Merge branch 'master' into fix/docs-nonexistent-install-command-3502

* fix(test): make resetGateway restore the test baseline instead of unconfiguring (#3554)

bunfig.toml's legacy-embedding-preload pins the gateway once at process
start to openai:text-embedding-3-large @ 1536, but resetGateway() wiped
that pin to _config = null. The next test file's beforeAll engine-connect
then reconfigured from the SHIPPED default (zembed-1 @ 1280) before the
preload's per-test beforeEach could restore anything, and every 1536-d
fixture in that file failed with `expected 1280 dimensions, not 1536`.
Which file pairs collided depended on shard bin-packing, so adding ANY
test file reshuffled the mines (this is what blocks #3545).

Fix: the preload registers its config as a reset baseline via a new
test-only seam (__setGatewayResetBaselineForTests); resetGateway() clears
all module state as before, then re-applies the baseline. All 93 existing
resetGateway() call sites get the correct behavior with zero edits.
Production is untouched: nothing in src/ calls resetGateway() or the
setter, so the baseline is never registered outside tests and
resetGateway() still fully unconfigures there.

Five tests genuinely need an unconfigured gateway (no_gateway_config
diagnosis, isAvailable=false, the #2590 cold-gateway path, the registry
builtin-default tier); they switch to the new __unconfigureGatewayForTests.
Two files' hand-rolled "restore the legacy pin in afterAll/finally"
workarounds for this exact bug are now redundant and simplified away.

Guard test (test/ai/gateway-reset-baseline.test.ts) pins the contract:
1536/openai immediately after resetGateway(), transports still cleared,
hard-unconfigure still available.

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

* fix(test): restore preload's GBRAIN_AUDIT_DIR instead of deleting it (#3554 sibling)

Same bug class as the gateway fix in this PR: state set once by a bunfig
preload (audit-dir-preload's scratch GBRAIN_AUDIT_DIR), wiped by one
file's cleanup, blast radius decided by shard bin-packing. In shard 6,
test/minions-shell.test.ts (position 12) unconditionally deleted the var
in afterAll; test/audit/audit-dir-preload.test.ts (position 93) then
found it undefined and failed 3 tests — and every file in between wrote
audit fixtures toward the operator's real ~/.gbrain/audit/.

Fix: capture the prior value at file load and conditionally restore it,
the same inline save/restore pattern 11 sibling files already use.
test/e2e/skill-brain-first.test.ts had the identical unconditional
delete in afterEach; fixed the same way. Sweep of every
`delete process.env.GBRAIN_AUDIT_DIR` in test/ confirms all remaining
sites are conditional restores.

Ordered-pair proof (minions-shell.test.ts then
audit/audit-dir-preload.test.ts, one process): 3 fail on master,
43/43 pass with this fix.

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

---------

Co-authored-by: Garry Tan <garrytan@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>

.gitattributes

@@ -0,0 +1,16 @@
+# Line-ending policy.
+#
+# Shell scripts MUST be checked out with LF endings on every platform.
+# Git for Windows installs with `core.autocrlf=true` by default, which
+# rewrites LF -> CRLF on checkout. A strict bash (WSL, Linux CI, macOS)
+# then chokes on the trailing CR:
+#
+#   scripts/run-unit-parallel.sh: line 23: $'\r': command not found
+#   scripts/run-unit-parallel.sh: line 24: set: pipefail : invalid option name
+#   scripts/run-unit-parallel.sh: line 32: syntax error near unexpected token `$'{\r''
+#
+# That silently disabled `bun run test`, `bun run verify`, `bun run ci:local`
+# and `bun run test:e2e` for Windows contributors, since all four dispatch
+# through bash. `eol=lf` pins the checkout regardless of the user's
+# core.autocrlf setting.
+*.sh text eol=lf

.github/workflows/actionlint.yml

@@ -28,5 +28,5 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 5
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: rhysd/actionlint@393031adb9afb225ee52ae2ccd7a5af5525e03e8  # v1.7.11

.github/workflows/e2e.yml

@@ -45,7 +45,7 @@ jobs:
           --health-timeout 5s
           --health-retries 5
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
           bun-version: 1.3.13
@@ -82,7 +82,7 @@ jobs:
           --health-timeout 5s
           --health-retries 5
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
           bun-version: 1.3.13
@@ -116,7 +116,7 @@ jobs:
           --health-timeout 5s
           --health-retries 5
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
           bun-version: 1.3.13

.github/workflows/heavy-tests.yml

@@ -55,7 +55,7 @@ jobs:
           --health-timeout 5s
           --health-retries 5
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
           bun-version: 1.3.13

.github/workflows/release.yml

@@ -24,7 +24,7 @@ jobs:
       id-token: write      # for attest-build-provenance (Sigstore OIDC)
       attestations: write  # for attest-build-provenance
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
           bun-version: 1.3.13
@@ -49,7 +49,7 @@ jobs:
         with:
           path: artifacts
       - name: Create release
-        uses: softprops/action-gh-release@153bb8e04406b158c6c84fc1615b65b24149a1fe  # v2
+        uses: softprops/action-gh-release@3bb12739c298aeb8a4eeaf626c5b8d85266b0e65  # v2
         with:
           files: |
             artifacts/gbrain-darwin-arm64/gbrain-darwin-arm64

.github/workflows/semgrep.yml

@@ -26,7 +26,7 @@ jobs:
     container:
       image: semgrep/semgrep:1.170.0@sha256:c98f8829eea377274ee4b10656458b078b88232469b2ff913f091c2317347c9d
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # 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

.github/workflows/test.yml

@@ -43,7 +43,7 @@ jobs:
       hit: ${{ steps.lookup.outputs.cache-hit }}
       hash: ${{ steps.compute.outputs.hash }}
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - name: Compute content hash
         id: compute
         run: |
@@ -84,7 +84,7 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 10
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
         with:
           fetch-depth: 0
       - uses: gitleaks/gitleaks-action@dcedce43c6f43de0b836d1fe38946645c9c638dc  # v2
@@ -103,7 +103,7 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 12
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
           bun-version: 1.3.13
@@ -124,7 +124,7 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 15
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
           bun-version: 1.3.13
@@ -149,7 +149,7 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 12
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
           bun-version: 1.3.13
@@ -172,7 +172,7 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 12
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
           bun-version: 1.3.13
@@ -216,7 +216,7 @@ jobs:
       matrix:
         shard: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
           bun-version: 1.3.13

.gitignore

@@ -1,4 +1,7 @@
-node_modules/
+# No trailing slash: a bare `node_modules/` pattern matches directories only,
+# so a *symlink* named node_modules slips past it and can be committed
+# (that's how the /tmp-pointing symlink in faf5cdba got in). Match any type.
+node_modules
 bin/
 .DS_Store
 *.log
@@ -15,7 +18,7 @@ supabase/.temp/
 # self-contained binaries (the bun --compile path embeds it via
 # `import path from 'admin/dist/index.html' with { type: 'file' }`).
 # Build via: cd admin && bun install && bun run build.
-admin/node_modules/
+admin/node_modules
 .idea
 eval/reports/
 eval/data/world-v1/world.html
@@ -35,6 +38,11 @@ export/
 # .context/test-shards/. Workspace-local by design — never committed.
 .context/
 
+# Local agent instruction overrides (CLAUDE.local.md / AGENTS.local.md) — personal,
+# per-clone, loaded after the committed CLAUDE.md/AGENTS.md. Never committed.
+CLAUDE.local.md
+AGENTS.local.md
+
 # Tier 3 PGLite snapshot fixture (built on demand by build:pglite-snapshot)
 test/fixtures/pglite-snapshot.tar
 test/fixtures/pglite-snapshot.version

CHANGELOG.md

@@ -2,6 +2,296 @@
 
 All notable changes to GBrain will be documented in this file.
 
+## [0.42.67.0] - 2026-07-28
+
+**If you develop GBrain on Windows, the test and check commands now actually run. Until this release they were quietly doing almost nothing.**
+
+`bun run test`, `bun run verify`, `bun run ci:local` and `bun run test:e2e` all hand off to shell scripts, and on Windows that hand-off was broken in two separate places. The commands did not stop with an obvious error. They reported a result, so a run could look finished when barely any of the checks had actually inspected anything. On a clean Windows clone, `bun run verify` got 1 check to pass and 31 to fail. It now gets 25 to pass and 7 to fail, and none of the 7 are caused by this change.
+
+The first problem was line endings. Git for Windows installs with `core.autocrlf=true`, which rewrites shell scripts to Windows line endings when you clone or check out. Bash refuses to run those, so a script died on its second line before doing any work. The scripts stored in the repository were always correct; only the copy on your disk was wrong. A new `.gitattributes` pins every `.sh` file to Unix line endings at checkout, no matter how your Git is configured.
+
+The second problem was how the checks were started. Thirty three of them pointed straight at a `.sh` file. On macOS and Linux the shell reads the `#!/usr/bin/env bash` line at the top of the script and runs it correctly. Bun on Windows does not do that, so those commands failed the moment they were called. They now go through `bash` explicitly, the same way the other eleven were already written.
+
+Nothing changes for macOS and Linux. No stored file content moves, and no check behaves differently on those platforms.
+
+## To take advantage of v0.42.67.0
+
+Only Windows contributors need to do anything, and only once. `.gitattributes` applies at checkout time, so shell scripts already sitting on your disk keep their old line endings until you refresh them.
+
+1. **Refresh the working copy** from the repository root:
+   ```bash
+   git rm --cached -r . -q
+   git reset --hard
+   ```
+2. **Confirm bash can read the scripts:**
+   ```bash
+   bash -n scripts/run-unit-parallel.sh
+   ```
+   Silence means it worked. `$'\r': command not found` means step 1 did not take effect.
+3. **Run the gate:**
+   ```bash
+   bun run verify
+   ```
+
+### Itemized changes
+
+- New root `.gitattributes` pins `*.sh text eol=lf`, so shell scripts check out with Unix line endings regardless of the contributor's `core.autocrlf` setting. All 59 tracked `.sh` files were already stored with Unix endings, so `git add --renormalize .` reports nothing to do and no stored content changes.
+- `package.json` now routes the remaining 33 `.sh` check commands through `bash`, matching the 11 that already did. Every tracked `.sh` file carries a bash shebang (52 `#!/usr/bin/env bash` and 7 `#!/bin/bash`), so the treatment is uniform across all of them.
+- The five `scripts/*.ts` entries still run under bun and are untouched.
+- `CONTRIBUTING.md` gains a Windows section covering the one-time working-copy refresh and the `bash scripts/<name>.sh` convention for new checks.
+- `docs/TESTING.md` records how the test commands dispatch through bash, and notes that three tree-walking checks plus `typecheck` can exceed the 120s per-check cap on Windows while passing on Linux and macOS.
+
+## [0.42.66.1] - 2026-07-27
+
+### Fixed
+
+- `gbrain doctor` now treats embedding columns wider than pgvector's HNSW limit as healthy exact-scan configurations instead of prescribing an index PostgreSQL cannot build.
+- Local CI now passes an empty Docker mount list correctly and compiles the embedded-WASM smoke binary from container-local storage on Docker Desktop.
+
+## [0.42.66.0] - 2026-07-24
+
+**54 verified fixes from the community backlog: background enrichment stops wasting money on dead pages, autopilot stops killing its own healthy runs, and search respects your settings.**
+
+This release is the second big sweep through the open pull-request backlog, with every change reviewed and tested individually before merging. The theme is trust in the background machinery. The overnight "dream" cycle now remembers which pages produced nothing and stops re-reading them every night, meters its small-model calls against your spend caps, and keeps claim proposals from silently overwriting each other. Long consolidation runs get a 30-minute deadline instead of being killed at 10 minutes mid-work. A wedged server boot now releases its database lock instead of blocking every later command.
+
+Search behaves the way you configured it: the recency-decay setting now actually applies to hybrid search, a local `list_pages` call returns as many rows as you asked for, and when a listing is cut short it says so instead of looking complete. Slack conversation exports parse cleanly, with an optional AI fallback for formats the parser does not know.
+
+New provider recipes: DashScope reranking, OpenRouter reranking, and a claude-cli recipe for dispatching subagents through the gateway.
+
+## To take advantage of v0.42.66.0
+
+`gbrain upgrade` should do this automatically. One schema migration ships in this release (v125, take-proposal idempotency); it is idempotent and needs no manual action.
+
+1. **Upgrade and verify:**
+   ```bash
+   gbrain upgrade
+   gbrain doctor
+   gbrain stats
+   ```
+2. **If `gbrain doctor` warns about a partial migration**, run the orchestrator manually:
+   ```bash
+   gbrain apply-migrations --yes
+   ```
+3. **If any step fails,** please file an issue at https://github.com/garrytan/gbrain/issues with the output of `gbrain doctor` and `~/.gbrain/upgrade-errors.jsonl` if it exists.
+
+### Itemized changes
+
+#### Dream cycle, takes, and spend control
+
+- Pages whose extraction yields zero claims are memoized, so the cycle stops re-spending on them every night. (#2514, #3319, contributed by @ivandebot)
+- Zero-yield pages are tombstoned so `extract_atoms` stops rediscovering them. (#2144, #3304, contributed by @ChenyqThu)
+- `extract_atoms` Haiku calls are metered against the cost gate. (#2371, #3329, contributed by @TheRealMrSystem)
+- `extract_atoms` stamps concepts so `synthesize_concepts` has material to work with. (#2123, #3308, contributed by @ChenyqThu)
+- `extract_facts` requires a live backing page, not just a non-NULL entity slug. (#2497, #3321, contributed by @javieraldape)
+- Multi-claim pages keep every proposal instead of only the first (migration v125 makes the idempotency key per claim). (#3297, contributed by @rp-agent-bot)
+- Superseding a take now queries the active row first. (#3275, contributed by @arisgysel-design)
+- Takes keyword search matches words inside long claims via `word_similarity`. (#3267)
+- Dream-generated orphan pages stay scoped to their source. (#2368, #3344, contributed by @snvtac)
+- Drift detection is wired into the dream cycle, report-only for now. (#2653, #3317)
+
+#### Autopilot, jobs, and serve
+
+- Full consolidation cycles get a 30-minute timeout floor; lighter dispatches keep the interval-derived budget. (#2852, #3338, contributed by @sanchalr)
+- The cron wrapper exports `~/.bun/bin` onto PATH so autopilot survives minimal environments. (#2013, #3305, contributed by @klampatech)
+- Dead or cancelled jobs no longer block idempotent re-submission. (#2253, #3306, contributed by @rafaelreis-r)
+- Contextual reindex jobs get a default timeout. (#2611, #3323, contributed by @spiky02plateau)
+- Onboarding stops repeating the same auto-remediation within a single run. (#2854, #3342, contributed by @sanchalr)
+- A wedged `gbrain serve` boot hits a readiness deadline and releases the PGLite lock. (#3335)
+
+#### Search, retrieval, and health
+
+- The recency-decay config is honored on the hybrid search path. (#2386, #3312, contributed by @rwbaker)
+- `list_pages` honors explicit limits for local callers, warns on remote clamping, and threads `offset`. (#2591, #3322, contributed by @deacon-botdoctor)
+- Truncated `list_pages` results say so instead of silently capping. (#2865, #3341, contributed by @paul-0320)
+- Negative metrics no longer invert trajectory regression signals. (#2621, #3324, contributed by @morluto)
+- Per-chunk synopsis generation in contextual retrieval is concurrency-bounded. (#2628, #3326, contributed by @spiky02plateau)
+- Graph health metrics count `entity` pages. (#2639, #3330, contributed by @tylr-r)
+
+#### Ingestion, extraction, and links
+
+- Conversation parsing gains an opt-in LLM fallback for unknown formats. (#2247, #3371, contributed by @danwiggins)
+- Normalized Slack markdown parses into conversations. (#3289, #3372, contributed by @danwiggins)
+- Conversation backfill outcomes are durable, so completed pages skip on the next run. (#3293, #3373, contributed by @danwiggins)
+- Reference-style wikilinks are recognized during extraction. (#2071, #3303, contributed by @mzkarami)
+- `[[wikilink]]` frontmatter values resolve via global basename lookup. (#2406, #3313, contributed by @spiky02plateau)
+- Incremental push syncs extract links. (#2850, #3337, contributed by @patentsong)
+- `<think>` reasoning tags in extractor output are handled. (#2559, #3318, contributed by @qaz8545355)
+- Tiktoken special tokens no longer crash code-chunker token estimates. (#2453, #3315, contributed by @Jiglet)
+- Source config stops re-wrapping into a growing JSON string scalar. (#2829, #3334, contributed by @1alessio)
+
+#### Providers and recipes
+
+- DashScope reranking recipe (DashScope serves a plural `/reranks` endpoint under its compatible API). (#2644, #3328, contributed by @YiconZiwei)
+- OpenRouter reranking touchpoint. (#2164, #3302, contributed by @Hippityy)
+- claude-cli recipe for native gateway-based subagent dispatch. (#2277, #3310, contributed by @brettdavies)
+- Prefixed model IDs work on the openai-compatible embedding-dimensions path. (#2325, #3309, contributed by @noetherly)
+- Embeddings stamp the gateway-resolved model in `content_chunks.model`, not the compiled default. (#2846, #3343, contributed by @SailorJoe6)
+- Bun-on-Windows write-through EEXIST fixed, non-Anthropic `--max-cost` pricing works, dream pages excluded from enrich. (#2407, #3316, contributed by @nguyenchiviet)
+- Supabase signed URLs prepend `/storage/v1`. (#2565, #3320, contributed by @danwiggins)
+
+#### Sources, auth, and multi-brain
+
+- Federated-source pages are visible to `get_page`, `list_pages`, `resolve_slugs`, and no-grant MCP callers. (#3242, #3301)
+- Admin-gated rescope surface for DCR clients stuck on a default scope. (#3299)
+- `whoami` exposes OAuth source grants. (#3279, #3332, contributed by @boundless-forest)
+- Thin-client `--source` maps onto `source_id` for remote-routed operations. (#3086)
+
+#### CLI, doctor, and init
+
+- `gbrain doctor` stops claiming "Brain is at target" when the target is unreachable. (#2151, #3339, contributed by @brettdavies)
+- Doctor gains a raw-source persistence guarantee for synthesized pages, warn-only for now. (#3300)
+- Doctor timeline labels disambiguate entity coverage from the brain-score component. (#2298, #3073, contributed by @TurgutKural)
+- Unknown `gbrain init` flags are rejected before migrations run. (#2201, #3307, contributed by @caioribeiroclw-pixel)
+- The init soul-audit hint points at the conversational skill, not a nonexistent CLI verb. (#2486, #3314, contributed by @SeanGearin)
+- `--force` retry escapes completed migration-ledger entries. (#2616, #3325, contributed by @spiky02plateau)
+- PGLite data-dir lock contention gets a clear error message. (#2658, #3336, contributed by @zaycruz)
+- Frontmatter validation derives slugs from the brain root, not the absolute path. (#2340, #3311, contributed by @alessioalionco)
+
+#### For contributors
+
+- Docker network isolation guidance for co-located self-hosted Postgres. (#3270, #3331)
+- `CLAUDE.local.md` / `AGENTS.local.md` are gitignored. (#3290, contributed by @igbymyboy)
+- The hybrid-reranker integration test isolates `GBRAIN_HOME`. (#1527, #3327, contributed by @Willisbest)
+- Test-shard scripts capture the real exit code before watchdog teardown in the no-timeout fallback. (#2864, #3340, contributed by @paul-0320)
+
+## [0.42.65.0] - 2026-07-23
+
+**A large maintenance release: 93 verified fixes and small features merged since v0.42.64.0, most of them community contributions.**
+
+If you use gbrain day to day, this release makes the boring parts trustworthy. Importing and syncing notes is safer: a failed pull no longer pretends everything is up to date, imported pages are read back after writing to confirm they landed, and a page with real content can no longer be silently overwritten by an empty one. Search answers get better inputs: the think command now picks excerpts that actually match your question, and results respect your federated source settings. Background enrichment (the "dream" cycle) wastes less money and retries properly when an AI provider is down. Spending caps now fail closed, so a billing hiccup can never turn into an uncapped spend. And `gbrain doctor` is quieter, with several false alarms removed and real problems (like an embedding backlog with no worker running) now flagged.
+
+More AI providers work out of the box, including OpenRouter prompt caching, MiniMax and Zhipu GLM recipes, Ollama Matryoshka embedding dimensions, and llama-server batch limits.
+
+## To take advantage of v0.42.65.0
+
+`gbrain upgrade` should do this automatically. No new schema migrations ship in this release.
+
+1. **Upgrade and verify:**
+   ```bash
+   gbrain upgrade
+   gbrain doctor
+   gbrain stats
+   ```
+2. **If `gbrain doctor` reports new findings after upgrading,** that is the quieter, more accurate check set working as intended. Each finding names its fix.
+3. **If any step fails,** please file an issue at https://github.com/garrytan/gbrain/issues with the output of `gbrain doctor` and `~/.gbrain/upgrade-errors.jsonl` if it exists.
+
+### Itemized changes
+
+#### Security
+
+- MCP source scoping for remote callers got a hardening pass, so agent-facing connections stay confined to the sources they were granted. (#2881, contributed by @spinsirr)
+- Paid MCP spend accounting is now atomic and fails closed, and resolver spend is recorded before a cap error is raised, so caps cannot be raced past or undercounted. (#3203, #3204, contributed by @caterpillarC15)
+- The OAuth token endpoint rate limit on the HTTP server is now configurable via env for deployments behind shared IPs. (#3114, contributed by @time-attack)
+- `WWW-Authenticate` responses now carry `resource_metadata` per the MCP spec and RFC 9728, so conforming clients can discover the auth server. (#1410, contributed by @rayers)
+
+#### Search, retrieval, and think
+
+- `think` selects query-relevant excerpts instead of generic ones. (#3197, contributed by @Y0lan)
+- Unqualified local CLI `search`/`query` now honors `sources.config.federated` read visibility. (#2561, #3141, contributed by @time-attack)
+- Email citation metadata is projected into search results. (#2873, contributed by @amtagrwl)
+- The `think` Gaps section renders once instead of twice. (#1662, contributed by @howwohmm)
+- Fuzzy entity lookup threads the caller's source scope and skips soft-deleted entities. (#1508, contributed by @tim404x)
+- `code-def` surfaces method, constructor, field, and struct definitions, not just top-level symbols. (#1628, contributed by @rayers)
+- Briefing pages are excluded from their own Brain Pulse salience. (#1202, contributed by @rwbaker)
+- Reranker calls with missing auth are classified as configuration errors before falling back. (#2059, #3139, contributed by @time-attack)
+
+#### Import, sync, and ingestion
+
+- A failed git pull with zero imports reports `partial (pull_failed)` instead of `up_to_date`. (#3068, #3253, contributed by @Masashi-Ono0611)
+- Imports run a post-write read-back verification with a durable ingest-log record. (#2869, contributed by @Andredsouza1984)
+- `put` refuses to overwrite a non-empty page with empty content. (#2708, contributed by @symmetric-matthew)
+- `putPage` restores soft-deleted rows instead of colliding with them. (#2779, contributed by @RerankerGuo)
+- Mixed-case slugs are normalized before chunk upsert, ending duplicate-chunk churn. (#430, #3143, contributed by @time-attack)
+- Imports fall back to the body H1 for the title when frontmatter lacks `title:`. (#2446, #3072, contributed by @time-attack)
+- YAML comments inside the frontmatter fence are no longer treated as markdown headings. (#3225, #3247, contributed by @Masashi-Ono0611)
+- Write-through guards case-insensitive filesystem collisions before the atomic write. (#2831, #3119, contributed by @time-attack)
+- Path-qualified wikilinks outside the known directory pattern resolve on the DB/put_page path. (#2866, contributed by @paul-0320)
+- CJK slugs are supported in the slug registry and dream-cycle summary slugs. (#782, #738, #3083, contributed by @time-attack)
+- Three ingest/sync/serve singleton fixes: page-type round-trip, deleted-slug embed noise, and a stateless width guard. (#3140, contributed by @time-attack)
+- Sync honors the `embedding_disabled` sentinel as an implicit `--no-embed`. (#2879, contributed by @gawievanblerk)
+- Verified sync head sentinels are cleared correctly. (#2734, contributed by @symmetric-matthew)
+- Resumed syncs report the pinned commit they actually landed on. (#3202, contributed by @caterpillarC15)
+- The expected `discover_git_root` probe failure stays off stderr. (#3232, contributed by @Masashi-Ono0611)
+- `extract --stale` runs the real resolver so basename resolution reaches stale pages, and clears pre-version-bump pages. (#2576, #2717, contributed by @paul-0320; #1791, contributed by @Nazim22)
+- Oversized code chunks are capped so they stay embeddable, and code-chunk metadata survives re-embeds. (#1675, contributed by @lubosxyz; #769, #1232, contributed by @rayers)
+
+#### Background cycle, dream, and facts
+
+- Path-derived dream sources are stamped, and the engine closes cleanly on autopilot shutdown. (#3178, contributed by @time-attack)
+- All-provider-failed atom drains propagate so durable jobs retry instead of silently dropping work. (#3218, #3248, contributed by @Masashi-Ono0611)
+- Atom extraction raises `maxTokens` and case-normalizes `atom_type` for Gemini models. (#3211, contributed by @alexey-metaengage)
+- The conversation extractor gates anonymous-speaker self-attribution instead of guessing. (#3228, contributed by @asenkovskiy)
+- Incremental dream extraction stamps its watermark so re-runs stop reprocessing. (#2636, #3115, contributed by @time-attack)
+- `dream --dry-run --json` keeps stdout clean of embed summaries. (#394, #3109, contributed by @time-attack)
+- Synthesized dream pages require a self-contained opening summary. (#2770, contributed by @Masashi-Ono0611)
+- PGLite inline synth subagent drains complete, and `lint` gains `--exclude`. (#2699, #2649, #3162, contributed by @time-attack)
+- Live context reads the documented "P1 Today" heading form with plain checkbox tasks, matching the daily-task-manager skill's output format. (#2186, #3124, contributed by @time-attack)
+- Queued AI jobs refresh gateway config at execution time instead of using a stale snapshot. (#2125, contributed by @maxpetrusenkoagent)
+- `brainstorm`/`propose_takes` honor configured models: cost preview uses the configured model, the judge reads its config key, provider probes are skipped when unneeded, and page projection is narrowed. (#3120, contributed by @time-attack)
+- Backlog hardening wave: x-to-brain health check, propose_takes deadlines, capture title truncation, extract_atoms backlog handling, and pooler direct-URL routing. (#3165, contributed by @time-attack)
+- `skillopt` emits `proposed.md` in no-mutate mode. (#2635, #3182, contributed by @time-attack)
+- Nightly quality probe enable path and conversation-parser probe are wired up. (#2629, #2630, #3094, contributed by @time-attack)
+
+#### Doctor, health, and maintenance
+
+- New safe maintenance automation with a shared orphan-exclusion policy, so routine cleanup runs without risking linked content. (#3015, #3023, contributed by @time-attack)
+- `orphan_ratio` excludes the chronicle volume under `life/events/`. (#2264, #3214, contributed by @asenkovskiy)
+- `brain_score` orphan/timeline components use the orphans-audit linkable scope. (#3155, contributed by @time-attack)
+- Entity timeline coverage is measured separately from whole-brain density. (#2761, contributed by @TurgutKural)
+- Doctor flags embed backfills queued with no worker running. (#2696, contributed by @javieraldape)
+- Two doctor false-positive/timeout fixes: the drift walk skips `node_modules`, and the bare-tweet check skips inline code and cited lines. (#1772, contributed by @sonlndv)
+- A dead `llm_fallback_enabled` recommendation is dropped from conversation format coverage. (#1903, contributed by @ElliotDrel)
+- Skill triggers with CRLF line endings parse on Windows. (#1149, contributed by @samporter-31)
+- Onboard check names are registered in doctor categories, ending unknown-check warnings, and onboard-check remediations survive the `--apply --auto` path. (#3075, #3097, contributed by @time-attack)
+- Dead slug prefixes are counted by slug. (#2697, contributed by @RerankerGuo)
+- The backlinks worker defaults to check, not fix, and `check-backlinks` honors its positional directory argument. (#1853, contributed by @choomz; #3076, contributed by @time-attack)
+- Calibration resolves the owner holder via config, defaulting to `self`. (#3077, contributed by @time-attack)
+- Memory throttling on Linux reads `/proc/meminfo` MemAvailable. (#556, contributed by @chengzehsu)
+
+#### AI providers and gateway
+
+- OpenRouter gets family-scoped prompt caching, and query expansion works on chat-capable openai-compat recipes. (#3152, contributed by @time-attack)
+- MiniMax recipe: embedding wire-shape compat fetch plus a chat touchpoint. (#1977, #3089, contributed by @time-attack)
+- The Zhipu recipe gains a chat touchpoint so GLM subagents work. (#1157, #3084, contributed by @time-attack)
+- Tier-configured models reach the recipe allowlist, Anthropic model lists are refreshed, tier resolutions are registered, and probe labels are honest. (#2800, contributed by @p3ob7o)
+- Provider base URL config merges from the DB. (#1676, contributed by @TheLordArgus)
+- The gateway falls back to the pooler when the derived direct host is unreachable. (#1641, #3088, contributed by @time-attack)
+- Config-plane `voyage_api_key` folds into `VOYAGE_API_KEY` like the other hosted keys. (#3236, contributed by @Masashi-Ono0611)
+- The `zeroentropyai:zerank-2` reranker has a pricing entry so the budget tracker can meter it. (#3223, #3233, contributed by @Masashi-Ono0611)
+- llama-server embedding batches are capped at its 32-input request limit. (#1281, contributed by @mmekkaoui)
+- Matryoshka dimensions thread through for Qwen3-Embedding on Ollama. (#1072, contributed by @mgandal)
+- `init` seeds AI options from env on cold install, and `whoami` reports the stdio transport. (#3091, contributed by @time-attack)
+- The `models` dispatch subcommand reads its first argument correctly. (#1428, contributed by @BenjaminDSmithy)
+- Synopsis generation tail-truncates document text for small-model chat handlers. (#1427, contributed by @BenjaminDSmithy)
+- The contradiction judge token cap is raised for thinking models. (#3210, contributed by @alexey-metaengage)
+
+#### Schema, migrations, and storage engines
+
+- Engine migration counts and surfaces per-page copy failures instead of silently advancing. (#3241, contributed by @Masashi-Ono0611)
+- Invalid `CONCURRENTLY`-build index remnants are dropped without a DO block. (#3191, contributed by @Masashi-Ono0611)
+- Unsupported large-dimension HNSW indexes are skipped instead of failing schema setup. (#1734, #3080, contributed by @time-attack)
+- The v0.32.2 migration dirty-check scopes to targeted sources and surfaces failed phase detail. (#3093, contributed by @time-attack)
+- Schema packs merge the full `extends` chain and `borrow_from` into the resolved manifest. (#1749, #3181, contributed by @time-attack)
+- The schema-pack stats catch-all is narrowed so masked errors surface instead of fake zero-page counts. (#2466, #3133, contributed by @time-attack)
+- Bundled schema-pack inspection reports the pack actually shipped in the binary, and minion subagent auth resolves through config. (#3110, contributed by @time-attack)
+- PGLite `putPage` guards against zero-row RETURNING. (#1649, contributed by @alexhawkins)
+
+#### MCP server and CLI surface
+
+- `list_pages` rows include `source_id`. (#3209, contributed by @alexey-metaengage)
+- Running CLI commands while `gbrain serve` (MCP) holds the brain now notifies about the conflict instead of failing confusingly. (#3243, contributed by @fdefitte)
+- The OpenClaw plugin manifest entry is declared so the plugin loads. (#2551, #3185, contributed by @time-attack)
+
+#### For contributors
+
+- CI scanner roots are normalized on macOS. (#3198, contributed by @caterpillarC15)
+- CI shard timeout raised to 22 minutes plus a delta-assert reporter leak test. (#3231, contributed by @time-attack)
+- E2E suite hardening: flaky tests, no-op assertions, and cross-test coupling removed. (#1704, contributed by @auroracapital)
+- `mechanical.test.ts` isolates `$HOME` so the E2E suite stops clobbering user config. (#434, contributed by @lloydarmbrust)
+- The lint code-fence-wrap detector and fixer regex now agree. (#1597, contributed by @chungty)
+- README project links for OpenClaw and Hermes are corrected. (#1961, #3179, contributed by @time-attack)
+- A completed TODOS entry is dropped. (#3229, contributed by @Masashi-Ono0611)
+
 ## [0.42.64.0] - 2026-07-20
 
 ### Fixed

CONTRIBUTING.md

@@ -11,6 +11,28 @@ bun test
 
 Requires Bun 1.0+.
 
+### Windows
+
+`bun run test`, `verify`, `ci:local` and `test:e2e` all dispatch through bash, so
+the shell scripts under `scripts/` must be checked out with Unix line endings.
+The root `.gitattributes` pins `*.sh text eol=lf`, which overrides the
+`core.autocrlf=true` that Git for Windows installs by default. A fresh clone is
+correct with no extra steps.
+
+If you cloned before that pin existed, your working copy still has the old
+Windows line endings and bash will fail with `$'\r': command not found`. Refresh
+it once, from the repository root:
+
+```bash
+git rm --cached -r . -q
+git reset --hard
+bash -n scripts/run-unit-parallel.sh   # silence means bash can read the scripts
+```
+
+Every `check:*` entry in `package.json` invokes its script as `bash scripts/<name>.sh`
+rather than relying on the shebang, because bun on Windows cannot exec a `.sh`
+directly. Keep that prefix when you add a new shell-script check.
+
 ## Project structure
 
 ```
@@ -163,6 +185,14 @@ host port with `GBRAIN_CI_PG_PORT=5435 bun run ci:local` if 5434 collides.
 Fail-closed selector: an unmapped `src/` change runs all 29 E2E files. Hand-tune
 narrower mappings via `scripts/e2e-test-map.ts`.
 
+### PR-side security checks
+
+Besides the test gate, PRs may trigger three security workflows: Semgrep CE
+SAST (every PR — **advisory/non-blocking** while the baseline is tuned, so a
+Semgrep finding won't fail your PR), OSV-Scanner (only when `package.json` or
+`bun.lock` change), and actionlint (only when `.github/workflows/**` change).
+See `SECURITY.md` → "Automated security scanning" for details.
+
 ## Building
 
 ```bash

SECURITY.md

@@ -8,6 +8,30 @@ on GitHub.
 
 Do not open a public issue for security vulnerabilities.
 
+## Automated security scanning
+
+CI runs three automated security checks alongside secret scanning (Gitleaks):
+
+- **Dependency vulnerabilities** — OSV-Scanner
+  (`.github/workflows/osv-scanner.yml`) runs weekly and on any PR that touches
+  `package.json` or `bun.lock`.
+- **Static analysis (SAST)** — Semgrep CE (`.github/workflows/semgrep.yml`)
+  runs on every PR and weekly. It is currently **advisory (non-blocking)**
+  while the finding baseline is tuned; the graduation path to a blocking check
+  is documented in the workflow file.
+- **Release binary provenance** — release builds
+  (`.github/workflows/release.yml`) attest each compiled binary with
+  [GitHub artifact attestations](https://docs.github.com/en/actions/security-for-github-actions/using-artifact-attestations).
+  Verify a downloaded release binary with:
+
+  ```bash
+  gh attestation verify ./gbrain-darwin-arm64 -R garrytan/gbrain
+  gh attestation verify ./gbrain-linux-x64 -R garrytan/gbrain
+  ```
+
+All security workflows use SHA-pinned actions and least-privilege permissions,
+enforced structurally by actionlint on every workflow change.
+
 ## Remote MCP Security
 
 ### ⚠️ Do NOT use open OAuth client registration for remote MCP
@@ -135,6 +159,18 @@ the PGLite schema. Local agents continue to use stdio (`gbrain serve`).
 Running `--http` against a PGLite-backed install fails fast with a clear
 error message at startup.
 
+### Docker network isolation (self-hosted Postgres)
+
+OAuth and source scoping enforce isolation on the `serve --http` path only.
+Raw Postgres reachability bypasses both: a container that shares Docker's
+default `bridge` network with the brain's Postgres can open a direct DB
+session without any token and read every source. Put the brain's Postgres on
+a user-defined Docker network with nothing untrusted on it, publish its port
+loopback-only (if at all), and never put `DATABASE_URL` or a Postgres
+password in untrusted agent containers — those should reach the brain
+exclusively via OAuth against `serve --http`. Full operator checklist:
+[docs/mcp/DEPLOY.md — Co-located Docker workloads](docs/mcp/DEPLOY.md#co-located-docker-workloads-self-hosted-postgres).
+
 ### CORS
 
 Default-deny: no `Access-Control-Allow-Origin` header is sent unless an

TODOS.md

@@ -1,10 +1,31 @@
 # TODOS
 
+## v0.42.67.0 follow-ups (Windows build tooling)
+
+Filed as follow-ups from v0.42.67.0 (`.gitattributes` LF pin for `*.sh` +
+`bash` prefix on the 33 `package.json` check commands). Both items are newly
+observable: before that release these checks never executed on Windows at all,
+so nothing about their runtime was measurable.
+
+- [ ] **P2 — three guard scripts exceed the 120s `run-verify-parallel.sh` cap on Windows.**
+  With the dispatch fixed, `bun run verify` on Windows gets 25 passes and 7 failures, and
+  `check:privacy`, `check:test-names` and `check:test-isolation` are timeouts rather than
+  real failures (they pass on Linux and macOS well inside the cap). They walk the tree with
+  per-file shell loops, which is far slower under Windows process creation. Either raise the
+  cap for these three, or replace the per-file loop with a single `grep -r` pass. Same cap
+  swallows `typecheck`, though standalone `bun run typecheck` exits 0.
+- [ ] **P3 — `check:wasm` cannot create its `node_modules` symlink on Windows.**
+  `scripts/check-wasm-embedded.sh` fails with `ln: failed to create symbolic link
+  '/tmp/gbrain-wasm-check.XXXX/node_modules': No such file or directory`. Unprivileged
+  Windows accounts cannot create symlinks without developer mode. Consider a junction, a
+  copy, or skipping the check with a clear message when symlink creation is unavailable.
+
 ## community fix-wave follow-ups (filed v0.42.60.0)
 
-- [ ] **P2 — cherry-pick #2112's uncovered doctor.ts hunk.** Fix-wave A (#2820) superseded
+- [x] **P2 — cherry-pick #2112's uncovered doctor.ts hunk.** Fix-wave A (#2820) superseded
   most of #2112 but not its `checkSubagentCapability` fix (check explicit `models.subagent`
-  before `models.tier.subagent`). Refile or cherry-pick; the rest of that PR is covered.
+  before `models.tier.subagent`). Implemented: `checkSubagentCapability` now resolves
+  `models.subagent` before tier/default fallbacks and has regression coverage.
 
 ## v0.42.59.0 follow-ups (five-fix rollup #2735–#2739)
 
@@ -61,17 +82,20 @@ Deferred from the provider-agnostic plumbing wave (#1249/#1250/#1292/#2271/#2209
 Plan + review trail at `~/.claude/plans/system-instruction-you-are-working-keen-newell.md`.
 The eng-review + Codex outside-voice narrowed the wave to these deferrals:
 
-- [ ] **P2 — Capability-aware query expansion on OpenAI-compat providers (#2372).**
+- [x] **P2 — Capability-aware query expansion on OpenAI-compat providers (#2372).**
   Expansion only runs for recipes that declare an `expansion` touchpoint, and only the
   native providers (anthropic/openai/google) do. To make expansion work on
   litellm/openrouter/groq/together/deepseek you must ADD expansion touchpoints to those
   chat-capable recipes AND add a `generateObject`→`generateText` capability fallback for
   backends without strict structured outputs. Feature-shaped; overlaps the general
   OpenAI-compat proxy story (`docs/designs/COMMUNITY_IDEAS.md`). Community PR #2373 is a
-  starting point. Where: `src/core/ai/gateway.ts:expand`, recipe files, `types.ts` (ExpansionTouchpoint).
-- [ ] **P2 — LiteLLM as a chat/expansion backend.** `litellm-proxy` declares ONLY an
+  starting point. Implemented by #2373 plus the DeepSeek/Groq/Together recipe wave,
+  LiteLLM chat/expansion support, and the OpenRouter expansion touchpoint. Where:
+  `src/core/ai/gateway.ts:expand`, recipe files, `types.ts` (ExpansionTouchpoint).
+- [x] **P2 — LiteLLM as a chat/expansion backend.** `litellm-proxy` declares ONLY an
   embedding touchpoint, so `think`/chat on LiteLLM is dead. Add chat (and expansion) so a
-  LiteLLM proxy is a full LLM backend, not embedding-only. The general OpenAI-compat proxy story.
+  LiteLLM proxy is a full LLM backend, not embedding-only. Implemented by #2208.
+  The general OpenAI-compat proxy story.
 - [ ] **P3 — Per-model embedding dims metadata on `EmbeddingTouchpoint`.** `default_dims`
   is recipe-wide, so a recipe (ollama) can't carry different native dims per model. This
   wave added the modern ollama model NAMES + a `trust_custom_dims` passthrough (user supplies

VERSION

@@ -1 +1 @@
-0.42.64.0
+0.42.67.0

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-CoGEje3-.js"></script>
+  <script type="module" crossorigin src="/admin/assets/index-CviJXT-1.js"></script>
   <link rel="stylesheet" crossorigin href="/admin/assets/index-GxkWX7v3.css">
 </head>
 <body>

admin/src/api.ts

@@ -39,11 +39,21 @@ export const api = {
   stats: () => apiFetch('/admin/api/stats'),
   health: () => apiFetch('/admin/api/health-indicators'),
   agents: () => apiFetch('/admin/api/agents'),
+  sources: () => apiFetch('/admin/api/sources'),
   requests: (page = 1, qs = '') => apiFetch(`/admin/api/requests?page=${page}${qs}`),
   apiKeys: () => apiFetch('/admin/api/api-keys'),
-  createApiKey: (name: string) => apiFetch('/admin/api/api-keys', { method: 'POST', body: JSON.stringify({ name }) }),
-  revokeApiKey: (name: string) => apiFetch('/admin/api/api-keys/revoke', { method: 'POST', body: JSON.stringify({ name }) }),
+  createApiKey(keyName: string) {
+    return apiFetch('/admin/api/api-keys', { method: 'POST', body: JSON.stringify({ name: keyName }) });
+  },
+  revokeApiKey(keyName: string) {
+    return apiFetch('/admin/api/api-keys/revoke', { method: 'POST', body: JSON.stringify({ name: keyName }) });
+  },
   updateClientTtl: (clientId: string, tokenTtl: number | null) => apiFetch('/admin/api/update-client-ttl', { method: 'POST', body: JSON.stringify({ clientId, tokenTtl }) }),
+  rescopeClient: (clientId: string, sourceId: string, federatedRead: string[]) =>
+    apiFetch('/admin/api/rescope-client', {
+      method: 'POST',
+      body: JSON.stringify({ clientId, sourceId, federatedRead }),
+    }),
   revokeClient: (clientId: string) => apiFetch('/admin/api/revoke-client', { method: 'POST', body: JSON.stringify({ clientId }) }),
   // v0.36.1.0 (T15 / E6) — calibration endpoints.
   calibrationProfile: (holder?: string) =>

admin/src/pages/Agents.tsx

@@ -18,6 +18,8 @@ interface Agent {
   client_name?: string; // compat
   grant_types: string[];
   scope: string;
+  source_id: string | null;
+  federated_read: string[];
   created_at: string;
   last_used_at: string | null;
   total_requests: number;
@@ -26,6 +28,12 @@ interface Agent {
   status: 'active' | 'revoked';
 }
 
+interface Source {
+  id: string;
+  name: string;
+  federated: boolean;
+}
+
 interface ApiKey {
   id: string;
   name: string;
@@ -36,6 +44,7 @@ interface ApiKey {
 
 export function AgentsPage() {
   const [agents, setAgents] = useState<Agent[]>([]);
+  const [sources, setSources] = useState<Source[]>([]);
   const [hideRevoked, setHideRevoked] = useState(true);
   const [showRegister, setShowRegister] = useState(false);
   const [showCredentials, setShowCredentials] = useState<{ clientId: string; clientSecret: string; name: string } | null>(null);
@@ -43,7 +52,10 @@ export function AgentsPage() {
   const [showApiKeyToken, setShowApiKeyToken] = useState<{ name: string; token: string } | null>(null);
   const [selectedAgent, setSelectedAgent] = useState<Agent | null>(null);
 
-  useEffect(() => { loadAgents(); }, []);
+  useEffect(() => {
+    loadAgents();
+    api.sources().then(setSources).catch(() => {});
+  }, []);
 
   const loadAgents = () => { api.agents().then(setAgents).catch(() => {}); };
 
@@ -88,6 +100,7 @@ export function AgentsPage() {
                 <th>Name</th>
                 <th>Type</th>
                 <th>Scopes</th>
+                <th>Sources</th>
                 <th>Status</th>
                 <th>Requests</th>
                 <th>Last Used</th>
@@ -108,6 +121,11 @@ export function AgentsPage() {
                       <span key={s} className={`badge badge-${s}`} style={{ marginRight: 4 }}>{s}</span>
                     ))}
                   </td>
+                  <td style={{ color: 'var(--text-secondary)', fontSize: 12 }}>
+                    {a.auth_type === 'oauth'
+                      ? `${a.source_id || 'none'} · ${(a.federated_read || []).length} readable`
+                      : 'Unscoped'}
+                  </td>
                   <td>
                     <span className={`badge ${a.status === 'active' ? 'badge-success' : 'badge-danger'}`}>{a.status}</span>
                   </td>
@@ -144,7 +162,21 @@ export function AgentsPage() {
       )}
 
       {selectedAgent && (
-        <AgentDrawer agent={selectedAgent} onClose={() => setSelectedAgent(null)} onRevoked={loadAgents} />
+        <AgentDrawer
+          key={selectedAgent.id}
+          agent={selectedAgent}
+          sources={sources}
+          onClose={() => setSelectedAgent(null)}
+          onRevoked={loadAgents}
+          onRescoped={({ sourceId, federatedRead }) => {
+            setSelectedAgent(current => current ? {
+              ...current,
+              source_id: sourceId,
+              federated_read: federatedRead,
+            } : current);
+            loadAgents();
+          }}
+        />
       )}
 
       {showApiKeyCreate && (
@@ -381,7 +413,127 @@ function CredentialsModal({ credentials, onClose }: {
   );
 }
 
-function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: () => void; onRevoked: () => void }) {
+function SourceAccessEditor({ clientId, agent, sources, onRescoped }: {
+  clientId: string;
+  agent: Agent;
+  sources: Source[];
+  onRescoped: (scope: { sourceId: string; federatedRead: string[] }) => void;
+}) {
+  const [writeSource, setWriteSource] = useState(agent.source_id || 'default');
+  const [readSources, setReadSources] = useState<string[]>(agent.federated_read || []);
+  const [saving, setSaving] = useState(false);
+  const [error, setError] = useState('');
+  const [saved, setSaved] = useState(false);
+  const readableSet = new Set(readSources);
+  const activeSourceIds = new Set(sources.map(source => source.id));
+  const unavailableReadSources = readSources.filter(sourceId => !activeSourceIds.has(sourceId));
+  const primaryUnavailable = !activeSourceIds.has(writeSource);
+
+  const save = async () => {
+    if (readSources.length === 0) {
+      setError('Select at least one readable source.');
+      return;
+    }
+    setSaving(true);
+    setError('');
+    setSaved(false);
+    try {
+      const result = await api.rescopeClient(clientId, writeSource, readSources) as {
+        sourceId: string;
+        federatedRead: string[];
+      };
+      setWriteSource(result.sourceId);
+      setReadSources(result.federatedRead);
+      setSaved(true);
+      onRescoped(result);
+    } catch (e) {
+      setError(e instanceof Error ? e.message : 'Failed to save source access');
+    } finally {
+      setSaving(false);
+    }
+  };
+
+  return (
+    <>
+      <div className="section-title">Source Access</div>
+      <div style={{ color: 'var(--text-secondary)', fontSize: 12, lineHeight: 1.5, marginBottom: 12 }}>
+        The primary source is the write destination. Read access is an explicit allowlist and does not widen automatically.
+      </div>
+      <div style={{ marginBottom: 14 }}>
+        <label htmlFor="agent-write-source">Primary / write source</label>
+        <select
+          id="agent-write-source"
+          value={writeSource}
+          onChange={e => { setWriteSource(e.target.value); setSaved(false); }}
+          style={{ width: '100%', background: 'var(--bg-secondary)', color: 'var(--text-primary)', border: '1px solid var(--border)', borderRadius: 6, padding: '6px 10px', fontSize: 14 }}
+        >
+          {primaryUnavailable && (
+            <option value={writeSource} disabled>{writeSource} · unavailable</option>
+          )}
+          {sources.map(source => (
+            <option key={source.id} value={source.id}>{source.name} ({source.id})</option>
+          ))}
+        </select>
+      </div>
+      <fieldset style={{ border: 0, padding: 0, margin: '0 0 14px' }}>
+        <legend>Readable sources</legend>
+        <div className="checkbox-group" style={{ marginTop: 6 }}>
+          {sources.map(source => (
+            <label key={source.id} className="checkbox-label">
+              <input
+                type="checkbox"
+                checked={readableSet.has(source.id)}
+                onChange={e => {
+                  setSaved(false);
+                  setReadSources(current => e.target.checked
+                    ? [...current, source.id]
+                    : current.filter(id => id !== source.id));
+                }}
+              />
+              {source.name} ({source.id}){source.federated ? ' · federated' : ' · private'}
+            </label>
+          ))}
+          {unavailableReadSources.map(sourceId => (
+            <label key={sourceId} className="checkbox-label" style={{ color: 'var(--warning)' }}>
+              <input
+                type="checkbox"
+                checked
+                onChange={() => {
+                  setSaved(false);
+                  setReadSources(current => current.filter(id => id !== sourceId));
+                }}
+              />
+              {sourceId} · unavailable (clear to remove grant)
+            </label>
+          ))}
+        </div>
+      </fieldset>
+      {(primaryUnavailable || unavailableReadSources.length > 0) && (
+        <div style={{ color: 'var(--warning)', fontSize: 13, marginBottom: 10 }}>
+          This client references unavailable or archived sources. Choose an active primary source and clear unavailable read grants before saving.
+        </div>
+      )}
+      {error && <div style={{ color: 'var(--error)', fontSize: 13, marginBottom: 10 }}>{error}</div>}
+      {saved && <div style={{ color: 'var(--success)', fontSize: 13, marginBottom: 10 }}>Source access saved.</div>}
+      <button
+        type="button"
+        className="btn btn-primary"
+        disabled={saving || readSources.length === 0 || sources.length === 0 || primaryUnavailable || unavailableReadSources.length > 0}
+        onClick={save}
+      >
+        {saving ? 'Saving...' : 'Save Source Access'}
+      </button>
+    </>
+  );
+}
+
+function AgentDrawer({ agent, sources, onClose, onRevoked, onRescoped }: {
+  agent: Agent;
+  sources: Source[];
+  onClose: () => void;
+  onRevoked: () => void;
+  onRescoped: (scope: { sourceId: string; federatedRead: string[] }) => void;
+}) {
   const [tab, setTab] = useState<'claude-code' | 'chatgpt' | 'claude-cowork' | 'perplexity' | 'cursor' | 'json'>('claude-code');
   const copy = (text: string) => navigator.clipboard.writeText(text);
   const serverUrl = window.location.origin;
@@ -553,6 +705,15 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
           <span>{agent.token_ttl ? (agent.token_ttl >= 31536000 ? 'No expiry' : agent.token_ttl >= 86400 ? `${Math.floor(agent.token_ttl / 86400)}d` : agent.token_ttl >= 3600 ? `${Math.floor(agent.token_ttl / 3600)}h` : `${agent.token_ttl}s`) : '1h (default)'}</span>
         </div>
 
