { encoding: 'utf-8', stdio: ['ignore', 'pipe', 'ignore'] }).trim();
+    // #2747: `env: process.env` required under Bun — see the sibling copy
+    // of this function in commands/autopilot.ts for the full explanation
+    // (Bun snapshots process.env at its own startup; execSync without an
+    // explicit env is blind to any PATH mutation since then).
+    const which = execSync('which gbrain', {
+      encoding: 'utf-8',
+      stdio: ['ignore', 'pipe', 'ignore'],
+      env: process.env,
+    }).trim();
     if (which) return which;
   } catch { /* not on PATH */ }
   const exec = process.execPath ?? '';
@@ -183,15 +191,17 @@ if [ "\${1:-}" = "--push-only" ]; then
 fi
 
 _msg="\${1:?usage: brain-commit-push.sh <message> <path> [paths...]}"; shift || true
-# Pull first so the local tree is current before we stage.
-git fetch origin >/dev/null 2>&1 || true
-git pull --rebase origin "$_branch" || { git rebase --abort >/dev/null 2>&1 || true; echo "rebase conflict: manual attention needed" >&2; exit 3; }
 
 # EXPLICIT paths only — never a blind 'git add -A' (would risk committing
 # secrets, temp files, or unrelated edits).
 if [ "$#" -eq 0 ]; then
   echo "refusing blind 'git add -A' — pass explicit path(s) to commit" >&2; exit 2
 fi
+# COMMIT BEFORE PULL (#2426): the old order (fetch + pull --rebase, THEN stage)
+# aborted on any dirty tree — 'cannot pull with rebase: You have unstaged
+# changes' — so the helper could never commit a MODIFIED page (exactly the
+# write-through case). Stage + commit first; brain_push below already handles
+# a remote that advanced (push -> rejected -> pull --rebase -> push).
 git add -- "$@"
 if git diff --cached --quiet; then echo "nothing to commit"; exit 0; fi
 git commit -m "$_msg"
@@ -337,6 +347,47 @@ function uninstallLocalHook(repoPath: string): boolean {
   return true;
 }
 
+/**
+ * True when the gbrain durability post-commit hook is installed — i.e. the
+ * user opted this repo into push-durability via `gbrain sources harden`.
+ * Cheap (one git-config read + one file read); used as the gate for
+ * write-through auto-commit (#2426).
+ */
+export function isDurabilityHardened(repoPath: string): boolean {
+  try {
+    const { dir } = resolveHooksDir(repoPath);
+    const hookPath = join(dir, 'post-commit');
+    return existsSync(hookPath) && readFileSync(hookPath, 'utf-8').includes(HOOK_BANNER);
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * #2426: best-effort commit of a single write-through artifact so DB writes
+ * reach git (the post-commit hook then background-pushes). Pre-fix,
+ * write-through `.md` accumulated uncommitted forever: it never reached the
+ * remote, froze `last_sync_at` (HEAD never moved), and a later `sync --full`
+ * delete-reconcile treated the never-committed pages as disposable.
+ *
+ * Path-limited (`git commit -- <path>`) so unrelated staged/dirty edits are
+ * never swept into the commit. Never throws; returns false on any failure
+ * (index.lock contention, nothing changed, detached states) — the DB row and
+ * the on-disk file remain the durable sinks either way.
+ */
+export function commitWriteThroughFile(repoPath: string, absPath: string, slug: string): boolean {
+  try {
+    const rel = relative(repoPath, absPath);
+    if (!rel || rel.startsWith('..') || isAbsolute(rel)) return false;
+    const gitOpts = { stdio: 'ignore', timeout: 30_000, env: { ...process.env, ...GIT_ENV } } as const;
+    execFileSync('git', ['-C', repoPath, 'add', '--', rel], gitOpts);
+    execFileSync('git', ['-C', repoPath, 'commit', '-m', `gbrain: write-through ${slug}`, '--', rel], gitOpts);
+    return true;
+  } catch {
+    return false;
+  }
+}
+
 // ── Committed helper ────────────────────────────────────────────────────────
 
 function installHelper(repoPath: string, dryRun: boolean): { status: StepStatus; detail: string } {

src/core/brain-writer.ts

@@ -22,6 +22,7 @@ import { join, relative, resolve, dirname, basename, isAbsolute } from 'path';
 import type { BrainEngine } from './engine.ts';
 import type { ProgressReporter } from './progress.ts';
 import { gbrainPath } from './config.ts';
+import { collectGitVisibleFiles } from './git-visible-files.ts';
 import {
   parseMarkdown,
   type ParseValidationCode,
@@ -408,6 +409,11 @@ export interface ScanOpts {
   visitDir?: (dirPath: string) => void;
 }
 
+/** Timeout-arm winner for the COUNT-vs-deadline race in scanBrainSources.
+ *  A unique object so it can never collide with a legitimate COUNT result
+ *  (number | null). Module-private. */
+const DEADLINE_SENTINEL: unique symbol = Symbol('gbrain.scan.deadline');
+
 export async function scanBrainSources(
   engine: BrainEngine,
   opts: ScanOpts = {},
@@ -479,41 +485,43 @@ export async function scanBrainSources(
     // pool can make this await hang past the budget. Without the race, we'd
     // wait indefinitely AND defeat the wall-clock guarantee.
     let dbPageCount: number | null = null;
+    // Set when the deadline race's timeout arm wins: the verdict that the
+    // budget is spent, independent of any later Date.now() reading. Timer
+    // callbacks on loaded runners can fire measurably EARLY relative to the
+    // wall clock (a +1ms pad was drifted past in practice — see the flake
+    // lineage in test/brain-writer-partial-scan.test.ts and issue #2946), so
+    // the hung-COUNT path must not re-derive "did the deadline fire?" from
+    // the clock the timer just raced against.
+    let deadlineHit = false;
     if (opts.dbPageCountForSource) {
       try {
         if (opts.deadline) {
           const remainingMs = opts.deadline - Date.now();
           if (remainingMs <= 0) {
             dbPageCount = null;
+            deadlineHit = true;
           } else {
-            // Race COUNT against the deadline so a hung query can't eat the budget.
-            //
-            // Boundary overshoot (+1ms): the post-await deadline check at line
-            // ~512 uses `Date.now() >= deadline`. setTimeout fires AT OR AFTER
-            // the requested delay, so in theory the check always passes. In
-            // practice on heavily-loaded CI runners (8 parallel shards × 4
-            // concurrent test files = ~32 concurrent bun processes) we saw
-            // intermittent failures where the timer callback resolved
-            // microseconds BEFORE the wall-clock boundary, leaving Date.now()
-            // a tick below deadline and the skip-check evaluating false. The
-            // src-a scan then ran on a populated dir before src-b's
-            // between-source check caught up — causing
-            // `firstSource.status === 'skipped'` to receive 'scanned'.
-            //
-            // Adding 1ms guarantees the timer fires past the deadline by at
-            // least one millisecond regardless of runner timer drift. Cost is
-            // 1ms additional wall-clock latency on hung COUNT queries, which
-            // is operationally negligible. Flake repro:
-            // https://github.com/garrytan/gbrain/actions/runs/77611667786
-            dbPageCount = await Promise.race([
+            // Race COUNT against the deadline so a hung query can't eat the
+            // budget. The timeout arm resolves a private sentinel — NOT null —
+            // so a deadline win is distinguishable from a COUNT that resolved
+            // null (failed/absent count keeps its existing semantics).
+            const raced = await Promise.race([
               opts.dbPageCountForSource(src.id),
-              new Promise<null>(resolve => setTimeout(() => resolve(null), remainingMs + 1)),
+              new Promise<typeof DEADLINE_SENTINEL>(resolve =>
+                setTimeout(() => resolve(DEADLINE_SENTINEL), remainingMs)),
             ]);
+            if (raced === DEADLINE_SENTINEL) {
+              dbPageCount = null;
+              deadlineHit = true;
+            } else {
+              dbPageCount = raced;
+            }
           }
         } else {
           dbPageCount = await opts.dbPageCountForSource(src.id);
         }
       } catch {
+        // A throwing COUNT is a failed count, not a deadline verdict.
         dbPageCount = null;
       }
     }
@@ -523,11 +531,11 @@ export async function scanBrainSources(
     // status='partial' with files_scanned=0, which is misleading ("partial
     // scan" when actually nothing was scanned). Mark this source + remainder
     // as 'skipped' so the doctor message is honest.
-    // `>=` matches the between-source check above (line 445). The Promise.race
-    // setTimeout resolves null at exactly `remainingMs` from now, so post-await
-    // Date.now() often equals deadline within integer-ms precision — strict `>`
-    // missed those landings on CI and let the next scanOneSource run anyway.
-    if (opts.signal?.aborted || (opts.deadline && Date.now() >= opts.deadline)) {
+    // `deadlineHit` is the authoritative verdict for the hung-COUNT path (the
+    // sentinel above); the wall-clock re-check (`>=`, matching the
+    // between-source check at line ~445) still covers a COUNT that RESOLVED
+    // slowly enough to eat the budget without the timer winning.
+    if (opts.signal?.aborted || deadlineHit || (opts.deadline && Date.now() >= opts.deadline)) {
       if (abortedAtSource === null) {
         abortedAtSource = src.id;
       }
@@ -579,7 +587,7 @@ function scanOneSource(
   let ignoredMissingOpen = 0;
   let interrupted = false;
 
-  walkDir(rootResolved, (absPath) => {
+  const visitFile = (absPath: string): boolean | void => {
     // Per-file deadline + abort gate. Deadline is the load-bearing
     // wall-clock bound (sync I/O blocks the event loop so timer-based
     // AbortSignal.timeout can't fire mid-walk — codex C1).
@@ -625,7 +633,17 @@ function scanOneSource(
       opts.onProgress.tick(50);
     }
     return true;
-  }, opts.visitDir);
+  };
+
+  const gitFiles = collectGitVisibleFiles(rootResolved, (rel) => isSyncable(rel, { strategy: 'markdown' }));
+  if (gitFiles) {
+    if (opts.visitDir) opts.visitDir(rootResolved);
+    for (const absPath of gitFiles) {
+      if (visitFile(absPath) === false) break;
+    }
+  } else {
+    walkDir(rootResolved, visitFile, opts.visitDir);
+  }
 
   if (opts.onProgress) {
     opts.onProgress.heartbeat(`scanned ${scanned} pages in ${sourceId}`);

src/core/chronicle/extract-events.ts

@@ -26,7 +26,17 @@ export interface ChronicleJudgeInput {
   effectiveDate: string | null;   // depth page effective_date (deterministic when)
   attendees: string[];            // deterministic who from frontmatter
 }
-export interface ChronicleJudgeResult { events: ChronicleEventProposal[] }
+export interface ChronicleJudgeResult {
+  events: ChronicleEventProposal[];
+  /**
+   * #2606 — distinct judge-failure signal so an unusable response is never
+   * recorded as a legitimate `no_events`:
+   *   - 'truncated': the model hit the output-token cap (stopReason 'length');
+   *     the JSON array was cut mid-stream and must not be parsed as complete.
+   *   - 'parse_failed': the model returned text but no valid JSON array.
+   */
+  failure?: 'truncated' | 'parse_failed';
+}
 export type ChronicleJudge = (input: ChronicleJudgeInput) => Promise<ChronicleJudgeResult>;
 
 export interface ChronicleExtractResult {
@@ -126,6 +136,12 @@ export async function runChronicleExtract(
     return { slug: opts.slug, status: 'skipped', events_written: 0, reason: 'judge_error' };
   }
 
+  // #2606: a truncated or unparseable judge response is a FAILURE, not an
+  // empty page. Record it as a distinct skipped reason so operators (and
+  // retries) can tell it apart from a genuine no_events.
+  if (result?.failure) {
+    return { slug: opts.slug, status: 'skipped', events_written: 0, reason: `judge_${result.failure}` };
+  }
   const proposals = Array.isArray(result?.events) ? result.events : [];
   if (proposals.length === 0) return { slug: opts.slug, status: 'no_events', events_written: 0 };
   // PARSE BARRIER — reject the WHOLE batch on any malformed proposal; no partial writes.
@@ -167,11 +183,25 @@ const JUDGE_SYSTEM = `You segment a meeting/transcript page into discrete timeli
 Return ONLY a JSON array. Each element: {"when": ISO datetime or YYYY-MM-DD, "who": [entity slugs/names], "what": one-clause summary, "where": optional string, "kind": one of meeting|call|meal|solo|travel|work|commitment|decision|intro|conflict|milestone|event}.
 Prefer the page's known date for "when" when the text gives no explicit time. Use the provided attendee slugs for "who" when the text does not name participants. No prose, no markdown — just the JSON array.`;
 
+/**
+ * #2606: default output-token cap for the judge. Raised from the original
+ * 1500 (which event-dense pages overflowed, silently truncating the JSON
+ * array). Override via `chronicle.judge_max_tokens`.
+ */
+const DEFAULT_JUDGE_MAX_TOKENS = 4000;
+
 function defaultJudge(engine: BrainEngine): ChronicleJudge {
   return async (input) => {
     const { isAvailable, chat } = await import('../ai/gateway.ts');
     if (!isAvailable('chat')) return { events: [] };
     const body = (input.body || '').slice(0, 12_000);
+    // #2606: configurable cap so event-dense pages have headroom.
+    let maxTokens = DEFAULT_JUDGE_MAX_TOKENS;
+    const capRaw = await engine.getConfig('chronicle.judge_max_tokens').catch(() => null);
+    if (capRaw) {
+      const n = parseInt(capRaw, 10);
+      if (Number.isFinite(n) && n > 0) maxTokens = n;
+    }
     let text: string;
     try {
       const res = await chat({
@@ -183,32 +213,44 @@ function defaultJudge(engine: BrainEngine): ChronicleJudge {
             `${input.title}\n\n${body}\n</page>\n\n` +
             `Known attendees: ${input.attendees.slice(0, 10).join(', ') || '(none)'}.\nExtract the events.`,
         }],
-        maxTokens: 1500,
+        maxTokens,
       });
       if (res.stopReason === 'refusal' || res.stopReason === 'content_filter') return { events: [] };
+      // #2606: output hit the token cap — the JSON array is cut mid-stream.
+      // Do NOT feed it to the parser as if complete; surface the truncation.
+      if (res.stopReason === 'length') return { events: [], failure: 'truncated' };
       text = res.text;
     } catch (err) {
       if ((err as Error)?.name === 'AbortError') throw err;
       return { events: [] };
     }
     const parsed = parseJudgeJson(text);
+    // #2606: non-empty model text with no parseable JSON array is a parse
+    // failure, distinct from the model legitimately answering `[]`.
+    if (parsed === null) return { events: [], failure: 'parse_failed' };
     return { events: parsed };
   };
 }
 
-/** Tolerant JSON-array extraction from a model response (mirrors facts parser). */
-export function parseJudgeJson(text: string): ChronicleEventProposal[] {
-  if (!text) return [];
+/**
+ * Tolerant JSON-array extraction from a model response (mirrors facts parser).
+ *
+ * #2606: returns `null` on parse FAILURE (empty text, no `[...]` found,
+ * JSON.parse throw, non-array result) so callers can distinguish "the model
+ * said no events" (a legitimate `[]`) from "the response was unusable".
+ */
+export function parseJudgeJson(text: string): ChronicleEventProposal[] | null {
+  if (!text) return null;
   let s = text.trim();
   const fence = s.match(/```(?:json)?\s*([\s\S]*?)```/i);
   if (fence) s = fence[1].trim();
   const start = s.indexOf('[');
   const end = s.lastIndexOf(']');
-  if (start === -1 || end === -1 || end < start) return [];
+  if (start === -1 || end === -1 || end < start) return null;
   try {
     const arr = JSON.parse(s.slice(start, end + 1));
-    return Array.isArray(arr) ? arr : [];
+    return Array.isArray(arr) ? arr : null;
   } catch {
-    return [];
+    return null;
   }
 }

src/core/cli-force-exit.ts

@@ -114,6 +114,26 @@ function resolveFlushGraceMs(): number {
 /** Default per-sink drain budget (matches drainAllBackgroundWorkForCliExit). */
 const DEFAULT_DRAIN_TIMEOUT_MS = 2_000;
 
+/**
+ * Resolve the per-sink drain budget: `GBRAIN_DRAIN_TIMEOUT_MS` env override
+ * (slow-provider escape hatch, same env-only pattern as
+ * GBRAIN_TEARDOWN_DEADLINE_MS) over the 2000ms default. An explicit
+ * `drainTimeoutMs` from a call site still wins — the env replaces only the
+ * DEFAULT. The 2s default assumes a sub-second cloud chat provider; a
+ * self-hosted model (e.g. ollama at 10-20s per completion) can never finish a
+ * fire-and-forget facts:absorb extraction inside it, so every one-shot CLI
+ * exit — sync timers especially — aborts the in-flight chat and the
+ * extraction never lands, retrying (and re-aborting) on each subsequent sync
+ * of the same page. Raising the budget via env lets those installs drain
+ * instead of abort; computeTeardownDeadlineMs already scales the backstop
+ * from the resolved value, so the deadline widens with it.
+ */
+export function resolveDrainTimeoutMs(): number {
+  const env = Number(process.env.GBRAIN_DRAIN_TIMEOUT_MS);
+  if (Number.isFinite(env) && env > 0) return env;
+  return DEFAULT_DRAIN_TIMEOUT_MS;
+}
+
 /**
  * Backstop deadline for drain + disconnect COMBINED, computed from the bounds
  * it guards so it fires only when a component violated its own bound (#2084
@@ -262,7 +282,10 @@ export function flushThenExit(code: number, opts: FlushThenExitOpts = {}): void
 export interface FinishCliTeardownOpts {
   /** Engine to disconnect. A disconnect throw is warned + swallowed (D3). */
   engine: { disconnect(): Promise<void> };
-  /** Per-sink drain budget. Default 2000 (the registry default). */
+  /**
+   * Per-sink drain budget. Default: `GBRAIN_DRAIN_TIMEOUT_MS` env override,
+   * else 2000 (the registry default).
+   */
   drainTimeoutMs?: number;
   /** Test seam — wins over the env override and the computed formula. */
   deadlineMs?: number;
@@ -284,7 +307,7 @@ export interface FinishCliTeardownOpts {
  * exit in here, and it means a component violated its own bound.
  */
 export async function finishCliTeardown(opts: FinishCliTeardownOpts): Promise<void> {
-  const drainTimeoutMs = opts.drainTimeoutMs ?? DEFAULT_DRAIN_TIMEOUT_MS;
+  const drainTimeoutMs = opts.drainTimeoutMs ?? resolveDrainTimeoutMs();
   const warn = opts.warn ?? ((m: string) => console.warn(m));
   const drain = opts.drain ?? drainAllBackgroundWorkForCliExit;
   const deadlineMs =

src/core/config.ts

@@ -271,6 +271,8 @@ export interface GBrainConfig {
       verdict_model?: string;
       max_prompt_tokens?: number;
       max_chunks_per_transcript?: number;
+      subagent_timeout_ms?: number;
+      subagent_wait_timeout_ms?: number;
     };
     patterns?: {
       lookback_days?: number;
@@ -710,6 +712,12 @@ export async function loadConfigWithEngine(
     const n = parseInt(v, 10);
     return Number.isFinite(n) && n > 0 ? n : undefined;
   }
+  async function dbNum(key: string): Promise<number | undefined> {
+    const v = await dbStr(key);
+    if (v === undefined) return undefined;
+    const n = Number(v);
+    return Number.isNaN(n) ? undefined : n;
+  }
   const dbWarnBytes = await dbInt('content_sanity.bytes_warn');
   const dbBlockBytes = await dbInt('content_sanity.bytes_block');
   const dbJunkEnabled = await dbBool('content_sanity.junk_patterns_enabled');
@@ -759,6 +767,8 @@ export async function loadConfigWithEngine(
   const dbVerdictModel = await dbStr('dream.synthesize.verdict_model');
   const dbMaxPromptTokens = await dbInt('dream.synthesize.max_prompt_tokens');
   const dbMaxChunksPerTranscript = await dbInt('dream.synthesize.max_chunks_per_transcript');
+  const dbSubagentTimeoutMs = await dbNum('dream.synthesize.subagent_timeout_ms');
+  const dbSubagentWaitTimeoutMs = await dbNum('dream.synthesize.subagent_wait_timeout_ms');
   const dbLookbackDays = await dbInt('dream.patterns.lookback_days');
   const dbMinEvidence = await dbInt('dream.patterns.min_evidence');
 
@@ -783,6 +793,12 @@ export async function loadConfigWithEngine(
   if (mergedSynth.max_chunks_per_transcript === undefined && dbMaxChunksPerTranscript !== undefined) {
     mergedSynth.max_chunks_per_transcript = dbMaxChunksPerTranscript;
   }
+  if (mergedSynth.subagent_timeout_ms === undefined && dbSubagentTimeoutMs !== undefined) {
+    mergedSynth.subagent_timeout_ms = dbSubagentTimeoutMs;
+  }
+  if (mergedSynth.subagent_wait_timeout_ms === undefined && dbSubagentWaitTimeoutMs !== undefined) {
+    mergedSynth.subagent_wait_timeout_ms = dbSubagentWaitTimeoutMs;
+  }
   if (mergedPatterns.lookback_days === undefined && dbLookbackDays !== undefined) {
     mergedPatterns.lookback_days = dbLookbackDays;
   }
@@ -854,6 +870,8 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
   // subagent handler's error message tells users to `config set` this, so it
   // must be a known key or `config set` rejects it without --force.
   'agent.use_gateway_loop',
+  // #2778: per-turn output-token cap for the subagent loop (default 8192).
+  'agent.max_output_tokens',
   // DB-plane (v0.32.3 search modes + related)
   'search.mode',
   'search.cache.enabled',
@@ -888,6 +906,8 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
   'models.chat',
   'models.eval.longmemeval',
   'facts.extraction_model',
+  // #2113: output-token cap for the per-turn facts extractor (default 4000).
+  'facts.extraction_max_tokens',
   // Dream cycle config
   'dream.synthesize.session_corpus_dir',
   'dream.synthesize.meeting_transcripts_dir',
@@ -895,8 +915,16 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
   'dream.synthesize.verdict_model',
   'dream.synthesize.max_prompt_tokens',
   'dream.synthesize.max_chunks_per_transcript',
+  // #2415: top-level namespace for synthesize/patterns output (default 'wiki').
+  'dream.synthesize.output_root',
+  'dream.synthesize.subagent_timeout_ms',
+  'dream.synthesize.subagent_wait_timeout_ms',
   'dream.patterns.lookback_days',
   'dream.patterns.min_evidence',
+  // #2782-family: patterns-phase subagent timeouts (mirror of the
+  // dream.synthesize.* pair from #1594).
+  'dream.patterns.subagent_timeout_ms',
+  'dream.patterns.subagent_wait_timeout_ms',
   // Emotional weight (v0.29)
   'emotional_weight.high_tags',
   'emotional_weight.user_holder',
@@ -945,6 +973,10 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
   // operator had to discover --force by reading source. Same class as the
   // spend-controls registration above.
   'auto_chronicle',
+  // #2606: chronicle judge output-token cap (default 4000). Event-dense
+  // pages overflowed the old hardcoded 1500 and were misrecorded as
+  // no_events; the cap is now configurable and truncation is surfaced.
+  'chronicle.judge_max_tokens',
   // Takes bootstrap (v0.41.18.0, A12). The onboard remediation's two-gate
   // consent reads this key, and enabling it is the documented path to
   // `gbrain takes extract --from-pages` — same unregistered-key class.

