fix(deps): bump four override pins past newly-published CVEs

osv-scan passed on the last two release PRs and fails on this one, so these are
newly published, not tolerated debt: 2 High + 4 Medium across fast-uri (3.1.4 →
3.1.5), hono (4.12.25 → 4.12.34), ip-address (10.1.1 → 10.3.1), and admin's
postcss (8.5.10 → 8.5.23). All four are transitive and pinned through the
overrides block, so the fix is the pin, not a dependency addition.

Resolved: fast-uri@3.1.5, hono@4.13.0, ip-address@10.4.0, postcss@8.5.25.

.gitattributes

@@ -14,3 +14,16 @@
 # through bash. `eol=lf` pins the checkout regardless of the user's
 # core.autocrlf setting.
 *.sh text eol=lf
+
+# Markdown gets the same pin, for a different failure mode: the frontmatter
+# parsers anchor on LF. Under a CRLF checkout the opening fence becomes
+# "---\r\n", which an LF-only /^---\n/ (or a startsWith("---\n")) does not
+# match, so a well-formed document silently parses as having no frontmatter.
+# There is no error -- the field just comes back empty. That has surfaced as
+# blank skill descriptions, a fixer inserting its banner above the
+# frontmatter instead of below it, resolver trigger extraction dropping
+# entries, and a generated-doc freshness check reporting every line as
+# drifted. The parsers stay CR-tolerant on their own merits (gbrain reads
+# Markdown it does not own), but pinning this repo's own .md checkout to LF
+# removes the whole class for anyone working here.
+*.md text eol=lf

.github/ISSUE_TEMPLATE/bug_report.md

@@ -4,6 +4,19 @@ about: Something isn't working
 labels: bug
 ---
 
+**Why are you opening this? (human-written, required)**
+
+<!-- Write this yourself. Not AI-generated, not AI-polished. What were you
+     doing, what happened, why does it matter to you? Rough is fine.
+     Issues/PRs without this are closed unreviewed. -->
+
+
+**Screenshot of gbrain in use (required)**
+
+<!-- Your terminal / agent session / logs showing the real situation.
+     Redact private names, keys, and brain contents first. -->
+
+
 **What happened?**
 
 

.github/ISSUE_TEMPLATE/feature_request.md

@@ -4,6 +4,19 @@ about: Suggest an improvement
 labels: enhancement
 ---
 
+**Why are you opening this? (human-written, required)**
+
+<!-- Write this yourself. Not AI-generated, not AI-polished. What were you
+     doing, what happened, why does it matter to you? Rough is fine.
+     Issues/PRs without this are closed unreviewed. -->
+
+
+**Screenshot of gbrain in use (required)**
+
+<!-- Your terminal / agent session / logs showing the real situation.
+     Redact private names, keys, and brain contents first. -->
+
+
 **What problem does this solve?**
 
 

.github/pull_request_template.md

@@ -0,0 +1,17 @@
+**Why are you opening this? (human-written, required)**
+
+<!-- Write this yourself. Not AI-generated, not AI-polished. What were you
+     doing, what went wrong or what you needed, why it matters to you.
+     Rough grammar is fine. PRs without this are closed unreviewed. -->
+
+
+**Screenshot of gbrain in use (required)**
+
+<!-- Your terminal / agent session / logs showing the real need this fixes.
+     Redact private names, keys, and brain contents first. -->
+
+
+**What changed**
+
+
+**How it was tested**

.github/workflows/e2e.yml

@@ -61,7 +61,10 @@ jobs:
       - name: Run JSONB double-encode parity tests on real Postgres
         env:
           DATABASE_URL: postgresql://postgres:postgres@localhost:5432/gbrain_test
-        run: bun test test/e2e/op-checkpoint-jsonb-parity.test.ts test/e2e/jsonb-roundtrip.test.ts
+        # --timeout also raises bun's 5s default hook budget (beforeAll/afterAll
+        # do NOT inherit a test's third-arg timeout; verified on bun 1.3.x).
+        # Every runner script in scripts/ passes it; bare invocations must too.
+        run: bun test --timeout=60000 test/e2e/op-checkpoint-jsonb-parity.test.ts test/e2e/jsonb-roundtrip.test.ts
 
   tier1:
     name: Tier 1 (Mechanical)
@@ -88,7 +91,7 @@ jobs:
           bun-version: 1.3.13
       - run: bun install
       - name: Run Tier 1 E2E tests
-        run: bun test test/e2e/mechanical.test.ts test/e2e/mcp.test.ts
+        run: bun test --timeout=60000 test/e2e/mechanical.test.ts test/e2e/mcp.test.ts
         env:
           DATABASE_URL: postgresql://postgres:postgres@localhost:5432/gbrain_test
 
@@ -155,7 +158,7 @@ jobs:
           }
           EOF
       - name: Run Tier 2 skill tests
-        run: bun test test/e2e/skills.test.ts test/e2e/zeroentropy-live.test.ts
+        run: bun test --timeout=60000 test/e2e/skills.test.ts test/e2e/zeroentropy-live.test.ts
         env:
           DATABASE_URL: postgresql://postgres:postgres@localhost:5432/gbrain_test
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

.github/workflows/pr-gate.yml

@@ -0,0 +1,110 @@
+name: PR Gate
+
+# Strict PR usefulness gate (#3698): classifies every PR to master into
+# merge-lane / close-lane / needs-maintainer BEFORE any human review effort.
+# Verdict + reviewer checklist land in one sticky comment; exactly one
+# gate:* label is applied; close-lane exits 1 (red X = strong signal).
+#
+# SECURITY MODEL (pull_request_target on a 30k-star public repo):
+# - PR code is NEVER checked out or executed. Metadata + diff come from the
+#   GitHub API only; the diff is capped at 120KB.
+# - The checkout below is the BASE repo (master) — rubric/script only.
+#   NEVER add a `ref:` pointing at the PR head.
+# - Attacker-controlled values (title/body/diff) never touch the shell:
+#   every ${{ }} is env-bound; run: scripts use plain env vars.
+# - Only the issues API is used (comments + labels), so issues:write is the
+#   single write grant; the checkout drops its credentials.
+# - The mechanical CONTRIBUTING.md #3745 check (intent paragraph + screenshot)
+#   runs BEFORE any API dependency, so a PR missing either still lands in
+#   close-lane during an Anthropic outage — an outage is not a way through.
+# - If ANTHROPIC_API_KEY is missing or the API is unreachable on an otherwise
+#   compliant PR, the script NEUTRAL-skips loudly (sticky comment + warning
+#   annotation, exit 0) and CLEARS any stale gate:* label — never a silent
+#   green, never a red X for a missing secret, never a stale verdict. A model
+#   REFUSAL is not a skip: it routes to needs-maintainer so refusing is not a
+#   way to dodge the gate.
+#
+# #3745 EXEMPTION (deliberate — mirrors policyExemption() in
+# scripts/pr-gate.mjs): the intent-paragraph + screenshot requirement filters
+# INCOMING OUTSIDE CONTRIBUTIONS. It is waived for repo owners / members /
+# collaborators, bot authors, and drafts.
+# Release automation cannot take a screenshot of itself, and without the
+# exemption every /ship release PR lands in close-lane
+# (measured: 40 of the last 40 merged PRs) — a check that is red
+# on every release gets switched off within a week, and then it filters
+# nothing. Exempt PRs still get the FULL usefulness verdict, the title rule and
+# every mechanical red flag; only the description requirement is skipped, and
+# the sticky comment says so on its own line.
+# author_association / draft / user.type are read from the pr.json fetched
+# below — GitHub-computed, not author-settable (except `draft`), and already
+# on disk, so nothing new is fetched and there is one source of truth.
+# `ready_for_review` is in the trigger list precisely because `draft` IS
+# author-settable: leaving draft re-runs the gate with the exemption gone, and
+# the exemption is folded into the spend-guard hash so the draft-era verdict
+# cannot be reused.
+# Pinned by test/pr-gate-workflow.test.ts.
+
+on:
+  pull_request_target:
+    types: [opened, edited, synchronize, reopened, ready_for_review]
+    branches: [master]
+
+# issues:write is the ONLY write grant. Everything the script calls is the
+# issues API (comments, label create, label add/remove on the PR's issue), so
+# pull-requests:write would be a redundant second grant on the same objects.
+permissions:
+  contents: read
+  issues: write
+
+concurrency:
+  group: pr-gate-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
+
+jobs:
+  gate:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      # Base repo (master) only — provides scripts/pr-gate.mjs.
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
+        with:
+          # Nothing here needs git auth after the clone; don't leave a token
+          # in .git/config for the rest of the job.
+          persist-credentials: false
+
+      - name: Fetch PR metadata + diff (API only — PR code is never checked out)
+        env:
+          GH_TOKEN: ${{ github.token }}
+          REPO: ${{ github.repository }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+        run: |
+          set -euo pipefail
+          mkdir -p "$RUNNER_TEMP/pr-gate"
+          gh api "repos/${REPO}/pulls/${PR_NUMBER}" > "$RUNNER_TEMP/pr-gate/pr.json"
+          # First 100 files is enough: red flags key off pr.json's changed_files
+          # count, and >40 files already flags.
+          gh api "repos/${REPO}/pulls/${PR_NUMBER}/files?per_page=100" \
+            > "$RUNNER_TEMP/pr-gate/files.json"
+          # Diff via the .diff media type; GitHub can 406 on huge diffs —
+          # degrade to a marker instead of failing the gate.
+          gh api "repos/${REPO}/pulls/${PR_NUMBER}" \
+            -H "Accept: application/vnd.github.diff" \
+            > "$RUNNER_TEMP/pr-gate/pr.diff.full" \
+            || printf '[diff unavailable from the GitHub API — too large or unfetchable]\n' \
+              > "$RUNNER_TEMP/pr-gate/pr.diff.full"
+          MAX=122880  # 120KB cap
+          if [ "$(wc -c < "$RUNNER_TEMP/pr-gate/pr.diff.full")" -gt "$MAX" ]; then
+            head -c "$MAX" "$RUNNER_TEMP/pr-gate/pr.diff.full" > "$RUNNER_TEMP/pr-gate/pr.diff"
+            printf '\n\n[TRUNCATED: diff capped at 120KB]\n' >> "$RUNNER_TEMP/pr-gate/pr.diff"
+          else
+            mv "$RUNNER_TEMP/pr-gate/pr.diff.full" "$RUNNER_TEMP/pr-gate/pr.diff"
+          fi
+          rm -f "$RUNNER_TEMP/pr-gate/pr.diff.full"
+
+      - name: Gate verdict (sticky comment + label; exit 1 only on close-lane)
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          GITHUB_REPOSITORY: ${{ github.repository }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+        run: node scripts/pr-gate.mjs "$RUNNER_TEMP/pr-gate"

.github/workflows/release.yml

@@ -1,14 +1,67 @@
 name: Release
 
+# Publishes a GitHub release for every VERSION bump that lands on master:
+# tag + title `v<VERSION>`, notes from that version's CHANGELOG.md entry,
+# compiled binaries attached (#3521).
+#
+# Why every bump: `gbrain check-update` resolves the latest version from the
+# VERSION file on master, but binary self-update
+# (src/core/binary-self-update.ts) downloads assets from `releases/latest`.
+# If releases lag VERSION, binary installs are told an upgrade exists that
+# self-update cannot apply. Keeping releases/latest == VERSION closes that gap.
+#
+# Idempotent: the `version` job skips build+release when a release for
+# v<VERSION> already exists WITH all expected assets. A half-published release
+# (tag exists / assets incomplete) is repaired on the next run — softprops
+# updates the existing release in place. Historical 3-segment tags are never
+# touched; a new 4-segment VERSION always mints a new tag.
+#
+# The asset names are a contract with expectedAssetName() in
+# src/core/binary-self-update.ts, pinned by test/release-workflow.test.ts.
+
 on:
   push:
-    tags: ['v*']
+    branches: [master]
+    paths: [VERSION]
+  workflow_dispatch: {}  # manual first run / backfill of the current VERSION
 
 permissions:
-  contents: write
+  contents: read
+
+concurrency:
+  group: release
+  cancel-in-progress: false
 
 jobs:
+  version:
+    runs-on: ubuntu-latest
+    outputs:
+      version: ${{ steps.v.outputs.version }}
+      exists: ${{ steps.v.outputs.exists }}
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
+      - id: v
+        name: Read VERSION and check for an existing complete release
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          version="$(tr -d '[:space:]' < VERSION)"
+          echo "version=$version" >> "$GITHUB_OUTPUT"
+          # Complete = release exists AND carries every asset the self-updater
+          # can request. A partial release must NOT short-circuit, so a re-run
+          # can repair it.
+          assets="$(gh release view "v$version" --repo "$GITHUB_REPOSITORY" \
+            --json assets --jq '[.assets[].name] | sort | join(",")' 2>/dev/null || true)"
+          if [ "$assets" = "gbrain-darwin-arm64,gbrain-linux-x64" ]; then
+            echo "exists=true" >> "$GITHUB_OUTPUT"
+            echo "Release v$version already published with all assets — nothing to do."
+          else
+            echo "exists=false" >> "$GITHUB_OUTPUT"
+          fi
+
   build:
+    needs: version
+    if: needs.version.outputs.exists == 'false'
     strategy:
       matrix:
         include:
@@ -29,9 +82,19 @@ jobs:
         with:
           bun-version: 1.3.13
       - run: bun install
-      - run: bun test
-      - run: bun run verify
+      # No test re-run here: the Test workflow already gated this exact SHA at
+      # merge (10 shards + E2E). Re-running the whole suite serially on the
+      # release runner is a flakier duplicate gate — it blocked the first
+      # release on ambient-env tests (run 30698650484). The build job's gate
+      # is the artifact itself: compile, then smoke-test the binary.
       - run: bun build --compile --target=${{ matrix.target }} --outfile bin/${{ matrix.artifact }} src/cli.ts
+      - name: Smoke-test the compiled binary
+        run: |
+          chmod +x bin/${{ matrix.artifact }}
+          out="$(./bin/${{ matrix.artifact }} --version)"
+          echo "binary reports: $out"
+          v="$(tr -d '[:space:]' < VERSION)"
+          case "$out" in *"$v"*) echo "version matches VERSION file" ;; *) echo "binary version '$out' does not contain '$v'" >&2; exit 1 ;; esac
       - name: Attest build provenance
         uses: actions/attest-build-provenance@0f67c3f4856b2e3261c31976d6725780e5e4c373  # v4.1.1
         with:
@@ -42,16 +105,35 @@ jobs:
           path: bin/${{ matrix.artifact }}
 
   release:
-    needs: build
+    needs: [version, build]
+    if: needs.version.outputs.exists == 'false'
     runs-on: ubuntu-latest
+    permissions:
+      contents: write  # create the tag + release (scoped to this job only)
     steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
       - uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093  # v4
         with:
           path: artifacts
+      - name: Extract CHANGELOG entry for release notes
+        # env-bound, not inlined into the script: VERSION comes from master so
+        # it isn't attacker-reachable today, but a `${{ }}` inside `run:` is
+        # shell injection by construction if that ever changes.
+        env:
+          RELEASE_VERSION: ${{ needs.version.outputs.version }}
+        run: |
+          v="$RELEASE_VERSION"
+          if ! bash scripts/changelog-entry.sh "$v" > /tmp/release-notes.md || ! [ -s /tmp/release-notes.md ]; then
+            echo "See [CHANGELOG.md](https://github.com/${GITHUB_REPOSITORY}/blob/master/CHANGELOG.md) for v$v." > /tmp/release-notes.md
+          fi
       - name: Create release
         uses: softprops/action-gh-release@3bb12739c298aeb8a4eeaf626c5b8d85266b0e65  # v2
         with:
+          tag_name: v${{ needs.version.outputs.version }}
+          name: v${{ needs.version.outputs.version }}
+          target_commitish: ${{ github.sha }}
+          body_path: /tmp/release-notes.md
+          fail_on_unmatched_files: true
           files: |
             artifacts/gbrain-darwin-arm64/gbrain-darwin-arm64
             artifacts/gbrain-linux-x64/gbrain-linux-x64
-          generate_release_notes: true

.github/workflows/test.yml

@@ -87,7 +87,7 @@ jobs:
       - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
         with:
           fetch-depth: 0
-      - uses: gitleaks/gitleaks-action@dcedce43c6f43de0b836d1fe38946645c9c638dc  # v2
+      - uses: gitleaks/gitleaks-action@ff98106e4c7b2bc287b24eaf42907196329070c7  # v2
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -113,6 +113,11 @@ jobs:
           key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
       - run: bun install
       - run: bun run verify
+      # Guard: no bare `bun test` in workflows/scripts — bun ignores
+      # bunfig.toml's timeout, and hooks (beforeAll/afterAll) get the 5s
+      # default regardless of per-test third-arg timeouts. Runs directly
+      # (not via verify's CHECKS array) to avoid a package.json edit.
+      - run: bash scripts/check-bun-test-timeout.sh
 
   serial-tests:
     # *.serial.test.ts at --max-concurrency=1. Lives in its own runner so

CHANGELOG.md

@@ -2,6 +2,200 @@
 
 All notable changes to GBrain will be documented in this file.
 
+## [0.42.73.0] - 2026-08-04
+
+**Every incoming pull request now gets a verdict before anyone reads it — and five contributed fixes for silent wrong answers.**
+
+**The PR gate.** Open a pull request against gbrain and an automated check now posts a single verdict comment within a minute: **merge-lane**, **close-lane**, or **needs-maintainer**, with its reasons and a checklist of what a human reviewer should verify for that specific diff. It also checks mechanically that the description carries the human-written intent paragraph and the screenshot of gbrain in use that `CONTRIBUTING.md` requires, and that the title leads with its version.
+
+It is deliberately **advisory** — a triage signal and a reviewer checklist, not an authorization boundary. A green verdict is not permission to merge; a maintainer still decides. Pull-request code is never checked out or executed: the verdict comes from the description and the diff read through the API. Maintainer, bot, and draft pull requests are exempt from the intent-and-screenshot floor only (release automation cannot screenshot itself); they still receive the full verdict. Where the rubric can be argued with, the decision is taken away from it: a merge-lane recommendation is downgraded automatically when a diff adds a dependency, a new provider recipe, or new config keys, edits workflows, deletes a test, exceeds 40 files or 400 net source lines, or changes `src/` without touching a single test.
+
+**Your import output parses again.** `gbrain import <dir> --json` printed five informational lines to stdout ahead of the JSON payload, so anything parsing that output read zero imports while its own bookkeeping recorded the files as ingested — and the next run skipped them permanently. Those lines now go to stderr under `--json`; human output is byte-for-byte unchanged.
+
+**`sources harden --dry-run` no longer changes anything.** It reset the helper's executable bit before reaching the dry-run check, so a documented preview quietly mutated permissions.
+
+**Telemetry records the model that actually ran.** Two nightly-cycle phases wrote a hardcoded or unrelated model name into their verdict cache, evidence signature, and spend metering while the gateway ran whatever chat model you configured. On any brain with a non-default model, the recorded history was fiction.
+
+**`gbrain integrity` stops contradicting itself.** Dead-link findings were counted in the "Review queue" total but written to a different file, so `integrity review` disagreed with `integrity auto`'s own summary. They now get their own line.
+
+**Retype rules can address API-ingested pages.** Mapping rules could only filter on a file path, which is empty for every page written through `put_page` — so no rule could target that whole class. A new `slug_filter` filters on the slug instead, and combines with the path filter when both are given.
+
+Also: the `integrity` source comment no longer documents a `--dry-run` subcommand form that exits with an error.
+
+### To take advantage of v0.42.73.0
+
+```bash
+gbrain upgrade
+gbrain import <dir> --json | jq .    # now parses
+gbrain integrity auto                # dead links reported separately
+```
+
+Nothing to configure for the gate — it runs on pull requests to this repository. If you maintain a fork and want it, the workflow needs an `ANTHROPIC_API_KEY` secret; without one it skips loudly rather than blocking anyone.
+
+### For contributors
+
+The gate went through six rounds against two independent blind reviewers, each judging cold. The findings that changed the design most were not exploits but false positives: a code fence that swallowed the rest of a description, an explanation written as bullet points scoring zero words, a word floor stricter than the published policy, and a comment telling contributors to reopen a pull request that was never closed. Those four descriptions are now permanent regression fixtures — a gate that insults a first-time contributor is worse than no gate. Two properties are deliberate and documented rather than fixed: the mechanical floor is a floor (a determined author clears it in seconds), and a bare URL in a cited reason still autolinks.
+
+Contributed by @YiconZiwei (#2655), @time-attack (#3764, #3759, #3726, #3751, #3739, and the gate groundwork in #3573/#3698).
+
+## [0.42.72.1] - 2026-08-02
+
+**Every issue and pull request now needs a human-written paragraph and a screenshot of gbrain actually being used.**
+
+Effective immediately, opening an issue or a PR requires two things from you personally: a paragraph you wrote yourself saying why you're opening it — what you were doing, what went wrong or what you needed, why it matters — and a screenshot of your terminal, agent session, or logs showing the real situation. Rough grammar is fine and preferred over polish. AI-generated or AI-polished intent text is not accepted; the paragraph is the human part. AI assistance for the *code* is still welcome.
+
+Issues and PRs missing either are closed without review, and can be reopened once both are added. Scrub private names, companies, keys, and brain contents from screenshots before attaching — a redacted screenshot is fine, a missing one is not.
+
+The requirement is stated in `CONTRIBUTING.md` and pre-filled in the bug-report and feature-request issue templates plus a new pull-request template, so the fields are in front of you when you open one.
+
+## [0.42.72.0] - 2026-08-01
+
+**Per-person write isolation inside a shared source, and a guide for putting gbrain behind a multi-user agent harness.**
+
+Until now, `--source` was the only write boundary: a client could write anywhere inside the source it was scoped to, and keeping each person in their own folder was a convention the agent had to honor by itself. Registering a client with `--bound-slug-prefixes` now makes that boundary real. Writes outside the bound prefixes are refused by the server, on every op that can name a page.
+
+**Adding a binding to an existing client narrows it on purpose.** Ops that write by something other than a page slug can't be confined to a prefix, so a bound client is refused them outright rather than left with an unfenced path: `extract_entities`, `extract_facts`, `forget_fact`, `ontology_propose`, `sources_add`/`sources_remove`, and `POST /ingest`. `put_page`'s automatic fact extraction is skipped for the same reason — it writes to entity pages the caller never named. Reads are unaffected, and unbound clients behave exactly as before. The gate keys on "anything that is not a plain read", so an op added in a future release is refused to bound clients until it is explicitly fenced.
+
+Both prefix spellings work: the `wiki/agents/alice/*` glob that `submit_agent` bindings already use, and the plainer `emp-alice/` form. Change a binding in place with `gbrain auth rescope-client <id> --bound-slug-prefixes <p1,p2|none>` — existing tokens pick it up on their next request, so no secret rotation is needed when someone joins or leaves a team.
+
+**New guide: [gbrain as the company brain for a qm deployment](docs/integrations/qm-harness.md).** qm is a multiplayer agent harness where each employee and each channel gets an isolated agent scope. The guide covers the whole path — one central `gbrain serve --http`, the thin-client binary baked into the sandbox image, one OAuth client per scope, and a roster-driven provisioning script that converges the brain to a list of people and channels. It also states plainly what the model does *not* give you: within a shared source, reads stay source-granular, so prefix isolation is a write boundary, not a privacy boundary.
+gbrain upgrade                    # or: bun install -g gbrain@0.42.72.0
+gbrain apply-migrations --yes     # required: the fence refuses writes it cannot evaluate
+```
+
+To fence an existing client to a folder:
+
+```bash
+gbrain auth rescope-client <client_id> --bound-slug-prefixes partners/alice-example/
+gbrain auth rescope-client <client_id> --bound-slug-prefixes none   # undo
+```
+
+Verify it took, from a client holding that credential — the first write should succeed and the second should be refused:
+
+```bash
+gbrain put partners/alice-example/notes/test --content "mine"
+gbrain put partners/bob-example/notes/test --content "not mine"
+```
+
+## [0.42.71.0] - 2026-08-01
+
+**GBrain now publishes real releases. Every version bump from here on lands on the [Releases page](https://github.com/garrytan/gbrain/releases) with organized notes and downloadable binaries — and binary self-update finally works.**
+
+Until now the repo had no releases at all: `gbrain check-update` could tell you a new version existed, but `gbrain self-upgrade` downloaded from an empty releases API and failed every time, and anyone trying to follow what shipped had to read raw commit history. That's what people have been (rightly) complaining about.
+
+From this release forward, every version bump automatically:
+
+- **Tags the commit** (`v0.42.71.0`) so versions are addressable in git.
+- **Publishes a GitHub Release** whose notes are that version's CHANGELOG entry — the same organized, user-facing writeup, not a commit dump.
+- **Attaches compiled binaries** for macOS (arm64) and Linux (x64), so `gbrain self-upgrade` and fresh binary installs work without a toolchain.
+
+The pipeline is idempotent: a partial release (tag exists, assets incomplete) is repaired on the next run instead of wedging. It runs post-merge, so a flaky release build can never turn master red. Releases for today's two fix waves (v0.42.69.0 and v0.42.70.0) have been backfilled with their CHANGELOG notes so the Releases page tells the whole story of the day; binaries attach from v0.42.71.0 onward.
+
+### To take advantage of v0.42.71.0
+
+```bash
+gbrain check-update            # now resolves against real releases
+gbrain self-upgrade            # now actually downloads a binary
+```
+
+Or browse https://github.com/garrytan/gbrain/releases for organized per-version notes.
+
+### For contributors
+
+`docs/RELEASING.md` gains the release-publication section; `scripts/changelog-entry.sh` extracts a version's CHANGELOG section (used for release notes — keep entries under the standard `## [X.Y.Z.W]` headers and they publish verbatim). The workflow keeps all actions SHA-pinned, tightens top-level permissions to `contents: read` with write scoped to the release job only, and env-binds all interpolations.
+
+Contributed by @time-attack (#3573, closing #3521).
+
+## [0.42.70.0] - 2026-08-01
+
+**Community fix wave two: 18 contributed fixes. The headline: several things you asked gbrain to do were being quietly ignored — and now they aren't.**
+
+**`--brain` now actually routes.** The documented `gbrain query "X" --brain media-team` parsed the flag and then ran against your host brain anyway. It now routes to the named brain, and an unknown brain name fails loudly instead of silently answering from the wrong database.
+
+**`sync --dry-run` no longer touches anything.** A dry run could pull from the remote and — if your sync strategy had changed — delete indexed pages before the "dry run" early-return was reached. Previews are now read-only, full stop.
+
+**`apply-migrations --yes` applies.** It previously warned that your schema was behind and then printed "All migrations up to date" with exit 0. If you have wedged brains that upgrade never healed, this was why.
+
+**Links between your pages resolve the way you write them.** Dir-qualified wikilinks with raw Obsidian names (`[[wiki/entities/AI 3.0]]`) now resolve to the sync-slugified page; references in non-whitelisted directories are no longer silently dropped; and a scan bug that could add an edge to a *parent* page you never referenced was caught in the wave's composite review and fixed before shipping.
+
+**Windows and self-hosters.** Markdown files keep LF endings so frontmatter parsers stop mis-reading on Windows checkouts; the archive-crawler path gate no longer denies every real Windows path (and no longer fail-opens on NTFS case-insensitivity); a chat-synopsis tier that was hardcoded to one provider now follows your configured models; vector search asks the index for as many candidates as it was told to consider.
+
+**Quieter, more honest infrastructure.** `serve --http` no longer leaves an orphan holding the database lock after Ctrl-C; a minion child that fails to launch settles immediately instead of hanging its slot; doctor gains checks for content-hash duplicates, undeclared database-only pages, stale heartbeats, and a tamper-evident manifest for the skills directory; federated reads respect per-source isolation settings in two more paths; and the security docs were rewritten to describe fixes without cataloguing attack surface.
+gbrain upgrade
+gbrain extract --stale        # re-extracts links under the fixed resolver
+gbrain doctor                 # includes the new silent-failure checks
+```
+
+If your brain uses `link_resolution.global_basename` and was populated before this release, a small number of superseded `wikilink_basename` edges can linger beside their newer typed replacements after re-extraction (edge writes are append-only by design). `gbrain reconcile-links` cleans them up; they are harmless to queries that dedup on target.
+
+### For contributors
+
+The composite review of this wave (two independent max-effort review passes over the combined branch) caught two interaction defects that per-PR review could not: the ungated bare-path scanner reading inside wikilink spans, and an extraction watermark set to a date that same-day stamps would already outrun. Both were fixed in the wave with discriminating tests. One reviewed-and-approved PR was deliberately held out: it conflicts semantically with its author's own sibling PR in this wave, and choosing between their two path-resolution mechanisms is the author's call.
+
+Contributed by @time-attack (#3618, #3085, #3539, #3576, #3533, #3453, #3457, #3560, #3161), @daragao3 (#3619, #3536, #3517, #3578), @paul-0320 (#3613, #3564), @cvillarroel2 (#3678), @mamedov (#3624), @dialthewolff (#3550).
+
+## [0.42.69.0] - 2026-08-01
+
+**A community fix wave: 22 contributed fixes, most of them for work your brain was quietly not doing.**
+
+The theme of this release is silent failure. A nightly cycle that reported `ok` while extracting nothing. An `embed` run that left a whole page unsearchable because one chunk in it failed, then exited 0. A health metric that recommended the same step forever because it counted one thing and the fix measured another. None of these looked broken from the outside, which is exactly why they lasted.
+
+**If you run a local or non-Anthropic model, atom extraction was doing nothing.** With a cost cap set, any model absent from the pricing tables made the first work item hard-fail, which latched a budget flag and skipped every remaining item — while the phase still reported success. Local models (`ollama`, `llama-server`) now price at $0, because local inference costs electricity rather than tokens, so their caps stay enforceable. Genuinely unpriced paid providers still skip, but loudly now instead of silently.
+
+**`gbrain embed` no longer lets one bad chunk darken an entire page,** and it exits non-zero when embeddings actually fail. If you have a cron wrapping `gbrain embed`, a brain holding permanently un-embeddable content will now turn that cron red. That is the intended change — it was previously green while silently incomplete.
+
+**Non-Latin and diacritic names now survive mention extraction.** The by-mention tokenizer matched ASCII letters and digits only, so `Đà Nẵng` shredded into one- and two-character fragments and never matched anything. Names in Vietnamese, and any script outside ASCII, are now tokenized properly.
+
+**Self-hosted embedding backends work.** Fixed-dimension OpenAI-compatible servers that reject an explicit `dimensions` parameter no longer get sent one when the requested width already matches the model's native width. A vector search on the embedded database also now asks the index for as many candidates as it was told to consider, instead of silently truncating the pool to the driver default.
+
+**Multi-source brains route correctly in two more places.** A programmatic `sync_brain` call now syncs the source it was handed rather than the global default, and entity slug resolution keeps its path separators instead of flattening `people/alice-example` into an id no page can hold.
+
+**Safer default on a destructive migration.** Submitting the type-unification job without an explicit `apply` now previews instead of applying. If you have that command in a runbook, add `"apply":true` — the playbooks and README were updated to show it.
+
+Also: interrupted imports keep their tail instead of losing progress below the next 100-file boundary; `gbrain init --help` prints its own help instead of a stub; `doctor` stops reporting Windows drive paths as missing files under WSL and bounds its embedding health probe instead of retrying a permanent auth failure three times; cycle lock-release and stamp-write failures are visible instead of swallowed; and references to a `gbrain install` command that never existed are gone from the docs.
+
+### To take advantage of v0.42.69.0
+
+```bash
+gbrain upgrade                    # or: bun install -g gbrain@0.42.69.0
+gbrain doctor                     # confirms the health metric now converges
+gbrain embed --stale              # exits non-zero if anything is genuinely un-embeddable
+```
+
+If you use a local chat model for the nightly cycle, re-run it once and check that atoms actually land:
+
+```bash
+gbrain dream --json | jq '.phases[] | select(.name=="extract_atoms")'
+```
+
+If you have `gbrain jobs submit unify-types` in a runbook or script, add `"apply":true` to its `--params` or it will now preview only.
+
+### For contributors
+
+Two defects existed only in the *combination* of otherwise-sound fixes, and were caught by reviewing the composed branch rather than the individual changes:
+
+- `isModelPriceable` was introduced with a test asserting `llama-server` is unpriced, while a second fix in the same wave priced `llama-server` at $0. Together the assertion inverted. Reconciled by using a genuinely unpriced provider in the test and pinning the positive case: free local providers are priceable at $0, so their caps stay enforced.
+- The type-unification default flipped to dry-run, but three agent-facing playbooks still presented a bare submit as the apply step. Because a second fix in the same wave also edited one of those files, each change looked self-consistent alone. Skills ship downstream via the skillpack, so this would have propagated a playbook whose apply step silently did nothing.
+
+One reviewed fix was deliberately held back: extending the inline subagent drain to Postgres composes badly with this wave's minion connection-recovery work, since the drain calls the same queue operations without the new recovery path and can strand a child job in a per-run queue no worker will claim.
+
+Contributed by @alexey-metaengage (#3652), @time-attack (#3568, #3572, #3567, #3555, #3523, #3144, #3574, #3532, #3545), @brettdavies (#3552, #3553), @mattchronicle (#3364), @rayers (#3589), @zenspam (#3699), @awilhite (#3691), @Grimnoth (#3541), @georgell-ceo (#3634), @Vyacheslav-Zakharov (#3631), @Kyzcreig (#3585), @HammerTech-Z (#3581), @cfeddersen (#3563).
+
+## [0.42.68.1] - 2026-07-30
+
+**If you run `gbrain reindex-frontmatter` or `gbrain backfill` on the default embedded database, they now work. Until this release both failed every time, after waiting 30 seconds.**
+
+The embedded database allows one process at a time, and holds a lock to enforce it. These two commands opened a second connection to the same database from inside the process that already held that lock, then waited for a lock that could never be released — because the thing holding it was the waiting process itself. The wait ran its full 30 seconds and the command exited with an error naming a blocking process that was, in fact, itself. Both commands now reuse the connection that is already open.
+
+Nothing changes for brains on Postgres, where a second connection was always allowed.
+
+## To take advantage of v0.42.68.1
+
+Nothing to undo — the commands failed without writing anything. Just run whichever you needed:
+```bash
+gbrain reindex-frontmatter
+```
+
 ## [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.**