+        {isOAuth && (
+          <SourceAccessEditor
+            clientId={cid}
+            agent={agent}
+            sources={sources}
+            onRescoped={onRescoped}
+          />
+        )}
+
         {/*
           Config Export visible for both auth_type=oauth AND auth_type=api_key.
           Claude Code + Cursor + JSON tabs render real snippets regardless
@@ -579,7 +740,11 @@ function AgentDrawer({ agent, onClose, onRevoked }: { agent: Agent; onClose: ()
         {(() => {
           const oauthOnlyTabs = new Set(['chatgpt', 'claude-cowork', 'perplexity']);
           if (!isOAuth && oauthOnlyTabs.has(tab)) {
-            const clientName = { chatgpt: 'ChatGPT', 'claude-cowork': 'Claude.ai', perplexity: 'Perplexity' }[tab] || tab;
+            const clientName = tab === 'chatgpt'
+              ? 'ChatGPT'
+              : tab === 'claude-cowork'
+                ? 'Claude.ai'
+                : 'Perplexity';
             return (
               <div style={{
                 background: 'rgba(255, 200, 100, 0.08)',

bun.lock

@@ -51,8 +51,9 @@
     "@electric-sql/pglite",
   ],
   "overrides": {
-    "@hono/node-server": "^1.19.13",
-    "fast-uri": "^3.1.2",
+    "@hono/node-server": "^2.0.5",
+    "body-parser": "^2.3.0",
+    "fast-uri": "^3.1.4",
     "fast-xml-builder": "^1.1.7",
     "fast-xml-parser": "^5.7.0",
     "form-data": "^4.0.6",
@@ -162,7 +163,7 @@
 
     "@electric-sql/pglite": ["@electric-sql/pglite@0.4.3", "", {}, "sha512-ichuWTgtd4mOM1G4SpyGJa5trT03lWbMypDV0fUXUCXg5hiHqVAz/bZyV68NqmkLB7WcYmj1RMJVSp8HV/v/ZQ=="],
 
-    "@hono/node-server": ["@hono/node-server@1.19.14", "", { "peerDependencies": { "hono": "^4" } }, "sha512-GwtvgtXxnWsucXvbQXkRgqksiH2Qed37H9xHZocE5sA3N8O8O8/8FA3uclQXxXVzc9XBZuEOMK7+r02FmSpHtw=="],
+    "@hono/node-server": ["@hono/node-server@2.0.11", "", { "peerDependencies": { "hono": "^4" } }, "sha512-bjD221KPLoJTWUwso1J6fGKiTXEUFedG/s0visavY4zakFPkeGURMRNly+FhBHs7T8Dz4qHaZIMX9ZoJHSJtKA=="],
 
     "@jsquash/avif": ["@jsquash/avif@2.1.1", "", { "dependencies": { "wasm-feature-detect": "^1.2.11" } }, "sha512-LMRxd0fMgfCLtobDh0/sFYJMMiRJTNYSEEWvRDKXlAeZ08t3gI5V+1thIT0XjXJ+SVG7Zug9B0XPyx0Ti5VRNA=="],
 
@@ -326,7 +327,7 @@
 
     "asynckit": ["asynckit@0.4.0", "", {}, "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="],
 
-    "body-parser": ["body-parser@2.2.2", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.1", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-oP5VkATKlNwcgvxi0vM0p/D3n2C3EReYVX+DNYs5TjZFn/oQt2j+4sVJtSMr18pdRr8wjTcBl6LoV+FUwzPmNA=="],
+    "body-parser": ["body-parser@2.3.0", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^2.0.0", "debug": "^4.4.3", "http-errors": "^2.0.1", "iconv-lite": "^0.7.2", "on-finished": "^2.4.1", "qs": "^6.15.2", "raw-body": "^3.0.2", "type-is": "^2.1.0" } }, "sha512-2cGmJupaNgg+QUwVLAucDuWuoMZ6EX9iHDRswZ5lsNYEmwPaRknMPCLZz07yTzVq/83p4o/wzbDZbBrTvGGTIw=="],
 
     "bowser": ["bowser@2.14.1", "", {}, "sha512-tzPjzCxygAKWFOJP011oxFHs57HzIhOEracIgAePE4pqB3LikALKnSzUyU4MGs9/iCEUuHlAJTjTc5M+u7YEGg=="],
 
@@ -400,7 +401,7 @@
 
     "fast-deep-equal": ["fast-deep-equal@3.1.3", "", {}, "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q=="],
 
-    "fast-uri": ["fast-uri@3.1.3", "", {}, "sha512-i70LwGWUduXqzicKXWshooq+sWL1K3WUU5rKZNG/0i3a1OSoX3HqhH5WbWwTmqWfor4urUakGPiRQcleRZTwOg=="],
+    "fast-uri": ["fast-uri@3.1.4", "", {}, "sha512-8JnbkQ4juDyvYs4mgFGQqg4yCYtFDtUtmp2QIQq11ZZe5CFQ5wcqm1rqDgAh/QdMySuBnPzMUiJUNZG5N/AiQw=="],
 
     "fast-xml-builder": ["fast-xml-builder@1.3.0", "", { "dependencies": { "path-expression-matcher": "^1.6.2", "xml-naming": "^0.3.0" } }, "sha512-F74cZEdCvuw9P41GAC3rod4X04jjWGM1JPEv/GWSqFTWLsdyMSBMBMlm9Hk3GLBgLBbdBNY8yee0pQh2RBVESQ=="],
 
@@ -614,6 +615,10 @@
 
     "@types/bun/bun-types": ["bun-types@1.3.11", "", { "dependencies": { "@types/node": "*" } }, "sha512-1KGPpoxQWl9f6wcZh57LvrPIInQMn2TQ7jsgxqpRzg+l0QPOFvJVH7HmvHo/AiPgwXy+/Thf6Ov3EdVn1vOabg=="],
 
+    "body-parser/content-type": ["content-type@2.0.0", "", {}, "sha512-j/O/d7GcZCyNl7/hwZAb606rzqkyvaDctLmckbxLzHvFBzTJHuGEdodATcP3yIRoDrLHkIATJuvzbFlp/ki2cQ=="],
+
+    "body-parser/type-is": ["type-is@2.1.0", "", { "dependencies": { "content-type": "^2.0.0", "media-typer": "^1.1.0", "mime-types": "^3.0.0" } }, "sha512-faYHw0anBbc/kWF3zFTEnxSFOAGUX9GFbOBthvDdLsIlEoWOFOtS0zgCiQYwIskL9iGXZL3kAXD8OoZ4GmMATA=="],
+
     "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=="],

docs/INSTALL.md

@@ -39,10 +39,11 @@ gbrain migrate --to pglite       # Postgres → PGLite (rare)
 
 For shared / large / multi-machine deployments (a team or company brain with multiple users hitting one server over HTTP MCP with OAuth scoping per user), follow the dedicated walkthrough: **[Tutorial: set up GBrain as your company brain](tutorials/company-brain.md)**.
 
-API keys live in `~/.gbrain/config.json` (file plane) or env vars (`OPENAI_API_KEY`, `ZEROENTROPY_API_KEY`, `VOYAGE_API_KEY`, `ANTHROPIC_API_KEY`). Set via CLI:
+API keys live in `~/.gbrain/config.json` (file plane) or env vars (`OPENAI_API_KEY`, `OPENROUTER_API_KEY`, `ZEROENTROPY_API_KEY`, `VOYAGE_API_KEY`, `ANTHROPIC_API_KEY`). Set via CLI:
 
 ```bash
 gbrain config set zeroentropy_api_key sk-...
+gbrain config set openrouter_api_key sk-or-...
 gbrain config set anthropic_api_key sk-ant-...
 ```
 

docs/TESTING.md

@@ -19,6 +19,29 @@ Seven test command tiers, each with a clear scope:
 | `bun run test:e2e` | Real Postgres E2E. Requires Docker + `DATABASE_URL`. Sequential. | ~5-10min | Pre-ship; nightly. |
 | `bun run check:all` | The historical pre-check scripts (22, chained sequentially in package.json). Overlaps `verify` heavily but is NOT a superset — `verify`'s `CHECKS` array in `scripts/run-verify-parallel.sh` (~30 entries incl. typecheck) is the authoritative gate; `check:all` keeps a few local-only extras (trailing-newline, exports-count, no-legacy-getconnection). | ~10s | Local-only sweep for the extras. |
 
+### Shell dispatch and Windows
+
+All four of `test`, `verify`, `ci:local` and `test:e2e` hand off to shell scripts
+under `scripts/`, so every `check:*` entry in `package.json` invokes its script as
+`bash scripts/<name>.sh` instead of relying on the shebang — bun on Windows cannot
+exec a `.sh` directly. Add a new shell-script check with that same prefix. The
+`scripts/*.ts` entries run under bun and take no prefix.
+
+The scripts must also be on disk with Unix line endings. A strict bash (WSL, Linux
+CI, macOS) rejects CRLF and dies on the script's first meaningful line; the Cygwin
+bash that ships with Git for Windows tolerates it, so a green local run is not by
+itself evidence that a script is CRLF-clean.
+The root `.gitattributes` pins `*.sh text eol=lf`, which overrides the
+`core.autocrlf=true` default that Git for Windows installs. Working copies cloned
+before that pin need a one-time `git rm --cached -r . -q && git reset --hard` to
+pick it up; see the Windows section of `CONTRIBUTING.md`.
+
+Wallclock figures in the table above are from a Mac dev box. Windows is
+substantially slower because each check pays full process-creation cost, and three
+tree-walking checks (`check:privacy`, `check:test-names`, `check:test-isolation`)
+plus `typecheck` can exceed the 120s per-check cap in `run-verify-parallel.sh`
+there even though they pass on Linux and macOS.
+
 ### CI vs local: intentionally divergent file sets
 
 - **CI matrix** (`.github/workflows/test.yml`) runs `scripts/test-shard.sh` across 10 matrix shards partitioned by weight-aware LPT bin-packing (`scripts/sharding.ts`) and INCLUDES `*.slow.test.ts` (the two outlier slow files run as dedicated jobs alongside the matrix). CI EXCLUDES `*.serial.test.ts` from the shards and runs them in a dedicated job via `bun run test:serial`, one bun process per file — keeping serial files out of the shard processes is what preserves the `mock.module` quarantine (a top-level mock in one file leaks into every other file sharing its process). `bun run verify` gets its own job too. CI is the ground truth for "did everything pass."
@@ -192,6 +215,7 @@ Unit tests and what they cover:
 - `test/sync-pull-failed-anchor.serial.test.ts` — #3068 regression: a failed internal `git pull` (local-path origin vs `protocol.file.allow=never`) with zero imports returns `partial`/`pull_failed` (not `up_to_date`), freezes `last_commit` + `last_sync_at`, recovers after a manual pull; fall-through import of local commits preserved. Serial: pins `GBRAIN_HOME` to a temp dir for the whole file.
 - `test/sync-concurrency.test.ts` — `autoConcurrency()` thresholds + PGLite-forces-serial + explicit-override clamping; `shouldRunParallel()` explicit-bypasses-floor contract; `parseWorkers()` validation rejecting `'0'`/`'-3'`/`'foo'`/`'1.5'`/trailing chars.
 - `test/sync-parallel.test.ts` — PGLite-routed coverage of the bookmark gate under concurrency, head-drift gate, vanished-file failure capture, PGLite-stays-serial, and the `gbrain-sync` writer-lock contract.
+- `test/sync-all-missing-path.test.ts` — `sync --all --missing-path <fail|skip>` pure helpers: `parseMissingPathMode` (default fail, explicit values, loud rejection of bad/dangling values, never swallows a following flag) and `partitionMissingPathSources` (classification driven only by the injected pathExists predicate — no fs; null `local_path` passes through runnable; order preserved).
 - `test/sync-failures.test.ts` — `classifyErrorCode` regex coverage for all 12 codes against literal production message strings from `markdown.ts` and `import-file.ts`; `summarizeFailuresByCode` sort + pre-classified-honor; `recordSyncFailures` code-field persistence; `acknowledgeSyncFailures` `AcknowledgeResult` shape + backfill on legacy entries.
 - `test/doctor.test.ts` — doctor command; assertions that `jsonb_integrity` scans the four JSONB write sites and `markdown_body_completeness` is present.
 - `test/utils.test.ts` — shared SQL utilities + `tryParseEmbedding` null-return and single-warn semantics.

docs/architecture/RETRIEVAL.md

@@ -87,6 +87,15 @@ embedding proximity. Four layers, added after the incident in
   deciding "is this page already here, safe to NOT write a duplicate?" keys off
   `create_safety`, not a raw blended score.
 
+**Extraction quarantine lane (issue #160):** pages carrying the unverified
+auto-extracted markers (frontmatter `provenance: auto-extracted` +
+`status: unverified`, see `src/core/extraction-review.ts`) rank as ordinary
+content — they are skipped by the compiled-truth fusion boost and by the
+`people/`/`companies/` namespace source-boost, and every search result from
+such a page carries `unverified: true` so agents can label the provenance.
+Promote or reject them via `gbrain extraction-pending` / `gbrain
+extraction-review`.
+
 The `search` MCP/CLI op is **cheap-hybrid** (vector + keyword + RRF + pool +
 title + alias, expansion off); `query` is the full-control variant. NamedThingBench
 (`gbrain eval retrieval-quality`) gates these families on every PR. Diagnose a

docs/architecture/conversation-parser-patterns.md

@@ -0,0 +1,146 @@
+# Conversation parser patterns
+
+The conversation parser turns exported chat and meeting transcripts into a
+common message stream without requiring an LLM call for known formats. This
+document describes the built-in pattern contract and the checks required when
+adding or changing a format.
+
+## Data flow
+
+`parseConversation` uses this sequence:
+
+1. Resolve the page date and timezone context.
+2. Score every enabled built-in and user pattern against the first ten
+   non-blank lines.
+3. Re-score the full body when the head score is inconclusive, or when a broad
+   pattern explicitly requires full-body scoring.
+4. Reject the winner when its acceptance score is below the false-positive
+   floor.
+5. Apply the winning pattern to every line and attach continuation lines to the
+   preceding message.
+6. Optionally run LLM polish or fallback when those features are enabled.
+
+Pattern order is only a tie-breaker. A new regex must be structurally distinct
+from neighboring formats; moving it earlier in the registry is not a valid
+non-shadowing strategy.
+
+## Built-in pattern contract
+
+Every `PatternEntry` in `builtins.ts` declares:
+
+- A stable, kebab-case `id`.
+- A hand-vetted line regex and explicit capture-group indexes.
+- Where the date comes from and how the time is represented.
+- A timezone policy.
+- Whether the format supports multi-line message bodies.
+- Positive and negative samples that run during module initialization.
+- A documentation pointer describing the source format.
+
+The registry refuses to load when a positive sample stops matching, a negative
+sample starts matching, or a capture map becomes invalid. This catches local
+regex mistakes before extraction can silently produce empty conversations.
+
+### Date and timezone rules
+
+Formats with an inline date should capture it from each message. Time-only
+formats use an explicit caller fallback first, then the page frontmatter date,
+then the page effective date. If none is available, the parser uses
+`1970-01-01` so the missing date remains visible instead of inventing a current
+date.
+
+Time-only formats normally use `utc_assumed_with_warn`. The parser constructs a
+UTC timestamp and returns a timezone warning when the page does not provide a
+timezone. A new pattern should not imply local-time precision that the source
+format does not contain.
+
+### Multi-line messages
+
+An anchor regex identifies the first line of a message. Subsequent non-anchor
+lines are appended to that message until another anchor appears. Set
+`multi_line: true` when continuation content is part of the documented format,
+such as Markdown bullets, blockquotes, or an exported message body on the next
+line.
+
+Tests for a multi-line format should assert the complete message text, including
+newlines. A message-count assertion alone will not detect lost bullets or a
+continuation attached to the wrong speaker.
+
+### Scoring and false positives
+
+The score compares matched anchors with the pattern's relevant candidate lines.
+The first pass uses the head of the page for speed. Low-confidence pages are
+re-scored across the full body before the parser accepts a winner.
+
+Multi-line formats may opt into `score_continuations_as_body` when their anchor
+grammar is distinctive. Candidate-only scoring activates only after two anchors
+match, or when the first non-blank line is an anchor. This evidence threshold
+lets a single long message keep its continuation body without turning one stray
+anchor in a prose page into a conversation. Candidate anchor lines that fail the
+full regex still lower the score. Other patterns continue to use all non-blank
+lines in their density score.
+
+Use `score_full_body: true` for a broad grammar that also occurs in ordinary
+prose. For example, `**Label:** text` can be either a transcript line or a bold
+label in meeting notes. Narrow formats with a timestamp and a distinctive
+separator generally do not need this override.
+
+`quick_reject` is a performance hint, not an acceptance rule. It should cheaply
+exclude obviously unrelated lines while admitting every string accepted by the
+main regex.
+
+## Normalized Slack Markdown
+
+The `bold-time-dash` pattern parses message anchors shaped like:
+
+```text
+**Alice Example** 09:15 — first message
+- supporting detail
+**Bob Example** 09:18 — second message
+```
+
+Its grammar is:
+
+```text
+**speaker** H:MM <dash> text
+```
+
+where:
+
+- `H:MM` is a valid 24-hour time from `0:00` through `23:59`.
+- `<dash>` may be an em dash (`—`), en dash (`–`), or ASCII hyphen (`-`).
+- The date comes from the resolved page date context.
+- Continuation lines belong to the preceding message.
+- The captured clock value is emitted with `Z`. Timezone metadata suppresses
+  the missing-timezone warning but is not currently used for IANA conversion.
+
+The required time and dash distinguish it from all existing bold-speaker
+formats:
+
+- `**Speaker** (09:15): text` uses `bold-paren-time`.
+- `**Speaker** (9:15 AM): text` uses `bold-paren-time-12h`.
+- `**Speaker:** text` uses `bold-name-no-time`.
+- `**Speaker** (2026-04-09 9:15 AM): text` uses `imessage-slack`.
+
+Keeping these examples in both `test_negative` and parser regression tests makes
+the non-shadowing contract executable.
+
+## Adding a built-in format
+
+1. Collect multiple anonymized examples, including separator and timestamp
+   variants that occur in the same export family.
+2. Choose the narrowest grammar that represents the format. Constrain numeric
+   fields such as hours and minutes when possible.
+3. Add at least two positive module-load samples and negative samples for every
+   neighboring pattern that could plausibly overlap.
+4. Add parser tests that verify speakers, timestamps, text, continuation
+   handling, and non-shadowing behavior.
+5. Add a dedicated JSONL fixture and include the same cases in
+   `test/fixtures/conversation-formats/all.jsonl`.
+6. Run the focused parser tests and the fixture evaluator.
+7. Run the repository verification and full test suites before submission.
+8. Update `docs/architecture/KEY_FILES.md` when the registry count or supported
+   format inventory changes.
+
+Use generic fixture identities such as `Alice Example`, `Bob Example`, and
+`Summary Bot`. Never copy real transcript names or private content into source,
+tests, documentation, commits, or pull-request descriptions.

docs/architecture/pack-upgrade-mechanism.md

@@ -229,7 +229,7 @@ add `GBRAIN_AUDIT_FULL=1` (v0.43+ TODO; not yet wired).
 - Per-source pack-upgrade (the handler accepts `sourceId` but
   `findPackSuccessors` doesn't yet pass it through)
 - Cross-brain federated mounts that disagree on canonical packs
-- Automatic rollback (today: manual SQL or `gbrain pages restore`)
+- Automatic rollback (today: manual SQL or `gbrain restore`)
 - LLM-assisted mapping_rules codegen from production data (`gbrain
   schema detect-mappings`; deferred to v0.43+)
 

docs/architecture/schema-packs.md

@@ -214,7 +214,7 @@ gbrain schema downgrade
 
 1. `git revert <merge-commit>` — restores the code.
 2. `gbrain schema downgrade --to gbrain-base` — restores config.
-3. (Optional) `gbrain pages purge-deleted --older-than 0h` — drops
+3. (Optional) `gbrain purge-deleted --older-than 0h` — drops
    v0.39-typed pages that no longer have a matching type in the active
    pack.
 

docs/architecture/system-of-record.md

@@ -19,11 +19,13 @@ entire DB from scratch.
 
 This means:
 
-- **Disaster recovery is one command.** If your DB volume corrupts, if
-  Postgres eats itself, if PGLite's WASM lock wedges — you don't need
-  a backup. You wipe the DB, re-import from your brain repo, and the
-  derived state regenerates. v0.32.3 ships `gbrain rebuild
-  --confirm-destructive` as the documented one-liner.
+- **Disaster recovery is a short, boring sequence.** If your DB volume
+  corrupts, if Postgres eats itself, if PGLite's WASM lock wedges — you
+  don't need a backup. You wipe the derived tables (on PGLite,
+  `gbrain reinit-pglite` wipes the whole embedded DB), re-import from
+  your brain repo with `gbrain sync`, and `gbrain extract all`
+  regenerates the derived state. See "Disaster recovery" below for the
+  exact commands.
 - **Multi-machine sync is git.** Your brain is a repo. Push from one
   machine, pull from another, and the second machine's DB rebuilds on
   its next sync. No "back up the database" step.
@@ -146,11 +148,9 @@ The promise the rule makes:
 # Snapshot what's there
 gbrain stats > /tmp/before.txt
 
-# Wipe and rebuild
-gbrain rebuild --confirm-destructive   # v0.32.3 — deletes derived tables
-                                       # (pages + content_chunks survive
-                                       # the CASCADE-safe design)
-                                       # OR manually for v0.32.2:
+# Wipe and rebuild — delete the derived tables (pages + content_chunks
+# survive the CASCADE-safe design), then re-derive from the repo.
+# On PGLite, `gbrain reinit-pglite` wipes the whole embedded DB instead.
 psql -c 'DELETE FROM facts; DELETE FROM takes; DELETE FROM links; DELETE FROM timeline_entries;'
 gbrain sync
 gbrain extract all

docs/architecture/type-taxonomy.md

@@ -108,8 +108,8 @@ Every primitive ships with a documented rollback:
 | Operation | Rollback |
 |-----------|----------|
 | Retype | `frontmatter.legacy_type = <original>` preserved on every page (D8). One SQL UPDATE restores types: `UPDATE pages SET type = frontmatter->>'legacy_type' WHERE frontmatter ? 'legacy_type'`. |
-| Page-to-link | Source page soft-deleted with 72h TTL. `gbrain pages restore <slug>` within 72h. Link row stays harmless if source restored. |
-| Page-to-alias | Source page soft-deleted with 72h TTL. `gbrain pages restore <slug>` within 72h. Alias row stays harmless (or `DELETE FROM slug_aliases WHERE alias_slug = <slug>` to clean up). |
+| Page-to-link | Source page soft-deleted with 72h TTL. `gbrain restore <slug>` within 72h. Link row stays harmless if source restored. |
+| Page-to-alias | Source page soft-deleted with 72h TTL. `gbrain restore <slug>` within 72h. Alias row stays harmless (or `DELETE FROM slug_aliases WHERE alias_slug = <slug>` to clean up). |
 | Active-pack flip | `gbrain schema use gbrain-base` reverses the flip. |
 
 ## What if my brain doesn't fit?

docs/ethos/MARKDOWN_SKILLS_AS_RECIPES.md

@@ -183,6 +183,6 @@ This also means the best AI agent setups will be open source by default. Closed,
 
 Software distribution reimagined: the package is a markdown file, the runtime is a sufficiently smart model, the package manager is your AI agent, and the app store is a git repo.
 
-`gbrain install voice-agent`
+`gbrain skillpack scaffold voice-agent`
 
 That's it.

docs/guides/agent-to-gbrain.md

@@ -159,7 +159,8 @@ proxy for worker env.
   If a brain DB ever traverses a trust boundary, secrets stay out.
 - **Free-form names.** `inherit:` accepts any snake_case config-key on your
   worker — `database_url`, `anthropic_api_key`, `openai_api_key`,
-  `voyage_api_key`, `groq_api_key`, `zeroentropy_api_key`, or any custom
+  `openrouter_api_key`, `voyage_api_key`, `groq_api_key`,
+  `zeroentropy_api_key`, or any custom
   field you stuff into `~/.gbrain/config.json`. The agent picks what it
   needs.
 - **`env:` still works** for non-secret values, or for cases where you

docs/guides/compiled-truth.md

@@ -69,7 +69,7 @@ update_brain_page(slug, new_info, source):
   page = gbrain get {slug}
 
   // TIMELINE: always APPEND (never edit existing entries)
-  gbrain add_timeline_entry {slug} {
+  gbrain timeline-add {slug} {
     date: today,
     summary: new_info.summary,
     detail: new_info.detail,

docs/guides/content-media.md

@@ -46,10 +46,10 @@ on user_shares_media(url_or_file):
 
         # Step 4: Extract and cross-reference entities
         for person in transcript.mentioned_people:
-            gbrain add_link <slug> <person_slug>
-            gbrain add_link <person_slug> <slug>
-            gbrain add_timeline_entry <person_slug> \
-                --entry "Discussed in {video_title}: {what_was_said}" \
+            gbrain link <slug> <person_slug>
+            gbrain link <person_slug> <slug>
+            gbrain timeline-add <person_slug> {date} \
+                "Discussed in {video_title}: {what_was_said}" \
                 --source "YouTube: {url}"
 
     # PATTERN 2: Social Media Bundles
@@ -80,8 +80,8 @@ on user_shares_media(url_or_file):
 
         # Extract entities and cross-reference
         for entity in bundle.mentioned_entities:
-            gbrain add_link <slug> <entity_slug>
-            gbrain add_link <entity_slug> <slug>
+            gbrain link <slug> <entity_slug>
+            gbrain link <entity_slug> <slug>
 
     # PATTERN 3: PDFs and Documents
     elif media.type == "pdf" or media.type == "document":
@@ -109,8 +109,8 @@ on user_shares_media(url_or_file):
         """
 
         for entity in document.mentioned_entities:
-            gbrain add_link <slug> <entity_slug>
-            gbrain add_link <entity_slug> <slug>
+            gbrain link <slug> <entity_slug>
+            gbrain link <entity_slug> <slug>
 
     # Always sync after ingestion
     gbrain sync
@@ -127,7 +127,7 @@ on user_shares_media(url_or_file):
 ## How to Verify
 
 1. Ingest a YouTube video. Run `gbrain get media/youtube/{slug}`. Confirm the page has: the agent's analysis (not just a summary), key quotes with speaker attribution, and the full diarized transcript.
-2. Run `gbrain get_links media/youtube/{slug}`. Confirm back-links exist to brain pages for every person and company mentioned in the video.
+2. Run `gbrain call get_links '{"slug": "media/youtube/{slug}"}'`. Confirm back-links exist to brain pages for every person and company mentioned in the video.
 3. Pick a person mentioned in the video. Run `gbrain get <person_slug>`. Confirm their timeline has a new entry referencing the video with specific context.
 4. Ingest a tweet. Confirm the brain page includes the thread context, linked article summaries, and entity cross-references -- not just the tweet text.
 5. Run `gbrain search "{topic_from_video}"`. Confirm the media page appears in search results (verifies the content is indexed and searchable).

docs/guides/embedding-migration.md

@@ -0,0 +1,138 @@
+# Embedding migration — moving a brain to another embedding provider
+
+`gbrain migrate embeddings` re-embeds an entire brain onto a different
+embedding provider/model, safely and resumably. It is the forward path off a
+sunsetting provider (for example ZeroEntropy's hosted API, which shuts down
+2026-09-04 and is the shipped default for brains that never picked a model) —
+but it is provider-agnostic: any configured `provider:model` works as a
+target.
+
+Also reachable as `gbrain retrieval-upgrade` (the name `doctor` and the
+README reference).
+
+## Quick start
+
+```bash
+# Preview the work + cost. Changes nothing.
+gbrain migrate embeddings --to openai:text-embedding-3-small --dry-run
+
+# Run it (interactive confirm shows chunk count + $ estimate first).
+gbrain migrate embeddings --to openai:text-embedding-3-small
+
+# Non-interactive (cron / scripts): --yes is required, else exit 2.
+gbrain migrate embeddings --to voyage:voyage-3-large --yes
+```
+
+`--dim <N>` overrides the target width; it defaults to the provider recipe's
+declared width and is required for recipes that don't declare one (litellm,
+llama-server, and other bring-your-own-model providers).
+
+## What it does, in order
+
+1. **Plan.** Counts every chunk not already in the target embedding space —
+   including chunks on pages with **no recorded embedding signature**
+   (pages embedded before the v108 provenance stamp). Prices the re-embed
+   from the pricing table; unknown providers print "estimate unavailable"
+   instead of a fabricated number.
+2. **Consent gate.** Prints the plan; requires an interactive `y` or `--yes`.
+   Non-TTY without `--yes` refuses with exit 2 (mirrors the `reindex-code`
+   gate in [spend-controls](../operations/spend-controls.md)). Unlike the pure
+   cost gates there, `spend.posture=tokenmax` does **not** bypass this one:
+   posture waives the spend *ceiling*, and this gate also guards a
+   destructive schema rebuild. Under `tokenmax` the dollar figure is marked
+   informational and the confirmation is still asked. `--yes` is the single
+   scripted bypass.
+3. **Live probe.** One tiny embed against the TARGET provider before any
+   mutation — validates the API key, model id, and dimension support in a
+   single call. A bad key fails here, with nothing changed.
+4. **Env-override gate.** Refuses when `GBRAIN_EMBEDDING_MODEL` /
+   `GBRAIN_EMBEDDING_DIMENSIONS` would silently defeat the switch at
+   runtime (the same guard `ze-switch` uses). `--ignore-env-override` for
+   people running deliberate experiments.
+5. **Apply.** When the target width differs from the actual column width,
+   runs the same atomic schema transition `ze-switch` uses, in one
+   transaction. It rebuilds **all three dim-pinned text-embedding-space
+   columns** — `content_chunks.embedding`, `query_cache.embedding`, and
+   `facts.embedding` — at the new width, preserving each column's type
+   (`vector` vs `halfvec`) and recreating its HNSW index. Missing any of the
+   three leaves it silently broken: a narrow `query_cache.embedding` makes
+   every cache write and read fail *by design* (the cache swallows errors so
+   it can never break search) for a permanent 0% hit rate, and a narrow
+   `facts.embedding` fails every per-fact embed write. The image/multimodal
+   columns ARE deliberately untouched — they use separate models whose
+   dimensions are independent of the text embedding model.
+   Writes `embedding_model` + `embedding_dimensions` to BOTH config planes
+   (file plane for the runtime gateway, DB plane for doctor), invalidates
+   every chunk still in the old space — **including NULL-signature pages** —
+   and purges the semantic query cache so stale cached results can't be
+   served across the swap.
+6. **Re-embed.** The standard embed pipeline (`embed --stale --catch-up`)
+   with per-source single-flight locks, rate-limit backoff, stderr progress,
+   and optional DB-contention pacing (`--pace[=mode]`).
+
+## What the rebuild deletes
+
+The dimension change **deletes every stored embedding vector** in the brain —
+they are in the old model's space and unusable. They are not recoverable:
+going back to the previous provider means paying for a second full re-embed.
+`content_chunks` vectors are rebuilt by the re-embed pass, the query cache
+refills on the next query, and fact embeddings are rewritten on their next
+write (or a `gbrain extract` pass).
+
+## Resume after a kill
+
+The NULL-embedding column is the checkpoint. If the run is killed (or some
+pages fail to embed), re-run the **same command**: chunks already embedded on
+the target are never re-embedded, the schema/config steps no-op, and the run
+continues where it stopped. An in-flight marker (`embedding_migration.state`
+in DB config) records the target; it is cleared only when the backlog drains
+to zero.
+
+A page whose chunks straddle two stale batches is embedded correctly but not
+stamped by the embed loop (which only stamps all-or-nothing per batch), so the
+migration runs one reconcile pass after the drain that stamps every
+fully-embedded page. Without it a large brain would report "incomplete" and the
+re-run would pay again for those pages. `--batch-size N` tunes the batch
+(default 2000).
+
+`--no-embed` applies schema + config + invalidation and stops, so you can run
+the (potentially long) re-embed later or in the background:
+
+```bash
+gbrain migrate embeddings --to openai:text-embedding-3-small --yes --no-embed
+gbrain embed --stale --catch-up --include-null-signature --background
+```
+
+## During the migration
+
+While the re-embed runs, semantic search returns degraded (lexical-arm-only)
+results for not-yet-re-embedded content. Pick a quiet window for large
+brains, or use `--pace` to keep the DB responsive.
+
+## Pages without an embedding signature (#3391)
+
+Pages embedded before provenance stamping have `embedding_signature IS NULL`
+and are grandfathered by the routine stale sweep (so an upgrade never
+surprise-re-embeds a whole corpus). After a provider swap that grandfather
+clause would silently leave those pages in the OLD embedding space — mixed
+vector spaces in one index, degrading retrieval with nothing in the logs.
+
+- `gbrain migrate embeddings` always includes them.
+- Plain `gbrain embed --stale` warns when a model swap leaves NULL-signature
+  pages behind, and `gbrain embed --stale --include-null-signature` re-embeds
+  them.
+
+## Reranker
+
+Migrating embeddings does not touch the reranker. If
+`search.reranker.model` points at the outgoing provider, the plan prints a
+warning; disable it (`gbrain config set search.reranker.enabled false`) or
+point it at another provider.
+
+## Self-hosting instead of migrating
+
+If the outgoing model's weights are available (zembed-1's are Apache-2.0),
+serving them locally via `llama-server` / `ollama` / a LiteLLM proxy
+preserves your existing vectors — no re-embed at all. Point
+`embedding_model` at the local recipe and keep the same dimensions. The
+migration command is for when you'd rather move to a hosted provider.

docs/guides/enrichment-pipeline.md

@@ -49,23 +49,23 @@ on enrich(entity, trigger):
         data["contacts"] = google_contacts(entity.email)   # Contact data
 
     # Step 5: Store raw data (auditable, re-processable)
-    gbrain put_raw_data <entity_slug> \
-        --data '{"sources": {"crustdata": {"fetched_at": "...", "data": {...}}, ...}}'
+    gbrain call put_raw_data \
+        '{"slug": "<entity_slug>", "data": {"sources": {"crustdata": {"fetched_at": "...", "data": {...}}, ...}}}'
     # Overwrite on re-enrichment, don't append
 
     # Step 6: Write to brain page
     if path == "CREATE":
         gbrain put <entity_slug> --content "<compiled_truth_from_all_sources>"
-        gbrain add_timeline_entry <entity_slug> --entry "Page created via enrichment"
+        gbrain timeline-add <entity_slug> {date} "Page created via enrichment"
     elif path == "UPDATE":
         # Append timeline, update compiled truth ONLY if materially new
-        gbrain add_timeline_entry <entity_slug> --entry "Enriched: {new_signal}"
+        gbrain timeline-add <entity_slug> {date} "Enriched: {new_signal}"
         # Flag contradictions -- don't silently resolve them
 
     # Step 7: Cross-reference the graph
-    gbrain add_link <person_slug> <company_slug>       # person -> company
-    gbrain add_link <company_slug> <person_slug>       # company -> person
-    gbrain add_link <person_slug> <deal_slug>          # person -> deal
+    gbrain link <person_slug> <company_slug>       # person -> company
+    gbrain link <company_slug> <person_slug>       # company -> person
+    gbrain link <person_slug> <deal_slug>          # person -> deal
     # Every entity page links to every other entity page that references it
 
 # People page sections (not a LinkedIn profile -- a living portrait):
@@ -94,8 +94,8 @@ on enrich(entity, trigger):
 ## How to Verify
 
 1. Enrich a Tier 1 person. Run `gbrain get <slug>` and confirm the page has Executive Summary, State, What They Believe, Contact, and Timeline sections populated from multiple sources.
-2. Run `gbrain get_raw_data <slug>`. Confirm raw API responses are stored with `sources.{provider}.fetched_at` timestamps.
-3. Run `gbrain get_links <slug>`. Confirm cross-reference links exist to the person's company page, deal pages, and related entities.
+2. Run `gbrain call get_raw_data '{"slug": "<slug>"}'`. Confirm raw API responses are stored with `sources.{provider}.fetched_at` timestamps.
+3. Run `gbrain call get_links '{"slug": "<slug>"}'`. Confirm cross-reference links exist to the person's company page, deal pages, and related entities.
 4. Check a page that was enriched AND has a user-written Assessment. Confirm the Assessment section was preserved, not overwritten by API data.
 5. Try to re-enrich the same person. Confirm the system checks the `fetched_at` timestamp and skips if less than a week old.
 

docs/guides/executive-assistant.md

@@ -53,7 +53,7 @@ on upcoming_meeting(meeting):
                 "last_interaction": page.timeline[0],     # most recent
                 "open_threads": page.open_threads,
                 "relationship_temperature": page.relationship,
-                "relevant_deals": gbrain get_links <attendee_slug>,
+                "relevant_deals": gbrain call get_links '{"slug": "<attendee_slug>"}',
             }
         else:
             briefing[attendee] = "No brain page -- consider enriching"
@@ -67,14 +67,14 @@ on inbox_cleared():
     for email in processed_emails:
         if email.contained_new_information:
             # Update the sender's brain page with new signal
-            gbrain add_timeline_entry <sender_slug> \
-                --entry "Email re: {subject}. Key info: {extracted_signal}" \
+            gbrain timeline-add <sender_slug> {date} \
+                "Email re: {subject}. Key info: {extracted_signal}" \
                 --source "email from {sender} re {subject}, {date}"
 
             # Update any mentioned entity pages too
             for entity in email.mentioned_entities:
-                gbrain add_timeline_entry <entity_slug> \
-                    --entry "{what_was_said_about_them}" \
+                gbrain timeline-add <entity_slug> {date} \
+                    "{what_was_said_about_them}" \
                     --source "email from {sender}, {date}"
 
 # WORKFLOW 4: Scheduling Nudges

docs/guides/meeting-ingestion.md

@@ -32,15 +32,15 @@ on new_meeting_transcript(meeting):
 
     # Step 3: Propagate to ALL entity pages (MANDATORY -- most agents skip this)
     for person in meeting.attendees + meeting.mentioned_people:
-        gbrain add_timeline_entry <person_slug> \
-            --entry "Met in '{meeting.title}' on {date}. Key points: ..." \
+        gbrain timeline-add <person_slug> {date} \
+            "Met in '{meeting.title}' on {date}. Key points: ..." \
             --source "Meeting notes '{meeting.title}', {date}"
         # Update their State section if new information surfaced
         # Update company pages for each person's company if relevant
 
     for company in meeting.mentioned_companies:
-        gbrain add_timeline_entry <company_slug> \
-            --entry "Discussed in '{meeting.title}': {what_was_said}" \
+        gbrain timeline-add <company_slug> {date} \
+            "Discussed in '{meeting.title}': {what_was_said}" \
             --source "Meeting notes '{meeting.title}', {date}"
 
     # Step 4: Extract action items
@@ -49,8 +49,8 @@ on new_meeting_transcript(meeting):
 
     # Step 5: Back-link everything (bidirectional graph)
     for entity in all_entities_mentioned:
-        gbrain add_link <slug> <entity_slug>   # meeting -> entity
-        gbrain add_link <entity_slug> <slug>    # entity -> meeting
+        gbrain link <slug> <entity_slug>   # meeting -> entity
+        gbrain link <entity_slug> <slug>    # entity -> meeting
 
     # Step 6: Sync so new pages are immediately searchable
     gbrain sync
@@ -73,7 +73,7 @@ on new_meeting_transcript(meeting):
 1. After ingesting a meeting, run `gbrain get meetings/{date}-{slug}`. Confirm the page has the agent's analysis above the bar and the full diarized transcript below it.
 2. For each attendee, run `gbrain get <attendee_slug>`. Check that their timeline has a new entry referencing the meeting with specific insights (not just "attended meeting").
 3. Pick a company mentioned in the meeting. Run `gbrain get <company_slug>`. Confirm a timeline entry exists referencing what was discussed about the company.
-4. Run `gbrain get_links meetings/{date}-{slug}`. Verify back-links exist to all attendee and entity pages.
+4. Run `gbrain call get_links '{"slug": "meetings/{date}-{slug}"}'`. Verify back-links exist to all attendee and entity pages.
 5. Run `gbrain search "{meeting_topic}"`. Confirm the meeting page appears in search results (verifies sync ran).
 
 ---

docs/guides/minions-shell-jobs.md

@@ -155,6 +155,7 @@ child-spawn time:
 - `inherit: ["database_url"]` → child env `GBRAIN_DATABASE_URL`
 - `inherit: ["anthropic_api_key"]` → child env `ANTHROPIC_API_KEY`
 - `inherit: ["openai_api_key"]` → child env `OPENAI_API_KEY`
+- `inherit: ["openrouter_api_key"]` → child env `OPENROUTER_API_KEY`
 - `inherit: ["voyage_api_key"]` → child env `VOYAGE_API_KEY`
 - `inherit: ["groq_api_key", "zeroentropy_api_key"]` → both injected
 - Or any arbitrary config-key your worker has (`my_custom_field` →

docs/guides/multi-source-brains.md

@@ -91,7 +91,7 @@ first):
 6. The seeded `default` source.
 
 So inside `~/.gstack/plans/` on a brain that pinned `gstack` to
-`~/.gstack` via `.gbrain-source`, `gbrain put-page` implicitly writes to
+`~/.gstack` via `.gbrain-source`, `gbrain put` implicitly writes to
 the `gstack` source. Outside any registered directory with no env/dotfile
 set, it writes to the default.
 
@@ -188,10 +188,10 @@ citations keep working.
 
 ```bash
 # Pass --source explicitly
-gbrain put-page topics/ai ... --source wiki
+gbrain put topics/ai ... --source wiki
 
 # Or rely on the dotfile / env / CWD match
-cd ~/.gstack && gbrain put-page plans/multi-repo ...
+cd ~/.gstack && gbrain put plans/multi-repo ...
 # → source auto-resolves to gstack
 ```
 

docs/guides/operational-disciplines.md

@@ -20,8 +20,8 @@ on every_inbound_message(message):
     for entity in entities:
         existing = gbrain search "{entity.name}"
         if existing:
-            gbrain add_timeline_entry <entity_slug> \
-                --entry "{what_was_said}" \
+            gbrain timeline-add <entity_slug> {date} \
+                "{what_was_said}" \
                 --source "User, direct message, {timestamp}"
         # else: flag for enrichment if important enough
 
@@ -64,13 +64,13 @@ on nightly_schedule("02:00"):
     # The brain COMPOUNDS overnight.
 
     # 5a: Entity sweep -- find unlinked mentions
-    pages = gbrain list_pages
+    pages = gbrain list
     for page in pages:
         mentions = extract_entity_mentions(page.content)
-        existing_links = gbrain get_links <page.slug>
+        existing_links = gbrain call get_links '{"slug": "<page.slug>"}'
         for mention in mentions:
             if mention not in existing_links:
-                gbrain add_link <page.slug> <mention_slug>  # fix broken graph
+                gbrain link <page.slug> <mention_slug>  # fix broken graph
 
     # 5b: Citation audit -- find facts without sources
     for page in pages:
@@ -80,7 +80,7 @@ on nightly_schedule("02:00"):
 
     # 5c: Memory consolidation -- update compiled truth from timeline
     for page in stale_pages(older_than="7d"):
-        timeline = gbrain get_timeline <page.slug>
+        timeline = gbrain timeline <page.slug>
         if timeline.has_new_entries_since_last_consolidation:
             # Re-synthesize compiled truth from accumulated timeline
             updated_truth = consolidate(page.compiled_truth, timeline.new_entries)
@@ -110,11 +110,11 @@ on nightly_schedule("02:00"):
 
 ## How to Verify
 
-1. Send a message mentioning a person with a brain page. Confirm the agent detects the entity and adds a timeline entry to their page (`gbrain get_timeline <slug>`).
+1. Send a message mentioning a person with a brain page. Confirm the agent detects the entity and adds a timeline entry to their page (`gbrain timeline <slug>`).
 2. Ask the agent about someone in the brain. Confirm it runs `gbrain search` or `gbrain get` BEFORE reaching for external APIs (check the tool call order).
 3. Write a new page with `gbrain put`, then immediately run `gbrain search` for it. Confirm it appears in results (verifies sync ran).
 4. Run `gbrain doctor`. Confirm it returns a health report with database status, page count, and any flagged issues.
-5. After a dream cycle runs, check a page that had unlinked entity mentions. Confirm new links were added (`gbrain get_links <slug>`).
+5. After a dream cycle runs, check a page that had unlinked entity mentions. Confirm new links were added (`gbrain call get_links '{"slug": "<slug>"}'`).
 
 ---
 *Part of the [GBrain Skillpack](../GBRAIN_SKILLPACK.md).*

docs/guides/originals-folder.md

@@ -47,8 +47,8 @@ on user_message(message):
 
         # Step 3: Cross-link to everything that shaped the thinking
         for entity in idea.influences:
-            gbrain add_link originals/{slug} <entity_slug>
-            gbrain add_link <entity_slug> originals/{slug}
+            gbrain link originals/{slug} <entity_slug>
+            gbrain link <entity_slug> originals/{slug}
 
         # Step 4: Sync
         gbrain sync
@@ -79,7 +79,7 @@ on user_message(message):
 
 1. Generate an original idea in conversation (e.g., "I call this the 'ambition debt' problem -- every year you delay going big, the compound interest works against you"). Confirm a new page appears at `brain/originals/ambition-debt` with `gbrain get originals/ambition-debt`.
 2. Check that the page uses the user's exact phrasing for the title and slug -- not a sanitized version.
-3. Run `gbrain get_links originals/ambition-debt`. Confirm cross-links exist to related people, meetings, or other originals.
+3. Run `gbrain call get_links '{"slug": "originals/ambition-debt"}'`. Confirm cross-links exist to related people, meetings, or other originals.
 4. Express a take on someone else's idea (e.g., "I think Thiel's contrarian question is wrong because..."). Confirm it goes to `originals/` (synthesis is original), not `concepts/`.
 5. Run `gbrain search "ambition debt"`. Confirm the originals page appears in search results and is discoverable.
 

docs/guides/plugin-authors.md

@@ -87,7 +87,7 @@ expect it.
 | `version`        | string | yes      | Your plugin's semver. Informational.                               |
 | `plugin_version` | string | yes      | Contract lock. Must equal `"gbrain-plugin-v1"` for v0.15.          |
 | `subagents`      | string | no       | Subdir name (default `subagents`). Escape-attempts are rejected.   |
-| `description`    | string | no       | Shown in future `gbrain plugin list`.                              |
+| `description`    | string | no       | Shown in a future plugin-listing command.                          |
 
 ## Subagent definition files
 

docs/integrations/embedding-providers.md

@@ -103,7 +103,7 @@ For GCP service-account / Vertex AI auth (production deployments), see the v0.32
 
 ### OpenRouter
 
-Single OpenAI-compatible API for fan-out to OpenAI, Anthropic, Google, DeepSeek, Meta Llama, Qwen, and dozens of other hosted providers. One key, many models. Set `OPENROUTER_API_KEY` and use `openrouter:<provider>/<model>` (e.g. `openrouter:openai/gpt-5.2`, `openrouter:anthropic/claude-sonnet-4.6`).
+Single OpenAI-compatible API for fan-out to OpenAI, Anthropic, Google, DeepSeek, Meta Llama, Qwen, and dozens of other hosted providers. One key, many models. Set `OPENROUTER_API_KEY` or `openrouter_api_key` in `~/.gbrain/config.json`, then use `openrouter:<provider>/<model>` (e.g. `openrouter:openai/gpt-5.2`, `openrouter:anthropic/claude-sonnet-4.6`).
 
 **Embedding**: `openai/text-embedding-3-small` (1536d default, Matryoshka shrink to 512/768/1024). OR's embedding catalog also includes `text-embedding-3-large`, `google/gemini-embedding-2-preview`, `qwen/qwen3-embedding-8b`, `bge-m3` — opt in via `--embedding-model openrouter:<id>`. Pricing matches the upstream provider (OR adds a small markup).
 

docs/mcp/DEPLOY.md

@@ -250,7 +250,7 @@ All 30 GBrain operations are available remotely, including `sync_brain` and
 directory where `gbrain serve` was launched. Symlinks, `..` traversal, and absolute
 paths outside cwd are rejected. Page slugs and filenames are allowlist-validated
 (alphanumeric + hyphens; no control chars, RTL overrides, or backslashes). Local
-CLI callers (`gbrain file upload ...`) keep unrestricted filesystem access since
+CLI callers (`gbrain files upload ...`) keep unrestricted filesystem access since
 the user owns the machine.
 