src/core/contextual-retrieval-service.ts

@@ -54,6 +54,7 @@ import {
 import {
   generatePerChunkSynopsis,
   SYNOPSIS_PROMPT_VERSION,
+  SYNOPSIS_DOC_MAX_CHARS,
   type GeneratePerChunkSynopsisResult,
 } from './page-summary.ts';
 import {
@@ -103,8 +104,17 @@ function getEmbeddingModelTag(): string {
 export function computeCorpusGeneration(args: {
   crMode: CRMode;
   haikuModel: string;
+  /**
+   * Resolved `SYNOPSIS_DOC_MAX_CHARS` for per_chunk_synopsis runs. When
+   * present, folded into the hash so changes to
+   * `GBRAIN_SYNOPSIS_DOC_MAX_CHARS` invalidate the prior cache cleanly.
+   * Omit for `crMode !== 'per_chunk_synopsis'` — title / none modes
+   * don't consult the cap and the field stays out of the hash for
+   * back-compat with pre-cap embeddings.
+   */
+  synopsisDocMaxChars?: number;
 }): string {
-  return createHash('sha256')
+  const h = createHash('sha256')
     .update(args.crMode)
     .update('|')
     .update(String(SYNOPSIS_PROMPT_VERSION))
@@ -113,9 +123,11 @@ export function computeCorpusGeneration(args: {
     .update('|')
     .update(String(TITLE_WRAPPER_VERSION))
     .update('|')
-    .update(getEmbeddingModelTag())
-    .digest('hex')
-    .slice(0, 16);
+    .update(getEmbeddingModelTag());
+  if (args.synopsisDocMaxChars !== undefined) {
+    h.update('|doc_cap=').update(String(args.synopsisDocMaxChars));
+  }
+  return h.digest('hex').slice(0, 16);
 }
 
 /**
@@ -253,7 +265,11 @@ export async function reembedPageWithContextualRetrieval(
       args.pageSlug,
       args.sourceId,
       resolution.mode,
-      computeCorpusGeneration({ crMode: resolution.mode, haikuModel: args.haikuModel ?? DEFAULT_HAIKU_MODEL }),
+      computeCorpusGeneration({
+        crMode: resolution.mode,
+        haikuModel: args.haikuModel ?? DEFAULT_HAIKU_MODEL,
+        synopsisDocMaxChars: resolution.mode === 'per_chunk_synopsis' ? SYNOPSIS_DOC_MAX_CHARS : undefined,
+      }),
     );
     return { kind: 'skipped', reason: 'no_chunks' };
   }
@@ -282,6 +298,7 @@ export async function reembedPageWithContextualRetrieval(
       const corpus_generation = computeCorpusGeneration({
         crMode: attemptMode,
         haikuModel,
+        synopsisDocMaxChars: attemptMode === 'per_chunk_synopsis' ? SYNOPSIS_DOC_MAX_CHARS : undefined,
       });
 
       // ── PHASE 2: single DB transaction ───────────────────────────

src/core/conversation-parser/builtins.ts

@@ -1,7 +1,7 @@
 /**
  * v0.41.16.0 — Built-in conversation parser pattern registry.
  *
- * Fourteen hand-vetted patterns covering the chat-export formats this
+ * Fifteen hand-vetted patterns covering the chat-export formats this
  * codebase is most likely to encounter. Each pattern's regex was
  * derived from a public format reference (source_doc field) so future
  * maintainers can verify against the wild shape.
@@ -50,7 +50,7 @@ export function cleanSpeaker(raw: string, override?: RegExp): string {
   return stripped || raw.trim();
 }
 
-/** The 14 hand-vetted built-in patterns. */
+/** The 15 hand-vetted built-in patterns. */
 export const BUILTIN_PATTERNS: readonly PatternEntry[] = [
   // -------------------------------------------------------------------
   // INLINE-DATE patterns (date in every line; less ambiguous; tried first).
@@ -178,6 +178,41 @@ export const BUILTIN_PATTERNS: readonly PatternEntry[] = [
       'OpenClaw meeting-ingestion pipeline reformat of Circleback transcripts (see your OpenClaw skills/meeting-ingestion/SKILL.md)',
   },
 
+  {
+    // iMessage sync's time-only 12-hour shape. AM/PM is required so this
+    // cannot shadow bold-paren-time's 24-hour form or imessage-slack's
+    // full-date form.
+    id: 'bold-paren-time-12h',
+    origin: 'builtin',
+    regex: /^\*\*(.+?)\*\*\s*\((\d{1,2}):(\d{2})\s*(AM|PM|am|pm)\)\s*:\s*(.*)$/,
+    captures: {
+      speaker_group: 1,
+      hour_group: 2,
+      minute_group: 3,
+      ampm_group: 4,
+      text_group: 5,
+    },
+    date_source: 'frontmatter',
+    time_format: '12h_ampm',
+    timezone_policy: 'utc_assumed_with_warn',
+    multi_line: false,
+    quick_reject: /^\*\*/,
+    test_positive: [
+      '**Me** (9:04 AM): sounds good, see you then',
+      '**+155****0135** (9:39 AM): Will do',
+      '**Alice Example** (12:00 PM): noon message',
+      '**Bob Example** (5:38 pm): lowercase ampm',
+    ],
+    test_negative: [
+      '**Alice** (00:00): 24h shape',
+      '**Alice Example** (2024-03-15 9:00 AM): full-date iMessage shape',
+      '**[18:37] G T:** telegram bracket',
+      'Alice (9:00 AM): missing the bold',
+    ],
+    source_doc:
+      'Time-only 12h AM/PM iMessage export shape: `**Speaker** (H:MM AM): text`',
+  },
+
   {
     // Fathom/phone-call raw transcripts in this workspace use a plain
     // `Speaker A: ...` / `Speaker B: ...` shape with no per-line time.

src/core/conversation-parser/parse.ts

@@ -321,11 +321,22 @@ export function applyPattern(
   if (!body) return [];
   const out: MatchedMessage[] = [];
   const lines = body.split(/\r?\n/);
+  // Some multi-day conversation exports use markdown date headings instead
+  // of repeating a date on every message. Keep the caller's context immutable
+  // while advancing a local date anchor as those headings are encountered.
+  const runningCtx: DateContext = { ...dateCtx };
+  const dateHeaderRe = /^#{1,4}\s+(\d{4}-\d{2}-\d{2})\s*$/;
   for (let i = 0; i < lines.length; i++) {
     const rawLine = lines[i];
     const line = rawLine.trim();
     if (!line) continue;
 
+    const dateHeader = dateHeaderRe.exec(line);
+    if (dateHeader) {
+      runningCtx.fallbackDate = dateHeader[1];
+      continue;
+    }
+
     // Quick-reject fast path.
     if (entry.quick_reject && !entry.quick_reject.test(line)) {
       // Continuation handling for orphan lines.
@@ -339,7 +350,7 @@ export function applyPattern(
 
     const m = entry.regex.exec(line);
     if (m) {
-      const iso = buildIso(m, entry, dateCtx);
+      const iso = buildIso(m, entry, runningCtx);
       if (iso === null) continue; // reconstruction failed; skip line
       const rawSpeaker = m[entry.captures.speaker_group] ?? '';
       const speaker = cleanSpeaker(rawSpeaker, entry.speaker_clean);
@@ -380,7 +391,7 @@ function getNonBlankLines(body: string, headCap?: number): string[] {
  * window) and `scorePatternFull` (whole body) delegate here so the
  * quick_reject + regex loop lives in one place. Reused by
  * `parseConversation`'s fallback path which pre-splits ONCE and
- * passes the array to all 12 candidates (saves 11 redundant body
+ * passes the array to all 15 candidates (saves 14 redundant body
  * splits per fallback pass).
  */
 function scoreFromLines(

src/core/cycle.ts

@@ -479,6 +479,37 @@ export interface CycleOpts {
    * Validated via `assertValidSourceId` in `cycleLockIdFor` (defense-in-depth).
    */
   sourceId?: string;
+  /**
+   * issue #2860 — one-shot per-invocation bypass of a phase's own
+   * `dream.<phase>.enabled` / `cycle.<phase>.enabled` config gate. Wired
+   * from `gbrain dream --phase <name> --once`.
+   *
+   * Deliberately typed as the SINGLE named `CyclePhase`, not a boolean —
+   * each gated phase's dispatch block below only honors the override when
+   * `onceForPhase` matches ITS OWN phase name, so the bypass can never leak
+   * to a different phase even if a caller passes a wider `phases` array
+   * than the CLI does (the CLI always restricts to `phases: [phase]`).
+   *
+   * Never reads or writes config — the phase still evaluates its config
+   * gate every call; this only overrides the boolean OUTCOME for that one
+   * call. Applies to: patterns, synthesize, conversation_facts_backfill,
+   * enrich_thin, skillopt (the phases that gate on a `.enabled` config
+   * key read inside the phase's own module). Does NOT apply to
+   * extract_atoms / synthesize_concepts — those are pack-gated via
+   * `packDeclaresPhase`, a different mechanism with its own existing
+   * one-shot escape hatch (`--drain` for extract_atoms).
+   */
+  onceForPhase?: CyclePhase;
+  /**
+   * Absolute wall-clock deadline (epoch ms) of the enclosing minion job,
+   * from `MinionJobContext.deadlineAtMs` (the claim-time `timeout_at`
+   * stamp). Phases that spawn bounded sub-work (patterns' subagent) clamp
+   * their own timeouts to the REMAINING time so one phase's fixed
+   * worst-case can't blow past the job budget and dead-letter the whole
+   * cycle mid-phase (#2781). Unset for direct callers (`gbrain dream`) —
+   * phases then use their configured timeouts unchanged.
+   */
+  deadlineAtMs?: number | null;
 }
 
 // ─── Lock primitives ───────────────────────────────────────────────
@@ -956,6 +987,12 @@ async function runPhaseExtract(
   dryRun: boolean,
   changedSlugs?: string[],
   signal?: AbortSignal,
+  // #1503: the brain source the cycle is scoped to (cycleSourceId — explicit
+  // --source or resolved from brainDir). Threaded to runExtractCore so
+  // fs-walk link/timeline rows carry source_id; without it addLinksBatch maps
+  // missing → 'default' and its pages JOIN drops every row on a federated
+  // brain ("Links: created 0 from N pages" every cycle).
+  sourceId?: string,
 ): Promise<PhaseResult> {
   try {
     const { runExtractCore } = await import('../commands/extract.ts');
@@ -978,6 +1015,7 @@ async function runPhaseExtract(
       dir: brainDir,
       slugs: changedSlugs,  // undefined = full walk (first run / manual)
       signal,
+      sourceId,
     });
     const linksCreated = result?.links_created ?? 0;
     const timelineCreated = result?.timeline_entries_created ?? 0;
@@ -1675,6 +1713,10 @@ export async function runCycle(
           from: opts.synthFrom,
           to: opts.synthTo,
           bypassDreamGuard: opts.synthBypassDreamGuard,
+          // #1586: scope synthesized writes to the cycle's resolved source
+          // (explicit --source wins, else derived from the checkout dir).
+          sourceId: cycleSourceId,
+          once: opts.onceForPhase === 'synthesize',
         }));
         result.duration_ms = duration_ms;
         phaseResults.push(result);
@@ -1706,7 +1748,7 @@ export async function runCycle(
         // If sync didn't run (phases exclude it) or failed, syncPagesAffected
         // is undefined → extract falls back to full walk (safe default).
         progress.start('cycle.extract');
-        const { result, duration_ms } = await timePhase(() => runPhaseExtract(engine, brainDir, dryRun, syncPagesAffected, opts.signal));
+        const { result, duration_ms } = await timePhase(() => runPhaseExtract(engine, brainDir, dryRun, syncPagesAffected, opts.signal, cycleSourceId));
         result.duration_ms = duration_ms;
         phaseResults.push(result);
         progress.finish();
@@ -1878,6 +1920,8 @@ export async function runCycle(
           brainDir,
           dryRun,
           yieldDuringPhase: opts.yieldDuringPhase,
+          once: opts.onceForPhase === 'patterns',
+          deadlineAtMs: opts.deadlineAtMs ?? null,
         }));
         result.duration_ms = duration_ms;
         phaseResults.push(result);
@@ -2093,7 +2137,11 @@ export async function runCycle(
         progress.start('cycle.conversation_facts_backfill');
         const { runPhaseConversationFactsBackfill } = await import('./cycle/conversation-facts-backfill.ts');
         const { result, duration_ms } = await timePhase(() =>
-          runPhaseConversationFactsBackfill(engine, { dryRun, signal: opts.signal }),
+          runPhaseConversationFactsBackfill(engine, {
+            dryRun,
+            signal: opts.signal,
+            once: opts.onceForPhase === 'conversation_facts_backfill',
+          }),
         );
         result.duration_ms = duration_ms;
         phaseResults.push(result);
@@ -2121,7 +2169,11 @@ export async function runCycle(
         progress.start('cycle.enrich_thin');
         const { runPhaseEnrichThin } = await import('./cycle/enrich-thin.ts');
         const { result, duration_ms } = await timePhase(() =>
-          runPhaseEnrichThin(engine, { dryRun, signal: opts.signal }),
+          runPhaseEnrichThin(engine, {
+            dryRun,
+            signal: opts.signal,
+            once: opts.onceForPhase === 'enrich_thin',
+          }),
         );
         result.duration_ms = duration_ms;
         phaseResults.push(result);
@@ -2152,6 +2204,7 @@ export async function runCycle(
           runPhaseSkillopt({
             engine,
             dryRun,
+            once: opts.onceForPhase === 'skillopt',
             ...(opts.signal ? { signal: opts.signal } : {}),
           }),
         );

src/core/cycle/conversation-facts-backfill.ts

@@ -57,6 +57,14 @@ import {
 export interface ConversationFactsBackfillPhaseOpts {
   dryRun?: boolean;
   signal?: AbortSignal;
+  /**
+   * issue #2860 — `gbrain dream --phase conversation_facts_backfill --once`.
+   * Bypasses the `cycle.conversation_facts_backfill.enabled` gate for THIS
+   * call only; never reads or writes config. Per-source + brain-wide cost/
+   * walltime caps still apply — the override lifts the on/off switch, not
+   * the spend guards.
+   */
+  once?: boolean;
 }
 
 /** Phase return shape (matches PhaseResult contract from cycle.ts). */
@@ -155,17 +163,23 @@ export async function runPhaseConversationFactsBackfill(
   const cfg = await loadCfg(engine);
 
   if (!cfg.enabled) {
-    return {
-      phase: 'conversation_facts_backfill',
-      status: 'skipped',
-      duration_ms: 0,
-      summary: 'cycle.conversation_facts_backfill.enabled=false (default OFF)',
-      details: {
-        reason: 'disabled',
-        enable_hint:
-          'gbrain config set cycle.conversation_facts_backfill.enabled true',
-      },
-    };
+    if (!opts.once) {
+      return {
+        phase: 'conversation_facts_backfill',
+        status: 'skipped',
+        duration_ms: 0,
+        summary: 'cycle.conversation_facts_backfill.enabled=false (default OFF)',
+        details: {
+          reason: 'disabled',
+          enable_hint:
+            'gbrain config set cycle.conversation_facts_backfill.enabled true',
+        },
+      };
+    }
+    process.stderr.write(
+      '[dream] --once: cycle.conversation_facts_backfill.enabled is false but ' +
+      '--phase conversation_facts_backfill --once forces this run (config untouched)\n',
+    );
   }
 
   const startedAt = Date.now();

src/core/cycle/enrich-thin.ts

@@ -45,6 +45,12 @@ import {
 export interface EnrichThinPhaseOpts {
   dryRun?: boolean;
   signal?: AbortSignal;
+  /**
+   * issue #2860 — `gbrain dream --phase enrich_thin --once`. Bypasses the
+   * `cycle.enrich_thin.enabled` gate for THIS call only; never reads or
+   * writes config. Per-source + brain-wide cost/walltime caps still apply.
+   */
+  once?: boolean;
 }
 
 export interface EnrichThinPhaseResult {
@@ -139,16 +145,22 @@ export async function runPhaseEnrichThin(
   const cfg = await loadCfg(engine);
 
   if (!cfg.enabled) {
-    return {
-      phase: 'enrich_thin',
-      status: 'skipped',
-      duration_ms: 0,
-      summary: 'cycle.enrich_thin.enabled=false (default OFF)',
-      details: {
-        reason: 'disabled',
-        enable_hint: 'gbrain config set cycle.enrich_thin.enabled true',
-      },
-    };
+    if (!opts.once) {
+      return {
+        phase: 'enrich_thin',
+        status: 'skipped',
+        duration_ms: 0,
+        summary: 'cycle.enrich_thin.enabled=false (default OFF)',
+        details: {
+          reason: 'disabled',
+          enable_hint: 'gbrain config set cycle.enrich_thin.enabled true',
+        },
+      };
+    }
+    process.stderr.write(
+      '[dream] --once: cycle.enrich_thin.enabled is false but ' +
+      '--phase enrich_thin --once forces this run (config untouched)\n',
+    );
   }
 
   const startedAt = Date.now();

src/core/cycle/extract-facts.ts

@@ -11,15 +11,17 @@
  *   1. Reads the markdown body (DB-side fetch via engine.getPage).
  *   2. Parses the `## Facts` fence with parseFactsFence.
  *   3. Maps ParsedFact → FenceExtractedFact via extractFactsFromFenceText.
- *   4. Wipes the page's DB index via deleteFactsForPage.
- *   5. Re-inserts via engine.insertFacts batch.
+ *   4. De-dupes rows by canonical (claim, source) content key.
+ *   5. Reconciles the page-scoped DB index: no-op when already in sync,
+ *      insert only missing keys when possible, or wipe/reinsert when stale
+ *      DB rows need cleanup (#1781 — the unconditional wipe-and-reinsert
+ *      made every cycle non-idempotent, re-appending duplicate rows).
  *
- * After the phase, the DB index for every affected page byte-matches
- * the fence (modulo embeddings + runtime-derived fields). Pages with
- * no fence go through delete-then-empty-insert — DB rows for that
- * page coordinate are wiped; legacy NULL-source_markdown_slug rows
- * survive because deleteFactsForPage targets source_markdown_slug =
- * slug only.
+ * After the phase, the DB index for every affected page matches the
+ * fence's canonical (claim, source) row set (modulo embeddings +
+ * runtime-derived fields). Pages with no fence wipe DB rows for that
+ * page coordinate only; legacy NULL-source_markdown_slug rows survive
+ * because deleteFactsForPage targets source_markdown_slug = slug only.
  *
  * Empty-fence guard (Codex R2-#7): the phase refuses to do its
  * destructive reconciliation pass when legacy rows (row_num IS NULL,
@@ -35,7 +37,11 @@ import type { BrainEngine } from '../engine.ts';
 import { writeReceipt } from '../extract/receipt-writer.ts';
 import { upsertExtractRollup } from '../extract/rollup-writer.ts';
 import { parseFactsFence } from '../facts-fence.ts';
-import { extractFactsFromFenceText } from '../facts/extract-from-fence.ts';
+import {
+  extractFactsFromFenceText,
+  FENCE_SOURCE_DEFAULT,
+  type FenceExtractedFact,
+} from '../facts/extract-from-fence.ts';
 import {
   runPhantomRedirectPass,
   emptyPhantomPassResult,
@@ -44,6 +50,51 @@ import {
 import { embed, isAvailable } from '../ai/gateway.ts';
 import { isAborted } from '../abort-check.ts';
 
+interface ExistingPageFact {
+  fact: string;
+  source: string | null;
+  row_num: number | string | null;
+}
+
+function factContentKey(fact: string, source: string | null | undefined): string {
+  return `${fact}\u0000${source ?? FENCE_SOURCE_DEFAULT}`;
+}
+
+function dedupeFactsByContentKey(facts: FenceExtractedFact[]): FenceExtractedFact[] {
+  const seen = new Set<string>();
+  const deduped: FenceExtractedFact[] = [];
+  for (const fact of facts) {
+    const key = factContentKey(fact.fact, fact.source);
+    if (seen.has(key)) continue;
+    seen.add(key);
+    deduped.push(fact);
+  }
+  return deduped;
+}
+
+/**
+ * Fence-owned DB rows for one page coordinate. Excludes `cli:`-origin
+ * conversation facts (#1928) — they are not fence-owned, so they must
+ * neither count as "stale" (which would force a wipe every cycle) nor
+ * be compared against the fence's row set. Mirrors the
+ * excludeSourcePrefixes filter deleteFactsForPage applies on the wipe.
+ */
+async function listExistingFactsForPage(
+  engine: BrainEngine,
+  slug: string,
+  sourceId: string,
+): Promise<ExistingPageFact[]> {
+  return engine.executeRaw<ExistingPageFact>(
+    `SELECT fact, source, row_num
+       FROM facts
+      WHERE source_id = $1
+        AND source_markdown_slug = $2
+        AND COALESCE(source, '') NOT LIKE 'cli:%'
+      ORDER BY row_num ASC, id ASC`,
+    [sourceId, slug],
+  );
+}
+
 export interface ExtractFactsOpts {
   /** Subset of slugs to reconcile. undefined = walk every page in the brain. */
   slugs?: string[];
@@ -220,28 +271,70 @@ export async function runExtractFacts(
 
     if (parsed.facts.length > 0) result.pagesWithFacts += 1;
 
-    if (opts.dryRun) continue;
-
-    // Wipe-and-reinsert per page. The delete targets source_markdown_slug =
-    // slug only, so NULL-source_markdown_slug legacy rows survive (the
-    // partial-UNIQUE-index keyspace). #1928: `cli:`-origin facts (conversation
-    // facts from extract-conversation-facts) are NOT fence-owned — the page
-    // carries no `## Facts` fence to recreate them — so they MUST survive this
-    // reconcile. Exclude them from the wipe.
-    const deleted = await engine.deleteFactsForPage(slug, sourceId, {
-      excludeSourcePrefixes: ['cli:'],
-    });
-    result.factsDeleted += deleted.deleted;
-
-    if (parsed.facts.length === 0) continue;
-
     // v0.35.4 (D-ENG-1) — thread page.effective_date as the fallback
     // valid_from. Without this, fence rows without explicit `validFrom:`
     // land with `valid_from = now()` (import timestamp) and every
     // trajectory query against the page returns import dates instead of
     // claim dates.
     const pageEffectiveDate = page.effective_date ? new Date(page.effective_date) : null;
-    const extracted = extractFactsFromFenceText(parsed.facts, slug, sourceId, { pageEffectiveDate });
+    const extracted = dedupeFactsByContentKey(
+      extractFactsFromFenceText(parsed.facts, slug, sourceId, { pageEffectiveDate }),
+    );
+
+    if (opts.dryRun) continue;
+
+    // #1781 — reconcile instead of unconditional wipe-and-reinsert. Compare
+    // the fence's canonical (claim, source) row set against the page's
+    // fence-owned DB rows: no-op when already in sync, insert only missing
+    // keys when possible, wipe/reinsert only when stale rows need cleanup.
+    const existing = await listExistingFactsForPage(engine, slug, sourceId);
+    const existingKeys = new Set(existing.map(f => factContentKey(f.fact, f.source)));
+    const desiredByKey = new Map(extracted.map(f => [factContentKey(f.fact, f.source), f]));
+
+    if (extracted.length === 0) {
+      if (existing.length > 0) {
+        // The delete targets source_markdown_slug = slug only, so
+        // NULL-source_markdown_slug legacy rows survive (the
+        // partial-UNIQUE-index keyspace). #1928: `cli:`-origin facts
+        // (conversation facts from extract-conversation-facts) are NOT
+        // fence-owned — the page carries no `## Facts` fence to recreate
+        // them — so they MUST survive this reconcile.
+        const deleted = await engine.deleteFactsForPage(slug, sourceId, {
+          excludeSourcePrefixes: ['cli:'],
+        });
+        result.factsDeleted += deleted.deleted;
+      }
+      continue;
+    }
+
+    const hasStaleExisting = existing.some(f => !desiredByKey.has(factContentKey(f.fact, f.source)));
+    const hasDuplicateExisting = existing.length !== existingKeys.size;
+    const hasRowNumDrift = existing.some(f => {
+      const desired = desiredByKey.get(factContentKey(f.fact, f.source));
+      return desired !== undefined && Number(f.row_num) !== desired.row_num;
+    });
+
+    if (
+      existing.length === extracted.length &&
+      !hasStaleExisting &&
+      !hasDuplicateExisting &&
+      !hasRowNumDrift
+    ) {
+      continue;
+    }
+
+    let toInsert = extracted.filter(f => !existingKeys.has(factContentKey(f.fact, f.source)));
+    if (hasStaleExisting || hasDuplicateExisting || hasRowNumDrift) {
+      // Fall back to the legacy page-level reconcile when old DB rows must
+      // be removed. Same delete scoping as above: legacy
+      // NULL-source_markdown_slug rows and `cli:`-origin conversation
+      // facts (#1928) survive.
+      const deleted = await engine.deleteFactsForPage(slug, sourceId, {
+        excludeSourcePrefixes: ['cli:'],
+      });
+      result.factsDeleted += deleted.deleted;
+      toInsert = extracted;
+    }
 