CLAUDE.md

@@ -67,6 +67,19 @@ Per-file detail is in `docs/architecture/KEY_FILES.md`.
   text, the cast parses it). Guarded by `scripts/check-jsonb-pattern.sh` (template grep) +
   `scripts/check-jsonb-params.mjs` (positional AST scanner); the real backstop is the DATABASE_URL-gated
   e2e parity tests, since PGLite can't surface the bug. Full rule in `docs/ENGINES.md`.
+- **Engine-live paths avoid runtime dynamic `import()` for helper dependencies.** In
+  `src/core/pglite-engine.ts`, `src/core/postgres-engine.ts`, and
+  `src/core/migrate.ts`, dependencies previously reached through runtime dynamic
+  imports use static top-level imports. The only current dynamic-`import()` exceptions
+  are the four `ai/gateway.ts` lookups in both engines'
+  `initSchema()` and `_upsertChunksOnce()` methods; each remains lazy inside a
+  local `try/catch` because the gateway has a large provider/config closure and,
+  more importantly, eager evaluation would occur before the catch and could
+  turn a recoverable default/config-row fallback into a module-load failure.
+  Every exception carries `engine-dynamic-import-ok` on the import line.
+  `scripts/check-engine-dynamic-import.sh` enforces the rule. For history, use
+  `git log -G'await[[:space:]]+import\\('`, not `git log -S`: a dynamic-to-static
+  rewrite can preserve the searched token while changing its context.
 - **Engine parity.** `src/core/postgres-engine.ts` and `src/core/pglite-engine.ts` move in
   lockstep — a new method/SQL shape lands in BOTH, pinned by `test/e2e/engine-parity.test.ts`.
   Forward-referenced columns/indexes go in the bootstrap probe set (guarded by

CONTRIBUTING.md

@@ -1,5 +1,27 @@
 # Contributing to GBrain
 
+## Human-authored intent (required, no exceptions)
+
+Effective 2026-08-02, every issue and every pull request must include:
+
+1. **A paragraph you wrote yourself**, explaining why you are opening this.
+   What you were doing, what went wrong or what you needed, why it matters to
+   you. AI-generated or AI-polished text is not accepted here — this one
+   paragraph is the human part. Rough grammar is fine and preferred over
+   polish.
+2. **A screenshot showing gbrain actually being used** in the situation you
+   are describing — your terminal, your agent session, your logs. Proof the
+   need is real, not hypothetical.
+
+Issues or PRs without both are closed without review. You may reopen once
+they're added.
+
+Scrub anything private before you attach a screenshot: real names, companies,
+API keys, brain contents. See the privacy rule in `CLAUDE.md`. A redacted
+screenshot is fine; a missing one is not.
+
+AI assistance for the *code* is fine. The intent paragraph is not code.
+
 ## Setup
 
 ```bash
@@ -19,14 +41,20 @@ 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 `$'\r': command not found`. Refresh
-it once, from the repository root:
+`.gitattributes` pins `*.md text eol=lf` for the same reason. The frontmatter
+readers anchor on a `---` fence followed by a Unix line ending, so a CRLF
+checkout makes a well-formed document parse as having no frontmatter. That
+failure is silent: no error, the field just comes back empty.
+
+If you cloned before either pin existed, your working copy still has the old
+Windows line endings. Bash will fail with `$'\r': command not found`, and
+frontmatter will read as absent. 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
+bash -n scripts/run-unit-parallel.sh          # silence means bash can read the scripts
+git ls-files --eol -- '*.md' | grep -c w/crlf # 0 means Markdown is clean
 ```
 
 Every `check:*` entry in `package.json` invokes its script as `bash scripts/<name>.sh`

INSTALL_FOR_AGENTS.md

@@ -16,6 +16,13 @@ If you fetched this file by URL without cloning yet, the companion files live at
 