 ## Deployment Options
@@ -258,6 +258,43 @@ the user owns the machine.
 See [ALTERNATIVES.md](ALTERNATIVES.md) for a comparison of ngrok, Tailscale
 Funnel, and cloud hosts (Fly.io, Railway).
 
+### Co-located Docker workloads (self-hosted Postgres)
+
+OAuth scopes and source scoping guard the `gbrain serve --http` path. They do
+NOT guard raw Postgres. If the brain's Postgres runs as a container on the same
+Docker host as other workloads (agent runtimes, n8n, staging fixtures), any
+container sharing Docker's default `bridge` network can open a direct DB
+session — no OAuth token required — and read every source. That silently
+recreates a privileged path underneath the isolation you configured at the MCP
+layer.
+
+Network-zone the host so untrusted containers can never reach Postgres:
+
+```
+Docker host
+├── gbrain-net          ← ONLY the brain's Postgres (+ gbrain serve, if containerized)
+├── agent-<id>-net      ← each untrusted agent runtime, isolated
+└── default bridge      ← no secret-bearing databases
+```
+
+Operator checklist:
+
+```text
+[ ] Postgres is on a user-defined Docker network, not the default bridge
+    (or nothing else runs on that bridge)
+[ ] If Postgres publishes a host port at all, it binds loopback only
+    (`-p 127.0.0.1:5432:5432`, never `0.0.0.0`)
+[ ] Untrusted agent containers have no DATABASE_URL or Postgres password
+[ ] Untrusted agents reach the brain via OAuth/Bearer against serve --http only
+    (host loopback via host.docker.internal / host gateway — never gbrain-net)
+[ ] OAuth clients are least-privilege: scoped --source / --federated-read,
+    pre-minted short-lived tokens preferred over long-lived client secrets
+[ ] Isolation verified: a team-scoped client cannot read internal-only sources
+```
+
+Optional defense-in-depth: a dedicated Postgres role (or RLS) limited to the
+allowed `source_id`s, so even a leaked connection string can't read everything.
+
 ## Troubleshooting
 
 **"missing_auth" error**

docs/operations/conversation-backfill-outcomes.md

@@ -0,0 +1,227 @@
+# Conversation backfill durable outcomes
+
+`gbrain extract-conversation-facts` stores page-level outcomes in `facts` so
+bulk runs, autopilot, and `gbrain doctor` can distinguish finished work from
+retryable work without adding another state table.
+
+This is completion authority, not ordinary extracted knowledge. The authority
+is deliberately narrow: a marker is valid only for the exact page or transcript
+snapshot that was parsed, and only after every required operation succeeded.
+
+## Outcome protocol
+
+The current protocol is v2. Its source names are versioned so rows written by
+older best-effort implementations cannot suppress a corrective replay.
+
+| Outcome | `facts.source` | Meaning |
+|---|---|---|
+| Complete | `cli:extract-conversation-facts:terminal:v2` | Every eligible segment was extracted and inserted successfully, the input remained unchanged, and the terminal write succeeded. |
+| Scanned, not extractable | `cli:extract-conversation-facts:non-extractable:v2` | A recognized input was scanned successfully but contained no eligible multi-message segment. |
+| Unfinished | no matching v2 outcome | Work is pending, failed, was not recognized, changed during extraction, or has only a legacy marker. |
+
+The non-extractable outcome is intentionally separate from completion. It does
+not claim that knowledge facts were extracted. CLI counters, cycle details, and
+doctor output preserve that distinction.
+
+## Snapshot identity
+
+Every v2 marker binds `source_session` to the parser input snapshot:
+
+```text
+<outcome-source>:<page-slug>:<version-token>
+```
+
+There are two token forms.
+
+### Database-backed page body
+
+For pages parsed from `compiled_truth` and `timeline`, the token is:
+
+```text
+page-<pages.content_hash>-<effective-date>
+```
+
+`content_hash` covers title, type, compiled truth, timeline, and frontmatter.
+The effective-date suffix covers the remaining date input used by parsing. This
+identity does not depend on JavaScript's millisecond timestamp precision, so two
+writes within one PostgreSQL millisecond still produce different tokens when
+parser input changes. A legacy page with a null content hash uses a computed
+SHA-256 fallback and is verified in-process by both extraction and doctor.
+
+### Raw transcript sidecar
+
+When frontmatter contains `raw_transcript`, the source text lives outside the
+page row and may change without changing `pages.updated_at`. Its token is:
+
+```text
+sidecar-<SHA-256>
+```
+
+The digest covers the exact body given to the parser plus parser-relevant page
+metadata: title, type, frontmatter, and effective date. Selection recomputes
+the digest before skipping work. A sidecar-only edit therefore reopens the page.
+
+`gbrain doctor` cannot read sidecars in its SQL aggregate, so it enumerates those
+pages in bounded batches and calls the same canonical verifier used by
+extraction. Doctor and extraction therefore agree after sidecar-only edits.
+
+## Selection and locking
+
+Bulk extraction follows this sequence:
+
+1. Enumerate candidate pages in bounded batches.
+2. Filter candidates with matching v2 outcomes.
+3. Apply `--limit` to the remaining pages that actually need work.
+4. Acquire the source-and-slug advisory lock.
+5. Re-fetch the page under that lock.
+6. Recompute and recheck the snapshot-bound outcome.
+7. Prepare one immutable parser snapshot and process it.
+8. Re-fetch and recompute the snapshot before writing an outcome.
+
+The pre-lock check avoids parser, filesystem, and model work for ordinary
+completed pages. The under-lock refetch prevents a stale enumeration object
+from becoming the certified input. The final comparison prevents an edit that
+happens during model or insertion work from receiving a marker for old content.
+
+An edit can occur after the final comparison and before marker insertion. That
+is still safe because the marker contains the old version token. Future
+selection compares the token, not marker creation time, and reopens the page.
+
+Single-page `--slug` runs use the same under-lock path.
+
+## Strict extraction success
+
+The general `extractFactsFromTurn` API remains best-effort for interactive
+callers. It historically returns an empty array for both a legitimate zero-fact
+answer and several model failures.
+
+Conversation backfill instead uses `extractFactsFromTurnWithOutcome`, whose
+result separates:
+
+- `{ ok: true, facts: [] }`, a successful extraction with no durable facts;
+- `{ ok: true, facts: [...] }`, a successful extraction with facts; and
+- `{ ok: false, reason, error? }`, an unavailable provider, provider error,
+  refusal, content filter, malformed output, or repeated truncation.
+
+Any failed segment aborts the page attempt. Any `insertFacts` failure also
+aborts it. The page receives neither a checkpoint advancement nor a terminal
+outcome. Facts inserted by earlier segments may remain temporarily, but the
+next claim deletes this command's rows for the page and replays cleanly.
+
+Bulk workers continue past an individual page failure, but they do not hide it.
+`pages_failed` counts failed claims, stderr names each page, the CLI exits 1,
+the autopilot phase reports `warn`, and receipts/rollups classify the run as
+incomplete. A tolerant pool is therefore observable without sacrificing the
+rest of a large backfill.
+
+This distinction is load-bearing. Treating a provider outage as a successful
+zero-fact response would make a transient failure durable and permanently hide
+the page from later runs.
+
+## Non-extractable authority
+
+A non-extractable marker is written only when all of the following are true:
+
+- a deterministic or accepted parser format recognized the input;
+- ordinary segmentation produced no eligible multi-message segment;
+- the parser phase was not `no_match`;
+- cleanup of prior command-owned rows succeeded; and
+- the input snapshot was still current immediately before cleanup and write.
+
+A `no_match` result stays unfinished so a new parser pattern, optional fallback,
+or corrected input can recover it. Oversize pages, disappeared pages, lock
+contention, dry runs, aborts, cleanup errors, provider failures, extraction
+failures, insertion failures, and outcome-write failures also stay unfinished.
+
+Cleanup errors are never interpreted as "zero rows deleted." Propagating them
+prevents a fresh non-extractable marker from coexisting with stale extracted
+facts that could not be removed.
+
+## Checkpoints are not authority
+
+Operation checkpoints are only progress hints. They do not prove which page
+snapshot was processed, and old checkpoint entries do not include a snapshot
+token. When a page lacks a matching v2 outcome, the command discards that
+page's checkpoint entry and performs a delete-first full replay.
+
+This rule prevents two corruption classes:
+
+- edited text with timestamps older than the old watermark being skipped; and
+- command-owned facts being deleted while the checkpoint skips the segments
+  needed to recreate them.
+
+Deleting `op_checkpoints` does not reopen pages with matching v2 outcomes.
+Deleting or editing an outcome does not make a checkpoint authoritative.
+
+## `--limit` semantics
+
+`--limit N` caps pages that require processing, not completed pages inspected
+while finding them. Durable filtering happens before clipping a batch. With a
+completed page first and a pending page second, `--limit 1` processes the
+pending page rather than consuming the limit on the completed page.
+
+`pages_considered` may therefore exceed `--limit` because it includes durable
+outcomes observed during selection. Model-bearing page work does not exceed the
+limit.
+
+## `--force`
+
+`--force` bypasses durable outcome selection and clears the page checkpoint.
+It still uses delete-first replay, strict extraction outcomes, advisory locks,
+and snapshot verification. Force means "recompute" rather than "relax safety."
+
+## Operator signals
+
+The result exposes separate counters:
+
+- `pages_skipped_completed`
+- `pages_skipped_non_extractable`
+- `pages_marked_non_extractable`
+- `pages_failed`
+
+The CLI aggregates these across sources. The autopilot backfill phase includes
+them in phase details. `gbrain doctor` reports `completed`,
+`scanned_not_extractable`, and `backlog` independently.
+
+Run a small canary twice:
+
+```bash
+gbrain extract-conversation-facts --source-id default --limit 10 --workers 1 --max-cost-usd 0.25 --yes
+gbrain extract-conversation-facts --source-id default --limit 10 --workers 1 --max-cost-usd 0.25 --yes
+gbrain doctor
+```
+
+On the second run, unchanged pages should move through durable skip counters.
+Edit one page or raw transcript sidecar and rerun; that page should process
+again and receive a marker with a new token.
+
+## Maintainer contracts
+
+- Version completion protocols when their success guarantees change.
+- Require an exact `source`, page slug, and snapshot-bound `source_session`.
+- Keep completion and non-extractable as different sources and counters.
+- Re-fetch after acquiring the lock; never certify the enumeration object.
+- Revalidate the snapshot before writing either durable outcome.
+- Keep sidecar content in the version identity.
+- Keep regular-page content hash and effective date in the version identity.
+- Never turn model, insertion, cleanup, cancellation, or parser failures into
+  successful empty extraction.
+- Never classify `no_match` or dry-run output as a durable negative.
+- Do not make operation checkpoints completion authority.
+- Apply work limits after durable filtering.
+- Keep doctor source-scoped by both page and fact `source_id`.
+- Give terminal completion precedence if both current outcome rows exist.
+- Update CLI and cycle aggregation whenever a result counter changes.
+
+## Focused verification
+
+```bash
+bun test test/extract-conversation-facts.test.ts
+bun test test/doctor-conversation-facts-backlog.test.ts
+bun x tsc --noEmit
+```
+
+The focused suite covers checkpoint garbage collection, same-timestamp edits,
+edits during extraction, sidecar-only edits, legacy marker replay, provider and
+insert failures, cleanup failure, recognized non-extractable scans, retryable
+parser misses, post-filter limits, force replay, and doctor accounting.

docs/operations/conversation-parser-llm-fallback.md

@@ -0,0 +1,240 @@
+# Conversation parser LLM fallback
+
+The conversation parser has two stages:
+
+1. A deterministic registry recognizes known transcript formats.
+2. An optional LLM fallback parses pages that every built-in pattern rejects.
+
+The second stage is disabled by default. Enabling it is a privacy decision
+because unmatched transcript text can be sent to the configured utility-tier
+model provider.
+
+## Enable or disable the fallback
+
+Enable it for the current brain:
+
+```bash
+gbrain config set conversation_parser.llm_fallback_enabled true
+```
+
+Disable it:
+
+```bash
+gbrain config set conversation_parser.llm_fallback_enabled false
+```
+
+The key is registered explicitly, so neither command needs `--force`.
+Values other than the exact string `true` leave the fallback disabled.
+
+The setting affects conversation fact extraction. It does not make the
+synchronous `conversation-parser scan` command call a model, and it does not
+enable the separate LLM polish scaffold.
+
+## Select the utility model and run a canary
+
+Inspect the model routing before enabling a production run:
+
+```bash
+gbrain models
+```
+
+The fallback uses the resolved `utility` tier. Override that tier when the
+brain should use a different configured provider or model:
+
+```bash
+gbrain config set models.tier.utility <provider:model>
+```
+
+Start with one known unmatched page and an explicit cost cap:
+
+```bash
+gbrain extract-conversation-facts \
+  --source-id <source-id> \
+  --slug <conversation-slug> \
+  --max-cost-usd 1
+```
+
+Do not add `--dry-run` to this canary. Dry runs deliberately stop before the
+fallback boundary, so they cannot prove provider routing or model output.
+Success emits the per-page fallback log described under
+[Operator visibility](#operator-visibility). After the canary, remove `--slug`
+to process the source normally.
+
+## When the fallback runs
+
+For each eligible conversation page, extraction:
+
+1. Reads the same body used by the deterministic parser, including a configured
+   raw transcript sidecar for meeting pages.
+2. Calls `parseConversation(body, { page })`.
+3. Uses the deterministic messages when any built-in pattern succeeds.
+4. Calls the LLM fallback only when the parse phase is exactly `no_match`, the
+   message list is empty, the opt-in key is `true`, and this is not a dry run.
+5. Splits accepted fallback messages into the normal extraction segments.
+
+The fallback never replaces, edits, or polishes a successful deterministic
+parse. Adding a built-in pattern therefore removes model use for that format
+without changing configuration.
+
+Dry runs remain local and cost-free. They report deterministic segmentation
+only and never send unmatched content to a provider.
+
+## Data sent to the model
+
+The full unmatched body is processed in overlapping windows of at most 100
+non-empty lines, with up to 20 lines of preceding context. Blank lines are
+omitted. Every model request receives:
+
+- an instruction to treat the transcript as untrusted data;
+- an authoritative page date when one can be derived;
+- the sampled transcript inside an explicit chat-log envelope.
+
+The system prompt tells the model not to follow commands or instructions found
+inside transcript content. It asks for message extraction only.
+
+Each window is cached independently. Overlap results with the same normalized
+speaker and timestamp are deduplicated; when one body contains the other, the
+longer body wins. This preserves common multi-line messages that straddle a
+window boundary. If any later window has an ordinary provider or parse failure,
+the fallback returns no page result and extraction does not advance the
+checkpoint. Successful earlier windows stay cached for the retry.
+
+Fallback calls allow up to 8,000 output tokens. Any non-terminal model stop,
+including length truncation, refusal, content filtering, tool use, or an
+unrecognized provider stop, is rejected before parsing and caching. A
+syntactically valid partial JSON array therefore cannot advance a checkpoint.
+
+The utility model is resolved once per source run through the normal model
+configuration chain. The default fallback is the utility-tier Anthropic model.
+
+## Date and timestamp behavior
+
+The fallback uses the deterministic parser's date precedence:
+
+1. an explicit caller date;
+2. `frontmatter.date`;
+3. the page effective date;
+4. `1970-01-01` when no date is known.
+
+A real page date is included in both the prompt and the content-hash cache key.
+Two pages with identical time-only transcript text but different dates cannot
+share a cached parse.
+
+Returned timestamps must be strict RFC3339 date-times with seconds and an
+explicit `Z` or numeric timezone offset. Calendar fields are validated before
+parsing. Accepted timestamps are normalized to whole-second UTC form:
+
+```text
+YYYY-MM-DDTHH:MM:SSZ
+```
+
+Date-only values, timezone-less values, impossible calendar dates, timestamps
+more than 24 hours in the future, blank speakers, and blank message bodies are
+discarded. Valid messages are stable-sorted by timestamp before segmentation.
+Canonical chronological UTC output keeps segment filtering and durable
+checkpoint comparisons stable and prevents future checkpoint poisoning.
+
+If no page date is known, the prompt retains the historical epoch fallback.
+Full timestamps present in the transcript can still be extracted normally.
+
+## Non-chat and failure behavior
+
+The model is instructed to return an empty JSON array for non-chat content.
+An empty response, malformed JSON, unavailable provider, or transport failure
+leaves the page with no messages. Extraction skips that page and continues.
+
+The fallback is fail-open with respect to parser availability. It does not turn
+a model outage into a deterministic-parser outage.
+
+Cancellation and `BudgetExhausted` are control-flow signals, not provider
+failures. The extraction caller explicitly propagates them through the
+fail-open boundary so aborts stay prompt and hard cost caps remain effective.
+An `AbortError` from a provider timeout still fails open while the caller's own
+abort signal remains live.
+
+The gateway can discover an underestimated budget overage only after the final
+provider result. Extraction checks tracker spend against its cap after the run,
+so an overage remains visible even when there is no next model reservation.
+
+## Cache and repeat runs
+
+Successful fallback results use the shared conversation-parser cache:
+
+- an in-process map for repeat calls during one process;
+- the `conversation_parser_llm_cache` table for repeat calls across processes.
+
+Each chunk's cache key includes the call shape, resolved model, page date
+metadata, and chunk content hash. A cached response is still validated before
+it originally enters the cache.
+
+Once fallback messages produce extractable segments, the ordinary per-page
+checkpoint advances to the newest segment timestamp. A later run can read the
+cached parse, apply the checkpoint watermark, and skip already completed
+segments without another provider call.
+
+## Operator visibility
+
+`ExtractConversationFactsResult.pages_llm_fallback` counts pages for which the
+fallback returned at least one valid message. The command also logs:
+
+```text
+[extract-conversation-facts] LLM fallback parsed N message(s) for <slug>
+```
+
+The multi-source CLI summary reports the total number of fallback-parsed pages.
+A zero count means either the fallback was disabled, deterministic patterns
+handled every page, or fallback attempts returned no valid messages.
+
+## Maintainer contracts
+
+Keep these boundaries intact when changing the fallback:
+
+- Default off. Page text must not reach the fallback without the exact opt-in.
+- Never call the provider during `--dry-run`.
+- Deterministic first. Invoke it only for phase `no_match`.
+- One model resolution per source run, not per page.
+- Use `deriveDateContext({ page })` so regex and LLM timestamps share metadata.
+- Put date metadata in the hashed request content to prevent cross-date cache
+  collisions.
+- Process every non-empty line in bounded cached overlapping windows. Preserve
+  common cross-boundary continuations through overlap and deterministic
+  deduplication. Never checkpoint a partial page after a later window fails or
+  returns a non-terminal stop reason.
+- Validate and canonicalize all model-produced fields before segmentation.
+- Stable-sort accepted messages before segmenting or checkpointing them.
+- Keep the exact config key in `KNOWN_CONFIG_KEYS`. Do not register the whole
+  `conversation_parser.*` namespace while other scaffolded keys remain unwired.
+- Preserve `[]` and `null` as skip-page outcomes.
+- Propagate cancellation and budget-stop errors selected by the extraction
+  caller; fail open only for ordinary provider and parse failures.
+- Never persist inferred regexes or promote model guesses into the built-in
+  registry.
+
+## Test coverage
+
+The focused tests cover:
+
+- default-off behavior with zero fallback calls;
+- enabled dry-run behavior with zero provider calls;
+- exact config-key registration;
+- a successful production-path fallback;
+- page-date prompt and cache-key separation;
+- durable checkpoint advancement and cache reuse;
+- complete processing beyond the first 100 non-empty lines;
+- cross-boundary continuation preservation and overlap deduplication;
+- rejection of truncated, refused, and content-filtered model results;
+- all-or-nothing page results when a later chunk fails;
+- non-chat empty arrays and malformed output;
+- strict timestamp normalization, ordering, and invalid-item filtering;
+- provider-unavailable and transport-failure behavior;
+- provider-timeout versus caller-cancellation behavior;
+- thrown and post-record budget-stop reporting.
+
+Run the focused surface with:
+
+```bash
+bun test test/conversation-parser/llm-base.test.ts \
+  test/conversation-parser/llm-fallback.test.ts \
+  test/extract-conversation-facts.test.ts \
+  test/config-set.test.ts
+```

docs/operations/spend-controls.md

@@ -49,6 +49,7 @@ The USD-limit knobs accept `off`, `unlimited`, or `none` (case-insensitive) to m
 | Backfill per-job budget | `embed.backfill_max_usd` | `10` | caps the job's tracker | `off` (`0` → default) | uncapped (still ledgered) |
 | Backfill cooldown | `embed.backfill_cooldown_min` | `10` | skips re-submission inside window | — (latency knob, not spend) | **not** bypassed |
 | `reindex-code` cost gate | — (preview before re-embed) | — | TTY prompt / non-TTY refuse + exit 2 | `--max-cost off` | informational |
+| `migrate embeddings` consent gate | — (plan + estimate before provider migration) | — | TTY y/N prompt / non-TTY refuse + exit 2 | `--yes` | estimate marked informational, but **still prompts** (guards a destructive schema rebuild, not just spend) |
 | `enrich` / `onboard --auto` | `--max-usd` (per-call) | — | refuse without a cap (non-TTY) | `--max-usd off` | runs uncapped (still ledgered) |
 
 ### Sync inline-embed cost gate

docs/progress-events.md

@@ -140,6 +140,9 @@ Stable phase names shipped in v0.15.2:
 - `import.files`
 - `sync.deletes`, `sync.renames`, `sync.imports`
 - `migrate.copy_pages`, `migrate.copy_links`
+- `migrate.reembed` (the re-embed pass of `gbrain migrate embeddings`; total is the
+  stale-chunk backlog at the start of the pass, so it can grow slightly if a
+  writer adds chunks mid-run)
 - `repair_jsonb.run`, `repair_jsonb.<table>.<column>`
 - `backlinks.scan`
 - `lint.pages`

docs/tutorials/README.md

@@ -13,7 +13,7 @@ Step-by-step walkthroughs that take you from zero to a working outcome. Concrete
 
 These are the next tutorials on the roadmap. Open an issue if one of them is the one you need most; that's how we'll prioritize.
 
-- **Set up GBrain for VC dealflow** — the operator's recipe. People pages for founders, companies with typed Facts fence carrying ARR / team-size / runway across dates, meetings auto-ingested, deal pages linking everything. Shows `gbrain whoknows`, `gbrain find_trajectory`, and `gbrain founder scorecard` on real workflows.
+- **Set up GBrain for VC dealflow** — the operator's recipe. People pages for founders, companies with typed Facts fence carrying ARR / team-size / runway across dates, meetings auto-ingested, deal pages linking everything. Shows `gbrain whoknows`, `gbrain find-trajectory`, and `gbrain founder scorecard` on real workflows.
 
 - **Migrate your existing vault into GBrain** — for Notion / Obsidian / Roam users with a vault that doesn't match GBrain's default layout. Walks through `gbrain schema detect` → `suggest` → `review-candidates` so the brain learns your shape instead of forcing you to learn its.
 

docs/tutorials/company-brain.md

@@ -484,6 +484,10 @@ Returns a per-source dashboard: when each source last synced, how many pages, ho
 
 The admin dashboard at `https://brain.acme-co.com/admin` shows live request volume, registered OAuth clients, recent activity, and brain stats. Use the admin bootstrap token from Part 4 to log in the first time, then register additional admin users from inside the dashboard.
 
+### If agents run as containers on the same Docker host
+
+OAuth source scoping only guards the HTTP MCP path. If the brain's Postgres and your teammates' agent runtimes are containers on the same Docker host, make sure the agents can't reach Postgres directly over Docker's default bridge network — a direct DB session skips OAuth entirely. Put Postgres on its own user-defined network, publish it loopback-only if at all, and never hand agent containers a `DATABASE_URL`. The copy-paste operator checklist lives in [docs/mcp/DEPLOY.md — Co-located Docker workloads](../mcp/DEPLOY.md#co-located-docker-workloads-self-hosted-postgres).
+
 ---
 
 ## Part 13: Cost and speed expectations
@@ -550,7 +554,7 @@ What to do next:
 
 - **Wire ingestion** from external systems (Granola, Linear, Slack) using the [ingestion source contract](../skillpack-anatomy.md). Most companies want their meetings auto-ingested so the brain stays current without anyone typing notes.
 - **Set up team-specific dashboards** through the admin UI. Each team lead can have their own view of brain health and activity.
-- **Explore the rest of the brain layer.** `gbrain whoknows` (find the expert on a topic), `gbrain find_trajectory` (how a metric changed over time), `gbrain founder scorecard` (especially useful for VC and ops teams), the contradiction-detection cycle that surfaces conflicts between different people's notes.
+- **Explore the rest of the brain layer.** `gbrain whoknows` (find the expert on a topic), `gbrain find-trajectory` (how a metric changed over time), `gbrain founder scorecard` (especially useful for VC and ops teams), the contradiction-detection cycle that surfaces conflicts between different people's notes.
 
 If you're building in this space (which YC has flagged as the [company-brain category in its Request for Startups](https://www.ycombinator.com/rfs#company-brain)), you might as well build on this. Everything described above is open source, MIT licensed, and what I run in production behind my own AI agents.
 

docs/tutorials/personal-brain.md

@@ -115,21 +115,21 @@ You can use the same keys across multiple agents.
 
 ## Step 6: Install GBrain
 
-Once OpenClaw is running:
+Once OpenClaw is running, installation is two commands — one in the brain repo, one in the agent workspace:
 
 ```bash
-gbrain install
+# In the BRAIN repo (the git repo that holds your markdown pages):
+gbrain init --supabase
+
+# In the AGENT WORKSPACE repo (where OpenClaw runs):
+gbrain skillpack scaffold --all
 ```
 
-This installs:
+`gbrain init --supabase` walks a short wizard that asks for your Supabase connection string and creates the schema. You'll get that connection string in Step 7 — read 7a and 7b first so you paste the right one (the transaction pooler, not the direct connection). If you'd rather try things locally before paying for a database, `gbrain init --pglite` gives you a zero-config embedded engine instead; you can migrate to Supabase later with `gbrain migrate --to supabase`.
 
-- About 60 skills
-- About 9 skill packs
-- Default brain structure
-- MCP server configuration
-- Supabase connection (for embeddings and search)
+`gbrain skillpack scaffold --all` copies the ~43 bundled skills into your agent workspace as first-class files you can edit freely. (The old managed-install model was retired in v0.36.0.0; see `docs/INSTALL.md` if you're upgrading from an older release.)
 
-GBrain populates the brain repo with its default directory structure, skill files, and configuration. From this point, the agent has working memory and access to every skill.
+From this point, the agent has working memory and access to every skill.
 
 ---
 

docs/what-schemas-unlock.md

@@ -32,7 +32,7 @@ gbrain schema sync --apply
 The sync backfills `page.type = 'meeting'` on all 4000 pages in 1000-row batches. Now:
 
 - `gbrain whoknows "Q3 roadmap discussion"` routes through the meeting type, ranking by `expert_routing` signal (attendees, recency, salience) instead of raw text.
-- `gbrain extract-facts` runs on every meeting page automatically (because `extractable: true`), pulling typed facts like `attended_by=alice-example`, `date=2026-05-23`.
+- The `extract_facts` cycle runs on every meeting page automatically (because `extractable: true`), pulling typed facts like `attended_by=alice-example`, `date=2026-05-23`.
 - The downstream `think` skill can now answer "what did we decide about pricing in the last three roadmap meetings" by querying the meeting graph instead of grep'ing 4000 files.
 
 One command. 4000 pages went from invisible to queryable. The content didn't change. The structure did.
@@ -62,7 +62,7 @@ gbrain schema add-link-type led-by      --page-type deal     --target-type inves
 gbrain schema sync --apply
 ```
 
-Now `gbrain whoknows "Series A SaaS"` routes through `investor` and `portco` types specifically, not the noisy general type set. `gbrain graph-query alice-example --type intro-from --depth 2` walks two hops of intros to surface "Alice introduced you to Bob who introduced you to Charlie." `gbrain extract-facts` starts producing typed claims from the fence in your deal pages: `(deals/acme-seed, raise=2000000, valuation=15000000, lead=widget-vc, closed_at=2026-05-23)`.
+Now `gbrain whoknows "Series A SaaS"` routes through `investor` and `portco` types specifically, not the noisy general type set. `gbrain graph-query alice-example --type intro-from --depth 2` walks two hops of intros to surface "Alice introduced you to Bob who introduced you to Charlie." The `extract_facts` cycle starts producing typed claims from the fence in your deal pages: `(deals/acme-seed, raise=2000000, valuation=15000000, lead=widget-vc, closed_at=2026-05-23)`.
 
 The CRM you've been promising yourself you'll set up next quarter? You just shipped it in 4 commands. It's downstream of your notes, not parallel to them.
 
@@ -143,7 +143,7 @@ Re-run the same `whoknows` query. Top-3 should shift, because the new type is no
 
 Three things gbrain does that generic note systems can't:
 
-**1. The brain knows the difference between a person and an idea.** Page-type matters at query time. `gbrain whoknows` only considers `expert_routing: true` types. `gbrain extract-facts` only runs on `extractable: true` types. `gbrain graph-query` walks declared link verbs. None of that works on a flat tag system because tags don't have semantics — they're labels. Types are first-class citizens with rules attached.
+**1. The brain knows the difference between a person and an idea.** Page-type matters at query time. `gbrain whoknows` only considers `expert_routing: true` types. The `extract_facts` cycle only runs on `extractable: true` types. `gbrain graph-query` walks declared link verbs. None of that works on a flat tag system because tags don't have semantics — they're labels. Types are first-class citizens with rules attached.
 
 **2. Untyped content is invisible content.** If your meetings are typed as `note`, expert routing skips them, facts extraction ignores them, link inference doesn't fire. They exist on disk and they're indexed for text search, but the structural surfaces (whoknows, find_experts, recall, think) treat them as second-class. Adding a type isn't cosmetic; it's structural promotion.
 

llms-full.txt

@@ -2316,7 +2316,7 @@ gbrain schema sync --apply
 The sync backfills `page.type = 'meeting'` on all 4000 pages in 1000-row batches. Now:
 
 - `gbrain whoknows "Q3 roadmap discussion"` routes through the meeting type, ranking by `expert_routing` signal (attendees, recency, salience) instead of raw text.
-- `gbrain extract-facts` runs on every meeting page automatically (because `extractable: true`), pulling typed facts like `attended_by=alice-example`, `date=2026-05-23`.
+- The `extract_facts` cycle runs on every meeting page automatically (because `extractable: true`), pulling typed facts like `attended_by=alice-example`, `date=2026-05-23`.
 - The downstream `think` skill can now answer "what did we decide about pricing in the last three roadmap meetings" by querying the meeting graph instead of grep'ing 4000 files.
 
 One command. 4000 pages went from invisible to queryable. The content didn't change. The structure did.
@@ -2346,7 +2346,7 @@ gbrain schema add-link-type led-by      --page-type deal     --target-type inves
 gbrain schema sync --apply
 ```
 
-Now `gbrain whoknows "Series A SaaS"` routes through `investor` and `portco` types specifically, not the noisy general type set. `gbrain graph-query alice-example --type intro-from --depth 2` walks two hops of intros to surface "Alice introduced you to Bob who introduced you to Charlie." `gbrain extract-facts` starts producing typed claims from the fence in your deal pages: `(deals/acme-seed, raise=2000000, valuation=15000000, lead=widget-vc, closed_at=2026-05-23)`.
+Now `gbrain whoknows "Series A SaaS"` routes through `investor` and `portco` types specifically, not the noisy general type set. `gbrain graph-query alice-example --type intro-from --depth 2` walks two hops of intros to surface "Alice introduced you to Bob who introduced you to Charlie." The `extract_facts` cycle starts producing typed claims from the fence in your deal pages: `(deals/acme-seed, raise=2000000, valuation=15000000, lead=widget-vc, closed_at=2026-05-23)`.
 
 The CRM you've been promising yourself you'll set up next quarter? You just shipped it in 4 commands. It's downstream of your notes, not parallel to them.
 
@@ -2427,7 +2427,7 @@ Re-run the same `whoknows` query. Top-3 should shift, because the new type is no
 
 Three things gbrain does that generic note systems can't:
 
-**1. The brain knows the difference between a person and an idea.** Page-type matters at query time. `gbrain whoknows` only considers `expert_routing: true` types. `gbrain extract-facts` only runs on `extractable: true` types. `gbrain graph-query` walks declared link verbs. None of that works on a flat tag system because tags don't have semantics — they're labels. Types are first-class citizens with rules attached.
+**1. The brain knows the difference between a person and an idea.** Page-type matters at query time. `gbrain whoknows` only considers `expert_routing: true` types. The `extract_facts` cycle only runs on `extractable: true` types. `gbrain graph-query` walks declared link verbs. None of that works on a flat tag system because tags don't have semantics — they're labels. Types are first-class citizens with rules attached.
 
 **2. Untyped content is invisible content.** If your meetings are typed as `note`, expert routing skips them, facts extraction ignores them, link inference doesn't fire. They exist on disk and they're indexed for text search, but the structural surfaces (whoknows, find_experts, recall, think) treat them as second-class. Adding a type isn't cosmetic; it's structural promotion.
 
@@ -3897,7 +3897,7 @@ All 30 GBrain operations are available remotely, including `sync_brain` and
 directory where `gbrain serve` was launched. Symlinks, `..` traversal, and absolute
 paths outside cwd are rejected. Page slugs and filenames are allowlist-validated
 (alphanumeric + hyphens; no control chars, RTL overrides, or backslashes). Local
-CLI callers (`gbrain file upload ...`) keep unrestricted filesystem access since
+CLI callers (`gbrain files upload ...`) keep unrestricted filesystem access since
 the user owns the machine.
 
 ## Deployment Options
@@ -3905,6 +3905,43 @@ the user owns the machine.
 See [ALTERNATIVES.md](ALTERNATIVES.md) for a comparison of ngrok, Tailscale
 Funnel, and cloud hosts (Fly.io, Railway).
 
+### Co-located Docker workloads (self-hosted Postgres)
+
+OAuth scopes and source scoping guard the `gbrain serve --http` path. They do
+NOT guard raw Postgres. If the brain's Postgres runs as a container on the same
+Docker host as other workloads (agent runtimes, n8n, staging fixtures), any
+container sharing Docker's default `bridge` network can open a direct DB
+session — no OAuth token required — and read every source. That silently
+recreates a privileged path underneath the isolation you configured at the MCP
+layer.
+
+Network-zone the host so untrusted containers can never reach Postgres:
+
+```
+Docker host
+├── gbrain-net          ← ONLY the brain's Postgres (+ gbrain serve, if containerized)
+├── agent-<id>-net      ← each untrusted agent runtime, isolated
+└── default bridge      ← no secret-bearing databases
+```
+
+Operator checklist:
+
+```text
+[ ] Postgres is on a user-defined Docker network, not the default bridge
+    (or nothing else runs on that bridge)
+[ ] If Postgres publishes a host port at all, it binds loopback only
+    (`-p 127.0.0.1:5432:5432`, never `0.0.0.0`)
+[ ] Untrusted agent containers have no DATABASE_URL or Postgres password
+[ ] Untrusted agents reach the brain via OAuth/Bearer against serve --http only
+    (host loopback via host.docker.internal / host gateway — never gbrain-net)
+[ ] OAuth clients are least-privilege: scoped --source / --federated-read,
+    pre-minted short-lived tokens preferred over long-lived client secrets
+[ ] Isolation verified: a team-scoped client cannot read internal-only sources
+```
+
+Optional defense-in-depth: a dedicated Postgres role (or RLS) limited to the
+allowed `source_id`s, so even a leaked connection string can't read everything.
+
 ## Troubleshooting
 
 **"missing_auth" error**

package.json

@@ -23,6 +23,7 @@
     "./backoff": "./src/core/backoff.ts",
     "./search/hybrid": "./src/core/search/hybrid.ts",
     "./search/expansion": "./src/core/search/expansion.ts",
+    "./think": "./src/core/think/index.ts",
     "./ai/gateway": "./src/core/ai/gateway.ts",
     "./extract": "./src/commands/extract.ts",
     "./ingestion": "./src/core/ingestion/index.ts",
@@ -41,20 +42,20 @@
     "eval:autocut": "bun test test/search/autocut-eval.test.ts",
     "test:full": "bun run verify && bash scripts/run-unit-parallel.sh && bun run test:slow && ([ -n \"$DATABASE_URL\" ] && bash scripts/run-e2e.sh || echo '[test:full] skipped E2E (no DATABASE_URL); run docker-compose -f docker-compose.ci.yml up + bun run test:e2e to include' 1>&2)",
     "verify": "bash scripts/run-verify-parallel.sh",
-    "check:source-config-leak": "scripts/check-source-config-leak.sh",
-    "check:no-pii-agent-voice": "scripts/check-no-pii-in-agent-voice.sh",
-    "check:synthetic-corpus-privacy": "scripts/check-synthetic-corpus-privacy.sh",
-    "check:system-of-record": "scripts/check-system-of-record.sh",
-    "check:admin-scope-drift": "scripts/check-admin-scope-drift.sh",
-    "check:cli-exec": "scripts/check-cli-executable.sh",
-    "check:all": "scripts/check-privacy.sh && scripts/check-proposal-pii.sh && scripts/check-test-real-names.sh && scripts/check-jsonb-pattern.sh && scripts/check-source-id-projection.sh && scripts/check-source-config-leak.sh && scripts/check-progress-to-stdout.sh && scripts/check-no-legacy-getconnection.sh && scripts/check-test-isolation.sh && scripts/check-trailing-newline.sh && scripts/check-wasm-embedded.sh && scripts/check-exports-count.sh && scripts/check-admin-build.sh && scripts/check-admin-scope-drift.sh && scripts/check-cli-executable.sh && scripts/check-skill-brain-first.sh && scripts/check-operations-filter-bypass.sh && scripts/check-gateway-routed-no-direct-anthropic.sh && scripts/check-worker-pool-atomicity.sh && scripts/check-key-files-current-state.sh && scripts/check-no-double-retry.sh && scripts/check-batch-audit-site.sh",
-    "check:gateway-routed": "scripts/check-gateway-routed-no-direct-anthropic.sh",
-    "check:worker-pool-atomicity": "scripts/check-worker-pool-atomicity.sh",
-    "check:doc-history": "scripts/check-key-files-current-state.sh",
+    "check:source-config-leak": "bash scripts/check-source-config-leak.sh",
+    "check:no-pii-agent-voice": "bash scripts/check-no-pii-in-agent-voice.sh",
+    "check:synthetic-corpus-privacy": "bash scripts/check-synthetic-corpus-privacy.sh",
+    "check:system-of-record": "bash scripts/check-system-of-record.sh",
+    "check:admin-scope-drift": "bash scripts/check-admin-scope-drift.sh",
+    "check:cli-exec": "bash scripts/check-cli-executable.sh",
+    "check:all": "bash scripts/check-privacy.sh && bash scripts/check-proposal-pii.sh && bash scripts/check-test-real-names.sh && bash scripts/check-jsonb-pattern.sh && bash scripts/check-source-id-projection.sh && bash scripts/check-source-config-leak.sh && bash scripts/check-progress-to-stdout.sh && bash scripts/check-no-tracked-symlinks.sh && bash scripts/check-no-legacy-getconnection.sh && bash scripts/check-test-isolation.sh && bash scripts/check-trailing-newline.sh && bash scripts/check-wasm-embedded.sh && bash scripts/check-exports-count.sh && bash scripts/check-admin-build.sh && bash scripts/check-admin-scope-drift.sh && bash scripts/check-cli-executable.sh && bash scripts/check-skill-brain-first.sh && bash scripts/check-operations-filter-bypass.sh && bash scripts/check-gateway-routed-no-direct-anthropic.sh && bash scripts/check-worker-pool-atomicity.sh && bash scripts/check-key-files-current-state.sh && bash scripts/check-no-double-retry.sh && bash scripts/check-batch-audit-site.sh",
+    "check:gateway-routed": "bash scripts/check-gateway-routed-no-direct-anthropic.sh",
+    "check:worker-pool-atomicity": "bash scripts/check-worker-pool-atomicity.sh",
+    "check:doc-history": "bash scripts/check-key-files-current-state.sh",
     "check:resolver": "bun src/cli.ts check-resolvable --strict --skills-dir skills/",
-    "check:skill-brain-first": "scripts/check-skill-brain-first.sh",
-    "check:wasm": "scripts/check-wasm-embedded.sh",
-    "check:newlines": "scripts/check-trailing-newline.sh",
+    "check:skill-brain-first": "bash scripts/check-skill-brain-first.sh",
+    "check:wasm": "bash scripts/check-wasm-embedded.sh",
+    "check:newlines": "bash scripts/check-trailing-newline.sh",
     "test:e2e": "bash scripts/run-e2e.sh",
     "test:slow": "bash scripts/run-slow-tests.sh",
     "test:heavy": "bash scripts/run-heavy.sh",
@@ -64,26 +65,27 @@
     "ci:local:diff": "bash scripts/ci-local.sh --diff",
     "ci:select-e2e": "bun run scripts/select-e2e.ts",
     "typecheck": "tsc --noEmit",
-    "check:jsonb": "scripts/check-jsonb-pattern.sh",
-    "check:search-path": "scripts/check-search-path.sh",
-    "check:no-double-retry": "scripts/check-no-double-retry.sh",
-    "check:batch-audit-site": "scripts/check-batch-audit-site.sh",
-    "check:worker-lock-renewal-shape": "scripts/check-worker-lock-renewal-shape.sh",
-    "check:source-id-projection": "scripts/check-source-id-projection.sh",
-    "check:privacy": "scripts/check-privacy.sh",
-    "check:proposal-pii": "scripts/check-proposal-pii.sh",
-    "check:eval-glossary": "scripts/check-eval-glossary-fresh.sh",
-    "check:test-names": "scripts/check-test-real-names.sh",
-    "check:progress": "scripts/check-progress-to-stdout.sh",
-    "check:exports-count": "scripts/check-exports-count.sh",
-    "check:admin-build": "scripts/check-admin-build.sh",
-    "check:admin-embedded": "scripts/check-admin-embedded.sh",
-    "check:test-isolation": "scripts/check-test-isolation.sh",
-    "check:fuzz-purity": "scripts/check-fuzz-purity.sh",
-    "check:operations-filter-bypass": "scripts/check-operations-filter-bypass.sh",
-    "check:fixture-privacy": "scripts/check-fixture-privacy.sh",
+    "check:jsonb": "bash scripts/check-jsonb-pattern.sh",
+    "check:search-path": "bash scripts/check-search-path.sh",
+    "check:no-double-retry": "bash scripts/check-no-double-retry.sh",
+    "check:batch-audit-site": "bash scripts/check-batch-audit-site.sh",
+    "check:worker-lock-renewal-shape": "bash scripts/check-worker-lock-renewal-shape.sh",
+    "check:source-id-projection": "bash scripts/check-source-id-projection.sh",
+    "check:privacy": "bash scripts/check-privacy.sh",
+    "check:proposal-pii": "bash scripts/check-proposal-pii.sh",
+    "check:eval-glossary": "bash scripts/check-eval-glossary-fresh.sh",
+    "check:test-names": "bash scripts/check-test-real-names.sh",
+    "check:progress": "bash scripts/check-progress-to-stdout.sh",
+    "check:no-tracked-symlinks": "bash scripts/check-no-tracked-symlinks.sh",
+    "check:exports-count": "bash scripts/check-exports-count.sh",
+    "check:admin-build": "bash scripts/check-admin-build.sh",
+    "check:admin-embedded": "bash scripts/check-admin-embedded.sh",
+    "check:test-isolation": "bash scripts/check-test-isolation.sh",
+    "check:fuzz-purity": "bash scripts/check-fuzz-purity.sh",
+    "check:operations-filter-bypass": "bash scripts/check-operations-filter-bypass.sh",
+    "check:fixture-privacy": "bash scripts/check-fixture-privacy.sh",
     "check:conversation-parser": "bun src/cli.ts eval conversation-parser test/fixtures/conversation-formats/all.jsonl --no-llm",
-    "check:source-scope-onboard": "scripts/check-source-scope-onboard.sh",
+    "check:source-scope-onboard": "bash scripts/check-source-scope-onboard.sh",
     "postinstall": "bun run scripts/postinstall.ts",
     "prepublish:clawhub": "bun run build:all",
     "publish:clawhub": "clawhub package publish . --family bundle-plugin"
@@ -144,10 +146,11 @@
     "bun": ">=1.3.10"
   },
   "license": "MIT",
-  "version": "0.42.64.0",
+  "version": "0.42.67.0",
   "overrides": {
-    "@hono/node-server": "^1.19.13",
-    "fast-uri": "^3.1.2",
+    "@hono/node-server": "^2.0.5",
+    "fast-uri": "^3.1.4",
+    "body-parser": "^2.3.0",
     "fast-xml-builder": "^1.1.7",
     "fast-xml-parser": "^5.7.0",
     "form-data": "^4.0.6",

scripts/check-exports-count.sh

@@ -19,7 +19,7 @@
 
 set -euo pipefail
 
-EXPECTED_COUNT=20
+EXPECTED_COUNT=21
 
 # Count top-level keys in the exports object. `node -e` parses JSON
 # reliably without needing jq (which isn't in every CI environment).

scripts/check-no-tracked-symlinks.sh

@@ -0,0 +1,67 @@
+#!/usr/bin/env bash
+# CI guard: fail if any symlink is tracked in git.
+#
+# A symlink committed from a build sandbox points at a path that exists on
+# exactly one machine. Everywhere else the checkout produces a dangling
+# link, and anything that opens it fails. That is not hypothetical: commit
+# faf5cdba landed `node_modules -> /tmp/fleet/repo/node_modules`, which made
+# `bun install` abort with `ENOENT: could not open the "node_modules"
+# directory` on every fresh clone, and took `gbrain upgrade`'s bun-link path
+# down with it (the auto-upgrade runs `bun install`, so the printed manual
+# fallback failed the same way).
+#
+# .gitignore alone does not prevent this. A `node_modules/` pattern with a
+# trailing slash matches directories ONLY, so a symlink of the same name is
+# never ignored. Dropping the slash closes that hole, but `git add -f` still
+# walks straight past it. This guard is the backstop.
+#
+# The repo has no legitimate tracked symlinks, so the allowlist starts
+# empty. If you ever need one, add its exact repo-relative path to ALLOWLIST
+# below and explain why — a relative link that resolves inside the repo is
+# defensible; an absolute one almost never is.
+#
+# Usage: scripts/check-no-tracked-symlinks.sh
+# Exit:  0 when clean, 1 when a tracked symlink is found.
+
+set -euo pipefail
+
+ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
+cd "$ROOT"
+
+# Paths permitted to be tracked symlinks. Empty by design.
+ALLOWLIST=()
+
+# Git records symlinks with mode 120000. Field 4 of `ls-files -s` is the path
+# (tab-separated from the stage number), so cut on the tab to keep paths with
+# spaces intact.
+found="$(git ls-files -s | awk '$1 == "120000"' | cut -f2- || true)"
+
+if [ -n "$found" ]; then
+  filtered="$found"
+  for f in "${ALLOWLIST[@]:-}"; do
+    [ -z "$f" ] && continue
+    filtered="$(echo "$filtered" | grep -vxF "$f" || true)"
+  done
+
+  if [ -n "$filtered" ]; then
+    echo "ERROR: symlink(s) tracked in git:"
+    echo
+    while IFS= read -r path; do
+      [ -z "$path" ] && continue
+      target="$(git cat-file blob ":$path" 2>/dev/null || echo '<unreadable>')"
+      echo "  $path -> $target"
+    done <<< "$filtered"
+    echo
+    echo "A committed symlink resolves on the machine that created it and"
+    echo "nowhere else. Untrack it:"
+    echo
+    echo "  git rm --cached <path>"
+    echo
+    echo "If the path is build output (node_modules, dist, bin), also confirm"
+    echo "it is covered by .gitignore WITHOUT a trailing slash — a trailing"
+    echo "slash matches directories only and lets the symlink through."
+    exit 1
+  fi
+fi
+
+echo "check-no-tracked-symlinks: OK (no tracked symlinks)"

scripts/check-wasm-embedded.sh

@@ -19,13 +19,25 @@ set -euo pipefail
 REPO_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
 cd "$REPO_ROOT"
 
-OUT_BIN="$(mktemp /tmp/gbrain-wasm-check.XXXXXX)"
-trap 'rm -f "$OUT_BIN"' EXIT
+# Build from a container-local copy. On Docker Desktop, Bun canonicalizes a
+# bind-mounted input to /run/host_virtiofs but keeps /app as the output path;
+# its final atomic rename then fails with ENOENT even though both names refer
+# to the same mount. Keeping inputs and output under /tmp avoids that alias.
+BUILD_DIR="$(mktemp -d /tmp/gbrain-wasm-check.XXXXXX)"
+OUT_BIN="$BUILD_DIR/chunker-smoketest"
+trap 'rm -rf "$BUILD_DIR"' EXIT
+mkdir -p "$BUILD_DIR/scripts"
+cp -R "$REPO_ROOT/src" "$BUILD_DIR/src"
+cp "$REPO_ROOT/scripts/chunker-smoketest.ts" "$BUILD_DIR/scripts/chunker-smoketest.ts"
+ln -s "$REPO_ROOT/node_modules" "$BUILD_DIR/node_modules"
 
 # Build a minimal smoketest binary that imports the chunker. We compile this
 # instead of the full gbrain CLI so the failure mode is laser-focused on
 # chunker + WASM path resolution, not unrelated CLI wiring.
-bun build --compile --outfile "$OUT_BIN" scripts/chunker-smoketest.ts >/dev/null 2>&1
+if ! (cd "$BUILD_DIR" && bun build --compile --outfile "$OUT_BIN" scripts/chunker-smoketest.ts >/dev/null); then
+  echo "[check-wasm-embedded] FAIL: bun could not compile the smoketest binary." >&2
+  exit 1
+fi
 
 # Run it and capture JSON output.
 OUTPUT="$("$OUT_BIN" 2>&1)"

scripts/ci-local.sh

@@ -350,7 +350,7 @@ if [ -f .git ]; then
 fi
 
 echo "[ci-local] Running checks inside runner container..."
-docker compose -f "$COMPOSE_FILE" run --rm "${EXTRA_MOUNTS[@]:-}" runner bash -c "$INNER_CMD"
+docker compose -f "$COMPOSE_FILE" run --rm "${EXTRA_MOUNTS[@]}" runner bash -c "$INNER_CMD"
 
 echo ""
 echo "[ci-local] All checks passed."

scripts/e2e-test-map.ts

@@ -42,8 +42,19 @@ export const E2E_TEST_MAP: Record<string, string[]> = {
   // phase, extract, integrity, embed, or migrate-engine change.
   "src/core/cycle/extract-takes.ts": ["test/e2e/multi-source-bug-class.test.ts"],
   "src/core/cycle/patterns.ts": ["test/e2e/multi-source-bug-class.test.ts"],
-  "src/core/cycle/synthesize.ts": ["test/e2e/multi-source-bug-class.test.ts"],
-  "src/commands/embed.ts": ["test/e2e/multi-source-bug-class.test.ts"],
+  "src/core/cycle/synthesize.ts": [
+    "test/e2e/multi-source-bug-class.test.ts",
+    "test/e2e/synthesize-bigint-job-id-postgres.test.ts",
+  ],
+  "src/commands/embed.ts": [
+    "test/e2e/multi-source-bug-class.test.ts",
+    // #3391: the NULL-signature stale predicates differ per engine.
+    "test/e2e/migrate-embeddings-postgres.test.ts",
+  ],
+  // #3390: runSchemaTransition's DDL path + the stale predicates behave
+  // differently on real pgvector than on PGLite.
+  "src/core/embedding-migration.ts": ["test/e2e/migrate-embeddings-postgres.test.ts"],
+  "src/core/retrieval-upgrade-planner.ts": ["test/e2e/migrate-embeddings-postgres.test.ts"],
   "src/commands/extract.ts": ["test/e2e/multi-source-bug-class.test.ts"],
   "src/commands/migrate-engine.ts": ["test/e2e/multi-source-bug-class.test.ts"],
   // Any minions queue/worker/handler change exercises all minion E2E.
@@ -61,6 +72,8 @@ export const E2E_TEST_MAP: Record<string, string[]> = {
     "test/e2e/jsonb-roundtrip.test.ts",
     "test/e2e/engine-parity.test.ts",
     "test/e2e/schema-drift.test.ts",
+    // #3391: includeNullSignature stale predicates (engine parity).
+    "test/e2e/migrate-embeddings-postgres.test.ts",
   ],
   // PGLite bootstrap path + parity guard.
   "src/core/pglite-engine.ts": [

scripts/run-unit-parallel.sh

@@ -133,6 +133,7 @@ for i in $(seq 1 "$N"); do
         env SHARD="$i/$N" \
         bash scripts/run-unit-shard.sh --max-concurrency="$INTRA_CONC" \
         > "$SHARD_LOG" 2>&1
+      rc=$?
     else
       env SHARD="$i/$N" \
         bash scripts/run-unit-shard.sh --max-concurrency="$INTRA_CONC" \
@@ -142,10 +143,20 @@ for i in $(seq 1 "$N"); do
         sleep 5 && kill -KILL "$pid" 2>/dev/null ) &
       cap_pid=$!
       wait "$pid" 2>/dev/null
+      # Capture the shard's exit code from ITS `wait`, before any watchdog
+      # teardown runs. The teardown commands below overwrite $? — the killed
+      # watchdog reports 143 — which used to get stamped into every shard's
+      # sentinel on machines with no gtimeout/timeout: every run "failed"
+      # with rc=143 summaries even when all tests passed.
+      rc=$?
+      # Reap the watchdog's `sleep` child too (pkill -P), then the watchdog.
+      # Killing only the subshell leaves the sleep orphaned until
+      # $SHARD_TIMEOUT elapses — same quirk the heartbeat cleanup below works
+      # around; CI's orphan-process sweep flags those.
+      pkill -P "$cap_pid" 2>/dev/null
       kill "$cap_pid" 2>/dev/null
       wait "$cap_pid" 2>/dev/null
     fi
-    rc=$?
     echo "$rc" > "$LOG_DIR/shard-$i.exit"
     [ "$rc" = "124" ] && echo "WEDGED" > "$LOG_DIR/shard-$i.wedged"
   ) &

scripts/run-verify-parallel.sh

@@ -42,6 +42,7 @@ CHECKS=(
   "check:source-id-projection"
   "check:source-config-leak"
   "check:progress"
+  "check:no-tracked-symlinks"
   "check:test-isolation"
   "check:wasm"
   "check:admin-build"
@@ -126,6 +127,7 @@ for c in "${CHECKS[@]}"; do
   (
     if [ -n "$TIMEOUT_BIN" ]; then
       "$TIMEOUT_BIN" "${TIMEOUT}s" bun run "$c" > "$LOG_FILE" 2>&1
+      rc=$?
     else
       bun run "$c" > "$LOG_FILE" 2>&1 &
       pid=$!
@@ -133,10 +135,20 @@ for c in "${CHECKS[@]}"; do
         sleep 5 && kill -KILL "$pid" 2>/dev/null ) &
       cap_pid=$!
       wait "$pid" 2>/dev/null
+      # Capture the check's exit code from ITS `wait`, before any watchdog
+      # teardown runs. The teardown commands below overwrite $? — the killed
+      # watchdog reports 143 — which used to get stamped into every sentinel
+      # on machines with no gtimeout/timeout: verify reported pass=0
+      # fail=<all> while every per-check log said OK.
+      rc=$?
+      # Reap the watchdog's `sleep` child too (pkill -P), then the watchdog.
+      # Killing only the subshell leaves the sleep orphaned until $TIMEOUT
+      # elapses — same quirk the heartbeat cleanup in run-unit-parallel.sh
+      # works around; CI's orphan-process sweep flags those.
+      pkill -P "$cap_pid" 2>/dev/null
       kill "$cap_pid" 2>/dev/null
       wait "$cap_pid" 2>/dev/null
     fi
-    rc=$?
     echo "$rc" > "$EXIT_FILE"
   ) &
   PIDS+=($!)

skills/book-mirror/SKILL.md

@@ -248,7 +248,7 @@ before submission.
 After the brain page is written, render to PDF using `skills/brain-pdf`:
 
 ```bash
-gbrain put_page  # already done by the CLI; nothing to add here
+gbrain put  # already done by the CLI; nothing to add here
 # Then invoke brain-pdf:
 # (see skills/brain-pdf/SKILL.md for the make-pdf invocation)
 ```

skills/conventions/cron-via-minions.md

@@ -73,13 +73,13 @@ stock worker auto-loads on startup) registers handlers before `start()`.
 Users who set `minion_mode: off` in `~/.gbrain/preferences.json` keep
 using `agentTurn`. Respect that. No auto-rewrite.
 