     // v0.35.4 (D-CDX-3) — batch-embed before insert. Without this,
     // cycle-inserted facts land with `embedding = NULL`, which breaks
@@ -250,17 +343,17 @@ export async function runExtractFacts(
     // unavailable (no API key configured), facts still insert with
     // NULL embeddings — drift_score gracefully returns null and
     // clustering falls back to recency.
-    if (isAvailable('embedding') && extracted.length > 0) {
+    if (isAvailable('embedding') && toInsert.length > 0) {
       try {
-        const texts = extracted.map(e => e.fact);
+        const texts = toInsert.map(e => e.fact);
         // #1972: forward the abort signal so a cancelled cycle's in-flight
         // batch embed (a network call) is itself abortable, not just the loop.
         const embeddings = await embed(texts, { abortSignal: opts.signal });
         // Defensive: embed should return one vector per input; if the
         // gateway returns a partial array (provider partial-batch retry
         // returning fewer than requested), only fill what we have.
-        for (let i = 0; i < extracted.length && i < embeddings.length; i++) {
-          extracted[i].embedding = embeddings[i];
+        for (let i = 0; i < toInsert.length && i < embeddings.length; i++) {
+          toInsert[i].embedding = embeddings[i];
         }
       } catch (err) {
         // Embedding failure is non-fatal — facts still get inserted, just
@@ -271,7 +364,9 @@ export async function runExtractFacts(
       }
     }
 
-    const inserted = await engine.insertFacts(extracted, { source_id: sourceId }); // gbrain-allow-direct-insert: extract_facts cycle phase reconciles fence → DB
+    if (toInsert.length === 0) continue;
+
+    const inserted = await engine.insertFacts(toInsert, { source_id: sourceId }); // gbrain-allow-direct-insert: extract_facts cycle phase reconciles fence → DB
     result.factsInserted += inserted.inserted;
   }
 

src/core/cycle/patterns.ts

@@ -19,7 +19,7 @@
  */
 
 import { join, dirname } from 'node:path';
-import { mkdirSync, writeFileSync, existsSync, readFileSync } from 'node:fs';
+import { mkdirSync, writeFileSync } from 'node:fs';
 import type { BrainEngine } from '../engine.ts';
 import type { PhaseResult, PhaseError } from '../cycle.ts';
 import { MinionQueue } from '../minions/queue.ts';
@@ -27,11 +27,73 @@ import { waitForCompletion, TimeoutError } from '../minions/wait-for-completion.
 import type { MinionJobInput, SubagentHandlerData } from '../minions/types.ts';
 import { serializeMarkdown } from '../markdown.ts';
 import type { Page, PageType } from '../types.ts';
+// #2415: allow-list + output-root resolution shared with the synthesize
+// phase — both phases must agree on the configured namespace.
+import { loadAllowedSlugPrefixes, loadOutputRoot } from './synthesize.ts';
+import { probeChatModel } from '../ai/gateway.ts';
+import { normalizeModelId } from '../model-id.ts';
 
 export interface PatternsPhaseOpts {
   brainDir: string;
   dryRun: boolean;
   yieldDuringPhase?: () => Promise<void>;
+  /**
+   * issue #2860 — `gbrain dream --phase patterns --once`. Bypasses the
+   * `dream.patterns.enabled` gate for THIS call only; never reads or
+   * writes config.
+   */
+  once?: boolean;
+  /**
+   * Absolute deadline (epoch ms) of the enclosing minion job, or null for
+   * direct callers (`gbrain dream`). When set, the subagent's job timeout
+   * and the wait timeout are clamped so the phase finishes (or times out)
+   * BEFORE the parent job's budget expires — a fixed 30/35-min default
+   * inside an interval-derived cycle budget dead-letters the whole cycle
+   * mid-phase and starves every tail phase (#2781).
+   */
+  deadlineAtMs?: number | null;
+}
+
+/**
+ * Stop-margin reserved under the parent deadline when clamping subagent
+ * budgets. NOT a promise that tail phases complete — the cycle is allowed
+ * to go partial and resume next tick. This only guarantees the phase's
+ * wait returns and the handler unwinds cleanly before the worker's abort
+ * fires: wait poll interval (5s) + worker force-evict grace (30s) + lock
+ * and DB cleanup headroom.
+ */
+export const CYCLE_DEADLINE_RESERVE_MS = 60 * 1000;
+
+/**
+ * Smallest remaining budget worth submitting a subagent for. Below this,
+ * the LLM call is near-certain to be killed mid-flight — wasted spend and
+ * a guaranteed-timeout child — so the phase skips honestly instead
+ * (`insufficient_cycle_budget`) and the next cycle retries with a fresh
+ * budget.
+ */
+export const MIN_PATTERNS_SUBAGENT_BUDGET_MS = 2 * 60 * 1000;
+
+/**
+ * Clamp the configured subagent budgets to the remaining parent-job time.
+ * Both timeouts derive from the SAME absolute child deadline
+ * (`deadlineAtMs - reserve`) so the child job's kill switch and our wait
+ * agree. Returns null when the remaining budget is below the minimum —
+ * caller should skip the phase without submitting.
+ */
+export function clampSubagentBudgets(
+  config: { subagentTimeoutMs: number; subagentWaitTimeoutMs: number },
+  deadlineAtMs: number | null | undefined,
+  nowMs: number,
+): { timeoutMs: number; waitTimeoutMs: number } | null {
+  if (deadlineAtMs == null) {
+    return { timeoutMs: config.subagentTimeoutMs, waitTimeoutMs: config.subagentWaitTimeoutMs };
+  }
+  const childBudgetMs = deadlineAtMs - CYCLE_DEADLINE_RESERVE_MS - nowMs;
+  if (childBudgetMs < MIN_PATTERNS_SUBAGENT_BUDGET_MS) return null;
+  return {
+    timeoutMs: Math.min(config.subagentTimeoutMs, childBudgetMs),
+    waitTimeoutMs: Math.min(config.subagentWaitTimeoutMs, childBudgetMs),
+  };
 }
 
 export async function runPhasePatterns(
@@ -43,11 +105,17 @@ export async function runPhasePatterns(
     const config = await loadPatternsConfig(engine);
 
     if (!config.enabled) {
-      return skipped('disabled', 'dream.patterns.enabled is false');
+      if (!opts.once) {
+        return skipped('disabled', 'dream.patterns.enabled is false');
+      }
+      process.stderr.write(
+        '[dream] --once: dream.patterns.enabled is false but ' +
+        '--phase patterns --once forces this run (config untouched)\n',
+      );
     }
 
     // Gather reflections within lookback window.
-    const reflections = await gatherReflections(engine, config.lookbackDays);
+    const reflections = await gatherReflections(engine, config.lookbackDays, config.outputRoot);
     if (reflections.length < config.minEvidence) {
       return skipped(
         'insufficient_evidence',
@@ -63,27 +131,51 @@ export async function runPhasePatterns(
       });
     }
 
-    // Submit one subagent for pattern detection.
-    if (!process.env.ANTHROPIC_API_KEY) {
-      return skipped('no_api_key', 'ANTHROPIC_API_KEY unset; pattern detection skipped');
+    // Submit one subagent for pattern detection. The subagent dispatches via
+    // the gateway model-tier resolver, so gate on "is the resolved model's
+    // provider reachable" rather than ANTHROPIC_API_KEY specifically — a
+    // hardcoded env gate misclassified non-Anthropic stacks (litellm,
+    // deepseek, openrouter, ...) as "no upstream" even though the subagent
+    // routes them through the gateway (agent.use_gateway_loop), and it missed
+    // Anthropic keys set via `gbrain config set anthropic_api_key`. Same
+    // probe semantics as think/index.ts + synthesize's makeJudgeClient:
+    // unknown provider/model or Anthropic-without-key skips cheaply; other
+    // providers' auth is checked lazily at dispatch and surfaces in the job
+    // outcome. (Takeover of PR #2279's intent by @brettdavies.)
+    const probe = probeChatModel(normalizeModelId(config.model));
+    if (!probe.ok) {
+      return skipped('no_provider', `pattern detection skipped: ${probe.detail}`);
     }
 
-    const allowedSlugPrefixes = await loadAllowedSlugPrefixes();
+    const allowedSlugPrefixes = await loadAllowedSlugPrefixes(config.outputRoot);
     if (allowedSlugPrefixes.length === 0) {
       return failed(makeError('InternalError', 'NO_ALLOWLIST',
         'skills/_brain-filing-rules.json missing dream_synthesize_paths.globs'));
     }
 
+    // #2781: budget the subagent from the REMAINING parent-job time, not
+    // the fixed config default. Checked after the cheap gates (disabled /
+    // insufficient_evidence / no_provider) so a skip for budget reasons
+    // only fires when the phase would otherwise have submitted.
+    const budgets = clampSubagentBudgets(config, opts.deadlineAtMs, Date.now());
+    if (budgets === null) {
+      return skipped(
+        'insufficient_cycle_budget',
+        `remaining cycle budget under ${Math.round(MIN_PATTERNS_SUBAGENT_BUDGET_MS / 1000)}s ` +
+        `(reserve ${Math.round(CYCLE_DEADLINE_RESERVE_MS / 1000)}s); next cycle retries with a fresh budget`,
+      );
+    }
+
     const queue = new MinionQueue(engine);
     const data: SubagentHandlerData = {
-      prompt: buildPatternsPrompt(reflections, config.minEvidence),
+      prompt: buildPatternsPrompt(reflections, config.minEvidence, config.outputRoot),
       model: config.model,
       max_turns: 30,
       allowed_slug_prefixes: allowedSlugPrefixes,
     };
     const submitOpts: Partial<MinionJobInput> = {
       max_stalled: 3,
-      timeout_ms: 30 * 60 * 1000,
+      timeout_ms: budgets.timeoutMs,
     };
     const job = await queue.add('subagent', data as unknown as Record<string, unknown>, submitOpts, {
       allowProtectedSubmit: true,
@@ -92,13 +184,23 @@ export async function runPhasePatterns(
     let outcome: string;
     try {
       const final = await waitForCompletion(queue, job.id, {
-        timeoutMs: 35 * 60 * 1000,
+        timeoutMs: budgets.waitTimeoutMs,
         pollMs: 5 * 1000,
       });
       outcome = final.status;
     } catch (e) {
-      if (e instanceof TimeoutError) outcome = 'timeout';
-      else throw e;
+      if (e instanceof TimeoutError) {
+        outcome = 'timeout';
+        // The child's own timeout_ms clock starts at ITS claim, not at
+        // submit — a child that sat queued behind other work can outlive
+        // the parent deadline this wait was clamped to. Cancel it so the
+        // subagent can't keep spending/writing after the phase gave up
+        // (waiting child → cancelled immediately; active child → lock
+        // stripped, worker abort fires on next renew tick).
+        try { await queue.cancelJob(job.id); } catch { /* best-effort */ }
+      } else {
+        throw e;
+      }
     }
 
     if (opts.yieldDuringPhase) {
@@ -113,13 +215,47 @@ export async function runPhasePatterns(
     // Reverse-write to fs.
     const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs);
 
-    return ok(`${writtenRefs.length} pattern page(s) written/updated (${outcome})`, {
+    const details = {
       reflections_considered: reflections.length,
       patterns_written: writtenRefs.length,
       reverse_write_count: reverseWriteCount,
       child_outcome: outcome,
       job_id: job.id,
-    });
+    };
+
+    // #2782: the phase status must reflect the child outcome. Pre-fix this
+    // returned status:ok even when the subagent timed out (e.g. no
+    // subagent-capable worker slot free for the whole wait window) and zero
+    // pattern pages were written — a silent no-op for days.
+    if (outcome !== 'complete') {
+      if (writtenRefs.length === 0) {
+        return {
+          phase: 'patterns',
+          status: 'fail',
+          duration_ms: 0,
+          summary: `pattern-detection subagent job ${job.id} ended '${outcome}'; nothing was written`,
+          details,
+          error: makeError(
+            outcome === 'timeout' ? 'Timeout' : 'InternalError',
+            `PATTERNS_CHILD_${outcome.toUpperCase()}`,
+            `subagent job ${job.id} outcome '${outcome}' with zero pattern pages written`,
+            outcome === 'timeout'
+              ? 'A timeout with zero writes usually means no subagent-capable worker claimed the job. Check `gbrain jobs list` and worker capacity.'
+              : undefined,
+          ),
+        };
+      }
+      // Partial: the child died/timed out but some pages landed first.
+      return {
+        phase: 'patterns',
+        status: 'warn',
+        duration_ms: 0,
+        summary: `${writtenRefs.length} pattern page(s) written but subagent job ${job.id} ended '${outcome}'`,
+        details,
+      };
+    }
+
+    return ok(`${writtenRefs.length} pattern page(s) written/updated (${outcome})`, details);
   } catch (e) {
     return failed(makeError('InternalError', 'PATTERNS_PHASE_FAIL',
       e instanceof Error ? (e.message || 'patterns phase threw') : String(e)));
@@ -135,6 +271,22 @@ interface PatternsConfig {
   lookbackDays: number;
   minEvidence: number;
   model: string;
+  /** #2415: shared output namespace (dream.synthesize.output_root, default 'wiki'). */
+  outputRoot: string;
+  /** #1594-family: subagent job timeout, config `dream.patterns.subagent_timeout_ms`. */
+  subagentTimeoutMs: number;
+  /** #1594-family: waitForCompletion timeout, config `dream.patterns.subagent_wait_timeout_ms`. */
+  subagentWaitTimeoutMs: number;
+}
+
+const DEFAULT_PATTERNS_SUBAGENT_TIMEOUT_MS = 30 * 60 * 1000;
+const DEFAULT_PATTERNS_SUBAGENT_WAIT_TIMEOUT_MS = 35 * 60 * 1000;
+
+async function getNumberConfig(engine: BrainEngine, key: string, fallback: number): Promise<number> {
+  const raw = await engine.getConfig(key);
+  if (raw === undefined || raw === null) return fallback;
+  const value = Number(raw);
+  return Number.isNaN(value) ? fallback : value;
 }
 
 async function loadPatternsConfig(engine: BrainEngine): Promise<PatternsConfig> {
@@ -155,6 +307,13 @@ async function loadPatternsConfig(engine: BrainEngine): Promise<PatternsConfig>
     lookbackDays: lookbackStr ? Math.max(1, parseInt(lookbackStr, 10) || 30) : 30,
     minEvidence: minEvidenceStr ? Math.max(1, parseInt(minEvidenceStr, 10) || 3) : 3,
     model,
+    outputRoot: await loadOutputRoot(engine),
+    subagentTimeoutMs: await getNumberConfig(
+      engine, 'dream.patterns.subagent_timeout_ms', DEFAULT_PATTERNS_SUBAGENT_TIMEOUT_MS,
+    ),
+    subagentWaitTimeoutMs: await getNumberConfig(
+      engine, 'dream.patterns.subagent_wait_timeout_ms', DEFAULT_PATTERNS_SUBAGENT_WAIT_TIMEOUT_MS,
+    ),
   };
 }
 
@@ -169,16 +328,19 @@ interface ReflectionRef {
 async function gatherReflections(
   engine: BrainEngine,
   lookbackDays: number,
+  outputRoot = 'wiki',
 ): Promise<ReflectionRef[]> {
   const since = new Date(Date.now() - lookbackDays * 24 * 60 * 60 * 1000).toISOString();
+  // #2415: reflections live under the configured output root (bound as a
+  // parameter; outputRoot is slug-grammar-validated by loadOutputRoot).
   const rows = await engine.executeRaw<{ slug: string; title: string | null; compiled_truth: string | null }>(
     `SELECT slug, title, compiled_truth
        FROM pages
-      WHERE slug LIKE 'wiki/personal/reflections/%'
+      WHERE slug LIKE $2
         AND updated_at >= $1::timestamptz
       ORDER BY updated_at DESC
       LIMIT 100`,
-    [since],
+    [since, `${outputRoot}/personal/reflections/%`],
   );
   return rows.map(r => ({
     slug: r.slug,
@@ -189,7 +351,7 @@ async function gatherReflections(
 
 // ── Prompt ────────────────────────────────────────────────────────────
 
-function buildPatternsPrompt(reflections: ReflectionRef[], minEvidence: number): string {
+function buildPatternsPrompt(reflections: ReflectionRef[], minEvidence: number, outputRoot = 'wiki'): string {
   const today = new Date().toISOString().slice(0, 10);
   const corpus = reflections
     .map((r, i) => `### ${i + 1}. [[${r.slug}]] — ${r.title}\n${r.excerpt}`)
@@ -199,15 +361,15 @@ function buildPatternsPrompt(reflections: ReflectionRef[], minEvidence: number):
 
 OUTPUT POLICY
 - Only name a pattern if it appears in at least ${minEvidence} DISTINCT reflections.
-- Each pattern page MUST cite the reflections that constitute its evidence (use [[wiki/personal/reflections/...]] wikilinks).
+- Each pattern page MUST cite the reflections that constitute its evidence (use [[${outputRoot}/personal/reflections/...]] wikilinks).
 - Use \`search\` to check whether a similar pattern page already exists; if yes, update it (use the same slug). If no, create a new one.
-- Pattern slug format: \`wiki/personal/patterns/<topic-slug>\` (lowercase alphanumeric + hyphens; no underscores, no extension, no date).
+- Pattern slug format: \`${outputRoot}/personal/patterns/<topic-slug>\` (lowercase alphanumeric + hyphens; no underscores, no extension, no date).
 - A "pattern" is a recurring theme, anxiety, decision pattern, relationship dynamic, or self-knowledge motif. NOT a single insight. NOT a list of unrelated topics.
 
 DO NOT WRITE
 - A "patterns from today" digest (that's the dream-cycle-summaries page; not your job).
 - Patterns with <${minEvidence} reflections cited.
-- Anything outside wiki/personal/patterns/.
+- Anything outside ${outputRoot}/personal/patterns/.
 
 CONTEXT
 - Today: ${today}
@@ -298,27 +460,6 @@ function renderPageToMarkdown(page: Page, tags: string[]): string {
   );
 }
 
-// ── Allow-list (shared with synthesize.ts) ───────────────────────────
-
-async function loadAllowedSlugPrefixes(): Promise<string[]> {
-  const candidates = [
-    join(process.cwd(), 'skills', '_brain-filing-rules.json'),
-    join(__dirname, '..', '..', '..', 'skills', '_brain-filing-rules.json'),
-  ];
-  for (const path of candidates) {
-    if (!existsSync(path)) continue;
-    try {
-      const raw = readFileSync(path, 'utf8');
-      const parsed = JSON.parse(raw) as { dream_synthesize_paths?: { globs?: unknown } };
-      const globs = parsed?.dream_synthesize_paths?.globs;
-      if (Array.isArray(globs) && globs.every(g => typeof g === 'string')) {
-        return globs as string[];
-      }
-    } catch { /* try next */ }
-  }
-  return [];
-}
-
 // ── Status helpers ───────────────────────────────────────────────────
 
 function ok(summary: string, details: Record<string, unknown> = {}): PhaseResult {

src/core/cycle/propose-takes.ts

@@ -39,7 +39,7 @@
 
 import { randomUUID, createHash } from 'node:crypto';
 import { BaseCyclePhase, type ScopedReadOpts, type BasePhaseOpts } from './base-phase.ts';
-import { chat as gatewayChat } from '../ai/gateway.ts';
+import { chat as gatewayChat, getChatModel } from '../ai/gateway.ts';
 import { writeReceipt } from '../extract/receipt-writer.ts';
 import { upsertExtractRollup } from '../extract/rollup-writer.ts';
 import { GBrainError } from '../types.ts';
@@ -330,6 +330,8 @@ class ProposeTakesPhase extends BaseCyclePhase {
       opts.reporter.start('propose_takes.pages' as never, pages.length);
     }
 
+    const modelId = opts.model ?? getChatModel();
+
     for (const page of pages) {
       result.pages_scanned += 1;
       this.tick(opts);
@@ -359,7 +361,7 @@ class ProposeTakesPhase extends BaseCyclePhase {
 