 ## Step 1: Install GBrain
 
+> **NEVER install from the npm registry.** GBrain is not distributed on npm; the npm
+> package named `gbrain` is an unrelated package. Do NOT run `npm install -g gbrain` or
+> `bun add -g gbrain` (note the missing `github:` prefix — that's the trap). The only
+> supported sources are `github:garrytan/gbrain` and a git clone, exactly as shown below.
+> If an unrelated npm install is already present, remove it first
+> (`npm uninstall -g gbrain` / `bun remove -g gbrain`); `gbrain doctor` also detects this.
+
 Default path (Bun is required — gbrain is a Bun + TypeScript runtime):
 
 ```bash

README.md

@@ -65,6 +65,16 @@ This is the difference between a search engine and a brain. Search finds the pag
 
 ## Install
 
+> [!WARNING]
+> **GBrain is NOT distributed on npm.** The npm package named `gbrain` is an unrelated
+> package with no connection to this project. Do not run `npm install -g gbrain` or
+> `bun add -g gbrain` — you'll get something else, and it can shadow the real binary on
+> your PATH. Install and upgrade ONLY via the documented paths below
+> (`bun install -g github:garrytan/gbrain`, or `git clone` + `bun install && bun link`).
+> If you already ran the npm install by mistake: `npm uninstall -g gbrain` /
+> `bun remove -g gbrain`, then reinstall from GitHub. `gbrain doctor` detects a
+> shadowing npm install and prints the fix.
+
 GBrain is designed to be installed and operated by an AI agent. The fastest path is to have your agent do it for you. The CLI and MCP paths below are for people who want to wire it up themselves.
 
 ### Have your agent install it (recommended)
@@ -206,7 +216,7 @@ Most personal-knowledge tools force one fixed layout: their idea of "notes" + "p
 **gbrain doesn't have a fixed layout.** It ships with bundled schema packs and lets you author your own when none fit:
 
 - **`gbrain-base-v2`** (default as of v0.41.22) — 15-type DRY/MECE canonical taxonomy (14 canonical + `note` catch-all): `person`, `company`, `media`, `tweet`, `social-digest`, `analysis`, `atom`, `concept`, `source`, `deal`, `email`, `slack`, `writing`, `project`, `note`. Subtypes/format/origin pushed to frontmatter. The taxonomy that responds to issue #1479.
-- **`gbrain-base`** (legacy, v0.41 and earlier brains) — the original 24-type layout. Stays bundled for back-compat; brains on it can upgrade via `gbrain onboard --check --explain` → `gbrain jobs submit unify-types --allow-protected --params '{"target_pack":"gbrain-base-v2"}'`.
+- **`gbrain-base`** (legacy, v0.41 and earlier brains) — the original 24-type layout. Stays bundled for back-compat; brains on it can upgrade via `gbrain onboard --check --explain` → `gbrain jobs submit unify-types --allow-protected --params '{"target_pack":"gbrain-base-v2","apply":true}'` (omit `"apply":true` for a dry-run preview — that is the default).
 - **`gbrain-recommended`** — extends `gbrain-base` with the 13 additional directories from `docs/GBRAIN_RECOMMENDED_SCHEMA.md` (source, place, trip, conversation, personal, civic, project, etc.). Activate with `gbrain schema use gbrain-recommended`.
 - **Your own pack** — `gbrain schema detect` clusters your actual filesystem into proposed types, `gbrain schema suggest` runs an LLM pass over them, and `gbrain schema review-candidates --apply` promotes the ones you like. Three commands and the brain knows your shape. Authoring a successor pack (declares `migration_from:` so existing brains can opt in): see [`docs/architecture/pack-upgrade-mechanism.md`](docs/architecture/pack-upgrade-mechanism.md).
 

SECURITY.md

@@ -34,15 +34,18 @@ enforced structurally by actionlint on every workflow change.
 
 ## Remote MCP Security
 
-### ⚠️ Do NOT use open OAuth client registration for remote MCP
+### Keep dynamic client registration disabled unless explicitly needed
 
-If you deploy GBrain's MCP server behind an HTTP wrapper with OAuth 2.1
-support, **never allow unauthenticated client registration**. An attacker
-who discovers your server URL can:
+GBrain disables Dynamic Client Registration (DCR) by default. Keep that
+default for internet-reachable deployments and pre-register trusted clients
+with operator-approved scopes and source access. Enabling DCR lets network
+callers create OAuth client records, so use it only when the deployment's
+trust model requires self-service registration and browser approval remains
+part of the authorization flow.
 
-1. Register a new OAuth client via `POST /register`
-2. Use `client_credentials` grant to obtain a bearer token
-3. Access all brain data via the MCP tools
+Do not enable `--enable-dcr-insecure` on an untrusted network. That option is
+reserved for deployments that intentionally allow self-registered
+machine-to-machine clients without browser approval.
 
 ### Recommended: `gbrain serve --http`
 
@@ -104,12 +107,10 @@ Auth methods (`--token-endpoint-auth-method`):
 - `none` — public PKCE-only client (no secret minted; ChatGPT custom
   connector, Claude Code, Cursor)
 
-The validator rejects unknown methods at the registration boundary, and
-the same gate applies to the admin endpoint `POST /admin/api/register-client`
-and the DCR `POST /register` path. Pre-v0.41.3 the CLI hard-coded
-`redirect_uris = []` and `token_endpoint_auth_method = NULL`, forcing
-operators to UPDATE `oauth_clients` rows by hand to make claude.ai work
-without `--enable-dcr`. That footgun is gone.
+The same validator applies to CLI, admin, and DCR registration paths, so
+unknown authentication methods are rejected consistently. Browser-based
+clients can be configured entirely through the supported CLI flags; operators
+do not need to edit OAuth database rows by hand.
 
 ### DCR consent default (v0.42.55+)
 
@@ -186,16 +187,10 @@ When the request `Origin` matches the allowlist, the server echoes it
 back in `Access-Control-Allow-Origin` (with `Vary: Origin`). Otherwise no
 CORS header is sent and the browser blocks the request.
 
-**v0.41.3:** the same allowlist now gates every OAuth endpoint (`/mcp`,
-`/token`, `/authorize`, `/register`, `/revoke`). Pre-v0.41.3 these used
-default-wide-open `cors()` middleware, leaking
-`Access-Control-Allow-Origin: *` on every response — any web origin could
-complete a token exchange from a logged-in operator's browser. The CORS
-preflight handler in the legacy bearer transport was also asymmetric
-(actual-request path correctly default-deny, but OPTIONS preflight leaked
-`Access-Control-Allow-Methods` + `Access-Control-Allow-Headers` to every
-Origin); both are now consolidated through a single allowlist-gated path.
-A startup stderr WARN fires when `--bind 0.0.0.0` is set without
+The same allowlist gates the complete MCP and OAuth HTTP surface. Actual
+requests and browser preflight requests use one allowlist-gated policy, so
+unlisted origins receive no cross-origin authorization. A startup stderr
+warning fires when `--bind 0.0.0.0` is set without
 `GBRAIN_HTTP_CORS_ORIGIN`, surfacing the default-deny posture before the
 first request.
 

TODOS.md

@@ -2580,7 +2580,7 @@ contributor traps.
 
 - [ ] **v0.37.x: Adopt `resolveDefaultHeaders` for Together / Groq / other attribution-bearing recipes.** v0.37.6.0's `default_headers` / `resolveDefaultHeaders` seam is generic — any recipe whose provider benefits from app-attribution headers can opt in. Together and Groq both have rankings/analytics tied to per-app headers. Add their respective attribution headers to each recipe, similar to OR's `HTTP-Referer` + `X-OpenRouter-Title`. No type-system or gateway changes needed; just `default_headers` blocks on the existing recipes plus `<PROVIDER>_REFERER` / `<PROVIDER>_TITLE` env vars in their `auth_env.optional`. Filed during v0.37.6.0 eng review as a D4 generalization opportunity.
 
-- [ ] **v0.37.x: Guard cli.ts `main()` so importing `buildGatewayConfig` doesn't print help.** v0.37.6.0 exported `buildGatewayConfig` from `src/cli.ts` for test access. Importing it triggers the file's top-level `main()` which prints help to stdout during tests — functionally harmless (tests pass) but noisy. Fix: wrap `main()` in `if (import.meta.main)` so it only runs when cli.ts is the entry point, not when imported. Touches one line; trivial. Filed during v0.37.6.0 implementation.
+- [x] **v0.37.x: Guard cli.ts `main()` so importing `buildGatewayConfig` doesn't print help.** v0.37.6.0 exported `buildGatewayConfig` from `src/cli.ts` for test access. Importing it triggers the file's top-level `main()` which prints help to stdout during tests — functionally harmless (tests pass) but noisy. Fix: wrap `main()` in `if (import.meta.main)` so it only runs when cli.ts is the entry point, not when imported. Touches one line; trivial. Filed during v0.37.6.0 implementation.
 
 
 ## v0.37.4.0 pgGraph CI scaffolding follow-ups (v0.37.x+)

VERSION

@@ -1 +1 @@
-0.42.67.0
+0.42.73.0

admin/bun.lock

@@ -19,7 +19,7 @@
   },
   "overrides": {
     "@babel/core": "^7.29.6",
-    "postcss": "^8.5.10",
+    "postcss": "^8.5.23",
   },
   "packages": {
     "@babel/code-frame": ["@babel/code-frame@7.29.7", "", { "dependencies": { "@babel/helper-validator-identifier": "^7.29.7", "js-tokens": "^4.0.0", "picocolors": "^1.1.1" } }, "sha512-Aup7aUOfpbAUg2ROOJN6Iw5f9DMBlzu0mIkm/malLQFN/YQgO48wCj0Kxa3sEHJvPVFg7siR+qRInwXd2qhQKw=="],
@@ -232,7 +232,7 @@
 
     "picomatch": ["picomatch@4.0.4", "", {}, "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A=="],
 
-    "postcss": ["postcss@8.5.19", "", { "dependencies": { "nanoid": "^3.3.12", "picocolors": "^1.1.1", "source-map-js": "^1.2.1" } }, "sha512-Mz8SaolMd8nB+G13WkORcxQKHZ/NE4xXevtkJHVuG+guo9/wYKlIMTKAqGdEmYOXR2ijPjTYNHssizdaVSUNdQ=="],
+    "postcss": ["postcss@8.5.25", "", { "dependencies": { "nanoid": "^3.3.16", "picocolors": "^1.1.1", "source-map-js": "^1.2.1" } }, "sha512-DTPx3RWSSnWyzLxQnlH0rJP+EW5ekl16ZU4/psbIhA0e53kJfdgaN5vKM+xP7yJtXVu+nfdVFmlgFDEKAe4Pyw=="],
 
     "react": ["react@19.2.5", "", {}, "sha512-llUJLzz1zTUBrskt2pwZgLq59AemifIftw4aB7JxOqf1HY2FDaGDxgwpAPVzHU1kdWabH7FauP4i1oEeer2WCA=="],
 

admin/package.json

@@ -20,6 +20,6 @@
   },
   "overrides": {
     "@babel/core": "^7.29.6",
-    "postcss": "^8.5.10"
+    "postcss": "^8.5.23"
   }
 }

bun.lock

@@ -53,12 +53,12 @@
   "overrides": {
     "@hono/node-server": "^2.0.5",
     "body-parser": "^2.3.0",
-    "fast-uri": "^3.1.4",
+    "fast-uri": "^3.1.5",
     "fast-xml-builder": "^1.1.7",
     "fast-xml-parser": "^5.7.0",
     "form-data": "^4.0.6",
-    "hono": "^4.12.25",
-    "ip-address": "^10.1.1",
+    "hono": "^4.12.34",
+    "ip-address": "^10.3.1",
     "js-yaml": "^3.15.0",
     "qs": "^6.15.2",
   },
@@ -401,7 +401,7 @@
 
     "fast-deep-equal": ["fast-deep-equal@3.1.3", "", {}, "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q=="],
 
-    "fast-uri": ["fast-uri@3.1.4", "", {}, "sha512-8JnbkQ4juDyvYs4mgFGQqg4yCYtFDtUtmp2QIQq11ZZe5CFQ5wcqm1rqDgAh/QdMySuBnPzMUiJUNZG5N/AiQw=="],
+    "fast-uri": ["fast-uri@3.1.5", "", {}, "sha512-gHwA1O9LDIcKunMKhObS/HimwtehO1nPUECKAu5TpKgaO19fcWEl4bliWe1jWxVFvIXztJjjQ4L8XQ1EU9f7Jw=="],
 
     "fast-xml-builder": ["fast-xml-builder@1.3.0", "", { "dependencies": { "path-expression-matcher": "^1.6.2", "xml-naming": "^0.3.0" } }, "sha512-F74cZEdCvuw9P41GAC3rod4X04jjWGM1JPEv/GWSqFTWLsdyMSBMBMlm9Hk3GLBgLBbdBNY8yee0pQh2RBVESQ=="],
 
@@ -437,7 +437,7 @@
 
     "heic-decode": ["heic-decode@2.1.0", "", { "dependencies": { "libheif-js": "^1.19.8" } }, "sha512-0fB3O3WMk38+PScbHLVp66jcNhsZ/ErtQ6u2lMYu/YxXgbBtl+oKOhGQHa4RpvE68k8IzbWkABzHnyAIjR758A=="],
 
-    "hono": ["hono@4.12.30", "", {}, "sha512-emn+JoJjrN9YTpRDS5it/UI2SO9BAE37T6I3d963RxcZ81G9A4pr2SZTEiiaiKbzx+NKRg5BZ89fCL7gCJCUog=="],
+    "hono": ["hono@4.13.0", "", {}, "sha512-jhunvfHWxd7J5EFfSgH4xsYJzSe/lfqbUCxiyyeaQasUsXeEHXtzVid+7EOGByc5JnFa23SSFL3Y2RV/z1T+eQ=="],
 
     "http-errors": ["http-errors@2.0.1", "", { "dependencies": { "depd": "~2.0.0", "inherits": "~2.0.4", "setprototypeof": "~1.2.0", "statuses": "~2.0.2", "toidentifier": "~1.0.1" } }, "sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ=="],
 
@@ -447,7 +447,7 @@
 
     "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
 
-    "ip-address": ["ip-address@10.2.0", "", {}, "sha512-/+S6j4E9AHvW9SWMSEY9Xfy66O5PWvVEJ08O0y5JGyEKQpojb0K0GKpz/v5HJ/G0vi3D2sjGK78119oXZeE0qA=="],
+    "ip-address": ["ip-address@10.4.0", "", {}, "sha512-oSK96Grm3aP6OrS263xVxbNDGVL7rzBtYdpGqlDG8iQdoenDoTs/nkki+DflYbAEE8Xl6o5YxhxlrKvI3nqKXQ=="],
 
     "ipaddr.js": ["ipaddr.js@1.9.1", "", {}, "sha512-0KI/607xoxSToH7GjN1FfSbLoU0+btTicjsQSWQlh/hZykN8KpmMf7uYwPW3R+akZ6R/w18ZlXSHBYXiYUPO3g=="],
 

docs/RELEASING.md

@@ -362,6 +362,39 @@ done
 
 If any SHA differs from what's in the workflow files, update the pin and version comment.
 
+## GitHub releases (binary assets + self-update) — #3521
+
+`.github/workflows/release.yml` publishes a GitHub release automatically for
+**every VERSION bump that lands on master** (trigger: push to master touching
+`VERSION`, plus `workflow_dispatch` for a manual first run or repair). No
+manual tag push is part of the ship flow — the workflow reads `VERSION` (the
+single source of truth), mints tag `v<VERSION>` at the pushed commit, titles
+the release the same, uses that version's `CHANGELOG.md` entry as the notes
+(`scripts/changelog-entry.sh`; falls back to a CHANGELOG link if the entry is
+missing), and attaches the compiled binaries.
+
+Why every bump, not selective: `gbrain check-update` resolves the latest
+version from `VERSION` on master, while binary self-update
+(`src/core/binary-self-update.ts`) downloads assets from `releases/latest`.
+Any release that lags `VERSION` tells binary installs an upgrade exists that
+self-update cannot apply. `releases/latest` must track `VERSION`.
+
+Invariants:
+
+- **Asset names are a contract.** The build matrix's `artifact:` names must
+  equal what `expectedAssetName()` in `src/core/binary-self-update.ts`
+  returns (`gbrain-darwin-arm64`, `gbrain-linux-x64` today). Adding a
+  platform means updating BOTH plus the version job's completeness check;
+  `test/release-workflow.test.ts` pins all of it.
+- **Idempotent + self-repairing.** The version job skips when a release for
+  `v<VERSION>` already exists with all expected assets; a partial release
+  (tag but no release, or missing assets) is completed on re-run. Racing
+  master pushes queue via the `release` concurrency group — a skipped
+  intermediate version is fine, latest is what matters.
+- **Historical tags are never rewritten.** Old 3-segment versions keep their
+  history; every new 4-segment `VERSION` mints a fresh tag.
+- **Permissions stay scoped.** `contents: write` lives on the release job
+  only; everything else runs read-only.
 
 ## PR descriptions cover the whole branch
 

docs/TESTING.md

@@ -32,9 +32,12 @@ CI, macOS) rejects CRLF and dies on the script's first meaningful line; the Cygw
 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`.
+`core.autocrlf=true` default that Git for Windows installs. It pins `*.md` the
+same way, because the frontmatter readers anchor on a `---` fence followed by a
+Unix line ending and a CRLF checkout makes a document parse as having no
+frontmatter, silently. Working copies cloned
+before those pins need a one-time `git rm --cached -r . -q && git reset --hard` to
+pick them 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
@@ -69,6 +72,15 @@ If a shard wedges (per-shard `GBRAIN_TEST_SHARD_TIMEOUT` cap, default 600s), the
 - `tests/heavy/*.sh` → ops-shape shell scripts. Cost minutes per run; NOT in default `bun test`. Run via `bun run test:heavy` or scheduled nightly via `.github/workflows/heavy-tests.yml`. Examples: pg_upgrade matrix (boot legacy brain → walk to head), RSS budget gate (measure peak worker RSS vs committed baseline), read-latency-under-sync (p50/p95/p99 under concurrent writer load), sync lock regression (N concurrent syncs assert 1 winner + N-1 lock-busy + zero leaked `gbrain_cycle_locks` rows). See `tests/heavy/README.md` for when to add a script here vs `*.slow.test.ts`. Files prefixed with `_` (e.g. `tests/heavy/_build_legacy_fixtures.sh`) are helpers/libs invoked by sibling tests — the runner skips them.
 - `test/fuzz/*.test.ts` → property-based fuzz harness. Pure-validator targets in `pure-validators.test.ts` are guarded by `scripts/check-fuzz-purity.sh` (in `bun run verify`), which `bun build --target=bun` bundles each target and greps the resulting bundle for banned transitive imports (`node:fs`, `node:child_process`, engine modules). Anything that fails the guard moves to `mixed-validators.test.ts` (still property-tested, but no purity guarantee) or `filesystem-validators.test.ts` (fs-backed, uses temp dirs). Fuzz tests run in the default `bun test` loop because they're fast (~3s for ~12 properties × 1000 runs each).
 
+### Skills-manifest freshness guard
+
+`skills/skills.lock.json` is a committed sha256 inventory of every bundled file under
+`skills/` (tamper evidence, not signatures — see `src/core/skills-integrity.ts`).
+Any change under `skills/` must regenerate it: `bun run scripts/generate-skills-manifest.ts`.
+`scripts/check-skills-manifest-fresh.sh` (`bun run check:skills-manifest`, wired into
+`bun run verify`) regenerates to a tmp file and diffs, failing CI on drift; at runtime
+`gbrain doctor` reports the same drift as a warn-only `skills_manifest_integrity` check.
+
 ### Test-isolation lint and helpers
 
 The cross-file flake class is enforced statically by `scripts/check-test-isolation.sh`, wired into `bun run verify` and `bun run check:all`. Rules (non-serial unit files only; `*.serial.test.ts` and `test/e2e/*` are skipped):

docs/architecture/pack-upgrade-mechanism.md

@@ -56,7 +56,8 @@ that tuple lights up the `pack_upgrade_available` onboard check.
 │  gbrain onboard --check --explain shows per-cluster narrative  │
 │  User reviews; if OK, runs:                                    │
 │    gbrain jobs submit unify-types --allow-protected \          │
-│      --params '{"target_pack":"gbrain-base-v2"}'               │
+│      --params '{"target_pack":"gbrain-base-v2","apply":true}'  │
+│  (omit "apply":true for a dry-run; that is the default)        │
 │  (Autopilot never auto-fires this; manual_only)                │
 └──────────────────────────┬─────────────────────────────────────┘
                            ↓
@@ -229,7 +230,7 @@ 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

@@ -76,7 +76,8 @@ gbrain onboard --check --explain               # per-cluster narrative dry-run
         ↓
 gbrain jobs submit unify-types \               # PROTECTED + manual_only
   --allow-protected \
-  --params '{"target_pack":"gbrain-base-v2"}'
+  --params '{"target_pack":"gbrain-base-v2","apply":true}'
+                                               # omit "apply":true → dry-run (default)
         ↓
 Handler runs 4 phases:
   ┌─────────────────────────────────────┐
@@ -108,8 +109,8 @@ 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?
@@ -127,7 +128,8 @@ For brains with substantial custom types that deserve their own canonical
 2. Edit your fork to add page_types + mapping_rules covering your
    custom domain.
 3. Target your fork: `gbrain jobs submit unify-types --allow-protected
-   --params '{"target_pack":"my-pack"}'`
+   --params '{"target_pack":"my-pack","apply":true}'` (omit `"apply":true`
+   for a dry-run preview — that is the default)
 
 Your fork can also declare `migration_from: {pack: gbrain-base-v2,
 version: "1.x"}` to register itself as a successor — future agents

docs/designs/COMMUNITY_IDEAS.md

@@ -154,10 +154,11 @@ these are the densest source of real bugs in the whole backlog.
   `aliases:`), first-H1-title, and basename fallback resolution (path-equality-only gives
   ~5.5% edge recall on real vaults). Master shipped global-basename (#1388); the alias/
   title fallbacks are the still-novel part.
-- **Schema-pack-aware link extraction** (#1547, @billy-armstrong) — **OPEN, high.** The
-  link extractor's `DIR_PATTERN` is a frozen 16-prefix const that ignores pack-declared
-  `path_prefixes`, so default-pack installs silently lose wikilinks to `person/`,
-  `writing/`, `wiki/*`. Resolve prefixes from the active pack.
+- **Schema-pack-aware link extraction** (#1547, @billy-armstrong) — **RESOLVED via #2576.**
+  The extractor no longer gates on the frozen `DIR_PATTERN` whitelist: any dir-shaped
+  path produces a candidate and the persist paths' page-existence checks decide, so
+  pack-declared directories (`person/`, `writing/`, `wiki/*`, `ops/`) link without a
+  prefix registry.
 - **DB-source extraction** (#1539, @afshaker) — **OPEN, high.** The cycle's extract phase
   only walks the filesystem, so DB-resident pages (imported transcripts, remote-DB brains)
   never get links/timeline and `brain_score` is capped. Thread `source:'db'`.

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/eval-takes-quality.md

@@ -31,7 +31,7 @@ receipt file from disk and re-renders it. The other modes need the brain.
 | `--budget-usd N` | unset | Abort before next call's projected cost would exceed cap. Models without a `pricing.ts` entry fail loud (codex #4). |
 | `--source db|fs` | `db` | `fs` is reserved for v0.33+. |
 | `--slug-prefix P` | unset | Filter takes to pages whose slug starts with P. |
-| `--models a,b,c` | `openai:gpt-4o,anthropic:claude-opus-4-7,google:gemini-1.5-pro` | Comma-separated panel. |
+| `--models a,b,c` | `openai:gpt-5.2,anthropic:claude-opus-4-7,google:gemini-2.0-flash` | Comma-separated panel. |
 | `--json` | off | Emit the full receipt to stdout. |
 
 ## Receipt JSON shape (`schema_version: 1`)
@@ -50,7 +50,7 @@ receipt file from disk and re-renders it. The other modes need the brain.
   },
   "prompt_sha8": "abcd1234",
   "models_sha8": "abcd1234",
-  "models": ["openai:gpt-4o", "anthropic:claude-opus-4-7", "google:gemini-1.5-pro"],
+  "models": ["openai:gpt-5.2", "anthropic:claude-opus-4-7", "google:gemini-2.0-flash"],
   "cycles_run": 3,
   "successes_per_cycle": [3, 3, 2],
   "verdict": "pass",

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/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/multi-language-fts.md

@@ -59,6 +59,12 @@ streaming progress to stderr. It is idempotent: re-running with the same
 language produces identical vectors. `--json` prints a machine-readable
 result envelope but still requires `--yes` (or an interactive confirm).
 
+No cache purge is needed. The resolved language is part of the query-cache
+key, so rows written under the previous language are unreachable after the
+switch — searches read the retokenized index immediately instead of being
+served pre-switch results for up to `search.cache.ttl_seconds`. Switching
+back reaches the original rows rather than rebuilding them.
+
 ## Recipe: accent-insensitive Portuguese (`pt_br`)
 
 Brazilian Portuguese content often mixes accented and unaccented spellings

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/README.md

@@ -44,6 +44,7 @@ These require manual setup (no self-installing recipe yet):
 |-------|-------------|
 | [Credential Gateway](credential-gateway.md) | Set up ClawVisor or Hermes for Gmail, Calendar, Contacts access |
 | [Meeting & Call Webhooks](meeting-webhooks.md) | Circleback meeting transcripts + Quo/OpenPhone SMS/calls |
+| [qm Harness](qm-harness.md) | gbrain as the company brain for a qm (multi-user agent harness) deployment — central HTTP MCP, per-scope clients, roster provisioning, write fencing |
 
 ## How to Read a Recipe
 
@@ -69,6 +70,12 @@ health_checks:                  # typed DSL to verify the integration is working
     auth_user: "$TWILIO_ACCOUNT_SID"
     auth_token: "$TWILIO_AUTH_TOKEN"
     label: "Twilio account"
+  - type: heartbeat_max_age     # staleness gate: FAILS `integrations doctor`
+    max_age: 48h                # when the newest heartbeat event is older.
+    label: "Data freshness"     # The other types are point-in-time and stay
+                                # green even when a sense stops producing data.
+output_paths:                   # repo-relative dirs the collector writes files to;
+  - daily/voice/                # lets doctor/sync warn if one lands in db_only
 setup_time: 30 min              # estimated time to complete setup
 ---
 
@@ -86,7 +93,8 @@ a source install, or the global install copy) are trusted. Recipes discovered at
 runtime from `$GBRAIN_RECIPES_DIR` or a cwd-local `./recipes/` are marked untrusted:
 they cannot run `command` health checks, cannot run `http` health checks (SSRF
 defense), and cannot use the deprecated string health_check form. Untrusted recipes
-can still use `env_exists` and `any_of` compositions. To ship a recipe that runs
+can still use `env_exists`, `heartbeat_max_age` (reads only the local heartbeat
+file — no exec, no network), and `any_of` compositions. To ship a recipe that runs
 live checks, contribute it upstream so it becomes package-bundled.
 
 ## The Deterministic Collector Pattern

docs/integrations/qm-harness-snippets/SKILL.md

@@ -0,0 +1,79 @@
+---
+name: gbrain
+description: Search and write the company knowledge brain. Use for any question about the org, people, projects, decisions, or history, and to persist durable knowledge beyond this scope's notebook.
+---
+
+# gbrain — the company brain
+
+This sandbox has the `gbrain` CLI connected (thin-client) to the org's central
+brain. It is the deep, indexed, cross-source memory: org docs, shared channel
+knowledge, and every agent's durable notes. Your scope's own notebook stays the
+fast per-turn memory; the brain is where knowledge outlives a scope and becomes
+searchable by everyone entitled to it.
+
+## First-run setup (once per sandbox — skip if `gbrain remote doctor` passes)
+
+Your scope's brain credentials arrive via the deployment's secret handoff
+(keychain entry or one-time secret drop named `gbrain`). Then:
+
+```bash
+gbrain init --mcp-only \
+  --issuer-url "https://brain.<org>.com" \
+  --mcp-url "https://brain.<org>.com/mcp" \
+  --oauth-client-id "<client id from the handoff>" \
+  --oauth-client-secret "<client secret from the handoff>"
+gbrain whoami   # must succeed before using any other command
+```
+
+Pass the secret with `--oauth-client-secret`, not via `GBRAIN_REMOTE_CLIENT_SECRET`:
+an env-sourced secret is deliberately NOT written to `~/.gbrain/config.json`, so
+every later command would fail with "No client_secret available" once the
+variable is out of scope. The flag persists it to the config file on this
+sandbox's durable disk, which is what the tool's credential capture expects.
+
+Do not run `gbrain remote doctor` — it needs `admin` scope, which your client
+does not have (by design). `gbrain whoami` is the read-scope health check.
+
+## Reading (do this liberally)
+
+```bash
+gbrain search "who decided X and why"     # hybrid semantic + keyword search
+gbrain get <slug>                          # read one page
+gbrain query "question" --json             # search tuned for agent consumption
+```
+
+You can read: the shared agent-memory source, org read-only sources (wiki,
+handbook), and everything under them. Reads are isolation-enforced server-side;
+you only ever see sources your client is entitled to.
+
+## Writing (durable knowledge only, under YOUR prefixes)
+
+Your client is write-fenced to slug prefixes — your own namespace plus the
+channels you belong to. Writes outside them are rejected server-side.
+
+```bash
+# personal durable memory (your namespace):
+gbrain put emp-<your-slug>/people/jane-example --content "..."
+
+# shared channel knowledge (channels you are in):
+gbrain put chan-eng/decisions/2026-08-database-choice --content "..."
+```
+
+Conventions:
+- Write conclusions and durable facts, not chat transcripts. One page per
+  entity/decision/topic; update the page rather than appending near-duplicates.
+- Markdown with YAML frontmatter; the brain chunks, embeds, and links it.
+- Cross-reference liberally: `gbrain link <from> <to>` (from must be in your
+  namespace; linking TO any readable page is fine).
+- When you learn something channel-relevant in personal work, mirror the
+  conclusion into the channel prefix with a `(said in <where>)` provenance
+  note.
+
+## When to reach for the brain
+
+- Any question about the org, a person, a project, a decision, or history →
+  `gbrain search` FIRST, then answer.
+- You produced knowledge with value beyond this conversation → `gbrain put`.
+- Something looks wrong (auth errors, empty results you don't expect) →
+  `gbrain whoami` to confirm which client and scopes you're using, and report
+  its output.

docs/integrations/qm-harness-snippets/provision-scopes.sh

@@ -0,0 +1,258 @@
+#!/usr/bin/env bash
+# provision-scopes.sh — roster-driven gbrain provisioning for a qm deployment
+# (or any multi-user agent harness with per-person + per-channel scopes).
+#
+# Reads a roster of channels + employees and converges the brain to it:
+#   - ensures the shared agent-memory source exists (path-less: agents write
+#     pages into it over MCP; `gbrain sync` skips it; if the brain host has
+#     sync.repo_path configured, pages also write through to .sources/<id>/
+#     on disk for git-backed durability)
+#   - registers one OAuth client per employee, write-fenced via
+#     bound_slug_prefixes to emp-<slug>/ plus chan-<c>/ for each channel
+#     they are in, with federated reads over the memory source + any
+#     read-only sources you pass
+#   - re-running after roster edits rescopes existing clients IN PLACE
+#     (client ids are remembered in the state file; secrets never rotate
+#     unless you revoke + delete the state row)
+#
+# Usage:
+#   provision-scopes.sh roster.tsv \
+#     [--memory-source agents] [--read-sources org-wiki,handbook] \
+#     [--budget-usd-per-day 5] [--state-file roster.state.tsv] \
+#     [--secrets-out new-credentials.tsv] [--gbrain gbrain] [--dry-run]
+#
+# Roster format (one entry per line; '#' comments and blank lines ignored):
+#   channel <slug>
+#   employee <slug> [comma-separated channel slugs]
+#
+# SECURITY: --secrets-out receives client secrets for NEW registrations,
+# written exactly once (gbrain never re-shows them). Deliver each row to its
+# scope's sandbox (e.g. via the harness keychain or a one-time secret drop),
+# then delete the file.
+#
+# ponytail: sequential CLI loop, one gbrain invocation per roster row — fine
+# to hundreds of employees; batch via the admin API if that ever hurts.
+
+# -f (noglob) is load-bearing, not stylistic: roster lines are word-split
+# unquoted below, so without it a line like `employee * eng` would expand
+# against the working directory and silently provision a filename as a
+# person — i.e. the wrong write fence. Nothing here needs globbing.
+set -euf -o pipefail
+
+# Client secrets and the id state file are written by this script; 077 makes
+# them 0600 instead of the default 0644. Set before the first file is created.
+umask 077
+
+die() { echo "ERROR: $*" >&2; exit 1; }
+
+# Slugs become source ids, client names, AND slug-prefix write fences. The
+# fence list is comma-separated, so an unvalidated slug containing a comma
+# would inject an EXTRA prefix and hand the client write access to someone
+# else's namespace. Fail closed on anything that isn't plain kebab-case.
+valid_slug() {
+  case "$1" in
+    '') return 1 ;;
+    -*|*-) return 1 ;;
+    *[!a-z0-9-]*) return 1 ;;
+    *) return 0 ;;
+  esac
+}
+require_slug() {
+  valid_slug "$2" || die "roster: invalid $1 slug '$2' (allowed: lowercase a-z, 0-9, interior hyphens)"
+}
+
+ROSTER="${1:-}"
+[ -n "$ROSTER" ] && [ -f "$ROSTER" ] || die "usage: provision-scopes.sh <roster-file> [flags] (roster not found: '$ROSTER')"
+shift
+
+GBRAIN="${GBRAIN:-gbrain}"
+MEMORY_SOURCE="agents"
+READ_SOURCES=""
+BUDGET="5"
+STATE_FILE=""
+SECRETS_OUT=""
+DRY_RUN=0
+
+while [ $# -gt 0 ]; do
+  case "$1" in
+    --memory-source)      MEMORY_SOURCE="$2"; shift 2 ;;
+    --read-sources)       READ_SOURCES="$2"; shift 2 ;;
+    --budget-usd-per-day) BUDGET="$2"; shift 2 ;;
+    --state-file)         STATE_FILE="$2"; shift 2 ;;
+    --secrets-out)        SECRETS_OUT="$2"; shift 2 ;;
+    --gbrain)             GBRAIN="$2"; shift 2 ;;
+    --dry-run)            DRY_RUN=1; shift ;;
+    *) die "unknown flag: $1" ;;
+  esac
+done
+
+STATE_FILE="${STATE_FILE:-${ROSTER}.state.tsv}"
+SECRETS_OUT="${SECRETS_OUT:-${ROSTER}.new-credentials.tsv}"
+
+# The roster usually lives in the deployment repo, so the default secrets and
+# state paths land there too — one `git add -A` from committing live
+# credentials. The STATE file matters as much as the secrets file: it maps
+# employee -> client_id, and this script feeds that id straight to
+# `rescope-client`, so whoever can write it decides which client receives a
+# given employee's write authority. Treat both as privileged infrastructure,
+# at the same trust level as the roster itself.
+for f in "$SECRETS_OUT" "$STATE_FILE"; do
+  if git -C "$(dirname "$f")" rev-parse --is-inside-work-tree >/dev/null 2>&1; then
+    echo "WARN: $f is inside a git work tree. Never commit it;" >&2
+    echo "      gitignore it, or pass --secrets-out/--state-file outside the repo." >&2
+  fi
+done
+
+# A group/world-writable parent directory defeats the symlink and ownership
+# checks below: anyone with write access there can swap the file between our
+# check and our append. Refuse rather than pretend the checks hold.
+for d in "$(dirname "$SECRETS_OUT")" "$(dirname "$STATE_FILE")"; do
+  perms=$(ls -ld "$d" | awk '{print $1}')
+  case "$perms" in
+    ?????w*|????????w*) die "refusing to write credentials into a group/world-writable directory: $d ($perms)" ;;
+  esac
+done
+
+# Secure the credential sinks BEFORE anything is appended. umask only governs
+# files this script creates; a pre-existing world-readable file would receive
+# secrets first and be chmod'ed only afterwards, and a symlink planted at
+# either path would redirect them entirely.
+for f in "$SECRETS_OUT" "$STATE_FILE"; do
+  [ -L "$f" ] && die "refusing to write credentials through a symlink: $f"
+  if [ -e "$f" ]; then
+    [ -f "$f" ] || die "refusing to write credentials to a non-regular file: $f"
+    [ -O "$f" ] || die "refusing to write credentials to a file owned by another user: $f"
+  else
+    : > "$f"
+  fi
+  chmod 600 "$f"
+done
+
+run() {
+  if [ "$DRY_RUN" = 1 ]; then echo "DRY-RUN: $GBRAIN $*" >&2; return 0; fi
+  # shellcheck disable=SC2086 — $GBRAIN may carry args ("bun run src/cli.ts")
+  $GBRAIN "$@"
+}
+
+state_lookup() { # state_lookup <employee-slug> -> client_id or empty
+  [ -f "$STATE_FILE" ] || return 0
+  awk -F'\t' -v s="$1" '$1 == s { print $2; exit }' "$STATE_FILE"
+}
+
+# ── Pass 1: parse roster, collect declared channels ─────────────────────────
+CHANNELS=""
+EMPLOYEES=""
+lineno=0
+while IFS= read -r line || [ -n "$line" ]; do
+  lineno=$((lineno + 1))
+  line="${line%%#*}"
+  line="${line%$'\r'}"   # a CRLF roster would otherwise yield 'emp-alice\r/' prefixes that fence everything out
+  [ -z "${line//[[:space:]]/}" ] && continue
+  # shellcheck disable=SC2086 — deliberate word split; globbing is off (set -f above)
+  set -- $line
+  [ "$#" -le 3 ] || die "roster line $lineno: too many fields ('$line'). Channels are ONE comma-separated field with no spaces: 'employee alice eng,product'"
+  case "$1" in
+    channel)
+      require_slug channel "${2:-}"
+      CHANNELS="$CHANNELS $2"
+      ;;
+    employee)
+      require_slug employee "${2:-}"
+      case " $EMPLOYEES " in *" $2:"*) die "roster line $lineno: employee '$2' listed twice" ;; esac
+      if [ -n "${3:-}" ]; then
+        for c in ${3//,/ }; do require_slug "channel-reference" "$c"; done
+      fi
+      EMPLOYEES="$EMPLOYEES $2:${3:-}"
+      ;;
+    *) die "roster line $lineno: unknown entry type '$1' (expected 'channel' or 'employee')" ;;
+  esac
+done < "$ROSTER"
+
+# ── Pass 2: ensure the shared memory source exists (path-less) ──────────────
+if out=$(run sources add "$MEMORY_SOURCE" --name "agent memory ($MEMORY_SOURCE)" 2>&1); then
+  echo "source '$MEMORY_SOURCE': created"
+else
+  echo "$out" | grep -q "already registered" || die "sources add failed: $out"
+  echo "source '$MEMORY_SOURCE': already exists"
+fi
+
+# ── Pass 3: converge one client per employee ────────────────────────────────
+FED_READ="$MEMORY_SOURCE${READ_SOURCES:+,$READ_SOURCES}"
+new_secrets=0
+
+for entry in $EMPLOYEES; do
+  slug="${entry%%:*}"
+  chans="${entry#*:}"
+
+  prefixes="emp-$slug/"
+  if [ -n "$chans" ]; then
+    for c in ${chans//,/ }; do
+      echo " $CHANNELS " | grep -q " $c " || echo "WARN: employee '$slug' references undeclared channel '$c'" >&2
+      prefixes="$prefixes,chan-$c/"
+    done
+  fi
+
+  client_id="$(state_lookup "$slug")"
+  if [ -n "$client_id" ]; then
+    # The state file usually sits in the deployment repo, so anyone who can
+    # edit it could otherwise retarget this privileged rescope at an arbitrary
+    # client id (e.g. point alice's row at an admin client). Shape-check it.
+    case "$client_id" in
+      gbrain_cl_) die "state file: empty client id for '$slug'" ;;
+      gbrain_cl_*[!a-zA-Z0-9_]*) die "state file: malformed client id for '$slug': $client_id" ;;
+      gbrain_cl_*) ;;
+      *) die "state file: client id for '$slug' does not look like a gbrain client: $client_id" ;;
+    esac
+    # --source too, so a re-run actually CONVERGES the client to the roster:
+    # without it, changing --memory-source (or inheriting a state row written
+    # against an older one) silently leaves the old write source in place
+    # while the script reports success.
+    run auth rescope-client "$client_id" --source "$MEMORY_SOURCE" \
+      --federated-read "$FED_READ" --bound-slug-prefixes "$prefixes" >/dev/null
+    echo "employee '$slug': rescoped $client_id  [write: $prefixes]"
+  elif [ "$DRY_RUN" = 1 ]; then
+    echo "employee '$slug': WOULD register qm-emp-$slug  [write: $prefixes] [read: $FED_READ]"
+    continue
+  else
+    out=$(run auth register-client "qm-emp-$slug" \
+      --grant-types client_credentials --scopes "read write" \
+      --source "$MEMORY_SOURCE" --federated-read "$FED_READ" \
+      --bound-slug-prefixes "$prefixes" --budget-usd-per-day "$BUDGET" 2>&1) \
+      || die "register-client failed for '$slug' (output withheld: it can contain a secret). Re-run the command by hand to see why."
+    client_id=$(echo "$out" | sed -n 's/.*Client ID:[[:space:]]*\(gbrain_cl_[^[:space:]]*\).*/\1/p' | head -1)
+    secret=$(echo "$out"    | sed -n 's/.*Client Secret:[[:space:]]*\(gbrain_cs_[^[:space:]]*\).*/\1/p' | head -1)
+    if [ -z "$client_id" ] || [ -z "$secret" ]; then
+      # The client may well have been created — dying silently would strand a
+      # live credential nobody can find. Say so WITHOUT echoing the captured
+      # output: it contains the freshly minted secret, and this path ends up
+      # in CI logs.
+      die "could not parse client id/secret for '$slug' from register-client output (output withheld: it contains a secret). A client MAY have been created; check \`gbrain auth list\` and revoke any stray 'qm-emp-$slug'."
+    fi
+    printf '%s\t%s\n' "$slug" "$client_id" >> "$STATE_FILE"
+    printf '%s\t%s\t%s\n' "$slug" "$client_id" "$secret" >> "$SECRETS_OUT"
+    chmod 600 "$STATE_FILE" "$SECRETS_OUT" 2>/dev/null || true  # umask covers new files; this covers pre-existing ones
+    new_secrets=$((new_secrets + 1))
+    echo "employee '$slug': registered $client_id  [write: $prefixes]"
+  fi
+done
+
+# ── Pass 4: flag offboarded employees ───────────────────────────────────────
+# Removing someone from the roster is the highest-stakes edit there is, and
+# this script cannot safely revoke on its own (a typo'd roster would nuke live
+# credentials). Report instead, with the exact command.
+if [ -f "$STATE_FILE" ]; then
+  while IFS=$'\t' read -r st_slug st_client _rest; do
+    [ -n "${st_slug:-}" ] || continue
+    case " $EMPLOYEES " in
+      *" $st_slug:"*) ;;
+      *) echo "STALE: '$st_slug' ($st_client) is no longer in the roster but its credentials still work." >&2
+         echo "       Revoke with: $GBRAIN auth revoke-client $st_client" >&2 ;;
+    esac
+  done < "$STATE_FILE"
+fi
+
+echo
+echo "Done. State: $STATE_FILE"
+if [ "$new_secrets" -gt 0 ]; then
+  echo "$new_secrets NEW client secret(s) written to $SECRETS_OUT — deliver to each scope's sandbox, then DELETE the file."
+fi

docs/integrations/qm-harness-snippets/roster.example.tsv

@@ -0,0 +1,10 @@
+# Roster for provision-scopes.sh — one line per channel / employee.
+# channel <slug>
+# employee <slug> [comma-separated channels they belong to]
+
+channel eng
+channel product
+
+employee alice-example eng,product
+employee bob-example eng
+employee carol-example

docs/integrations/qm-harness-snippets/tool.json

@@ -0,0 +1,19 @@
+{
+  "id": "gbrain",
+  "label": "gbrain company brain",
+  "advertise": "gbrain",
+  "hints": [
+    "Company knowledge brain: searchable, cross-source, persistent.",
+    "Search it BEFORE answering questions about the org, people, projects, decisions, or history: `gbrain search \"<question>\"`.",
+    "Write durable knowledge with `gbrain put <slug> --content ...`, only under your own slug prefixes.",
+    "See the gbrain skill for slug conventions and first-run setup."
+  ],
+  "auth": {
+    "check": "gbrain whoami",
+    "reauth": "gbrain init --mcp-only --force --issuer-url \"$GBRAIN_ISSUER_URL\" --mcp-url \"$GBRAIN_MCP_URL\" --oauth-client-id \"$GBRAIN_CLIENT_ID\" --oauth-client-secret \"$GBRAIN_CLIENT_SECRET\"",
+    "credentialPaths": [
+      { "path": ".gbrain/config.json", "kind": "file" }
+    ]
+  },
+  "install": { "binary": "gbrain" }
+}

docs/integrations/qm-harness.md

@@ -0,0 +1,224 @@
+# qm (multi-user agent harness) — gbrain as the company brain
+
+Connect gbrain to [qm](https://github.com/yc-software/qm) — the multiplayer
+agent harness where each employee and each channel gets an isolated agent
+scope — so every scope's agent can search and write one shared, indexed,
+isolation-enforced company brain. The same recipe fits any harness with
+per-person sandboxes that can run a CLI.
+
+**Shape:** one central `gbrain serve --http` (OAuth 2.1) next to qm's core;
+the `gbrain` binary baked into qm's sandbox image as a thin client; one OAuth
+client per employee, read-fenced by source federation and write-fenced by
+`bound_slug_prefixes`. Zero qm code changes — everything lives in the qm
+*deployment directory*.
+
+qm's native memory (per-scope notebook) stays as-is for fast per-turn recall.
+gbrain adds what qm doesn't have: semantic + hybrid search, cross-scope
+knowledge, entity graphs, and durable memory that outlives a scope.
+
+## Topology
+
+| gbrain concept | qm concept |
+|---|---|
+| one brain (one Postgres/Supabase DB) | the org |
+| source `agents` (path-less, shared) | all agent-written memory |
+| slug prefix `emp-<slug>/` in `agents` | an employee's personal scope |
+| slug prefix `chan-<slug>/` in `agents` | a channel/room scope |
+| source `org-wiki` (git-backed, read-only) | company docs |
+| OAuth client `qm-emp-<slug>` | one employee's agent identity |
+
+Isolation model:
+
+- **Reads** are source-granular, SQL-enforced (`federated_read`): every
+  employee client reads `agents` + the read-only sources you grant.
+- **Writes** are slug-prefix-granular, server-enforced (`bound_slug_prefixes`,
+  v0.42.72.0+): a client can only mutate pages under its own `emp-<slug>/`
+  and its channels' `chan-<x>/` prefixes — on `put_page`, `delete_page`,
+  `restore_page`, `add_tag`, `remove_tag`, `add_link`/`remove_link`,
+  `add_timeline_entry`, `revert_version` and `put_raw_data`, plus the
+  `POST /ingest` webhook route. Not by convention.
+- **Every op that is not a plain read is denied unless allow-listed.** Ops
+  that write by a key other than a slug — `extract_entities` and
+  `extract_facts` (which mutate `people/*` and `companies/*`), `forget_fact`
+  (targets a fact by numeric id, across sources), `ontology_propose`, and the
+  `sources_admin` pair `sources_add`/`sources_remove` — cannot be fenced by
+  slug, so a bound client gets `permission_denied` at dispatch. The gate keys
+  on "not a pure read", not on a list of scope strings, so a write op added
+  later (or one carrying a bespoke scope) is denied until it is explicitly
+  fenced and added to `CLIENT_FENCED_WRITE_OPS` (`src/core/operations.ts`).
+  `think` is allow-listed because remote callers cannot persist from it;
+  `submit_agent` because it enforces this same column itself.
+- **Indirect write paths are gated too, not just the ops.** `put_page`'s
+  facts backstop would otherwise extract entities from the page body and
+  write fact rows (and a `## Facts` fence on git-backed sources) onto
+  `people/*` pages the caller never named — the same capability
+  `extract_facts` is denied for, reached through an in-prefix write. It is
+  skipped for bound clients. `POST /ingest` is refused outright: its handler
+  bypasses the op layer *and* discards the source grant for untrusted
+  payloads, so it would write into the `default` source.
+### Known limitations — read these before you rely on the fence
+
+The write fence is a **write** boundary within a source. It is not a privacy
+boundary, and it does not make every side effect prefix-clean. As of
+v0.42.72.0:
+
+- **`add_link`/`remove_link` fence the `from` endpoint only.** A bound client
+  can create an edge pointing AT a page it cannot write; the edge's `context`
+  text surfaces in that page's backlinks and contributes to its search
+  ranking. Fencing `to` would break legitimate cross-referencing into
+  `org-wiki`, so this is deliberate — treat inbound-edge context as untrusted
+  content, the same way you treat page bodies.
+- **Reads are source-granular, never prefix-granular.** Everyone entitled to
+  a source can read every prefix in it. If a scope needs genuine read
+  privacy, give it its own source.
+- **`put_page` can create one reverse graph edge outside the fence.** If a
+  page body cites a code location (`src/x.ts:42`) and a code page for it
+  exists *in the same source*, doc↔impl reconciliation adds an edge
+  originating from that code page. It affects graph/backlink ranking, not
+  page content. Unreachable in the layout above (the `agents` source is
+  path-less and holds no code pages); it applies only if you point employee
+  writes at a code-synced source.
+- **A few read ops are still brain-wide** and ignore the federated grant:
+  `get_recent_salience`, `find_anomalies`, `find_contradictions`, and
+  `sources_list`/`sources_status` (which expose source ids, paths and URLs).
+  A read-scoped client can learn facts derived from sources it was not
+  granted. Pre-existing, not introduced by the fence; if that matters for
+  your deployment, withhold those tools at the harness layer for now.
+- **Reads touch `last_retrieved_at`** on the pages they return, including
+  pages in read-only sources. Freshness/usage signals are therefore
+  writable-by-reading; nothing else about the page is.
+- **`POST /ingest` writes land in the `default` source** regardless of the
+  calling client's `source_id`, because the handler discards the source for
+  untrusted payloads. Bound clients are refused the route outright for this
+  reason; if you point a webhook integration at it, scope that brain's
+  `default` source deliberately.
+- **Tradeoff to state out loud:** read isolation is per-source, so within the
+  shared `agents` source every employee can *read* every prefix (including
+  other employees' `emp-*/`). That matches qm's transparent-by-default,
+  everything-audited posture. If you need hard read privacy for personal
+  memory, give those employees their own write source instead of a prefix
+  (one `sources add emp-<slug>` + `--source emp-<slug>` per client) and keep
+  channel prefixes in `agents` via a second, channels-only client — at the
+  cost of two credentials in that sandbox.
+
+## Host setup (the machine running qm's core, or any box its sandboxes can reach)
+
+```bash
+# 1. Engine: Postgres/Supabase. PGLite is single-process and cannot serve
+#    many concurrent sandboxes.
+gbrain init --supabase --embedding-model voyage:voyage-4-large
+
+# 2. Modes + gates (publish_* default OFF and fail as silent 403s):
+gbrain config set search.mode balanced
+gbrain config set mcp.publish_skills true
+gbrain config set mcp.publish_advisor true
+
+# 3. Read-only org sources + first sync:
+gbrain sources add org-wiki --path ~/brains/org-wiki
+gbrain sync --all        # cron this
+
+# 4. Serve over HTTP MCP (OAuth 2.1):
+gbrain serve --http --bind 0.0.0.0 --port 3131 \
+  --public-url https://brain.acme-example.com
+```
+
+Never hand sandboxes `DATABASE_URL` — direct DB access bypasses OAuth, source
+federation, and the write fence entirely.
+
+## Provision scopes from a roster
+
+[`qm-harness-snippets/provision-scopes.sh`](qm-harness-snippets/provision-scopes.sh)
+converges the brain to a roster file
+([`roster.example.tsv`](qm-harness-snippets/roster.example.tsv)):
+
+```bash
+bash provision-scopes.sh roster.tsv --read-sources org-wiki
+```
+
+- Creates the path-less `agents` source (agent-written memory needs no git
+  clone; if the host has `sync.repo_path` configured, pages also write
+  through to `.sources/agents/` for git-backed durability).
+- Registers `qm-emp-<slug>` clients: `--scopes "read write"`,
+  `--source agents`, `--federated-read agents,org-wiki`,
+  `--bound-slug-prefixes emp-<slug>/,chan-<a>/,...`, per-day budget.
+- **Idempotent:** re-run after every roster edit; existing clients are
+  `rescope-client`ed in place (channel joins/leaves update the write fence
+  without rotating secrets).
+- New client secrets land once in `<roster>.new-credentials.tsv` — deliver
+  each row to its scope (qm keychain / one-time secret drop), then delete
+  the file.
+
+## qm deployment directory
+
+In the org's qm deployment repo (the directory `qm init` produced):
+
+1. **Tool:** copy [`qm-harness-snippets/tool.json`](qm-harness-snippets/tool.json)
+   to `sandbox/tools/gbrain/tool.json` and drop the compiled `gbrain` binary
+   beside it (`bun build --compile --outfile gbrain src/cli.ts`, built for
+   the sandbox image's OS/arch). `auth.credentialPaths` marks
+   `~/.gbrain/config.json` as the scope's resident credential file;
+   `auth.check` wires `gbrain whoami` into qm's connector status (read-scope;
+   see the note below on why `remote doctor` cannot be used here).
+2. **Skill:** copy [`qm-harness-snippets/SKILL.md`](qm-harness-snippets/SKILL.md)
+   to `sandbox/skills/gbrain/SKILL.md` (edit slug conventions to taste).
+3. Ship it: `qm sandbox build && qm sandbox publish && qm up`.
+
+Per scope, one-time (agent- or operator-run, credentials from the handoff):
+
+```bash
+gbrain init --mcp-only \
+  --issuer-url https://brain.acme-example.com \
+  --mcp-url https://brain.acme-example.com/mcp \
+  --oauth-client-id gbrain_cl_... --oauth-client-secret gbrain_cs_...
+gbrain whoami                       # must succeed
+```
+
+Use `--oauth-client-secret`, not `GBRAIN_REMOTE_CLIENT_SECRET`: an env-sourced
+secret is deliberately not written to `~/.gbrain/config.json`
+(`src/commands/init.ts`), so with the env var alone every later command fails
+once it leaves scope — and qm's `sandbox.secretEnv` is org-wide, so there is no
+per-scope env to keep it in. With the flag, the credential lands in the config
+file on the scope's durable disk and this runs once per scope, ever.
+
+`gbrain remote doctor` is **not** the health check here: `run_doctor` is an
+`admin`-scope op and these clients are `read write` on purpose. `gbrain whoami`
+is read-scope and reports the client's identity, source, and grants.
+
+## Verify isolation before rollout
+
+From two differently-scoped sandboxes (or two thin-client configs):
+
+```bash
+# alice-example (bound to emp-alice-example/, chan-eng/):
+gbrain put emp-alice-example/notes/test --content "mine"        # OK
+gbrain put chan-eng/notes/test --content "shared"               # OK
+gbrain put emp-bob-example/notes/test --content "not mine"      # permission_denied
+gbrain put chan-product/notes/test --content "not my channel"   # permission_denied
+gbrain search "test"                                            # sees agents + org-wiki only
+```
+
+## Cost + operations
+
+- `search.mode balanced` (12K token budget, relational retrieval on) is the
+  right default for a startup fleet; see `docs/guides/search-modes.md` for
+  the cost matrix before changing it.
+- Budgets: `--budget-usd-per-day` is recorded on the client but only enforced
+  on the `submit_agent` path (`src/core/minions/budget-meter.ts`), which these
+  `read write` clients cannot reach — so it does **not** cap spend from
+  ordinary `search`/`put_page` traffic. Treat runaway-agent containment as an
+  open item: watch the admin SPA (`/admin`) and `gbrain search stats`, and cap
+  at the model/harness layer.
+- Backfills on a live brain: `gbrain embed --stale --pace` (see Pace Mode in
+  CLAUDE.md / `docs/operations/spend-controls.md`).
+
+## Deliberately deferred
+
+- **qm `MemoryService` decorator** (mirror notebook captures into gbrain,
+  fan `recall` out and merge, `volunteer_context` push): needs a qm code
+  change; today's integration is agent-initiated via the CLI + skill.
+- **MCP-native attach:** qm pins `strictMcpConfig` with only its in-process
+  server, so gbrain's MCP-discovered brain-resident skillpacks don't reach
+  qm agents; the sandbox skill above covers it.
+- **Read-side prefix fencing** (hard privacy for `emp-*/` inside a shared
+  source) — tracked upstream; the roster layout is forward-compatible with
+  it.

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

docs/storage-tiering.md

@@ -51,6 +51,18 @@ When storage configuration is present, `gbrain sync` automatically manages `.git
 - Skipped when the repo is a git submodule (`.git` is a file, not a directory) — submodule .gitignore changes don't survive parent updates. A warning explains.
 - Skipped entirely when `GBRAIN_NO_GITIGNORE=1` is set (escape hatch for shared-repo setups where a maintainer wants gbrain to leave .gitignore alone).
 - Failures (write permission denied, etc.) are caught and logged, never crash sync.
+- Warns when a configured collector's declared output dir (recipe `output_paths`
+  frontmatter) sits inside a `db_only` path: gitignored files never appear in the
+  git-walking sync diff, and `gbrain import` honors `.gitignore` too — the
+  collector would run green while nothing reaches the DB. The
+  `db_only_collector_collision` doctor check surfaces the same trap.
+
+Related doctor coverage: `undeclared_db_only_pages` warns about DB pages with no
+backing file that sit outside every declared `db_only` path. The engine's own
+derive-phase output prefixes (`life/events/`, `atoms/`, `extracts/`,
+`dream-cycle-summaries/`) count as implicitly declared for that check, so healthy
+brains stay quiet without adding them to `gbrain.yml`. They are NOT auto-added to
+`.gitignore` — only explicitly declared `db_only` dirs are.
 
 Example `.gitignore` addition:
 

docs/superpowers/plans/2026-07-28-engine-dynamic-import-reconciliation.md

@@ -0,0 +1,690 @@
+# Engine Dynamic-Import Reconciliation Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Reconstruct the missing engine-path static-import hardening, preserve the four load-bearing lazy gateway fallbacks, and prevent unreviewed dynamic imports from returning.
+
+**Architecture:** Make the 13 safe engine/migration import statements static and leave only four line-marked `ai/gateway.ts` imports inside their existing soft-failure `try/catch` boundaries. Enforce that current state with a repository-anchored Bash wrapper delegating to a fail-closed TypeScript AST scanner, a hermetic Bun regression test, package/verify wiring, and current-state architecture documentation.
+
+**Tech Stack:** TypeScript compiler API, Bun test runner, Bash, Git, generated llms documentation bundles.
+
+## Global Constraints
+
+- Reconstruct directly on branch `claude/kind-meitner-330c90`, based on investigated `origin/master` commit `6136e139972a5449630b4f47f5ed7b4cbe5b811b` plus design commit `d7f52d8c`.
+- Do not merge or cherry-pick `48ada48f`, `248bfe55`, `ef4cf7a8`, or either historical branch wholesale.
+- Do not modify `VERSION`, `CHANGELOG.md`, `TODOS.md`, or release metadata; this is a no-version-bump reconciliation.
+- Keep all four `await import('./ai/gateway.ts')` calls lazy: PGLite and Postgres `initSchema`, plus both `_upsertChunksOnce` methods.
+- Every allowed lazy gateway line must carry `engine-dynamic-import-ok`; there is no file-level exemption.
+- Preserve the stronger gateway rationale: the static closure is large, and eager module evaluation would occur outside the local `try/catch`, potentially converting a recoverable configuration/import failure into a module-load-time hard failure.
+- Describe the hoists as engine-path hardening. Do not claim every dynamic import deterministically causes a Windows crash; system-wide commit exhaustion confounded prior measurements.
+- Keep shared PGLite/Postgres behavior in parity.
+- Invoke repository shell scripts through `bash` in `package.json`.
+- Capture complete test/check output to workspace-local `.context/*.txt` files before inspecting it; never pipe a test command directly through `head` or `tail`.
+- Use `git log -G`, not `git log -S`, for any additional dynamic-to-static import history work.
+- Keep every implementation and verification commit local. Do not push, create a PR, comment upstream, or otherwise publish without explicit user approval after local completion.
+- Before editing any affected function, run GBrain `code_blast` and `code_callers` for that symbol and inspect any disambiguation candidates.
+
+---
+
+## File Map
+
+- Create `scripts/check-engine-dynamic-import.sh` — repository-anchored Bash wrapper for default and explicit input routing.
+- Create `scripts/check-engine-dynamic-import.ts` — TypeScript AST policy scanner for runtime `import()` expressions, parse/read failures, and exact-line comment-trivia opt-outs.
+- Create `test/scripts/check-engine-dynamic-import.test.ts` — 22 hermetic adversarial, CRLF, fail-closed, real-tree, and wiring tests.
+- Modify `src/core/pglite-engine.ts` — hoist three safe import statements and mark two deliberate gateway imports.
+- Modify `src/core/postgres-engine.ts` — hoist eight safe import statements and mark two deliberate gateway imports.
+- Modify `src/core/migrate.ts` — hoist two safe migration helper import statements.
+- Modify `package.json` — expose `check:engine-dynamic-import` and append it to `check:all` through `bash`.
+- Modify `scripts/run-verify-parallel.sh` — add the package check to the authoritative verify dispatcher.
+- Modify `CLAUDE.md` — add the cross-cutting current-state invariant.
+- Modify `docs/architecture/KEY_FILES.md` — update current-state entries for the three engine-path files.
+- Regenerate `llms.txt` and `llms-full.txt` — required derived bundles after CLAUDE/reference documentation changes.
+
+---
+