-## Forward note (v0.12.0)
+## Forward note
 
-GBrain v0.12.0 ships `gbrain cron`: a scheduler loop inside
-`gbrain jobs work` that owns cron expressions natively — no more
-handing off to host schedulers. Until v0.12.0 lands, the host
-scheduler keeps firing on schedule; v0.11.1 only replaces the execution
-layer (what the cron trigger *does*), not the scheduling layer.
+A native scheduler loop inside `gbrain jobs work` (owning cron
+expressions directly, with no host-scheduler hand-off) has been on the
+roadmap since v0.11.1 but has not shipped. The host scheduler keeps
+firing on schedule; this convention only replaces the execution layer
+(what the cron trigger *does*), not the scheduling layer.
 
 ## Related
 

skills/data-research/SKILL.md

@@ -54,8 +54,8 @@ Ask the user what they want to track. Either:
 - Define a custom recipe with: source queries, classification rules, extraction schema,
   tracker page path, tracker format
 
-Recipes are YAML files at `~/.gbrain/recipes/{name}.yaml`. Use `gbrain research init`
-to scaffold a new one.
+Recipes are YAML files at `~/.gbrain/recipes/{name}.yaml`. Scaffold a new one by
+copying a built-in recipe file and editing its fields.
 
 ### Phase 2: Search Sources
 

skills/eiirp/SKILL.md

@@ -201,7 +201,7 @@ Use the brain page template. MUST include:
 
 ### 4b. Entity pages (people, companies)
 For each entity mentioned:
-- Check if a brain page exists (`gbrain search "<name>"` or `gbrain get_page people/<slug>`).
+- Check if a brain page exists (`gbrain search "<name>"` or `gbrain get people/<slug>`).
 - If exists: update State, append Timeline entry citing this research.
 - If not: create with enrichment.
 

skills/perplexity-research/SKILL.md

@@ -112,7 +112,7 @@ gbrain query "<topic keywords>"
 #      -d '{"model": "sonar-pro", "messages": [{"role":"user","content":"..."}]}'
 
 # 4. Write the structured research page via put_page:
-gbrain put_page research/<slug>      # via the put_page operation
+gbrain put research/<slug>      # via the put_page operation
 
 # 5. Cross-link entities mentioned (people, companies) per Iron Law.
 ```

skills/schema-unify/SKILL.md

@@ -11,7 +11,7 @@ tools:
   - gbrain schema active
   - gbrain schema use
   - gbrain schema stats
-  - gbrain pages restore
+  - gbrain restore
   - mcp:run_onboard
 triggers:
   - "unify my types"
@@ -143,7 +143,7 @@ WHERE source_id = 'default' AND frontmatter->>'legacy_type' IS NOT NULL;
 Page-to-alias and page-to-link source pages soft-delete with 72h TTL. Restore within that window:
 