       // Budget pre-check before the LLM call. Estimate: ~1500 input tokens + 500 output.
       const budget = this.checkBudget({
-        modelId: opts.model ?? 'claude-sonnet-4-6',
+        modelId,
         estimatedInputTokens: 1500,
         maxOutputTokens: 500,
       });
@@ -408,7 +410,7 @@ class ProposeTakesPhase extends BaseCyclePhase {
             p.weight,
             p.domain ?? null,
             JSON.stringify(existingTakes),
-            opts.model ?? 'claude-sonnet-4-6',
+            modelId,
           ],
         );
         result.proposals_inserted += 1;

src/core/cycle/synthesize-concepts.ts

@@ -23,7 +23,13 @@ import type { PhaseResult } from '../cycle.ts';
 import type { ProgressReporter } from '../progress.ts';
 import { writeReceipt } from '../extract/receipt-writer.ts';
 import { upsertExtractRollup } from '../extract/rollup-writer.ts';
-import { chat as gatewayChat } from '../ai/gateway.ts';
+import { chat as gatewayChat, isAvailable } from '../ai/gateway.ts';
+// #2163: concept pages route through importFromContent (the same
+// parse→chunk→embed pipeline put_page uses) instead of a bare engine.putPage,
+// so they land in the retrieval surface (content_chunks + embeddings) where
+// source-boost's 1.3× 'concepts/' weighting can actually reach them.
+import { importFromContent } from '../import-file.ts';
+import { serializeMarkdown } from '../markdown.ts';
 
 const DEFAULT_BUDGET_USD = 1.5;
 const TIER_T1_MIN = 10;
@@ -216,19 +222,23 @@ export async function runPhaseSynthesizeConcepts(
 
     if (!opts.dryRun) {
       const title = group.conceptSlug.split('/').pop() ?? group.conceptSlug;
-      await engine.putPage(`concepts/${title}`, {
-        title: title.replace(/-/g, ' '),
-        type: 'concept',
-        compiled_truth: narrative,
-        frontmatter: {
-          type: 'concept',
+      // #2163: serialize to markdown and import via the canonical pipeline so
+      // the page is chunked (+ embedded when a provider is configured) —
+      // mirrors put_page's isAvailable('embedding') → noEmbed gate.
+      const md = serializeMarkdown(
+        {
           tier: group.tier,
           mention_count: group.atomTitles.length,
           composite_score: group.atomTitles.length,
           synthesized_at: new Date().toISOString(),
           synthesized_by: 'synthesize_concepts-v0.41',
         },
-        timeline: '',
+        narrative,
+        '',
+        { type: 'concept', title: title.replace(/-/g, ' '), tags: [] },
+      );
+      await importFromContent(engine, `concepts/${title}`, md, {
+        noEmbed: !isAvailable('embedding'),
       });
     }
     conceptsWritten++;

src/core/cycle/synthesize.ts

@@ -75,6 +75,8 @@ const MIN_PROMPT_TOKENS = 100_000;
 const DEFAULT_MAX_CHUNKS = 24;
 /** Conservative default budget when model is unknown (200K × HEADROOM_RATIO). */
 const UNKNOWN_MODEL_BUDGET_TOKENS = 180_000;
+const DEFAULT_SUBAGENT_TIMEOUT_MS = 30 * 60 * 1000;
+const DEFAULT_SUBAGENT_WAIT_TIMEOUT_MS = 35 * 60 * 1000;
 
 /**
  * Compute per-chunk character budget for the resolved model + config override.
@@ -242,6 +244,21 @@ export interface SynthesizePhaseOpts {
    * the synthesize loop. Caller must opt in explicitly.
    */
   bypassDreamGuard?: boolean;
+  /**
+   * #1586: the cycle's resolved brain source (cycleSourceId from cycle.ts —
+   * explicit --source wins, else derived from the checkout dir). Threaded to
+   * every subagent child as `source_id` so put_page writes land in this
+   * source, and stamped onto collected refs so reverse-writes read the
+   * correct (source_id, slug) row. Unset → legacy 'default'.
+   */
+  sourceId?: string;
+  /**
+   * issue #2860 — `gbrain dream --phase synthesize --once`. Bypasses the
+   * `dream.synthesize.enabled` gate for THIS call only (does NOT bypass
+   * the `session_corpus_dir` not-configured check — there's nothing to
+   * run without a corpus). Never reads or writes config.
+   */
+  once?: boolean;
 }
 
 export async function runPhaseSynthesize(
@@ -275,8 +292,14 @@ export async function runPhaseSynthesize(
         'dream.synthesize.session_corpus_dir is unset');
     }
     if (!opts.inputFile && !config.enabled) {
-      return skipped('not_configured',
-        'dream.synthesize.enabled is explicitly false');
+      if (!opts.once) {
+        return skipped('not_configured',
+          'dream.synthesize.enabled is explicitly false');
+      }
+      process.stderr.write(
+        '[dream] --once: dream.synthesize.enabled is false but ' +
+        '--phase synthesize --once forces this run (config untouched)\n',
+      );
     }
 
     // Cooldown check (skipped for explicit --input / --date / --from / --to runs).
@@ -397,7 +420,7 @@ export async function runPhaseSynthesize(
 
     // Fan-out: submit one subagent per worth-processing transcript (or one
     // per chunk for transcripts that exceed the model's per-prompt budget).
-    const allowedSlugPrefixes = await loadAllowedSlugPrefixes();
+    const allowedSlugPrefixes = await loadAllowedSlugPrefixes(config.outputRoot);
     if (allowedSlugPrefixes.length === 0) {
       return failed(makeError('InternalError', 'NO_ALLOWLIST',
         'skills/_brain-filing-rules.json missing dream_synthesize_paths.globs'));
@@ -460,10 +483,13 @@ export async function runPhaseSynthesize(
           : config.model;
       for (let i = 0; i < chunks.length; i++) {
         const childData: SubagentHandlerData = {
-          prompt: buildSynthesisPrompt(t, chunks[i], i, chunks.length, priorContradictionsBlock),
+          prompt: buildSynthesisPrompt(t, chunks[i], i, chunks.length, priorContradictionsBlock, config.outputRoot),
           model: subagentModel,
           max_turns: 30,
           allowed_slug_prefixes: allowedSlugPrefixes,
+          // #1586: scope every child tool call to the cycle's resolved source
+          // so put_page writes land there instead of the hardcoded 'default'.
+          ...(opts.sourceId ? { source_id: opts.sourceId } : {}),
         };
         // Idempotency key parity:
         //   - single-chunk → legacy `dream:synth:<filePath>:<hash16>` (byte-
@@ -478,7 +504,7 @@ export async function runPhaseSynthesize(
           max_stalled: 3,
           on_child_fail: 'continue',
           idempotency_key,
-          timeout_ms: 30 * 60 * 1000, // 30 min per chunk
+          timeout_ms: config.subagentTimeoutMs,
         };
         const child = await queue.add(
           'subagent',
@@ -499,7 +525,7 @@ export async function runPhaseSynthesize(
     for (const jobId of childIds) {
       try {
         const job = await waitForCompletion(queue, jobId, {
-          timeoutMs: 35 * 60 * 1000,
+          timeoutMs: config.subagentWaitTimeoutMs,
           pollMs: 5 * 1000,
         });
         childOutcomes.push({ jobId, status: job.status });
@@ -522,20 +548,29 @@ export async function runPhaseSynthesize(
     // bare-hash slugs to `<hash6>-c<idx>` so chunked siblings can't collide
     // even if Sonnet drops the chunk suffix.
     // v0.32.8: refs carry source_id so reverseWriteRefs picks the correct
-    // (source, slug) row (currently always 'default' from subagent put_page).
-    const writtenRefs = await collectChildPutPageSlugs(engine, childIds, chunkInfo);
+    // (source, slug) row. #1586: refs are stamped with the cycle's resolved
+    // source (children write there via SubagentHandlerData.source_id).
+    const cycleSourceId = opts.sourceId ?? 'default';
+    const writtenRefs = await collectChildPutPageSlugs(engine, childIds, chunkInfo, cycleSourceId);
+
+    const summaryDate = opts.date ?? today();
+
+    // #2569: persist the dream-output identity marker into the DB frontmatter
+    // of every child-written page BEFORE reverse-rendering, so generated pages
+    // are queryable (`frontmatter->>'dream_generated'`) and a later put_page
+    // write-through (which re-renders from the DB row) can't erase the stamp.
+    await stampDreamProvenance(engine, writtenRefs, summaryDate);
 
     // Dual-write: reverse-render each DB row → markdown file.
-    const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs);
+    const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs, cycleSourceId);
 
     // Summary index page (deterministic; orchestrator-written via direct
     // engine.putPage so no allow-list path needed).
-    const summaryDate = opts.date ?? today();
     const summarySlug = `dream-cycle-summaries/${summaryDate}`;
     // Back-compat: writeSummaryPage takes string[] for display; map refs back to slugs.
     const writtenSlugs = writtenRefs.map(r => r.slug);
     if (SUMMARY_SLUG_RE.test(summarySlug)) {
-      await writeSummaryPage(engine, opts.brainDir, summarySlug, summaryDate, writtenSlugs, childOutcomes);
+      await writeSummaryPage(engine, opts.brainDir, summarySlug, summaryDate, writtenSlugs, childOutcomes, cycleSourceId);
     }
 
     // Write completion timestamp ON SUCCESS only.
@@ -593,6 +628,27 @@ interface SynthConfig {
    * `dream.synthesize.max_chunks_per_transcript`.
    */
   maxChunksPerTranscript: number;
+  /**
+   * #2415: top-level namespace for synthesized output (reflections, originals,
+   * patterns). Config key `dream.synthesize.output_root`; default 'wiki' —
+   * zero behavior change unless set. No trailing slash. Must satisfy the slug
+   * grammar; invalid values fall back to 'wiki' with a stderr warning.
+   */
+  outputRoot: string;
+  subagentTimeoutMs: number;
+  subagentWaitTimeoutMs: number;
+}
+
+/** #2415: shared output-root resolution (synthesize + patterns phases). */
+export async function loadOutputRoot(engine: BrainEngine): Promise<string> {
+  const raw = await engine.getConfig('dream.synthesize.output_root');
+  if (!raw) return 'wiki';
+  const trimmed = raw.trim().replace(/^\/+|\/+$/g, '');
+  if (SUMMARY_SLUG_RE.test(trimmed)) return trimmed;
+  process.stderr.write(
+    `[dream] dream.synthesize.output_root "${raw}" is not a valid slug prefix; falling back to "wiki".\n`,
+  );
+  return 'wiki';
 }
 
 async function loadSynthConfig(engine: BrainEngine): Promise<SynthConfig> {
@@ -621,6 +677,16 @@ async function loadSynthConfig(engine: BrainEngine): Promise<SynthConfig> {
   const cooldownHoursStr = await engine.getConfig('dream.synthesize.cooldown_hours');
   const maxPromptTokensStr = await engine.getConfig('dream.synthesize.max_prompt_tokens');
   const maxChunksStr = await engine.getConfig('dream.synthesize.max_chunks_per_transcript');
+  const subagentTimeoutMs = await getNumberConfig(
+    engine,
+    'dream.synthesize.subagent_timeout_ms',
+    DEFAULT_SUBAGENT_TIMEOUT_MS,
+  );
+  const subagentWaitTimeoutMs = await getNumberConfig(
+    engine,
+    'dream.synthesize.subagent_wait_timeout_ms',
+    DEFAULT_SUBAGENT_WAIT_TIMEOUT_MS,
+  );
 
   let excludePatterns: string[] = ['medical', 'therapy'];
   if (excludeStr) {
@@ -658,9 +724,23 @@ async function loadSynthConfig(engine: BrainEngine): Promise<SynthConfig> {
     cooldownHours: cooldownHoursStr ? Math.max(0, parseInt(cooldownHoursStr, 10) || 12) : 12,
     maxPromptTokens,
     maxChunksPerTranscript,
+    outputRoot: await loadOutputRoot(engine),
+    subagentTimeoutMs,
+    subagentWaitTimeoutMs,
   };
 }
 
+async function getNumberConfig(
+  engine: BrainEngine,
+  key: string,
+  fallback: number,
+): Promise<number> {
+  const raw = await engine.getConfig(key);
+  if (raw === undefined || raw === null) return fallback;
+  const value = Number(raw);
+  return Number.isNaN(value) ? fallback : value;
+}
+
 async function checkCooldown(
   engine: BrainEngine,
   hours: number,
@@ -677,7 +757,13 @@ async function checkCooldown(
 
 // ── Allow-list source of truth ───────────────────────────────────────
 
-async function loadAllowedSlugPrefixes(): Promise<string[]> {
+/**
+ * #2415: `outputRoot` remaps the canonical `wiki/`-rooted globs to the
+ * configured namespace (e.g. `notes/personal/reflections/*`). Default 'wiki'
+ * returns the globs verbatim. Shared by the patterns phase (imported there —
+ * the two phases must enforce the same allow-list).
+ */
+export async function loadAllowedSlugPrefixes(outputRoot = 'wiki'): Promise<string[]> {
   // Search a few known locations relative to the binary / repo. The first
   // hit wins; if none found, return [].
   const candidates = [
@@ -691,7 +777,10 @@ async function loadAllowedSlugPrefixes(): Promise<string[]> {
       const parsed = JSON.parse(raw) as { dream_synthesize_paths?: { globs?: unknown } };
       const globs = parsed?.dream_synthesize_paths?.globs;
       if (Array.isArray(globs) && globs.every(g => typeof g === 'string')) {
-        return globs as string[];
+        if (outputRoot === 'wiki') return globs as string[];
+        return (globs as string[]).map(g =>
+          g.startsWith('wiki/') ? `${outputRoot}/${g.slice('wiki/'.length)}` : g,
+        );
       }
     } catch { /* try next */ }
   }
@@ -939,6 +1028,7 @@ function buildSynthesisPrompt(
   chunkIdx: number,
   chunkTotal: number,
   priorContradictionsBlock = '',
+  outputRoot = 'wiki',
 ): string {
   const dateHint = t.inferredDate ?? today();
   const baseSlugSegment = sanitizeForSlug(t.basename) || `session-${dateHint}`;
@@ -964,13 +1054,14 @@ OUTPUT POLICY (ALL of these are required)
 2. Cross-reference compulsively: every new page MUST contain at least one wikilink (e.g., \`[ref](people/jane-doe)\` or \`[[people/jane-doe]]\`) to existing brain content. Use the search tool to find existing pages first.
 3. Do NOT write to any path outside the allow-list shown in the put_page schema.
 4. Slug discipline: lowercase alphanumeric and hyphens only, slash-separated segments. NO underscores, NO file extensions.
+5. Self-contained opening: begin every new page's body with a 2-3 sentence summary that a reader unfamiliar with this transcript could understand on its own, before any quotes or detail. Do not assume the reader has the source conversation for context.
 
 TASKS
 A. Reflections (self-knowledge, pattern recognition, emotional processing):
-   slug: \`wiki/personal/reflections/${dateHint}-<topic-slug>-${hashSuffix}\`
+   slug: \`${outputRoot}/personal/reflections/${dateHint}-<topic-slug>-${hashSuffix}\`
 
 B. Originals (new ideas, frames, theses, mental models):
-   slug: \`wiki/originals/ideas/${dateHint}-<idea-slug>-${hashSuffix}\`
+   slug: \`${outputRoot}/originals/ideas/${dateHint}-<idea-slug>-${hashSuffix}\`
 
 C. People mentions: search first; if a page exists, do not put_page over it (the orchestrator handles people enrichment via timeline entries — your job is the reflection/original synthesis, NOT modifying existing person pages).
 
@@ -1011,6 +1102,7 @@ async function collectChildPutPageSlugs(
   engine: BrainEngine,
   childIds: number[],
   chunkInfo: Map<number, { idx: number; hash6: string }>,
+  sourceId = 'default',
 ): Promise<Array<{ slug: string; source_id: string }>> {
   if (childIds.length === 0) return [];
   // Raw fetch — NO SELECT DISTINCT. Preserves per-child slug duplicates so
@@ -1020,10 +1112,10 @@ async function collectChildPutPageSlugs(
   //
   // v0.32.8: returns Array<{slug, source_id}> instead of string[]. Subagent
   // put_page tool schema doesn't expose source_id (subagents are scoped to
-  // a single source); default to 'default' for the current dream-cycle
-  // product behavior. Threading the source_id through reverseWriteRefs
-  // guarantees getPage targets the correct (source, slug) row instead of
-  // the first DB match.
+  // a single source). #1586: the orchestrator scopes each child to the
+  // cycle's resolved source via SubagentHandlerData.source_id, and stamps
+  // the SAME source here so reverseWriteRefs / provenance reads target the
+  // correct (source_id, slug) row. Unset → legacy 'default'.
   const rows = await engine.executeRaw<{ job_id: number; slug: string }>(
     `SELECT job_id,
             COALESCE(input->>'slug', (input #>> '{}')::jsonb->>'slug') AS slug
@@ -1039,7 +1131,7 @@ async function collectChildPutPageSlugs(
     const ci = chunkInfo.get(r.job_id);
     rewritten.add(ci ? rewriteChunkedSlug(r.slug, ci.hash6, ci.idx) : r.slug);
   }
-  return Array.from(rewritten).sort().map(slug => ({ slug, source_id: 'default' }));
+  return Array.from(rewritten).sort().map(slug => ({ slug, source_id: sourceId }));
 }
 
 /**
@@ -1068,12 +1160,52 @@ async function hasLegacySingleChunkCompletion(
   return rows.length > 0;
 }
 
+// ── Dream-provenance DB stamp (#2569) ────────────────────────────────
+
+/**
+ * Persist the dream-output identity marker (`dream_generated: true` +
+ * `dream_cycle_date`) into the `pages.frontmatter` JSONB row for every page
+ * a synthesize child wrote. Render-time `frontmatterOverrides` alone only
+ * reach the markdown FILE — the DB row stayed unstamped, so DB consumers
+ * couldn't enumerate generated pages and a later put_page write-through
+ * (which re-renders from the DB row) silently erased the marker.
+ *
+ * Plain UPDATE through executeRawJsonb (raw object bound to $3::jsonb —
+ * never JSON.stringify into a ::jsonb cast; engine-parity safe, no new
+ * engine method). Best-effort per row: a stamp failure never kills the
+ * phase (the render-time override still covers the file).
+ */
+async function stampDreamProvenance(
+  engine: BrainEngine,
+  refs: Array<{ slug: string; source_id: string }>,
+  cycleDate: string,
+): Promise<void> {
+  if (refs.length === 0) return;
+  const { executeRawJsonb } = await import('../sql-query.ts');
+  for (const { slug, source_id } of refs) {
+    try {
+      await executeRawJsonb(
+        engine,
+        `UPDATE pages
+            SET frontmatter = COALESCE(frontmatter, '{}'::jsonb) || $3::jsonb
+          WHERE slug = $1 AND source_id = $2`,
+        [slug, source_id],
+        [{ dream_generated: true, dream_cycle_date: cycleDate }],
+      );
+    } catch (e) {
+      const msg = e instanceof Error ? e.message : String(e);
+      process.stderr.write(`[dream] provenance stamp ${slug}@${source_id} failed: ${msg}\n`);
+    }
+  }
+}
+
 // ── Reverse-write DB rows → markdown files ───────────────────────────
 
 async function reverseWriteRefs(
   engine: BrainEngine,
   brainDir: string,
   refs: Array<{ slug: string; source_id: string }>,
+  nativeSourceId = 'default',
 ): Promise<number> {
   let count = 0;
   for (const { slug, source_id } of refs) {
@@ -1084,10 +1216,11 @@ async function reverseWriteRefs(
     const tags = await engine.getTags(slug, { sourceId: source_id });
     try {
       const md = renderPageToMarkdown(page, tags);
-      // v0.32.8 F6: non-default sources land at brainDir/.sources/<id>/<slug>.md
-      // so same-slug-different-source pages don't collide. Default-source
-      // pages stay at brainDir/<slug>.md so single-source brains see no change.
-      const filePath = source_id === 'default'
+      // v0.32.8 F6: foreign-source pages land at brainDir/.sources/<id>/<slug>.md
+      // so same-slug-different-source pages don't collide. Pages belonging to
+      // the cycle's own source (#1586: brainDir IS that source's checkout —
+      // legacy 'default' when unscoped) stay at brainDir/<slug>.md.
+      const filePath = source_id === nativeSourceId
         ? join(brainDir, `${slug}.md`)
         : join(brainDir, '.sources', source_id, `${slug}.md`);
       mkdirSync(dirname(filePath), { recursive: true });
@@ -1134,6 +1267,7 @@ async function writeSummaryPage(
   summaryDate: string,
   writtenSlugs: string[],
   childOutcomes: Array<{ jobId: number; status: string }>,
+  sourceId = 'default',
 ): Promise<void> {
   const completed = childOutcomes.filter(c => c.status === 'completed').length;
   const failed = childOutcomes.length - completed;
@@ -1171,13 +1305,15 @@ async function writeSummaryPage(
   // unnecessarily; we go straight to the engine.
   const { parseMarkdown } = await import('../markdown.ts');
   const parsed = parseMarkdown(fullMarkdown);
+  // #1586: summary lands in the cycle's resolved source too — otherwise the
+  // children live in the named source while the index drifts to 'default'.
   await engine.putPage(summarySlug, {
     type: parsed.type,
     title: parsed.title,
     compiled_truth: parsed.compiled_truth,
     timeline: parsed.timeline,
     frontmatter: parsed.frontmatter,
-  });
+  }, { sourceId });
 
   // Also write to disk (orchestrator dual-write).
   try {
@@ -1242,4 +1378,7 @@ function makeError(cls: string, code: string, message: string, hint?: string): P
 // double-encoded jsonb regression). Not part of the runtime contract.
 export const __testing = {
   collectChildPutPageSlugs,
+  buildSynthesisPrompt,
+  stampDreamProvenance,
+  reverseWriteRefs,
 };

src/core/embed-stale.ts

@@ -206,6 +206,22 @@ export async function embedStaleForSource(
           chunk_source: c.chunk_source,
           embedding: staleIdxToEmbedding.get(c.chunk_index) ?? undefined,
           token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
+          // Carry through per-chunk metadata. upsertChunks writes these as
+          // EXCLUDED.<col> (not COALESCE), so omitting them here resets image
+          // rows to modality='text' (breaking the image search arm's
+          // modality='image' filter) and wipes code-chunk symbol metadata on
+          // every embed-stale pass. embedding_image is deliberately NOT
+          // carried: the upsert COALESCEs it, and getChunks returns the
+          // pgvector as a string which upsertChunks would mis-serialize.
+          modality: c.modality ?? undefined,
+          language: c.language ?? undefined,
+          symbol_name: c.symbol_name ?? undefined,
+          symbol_type: c.symbol_type ?? undefined,
+          start_line: c.start_line ?? undefined,
+          end_line: c.end_line ?? undefined,
+          parent_symbol_path: c.parent_symbol_path ?? undefined,
+          doc_comment: c.doc_comment ?? undefined,
+          symbol_name_qualified: c.symbol_name_qualified ?? undefined,
         }));
         await observed(pacer, () => engine.upsertChunks(slug, merged, { sourceId: keySourceId }));
         // v0.41.31: stamp provenance only when EVERY chunk was stale (fully

src/core/embedding-dim-check.ts

@@ -29,6 +29,9 @@ import {
   isOpenAITextEmbedding3Model,
   isValidOpenAITextEmbedding3Dim,
   maxOpenAITextEmbedding3Dim,
+  nvidiaEmbeddingDim,
+  nvidiaEmbeddingDimOptions,
+  supportsNvidiaEmbeddingDimension,
 } from './ai/dims.ts';
 
 /**
@@ -366,7 +369,9 @@ function validateDimAgainstTouchpoint(
   dimsOptions: number[] | undefined,
   requestedDims: number | undefined,
 ): ResolveSchemaDimResult {
-  const dim = requestedDims ?? defaultDims;
+  const nvidiaNaturalDims = recipe.id === 'nvidia' ? nvidiaEmbeddingDim(modelId) : undefined;
+  const effectiveDefaultDims = nvidiaNaturalDims ?? defaultDims;
+  const dim = requestedDims ?? effectiveDefaultDims;
 
   if (!Number.isInteger(dim) || dim <= 0) {
     return {
@@ -396,7 +401,7 @@ function validateDimAgainstTouchpoint(
     dim,
     model: `${recipe.id}:${modelId}`,
     provider: recipe.id,
-    recipeDefault: defaultDims,
+    recipeDefault: effectiveDefaultDims,
   };
 }
 