+### Task 1: Establish and enforce the source invariant
+
+**Files:**
+- Create: `scripts/check-engine-dynamic-import.sh`
+- Create: `scripts/check-engine-dynamic-import.ts`
+- Create: `test/scripts/check-engine-dynamic-import.test.ts`
+- Modify: `src/core/pglite-engine.ts`
+- Modify: `src/core/postgres-engine.ts`
+- Modify: `src/core/migrate.ts`
+
+**Interfaces:**
+- Consumes: shell positional arguments `FILE...`; without arguments, the guard scans the three repository files.
+- Produces: `scripts/check-engine-dynamic-import.sh [FILE...]`, exit `0` when every runtime dynamic import is allowed and exit `1` after reporting every `file:line:text` violation plus every read/parse error on stderr.
+- Produces: one line-level opt-out token, `engine-dynamic-import-ok`, accepted only in real comment trivia on the same physical line as the deliberately lazy import.
+- Fails closed on missing/unreadable inputs, TypeScript parse diagnostics, and scanner/process failures; comments, strings, templates, regex literals, and type-position `import(...)` syntax are not runtime imports.
+
+- [ ] **Step 1: Record call-graph blast radius before touching functions**
+
+First call `sources_list` and select the source whose registered path is this gbrain checkout. Then run `code_blast` and `code_callers` for these qualified symbols with that exact `source_id`, following `did_you_mean`/`candidates` when a method name is ambiguous:
+
+```text
+src/core/pglite-engine.ts::PGLiteEngine.initSchema
+src/core/pglite-engine.ts::PGLiteEngine.batchRetry
+src/core/pglite-engine.ts::PGLiteEngine._upsertChunksOnce
+src/core/pglite-engine.ts::PGLiteEngine.mergeOntologyFact
+src/core/pglite-engine.ts::PGLiteEngine.getRecentSalience
+src/core/postgres-engine.ts::PostgresEngine.disconnect
+src/core/postgres-engine.ts::PostgresEngine.initSchema
+src/core/postgres-engine.ts::PostgresEngine.batchRetry
+src/core/postgres-engine.ts::PostgresEngine._upsertChunksOnce
+src/core/postgres-engine.ts::PostgresEngine.mergeOntologyFact
+src/core/postgres-engine.ts::PostgresEngine.reconnect
+src/core/postgres-engine.ts::PostgresEngine.getRecentSalience
+src/core/migrate.ts::runMigrationSQLWithRetry
+src/core/migrate.ts::runMigrations
+```
+
+Use `depth: 5`, `max_nodes: 200`, and `limit: 100`. Expected: no caller requires a signature or behavior change; the patch only changes module binding time and retains all local fallback/error handling.
+
+- [ ] **Step 2: Write the failing guard regression test**
+
+Create `test/scripts/check-engine-dynamic-import.test.ts` as a hermetic subprocess suite. The completed 22-test surface covers:
+
+- unmarked runtime `import()` rejection, including bare and trivia-separated forms;
+- same-line markers in real line or multiline block-comment trivia;
+- rejection of markers on prior lines or inside strings, templates, and module paths;
+- comments and comment-like delimiters inside strings, templates, and regex literals;
+- live code after same-line or multiline block comments close;
+- CRLF input and complete multi-file violation aggregation;
+- missing/readable mixed inputs and TypeScript parse diagnostics;
+- default repository anchoring when invoked from a foreign Git repository;
+- the reconciled three-file source scan plus package/parallel-verifier wiring.
+
+Use the TypeScript parser rather than a partial lexical reimplementation. On Windows, set the test default to 30 seconds because each case launches Git Bash and Bun, whose startup can exceed Bun's 5-second per-test default.
+
+- [ ] **Step 3: Run the test to prove the pre-implementation red state**
+
+```bash
+bun test test/scripts/check-engine-dynamic-import.test.ts > .context/engine-dynamic-import-red.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit 0
+```
+
+Expected: non-zero Bun result captured inside the log. At minimum, the `exists` assertion fails because `scripts/check-engine-dynamic-import.sh` does not exist. Read `.context/engine-dynamic-import-red.txt`; do not infer the result from a truncated pipeline.
+
+- [ ] **Step 4: Add the CRLF-safe, fail-closed guard**
+
+Create `scripts/check-engine-dynamic-import.sh` as a thin LF-terminated wrapper. Resolve its own directory first; when no explicit files are passed, anchor the repository with `git -C "$SCRIPT_DIR/.."` and scan the two engines plus `migrate.ts`. Delegate with `exec bun "$SCRIPT_DIR/check-engine-dynamic-import.ts" "${FILES[@]}"` so scanner failures propagate.
+
+Create `scripts/check-engine-dynamic-import.ts` using the TypeScript compiler API:
+
+- read every requested file and aggregate read failures;
+- parse as TypeScript and aggregate parse diagnostics;
+- walk the AST for `CallExpression`s whose expression is `ImportKeyword`;
+- locate all marker occurrences in the full source and use `ts.getTokenAtPosition` to admit only occurrences outside AST tokens (real comment trivia), recording their physical source lines;
+- require each runtime import's line to have an admitted marker or report its original `file:line:text`;
+- print every read/parse error and every violation before exiting nonzero.
+
+This preserves CRLF line accounting, ignores comment/literal/type-only false positives, catches every legal runtime `import()` shape the TypeScript parser recognizes, rejects marker spoofing, and fails closed.
+
+- [ ] **Step 5: Run the guard test to prove the source-tree midpoint is still red**
+
+```bash
+bun test test/scripts/check-engine-dynamic-import.test.ts > .context/engine-dynamic-import-midpoint.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit 0
+```
+
+Expected: the synthetic violation, marker, comments, and CRLF cases pass. The default repository scan fails and reports all 17 current imports: 13 unmarked safe candidates plus the four not-yet-marked gateway calls.
+
+- [ ] **Step 6: Hoist the three safe PGLite import statements**
+
+Replace the existing `retry.ts` import and add the ontology/recency imports near the top of `src/core/pglite-engine.ts`:
+
+```ts
+// Engine-path imports stay static unless a call site carries an explicit
+// engine-dynamic-import-ok justification. The gateway is the only current
+// exception because its local try/catch preserves a soft fallback.
+import {
+  withRetry,
+  BULK_RETRY_OPTS,
+  resolveBulkRetryOpts,
+  computeNextDelay,
+  isRetryableConnError,
+  type BatchAuditSite,
+} from './retry.ts';
+import {
+  valueHash,
+  normalizeDimension,
+  isNovelDimension,
+} from './chronicle/ontology.ts';
+import {
+  resolveRecencyDecayMap,
+  DEFAULT_FALLBACK,
+} from './search/recency-decay.ts';
+```
+
+Delete only these three in-method destructuring imports, leaving their uses unchanged:
+
+```ts
+const { isRetryableConnError } = await import('./retry.ts');
+const { valueHash, normalizeDimension, isNovelDimension } = await import('./chronicle/ontology.ts');
+const { resolveRecencyDecayMap, DEFAULT_FALLBACK } = await import('./search/recency-decay.ts');
+```
+
+- [ ] **Step 7: Mark both PGLite gateway soft-failure boundaries**
+
+In `PGLiteEngine.initSchema`, preserve the `try/catch` and accessors, changing only the rationale and import line:
+
+```ts
+try {
+  // Keep the gateway lazy: its static closure is large, and evaluation inside
+  // this try/catch preserves the unconfigured-gateway default fallback.
+  const gw = await import('./ai/gateway.ts'); // engine-dynamic-import-ok
+  // Both accessors THROW when the gateway is unconfigured (they never
+  // return falsy), so the catch below is the only fallback path (#3461).
+  dims = gw.getEmbeddingDimensions();
+  model = gw.getEmbeddingModel();
+} catch { /* gateway not configured — use defaults */ }
+```
+
+In `PGLiteEngine._upsertChunksOnce`, preserve the config-row and compile-time fallback chain:
+
+```ts
+try {
+  // Keep the gateway lazy so module-load failure remains inside this soft
+  // fallback boundary; eager evaluation would bypass the config-row fallback.
+  const gw = await import('./ai/gateway.ts'); // engine-dynamic-import-ok
+  resolvedModel = gw.getEmbeddingModel();
+} catch {
+```
+
+- [ ] **Step 8: Hoist the eight safe Postgres import statements**
+
+Replace the existing `retry.ts` import and add these imports near the top of `src/core/postgres-engine.ts`:
+
+```ts
+// Engine-path imports stay static unless a call site carries an explicit
+// engine-dynamic-import-ok justification. The gateway is the only current
+// exception because its local try/catch preserves a soft fallback.
+import {
+  withRetry,
+  BULK_RETRY_OPTS,
+  resolveBulkRetryOpts,
+  computeNextDelay,
+  isRetryableConnError,
+  type BatchAuditSite,
+} from './retry.ts';
+import { isConnectionEndedError } from './retry-matcher.ts';
+import {
+  valueHash,
+  normalizeDimension,
+  isNovelDimension,
+} from './chronicle/ontology.ts';
+import {
+  resolveRecencyDecayMap,
+  DEFAULT_FALLBACK,
+} from './search/recency-decay.ts';
+import { logDbDisconnect } from './audit/db-disconnect-audit.ts';
+import { logPoolRecovery } from './audit/pool-recovery-audit.ts';
+```
+
+Delete the eight safe dynamic-import statements while keeping their surrounding `try/catch` blocks and calls unchanged:
+
+```ts
+const { logDbDisconnect } = await import('./audit/db-disconnect-audit.ts');
+const { isRetryableConnError } = await import('./retry.ts');
+const { valueHash, normalizeDimension, isNovelDimension } = await import('./chronicle/ontology.ts');
+const { isConnectionEndedError } = await import('./retry-matcher.ts');
+const { logPoolRecovery } = await import('./audit/pool-recovery-audit.ts');
+const { logPoolRecovery } = await import('./audit/pool-recovery-audit.ts');
+const { logPoolRecovery } = await import('./audit/pool-recovery-audit.ts');
+const { resolveRecencyDecayMap, DEFAULT_FALLBACK } = await import('./search/recency-decay.ts');
+```
+
+Update the stale `batchRetry` comment from “Lazy-import to avoid a circular dep concern” to current truth:
+
+```ts
+// retry.ts is already in this module's static graph through withRetry, so
+// classifying the exhausted error does not need a second runtime import.
+```
+
+- [ ] **Step 9: Mark both Postgres gateway soft-failure boundaries**
+
+In `PostgresEngine.initSchema`, mirror the PGLite rationale and preserve behavior:
+
+```ts
+try {
+  // Keep the gateway lazy: its static closure is large, and evaluation inside
+  // this try/catch preserves the unconfigured-gateway default fallback.
+  const gw = await import('./ai/gateway.ts'); // engine-dynamic-import-ok
+  // Both accessors THROW when the gateway is unconfigured (they never
+  // return falsy), so the catch below is the only fallback path (#3461).
+  dims = gw.getEmbeddingDimensions();
+  model = gw.getEmbeddingModel();
+} catch { /* gateway not yet configured — use defaults */ }
+```
+
+In `PostgresEngine._upsertChunksOnce`, preserve the DB-config fallback:
+
+```ts
+try {
+  // Keep the gateway lazy so module-load failure remains inside this soft
+  // fallback boundary; eager evaluation would bypass the config-row fallback.
+  const gw = await import('./ai/gateway.ts'); // engine-dynamic-import-ok
+  resolvedModel = gw.getEmbeddingModel();
+} catch {
+```
+
+- [ ] **Step 10: Hoist the two migration helper import statements**
+
+Add these static imports at the top of `src/core/migrate.ts`:
+
+```ts
+// runMigrations executes while an initialized engine is live. Keep its helper
+// modules in the static graph rather than importing them from async handlers.
+import {
+  isStatementTimeoutError,
+  isRetryableConnError,
+} from './retry-matcher.ts';
+import { repairTimelineDedupIndex } from './timeline-dedup-repair.ts';
+```
+
+Delete only these two local destructuring imports:
+
+```ts
+const { isStatementTimeoutError, isRetryableConnError } = await import('./retry-matcher.ts');
+const { repairTimelineDedupIndex } = await import('./timeline-dedup-repair.ts');
+```
+
+- [ ] **Step 11: Run the complete guard test and direct guard**
+
+```bash
+bun test test/scripts/check-engine-dynamic-import.test.ts > .context/engine-dynamic-import-green.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`; the full guard regression suite passes.
+
+```bash
+bash scripts/check-engine-dynamic-import.sh > .context/engine-dynamic-import-guard.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`; output contains `check-engine-dynamic-import: ok (3 file(s) scanned)`.
+
+- [ ] **Step 12: Prove the guard leaves exactly four marked dynamic imports**
+
+```bash
+git grep -n -F "import('./ai/gateway.ts'); // engine-dynamic-import-ok" -- src/core/pglite-engine.ts src/core/postgres-engine.ts src/core/migrate.ts > .context/engine-dynamic-import-sites.txt; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exactly four lines, all importing `./ai/gateway.ts` and all carrying `engine-dynamic-import-ok`; no match in `src/core/migrate.ts`.
+
+- [ ] **Step 13: Run focused behavior tests**
+
+```bash
+bun test test/chronicle-ontology.test.ts test/chronicle-ontology-ops.test.ts test/recency-decay.test.ts test/core/retry.test.ts test/retry-matcher.test.ts test/audit/pool-recovery-audit.test.ts test/migrate-retry.test.ts test/timeline-dedup-repair.test.ts > .context/engine-dynamic-import-focused.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`. If Windows resource pressure aborts the process, record the exact exit code and rerun the failing file alone; do not relabel an infrastructure abort as a source pass.
+
+- [ ] **Step 14: Commit the source invariant locally**
+
+```bash
+git add scripts/check-engine-dynamic-import.sh scripts/check-engine-dynamic-import.ts test/scripts/check-engine-dynamic-import.test.ts src/core/pglite-engine.ts src/core/postgres-engine.ts src/core/migrate.ts
+```
+
+```bash
+git commit -m "fix(engine): reconcile dynamic import hardening"
+```
+
+Expected: one local commit; no version or release files staged.
+
+---
+
+### Task 2: Wire the guard into repository checks
+
+**Files:**
+- Modify: `test/scripts/check-engine-dynamic-import.test.ts`
+- Modify: `package.json`
+- Modify: `scripts/run-verify-parallel.sh`
+
+**Interfaces:**
+- Consumes: `scripts/check-engine-dynamic-import.sh` from Task 1.
+- Produces: package script `check:engine-dynamic-import` and verify dry-list entry of the same name.
+
+- [ ] **Step 1: Add failing wiring assertions**
+
+Add these imports/constants to `test/scripts/check-engine-dynamic-import.test.ts`:
+
+```ts
+const PACKAGE_JSON = resolve(REPO_ROOT, 'package.json');
+```
+
+Append this test block:
+
+```ts
+describe('engine dynamic-import guard wiring', () => {
+  it('is invoked through bash by check:all', () => {
+    const pkg = JSON.parse(readFileSync(PACKAGE_JSON, 'utf8')) as {
+      scripts: Record<string, string>;
+    };
+    expect(pkg.scripts['check:engine-dynamic-import']).toBe(
+      'bash scripts/check-engine-dynamic-import.sh',
+    );
+    expect(pkg.scripts['check:all']).toContain(
+      'bash scripts/check-engine-dynamic-import.sh',
+    );
+  });
+
+  it('is listed by the authoritative verify dispatcher', () => {
+    const result = spawnSync(BASH, [VERIFY_DISPATCHER, '--dry-list'], {
+      cwd: REPO_ROOT,
+      encoding: 'utf8',
+      timeout: 30_000,
+    });
+    expect(result.status).toBe(0);
+    expect(new Set((result.stdout ?? '').trim().split('\n'))).toContain(
+      'check:engine-dynamic-import',
+    );
+  });
+});
+```
+
+- [ ] **Step 2: Run the test and verify both wiring assertions fail**
+
+```bash
+bun test test/scripts/check-engine-dynamic-import.test.ts > .context/engine-dynamic-import-wiring-red.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit 0
+```
+
+Expected: non-zero Bun result. The source guard tests remain green; package-script and verify-list assertions fail because the wiring is absent.
+
+- [ ] **Step 3: Add the package scripts**
+
+In `package.json`, add this script alongside the other `check:*` entries:
+
+```json
+"check:engine-dynamic-import": "bash scripts/check-engine-dynamic-import.sh"
+```
+
+Append the guard to the existing `check:all` chain, preserving every existing check:
+
+```text
+&& bash scripts/check-engine-dynamic-import.sh
+```
+
+Do not rewrite any existing shell entry without its `bash` prefix.
+
+- [ ] **Step 4: Add the authoritative verify entry**
+
+In `scripts/run-verify-parallel.sh`, add this stable `CHECKS` entry near the other source-shape guards:
+
+```bash
+  "check:engine-dynamic-import"
+```
+
+- [ ] **Step 5: Run the regression test and package check**
+
+```bash
+bun test test/scripts/check-engine-dynamic-import.test.ts > .context/engine-dynamic-import-wiring-green.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`; the full guard regression suite passes.
+
+```bash
+bun run check:engine-dynamic-import > .context/engine-dynamic-import-package-check.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0` and three files scanned.
+
+- [ ] **Step 6: Commit the wiring locally**
+
+```bash
+git add package.json scripts/run-verify-parallel.sh test/scripts/check-engine-dynamic-import.test.ts
+```
+
+```bash
+git commit -m "test(engine): guard dynamic import policy"
+```
+
+Expected: one local commit with the guard wiring and its regression assertions.
+
+---
+
+### Task 3: Document the current-state invariant
+
+**Files:**
+- Modify: `CLAUDE.md`
+- Modify: `docs/architecture/KEY_FILES.md`
+- Regenerate: `llms.txt`
+- Regenerate: `llms-full.txt`
+
+**Interfaces:**
+- Consumes: the four-marked-import source state and the `check:engine-dynamic-import` package surface.
+- Produces: current-state contributor guidance and fresh generated documentation bundles.
+
+- [ ] **Step 1: Add the cross-cutting invariant to `CLAUDE.md`**
+
+Add this bullet under “Cross-cutting invariants” near the other language/filesystem guards:
+
+```md
+- **Engine-live paths use static imports by default.** In
+  `src/core/pglite-engine.ts`, `src/core/postgres-engine.ts`, and
+  `src/core/migrate.ts`, helper modules are top-level imports. The only current
+  exceptions are the four `ai/gateway.ts` lookups in both engines'
+  `initSchema()` and `_upsertChunksOnce()` methods; each remains lazy inside a
+  local `try/catch` because the gateway has a large provider/config closure and,
+  more importantly, eager evaluation would occur before the catch and could
+  turn a recoverable default/config-row fallback into a module-load failure.
+  Every exception carries `engine-dynamic-import-ok` on the import line.
+  `scripts/check-engine-dynamic-import.sh` enforces the rule. For history, use
+  `git log -G'await[[:space:]]+import\\('`, not `git log -S`: a dynamic-to-static
+  rewrite can preserve the searched token while changing its context.
+```
+
+Do not add release tags, Windows-crash certainty, or historical branch names.
+
+- [ ] **Step 2: Update the PGLite current-state entry in `KEY_FILES.md`**
+
+Append this current-state sentence to the existing `src/core/pglite-engine.ts` entry, preserving the entry as one bullet:
+
+```md
+Engine-path helper dependencies (`retry`, ontology, recency decay) bind statically; the only lazy imports are `ai/gateway.ts` in `initSchema` and `_upsertChunksOnce`, line-marked because their local catches preserve compiled-default and stored-config fallbacks that eager module evaluation would bypass.
+```
+
+- [ ] **Step 3: Update the Postgres current-state entry in `KEY_FILES.md`**
+
+Append this sentence to the existing `src/core/postgres-engine.ts` entry:
+
+```md
+Retry classifiers, ontology/recency helpers, and disconnect/pool-recovery audit writers bind statically; only the two `ai/gateway.ts` fallback lookups stay lazy and line-marked, in parity with PGLite.
+```
+
+- [ ] **Step 4: Update the migration current-state entry in `KEY_FILES.md`**
+
+Append this sentence to the canonical `src/core/migrate.ts` entry (the broad runner entry, not the older v95-specific index note):
+
+```md
+`retry-matcher.ts` and `timeline-dedup-repair.ts` are static dependencies because `runMigrations()` executes from live engine initialization; the engine dynamic-import guard scans this file with both engine implementations.
+```
+
+Keep all three entries current-state only: no `v0.42.x`, branch, commit, “previously,” or “was/now” narration.
+
+- [ ] **Step 5: Regenerate the llms bundles**
+
+```bash
+bun run build:llms > .context/engine-dynamic-import-build-llms.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`; `llms.txt` and/or `llms-full.txt` update according to their configured linked/inlined status. Byte-identical output for a linked source is acceptable; the freshness test is authoritative.
+
+- [ ] **Step 6: Run documentation freshness checks**
+
+```bash
+bun test test/build-llms.test.ts > .context/engine-dynamic-import-llms-test.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`.
+
+```bash
+bun run check:doc-history > .context/engine-dynamic-import-doc-history.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`; no release-history marker is introduced into current-state reference docs.
+
+- [ ] **Step 7: Confirm prohibited release files remain untouched**
+
+```bash
+git diff --name-only d7f52d8c..HEAD -- VERSION CHANGELOG.md TODOS.md
+```
+
+Expected: no output.
+
+- [ ] **Step 8: Commit documentation and generated bundles locally**
+
+```bash
+git add CLAUDE.md docs/architecture/KEY_FILES.md llms.txt llms-full.txt
+```
+
+```bash
+git commit -m "docs(engine): record static import invariant"
+```
+
+Expected: one local documentation commit. If one generated bundle is byte-identical, Git simply omits it.
+
+---
+
+### Task 4: Verify and review the complete local reconciliation
+
+**Files:**
+- Verify all files changed since `d7f52d8c`.
+- Do not create or modify release/publication metadata.
+
+**Interfaces:**
+- Consumes: Tasks 1–3.
+- Produces: full local verification evidence and an implementation diff ready for user review, not publication.
+
+- [ ] **Step 1: Run the regression test and direct guard again**
+
+```bash
+bun test test/scripts/check-engine-dynamic-import.test.ts > .context/engine-dynamic-import-final-test.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`; the full guard regression suite passes.
+
+```bash
+bash scripts/check-engine-dynamic-import.sh > .context/engine-dynamic-import-final-guard.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`; three files scanned.
+
+- [ ] **Step 2: Run TypeScript checking**
+
+```bash
+bun run typecheck > .context/engine-dynamic-import-typecheck.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`. Report exact diagnostics if the branch or current Windows environment has a pre-existing failure.
+
+- [ ] **Step 3: Run the authoritative verify dispatcher**
+
+```bash
+bun run verify > .context/engine-dynamic-import-verify.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`, including `check:engine-dynamic-import`. On Windows, classify any per-check timeout from the complete log instead of treating the aggregate result as a source regression without evidence.
+
+- [ ] **Step 4: Re-run focused tests as an ownership check**
+
+```bash
+bun test test/chronicle-ontology.test.ts test/chronicle-ontology-ops.test.ts test/recency-decay.test.ts test/core/retry.test.ts test/retry-matcher.test.ts test/audit/pool-recovery-audit.test.ts test/migrate-retry.test.ts test/timeline-dedup-repair.test.ts > .context/engine-dynamic-import-final-focused.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`; record any infrastructure abort separately and rerun only the named file before classifying it.
+
+- [ ] **Step 5: Run the llms freshness test after all documentation settles**
+
+```bash
+bun test test/build-llms.test.ts > .context/engine-dynamic-import-final-llms.txt 2>&1; rc=$?; printf 'EXIT=%s\n' "$rc"; exit "$rc"
+```
+
+Expected: exit `0`.
+
+- [ ] **Step 6: Run whitespace and scope checks**
+
+```bash
+git diff --check d7f52d8c..HEAD
+```
+
+Expected: exit `0`, no output.
+
+```bash
+git diff --name-only d7f52d8c..HEAD
+```
+
+Expected files only:
+
+```text
+CLAUDE.md
+docs/architecture/KEY_FILES.md
+docs/superpowers/plans/2026-07-28-engine-dynamic-import-reconciliation.md
+llms-full.txt
+llms.txt
+package.json
+scripts/check-engine-dynamic-import.sh
+scripts/check-engine-dynamic-import.ts
+scripts/run-verify-parallel.sh
+src/core/migrate.ts
+src/core/pglite-engine.ts
+src/core/postgres-engine.ts
+test/scripts/check-engine-dynamic-import.test.ts
+```
+
+Either generated llms file may be absent if regeneration proves it byte-identical. `VERSION`, `CHANGELOG.md`, and `TODOS.md` must be absent.
+
+- [ ] **Step 7: Review the exact implementation diff**
+
+```bash
+git diff --stat d7f52d8c..HEAD && git diff d7f52d8c..HEAD -- src/core/pglite-engine.ts src/core/postgres-engine.ts src/core/migrate.ts scripts/check-engine-dynamic-import.sh test/scripts/check-engine-dynamic-import.test.ts package.json scripts/run-verify-parallel.sh CLAUDE.md docs/architecture/KEY_FILES.md
+```
+
+Expected review findings:
+
+- Exactly 13 safe `await import(...)` statements are removed.
+- Exactly four `ai/gateway.ts` imports remain, all marked on the same line.
+- All four gateway imports remain inside their original local `try/catch` fallback boundaries.
+- No accessor logic, fallback ordering, SQL, public signature, or engine parity behavior changes.
+- The parser-backed guard reports all violations plus read/parse failures, preserves CRLF line accounting, ignores comments/literals/type-only syntax, detects every runtime `import()` call expression, and accepts opt-outs only from real comment trivia on the same physical line.
+- The package script invokes the shell guard through Bash; `check:all` invokes that shell guard directly, and the parallel verify dispatcher invokes the package check.
+- Documentation is current-state and makes no deterministic Windows-crash claim.
+
+**Observed Windows verification classification:** The authoritative aggregate completed with 25 of 33 checks passing. Individual reruns showed `check:test-names` and `typecheck` green; privacy/isolation exceeded Windows timing budgets; WASM failed in unrelated temporary-symlink setup; eval-glossary was CRLF/LF drift; resolver/brain-first findings predated and did not intersect this branch. The focused aggregate produced 103 pass / 5 fail: three setup-hook timeouts reproduced at the untouched base, and the known `migrate-retry` polling failure reproduced there. Its additional race-status assertion did not reproduce at base, so it remains an unresolved timing-sensitive limitation in untouched code—not evidence of an in-scope defect and not claimed as conclusively pre-existing.
+
+- [ ] **Step 8: Commit the approved plan document locally**
+
+The plan is an approved, tracked execution artifact and must not be left as an uncommitted file after implementation:
+
+```bash
+git add docs/superpowers/plans/2026-07-28-engine-dynamic-import-reconciliation.md
+```
+
+```bash
+git commit -m "docs: plan engine dynamic-import reconciliation"
+```
+
+Expected: one local plan commit; no release metadata staged.
+
+- [ ] **Step 9: Inspect final status without publishing**
+
+```bash
+git status --short --branch
+```
+
+Expected: branch `claude/kind-meitner-330c90` with a clean working tree. No push, PR, upstream comment, or other external side effect.
+
+- [ ] **Step 10: Capture the completed milestone to memory**
+
+Before writing, search MemPalace wing `gbrain` for this exact reconciliation to avoid duplication. Add a verbatim drawer recording exact base/head commits, the 13 hoists, four gateway opt-outs and rationale, guard/test/docs files, every verification command with exit code, and any environment-owned failures. Add a GBrain project timeline entry only if there is an existing relevant gbrain project page; do not create duplicate release metadata.
+
+- [ ] **Step 11: Report the local result and ask separately before publication**
+
+Report:
+
+- exact local commits;
+- changed files;
+- test/check exit codes;
+- any blocked or pre-existing failures;
+- confirmation that release files were untouched;
+- confirmation that nothing was pushed or published.
+
+Do not run any publication command. Wait for explicit user approval before any push, PR, or upstream interaction.

docs/superpowers/plans/2026-07-30-scalar-source-backlink-validation.md

@@ -0,0 +1,175 @@
+# Scalar-source Backlink Validation Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Make backlink validation compare exact `(source_id, slug)` endpoint identities while preserving existing scalar, unscoped, and federated link-read semantics.
+
+**Architecture:** Enrich every engine link-read row with the source identity of its joined from, to, and visible origin pages. Pass the validated page's scalar or federated scope into validator context; the backlink validator scopes its initial read consistently, groups targets by exact identity, and accepts only an exact reverse endpoint pair. SQL predicates remain unchanged, so trusted scalar cross-source visibility and federated all-endpoint containment remain intact.
+
+**Tech Stack:** TypeScript, Bun test, PGLite, PostgreSQL/postgres.js.
+
+## Global Constraints
+
+- Use strict red-before-green TDD with duplicate slugs across sources.
+- Preserve unscoped historical reads, scalar near-endpoint scoping, scalar explicit cross-source visibility, federated all-endpoint containment, and `sourceIds` precedence.
+- Keep PostgreSQL and PGLite projections in parity.
+- Do not change schema or conditional-write conflict semantics.
+- Keep deployment, restart, migration, and push actions outside the implementation tasks; a separately authorized release workflow may perform them after verification.
+- Capture full test output to files before inspecting it.
+
+---
+
+### Task 1: Pin the backlink false-negative in PGLite
+
+**Files:**
+- Modify: `test/writer.test.ts`
+
+**Interfaces:**
+- Consumes: `backLinkValidator.validate(PageValidationContext)` and source-qualified `putPage`/`addLink`.
+- Produces: regressions for wrong-source reverse rejection, exact reverse acceptance, cross-source pair acceptance, and exact target deduplication.
+
+- [ ] **Step 1: Add the minimal failing duplicate-slug regression**
+
+Create `default` and `team-x` copies of the origin and target, add `(team-x, origin) -> (team-x, target)` plus the wrong reverse `(team-x, target) -> (default, origin)`, validate with `sourceId: 'team-x'`, and require one warning.
+
+- [ ] **Step 2: Run the focused test and verify RED**
+
+```bash
+bun test test/writer.test.ts -t "wrong-source reverse" > "$TEMP/backlink-red.txt" 2>&1
+```
+
+Expected: assertion failure because current slug-only validation returns zero findings.
+
+- [ ] **Step 3: Add the remaining behavioral regressions after the first red is recorded**
+
+Add tests proving that the exact reverse clears the warning, a legitimate cross-source forward/reverse pair passes, and two destinations sharing one slug but differing by source are validated independently.
+
+### Task 2: Expose exact endpoint identity from both engines
+
+**Files:**
+- Modify: `src/core/types.ts:1204-1229`
+- Modify: `src/core/postgres-engine.ts:3021-3124`
+- Modify: `src/core/pglite-engine.ts:2941-3037`
+- Modify: `test/get-page-federated-scope.test.ts:187-246,289-306`
+- Modify: `test/e2e/multi-source-bug-class.test.ts:184-205`
+- Modify: `test/e2e/engine-parity.test.ts:813-875`
+
+**Interfaces:**
+- Produces: `Link.from_source_id: string`, `Link.to_source_id: string`, and `Link.origin_source_id?: string | null`.
+- Preserves: `getLinks(slug, { sourceId?, sourceIds? })` and `getBacklinks(...)` filtering semantics.
+
+- [ ] **Step 1: Add engine-contract assertions before implementation**
+
+Assert scalar cross-source rows expose `beta -> default`, federated rows expose only in-grant endpoint IDs, `sourceIds` still beats scalar `sourceId`, and an out-of-grant origin has both `origin_slug` and `origin_source_id` null.
+
+- [ ] **Step 2: Run the focused contract tests and verify RED**
+
+```bash
+bun test test/get-page-federated-scope.test.ts test/e2e/multi-source-bug-class.test.ts > "$TEMP/link-identity-red.txt" 2>&1
+```
+
+Expected: source-ID assertions fail because fields are absent.
+
+- [ ] **Step 3: Extend `Link` and project IDs without changing predicates**
+
+Use this additive contract:
+
+```ts
+export interface Link {
+  from_slug: string;
+  from_source_id: string;
+  to_slug: string;
+  to_source_id: string;
+  link_type: string;
+  context: string;
+  link_source?: string | null;
+  origin_slug?: string | null;
+  origin_source_id?: string | null;
+  origin_field?: string | null;
+}
+```
+
+In all six branches per engine, project:
+
+```sql
+f.source_id AS from_source_id,
+t.source_id AS to_source_id,
+o.source_id AS origin_source_id
+```
+
+Keep every `WHERE` and grant-aware origin `LEFT JOIN` unchanged.
+
+- [ ] **Step 4: Re-run contract tests and verify GREEN**
+
+Use the same command and require all focused tests to pass.
+
+### Task 3: Validate exact reverse identities and propagate scope
+
+**Files:**
+- Modify: `src/core/output/writer.ts:89-96,240-318`
+- Modify: `src/core/output/post-write.ts:36-41,73-118`
+- Modify: `src/core/output/validators/back-link.ts:24-47`
+- Modify: `src/core/operations.ts:1227-1246`
+- Modify: `test/post-write-lint.test.ts:67-130`
+
+**Interfaces:**
+- Produces: optional `PageValidationContext.sourceId` and `sourceIds`, with `sourceIds` taking precedence.
+- `runPostWriteLint(..., opts)` accepts the same optional scope and loads the validated page through it.
+
+- [ ] **Step 1: Add a post-write nested-read regression and verify RED**
+
+Validate a non-default page with a wrong-source reverse via `runPostWriteLint(..., { force: true, noLog: true, sourceId: 'team-x' })`; require a backlink warning.
+
+- [ ] **Step 2: Implement minimal scope propagation**
+
+Add `sourceId?`/`sourceIds?` to validation context and lint options. Load pages using `sourceIds` when non-empty, otherwise scalar `sourceId`. Pass the same scope into nested validators. In the put-page success hook, call lint with the already-resolved write source ID.
+
+- [ ] **Step 3: Implement exact backlink matching**
+
+Initial outbound reads use the validation scope. Deduplicate rows by all four endpoint identity fields so every distinct expected origin remains represented even when targets share a source-qualified identity. Read each target using the federated grant when present, otherwise the target's exact scalar source. Accept only a row matching all four endpoint fields of the expected reverse.
+
+- [ ] **Step 4: Run writer and post-write tests and verify GREEN**
+
+```bash
+bun test test/writer.test.ts test/post-write-lint.test.ts > "$TEMP/backlink-green.txt" 2>&1
+```
+
+Expected: all tests pass, including the recorded false-negative.
+
+### Task 4: Verify PostgreSQL/PGLite parity and final scope
+
+**Files:**
+- Modify: `test/e2e/engine-parity.test.ts:813-875`
+- Verify: all files above
+
+**Interfaces:**
+- Consumes: exact endpoint fields and unchanged filtering semantics.
+- Produces: parity evidence for scalar cross-source and federated reads.
+
+- [ ] **Step 1: Compare complete endpoint tuples across engines**
+
+Compare sorted tuples containing `from_source_id`, `from_slug`, `to_source_id`, `to_slug`, `origin_source_id`, and `origin_slug` for scalar and federated fixtures.
+
+- [ ] **Step 2: Run focused PGLite/source-isolation tests**
+
+```bash
+bun test test/writer.test.ts test/post-write-lint.test.ts test/get-page-federated-scope.test.ts test/e2e/multi-source-bug-class.test.ts > "$TEMP/backlink-focused.txt" 2>&1
+```
+
+Expected: exit 0.
+
+- [ ] **Step 3: Run PostgreSQL parity when the test database is available**
+
+```bash
+bun test test/e2e/engine-parity.test.ts -t "federated sourceIds" --timeout=300000 > "$TEMP/backlink-parity.txt" 2>&1
+```
+
+Expected: exit 0; if the configured test database is unavailable, report the exact environmental blocker rather than claiming parity execution.
+
+- [ ] **Step 4: Typecheck and inspect the final diff**
+
+```bash
+bun run typecheck > "$TEMP/backlink-typecheck.txt" 2>&1
+```
+
+Expected: exit 0. Then run `git diff --check` and confirm no version, schema, migration, deployment, or conditional-write files changed.

docs/superpowers/specs/2026-07-28-engine-dynamic-import-reconciliation-design.md

@@ -0,0 +1,142 @@
+# Engine dynamic-import reconciliation design
+
+**Date:** 2026-07-28
+
+## Goal
+
+Reconcile the overlapping engine dynamic-import changes from:
+
+- `claude/hungry-edison-8bb1cd` at release commits `48ada48f` and `248bfe55`
+- `claude/elegant-gates-e5275e` at `ef4cf7a8`
+
+onto a fresh branch from current `origin/master`, without merging or cherry-picking either lineage wholesale and without adding a release/version bump.
+
+## Established state
+
+At investigation time:
+
+- `origin/master` was `6136e139972a5449630b4f47f5ed7b4cbe5b811b`, version `0.42.67.0`.
+- Upstream PR #3511 was still open, so trunk did not contain its two `chronicle/ontology.ts` hoists.
+- Neither source branch was an ancestor of trunk.
+- Trunk contained 17 dynamic imports in the three engine-path files:
+  - 13 safe-hoist candidates: two ontology imports, nine engine helper/audit imports, and two migration imports.
+  - Four `ai/gateway.ts` imports, all inside `try/catch` fallback paths.
+- `git log -G` showed the separate ontology, helper, migration, and gateway histories. `git log -S` is not suitable for this dynamic-to-static replacement because the relevant token can remain present while its context changes.
+- The guard from `ef4cf7a8` passed against that commit but failed against trunk. It also knew about only two gateway opt-outs because two `_upsertChunksOnce` gateway lookups landed later in trunk.
+
+## Selected approach
+
+Reconstruct the intended current state directly on fresh `origin/master`.
+
+Do not merge or cherry-pick either old lineage. Selectively reproduce the desired source changes, adapt the guard to the current four gateway call sites, and write current-state documentation. This avoids importing stale release metadata, stale TODO claims, and unrelated lineage changes.
+
+## Source changes
+
+### Safe static imports
+
+Hoist all 13 safe candidates:
+
+- `src/core/pglite-engine.ts`
+  - `valueHash`, `normalizeDimension`, `isNovelDimension` from `chronicle/ontology.ts`
+  - `isRetryableConnError` through the existing `retry.ts` import
+  - `resolveRecencyDecayMap`, `DEFAULT_FALLBACK` from `search/recency-decay.ts`
+- `src/core/postgres-engine.ts`
+  - the same ontology, retry, and recency helpers
+  - `isConnectionEndedError` from `retry-matcher.ts`
+  - `logDbDisconnect` from `audit/db-disconnect-audit.ts`
+  - `logPoolRecovery` from `audit/pool-recovery-audit.ts`
+- `src/core/migrate.ts`
+  - `isStatementTimeoutError`, `isRetryableConnError` from `retry-matcher.ts`
+  - `repairTimelineDedupIndex` from `timeline-dedup-repair.ts`
+
+The implementation must keep the two engines in parity where the behavior is shared. Comments should describe current invariants, not repeat an unproven causal claim that these hoists fix the Windows test-runner crash.
+
+### Deliberately lazy gateway imports
+
+Keep all four `await import('./ai/gateway.ts')` call sites lazy:
+
+- PGLite `initSchema`
+- PGLite `_upsertChunksOnce`
+- Postgres `initSchema`
+- Postgres `_upsertChunksOnce`
+
+Each line receives the explicit `engine-dynamic-import-ok` marker and a concise nearby rationale.
+
+The rationale has two parts:
+
+1. The gateway's static closure includes the AI SDK, provider packages, and validation/config machinery, so eager loading would tax engine startup paths that do not otherwise need it.
+2. More importantly, each lookup is inside a `try/catch` that preserves a soft fallback (compiled defaults or the brain's stored embedding-model config). Hoisting the module would evaluate it before that catch can run and could convert a recoverable configuration/import failure into a module-load-time hard failure.
+
+The guard must not allow unmarked gateway imports or a broad file-level exemption.
+
+## Guard and wiring
+
+Add `scripts/check-engine-dynamic-import.sh`, adapted from `ef4cf7a8`, with these properties:
+
+- Default scan set:
+  - `src/core/pglite-engine.ts`
+  - `src/core/postgres-engine.ts`
+  - `src/core/migrate.ts`
+- Normalize trailing CR before matching so CRLF checkouts cannot bypass the check.
+- Ignore comment-only lines.
+- Ignore only lines carrying `engine-dynamic-import-ok`.
+- Report every unmarked `await import(` with file and line.
+- Explain that contributors should prefer a static import and must justify a real opt-out.
+- Avoid asserting that every dynamic import deterministically crashes Windows; the measured evidence supports treating the pattern as an engine-path hardening invariant, while box-level commit exhaustion remained a confound in prior runs.
+
+Wire it into:
+
+- `package.json` as `check:engine-dynamic-import`
+- `package.json` `check:all`
+- `scripts/run-verify-parallel.sh`
+
+Follow trunk's current rule that package scripts invoke repository shell scripts through `bash`.
+
+## Regression coverage
+
+Add an automated test for the guard. It must cover:
+
+- A real dynamic import produces exit 1 and is reported.
+- A line carrying `engine-dynamic-import-ok` is allowed.
+- Line comments and block-comment lines do not produce findings.
+- The same violation is caught with CRLF input.
+- The default repository scan passes after the source reconciliation.
+
+Use a temporary fixture rather than mutating tracked source files. Keep assertions path-portable.
+
+The pre-fix red demonstration is the exact guard from `ef4cf7a8` run against current trunk: it exits 1 and reports the existing unmarked imports. The post-fix guard and test must pass.
+
+## Documentation policy
+
+Preserve current behavior, not either old release narrative:
+
+- Do not modify `VERSION` or add a release `CHANGELOG.md` entry.
+- Do not copy old version headings or completed release TODO blocks.
+- Do not retain the old TODO claiming that extracting gateway accessors is necessarily the fix; the lazy imports are deliberately protected by their local soft-failure boundaries.
+- Add the cross-cutting no-unmarked-dynamic-import invariant to `CLAUDE.md`.
+- Update the current-state entries for `src/core/pglite-engine.ts`, `src/core/postgres-engine.ts`, and `src/core/migrate.ts` in `docs/architecture/KEY_FILES.md` where needed.
+- Regenerate `llms.txt` and `llms-full.txt` after the documentation edits.
+- Add a TODO only if implementation uncovers a real unresolved action.
+
+Public documentation must use generic language and must not overstate the historical Windows crash causality.
+
+## Verification
+
+Capture full output to files before inspecting summaries. Run, at minimum:
+
+1. The guard regression test.
+2. `bash scripts/check-engine-dynamic-import.sh`.
+3. Focused tests that exercise the touched engine, migration, retry, audit, and recency modules.
+4. `bun run typecheck`.
+5. `bun run verify`.
+6. `bun run build:llms` followed by `bun test test/build-llms.test.ts`.
+7. `git diff --check` and a final clean-status/diff review.
+
+If platform contention or existing Windows suite defects block a broad test, report the exact command, exit code, and ownership classification rather than declaring success from a partial run.
+
+## Git and publication boundary
+
+- Work on `claude/kind-meitner-330c90`, reset locally to the exact investigated `origin/master` base.
+- Preserve the previous worktree tip under `claude/kind-meitner-330c90-pre-reconcile`.
+- Keep implementation and verification commits local.
+- Do not push, create a PR, comment upstream, or otherwise publish without explicit user approval after the local result is complete.

docs/superpowers/specs/2026-07-30-scalar-source-backlink-validation-design.md

@@ -0,0 +1,184 @@
+# Scalar-source backlink validation design
+
+## Problem
+
+A page identity in a multi-source brain is `(source_id, slug)`, but the back-link validator currently reasons only about `slug`.
+
+For an outbound edge:
+
+```text
+(source-a, concepts/origin) -> (source-a, people/target)
+```
+
+the validator accepts any reverse row whose bare slugs are:
+
+```text
+people/target -> concepts/origin
+```
+
+That can incorrectly accept a row ending at `(default, concepts/origin)` instead of `(source-a, concepts/origin)`.
+
+The bug is not that scalar `getLinks(slug, { sourceId })` permits cross-source destinations. That behavior is intentional: scalar scope qualifies the near/from endpoint while trusted local callers retain visibility into explicit cross-source edges. The gap is that a returned `Link` does not carry the source identity of either endpoint, so callers cannot distinguish same-slug pages.
+
+## Reproduction and evidence
+
+A deterministic PGLite reproduction creates duplicate `concepts/a` and `people/b` pages in `default` and `team-x`, then adds:
+
+```text
+(team-x, concepts/a) -> (team-x, people/b)
+(team-x, people/b) -> (default, concepts/a)
+```
+
+The second edge is not a valid reverse of the first. Nevertheless:
+
+```ts
+await engine.getLinks('people/b', { sourceId: 'team-x' })
+```
+
+returns the second row, and the current validator accepts it because `to_slug === 'concepts/a'`.
+
+Both engines implement the same scalar rule: filter `f.slug` and `f.source_id`, join the actual destination by `to_page_id`, and do not filter `t.source_id`. Federated `sourceIds` is a separate branch that constrains all visible endpoints and takes precedence over scalar scope.
+
+## Goals
+
+1. Validate back-links by exact source-qualified endpoint identity.
+2. Preserve explicit cross-source links for trusted scalar reads.
+3. Preserve federated all-endpoint containment and `sourceIds` precedence.
+4. Keep PostgreSQL and PGLite behavior identical.
+5. Add strict red-before-green regressions using duplicate slugs across sources.
+6. Avoid schema migrations and production operational changes.
+
+## Non-goals
+
+- Changing scalar link reads to same-source-only reads.
+- Weakening or widening federated reads.
+- Changing link write identity or database schema.
+- Refactoring the atomic conditional-write branch.
+- Coupling deployment, restart, or migration mechanics to the backlink code change. Release operations are handled separately after verification.
+
+## Chosen approach
+
+Extend the engine `Link` result with endpoint source identities and use those fields in the validator.
+
+```ts
+interface Link {
+  from_slug: string;
+  from_source_id: string;
+  to_slug: string;
+  to_source_id: string;
+  // existing fields
+  origin_slug?: string | null;
+  origin_source_id?: string | null;
+}
+```
+
+All `getLinks` and `getBacklinks` query branches in PostgreSQL and PGLite will project the source IDs from the pages already joined as `f`, `t`, and `o`. No filtering behavior changes.
+
+This approach is preferred over a dedicated `hasExactLink` method because it keeps source identity attached to the link data everywhere, avoids duplicate engine SQL and per-edge existence queries, and matches existing source-qualified link-write and batch-row contracts.
+
+Validator-only raw SQL is rejected because validators should consume the `BrainEngine` contract rather than bypass it with engine-specific schema knowledge.
+
+## Engine semantics
+
+The existing three read modes remain unchanged.
+
+### Unscoped
+
+`getLinks(slug)` returns rows from all same-slug from-pages across sources. Each row identifies the actual source of both endpoints.
+
+### Scalar source
+
+`getLinks(slug, { sourceId })` matches exactly `(sourceId, slug)` on the from side. A destination may belong to another source, and `to_source_id` reveals that exact identity.
+
+The corresponding scalar `getBacklinks` rule continues to match the exact destination/to-page identity while allowing a cross-source referrer.
+
+### Federated sources
+
+`getLinks(slug, { sourceIds })` continues to constrain from and to endpoints to the grant. The origin join continues to redact an out-of-grant origin. `sourceIds` continues to take precedence over scalar `sourceId`.
+
+Adding source IDs to returned in-grant endpoints does not disclose anything new: the existing result already discloses those pages' slugs and edges. An out-of-grant endpoint remains absent.
+
+## Validator algorithm
+
+The validator receives the source scope associated with the page being validated.
+
+For every outbound edge:
+
+```text
+(from_source_id, from_slug) -> (to_source_id, to_slug)
+```
+
+it requires a reverse row:
+
+```text
+(to_source_id, to_slug) -> (from_source_id, from_slug)
+```
+
+Duplicate edge rows are deduplicated by the full endpoint pair `(from_source_id, from_slug, to_source_id, to_slug)`, not by bare target slug. This preserves separate reverse requirements when multiple same-slug origin pages point to one exact target.
+
+For each target:
+
+1. Read target outbound links using the target's exact scalar source when validation is scalar-scoped.
+2. Under federated validation, retain the caller's `sourceIds` grant rather than converting it to scalar scope.
+3. Accept only a returned row whose `from_source_id`, `from_slug`, `to_source_id`, and `to_slug` exactly match the expected reverse identity.
+4. Emit the existing warning when no exact reverse exists.
+
+This preserves legitimate cross-source pairs. For example:
+
+```text
+(source-a, concepts/origin) -> (source-b, people/target)
+(source-b, people/target) -> (source-a, concepts/origin)
+```
+
+is valid.
+
+## Validation context propagation
+
+`PageValidationContext` must carry the relevant scalar or federated source scope. The writer and post-write lint paths must load the page with that scope and pass the same scope to nested validator reads.
+
+This change is scoped to source routing needed by validation. It does not modify conditional-write revision or conflict semantics and must not be applied to the atomic conditional-write branch.
+
+## Testing strategy
+
+### PGLite strict-TDD regression
+
+Add duplicate pages across `default` and a second source, then prove before the production fix that:
+
+1. A forward edge in the second source plus a wrong-source reverse produces a warning.
+2. Adding the exact reverse removes the warning.
+3. A legitimate cross-source forward/reverse pair passes.
+4. Two same-slug destination pages are not collapsed into one target identity.
+
+The first assertion must fail against the pre-fix implementation.
+
+### Engine contract tests
+
+For PGLite and PostgreSQL:
+
+1. Assert link rows expose exact from/to source IDs.
+2. Assert scalar reads still return explicit cross-source destinations.
+3. Assert federated reads still exclude out-of-grant endpoints.
+4. Assert `sourceIds` still takes precedence over scalar `sourceId`.
+5. Assert origin source identity is null when the origin is redacted by the federated branch.
+
+### Parity and focused verification
+
+Run:
+
+- the focused backlink validator test;
+- source-isolation and federated link tests;
+- the Postgres/PGLite parity fixture with a test database;
+- related writer/post-write tests;
+- `bun run typecheck`.
+
+Capture complete command output to files before inspecting summaries. Do not use production databases or restart the live service.
+
+## Compatibility
+
+The `Link` change is additive at runtime. Existing consumers that read only slug or provenance fields continue to work. TypeScript object literals typed as complete `Link` values may need source fields; if compatibility pressure is high, the source fields can initially be optional in the public type while engine implementations and validator tests require their presence. The preferred contract is required endpoint source IDs because every persisted link always has both pages and therefore both source IDs.
+
+No schema migration is required because source IDs already live on the joined `pages` rows.
+
+## Operational constraints
+
+The implementation phase does not deploy, restart GBrain, run production migrations, or alter the atomic conditional-write branch. Release, migration, and restart operations are a separate verified workflow and do not change this design's engine or validator semantics.

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

@@ -93,7 +93,7 @@ There are two ways to scope teammates' access. They suit different deployment sh
 
 **Model A: separate sources with OAuth scoping (recommended for true multi-user with different AI clients).** What this tutorial walks you through. Each teammate gets their own OAuth client, which carries `--source` + `--federated-read` flags. The brain refuses cross-source reads at the SQL layer; isolation is database-enforced. Each teammate can run their own MCP-aware client (Claude Code, Cursor, their own OpenClaw, etc.) and the scoping holds.
 
-**Model B: one source, directory-based per-person scoping (simpler for one-agent-serves-everyone setups).** The shape I actually run in production: a single source called `default`, with a `partners/<slug>/` convention inside it (e.g. `partners/alice-example/`, `partners/bob-example/`). Each partner gets their own subdirectory holding their personal pages: `partners/alice-example/USER.md`, `partners/alice-example/concepts/`, `partners/alice-example/sources/`, etc. There's no OAuth-enforced isolation; the agent itself enforces "Alice's writes go to her partners/ subdir." This is the right model when ONE agent (yours) serves everyone over Telegram or a single shared interface. It's simpler ops, no per-user OAuth, but the scoping is convention-only.
+**Model B: one source, directory-based per-person scoping (simpler for one-agent-serves-everyone setups).** The shape I actually run in production: a single source called `default`, with a `partners/<slug>/` convention inside it (e.g. `partners/alice-example/`, `partners/bob-example/`). Each partner gets their own subdirectory holding their personal pages: `partners/alice-example/USER.md`, `partners/alice-example/concepts/`, `partners/alice-example/sources/`, etc. This is the right model when ONE agent (yours) serves everyone over Telegram or a single shared interface. It's simpler ops, no per-user OAuth. **Write scoping within the shared source can be server-enforced:** register each per-person client with `--bound-slug-prefixes partners/alice-example/` and every slug-mutating write outside that prefix is rejected with `permission_denied` (v0.42.72.0+). Without the binding, the scoping is convention-only (the agent polices itself). Read scoping stays source-granular in both models — within a shared source, everyone entitled to the source can read every folder.
 
 For most company-brain installs (10+ teammates each with their own AI client), Model A is the right starting point. If you're running the fat-agent-serves-everyone pattern from the personal-brain tutorial, Model B is genuinely simpler. You can also mix: separate sources for the obviously-different ones (customer notes vs internal-only) AND a `partners/<slug>/` convention inside the shared source for per-person workspace.
 
@@ -210,7 +210,7 @@ Each `register-client` command prints a `client_id` and a `client_secret`. Save
 A note on the flags:
 
 - `--scopes read,write` lets the client query the brain and write new pages. You can omit `write` for read-only clients (executive summaries, dashboards). The `admin` scope is needed for operational commands like `gbrain remote doctor` and is usually reserved for your own admin client.
-- `--source` controls write authority. A client can only write to one source. Within that source, your folder convention from Part 3 keeps each person's writes in their own subfolder.
+- `--source` controls write authority. A client can only write to one source. Within that source, your folder convention from Part 3 keeps each person's writes in their own subfolder — and you can make that server-enforced with `--bound-slug-prefixes alice-example/` (v0.42.72.0+): every slug-mutating write op (put_page, delete_page, tags, links, timeline, revert, raw data) outside the bound prefixes is rejected with `permission_denied`. Update the binding later with `gbrain auth rescope-client <id> --bound-slug-prefixes <p1,p2|none>`. **Adding a binding to an existing client narrows it in ways you should expect:** ops that write by something other than a slug (`extract_entities`, `extract_facts`, `forget_fact`, `ontology_propose`, `sources_add`/`sources_remove`) and `POST /ingest` become unavailable to that client, and `put_page`'s automatic fact extraction is skipped — all because none of them can be confined to a prefix. Reads are unaffected. See [the qm-harness guide](../integrations/qm-harness.md) for the full model.
 - `--federated-read` controls read scope. A client can read from one or more sources.
 
 ### Verify the scoping actually scopes
@@ -554,7 +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

@@ -216,6 +216,19 @@ Per-file detail is in `docs/architecture/KEY_FILES.md`.
   text, the cast parses it). Guarded by `scripts/check-jsonb-pattern.sh` (template grep) +
   `scripts/check-jsonb-params.mjs` (positional AST scanner); the real backstop is the DATABASE_URL-gated
   e2e parity tests, since PGLite can't surface the bug. Full rule in `docs/ENGINES.md`.
+- **Engine-live paths avoid runtime dynamic `import()` for helper dependencies.** In
+  `src/core/pglite-engine.ts`, `src/core/postgres-engine.ts`, and
+  `src/core/migrate.ts`, dependencies previously reached through runtime dynamic
+  imports use static top-level imports. The only current dynamic-`import()` exceptions
+  are the four `ai/gateway.ts` lookups in both engines'
+  `initSchema()` and `_upsertChunksOnce()` methods; each remains lazy inside a
+  local `try/catch` because the gateway has a large provider/config closure and,
+  more importantly, eager evaluation would occur before the catch and could
+  turn a recoverable default/config-row fallback into a module-load failure.
+  Every exception carries `engine-dynamic-import-ok` on the import line.
+  `scripts/check-engine-dynamic-import.sh` enforces the rule. For history, use
+  `git log -G'await[[:space:]]+import\\('`, not `git log -S`: a dynamic-to-static
+  rewrite can preserve the searched token while changing its context.
 - **Engine parity.** `src/core/postgres-engine.ts` and `src/core/pglite-engine.ts` move in
   lockstep — a new method/SQL shape lands in BOTH, pinned by `test/e2e/engine-parity.test.ts`.
   Forward-referenced columns/indexes go in the bootstrap probe set (guarded by
@@ -1006,6 +1019,13 @@ If you fetched this file by URL without cloning yet, the companion files live at
 
 ## Step 1: Install GBrain
 
+> **NEVER install from the npm registry.** GBrain is not distributed on npm; the npm
+> package named `gbrain` is an unrelated package. Do NOT run `npm install -g gbrain` or
+> `bun add -g gbrain` (note the missing `github:` prefix — that's the trap). The only
+> supported sources are `github:garrytan/gbrain` and a git clone, exactly as shown below.
+> If an unrelated npm install is already present, remove it first
+> (`npm uninstall -g gbrain` / `bun remove -g gbrain`); `gbrain doctor` also detects this.
+
 Default path (Bun is required — gbrain is a Bun + TypeScript runtime):
 