 ```bash
-gbrain pages restore <slug>
+gbrain restore <slug>
 ```
 
 Revert the active pack flip:
@@ -197,7 +197,7 @@ Outputs:
 - Active pack flipped to `gbrain-base-v2` atomically at end of successful run.
 
 Side effects:
-- Source pages soft-deleted with 72h restore TTL (`gbrain pages restore <slug>`).
+- Source pages soft-deleted with 72h restore TTL (`gbrain restore <slug>`).
 - One-time cache invalidation on KNOBS_HASH_VERSION bump (5→6); self-healing in `cache.ttl_seconds`.
 - Query-time `--type X` alias-expands via `expandTypeFilter` (D14 back-compat).
 
@@ -212,7 +212,7 @@ DON'T:
 - Submit `unify-types` directly via the MCP `submit_job` op without `--allow-protected`. PROTECTED handlers require trusted local callers; remote MCP rejection is the intentional trust boundary.
 - Edit `mapping_rules` in `gbrain-base-v2.yaml` to skip clusters you don't trust. Fork the pack instead (`gbrain schema fork`) so the source-of-truth migration stays consistent across brains.
 - Run `unify-types` from inside an autopilot tick. The check is `manual_only` per D17 — autopilot deliberately never auto-fires it because pack upgrades are one-time consenting taxonomy decisions.
-- Hard-delete soft-deleted source pages before the 72h restore window. Use `gbrain pages restore <slug>` first if rollback is needed.
+- Hard-delete soft-deleted source pages before the 72h restore window. Use `gbrain restore <slug>` first if rollback is needed.
 - Assume `frontmatter.legacy_type` survives every roundtrip. The marker is canonical for the immediate post-migration window; downstream re-imports may overwrite it.
 
 ## Output Format

skills/skillify/SKILL.md

@@ -60,7 +60,14 @@ Before skillifying, check:
 - Is there >20 lines of logic? (Trivial helpers don't need full infrastructure)
 - Does it have a clear trigger phrase a user would actually say?
 
-If no to all three, it's a script, not a skill. Move on.
+If ANY answer is no, it's a script, not a skill — stop here. Do not scaffold, write a SKILL.md, run evals, or write tests for it. Tell the user why and move on.
+
+Scope check (upper bound): one skill = one capability = one coherent trigger
+family. If the target spans multiple distinct intents users would invoke
+separately ("run the build" / "roll back the deploy" / "notify the team" are
+three intents, not one), do NOT build one skill covering them all. Stop,
+propose splitting into separate skillify targets, and ask the user which one
+to skillify first.
 
 ## Phase 1: Audit
 

skills/voice-note-ingest/SKILL.md

@@ -43,8 +43,9 @@ The Analysis section can interpret; the transcript section is sacred.
 
 The user sends an audio or voice message via any channel (Telegram, voice
 memo upload, openclaw audio attachment). The host agent typically provides
-the transcript text. If not, transcribe via `gbrain transcription` (Groq
-Whisper by default; OpenAI fallback for audio > 25MB segmented via ffmpeg).
+the transcript text. If not, transcribe it with your host's transcription
+tool (Groq Whisper is fast and cheap; OpenAI Whisper works too — segment
+audio > 25MB via ffmpeg first).
 
 ## The pipeline
 
@@ -52,8 +53,9 @@ Whisper by default; OpenAI fallback for audio > 25MB segmented via ffmpeg).
 1. STORE       → Upload original audio to gbrain storage backend
                  (S3 / Supabase Storage / local — pluggable per
                  src/core/storage.ts).
-2. TRANSCRIBE  → Use the agent-provided transcript verbatim, OR call
-                 gbrain transcription if no transcript was supplied.
+2. TRANSCRIBE  → Use the agent-provided transcript verbatim, OR
+                 transcribe the audio yourself (see "When to invoke")
+                 if no transcript was supplied.
 3. ROUTE       → Apply the decision tree (below) to find the right
                  destination directory.
 4. WRITE       → Create / update the destination brain page; preserve the

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 2026-05-27.
+// Source: admin/dist/ at 2026-07-24.
 //
 // Bun resolves the file: imports to a path that works at runtime even
 // inside a compiled binary (`bun build --compile`). The manifest maps
 // the request path the express handler sees to (resolved-path, mime).
 
 // @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
-import A_0_assets_index_CoGEje3__js from '../admin/dist/assets/index-CoGEje3-.js' with { type: 'file' };
+import A_0_assets_index_CviJXT_1_js from '../admin/dist/assets/index-CviJXT-1.js' with { type: 'file' };
 // @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
 import A_1_assets_index_GxkWX7v3_css from '../admin/dist/assets/index-GxkWX7v3.css' with { type: 'file' };
 // @ts-ignore — type: 'file' is Bun ESM, not in lib.d.ts
@@ -19,7 +19,7 @@ export interface AdminAsset {
 }
 
 export const ADMIN_ASSETS: Record<string, AdminAsset> = {
-  "/admin/assets/index-CoGEje3-.js": { path: A_0_assets_index_CoGEje3__js as unknown as string, mime: "application/javascript; charset=utf-8" },
+  "/admin/assets/index-CviJXT-1.js": { path: A_0_assets_index_CviJXT_1_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

@@ -9,7 +9,7 @@ installSigchldHandler();
 import { installSignalHandlers as installCleanupSignalHandlers } from './core/process-cleanup.ts';
 installCleanupSignalHandlers();
 
-import { readFileSync, existsSync, unlinkSync } from 'fs';
+import { readFileSync, existsSync, unlinkSync, fstatSync } from 'fs';
 import { spawn } from 'child_process';
 import {
   readUpdateCache,
@@ -24,6 +24,7 @@ import type { GBrainConfig } from './core/config.ts';
 import type { AIGatewayConfig } from './core/ai/types.ts';
 import type { BrainEngine } from './core/engine.ts';
 import { operations, OperationError } from './core/operations.ts';
+import { resolveSourceIdEngineFree } from './core/source-resolver.ts';
 import { formatVolunteeredPage } from './core/context/volunteer.ts';
 import type { Operation, OperationContext } from './core/operations.ts';
 import { shouldForceExitAfterMain, finishCliTeardown, flushThenExit, currentExitCode, setCliExitVerdict } from './core/cli-force-exit.ts';
@@ -54,12 +55,17 @@ 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', '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']);
+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', 'retrieval-upgrade', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector', 'pages', 'bench', 'backfill']);
 // 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.
 const CLI_ONLY_SELF_HELP = new Set([
   'upgrade', 'post-upgrade', 'check-update',
+  // #3502 sweep: pages + bench print their own usage (pages.ts printHelp,
+  // bench-publish.ts printHelp). Both were documented but undispatchable —
+  // `pages` had a live handleCliOnly case but was missing from CLI_ONLY
+  // (the #2035 calibration bug class); `bench` was never wired at all.
+  'pages', 'bench',
   'embed', 'config',
   'skillpack', 'skillpack-check',
   'integrations', 'friction',
@@ -106,6 +112,10 @@ const CLI_ONLY_SELF_HELP = new Set([
   // `gbrain connect --help` prints its own usage (flags + examples) from
   // runConnect; route around the generic one-line short-circuit.
   'connect',
+  // #3390 — `gbrain migrate embeddings --help` / `gbrain retrieval-upgrade
+  // --help` print the migration flags from runMigrateEmbeddings. `migrate`
+  // (engine transfer) keeps its own dispatch too.
+  'migrate', 'retrieval-upgrade',
 ]);
 
 // v114 (#1941): alias -> operation lookup, kept separate from `cliOps` so
@@ -339,6 +349,11 @@ async function main() {
   // them out of the engine try/catch is safe and unlocks routing.
   const params = parseOpArgs(op, subArgs);
 
+  // #3513: stdin fill moved out of parseOpArgs so a non-TTY stdin with no
+  // piped input can't block the parse forever — the bounded read leaves the
+  // param unset on timeout and the required-param check below fails fast.
+  await applyStdinParam(op, params);
+
   // v0.27.1 (`gbrain query --image <path>`): swap the `image` param from
   // a filesystem path into base64 bytes + mime. The op accepts base64; the
   // CLI accepts a path. Helper is exported so tests can exercise the
@@ -384,6 +399,15 @@ async function main() {
     if (op.localOnly) {
       refuseThinClient(command, cfgPre!.remote_mcp!.mcp_url);
     }
+    // #2098: the local path resolves --source / GBRAIN_SOURCE / .gbrain-source
+    // inside makeContext (ctx.sourceId), which this route never reaches — so
+    // scope must be mapped onto the op's source_id wire param before the call.
+    try {
+      applyThinClientSourceScope(op, params);
+    } catch (e: unknown) {
+      console.error(e instanceof Error ? e.message : String(e));
+      process.exit(1);
+    }
     await runThinClientRouted(op, params, cfgPre!, cliOpts);
     return;
   }
@@ -790,21 +814,157 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
     }
   }
 
-  // Read stdin for content params
-  if (op.cliHints?.stdin && !params[op.cliHints.stdin] && !process.stdin.isTTY) {
-    const stdinContent = readFileSync(0, 'utf-8');
-    const MAX_STDIN = 5_000_000; // 5MB
-    if (Buffer.byteLength(stdinContent, 'utf-8') > MAX_STDIN) {
-      console.error(`Error: stdin content exceeds ${MAX_STDIN} bytes. Split into smaller inputs.`);
-      process.exit(1);
-    }
-    params[op.cliHints.stdin] = stdinContent;
-  }
-
   return params;
 }
 
-async function makeContext(engine: BrainEngine, params: Record<string, unknown>): Promise<OperationContext> {
+/**
+ * #3513: read stdin into an op's stdin-capable param without ever blocking
+ * forever. The old inline `readFileSync(0)` in parseOpArgs assumed non-TTY
+ * implies piped content; a non-TTY stdin with NO input (CI step, cron job,
+ * agent harness holding an unwritten pipe open) blocked the read until kill.
+ *
+ * Strategy by fd kind (fstat):
+ *  - TTY: skip, as before (interactive input is not an op-param source).
+ *  - regular file / /dev/null / anything not a pipe or socket: readFileSync
+ *    returns without blocking (`gbrain put x < file`, `< /dev/null` → '').
+ *  - FIFO/socket: stream-read with a deadline on the FIRST byte only. A real
+ *    pipe (`echo foo | gbrain put x`, heredocs) delivers its first byte
+ *    within milliseconds; once any data arrives the deadline is lifted and
+ *    we read to EOF like readFileSync did (slow producers stay supported).
+ *    An empty-but-closed pipe (`: | gbrain put x`) EOFs immediately → ''.
+ *    A pipe that never delivers a byte times out → param stays unset, so
+ *    the existing required-param usage error fires (fail fast, exit 1).
+ *
+ * GBRAIN_STDIN_TIMEOUT_MS overrides the first-byte deadline (default 5000).
+ * Exported for tests; called by the op dispatch right after parseOpArgs.
+ */
+export async function applyStdinParam(
+  op: Operation,
+  params: Record<string, unknown>,
+): Promise<void> {
+  // Branch shape (stdin hint + missing param + `!process.stdin.isTTY` gate +
+  // 5MB cap) is pinned by the R4 regression test for PR #1325's Windows fix
+  // (test/cycle/regression-pr-wave-r1-r2-r4.test.ts) — keep the spelling.
+  if (op.cliHints?.stdin && !params[op.cliHints.stdin] && !process.stdin.isTTY) {
+    const content = await readStdinBounded();
+    if (content === null) return; // no input arrived — let the required-param check fail fast
+    const MAX_STDIN = 5_000_000; // 5MB
+    if (Buffer.byteLength(content, 'utf-8') > MAX_STDIN) {
+      console.error(`Error: stdin content exceeds ${MAX_STDIN} bytes. Split into smaller inputs.`);
+      process.exit(1);
+    }
+    params[op.cliHints.stdin] = content;
+  }
+}
+
+/** First-byte deadline for pipe/socket stdin (#3513). Env-overridable escape hatch. */
+function stdinFirstByteTimeoutMs(): number {
+  const n = Number(process.env.GBRAIN_STDIN_TIMEOUT_MS);
+  return Number.isFinite(n) && n > 0 ? n : 5000;
+}
+
+/**
+ * Returns the full stdin content, '' for a readable-but-empty stdin, or
+ * null when stdin is a pipe/socket that never delivered a byte within the
+ * first-byte deadline (or the fd is closed/unreadable).
+ */
+export async function readStdinBounded(): Promise<string | null> {
+  let isPipeOrSocket: boolean;
+  try {
+    const st = fstatSync(0);
+    isPipeOrSocket = st.isFIFO() || st.isSocket();
+  } catch {
+    return null; // closed/invalid fd — treat as no input
+  }
+  if (!isPipeOrSocket) {
+    // Regular file redirect, /dev/null, etc. — read returns without blocking.
+    try {
+      return readFileSync(0, 'utf-8');
+    } catch {
+      return null;
+    }
+  }
+  return await new Promise<string | null>((resolve) => {
+    const chunks: Buffer[] = [];
+    let gotData = false;
+    const timer = setTimeout(() => {
+      if (!gotData) {
+        process.stdin.destroy();
+        resolve(null);
+      }
+    }, stdinFirstByteTimeoutMs());
+    const finish = () => {
+      clearTimeout(timer);
+      resolve(Buffer.concat(chunks).toString('utf-8'));
+    };
+    process.stdin.on('data', (c: Buffer) => {
+      if (!gotData) {
+        gotData = true;
+        clearTimeout(timer); // deadline applies to the FIRST byte only
+      }
+      chunks.push(c);
+    });
+    process.stdin.once('end', finish);
+    process.stdin.once('error', finish);
+  });
+}
+
+/**
+ * #2098: thin-client source scoping. Locally, --source / GBRAIN_SOURCE /
+ * .gbrain-source resolve to ctx.sourceId in makeContext; the thin-client
+ * route short-circuits before that, so `gbrain query --source X` against a
+ * remote brain silently searched unscoped. This runs the engine-free tiers
+ * (flag → env → dotfile; the DB-backed tiers can't run without an engine —
+ * the server's grant scoping covers the rest) and maps the result onto the
+ * op's `source_id` wire param.
+ *
+ * Ops that declare their OWN `source` param (facts add, etc.) are left
+ * untouched — their --source is an op param, not scope. An explicit --source
+ * on an op with no source_id wire param throws (loud beats silent drop);
+ * ambient env/dotfile scope with nowhere to send it is ignored, matching the
+ * pre-fix behavior for non-scopeable ops. Exported for tests.
+ */
+// Ops whose `source_id` wire param is NOT read-scope semantics: get_skill's
+// source_id flips the lookup from host catalog to brain-resident-pack
+// (getResidentSkillDetail). Ambient env/dotfile scope must never leak into
+// these; an explicit --source-id still passes through untouched above.
+const NON_SCOPE_SOURCE_ID_OPS = new Set(['get_skill']);
+
+export function applyThinClientSourceScope(
+  op: Operation,
+  params: Record<string, unknown>,
+  cwd?: string,
+): void {
+  if ('source' in op.params) return; // the op owns --source; not a scope flag
+  const explicit = typeof params.source === 'string' && params.source.length > 0
+    ? (params.source as string)
+    : null;
+  delete params.source; // never a wire param on these ops — don't leak it
+  // Explicit per-call scope already on the wire wins over ambient tiers.
+  if (params.source_id !== undefined || params.all_sources === true) {
+    if (explicit) {
+      throw new Error('Pass either --source or --source-id/--all-sources, not both.');
+    }
+    return;
+  }
+  const resolved = resolveSourceIdEngineFree(explicit, cwd);
+  if (!resolved) return;
+  if (!('source_id' in op.params) || NON_SCOPE_SOURCE_ID_OPS.has(op.name)) {
+    if (explicit) {
+      const hint = NON_SCOPE_SOURCE_ID_OPS.has(op.name)
+        ? `(its source_id parameter is not a scope filter; pass --source-id explicitly if you mean it)`
+        : `(the remote op has no source_id parameter; the server scopes it to your grant)`;
+      throw new Error(
+        `gbrain ${op.cliHints?.name || op.name} does not accept --source on a thin-client install ${hint}.`,
+      );
+    }
+    return; // ambient env/dotfile scope with nowhere to send it
+  }
+  params.source_id = resolved;
+}
+
+// Exported for tests (same import-safety contract as applyThinClientSourceScope).
+export async function makeContext(engine: BrainEngine, params: Record<string, unknown>): Promise<OperationContext> {
   // v0.31.8 (D11): resolve sourceId via the canonical 6-tier chain. Honors
   // --source / GBRAIN_SOURCE / .gbrain-source / path-match / brain default /
   // 'default'. Wrapped in try/catch so a doctor / single-source brain that
@@ -816,16 +976,21 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
   // trusted local boundary) and consumed by federatedSearchScope in
   // operations.ts, which additionally gates on ctx.remote === false.
   let localFederated: string[] | undefined;
+  // params.source is set when a CLI flag was parsed for the op (rare; most
+  // CLI ops don't take --source). Falls through to env/dotfile/path-match.
+  const explicit = (params.source as string | undefined) ?? null;
   try {
     const { resolveSourceWithTier, localFederatedSourceIds } = await import('./core/source-resolver.ts');
-    // params.source is set when a CLI flag was parsed for the op (rare; most
-    // CLI ops don't take --source). Falls through to env/dotfile/path-match.
-    const explicit = (params.source as string | undefined) ?? null;
     const resolved = await resolveSourceWithTier(engine, explicit);
     sourceId = resolved.source_id;
     localFederated = await localFederatedSourceIds(engine, resolved.source_id, resolved.tier);
-  } catch {
-    // Source resolution failed (e.g. sources table doesn't exist on a fresh
+  } catch (err) {
+    // #1712: an EXPLICIT --source that fails to resolve (invalid id, or a
+    // source that doesn't exist) must error loudly — the blanket swallow
+    // turned `--source __all__` and typos into a silent `default` scope,
+    // which is how three bug reports became debugging sessions.
+    if (explicit) throw err;
+    // Ambient resolution failed (e.g. sources table doesn't exist on a fresh
     // pre-init brain). Leave sourceId unset; engine read methods fall through
     // to the cross-source view (D16 back-compat path).
     sourceId = undefined;
@@ -991,7 +1156,7 @@ export function formatResult(opName: string, result: unknown): string {
  * `runRemoteDoctor` for thin-client installs.
  */
 const THIN_CLIENT_REFUSED_COMMANDS = new Set([
-  'sync', 'embed', 'extract', 'extract-conversation-facts', 'enrich', 'migrate', 'apply-migrations',
+  'sync', 'embed', 'extract', 'extract-conversation-facts', 'enrich', 'migrate', 'retrieval-upgrade', 'apply-migrations',
   'repair-jsonb', 'orphans', 'integrity', 'serve',
   // v0.43 (#2095): watch streams against a LOCAL engine; thin clients get
   // the volunteer_context MCP op instead.
@@ -1038,6 +1203,7 @@ const THIN_CLIENT_REFUSE_HINTS: Record<string, string> = {
   'extract-conversation-facts': 'extract-conversation-facts runs on the host (requires local engine + chat gateway). Run on the host machine.',
   enrich: 'enrich runs on the host (requires local engine + chat gateway for grounded synthesis). Run on the host machine.',
   migrate: "migrate runs on the host's local engine. Run on the host machine.",
+  'retrieval-upgrade': "retrieval-upgrade (embedding migration) rebuilds the host brain's schema + re-embeds. Run on the host machine.",
   'apply-migrations': 'schema migrations run on the host. SSH and run there.',
   'repair-jsonb': 'repair-jsonb operates on the local DB only.',
   integrity: 'integrity scans local files. Run on the host machine.',
@@ -1104,6 +1270,20 @@ async function handleCliOnly(command: string, args: string[]) {
     await runInit(args);
     return;
   }
+  if (command === 'bench') {
+    // #3502 sweep: `gbrain bench publish` was documented (docs/eval-bench.md,
+    // KEY_FILES.md, and eval-gate's own --help text) but never dispatched —
+    // the promised-but-unwired class retrieval-upgrade (#3390) fixed before.
+    // Pure file-in/file-out (NDJSON → baseline); no DB, no engine.
+    if (args[0] === 'publish') {
+      const { runBenchPublish } = await import('./commands/bench-publish.ts');
+      await runBenchPublish(args.slice(1));
+      return;
+    }
+    console.error('Usage: gbrain bench publish --from <captured.ndjson> --to <X.baseline.ndjson> [flags]');
+    console.error('Run `gbrain bench publish --help` for the full flag list.');
+    process.exit(args[0] === '--help' || args[0] === '-h' ? 0 : 2);
+  }
   // v0.37 fix wave (deferred TODO, shipped): one-command wipe-and-reinit.
   // Spawns its own engine internally so no pre-bound engine needed.
   if (command === 'reinit-pglite') {
@@ -1688,10 +1868,33 @@ async function handleCliOnly(command: string, args: string[]) {
       }
       // doctor is handled before connectEngine() above
       case 'migrate': {
+        // #3390: `gbrain migrate embeddings --to <provider:model>` — the
+        // provider-agnostic embedding migration. Everything else stays the
+        // engine-transfer path (`migrate --to <supabase|pglite>`).
+        if (args[0] === 'embeddings') {
+          const { runMigrateEmbeddings } = await import('./commands/migrate-embeddings.ts');
+          await runMigrateEmbeddings(engine, args.slice(1));
+          break;
+        }
+        if (args.includes('--help') || args.includes('-h')) {
+          console.log('Usage: gbrain migrate --to <supabase|pglite> [--url <url>] [--path <path>] [--force]');
+          console.log('       gbrain migrate embeddings --to <provider:model> [--dim N] [--dry-run] [--yes]');
+          console.log('');
+          console.log('The first form transfers the brain between engines; the second re-embeds');
+          console.log('onto a different embedding provider (run `gbrain migrate embeddings --help`).');
+          break;
+        }
         const { runMigrateEngine } = await import('./commands/migrate-engine.ts');
         await runMigrateEngine(engine, args);
         break;
       }
+      case 'retrieval-upgrade': {
+        // The command README.md + doctor.ts promised since v0.36 but never
+        // dispatched. Alias for `migrate embeddings` (#3390).
+        const { runMigrateEmbeddings } = await import('./commands/migrate-embeddings.ts');
+        await runMigrateEmbeddings(engine, args);
+        break;
+      }
       case 'eval': {
         // v0.32 EXP-5: `eval takes-quality {run,trend,regress}` requires a
         // brain (samples takes from DB / reads runs table). `replay` was
@@ -2288,6 +2491,7 @@ USAGE
 SETUP
   init [--pglite|--supabase|--url]   Create brain (PGLite default, no server)
   migrate --to <supabase|pglite>     Transfer brain between engines
+  migrate embeddings --to <p:model>  Re-embed onto another embedding provider
   upgrade                            Self-update
   check-update [--json]              Check for new versions
   doctor [--json] [--fast]            Health check (resolver, skills, pgvector, RLS, embeddings)
@@ -2309,6 +2513,8 @@ IMPORT/EXPORT
   sync [--repo <path>] [flags]       Git-to-brain incremental sync
   sync --watch [--interval N]        Continuous sync (loops until stopped)
                                      See also: autopilot --install (continuous daemon).
+  sync --all --missing-path skip     Classify sources whose local_path is absent
+                                     on this machine as skipped, not failed
   export [--dir ./out/]              Export to markdown
   export --restore-only [--repo <p>] Restore missing supabase-only files
         [--type T] [--slug-prefix S] With optional filters
@@ -2353,6 +2559,7 @@ TOOLS
   publish <page.md> [--password]     Shareable HTML (strips private data, optional AES-256)
   check-backlinks <check|fix> [dir]  Find/fix missing back-links across brain
   lint <dir|file> [--fix]            Catch LLM artifacts, placeholder dates, bad frontmatter
+  backfill <kind|list>               v0.30.1: run a registered backfill (effective-date, ...)
   orphans [--json] [--count]         Find pages with no inbound wikilinks
   salience [--days N] [--kind P]     v0.29: pages ranked by emotional + activity salience
   anomalies [--since D] [--sigma N]  v0.29: cohort-based statistical anomalies (tag, type)

src/commands/agent.ts

@@ -66,7 +66,9 @@ USAGE
 SUBMITTING
   gbrain agent run <prompt>
     --subagent-def <name>        Named plugin subagent (from GBRAIN_PLUGIN_PATH)
-    --model <id>                 Anthropic model id (defaults to sonnet)
+    --model <id>                 Model id as provider:model (default: subagent tier model,
+                                  anthropic:claude-sonnet-4-6). Non-Anthropic providers need
+                                  agent.use_gateway_loop enabled — see NOTES below.
     --max-turns <n>              Max assistant turns (default 20)
     --tools a,b,c                Subset of registered tool names (comma list)
     --timeout-ms <n>             Per-job wall-clock timeout
@@ -87,9 +89,22 @@ VIEWING
     --since <spec>               ISO-8601 timestamp OR relative ("5m","1h","2d")
 
 NOTES
-  Submitting subagent jobs is trusted-only; MCP submitters receive
-  permission_denied. The worker needs ANTHROPIC_API_KEY set, or the
-  first LLM turn of a claimed job fails.
+  This CLI path is trusted-only. (Remote MCP callers reach subagents through
+  the scoped submit_agent operation, not through this command.)
+
+  By default the worker runs the legacy Anthropic-direct path, which needs an
+  Anthropic key — from ANTHROPIC_API_KEY or from anthropic_api_key in
+  ~/.gbrain/config.json — or the first LLM turn of a claimed job fails.
+
+  To run --model on a non-Anthropic provider, enable the provider-neutral
+  gateway loop first, then supply whatever credential that provider needs
+  (an API key for most; some recipes use OAuth or a local endpoint):
+    gbrain config set agent.use_gateway_loop true
+  Accepted values: true / 1 / yes / on.
+
+  The gateway loop needs a provider whose recipe supports chat WITH tool
+  calling — not every recipe under src/core/ai/recipes/ qualifies. A model
+  that cannot call tools is refused at job start with the reason named.
 `);
 }
 

src/commands/apply-migrations.ts

@@ -133,14 +133,15 @@ function indexCompleted(entries: CompletedMigrationEntry[]): CompletedIndex {
  * Returns the resolved status for a migration based on its entries.
  *
  * Semantics (Bug 3 — keep "complete wins" safety):
- *   - If any entry is `complete`, the version is complete. Terminal state.
- *   - Otherwise, if the latest entry is `retry`, the version is pending
- *     (user requested a fresh attempt).
+ *   - If the latest entry is `retry`, the version is pending. This is the
+ *     explicit escape hatch written by `--force-retry`, and it overrides an
+ *     earlier `complete` entry without hand-editing the ledger.
+ *   - Otherwise, if any entry is `complete`, the version is complete.
  *   - Otherwise, if any entry is `partial`, the version is partial.
  *   - Otherwise, pending.
  *
- * `complete` never regresses. A later accidental `partial` append cannot
- * undo a completed migration.
+ * `complete` never regresses accidentally. A later `partial` append cannot
+ * undo a completed migration; only a trailing, explicit `retry` marker can.
  */
 function statusForVersion(
   version: string,
@@ -148,9 +149,9 @@ function statusForVersion(
 ): 'complete' | 'partial' | 'pending' | 'wedged' {
   const entries = idx.byVersion.get(version) ?? [];
   if (entries.length === 0) return 'pending';
-  if (entries.some(e => e.status === 'complete')) return 'complete';
   const latest = entries[entries.length - 1];
   if (latest.status === 'retry') return 'pending';
+  if (entries.some(e => e.status === 'complete')) return 'complete';
   // Bug 3 attempt cap — count consecutive partials from the end (stopping
   // at any 'retry' or 'complete'). If we hit MAX_CONSECUTIVE_PARTIALS,
   // the migration is wedged and needs explicit --force-retry to try again.

src/commands/auth.ts

@@ -515,6 +515,60 @@ async function registerClient(name: string, args: string[]) {
   }
 }
 
+/**
+ * v0.42.x (#1914): rescope an existing OAuth client's write source and/or
+ * federated read scope. This is the operator surface the DCR registration
+ * comment promised ("rescope via the CLI later") — DCR clients land with
+ * source_id='default' / federated_read=['default'] and must not self-widen,
+ * so widening happens here (trusted local CLI) or via the requireAdmin
+ * /admin/api/rescope-client endpoint.
+ */
+async function rescopeClient(clientId: string, args: string[]) {
+  const usage = 'Usage: auth rescope-client <client_id> [--source SOURCE] [--federated-read SRC1,SRC2,...]';
+  if (!clientId) {
+    console.error(usage);
+    process.exit(1);
+  }
+  let sourceId: string | undefined;
+  let federatedRead: string[] | undefined;
+  for (let i = 0; i < args.length; i += 2) {
+    const flag = args[i];
+    const value = args[i + 1];
+    if (value === undefined || value.startsWith('--')) {
+      console.error(`Error: ${flag} requires a value`);
+      console.error(usage);
+      process.exit(1);
+    }
+    if (flag === '--source') sourceId = value;
+    else if (flag === '--federated-read') {
+      federatedRead = value.split(',').map(s => s.trim()).filter(Boolean);
+    } else {
+      console.error(`Error: Unknown flag: ${flag}`);
+      console.error(usage);
+      process.exit(1);
+    }
+  }
+  if (sourceId === undefined && federatedRead === undefined) {
+    console.error('Error: pass --source and/or --federated-read');
+    console.error(usage);
+    process.exit(1);
+  }
+  try {
+    await withConfiguredSql(async (sql) => {
+      const { GBrainOAuthProvider } = await import('../core/oauth-provider.ts');
+      const provider = new GBrainOAuthProvider({ sql });
+      const result = await provider.rescopeClient(clientId, { sourceId, federatedRead });
+      console.log(`OAuth client rescoped: "${result.clientName}" (${result.clientId})\n`);
+      console.log(`  Write source:        ${result.sourceId}`);
+      console.log(`  Federated reads:     ${result.federatedRead.join(', ') || '<none>'}`);
+      console.log('\nTakes effect on the client\'s next request (existing tokens included).');
+    });
+  } catch (e: any) {
+    console.error('Error:', e.message);
+    process.exit(1);
+  }
+}
+
 /**
  * Entry point for the `gbrain auth` CLI subcommand. Also reused by the
  * direct-script path (see bottom of file) so `bun run src/commands/auth.ts`
@@ -556,6 +610,7 @@ export async function runAuth(args: string[]): Promise<void> {
       return;
     }
     case 'register-client': await registerClient(rest[0], rest.slice(1)); return;
+    case 'rescope-client': await rescopeClient(rest[0], rest.slice(1)); return;
     case 'revoke-client': await revokeClient(rest[0]); return;
     case 'test': {
       const tokenIdx = rest.indexOf('--token');
@@ -593,6 +648,11 @@ Usage:
      --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 rescope-client <client_id> [options]        Change an existing client's source scope (e.g. a DCR
+                                                          client stuck on the 'default' source). Only the flags
+                                                          you pass change; the other axis is left as-is.
+     --source <id>                                        New write source
+     --federated-read <id1,id2,...>                       New read-scope source list
   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-timeout.ts

@@ -0,0 +1,9 @@
+export function resolveAutopilotDispatchTimeoutMs(
+  baseIntervalSeconds: number,
+  fullCycle: boolean,
+): number {
+  const intervalDerivedTimeoutMs = Math.max(baseIntervalSeconds * 2 * 1000, 300_000);
+  return fullCycle
+    ? Math.max(intervalDerivedTimeoutMs, 1_800_000)
+    : intervalDerivedTimeoutMs;
+}

src/commands/autopilot.ts

@@ -19,7 +19,7 @@
 
 import { existsSync, readFileSync, writeFileSync, mkdirSync, appendFileSync, utimesSync, unlinkSync, chmodSync } from 'fs';
 import { setCliExitVerdict } from '../core/cli-force-exit.ts';
-import { join } from 'path';
+import { join, dirname } from 'path';
 import { execSync } from 'child_process';
 import type { BrainEngine } from '../core/engine.ts';
 import { loadPreferences } from '../core/preferences.ts';
@@ -39,6 +39,7 @@ import { detectInstallMethod } from './upgrade.ts';
 import { evaluateQuietHours } from '../core/minions/quiet-hours.ts';
 import { inspectLock } from '../core/db-lock.ts';
 import { registerCleanup } from '../core/process-cleanup.ts';
+import { resolveAutopilotDispatchTimeoutMs } from './autopilot-timeout.ts';
 
 /**
  * v0.37.7.0 #1162 — classify autopilot reconnect-loop errors.
@@ -728,7 +729,7 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
         const queue = new MinionQueue(engine);
         const slotMs = Math.floor(Date.now() / (baseInterval * 1000)) * baseInterval * 1000;
         const slot = new Date(slotMs).toISOString();
-        const timeoutMs = Math.max(baseInterval * 2 * 1000, 300_000);
+        const timeoutMs = resolveAutopilotDispatchTimeoutMs(baseInterval, false);
 
         // ── v0.40 D17: per-source freshness check ────────────────────
         // Runs first; independent of score gate. Submits a 'sync' job per
@@ -983,7 +984,9 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
           const result = await dispatchPerSource(engine, queue, {
             repoPath,
             slot,
-            timeoutMs,
+            // Full cycles can outlive short daemon intervals. Keep lighter dispatches
+            // interval-derived while giving per-source consolidation enough time.
+            timeoutMs: resolveAutopilotDispatchTimeoutMs(baseInterval, true),
             fanoutMax,
             jsonMode,
           });
@@ -1309,6 +1312,17 @@ function writeWrapperScript(repoPath: string): string {
   const gbrainPath = resolveGbrainCliPath();
   const safeRepoPath = repoPath.replace(/'/g, "'\\''");
   const safeGbrainPath = gbrainPath.replace(/'/g, "'\\''");
+  // Bake the dir of the bun runtime actually executing this install onto PATH,
+  // so the wrapper finds bun wherever it lives — Homebrew (/opt/homebrew/bin),
+  // npm -g, Docker (/usr/local/bin), a custom BUN_INSTALL, or nix — not just
+  // ~/.bun/bin (which #3305 hardcoded, covering only the default bun.sh installer).
+  // dirname('') === '.', so guard the degenerate/empty case — otherwise a missing
+  // execPath would prepend '.' (cwd) onto a cron PATH. Empty prefix falls back to
+  // the #3305 behavior exactly.
+  const runtimeDir = dirname(process.execPath || '');
+  const runtimePathPrefix = runtimeDir && runtimeDir !== '.'
+    ? `'${runtimeDir.replace(/'/g, "'\\''")}':`
+    : '';
   const wrapper = `#!/bin/bash
 # Auto-generated by gbrain autopilot --install
 # Sources shell profile for API keys, then runs autopilot.
@@ -1318,6 +1332,16 @@ function writeWrapperScript(repoPath: string): string {
 # OPENAI/ANTHROPIC keys exported in zshenv reach autopilot.
 [ -f ~/.zshenv ] && source ~/.zshenv 2>/dev/null
 source ~/.zshrc 2>/dev/null || source ~/.bashrc 2>/dev/null || true
+# Belt-and-suspenders PATH fix. ~/.bashrc ships with a non-interactive guard
+# (\`case $- in *i*) ;; *) return;; esac\`) that exits early when launched from
+# cron/systemd/launchd — so its PATH exports never reach this subprocess.
+# Without bun on PATH, the exec'd gbrain (a \`#!/usr/bin/env bun\` script) fails
+# silently with "env: bun: No such file or directory" and leaves a stale
+# lockfile that blocks every subsequent tick. Prepending the running bun's own
+# dir (derived from process.execPath at install time), with ~/.bun/bin kept as a
+# fallback, keeps the wrapper self-contained regardless of where bun is installed
+# or which init file the OS loaded.
+export PATH=${runtimePathPrefix}"$HOME/.bun/bin:$PATH"
 exec '${safeGbrainPath}' autopilot --repo '${safeRepoPath}'
 `;
   writeFileSync(wrapperPath, wrapper, { mode: 0o755 });
@@ -1744,7 +1768,10 @@ function showStatus(json: boolean) {
   } else {
     try {
       const crontab = execSync('crontab -l 2>/dev/null || true', { encoding: 'utf-8' });
-      installed = crontab.includes('gbrain autopilot');
+      // The installed cron line invokes the generated wrapper (…/autopilot-run.sh);
+      // older installs called `gbrain autopilot` directly. Match either so status
+      // isn't a false negative after the wrapper indirection landed.
+      installed = crontab.includes('autopilot-run.sh') || crontab.includes('gbrain autopilot');
     } catch { /* no crontab */ }
   }
 

src/commands/check-update.ts

@@ -2,12 +2,13 @@ import { VERSION } from '../version.ts';
 import { detectInstallMethod } from './upgrade.ts';
 import {
   isMinorOrMajorBump,
+  isNewerVersion,
   isValidVersionString,
   parseSemver,
   semverGt,
   semverLte,
 } from '../core/semver.ts';
-import { writeUpdateCache, type UpdateMarker } from '../core/self-upgrade.ts';
+import { readUpdateCache, writeUpdateCache, type UpdateMarker } from '../core/self-upgrade.ts';
 
 /** Best-effort cache write — a read-only ~/.gbrain must never make the check throw. */
 function safeWriteCache(marker: UpdateMarker): void {
@@ -21,7 +22,7 @@ function safeWriteCache(marker: UpdateMarker): void {
 // Back-compat re-exports: these used to live here; moved to ../core/semver.ts
 // so the self-upgrade decision module can depend on them without an import
 // cycle. Existing importers (`test/check-update.test.ts`, etc.) keep working.
-export { parseSemver, isMinorOrMajorBump };
+export { parseSemver, isMinorOrMajorBump, isNewerVersion };
 
 interface CheckUpdateResult {
   current_version: string;
@@ -44,26 +45,53 @@ function upgradeCommandForMethod(method: string): string {
   }
 }
 
+/** Where the latest version is resolved from. gbrain publishes NO GitHub
+ * releases (the `releases/latest` API is a permanent 404), so the release
+ * train's source of truth is the `VERSION` file on master — same trusted host
+ * `fetchChangelog` already uses. An npm fallback was rejected: the `gbrain`
+ * package on npm is an unrelated GPU library (#505), so it would produce false
+ * upgrade prompts pointing at a stranger's package. */
+const VERSION_SOURCE_URL = 'https://raw.githubusercontent.com/garrytan/gbrain/master/VERSION';
+const RELEASE_NOTES_URL = 'https://github.com/garrytan/gbrain/blob/master/CHANGELOG.md';
+
+/** Extract a version from the raw VERSION file body: first line, optional `v`
+ * prefix, optional `-suffix` channel tag (`0.31.1.1-fixwave` compares as its
+ * numeric base — fail-safe: a suffix-only bump never prompts). Body is bounded
+ * before parsing so a malformed/huge response can't blow up the check. */
+export function parseVersionFileBody(body: string): string | null {
+  const firstLine = body.slice(0, 256).trim().split('\n')[0].trim();
+  const m = firstLine.match(/^v?(\d+\.\d+\.\d+(?:\.\d+)?)(?:[-+][0-9A-Za-z.-]+)?$/);
+  return m && isValidVersionString(m[1]) ? m[1] : null;
+}
+
+export type LatestReleaseResult =
+  | { ok: true; tag: string; published_at: string; url: string }
+  | { ok: false; reason: 'network_error' | 'no_releases' };
+
 /**
- * Fetch the latest GitHub release. Exported (v0.42) so the self-upgrade refresh
- * path and tests can reuse it. 5s timeout (was 10s) — this runs on the detached
- * refresh, never the hot path, but a tight bound keeps the refresh cheap.
+ * Resolve the latest published gbrain version (from VERSION on master — see
+ * VERSION_SOURCE_URL). Exported (v0.42) so the self-upgrade refresh path and
+ * tests can reuse it. 5s timeout — this runs on the detached refresh, never the
+ * hot path. Failures are discriminated: `network_error` (offline/timeout) vs
+ * `no_releases` (endpoint answered but no usable version).
  */
-export async function fetchLatestRelease(): Promise<{ tag: string; published_at: string; url: string } | null> {
+export async function fetchLatestRelease(): Promise<LatestReleaseResult> {
+  let res: Response;
   try {
-    const res = await fetch('https://api.github.com/repos/garrytan/gbrain/releases/latest', {
+    res = await fetch(VERSION_SOURCE_URL, {
       headers: { 'User-Agent': `gbrain/${VERSION}` },
       signal: AbortSignal.timeout(5_000),
     });
-    if (!res.ok) return null;
-    const data = await res.json() as any;
-    return {
-      tag: data.tag_name || '',
-      published_at: data.published_at || '',
-      url: data.html_url || '',
-    };
   } catch {
-    return null;
+    return { ok: false, reason: 'network_error' };
+  }
+  try {
+    if (!res.ok) return { ok: false, reason: 'no_releases' };
+    const tag = parseVersionFileBody(await res.text());
+    if (!tag) return { ok: false, reason: 'no_releases' };
+    return { ok: true, tag, published_at: '', url: RELEASE_NOTES_URL };
+  } catch {
+    return { ok: false, reason: 'network_error' };
   }
 }
 
@@ -117,21 +145,37 @@ export function extractChangelogBetween(changelog: string, from: string, to: str
 }
 
 /**
- * Fetch the latest release and write the self-upgrade cache (the marker line
- * read by the CLI startup hook). Fail-open: on any network failure we cache
- * `UP_TO_DATE <current>` so the TTL prevents hammering GitHub on every
- * invocation. Returns the resolved marker for callers that want it. This is the
- * function the detached single-flight refresh (`gbrain check-update
- * --refresh-cache`) invokes.
+ * A failed check must NEVER write `up_to_date` — that was #486: the fetch
+ * failed permanently (dead releases API) and every user was told "you're
+ * current" forever. Instead, re-write the last-known-good marker (bumping its
+ * mtime so the cache TTL still throttles retries and a network blip can't
+ * erase a pending upgrade_available notice). No prior marker → write nothing;
+ * the next invocation retries.
+ */
+function preserveCacheOnFailedCheck(): void {
+  try {
+    const prior = readUpdateCache();
+    if (prior) safeWriteCache(prior.marker);
+  } catch {
+    /* best-effort */
+  }
+}
+
+/**
+ * Fetch the latest version and write the self-upgrade cache (the marker line
+ * read by the CLI startup hook). On fetch failure the last-known-good marker is
+ * preserved (see preserveCacheOnFailedCheck) — never a fabricated `up_to_date`.
+ * This is the function the detached single-flight refresh (`gbrain
+ * check-update --refresh-cache`) invokes.
  */
 export async function refreshUpdateCache(): Promise<void> {
   const release = await fetchLatestRelease();
-  if (!release) {
-    safeWriteCache({ kind: 'up_to_date', current: VERSION });
+  if (!release.ok) {
+    preserveCacheOnFailedCheck();
     return;
   }
   const latestVersion = release.tag.replace(/^v/, '');
-  if (!isValidVersionString(latestVersion) || !isMinorOrMajorBump(VERSION, latestVersion)) {
+  if (!isValidVersionString(latestVersion) || !isNewerVersion(VERSION, latestVersion)) {
     safeWriteCache({ kind: 'up_to_date', current: VERSION });
     return;
   }
@@ -140,7 +184,7 @@ export async function refreshUpdateCache(): Promise<void> {
 
 export async function runCheckUpdate(args: string[]) {
   if (args.includes('--help') || args.includes('-h')) {
-    console.log('Usage: gbrain check-update [--json] [--refresh-cache]\n\nCheck for new GBrain versions.\n\nOnly reports minor/major version bumps (v0.X.0), not patches.\nFails silently on network errors.\n\n--refresh-cache  Fetch + update the self-upgrade cache, print nothing (used by\n                 the CLI startup hook\'s detached refresh).');
+    console.log('Usage: gbrain check-update [--json] [--refresh-cache]\n\nCheck for new GBrain versions.\n\nReports any strictly newer release, including patch and micro updates.\nFails silently on network errors.\n\n--refresh-cache  Fetch + update the self-upgrade cache, print nothing (used by\n                 the CLI startup hook\'s detached refresh).');
     return;
   }
 
@@ -165,9 +209,8 @@ export async function runCheckUpdate(args: string[]) {
 
   const release = await fetchLatestRelease();
 
-  if (!release) {
-    // Warm the cache fail-open so the startup hook doesn't re-fetch every call.
-    safeWriteCache({ kind: 'up_to_date', current: VERSION });
+  if (!release.ok) {
+    preserveCacheOnFailedCheck();
     if (json) {
       console.log(JSON.stringify({
         current_version: VERSION,
@@ -178,16 +221,18 @@ export async function runCheckUpdate(args: string[]) {
         release_url: '',
         changelog_diff: '',
         published_at: '',
-        error: 'no_releases',
+        error: release.reason,
       }, null, 2));
+    } else if (release.reason === 'network_error') {
+      console.log(`GBrain ${VERSION} — could not check for updates (network unavailable).`);
     } else {
-      console.log(`GBrain ${VERSION} — could not check for updates (no releases found or network unavailable).`);
+      console.log(`GBrain ${VERSION} — could not determine the latest published version.`);
     }
     return;
   }
 
   const latestVersion = release.tag.replace(/^v/, '');
-  const updateAvailable = isValidVersionString(latestVersion) && isMinorOrMajorBump(VERSION, latestVersion);
+  const updateAvailable = isValidVersionString(latestVersion) && isNewerVersion(VERSION, latestVersion);
 
   // Warm the self-upgrade cache so the next `gbrain <cmd>` startup hook can emit
   // the marker without a network call.

src/commands/doctor.ts

@@ -1,4 +1,5 @@
 import type { BrainEngine } from '../core/engine.ts';
+import { REPAIR_SOURCE_CONFIG_SQL } from '../core/source-config-sql.ts';
 import { setCliExitVerdict } from '../core/cli-force-exit.ts';
 import * as db from '../core/db.ts';
 import { LATEST_VERSION, getIdleBlockers } from '../core/migrate.ts';
@@ -39,7 +40,7 @@ import {
   buildBasenameIndex,
   queryBasenameIndex,
 } from '../core/link-extraction.ts';
-import { isSourceUnchangedSinceSync } from '../core/git-head.ts';
+import { probeSourceGitState } from '../core/git-head.ts';
 // v0.41.32.0: remote staleness reads the stored newest_content_at column via
 // this pure comparator (no git subprocess on the HTTP MCP doctor path).
 import { lagFromContentMs } from '../core/source-health.ts';
@@ -52,6 +53,8 @@ import { isUndefinedColumnError } from '../core/utils.ts';
 // drift from what search actually filters.
 import { resolveHardExcludes, DEFAULT_HARD_EXCLUDES } from '../core/search/source-boost.ts';
 import { escapeLikePattern, buildVisibilityClause } from '../core/search/sql-ranking.ts';
+import { unverifiedExtractionFragment } from '../core/extraction-review.ts';
+import { hnswIndexExpected, hnswMaxDimsForType } from '../core/vector-index.ts';
 
 export interface Check {
   name: string;
@@ -529,6 +532,101 @@ export async function childTableOrphansCheck(engine: BrainEngine): Promise<Check
   };
 }
 
+/**
+ * Raw-source persistence guarantee (#1978, warn-only v1).
+ *
+ * Invariant: every synthesized/derived page (dream_generated:true frontmatter
+ * or type:synthesis) must either carry a raw trace or declare an explicit
+ * exemption. Accepted traces:
+ *   - frontmatter key `raw_trace` / `raw_source` / `source_uri`
+ *   - an attached `raw_data` row
+ *   - `synthesis_evidence` rows (think-op citations)
+ *   - explicit `raw_trace_exempt: true` (reason in `raw_trace_exempt_reason`)
+ *
+ * v1 is deliberately warn-only — no write path is blocked. Escalation to
+ * fail-closed enforcement in the synthesis/import write paths is the v2
+ * follow-up once real brains run clean.
+ *
+ * Pure helper (engine.executeRaw only) for parity with
+ * childTableOrphansCheck so tests can target it directly.
+ */
+export async function rawProvenanceCheck(engine: BrainEngine): Promise<Check> {
+  const where = `
+        p.deleted_at IS NULL
+    AND (COALESCE(p.frontmatter->>'dream_generated', '') = 'true' OR p.type = 'synthesis')
+    AND NOT (COALESCE(p.frontmatter, '{}'::jsonb) ?| ARRAY['raw_trace', 'raw_source', 'source_uri', 'raw_trace_exempt'])
+    AND NOT EXISTS (SELECT 1 FROM raw_data rd WHERE rd.page_id = p.id)
+    AND NOT EXISTS (SELECT 1 FROM synthesis_evidence se WHERE se.synthesis_page_id = p.id)`;
+  try {
+    const rows = await engine.executeRaw<{ n: string | number }>(
+      `SELECT COUNT(*)::int AS n FROM pages p WHERE ${where}`,
+    );
+    const n = Number(rows[0]?.n ?? 0);
+    if (n === 0) {
+      return {
+        name: 'raw_provenance',
+        status: 'ok',
+        message: 'All synthesized pages carry a raw trace or explicit exemption',
+      };
+    }
+    const sample = await engine.executeRaw<{ slug: string }>(
+      `SELECT p.slug FROM pages p WHERE ${where} ORDER BY p.slug LIMIT 5`,
+    );
+    const slugs = sample.map(r => r.slug).join(', ');
+    return {
+      name: 'raw_provenance',
+      status: 'warn',
+      message:
+        `${n} synthesized page(s) lack a raw trace (no raw_trace/raw_source/source_uri frontmatter, ` +
+        `raw_data row, or synthesis evidence) and carry no raw_trace_exempt marker. e.g. ${slugs}. ` +
+        `Fix: stamp raw_source (path/URI of the source material) or raw_trace_exempt: true + ` +
+        `raw_trace_exempt_reason in frontmatter. Warn-only (#1978).`,
+    };
+  } catch {
+    return { name: 'raw_provenance', status: 'warn', message: 'Could not check raw provenance (older schema?)' };
+  }
+}
+
+/**
+ * #2829: source `config` is a jsonb OBJECT column (`DEFAULT '{}'::jsonb`), but a
+ * re-wrapping bug could store it as a JSON string scalar ("{}", "\"{}\"", ...)
+ * that grows a layer on every read→write cycle. Any row where
+ * `jsonb_typeof(config) <> 'object'` is corrupted — federation and ACL settings
+ * on that source are read off a string instead of the settings object. Surface
+ * the affected sources with the repair path. The `gbrain sources` config writers
+ * now normalize before write, so any config-writing command self-heals the row
+ * (the app unwraps up to 10 nested layers); the SQL below repairs one layer
+ * directly for the common case.
+ */
+export async function checkSourceConfigShape(engine: BrainEngine): Promise<Check> {
+  try {
+    const rows = await engine.executeRaw<{ id: string; typ: string | null }>(
+      `SELECT id, jsonb_typeof(config) AS typ FROM sources WHERE jsonb_typeof(config) <> 'object'`,
+    );
+    if (rows.length === 0) {
+      return {
+        name: 'source_config_shape',
+        status: 'ok',
+        message: 'All source config values are JSON objects',
+      };
+    }
+    const affected = rows.map((r) => `${r.id} (${r.typ ?? 'null'})`).join(', ');
+    return {
+      name: 'source_config_shape',
+      status: 'warn',
+      message:
+        `${rows.length} source(s) have a non-object config — a JSON string/scalar ` +
+        `instead of an object (the #2829 re-wrapping bug): ${affected}. ` +
+        `Federation and ACL settings on these sources won't be read correctly. ` +
+        `Repair by running any 'gbrain sources' config write (self-heals nested ` +
+        `strings and recoverable arrays), or in SQL: ${REPAIR_SOURCE_CONFIG_SQL}`,
+    };
+  } catch (e) {
+    const msg = e instanceof Error ? e.message : String(e);
+    return { name: 'source_config_shape', status: 'warn', message: `Check failed: ${msg}` };
+  }
+}
+
 export async function doctorReportRemote(engine: BrainEngine): Promise<DoctorReport> {
   const checks: Check[] = [];
 
@@ -781,8 +879,8 @@ export async function doctorReportRemote(engine: BrainEngine): Promise<DoctorRep
   checks.push(await checkEmbeddingEnvOverride(engine));
 
   // v0.31.12 subagent runtime enforcement (Layer 3 of 3 — Codex F13).
-  // The subagent loop is Anthropic-only. If models.tier.subagent or
-  // models.default is explicitly set to a non-Anthropic provider, warn here
+  // The subagent loop requires native tool-calling. If models.subagent,
+  // models.tier.subagent, or models.default resolves to a limited provider, warn here
   // so the user sees it at the next `gbrain doctor` run instead of at the
   // next subagent job submission. (Layers 1+2 also enforce — this is the
   // surfacing layer.)
@@ -2956,6 +3054,7 @@ async function checkEmbeddingEnvOverride(engine: BrainEngine): Promise<Check> {
 export async function checkSubagentCapability(engine: BrainEngine): Promise<Check> {
   try {
     const { classifyCapabilities } = await import('../core/ai/capabilities.ts');
+    const modelsSubagent = await engine.getConfig('models.subagent');
     const tierSubagent = await engine.getConfig('models.tier.subagent');
     const modelsDefault = await engine.getConfig('models.default');
 
@@ -2996,12 +3095,23 @@ export async function checkSubagentCapability(engine: BrainEngine): Promise<Chec
       return null;
     };
 
-    if (tierSubagent) {
-      const issue = explain(tierSubagent, 'models.tier.subagent');
+    let resolvedSource: string | null = null;
+    let resolvedModel: string | null = null;
+    if (modelsSubagent) {
+      resolvedSource = 'models.subagent';
+      resolvedModel = modelsSubagent;
+      const issue = explain(modelsSubagent, resolvedSource);
       if (issue) return issue;
     } else if (modelsDefault) {
+      resolvedSource = 'models.default';
+      resolvedModel = modelsDefault;
       const issue = explain(modelsDefault, 'models.default');
       if (issue) return issue;
+    } else if (tierSubagent) {
+      resolvedSource = 'models.tier.subagent';
+      resolvedModel = tierSubagent;
+      const issue = explain(tierSubagent, resolvedSource);
+      if (issue) return issue;
     }
     // v0.37 (T10 / D7) + v0.38 (D7 capability rename): warn when the configured
     // chat_model is non-Anthropic AND ANTHROPIC_API_KEY isn't set. With
@@ -3014,9 +3124,9 @@ export async function checkSubagentCapability(engine: BrainEngine): Promise<Chec
       const { loadConfig } = await import('../core/config.ts');
       const cfg = loadConfig();
       const chatModel = cfg?.chat_model;
+      const { isConfigTruthy } = await import('../core/config.ts');
       const gatewayLoopRaw = await engine.getConfig('agent.use_gateway_loop').catch(() => null);
-      const gatewayLoopEnabled = typeof gatewayLoopRaw === 'string'
-        && ['true', '1', 'yes', 'on'].includes(gatewayLoopRaw.trim().toLowerCase());
+      const gatewayLoopEnabled = isConfigTruthy(gatewayLoopRaw);
       const { isAnthropicProvider } = await import('../core/model-config.ts');
       if (chatModel && !isAnthropicProvider(chatModel) && !process.env.ANTHROPIC_API_KEY && !gatewayLoopEnabled) {
         return {
@@ -3034,8 +3144,8 @@ export async function checkSubagentCapability(engine: BrainEngine): Promise<Chec
     return {
       name: 'subagent_capability',
       status: 'ok',
-      message: tierSubagent
-        ? `Subagent tier resolves to "${tierSubagent}" with full tool-loop capability`
+      message: resolvedModel && resolvedSource
+        ? `Subagent model resolves via ${resolvedSource} to "${resolvedModel}" with full tool-loop capability`
         : `Subagent tier resolves to default (claude-sonnet-4-6) — full tool-loop capability`,
     };
   } catch (e) {
@@ -3234,18 +3344,10 @@ export function computeNightlyQualityProbeHealthCheck(
  *   - OK when enabled=true AND backlog==0 OR no eligible pages exist.
  *   - WARN when enabled=true AND backlog>10.
  *
- * Backlog query uses the page-level TERMINAL audit row check (Eng-v2
- * C7), source-scoped via explicit predicate (Eng-v2 C2). Partial-
- * extraction pages stay in backlog because the terminal row isn't
- * written until ALL segments complete.
- *
- * Known approximation (documented in the details field): "complete"
- * means "terminal row exists" which means "all segments completed in
- * a prior run." A page with the terminal row from one run + new
- * messages since shows OK until the next run picks up new messages
- * and writes a fresh terminal row. The backlog is therefore an UPPER
- * BOUND on "pages with NO extraction at all", not "pages whose facts
- * are current."
+ * Backlog uses versioned, source-scoped outcomes. Regular pages bind the marker
+ * to pages.updated_at; raw-transcript sidecars carry a SHA-256 snapshot token
+ * and are revalidated by the extraction command before it skips model work.
+ * Legacy/unversioned rows and partial extraction remain in backlog.
  */
 export async function computeConversationFactsBacklogCheck(
   engine: BrainEngine,
@@ -3287,35 +3389,112 @@ export async function computeConversationFactsBacklogCheck(
       }
     }
 
-    // Source-scoped NOT EXISTS (Eng-v2 C2 + C7):
-    //   - facts.source matches TERMINAL audit source
-    //   - source_session matches terminal:<slug>
-    //   - source_id matches page's source_id (cross-source safety)
-    const rows = await engine.executeRaw<{ count: string | number }>(
-      `SELECT COUNT(*) AS count FROM pages p
-       WHERE p.type = ANY($1::text[])
-         AND p.deleted_at IS NULL
-         AND NOT EXISTS (
-           SELECT 1 FROM facts f
-           WHERE f.source = 'cli:extract-conversation-facts:terminal'
-             AND f.source_session = 'cli:extract-conversation-facts:terminal:' || p.slug
-             AND f.source_id = p.source_id
-         )`,
+    const rows = await engine.executeRaw<{
+      backlog: string | number;
+      completed: string | number;
+      non_extractable: string | number;
+    }>(
+      `WITH outcomes AS (
+         SELECT
+           p.source_id,
+           p.slug,
+           MAX(CASE WHEN f.source = 'cli:extract-conversation-facts:terminal:v2' THEN 1 ELSE 0 END) AS completed,
+           MAX(CASE WHEN f.source = 'cli:extract-conversation-facts:non-extractable:v2' THEN 1 ELSE 0 END) AS non_extractable
+         FROM pages p
+         LEFT JOIN facts f
+           ON f.source_id = p.source_id
+          AND f.source_markdown_slug = p.slug
+          AND f.source IN (
+            'cli:extract-conversation-facts:terminal:v2',
+            'cli:extract-conversation-facts:non-extractable:v2'
+          )
+          AND p.content_hash IS NOT NULL
+          AND f.source_session = f.source || ':' || p.slug || ':page-' ||
+            p.content_hash || '-' ||
+            COALESCE(TO_CHAR(p.effective_date AT TIME ZONE 'UTC', 'YYYY-MM-DD'), 'none')
+         WHERE p.type = ANY($1::text[])
+           AND p.deleted_at IS NULL
+           AND COALESCE(BTRIM(p.frontmatter->>'raw_transcript'), '') = ''
+           AND p.content_hash IS NOT NULL
+         GROUP BY p.source_id, p.slug
+       )
+       SELECT
+         COALESCE(SUM(CASE WHEN completed = 0 AND non_extractable = 0 THEN 1 ELSE 0 END), 0) AS backlog,
+         COALESCE(SUM(completed), 0) AS completed,
+         COALESCE(SUM(CASE WHEN completed = 0 THEN non_extractable ELSE 0 END), 0) AS non_extractable
+       FROM outcomes`,
       [types],
     );
 
-    const backlog = Number(rows[0]?.count ?? 0);
+    let backlog = Number(rows[0]?.backlog ?? 0);
+    let completed = Number(rows[0]?.completed ?? 0);
+    let nonExtractable = Number(rows[0]?.non_extractable ?? 0);
+
+    // SQL cannot read raw_transcript files or reproduce the fallback hash for a
+    // legacy NULL content_hash. Recompute those tokens through the command's
+    // canonical verifier. Pagination keeps memory bounded.
+    const { findFreshExtractionOutcomes } = await import(
+      './extract-conversation-facts.ts'
+    );