@@ -411,6 +416,22 @@ function isCustomDimValidForProvider(
   requestedDims: number,
   dimsOptions: number[] | undefined,
 ): CustomDimCheck {
+  // NVIDIA models are mixed: some fixed-dim, one Matryoshka-style. Handle
+  // them before generic recipe dims_options so llama-nemotron can use 1280d.
+  if (recipe.id === 'nvidia') {
+    const naturalDims = nvidiaEmbeddingDim(modelId);
+    if (naturalDims !== undefined && requestedDims === naturalDims) return { valid: true, error: '' };
+    if (supportsNvidiaEmbeddingDimension(modelId, requestedDims)) return { valid: true, error: '' };
+    const options = nvidiaEmbeddingDimOptions(modelId);
+    return {
+      valid: false,
+      error:
+        `NVIDIA model "${modelId}" does not support dimensions ${requestedDims}. ` +
+        `Natural dimensions: ${naturalDims ?? 'unknown'}. ` +
+        (options ? `Supported overrides: ${options.join(', ')}.` : 'No dimension overrides are supported for this NVIDIA model.'),
+    };
+  }
+
   // Tier 1: recipe-declared dims_options.
   if (dimsOptions && dimsOptions.length > 0) {
     if (dimsOptions.includes(requestedDims)) return { valid: true, error: '' };

src/core/embedding-pricing.ts

@@ -37,6 +37,9 @@ export const EMBEDDING_PRICING: Record<string, EmbeddingPricing> = {
   'voyage:voyage-4-large':         { pricePerMTok: 0.18 },
   // ZeroEntropy (https://zeroentropy.dev/pricing — zembed-1)
   'zeroentropyai:zembed-1':        { pricePerMTok: 0.05 },
+  // Mistral (https://mistral.ai/pricing/api/, verified 2026-07-19)
+  'mistral:mistral-embed':         { pricePerMTok: 0.10 },
+  'mistral:mistral-embed-2312':    { pricePerMTok: 0.10 },
 };
 
 export type PriceLookupResult =

src/core/engine.ts

@@ -936,6 +936,27 @@ export interface BrainEngine {
 
   // Search
   searchKeyword(query: string, opts?: SearchOpts): Promise<SearchResult[]>;
+  /**
+   * fix/title-retrieval-arm (D1): page-grain title candidate arm.
+   *
+   * content_chunks.search_vector never includes the page TITLE (it is
+   * doc_comment + symbol_name_qualified + chunk_text), so a page whose
+   * title tokens are absent from its body is unreachable by searchKeyword.
+   * This arm queries the PAGE-GRAIN DOCUMENT vector pages.search_vector —
+   * NOT titles alone: per trg_pages_search_vector it is title (weight 'A')
+   * + compiled_truth ('B') + timeline text ('C'). Ranked by ts_rank_cd,
+   * the 'A'-weighted title dominates, but body/timeline matches also
+   * produce (lower-ranked) candidates. Returns page-grain hits joined to
+   * ONE representative chunk per page (compiled_truth preferred, else
+   * lowest chunk_index) so rows are shaped like searchKeyword's output and
+   * can enter RRF fusion in hybridSearch.
+   *
+   * Deliberately NO query-length gating — unlike the alias hop (≤6-token
+   * guard) and the title-phrase re-rank boost, this arm must GENERATE
+   * candidates for long exact-title queries, which is exactly where
+   * chunk-grain AND FTS is weakest.
+   */
+  searchTitles(query: string, opts?: SearchOpts): Promise<SearchResult[]>;
   searchVector(embedding: Float32Array, opts?: SearchOpts): Promise<SearchResult[]>;
   /**
    * Hydrate embeddings for chunks already known by id. v0.36 (D9):

src/core/extract-takes-from-pages.ts

@@ -15,7 +15,7 @@
 
 import type { BrainEngine } from './engine.ts';
 import type { TakeBatchInput, TakeKind } from './engine.ts';
-import { chat, isAvailable } from './ai/gateway.ts';
+import { chat, getChatModel, isAvailable } from './ai/gateway.ts';
 
 export const ALLOWED_PAGE_TYPES = [
   'concept', 'atom', 'lore', 'briefing', 'writing', 'originals',
@@ -190,7 +190,11 @@ export async function extractTakesFromPages(
     let response: { text: string };
     try {
       response = await chat({
-        model: opts.model ?? 'anthropic:claude-haiku-4-5',
+        // #2997 — default to the configured chat model (file-plane gateway
+        // config, same idiom as enrich.ts) instead of hardcoded cloud Haiku.
+        // On OAuth/local-only installs the hardcoded model made every takes
+        // extraction die with llm_unavailable despite a working chat_model.
+        model: opts.model || getChatModel(),
         system: CLASSIFIER_SYSTEM,
         messages: [
           {

src/core/facts/extract.ts

@@ -67,6 +67,23 @@ export async function getFactsExtractionModel(engine?: BrainEngine): Promise<str
   return normalizeModelId(resolved);
 }
 
+/**
+ * #2113: output-token cap for the extractor call. The pre-fix hardcoded 1500
+ * silently truncated output on mandatory-reasoning models (thinking tokens
+ * count toward the cap), so the JSON never parsed and extraction returned
+ * zero facts with no signal. Configurable via
+ * `gbrain config set facts.extraction_max_tokens <n>`; default 4000.
+ */
+export const DEFAULT_EXTRACTION_MAX_TOKENS = 4000;
+
+export async function getFactsExtractionMaxTokens(engine?: BrainEngine): Promise<number> {
+  if (!engine) return DEFAULT_EXTRACTION_MAX_TOKENS;
+  const raw = await engine.getConfig('facts.extraction_max_tokens').catch(() => null);
+  if (raw == null || raw.trim() === '') return DEFAULT_EXTRACTION_MAX_TOKENS;
+  const n = Number(raw);
+  return Number.isFinite(n) && n > 0 ? Math.floor(n) : DEFAULT_EXTRACTION_MAX_TOKENS;
+}
+
 export const ALL_EXTRACT_KINDS: readonly FactKind[] = [
   'event', 'preference', 'commitment', 'belief', 'fact',
 ] as const;
@@ -164,24 +181,46 @@ export async function extractFactsFromTurn(input: ExtractInput): Promise<Extract
 
   const cap = Math.max(1, Math.min(input.maxFactsPerTurn ?? 10, 25));
   const defaultModel = await getFactsExtractionModel(input.engine);
+  const maxTokens = await getFactsExtractionMaxTokens(input.engine);
+  const model = input.model ?? defaultModel;
+  const userContent = `<turn>\n${cleaned}\n</turn>\n\nExtract up to ${cap} facts.${
+    input.entityHints && input.entityHints.length
+      ? ` Known entity slugs the user already mentioned: ${input.entityHints.slice(0, 5).join(', ')}.`
+      : ''
+  }`;
   let result: ChatResult;
   try {
     result = await chat({
-      model: input.model ?? defaultModel,
+      model,
       system: EXTRACTOR_SYSTEM,
-      messages: [
-        {
-          role: 'user',
-          content: `<turn>\n${cleaned}\n</turn>\n\nExtract up to ${cap} facts.${
-            input.entityHints && input.entityHints.length
-              ? ` Known entity slugs the user already mentioned: ${input.entityHints.slice(0, 5).join(', ')}.`
-              : ''
-          }`,
-        },
-      ],
-      maxTokens: 1500,
+      messages: [{ role: 'user', content: userContent }],
+      maxTokens,
       abortSignal: input.abortSignal,
     });
+    // #2113: never checked pre-fix — a truncated response (stopReason
+    // 'length', e.g. reasoning tokens eating the cap on mandatory-reasoning
+    // models) produced unparseable JSON and silently extracted zero facts.
+    // Retry ONCE at double the cap, then surface the truncation loudly.
+    if (result.stopReason === 'length') {
+      process.stderr.write(
+        `[facts-extract] WARN: extractor output truncated at maxTokens=${maxTokens} ` +
+        `(model=${model}); retrying once at ${maxTokens * 2}\n`,
+      );
+      result = await chat({
+        model,
+        system: EXTRACTOR_SYSTEM,
+        messages: [{ role: 'user', content: userContent }],
+        maxTokens: maxTokens * 2,
+        abortSignal: input.abortSignal,
+      });
+      if (result.stopReason === 'length') {
+        process.stderr.write(
+          `[facts-extract] WARN: extractor output STILL truncated at maxTokens=${maxTokens * 2} ` +
+          `(model=${model}); facts for this turn are likely lost. ` +
+          `Raise the cap: gbrain config set facts.extraction_max_tokens <n>\n`,
+        );
+      }
+    }
   } catch (err) {
     // Re-throw aborts; absorb other errors as "no extraction" — caller's
     // `put_page` backstop will still record the page itself.

src/core/fts-language.ts

@@ -0,0 +1,69 @@
+/**
+ * Full-text search language configuration.
+ *
+ * Postgres tsvector/tsquery require a text search configuration name (e.g.
+ * 'english', 'portuguese', 'spanish'). Historically GBrain hardcoded
+ * 'english' across engines and trigger functions, which broke search
+ * quality for non-English brains (no stemming, no stop-word removal).
+ *
+ * This helper centralizes the choice. Default stays 'english' for backward
+ * compatibility — only users who set GBRAIN_FTS_LANGUAGE see different
+ * behavior.
+ *
+ * Custom configs (e.g. accent-insensitive 'pt_br' built with unaccent +
+ * portuguese stemmer) are supported as long as the configuration exists
+ * in the target Postgres instance. See docs/guides/multi-language-fts.md
+ * for setup instructions.
+ *
+ * Validation: only allow lowercase letters, digits, and underscores. This
+ * prevents SQL injection when the value is interpolated into queries
+ * (Postgres tsvector functions don't accept parameterized config names —
+ * they must be literals or identifiers).
+ */
+
+const VALID_CONFIG_NAME = /^[a-z][a-z0-9_]*$/;
+const DEFAULT_LANGUAGE = 'english';
+
+let cachedLanguage: string | null = null;
+
+/**
+ * Returns the configured Postgres text search configuration name.
+ *
+ * Resolution order:
+ *   1. process.env.GBRAIN_FTS_LANGUAGE (if set and valid)
+ *   2. 'english' (default — preserves existing behavior)
+ *
+ * The return value is safe to interpolate directly into SQL because it
+ * passes the VALID_CONFIG_NAME guard. If validation fails, falls back to
+ * the default and emits a one-time warning.
+ *
+ * Cached on first call; reset with `resetFtsLanguageCache()` (test only).
+ */
+export function getFtsLanguage(): string {
+  if (cachedLanguage !== null) return cachedLanguage;
+
+  const raw = process.env.GBRAIN_FTS_LANGUAGE?.trim();
+  if (!raw) {
+    cachedLanguage = DEFAULT_LANGUAGE;
+    return cachedLanguage;
+  }
+
+  if (!VALID_CONFIG_NAME.test(raw)) {
+    console.warn(
+      `[gbrain] Invalid GBRAIN_FTS_LANGUAGE='${raw}' — must match /^[a-z][a-z0-9_]*$/. ` +
+      `Falling back to '${DEFAULT_LANGUAGE}'.`
+    );
+    cachedLanguage = DEFAULT_LANGUAGE;
+    return cachedLanguage;
+  }
+
+  cachedLanguage = raw;
+  return cachedLanguage;
+}
+
+/**
+ * Resets the cached language. Tests only — don't use in production code.
+ */
+export function resetFtsLanguageCache(): void {
+  cachedLanguage = null;
+}

src/core/git-remote.ts

@@ -303,6 +303,83 @@ export function validateRepoState(
   return 'healthy';
 }
 
+/**
+ * True if `path` is itself a git repo OR a subdirectory of one, per
+ * `git rev-parse --show-toplevel`. Mirrors the walk-up discovery
+ * `sync.ts:discoverGitRoot` performs at sync time (#753/#774 — subdir-of-git
+ * sources are valid), so a directory that passes this check is guaranteed
+ * not to hit sync's "Not inside a git repository" error later. Used by
+ * `addSource` (#2707) to validate `--path` at registration time instead of
+ * deferring the failure to the first sync.
+ */
+export function isInsideGitRepo(path: string): boolean {
+  try {
+    execFileSync('git', ['-C', path, 'rev-parse', '--show-toplevel'], {
+      stdio: ['ignore', 'pipe', 'pipe'],
+      timeout: 10_000,
+      env: { ...process.env, ...GIT_ENV },
+    });
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * The empty-tree object ID for `path`'s repo, derived (not hardcoded) so
+ * this works for both the default SHA-1 object format and the opt-in
+ * `--object-format=sha256` one (git 2.29+) — each has its own empty-tree
+ * OID. `git hash-object -t tree --stdin < /dev/null` computes the hash of
+ * a zero-entry tree using whatever hash algorithm `path`'s repo is
+ * configured for, without needing to know which one that is. #2707 codex
+ * round 4 (P2): an earlier version hardcoded the well-known SHA-1 constant
+ * (`4b825dc6...`), which silently mismatched — and so let an empty
+ * SHA-256 repo through — on a SHA-256 repo's real (different) empty-tree
+ * OID.
+ */
+function emptyTreeOid(path: string): string {
+  return execFileSync('git', ['-C', path, 'hash-object', '-t', 'tree', '--stdin'], {
+    input: '',
+    stdio: ['pipe', 'pipe', 'pipe'],
+    timeout: 10_000,
+    env: { ...process.env, ...GIT_ENV },
+  }).toString().trim();
+}
+
+/**
+ * True if `path`'s HEAD tree has at least one tracked entry scoped to
+ * `path` itself. `-C path` + the `HEAD:./` revision syntax resolves the
+ * tree object for `path` specifically (not the whole repo root), so this
+ * is correct for both a repo's toplevel AND a subdirectory-of-a-repo
+ * source — then a single OID comparison against that repo's empty-tree
+ * object (see `emptyTreeOid`) tells us whether that tree is empty. #2707
+ * codex round 3 (P2): unlike listing (`ls-tree`), this is O(1) output — no
+ * `maxBuffer` exposure on a repo with a very large number of entries.
+ *
+ * Subsumes "no commits at all" (`HEAD:./` on an unborn repo fails to
+ * resolve — there's no HEAD) AND "has a HEAD commit but it's empty"
+ * (#2707 codex round 2): `git commit --allow-empty` followed by creating
+ * untracked files resolves `HEAD:./` successfully (to the empty-tree OID)
+ * but that tree has zero entries — a directory that would pass a bare
+ * `rev-parse HEAD` check yet still can't sync (or worse, "succeeds"
+ * importing nothing and then never notices the untracked files change —
+ * the silent-staleness class #2707 exists to prevent). A directory
+ * that's `git init`ed but never committed, or where this specific path
+ * was never `git add`ed, fails this check either way.
+ */
+export function hasTrackedContent(path: string): boolean {
+  try {
+    const out = execFileSync('git', ['-C', path, 'rev-parse', '--verify', 'HEAD:./'], {
+      stdio: ['ignore', 'pipe', 'pipe'],
+      timeout: 10_000,
+      env: { ...process.env, ...GIT_ENV },
+    });
+    return out.toString().trim() !== emptyTreeOid(path);
+  } catch {
+    return false;
+  }
+}
+
 // ── Durability helpers (v0.42.44) ───────────────────────────────────────────
 // Used by the brain-repo durability feature (`gbrain sources harden/pull`) and
 // the DB-free pull cron. These are the auth-capable, rebase-aware counterparts

src/core/git-visible-files.ts

@@ -0,0 +1,59 @@
+import { execFileSync } from 'child_process';
+import { lstatSync } from 'fs';
+import { join } from 'path';
+
+/**
+ * Return files visible to git from `dir`, respecting .gitignore,
+ * .git/info/exclude, and global git excludes. Returns null when `dir` is not
+ * inside a git work tree or git is unavailable, so callers can keep their
+ * existing filesystem-walk fallback.
+ */
+export function collectGitVisibleFiles(
+  dir: string,
+  acceptRelPath: (relPath: string) => 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;
+  }
+
+  const ignoredTracked = new Set<string>();
+  try {
+    const ignoredStdout = execFileSync(
+      'git',
+      ['-C', dir, 'ls-files', '-ci', '--exclude-standard', '-z'],
+      { encoding: 'utf8', maxBuffer: 512 * 1024 * 1024, stdio: ['ignore', 'pipe', 'ignore'] },
+    );
+    for (const rel of ignoredStdout.split('\0')) {
+      if (rel) ignoredTracked.add(rel);
+    }
+  } catch {
+    // Best effort: older Git or unusual worktrees still get the standard list.
+  }
+
+  const files: string[] = [];
+  for (const rel of stdout.split('\0')) {
+    if (!rel) continue;
+    if (ignoredTracked.has(rel)) continue;
+    const normalizedRel = rel.replace(/\\/g, '/');
+    if (!acceptRelPath(normalizedRel)) continue;
+
+    const full = join(dir, rel);
+    let st: ReturnType<typeof lstatSync>;
+    try {
+      st = lstatSync(full);
+    } catch {
+      continue;
+    }
+    if (st.isSymbolicLink() || !st.isFile()) continue;
+    files.push(full);
+  }
+
+  return files.sort();
+}

src/core/import-checkpoint.ts

@@ -1,5 +1,5 @@
-import { existsSync, readFileSync, writeFileSync, renameSync, unlinkSync } from 'fs';
-import { relative, isAbsolute } from 'path';
+import { existsSync, readFileSync, writeFileSync, renameSync, unlinkSync, realpathSync } from 'fs';
+import { relative, isAbsolute, resolve } from 'path';
 
 /**
  * Path-based import checkpoint.
@@ -25,6 +25,12 @@ import { relative, isAbsolute } from 'path';
  * enter the set.
  */
 export interface ImportCheckpoint {
+  /** Checkpoint payload schema. v1 is path-based with explicit producer metadata. */
+  schema_version: 1;
+  /** Producer marker for downstream consumers that validate before acting. */
+  owner: 'gbrain';
+  /** Checkpoint kind. Prevents unrelated checkpoint files from being treated as import state. */
+  kind: 'import';
   /** Absolute brain directory the checkpoint was created against. Mismatch on resume → discard. */
   dir: string;
   /**
@@ -37,6 +43,21 @@ export interface ImportCheckpoint {
 }
 
 const OLD_FORMAT_LOG = 'Older checkpoint format detected — re-walking (cheap via content_hash)';
+export const IMPORT_CHECKPOINT_SCHEMA_VERSION = 1;
+export const IMPORT_CHECKPOINT_OWNER = 'gbrain';
+export const IMPORT_CHECKPOINT_KIND = 'import';
+
+/**
+ * Capture the import target once at run start. `resolve()` removes caller
+ * spelling such as `.` or `../staging`; `realpathSync()` collapses symlinks
+ * and proves the target exists. The returned value is the only directory
+ * identity import checkpoints should ever persist (#1728 — a raw `.` here
+ * made the checkpoint `dir` resolve to whatever CWD the NEXT consumer ran
+ * from, which downstream tooling treated as an owned staging directory).
+ */
+export function resolveImportTargetDir(dir: string): string {
+  return realpathSync(resolve(dir));
+}
 
 /**
  * Load a checkpoint and verify it's compatible with the current run.
@@ -72,11 +93,21 @@ export function loadCheckpoint(path: string, currentDir: string): ImportCheckpoi
   }
 
   if (typeof obj.dir !== 'string') return null;
+  if (!isAbsolute(obj.dir)) return null;
   if (obj.dir !== currentDir) return null;
+  // Self-describing metadata (#1728): absent fields are tolerated (legacy
+  // path-based checkpoints predate them), but present-and-wrong means the
+  // file was written by something else — don't resume from it.
+  if (obj.schema_version !== undefined && obj.schema_version !== IMPORT_CHECKPOINT_SCHEMA_VERSION) return null;
+  if (obj.owner !== undefined && obj.owner !== IMPORT_CHECKPOINT_OWNER) return null;
+  if (obj.kind !== undefined && obj.kind !== IMPORT_CHECKPOINT_KIND) return null;
   if (typeof obj.timestamp !== 'string') return null;
   if (!obj.completedPaths.every((p): p is string => typeof p === 'string')) return null;
 
   return {
+    schema_version: IMPORT_CHECKPOINT_SCHEMA_VERSION,
+    owner: IMPORT_CHECKPOINT_OWNER,
+    kind: IMPORT_CHECKPOINT_KIND,
     dir: obj.dir,
     completedPaths: obj.completedPaths,
     timestamp: obj.timestamp,
@@ -98,6 +129,9 @@ export function saveCheckpoint(path: string, cp: ImportCheckpoint): void {
     // Sort for stable serialization — keeps diffs across snapshots minimal
     // and tests deterministic.
     const payload: ImportCheckpoint = {
+      schema_version: IMPORT_CHECKPOINT_SCHEMA_VERSION,
+      owner: IMPORT_CHECKPOINT_OWNER,
+      kind: IMPORT_CHECKPOINT_KIND,
       dir: cp.dir,
       completedPaths: [...cp.completedPaths].sort(),
       timestamp: cp.timestamp,

src/core/import-file.ts

@@ -733,6 +733,11 @@ export async function importFromContent(
       : computeCorpusGeneration({
           crMode: effectiveCRMode,
           haikuModel: 'anthropic:claude-haiku-4-5-20251001',
+          // Inline import-file path never uses per_chunk_synopsis (refuses
+          // upstream); pass undefined so the doc-cap field stays out of
+          // the hash here. Per_chunk_synopsis runs through the Minion
+          // backfill handler which threads SYNOPSIS_DOC_MAX_CHARS through
+          // the service layer.
         });
 
   // Transaction wraps all DB writes. Every per-page tx call carries the

src/core/link-extraction.ts

@@ -489,7 +489,22 @@ export async function extractPageLinks(
       // text inside `[[...]]` before any `|`), NOT the display alias
       // (ref.name = match[2]). `[[struktura|the project]]` must resolve
       // `struktura`, not "the project". The display text is for context only.
-      const matches = await resolver.resolveBasenameMatches(ref.slug);
+      //
+      // The literal may be path-qualified (`[[notes/struktura]]`). The FS
+      // path (resolveSlugAll) strips the dirname before its basename lookup,
+      // but this path passed the raw literal to an index keyed by final
+      // segments only — so every slash-containing wikilink outside
+      // DIR_PATTERN silently resolved to nothing. Query by the final
+      // segment, then use the written path as a disambiguation filter
+      // (the analogue of the FS ancestor walk honoring the written path):
+      // a match must end with the literal, so `[[notes/struktura]]` can
+      // resolve to `vault/notes/struktura` but never to `wiki/struktura`.
+      const slashIdx = ref.slug.lastIndexOf('/');
+      const basename = slashIdx === -1 ? ref.slug : ref.slug.slice(slashIdx + 1);
+      let matches = await resolver.resolveBasenameMatches(basename);
+      if (slashIdx !== -1) {
+        matches = matches.filter(m => m === ref.slug || m.endsWith(`/${ref.slug}`));
+      }
       if (matches.length === 0) continue;
       const idx = content.indexOf(ref.slug);
       const context = idx >= 0 ? excerpt(content, idx, 240) : ref.name;

src/core/markdown.ts

@@ -213,39 +213,39 @@ function collectValidationErrors(
     return;
   }
 
-  // 3. MISSING_CLOSE — find the next `---` after the opener. If a markdown
-  //    heading appears before it, that's a strong signal the closing
-  //    delimiter is missing (the heading was meant to be in the body).
+  // 3. MISSING_CLOSE — find the next `---` after the opener.
   let closeLine = -1;
-  let headingBeforeClose = -1;
   for (let i = firstNonEmpty + 1; i < lines.length; i++) {
-    const t = lines[i].trim();
-    if (t === '---') {
+    if (lines[i].trim() === '---') {
       closeLine = i;
       break;
     }
-    if (/^#{1,6}\s/.test(t) && headingBeforeClose === -1) {
-      headingBeforeClose = i;
-    }
   }
   if (closeLine === -1) {
+    // No closing fence found. Surface the first heading-shaped line as a
+    // hint for where the parser thinks the frontmatter went off the rails —
+    // only useful when the close is genuinely missing, since YAML allows
+    // `#` comment lines inside a closed fence (see comment below).
+    let headingHint = -1;
+    for (let i = firstNonEmpty + 1; i < lines.length; i++) {
+      if (/^#{1,6}\s/.test(lines[i].trim())) {
+        headingHint = i;
+        break;
+      }
+    }
     errors.push({
       code: 'MISSING_CLOSE',
       message:
-        headingBeforeClose >= 0
-          ? `No closing --- before heading at line ${headingBeforeClose + 1}`
+        headingHint >= 0
+          ? `No closing --- before heading at line ${headingHint + 1}`
           : 'No closing --- delimiter found',
-      line: headingBeforeClose >= 0 ? headingBeforeClose + 1 : firstNonEmpty + 1,
+      line: headingHint >= 0 ? headingHint + 1 : firstNonEmpty + 1,
     });
     return;
   }
-  if (headingBeforeClose >= 0 && headingBeforeClose < closeLine) {
-    errors.push({
-      code: 'MISSING_CLOSE',
-      message: `Heading at line ${headingBeforeClose + 1} found inside frontmatter zone (closing --- comes after)`,
-      line: headingBeforeClose + 1,
-    });
-  }
+  // Closing fence found. Content between opening and closing is YAML, which
+  // permits `#` comment lines anywhere — those are not markdown headings
+  // and must not raise MISSING_CLOSE.
 