 ```bash
@@ -1559,6 +1579,16 @@ This is the difference between a search engine and a brain. Search finds the pag
 
 ## Install
 
+> [!WARNING]
+> **GBrain is NOT distributed on npm.** The npm package named `gbrain` is an unrelated
+> package with no connection to this project. Do not run `npm install -g gbrain` or
+> `bun add -g gbrain` — you'll get something else, and it can shadow the real binary on
+> your PATH. Install and upgrade ONLY via the documented paths below
+> (`bun install -g github:garrytan/gbrain`, or `git clone` + `bun install && bun link`).
+> If you already ran the npm install by mistake: `npm uninstall -g gbrain` /
+> `bun remove -g gbrain`, then reinstall from GitHub. `gbrain doctor` detects a
+> shadowing npm install and prints the fix.
+
 GBrain is designed to be installed and operated by an AI agent. The fastest path is to have your agent do it for you. The CLI and MCP paths below are for people who want to wire it up themselves.
 
 ### Have your agent install it (recommended)
@@ -1700,7 +1730,7 @@ Most personal-knowledge tools force one fixed layout: their idea of "notes" + "p
 **gbrain doesn't have a fixed layout.** It ships with bundled schema packs and lets you author your own when none fit:
 
 - **`gbrain-base-v2`** (default as of v0.41.22) — 15-type DRY/MECE canonical taxonomy (14 canonical + `note` catch-all): `person`, `company`, `media`, `tweet`, `social-digest`, `analysis`, `atom`, `concept`, `source`, `deal`, `email`, `slack`, `writing`, `project`, `note`. Subtypes/format/origin pushed to frontmatter. The taxonomy that responds to issue #1479.
-- **`gbrain-base`** (legacy, v0.41 and earlier brains) — the original 24-type layout. Stays bundled for back-compat; brains on it can upgrade via `gbrain onboard --check --explain` → `gbrain jobs submit unify-types --allow-protected --params '{"target_pack":"gbrain-base-v2"}'`.
+- **`gbrain-base`** (legacy, v0.41 and earlier brains) — the original 24-type layout. Stays bundled for back-compat; brains on it can upgrade via `gbrain onboard --check --explain` → `gbrain jobs submit unify-types --allow-protected --params '{"target_pack":"gbrain-base-v2","apply":true}'` (omit `"apply":true` for a dry-run preview — that is the default).
 - **`gbrain-recommended`** — extends `gbrain-base` with the 13 additional directories from `docs/GBRAIN_RECOMMENDED_SCHEMA.md` (source, place, trip, conversation, personal, civic, project, etc.). Activate with `gbrain schema use gbrain-recommended`.
 - **Your own pack** — `gbrain schema detect` clusters your actual filesystem into proposed types, `gbrain schema suggest` runs an LLM pass over them, and `gbrain schema review-candidates --apply` promotes the ones you like. Three commands and the brain knows your shape. Authoring a successor pack (declares `migration_from:` so existing brains can opt in): see [`docs/architecture/pack-upgrade-mechanism.md`](docs/architecture/pack-upgrade-mechanism.md).
 
@@ -2316,7 +2346,7 @@ 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 +2376,7 @@ 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 +2457,7 @@ 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 +3927,7 @@ 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

package.json

@@ -48,7 +48,8 @@
     "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:engine-dynamic-import": "bash scripts/check-engine-dynamic-import.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 && bash scripts/check-engine-dynamic-import.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",
@@ -74,6 +75,7 @@
     "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:skills-manifest": "bash scripts/check-skills-manifest-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",
@@ -146,16 +148,16 @@
     "bun": ">=1.3.10"
   },
   "license": "MIT",
-  "version": "0.42.67.0",
+  "version": "0.42.73.0",
   "overrides": {
     "@hono/node-server": "^2.0.5",
-    "fast-uri": "^3.1.4",
+    "fast-uri": "^3.1.5",
     "body-parser": "^2.3.0",
     "fast-xml-builder": "^1.1.7",
     "fast-xml-parser": "^5.7.0",
     "form-data": "^4.0.6",
-    "hono": "^4.12.25",
-    "ip-address": "^10.1.1",
+    "hono": "^4.12.34",
+    "ip-address": "^10.3.1",
     "qs": "^6.15.2",
     "js-yaml": "^3.15.0"
   }

recipes/calendar-to-brain.md

@@ -1,7 +1,7 @@
 ---
 id: calendar-to-brain
 name: Calendar-to-Brain
-version: 0.7.0
+version: 0.8.0
 description: Google Calendar events become searchable brain pages. Daily files with attendees, locations, and meeting prep context.
 category: sense
 requires: [credential-gateway]
@@ -28,6 +28,11 @@ health_checks:
       - type: env_exists
         name: GOOGLE_CLIENT_ID
         label: "Google OAuth"
+  - type: heartbeat_max_age
+    max_age: 48h
+    label: "Calendar data freshness"
+output_paths:
+  - daily/calendar/
 setup_time: 20 min
 cost_estimate: "$0 (both options are free)"
 ---

recipes/x-to-brain.md

@@ -1,12 +1,12 @@
 ---
 id: x-to-brain
 name: X-to-Brain
-version: 0.8.2
+version: 0.8.3
 description: Twitter timeline, mentions, and keyword monitoring flow into brain pages. Tracks deletions, engagement velocity, OCR on images, and real-time alerts.
 category: sense
 requires: []
 secrets:
-  - name: X_BEARER_TOKEN
+  - name: X_API_BEARER_TOKEN
     description: X API v2 Bearer token (Basic tier minimum, $200/mo for full archive search)
     where: https://developer.x.com/en/portal/dashboard — create a project + app, copy the Bearer Token from "Keys and tokens"
   - name: X_HANDLE
@@ -16,7 +16,7 @@ health_checks:
   - type: http
     url: "https://api.x.com/2/users/by/username/$X_HANDLE"
     auth: bearer
-    auth_token: "$X_BEARER_TOKEN"
+    auth_token: "$X_API_BEARER_TOKEN"
     label: "X API"
 setup_time: 15 min
 cost_estimate: "$0-200/mo (Free tier: 1 app, read-only. Basic: $200/mo for search + higher limits)"
@@ -118,11 +118,11 @@ Tell the user:
 Note: Free tier gives read-only access with low limits. Basic tier ($200/mo)
 gives search/recent endpoint and higher limits. Pro tier gets full archive search."
 
-Set both `X_BEARER_TOKEN` and `X_HANDLE` in the environment. Validate immediately
+Set both `X_API_BEARER_TOKEN` and `X_HANDLE` in the environment. Validate immediately
 (app-only bearer tokens cannot call `/users/me` — that endpoint requires
 user-context OAuth — so validation uses the by-username lookup):
 ```bash
-curl -sf -H "Authorization: Bearer $X_BEARER_TOKEN" \
+curl -sf -H "Authorization: Bearer $X_API_BEARER_TOKEN" \
   "https://api.x.com/2/users/by/username/$X_HANDLE" \
   && echo "PASS: X API connected" \
   || echo "FAIL: X API token invalid"
@@ -138,7 +138,7 @@ starting with 'AAA...', (3) if you just created the app, the token is valid imme
 
 ```bash
 # Look up the user's X user ID from their handle
-curl -sf -H "Authorization: Bearer $X_BEARER_TOKEN" \
+curl -sf -H "Authorization: Bearer $X_API_BEARER_TOKEN" \
   "https://api.x.com/2/users/by/username/$X_HANDLE" | grep -o '"id":"[^"]*"'
 ```
 
@@ -210,7 +210,7 @@ The agent should review collected data 2-3x daily and run enrichment.
 