+    const verifierSources = await engine.executeRaw<{ source_id: string }>(
+      `SELECT DISTINCT source_id
+         FROM pages
+        WHERE type = ANY($1::text[])
+          AND deleted_at IS NULL
+          AND (
+            COALESCE(BTRIM(frontmatter->>'raw_transcript'), '') <> ''
+            OR content_hash IS NULL
+          )
+        ORDER BY source_id`,
+      [types],
+    );
+    for (const { source_id: sourceId } of verifierSources) {
+      for (const type of types) {
+        let offset = 0;
+        // eslint-disable-next-line no-constant-condition
+        while (true) {
+          const batch = await engine.listPages({
+            type: type as NonNullable<Parameters<BrainEngine['listPages']>[0]>['type'],
+            sourceId,
+            limit: 10,
+            offset,
+          });
+          if (batch.length === 0) break;
+          const verifyInProcess = batch.filter((page) => {
+            const raw = page.frontmatter?.raw_transcript;
+            return (typeof raw === 'string' && raw.trim().length > 0) ||
+              page.content_hash == null;
+          });
+          if (verifyInProcess.length > 0) {
+            const outcomes = await findFreshExtractionOutcomes(
+              engine,
+              sourceId,
+              verifyInProcess,
+            );
+            for (const page of verifyInProcess) {
+              const outcome = outcomes.get(page.slug);
+              if (outcome === 'complete') completed++;
+              else if (outcome === 'non_extractable') nonExtractable++;
+              else backlog++;
+            }
+          }
+          offset += batch.length;
+          if (batch.length < 10) break;
+        }
+      }
+    }
 
     if (backlog === 0) {
       return {
         name,
         status: 'ok',
-        message: 'all eligible pages have extraction terminal audit rows',
+        message: 'all eligible pages have fresh durable extraction outcomes',
         details: {
           backlog,
+          completed,
+          scanned_not_extractable: nonExtractable,
           types,
-          known_approximation:
-            'backlog counts pages with NO extraction terminal row; pages with new messages since prior extraction may show OK until next run',
+          freshness_rule: 'v2 snapshot token (content hash + effective date or sidecar sha256)',
         },
       };
     }
@@ -3329,10 +3508,11 @@ export async function computeConversationFactsBacklogCheck(
         message: `${backlog} eligible pages without extraction. Fix: ${fixHint}`,
         details: {
           backlog,
+          completed,
+          scanned_not_extractable: nonExtractable,
           types,
           fix_hint: fixHint,
-          known_approximation:
-            'backlog counts pages with NO extraction terminal row; pages with new messages since prior extraction may show OK until next run',
+          freshness_rule: 'v2 snapshot token (content hash + effective date or sidecar sha256)',
         },
       };
     }
@@ -3341,7 +3521,13 @@ export async function computeConversationFactsBacklogCheck(
       name,
       status: 'ok',
       message: `${backlog} eligible page(s) below warn threshold (>10)`,
-      details: { backlog, types },
+      details: {
+        backlog,
+        completed,
+        scanned_not_extractable: nonExtractable,
+        types,
+        freshness_rule: 'v2 snapshot token (content hash + effective date or sidecar sha256)',
+      },
     };
   } catch (err) {
     return {
@@ -3435,6 +3621,52 @@ export async function checkLinksExtractionLag(
   }
 }
 
+/**
+ * issue #160 — unverified_extractions doctor check.
+ *
+ * The extraction quarantine lane parks auto-extracted entity stubs
+ * (frontmatter `provenance: 'auto-extracted'` + `status: 'unverified'`)
+ * until the owner promotes or rejects them. A queue nobody reviews decays
+ * into invisible clutter, so this check counts stubs older than N days
+ * (default 7) and nudges toward the review surface. Exported for direct
+ * testing (mirrors checkLinksExtractionLag).
+ */
+export async function checkUnverifiedExtractions(
+  engine: BrainEngine,
+  opts?: { sourceId?: string; days?: number },
+): Promise<Check> {
+  const name = 'unverified_extractions';
+  const days = opts?.days ?? 7;
+  const sourceId = opts?.sourceId;
+  try {
+    const params: unknown[] = [String(days)];
+    let srcClause = '';
+    if (sourceId) {
+      params.push(sourceId);
+      srcClause = 'AND p.source_id = $2';
+    }
+    const rows = await engine.executeRaw<{ n: string | number }>(
+      `SELECT COUNT(*)::int AS n FROM pages p
+       WHERE p.deleted_at IS NULL
+         AND ${unverifiedExtractionFragment('p')}
+         AND p.created_at < now() - ($1 || ' days')::interval
+         ${srcClause}`,
+      params,
+    );
+    const n = Number(rows[0]?.n ?? 0);
+    return {
+      name,
+      status: n > 0 ? 'warn' : 'ok',
+      message: n > 0
+        ? `${n} unverified auto-extracted entity stub(s) older than ${days} days awaiting review. List with 'gbrain extraction-pending'; promote/reject with 'gbrain extraction-review <promote|reject> --slugs <slug,...>'.`
+        : 'No stale unverified extraction stubs',
+      details: { count: n, days, source_id: sourceId ?? null },
+    };
+  } catch (e) {
+    return { name, status: 'warn', message: `Could not check unverified_extractions: ${(e as Error).message}` };
+  }
+}
+
 /**
  * issue #1678 — extract_atoms_backlog doctor check.
  *
@@ -3830,29 +4062,51 @@ export async function checkSyncFreshness(
       // All four must hold; otherwise fall through to the time-based check.
       // The chunker version match is computed here (not in the helper)
       // because it depends on engine state, not git state.
+      //
+      // Clone-unavailable fallback: on stateless deploys (Docker on EB /
+      // K8s / Fly — the platforms the cloud recipes produce), a container
+      // restart wipes `local_path` and each clone is only re-materialized
+      // when that source's next sync job runs. Until then the HEAD probe
+      // cannot run at all ('unavailable'), which previously fell through to
+      // raw wall-clock age — and since a no-op sync doesn't advance
+      // `last_sync_at`, every QUIET source read as stale/FAIL after a
+      // restart (score-sinking alert storm; observed live: 16-source brain,
+      // 12 clones gone after a config-update restart, doctor 70→30).
+      // 'unavailable' + chunker match now reuses the v0.41.32.0 REMOTE lag
+      // signal (newest_content_at) below — DB-only, no subprocess, and it
+      // still reports staleness whenever content really is newer than the
+      // last sync. 'changed' (readable clone with real work) keeps
+      // wall-clock exactly as before, and a chunker mismatch is never
+      // masked (D7): it disables the fallback too.
+      let cloneUnavailable = false;
       if (localOnly) {
-        const gitUnchanged = isSourceUnchangedSinceSync(
+        const gitState = probeSourceGitState(
           source.local_path,
           source.last_commit,
           { requireCleanWorkingTree: 'ignore-untracked' },
         );
         const chunkerMatch = source.chunker_version === currentChunkerVersion;
-        if (gitUnchanged && chunkerMatch) {
+        if (gitState === 'unchanged' && chunkerMatch) {
           unchanged_count++;
           continue;
         }
+        cloneUnavailable = gitState === 'unavailable' && chunkerMatch;
       }
 
       // v0.41.32.0: REMOTE path (doctorReportRemote, !localOnly) computes lag
       // from the stored newest_content_at column — NO git subprocess on a
       // DB-supplied local_path (preserves the v0.41.27.0 trust boundary). A
       // quiet repo whose newest commit predates its last sync reports 0; NULL
-      // column → wall-clock fallback. LOCAL fall-through keeps wall-clock: the
-      // short-circuit already failed, so the source genuinely has work and
-      // "hours since last sync" is the right staleness measure. The `ageMs < 0`
-      // skew check above still runs on raw wall-clock for both paths (A1).
+      // column → wall-clock fallback. LOCAL fall-through keeps wall-clock when
+      // the clone is READABLE: the short-circuit failed on real evidence
+      // (HEAD moved / dirty tree), so the source genuinely has work and
+      // "hours since last sync" is the right staleness measure. A local clone
+      // that is UNAVAILABLE (not yet re-materialized, see above) carries no
+      // evidence either way, so it borrows this same DB-only lag. The
+      // `ageMs < 0` skew check above still runs on raw wall-clock for both
+      // paths (A1).
       let thresholdAgeMs = ageMs;
-      if (!localOnly) {
+      if (!localOnly || cloneUnavailable) {
         const contentMs = source.newest_content_at
           ? new Date(source.newest_content_at).getTime()
           : null;
@@ -4470,11 +4724,10 @@ export async function buildChecks(
   const checks: Check[] = [];
   let autoFixReport: AutoFixReport | null = null;
 
-  // Progress reporter. `--json` is doctor's own JSON output (list of checks);
-  // progress events stay on stderr regardless, gated by the global --quiet /
-  // --progress-json flags. On a 52K-page brain the DB checks can take minutes,
-  // and without a heartbeat agents can't tell doctor from a hang.
-  const progress = createProgress(cliOptsToProgressOptions(getCliOptions()));
+  // Progress reporter. `--json` is doctor's machine-readable output, so plain
+  // progress must not leak to stderr unless the caller explicitly asks for
+  // structured progress with --progress-json.
+  const progress = createProgress(doctorProgressOptions(jsonOutput));
 
   // --- Filesystem checks (always run, no DB needed) ---
 
@@ -5739,7 +5992,7 @@ export async function buildChecks(
     // that doesn't match the gateway's resolved default. Empty-brain vs
     // non-empty-brain branching determines the repair hint:
     //   - empty brain (no embedded chunks) → `gbrain init --force --embedding-model …`
-    //   - non-empty brain → `gbrain retrieval-upgrade --to … --reindex`
+    //   - non-empty brain → `gbrain migrate embeddings --to … --dim …` (#3390)
     // The bug-reporter's `rm -rf ~/.gbrain` recovery is never the right answer.
     let surfacedUnconfiguredDrift = false;
     try {
@@ -5770,7 +6023,7 @@ export async function buildChecks(
           if (totalChunks > 0) {
             const fix = embeddedCount === 0
               ? `No embeddings yet — drop the empty schema and re-init at the right dim:\n        gbrain init --force --pglite --embedding-model ${configuredModel} --embedding-dimensions ${configuredDims}`
-              : `Non-empty brain (${embeddedCount} embedded chunks). Migrate cleanly:\n        gbrain retrieval-upgrade --to ${configuredModel} --reindex`;
+              : `Non-empty brain (${embeddedCount} embedded chunks). Migrate cleanly:\n        gbrain migrate embeddings --to ${configuredModel} --dim ${configuredDims}`;
 
             checks.push({
               name: 'embedding_provider',
@@ -5974,6 +6227,12 @@ export async function buildChecks(
           continue;
         }
         if (engine.kind === 'postgres' && haveIndex.get(colName) === false) {
+          if (!hnswIndexExpected(entry.type, entry.dimensions)) {
+            okColumns.push(
+              `${colName} (exact scan: ${entry.type}(${entry.dimensions}) exceeds HNSW cap ${hnswMaxDimsForType(entry.type)})`,
+            );
+            continue;
+          }
           issues.push(
             `${colName}: no HNSW index. Search works but uses sequential scan. ` +
               `Fix: CREATE INDEX IF NOT EXISTS idx_chunks_${colName} ON content_chunks USING hnsw (${quoteIdentifier(colName)} ${entry.type}_cosine_ops);`,
@@ -6290,6 +6549,18 @@ export async function buildChecks(
   progress.heartbeat('child_table_orphans');
   checks.push(await childTableOrphansCheck(engine));
 
+  // 10d. Raw-source persistence guarantee (#1978, warn-only v1).
+  // Every synthesized/derived page must carry a raw trace or an explicit
+  // exemption. Warn-only in v1 — surfaces violations, blocks nothing.
+  progress.heartbeat('raw_provenance');
+  checks.push(await rawProvenanceCheck(engine));
+
+  // #2829: detect sources whose jsonb `config` was re-wrapped into a string
+  // scalar (grows a layer per read→write cycle). Non-object configs break
+  // federation + ACL reads; surface them with the repair path.
+  progress.heartbeat('source_config_shape');
+  checks.push(await checkSourceConfigShape(engine));
+
   // v0.33: whoknows_health — fixture presence + row count. The eval
   // gate itself runs via `gbrain eval whoknows`; this check is the
   // "did you do the assignment?" signal.
@@ -6689,6 +6960,10 @@ export async function buildChecks(
     checks.push({ name: 'flagged_pages', status: 'ok', message: `Skipped (${msg})` });
   }
 
+  // issue #160: extraction quarantine lane review nudge.
+  progress.heartbeat('unverified_extractions');
+  checks.push(await checkUnverifiedExtractions(engine, { sourceId: orphanRatioSourceId }));
+
   // 11a. Frontmatter integrity (v0.22.4, hardened in v0.38.2.0).
   // scanBrainSources walks every registered source's local_path on disk
   // (not from the DB), invoking parseMarkdown(..., {validate:true}) per
@@ -7485,6 +7760,14 @@ export async function runDoctor(
 // Helpers
 // ---------------------------------------------------------------------------
 
+export function doctorProgressOptions(jsonOutput: boolean) {
+  const cliOpts = getCliOptions();
+  if (jsonOutput && !cliOpts.quiet && !cliOpts.progressJson) {
+    return { mode: 'quiet' as const };
+  }
+  return cliOptsToProgressOptions(cliOpts);
+}
+
 /** Print the auto-fix report in human-readable form. JSON output goes through
  *  outputResults alongside the check list; this is the pretty-print path. */
 function printAutoFixReport(report: AutoFixReport, dryRun: boolean, jsonOutput: boolean): void {
@@ -7863,27 +8146,71 @@ export async function runRemediationPlan(
     return;
   }
 
-  // Human output
-  console.log(`Brain score: ${plan.brain_score_current}/100 → target ${targetScore}`);
+  for (const line of renderRemediationPlanLines(plan, targetScore)) {
+    console.log(line);
+  }
+}
+
+/**
+ * Human-render the remediation plan into a sequence of console lines.
+ * Exported for unit-test access — `runRemediationPlan` consumes it
+ * verbatim and only adds the JSON-mode short-circuit.
+ *
+ * Gating the "at target" line on `brain_score_current >= targetScore`
+ * is load-bearing: when the plan is empty AND the target is unreachable,
+ * the prior shape printed both "Target unreachable: …" and "Brain is at
+ * target" back-to-back, which contradicted itself and hid the real next
+ * step (manual prereq config to lift `max_reachable_score`).
+ */
+export function renderRemediationPlanLines(
+  plan: RemediationPlanShape,
+  targetScore: number,
+): string[] {
+  const lines: string[] = [];
+  lines.push(`Brain score: ${plan.brain_score_current}/100 → target ${targetScore}`);
   if (plan.target_unreachable) {
-    console.log(`Target unreachable: max with autonomous remediation is ${plan.max_reachable_score}/100.`);
+    lines.push(`Target unreachable: max with autonomous remediation is ${plan.max_reachable_score}/100.`);
   }
   if (plan.plan.length === 0) {
-    console.log('No remediations needed. Brain is at target.');
+    if (plan.brain_score_current >= targetScore) {
+      lines.push('No remediations needed. Brain is at target.');
+    }
+    // When brain_score < targetScore and plan is empty, the unreachable
+    // line (if applicable) is the user-facing explanation; the blocked-
+    // checks block below surfaces the manual gap. Don't follow with a
+    // misleading "at target" claim.
   } else {
-    console.log(`Plan: ${plan.plan.length} step(s), est ${plan.est_total_seconds}s, est $${plan.est_total_usd_cost.toFixed(2)}`);
+    lines.push(`Plan: ${plan.plan.length} step(s), est ${plan.est_total_seconds}s, est $${plan.est_total_usd_cost.toFixed(2)}`);
     for (const step of plan.plan) {
       const protectedMark = step.protected ? ' [PROTECTED]' : '';
       const costMark = step.est_usd_cost ? ` ($${step.est_usd_cost.toFixed(2)})` : '';
-      console.log(`  ${step.step}. [${step.severity}] ${step.job}${protectedMark} — ${step.rationale}${costMark}`);
+      lines.push(`  ${step.step}. [${step.severity}] ${step.job}${protectedMark} — ${step.rationale}${costMark}`);
     }
   }
   if (plan.blocked.length > 0) {
-    console.log(`\nBlocked checks (prereq missing):`);
+    lines.push(`\nBlocked checks (prereq missing):`);
     for (const b of plan.blocked) {
-      console.log(`  - ${b.check}: ${b.reason}`);
+      lines.push(`  - ${b.check}: ${b.reason}`);
     }
   }
+  return lines;
+}
+
+interface RemediationPlanShape {
+  brain_score_current: number;
+  target_unreachable: boolean;
+  max_reachable_score: number;
+  plan: Array<{
+    step: number;
+    severity: string;
+    job: string;
+    protected?: boolean;
+    est_usd_cost?: number;
+    rationale: string;
+  }>;
+  est_total_seconds: number;
+  est_total_usd_cost: number;
+  blocked: Array<{ check: string; reason: string }>;
 }
 
 /**

src/commands/dream.ts

@@ -86,7 +86,7 @@ interface DreamArgs {
    * `--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.
+   * skillopt, drift) — a no-op for phases that always run when named directly.
    */
   once: boolean;
 }
@@ -367,7 +367,7 @@ Options:
                       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
+                      enrich_thin, skillopt, drift; 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

src/commands/embed.ts

@@ -19,6 +19,26 @@ import {
 } from '../core/pace-mode.ts';
 import { tryAcquireDbLock, type DbLockHandle } from '../core/db-lock.ts';
 import { embedBackfillLockId } from '../core/embed-backfill-lock.ts';
+import { wrapChunkTextsForStoredMode } from '../core/embedding-context.ts';
+import { titleTierCorpusGeneration } from '../core/contextual-retrieval-service.ts';
+import type { Page } from '../core/types.ts';
+
+/**
+ * #3507 — after a plain re-embed fully re-embedded a `per_chunk_synopsis`
+ * page at the title-only tier (see wrapChunkTextsForStoredMode), restamp the
+ * page's CR state to 'title' so `contextual_retrieval_mode` keeps describing
+ * the vectors actually in the column. The reindex sweep restores the synopsis
+ * tier later. No-op for every other mode.
+ */
+export async function restampIfDemotedToTitleTier(
+  engine: BrainEngine,
+  page: Pick<Page, 'contextual_retrieval_mode'> | null | undefined,
+  slug: string,
+  sourceId: string,
+): Promise<void> {
+  if (page?.contextual_retrieval_mode !== 'per_chunk_synopsis') return;
+  await engine.updatePageContextualRetrievalState(slug, sourceId, 'title', titleTierCorpusGeneration());
+}
 
 export interface EmbedOpts {
   /** Embed ALL pages (every chunk). */
@@ -115,6 +135,16 @@ export interface EmbedOpts {
    * Errors/warnings still go to stderr regardless.
    */
   quiet?: boolean;
+  /**
+   * #3391: widen signature-drift invalidation to pages with NO recorded
+   * embedding_signature (pre-v108). By default those are grandfathered
+   * (never invalidated) so a routine upgrade doesn't surprise-re-embed a
+   * whole corpus — but after a provider/model swap the grandfather clause
+   * silently leaves them in the OLD embedding space, mixing two vector
+   * spaces in one index. `gbrain migrate embeddings` and
+   * `gbrain embed --stale --include-null-signature` set this.
+   */
+  includeNullSignature?: boolean;
 }
 
 /**
@@ -356,6 +386,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
         pacer,
         paceMaxConcurrency,
         quiet: opts.quiet,
+        includeNullSignature: opts.includeNullSignature,
       }, opts.signal);
     } finally {
       // E1: surface pacing telemetry (human + structured) when pacing was on.
@@ -469,6 +500,8 @@ export async function runEmbed(engine: BrainEngine, args: string[]): Promise<Emb
   const priorityRaw = priorityIdx >= 0 ? args[priorityIdx + 1] : undefined;
   const priority = priorityRaw === 'recent' ? 'recent' as const : undefined;
   const catchUp = args.includes('--catch-up');
+  // #3391: re-embed pages that predate the embedding_signature stamp too.
+  const includeNullSignature = args.includes('--include-null-signature');
   const pace = parsePaceArgs(args);
 
   let opts: EmbedOpts;
@@ -476,11 +509,11 @@ export async function runEmbed(engine: BrainEngine, args: string[]): Promise<Emb
     opts = { slugs: args.slice(slugsIdx + 1).filter(a => !a.startsWith('--')), dryRun, sourceId, batchSize, priority, catchUp };
   } else if (all || stale) {
     // E-2: CLI-only single-flight for stale runs (the minion path locks itself).
-    opts = { all, stale, dryRun, sourceId, batchSize, priority, catchUp, ...(pace && { pace }), ...(stale && { singleFlight: true }) };
+    opts = { all, stale, dryRun, sourceId, batchSize, priority, catchUp, ...(pace && { pace }), ...(stale && { singleFlight: true }), ...(includeNullSignature && { includeNullSignature: true }) };
   } else {
     const slug = args.find(a => !a.startsWith('--'));
     if (!slug) {
-      serr('Usage: gbrain embed [<slug>|--all|--stale|--slugs s1 s2 ...] [--dry-run] [--batch-size N] [--priority recent] [--catch-up]');
+      serr('Usage: gbrain embed [<slug>|--all|--stale|--slugs s1 s2 ...] [--dry-run] [--batch-size N] [--priority recent] [--catch-up] [--include-null-signature]');
       process.exit(1);
     }
     opts = { slug, dryRun, sourceId, batchSize, priority, catchUp };
@@ -586,7 +619,11 @@ async function embedPage(
     return;
   }
 
-  const embeddings = await embedBatch(toEmbed.map(c => c.chunk_text), { abortSignal: signal });
+  // #3507: embed with the page's STORED wrapping convention (title-tier
+  // contextual prefix when the page was embedded wrapped), not raw
+  // chunk_text — otherwise a re-embed silently strips the contextual
+  // prefixes the sync path applied. fenced_code chunks stay unwrapped.
+  const embeddings = await embedBatch(wrapChunkTextsForStoredMode(page, toEmbed), { abortSignal: signal });
   const embeddingMap = new Map<number, Float32Array>();
   for (let j = 0; j < toEmbed.length; j++) {
     embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
@@ -609,6 +646,9 @@ async function embedPage(
   // such a page and then stamps it.
   if (toEmbed.length === chunks.length) {
     await engine.setPageEmbeddingSignature(slug, { sourceId, signature: currentEmbeddingSignature() });
+    // #3507: a fully re-embedded per_chunk_synopsis page landed at the
+    // title tier — keep the stamped mode honest.
+    await restampIfDemotedToTitleTier(engine, page, slug, page.source_id);
   }
   result.embedded += toEmbed.length;
   result.pages_processed++;
@@ -657,6 +697,8 @@ async function embedAll(
     paceMaxConcurrency?: number;
     /** #394: suppress human stdout summaries (structured-output callers). */
     quiet?: boolean;
+    /** #3391: lift the NULL-signature grandfather clause (see EmbedOpts). */
+    includeNullSignature?: boolean;
   },
   signal?: AbortSignal,
 ) {
@@ -748,7 +790,8 @@ async function embedAll(
     }
 
     try {
-      const embeddings = await embedBatch(toEmbed.map(c => c.chunk_text));
+      // #3507: reproduce the page's stored wrapping convention (see embedPage).
+      const embeddings = await embedBatch(wrapChunkTextsForStoredMode(page, toEmbed));
       // Build a map of new embeddings by chunk_index
       const embeddingMap = new Map<number, Float32Array>();
       for (let j = 0; j < toEmbed.length; j++) {
@@ -770,6 +813,11 @@ async function embedAll(
       await observed(pacer, () =>
         engine.setPageEmbeddingSignature(page.slug, { sourceId: pageSourceId, signature }),
       );
+      // #3507: --all fully re-embeds; a per_chunk_synopsis page landed at
+      // the title tier — keep the stamped mode honest.
+      await observed(pacer, () =>
+        restampIfDemotedToTitleTier(engine, page, page.slug, pageSourceId),
+      );
       result.embedded += toEmbed.length;
     } catch (e: unknown) {
       serr(`\n  Error embedding ${page.slug}: ${e instanceof Error ? e.message : e}`);
@@ -845,6 +893,8 @@ async function embedAllStale(
     paceMaxConcurrency?: number;
     /** #394: suppress human stdout summaries (structured-output callers). */
     quiet?: boolean;
+    /** #3391: lift the NULL-signature grandfather clause (see EmbedOpts). */
+    includeNullSignature?: boolean;
   },
   signature?: string,
   externalSignal?: AbortSignal,
@@ -852,6 +902,7 @@ async function embedAllStale(
   // D7: thread sourceId so source-scoped runs only count + visit
   // that source's NULL embeddings.
   const sourceOpt = sourceId ? { sourceId } : undefined;
+  const includeNullSig = !!staleOpts?.includeNullSignature;
 
   // v0.41.31: re-embed pages whose embedding_signature drifted (model/dims
   // swap). dry-run must NOT mutate, so it counts signature-stale via the
@@ -861,16 +912,46 @@ async function embedAllStale(
     const invalidated = await engine.invalidateStaleSignatureEmbeddings({
       signature,
       ...(sourceId && { sourceId }),
+      ...(includeNullSig && { includeNullSignature: true }),
     });
     if (invalidated > 0 && !staleOpts?.quiet) {
       slog(`[embed] invalidated ${invalidated} chunk(s) embedded under a prior model signature`);
     }
+    // #3391: the grandfather clause keeps NULL-signature pages on their OLD
+    // vectors — two embedding spaces mixed in one index. Loud stderr warning
+    // with the fix, instead of silent retrieval degradation.
+    //
+    // Deliberately NOT gated on `invalidated > 0`: the original bug report's
+    // shape is a brain where EVERY embedded page predates the signature stamp,
+    // so nothing drifts, nothing is invalidated — and pre-fix that brain got
+    // no warning AND no work, the exact silent case #3391 is about. The probe
+    // below computes the left-behind count directly, which is 0 on a healthy
+    // brain, so an unaffected run stays quiet.
+    if (!includeNullSig) {
+      try {
+        const wide = await engine.countStaleChunks({ ...sourceOpt, signature, includeNullSignature: true });
+        const narrow = await engine.countStaleChunks({ ...sourceOpt, signature });
+        const leftBehind = wide - narrow;
+        if (leftBehind > 0) {
+          serr(
+            `  [embed] WARNING: ${leftBehind} embedded chunk(s) sit on pages with no recorded ` +
+            `embedding signature and were NOT invalidated — they remain in the previous model's ` +
+            `embedding space. Re-run with --include-null-signature (or use ` +
+            `\`gbrain migrate embeddings\`) to re-embed them.`,
+          );
+        }
+      } catch {
+        // The warning probe is best-effort; never break the embed run.
+      }
+    }
   }
 
   // Pre-flight: 0 stale chunks → nothing to do, no further DB reads.
   // dry-run includes signature-drift in the count without mutating.
   const staleCount = await engine.countStaleChunks(
-    dryRun && signature ? { ...sourceOpt, signature } : sourceOpt,
+    dryRun && signature
+      ? { ...sourceOpt, signature, ...(includeNullSig && { includeNullSignature: true }) }
+      : sourceOpt,
   );
   if (staleCount === 0) {
     if (!staleOpts?.quiet) {
@@ -1050,7 +1131,13 @@ async function embedAllStale(
         const keySourceId = stale[0]?.source_id ?? 'default';
         const slug = stale[0].slug;
         try {
-          const embeddings = await embedBatchWithBackoff(stale.map(c => c.chunk_text), { abortSignal: effectiveSignal });
+          // #3507: fetch the page row for its title + stored CR mode so the
+          // re-embed reproduces the page's wrapping convention instead of
+          // silently stripping contextual prefixes — `embed --stale` is the
+          // NORMAL post-model-migration path, so raw-text embedding here
+          // quietly converted whole corpora to the unwrapped convention.
+          const pageRow = await observed(pacer, () => engine.getPage(slug, { sourceId: keySourceId }));
+          const embeddings = await embedBatchWithBackoff(wrapChunkTextsForStoredMode(pageRow, stale), { abortSignal: effectiveSignal });
           // Re-fetch existing chunks and merge to avoid deleting non-stale chunks.
           const existing = await observed(pacer, () => engine.getChunks(slug, { sourceId: keySourceId }));
           const staleIdxToEmbedding = new Map<number, Float32Array>();
@@ -1078,6 +1165,14 @@ async function embedAllStale(
               engine.setPageEmbeddingSignature(slug, { sourceId: keySourceId, signature }),
             );
           }
+          // #3507: a FULLY re-embedded per_chunk_synopsis page landed at the
+          // title tier — keep the stamped mode honest. Partially-stale pages
+          // stay stamped as-is (mixed provenance; reindex sweeps fix them).
+          if (stale.length === existing.length) {
+            await observed(pacer, () =>
+              restampIfDemotedToTitleTier(engine, pageRow, slug, keySourceId),
+            );
+          }
           result.embedded += stale.length;
         } catch (e: unknown) {
           // Budget/abort-fired cancellations are expected on the way out; don't
@@ -1138,7 +1233,9 @@ async function embedAllStale(
   // as a clean run — re-running won't help until the underlying failure is fixed.
   if (staleOpts?.catchUp && !effectiveSignal.aborted && embedFailures > 0) {
     const remaining = await engine.countStaleChunks(
-      signature ? { signature, ...(sourceId ? { sourceId } : {}) } : (sourceId ? { sourceId } : undefined),
+      signature
+        ? { signature, ...(sourceId ? { sourceId } : {}), ...(includeNullSig && { includeNullSignature: true }) }
+        : (sourceId ? { sourceId } : undefined),
     );
     if (remaining > 0) {
       serr(`\n  [embed] catch-up finished but ${remaining} chunk(s) remain stale after ${embedFailures} embed failure(s). These are not embeddable as-is; re-running won't clear them until the underlying error is resolved.`);

src/commands/extract-conversation-facts.ts

@@ -43,11 +43,10 @@
  *     (source_id, source_markdown_slug, row_num); per-segment row_num
  *     would collide on segment 2. Per-page counter increments across
  *     segments.
- *   - Terminal audit row on completion. After all segments commit, one
- *     extra fact row with source='cli:extract-conversation-facts:terminal'
- *     marks the page complete. Doctor's backlog query checks for the
- *     terminal row, NOT any fact — partial extraction → no terminal →
- *     next run resumes.
+ *   - Snapshot-bound terminal audit row on completion. After all segments
+ *     commit, one v2 row binds completion to the exact page version or raw
+ *     transcript digest. Partial extraction has no matching terminal and the
+ *     next claim performs a delete-first full replay.
  *   - Optional budgetTracker via opts. If a tracker is in opts, use it
  *     as-is (NO `withBudgetTracker` wrap, which would REPLACE the active
  *     tracker per gateway.ts AsyncLocalStorage semantics, defeating an
@@ -68,7 +67,7 @@
 import type { BrainEngine, NewFact } from '../core/engine.ts';
 import type { Page } from '../core/types.ts';
 import {
-  extractFactsFromTurn,
+  extractFactsFromTurnWithOutcome,
   isFactsExtractionEnabled,
 } from '../core/facts/extract.ts';
 import { configureGatewayIfUninitialized, isAvailable, withBudgetTracker } from '../core/ai/gateway.ts';
@@ -150,6 +149,40 @@ export const ALLOWED_TYPES = [
 ] as const;
 export type AllowedType = (typeof ALLOWED_TYPES)[number];
 
+/**
+ * Granular collector page-types that alias into each canonical conversation
+ * bucket. The v2 type-consolidation pack retypes these to the canonical names
+ * (`slack-dm-day`/`slack-thread` → `slack`, `email-digest` → `email`), but a
+ * brain that hasn't run that pack still carries the collector's granular types
+ * in `pages.type`. Without this expansion, `listPages({ type: 'slack' })`
+ * matches zero rows on such brains and the whole comms corpus is silently
+ * skipped (facts stay empty → `find_trajectory` returns nothing). The canonical
+ * name is always included first so consolidated brains keep working unchanged.
+ */
+export const ALLOWED_TYPE_ALIASES: Record<AllowedType, readonly string[]> = {
+  conversation: ['conversation'],
+  meeting: ['meeting'],
+  slack: ['slack', 'slack-dm-day', 'slack-thread'],
+  email: ['email', 'email-digest'],
+  imessage: ['imessage'],
+  'imessage-daily': ['imessage-daily'],
+};
+
+/**
+ * Expand the requested logical types to the concrete `pages.type` values to
+ * enumerate, canonical-first and de-duplicated. Unknown types pass through
+ * unchanged so an explicit override is never dropped.
+ */
+export function pageTypesForAllowed(types: readonly AllowedType[]): string[] {
+  const out: string[] = [];
+  for (const t of types) {
+    for (const concrete of ALLOWED_TYPE_ALIASES[t] ?? [t]) {
+      if (!out.includes(concrete)) out.push(concrete);
+    }
+  }
+  return out;
+}
+
 /**
  * Pagination batch size for listPages enumeration. Per-batch memory
  * worst case = BATCH × MAX_PAGE_BODY_BYTES = 250MB at default 10
@@ -172,7 +205,15 @@ export const PER_SEGMENT_SOURCE_PREFIX = 'cli:extract-conversation-facts';
  * the per-segment source. Partial extraction = no terminal row = page
  * stays in backlog.
  */
-export const TERMINAL_AUDIT_SOURCE = 'cli:extract-conversation-facts:terminal';
+export const TERMINAL_AUDIT_SOURCE = 'cli:extract-conversation-facts:terminal:v2';
+
+/**
+ * Durable outcome for a successfully scanned page that contains no eligible
+ * multi-message segment. Kept distinct from successful extraction so operator
+ * surfaces can report the truth without rescanning the page forever.
+ */
+export const NON_EXTRACTABLE_AUDIT_SOURCE =
+  'cli:extract-conversation-facts:non-extractable:v2';
 
 // ---------------------------------------------------------------------------
 // Public types.
@@ -253,6 +294,19 @@ export interface ExtractConversationFactsResult {
   pages_skipped: number;
   pages_skipped_too_large: number;
   pages_skipped_disappeared: number;
+  /** Fresh terminal outcomes skipped before parsing or model work. */
+  pages_skipped_completed: number;
+  /** Fresh scanned-not-extractable outcomes skipped before parser work. */
+  pages_skipped_non_extractable: number;
+  /** Durable scanned-not-extractable outcomes written by this run. */
+  pages_marked_non_extractable: number;
+  /** Pages whose claim reached extraction but failed before durable outcome. */
+  pages_failed: number;
+  /**
+   * Pages whose built-in parse returned `no_match` and whose messages were
+   * recovered by the explicitly enabled LLM fallback.
+   */
+  pages_llm_fallback: number;
   /**
    * v0.41.15.0 (D6): pages we attempted to claim but skipped because
    * another worker / parallel process held the advisory lock. The pages
@@ -290,10 +344,13 @@ export interface ExtractConversationFactsResult {
 // ---------------------------------------------------------------------------
 
 import {
+  deriveDateContext,
   parseConversation,
   type ParseConversationOpts as OrchestratorParseOpts,
 } from '../core/conversation-parser/parse.ts';
 import { readConversationBodyForParsing } from '../core/conversation-parser/body.ts';
+import { runLlmFallback } from '../core/conversation-parser/llm-fallback.ts';
+import { resolveModel } from '../core/model-config.ts';
 
 /**
  * v0.41.13.0 — back-compat shape for direct callers + the existing
@@ -583,31 +640,21 @@ async function deleteOrphanFactsForPage(
   sourceId: string,
   slug: string,
 ): Promise<number> {
-  try {
-    // The two write-source variants this command may have left behind:
-    //   - PER_SEGMENT_SOURCE_PREFIX  ('cli:extract-conversation-facts')
-    //   - TERMINAL_AUDIT_SOURCE      ('cli:extract-conversation-facts:terminal')
-    // Using a LIKE prefix match covers both with one statement.
-    const rows = await engine.executeRaw<{ count: string }>(
-      `WITH del AS (
-         DELETE FROM facts
-         WHERE source_id = $1
-           AND source_markdown_slug = $2
-           AND source LIKE 'cli:extract-conversation-facts%'
-         RETURNING 1
-       )
-       SELECT COUNT(*)::text AS count FROM del`,
-      [sourceId, slug],
-    );
-    const n = parseInt(rows[0]?.count ?? '0', 10);
-    return Number.isFinite(n) ? n : 0;
-  } catch {
-    // Best-effort: a missing source_markdown_slug column on pre-v0.32
-    // brains (or other rare DDL drift) falls through to "no orphans
-    // cleaned." The subsequent insertFacts call will surface any real
-    // schema issues with a clearer error.
-    return 0;
-  }
+  // A cleanup failure is authoritative: callers must not write a terminal or
+  // non-extractable marker while facts from an older snapshot may remain.
+  const rows = await engine.executeRaw<{ count: string }>(
+    `WITH del AS (
+       DELETE FROM facts
+       WHERE source_id = $1
+         AND source_markdown_slug = $2
+         AND source LIKE 'cli:extract-conversation-facts%'
+       RETURNING 1
+     )
+     SELECT COUNT(*)::text AS count FROM del`,
+    [sourceId, slug],
+  );
+  const n = parseInt(rows[0]?.count ?? '0', 10);
+  return Number.isFinite(n) ? n : 0;
 }
 
 // ---------------------------------------------------------------------------
@@ -631,6 +678,12 @@ interface ExtractCoreState {
    * batch boundaries + final flush.
    */
   cpMap: Map<string, string>;
+  /**
+   * Opt-in LLM parser state, resolved once per source run. A null model means
+   * the fallback is disabled and no chat content leaves the deterministic
+   * parser path.
+   */
+  llmFallbackModel: string | null;
 }
 
 function cpMapKey(sourceId: string, slug: string): string {
@@ -663,11 +716,150 @@ function cpEntriesToMap(entries: string[]): Map<string, string> {
   return map;
 }
 
+export type DurableExtractionOutcome = 'complete' | 'non_extractable';
+
+interface ConversationPageSnapshot {
+  page: Page;
+  body: string;
+  versionToken: string;
+}
+
+function hasRawTranscriptSidecar(page: Page): boolean {
+  const raw = page.frontmatter?.raw_transcript;
+  return typeof raw === 'string' && raw.trim().length > 0;
+}
+
+function regularPageVersionToken(page: Page): string {
+  // content_hash covers title, type, compiled_truth, timeline, and frontmatter.
+  // Unlike JavaScript Date, it cannot collapse distinct PostgreSQL updates that
+  // happen within the same millisecond. effective_date is parser input too.
+  const hash = page.content_hash ?? createHash('sha256')
+    .update(JSON.stringify({
+      title: page.title,
+      type: page.type,
+      compiled_truth: page.compiled_truth,
+      timeline: page.timeline || '',
+      frontmatter: page.frontmatter || {},
+    }))
+    .digest('hex');
+  const effectiveDate = page.effective_date
+    ? new Date(page.effective_date).toISOString().slice(0, 10)
+    : 'none';
+  return `page-${hash}-${effectiveDate}`;
+}
+
+function snapshotVersionToken(page: Page, body: string): string {
+  if (!hasRawTranscriptSidecar(page)) return regularPageVersionToken(page);
+  // Sidecar contents can change without touching pages.updated_at. Hash the
+  // exact parser input plus parser-relevant page metadata so those edits reopen
+  // the page without a schema migration.
+  return `sidecar-${createHash('sha256')
+    .update(
+      JSON.stringify({
+        body,
+        title: page.title,
+        type: page.type,
+        frontmatter: page.frontmatter,
+        effective_date: page.effective_date ?? null,
+      }),
+    )
+    .digest('hex')}`;
+}
+
+async function preparePageSnapshot(
+  engine: BrainEngine,
+  page: Page,
+): Promise<ConversationPageSnapshot> {
+  const body = await readConversationBodyForParsing(engine, page);
+  return { page, body, versionToken: snapshotVersionToken(page, body) };
+}
+
+function outcomeSession(source: string, slug: string, versionToken: string): string {
+  return `${source}:${slug}:${versionToken}`;
+}
+
+/**
+ * Find v2 outcomes bound to the exact parser input snapshot. Legacy outcome
+ * rows deliberately do not match and are replayed once under the strict v2
+ * protocol. Sidecar files are hashed because pages.updated_at cannot see them.
+ */
+export async function findFreshExtractionOutcomes(
+  engine: BrainEngine,
+  sourceId: string,
+  pages: readonly Page[],
+): Promise<Map<string, DurableExtractionOutcome>> {
+  if (pages.length === 0) return new Map();
+  const expected = new Map<string, string>();
+  for (const page of pages) {
+    // Batch enumeration can already be stale. Refresh before deciding to skip
+    // so an edit between listPages and this check cannot match an old marker.
+    const current = await engine.getPage(page.slug, { sourceId });
+    if (!current) continue;
+    const token = hasRawTranscriptSidecar(current)
+      ? (await preparePageSnapshot(engine, current)).versionToken
+      : regularPageVersionToken(current);
+    expected.set(current.slug, token);
+  }
+  const rows = await engine.executeRaw<{
+    slug: string;
+    source: string;
+    source_session: string | null;
+  }>(
+    `SELECT source_markdown_slug AS slug, source, source_session
+       FROM facts
+      WHERE source_id = $1
+        AND source_markdown_slug = ANY($2::text[])
+        AND source = ANY($3::text[])
+      ORDER BY source_markdown_slug,
+        CASE WHEN source = $4 THEN 0 ELSE 1 END`,
+    [
+      sourceId,
+      pages.map((page) => page.slug),
+      [TERMINAL_AUDIT_SOURCE, NON_EXTRACTABLE_AUDIT_SOURCE],
+      TERMINAL_AUDIT_SOURCE,
+    ],
+  );
+  const outcomes = new Map<string, DurableExtractionOutcome>();
+  for (const row of rows) {
+    if (outcomes.has(row.slug)) continue;
+    const token = expected.get(row.slug);
+    if (!token || row.source_session !== outcomeSession(row.source, row.slug, token)) {
+      continue;
+    }
+    outcomes.set(
+      row.slug,
+      row.source === TERMINAL_AUDIT_SOURCE ? 'complete' : 'non_extractable',
+    );
+  }
+  return outcomes;
+}
+
+function recordDurableOutcomeSkip(
+  state: ExtractCoreState,
+  outcome: DurableExtractionOutcome,
+): void {
+  state.result.pages_considered++;
+  if (outcome === 'complete') state.result.pages_skipped_completed++;
+  else state.result.pages_skipped_non_extractable++;
+}
+
+async function snapshotIsCurrent(
+  engine: BrainEngine,
+  sourceId: string,
+  snapshot: ConversationPageSnapshot,
+): Promise<boolean> {
+  const current = await engine.getPage(snapshot.page.slug, { sourceId });
+  if (!current) return false;
+  const currentSnapshot = await preparePageSnapshot(engine, current);
+  return currentSnapshot.versionToken === snapshot.versionToken;
+}
+
 async function processPage(
   state: ExtractCoreState,
-  page: Page,
+  snapshot: ConversationPageSnapshot,
   sinceIso: string | undefined,
 ): Promise<{ newEndIso: string | null }> {
+  const { page, body } = snapshot;
   state.result.pages_considered++;
 
   // Body cap check first — pre-parse, pre-segment, pre-extraction.
@@ -680,7 +872,6 @@ async function processPage(
     return { newEndIso: null };
   }
 
-  const body = await readConversationBodyForParsing(state.engine, page);
   // v0.41.13.0: thread the full Page through the orchestrator so D8
   // date-derivation chain (frontmatter.date > effective_date >
   // '1970-01-01') AND timezone_policy warnings apply. The historical
@@ -688,13 +879,71 @@ async function processPage(
   // meant Telegram-bracket pages with frontmatter dates landed at
   // 1970-01-01. Now they pick up the correct date.
   const parseResult = parseConversation(body, { page });
-  const messages = parseResult.messages;
+  let messages = parseResult.messages;
   if (parseResult.timezone_warning) {
     process.stderr.write(parseResult.timezone_warning + '\n');
   }
+  // The fallback runs only for a true built-in miss. It never replaces or
+  // polishes a deterministic parse, and it remains unreachable unless the
+  // operator explicitly enables conversation_parser.llm_fallback_enabled.
+  if (
+    !state.dryRun &&
+    messages.length === 0 &&
+    parseResult.phase === 'no_match' &&
+    state.llmFallbackModel
+  ) {
+    const fallbackMessages = await runLlmFallback({
+      modelStr: state.llmFallbackModel,
+      body,
+      engine: state.engine,
+      signal: state.signal,
+      fallbackDate: deriveDateContext({ page }).fallbackDate,
+      propagateError: (error) =>
+        error instanceof BudgetExhausted ||
+        (state.signal?.aborted === true && isAbortError(error)),
+    });
+    if (fallbackMessages && fallbackMessages.length > 0) {
+      messages = fallbackMessages;
+      state.result.pages_llm_fallback++;
+      process.stderr.write(
+        `[extract-conversation-facts] LLM fallback parsed ${fallbackMessages.length} message(s) for ${page.slug}\n`,
+      );
+    }
+  }
+  const allSegments = splitIntoSegments(messages);
   const segments = splitIntoSegments(messages, { sinceIso });
   if (segments.length === 0) {
     state.result.pages_skipped++;
+    if (
+      !state.dryRun &&
+      parseResult.phase !== 'no_match' &&
+      allSegments.length === 0
+    ) {
+      if (await snapshotIsCurrent(state.engine, state.sourceId, snapshot)) {
+        const cleaned = await deleteOrphanFactsForPage(
+          state.engine,
+          state.sourceId,
+          page.slug,
+        );
+        state.result.orphan_facts_cleaned += cleaned;
+        const rowNum = await peekRowNumStart(
+          state.engine,
+          state.sourceId,
+          page.slug,
+        );
+        await writeNonExtractableAuditRow(
+          state.engine,
+          state.sourceId,
+          page.slug,
+          rowNum,
+          snapshot.versionToken,
+          messages.length === 0
+            ? 'no conversation messages found'
+            : 'fewer than two eligible messages',
+        );
+        state.result.pages_marked_non_extractable++;
+      }
+    }
     return { newEndIso: null };
   }
 
@@ -730,24 +979,22 @@ async function processPage(
     const text = renderSegmentForExtraction(page.title || page.slug, seg);
     const sessionId = `${PER_SEGMENT_SOURCE_PREFIX}:${page.slug}`;
 
-    let extracted: Awaited<ReturnType<typeof extractFactsFromTurn>> = [];
-    try {
-      extracted = await extractFactsFromTurn({
-        turnText: text,
-        sessionId,
-        source: PER_SEGMENT_SOURCE_PREFIX,
-        engine: state.engine,
-        abortSignal: state.signal,
-      });
-    } catch (err) {
-      if (isAbortError(err)) throw err;
-      if (err instanceof BudgetExhausted) throw err;
-      // Per-segment LLM failures are best-effort; loop continues.
-      process.stderr.write(
-        `[extract-conversation-facts] segment ${seg.startIso}..${seg.endIso} extractor failed: ${(err as Error).message}\n`,
+    const extraction = await extractFactsFromTurnWithOutcome({
+      turnText: text,
+      sessionId,
+      source: PER_SEGMENT_SOURCE_PREFIX,
+      engine: state.engine,
+      abortSignal: state.signal,
+    });
+    if (!extraction.ok) {
+      const detail = extraction.error instanceof Error
+        ? `: ${extraction.error.message}`
+        : '';
+      throw new Error(
+        `segment ${seg.startIso}..${seg.endIso} extraction failed (${extraction.reason})${detail}`,
       );
-      extracted = [];
     }
+    const extracted = extraction.facts;
 
     state.result.segments_processed++;
     segmentsThisPage++;
@@ -772,19 +1019,9 @@ async function processPage(
         context:
           fact.context ?? `from ${page.slug} segment ${seg.startIso}..${seg.endIso}`,
       }));
-      try {
-        const ins = await state.engine.insertFacts(rows, { source_id: state.sourceId }); // gbrain-allow-direct-insert: canonical bulk extraction path for conversation pages — fences-as-system-of-record doesn't apply because conversations don't carry `## Facts` fences (the chat-log shape is the source-of-truth)
-        pageInsertedTotal += ins.inserted;
-        state.result.facts_inserted += ins.inserted;
-      } catch (err) {
-        if (isAbortError(err)) throw err;
-        // Batch failure is best-effort — segment is the transactional
-        // boundary, so a duplicate-key or constraint error rolls back
-        // this segment only. Loop continues.
-        process.stderr.write(
-          `[extract-conversation-facts] segment ${seg.startIso}..${seg.endIso} insertFacts failed: ${(err as Error).message}\n`,
-        );
-      }
+      const ins = await state.engine.insertFacts(rows, { source_id: state.sourceId }); // gbrain-allow-direct-insert: canonical bulk extraction path for conversation pages — fences-as-system-of-record doesn't apply because conversations don't carry `## Facts` fences (the chat-log shape is the source-of-truth)
+      pageInsertedTotal += ins.inserted;
+      state.result.facts_inserted += ins.inserted;
       rowNum += extracted.length;
     } else {
       // dry-run: count for reporting, no DB write.
@@ -800,20 +1037,28 @@ async function processPage(
   // segment (no break on segmentLimit; that's an explicit partial run).
   const fullyProcessed =
     state.segmentLimit === 0 || segmentsThisPage < state.segmentLimit;
-  if (!state.dryRun && fullyProcessed && newestEnd !== null) {
-    try {
-      await writeTerminalAuditRow(state.engine, state.sourceId, page.slug, rowNum);
-      rowNum++;
-    } catch (err) {
-      if (isAbortError(err)) throw err;
-      // Terminal-row write failure: page is NOT marked complete; next
-      // run resumes. Loud stderr so users see partial-success state.
-      process.stderr.write(
-        `[extract-conversation-facts] ${page.slug} terminal audit write failed: ${(err as Error).message}\n`,
-      );
-      // Suppress the resume-state update so doctor still flags this page.
-      newestEnd = null;
-    }
+  if (
+    !state.dryRun &&
+    fullyProcessed &&
+    newestEnd !== null &&
+    await snapshotIsCurrent(state.engine, state.sourceId, snapshot)
+  ) {
+    // A terminal insert is part of the page transaction contract. Propagate
+    // failure so bulk accounting, CLI exit status, cycle status, and rollups all
+    // report the page as unfinished.
+    await writeTerminalAuditRow(
+      state.engine,
+      state.sourceId,
+      page.slug,
+      rowNum,
+      snapshot.versionToken,
+    );
+    rowNum++;
+  } else if (!state.dryRun && fullyProcessed && newestEnd !== null) {
+    process.stderr.write(
+      `[extract-conversation-facts] ${page.slug} changed during extraction; leaving it unfinished for replay\n`,
+    );
+    newestEnd = null;
   }
 
   if (!state.dryRun && newestEnd !== null) {
@@ -838,13 +1083,14 @@ async function writeTerminalAuditRow(
   sourceId: string,
   slug: string,
   rowNum: number,
+  versionToken: string,
 ): Promise<void> {
   const fact: NewFact & { row_num: number; source_markdown_slug: string } = {
     fact: 'EXTRACTION_COMPLETE',
     kind: 'fact',
     entity_slug: null,
     source: TERMINAL_AUDIT_SOURCE,
-    source_session: `${TERMINAL_AUDIT_SOURCE}:${slug}`,
+    source_session: outcomeSession(TERMINAL_AUDIT_SOURCE, slug, versionToken),
     confidence: 1.0,
     notability: 'low',
     row_num: rowNum,
@@ -863,6 +1109,33 @@ async function writeTerminalAuditRow(
  *   - If absent: create a fresh tracker scoped to `opts.maxCostUsd`
  *     and run the body inside `withBudgetTracker`.
  */
+async function writeNonExtractableAuditRow(
+  engine: BrainEngine,
+  sourceId: string,
+  slug: string,
+  rowNum: number,
+  versionToken: string,
+  reason: string,
+): Promise<void> {
+  const fact: NewFact & { row_num: number; source_markdown_slug: string } = {
+    fact: 'EXTRACTION_NOT_APPLICABLE',
+    kind: 'fact',
+    entity_slug: null,
+    source: NON_EXTRACTABLE_AUDIT_SOURCE,
+    source_session: outcomeSession(
+      NON_EXTRACTABLE_AUDIT_SOURCE,
+      slug,
+      versionToken,
+    ),
+    confidence: 1.0,
+    notability: 'low',
+    context: `scanned, not extractable: ${reason}`,
+    row_num: rowNum,
+    source_markdown_slug: slug,
+  };
+  await engine.insertFacts([fact], { source_id: sourceId }); // gbrain-allow-direct-insert: durable non-extractable audit outcome prevents repeated scans while remaining distinct from successful extraction
+}
+
 export async function runExtractConversationFactsCore(
   engine: BrainEngine,
   opts: ExtractConversationFactsCoreOpts,
@@ -879,6 +1152,11 @@ export async function runExtractConversationFactsCore(
     pages_skipped: 0,
     pages_skipped_too_large: 0,
     pages_skipped_disappeared: 0,
+    pages_skipped_completed: 0,
+    pages_skipped_non_extractable: 0,
+    pages_marked_non_extractable: 0,
+    pages_failed: 0,
+    pages_llm_fallback: 0,
     pages_lock_skipped: 0,
     orphan_facts_cleaned: 0,
     segments_processed: 0,
@@ -924,6 +1202,18 @@ export async function runExtractConversationFactsCore(
   );
   const workers = workersResolved.workers;
 
+  // Privacy boundary: the parser never sends page content to an LLM unless
+  // this exact DB-plane key is explicitly true. Resolve the model once rather
+  // than probing configuration for every page.
+  const llmFallbackEnabled =
+    (await engine.getConfig('conversation_parser.llm_fallback_enabled')) === 'true';
+  const llmFallbackModel = llmFallbackEnabled
+    ? await resolveModel(engine, {
+        tier: 'utility',
+        fallback: 'anthropic:claude-haiku-4-5-20251001',
+      })
+    : null;
+
   const state: ExtractCoreState = {
     result,
     engine,
@@ -934,6 +1224,7 @@ export async function runExtractConversationFactsCore(
     types,
     signal,
     cpMap: new Map(),
+    llmFallbackModel,
   };
 
   // Run body. Either inside the externally-provided tracker scope (no
@@ -957,21 +1248,41 @@ export async function runExtractConversationFactsCore(
      */
     const processPageWithLock = async (page: Page): Promise<void> => {
       const lockId = extractConversationFactsLockId(sourceId, page.slug);
-
-      let sinceIso: string | undefined;
-      // Per-page resume: --force clears prior entries; normal path uses
-      // the latest endIso for this (sourceId, slug) from the shared map.
       if (opts.force) {
         state.cpMap.delete(cpMapKey(sourceId, page.slug));
       }
-      const checkpointed = state.cpMap.get(cpMapKey(sourceId, page.slug)) ?? null;
-      sinceIso = pickLaterIso(checkpointed, opts.sinceIso);
 
       try {
         await withRefreshingLock(
           engine,
           lockId,
-          () => processPage(state, page, sinceIso),
+          async () => {
+            // Re-fetch under the advisory lock. Batch enumeration is only a
+            // candidate list; it must never become the snapshot we certify.
+            const currentPage = await engine.getPage(page.slug, { sourceId });
+            if (!currentPage) {
+              state.result.pages_skipped_disappeared++;
+              return { newEndIso: null };
+            }
+
+            // Close the race between batch selection and lock acquisition.
+            if (!opts.force) {
+              const outcome = (
+                await findFreshExtractionOutcomes(engine, sourceId, [currentPage])
+              ).get(currentPage.slug);
+              if (outcome) {
+                recordDurableOutcomeSkip(state, outcome);
+                return { newEndIso: null };
+              }
+            }
+
+            // A checkpoint without a matching durable v2 outcome cannot prove
+            // which page snapshot it describes. Clear it and replay safely;
+            // delete-orphans-first makes that replay deterministic.
+            state.cpMap.delete(cpMapKey(sourceId, currentPage.slug));
+            const snapshot = await preparePageSnapshot(engine, currentPage);
+            return processPage(state, snapshot, opts.sinceIso);
+          },
           { ttlMinutes: PER_PAGE_LOCK_TTL_MINUTES },
         ).then(() => undefined);
       } catch (err) {
@@ -987,13 +1298,18 @@ export async function runExtractConversationFactsCore(
       }
     };
 
+    // Expand logical types (conversation/meeting/slack/email) to the concrete
+    // `pages.type` values to enumerate, so brains on the granular collector
+    // types are not silently skipped (see ALLOWED_TYPE_ALIASES).
+    const concreteTypes = pageTypesForAllowed(types);
+
     if (opts.slug) {
       const page = await engine.getPage(opts.slug, { sourceId });
       if (!page) {
         result.pages_skipped_disappeared++;
         return;
       }
-      if (!types.includes(page.type as AllowedType)) {
+      if (!concreteTypes.includes(page.type)) {
         result.pages_skipped++;
         return;
       }
@@ -1007,7 +1323,7 @@ export async function runExtractConversationFactsCore(
       // honors AbortSignal at each claim boundary and threads
       // BudgetExhausted abort (D13) automatically.
       let processedPagesCount = 0;
-      pageLoop: for (const type of types) {
+      pageLoop: for (const type of concreteTypes) {
         let offset = 0;
         // eslint-disable-next-line no-constant-condition
         while (true) {
@@ -1022,21 +1338,59 @@ export async function runExtractConversationFactsCore(
           });
           if (batch.length === 0) break;
 
-          // Respect --limit at batch granularity: clip the batch so we
-          // never overshoot the cap by `workers - 1` extra pages.
           let claimable = batch;
-          if (opts.limit) {
-            const remaining = opts.limit - processedPagesCount;
-            if (remaining < batch.length) claimable = batch.slice(0, remaining);
+          // Checkpoints are an intra-page cursor; fresh durable outcomes are
+          // the page-level selection authority and survive checkpoint GC.
+          if (!opts.force && claimable.length > 0) {
+            const fresh = await findFreshExtractionOutcomes(
+              engine,
+              sourceId,
+              claimable,
+            );
+            claimable = claimable.filter((page) => {
+              const outcome = fresh.get(page.slug);
+              if (!outcome) return true;
+              recordDurableOutcomeSkip(state, outcome);
+              return false;
+            });
           }
 
-          await runSlidingPool({
+          // Apply --limit after durable filtering. The limit caps pages that
+          // need work, not already-completed pages scanned to find that work.
+          if (opts.limit) {
+            const remaining = opts.limit - processedPagesCount;
+            if (remaining < claimable.length) {
+              claimable = claimable.slice(0, remaining);
+            }
+          }
+
+          const poolResult = await runSlidingPool({
             items: claimable,
             workers,
             signal,
             onItem: (page) => processPageWithLock(page),
+            onError: (error) => (isAbortError(error) ? 'abort' : 'continue'),
             failureLabel: (page) => page.slug,