   // 4. EMPTY_FRONTMATTER — open and close present but nothing meaningful between.
   const fmBody = lines.slice(firstNonEmpty + 1, closeLine).join('\n').trim();

src/core/migrate.ts

@@ -1,5 +1,6 @@
 import type { BrainEngine } from './engine.ts';
 import { slugifyPath } from './sync.ts';
+import { getFtsLanguage } from './fts-language.ts';
 
 /**
  * Schema migrations — run automatically on initSchema().
@@ -134,7 +135,10 @@ export const MIGRATIONS: Migration[] = [
           }
         }
       }
-      if (renamed > 0) console.log(`  Renamed ${renamed} slugs`);
+      // Migration progress goes to stderr — stdout must stay clean for
+      // callers parsing JSON (e.g. `gbrain doctor --json | jq`); migrations
+      // can run lazily inside ANY command's first DB connect.
+      if (renamed > 0) process.stderr.write(`  Renamed ${renamed} slugs\n`);
     },
   },
   {
@@ -5505,6 +5509,168 @@ export const MIGRATIONS: Migration[] = [
         WHERE dimension IS NOT NULL;
     `,
   },
+  {
+    version: 123,
+    name: 'configurable_fts_language',
+    // Recreate the two search_vector trigger functions using the language
+    // configured via GBRAIN_FTS_LANGUAGE (default 'english'). Idempotent:
+    // CREATE OR REPLACE swaps the function body atomically; no trigger
+    // recreation needed since the trigger references the function by name.
+    //
+    // Why a handler instead of a static SQL string: Postgres tsvector
+    // functions don't accept parameterized config names — the language
+    // must be a literal in the SQL. getFtsLanguage() validates the value
+    // (lowercase letters/digits/underscores only) before interpolation.
+    //
+    // Function bodies mirror schema.sql / pglite-schema.ts exactly —
+    // INCLUDING the `SET search_path = pg_catalog, public` hardening from
+    // v120/#1647 (CREATE OR REPLACE resets proconfig, so omitting it here
+    // would silently strip the hardening on every upgraded brain). Only
+    // the text-search config name is parameterized. Keep all copies in
+    // sync when the trigger logic changes.
+    //
+    // Backfill: after recreating the functions, re-tokenize existing rows
+    // under the new language. Skipped when the configured language is
+    // 'english' (trigger output identical — re-tokenizing is wasted I/O).
+    // To change language after this migration has run, use
+    // `gbrain reindex-search-vector`.
+    sql: '',
+    handler: async (engine) => {
+      const lang = getFtsLanguage();
+
+      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.compiled_truth, '')), 'B') ||
+            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);
+
+      if (lang === 'english') {
+        // stderr, NOT stdout: migrations run lazily inside any command's
+        // first DB connect — a console.log here polluted `doctor --json`
+        // stdout and broke jq consumers (heavy-tests fm_wallclock).
+        process.stderr.write(`  v123: trigger functions recreated with language='english' (default — no backfill needed)\n`);
+        return;
+      }
+
+      // Backfill existing rows under the new tokenizer. UPDATE-to-same-value
+      // re-fires the pages trigger; chunks are rewritten directly with the
+      // same expression as the trigger.
+      await engine.executeRaw(`
+        UPDATE pages SET id = id
+        WHERE search_vector IS NOT NULL;
+      `);
+
+      await engine.executeRaw(`
+        UPDATE content_chunks
+        SET search_vector =
+          setweight(to_tsvector('${lang}', COALESCE(doc_comment, '')), 'A') ||
+          setweight(to_tsvector('${lang}', COALESCE(symbol_name_qualified, '')), 'A') ||
+          setweight(to_tsvector('${lang}', COALESCE(chunk_text, '')), 'B')
+        WHERE search_vector IS NOT NULL;
+      `);
+
+      process.stderr.write(`  v123: trigger functions recreated with language='${lang}' + backfilled existing rows\n`);
+    },
+  },
+  {
+    version: 124,
+    name: 'page_search_vector_drop_compiled_truth',
+    // #2704: a single markdown page whose compiled_truth exceeds Postgres's
+    // hard 1,048,575-byte tsvector cap made update_page_search_vector()
+    // throw "string is too long for tsvector" INSIDE the pages UPSERT
+    // transaction — not a per-file ledger entry, a transaction abort. The
+    // whole source's sync checkpoint stayed pinned (Sync BLOCKED) until the
+    // oversized file was fixed or manually skipped, even though every
+    // OTHER file in the run imported fine.
+    //
+    // Fix: drop compiled_truth (the unbounded whole-page body) from this
+    // trigger. It was already redundant — content_chunks.search_vector
+    // (Cathedral II Layer 3, v0.20.0) is the ACTUAL keyword-search source:
+    // searchKeyword() in postgres-engine.ts/pglite-engine.ts ranks and
+    // queries `cc.search_vector` exclusively; `pages.search_vector` is
+    // written by this trigger but never read by any query in this
+    // codebase (verified: no `pages.search_vector`/bare `search_vector`
+    // appears on either side of a WHERE/ts_rank anywhere outside this
+    // trigger's own definition and the reindex/backfill machinery that
+    // maintains it). And chunking already bounds each chunk_text well
+    // under the tsvector limit (chunkText() targets embedding-sized
+    // pieces, several orders of magnitude smaller than 1MB) — the overflow
+    // was specific to the whole-page grain this trigger no longer builds.
+    //
+    // title + timeline (both naturally small — a compiled_truth-sized
+    // title or timeline field would be its own bug) stay, so
+    // pages.search_vector keeps carrying SOME signal rather than going
+    // fully inert; a future PR can drop the column outright once its
+    // last non-search consumer (if any turns up) is confirmed gone.
+    //
+    // No backfill: existing rows keep whatever search_vector they already
+    // computed until their next UPDATE (harmless — nothing reads this
+    // column, so staleness has zero behavioral effect). The brains that
+    // actually hit this bug never successfully wrote a value for the
+    // oversized page in the first place, so there's nothing stale to fix
+    // for them specifically — the NEXT sync of that exact file is what
+    // proves the fix, not a backfill of already-working rows.
+    //
+    // Function body mirrors reindex-search-vector.ts's recreatePagesFn
+    // (documented contract there: keep both in lockstep) and the fresh-
+    // install baselines in pglite-schema.ts / schema-embedded.ts — all
+    // four updated in the same commit as this migration.
+    sql: '',
+    handler: async (engine) => {
+      const lang = getFtsLanguage();
+      await engine.executeRaw(`
+        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;
+      `);
+      process.stderr.write(`  v124: update_page_search_vector() no longer indexes compiled_truth (was overflowing tsvector on large pages, #2704)
+`);
+    },
+  },
 ];
 
 export const LATEST_VERSION = MIGRATIONS.length > 0

src/core/minions/handlers/ingest-capture.ts

@@ -113,7 +113,36 @@ export function makeIngestCaptureHandler(engine: BrainEngine) {
     // by passing { noEmbed: false } in job.data.
     const noEmbed = (data as { noEmbed?: unknown }).noEmbed !== false;
 
-    const result = await importFromContent(engine, slug, event.content, { noEmbed });
+    // #1522: thread the validated event's provenance into the page write
+    // instead of dropping it on the floor. source_kind / source_uri are
+    // pure provenance strings (no scoping power) and persist
+    // unconditionally via importFromContent's putPage write-through.
+    //
+    // event.source_id is the emitter's IngestionSource instance id, NOT
+    // necessarily a registered brain source (the webhook path fabricates
+    // `webhook-<clientId>`, which pages.source_id's FK would reject). It
+    // routes the page write only when BOTH hold:
+    //   - the event is trusted (fail-closed: an untrusted webhook payload
+    //     carries a caller-controlled x-gbrain-source-id header and must
+    //     not get to choose its write source), AND
+    //   - the id names a registered source row.
+    // Otherwise the write keeps the pre-fix default-source routing.
+    let sourceId: string | undefined;
+    if (!untrustedPayload) {
+      const rows = await engine.executeRaw<{ id: string }>(
+        `SELECT id FROM sources WHERE id = $1`,
+        [event.source_id],
+      );
+      if (rows.length > 0) sourceId = event.source_id;
+    }
+
+    const result = await importFromContent(engine, slug, event.content, {
+      noEmbed,
+      sourceId,
+      source_kind: event.source_kind,
+      source_uri: event.source_uri,
+      ingested_via: 'ingest_capture',
+    });
 
     return {
       slug,

src/core/minions/handlers/subagent.ts

@@ -58,8 +58,29 @@ import { randomUUIDv7 } from 'bun';
 
 const DEFAULT_MODEL = 'claude-sonnet-4-6';
 const DEFAULT_MAX_TURNS = 20;
+const DEFAULT_MAX_OUTPUT_TOKENS = 8192;
 const DEFAULT_RATE_KEY = 'anthropic:messages';
 
+/**
+ * Resolve the per-turn output-token cap (#2778). Per-job data wins, then the
+ * `agent.max_output_tokens` config row, then the 8192 default (was a
+ * hardcoded 4096 that made pages >~12KB unwritable via put_page). Invalid
+ * values (NaN / zero / negative) fall through to the next tier.
+ */
+export function resolveMaxOutputTokens(
+  perJob: number | undefined,
+  configRaw: string | null | undefined,
+): number {
+  if (typeof perJob === 'number' && Number.isFinite(perJob) && perJob > 0) {
+    return Math.floor(perJob);
+  }
+  if (typeof configRaw === 'string' && configRaw.trim() !== '') {
+    const n = Number(configRaw);
+    if (Number.isFinite(n) && n > 0) return Math.floor(n);
+  }
+  return DEFAULT_MAX_OUTPUT_TOKENS;
+}
+
 /**
  * Resolve the rate-lease cap from the env var.
  *
@@ -212,6 +233,11 @@ export function makeSubagentHandler(deps: SubagentDeps) {
         fallback: TIER_DEFAULTS.subagent,
       });
     const maxTurns = data.max_turns ?? DEFAULT_MAX_TURNS;
+    // #2778: per-turn output cap — data.max_tokens → config → 8192 default.
+    const maxOutputTokens = resolveMaxOutputTokens(
+      data.max_tokens,
+      await engine.getConfig('agent.max_output_tokens').catch(() => null),
+    );
     // v0.41 Approach C: systemPrompt is now built AFTER toolDefs (a few
     // lines below) so the renderer can splice a tool-usage preamble
     // listing each available tool's usage_hint. The renderer is
@@ -246,6 +272,8 @@ export function makeSubagentHandler(deps: SubagentDeps) {
       config,
       brainId: data.brain_id,
       allowedSlugPrefixes: data.allowed_slug_prefixes,
+      // #1586: cycle-resolved source scope for tool-call OperationContexts.
+      sourceId: data.source_id,
     });
     const toolDefs = data.allowed_tools && data.allowed_tools.length > 0
       ? filterAllowedTools(registry, data.allowed_tools)
@@ -277,6 +305,7 @@ export function makeSubagentHandler(deps: SubagentDeps) {
         systemPrompt,
         toolDefs,
         maxTurns,
+        maxOutputTokens,
       });
     }
 
@@ -475,12 +504,67 @@ export function makeSubagentHandler(deps: SubagentDeps) {
       // covers the whole request. A mid-call renewal loop would add
       // complexity; for v0.15 we lean on the 120s TTL + abort-on-signal.
       try {
+        // --- Patch B (borrow-ahead, hand-authored): rolling conversation prompt-cache ---
+        // Direct path marks cache_control only on static system(485)+last-tool(498) ~5.2K;
+        // the growing anthroMessages conversation is re-billed every turn (6/18 v0.42.51
+        // regression). Anthropic caches up to the last cache_control block, so mark the last
+        // content block of the last message and keep the 4-breakpoint API limit
+        // (system + last-tool + 2 rolling = 4).
+        //
+        // Two rolling markers, not one: Anthropic's automatic cache lookup only walks
+        // back up to 20 content blocks from a breakpoint to find a prior cached prefix
+        // (see prompt-caching docs, "20-block lookback window"). A turn that adds more
+        // than 20 blocks since the last marker (e.g. a large parallel tool_use/tool_result
+        // round) would make a freshly-placed single marker miss the previous cache
+        // entirely. Keeping the immediately-preceding rolling marker in place — and only
+        // evicting anything older than that — guarantees at least that marker's prefix is
+        // still a valid, already-written cache read even when this turn's new marker's
+        // lookback comes up empty.
+        if (anthroMessages.length > 0) {
+          const markerIndices: number[] = [];
+          for (let i = 0; i < anthroMessages.length; i++) {
+            const m = anthroMessages[i] as any;
+            if (Array.isArray(m.content)) {
+              for (const b of m.content) {
+                if (b && typeof b === 'object' && 'cache_control' in b) {
+                  markerIndices.push(i);
+                  break;
+                }
+              }
+            }
+          }
+          const keepIdx = markerIndices.length > 0 ? markerIndices[markerIndices.length - 1] : -1;
+          for (const i of markerIndices) {
+            if (i === keepIdx) continue;
+            const m = anthroMessages[i] as any;
+            for (const b of m.content) {
+              if (b && typeof b === 'object' && 'cache_control' in b) delete b.cache_control;
+            }
+          }
+          const lastMsg = anthroMessages[anthroMessages.length - 1] as any;
+          // A fresh job's seed message has string content (see the
+          // `[{ role: 'user', content: data.prompt }]` init above), which
+          // the array-only check below would silently skip — leaving the
+          // very first call, and thus the common single-tool round-trip,
+          // with no rolling breakpoint at all. Normalize to a one-block
+          // array first so it gets the marker like every later turn.
+          if (typeof lastMsg.content === 'string') {
+            lastMsg.content = [{ type: 'text', text: lastMsg.content }];
+          }
+          if (Array.isArray(lastMsg.content) && lastMsg.content.length > 0) {
+            const lastBlock = lastMsg.content[lastMsg.content.length - 1];
+            if (lastBlock && typeof lastBlock === 'object') {
+              lastBlock.cache_control = { type: 'ephemeral' };
+            }
+          }
+        }
+        // --- end Patch B ---
         const params: Anthropic.MessageCreateParamsNonStreaming = {
           // v0.41 Bug 3: strip `provider:` prefix at the SDK call site only.
           // `model` stays qualified everywhere else (persistence, recipe
           // lookup at recipeIdFromModel(), capability gate).
           model: stripProviderPrefix(model),
-          max_tokens: 4096,
+          max_tokens: maxOutputTokens,
           system: [
             { type: 'text', text: systemPrompt, cache_control: { type: 'ephemeral' } },
           ] as any,
@@ -573,7 +657,10 @@ export function makeSubagentHandler(deps: SubagentDeps) {
           b.type === 'tool_use',
       );
       if (toolUses.length === 0) {
-        stopReason = 'end_turn';
+        // #2778: an output-cap hit is NOT end_turn — the text (and possibly a
+        // dropped trailing tool_use block) is truncated. Surface it as its own
+        // stop_reason instead of silently reporting a clean end_turn.
+        stopReason = assistantMsg.stop_reason === 'max_tokens' ? 'max_tokens' : 'end_turn';
         // Concatenate text blocks as the final answer.
         finalText = blocks
           .filter(b => b.type === 'text' && typeof b.text === 'string')
@@ -686,6 +773,24 @@ export function makeSubagentHandler(deps: SubagentDeps) {
         }
       }
 
+      // #2778: a max_tokens stop with tool_use blocks means the API dropped an
+      // incomplete trailing block (e.g. a large put_page body that overflowed
+      // the cap). Tell the model so it re-issues the cut-off call (split, or
+      // smaller pages) instead of assuming the write happened.
+      if (assistantMsg.stop_reason === 'max_tokens') {
+        toolResults.push({
+          type: 'text',
+          text: `[system] Your previous response hit the ${maxOutputTokens}-token output cap and was truncated; ` +
+            `any tool call cut off by the cap was DROPPED and did not execute. Re-issue it, splitting large content if needed.`,
+        } as ContentBlock);
+        logSubagentHeartbeat({
+          job_id: ctx.id,
+          event: 'llm_call_completed',
+          turn_idx: turnIdx,
+          error: `stop_reason=max_tokens at cap ${maxOutputTokens}; truncation note injected`,
+        });
+      }
+
       // 6. Append the synthesized user turn (tool_result wrappers) to the
       //    conversation and persist it so replay picks it up.
       const userIdx = nextMessageIdx++;
@@ -721,6 +826,8 @@ interface GatewayRunArgs {
   systemPrompt: string;
   toolDefs: ToolDef[];
   maxTurns: number;
+  /** #2778: per-turn output-token cap (resolved by resolveMaxOutputTokens). */
+  maxOutputTokens: number;
 }
 
 /**
@@ -738,7 +845,7 @@ interface GatewayRunArgs {
  * reconciler sees both shapes uniformly.
  */
 async function runSubagentViaGateway(args: GatewayRunArgs): Promise<SubagentResult> {
-  const { engine, ctx, data, model, systemPrompt, toolDefs, maxTurns } = args;
+  const { engine, ctx, data, model, systemPrompt, toolDefs, maxTurns, maxOutputTokens } = args;
 
   // Map ToolDef → ChatToolDef (gateway shape). The gateway's chat() bridges
   // this to provider-specific tool definitions via the Vercel AI SDK.
@@ -862,6 +969,7 @@ async function runSubagentViaGateway(args: GatewayRunArgs): Promise<SubagentResu
     tools: chatTools,
     toolHandlers,
     maxTurns,
+    maxTokens: maxOutputTokens,
     abortSignal: ctx.signal,
     cacheSystem,
     // ALWAYS pass replayState (even on fresh runs) so the gateway loop's

src/core/minions/queue.ts

@@ -163,24 +163,36 @@ export class MinionQueue {
       if (opts?.maxWaiting !== undefined) {
         const maxWaiting = Math.max(1, Math.floor(opts.maxWaiting));
         const backpressureQueue = opts?.queue ?? 'default';
+        // Multi-source scope: jobs of the same (name, queue) but different
+        // data.sourceId are independent workstreams (per-source sync/cycle).
+        // Counting them together made a waiting default-source sync swallow
+        // every other source's freshness sync — a secondary source sat 29h stale
+        // while dispatch logs showed its syncs "dispatched" (coalesced into
+        // the default row). Key the lock and the count on sourceId when the
+        // submission carries one; NULL keeps legacy single-scope behavior.
+        const bpSourceId = typeof (data as Record<string, unknown> | undefined)?.sourceId === 'string'
+          ? (data as Record<string, unknown>).sourceId as string
+          : null;
         await tx.executeRaw(
-          `SELECT pg_advisory_xact_lock(hashtext('minion_maxwaiting:' || $1 || ':' || $2))`,
-          [jobName, backpressureQueue]
+          `SELECT pg_advisory_xact_lock(hashtext('minion_maxwaiting:' || $1 || ':' || $2 || ':' || coalesce($3, '')))`,
+          [jobName, backpressureQueue, bpSourceId]
         );
         const waitingCountRows = await tx.executeRaw<{ count: string }>(
           `SELECT count(*)::text AS count
            FROM minion_jobs
-           WHERE name = $1 AND queue = $2 AND status = 'waiting'`,
-          [jobName, backpressureQueue]
+           WHERE name = $1 AND queue = $2 AND status = 'waiting'
+             AND ($3::text IS NULL OR data->>'sourceId' IS NOT DISTINCT FROM $3)`,
+          [jobName, backpressureQueue, bpSourceId]
         );
         const waitingCount = parseInt(waitingCountRows[0]?.count ?? '0', 10);
         if (waitingCount >= maxWaiting) {
           const existingWaiting = await tx.executeRaw<Record<string, unknown>>(
             `SELECT * FROM minion_jobs
              WHERE name = $1 AND queue = $2 AND status = 'waiting'
+               AND ($3::text IS NULL OR data->>'sourceId' IS NOT DISTINCT FROM $3)
              ORDER BY created_at DESC, id DESC
              LIMIT 1`,
-            [jobName, backpressureQueue]
+            [jobName, backpressureQueue, bpSourceId]
           );
           if (existingWaiting.length > 0) {
             const coalesced = rowToMinionJob(existingWaiting[0]);
@@ -471,12 +483,34 @@ export class MinionQueue {
     });
   }
 
-  /** Re-queue a failed or dead job for retry. */
+  /**
+   * Re-queue a failed or dead job for retry.
+   *
+   * #2783: an explicit `jobs retry` is an operator asserting "run this
+   * fresh" — so it clears `started_at` (re-stamped on re-claim via
+   * `claim()`'s `COALESCE(started_at, now())`, `queue.ts:620`) and resets
+   * `attempts_made`/`attempts_started` to 0. Without this, `started_at`
+   * kept the ORIGINAL first-claim time, so `handleWallClockTimeouts()`
+   * (anchored on `now() - started_at`, `queue.ts:729-749`) could measure
+   * from long before the retry — a retry issued more than `timeout_ms * 2`
+   * after the original claim was dead-lettered again in under a second,
+   * with `attempts_made` already past `max_attempts`. This made retry
+   * useless for exactly the case it exists for: recovering work after an
+   * outage that outlasted the job's timeout.
+   *
+   * Also resets `stalled_counter` (Codex review): `handleStalled()`
+   * dead-letters once `stalled_counter + 1 >= max_stalled` (`queue.ts:1190`).
+   * A job dead-lettered BY stall exhaustion, left un-reset, would hit that
+   * same threshold on its very first lock expiry after retry — a job
+   * killed by 3 stalls doesn't get a fresh stall budget, contradicting
+   * "run this fresh" the same way the unreset attempt counters did.
+   */
   async retryJob(id: number): Promise<MinionJob | null> {
     const rows = await this.engine.executeRaw<Record<string, unknown>>(
       `UPDATE minion_jobs SET status = 'waiting', error_text = NULL,
         lock_token = NULL, lock_until = NULL, delay_until = NULL,
-        finished_at = NULL, updated_at = now()
+        finished_at = NULL, started_at = NULL, attempts_made = 0,
+        attempts_started = 0, stalled_counter = 0, updated_at = now()
        WHERE id = $1 AND status IN ('failed', 'dead')
        RETURNING *`,
       [id]

src/core/minions/tools/brain-allowlist.ts

@@ -27,6 +27,7 @@ import type { GBrainConfig } from '../../config.ts';
 import { operations } from '../../operations.ts';
 import type { Operation, OperationContext } from '../../operations.ts';
 import { paramDefToSchema } from '../../../mcp/tool-defs.ts';
+import { validateSourceId } from '../../utils.ts';
 import type { ToolCtx, ToolDef } from '../types.ts';
 