 ```bash
 mkdir -p ~/.gbrain/integrations/x-to-brain
-echo '{"ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","event":"setup_complete","source_version":"0.8.2","status":"ok","details":{"user_id":"X_USER_ID"}}' >> ~/.gbrain/integrations/x-to-brain/heartbeat.jsonl
+echo '{"ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","event":"setup_complete","source_version":"0.8.3","status":"ok","details":{"user_id":"X_USER_ID"}}' >> ~/.gbrain/integrations/x-to-brain/heartbeat.jsonl
 ```
 
 ## Production Patterns (v0.8.1)
@@ -438,6 +438,14 @@ Free tier works for personal monitoring. Basic tier needed for keyword search.
 
 ## Troubleshooting
 
+**Upgrading from recipe v0.8.2 or earlier (token shows [missing] after upgrade):**
+- Older versions of this recipe named the token `X_BEARER_TOKEN`. The canonical
+  name is `X_API_BEARER_TOKEN` — the name the built-in `x_handle_to_tweet`
+  resolver reads. Rename the variable wherever you set it (shell profile, cron
+  environment, `.env`) — same value, new name. A collector installed under the
+  old name keeps running either way; the rename is what makes the integrations
+  dashboard and the resolver see the token.
+
 **API returns 403:**
 - Check your app has the right access level (Read or Read+Write)
 - Free tier apps can only use basic endpoints

scripts/changelog-entry.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+# Print the CHANGELOG.md body for one version (Keep-a-Changelog format),
+# without its `## [X.Y.Z.W] - date` header line. Used by
+# .github/workflows/release.yml as the GitHub release notes; tested by
+# test/release-workflow.test.ts.
+#
+# Usage: changelog-entry.sh <version> [changelog-file]
+# Exits 1 when the version has no entry (caller falls back to a link stub).
+set -euo pipefail
+
+ver="${1:?usage: changelog-entry.sh <version> [changelog-file]}"
+file="${2:-CHANGELOG.md}"
+
+# Exact-string prefix match on "## [<ver>]" — no regex, so dots in the
+# version can't glob and a 3-segment version can't match a 4-segment header.
+awk -v ver="$ver" '
+  index($0, "## [" ver "]") == 1 { found = 1; next }
+  found && /^## \[/ { exit }
+  found { print }
+  END { exit found ? 0 : 1 }
+' "$file"

scripts/check-bun-test-timeout.sh

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+# CI guard: every `bun test` invocation in workflows and runner scripts must
+# pass an explicit --timeout.
+#
+# Why: bun ignores bunfig.toml's `timeout` key (verified on 1.3.14), so a bare
+# `bun test` gets the 5000ms default for BOTH tests and beforeAll/beforeEach/
+# afterAll/afterEach hooks. Hooks do NOT inherit a test's third-arg timeout —
+# a file whose tests all declare `}, 30_000)` still has a 5s hook budget, and
+# slow setup (Postgres connect + migrations, PGLite cold start) flakes on
+# loaded CI runners with the signature `(unnamed) [5001ms] ... hook timed out`
+# (the #3545 jsonb-parity failure). The CLI --timeout flag is the one measured
+# mechanism that raises the hook budget uniformly; per-hook second-arg
+# timeouts work too but don't scale to ~400 slow hooks.
+#
+# Usage: scripts/check-bun-test-timeout.sh
+# Exit:  0 when clean, 1 when a bare `bun test` invocation is found.
+
+set -euo pipefail
+
+ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
+cd "$ROOT"
+
+# Match executable `bun test` invocations. Exclude comment lines (#, //, *)
+# and lines that already carry --timeout anywhere.
+# Scope: workflows + runner scripts (the surfaces CI executes). package.json
+# script bodies route through scripts/ already; editing it is out of scope here.
+violations="$(grep -rnE '\bbun test\b' .github/workflows scripts 2>/dev/null \
+  | grep -v -- '--timeout' \
+  | grep -vE ':[[:space:]]*(#|//|\*)' \
+  | grep -v 'check-bun-test-timeout' \
+  || true)"
+
+if [ -n "$violations" ]; then
+  echo "FAIL: bare 'bun test' without --timeout (5s default kills slow setup hooks):" >&2
+  echo "$violations" >&2
+  echo "" >&2
+  echo "Add --timeout=60000 (see scripts/run-unit-shard.sh for the convention)." >&2
+  exit 1
+fi
+
+echo "OK: every bun test invocation passes an explicit --timeout."

scripts/check-engine-dynamic-import.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+# Engine-live paths use static imports by default. A line-level
+# `engine-dynamic-import-ok` marker is required for a justified lazy import.
+#
+# Historical Windows runs associated imports on these paths with abrupt Bun
+# test-process exits, but system-wide commit exhaustion remained a confound.
+# This guard therefore enforces a reviewed engine-path hardening invariant; it
+# does not claim every dynamic import deterministically crashes Windows.
+#
+# Usage:
+#   bash scripts/check-engine-dynamic-import.sh
+#   bash scripts/check-engine-dynamic-import.sh FILE [FILE...]
+
+set -uo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)" || exit 1
+
+if [ "$#" -gt 0 ]; then
+  FILES=("$@")
+else
+  ROOT="$(git -C "$SCRIPT_DIR/.." rev-parse --show-toplevel 2>/dev/null || true)"
+  [ -n "$ROOT" ] || ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+  cd "$ROOT" || exit 1
+  FILES=(
+    src/core/pglite-engine.ts
+    src/core/postgres-engine.ts
+    src/core/migrate.ts
+  )
+fi
+
+exec bun "$SCRIPT_DIR/check-engine-dynamic-import.ts" "${FILES[@]}"

scripts/check-engine-dynamic-import.ts

@@ -0,0 +1,80 @@
+#!/usr/bin/env bun
+
+import { readFile } from 'node:fs/promises';
+import ts from 'typescript';
+
+const MARKER = 'engine-dynamic-import-ok';
+const MARKER_TOKEN_CHAR = /[\p{ID_Continue}$-]/u;
+const files = process.argv.slice(2);
+const violations: string[] = [];
+const readErrors: string[] = [];
+
+for (const file of files) {
+  let sourceText: string;
+  try {
+    sourceText = await readFile(file, 'utf8');
+  } catch (error) {
+    const detail = error instanceof Error ? error.message : String(error);
+    readErrors.push(`ERROR: cannot read input file ${file}: ${detail}`);
+    continue;
+  }
+
+  const sourceFile = ts.createSourceFile(
+    file,
+    sourceText,
+    ts.ScriptTarget.Latest,
+    true,
+    ts.ScriptKind.TS,
+  );
+  const lines = sourceText.split(/\r?\n/);
+  const markerLines = new Set<number>();
+
+  if (sourceFile.parseDiagnostics.length > 0) {
+    const diagnostics = sourceFile.parseDiagnostics
+      .map((diagnostic) => ts.flattenDiagnosticMessageText(diagnostic.messageText, ' '))
+      .join('; ');
+    readErrors.push(`ERROR: cannot parse input file ${file}: ${diagnostics}`);
+  }
+
+  for (let markerPos = sourceText.indexOf(MARKER); markerPos >= 0; markerPos = sourceText.indexOf(MARKER, markerPos + MARKER.length)) {
+    const before = Array.from(sourceText.slice(0, markerPos)).at(-1);
+    const after = Array.from(sourceText.slice(markerPos + MARKER.length))[0];
+    const standaloneMarker = (!before || !MARKER_TOKEN_CHAR.test(before))
+      && (!after || !MARKER_TOKEN_CHAR.test(after));
+    const token = ts.getTokenAtPosition(sourceFile, markerPos);
+    const insideToken = token.getStart(sourceFile) <= markerPos && markerPos < token.end;
+    if (standaloneMarker && !insideToken) {
+      markerLines.add(sourceFile.getLineAndCharacterOfPosition(markerPos).line);
+    }
+  }
+
+  function visit(node: ts.Node): void {
+    if (ts.isCallExpression(node) && node.expression.kind === ts.SyntaxKind.ImportKeyword) {
+      const { line } = sourceFile.getLineAndCharacterOfPosition(node.expression.getStart(sourceFile));
+      const sourceLine = lines[line] ?? '';
+      if (!markerLines.has(line)) {
+        violations.push(`  ${file}:${line + 1}:${sourceLine}`);
+      }
+    }
+    ts.forEachChild(node, visit);
+  }
+
+  visit(sourceFile);
+}
+
+for (const error of readErrors) console.error(error);
+
+if (violations.length > 0) {
+  console.error('ERROR: unreviewed dynamic import on an engine-live path:');
+  console.error();
+  console.error(violations.join('\n'));
+  console.error();
+  console.error('Prefer a static top-level import. If lazy loading is load-bearing,');
+  console.error("append 'engine-dynamic-import-ok' to that exact line and document");
+  console.error('the startup or soft-failure boundary that requires it.');
+  process.exit(1);
+}
+
+if (readErrors.length > 0) process.exit(1);
+
+console.log(`check-engine-dynamic-import: ok (${files.length} file(s) scanned)`);

scripts/check-skills-manifest-fresh.sh

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+# CI guard for skills/skills.lock.json freshness (#159).
+#
+# Mirrors scripts/check-eval-glossary-fresh.sh: regenerate the manifest into
+# a tmp file, diff against the committed version, fail the build if they
+# drift. Tamper-evidence, not a signature system — the point is that any
+# change under skills/ ships with an explicit manifest diff.
+#
+# Run: bash scripts/check-skills-manifest-fresh.sh
+# Wired through `bun run verify` (scripts/run-verify-parallel.sh) so PRs that
+# edit skills/ without regenerating the manifest are caught before review.
+
+set -euo pipefail
+
+REPO_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
+COMMITTED="$REPO_ROOT/skills/skills.lock.json"
+TMP="$(mktemp)"
+trap 'rm -f "$TMP"' EXIT
+
+if [ ! -f "$COMMITTED" ]; then
+  echo "ERROR: $COMMITTED not found." >&2
+  echo "Run: bun run scripts/generate-skills-manifest.ts" >&2
+  exit 1
+fi
+
+cd "$REPO_ROOT"
+# Render directly via bun + a one-liner that exposes the module function.
+bun -e "import { renderSkillsManifest } from './src/core/skills-integrity.ts'; process.stdout.write(renderSkillsManifest('skills'));" > "$TMP"
+
+if ! diff -q "$COMMITTED" "$TMP" >/dev/null 2>&1; then
+  echo "ERROR: skills/skills.lock.json is stale." >&2
+  echo "" >&2
+  echo "Diff between committed and freshly-generated:" >&2
+  echo "" >&2
+  diff -u "$COMMITTED" "$TMP" >&2 || true
+  echo "" >&2
+  echo "To regenerate: bun run scripts/generate-skills-manifest.ts" >&2
+  exit 1
+fi
+
+echo "✓ skills/skills.lock.json is fresh"

scripts/envelope-to-gbrain.mjs

@@ -0,0 +1,121 @@
+#!/usr/bin/env node
+/**
+ * Import an envelope-v0 file (a JSON serialization of AI chat history; format
+ * spec: github.com/memvelope/memvelope) into a brain repo as one Markdown page
+ * per conversation, which `gbrain sync` ingests.
+ *
+ * Usage:
+ *   node scripts/envelope-to-gbrain.mjs <envelope.mve.json> [outDir]
+ *
+ * Zero dependencies. Deterministic. No network. It does NOT call gbrain — it
+ * only writes Markdown files.
+ *
+ * Output layout:
+ *   - One page per conversation, filename = date + conversation id (shared
+ *     titles cannot collide; the id is the natural key). A duplicate id
+ *     overwrites its own filename and warns on stderr; stdout reports DISTINCT
+ *     files written, not write calls.
+ *   - Frontmatter: `type: conversation` (keeps pages eligible for
+ *     conversation-facts extraction and chronicle behavior after sync), the
+ *     source provider, the conversation id, and `origin: memvelope/envelope-v0`.
+ *   - Page `date` is the first 10 chars of the conversation's ISO-8601
+ *     `created_at`. Body keeps message-id citations beside each speaker turn.
+ *
+ * Memory: the whole envelope is held in memory (no streaming); envelopes are
+ * far smaller than the vendor exports they serialize.
+ *
+ * Verify:
+ *   node scripts/envelope-to-gbrain.mjs test/fixtures/memvelope/sample.mve.json /tmp/out
+ *     -> expect "wrote 1 markdown page(s)"
+ *   bun test test/envelope-to-gbrain.test.ts
+ *
+ * STATUS: live-verified against gbrain v0.42.56.0 on 2026-07-03: the sample
+ * fixture -> 1 page; a real 662MB Claude export -> 353 conversations = 353
+ * distinct pages (no collisions), searchable after sync with provenance and
+ * message-id citations intact.
+ */
+
+import { readFileSync, writeFileSync, mkdirSync } from 'node:fs';
+import { join } from 'node:path';
+
+const [, , envelopePath, outDir = './brain/conversations'] = process.argv;
+if (!envelopePath) {
+  console.error('usage: node envelope-to-gbrain.mjs <envelope.mve.json> [outDir]');
+  process.exit(1);
+}
+
+const env = JSON.parse(readFileSync(envelopePath, 'utf8'));
+if (env.memvelope !== 'envelope-v0') {
+  console.error(`not an envelope-v0 file (memvelope field = ${JSON.stringify(env.memvelope)})`);
+  process.exit(1);
+}
+
+const slug = (s, fallback) =>
+  (String(s || '').toLowerCase().replace(/[^a-z0-9]+/g, '-').replace(/^-+|-+$/g, '') || fallback).slice(0, 60);
+
+mkdirSync(outDir, { recursive: true });
+const filesWritten = new Set();
+let collisions = 0;
+const conversations = env.conversations || [];
+for (const [i, c] of conversations.entries()) {
+  const date = (c.created_at || '').slice(0, 10);
+  // Name the file by the conversation's own id — the natural unique key — so two
+  // conversations that share a date and title can never silently overwrite each
+  // other. The date only leads as a human/chronological sort prefix; the id
+  // carries uniqueness. Positional fallback keeps names unique and deterministic
+  // when an envelope omits an id.
+  // One predicate for "this conversation carries its own id", shared by the
+  // filename and the frontmatter below. Keeping it in a single place is what
+  // stops the two from disagreeing about whether an id exists.
+  const hasId = typeof c.id === 'string' && c.id.trim() !== '';
+  const convId = hasId ? c.id.trim() : `conv-${i + 1}`;
+  // `date` is third-party, exactly like `convId`, so it gets the same slug()
+  // treatment. Interpolating it raw let a `created_at` of `../…` resolve the
+  // join below outside outDir and write there.
+  const name = `${slug(date, '0000-00-00')}-${slug(convId, `conv-${i + 1}`)}.md`;
+  // gbrain reads YAML frontmatter + markdown body; keep provenance in frontmatter.
+  // Emit `type: conversation` so gbrain stores these as conversation pages rather
+  // than defaulting to the generic `concept`. gbrain is open-typed — it takes an
+  // explicit frontmatter `type` verbatim — and its conversation-aware features
+  // (conversation-facts extraction, the conversation_format_coverage check,
+  // chronicle eligibility) key off `type == 'conversation'`.
+  const front = [
+    '---',
+    'type: conversation',
+    // Every interpolated value below is quoted. An envelope is a third-party
+    // file, so any string carrying a newline would otherwise close its scalar
+    // and inject arbitrary frontmatter keys into the page gbrain ingests — or
+    // duplicate an existing key, which makes the parse throw and silently
+    // strips every provenance field from the page.
+    `title: ${JSON.stringify(c.title || 'Untitled conversation')}`,
+    // `date` is the first 10 chars of the envelope's `created_at`; 10 is plenty
+    // to smuggle a newline plus a short key. Absent stays an unquoted YAML null.
+    `date: ${date ? JSON.stringify(date) : 'null'}`,
+    `source: ${JSON.stringify(env.meta?.source_provider || 'unknown')}`,
+    // Omit the key entirely when the envelope carries no id, rather than
+    // emitting the literal `undefined` or a synthesized `conv-N` — the positional
+    // fallback names the file, but it is not a memvelope conversation id and
+    // must not be recorded as one.
+    ...(hasId ? [`memvelope_conversation_id: ${JSON.stringify(convId)}`] : []),
+    'origin: memvelope/envelope-v0',
+    '---',
+    '',
+  ].join('\n');
+  const body = (c.messages || [])
+    .map((m) => `**${m.role === 'user' ? 'Me' : 'Assistant'}** (${m.ts || 'no timestamp'} · ${m.id}):\n\n${m.text}`)
+    .join('\n\n---\n\n');
+  // Never lose a page silently: if two conversations still map to the same
+  // filename (e.g. an envelope carrying duplicate ids), warn loudly instead of
+  // overwriting in silence, and report the count of DISTINCT files written — not
+  // the number of write calls, which is what hid the old title-collision bug.
+  if (filesWritten.has(name)) {
+    collisions += 1;
+    console.warn(`warning: filename collision on "${name}" — conversation id ${JSON.stringify(c.id)} is not unique; overwriting the earlier page.`);
+  }
+  writeFileSync(join(outDir, name), front + `# ${c.title || 'Conversation'}\n\n` + body + '\n');
+  filesWritten.add(name);
+}
+console.log(`wrote ${filesWritten.size} markdown page(s) to ${outDir} — point gbrain's sync at this directory.`);
+if (collisions) {
+  console.warn(`warning: ${collisions} filename collision(s) — ${collisions} page(s) overwritten. Deduplicate conversation ids in the envelope to avoid data loss.`);
+}

scripts/generate-skills-manifest.ts

@@ -0,0 +1,24 @@
+#!/usr/bin/env bun
+/**
+ * Regenerates skills/skills.lock.json — the tamper-evidence manifest mapping
+ * every bundled file under skills/ to its sha256 (#159). Not a signature
+ * system: it turns silent skill edits into explicit diffs. `gbrain doctor`
+ * warns (never fails) on drift; scripts/check-skills-manifest-fresh.sh keeps
+ * the committed manifest in sync in CI.
+ *
+ * Run after any change under skills/:
+ *   bun run scripts/generate-skills-manifest.ts
+ */
+import { writeFileSync } from 'node:fs';
+import { dirname, join } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import {
+  SKILLS_MANIFEST_FILENAME,
+  renderSkillsManifest,
+} from '../src/core/skills-integrity.ts';
+
+const repoRoot = join(dirname(fileURLToPath(import.meta.url)), '..');
+const skillsDir = join(repoRoot, 'skills');
+const outPath = join(skillsDir, SKILLS_MANIFEST_FILENAME);
+writeFileSync(outPath, renderSkillsManifest(skillsDir));
+console.log(`Wrote ${outPath}`);

scripts/pr-gate.d.mts

@@ -0,0 +1,97 @@
+/** Type surface of scripts/pr-gate.mjs for test/pr-gate-workflow.test.ts (tsc-only). */
+export interface TitleCheck {
+  ok: boolean;
+  reason?: string;
+}
+export declare function checkTitle(title: string): TitleCheck;
+
+export interface ChangedFile {
+  filename: string;
+  status: string;
+  patch?: string;
+  additions?: number;
+  deletions?: number;
+}
+export interface RedFlag {
+  id: string;
+  detail: string;
+}
+export declare function detectRedFlags(input: {
+  changedFiles: number;
+  files: ChangedFile[];
+  diff: string;
+}): RedFlag[];
+
+export declare const RUBRIC: string;
+export declare const MAX_STRING: number;
+export declare const MAX_ITEMS: number;
+export declare const NET_SOURCE_LINE_LIMIT: number;
+export declare const DOWNGRADE_FLAG_IDS: string[];
+
+/** CONTRIBUTING.md #3745: human-written intent paragraph + screenshot of gbrain in use. */
+export declare const CONTRIBUTING_URL: string;
+export declare const INTENT_MIN_WORDS: number;
+export declare const POLICY_FLAG_IDS: string[];
+export declare const POLICY_SCAN_MAX: number;
+export declare const POLICY_EXEMPT_ASSOCIATIONS: string[];
+export declare const AI_INTENT_DOWNGRADE: string;
+export declare function stripCodeFences(body: unknown): string;
+export declare const MODEL_BODY_MAX: number;
+export declare function modelBody(pr: { body?: string } | null | undefined): string;
+export declare function hasScreenshot(body: unknown): boolean;
+export declare function intentWordCount(body: unknown): number;
+export declare function hasIntentParagraph(body: unknown): boolean;
+export declare function detectPolicyMisses(body: unknown): RedFlag[];
+
+export declare function sanitizeModelText(value: unknown, max?: number): string;
+export declare function sanitizeList(value: unknown, maxItems?: number, maxString?: number): string[];
+
+export declare function applyMechanicalDowngrades(
+  lane: string,
+  flags: RedFlag[],
+  intentAuthenticity?: string,
+): { lane: string; downgrades: string[] };
+
+/** The pr.json fields the #3745 exemption reads (all GitHub-computed). */
+export interface PrIdentity {
+  author_association?: string;
+  draft?: boolean;
+  user?: { type?: string; login?: string };
+}
+export declare function policyExemption(pr: PrIdentity | null | undefined): string | null;
+
+export interface GhComment {
+  id?: number;
+  body?: unknown;
+  user?: { type?: string; login?: string };
+}
+export declare function isOwnComment(comment: GhComment | null | undefined): boolean;
+
+export declare function hashInputs(
+  pr: PrIdentity & { title?: string; body?: string; head?: { sha?: string } },
+  /** The assembled model payload (changed files + diff). runGate always passes it. */
+  payload?: string,
+): string;
+export declare function parseState(body: unknown): { hash: string; lane?: string } | null;
+
+export declare function renderComment(input: {
+  lane?: string;
+  verdict?: { confidence?: number; reasons?: unknown; reviewer_checklist?: unknown };
+  titleCheck: TitleCheck;
+  flags: RedFlag[];
+  neutralReason?: string;
+  downgrades?: string[];
+  policyMisses?: RedFlag[];
+  policyExempt?: string | null;
+  labelsCleared?: boolean;
+  state?: { hash: string; lane: string };
+}): string;
+
+export declare function runGate(
+  dir: string,
+  env?: Record<string, string | undefined>,
+  fetchImpl?: typeof fetch,
+): Promise<number>;
+
+export declare function isPermissionFailure(err: unknown): boolean;
+export declare const PERMISSION_HELP: (msg: string) => string;

scripts/run-e2e.sh

@@ -162,8 +162,9 @@ for f in "${files[@]}"; do
   if [ -n "${DATABASE_URL:-}" ]; then
     psql "$DATABASE_URL" -At -c "SELECT pg_terminate_backend(pid) FROM pg_stat_activity WHERE pid != pg_backend_pid() AND datname = current_database()" >/dev/null 2>&1 || true
   fi
-  # Hard outer timeout (180s per file). bun's --timeout is per-test; if a
-  # PGLite WASM call hangs in beforeAll/afterAll, --timeout never fires and
+  # Hard outer timeout (180s per file). bun's --timeout covers tests AND
+  # hooks (measured on 1.3.14), but it's timer-based: a PGLite WASM call
+  # that blocks the event loop synchronously never lets the timer fire and
   # the file wedges indefinitely. gtimeout/timeout SIGKILLs the file so the
   # suite advances. gtimeout (macOS via coreutils) preferred; timeout (Linux)
   # fallback; bare bun (no outer cap) if neither is installed.

scripts/run-unit-parallel.sh

@@ -13,7 +13,8 @@
 #
 # Env overrides:
 #   SHARDS=N                     same as --shards
-#   GBRAIN_TEST_SHARD_TIMEOUT    per-shard wallclock cap, seconds (default 600)
+#   GBRAIN_TEST_SHARD_TIMEOUT    per-shard wallclock cap, seconds (default 1500)
+#   GBRAIN_TEST_SHARD_KILL_AFTER grace after TERM before KILL (default 30)
 #   GBRAIN_TEST_MAX_CONCURRENCY  passed through to bun test (default 4)
 #
 # Output files (workspace-local; falls back to /tmp if .context/ unwritable):
@@ -79,6 +80,10 @@ INTRA_CONC="${MAX_CONCURRENCY_OVERRIDE:-${GBRAIN_TEST_MAX_CONCURRENCY:-4}}"
 # 4-shard wallclock; real hangs still hit it. Override via
 # GBRAIN_TEST_SHARD_TIMEOUT=N.
 SHARD_TIMEOUT="${GBRAIN_TEST_SHARD_TIMEOUT:-1500}"
+SHARD_KILL_AFTER="${GBRAIN_TEST_SHARD_KILL_AFTER:-30}"
+if ! printf '%s' "$SHARD_KILL_AFTER" | grep -qE '^[0-9]+$' || [ "$SHARD_KILL_AFTER" -lt 1 ]; then
+  echo "ERROR: invalid shard kill-after: $SHARD_KILL_AFTER" >&2; exit 2
+fi
 
 # ──────────────────────────────────────────────────────────────────────────
 # Output directories. Prefer workspace-local .context/, fall back to /tmp.
@@ -109,7 +114,7 @@ elif command -v timeout >/dev/null 2>&1; then TIMEOUT_BIN="timeout"
 fi
 
 START_TS=$(date +%s)
-echo "[unit-parallel] N=$N shards | --max-concurrency=$INTRA_CONC | timeout=${SHARD_TIMEOUT}s | logs=$LOG_DIR" >&2
+echo "[unit-parallel] N=$N shards | --max-concurrency=$INTRA_CONC | timeout=${SHARD_TIMEOUT}s | kill-after=${SHARD_KILL_AFTER}s | logs=$LOG_DIR" >&2
 
 if [ "$DRY_RUN" = "1" ]; then
   echo "[unit-parallel] dry-run: would spawn $N shards with the above settings."
@@ -129,7 +134,7 @@ for i in $(seq 1 "$N"); do
   (
     SHARD_LOG="$LOG_DIR/shard-$i.log"
     if [ -n "$TIMEOUT_BIN" ]; then
-      "$TIMEOUT_BIN" "${SHARD_TIMEOUT}s" \
+      "$TIMEOUT_BIN" --signal=TERM --kill-after="${SHARD_KILL_AFTER}s" "${SHARD_TIMEOUT}s" \
         env SHARD="$i/$N" \
         bash scripts/run-unit-shard.sh --max-concurrency="$INTRA_CONC" \
         > "$SHARD_LOG" 2>&1
@@ -140,7 +145,7 @@ for i in $(seq 1 "$N"); do
         > "$SHARD_LOG" 2>&1 &
       pid=$!
       ( sleep "$SHARD_TIMEOUT" && kill -TERM "$pid" 2>/dev/null && \
-        sleep 5 && kill -KILL "$pid" 2>/dev/null ) &
+        sleep "$SHARD_KILL_AFTER" && 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
@@ -158,7 +163,7 @@ for i in $(seq 1 "$N"); do
       wait "$cap_pid" 2>/dev/null
     fi
     echo "$rc" > "$LOG_DIR/shard-$i.exit"
-    [ "$rc" = "124" ] && echo "WEDGED" > "$LOG_DIR/shard-$i.wedged"
+    { [ "$rc" = "124" ] || [ "$rc" = "137" ]; } && echo "WEDGED" > "$LOG_DIR/shard-$i.wedged"
   ) &
   SHARD_PIDS+=($!)
 done

scripts/run-verify-parallel.sh

@@ -50,6 +50,7 @@ CHECKS=(
   "check:cli-exec"
   "check:system-of-record"
   "check:eval-glossary"
+  "check:skills-manifest"
   "check:no-pii-agent-voice"
   "check:synthetic-corpus-privacy"
   "check:skill-brain-first"
@@ -64,6 +65,7 @@ CHECKS=(
   "check:source-scope-onboard"
   "check:no-double-retry"
   "check:batch-audit-site"
+  "check:engine-dynamic-import"
   "check:worker-lock-renewal-shape"
   "typecheck"
 )

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/conventions/schema-evolution.md

@@ -125,7 +125,8 @@ v0.41.22 ships **gbrain-base-v2** as the declared successor to
 gbrain-base@1.x — collapses 94 noisy types to 15 canonical via
 declarative mapping_rules. Run via `gbrain onboard --check --explain`
 (preview) → `gbrain jobs submit unify-types --allow-protected --params
-'{"target_pack":"gbrain-base-v2"}'` (apply). See
+'{"target_pack":"gbrain-base-v2","apply":true}'` (apply — `apply`
+defaults to false, so a bare submit is a dry run). See
 `skills/schema-unify/SKILL.md` for the full playbook.
 
 Authoring a successor pack: declare

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"
@@ -90,9 +90,13 @@ The handler is PROTECTED (manual_only per D17) — autopilot will never auto-fir
 ```bash
 gbrain jobs submit unify-types \
   --allow-protected \
-  --params '{"target_pack":"gbrain-base-v2"}'
+  --params '{"target_pack":"gbrain-base-v2","apply":true}'
 ```
 
+`apply` defaults to **false** (dry-run) per the handler contract, so
+`"apply":true` is required here or the job reports success having retyped
+nothing and left the active pack unflipped. Omit it to preview.
+
 Watch progress per phase:
 
 ```bash
@@ -143,7 +147,7 @@ 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 +201,7 @@ 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 +216,7 @@ 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

@@ -139,9 +139,9 @@ edits writes a new receipt).
 
 | Slot | Default | Provider |
 |------|---------|----------|
-| A | `openai:gpt-4o` | OpenAI |
+| A | `openai:gpt-5.2` | OpenAI |
 | B | `anthropic:claude-opus-4-7` | Anthropic |
-| C | `google:gemini-1.5-pro` | Google |
+| C | `deepseek:deepseek-v4-pro` | DeepSeek |
 
 **These MUST be frontier models from DIFFERENT providers.** Using a single
 provider's family or budget models defeats the purpose — different families

skills/skills.lock.json

@@ -0,0 +1,130 @@
+{
+  "RESOLVER.md": "ad9f85d0f953ad0ec80c70091cb31c7227a89e4a08c924454be1d61d4df5b65c",
+  "_AGENT_README.md": "3dd82df125ceb87bdbc1ad16be4306fb3ca6e3a491c70122f6c7724a862f0b21",
+  "_brain-filing-rules.json": "cf850df6a7425464c6d63b3ace71991cc93497fa0cc8cd21acd31883e17939c6",
+  "_brain-filing-rules.md": "2d2d75b7c76081c56f41b2c0a5a978c355ce957300f9b0a5575dc4079ef1f877",
+  "_friction-protocol.md": "1b6e7cfa58725a6a5dc2dc787242141bc33f5fde524540d85b14ec22266140f7",
+  "_output-rules.md": "239022bd9003b4d45870fea2ddb177a132f0684d898ed5075dc5dcb90cc56ab7",
+  "academic-verify/SKILL.md": "1c19e27e75249d869da428ce8d060075feef8fbbfe146af58b305d11a260ebbc",
+  "academic-verify/routing-eval.jsonl": "90d894a9829d9936e6ac7a6507e4de67ad26e46a1fe13b7a34e7dec1c0d887dd",
+  "archive-crawler/SKILL.md": "10c529797e1cba75da5bdb13bdd3609ae5f962f7dcc429c3b85d51c0032d9a26",
+  "archive-crawler/routing-eval.jsonl": "a90c607d69737adf58771d1b986c5a7d9d11f5303df7de4c7def74aa2c86a2f5",
+  "article-enrichment/SKILL.md": "fcdbce0f250aa2c38b86299dae510b8dc7f1e1cd854961cb8520c61642309549",
+  "article-enrichment/routing-eval.jsonl": "408fa8cc80caf1a2208afeb049e5ada69beb378f22d6b7114828201a4657e6e3",
+  "ask-user/SKILL.md": "a40f484721e548a3a14d4b33a4636111d92f99619ecc4e4ea54c3da3a15f8331",
+  "book-mirror/SKILL.md": "e8b8cc7a6eba4ecd302a840446b48c0e1aecc245e8f240e233c738daa8dff78a",
+  "book-mirror/routing-eval.jsonl": "79fd23642cfa37b1255a799907e71bb2904585cf79dd6a596e3a2f019787e54c",
+  "brain-ops/SKILL.md": "40553ad3bf0f27fc8363b69bec3ef89ae0ea0d9290de8d1efbaa0c532c2a9590",
+  "brain-pdf/SKILL.md": "13c3e3162763a4503685db0a10663475d3687c4874b5f04d539af83a990f643e",
+  "brain-pdf/routing-eval.jsonl": "119e4fa113ea45783cee4499e63a729fdeecb4d9a45d47497754b4f5b21d0734",
+  "brain-taxonomist/SKILL.md": "dea4557b540868ec2c56bf43ee7f63c5d03a22d4047cd0dfbeaf19adef334f60",
+  "brain-taxonomist/routing-eval.jsonl": "8b485b3d735aace60be703854f0f2e9d97c52d52564efdaf7334a0c39e8d20ae",
+  "briefing/SKILL.md": "a661804c3eb2ce5bd4eb6f3e7106283046913945d9dba0b967bdc8483a58dd66",
+  "capture/SKILL.md": "98568ac96331f57397ea072749641d9748b1ce31e8b09d512b8db25c8fcda65f",
+  "citation-fixer/SKILL.md": "abdadbf0740a529b9c4f86f05bba416417624503fdcbc6054402d5546afd08b4",
+  "citation-fixer/routing-eval.jsonl": "52b23b71e66fdc18aee67d0576099b0c83997d648cf4ecf8fe7753b91b6c9c53",
+  "cold-start/SKILL.md": "a2c42dd7c4eceb7d3ce6449a414b417d55195aa445e723e6c798d90906cbf4e6",
+  "concept-synthesis/SKILL.md": "2bc060ae6d706c4e8e7d784cbe3e577b85e211a21c68cba094a1754d3f34436b",
+  "concept-synthesis/routing-eval.jsonl": "51d1da894158503ce18b892a34edd203f40732e79ac1c0e85141fd37e0b9922f",
+  "conventions/brain-first.md": "29d020470d0168f8f0b29dde0350a485a9b0472f7ac9962e34948f4897455590",
+  "conventions/brain-routing.md": "a8035f7dbadff0ea68b8babb8314b3d044cafbed8242dce5b931fa08b028fc45",
+  "conventions/calibration.md": "eda7ca76f80c8a17ae546110484389f805c5b21fc0a57f951bbe8b6abba26e03",
+  "conventions/cron-via-minions.md": "badb1cd6cd825d6f1ac0b6b28cc47e5d80facc783a3e59a14146ae901ee0f933",
+  "conventions/cross-modal.yaml": "c012c3d72614a87b1ee698173dce2a0fb0d057a54df7aab87993c4b07fff6280",
+  "conventions/model-routing.md": "fb7ae8746a578500d6789b68ff40049037aa4d337b65b42f7c1745ae7080c2db",
+  "conventions/quality.md": "8aa681001114689d34268ccadaf0e2ff07b8f68aa5987c093a8c4a7a744f12a6",
+  "conventions/salience-and-recency.md": "62b0b303bf48bef10adcf08d3b51f23d3b1f1187b3850476a4b5532c2ee88926",
+  "conventions/schema-evolution.md": "b5cdd5a17e43b4f2d0546ebf8c421cc0378cbcf74cb2fe97199e115ccb05f9c2",
+  "conventions/search-modes.md": "2a920225d1c95ea978fb1c77c5170f6a598377ab86fc0024b70962d5a84d54d0",
+  "conventions/subagent-routing.md": "59afd362ff0cbaf3a63586e97c53f68feb837a258a2bd43f9177af4e57d2b20e",
+  "conventions/test-before-bulk.md": "5073e5b93d570445f72f3c10ed3e6ec10c1fee7574ad73c2e2695993c850eca5",
+  "cron-scheduler/SKILL.md": "e3f9745c4f8e2dacba5b055f408b1ffe541b450aee6bbfe4773f7b424d90e04c",
+  "cross-modal-review/SKILL.md": "685233b1afd477e96697562c502233eea22eda5db8df116b81dd2fa78f01f80c",
+  "daily-task-manager/SKILL.md": "e616f74a6befffc7bb64c0e29b2d2caa37c51bc470bca96df70101c772429d83",
+  "daily-task-prep/SKILL.md": "9fe89f85fae139adac25c3bdc6f23bbf64239f3738a9e679c447e686175516f0",
+  "data-research/SKILL.md": "990ccec01a23d3e46c7b5abbd2650ac5507480b50f7ec4de8b466863b3b61cb6",
+  "eiirp/SKILL.md": "9d42d6a5f61bba30cb47400db58927c501cd89e5cc3241b5218d7962d1a68804",
+  "eiirp/routing-eval.jsonl": "416459ff68da2e5f5eb216a0c24368c8eebdf4edbbc540a28fe730ceeb4c9700",
+  "enrich/SKILL.md": "9988168348f6c3391d3aeec6621f9c99c8d75d1e1bfdd6c44d48e4c1067ab775",
+  "frontmatter-guard/SKILL.md": "5142ab53f5428ebc084ded78f1fb7eb4bfa386d276ee034bf4d57273256570c6",
+  "frontmatter-guard/routing-eval.jsonl": "243c28b04b557bac5360318c0f47bb6f1dd56d2f720aad3763b93fc0b2ea081e",
+  "functional-area-resolver/SKILL.md": "52df04bc4f8e678f931c3b2078b2126524e6d2d72676ad46b6b710d13271b46c",
+  "functional-area-resolver/routing-eval.jsonl": "f80674d915acdfe229046737a5b171da834be15ac6524b5a3fd18048e9b37028",
+  "gbrain-advisor/SKILL.md": "c15c7a88bee2c96733d718a168dd9afcb123b7b6b2c0014c5260d37c72e8736a",
+  "gbrain-upgrade/SKILL.md": "7cd05f43027fa20d56ed651f696288f9e4814b7bdf7b396f132fde7c96dac620",
+  "idea-ingest/SKILL.md": "e118bc32d5044a4a6fba4fed1911b8be50210ade14957e6cfe8e7ed26ff95298",
+  "idea-lineage/SKILL.md": "bbf37781d93b71ddc7909ecc5ab635872c874fb8591995dbf88b45ffeac6b1de",
+  "idea-lineage/routing-eval.jsonl": "ee2e00704b9accb7dd58bb8f126a3bc04a2c40be499180fa505dbf6d5061cd41",
+  "ingest/SKILL.md": "dc40ecc0072806fb8c7bb6ab9cf1f103842e05653eb55d67632d7e3ffc4dd7d2",
+  "install/SKILL.md": "881bd0a422f34c6df4642aae66c51e2a4cc18ad5ca6d0b52d44b4de93512a3c4",
+  "maintain/SKILL.md": "e80cf5bb170c979b773a67a18e0d880c086e0b983db9a576a207074b0112c4f8",
+  "manifest.json": "52b970cfc3ed340ee4f25323b6fadeb5d125741b02d1d2dc2f85c39f0c701258",
+  "media-ingest/SKILL.md": "33db12830ed31a4ff4a6a58c4f126bf2596ee28d54cee0027680c83fee648a20",
+  "meeting-ingestion/SKILL.md": "7767334c63ff3bd8e60cd4d7cd1d1b44f0d6b0a7e0ac411529a1d59cc0a7781b",
+  "migrate/SKILL.md": "442c117cfe50026a142ff4f934e489c56ee226d454b639d20bba3b111a86d8fd",
+  "migrations/.gitkeep": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+  "migrations/v0.10.3.md": "1e12db6fdb88d21df479659e236bad111a041a205d47aa0894afde2f04903124",
+  "migrations/v0.11.0.md": "ac45c6144eeee5033f2b24308a5063ceced2be7831b04e48154aa0b6f8ff55d8",
+  "migrations/v0.12.0.md": "f30b452caed5ce2679cbd60dc2d0b9e60449bab20c3a3e0c895e6cd167644f44",
+  "migrations/v0.12.1.md": "a461d8fcd6b19dabe3a0ce849a54e3c577667ae2af41870c6f456c6195e76064",
+  "migrations/v0.13.0.md": "3bf61eb1da933e6c3c35d67d0ea6d9dada5d5f878bbd14020616d4e1fe48feb2",
+  "migrations/v0.14.0.md": "1025395f033b91480451aad6a98dc10f2c18bfacd1b1a4e2a9fb4dc99f8fb571",
+  "migrations/v0.15.2.md": "468a58e8a9f0f5c5867e0ed8eb9dd1bd60dbc8d66111647997ebd8d9d2119915",
+  "migrations/v0.17.0.md": "761dda3b6090bfe20c9b4354aff5248d5a9b6a79a24702ecc2b29873d4f5b413",
+  "migrations/v0.18.0.md": "94efc1d571070600a78aca13c2735866a987e6a8f188210b7062f81b54839986",
+  "migrations/v0.19.0.md": "c47584e8306680f21ddc7f21a4a89f2184da522acb177f0dd73a09f1cd77ae57",
+  "migrations/v0.21.0.md": "83569ce6fb2843f81964833affe5eae72c94a2983eba265c836aa05be7876957",
+  "migrations/v0.22.14.md": "8898c109716fbc48c058a44c606f50fb7c02be599541d367380aa2e63bffea9e",
+  "migrations/v0.22.4.md": "5f9b2ed86cb64d92416448e744ca6c4984b89728895cd4e363f9c76a860074d9",
+  "migrations/v0.23.0.md": "f0363274e5071fa35d0c60e3981c4caee0494c43adb254d65acf6b743d4762d5",
+  "migrations/v0.25.1.md": "981ef49abadf19a891cb68b655b9f35ee67d9f4ac232ceb29d83dfc3b1c9982e",
+  "migrations/v0.27.1.md": "719dd4ebcc7ac81413ee79af20f80de5141577e3860e5049a49fc8f6d09ddf89",
+  "migrations/v0.28.0.md": "21929a392af2e1f454272e80aade6c58c5f6ccd7253d24344d08c6b53bcdf4f9",
+  "migrations/v0.29.1.md": "7b85373a62a8500ee8c4238ffc9878318b44ee62543adb8b2462049c6c0cd1f8",
+  "migrations/v0.32.2.md": "101623fa48f946242d7edc8f126967822563c3fb30a6ad50d029894f5fe3499d",
+  "migrations/v0.32.6.md": "e9438a910afe8a1f7861c5222fd7db04a0f8d8b8283778476b07b7c3d539d3f0",
+  "migrations/v0.33.0.md": "11710cb11d6eb7dc3ea54b764e3c4a25f8679cf76590acd330f97bfa1c684945",
+  "migrations/v0.33.3.0.md": "188a03ca86a97a9aa697cbbc83cc8ca37843fab24db2bd82f1383c400173d5bd",
+  "migrations/v0.34.0.0.md": "d421c5ecff0765ac1de3592d3175734db7df52e8658ec101567779c7c56c2db2",
+  "migrations/v0.35.0.0.md": "0fc21dc0b098f87fff1ac79a669b00a3d69ab1510ebfc5eac4a66f5c6d783809",
+  "migrations/v0.35.7.0.md": "c6d4454bd39e2aa243b3b3d9bc72fe5a4fd25d097be7be2bb14b25604b5c2cc5",
+  "migrations/v0.36.2.0.md": "1b59328240ae19c5e7e8d3eafda245809cca1fea27146607334dbee53cbeb270",
+  "migrations/v0.36.5.0.md": "a01a722202dfc3c799693596750c8bee611fe4dafe3cb662f6b4cd0b635cb429",
+  "migrations/v0.40.3.0.md": "5f500f8c543c2b6f41778b0bd3beedada68f7284f7933ad8b769322b433a8fe9",
+  "migrations/v0.40.5.md": "b9837d52a030517698dfb31c439f562cde60a1015ae488dab09be2c16ff182e5",
+  "migrations/v0.41.11.0.md": "5c6873ab969d14def4a450d792f070f1259d08b3aca43bc7825d0a9114b2b36b",
+  "migrations/v0.5.0.md": "5e0dabc451595295c4d971e19bcb33c258a127223d25859d8321cb7e1ce60711",
+  "migrations/v0.7.0.md": "97c2740445a10b1c5c7123c17dbd625fa27a94095b85d27c2b278da756c4c59a",
+  "migrations/v0.8.0.md": "1919ff8b8f3680612ff888e7cfcc0d86ece5d5304ae19af4497bdf40b050561a",
+  "migrations/v0.8.1.md": "fad7341cfb5e02545fb8a23221d12ab395fc3d8db15d1d8ee8a18844aea6563a",
+  "migrations/v0.9.0.md": "773fab0a8d7f330576265a3f510c1f318f47789b6136c46d43e08121acbc20eb",
+  "migrations/v0.9.1.md": "75761bad6c0ad37b69ec8197c6a678bb6a1484f9a76e4b70f2d1e86dc80102b3",
+  "minion-orchestrator/SKILL.md": "669e23f485561cf6fef16d445dfb8a6d05f76127d0ebf9feb17534af8843df5f",
+  "perplexity-research/SKILL.md": "c25f5c471cbe3c6e0f975d8397e8382b00a85f8aa75302231d53c52855369e97",
+  "perplexity-research/routing-eval.jsonl": "f1a40d87e710d5d2acd602a372d83f46c95da022b6e635228fffeaacb3bb2b27",
+  "publish/SKILL.md": "e06b609db780a3cc93a1755a87b30ff08ffdc0fdbc834c1422b2ad2489b57497",
+  "query/SKILL.md": "e155a08049984c524b838988ba456d16ccedf162442160f6ba66bfd97cd5208e",
+  "query/routing-eval.jsonl": "74f5a91e52fabc54e0e9403fa17db87ee26bb7ebb8ae8005148c51142abc62fe",
+  "repo-architecture/SKILL.md": "4ec2b8f45d168aaa55f17ecd1ed404ab04217a75c2317f0710c71705846f5394",
+  "reports/SKILL.md": "5dc190a0c3a2ee518254e8b596418dbe19ff389ea5ec8c8d30fcb0dfef4d0ed5",
+  "schema-author/SKILL.md": "4da9a472c966f8e4fb43d97a3a3608c67ec3d43da6b8c626ee0c30a4e70da26f",
+  "schema-unify/SKILL.md": "e1d50a54a6ff29434d38a841a572e815d236a8167d459609ae697e548770f500",
+  "setup/SKILL.md": "4a47a5f6ee99ac8a2649a304abb261fd34810cf6185fd7d6a53e1b6c4cbc0764",
+  "signal-detector/SKILL.md": "64e4547f5a8624c53d875001b423d240ec73ee9fd026a96c7b799d287c5fb6e4",
+  "skill-creator/SKILL.md": "4a11f8935d4214b21b4664a5c0c03149733731020ec0d5d09dc9fd8c40bd92f6",
+  "skill-optimizer/SKILL.md": "ba3028c7351dec3e644a7114e08e59cae7c60dc367dc4fd10560265a162baa90",
+  "skill-optimizer/routing-eval.jsonl": "48f7fc04414b194ee8674577c3e58e03ebd7f74d836766bd16cb5abfd4effb76",
+  "skill-optimizer/skillopt-benchmark.jsonl": "5552457d6eaa32486b79796d12fcbe2c078b0c53d7fbdaf582f0fd1a17e9a381",
+  "skillify/SKILL.md": "a154e43409458136e1e1cea084aa973e4cf46cd8450c6be8e9891a4a3ddf6146",
+  "skillpack-check/SKILL.md": "3f347ec8b498530a662be212d05f4cd06b205bce5795c2231b6a4cecef149ea0",
+  "skillpack-harvest/SKILL.md": "3c4c591b33f03a5ccf11ca0ddde56b54fba541efef0d590b6d435687733182d7",
+  "skillpack-harvest/routing-eval.jsonl": "cb4783288e95af3132b32ecb40a54cffc095f57b36240f96a25c2d2adf5e68c6",
+  "smoke-test/SKILL.md": "f2f2172d41e63e288095451132a0c56848ccc34101d265b330b6cf00e5769f5d",
+  "soul-audit/SKILL.md": "7f162dddcc511e97a24db3a46136295fcbda76023019ad8994546744d7b8eb0a",
+  "strategic-reading/SKILL.md": "5be656c39c830153ec7c2f328dc8bdeac05c1412b01b3415de6b5b008926e7a2",
+  "strategic-reading/routing-eval.jsonl": "eb0fc239c93aac53cf7d856190967bb65eaf970b4fe8bd0aad1c87495fbb8ccd",
+  "testing/SKILL.md": "f1846ba7c35076d910744a6b867c9ee850c1895f75a104a319c9b7d18b1d5e90",
+  "voice-note-ingest/SKILL.md": "145c02e636430abba5648e026aef77606d6ba2594285fbfee4f4dd4253cf833a",
+  "voice-note-ingest/routing-eval.jsonl": "374aaec16fbde336d1e376edce89e51adc4ecaa93c13fb4a69b967ba299b8742",
+  "webhook-transforms/SKILL.md": "b774293297af4d513c7efa92a79cf65b8438a714adafc16802b492613e679d17"
+}