           });
+          const cancellation = poolResult.failures.find((failure) =>
+            isAbortError(failure.error),
+          );
+          if (cancellation) throw cancellation.error;
+          if (signal?.aborted) {
+            if (signal.reason instanceof Error) throw signal.reason;
+            throw Object.assign(new Error('caller cancelled'), {
+              name: 'AbortError',
+            });
+          }
+          result.pages_failed += poolResult.errored;
+          for (const failure of poolResult.failures) {
+            const message = failure.error instanceof Error
+              ? failure.error.message
+              : String(failure.error);
+            process.stderr.write(
+              `[extract-conversation-facts] ${failure.label} failed: ${message}\n`,
+            );
+          }
 
           processedPagesCount += claimable.length;
           offset += batch.length;
@@ -1057,6 +1411,7 @@ export async function runExtractConversationFactsCore(
     }
   };
 
+  let ownedTracker: BudgetTracker | null = null;
   try {
     if (opts.budgetTracker) {
       // Caller-managed scope — use as-is, no wrap (nested wrap REPLACES
@@ -1067,6 +1422,7 @@ export async function runExtractConversationFactsCore(
         maxCostUsd: opts.maxCostUsd ?? DEFAULT_MAX_COST_USD,
         label: `extract-conversation-facts:${sourceId}`,
       });
+      ownedTracker = tracker;
       try {
         await withBudgetTracker(tracker, body);
       } finally {
@@ -1090,13 +1446,34 @@ export async function runExtractConversationFactsCore(
     throw err;
   }
 
+  // gateway.chat preserves a successful provider result when the final
+  // tracker.record() discovers an underestimated overage. Usually the next
+  // reserve surfaces it, but a fallback that yields fewer than two messages
+  // has no next call. Detect that terminal overage so the result and rollup
+  // remain honest.
+  const effectiveTracker = opts.budgetTracker ?? ownedTracker;
+  if (
+    effectiveTracker?.cap !== undefined &&
+    effectiveTracker.totalSpent > effectiveTracker.cap
+  ) {
+    result.budget_exhausted = true;
+    result.spent_usd = effectiveTracker.totalSpent;
+  }
+
   // v0.42 — Wave B1: extract-conversation-facts writes a receipt page
   // (queryable + citable per D-EXTRACT-17/19) AND UPSERTs the per-day
   // rollup row (best-effort cache per F-OUT-19). Both are best-effort —
   // failures stderr-warn but never fail the parent operation.
   // --dry-run must not persist cache/knowledge state: skip the rollup UPSERT +
   // receipt-page write so a preview leaves no extract cache row behind.
-  if (!dryRun) await writeRunReceiptAndRollup(engine, sourceId, result, /* halted */ false);
+  if (!dryRun) {
+    await writeRunReceiptAndRollup(
+      engine,
+      sourceId,
+      result,
+      /* halted */ result.budget_exhausted === true,
+    );
+  }
 
   return result;
 }
@@ -1134,7 +1511,12 @@ async function writeRunReceiptAndRollup(
         extracted_at: now,
         total_rows: result.facts_inserted,
         cost_usd: result.spent_usd ?? 0,
-        summary: `Extracted ${result.facts_inserted} facts from ${result.pages_processed}/${result.pages_considered} eligible pages.`,
+        summary:
+          `Extracted ${result.facts_inserted} facts from ` +
+          `${result.pages_processed}/${result.pages_considered} eligible pages` +
+          (result.pages_failed > 0
+            ? `; ${result.pages_failed} page(s) failed and remain unfinished.`
+            : '.'),
       });
     } catch (err) {
       // Best-effort: receipt write failure shouldn't kill the run.
@@ -1148,12 +1530,13 @@ async function writeRunReceiptAndRollup(
   // Rollup UPSERT: ALWAYS fire so doctor's extract_health sees the
   // cycle ran (even no-op runs are signal — they prove the extractor
   // was alive). Best-effort per F-OUT-19.
+  const incomplete = halted || result.pages_failed > 0;
   await upsertExtractRollup(engine, {
     kind: 'facts.conversation',
     source_id: sourceId,
     cost_delta: result.spent_usd ?? 0,
-    round_completed_delta: halted ? 0 : 1,
-    halt_delta: halted ? 1 : 0,
+    round_completed_delta: incomplete ? 0 : 1,
+    halt_delta: incomplete ? 1 : 0,
   });
 }
 
@@ -1381,6 +1764,11 @@ export async function runExtractConversationFacts(
     pages_skipped: 0,
     pages_skipped_too_large: 0,
     pages_skipped_disappeared: 0,
+    pages_skipped_completed: 0,
+    pages_skipped_non_extractable: 0,
+    pages_marked_non_extractable: 0,
+    pages_failed: 0,
+    pages_llm_fallback: 0,
     pages_lock_skipped: 0,
     orphan_facts_cleaned: 0,
     segments_processed: 0,
@@ -1421,6 +1809,11 @@ export async function runExtractConversationFacts(
       aggregate.pages_skipped += perSource.pages_skipped;
       aggregate.pages_skipped_too_large += perSource.pages_skipped_too_large;
       aggregate.pages_skipped_disappeared += perSource.pages_skipped_disappeared;
+      aggregate.pages_skipped_completed += perSource.pages_skipped_completed;
+      aggregate.pages_skipped_non_extractable += perSource.pages_skipped_non_extractable;
+      aggregate.pages_marked_non_extractable += perSource.pages_marked_non_extractable;
+      aggregate.pages_failed += perSource.pages_failed;
+      aggregate.pages_llm_fallback += perSource.pages_llm_fallback;
       aggregate.pages_lock_skipped += perSource.pages_lock_skipped;
       aggregate.orphan_facts_cleaned += perSource.orphan_facts_cleaned;
       aggregate.segments_processed += perSource.segments_processed;
@@ -1452,6 +1845,21 @@ export async function runExtractConversationFacts(
   if (aggregate.pages_skipped_disappeared > 0) {
     console.log(`  Skipped ${aggregate.pages_skipped_disappeared} page(s) that disappeared between enumeration and fetch.`);
   }
+  if (aggregate.pages_skipped_completed > 0) {
+    console.log(`  Skipped ${aggregate.pages_skipped_completed} page(s) with fresh durable completion outcomes.`);
+  }
+  if (aggregate.pages_skipped_non_extractable > 0) {
+    console.log(`  Skipped ${aggregate.pages_skipped_non_extractable} page(s) previously scanned as not extractable.`);
+  }
+  if (aggregate.pages_marked_non_extractable > 0) {
+    console.log(`  Marked ${aggregate.pages_marked_non_extractable} page(s) as scanned, not extractable.`);
+  }
+  if (aggregate.pages_failed > 0) {
+    console.error(`  Failed ${aggregate.pages_failed} page(s); they remain unfinished and will retry.`);
+  }
+  if (aggregate.pages_llm_fallback > 0) {
+    console.log(`  Parsed ${aggregate.pages_llm_fallback} page(s) with the opt-in LLM fallback.`);
+  }
   if (aggregate.pages_lock_skipped > 0) {
     console.log(`  Skipped ${aggregate.pages_lock_skipped} page(s) held by another worker / process (will retry next run).`);
   }
@@ -1468,6 +1876,9 @@ export async function runExtractConversationFacts(
   // anyBudgetExhausted doesn't trigger exit 3; the budget message
   // above already tells the user what to do, and exit 0 is the right
   // signal for "ran to the cap intentionally."
+  if (aggregate.pages_failed > 0) {
+    process.exit(1);
+  }
   if (aggregate.pages_lock_skipped > 0 && !anyBudgetExhausted) {
     process.exit(3);
   }

src/commands/extract.ts

@@ -35,7 +35,7 @@ import type { BrainEngine, LinkBatchInput, TimelineBatchInput } from '../core/en
 import type { PageType } from '../core/types.ts';
 import { parseMarkdown } from '../core/markdown.ts';
 import {
-  extractPageLinks, parseTimelineEntries, inferLinkType, makeResolver,
+  extractPageLinks, parseTimelineEntries, deriveTimelineAnchor, inferLinkType, makeResolver,
   extractFrontmatterLinks, isGlobalBasenameEnabled, LINK_EXTRACTOR_VERSION_TS,
   WIKILINK_BASENAME_LINK_TYPE,
   buildBasenameIndex, queryBasenameIndex, stripCodeBlocks,
@@ -433,7 +433,10 @@ export async function extractLinksFromFile(
       async resolve(name: string, dirHint?: string | string[]): Promise<string | null> {
         if (!name) return null;
         const trimmed = name.trim();
-        if (/^[a-z][a-z0-9-]*\/[a-z0-9][a-z0-9-]*$/.test(trimmed) && allSlugs.has(trimmed)) {
+        // Same broadened slug-shape as makeResolver step 1: accepts
+        // digit-leading folders (`90-people/nicolai`) and nested paths.
+        // Exact Set membership guards it — no false positives.
+        if (/\//.test(trimmed) && /^[a-z0-9][a-z0-9/_-]*$/.test(trimmed) && allSlugs.has(trimmed)) {
           return trimmed;
         }
         const hints = Array.isArray(dirHint) ? dirHint : (dirHint ? [dirHint] : []);
@@ -582,6 +585,17 @@ export interface ExtractOpts {
    * before (single-'default'-source brains unaffected).
    */
   sourceId?: string;
+  /**
+   * v0.42 — also extract frontmatter links on the incremental (slugs) path.
+   * `extractForSlugs` extracts BODY links only by default; set this true to also
+   * parse each changed page's frontmatter so `sources:`/`related:` edges stay fresh
+   * when YAML is edited externally and synced in. Applied PER changed page, so the
+   * incremental walk stays bounded (no switch to a full DB scan). Only honored on
+   * the incremental path (`slugs` defined); the full-walk path already covers
+   * frontmatter via its own dispatch. Gated upstream by the config key
+   * `autopilot.incremental_extract_include_frontmatter` (default off).
+   */
+  includeFrontmatter?: boolean;
 }
 
 /**
@@ -620,7 +634,7 @@ export async function runExtractCore(engine: BrainEngine, opts: ExtractOpts): Pr
       // Nothing changed — skip entirely.
       return result;
     }
-    const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers, opts.signal, opts.sourceId);
+    const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers, opts.signal, opts.sourceId, opts.includeFrontmatter);
     result.links_created = r.links_created;
     result.timeline_entries_created = r.timeline_created;
     result.pages_processed = r.pages;
@@ -735,6 +749,12 @@ export async function runExtract(engine: BrainEngine, args: string[]) {
   // v0.41.18.0 (A11, T8): --from-meetings extracts timeline entries from
   // meeting pages onto each discussed entity. Timeline subcommand only.
   const fromMeetings = args.includes('--from-meetings');
+  // --infer-dates: for pages whose body has NO parseable timeline line, anchor
+  // one entry at the page's computed effective_date (frontmatter / filename date,
+  // never the updated_at fallback). Default OFF for back-compat — comms/calendar
+  // brains opt in to populate timeline from slug/frontmatter dates. DB-source only
+  // (needs the full Page.effective_date, which getPage projects).
+  const inferDates = args.includes('--infer-dates');
   // v0.41.17.0 (T7, D9): --workers N parsed via the shared validator.
   // Honored on the fs-walk inner loops only; DB-source paths stay
   // serial in v0.41.17.0 (see ExtractOpts.workers doc).
@@ -949,7 +969,7 @@ Status (v0.42):
           result.pages_processed = r.pages;
         }
         if (subcommand === 'timeline' || subcommand === 'all') {
-          const r = await extractTimelineFromDB(engine, dryRun, jsonMode, typeFilter, since, { sourceIdFilter });
+          const r = await extractTimelineFromDB(engine, dryRun, jsonMode, typeFilter, since, { sourceIdFilter, inferDates });
           result.timeline_entries_created = r.created;
           result.pages_processed = Math.max(result.pages_processed, r.pages);
         }
@@ -1011,6 +1031,11 @@ async function extractForSlugs(
   signal?: AbortSignal,
   // #1747/#1503: stamp resolved brain source id on batch rows (see ExtractOpts.sourceId).
   sourceId?: string,
+  // v0.42: when true, also extract frontmatter links per changed page so
+  // externally-edited YAML (`sources:`/`related:`) stays fresh on the cycle.
+  // Default false preserves the body-only incremental behavior. Gated upstream
+  // by `autopilot.incremental_extract_include_frontmatter`.
+  includeFrontmatter: boolean = false,
 ): 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);
@@ -1089,7 +1114,7 @@ async function extractForSlugs(
         const content = readFileSync(fullPath, 'utf-8');
 
         if (doLinks) {
-          const links = await extractLinksFromFile(content, relPath, allSlugs, { globalBasename });
+          const links = await extractLinksFromFile(content, relPath, allSlugs, { globalBasename, includeFrontmatter });
           for (const link of links) {
             if (dryRun) {
               if (!jsonMode) console.log(`  ${link.from_slug} → ${link.to_slug} (${link.link_type})`);
@@ -1564,7 +1589,7 @@ async function extractTimelineFromDB(
   jsonMode: boolean,
   typeFilter: PageType | undefined,
   since: string | undefined,
-  opts?: { sourceIdFilter?: string },
+  opts?: { sourceIdFilter?: string; inferDates?: boolean },
 ): Promise<{ created: number; pages: number }> {
   // v0.32.8: listAllPageRefs enumerates (slug, source_id) pairs so we can
   // thread sourceId to getPage and addTimelineEntriesBatch. Pre-fix used
@@ -1573,6 +1598,7 @@ async function extractTimelineFromDB(
   // v0.37.7.0 #1204: when sourceIdFilter is set, scope the walk to one
   // source so federated brain users can extract per-source.
   const sourceIdFilter = opts?.sourceIdFilter;
+  const inferDates = opts?.inferDates ?? false;
   const allRefs = sourceIdFilter
     ? (await engine.listAllPageRefs()).filter(r => r.source_id === sourceIdFilter)
     : await engine.listAllPageRefs();
@@ -1612,7 +1638,19 @@ async function extractTimelineFromDB(
     }
 
     const fullContent = page.compiled_truth + '\n' + page.timeline;
-    const entries = parseTimelineEntries(fullContent);
+    let entries = parseTimelineEntries(fullContent);
+    // --infer-dates: pages with no in-body timeline line but a trustworthy
+    // content date (frontmatter / filename) get one anchor entry at that date.
+    // Applied ONLY on the zero-entry path so it never shadows a real timeline.
+    if (entries.length === 0 && inferDates) {
+      const anchor = deriveTimelineAnchor({
+        slug,
+        title: page.title,
+        effectiveDate: page.effective_date,
+        effectiveDateSource: page.effective_date_source,
+      });
+      if (anchor) entries = [anchor];
+    }
 
     for (const entry of entries) {
       if (dryRunSeen) {

src/commands/frontmatter.ts

@@ -17,7 +17,7 @@
 
 import { readFileSync, writeFileSync, existsSync, lstatSync, readdirSync } from 'fs';
 import { setCliExitVerdict } from '../core/cli-force-exit.ts';
-import { join, relative, resolve } from 'path';
+import { join, relative, resolve, basename, dirname } from 'path';
 import type { BrainEngine } from '../core/engine.ts';
 import { loadConfig, toEngineConfig } from '../core/config.ts';
 import { createEngine } from '../core/engine-factory.ts';
@@ -155,6 +155,27 @@ interface FileValidation {
   backupPath?: string;
 }
 
+/**
+ * Walk up from `start` (file or dir) to the brain root — the nearest ancestor
+ * containing a `.git` marker — so slug derivation is brain-root-relative,
+ * matching how sync/extract compute slugs. Falls back to the start's own
+ * directory when no marker is found. Fixes #565: for a single-file target,
+ * `relative(resolve(target), file)` was empty (target === file) and fell back
+ * to the ABSOLUTE path, yielding bogus "root/brain/..." slugs and false
+ * SLUG_MISMATCH — which the install-hook pre-commit hook hits on every commit.
+ */
+function findBrainRoot(start: string): string {
+  const startDir = lstatSync(start).isDirectory() ? start : dirname(start);
+  let candidate = startDir;
+  for (let i = 0; i < 40; i++) {
+    if (existsSync(join(candidate, '.git'))) return candidate;
+    const parent = resolve(candidate, '..');
+    if (parent === candidate) break;
+    candidate = parent;
+  }
+  return startDir;
+}
+
 async function runValidate(rest: string[]): Promise<void> {
   const flags: ValidateFlags = { json: false, fix: false, dryRun: false };
   let target: string | null = null;
@@ -177,13 +198,17 @@ async function runValidate(rest: string[]): Promise<void> {
     return;
   }
 
+  const brainRoot = findBrainRoot(resolved);
   const files = collectFiles(resolved);
   const results: FileValidation[] = [];
   const backupRunId = makeFrontmatterBackupRunId();
 
   for (const file of files) {
     const content = readFileSync(file, 'utf8');
-    const expectedSlug = slugifyPath(relative(resolve(target), file) || file);
+    const rel = relative(brainRoot, file);
+    // Files above/outside the brain root fall back to basename rather than
+    // emitting a "../"-prefixed slug for non-brain files.
+    const expectedSlug = slugifyPath(rel && !rel.startsWith('..') ? rel : basename(file));
     const parsed = parseMarkdown(content, file, { validate: true, expectedSlug });
     const errs = parsed.errors ?? [];
     const result: FileValidation = {

src/commands/import.ts

@@ -59,6 +59,11 @@ export async function runImport(
      * Threaded by performFullSync for `gbrain sync --exclude`.
      */
     exclude?: string[];
+    /**
+     * Opt out of the git-visible fast path and walk the filesystem directly,
+     * so markdown/code files matched by .gitignore can still be imported.
+     */
+    includeGitignored?: boolean;
     /**
      * #753/#774 monorepo subdir-source support: when set, slugs and
      * `source_path` are computed relative to this root (the git repo root)
@@ -71,6 +76,7 @@ export async function runImport(
   const noEmbed = args.includes('--no-embed');
   const fresh = args.includes('--fresh');
   const jsonOutput = args.includes('--json');
+  const includeGitignored = args.includes('--include-gitignored') || opts.includeGitignored === true;
 
   // T7 (D9): refuse cleanly when init persisted the deferred-setup sentinel,
   // unless the user is explicitly skipping embedding via `--no-embed` (in
@@ -185,7 +191,7 @@ export async function runImport(
   const dirArg = args.find((a, i) => !a.startsWith('--') && !flagValues.has(i));
 
   if (!dirArg) {
-    console.error('Usage: gbrain import <dir> [--no-embed] [--workers N] [--fresh] [--source-id <id>] [--json]');
+    console.error('Usage: gbrain import <dir> [--no-embed] [--workers N] [--fresh] [--source-id <id>] [--include-gitignored] [--json]');
     process.exit(1);
   }
   // #1728: capture the import target ONCE as an absolute real path. Every
@@ -209,7 +215,7 @@ export async function runImport(
   const strategy: SyncStrategy = opts.strategy ?? 'markdown';
   const _walkT0 = Date.now();
   console.error(`[gbrain phase] import.collect_files start dir=${dir} strategy=${strategy}`);
-  let allFiles = collectSyncableFiles(dir, { strategy });
+  let allFiles = collectSyncableFiles(dir, { strategy, includeGitignored });
   console.error(
     `[gbrain phase] import.collect_files done ${Date.now() - _walkT0}ms files=${allFiles.length}`,
   );
@@ -545,6 +551,7 @@ function resolveMaxWalkDepth(): number {
 
 interface CollectOpts {
   strategy?: SyncStrategy;
+  includeGitignored?: boolean;
 }
 
 /**
@@ -675,8 +682,10 @@ export function collectSyncableFiles(dir: string, opts: CollectOpts = {}): strin
   // vendored data/fixtures). `--cached --others --exclude-standard` = tracked
   // PLUS untracked-not-ignored, so uncommitted source is still indexed. Non-git
   // dirs (or git unavailable) fall through to the FS walk below.
-  const gitFiles = gitListSyncableFiles(dir, strategy, multimodalOn);
-  if (gitFiles) return gitFiles;
+  if (!opts.includeGitignored) {
+    const gitFiles = gitListSyncableFiles(dir, strategy, multimodalOn);
+    if (gitFiles) return gitFiles;
+  }
 
   const maxDepth = resolveMaxWalkDepth();
   const visitedInodes = new Map<string, true>();

src/commands/init.ts

@@ -26,6 +26,8 @@ export async function runInit(args: string[]) {
     return;
   }
 
+  validateInitFlags(args);
+
   const isSupabase = args.includes('--supabase');
   const isPGLite = args.includes('--pglite');
   const isMcpOnly = args.includes('--mcp-only');
@@ -151,6 +153,65 @@ export async function runInit(args: string[]) {
   return initPostgres({ databaseUrl, jsonOutput, apiKey, aiOpts, schemaPack, skipEmbedCheck });
 }
 
+const INIT_BOOLEAN_FLAGS = new Set([
+  '--pglite',
+  '--supabase',
+  '--mcp-only',
+  '--force',
+  '--non-interactive',
+  '--migrate-only',
+  '--json',
+  '--no-embedding',
+  '--skip-embed-check',
+]);
+
+const INIT_VALUE_FLAGS = new Set([
+  '--url',
+  '--key',
+  '--path',
+  '--schema-pack',
+  '--embedding-model',
+  '--model',
+  '--embedding-dimensions',
+  '--expansion-model',
+  '--chat-model',
+  '--mcp-url',
+  '--issuer-url',
+  '--oauth-client-id',
+  '--oauth-client-secret',
+]);
+
+function validateInitFlags(args: string[]) {
+  for (let i = 0; i < args.length; i++) {
+    const arg = args[i];
+    if (!arg.startsWith('-')) continue;
+
+    if (INIT_BOOLEAN_FLAGS.has(arg)) continue;
+
+    if (INIT_VALUE_FLAGS.has(arg)) {
+      if (i + 1 >= args.length || args[i + 1].startsWith('-')) {
+        failInitFlag(`gbrain init: ${arg} requires a value`, args.includes('--json'));
+      }
+      i += 1;
+      continue;
+    }
+
+    if (arg.startsWith('--')) {
+      failInitFlag(`gbrain init: unknown flag ${arg}`, args.includes('--json'));
+    }
+  }
+}
+
+function failInitFlag(message: string, jsonOutput: boolean): never {
+  if (jsonOutput) {
+    console.log(JSON.stringify({ status: 'error', reason: 'invalid_flag', message }));
+  } else {
+    console.error(message);
+    console.error('Run `gbrain init --help` for supported flags.');
+  }
+  process.exit(1);
+}
+
 interface ResolveAIOptionsArgs {
   verbose: string | null;        // --embedding-model
   shorthand: string | null;      // --model
@@ -276,7 +337,9 @@ async function resolveAIOptions(opts: ResolveAIOptionsArgs): Promise<ResolvedAIO
       process.exit(1);
     }
     out.embedding_model = `${shorthand}:${firstModel}`;
-    out.embedding_dimensions = recipe.touchpoints.embedding!.default_dims;
+    // #2051: width follows the model actually chosen, not the recipe default.
+    const { embeddingDimsForModel } = await import('../core/ai/model-resolver.ts');
+    out.embedding_dimensions = embeddingDimsForModel(recipe, firstModel);
   }
 
   if (dimsArg !== null && !Number.isNaN(dimsArg) && dimsArg > 0) {
@@ -300,8 +363,13 @@ async function resolveAIOptions(opts: ResolveAIOptionsArgs): Promise<ResolvedAIO
       );
       process.exit(1);
     }
-    if (recipe?.touchpoints.embedding?.default_dims) {
-      out.embedding_dimensions = recipe.touchpoints.embedding.default_dims;
+    // #2051: resolve the width from the SPECIFIC model, not the recipe-wide
+    // default. `--embedding-model ollama:bge-m3` must yield 1024, not Ollama's
+    // nomic-shaped 768.
+    if (recipe) {
+      const { embeddingDimsForModel } = await import('../core/ai/model-resolver.ts');
+      const dims = embeddingDimsForModel(recipe, out.embedding_model);
+      if (dims > 0) out.embedding_dimensions = dims;
     }
   }
 
@@ -464,9 +532,11 @@ async function resolveEmbeddingByEnv(out: ResolvedAIOptions, nonInteractive: boo
       // legacy OpenAI 1536), not the recipe's 2560.
       const { DEFAULT_EMBEDDING_MODEL, DEFAULT_EMBEDDING_DIMENSIONS } =
         await import('../core/ai/defaults.ts');
+      const { embeddingDimsForModel } = await import('../core/ai/model-resolver.ts');
+      // #2051: non-canonical models resolve per-model, not recipe-wide.
       const dims = fullModel === DEFAULT_EMBEDDING_MODEL
         ? DEFAULT_EMBEDDING_DIMENSIONS
-        : tp.default_dims;
+        : embeddingDimsForModel(r, model);
       out.embedding_model = fullModel;
       out.embedding_dimensions = dims;
       console.error(
@@ -1047,12 +1117,12 @@ async function initPostgres(opts: {
 
   // v0.37.10.0 T6 (D11) + v0.37.11.0 Lane B.2: ALWAYS configure gateway BEFORE
   // initSchema. Same preflight contract as PGLite. Refuse to call initSchema
-  // until the gateway-resolved dim is validated. Schema substitution in
-  // src/schema.sql is currently a static `vector(1536)` for Postgres (unlike
-  // PGLite's templated dim), so a Voyage/ZE-configured Postgres brain will
-  // still need a future schema rewrite path — preflight makes the
-  // not-yet-supported case fail loud rather than silently produce a stuck
-  // 1536d column.
+  // until the gateway-resolved dim is validated. PostgresEngine.initSchema()
+  // passes the resolved model and dimensions through getPostgresSchema(),
+  // which templates the static `vector(1536)` source before executing it.
+  // Preflight therefore prevents an invalid dimension from reaching schema
+  // generation, while the post-init assertion below guards against templating
+  // drift.
   let resolvedDim: number | undefined;
   let resolvedModel: string | undefined;
   if (opts.aiOpts?.noEmbedding) {
@@ -1491,7 +1561,7 @@ export function reportModStatus(): void {
     console.log('  cd ~/.claude/skills/gstack && ./setup');
   }
   console.log('Resolver: skills/RESOLVER.md');
-  console.log('Soul audit: run `gbrain soul-audit` to customize agent identity');
+  console.log('Soul audit: ask your agent to "run a soul audit" to customize its identity (see skills/soul-audit)');
   // Retrieval Reflex (#1981): the deterministic pointer layer is ON by default
   // (no action needed). The policy skill is installed into the HOST repo on
   // request — we PRINT the command rather than silently mutating the host repo.

src/commands/jobs.ts

@@ -143,6 +143,31 @@ export function resolveWorkerConcurrency(args: string[], env: NodeJS.ProcessEnv
   return parsed;
 }
 
+/**
+ * #3026: the thin-client `list`/`get` branches receive jobs as parsed JSON
+ * off the MCP wire, where every timestamp is an ISO string — but formatJob /
+ * formatJobDetail (and the stalled-detection comparison) hold a Date
+ * contract, hydrated locally by MinionQueue.rowToJob. Rehydrate once at the
+ * unpack boundary so both paths hand the formatters real Dates. Exported for
+ * unit tests.
+ */
+const JOB_DATE_FIELDS = [
+  'created_at', 'updated_at', 'started_at', 'finished_at', 'lock_until', 'delay_until',
+] as const;
+
+export function rehydrateJobDates<T>(job: T): T {
+  if (!job || typeof job !== 'object') return job;
+  const rec = job as { [k: string]: unknown };
+  for (const field of JOB_DATE_FIELDS) {
+    const v = rec[field];
+    if (typeof v === 'string') {
+      const d = new Date(v);
+      if (!Number.isNaN(d.getTime())) rec[field] = d;
+    }
+  }
+  return job;
+}
+
 function formatJob(job: MinionJob): string {
   const dur = job.finished_at && job.started_at
     ? `${((job.finished_at.getTime() - job.started_at.getTime()) / 1000).toFixed(1)}s`
@@ -208,7 +233,7 @@ USAGE
   gbrain jobs get <id>
   gbrain jobs cancel <id>
   gbrain jobs retry <id>
-  gbrain jobs prune [--older-than 30d]
+  gbrain jobs prune [--older-than 30d] [--dry-run]
   gbrain jobs delete <id>
   gbrain jobs stats
   gbrain jobs smoke
@@ -496,7 +521,7 @@ HANDLER TYPES (built in)
         const raw = await callRemoteTool(cfg!, 'list_jobs', {
           status, queue: queueName, limit,
         }, { timeoutMs: 30_000 });
-        jobs = unpackToolResult<MinionJob[]>(raw);
+        jobs = unpackToolResult<MinionJob[]>(raw).map((j) => rehydrateJobDates(j));
       } else {
         try { await queue.ensureSchema(); }
         catch (e) { console.error(e instanceof Error ? e.message : String(e)); process.exit(1); }
@@ -525,7 +550,7 @@ HANDLER TYPES (built in)
       if (isThinClient(cfg)) {
         try {
           const raw = await callRemoteTool(cfg!, 'get_job', { id }, { timeoutMs: 30_000 });
-          job = unpackToolResult<MinionJob | null>(raw);
+          job = rehydrateJobDates(unpackToolResult<MinionJob | null>(raw));
         } catch (e) {
           // The remote op throws `invalid_params` on not-found; surface as
           // the same "Job not found" exit-1 the local path produces.
@@ -608,8 +633,15 @@ HANDLER TYPES (built in)
       try { await queue.ensureSchema(); }
       catch (e) { console.error(e instanceof Error ? e.message : String(e)); process.exit(1); }
 
-      const count = await queue.prune({ olderThan: new Date(Date.now() - days * 86400000) });
-      console.log(`Pruned ${count} jobs older than ${days} days.`);
+      // #2712: --dry-run previews the count without deleting. It used to be
+      // silently ignored (the destructive default ran anyway).
+      const dryRun = hasFlag(args, '--dry-run');
+      const count = await queue.prune({ olderThan: new Date(Date.now() - days * 86400000), dryRun });
+      if (dryRun) {
+        console.log(`[dry-run] Would prune ${count} jobs older than ${days} days. Nothing deleted.`);
+      } else {
+        console.log(`Pruned ${count} jobs older than ${days} days.`);
+      }
       break;
     }
 
@@ -1885,6 +1917,7 @@ export async function registerBuiltinHandlers(
       signal: job.signal,
       deadlineAtMs: job.deadlineAtMs, // #2781: phases budget sub-work from remaining time
       phases,
+      forceGlobalOrphans: true,
       yieldBetweenPhases: async () => { await new Promise<void>((r) => setImmediate(r)); },
     });
 

src/commands/migrate-embeddings.ts

@@ -0,0 +1,402 @@
+/**
+ * `gbrain migrate embeddings --to <provider:model>` (#3390) — the
+ * provider-agnostic forward migration off any embedding provider, built for
+ * the ZeroEntropy 2026-09-04 sunset but not keyed to it.
+ *
+ * Also reachable as `gbrain retrieval-upgrade` — the command README.md and
+ * doctor.ts have promised since v0.36 but which never had a dispatch branch.
+ *
+ * Flow (everything heavy is reused, see src/core/embedding-migration.ts):
+ *   1. plan     — chunk/char counts via the widened stale predicates,
+ *                 cost estimate from embedding-pricing.ts
+ *   2. preflight— print estimate; require --yes or interactive confirm
+ *                 (non-TTY without --yes refuses with exit 2, mirroring the
+ *                 reindex-code cost gate in docs/operations/spend-controls.md)
+ *   3. probe    — one live embed against the TARGET provider BEFORE any
+ *                 mutation (validates key + model + dims in one shot)
+ *   4. apply    — schema transition (dim change), config (DB + file plane),
+ *                 #3391 NULL-signature-inclusive invalidation, cache purge
+ *   5. re-embed — runEmbedCore --stale --catch-up with single-flight locks,
+ *                 pacing (--pace), progress reporting. Resumable: a killed
+ *                 run re-runs the SAME command; the NULL-embedding cursor is
+ *                 the checkpoint and steps 3-4 no-op on the second pass.
+ */
+
+import type { BrainEngine } from '../core/engine.ts';
+import { serr, slog } from '../core/console-prefix.ts';
+import {
+  planEmbeddingMigration,
+  applyEmbeddingMigration,
+  completeEmbeddingMigration,
+  reconcilePageSignatures,
+  MIGRATION_STATE_KEY,
+  type EmbeddingMigrationPlan,
+} from '../core/embedding-migration.ts';
+import { formatEnvOverrideWarning } from '../core/retrieval-upgrade-planner.ts';
+import { parsePaceArgs, runEmbedCore } from './embed.ts';
+
+export interface MigrateEmbeddingsFlags {
+  to?: string;
+  dim?: number;
+  yes: boolean;
+  dryRun: boolean;
+  json: boolean;
+  noEmbed: boolean;
+  ignoreEnvOverride: boolean;
+  batchSize?: number;
+  pace?: ReturnType<typeof parsePaceArgs>;
+}
+
+export function parseMigrateEmbeddingsFlags(args: string[]): MigrateEmbeddingsFlags {
+  const toIdx = args.indexOf('--to');
+  const dimIdx = args.indexOf('--dim');
+  const dimRaw = dimIdx >= 0 ? parseInt(args[dimIdx + 1] ?? '', 10) : NaN;
+  const bsIdx = args.indexOf('--batch-size');
+  const bsRaw = bsIdx >= 0 ? parseInt(args[bsIdx + 1] ?? '', 10) : NaN;
+  const batchSize = Number.isFinite(bsRaw) && bsRaw > 0 ? Math.min(10_000, bsRaw) : undefined;
+  return {
+    to: toIdx >= 0 ? args[toIdx + 1] : undefined,
+    dim: Number.isFinite(dimRaw) && dimRaw > 0 ? dimRaw : undefined,
+    yes: args.includes('--yes') || args.includes('--non-interactive'),
+    dryRun: args.includes('--dry-run'),
+    json: args.includes('--json'),
+    noEmbed: args.includes('--no-embed'),
+    ignoreEnvOverride: args.includes('--ignore-env-override'),
+    ...(batchSize !== undefined && { batchSize }),
+    pace: parsePaceArgs(args),
+  };
+}
+
+function printHelp(): void {
+  process.stdout.write(`Usage: gbrain migrate embeddings --to <provider:model> [flags]
+
+Re-embed the whole brain onto a different embedding provider/model. Handles
+dimension changes (schema transition), pages without a recorded embedding
+signature (#3391), the query cache, and resume-after-kill. The forward path
+off a sunsetting provider.
+
+Flags:
+  --to <provider:model>   Target embedding model (e.g. openai:text-embedding-3-small).
+  --dim <N>               Target dimensions. Defaults to the provider recipe's
+                          declared width; required when the recipe declares none.
+  --dry-run               Plan + cost estimate only; change nothing.
+  --yes                   Skip the confirm prompt (required non-interactively).
+  --json                  Machine-readable envelope on stdout.
+  --no-embed              Apply schema + config + invalidation, but skip the
+                          re-embed pass (run \`gbrain embed --stale --include-null-signature\`
+                          or \`... --background\` yourself).
+  --batch-size <N>        Stale-chunk batch size for the re-embed (default 2000).
+  --pace[=mode]           DB-contention pacing for the re-embed (off|gentle|balanced|aggressive).
+  --ignore-env-override   Proceed even when GBRAIN_EMBEDDING_* env vars would
+                          override the target at runtime (you know why).
+  --help                  Show this help.
+
+A killed run is resumable: re-run the same command. Already-migrated chunks
+are never re-embedded twice.
+`);
+}
+
+function renderPlan(plan: EmbeddingMigrationPlan): string {
+  const lines: string[] = [];
+  lines.push('Embedding migration plan');
+  lines.push(`  From: ${plan.from_model} (${plan.from_dims}d${plan.column_dims !== null && plan.column_dims !== plan.from_dims ? `; column is actually ${plan.column_dims}d` : ''})`);
+  lines.push(`  To:   ${plan.to_model} (${plan.to_dims}d)`);
+  if (plan.dim_change) {
+    lines.push(`  DESTRUCTIVE: the embedding column is rebuilt at ${plan.to_dims}d, which DELETES`);
+    lines.push('          every stored embedding vector in this brain. They are not recoverable —');
+    lines.push('          going back to the old provider means paying for a second full re-embed.');
+    lines.push('          Until the re-embed finishes, semantic search is degraded to lexical-only.');
+    lines.push(`          The query cache and fact embeddings are rebuilt at ${plan.to_dims}d too`);
+    lines.push('          (cache refills on next query; facts re-embed on their next write).');
+  }
+  lines.push(`  Chunks to re-embed: ${plan.chunks_to_embed}${plan.null_signature_chunks > 0 ? ` (includes ${plan.null_signature_chunks} on pages with no recorded embedding signature)` : ''}`);
+  lines.push(
+    plan.price_known
+      ? `  Estimated cost: $${plan.est_cost_usd.toFixed(2)} (${plan.total_chars} chars at the ${plan.to_model} rate)`
+      : `  Estimated cost: unknown — no pricing entry for ${plan.to_model}. Check the provider's pricing before proceeding.`,
+  );
+  if (plan.resuming) {
+    lines.push('  Resuming: a prior migration to this target was interrupted; continuing it.');
+  }
+  if (plan.reranker_warning) {
+    lines.push(`  WARNING: ${plan.reranker_warning}`);
+  }
+  return lines.join('\n');
+}
+
+/** Single-keypress y/N confirm on stdin. Injectable for tests. */
+async function defaultConfirm(question: string): Promise<boolean> {
+  process.stderr.write(`${question} [y/N] `);
+  const stdin = process.stdin;
+  stdin.setRawMode?.(true);
+  stdin.resume();
+  const key: string = await new Promise((resolve) => {
+    stdin.once('data', (d) => resolve(d.toString()));
+  });
+  stdin.setRawMode?.(false);
+  stdin.pause();
+  process.stderr.write('\n');
+  return key.trim().toLowerCase().startsWith('y');
+}
+
+/**
+ * One tiny embed against the TARGET provider, BEFORE any mutation: validates
+ * the API key, the model id, and dimension support in a single call, so a bad
+ * target fails with the brain untouched instead of after the column is
+ * dropped. Shared by the CLI and the `migrate_embeddings` op (the op used to
+ * skip it, which let `yes:true` drop the column against a bad key).
+ */
+export async function probeTargetProvider(
+  toModel: string,
+  toDims: number,
+): Promise<{ ok: true } | { ok: false; message: string }> {
+  try {
+    const { embed } = await import('../core/ai/gateway.ts');
+    const vecs = await embed(['gbrain embedding migration probe'], {
+      embeddingModel: toModel,
+      dimensions: toDims,
+    });
+    const got = vecs[0]?.length ?? 0;
+    if (got !== toDims) {
+      return {
+        ok: false,
+        message: `Target provider returned ${got}-dim vectors, expected ${toDims}. Pass a valid --dim for ${toModel}.`,
+      };
+    }
+    return { ok: true };
+  } catch (e) {
+    return {
+      ok: false,
+      message: `Preflight embed against ${toModel} failed — nothing was changed:\n  ${e instanceof Error ? e.message : String(e)}`,
+    };
+  }
+}
+
+/**
+ * Persist the target model+dims to the FILE plane and reconfigure the
+ * in-process gateway. The gateway reads file/env config, not the DB plane —
+ * without this the re-embed would silently run against the OLD provider.
+ * Shared by the CLI command and the `migrate_embeddings` op handler.
+ */
+export async function persistEmbeddingFileConfig(
+  toModel: string,
+  toDims: number,
+): Promise<void> {
+  const { loadConfig, saveConfig } = await import('../core/config.ts');
+  const { configureGateway } = await import('../core/ai/gateway.ts');
+  const { buildGatewayConfig } = await import('../core/ai/build-gateway-config.ts');
+  const cfg = loadConfig();
+  if (!cfg) {
+    // REFUSE rather than warn-and-proceed. Without a file plane to write, the
+    // switch would not survive this process: the next `gbrain` invocation
+    // reads file/env config, sees the OLD provider, and re-embeds the brain
+    // back into the old space (paying twice) — or fails outright against a
+    // column that is now the new width. Thrown from inside
+    // applyEmbeddingMigration's try, so it surfaces as status: 'failed'
+    // BEFORE the config/cache steps and the caller exits non-zero.
+    throw new Error(
+      'No ~/.gbrain/config.json found — refusing to migrate.\n' +
+      '  The embed pipeline reads file/env config, so without a file plane this switch\n' +
+      '  would not survive the process and the next run would re-embed into the old space.\n' +
+      '  Fix: run `gbrain init` (or set GBRAIN_EMBEDDING_MODEL + GBRAIN_EMBEDDING_DIMENSIONS\n' +
+      '  in the environment of every gbrain process) and re-run.',
+    );
+  }
+  cfg.embedding_model = toModel;
+  cfg.embedding_dimensions = toDims;
+  saveConfig(cfg);
+  configureGateway(buildGatewayConfig(cfg));
+}
+
+export interface RunMigrateEmbeddingsOpts {
+  /** Test seams. */
+  confirm?: (question: string) => Promise<boolean>;
+  isTTY?: boolean;
+  exit?: (code: number) => never;
+}
+
+export async function runMigrateEmbeddings(
+  engine: BrainEngine,
+  args: string[],
+  opts: RunMigrateEmbeddingsOpts = {},
+): Promise<void> {
+  // Explicit `never` annotation so TS control-flow analysis treats every
+  // exit() call as terminal (required for narrowing after the guard blocks).
+  const exit: (code: number) => never = opts.exit ?? ((code: number) => process.exit(code));
+  if (args.includes('--help') || args.includes('-h')) {
+    printHelp();
+    exit(0);
+  }
+  const flags = parseMigrateEmbeddingsFlags(args);
+  if (!flags.to) {
+    serr('Missing --to <provider:model>. Example: gbrain migrate embeddings --to openai:text-embedding-3-small');
+    serr('Run with --help for all flags.');
+    exit(1);
+  }
+
+  // From-state as the gateway resolved it (file/env config + defaults) —
+  // the truth for what embeds run under TODAY.
+  let fromModel: string | undefined;
+  let fromDims: number | undefined;
+  try {
+    const { getEmbeddingModel, getEmbeddingDimensions } = await import('../core/ai/gateway.ts');
+    fromModel = getEmbeddingModel();
+    fromDims = getEmbeddingDimensions();
+  } catch {
+    // Gateway unconfigured — plan falls back to shipped defaults.
+  }
+
+  let plan: EmbeddingMigrationPlan;
+  try {
+    plan = await planEmbeddingMigration(engine, {
+      to: flags.to!,
+      ...(flags.dim !== undefined && { dim: flags.dim }),
+      ...(fromModel !== undefined && { fromModel }),
+      ...(fromDims !== undefined && { fromDims }),
+    });
+  } catch (e) {
+    serr(e instanceof Error ? e.message : String(e));
+    exit(1);
+    return; // unreachable; keeps TS happy for injected exit seams
+  }
+
+  if (flags.json) {
+    // Human plan goes to stderr so stdout stays JSON-clean.
+    serr(renderPlan(plan));
+  } else {
+    console.log(renderPlan(plan));
+  }
+
+  if (plan.chunks_to_embed === 0 && !plan.dim_change && plan.from_model === plan.to_model) {
+    if (flags.json) console.log(JSON.stringify({ status: 'skipped_no_work', plan }, null, 2));
+    else console.log('Nothing to migrate — brain is already on the target model.');
+    exit(0);
+  }
+
+  if (flags.dryRun) {
+    if (flags.json) console.log(JSON.stringify({ status: 'planned', plan }, null, 2));
+    exit(0);
+  }
+
+  // ── Consent gate. Unlike the pure cost gates in
+  // docs/operations/spend-controls.md, `spend.posture=tokenmax` does NOT
+  // bypass this one: posture waives the SPEND ceiling, and this gate also
+  // guards a destructive schema rebuild (existing vectors are dropped, and
+  // retrieval is degraded until the re-embed finishes). We honor the posture
+  // by marking the dollar figure informational, and still ask.
+  if (!flags.yes) {
+    const { resolveSpendPosture } = await import('../core/spend-posture.ts');
+    const posture = await resolveSpendPosture(engine);
+    if (posture === 'tokenmax') {
+      serr('  [migrate] spend.posture=tokenmax: the cost estimate above is informational.');
+      serr('  [migrate] Confirmation is still required — this rebuilds the embedding column (destructive, not just costly).');
+    }
+    const isTTY = opts.isTTY ?? Boolean(process.stdin.isTTY);
+    if (!isTTY) {
+      serr('Refusing to migrate without confirmation in a non-TTY environment. Re-run with --yes.');
+      exit(2);
+    }
+    const confirm = opts.confirm ?? defaultConfirm;
+    const priceNote = plan.price_known ? `~$${plan.est_cost_usd.toFixed(2)}` : 'an UNKNOWN amount';
+    const ok = await confirm(`Re-embed ${plan.chunks_to_embed} chunks (${priceNote})?`);
+    if (!ok) {
+      serr('Aborted. Nothing was changed.');
+      exit(1);
+    }
+  }
+
+  // ── Live probe BEFORE any mutation: one tiny embed against the TARGET
+  // provider validates API key, model id, and dimension support in one call.
+  const probe = await probeTargetProvider(plan.to_model, plan.to_dims);
+  if (!probe.ok) {
+    serr(probe.message);
+    exit(1);
+  }
+
+  // ── Apply: schema + config + invalidation + cache purge.
+  const applied = await applyEmbeddingMigration(engine, plan, {
+    ignoreEnvOverride: flags.ignoreEnvOverride,
+    persistConfig: (toModel, toDims) => persistEmbeddingFileConfig(toModel, toDims),
+  });
+
+  if (applied.status === 'refused') {
+    if (flags.json) console.log(JSON.stringify(applied, null, 2));
+    else serr(formatEnvOverrideWarning(applied.warning));
+    exit(1);
+  }
+  if (applied.status === 'failed') {
+    if (flags.json) console.log(JSON.stringify(applied, null, 2));
+    else serr(`Migration apply failed: ${applied.reason}`);
+    exit(1);
+  }
+
+  serr(`  [migrate] schema ${applied.schema_transitioned ? `rebuilt at ${plan.to_dims}d` : 'unchanged'}; ` +
+    `${applied.invalidated} chunk(s) invalidated; query cache purged (${applied.cache_cleared} row(s)).`);
+
+  if (flags.noEmbed) {
+    const msg = 'Config + schema migrated. Re-embed deferred — run: gbrain embed --stale --catch-up --include-null-signature';
+    if (flags.json) console.log(JSON.stringify({ ...applied, status: 'applied_no_embed', plan }, null, 2));
+    else console.log(msg);
+    exit(0);
+  }
+
+  // ── Re-embed. All the machinery (locks, pacing, backoff, progress,
+  // signature stamping) is the standard embed pipeline.
+  const { createProgress } = await import('../core/progress.ts');
+  const { getCliOptions, cliOptsToProgressOptions } = await import('../core/cli-options.ts');
+  const progress = createProgress(cliOptsToProgressOptions(getCliOptions()));
+  let progressStarted = false;
+  const embedResult = await runEmbedCore(engine, {
+    stale: true,
+    catchUp: true,
+    singleFlight: true,
+    includeNullSignature: true,
+    quiet: flags.json,
+    ...(flags.batchSize !== undefined && { batchSize: flags.batchSize }),
+    ...(flags.pace && { pace: flags.pace }),
+    onProgress: (done, total) => {
+      if (!progressStarted) {
+        progress.start('migrate.reembed', total);
+        progressStarted = true;
+      }
+      progress.tick(1);
+    },
+  });
+  if (progressStarted) progress.finish();
+
+  // Reconcile signatures BEFORE the completion probe: pages straddling a
+  // stale-batch boundary are embedded correctly but left unstamped by the
+  // embed loop's all-or-nothing stamp rule. Without this the probe would call
+  // a fully-migrated brain "incomplete" and the re-run would pay again.
+  const reconciled = await reconcilePageSignatures(engine, plan);
+  if (reconciled > 0) {
+    serr(`  [migrate] reconciled the embedding signature on ${reconciled} fully-embedded page(s) (batch-boundary pages).`);
+  }
+
+  const remaining = await engine.countStaleChunks({
+    signature: `${plan.to_model}:${plan.to_dims}`,
+    includeNullSignature: true,
+  });
+
+  if (remaining === 0) {
+    await completeEmbeddingMigration(engine, plan);
+    if (flags.json) {
+      console.log(JSON.stringify({ status: 'completed', plan, embedded: embedResult.embedded, remaining: 0 }, null, 2));
+    } else {
+      slog(`Migration complete: ${embedResult.embedded} chunk(s) embedded on ${plan.to_model} (${plan.to_dims}d).`);
+      if (plan.reranker_warning) serr(`  [migrate] reminder: ${plan.reranker_warning}`);
+    }
+    exit(0);
+  } else {
+    if (flags.json) {
+      console.log(JSON.stringify({ status: 'incomplete', plan, embedded: embedResult.embedded, remaining }, null, 2));
+    } else {
+      serr(`Migration incomplete: ${remaining} chunk(s) still stale (embed failures or an interrupted run).`);
+      serr('Re-run the same command to resume — completed chunks are never re-embedded.');
+    }
+    exit(1);
+  }
+}
+
+/** Re-export for the op handler + tests. */
+export { MIGRATION_STATE_KEY };

src/commands/providers.ts

@@ -134,7 +134,7 @@ EXAMPLES
   gbrain providers list
   gbrain providers test --model openai:text-embedding-3-large
   gbrain providers test --touchpoint chat --model anthropic:claude-haiku-4-5
-  gbrain providers test --touchpoint chat --model deepseek:deepseek-chat
+  gbrain providers test --touchpoint chat --model deepseek:deepseek-v4-flash
   gbrain providers env ollama
   gbrain providers explain --json
 `);

src/commands/self-upgrade.ts

@@ -1,5 +1,5 @@
 import { VERSION } from '../version.ts';
-import { isMinorOrMajorBump, isValidVersionString } from '../core/semver.ts';
+import { isNewerVersion, isValidVersionString } from '../core/semver.ts';
 import { fetchChangelog, fetchLatestRelease } from './check-update.ts';
 import { detectInstallMethod, runUpgrade } from './upgrade.ts';
 import { writeUpdateCache } from '../core/self-upgrade.ts';
@@ -35,9 +35,10 @@ export async function runSelfUpgrade(args: string[]): Promise<void> {
   const force = args.includes('--force');
   const json = args.includes('--json');
 
-  const release = await fetchLatestRelease();
+  const result = await fetchLatestRelease();
+  const release = result.ok ? result : null;
   const latest = release ? release.tag.replace(/^v/, '') : null;
-  const behind = !!latest && isValidVersionString(latest) && isMinorOrMajorBump(VERSION, latest);
+  const behind = !!latest && isValidVersionString(latest) && isNewerVersion(VERSION, latest);
 
   // Warm the cache so the next invocation's startup hook can emit without a fetch.
   try {

src/commands/serve-http.ts

@@ -1156,7 +1156,8 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
       // Unified view: OAuth clients + legacy API keys
       const oauthClients = await sql`
         SELECT c.client_id as id, c.client_name as name, 'oauth' as auth_type,
-          c.grant_types, c.scope, c.created_at, c.token_ttl,
+          c.grant_types, c.scope, c.source_id, c.federated_read,
+          c.created_at, c.token_ttl,
           CASE WHEN c.deleted_at IS NOT NULL THEN 'revoked' ELSE 'active' END as status,
           (SELECT max(created_at) FROM mcp_request_log WHERE token_name = c.client_id) as last_used_at,
           (SELECT count(*)::int FROM mcp_request_log WHERE token_name = c.client_id) as total_requests,
@@ -1172,12 +1173,25 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
           (SELECT count(*)::int FROM mcp_request_log WHERE token_name = a.name AND created_at > now() - interval '24 hours') as requests_today
         FROM access_tokens a ORDER BY a.created_at DESC
       `;
-      res.json([...oauthClients, ...legacyKeys]);
+      res.json([
+        ...oauthClients,
+        ...legacyKeys.map((key) => ({ ...key, source_id: null, federated_read: [] })),
+      ]);
     } catch (e) {
       res.status(503).json({ error: 'service_unavailable' });
     }
   });
 
+  app.get('/admin/api/sources', requireAdmin, async (_req: Request, res: Response) => {
+    try {
+      const { listSources } = await import('../core/sources-ops.ts');
+      const sources = await listSources(engine);
+      res.json(sources.map(({ id, name, federated }) => ({ id, name, federated })));
+    } catch {
+      res.status(503).json({ error: 'service_unavailable' });
+    }
+  });
+
   // v0.38 Slice 4 — per-OAuth-client agent spend viewer. Pre-computes today's
   // spend (committed + pending reservations) per client so the Agents tab
   // can render a "$X / $Y today" cell. Read-side endpoint only — no mutation.
@@ -1567,6 +1581,38 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
     }
   });
 
+  // v0.42.x (#1914): rescope an OAuth client's write source / federated read
+  // scope. Admin-gated on purpose — DCR clients must never self-widen their
+  // scope (fail-closed trust); only the operator rescopes, here or via
+  // `gbrain auth rescope-client`. Source ids are validated by the canonical
+  // validator inside rescopeClient.
+  app.post('/admin/api/rescope-client', requireAdmin, express.json(), async (req: Request, res: Response) => {
+    try {
+      const { clientId, sourceId, federatedRead } = req.body ?? {};
+      if (!clientId || typeof clientId !== 'string') {
+        res.status(400).json({ error: 'clientId required' });
+        return;
+      }
+      if (federatedRead !== undefined &&
+          !(Array.isArray(federatedRead) && federatedRead.every((s: unknown) => typeof s === 'string'))) {
+        res.status(400).json({ error: 'federatedRead must be an array of source id strings' });
+        return;
+      }
+      if (sourceId !== undefined && typeof sourceId !== 'string') {
+        res.status(400).json({ error: 'sourceId must be a string' });
+        return;
+      }
+      const result = await oauthProvider.rescopeClient(clientId, { sourceId, federatedRead });
+      res.json(result);
+    } catch (e) {
+      const message = e instanceof Error ? e.message : 'Rescope failed';
+      const status = /No OAuth client found/.test(message) ? 404
+        : /Invalid source_id|requires --source|cannot be empty|does not exist/.test(message) ? 400
+        : 500;
+      res.status(status).json({ error: message });
+    }
+  });
+
   // Revoke OAuth client
   app.post('/admin/api/revoke-client', requireAdmin, express.json(), async (req: Request, res: Response) => {
     try {
@@ -2217,8 +2263,10 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
   //     Other event types (ping, pull_request, etc.) return 202 'ignored'
   //     so GitHub doesn't retry.
   // D15.5: HMAC compare uses the shared safeHexEqual helper.
-  // D18: submits 'sync' job with auto_embed_backfill=true and priority -10
-  //     (above autopilot's 0).
+  // D18: submits 'sync' job with extraction + auto_embed_backfill enabled and
+  //     priority -10 (above autopilot's 0). This opts normal incremental pushes
+  //     into sync's inline extraction while pagesAffected still identifies the
+  //     changed pages. The sync core can still defer large (>100) changes.
   // ---------------------------------------------------------------------------
   const githubWebhookLimiter = rateLimit({
     windowMs: 60_000,
@@ -2338,6 +2386,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
           'sync',
           {
             sourceId: source.id,
+            noExtract: false,
             auto_embed_backfill: true,
             embed_reason: 'webhook',
           },

src/commands/serve.ts

@@ -9,6 +9,17 @@ import { startMcpServer } from '../mcp/server.ts';
 // the dir, sees a dead PID, and removes it).
 const CLEANUP_DEADLINE_MS = 5_000;
 
+// Boot-readiness deadline (#3273). A serve process that wedges mid-boot
+// (e.g. an MCP boot step that never completes because a configured
+// upstream is unreachable) holds the PGLite write lock indefinitely: the
+// post-#2348 lock discipline never steals from a live holder, so every
+// CLI consumer times out until someone hunts down and kills the PID. If
+// startMcpServer hasn't finished connecting the transport within this
+// window, we release the engine (dropping the lock) and exit non-zero so
+// a supervisor can restart with backoff. Env-tunable via
+// GBRAIN_SERVE_BOOT_TIMEOUT_SECONDS; 0 disables.
+const DEFAULT_BOOT_TIMEOUT_SECONDS = 60;
+
 // How often the parent-process watchdog polls the live kernel parent PID
 // (via `readLiveParentPid`, NOT the cached `process.ppid` — see that
 // helper's comment). We don't receive a signal when our parent dies (the
@@ -67,6 +78,10 @@ export interface ServeOptions {
   // transport.onclose still cover legitimate shutdown.
   // Defaults to `process.env.MCP_STDIO === '1'` when omitted.
   mcpStdio?: boolean;
+  // Test seam for the boot-readiness deadline (#3273). Milliseconds.
+  // Defaults to GBRAIN_SERVE_BOOT_TIMEOUT_SECONDS (seconds; 60 when
+  // unset, 0 disables) when omitted.
+  bootTimeoutMs?: number;
 }
 
 export async function runServe(
@@ -142,7 +157,43 @@ export async function runServe(
   installStdioLifecycle(engine, args, opts);
 
   const start = opts.startMcpServer ?? startMcpServer;
-  await start(engine);
+
+  // Boot-readiness deadline (#3273): never sit on the PGLite write lock
+  // forever with a boot that never completes. On expiry: log, release the
+  // engine (drops the lock), exit non-zero so supervisors restart with
+  // backoff. The disconnect itself is raced against CLEANUP_DEADLINE_MS,
+  // same as the graceful-shutdown path, so a wedged WASM close can't trap
+  // us either.
+  const bootTimeoutMs = opts.bootTimeoutMs ?? resolveBootTimeoutMs();
+  let bootDeadline: ReturnType<typeof setTimeout> | null = null;
+  if (bootTimeoutMs > 0) {
+    const log = opts.log ?? ((msg: string) => console.error(msg));
+    const exit = opts.exit ?? ((code?: number) => { process.exit(code); });
+    bootDeadline = setTimeout(() => {
+      log(
+        `GBrain MCP server: boot did not complete within ${bootTimeoutMs}ms — releasing DB lock and exiting so other consumers unblock (check configured provider endpoints; tune via GBRAIN_SERVE_BOOT_TIMEOUT_SECONDS, 0 disables)`,
+      );
+      const cleanup = setTimeout(() => { exit(1); }, CLEANUP_DEADLINE_MS);
+      cleanup.unref?.();
+      Promise.resolve()
+        .then(() => engine.disconnect())
+        .catch((err: unknown) => {
+          const msg = err instanceof Error ? err.message : String(err);
+          log(`GBrain MCP server: boot-deadline cleanup error: ${msg}`);
+        })
+        .finally(() => {
+          clearTimeout(cleanup);
+          exit(1);
+        });
+    }, bootTimeoutMs);
+    bootDeadline.unref?.();
+  }
+
+  try {
+    await start(engine);
+  } finally {
+    if (bootDeadline) clearTimeout(bootDeadline);
+  }
   // startMcpServer's `await server.connect(transport)` resolves once the
   // SDK has wired up its stdin 'data' listener; that listener keeps the
   // event loop alive. We deliberately do NOT add `await new Promise(() =>
@@ -150,6 +201,22 @@ export async function runServe(
   // hooks from being able to call process.exit() cleanly.
 }
 
+// Env resolution for the boot deadline. Lenient (warn + default) rather
+// than throw: this is an incident-time escape hatch, and a typo'd env var
+// must not turn a boot-safety net into a boot failure of its own.
+function resolveBootTimeoutMs(): number {
+  const raw = process.env.GBRAIN_SERVE_BOOT_TIMEOUT_SECONDS;
+  if (raw === undefined || raw.trim() === '') return DEFAULT_BOOT_TIMEOUT_SECONDS * 1000;
+  const n = Number(raw);
+  if (!Number.isFinite(n) || n < 0) {
+    console.error(
+      `[gbrain serve] ignoring invalid GBRAIN_SERVE_BOOT_TIMEOUT_SECONDS=${JSON.stringify(raw)} — using default ${DEFAULT_BOOT_TIMEOUT_SECONDS}s`,
+    );
+    return DEFAULT_BOOT_TIMEOUT_SECONDS * 1000;
+  }
+  return n * 1000;
+}
+
 interface StdioLifecycleDeps {
   stdin: NodeJS.ReadableStream & { isTTY?: boolean };
   signals: Pick<NodeJS.Process, 'on'>;

src/commands/sources.ts

@@ -53,6 +53,7 @@ import {
 import {
   loadAllSources,
   parseSourceConfig,
+  normalizeSourceConfig,
   isSourceFederated,
   type SourceRow as LoadedSourceRow,
 } from '../core/sources-load.ts';
@@ -711,7 +712,7 @@ async function runFederate(engine: BrainEngine, args: string[], value: boolean):
   config.federated = value;
   await engine.executeRaw(
     `UPDATE sources SET config = $1::text::jsonb WHERE id = $2`,
-    [JSON.stringify(config), id],
+    [JSON.stringify(normalizeSourceConfig(config)), id],
   );
   console.log(`Source "${id}" is now ${value ? 'federated (appears in cross-source default search)' : 'isolated (only searched when explicitly named)'}.`);
 
@@ -898,7 +899,7 @@ async function runWebhookSet(engine: BrainEngine, args: string[]): Promise<void>
   cfg.github_repo = githubRepo;
   await engine.executeRaw(
     `UPDATE sources SET config = $1::text::jsonb WHERE id = $2`,
-    [JSON.stringify(cfg), id],
+    [JSON.stringify(normalizeSourceConfig(cfg)), id],
   );
 
   console.log(`Webhook configured for source "${id}":`);
@@ -954,7 +955,7 @@ async function runWebhookRotate(engine: BrainEngine, args: string[]): Promise<vo
   cfg.webhook_secret = secret;
   await engine.executeRaw(
     `UPDATE sources SET config = $1::text::jsonb WHERE id = $2`,