 /**
@@ -61,6 +62,12 @@ export const BRAIN_TOOL_ALLOWLIST: ReadonlySet<string> = new Set([
   'resolve_slugs',
   'get_ingest_log',
   'put_page',
+  // #2778: the canonical timeline-write op. Fenced exactly like put_page —
+  // operations.ts:enforceSubagentSlugFence confines the target slug to the
+  // trusted-workspace allow-list (or the wiki/agents/<id>/ namespace) when
+  // ctx.viaSubagent=true, so a subagent can only append timeline entries to
+  // pages it could have written anyway.
+  'add_timeline_entry',
   // v0.29 — Salience + Anomaly Detection. Both read-only. `get_recent_transcripts`
   // is intentionally NOT included: subagent calls always have ctx.remote=true,
   // and the v0.29 trust gate rejects remote callers — adding it here would be
@@ -97,6 +104,7 @@ export const BRAIN_TOOL_USAGE_HINTS: Readonly<Record<string, string>> = {
   resolve_slugs: 'Resolve free-form entity names to canonical slugs (e.g. "Alice" → `people/alice-example`). Use before any tool that takes a slug if the user gave a name not a slug.',
   get_ingest_log: 'Read the brain ingestion log for diagnostic / verification queries.',
   put_page: 'Write a markdown page to the gbrain DATABASE (NOT the local filesystem). Page becomes searchable + linkable. Slug must match the agent\'s allowed namespace.',
+  add_timeline_entry: 'Append a dated timeline entry to an existing page (the canonical timeline write). Use over rewriting the page body when recording a dated event. Slug must match the agent\'s allowed namespace.',
   get_recent_salience: 'Read pages ranked by emotional + activity salience over a recency window. Use for "what\'s been on my mind lately".',
   find_anomalies: 'Read cohort-level activity outliers (e.g. tag-cohort or type-cohort with unusual recent volume). Use for "what\'s unusual lately".',
 };
@@ -194,6 +202,13 @@ export interface BuildBrainToolsOpts {
    * SubagentHandlerData.allowed_slug_prefixes via the handler.
    */
   allowedSlugPrefixes?: readonly string[];
+  /**
+   * Brain source every tool-call OperationContext is scoped to (#1586).
+   * Trusted (flows from SubagentHandlerData.source_id, which only
+   * PROTECTED_JOB_NAMES-gated submitters can set); validated at build time.
+   * Unset → legacy 'default'.
+   */
+  sourceId?: string;
 }
 
 interface OpContextDeps {
@@ -204,6 +219,7 @@ interface OpContextDeps {
   signal?: AbortSignal;
   brainId?: string;
   allowedSlugPrefixes?: readonly string[];
+  sourceId?: string;
 }
 
 function buildOpContext(deps: OpContextDeps): OperationContext {
@@ -217,7 +233,8 @@ function buildOpContext(deps: OpContextDeps): OperationContext {
     },
     dryRun: false,
     remote: true,                // match MCP trust boundary for auto-link skip
-    sourceId: 'default',         // v0.34 D4: required; subagent tools default to host source
+    // #1586: cycle-resolved source when provided; legacy host default else.
+    sourceId: deps.sourceId ?? 'default',
     jobId: deps.jobId,
     subagentId: deps.subagentId,
     viaSubagent: true,           // FAIL-CLOSED: put_page etc. enforce namespace
@@ -241,6 +258,11 @@ export function buildBrainTools(opts: BuildBrainToolsOpts): ToolDef[] {
     op => BRAIN_TOOL_ALLOWLIST.has(op.name) && filter.has(op.name),
   );
 
+  // #1586: fail fast on a malformed source id before any tool executes
+  // (defense-in-depth — the seam is trusted, but the value round-trips
+  // through the job payload).
+  if (opts.sourceId !== undefined) validateSourceId(opts.sourceId);
+
   return picked.map<ToolDef>(op => {
     const schema = op.name === 'put_page'
       ? namespacedPutPageSchema(op, opts.subagentId, opts.allowedSlugPrefixes)
@@ -270,6 +292,7 @@ export function buildBrainTools(opts: BuildBrainToolsOpts): ToolDef[] {
           signal: ctx.signal,
           brainId: opts.brainId,
           allowedSlugPrefixes: opts.allowedSlugPrefixes,
+          sourceId: opts.sourceId,
         });
         const params = (input && typeof input === 'object') ? input as Record<string, unknown> : {};
         return op.handler(opCtx, params);

src/core/minions/types.ts

@@ -200,6 +200,12 @@ export interface MinionJobContext {
   attempts_made: number;
   /** AbortSignal for cooperative cancellation (fires on timeout, cancel, pause, or lock loss). */
   signal: AbortSignal;
+  /** Absolute wall-clock deadline (epoch ms) from the claim-time `timeout_at` stamp,
+   *  or null when the job has no per-job timeout. This is the DB's ground truth —
+   *  the same instant handleTimeouts() dead-letters against — so handlers that
+   *  spawn bounded sub-work (e.g. autopilot-cycle's subagent phases) can budget
+   *  from the REMAINING time instead of a fixed constant that may exceed it. */
+  deadlineAtMs: number | null;
   /** AbortSignal that fires only on worker process SIGTERM/SIGINT. Handlers sensitive
    *  to deploy restarts (e.g. the shell handler, which must run a SIGTERM → 5s → SIGKILL
    *  sequence on its child) listen to this in addition to `signal`. Most handlers can
@@ -411,6 +417,12 @@ export interface SubagentHandlerData {
   model?: string;
   /** Max assistant turns before the loop fails with stop_reason='max_turns'. */
   max_turns?: number;
+  /**
+   * Per-turn max output tokens (#2778). Resolution: this field →
+   * `agent.max_output_tokens` config → 8192 default. The pre-#2778
+   * hardcoded 4096 made pages >~12KB unwritable via put_page.
+   */
+  max_tokens?: number;
   /**
    * Whitelist of tool names the agent may call. MUST be a subset of the
    * derived registry names — invalid entries are rejected at tool-dispatch
@@ -449,6 +461,17 @@ export interface SubagentHandlerData {
    * and direct CLI submitters set it.
    */
   allowed_slug_prefixes?: string[];
+  /**
+   * Brain source the subagent's tool calls are scoped to (#1586).
+   *
+   * When set, every tool-call `OperationContext.sourceId` uses this value
+   * instead of the legacy 'default', so put_page writes land in the cycle's
+   * resolved source. Same trust story as `allowed_slug_prefixes`:
+   * PROTECTED_JOB_NAMES gates subagent submission, so only cycle.ts and
+   * direct CLI submitters can set it. Validated via `validateSourceId` at
+   * tool-registry build time.
+   */
+  source_id?: string;
   /**
    * v0.41 Approach C: opt out of the auto-generated tool-usage preamble
    * that `buildSystemPrompt()` splices into `system`. Default behavior
@@ -562,6 +585,7 @@ export type ContentBlock =
 export type SubagentStopReason =
   | 'end_turn'    // Anthropic says end_turn and last message has no tool_use
   | 'max_turns'   // hit max_turns budget before end_turn
+  | 'max_tokens'  // final turn hit the output-token cap — result text is TRUNCATED (#2778)
   | 'refusal'     // detected via stop_reason + content shape
   | 'error';      // unrecoverable (empty response retry exhausted, etc.)
 

src/core/minions/worker.ts

@@ -507,7 +507,17 @@ export class MinionWorker extends EventEmitter {
         try {
           await this.queue.promoteDelayed();
         } catch (e) {
-          console.error('Promotion error:', e instanceof Error ? e.message : String(e));
+          const msg = e instanceof Error ? e.message : String(e);
+          console.error('Promotion error:', msg);
+          // issue #1491: a retryable pool/connection loss during promotion used
+          // to be logged and ignored, leaving the worker in a repeated
+          // "Promotion error: No database connection" loop until a later path
+          // happened to reconnect or crash. Promotion is a standalone UPDATE
+          // from delayed→waiting, so after a connection failure we can safely
+          // rebuild the worker-owned pool before continuing to claim work.
+          if (isRetryableConnError(e)) {
+            await this.reconnectAfterConnectionError('promoteDelayed', e);
+          }
         }
 
         // Claim jobs up to concurrency limit
@@ -532,13 +542,7 @@ export class MinionWorker extends EventEmitter {
             if (!isRetryableConnError(e)) throw e;
             const msg = e instanceof Error ? e.message : String(e);
             console.error(`[worker] claim hit a connection error; reconnecting, retry on next tick: ${msg}`);
-            const reconnect = (this.engine as { reconnect?: () => Promise<void> }).reconnect;
-            if (reconnect) {
-              try { await reconnect.call(this.engine); }
-              catch (re) {
-                console.error(`[worker] reconnect after claim error failed: ${re instanceof Error ? re.message : String(re)}`);
-              }
-            }
+            await this.reconnectAfterConnectionError('claim', e);
             await new Promise(resolve => setTimeout(resolve, this.opts.pollInterval));
             continue;
           }
@@ -658,6 +662,22 @@ export class MinionWorker extends EventEmitter {
     this.running = false;
   }
 
+  /**
+   * Rebuild the worker-owned DB pool after a retryable connection failure.
+   *
+   * PostgresEngine exposes reconnect(); PGLite and test doubles may not. Absence
+   * is a no-op so non-Postgres workers preserve their legacy behavior.
+   */
+  private async reconnectAfterConnectionError(site: string, error: unknown): Promise<void> {
+    const reconnect = (this.engine as { reconnect?: (ctx?: { error?: unknown }) => Promise<void> }).reconnect;
+    if (!reconnect) return;
+    try {
+      await reconnect.call(this.engine, { error });
+    } catch (re) {
+      console.error(`[worker] reconnect after ${site} error failed: ${re instanceof Error ? re.message : String(re)}`);
+    }
+  }
+
   /** RSS watchdog. Called from the per-job finally and the periodic timer.
    *  Idempotent: returns early if already not running or already shut down.
    *  When threshold is exceeded, hands off to gracefulShutdown(). */
@@ -880,15 +900,22 @@ export class MinionWorker extends EventEmitter {
 
     // Per-job wall-clock timeout (timer-armed only if `timeout_ms` was
     // set on the job; the grace-evict pattern above now lives outside
-    // this branch).
+    // this branch). The delay derives from the claim-time `timeout_at`
+    // stamp when present so this timer, the DB sweeper (handleTimeouts),
+    // and the handler-visible `deadlineAtMs` all agree on ONE absolute
+    // deadline instead of three clocks started at slightly different
+    // instants.
     let timeoutTimer: ReturnType<typeof setTimeout> | null = null;
     if (job.timeout_ms != null) {
+      const delayMs = job.timeout_at != null
+        ? Math.max(0, job.timeout_at.getTime() - Date.now())
+        : job.timeout_ms;
       timeoutTimer = setTimeout(() => {
         if (!abort.signal.aborted) {
           console.warn(`Job ${job.id} (${job.name}) hit per-job timeout (${job.timeout_ms}ms), aborting`);
           abort.abort(new Error('timeout'));
         }
-      }, job.timeout_ms);
+      }, delayMs);
     }
 
     const promise = this.executeJob(job, lockToken, abort, lockTimer)
@@ -944,6 +971,7 @@ export class MinionWorker extends EventEmitter {
       data: job.data,
       attempts_made: job.attempts_made,
       signal: abort.signal,
+      deadlineAtMs: job.timeout_at != null ? job.timeout_at.getTime() : null,
       shutdownSignal: this.shutdownAbort.signal,
       updateProgress: async (progress: unknown) => {
         await this.queue.updateProgress(job.id, lockToken, progress);

src/core/oauth-provider.ts

@@ -30,6 +30,15 @@ import { parseLegacyTokenScope } from './legacy-token-scope.ts';
 import type { SqlQuery, SqlValue } from './sql-query.ts';
 export type { SqlQuery, SqlValue };
 
+export interface AgentClientBindings {
+  boundTools?: string[];
+  boundSourceId?: string;
+  boundBrainId?: string;
+  boundSlugPrefixes?: string[];
+  boundMaxConcurrent?: number;
+  budgetUsdPerDay?: string;
+}
+
 // ---------------------------------------------------------------------------
 // Types
 // ---------------------------------------------------------------------------
@@ -885,6 +894,7 @@ export class GBrainOAuthProvider implements OAuthServerProvider {
     sourceId: string = 'default',
     federatedRead?: string[],
     tokenEndpointAuthMethod?: string,
+    agentBindings?: AgentClientBindings,
   ): Promise<{ clientId: string; clientSecret?: string }> {
     // v0.28: ALLOWED_SCOPES allowlist. Reject `--scopes "read flying-unicorn"`
     // at registration so meaningless scope strings can't pile up in the DB.
@@ -917,16 +927,44 @@ export class GBrainOAuthProvider implements OAuthServerProvider {
     //                    has read scope == write scope, the v0.33 default)
     const federated = federatedRead && federatedRead.length > 0 ? federatedRead : [sourceId];
     try {
-      await this.sql`
-        INSERT INTO oauth_clients (client_id, client_secret_hash, client_name, redirect_uris,
-                                    grant_types, scope, token_endpoint_auth_method,
-                                    client_id_issued_at,
-                                    source_id, federated_read)
-        VALUES (${clientId}, ${secretHash}, ${name},
-                ${pgArray(redirectUris)}, ${pgArray(grantTypes)}, ${scopes}, ${authMethod}, ${now},
-                ${sourceId}, ${pgArray(federated)})
-      `;
+      if (agentBindings) {
+        await this.sql`
+          INSERT INTO oauth_clients (client_id, client_secret_hash, client_name, redirect_uris,
+                                      grant_types, scope, token_endpoint_auth_method,
+                                      client_id_issued_at,
+                                      source_id, federated_read,
+                                      bound_tools, bound_source_id, bound_brain_id,
+                                      bound_slug_prefixes, bound_max_concurrent, budget_usd_per_day)
+          VALUES (${clientId}, ${secretHash}, ${name},
+                  ${pgArray(redirectUris)}, ${pgArray(grantTypes)}, ${scopes}, ${authMethod}, ${now},
+                  ${sourceId}, ${pgArray(federated)},
+                  ${agentBindings.boundTools ? pgArray(agentBindings.boundTools) : null},
+                  ${agentBindings.boundSourceId ?? null}, ${agentBindings.boundBrainId ?? null},
+                  ${agentBindings.boundSlugPrefixes ? pgArray(agentBindings.boundSlugPrefixes) : null},
+                  ${agentBindings.boundMaxConcurrent ?? 1}, ${agentBindings.budgetUsdPerDay ?? null})
+        `;
+      } else {
+        await this.sql`
+          INSERT INTO oauth_clients (client_id, client_secret_hash, client_name, redirect_uris,
+                                      grant_types, scope, token_endpoint_auth_method,
+                                      client_id_issued_at,
+                                      source_id, federated_read)
+          VALUES (${clientId}, ${secretHash}, ${name},
+                  ${pgArray(redirectUris)}, ${pgArray(grantTypes)}, ${scopes}, ${authMethod}, ${now},
+                  ${sourceId}, ${pgArray(federated)})
+        `;
+      }
     } catch (err) {
+      if (agentBindings && (
+        isUndefinedColumnError(err, 'bound_tools') ||
+        isUndefinedColumnError(err, 'bound_source_id') ||
+        isUndefinedColumnError(err, 'bound_brain_id') ||
+        isUndefinedColumnError(err, 'bound_slug_prefixes') ||
+        isUndefinedColumnError(err, 'bound_max_concurrent') ||
+        isUndefinedColumnError(err, 'budget_usd_per_day')
+      )) {
+        throw new Error('register-client --bound-* flags require an up-to-date OAuth schema; run `gbrain apply-migrations --yes` and retry.');
+      }
       // Pre-v60 / pre-v61 brain: column missing. Fall back through both
       // projections so registration still works until apply-migrations.
       if (isUndefinedColumnError(err, 'federated_read')) {

src/core/operations.ts

@@ -193,6 +193,39 @@ export function matchesSlugAllowList(slug: string, prefixes: readonly string[]):
   return false;
 }
 
+/**
+ * Subagent slug-fence enforcement, shared by every mutating op a subagent
+ * can reach (put_page, add_timeline_entry). FAIL-CLOSED: `viaSubagent=true`
+ * enforces the check even if the dispatcher forgot to populate `subagentId`.
+ *
+ *   - Trusted-workspace path (ctx.allowedSlugPrefixes set by cycle.ts under
+ *     PROTECTED_JOB_NAMES \u2014 MCP cannot reach it): slug must match the
+ *     allow-list globs.
+ *   - Legacy default: slug must live under `wiki/agents/<subagentId>/...`
+ *     (anchored, slash-boundary \u2014 `wiki/agents/12evil/*` can't impersonate
+ *     subagent 12).
+ */
+function enforceSubagentSlugFence(ctx: OperationContext, slug: string, opName: string): void {
+  if (ctx.viaSubagent !== true) return;
+  if (typeof ctx.subagentId !== 'number' || Number.isNaN(ctx.subagentId)) {
+    throw new OperationError('permission_denied', `${opName} via subagent requires ctx.subagentId`);
+  }
+  const allowList = ctx.allowedSlugPrefixes;
+  if (allowList && allowList.length > 0) {
+    if (!matchesSlugAllowList(slug, allowList)) {
+      throw new OperationError(
+        'permission_denied',
+        `${opName} slug '${slug}' is not within the trusted-workspace allow-list (${allowList.join(', ')})`
+      );
+    }
+  } else {
+    const prefix = `wiki/agents/${ctx.subagentId}/`;
+    if (!slug.startsWith(prefix) || slug.length === prefix.length) {
+      throw new OperationError('permission_denied', `${opName} via subagent must write under '${prefix}...'`);
+    }
+  }
+}
+
 /**
  * Allowlist validator for uploaded file basenames. Rejects control chars, backslashes,
  * RTL overrides (\u202E), leading dot (hidden files) and leading dash (CLI flag confusion).
@@ -784,37 +817,9 @@ const put_page: Operation = {
     }
 
     // Subagent namespace enforcement (v0.15+). Runs BEFORE the dry-run
-    // short-circuit so preview calls surface the same rejection. Confines
-    // LLM-driven writes to wiki/agents/<subagentId>/... — no leading slash
-    // (slug grammar rejects that), anchored, slash-boundary to defeat prefix
-    // collisions like `wiki/agents/12evil/*` impersonating subagent 12.
-    //
-    // FAIL-CLOSED: `viaSubagent=true` enforces the check even if the
-    // dispatcher forgot to populate `subagentId`. Agent-originated writes
-    // without an owning subagent id are rejected outright.
-    if (ctx.viaSubagent === true) {
-      if (typeof ctx.subagentId !== 'number' || Number.isNaN(ctx.subagentId)) {
-        throw new OperationError('permission_denied', 'put_page via subagent requires ctx.subagentId');
-      }
-      const allowList = ctx.allowedSlugPrefixes;
-      if (allowList && allowList.length > 0) {
-        // Trusted-workspace path: explicit allow-list bounds writes.
-        // Set only by cycle.ts (synthesize/patterns) which submits subagent
-        // jobs under PROTECTED_JOB_NAMES — MCP cannot reach this branch.
-        if (!matchesSlugAllowList(slug, allowList)) {
-          throw new OperationError(
-            'permission_denied',
-            `put_page slug '${slug}' is not within the trusted-workspace allow-list (${allowList.join(', ')})`
-          );
-        }
-      } else {
-        // Legacy default: agent-namespace confinement.
-        const prefix = `wiki/agents/${ctx.subagentId}/`;
-        if (!slug.startsWith(prefix) || slug.length === prefix.length) {
-          throw new OperationError('permission_denied', `put_page via subagent must write under '${prefix}...'`);
-        }
-      }
-    }
+    // short-circuit so preview calls surface the same rejection. See
+    // enforceSubagentSlugFence for the fail-closed policy.
+    enforceSubagentSlugFence(ctx, slug, 'put_page');
 
     if (ctx.dryRun) return { dry_run: true, action: 'put_page', slug: p.slug };
     // Skip embedding when the AI gateway has no embedding provider configured.
@@ -2149,6 +2154,11 @@ const add_timeline_entry: Operation = {
   mutating: true,
   scope: 'write',
   handler: async (ctx, p) => {
+    // #2778: same fail-closed slug fence as put_page. add_timeline_entry is
+    // subagent-allowlisted (brain-allowlist.ts), so timeline writes must be
+    // confined to the same namespace/allow-list as page writes. Runs before
+    // the dry-run short-circuit so preview calls surface the same rejection.
+    enforceSubagentSlugFence(ctx, p.slug as string, 'add_timeline_entry');
     if (ctx.dryRun) return { dry_run: true, action: 'add_timeline_entry', slug: p.slug };
     const date = p.date as string;
     // Reject anything that isn't a strict YYYY-MM-DD with year 1900-2199 and

src/core/orphan-policy.ts

@@ -0,0 +1,116 @@
+/**
+ * Shared orphan-reporting exclusion policy.
+ *
+ * These are pages where "no inbound links" is expected and should not count
+ * against health. Keep this in core so the CLI orphan report and engine health
+ * dashboard cannot drift.
+ *
+ * Defaults are GBrain-wide conventions only. Brain-specific exclusions
+ * (private folder names, one-off fixture slugs) belong in the brain's own
+ * config, not here:
+ *
+ *   gbrain config set orphans.exclude_prefixes "my-private-folder/,archive/"
+ *   gbrain config set orphans.exclude_slugs "some-one-off-page"
+ */
+
+const AUTO_SUFFIX_PATTERNS = ['/_index', '/log'];
+
+const PSEUDO_SLUGS = new Set(['_atlas', '_index', '_stats', '_orphans', '_scratch', 'claude']);
+
+const RAW_SEGMENT = '/raw/';
+
+const DENY_PREFIXES = [
+  'output/',
+  'dashboards/',
+  'scripts/',
+  'templates/',
+  '_templates/',
+  'openclaw/config/',
+  'extracts/',
+];
+
+const FIRST_SEGMENT_EXCLUSIONS = new Set([
+  'scratch',
+  'thoughts',
+  'catalog',
+  'entities',
+  'raw',
+  'atoms',
+  'skills',
+  'dreaming',
+  'daily',
+]);
+
+const ROOT_DATE_SLUG = /^\d{4}-\d{2}-\d{2}(?:-.+)?$/;
+
+function isAgentWorkspaceConvention(slug: string): boolean {
+  if (!slug.startsWith('agents/')) return false;
+  if (slug.includes('/memory/dreaming/')) return true;
+  return /^agents\/[^/]+\/(?:agents|identity|soul|tools|user|heartbeat|dreams|dormant)$/.test(slug);
+}
+
+/** Per-brain additions to the convention defaults (from config). */
+export interface OrphanPolicyOverrides {
+  excludePrefixes?: string[];
+  excludeSlugs?: string[];
+}
+
+/** Config keys for per-brain orphan exclusions (comma-separated values). */
+export const ORPHAN_EXCLUDE_PREFIXES_KEY = 'orphans.exclude_prefixes';
+export const ORPHAN_EXCLUDE_SLUGS_KEY = 'orphans.exclude_slugs';
+
+function parseList(value: string | null): string[] {
+  if (!value) return [];
+  return value.split(',').map(s => s.trim()).filter(Boolean);
+}
+
+/**
+ * Load per-brain orphan exclusions from the brain config table. Callers with
+ * an engine in hand (getHealth, `gbrain orphans`) pass the result as the
+ * second argument to shouldExcludeFromOrphanReporting.
+ */
+export async function loadOrphanPolicyOverrides(
+  engine: { getConfig(key: string): Promise<string | null> },
+): Promise<OrphanPolicyOverrides> {
+  const [prefixes, slugs] = await Promise.all([
+    engine.getConfig(ORPHAN_EXCLUDE_PREFIXES_KEY),
+    engine.getConfig(ORPHAN_EXCLUDE_SLUGS_KEY),
+  ]);
+  return { excludePrefixes: parseList(prefixes), excludeSlugs: parseList(slugs) };
+}
+
+export function shouldExcludeFromOrphanReporting(
+  slug: string,
+  overrides?: OrphanPolicyOverrides,
+): boolean {
+  if (PSEUDO_SLUGS.has(slug)) return true;
+
+  for (const suffix of AUTO_SUFFIX_PATTERNS) {
+    if (slug.endsWith(suffix)) return true;
+  }
+
+  if (slug.includes(RAW_SEGMENT)) return true;
+  if (slug.includes('/daily/')) return true;
+
+  for (const prefix of DENY_PREFIXES) {
+    if (slug.startsWith(prefix)) return true;
+  }
+
+  const firstSegment = slug.split('/')[0];
+  if (FIRST_SEGMENT_EXCLUSIONS.has(firstSegment)) return true;
+
+  if (ROOT_DATE_SLUG.test(slug)) return true;
+
+  if (slug.startsWith('_brain-')) return true;
+
+  if (isAgentWorkspaceConvention(slug)) return true;
+
+  if (overrides) {
+    if (overrides.excludeSlugs?.includes(slug)) return true;
+    for (const prefix of overrides.excludePrefixes ?? []) {
+      if (slug.startsWith(prefix)) return true;
+    }
+  }
+
+  return false;
+}

src/core/page-summary.ts

@@ -44,6 +44,33 @@ const HAIKU_MAX_TOKENS = 200;
 /** Default model when caller doesn't override. Resolves through the gateway. */
 const DEFAULT_SYNOPSIS_MODEL = 'anthropic:claude-haiku-4-5-20251001';
 