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/cli.ts

@@ -55,12 +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', 'retrieval-upgrade', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector', 'backfill']);
+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',
@@ -107,6 +112,11 @@ 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',
+  // `gbrain init --help` prints its own usage from runInit; route around the
+  // generic one-line short-circuit (matches `connect`). Without this, `init`
+  // is in CLI_ONLY but not CLI_ONLY_SELF_HELP, so the dispatcher's generic
+  // short-circuit fires and the printInitHelp() guard in init.ts is dead code.
+  'init',
   // #3390 — `gbrain migrate embeddings --help` / `gbrain retrieval-upgrade
   // --help` print the migration flags from runMigrateEmbeddings. `migrate`
   // (engine transfer) keeps its own dispatch too.
@@ -394,6 +404,18 @@ async function main() {
     if (op.localOnly) {
       refuseThinClient(command, cfgPre!.remote_mcp!.mcp_url);
     }
+    // A thin client has no local mounts — an explicit --brain cannot be
+    // honored and must not be silently dropped (same loud-beats-silent rule
+    // as applyThinClientSourceScope's --source refusal). Ambient tiers
+    // (GBRAIN_BRAIN_ID / .gbrain-mount) are ignored here, matching the
+    // source axis's ambient-with-nowhere-to-send behavior.
+    if (cliOpts.brain) {
+      console.error(
+        '--brain is not supported on a thin-client install: the remote server is a single brain. ' +
+        'Remove the flag, or run from a machine with local mounts (gbrain mounts list).',
+      );
+      process.exit(1);
+    }
     // #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.
@@ -1004,6 +1026,10 @@ export async function makeContext(engine: BrainEngine, params: Record<string, un
     // table). Matches dispatch.ts's auto-fill so the contract holds across
     // every transport.
     sourceId: sourceId ?? 'default',
+    // Brain axis: the id connectEngine resolved for this process. Module
+    // state, NEVER params — caller-supplied params.brain must not select a
+    // brain (that would be an untrusted-caller cross-brain hole over MCP).
+    brainId: activeBrainId,
     ...(localFederated ? { localFederatedSourceIds: localFederated } : {}),
   };
 }
@@ -1265,6 +1291,20 @@ 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') {
@@ -1707,14 +1747,12 @@ async function handleCliOnly(command: string, args: string[]) {
   // Per-command default: search 30s, sources list 10s. User --timeout=Ns wins.
   // Other commands (import, embed, doctor, etc.) keep their existing
   // unbounded connect — destructive / long-running commands shouldn't get
-  // a default kill switch.
-  const readOnlyDefaultTimeoutMs =
-    command === 'search' ? 30_000 :
-    command === 'sources' && (args[0] === 'list' || args[0] === undefined) ? 10_000 :
-    null;
+  // a default kill switch. The gate below is per-command (#3013): only the
+  // commands dispatchReadOnlyCommand handles may enter this path — a
+  // user-supplied --timeout on a write command must never reroute it here.
   const cliOptsResolved = getCliOptions();
   const userTimeoutMs = cliOptsResolved.timeoutMs;
-  const readOnlyTimeoutMs = userTimeoutMs ?? readOnlyDefaultTimeoutMs;
+  const readOnlyTimeoutMs = resolveReadOnlyDispatchTimeoutMs(command, args, userTimeoutMs);
 
   if (readOnlyTimeoutMs !== null) {
     const { withTimeout, OperationTimeoutError } = await import('./core/timeout.ts');
@@ -1829,7 +1867,14 @@ async function handleCliOnly(command: string, args: string[]) {
       }
       case 'embed': {
         const { runEmbed } = await import('./commands/embed.ts');
-        await runEmbed(engine, args);
+        // #3037: mirror the `import` case above — the CLI was discarding the
+        // result, so a run where every chunk failed to embed still exited 0
+        // and cron/CI/health gates read total silence as success. Surface
+        // non-zero on failures > 0. (undefined = backgrounded via --background.)
+        const embedResult = await runEmbed(engine, args);
+        if (embedResult && embedResult.failures > 0) {
+          setCliExitVerdict(1);
+        }
         break;
       }
       case 'serve': {
@@ -2253,16 +2298,24 @@ async function handleCliOnly(command: string, args: string[]) {
         //
         // v0.30.1: still works; canonical entrypoint is now `gbrain backfill
         // effective_date`. This command stays as a thin alias for back-compat.
+        //
+        // #1963: pass the already-connected engine. The command used to build
+        // + connect its OWN engine here, which self-deadlocked on the PGLite
+        // data-dir lock (this process already holds it via connectEngine
+        // above) — 30s spin, then exit 1, on every PGLite invocation.
         const { reindexFrontmatterCli } = await import('./commands/reindex-frontmatter.ts');
-        await reindexFrontmatterCli(args);
-        return; // reindexFrontmatterCli handles its own engine lifecycle
+        await reindexFrontmatterCli(engine, args);
+        break;
       }
       case 'backfill': {
         // v0.30.1: first-class generic backfill command. Subcommand dispatch
         // is inside runBackfillCommand (kind | list | --help).
+        // #1963: same double-connect class as reindex-frontmatter — reuse the
+        // connected engine instead of building a second one on the same
+        // PGLite data dir.
         const { runBackfillCommand } = await import('./commands/backfill.ts');
-        await runBackfillCommand(args);
-        return;
+        await runBackfillCommand(engine, args);
+        break;
       }
       case 'code-callers': {
         // v0.20.0 Cathedral II Layer 10 (C4): "who calls <symbol>?"
@@ -2305,6 +2358,28 @@ async function handleCliOnly(command: string, args: string[]) {
   }
 }
 
+/**
+ * #3013: decide whether an invocation enters the read-only connect+dispatch
+ * timeout path, and with what wallclock. Returns null for every command
+ * dispatchReadOnlyCommand can't handle. The gate used to be "a timeout is
+ * present" — so a user-supplied --timeout on a write command (`sync`,
+ * `embed`, `import`, ...) hijacked dispatch into the read-only path, which
+ * threw and exited 1 before any work ran. Pure; exported for the
+ * regression test.
+ */
+export function resolveReadOnlyDispatchTimeoutMs(
+  command: string,
+  subArgs: string[],
+  userTimeoutMs: number | null,
+): number | null {
+  if (command !== 'search' && command !== 'sources') return null;
+  const defaultMs =
+    command === 'search' ? 30_000 :
+    (subArgs[0] === 'list' || subArgs[0] === undefined) ? 10_000 :
+    null;
+  return userTimeoutMs ?? defaultMs;
+}
+
 /**
  * v0.41.6.0 D3: dispatch helper for the read-only commands that take a
  * default wallclock timeout (`gbrain search`, `gbrain sources list`).
@@ -2340,7 +2415,52 @@ async function dispatchReadOnlyCommand(engine: BrainEngine, command: string, arg
 import { buildGatewayConfig } from './core/ai/build-gateway-config.ts';
 export { buildGatewayConfig };
 
+/**
+ * Which brain this process's engine targets. Set by connectEngine after brain
+ * resolution; read by makeContext so ctx.brainId carries the audit id. Never
+ * derived from op params — an untrusted caller must not be able to name a
+ * brain (same fail-closed shape as the #3524 remote source sentinel).
+ */
+let activeBrainId: string = 'host';
+
+/**
+ * Connect to a mounted brain (brain axis, non-host). Routes through
+ * BrainRegistry so:
+ *   - an unknown/disabled mount id throws UnknownBrainError. Fail-closed:
+ *     the pre-fix CLI silently fell back to the host brain, returning
+ *     confident wrong answers (mirror of #3524's explicit --source decision);
+ *   - postgres mounts get a per-instance pool, never the db.ts singleton;
+ *   - NO migrations run against the mount — schema is the publisher's job
+ *     (same decision as BrainRegistry.initMountBrain). Write access control
+ *     is the mount's own DB credential grants: a read-only role rejects
+ *     writes at the database; gbrain does not re-implement that client-side.
+ * The AI gateway still configures from the HOST config (the caller's API
+ * keys + model tiers) — embedding/expansion spend stays the caller's, and
+ * a mount's DB-plane model config is never merged into the caller's gateway.
+ */
+async function connectMountEngine(brainId: string): Promise<BrainEngine> {
+  const config = loadConfig();
+  if (config) {
+    const { configureGateway } = await import('./core/ai/gateway.ts');
+    configureGateway(buildGatewayConfig(config));
+  }
+  const { loadRegistry } = await import('./core/brain-registry.ts');
+  const handle = await loadRegistry().getBrain(brainId);
+  activeBrainId = brainId;
+  return handle.engine;
+}
+
 async function connectEngine(opts?: { probeOnly?: boolean }): Promise<BrainEngine> {
+  // Brain axis: resolve WHICH DATABASE this invocation targets before touching
+  // the host engine. --brain (global flag) / GBRAIN_BRAIN_ID / .gbrain-mount /
+  // mount-path-prefix resolve via the canonical 6-tier chain — the mirror of
+  // the source axis in makeContext. connectEngine is the single choke point
+  // every local CLI command routes through (shared ops, CLI-only commands,
+  // and the search-dashboard path), so routing lands here once.
+  const { resolveBrainId } = await import('./core/brain-resolver.ts');
+  const brainId = resolveBrainId(getCliOptions().brain);
+  if (brainId !== 'host') return connectMountEngine(brainId);
+
   const config = loadConfig();
   if (!config) {
     console.error('No brain configured. Run: gbrain init');

src/commands/apply-migrations.ts

@@ -108,7 +108,7 @@ Flags:
 
 Exit codes:
   0  Success (including "nothing to do").
-  1  An orchestrator failed.
+  1  An orchestrator failed, or schema migrations are pending (re-run with --yes).
   2  Invalid arguments.
 `);
 }
@@ -260,6 +260,41 @@ function printDryRun(plan: Plan, installed: string): void {
   }
 }
 
+/**
+ * #1530: schema-drift pre-flight resolution. When the schema version is
+ * behind, `--yes`/`--non-interactive` runs the schema migrations right there
+ * (the engine is already connected); interactive runs warn and return true so
+ * the caller exits non-zero instead of claiming "All migrations up to date".
+ * All output goes to stderr (migrations never print to stdout).
+ *
+ * Returns true when the schema is STILL behind after this call.
+ */
+async function resolveSchemaBehind(opts: {
+  schemaVer: number;
+  latest: number;
+  autoApply: boolean;
+  run: () => Promise<{ applied: number; current: number }>;
+}): Promise<boolean> {
+  const { schemaVer, latest, autoApply, run } = opts;
+  if (schemaVer >= latest) return false;
+  if (autoApply) {
+    console.error(`Schema version ${schemaVer} is behind latest ${latest}; running schema migrations...`);
+    try {
+      const result = await run();
+      console.error(`Applied ${result.applied} schema migration(s); now at v${result.current}.`);
+      return false;
+    } catch (err) {
+      console.error(`Schema migration failed: ${err instanceof Error ? err.message : String(err)}`);
+      return true;
+    }
+  }
+  console.warn(
+    `\n⚠️  Schema version ${schemaVer} is behind latest ${latest}.\n` +
+    `   Run \`gbrain apply-migrations --yes\` to apply now, or \`gbrain init --migrate-only\`.\n`,
+  );
+  return true;
+}
+
 function orchestratorOptsFrom(cli: ApplyMigrationsArgs): OrchestratorOpts {
   return {
     yes: cli.yes || cli.nonInteractive,
@@ -355,10 +390,13 @@ export async function runApplyMigrations(args: string[]): Promise<void> {
     if (cli.forceAll) return; // both surfaces flushed
   }
 
-  // Pre-flight: warn if schema migrations (migrate.ts) are behind.
-  // apply-migrations runs orchestrator migrations only; schema migrations
-  // run via connectEngine() / initSchema(). Users often expect this CLI
-  // to handle everything (Issue 1 from v0.18.0 field report).
+  // Pre-flight: detect schema migrations (migrate.ts) being behind.
+  // apply-migrations historically ran orchestrator migrations only; schema
+  // migrations run via connectEngine() / initSchema(). Users expect this CLI
+  // to handle everything (Issue 1 from v0.18.0 field report; #1530). With
+  // --yes/--non-interactive we apply them here; otherwise we warn and make
+  // sure the run does NOT report "All migrations up to date" with exit 0.
+  let schemaBehind = false;
   try {
     const { LATEST_VERSION } = await import('../core/migrate.ts');
     const { loadConfig: lc, toEngineConfig } = await import('../core/config.ts');
@@ -378,14 +416,16 @@ export async function runApplyMigrations(args: string[]): Promise<void> {
         await eng.connect(toEngineConfig(cfg));
         const verStr = await eng.getConfig('version');
         const schemaVer = parseInt(verStr || '1', 10);
+        const { runMigrations } = await import('../core/migrate.ts');
+        schemaBehind = await resolveSchemaBehind({
+          schemaVer,
+          latest: LATEST_VERSION,
+          // --list and --dry-run are read-only surfaces: never mutate schema
+          // even when combined with --yes/--non-interactive.
+          autoApply: (cli.yes || cli.nonInteractive) && !cli.dryRun && !cli.list,
+          run: () => runMigrations(eng),
+        });
         await eng.disconnect();
-        if (schemaVer < LATEST_VERSION) {
-          console.warn(
-            `\n⚠️  Schema version ${schemaVer} is behind latest ${LATEST_VERSION}.\n` +
-            `   Schema migrations run automatically on next connectEngine() / initSchema().\n` +
-            `   To run them now: gbrain init --migrate-only\n`,
-          );
-        }
       }
     }
   } catch {
@@ -420,6 +460,13 @@ export async function runApplyMigrations(args: string[]): Promise<void> {
 
   const toRun: Migration[] = [...plan.partial, ...plan.pending];
   if (toRun.length === 0) {
+    if (schemaBehind) {
+      console.error(
+        'Orchestrator migrations are up to date, but schema migrations are behind. ' +
+        'Run `gbrain apply-migrations --yes` (or `--force-schema`) to apply them.',
+      );
+      process.exit(1);
+    }
     console.log('All migrations up to date.');
     process.exit(0);
   }
@@ -511,4 +558,5 @@ export const __testing = {
   buildPlan,
   indexCompleted,
   statusForVersion,
+  resolveSchemaBehind,
 };

src/commands/auth.ts

@@ -524,13 +524,17 @@ async function registerClient(name: string, args: string[]) {
  * /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,...]';
+  const usage = 'Usage: auth rescope-client <client_id> [--source SOURCE] [--federated-read SRC1,SRC2,...] [--bound-slug-prefixes P1,P2|none]';
   if (!clientId) {
     console.error(usage);
     process.exit(1);
   }
   let sourceId: string | undefined;
   let federatedRead: string[] | undefined;
+  // v0.42.72.0: tri-state — undefined = untouched, null = clear ('none'),
+  // array = replace. Lets roster churn (channel joins/leaves) update the
+  // write fence in place instead of register+rotate.
+  let boundSlugPrefixes: string[] | null | undefined;
   for (let i = 0; i < args.length; i += 2) {
     const flag = args[i];
     const value = args[i + 1];
@@ -542,14 +546,18 @@ async function rescopeClient(clientId: string, args: string[]) {
     if (flag === '--source') sourceId = value;
     else if (flag === '--federated-read') {
       federatedRead = value.split(',').map(s => s.trim()).filter(Boolean);
+    } else if (flag === '--bound-slug-prefixes') {
+      boundSlugPrefixes = value === 'none'
+        ? null
+        : value.split(',').map(s => s.trim()).filter(Boolean);
     } else {
       console.error(`Error: Unknown flag: ${flag}`);
       console.error(usage);
       process.exit(1);
     }
   }
-  if (sourceId === undefined && federatedRead === undefined) {
-    console.error('Error: pass --source and/or --federated-read');
+  if (sourceId === undefined && federatedRead === undefined && boundSlugPrefixes === undefined) {
+    console.error('Error: pass --source, --federated-read, and/or --bound-slug-prefixes');
     console.error(usage);
     process.exit(1);
   }
@@ -557,10 +565,13 @@ async function rescopeClient(clientId: string, args: string[]) {
     await withConfiguredSql(async (sql) => {
       const { GBrainOAuthProvider } = await import('../core/oauth-provider.ts');
       const provider = new GBrainOAuthProvider({ sql });
-      const result = await provider.rescopeClient(clientId, { sourceId, federatedRead });
+      const result = await provider.rescopeClient(clientId, { sourceId, federatedRead, boundSlugPrefixes });
       console.log(`OAuth client rescoped: "${result.clientName}" (${result.clientId})\n`);
       console.log(`  Write source:        ${result.sourceId}`);
       console.log(`  Federated reads:     ${result.federatedRead.join(', ') || '<none>'}`);
+      if (result.boundSlugPrefixes !== undefined) {
+        console.log(`  Bound slug prefixes: ${result.boundSlugPrefixes?.join(', ') ?? '<none — full-source write authority>'}`);
+      }
       console.log('\nTakes effect on the client\'s next request (existing tokens included).');
     });
   } catch (e: any) {
@@ -645,14 +656,22 @@ Usage:
      --bound-tools <tool1,tool2>                           Bind submit_agent to an allow-list of tools
      --bound-source <id>                                   Bind submit_agent jobs to a source id
      --bound-brain <id>                                    Bind submit_agent jobs to a brain id
-     --bound-slug-prefixes <prefix1,prefix2>               Bind submit_agent writes to slug prefixes
+     --bound-slug-prefixes <prefix1,prefix2>               Fence ALL direct slug writes (put_page, delete_page,
+                                                          tags, links, timeline, revert, raw data) AND
+                                                          submit_agent to these prefixes. Each MUST end with
+                                                          '/' or '/*' — a boundary-less 'emp-alice' would also
+                                                          name 'emp-alice-2/...'. Ops that write by something
+                                                          other than a slug (extract_*, forget_fact,
+                                                          ontology_propose, sources_*) and POST /ingest become
+                                                          unavailable to a bound client. Omit = full-source writes.
      --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.
+                                                          you pass change; the other axes are left as-is.
      --source <id>                                        New write source
      --federated-read <id1,id2,...>                       New read-scope source list
+     --bound-slug-prefixes <p1,p2|none>                   Replace the slug-prefix write fence ('none' clears it)
   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

@@ -1,9 +1,42 @@
+import { defaultTimeoutMsFor } from '../core/minions/handler-timeouts.ts';
+
+// #2781: the full-cycle floor used to be a literal `1_800_000` that merely
+// HAPPENED to match the 'autopilot-cycle' / 'autopilot-global-maintenance'
+// handler anchors (`HANDLER_DEFAULT_TIMEOUT_MS`, #1737) instead of being
+// derived from them. A duplicated literal can silently drift from the
+// handler default it's supposed to track — which is exactly the bug class
+// #2781 reported (an explicit `timeout_ms` stamp permanently overrides the
+// handler default per `queue.ts`'s `opts?.timeout_ms ?? defaultTimeoutMsFor`,
+// so a stale/lower literal here would starve a phase the handler default
+// was sized for). Deriving the floor from `defaultTimeoutMsFor` for both
+// full-cycle job names keeps the stamp coupled to its anchor by construction.
+// Fail fast (not `?? 0`) if either handler ever loses its entry in
+// HANDLER_DEFAULT_TIMEOUT_MS — silently falling back to "no floor" would
+// reintroduce #2781 rather than surface the drift.
+function requireHandlerAnchorMs(jobName: string): number {
+  const ms = defaultTimeoutMsFor(jobName);
+  if (ms === null) {
+    throw new Error(
+      `resolveAutopilotDispatchTimeoutMs: '${jobName}' has no entry in HANDLER_DEFAULT_TIMEOUT_MS ` +
+      '(handler-timeouts.ts) — the full-cycle timeout floor can no longer be derived from it. ' +
+      'See #2781: a missing/removed anchor here silently reintroduces the interval-derived stamp ' +
+      'permanently overriding the handler default.',
+    );
+  }
+  return ms;
+}
+
+const FULL_CYCLE_TIMEOUT_FLOOR_MS = Math.max(
+  requireHandlerAnchorMs('autopilot-cycle'),
+  requireHandlerAnchorMs('autopilot-global-maintenance'),
+);
+
 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)
+    ? Math.max(intervalDerivedTimeoutMs, FULL_CYCLE_TIMEOUT_FLOOR_MS)
     : intervalDerivedTimeoutMs;
 }

src/commands/autopilot.ts

@@ -981,12 +981,21 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
           // can't shrink throughput (codex #9/D5). autopilot-cycle jobs run on
           // the 'default' queue, so that's the concurrency we compare against.
           const fanoutMax = await resolveEffectiveFanoutMax(engine, 'default');
+          // #2781: both 'autopilot-cycle' (per-source) and 'autopilot-global-
+          // maintenance' carry a 30-min handler anchor (handler-timeouts.ts)
+          // because a full cycle can outlive short daemon intervals — unlike
+          // the lighter interval-derived `timeoutMs` above (sync/freshness,
+          // extract-atoms-drain, targeted small-plan steps), which have no
+          // such anchor and are meant to stay interval-derived. Naming this
+          // separately (rather than reusing the outer `timeoutMs`) avoids
+          // the #2781 bug class: dispatchGlobalMaintenance previously reused
+          // the outer non-full-cycle `timeoutMs` by shorthand, silently
+          // dropping its own handler anchor.
+          const fullCycleTimeoutMs = resolveAutopilotDispatchTimeoutMs(baseInterval, true);
           const result = await dispatchPerSource(engine, queue, {
             repoPath,
             slot,
-            // Full cycles can outlive short daemon intervals. Keep lighter dispatches
-            // interval-derived while giving per-source consolidation enough time.
-            timeoutMs: resolveAutopilotDispatchTimeoutMs(baseInterval, true),
+            timeoutMs: fullCycleTimeoutMs,
             fanoutMax,
             jsonMode,
           });
@@ -997,7 +1006,7 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
           // the per-source path (legacy single-source still runs everything).
           if (!result.legacy_fallback) {
             try {
-              await dispatchGlobalMaintenance(engine, queue, { repoPath, slot, timeoutMs, jsonMode });
+              await dispatchGlobalMaintenance(engine, queue, { repoPath, slot, timeoutMs: fullCycleTimeoutMs, jsonMode });
             } catch (e) {
               if (jsonMode) process.stderr.write(JSON.stringify({ event: 'global_maintenance_dispatch_failed', error: e instanceof Error ? e.message : String(e) }) + '\n');
             }

src/commands/backfill.ts

@@ -16,10 +16,10 @@
  * always reserving 1 connection for HNSW + heartbeat + doctor probes.
  */
 
+import type { BrainEngine } from '../core/engine.ts';
 import { resolveDirectPoolSize } from '../core/connection-manager.ts';
 import { listBackfills, getBackfill } from '../core/backfill-registry.ts';
 import { runBackfill, clearBackfillCheckpoint } from '../core/backfill-base.ts';
-import { loadConfig, toEngineConfig } from '../core/config.ts';
 
 interface BackfillArgs {
   kind?: string;
@@ -114,7 +114,14 @@ function clampConcurrency(requested: number | undefined): { effective: number; w
   return { effective: requested };
 }
 
-export async function runBackfillCommand(args: string[]): Promise<void> {
+/**
+ * #1963 (same class as reindex-frontmatter): takes the ALREADY-CONNECTED
+ * engine from cli.ts's dispatch. Building a second engine here deadlocked on
+ * the PGLite data-dir lock (cli.ts's `connectEngine()` already holds it in
+ * this same process) — every `gbrain backfill <kind>` on PGLite timed out
+ * after 30s. Engine lifecycle belongs to cli.ts's connect + teardown.
+ */
+export async function runBackfillCommand(engine: BrainEngine, args: string[]): Promise<void> {
   const cli = parseArgs(args);
   if (cli.help) { printHelp(); return; }
 
@@ -144,20 +151,10 @@ export async function runBackfillCommand(args: string[]): Promise<void> {
     process.exit(2);
   }
 
-  const config = loadConfig();
-  if (!config) {
-    console.error('No brain configured. Run: gbrain init');
-    process.exit(2);
-  }
-
   // X5 admission control — clamp concurrency to direct-pool capacity.
   const { effective: concurrency, warning } = clampConcurrency(cli.concurrency);
   if (warning) console.warn(warning);
 
-  const { createEngine } = await import('../core/engine-factory.ts');
-  const engine = await createEngine(toEngineConfig(config));
-  await engine.connect(toEngineConfig(config));
-
   if (cli.fresh) {
     await clearBackfillCheckpoint(engine, reg.spec.name);
     console.log(`Cleared checkpoint for backfill.${reg.spec.name}`);
@@ -192,7 +189,6 @@ export async function runBackfillCommand(args: string[]): Promise<void> {
   if (result.cappedByMaxRows) console.log(`  ⚠️  Capped by --max-rows; more remain.`);
   if (result.cappedByErrors) console.log(`  ⚠️  Capped by --max-errors at ${result.errors}.`);
 
-  await engine.disconnect();
   if (result.cappedByErrors) process.exit(1);
 }
 

src/commands/check-update.ts

@@ -45,12 +45,15 @@ 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. */
+/** Where the latest version is resolved from. The release train's source of
+ * truth is the `VERSION` file on master — same trusted host `fetchChangelog`
+ * already uses. GitHub releases are published from it per VERSION bump
+ * (`.github/workflows/release.yml`, #3521) and carry the binary assets, but
+ * this check deliberately does NOT read `releases/latest`: it was a permanent
+ * 404 before releases existed (#3520) and can still lag master. 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';
 

src/commands/config.ts

@@ -46,7 +46,14 @@ export async function runConfig(engine: BrainEngine, args: string[]) {
     }
     console.log('GBrain config:');
     for (const [k, v] of Object.entries(config)) {
-      const display = typeof v === 'string' ? redactConfigValue(k, v) : v;
+      // #575: objects interpolated into the template literal printed
+      // `[object Object]` — render them as JSON instead. Sensitive keys
+      // stay redacted whether the value is a string or an object.
+      const display = typeof v === 'string'
+        ? redactConfigValue(k, v)
+        : v !== null && typeof v === 'object'
+          ? (isSensitiveConfigKey(k) ? '***' : JSON.stringify(v))
+          : v;
       console.log(`  ${k}: ${display}`);
     }
     return;

src/commands/doctor-asset-paths.ts

@@ -0,0 +1,108 @@
+/**
+ * #1835 — storage_path resolution for the doctor `image_assets` check.
+ *
+ * `files.storage_path` rows written by a Windows gbrain install carry Windows
+ * drive paths (`D:/foo/img.jpg`, `D:\foo\img.jpg`). On POSIX,
+ * `path.isAbsolute()` is false for those, so the old code joined them onto the
+ * repo root and produced a path that can never exist — a false-positive
+ * "missing from disk, restore from git" WARN under WSL and macOS.
+ *
+ * Policy:
+ *   - win32: drive paths are absolute; stat them as-is.
+ *   - WSL (linux + "microsoft" in /proc/version): translate `D:/x` to
+ *     `<automount root>/d/x` (automount root read from /etc/wsl.conf
+ *     `[automount] root`, default `/mnt`) and stat that.
+ *   - any other POSIX host (macOS, plain Linux): the path is unresolvable on
+ *     this platform — report it as foreign so the caller SKIPS the stat
+ *     instead of inventing a path that will never exist.
+ *
+ * Kept in its own module (not doctor.ts) so the pure tests don't pull the
+ * 7k-line doctor dep graph, and so open PRs rewriting the image_assets block
+ * (e.g. a `resolveImageAssetPath` helper) can adopt it with a one-line call.
+ */
+import { readFileSync } from 'node:fs';
+import { join, posix, win32 } from 'node:path';
+
+const WINDOWS_DRIVE_RE = /^([A-Za-z]):[\\/](.*)$/;
+
+export interface AssetPathResolution {
+  /** Absolute path to stat, or null when the path is unresolvable here. */
+  abs: string | null;
+  /** True when storage_path is a Windows drive path this host cannot stat. */
+  foreign: boolean;
+}
+
+/**
+ * Resolve a files.storage_path to a stat-able absolute path.
+ * `opts.platform` / `opts.wslMountRoot` exist for tests; production callers
+ * pass neither (process.platform + detected WSL automount root).
+ * `wslMountRoot: null` means "not under WSL".
+ */
+export function resolveAssetPath(
+  storagePath: string,
+  repoRoot: string,
+  opts: { platform?: NodeJS.Platform; wslMountRoot?: string | null } = {},
+): AssetPathResolution {
+  const platform = opts.platform ?? process.platform;
+  if (platform !== 'win32') {
+    const m = WINDOWS_DRIVE_RE.exec(storagePath);
+    if (m) {
+      const root = opts.wslMountRoot !== undefined ? opts.wslMountRoot : detectWslMountRoot();
+      if (root === null) return { abs: null, foreign: true };
+      const abs = `${root.replace(/\/+$/, '')}/${m[1].toLowerCase()}/${m[2].replace(/\\/g, '/')}`;
+      return { abs, foreign: false };
+    }
+  }
+  // Platform-appropriate absoluteness (not the host's) so injected-platform
+  // tests behave identically everywhere; in production platform === host.
+  const isAbs = platform === 'win32' ? win32.isAbsolute(storagePath) : posix.isAbsolute(storagePath);
+  return {
+    abs: isAbs ? storagePath : join(repoRoot, storagePath),
+    foreign: false,
+  };
+}
+
+/**
+ * Extract the `[automount] root` value from /etc/wsl.conf content.
+ * Defaults to `/mnt` (WSL's own default) when absent/unparseable.
+ */
+export function parseWslAutomountRoot(conf: string): string {
+  let inAutomount = false;
+  for (const raw of conf.split(/\r?\n/)) {
+    const line = raw.replace(/[#;].*$/, '').trim();
+    if (line.startsWith('[')) {
+      inAutomount = /^\[automount\]$/i.test(line);
+      continue;
+    }
+    if (!inAutomount) continue;
+    const m = /^root\s*=\s*"?([^"]+?)"?\s*$/.exec(line);
+    if (m) return m[1];
+  }
+  return '/mnt';
+}
+
+let cachedWslMountRoot: string | null | undefined;
+
+/**
+ * Detect the WSL Windows-drive automount root. Returns null when not running
+ * under WSL (including macOS and plain Linux). Memoized per process.
+ */
+export function detectWslMountRoot(): string | null {
+  if (cachedWslMountRoot === undefined) cachedWslMountRoot = computeWslMountRoot();
+  return cachedWslMountRoot;
+}
+
+function computeWslMountRoot(): string | null {
+  if (process.platform !== 'linux') return null;
+  try {
+    // The standard WSL tell: kernel version string names Microsoft.
+    if (!/microsoft/i.test(readFileSync('/proc/version', 'utf8'))) return null;
+  } catch {
+    return null;
+  }
+  try {
+    return parseWslAutomountRoot(readFileSync('/etc/wsl.conf', 'utf8'));
+  } catch {
+    return '/mnt'; // WSL default when wsl.conf is absent.
+  }
+}

src/commands/doctor.ts

@@ -6,6 +6,11 @@ import { LATEST_VERSION, getIdleBlockers } from '../core/migrate.ts';
 import { checkResolvable } from '../core/check-resolvable.ts';
 import { autoFixDryViolations, type AutoFixReport, type FixOutcome } from '../core/dry-fix.ts';
 import { autoDetectSkillsDirReadOnly } from '../core/repo-root.ts';
+import {
+  SKILLS_MANIFEST_FILENAME,
+  verifySkillsManifest,
+  type SkillsManifest,
+} from '../core/skills-integrity.ts';
 import { loadOrDeriveManifest } from '../core/skill-manifest.ts';
 import { parseSkillFrontmatter } from '../core/skill-frontmatter.ts';
 import {
@@ -47,6 +52,13 @@ import { lagFromContentMs } from '../core/source-health.ts';
 import { CHUNKER_VERSION } from '../core/chunkers/code.ts';
 import { LINK_EXTRACTOR_VERSION_TS } from '../core/link-extraction.ts';
 import { isUndefinedColumnError } from '../core/utils.ts';
+import {
+  loadStorageConfig,
+  effectiveDbOnlyDirs,
+  DERIVE_PHASE_DB_ONLY_DEFAULTS,
+  findDbOnlyCollisions,
+} from '../core/storage-config.ts';
+import { slugifyPath } from '../core/sync.ts';
 // issue #1777: hidden_by_search_policy — count chunked pages withheld from
 // default search by the hard-exclude prefix policy. Reuses the canonical
 // exclude resolver + LIKE escaper + visibility clause so the doctor count can't
@@ -3667,6 +3679,198 @@ export async function checkUnverifiedExtractions(
   }
 }
 