-    [JSON.stringify(cfg), id],
+    [JSON.stringify(normalizeSourceConfig(cfg)), id],
   );
   console.log(`New webhook secret for source "${id}":`);
   console.log(`  ${secret}`);
@@ -978,7 +979,7 @@ async function runWebhookClear(engine: BrainEngine, args: string[]): Promise<voi
   delete cfg.github_repo;
   await engine.executeRaw(
     `UPDATE sources SET config = $1::text::jsonb WHERE id = $2`,
-    [JSON.stringify(cfg), id],
+    [JSON.stringify(normalizeSourceConfig(cfg)), id],
   );
   console.log(`Webhook configuration cleared for source "${id}".`);
 }
@@ -1003,7 +1004,7 @@ async function runTrackedBranch(engine: BrainEngine, args: string[]): Promise<vo
     cfg.tracked_branch = setArg;
     await engine.executeRaw(
       `UPDATE sources SET config = $1::text::jsonb WHERE id = $2`,
-      [JSON.stringify(cfg), id],
+      [JSON.stringify(normalizeSourceConfig(cfg)), id],
     );
     console.log(`Tracked branch for source "${id}" set to "${setArg}".`);
     return;
@@ -1019,7 +1020,7 @@ async function runTrackedBranch(engine: BrainEngine, args: string[]): Promise<vo
       cfg.tracked_branch = branch;
       await engine.executeRaw(
         `UPDATE sources SET config = $1::text::jsonb WHERE id = $2`,
-        [JSON.stringify(cfg), id],
+        [JSON.stringify(normalizeSourceConfig(cfg)), id],
       );
       console.log(`Detected branch "${branch}" for source "${id}"; persisted to config.tracked_branch.`);
     } catch (e) {

src/commands/sync.ts

@@ -1,6 +1,6 @@
 import { existsSync, readFileSync, writeFileSync, statSync, realpathSync } from 'fs';
 import { execFileSync } from 'child_process';
-import { join, relative } from 'path';
+import { isAbsolute, join, relative, sep } from 'path';
 import type { BrainEngine } from '../core/engine.ts';
 import { DELETE_BATCH_SIZE } from '../core/engine-constants.ts';
 import { importFile } from '../core/import-file.ts';
@@ -239,11 +239,12 @@ export interface SyncResult {
 export function estimateSourceTreeTokens(
   localPath: string,
   strategy: 'markdown' | 'code' | 'auto',
+  opts: { includeGitignored?: boolean } = {},
 ): { tokens: number; files: number } {
   let tokens = 0;
   let files = 0;
   try {
-    const fileList = collectSyncableFiles(localPath, { strategy });
+    const fileList = collectSyncableFiles(localPath, { strategy, includeGitignored: opts.includeGitignored });
     for (const fullPath of fileList) {
       try {
         const stat = statSync(fullPath);
@@ -376,6 +377,7 @@ export function estimateInlineNewTokens(
     chunker_version: string | null;
   }>,
   currentChunkerVersion: string,
+  opts: { forceFullTree?: boolean } = {},
 ): InlineEstimate {
   let tokens = 0;
   let changedSources = 0;
@@ -398,6 +400,14 @@ export function estimateInlineNewTokens(
     const strategy = cfg.strategy ?? 'markdown';
     const localPath = src.local_path;
 
+    if (opts.forceFullTree) {
+      tokens += estimateSourceTreeTokens(localPath, strategy, { includeGitignored: true }).tokens;
+      changedSources++;
+      hadCeiling = true;
+      ceilingReasons.push('include_gitignored');
+      continue;
+    }
+
     // Rung 2: chunker drift forces a full re-chunk → full re-embed. CEILING.
     if (src.chunker_version !== currentChunkerVersion) {
       ceiling(localPath, strategy, 'chunker_drift');
@@ -542,6 +552,7 @@ interface CostGateContext {
   jsonOut: boolean;
   yesFlag: boolean;
   full: boolean;
+  includeGitignored?: boolean;
   /** Message prefix ('sync --all' | 'sync'). */
   label: string;
 }
@@ -626,7 +637,9 @@ async function runInlineCostGate(
   }
 
   // ── Inline path ───────────────────────────────────────────────
-  const inline = estimateInlineNewTokens(sources, String(CHUNKER_VERSION));
+  const inline = estimateInlineNewTokens(sources, String(CHUNKER_VERSION), {
+    forceFullTree: ctx.includeGitignored === true,
+  });
   // D7A: `--full` runs `performFullSync` → `runEmbedCore({stale:true})`, which
   // sweeps the pre-existing stale backlog INLINE on top of the delta. Price it.
   const costUsd = estimateEmbeddingCostUsd(inline.tokens) + (full ? staleCostUsd : 0);
@@ -764,6 +777,11 @@ export interface SyncOpts {
    * matching the #1433 metafile posture).
    */
   exclude?: string[];
+  /**
+   * Include files matched by .gitignore. Git cannot report untracked ignored
+   * changes in diffs, so sync uses the full filesystem walker when this is set.
+   */
+  includeGitignored?: boolean;
   /**
    * Number of parallel workers for the import phase. When > 1, each worker
    * gets its own small Postgres connection pool and files are dispatched via
@@ -1152,6 +1170,20 @@ function createSyncBaselineCommit(repoPath: string): void {
   );
 }
 
+/**
+ * True when `childReal` is `rootReal` itself or lives inside it. Both arguments
+ * must already be realpath-resolved. Containment is decided by `relative()`
+ * rather than a string prefix, so it holds on Windows too: `realpathSync`
+ * returns backslash paths there, and a literal `rootReal + '/'` prefix can
+ * never match one. A sibling (`root-evil`) is rejected because `relative`
+ * yields `../root-evil`, and a cross-drive path because it yields an absolute.
+ */
+export function isWithinRoot(childReal: string, rootReal: string): boolean {
+  if (childReal === rootReal) return true;
+  const rel = relative(rootReal, childReal);
+  return rel !== '' && rel !== '..' && !rel.startsWith('..' + sep) && !isAbsolute(rel);
+}
+
 /**
  * #774 NAV-1 TOCTOU: true only if filePath realpath-resolves inside gitRoot.
  * Guards symlink escape at the per-file level (a committed symlink whose
@@ -1159,9 +1191,7 @@ function createSyncBaselineCommit(repoPath: string): void {
  */
 function isPathSafe(filePath: string, gitRoot: string): boolean {
   try {
-    const real = realpathSync(filePath);
-    const rootReal = realpathSync(gitRoot);
-    return real === rootReal || real.startsWith(rootReal + '/');
+    return isWithinRoot(realpathSync(filePath), realpathSync(gitRoot));
   } catch {
     return false;
   }
@@ -1423,6 +1453,7 @@ See also:
     {
       sourceId: sourceIdArg,
       repoPath: source.local_path,
+      noExtract: false,
       auto_embed_backfill: true,
       embed_reason: 'sync_trigger',
     },
@@ -1931,7 +1962,7 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
   // NAV-1/NAV-2 scope-entry guard: the realpath-resolved scope must live
   // inside the realpath-resolved git root. Catches `--src-subpath ../escape`
   // AND a symlinked subdir pointing outside the repo, before any git op runs.
-  if (syncScopeRoot !== gitContextRoot && !syncScopeRoot.startsWith(gitContextRoot + '/')) {
+  if (!isWithinRoot(syncScopeRoot, gitContextRoot)) {
     throw new Error(
       `Sync scope ${syncScopeRoot} resolves outside git repo ${gitContextRoot}. ` +
       `Refusing to sync: possible path traversal via --src-subpath.`,
@@ -2157,6 +2188,14 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
     return performFullSync(engine, fullSyncRoots, headCommit, opts);
   }
 
+  if (opts.includeGitignored) {
+    slog(
+      `[sync] --include-gitignored: running full filesystem reconcile because ` +
+      `git diff cannot report untracked ignored files.`,
+    );
+    return performFullSync(engine, fullSyncRoots, headCommit, opts);
+  }
+
   // v0.42.x (#1794): resumable incremental sync — resolve the PINNED target.
   // last_commit advances only at FULL import completion, so a killed run keeps
   // lastCommit fixed and the checkpoint key stable across every resume even as
@@ -3384,6 +3423,9 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
 
   // Log ingest
   await engine.logIngest({
+    // #3242 (attribution sub-bug): credit the sync to the source it wrote
+    // to, not the shared 'default' bucket.
+    ...(opts.sourceId ? { source_id: opts.sourceId } : {}),
     source_type: 'git_sync',
     source_ref: `${repoPath} @ ${headCommit.slice(0, 8)}`,
     pages_updated: pagesAffected,
@@ -3553,7 +3595,10 @@ async function performFullSync(
   // code --dry-run` always reported zero files even when ~1500 code
   // files were waiting.
   if (opts.dryRun) {
-    let allFiles = collectSyncableFiles(syncScopeRoot, { strategy: opts.strategy ?? 'markdown' });
+    let allFiles = collectSyncableFiles(syncScopeRoot, {
+      strategy: opts.strategy ?? 'markdown',
+      includeGitignored: opts.includeGitignored,
+    });
     if (opts.exclude && opts.exclude.length > 0) {
       allFiles = allFiles.filter(abs => !matchesAnyGlob(relative(syncScopeRoot, abs), opts.exclude));
     }
@@ -3587,6 +3632,7 @@ async function performFullSync(
   const { runImport } = await import('./import.ts');
   const importArgs = [syncScopeRoot];
   if (opts.noEmbed) importArgs.push('--no-embed');
+  if (opts.includeGitignored) importArgs.push('--include-gitignored');
   if (fullConcurrency > 1) importArgs.push('--workers', String(fullConcurrency));
   // v0.31.2: thread strategy through so code-strategy first sync
   // actually enumerates code files (closes bug 1).
@@ -3600,6 +3646,7 @@ async function performFullSync(
     strategy: opts.strategy,
     sourceId: opts.sourceId,
     exclude: opts.exclude,
+    includeGitignored: opts.includeGitignored,
     slugRoot,
     // issue #1939: performFullSync owns the failure ledger + bookmark via the
     // shared gate below; don't let runImport double-record or write its own.
@@ -3712,7 +3759,10 @@ async function performFullSync(
     // #774: scoped syncs store git-root-relative source_paths (slugRoot), so
     // relativize the walk to the same base — otherwise every page mismatches
     // and the mass-delete valve trips on a perfectly healthy scoped source.
-    const currentFiles = collectSyncableFiles(syncScopeRoot, { strategy: opts.strategy ?? 'markdown' })
+    const currentFiles = collectSyncableFiles(syncScopeRoot, {
+      strategy: opts.strategy ?? 'markdown',
+      includeGitignored: opts.includeGitignored,
+    })
       .map(abs => relative(slugRoot ?? syncScopeRoot, abs));
     const rows = await engine.executeRaw<{ slug: string; source_path: string | null }>(
       `SELECT slug, source_path FROM pages WHERE source_id = $1 AND source_path IS NOT NULL AND deleted_at IS NULL`,
@@ -4093,6 +4143,9 @@ Options:
                        subdirectory directly as --repo also works.
   --exclude <glob>     Exclude files matching the glob from sync (repeatable;
                        matched against the scope-relative path).
+  --include-gitignored Include otherwise-syncable files matched by .gitignore.
+                       Forces a full filesystem walk so periodic syncs see
+                       ignored untracked content.
   --dry-run            Show what would be synced without writing.
   --skip-failed        Acknowledge previously-recorded sync failures so
                        the bookmark can advance past unparseable files.
@@ -4116,12 +4169,22 @@ Options:
                        connections per wave ≈ parallel × workers × 2
                        (per-file pool) + parent pool. Pass --parallel 1
                        to force serial.
+  --missing-path M     (with --all) What to do when a source's local_path
+                       does not exist on this machine: 'fail' (default —
+                       loud, current behavior) or 'skip' (classify as
+                       skipped_missing_path: ⊘ in the aggregate, excluded
+                       from error_count and the rc=1 gate). Use skip on
+                       brains whose sources were registered from more
+                       than one machine.
   --json               Emit a structured JSON envelope on stdout
                        ({schema_version: 1, sources, parallel,
-                       ok_count, error_count}). Human banners route to
-                       stderr so '--json | jq' parses cleanly.
-                       Exit codes: 0 = all sources ok, 1 = any error,
-                       2 = cost-prompt-not-confirmed.
+                       ok_count, error_count, skipped_count}). Sources
+                       skipped by --missing-path skip appear with
+                       status 'skipped_missing_path' and their
+                       local_path. Human banners route to stderr so
+                       '--json | jq' parses cleanly.
+                       Exit codes: 0 = all sources ok or skipped,
+                       1 = any error, 2 = cost-prompt-not-confirmed.
   --yes                Accept any interactive prompts (CI / non-TTY).
 
 See also:
@@ -4143,7 +4206,21 @@ See also:
   const skipFailed = args.includes('--skip-failed');
   const retryFailed = args.includes('--retry-failed');
   const noSchemaPack = args.includes('--no-schema-pack'); // v0.41.37.0 #1569
+  const includeGitignored = args.includes('--include-gitignored');
   const syncAll = args.includes('--all');
+  let missingPathMode: MissingPathMode = 'fail';
+  try {
+    missingPathMode = parseMissingPathMode(args);
+  } catch (e) {
+    console.error(e instanceof Error ? e.message : String(e));
+    process.exit(2);
+  }
+  if (missingPathMode !== 'fail' && !syncAll) {
+    // Single-source sync on a missing path should stay loud — an explicit
+    // `--source X` naming an absent checkout is an operator error, not a
+    // multi-machine artifact. Warn instead of silently ignoring the flag.
+    console.error('[gbrain] WARN: --missing-path only applies to `sync --all`; ignored here.');
+  }
   const jsonOut = args.includes('--json');
   const yesFlag = args.includes('--yes');
   // v0.41.6.0 D3: lock-recovery flags. --break-lock (safe) verifies the
@@ -4399,7 +4476,7 @@ See also:
     if (!noEmbed) {
       const mode = willEmbedSynchronously({ v2Enabled, serialFlag, noEmbed });
       const gate = await runInlineCostGate(engine, {
-        sources, mode, dryRun, jsonOut, yesFlag, full, label: 'sync --all',
+        sources, mode, dryRun, jsonOut, yesFlag, full, includeGitignored, label: 'sync --all',
       });
       if (gate.action === 'stop') return;
       autoDeferEmbeds = gate.autoDeferEmbeds;
@@ -4430,14 +4507,40 @@ See also:
       writeHuman(`Skipping ${disabledCount} disabled source(s).`);
     }
 
-    if (activeSources.length === 0) {
+    // --missing-path skip: classify sources whose checkout is not on this
+    // machine instead of failing them (see parseMissingPathMode's rationale).
+    // Under the default 'fail' this is a no-op and behavior is unchanged.
+    let skippedMissingPath: typeof activeSources = [];
+    let runnableSources = activeSources;
+    if (missingPathMode === 'skip') {
+      const parts = partitionMissingPathSources(activeSources, existsSync);
+      runnableSources = parts.runnable;
+      skippedMissingPath = parts.missing;
+      for (const src of skippedMissingPath) {
+        writeHuman(`  ⊘ ${src.name}: skipped — local_path not present on this host (${src.local_path})`);
+      }
+      if (skippedMissingPath.length > 0) {
+        writeHuman(`Skipped ${skippedMissingPath.length} source(s) whose local_path is not present on this host (--missing-path skip).`);
+      }
+    }
+
+    if (runnableSources.length === 0) {
       if (jsonOut) {
         console.log(JSON.stringify({
           schema_version: 1,
-          sources: [],
+          sources: skippedMissingPath
+            .slice()
+            .sort((a, b) => a.id.localeCompare(b.id))
+            .map((s) => ({
+              source_id: s.id,
+              name: s.name,
+              status: 'skipped_missing_path',
+              local_path: s.local_path,
+            })),
           parallel: 0,
           ok_count: 0,
           error_count: 0,
+          skipped_count: skippedMissingPath.length,
         }));
       }
       return;
@@ -4447,11 +4550,20 @@ See also:
     type PerSourceResult = {
       sourceId: string;
       sourceName: string;
-      status: 'ok' | 'error';
+      status: 'ok' | 'error' | 'skipped_missing_path';
       result?: SyncResult;
       error?: string;
+      localPath?: string;
     };
     const perSourceResults: PerSourceResult[] = [];
+    for (const src of skippedMissingPath) {
+      perSourceResults.push({
+        sourceId: src.id,
+        sourceName: src.name,
+        status: 'skipped_missing_path',
+        localPath: src.local_path ?? undefined,
+      });
+    }
 
     // #1633 (Part B): one shared SIGINT controller for the whole --all fan-out.
     // process-cleanup.ts doesn't own SIGINT, so without this Ctrl-C hard-cuts the
@@ -4497,6 +4609,7 @@ See also:
         noEmbed: effectiveNoEmbed,
         noExtract,
         skipFailed, retryFailed, noSchemaPack,
+        includeGitignored,
         sourceId: src.id,
         strategy: cfg.strategy,
         concurrency,
@@ -4560,7 +4673,7 @@ See also:
     };
 
     const parallelEligible =
-      v2Enabled && !serialFlag && engine.kind !== 'pglite' && activeSources.length > 1;
+      v2Enabled && !serialFlag && engine.kind !== 'pglite' && runnableSources.length > 1;
 
     // v0.42.42.0 (#2139, D13C): the v0.40.6.0 (D15) refusal of --skip-failed /
     // --retry-failed under parallel sync is LIFTED. It existed because the
@@ -4574,7 +4687,7 @@ See also:
     // know how the run was actually dispatched. 1 in the serial fallback,
     // capped at min(sourceCount, --max-sources, 8) in the parallel path.
     const effectiveParallel = parallelEligible
-      ? Math.min(activeSources.length, maxSources ?? 8)
+      ? Math.min(runnableSources.length, maxSources ?? 8)
       : 1;
 
     process.on('SIGINT', onAllSigint);
@@ -4598,8 +4711,8 @@ See also:
         );
       }
 
-      writeHuman(`\nParallel sync: ${activeSources.length} sources, ${cap} concurrent workers.\n`);
-      const results = await pMapAllSettled(activeSources, cap, async (src) => {
+      writeHuman(`\nParallel sync: ${runnableSources.length} sources, ${cap} concurrent workers.\n`);
+      const results = await pMapAllSettled(runnableSources, cap, async (src) => {
         const r = await runOne(src);
         return { name: src.name, result: r };
       });
@@ -4607,7 +4720,7 @@ See also:
       writeHuman('\n--- sync --all aggregate ---');
       for (let i = 0; i < results.length; i++) {
         const r = results[i];
-        const src = activeSources[i];
+        const src = runnableSources[i];
         if (r.status === 'fulfilled') {
           writeHuman(`  ✓ ${src.name}: ${r.value.result.status} (added=${r.value.result.added}, modified=${r.value.result.modified}, deleted=${r.value.result.deleted})`);
           perSourceResults.push({
@@ -4628,7 +4741,7 @@ See also:
         }
       }
     } else {
-      for (const src of activeSources) {
+      for (const src of runnableSources) {
         writeHuman(`\n--- Syncing source: ${src.name} ---`);
         try {
           const result = await runOne(src);
@@ -4668,6 +4781,7 @@ See also:
           source_id: r.sourceId,
           name: r.sourceName,
           status: r.status,
+          ...(r.localPath ? { local_path: r.localPath } : {}),
           ...(r.result ? {
             sync_status: r.result.status,
             // #3068: surface the partial reason (e.g. pull_failed) so JSON
@@ -4687,6 +4801,7 @@ See also:
         parallel: effectiveParallel,
         ok_count: okCount,
         error_count: errCount,
+        skipped_count: perSourceResults.filter((r) => r.status === 'skipped_missing_path').length,
       }));
     }
 
@@ -4721,7 +4836,7 @@ See also:
   const singleSourceInterrupt = new AbortController();
   const onSingleSourceSigint = () => { try { singleSourceInterrupt.abort(new Error('SIGINT')); } catch { /* */ } };
   const opts: SyncOpts = {
-    repoPath, dryRun, full, noPull, noEmbed, noExtract, skipFailed, retryFailed, noSchemaPack, sourceId,
+    repoPath, dryRun, full, noPull, noEmbed, noExtract, skipFailed, retryFailed, noSchemaPack, includeGitignored, sourceId,
     strategy: strategyArg, concurrency,
     srcSubpath,
     exclude: excludePatterns.length > 0 ? excludePatterns : undefined,
@@ -4750,7 +4865,7 @@ See also:
         chunker_version: gateRows[0].chunker_version,
       }];
       const gate = await runInlineCostGate(engine, {
-        sources: gateSources, mode: 'inline', dryRun: false, jsonOut, yesFlag, full, label: 'sync',
+        sources: gateSources, mode: 'inline', dryRun: false, jsonOut, yesFlag, full, includeGitignored, label: 'sync',
       });
       if (gate.action === 'stop') return;
       if (gate.autoDeferEmbeds) {
@@ -4883,6 +4998,63 @@ See also:
   }
 }
 
+/** Mode for `sync --all --missing-path`: what to do when a source's
+ * local_path does not exist on this machine. */
+export type MissingPathMode = 'fail' | 'skip';
+
+/**
+ * Parse `--missing-path <fail|skip>` (default: fail).
+ *
+ * Why the flag exists: `sources.local_path` is machine-specific state in a
+ * brain-wide table. Any brain whose sources were registered from more than
+ * one machine — or a sanctioned setup mid-migration (topologies.md Topology 2,
+ * or the system-of-record git flow before every repo is cloned here) — has
+ * sources whose checkout simply is not present on the machine running
+ * `sync --all`. Each used to surface as a hard failure ("Not a git
+ * repository: <path>") and force rc=1 on every run; on one observed fleet
+ * that was 12 phantom failures per hour, which trains operators to ignore
+ * the exit code.
+ *
+ * The DEFAULT stays `fail`: on a single-machine brain a missing local_path
+ * usually means an unmounted volume or a deleted checkout, and silently
+ * skipping it would hide real data loss. Skip is an explicit opt-in.
+ *
+ * Throws on a bad/absent value with a paste-ready hint (caller converts to
+ * stderr + exit 2, same as other flag-misuse exits).
+ */
+export function parseMissingPathMode(args: string[]): MissingPathMode {
+  const idx = args.indexOf('--missing-path');
+  if (idx === -1) return 'fail';
+  const val = args[idx + 1];
+  if (val === 'fail' || val === 'skip') return val;
+  throw new Error(
+    `--missing-path expects 'fail' or 'skip', got: ${val ?? '(nothing)'}. ` +
+    `Use \`--missing-path skip\` to classify sources whose local_path is not ` +
+    `present on this machine as skipped instead of failed, or \`--missing-path ` +
+    `fail\` (the default) to keep them loud.`,
+  );
+}
+
+/**
+ * Partition `--all` sources by whether their local_path exists on THIS
+ * machine. Classification is driven only by the injected predicate so tests
+ * never touch the filesystem. A null local_path passes through as runnable —
+ * pure-DB sources are already excluded from `--all` by the
+ * `local_path IS NOT NULL` SELECT; this is defensive, not load-bearing.
+ */
+export function partitionMissingPathSources<T extends { local_path: string | null }>(
+  sources: T[],
+  pathExists: (p: string) => boolean,
+): { runnable: T[]; missing: T[] } {
+  const runnable: T[] = [];
+  const missing: T[] = [];
+  for (const s of sources) {
+    if (s.local_path != null && !pathExists(s.local_path)) missing.push(s);
+    else runnable.push(s);
+  }
+  return { runnable, missing };
+}
+
 /**
  * v0.40.3.0 — resolve effective per-source concurrency for `sync --all`.
  *
@@ -4960,6 +5132,7 @@ export async function syncOneSource(
     noSchemaPack?: boolean;
     /** v0.42.7 #1696: propagate --no-extract into every per-source sync. */
     noExtract?: boolean;
+    includeGitignored?: boolean;
   },
 ): Promise<{ result: SyncResult; log: string }> {
   const cfg = (src.config || {}) as { strategy?: 'markdown' | 'code' | 'auto' };
@@ -4974,6 +5147,7 @@ export async function syncOneSource(
     skipFailed: shared.skipFailed,
     retryFailed: shared.retryFailed,
     noSchemaPack: shared.noSchemaPack,
+    includeGitignored: shared.includeGitignored,
     sourceId: src.id,
     strategy: cfg.strategy,
     concurrency: shared.concurrency,

src/commands/takes.ts

@@ -3,6 +3,7 @@
  *
  * Subcommands:
  *   takes <slug>                          — list takes for a page
+ *   takes list                            — list all active takes (#2079)
  *   takes search "<query>" [--who h]       — keyword search across all takes
  *   takes add <slug> ...flags              — append a take (markdown + DB)
  *   takes update <slug> --row N ...flags   — update mutable fields
@@ -129,11 +130,10 @@ function writeBody(path: string, body: string): void {
 // --- Subcommands ---
 
 async function cmdList(engine: BrainEngine, args: string[]): Promise<void> {
-  const slug = args[0];
-  if (!slug) {
-    console.error('Usage: gbrain takes <slug> [--json]');
-    process.exit(1);
-  }
+  // #2079: slug is optional. `gbrain takes list` (no slug) lists ALL active
+  // takes — CLI parity with the takes_list operation. A leading flag is not
+  // a slug.
+  const slug = args[0] && !args[0].startsWith('-') ? args[0] : undefined;
   const json = flagPresent(args, '--json');
   const holder = flagValue(args, '--who');
   const kind = flagValue(args, '--kind') as string | undefined;
@@ -153,17 +153,19 @@ async function cmdList(engine: BrainEngine, args: string[]): Promise<void> {
     return;
   }
 
+  const scope = slug ?? 'this brain';
   if (takes.length === 0) {
-    console.log(`No takes on ${slug}.`);
+    console.log(`No takes on ${scope}.`);
     return;
   }
-  console.log(`# Takes on ${slug}\n`);
+  console.log(`# Takes on ${scope}\n`);
   for (const t of takes) {
     const tag = t.active ? '' : ' [superseded]';
     const w = Number(t.weight).toFixed(2);
     const since = t.since_date ?? '';
     const src = t.source ? ` — ${t.source}` : '';
-    console.log(`#${t.row_num} [${t.kind} • ${t.holder} • w=${w}${since ? ` • ${since}` : ''}]${tag}\n  ${t.claim}${src}\n`);
+    const where = slug ? '' : `${t.page_slug} `;
+    console.log(`${where}#${t.row_num} [${t.kind} • ${t.holder} • w=${w}${since ? ` • ${since}` : ''}]${tag}\n  ${t.claim}${src}\n`);
   }
 }
 
@@ -292,7 +294,7 @@ async function cmdSupersede(engine: BrainEngine, args: string[], sourceId?: stri
     const pageId = await getPageId(engine, slug, sourceId);
 
     // Read existing row to inherit kind/holder unless overridden
-    const existing = await engine.listTakes({ page_id: pageId, active: false, limit: 500 });
+    const existing = await engine.listTakes({ page_id: pageId, active: true, limit: 500 });
     const target = existing.find(t => t.row_num === rowNum);
     if (!target) {
       console.error(`Row #${rowNum} not found on ${slug}.`);
@@ -555,6 +557,8 @@ export async function runTakes(engine: BrainEngine, args: string[]): Promise<voi
 Subcommands:
   takes <slug> [--json] [--who h] [--kind k] [--sort weight|since_date|created_at] [--expired]
                                           List takes for a page
+  takes list [--json] [--who h] [--kind k] [--sort ...] [--expired]
+                                          List all active takes across the brain (#2079)
   takes search "<query>" [--limit N] [--json]
                                           Keyword search across all takes
   takes add <slug> --claim "..." --kind <fact|take|bet|hunch> --who <holder>
@@ -584,6 +588,9 @@ Common flags:
   const rest = args.slice(1);
 
   switch (sub) {
+    // #2079: `takes list` used to be parsed as page slug "list" and printed
+    // "No takes on list." — reading exactly like an empty takes table.
+    case 'list':        return cmdList(engine, rest);
     case 'search':      return cmdSearch(engine, rest);
     case 'add':         return cmdAdd(engine, rest, await resolveTakesSourceId(engine));
     case 'update':      return cmdUpdate(engine, rest, await resolveTakesSourceId(engine));

src/commands/think.ts

@@ -9,6 +9,7 @@ import type { BrainEngine } from '../core/engine.ts';
 import { runThink, persistSynthesis, stripGapsSection } from '../core/think/index.ts';
 import { loadConfig, isThinClient } from '../core/config.ts';
 import { callRemoteTool, unpackToolResult } from '../core/mcp-client.ts';
+import { canonicalLookup } from '../core/model-pricing.ts';
 
 function flagValue(args: string[], name: string): string | undefined {
   const i = args.indexOf(name);
@@ -20,6 +21,27 @@ function flagPresent(args: string[], name: string): boolean {
   return args.includes(name);
 }
 
+/**
+ * think's own cost was previously unsurfaced anywhere: not in this CLI's own
+ * `--json` output, not in `budget_ledger`, and invisible to a wrapping
+ * caller's own token accounting (the LLM call `think` makes is its own,
+ * separate API call). Returns undefined when `usage` is absent (no-client/
+ * stub paths, or a remote-MCP call that didn't forward it) or when the
+ * resolved model has no entry in the canonical pricing table.
+ */
+export function computeThinkCostUsd(
+  usage: { input_tokens: number; output_tokens: number } | undefined,
+  modelUsed: string,
+): number | undefined {
+  if (!usage) return undefined;
+  const pricing = canonicalLookup(modelUsed);
+  if (!pricing) return undefined;
+  return Number(
+    ((usage.input_tokens / 1_000_000) * pricing.input
+      + (usage.output_tokens / 1_000_000) * pricing.output).toFixed(4),
+  );
+}
+
 export async function runThinkCli(engine: BrainEngine, args: string[]): Promise<void> {
   if (args.length === 0 || args.includes('--help') || args.includes('-h')) {
     console.log(`Usage: gbrain think "<question>" [options]
@@ -146,9 +168,15 @@ prints what would have been the input (exit 0).
     }
   }
 
+  const costUsd = computeThinkCostUsd(
+    (result as { usage?: { input_tokens: number; output_tokens: number } }).usage,
+    result.modelUsed,
+  );
+
   if (json) {
     console.log(JSON.stringify({
       ...result,
+      cost_usd: costUsd ?? null,
       saved_slug: savedSlug ?? null,
       evidence_inserted: evidenceInserted,
     }, null, 2));
@@ -165,7 +193,8 @@ prints what would have been the input (exit 0).
     console.log('');
   }
   console.log('---');
-  console.log(`Model: ${result.modelUsed} | Pages: ${result.pagesGathered} | Takes: ${result.takesGathered} | Graph: ${result.graphHits} | Citations: ${result.citations.length}`);
+  const costSuffix = costUsd !== undefined ? ` | Cost: $${costUsd.toFixed(4)}` : '';
+  console.log(`Model: ${result.modelUsed} | Pages: ${result.pagesGathered} | Takes: ${result.takesGathered} | Graph: ${result.graphHits} | Citations: ${result.citations.length}${costSuffix}`);
   if (savedSlug) {
     console.log(`Saved: ${savedSlug} (${evidenceInserted} evidence rows)`);
   }

src/commands/upgrade.ts

@@ -462,6 +462,53 @@ export async function runPostUpgrade(args: string[] = []): Promise<void> {
           // Banner is cosmetic; never block the upgrade.
         }
 
+        // #3390: ZeroEntropy sunset notice. ZE announced (2026-07-24) that
+        // its hosted endpoints — including /models/embed and /models/rerank —
+        // shut down on 2026-09-04. Any brain resolving to a zeroentropyai:*
+        // embedding model (including default-config brains that never set
+        // one) loses SEMANTIC RETRIEVAL ENTIRELY on that date: the query
+        // embedding uses the same endpoint, so existing vectors become
+        // unqueryable. One-shot per install, gated by
+        // `ze_sunset_notice_shown` (same pattern as the search-mode banner).
+        try {
+          const shown = await engine.getConfig('ze_sunset_notice_shown');
+          const { DEFAULT_EMBEDDING_MODEL } = await import('../core/ai/defaults.ts');
+          const effectiveModel = cfgSchema.embedding_model ?? DEFAULT_EMBEDDING_MODEL;
+          const rerankerModel = await engine.getConfig('search.reranker.model');
+          const onZeEmbedding = effectiveModel.startsWith('zeroentropyai:');
+          const onZeReranker = !!rerankerModel?.startsWith('zeroentropyai:');
+          if (shown !== 'true' && (onZeEmbedding || onZeReranker)) {
+            console.log('');
+            console.log('═══════════════════════════════════════════════════════════════');
+            console.log('[gbrain] ACTION REQUIRED: ZeroEntropy hosted API sunsets 2026-09-04.');
+            if (onZeEmbedding) {
+              console.log(`[gbrain] This brain embeds with ${effectiveModel}. After the sunset,`);
+              console.log('[gbrain] semantic retrieval STOPS WORKING (queries can no longer be');
+              console.log('[gbrain] embedded against your existing vectors).');
+            }
+            if (onZeReranker) {
+              console.log(`[gbrain] The reranker (${rerankerModel}) also sunsets; search falls`);
+              console.log('[gbrain] back to unreranked ordering.');
+            }
+            console.log('═══════════════════════════════════════════════════════════════');
+            console.log('');
+            console.log('Migrate before the sunset (resumable; preview cost first):');
+            console.log('  gbrain migrate embeddings --to <provider:model> --dry-run');
+            console.log('  gbrain migrate embeddings --to <provider:model>');
+            console.log('');
+            console.log('Self-hosting zembed-1 (weights are Apache-2.0) via llama-server /');
+            console.log('ollama also works and preserves your existing vectors — point');
+            console.log('embedding at the local endpoint instead of migrating.');
+            if (onZeReranker) {
+              console.log('Reranker: gbrain config set search.reranker.enabled false (or pick another).');
+            }
+            console.log('');
+            await engine.setConfig('ze_sunset_notice_shown', 'true');
+          }
+        } catch {
+          // Banner is cosmetic; never block the upgrade.
+        }
+
         // PR1: skill-catalog publish consent. New installs default ON at
         // `gbrain init`; EXISTING installs stay OFF (default-OFF runtime = no
         // silent capability grant on upgrade) until the owner opts in HERE.

src/core/ai/anthropic-key.ts

@@ -18,12 +18,22 @@
 import { loadConfig } from '../config.ts';
 
 export function hasAnthropicKey(): boolean {
-  if (process.env.ANTHROPIC_API_KEY) return true;
+  return resolveAnthropicKey() !== undefined;
+}
+
+/**
+ * Resolve the actual key value: env first, then the gbrain config file.
+ * Callers constructing an Anthropic client directly (e.g. the legacy
+ * subagent path) must pass this as `apiKey` — a bare `new Anthropic()`
+ * only sees env, so launchd/MCP workers with config-stored keys fail.
+ */
+export function resolveAnthropicKey(): string | undefined {
+  if (process.env.ANTHROPIC_API_KEY) return process.env.ANTHROPIC_API_KEY;
   try {
     const cfg = loadConfig();
-    if (cfg?.anthropic_api_key) return true;
+    if (cfg?.anthropic_api_key) return cfg.anthropic_api_key;
   } catch {
     // loadConfig may throw on first-run installs; treat as no key available.
   }
-  return false;
+  return undefined;
 }

src/core/ai/build-gateway-config.ts

@@ -44,6 +44,13 @@ export function buildGatewayConfig(c: GBrainConfig): AIGatewayConfig {
   // multimodal/image embeds despite config.json looking complete. process.env
   // still wins via the later spread.
   if (c.voyage_api_key) envFromConfig.VOYAGE_API_KEY = c.voyage_api_key;
+  // Azure OpenAI (keyless/Entra): fold the non-secret endpoint/deployment + the
+  // Entra opt-in into the gateway env so the azure-openai recipe works in any
+  // shell (incl. non-interactive agent shells). The bearer token is minted at
+  // request time via `az`; no secret is stored in config.json.
+  if (c.azure_openai_endpoint) envFromConfig.AZURE_OPENAI_ENDPOINT = c.azure_openai_endpoint;
+  if (c.azure_openai_deployment) envFromConfig.AZURE_OPENAI_DEPLOYMENT = c.azure_openai_deployment;
+  if (c.azure_openai_use_entra) envFromConfig.AZURE_OPENAI_USE_ENTRA = c.azure_openai_use_entra;
 
   // v0.32 codex finding #4+#5 fix: thread local-server _BASE_URL env vars
   // into base_urls so the gateway hits the user's configured port. Without

src/core/ai/dims.ts

@@ -90,6 +90,30 @@ export function isValidOpenAITextEmbedding3Dim(modelId: string, dims: number): b
   return Number.isInteger(dims) && dims >= 1 && dims <= max;
 }
 
+// Perplexity hosted embeddings (#1046): Matryoshka-style flexible dims,
+// any integer from 128 up to the model's native size. `dimensions` is the
+// native wire field (no translation needed); output encoding divergence
+// (base64 int8) is handled by perplexityCompatFetch in gateway.ts.
+const PERPLEXITY_EMBEDDING_MAX_DIMS: Record<string, number> = {
+  'pplx-embed-v1-0.6b': 1024,
+  'pplx-embed-v1-4b': 2560,
+};
+export const PERPLEXITY_MIN_DIMS = 128;
+
+export function isPerplexityEmbeddingModel(modelId: string): boolean {
+  return modelId in PERPLEXITY_EMBEDDING_MAX_DIMS;
+}
+
+export function maxPerplexityEmbeddingDim(modelId: string): number | undefined {
+  return PERPLEXITY_EMBEDDING_MAX_DIMS[modelId];
+}
+
+export function isValidPerplexityDim(modelId: string, dims: number): boolean {
+  const max = PERPLEXITY_EMBEDDING_MAX_DIMS[modelId];
+  if (max === undefined) return false;
+  return Number.isInteger(dims) && dims >= PERPLEXITY_MIN_DIMS && 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
@@ -226,6 +250,23 @@ export function dimsProviderOptions(
           },
         };
       }
+      // Perplexity pplx-embed-v1-* — flexible dims via the native
+      // `dimensions` field. Fail-loud when the configured dim is outside
+      // the model's range (same rationale as the Voyage/ZE guards: the
+      // upstream HTTP 400 misroutes as a transient network error).
+      // Symmetric retrieval — inputType is never emitted.
+      if (isPerplexityEmbeddingModel(modelId)) {
+        if (!isValidPerplexityDim(modelId, dims)) {
+          const max = maxPerplexityEmbeddingDim(modelId)!;
+          throw new AIConfigError(
+            `Perplexity model "${modelId}" supports embedding_dimensions in ` +
+            `${PERPLEXITY_MIN_DIMS}..${max}, got ${dims}.`,
+            `Set \`embedding_dimensions\` to a value between ${PERPLEXITY_MIN_DIMS} and ${max} ` +
+            `in your gbrain config.`,
+          );
+        }
+        return { openaiCompatible: { dimensions: dims } };
+      }
       // NVIDIA NIM hosted embeddings are OpenAI-compatible but require
       // asymmetric input_type. Use passage for indexing/document-side vectors
       // and query for search-side vectors. Only llama-nemotron-embed-1b-v2
@@ -244,9 +285,10 @@ export function dimsProviderOptions(
       // configured for a smaller width (e.g. 1536) hard-fail at first embed.
       // Azure/OpenAI-compat embeddings are symmetric — inputType ignored.
       // v0.36.0.0 (D13): same range validation as native-openai path.
-      if (modelId.startsWith('text-embedding-3')) {
-        if (isOpenAITextEmbedding3Model(modelId) && !isValidOpenAITextEmbedding3Dim(modelId, dims)) {
-          const max = maxOpenAITextEmbedding3Dim(modelId)!;
+      const bareModelId = modelId.includes('/') ? modelId.split('/').pop()! : modelId;
+      if (bareModelId.startsWith('text-embedding-3')) {
+        if (isOpenAITextEmbedding3Model(bareModelId) && !isValidOpenAITextEmbedding3Dim(bareModelId, dims)) {
+          const max = maxOpenAITextEmbedding3Dim(bareModelId)!;
           throw new AIConfigError(
             `OpenAI model "${modelId}" supports embedding_dimensions in 1..${max}, got ${dims}.`,
             `Set \`embedding_dimensions\` to a value between 1 and ${max} ` +

src/core/ai/gateway.ts

@@ -52,6 +52,7 @@ import {
   openrouterRequiresExplicitPromptCache,
 } from './recipes/openrouter.ts';
 import { resolveModel, TIER_DEFAULTS } from '../model-config.ts';
+import { parseLlmJson } from '../llm-json.ts';
 import type { BrainEngine } from '../engine.ts';
 import { dimsProviderOptions } from './dims.ts';
 import { hasAnthropicKey } from './anthropic-key.ts';
@@ -267,6 +268,18 @@ export class ZeroEntropyResponseTooLargeError extends Error {
   }
 }
 
+/** Perplexity twin of the Voyage/ZE OOM caps (#1046). Int8 components are
+ * 1 byte each, so a real response (512 texts × 2560 dims) is ~1.3 MB —
+ * anything near this cap is unambiguously not legitimate. */
+const MAX_PERPLEXITY_RESPONSE_BYTES = 256 * 1024 * 1024;
+
+export class PerplexityResponseTooLargeError extends Error {
+  constructor(message: string) {
+    super(message);
+    this.name = 'PerplexityResponseTooLargeError';
+  }
+}
+
 // ---- Unified auth resolution (D12=A) ----
 //
 // Pre-v0.32, openai-compatible auth was duplicated across instantiateEmbedding,
@@ -439,6 +452,20 @@ export function resolveNativeBaseUrl(
   return /\/v1$/.test(trimmed) ? trimmed : `${trimmed}/v1`;
 }
 
+/**
+ * Whether an openai-compatible recipe's backend honors OpenAI structured
+ * outputs. Threaded into `createOpenAICompatible`'s `supportsStructuredOutputs`
+ * at the chat + expansion build sites, and consulted by `expand()` to pick the
+ * strict `generateObject` path over the schemaless text path. Single source of
+ * truth read from the chat touchpoint: the backend serves both chat and
+ * expansion, so the capability is declared once.
+ *
+ * @internal exported for tests.
+ */
+export function recipeSupportsStructuredOutputs(recipe: Recipe): boolean {
+  return recipe.touchpoints.chat?.supports_structured_outputs === true;
+}
+
 /** Configure the gateway. Called by cli.ts#connectEngine. Clears cached models. */
 export function configureGateway(config: AIGatewayConfig): void {
   _config = {
@@ -615,8 +642,42 @@ function warnRecipesMissingBatchTokens(): void {
   }
 }
 
-/** Reset (for tests). */
-export function resetGateway(): void {
+/**
+ * Test-only reset baseline (#3554). The bunfig preload
+ * (`test/helpers/legacy-embedding-preload.ts`) pins the gateway to the legacy
+ * OpenAI/1536 config at process start, but `resetGateway()` used to wipe that
+ * pin to `_config = null`. The next test file's engine connect then
+ * reconfigured from the SHIPPED default (zembed-1 @ 1280) and every 1536-d
+ * fixture in that file exploded with `expected 1280 dimensions, not 1536` —
+ * a cross-file mine whose placement depended on shard bin-packing.
+ *
+ * When a baseline factory is registered, `resetGateway()` means "back to the
+ * test baseline" instead of "unconfigured": it clears everything as before,
+ * then re-applies the factory's config via `configureGateway()`. A factory
+ * (not a frozen config) so each re-application captures fresh
+ * `process.env`, matching the preload's original `applyLegacy()` semantics.
+ *
+ * Production is untouched: nothing in `src/` calls `resetGateway()` or this
+ * setter, so in production the baseline is never registered and
+ * `resetGateway()` still fully unconfigures. Same `__*ForTests` seam
+ * convention as `__setEmbedTransportForTests` above.
+ */
+let _resetBaseline: (() => AIGatewayConfig) | null = null;
+
+/**
+ * Register (or clear, with `null`) the config factory that `resetGateway()`
+ * re-applies. Called once by the bunfig test preload.
+ *
+ * @internal exported for tests; not part of the public gateway API.
+ */
+export function __setGatewayResetBaselineForTests(
+  factory: (() => AIGatewayConfig) | null,
+): void {
+  _resetBaseline = factory;
+}
+
+/** Clear every piece of module state. Shared by both reset flavors. */
+function clearGatewayState(): void {
   _config = null;
   _modelCache.clear();
   _shrinkState.clear();
@@ -628,6 +689,33 @@ export function resetGateway(): void {
   _extendedModels.clear();
 }
 
+/**
+ * Reset (for tests). Clears all module state (config, model cache, shrink
+ * state, transports, warned recipes, extended models), then — if a test
+ * baseline is registered — re-applies it so the gateway returns to the
+ * process-wide test default instead of an unconfigured limbo (#3554).
+ */
+export function resetGateway(): void {
+  clearGatewayState();
+  // configureGateway re-clears _modelCache/_shrinkState/_extendedModels and
+  // registers the baseline's models; transports are NOT touched by it, so a
+  // stale test transport can never leak back in through this path.
+  if (_resetBaseline) configureGateway(_resetBaseline());
+}
+
+/**
+ * Reset AND stay unconfigured, ignoring any registered baseline. For the
+ * handful of tests that assert genuine no-gateway behavior
+ * (`no_gateway_config` diagnosis, `isAvailable() === false`, graceful
+ * degradation paths). The preload's per-test beforeEach restores the
+ * baseline before the next test, so this cannot leak across tests.
+ *
+ * @internal exported for tests; not part of the public gateway API.
+ */
+export function __unconfigureGatewayForTests(): void {
+  clearGatewayState();
+}
+
 /**
  * Test-only seam. Replaces the function the gateway calls to embed a
  * sub-batch. Pass `null` to restore the real `embedMany` from the AI SDK.
@@ -1298,6 +1386,103 @@ const openAICompatAsymmetricFetch = (async (input: RequestInfo | URL, init?: Req
   return fetch(typeof input === 'string' ? input : input.toString(), baseInit);
 }) as unknown as typeof fetch;
 
+/**
+ * Perplexity compatibility shim (#1046). Perplexity's `/v1/embeddings`
+ * endpoint is OpenAI-shaped but diverges on two points that break the AI
+ * SDK's openai-compatible adapter:
+ *   - `encoding_format` only accepts 'base64_int8' (default) or
+ *     'base64_binary'; the SDK sends 'float', which Perplexity rejects.
+ *     Force 'base64_int8' on the wire.
+ *   - The response `embedding` is a base64 string encoding SIGNED INT8
+ *     components (natively quantized output). The SDK schema expects
+ *     `number[]` — decode Int8Array → number[] here. Cosine similarity is
+ *     scale-invariant, so the raw int8 components rank correctly.
+ * `dimensions` is Perplexity's native field name — no translation needed
+ * (dims.ts emits it directly). Layer 1/Layer 2 OOM caps mirror the Voyage
+ * pattern.
+ *
+ * Exported for tests (behavioral coverage of the int8 decode); not part of
+ * the public gateway API.
+ */
+export const perplexityCompatFetch = (async (input: RequestInfo | URL, init?: RequestInit) => {
+  // OUTBOUND: force the encoding Perplexity actually accepts.
+  if (init?.body && typeof init.body === 'string') {
+    try {
+      const parsed = JSON.parse(init.body);
+      if (parsed && typeof parsed === 'object' && parsed.encoding_format !== 'base64_int8') {
+        parsed.encoding_format = 'base64_int8';
+        // Drop Content-Length so fetch recomputes from the new body.
+        const headers = new Headers(init.headers ?? {});
+        headers.delete('content-length');
+        init = { ...init, body: JSON.stringify(parsed), headers };
+      }
+    } catch {
+      // Body wasn't JSON — pass through untouched.
+    }
+  }
+
+  const resp = await fetch(input as any, init);
+  if (!resp.ok) return resp;
+  const ct = resp.headers.get('content-type') ?? '';
+  if (!ct.toLowerCase().includes('application/json')) return resp;
+
+  // Layer 1: Content-Length pre-check BEFORE the body is parsed.
+  const contentLengthHeader = resp.headers.get('content-length');
+  if (contentLengthHeader) {
+    const len = parseInt(contentLengthHeader, 10);
+    if (Number.isFinite(len) && len > MAX_PERPLEXITY_RESPONSE_BYTES) {
+      throw new PerplexityResponseTooLargeError(
+        `Perplexity response Content-Length=${len} exceeds ${MAX_PERPLEXITY_RESPONSE_BYTES} bytes — ` +
+        `likely compromised endpoint or misconfiguration`,
+      );
+    }
+  }
+
+  // INBOUND: decode base64 int8 embeddings to number[] so the SDK's Zod
+  // schema validates.
+  try {
+    const json: any = await resp.clone().json();
+    if (!json || typeof json !== 'object') return resp;
+    let modified = false;
+    if (Array.isArray(json.data)) {
+      for (const item of json.data) {
+        if (item && typeof item.embedding === 'string') {
+          // Layer 2: per-embedding cap for chunked responses that skipped
+          // Layer 1. base64 → bytes is the canonical 0.75 ratio.
+          const estDecoded = Math.ceil(item.embedding.length * 0.75);
+          if (estDecoded > MAX_PERPLEXITY_RESPONSE_BYTES) {
+            throw new PerplexityResponseTooLargeError(
+              `Perplexity embedding base64 exceeds ${MAX_PERPLEXITY_RESPONSE_BYTES} bytes ` +
+              `(estimated ${estDecoded} bytes from ${item.embedding.length} base64 chars)`,
+            );
+          }
+          // base64_int8: one signed int8 per component.
+          const bytes = Buffer.from(item.embedding, 'base64');
+          item.embedding = Array.from(new Int8Array(bytes.buffer, bytes.byteOffset, bytes.byteLength));
+          modified = true;
+        }
+      }
+    }
+    if (json.usage && typeof json.usage === 'object' && json.usage.prompt_tokens === undefined) {
+      json.usage.prompt_tokens = typeof json.usage.total_tokens === 'number'
+        ? json.usage.total_tokens
+        : 0;
+      modified = true;
+    }
+    if (!modified) return resp;
+    return new Response(JSON.stringify(json), {
+      status: resp.status,
+      statusText: resp.statusText,
+      headers: resp.headers,
+    });
+  } catch (err) {
+    // OOM-cap throws MUST propagate; anything else falls back to the
+    // original response (same contract as voyageCompatFetch).
+    if (err instanceof PerplexityResponseTooLargeError) throw err;
+    return resp;
+  }
+}) as unknown as typeof fetch;
+
 async function resolveEmbeddingProvider(modelStr: string): Promise<{ model: any; recipe: Recipe; modelId: string }> {
   const { parsed, recipe } = resolveRecipe(modelStr);
   assertTouchpoint(recipe, 'embedding', parsed.modelId, getExtendedModelsForProvider(parsed.providerId));
@@ -1342,6 +1527,10 @@ function instantiateEmbedding(recipe: Recipe, modelId: string, cfg: AIGatewayCon
       throw new AIConfigError(
         `Anthropic has no embedding model. Use openai or google for embeddings.`,
       );
+    case 'claude-cli':
+      throw new AIConfigError(
+        `claude-cli has no embedding model. Use openai or google for embeddings.`,
+      );
     case 'openai-compatible': {
       // D12=A: unified auth via Recipe.resolveAuth (or default).
       const auth = applyResolveAuth(recipe, cfg, 'embedding');
@@ -1366,6 +1555,8 @@ function instantiateEmbedding(recipe: Recipe, modelId: string, cfg: AIGatewayCon
           ? zeroEntropyCompatFetch
           : recipe.id === 'nvidia'
           ? nvidiaCompatFetch
+          : recipe.id === 'perplexity'
+          ? perplexityCompatFetch
           : openAICompatAsymmetricFetch);
       const client = createOpenAICompatible({
         name: recipe.id,
@@ -2284,6 +2475,15 @@ function instantiateExpansion(recipe: Recipe, modelId: string, cfg: AIGatewayCon
       const baseURL = resolveNativeBaseUrl('anthropic', cfg);
       return createAnthropic({ apiKey, ...(baseURL ? { baseURL } : {}) }).languageModel(modelId);
     }
+    case 'claude-cli': {
+      // The CLI handles its own auth (OAuth session); spawn the subprocess
+      // directly via the same LanguageModelV2 implementation chat uses. There
+      // is no separate expansion path because claude-cli does not declare a
+      // separate expansion touchpoint — but routing here keeps the switch
+      // exhaustive and lets a future expansion touchpoint use the same code.
+      const { ClaudeCliLanguageModel } = require('./providers/claude-cli-language-model.ts');
+      return new ClaudeCliLanguageModel(modelId);
+    }
     case 'openai-compatible': {
       // D12=A: unified auth via Recipe.resolveAuth (or default).
       const auth = applyResolveAuth(recipe, cfg, 'expansion');
@@ -2294,6 +2494,7 @@ function instantiateExpansion(recipe: Recipe, modelId: string, cfg: AIGatewayCon
         baseURL: compat.baseURL,
         ...(compat.fetch ? { fetch: compat.fetch } : {}),
         ...auth,
+        supportsStructuredOutputs: recipeSupportsStructuredOutputs(recipe),
       }).languageModel(modelId);
     }
   }
@@ -2303,6 +2504,20 @@ const ExpansionSchema = z.object({
   queries: z.array(z.string()).min(1).max(5),
 });
 
+/**
+ * Recover expansion queries from a schemaless model response. Used by the
+ * openai-compatible expansion paths: a tolerant JSON decode plus schema
+ * validation pulls the `queries` array out of the model's text (the prompt
+ * pins it to a bare JSON object). Returns null when the text carries no valid
+ * `{ queries: string[] }` object.
+ *
+ * @internal exported for tests.
+ */
+export function parseExpansionResponse(text: string): string[] | null {
+  const parsed = ExpansionSchema.safeParse(parseLlmJson<unknown>(text));
+  return parsed.success ? parsed.data.queries : null;
+}
+
 /**
  * Expand a search query into up to 4 related queries.
  * Returns the original query PLUS expansions. On failure, returns just the original.
@@ -2319,24 +2534,63 @@ export async function expand(query: string): Promise<string[]> {
     metadata: { query_chars: query.length },
   });
 
+  const expansionPrompt = [
+    'Rewrite the search query below into 3-4 different, related queries that would help find relevant documents. Respond with a JSON object in exactly this shape: {"queries": ["rewrite1", "rewrite2", "rewrite3"]}. The JSON key MUST be exactly "queries" (not "rewrites" or any other variation).',
+    'Return ONLY the JSON object. Do NOT include the original query in the result.',
+    'Each rewrite should emphasize different aspects, synonyms, or framings.',
+    '',
+    `Query: ${query}`,
+  ].join('\n');
+
   try {
     const { model, recipe, modelId } = await resolveExpansionProvider(getExpansionModel());
-    const result = await generateObject({
-      model,
-      schema: ExpansionSchema,
-      // v0.42.20.0 (codex P0) — expansion had NO abortSignal; same stalled-socket
-      // class as chat. Default the chat timeout.
-      abortSignal: withDefaultTimeout(undefined, AI_CHAT_TIMEOUT_MS),
-      prompt: [
-        'Rewrite the search query below into 3-4 different, related queries that would help find relevant documents.',
-        'Return ONLY the JSON object. Do NOT include the original query in the result.',
-        'Each rewrite should emphasize different aspects, synonyms, or framings.',
-        '',
-        `Query: ${query}`,
-      ].join('\n'),
-    });
 
-    const expansions = result.object?.queries ?? [];
+    let expansions: string[];
+
+    // Schemaless text path for openai-compatible backends whose structured-output
+    // support is unknown: the AI SDK can't send a json_schema response_format
+    // there, so generateObject would warn and silently degrade. generateText + a
+    // tolerant parse recovers the queries instead. Fresh abortSignal per call.
+    const viaText = async (): Promise<string[]> => {
+      const { text } = await generateText({
+        model,
+        abortSignal: withDefaultTimeout(undefined, AI_CHAT_TIMEOUT_MS),
+        prompt: expansionPrompt,
+      });
+      return parseExpansionResponse(text) ?? [];
+    };
+
+    if (recipe.implementation !== 'openai-compatible') {
+      // Native providers (Anthropic, OpenAI, Google) support generateObject's
+      // structured output natively — unchanged path.
+      const result = await generateObject({
+        model,
+        schema: ExpansionSchema,
+        abortSignal: withDefaultTimeout(undefined, AI_CHAT_TIMEOUT_MS),
+        prompt: expansionPrompt,
+      });
+      expansions = result.object?.queries ?? [];
+    } else if (recipeSupportsStructuredOutputs(recipe)) {
+      // openai-compatible backend that honors strict json_schema: request the
+      // schema (strict validation), and fall back to the text path if it is
+      // rejected at call time so a mis-declared capability never drops expansion.
+      try {
+        const result = await generateObject({
+          model,
+          schema: ExpansionSchema,
+          abortSignal: withDefaultTimeout(undefined, AI_CHAT_TIMEOUT_MS),
+          prompt: expansionPrompt,
+        });
+        expansions = result.object?.queries ?? [];
+      } catch {
+        expansions = await viaText();
+      }
+    } else {
+      // openai-compatible backend, structured-output support unknown: skip the
+      // json_schema attempt entirely (no SDK warning, no silent degradation).
+      expansions = await viaText();
+    }
+
     // Deduplicate + include the original query
     const seen = new Set<string>();
     const all = [query, ...expansions].filter(q => {
@@ -2783,6 +3037,15 @@ function instantiateChat(recipe: Recipe, modelId: string, cfg: AIGatewayConfig):
       const baseURL = resolveNativeBaseUrl('anthropic', cfg);
       return createAnthropic({ apiKey, ...(baseURL ? { baseURL } : {}) }).languageModel(modelId);
     }
+    case 'claude-cli': {
+      // The CLI handles its own auth (OAuth session managed by `claude`
+      // login). Subprocess-based LanguageModelV2 dispatches via the recipe
+      // path so per-call routing works: `claude-cli:claude-sonnet-4-6` lands
+      // here, while sibling `litellm:gpt-5.4` continues through the
+      // openai-compatible path below. No env-var switch, no global flag.
+      const { ClaudeCliLanguageModel } = require('./providers/claude-cli-language-model.ts');
+      return new ClaudeCliLanguageModel(modelId);
+    }
     case 'openai-compatible': {
       // D12=A: unified auth via Recipe.resolveAuth (or default).
       const auth = applyResolveAuth(recipe, cfg, 'chat');
@@ -2793,6 +3056,7 @@ function instantiateChat(recipe: Recipe, modelId: string, cfg: AIGatewayConfig):
         baseURL: compat.baseURL,
         ...(compat.fetch ? { fetch: compat.fetch } : {}),
         ...auth,
+        supportsStructuredOutputs: recipeSupportsStructuredOutputs(recipe),
       }).languageModel(modelId);
     }
     default:

src/core/ai/model-resolver.ts

@@ -144,3 +144,35 @@ export function assertTouchpoint(
 export function knownProviderIds(): string[] {
   return [...RECIPES.keys()];
 }
+
+/**
+ * Native embedding width for `modelId` under `recipe`.
+ *
+ * Resolution: the recipe's `model_dims` entry for this model, else the
+ * recipe-wide `default_dims`. Returns 0 when neither is known (the
+ * user-provided-model recipes declare `default_dims: 0` to force an explicit
+ * `--embedding-dimensions`), so callers keep their existing falsy checks.
+ *
+ * Accepts a bare model id (`bge-m3`) or a qualified one (`ollama:bge-m3`);
+ * the provider prefix is stripped before lookup so call sites can pass
+ * whichever they hold.
+ *
+ * Fixes #2051: a recipe-wide default silently picked 768 for every Ollama
+ * model, so `init --embedding-model ollama:bge-m3` built a 768-wide column
+ * for a model that emits 1024 and only failed at first insert.
+ */
+export function embeddingDimsForModel(
+  recipe: Recipe,
+  modelId: string | undefined,
+): number {
+  const tp = recipe.touchpoints.embedding;
+  if (!tp) return 0;
+  if (!modelId) return tp.default_dims ?? 0;
+  // Strip a leading `provider:` so both forms resolve. Slash-form ids
+  // (openrouter nested) are left intact — they're the model id.
+  const colon = modelId.indexOf(':');
+  const bare = colon === -1 ? modelId : modelId.slice(colon + 1);
+  const declared = tp.model_dims?.[bare];
+  if (typeof declared === 'number' && declared > 0) return declared;
+  return tp.default_dims ?? 0;
+}