+/**
+ * Hard cap on `documentText` length (chars) before send.
+ *
+ * 2026-05-25 fix wave: small local chat models (Gemma 4 E2B, Qwen3 4B) get
+ * dramatically slower on long contexts even with 131K-token windows declared.
+ * A 73K-char page synopsis on Gemma 4 E2B takes 60-120s, exceeding the
+ * worker's default 30s `lockDuration` and tripping `lock-lost` errors.
+ *
+ * Truncate to a budget that fits a small model's effective throughput while
+ * preserving enough document context for the synopsis to be useful. Truncates
+ * the TAIL because the head (title, frontmatter, intro) carries the
+ * document-level anchor the synopsis needs.
+ *
+ * Override per workload via `GBRAIN_SYNOPSIS_DOC_MAX_CHARS`. Default 32768
+ * (~8K tokens at 4 chars/tok) keeps small-model synopsis under ~30s.
+ * Anthropic Haiku is unaffected at this cap; bump higher when running
+ * frontier models if you want richer document anchoring.
+ */
+export const SYNOPSIS_DOC_MAX_CHARS = (() => {
+  const env = process.env.GBRAIN_SYNOPSIS_DOC_MAX_CHARS;
+  if (env && /^\d+$/.test(env)) {
+    const n = parseInt(env, 10);
+    if (n >= 512 && n <= 1_048_576) return n;
+  }
+  return 32768;
+})();
+
 /**
  * Synopsis prompt version. Folded into corpus_generation so prompt edits
  * invalidate prior embeddings via the v0.40.3.0 query_cache.page_generations
@@ -188,11 +215,19 @@ function buildUserPrompt(
   documentText: string,
   chunkText: string,
 ): string {
+  // Tail-truncate `documentText` to `SYNOPSIS_DOC_MAX_CHARS` so small local
+  // chat models don't stall on >100KB pages. Head preserved (title block,
+  // frontmatter, intro paragraphs carry the document-level anchor).
+  let trimmedDoc = documentText;
+  if (documentText.length > SYNOPSIS_DOC_MAX_CHARS) {
+    trimmedDoc = documentText.slice(0, SYNOPSIS_DOC_MAX_CHARS) +
+      `\n\n[... ${documentText.length - SYNOPSIS_DOC_MAX_CHARS} chars truncated for synopsis budget ...]`;
+  }
   return [
     `<page_title>${pageTitle}</page_title>`,
     '',
     '<full_document>',
-    documentText,
+    trimmedDoc,
     '</full_document>',
     '',
     '<chunk>',

src/core/pglite-engine.ts

@@ -23,7 +23,9 @@ import { runMigrations } from './migrate.ts';
 import { PGLITE_SCHEMA_SQL, getPGLiteSchema } from './pglite-schema.ts';
 import { DEFAULT_EMBEDDING_MODEL, DEFAULT_EMBEDDING_DIMENSIONS } from './ai/defaults.ts';
 import { DELETE_BATCH_SIZE } from './engine-constants.ts';
+import { MARKDOWN_CHUNKER_VERSION } from './chunkers/recursive.ts';
 import { acquireLock, releaseLock, type LockHandle } from './pglite-lock.ts';
+import { getFtsLanguage } from './fts-language.ts';
 import type {
   Page, PageInput, PageFilters, PageType,
   Chunk, ChunkInput, StaleChunkRow, StalePageRow,
@@ -54,7 +56,9 @@ import { GBrainError, PAGE_SORT_SQL, ENRICH_ORDER_SQL } from './types.ts';
 import { finalizeLastSeen } from './chronicle/last-seen.ts';
 import { computeAnomaliesFromBuckets } from './cycle/anomaly.ts';
 import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
-import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte } from './search/sql-ranking.ts';
+import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
+import { shouldExcludeFromOrphanReporting, loadOrphanPolicyOverrides } from './orphan-policy.ts';
+import { LINK_EXTRACTOR_VERSION_TS } from './link-extraction.ts';
 import {
   normalizeEngineColumn,
   buildVectorCastFragment,
@@ -1034,7 +1038,7 @@ export class PGLiteEngine implements BrainEngine {
     const ingestedAt = (sourceKind || sourceUri || ingestedVia) ? new Date().toISOString() : null;
     const { rows } = await this.db.query(
       `INSERT INTO pages (source_id, slug, type, page_kind, title, compiled_truth, timeline, frontmatter, content_hash, updated_at, effective_date, effective_date_source, import_filename, chunker_version, source_path, source_kind, source_uri, ingested_via, ingested_at)
-       VALUES ($1, $2, $3, $4, $5, $6, $7, $8::jsonb, $9, now(), $10::timestamptz, $11, $12, COALESCE($13, 1), $14, $15, $16, $17, $18::timestamptz)
+       VALUES ($1, $2, $3, $4, $5, $6, $7, $8::jsonb, $9, now(), $10::timestamptz, $11, $12, COALESCE($13, ${MARKDOWN_CHUNKER_VERSION}), $14, $15, $16, $17, $18::timestamptz)
        ON CONFLICT (source_id, slug) DO UPDATE SET
          type = EXCLUDED.type,
          page_kind = EXCLUDED.page_kind,
@@ -1625,20 +1629,24 @@ export class PGLiteEngine implements BrainEngine {
       extraFilter += ` AND p.source_id = $${params.length}`;
     }
 
-    const { rows } = await this.db.query(
+    // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
+    // — safe to interpolate into raw SQL.
+    const ftsLang = getFtsLanguage();
+
+    const keywordSql =
       `WITH ranked AS (
          SELECT
            p.slug, p.id as page_id, p.title, p.type, p.source_id,
            p.effective_date, p.effective_date_source,
            cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-           ts_rank(cc.search_vector, websearch_to_tsquery('english', $1)) * ${sourceFactorCase} AS score,
+           ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
            CASE WHEN p.updated_at < (
              SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
            ) THEN true ELSE false END AS stale
          FROM content_chunks cc
          JOIN pages p ON p.id = cc.page_id
          JOIN sources s ON s.id = p.source_id
-         WHERE cc.search_vector @@ websearch_to_tsquery('english', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
+         WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
            -- v0.27.1: hide image rows from default text-keyword search so
            -- OCR text doesn't drown text-page hits. Image-similarity queries
            -- run a separate vector path on embedding_image.
@@ -1649,10 +1657,140 @@ export class PGLiteEngine implements BrainEngine {
        ${buildBestPerPagePoolCte('ranked')}
        SELECT * FROM best_per_page
        ORDER BY score DESC, page_id ASC, chunk_id ASC
-       LIMIT $3 OFFSET $4`,
-      params
-    );
+       LIMIT $3 OFFSET $4`;
 
+    let { rows } = await this.db.query(keywordSql, params);
+    // D2 fix (fix/title-retrieval-arm): websearch AND semantics at chunk
+    // grain mean one non-co-occurring token zeroes keyword recall. When the
+    // strict query returns nothing, retry ONCE with OR-of-terms. Strict-AND
+    // results always win when non-empty (no change for working queries).
+    // Opt-in via SearchOpts.orFallback (Reviewer F1): only hybridSearch's
+    // recall arm relaxes; precision consumers (countMentions,
+    // link-extraction, eval) keep the strict-AND contract.
+    if (rows.length === 0 && opts?.orFallback) {
+      const orQuery = buildOrFallbackWebsearchQuery(query);
+      if (orQuery) {
+        const fallbackParams = [...params];
+        fallbackParams[0] = orQuery;
+        ({ rows } = await this.db.query(keywordSql, fallbackParams));
+      }
+    }
+
+    return (rows as Record<string, unknown>[]).map(rowToSearchResult);
+  }
+
+  /**
+   * fix/title-retrieval-arm (D1): page-grain title candidate arm. See the
+   * BrainEngine interface doc for the full contract. Queries
+   * pages.search_vector (title weight 'A' dominates ts_rank_cd by
+   * construction) with the same page-grain filters the keyword arm applies
+   * (type/types/excludeSlugs/date/source scoping, hard-excludes,
+   * visibility), joined to one representative chunk per page. Applies the
+   * same AND→OR recall fallback as searchKeyword. NO query-length gate —
+   * long exact-title queries are the case this arm exists for.
+   *
+   * CJK queries fall through to websearch FTS here (a single-token CJK
+   * query CAN exact-match a single-token CJK title); the richer CJK ILIKE
+   * fallback stays keyword-arm-only.
+   */
+  async searchTitles(query: string, opts?: SearchOpts): Promise<SearchResult[]> {
+    // language/symbolKind are chunk-grain code filters with no page-grain
+    // meaning; a code-scoped query gets no title candidates rather than
+    // rows that silently violate the caller's filter.
+    if (opts?.language || opts?.symbolKind) return [];
+    const limit = clampSearchLimit(opts?.limit);
+    const offset = opts?.offset || 0;
+    const detailLow = opts?.detail === 'low';
+
+    if (opts?.limit && opts.limit > MAX_SEARCH_LIMIT) {
+      console.warn(`[gbrain] Warning: search limit clamped from ${opts.limit} to ${MAX_SEARCH_LIMIT}`);
+    }
+
+    const boostMap = resolveBoostMap();
+    const sourceFactorCase = buildSourceFactorCase('p.slug', boostMap, opts?.detail);
+    const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
+    const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
+    const visibilityClause = buildVisibilityClause('p', 's');
+    // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
+    // — safe to interpolate into raw SQL.
+    const ftsLang = getFtsLanguage();
+
+    const params: unknown[] = [query, limit, offset];
+    let extraFilter = '';
+    if (opts?.type) {
+      params.push(opts.type);
+      extraFilter += ` AND p.type = $${params.length}`;
+    }
+    if (opts?.types && opts.types.length > 0) {
+      params.push(opts.types);
+      extraFilter += ` AND p.type = ANY($${params.length}::text[])`;
+    }
+    if (opts?.exclude_slugs?.length) {
+      params.push(opts.exclude_slugs);
+      extraFilter += ` AND p.slug != ALL($${params.length}::text[])`;
+    }
+    if (opts?.afterDate) {
+      params.push(opts.afterDate);
+      extraFilter += ` AND COALESCE(p.effective_date, p.updated_at, p.created_at) > $${params.length}::timestamptz`;
+    }
+    if (opts?.beforeDate) {
+      params.push(opts.beforeDate);
+      extraFilter += ` AND COALESCE(p.effective_date, p.updated_at, p.created_at) < $${params.length}::timestamptz`;
+    }
+    if (opts?.sourceIds && opts.sourceIds.length > 0) {
+      params.push(opts.sourceIds);
+      extraFilter += ` AND p.source_id = ANY($${params.length}::text[])`;
+    } else if (opts?.sourceId) {
+      params.push(opts.sourceId);
+      extraFilter += ` AND p.source_id = $${params.length}`;
+    }
+
+    // Page grain — one row per page by construction, so no best_per_page
+    // pooling CTE is needed. The LEFT JOIN LATERAL picks the representative
+    // chunk (compiled_truth first, then lowest chunk_index); COALESCEs keep
+    // chunkless pages retrievable (the extreme D1 case: a title with no
+    // body) with the alias-hop row shape (chunk_id 0, empty chunk_text).
+    // Accepted limitations (Reviewer F5/F6): the synthetic chunkless row
+    // inherits the compiled-truth RRF boost and dedups on empty chunk_text;
+    // and detail='low' filters only the REPRESENTATIVE — pages without a
+    // compiled_truth chunk still surface (unlike the keyword arm's filter).
+    const titlesSql =
+      `SELECT
+         p.slug, p.id as page_id, p.title, p.type, p.source_id,
+         p.effective_date, p.effective_date_source,
+         COALESCE(rep.id, 0) as chunk_id,
+         COALESCE(rep.chunk_index, 0) as chunk_index,
+         COALESCE(rep.chunk_text, '') as chunk_text,
+         COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
+         ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
+         CASE WHEN p.updated_at < (
+           SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
+         ) THEN true ELSE false END AS stale
+       FROM pages p
+       JOIN sources s ON s.id = p.source_id
+       LEFT JOIN LATERAL (
+         SELECT cc.id, cc.chunk_index, cc.chunk_text, cc.chunk_source
+         FROM content_chunks cc
+         WHERE cc.page_id = p.id
+           AND cc.modality = 'text'
+           ${detailLow ? `AND cc.chunk_source = 'compiled_truth'` : ''}
+         ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
+         LIMIT 1
+       ) rep ON true
+       WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
+         ${extraFilter} ${hardExcludeClause} ${visibilityClause}
+       ORDER BY score DESC, p.id ASC
+       LIMIT $2 OFFSET $3`;
+
+    let { rows } = await this.db.query(titlesSql, params);
+    if (rows.length === 0) {
+      const orQuery = buildOrFallbackWebsearchQuery(query);
+      if (orQuery) {
+        const fallbackParams = [...params];
+        fallbackParams[0] = orQuery;
+        ({ rows } = await this.db.query(titlesSql, fallbackParams));
+      }
+    }
     return (rows as Record<string, unknown>[]).map(rowToSearchResult);
   }
 
@@ -1857,20 +1995,23 @@ export class PGLiteEngine implements BrainEngine {
     }
 
     // visibilityClause already declared above (v0.32.7: hoisted so CJK branch can reuse).
+    // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
+    // — safe to interpolate into raw SQL.
+    const ftsLang = getFtsLanguage();
 
     const { rows } = await this.db.query(
       `SELECT
          p.slug, p.id as page_id, p.title, p.type, p.source_id,
          p.effective_date, p.effective_date_source,
          cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-         ts_rank(cc.search_vector, websearch_to_tsquery('english', $1)) * ${sourceFactorCase} AS score,
+         ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
          CASE WHEN p.updated_at < (
            SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
          ) THEN true ELSE false END AS stale
        FROM content_chunks cc
        JOIN pages p ON p.id = cc.page_id
        JOIN sources s ON s.id = p.source_id
-       WHERE cc.search_vector @@ websearch_to_tsquery('english', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
+       WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
        ORDER BY score DESC
        LIMIT $2 OFFSET $3`,
       params
@@ -2183,6 +2324,10 @@ export class PGLiteEngine implements BrainEngine {
     // v0.40.3.0 D24 NULL→non-NULL race fix mirrors postgres-engine.ts. Two writers
     // racing on the same chunk previously raced last-write-wins; the fix lets the
     // fresher `embedded_at` win in the text-unchanged branch.
+    //
+    // Code-chunk metadata columns follow the same chunk_text-gated CASE pattern as `embedding`
+    // (#769). Re-chunk trusts EXCLUDED outright; pure re-embed COALESCEs so a caller carrying
+    // only embedding-shaped fields doesn't clobber metadata to NULL.
     await this.db.query(
       `INSERT INTO content_chunks ${cols} VALUES ${rowParts.join(', ')}
        ON CONFLICT (page_id, chunk_index) DO UPDATE SET
@@ -2206,14 +2351,14 @@ export class PGLiteEngine implements BrainEngine {
                 THEN EXCLUDED.embedded_at
            ELSE content_chunks.embedded_at
          END,
-         language = EXCLUDED.language,
-         symbol_name = EXCLUDED.symbol_name,
-         symbol_type = EXCLUDED.symbol_type,
-         start_line = EXCLUDED.start_line,
-         end_line = EXCLUDED.end_line,
-         parent_symbol_path = EXCLUDED.parent_symbol_path,
-         doc_comment = EXCLUDED.doc_comment,
-         symbol_name_qualified = EXCLUDED.symbol_name_qualified,
+         language = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.language ELSE COALESCE(EXCLUDED.language, content_chunks.language) END,
+         symbol_name = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.symbol_name ELSE COALESCE(EXCLUDED.symbol_name, content_chunks.symbol_name) END,
+         symbol_type = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.symbol_type ELSE COALESCE(EXCLUDED.symbol_type, content_chunks.symbol_type) END,
+         start_line = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.start_line ELSE COALESCE(EXCLUDED.start_line, content_chunks.start_line) END,
+         end_line = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.end_line ELSE COALESCE(EXCLUDED.end_line, content_chunks.end_line) END,
+         parent_symbol_path = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.parent_symbol_path ELSE COALESCE(EXCLUDED.parent_symbol_path, content_chunks.parent_symbol_path) END,
+         doc_comment = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.doc_comment ELSE COALESCE(EXCLUDED.doc_comment, content_chunks.doc_comment) END,
+         symbol_name_qualified = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.symbol_name_qualified ELSE COALESCE(EXCLUDED.symbol_name_qualified, content_chunks.symbol_name_qualified) END,
          modality = EXCLUDED.modality,
          embedding_image = COALESCE(EXCLUDED.embedding_image, content_chunks.embedding_image)`,
       params
@@ -3536,6 +3681,13 @@ export class PGLiteEngine implements BrainEngine {
                  THEN ep.frontmatter->'event'->'who' ELSE '[]'::jsonb END
           ) AS w(name) WHERE w.name = $1 OR w.name LIKE $2)))`,
     ];
+    // "Last seen" is a PAST relation: chronicle stores future events
+    // (calendar-event is eligible), which must not read as "last seen".
+    // Bound to <= asof/today, mirroring getOnThisDay's `te.date < target`.
+    let seenThrough: string;
+    if (opts?.asof) { params.push(opts.asof); seenThrough = `$${params.length}::date`; }
+    else { seenThrough = `current_date`; }
+    where.push(`te.date <= ${seenThrough}`);
     this.pushChronicleSource(where, params, opts);
     const result = await this.db.query(
       `SELECT te.date::text AS last_date, ep.slug AS last_event_slug
@@ -5029,7 +5181,7 @@ export class PGLiteEngine implements BrainEngine {
     `);
 
     const { rows: types } = await this.db.query(
-      `SELECT type, count(*)::int as count FROM pages GROUP BY type ORDER BY count DESC`
+      `SELECT type, count(*)::int as count FROM pages WHERE deleted_at IS NULL GROUP BY type ORDER BY count DESC`
     );
     const pages_by_type: Record<string, number> = {};
     for (const t of types as { type: string; count: number }[]) {
@@ -5061,15 +5213,10 @@ export class PGLiteEngine implements BrainEngine {
         (SELECT count(*) FROM pages) as page_count,
         (SELECT count(*) FROM content_chunks WHERE embedded_at IS NOT NULL)::float /
           GREATEST((SELECT count(*) FROM content_chunks), 1)::float as embed_coverage,
-        (SELECT count(*) FROM pages p
-         WHERE p.updated_at < (SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id)
-        ) as stale_pages,
-        -- Bug 11 — orphan = islanded (no inbound AND no outbound).
-        -- See BrainHealth.orphan_pages docstring; docs updated to match this.
-        (SELECT count(*) FROM pages p
-         WHERE NOT EXISTS (SELECT 1 FROM links l WHERE l.to_page_id = p.id)
-           AND NOT EXISTS (SELECT 1 FROM links l WHERE l.from_page_id = p.id)
-        ) as orphan_pages,
+        0 as stale_pages,
+        -- Bug 11 — orphan = islanded (no inbound AND no outbound). The raw
+        -- list is filtered in TS using the shared orphan-reporting policy.
+        0 as orphan_pages,
         (SELECT count(*) FROM links l
          WHERE NOT EXISTS (SELECT 1 FROM pages p WHERE p.id = l.to_page_id)
         ) as dead_links,
@@ -5094,10 +5241,20 @@ export class PGLiteEngine implements BrainEngine {
       LIMIT 5
     `);
 
+    const { rows: islandedRows } = await this.db.query(`
+      SELECT p.slug
+      FROM pages p
+      WHERE NOT EXISTS (SELECT 1 FROM links l WHERE l.to_page_id = p.id)
+        AND NOT EXISTS (SELECT 1 FROM links l WHERE l.from_page_id = p.id)
+    `);
+
     const r = h as Record<string, unknown>;
     const pageCount = Number(r.page_count);
     const embedCoverage = Number(r.embed_coverage);
-    const orphanPages = Number(r.orphan_pages);
+    const stalePages = await this.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS });
+    const orphanOverrides = await loadOrphanPolicyOverrides(this);
+    const orphanPages = (islandedRows as { slug: string }[])
+      .filter(row => !shouldExcludeFromOrphanReporting(row.slug, orphanOverrides)).length;
     const deadLinks = Number(r.dead_links);
     const linkCount = Number(r.link_count);
     const pagesWithTimeline = Number(r.pages_with_timeline);
@@ -5125,7 +5282,7 @@ export class PGLiteEngine implements BrainEngine {
     return {
       page_count: pageCount,
       embed_coverage: embedCoverage,
-      stale_pages: Number(r.stale_pages),
+      stale_pages: stalePages,
       orphan_pages: orphanPages,
       missing_embeddings: Number(r.missing_embeddings),
       brain_score: brainScore,