+/**
+ * issue #2250 (reported by @615Works) — content_hash_duplicates.
+ *
+ * `gbrain import` run from the wrong root (one level too deep) drops the
+ * path prefix from every slug, leaving `people/x` and `x` coexisting with
+ * identical content. `dream --phase purge` never removes them (they aren't
+ * file-backed orphans) and nothing surfaced the condition. One GROUP BY —
+ * never an N² hash comparison — flags hash groups that contain BOTH a bare
+ * slug (no '/') and a path-prefixed slug.
+ */
+export async function checkContentHashDuplicates(engine: BrainEngine): Promise<Check> {
+  const name = 'content_hash_duplicates';
+  const fix = 'Fix: gbrain pages delete <bare-slug> for each pair, then gbrain pages purge-deleted --older-than 0';
+  try {
+    const rows = await engine.executeRaw<{ source_id: string; content_hash: string; slugs: string }>(
+      `SELECT source_id, content_hash,
+              string_agg(slug, '|' ORDER BY length(slug), slug) AS slugs
+         FROM pages
+        WHERE deleted_at IS NULL AND content_hash IS NOT NULL AND content_hash <> ''
+        GROUP BY source_id, content_hash
+       HAVING count(*) > 1
+          AND count(*) FILTER (WHERE strpos(slug, '/') = 0) > 0
+          AND count(*) FILTER (WHERE strpos(slug, '/') > 0) > 0
+        LIMIT 50`,
+    );
+    if (rows.length === 0) {
+      return { name, status: 'ok', message: 'No content-hash duplicate pairs (bare vs path-prefixed slugs)' };
+    }
+    let pairCount = 0;
+    const samples: string[] = [];
+    for (const r of rows) {
+      const slugs = String(r.slugs).split('|');
+      const prefixed = slugs.filter(s => s.includes('/'));
+      for (const bare of slugs.filter(s => !s.includes('/'))) {
+        const twin = prefixed.find(p => p.endsWith('/' + bare)) ?? prefixed[0];
+        pairCount++;
+        if (samples.length < 5) samples.push(`${bare} <-> ${twin}`);
+      }
+    }
+    return {
+      name,
+      status: 'warn',
+      message: `${pairCount} content-hash duplicate pair(s) detected (same content, differing slug forms — usually an import run from the wrong root, which drops the path prefix). Sample: ${samples.join('; ')}. ${fix}`,
+      details: { pair_count: pairCount, hash_groups: rows.length, sample_pairs: samples },
+    };
+  } catch (e) {
+    return { name, status: 'warn', message: `Could not check content-hash duplicates: ${(e as Error).message}` };
+  }
+}
+
+/** Walk a repo for markdown files and return their slugified (lowercased) slugs. */
+function collectMarkdownSlugs(root: string): Set<string> {
+  const out = new Set<string>();
+  const stack = [''];
+  while (stack.length > 0) {
+    const rel = stack.pop()!;
+    let entries;
+    try {
+      entries = readdirSync(rel ? join(root, rel) : root, { withFileTypes: true });
+    } catch {
+      continue;
+    }
+    for (const e of entries) {
+      if (e.name.startsWith('.') || e.name === 'node_modules') continue;
+      const childRel = rel ? `${rel}/${e.name}` : e.name;
+      if (e.isDirectory()) stack.push(childRel);
+      else if (/\.mdx?$/i.test(e.name)) out.add(slugifyPath(childRel).toLowerCase());
+    }
+  }
+  return out;
+}
+
+/**
+ * issue #2784 (reported by @alexputici) — undeclared_db_only_pages.
+ *
+ * A markdown page with no backing file that sits outside every declared
+ * db_only path is invisible to any file-lane backup/recovery reasoning: an
+ * operator auditing "what would survive a DB loss" gets a silently wrong
+ * answer. The engine's own derive-phase output prefixes
+ * (DERIVE_PHASE_DB_ONLY_DEFAULTS) count as implicitly declared so the check
+ * stays quiet on healthy brains. Deliberately allowed to stat the source
+ * repo (the one thing the SQL-only check registry could never see).
+ */
+export async function checkUndeclaredDbOnlyPages(engine: BrainEngine): Promise<Check> {
+  const name = 'undeclared_db_only_pages';
+  try {
+    const sources = await engine.executeRaw<{ id: string; local_path: string | null }>(
+      `SELECT id, local_path FROM sources WHERE local_path IS NOT NULL`,
+    );
+    const checkable = sources.filter(s => s.local_path && existsSync(s.local_path));
+    if (checkable.length === 0) {
+      return { name, status: 'ok', message: 'Not applicable (no sources with a local repo path on this host)' };
+    }
+    let total = 0;
+    const samples: string[] = [];
+    const perSource: Record<string, number> = {};
+    for (const src of checkable) {
+      let declared: string[] = [];
+      try {
+        declared = loadStorageConfig(src.local_path)?.db_only ?? [];
+      } catch {
+        // invalid gbrain.yml — treated as no declarations; the sync path
+        // already surfaces the config error itself.
+      }
+      const dbOnlyDirs = effectiveDbOnlyDirs(declared);
+      const rows = await engine.executeRaw<{ slug: string }>(
+        `SELECT slug FROM pages WHERE deleted_at IS NULL AND source_id = $1 AND page_kind = 'markdown'`,
+        [src.id],
+      );
+      if (rows.length === 0) continue;
+      const backed = collectMarkdownSlugs(src.local_path!);
+      for (const { slug } of rows) {
+        if (dbOnlyDirs.some(dir => slug.startsWith(dir))) continue;
+        if (backed.has(slug)) continue;
+        total++;
+        perSource[src.id] = (perSource[src.id] ?? 0) + 1;
+        if (samples.length < 5) samples.push(`${slug} (src=${src.id})`);
+      }
+    }
+    if (total === 0) {
+      return {
+        name,
+        status: 'ok',
+        message: `Every DB page is file-backed or under a declared/default db_only path (derive-phase defaults: ${DERIVE_PHASE_DB_ONLY_DEFAULTS.join(' ')})`,
+      };
+    }
+    return {
+      name,
+      status: 'warn',
+      message: `${total} DB page(s) have no backing file and sit outside every declared/default db_only path — invisible to file-lane backup/recovery. Sample: ${samples.join('; ')}. Fix: restore or export the files, or declare their prefixes under storage.db_only in gbrain.yml (derive-phase defaults already cover: ${DERIVE_PHASE_DB_ONLY_DEFAULTS.join(' ')})`,
+      details: { total, per_source: perSource, sample_slugs: samples },
+    };
+  } catch (e) {
+    return { name, status: 'warn', message: `Could not check undeclared db-only pages: ${(e as Error).message}` };
+  }
+}
+
+/**
+ * issue #2788 (reported by @alexputici) — db_only_collector_collision.
+ *
+ * Declaring a collector's output dir in storage.db_only silently kills its
+ * ingestion: manageGitignore auto-gitignores the dir, the git-walking sync
+ * never sees the files, and import honors .gitignore too — everything stays
+ * green while nothing reaches the DB (a 7-week outage in the field). The
+ * recipe's `output_paths` frontmatter is the ground truth; the same warning
+ * also fires at .gitignore-write time inside sync's manageGitignore.
+ */
+export async function checkDbOnlyCollectorCollision(
+  engine: BrainEngine,
+  opts?: { collectors?: Array<{ id: string; output_path: string }> },
+): Promise<Check> {
+  const name = 'db_only_collector_collision';
+  try {
+    let collectors = opts?.collectors;
+    if (!collectors) {
+      const { getConfiguredCollectorOutputs } = await import('./integrations.ts');
+      collectors = getConfiguredCollectorOutputs();
+    }
+    if (collectors.length === 0) {
+      return { name, status: 'ok', message: 'No configured collectors declare output paths' };
+    }
+    const sources = await engine.executeRaw<{ id: string; local_path: string | null }>(
+      `SELECT id, local_path FROM sources WHERE local_path IS NOT NULL`,
+    );
+    const hits: string[] = [];
+    for (const src of sources) {
+      if (!src.local_path || !existsSync(src.local_path)) continue;
+      let dbOnly: string[] = [];
+      try {
+        dbOnly = loadStorageConfig(src.local_path)?.db_only ?? [];
+      } catch {
+        continue;
+      }
+      if (dbOnly.length === 0) continue;
+      for (const hit of findDbOnlyCollisions(collectors, dbOnly)) {
+        hits.push(`collector '${hit.id}' writes to '${hit.output_path}' which is inside db_only path '${hit.db_only_dir}' (source ${src.id})`);
+      }
+    }
+    if (hits.length === 0) {
+      return { name, status: 'ok', message: 'No collector output dir falls inside a db_only path' };
+    }
+    return {
+      name,
+      status: 'warn',
+      message: `${hits.length} collector/db_only collision(s): ${hits.join('; ')}. db_only dirs are auto-gitignored, so sync AND import silently skip files there — the collector runs green while nothing reaches the DB. Fix: remove the prefix from storage.db_only in gbrain.yml, or move the collector output.`,
+      details: { collisions: hits },
+    };
+  } catch (e) {
+    return { name, status: 'warn', message: `Could not check collector/db_only collisions: ${(e as Error).message}` };
+  }
+}
+
 /**
  * issue #1678 — extract_atoms_backlog doctor check.
  *
@@ -4349,8 +4553,18 @@ export async function checkCycleFreshness(
         : `'${source.id}'`;
       const raw = source.config?.last_full_cycle_at;
       if (typeof raw !== 'string') {
+        // #2540: WARN, not FAIL. This check iterates EVERY local_path source,
+        // so on a multi-source install where only some vaults are cycled
+        // (e.g. one nightly `gbrain dream --dir <vault>`), a never-cycled
+        // sibling source turned doctor permanently red — which erodes the
+        // check's signal until real staleness hides inside the noise (the
+        // reporter's install masked genuinely stale sources for weeks this
+        // way). "Never cycled" also fires on a source added minutes ago.
+        // A source that HAS cycled and then went stale still escalates
+        // through the warn/fail age thresholds below — that is the
+        // regression signal this check exists for.
         issues.push(`Source ${display} has never completed a full cycle`);
-        hasFailures = true;
+        hasWarnings = true;
         continue;
       }
       const last = new Date(raw).getTime();
@@ -4386,7 +4600,7 @@ export async function checkCycleFreshness(
       return {
         name: 'cycle_freshness',
         status: 'warn',
-        message: `${issues.join('; ')}.`,
+        message: `${issues.join('; ')}. Run \`gbrain dream --source <id>\` to cycle a source, or start \`gbrain autopilot\`.`,
       };
     }
     return {
@@ -4835,6 +5049,15 @@ export async function buildChecks(
     checks.push(skillBrainFirstCheck(skillsDir));
   }
 
+  // 2c. Skills manifest integrity (#159): tamper-evidence, not signatures.
+  // Compares the skills tree against its committed skills.lock.json and
+  // WARNS on drift — never fails, never blocks. No manifest (e.g. a user
+  // workspace skills dir, or a compiled binary far from the repo) → ok/skip.
+  // SKILL group — gated.
+  if (scope === 'all' && skillsDir) {
+    checks.push(skillsManifestIntegrityCheck(skillsDir));
+  }
+
   // 3. Half-migrated Minions detection (filesystem-only).
   // If completed.jsonl has any status:"partial" entry with no later
   // status:"complete" for the same version, the install is mid-migration.
@@ -5592,6 +5815,42 @@ export async function buildChecks(
     // Best-effort filesystem-hygiene check; never block doctor.
   }
 
+  // 3f. npm_squat (#505). The npm registry name `gbrain` belongs to an
+  // unrelated third-party package — this project is NOT distributed on npm.
+  // A reflexive `npm i -g gbrain` / `bun add -g gbrain` installs something
+  // unrelated that can shadow the real binary on PATH. Classify every
+  // `gbrain` that `which -a` finds (pure helpers in
+  // src/core/npm-squat-check.ts) and warn when an unrelated install wins on
+  // PATH or the entry is broken. Skips silently when gbrain isn't on PATH
+  // at all (e.g. running via `bun src/cli.ts`).
+  try {
+    const { execSync } = await import('node:child_process');
+    let candidates: string[] = [];
+    try {
+      candidates = execSync('which -a gbrain', {
+        encoding: 'utf8',
+        stdio: ['ignore', 'pipe', 'ignore'],
+      })
+        .split('\n')
+        .map((s) => s.trim())
+        .filter(Boolean);
+    } catch {
+      // `which` exits non-zero when gbrain isn't on PATH (or is missing
+      // entirely on this platform) — nothing to check.
+    }
+    const { assessGbrainBinaries } = await import('../core/npm-squat-check.ts');
+    const assessment = assessGbrainBinaries(candidates);
+    if (assessment.status !== 'skip') {
+      checks.push({
+        name: 'npm_squat',
+        status: assessment.status,
+        message: assessment.message,
+      });
+    }
+  } catch {
+    // Best-effort environment check; never block doctor.
+  }
+
   // 3b-multi-source. Multi-source drift (v0.31.8 — D8 + D17 + OV12 + OV13).
   // Pre-v0.30.3 putPage misrouted multi-source writes to (default, slug).
   // For each non-default source with local_path set, walk the FS and surface
@@ -6056,7 +6315,10 @@ export async function buildChecks(
     } else {
       // Live embed test
       const start = Date.now();
-      const vec = await embedOne('gbrain doctor embedding smoke test');
+      // Doctor is itself the provider-health circuit breaker. A permanent
+      // billing/auth failure must be sampled once, not multiplied by the AI
+      // SDK's default retries (which can add ~90s to every health check).
+      const vec = await embedOne('gbrain doctor embedding smoke test', { maxRetries: 0 });
       const ms = Date.now() - start;
       const actualDims = vec.length;
 
@@ -7536,33 +7798,44 @@ export async function buildChecks(
         `SELECT storage_path FROM files WHERE mime_type LIKE 'image/%' LIMIT 1000`
       );
       let vanished = 0;
+      let foreign = 0;
       const vanishedPaths: string[] = [];
       const fs = await import('node:fs');
-      const nodePath = await import('node:path');
+      const { resolveAssetPath } = await import('./doctor-asset-paths.ts');
       // storage_path is repo-relative for sync-ingested assets. Resolving
       // against cwd made this check a false-positive WARN whenever doctor
       // ran outside the brain repo.
       const repoRoot = (await engine.getConfig('sync.repo_path')) ?? process.cwd();
       for (const r of rows) {
-        const abs = nodePath.isAbsolute(r.storage_path)
-          ? r.storage_path
-          : nodePath.join(repoRoot, r.storage_path);
+        // #1835: Windows drive paths (D:/…) translate to the WSL automount
+        // (/mnt/d/…) under WSL, and are SKIPPED (not "missing") on hosts
+        // where they cannot exist (macOS / plain Linux) — never joined onto
+        // repoRoot, which produced a false "restore from git" WARN.
+        const resolved = resolveAssetPath(r.storage_path, repoRoot);
+        if (resolved.abs === null) {
+          foreign++;
+          continue;
+        }
         try {
-          fs.statSync(abs);
+          fs.statSync(resolved.abs);
         } catch {
           vanished++;
           if (vanishedPaths.length < 5) vanishedPaths.push(r.storage_path);
         }
       }
+      const checked = rows.length - foreign;
+      const foreignNote = foreign > 0
+        ? ` (${foreign} Windows-drive path(s) skipped — not resolvable on this platform)`
+        : '';
       if (rows.length === 0) {
         checks.push({ name: 'image_assets', status: 'ok', message: 'No image assets indexed yet' });
       } else if (vanished === 0) {
-        checks.push({ name: 'image_assets', status: 'ok', message: `${rows.length} image(s) all present on disk` });
+        checks.push({ name: 'image_assets', status: 'ok', message: `${checked} image(s) all present on disk${foreignNote}` });
       } else {
         checks.push({
           name: 'image_assets',
           status: 'warn',
-          message: `${vanished} of ${rows.length} image(s) missing from disk (e.g. ${vanishedPaths.join(', ')}). ` +
+          message: `${vanished} of ${checked} image(s) missing from disk (e.g. ${vanishedPaths.join(', ')})${foreignNote}. ` +
                    `Fix: restore from git, or \`gbrain sync --skip-failed\` to acknowledge.`,
         });
       }
@@ -7622,6 +7895,14 @@ export async function buildChecks(
     // per-source dispatch gate sees.
     progress.heartbeat('cycle_freshness');
     checks.push(await checkCycleFreshness(engine));
+    // Silent-failure batch (#2250 / #2784 / #2788): wrong-root import
+    // duplicates, undeclared DB-only pages, collector-output-in-db_only.
+    progress.heartbeat('content_hash_duplicates');
+    checks.push(await checkContentHashDuplicates(engine));
+    progress.heartbeat('undeclared_db_only_pages');
+    checks.push(await checkUndeclaredDbOnlyPages(engine));
+    progress.heartbeat('db_only_collector_collision');
+    checks.push(await checkDbOnlyCollectorCollision(engine));
   }
 
   // v0.32.3 search-lite — mode + eval_drift surfaces. Status stays 'ok' per
@@ -7856,6 +8137,51 @@ export function skillConformanceCheck(skillsDir: string): Check {
  * Test seam: pure function, no `process.exit`. Direct call from tests
  * with a synthetic skills dir under tempdir.
  */
+/**
+ * Skills-manifest integrity check (#159). Verifies the skills tree against
+ * the committed skills.lock.json tamper-evidence manifest. Advisory only:
+ * drift is a WARN (local edits are legitimate), and a missing/unreadable
+ * manifest is an ok/skip — a user's workspace skills dir or a compiled
+ * binary far from the repo has no manifest, and that is not a problem.
+ */
+export function skillsManifestIntegrityCheck(skillsDir: string): Check {
+  const name = 'skills_manifest_integrity';
+  const manifestPath = join(skillsDir, SKILLS_MANIFEST_FILENAME);
+  if (!existsSync(manifestPath)) {
+    return { name, status: 'ok', message: `No ${SKILLS_MANIFEST_FILENAME} in ${skillsDir} — integrity check not applicable` };
+  }
+  let drift: ReturnType<typeof verifySkillsManifest>;
+  let tracked: number;
+  try {
+    const manifest = JSON.parse(readFileSync(manifestPath, 'utf-8')) as SkillsManifest;
+    tracked = Object.keys(manifest).length;
+    drift = verifySkillsManifest(skillsDir, manifest);
+  } catch (err) {
+    // Fail-safe: an unreadable/unparseable manifest or a filesystem error
+    // skips the check rather than warning — this check must never block.
+    const msg = err instanceof Error ? err.message : String(err);
+    return { name, status: 'ok', message: `Could not verify ${SKILLS_MANIFEST_FILENAME} (${msg}) — integrity check skipped` };
+  }
+  const total = drift.modified.length + drift.missing.length + drift.extra.length;
+  if (total === 0) {
+    return { name, status: 'ok', message: `${tracked} bundled skill files match ${SKILLS_MANIFEST_FILENAME}` };
+  }
+  const sample = (files: string[]): string =>
+    files.slice(0, 5).join(', ') + (files.length > 5 ? `, … +${files.length - 5} more` : '');
+  const parts: string[] = [];
+  if (drift.modified.length > 0) parts.push(`${drift.modified.length} modified (${sample(drift.modified)})`);
+  if (drift.missing.length > 0) parts.push(`${drift.missing.length} missing (${sample(drift.missing)})`);
+  if (drift.extra.length > 0) parts.push(`${drift.extra.length} extra (${sample(drift.extra)})`);
+  return {
+    name,
+    status: 'warn',
+    message:
+      `skills/ drifted from ${SKILLS_MANIFEST_FILENAME} (advisory — local edits are fine): ${parts.join('; ')}. ` +
+      `If intentional, regenerate: bun run scripts/generate-skills-manifest.ts`,
+    details: { modified: drift.modified, missing: drift.missing, extra: drift.extra },
+  };
+}
+
 export function skillBrainFirstCheck(skillsDir: string): Check {
   let manifest: ReturnType<typeof loadOrDeriveManifest>;
   try {

src/commands/embed.ts

@@ -19,10 +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 { AITransientError } from '../core/ai/errors.ts';
 import { wrapChunkTextsForStoredMode } from '../core/embedding-context.ts';
 import { titleTierCorpusGeneration } from '../core/contextual-retrieval-service.ts';
 import type { Page } from '../core/types.ts';
 
+/** #3037: cap failure samples so a corpus-wide outage doesn't bloat --json. */
+const FAILURE_SAMPLE_CAP = 10;
+
+/**
+ * #3037: record embed failures on the run result. `chunkCount` is the number
+ * of chunks left un-embedded by this failure (1 for page-level errors where
+ * the chunk count isn't known at the catch site).
+ */
+function recordFailure(result: EmbedResult, chunkCount: number, slug: string, e: unknown): void {
+  result.failures += chunkCount;
+  if (result.failure_samples.length < FAILURE_SAMPLE_CAP) {
+    result.failure_samples.push(`${slug}: ${e instanceof Error ? e.message : String(e)}`);
+  }
+}
+
 /**
  * #3507 — after a plain re-embed fully re-embedded a `per_chunk_synopsis`
  * page at the title-only tier (see wrapChunkTextsForStoredMode), restamp the
@@ -166,6 +182,20 @@ export interface EmbedResult {
   total_chunks: number;
   /** Number of pages processed (whether or not they had stale chunks). */
   pages_processed: number;
+  /**
+   * #3037: chunks that FAILED to embed this run (batch failures + per-chunk
+   * isolation failures). Callers must not read total silence as success:
+   * `src/cli.ts` turns `failures > 0` into a non-zero exit verdict (mirrors
+   * the `import` errors>0 guard), and structured consumers (--json, minion
+   * handlers) can surface it. 0 on a clean run. Additive field.
+   */
+  failures: number;
+  /**
+   * #3037: up to 10 `slug: error-message` samples of what failed, so the
+   * operator gets a diagnosis without scrolling stderr. Capped so a
+   * corpus-wide outage doesn't bloat structured output. Additive field.
+   */
+  failure_samples: string[];
   /** True if this run was a dry-run. */
   dryRun: boolean;
   /**
@@ -284,6 +314,8 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
     would_embed: 0,
     total_chunks: 0,
     pages_processed: 0,
+    failures: 0,
+    failure_samples: [],
     dryRun: !!opts.dryRun,
   };
 
@@ -293,6 +325,11 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
       try {
         await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal, opts.quiet);
       } catch (e: unknown) {
+        if (isAborted(opts.signal)) break; // shutdown, not a failure
+        // #3037: a page-level error (not found, DB write) must not exit 0.
+        // Chunk-level embed failures are counted inside embedPage; this
+        // counts the page itself (chunk count unknown at this site).
+        recordFailure(result, 1, s, e);
         serr(`  Error embedding ${s}: ${e instanceof Error ? e.message : e}`);
       }
     }
@@ -535,6 +572,12 @@ export async function runEmbed(engine: BrainEngine, args: string[]): Promise<Emb
   try {
     const result = await runEmbedCore(engine, opts);
     if (progressStarted) progress.finish();
+    // #3037: loud end-of-run summary so failures are visible even when the
+    // per-page stderr lines scrolled away. cli.ts turns failures>0 into a
+    // non-zero exit verdict.
+    if (result.failures > 0) {
+      serr(`[embed] ${result.failures} chunk(s) failed to embed. First error: ${result.failure_samples[0] ?? 'unknown'}`);
+    }
     return result;
   } catch (e) {
     if (progressStarted) progress.finish();
@@ -623,10 +666,32 @@ async function embedPage(
   // 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 });
+  // #3037: per-chunk failure isolation — one bad chunk must not leave the
+  // page's sibling chunks NULL. The wrapped texts (computed once) feed the
+  // fan-out too, so an isolation retry never strips the prefixes. Total
+  // embed failure is recorded here (where the chunk count is known) and
+  // swallowed: the page stays NULL exactly as before, but the run now
+  // reports it (result.failures → non-zero exit) instead of pretending
+  // success. Abort (shutdown) still propagates.
+  let embeddings: (Float32Array | null)[];
+  let failed = 0;
+  let firstError: unknown;
+  try {
+    ({ embeddings, failed, firstError } = await embedPageTexts(
+      wrapChunkTextsForStoredMode(page, toEmbed),
+      signal ? { abortSignal: signal } : {},
+    ));
+  } catch (e: unknown) {
+    if (isAborted(signal)) throw e;
+    recordFailure(result, toEmbed.length, slug, e);
+    result.pages_processed++;
+    serr(`  Error embedding ${slug}: ${e instanceof Error ? e.message : e}`);
+    return;
+  }
   const embeddingMap = new Map<number, Float32Array>();
   for (let j = 0; j < toEmbed.length; j++) {
-    embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
+    const emb = embeddings[j];
+    if (emb) embeddingMap.set(toEmbed[j].chunk_index, emb);
   }
   const updated: ChunkInput[] = chunks.map(c => preserveCodeMetadata(c, {
     chunk_index: c.chunk_index,
@@ -643,16 +708,21 @@ async function embedPage(
   // Guard: only stamp when EVERY chunk was (re)embedded this pass. If some
   // chunks were preserved from a prior embed (unknown/old provenance), the
   // page is mixed — don't claim it's current. `embed --all` fully re-embeds
-  // such a page and then stamps it.
-  if (toEmbed.length === chunks.length) {
+  // such a page and then stamps it. #3037: a partial failure leaves failed
+  // chunks NULL, so don't stamp then either.
+  if (failed === 0 && 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.embedded += toEmbed.length - failed;
+  if (failed > 0) {
+    recordFailure(result, failed, slug, firstError);
+    serr(`  ${slug}: ${failed} chunk(s) failed to embed; embedded the other ${toEmbed.length - failed}`);
+  }
   result.pages_processed++;
-  if (!quiet) slog(`${slug}: embedded ${toEmbed.length} chunks`);
+  if (!quiet) slog(`${slug}: embedded ${toEmbed.length - failed} chunks`);
 }
 
 /**
@@ -791,11 +861,18 @@ async function embedAll(
 
     try {
       // #3507: reproduce the page's stored wrapping convention (see embedPage).
-      const embeddings = await embedBatch(wrapChunkTextsForStoredMode(page, toEmbed));
+      // #3037: per-chunk failure isolation — one bad chunk costs one chunk,
+      // not the whole page's siblings. The wrapped texts feed the fan-out
+      // too, so an isolation retry never strips the contextual prefixes.
+      const { embeddings, failed, firstError } = await embedPageTexts(
+        wrapChunkTextsForStoredMode(page, toEmbed),
+        signal ? { abortSignal: signal } : {},
+      );
       // Build a map of new embeddings by chunk_index
       const embeddingMap = new Map<number, Float32Array>();
       for (let j = 0; j < toEmbed.length; j++) {
-        embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
+        const emb = embeddings[j];
+        if (emb) embeddingMap.set(toEmbed[j].chunk_index, emb);
       }
       // Preserve ALL chunks, only update embeddings for stale ones.
       // preserveCodeMetadata threads code-chunk metadata (#769) so re-embed
@@ -809,17 +886,30 @@ async function embedAll(
       }));
       await observed(pacer, () => engine.upsertChunks(page.slug, updated, pageOpts));
       // v0.41.31: stamp embedding provenance so a later model swap is
-      // detectable as stale.
-      await observed(pacer, () =>
-        engine.setPageEmbeddingSignature(page.slug, { sourceId: pageSourceId, signature }),
-      );
-      // #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;
+      // detectable as stale. #3037: not on partial failure — failed chunks
+      // stay NULL under unknown provenance.
+      if (failed === 0) {
+        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. #3037: gated on
+        // failed === 0 — a partially-failed page was NOT fully re-embedded,
+        // so restamping would make contextual_retrieval_mode lie again
+        // (the exact #3461 bug).
+        await observed(pacer, () =>
+          restampIfDemotedToTitleTier(engine, page, page.slug, pageSourceId),
+        );
+      }
+      result.embedded += toEmbed.length - failed;
+      if (failed > 0) {
+        recordFailure(result, failed, page.slug, firstError);
+        serr(`\n  ${page.slug}: ${failed} chunk(s) failed to embed; embedded the other ${toEmbed.length - failed}`);
+      }
     } catch (e: unknown) {
+      // #3037: count the darkened page so the run can't exit 0 (abort is a
+      // shutdown, not a failure).
+      if (!isAborted(signal)) recordFailure(result, toEmbed.length, page.slug, e);
       serr(`\n  Error embedding ${page.slug}: ${e instanceof Error ? e.message : e}`);
     }
 
@@ -1037,10 +1127,8 @@ async function embedAllStale(
   let afterUpdatedAt: string | null = null;
   let totalChunksLoaded = 0;
   let budgetExitNotified = false;
-  // #1946 (OV2a): track chunks that errored out so a catch-up pass that finishes
-  // with stale chunks still remaining (un-embeddable for a non-transient reason)
-  // surfaces that loudly instead of looking like a clean run.
-  let embedFailures = 0;
+  // #1946 (OV2a) + #3037: embed failures are tracked on result.failures so
+  // the catch-up warning below AND the CLI exit verdict both see them.
 
   // E-3 (paced-backfill): bounded end-of-run re-entry. A longer paced run gives
   // a live writer (sync / put_page) more time to insert NEW stale rows BEHIND
@@ -1137,12 +1225,19 @@ async function embedAllStale(
           // 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 });
+          // #3037: per-chunk failure isolation — one bad chunk costs one
+          // chunk, not the whole page's siblings. The wrapped texts feed the
+          // fan-out too, so an isolation retry never strips the prefixes.
+          const { embeddings, failed, firstError } = await embedPageTexts(
+            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>();
           for (let j = 0; j < stale.length; j++) {
-            staleIdxToEmbedding.set(stale[j].chunk_index, embeddings[j]);
+            const emb = embeddings[j];
+            if (emb) staleIdxToEmbedding.set(stale[j].chunk_index, emb);
           }
           // preserveCodeMetadata threads code-chunk metadata (#769) so the
           // autopilot --stale path doesn't clobber language/symbol_name/etc
@@ -1160,7 +1255,8 @@ async function embedAllStale(
           // A partially-stale page keeps preserved chunks of unknown/old
           // provenance, so don't claim it's current. (After invalidate, a
           // signature-drifted page IS fully stale → this stamps it.)
-          if (signature && stale.length === existing.length) {
+          // #3037: not on partial failure — failed chunks stay NULL.
+          if (signature && failed === 0 && stale.length === existing.length) {
             await observed(pacer, () =>
               engine.setPageEmbeddingSignature(slug, { sourceId: keySourceId, signature }),
             );
@@ -1168,17 +1264,24 @@ async function embedAllStale(
           // #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) {
+          // #3037: `failed === 0` is part of "fully re-embedded" — if the
+          // per-chunk isolation left some chunks NULL, restamping would make
+          // contextual_retrieval_mode lie again (the exact #3461 bug).
+          if (failed === 0 && stale.length === existing.length) {
             await observed(pacer, () =>
               restampIfDemotedToTitleTier(engine, pageRow, slug, keySourceId),
             );
           }
-          result.embedded += stale.length;
+          result.embedded += stale.length - failed;
+          if (failed > 0) {
+            recordFailure(result, failed, slug, firstError);
+            serr(`\n  ${slug}: ${failed} chunk(s) failed to embed; embedded the other ${stale.length - failed}`);
+          }
         } catch (e: unknown) {
           // Budget/abort-fired cancellations are expected on the way out; don't
           // spam per-page "Error embedding" lines when we're shutting down.
           if (effectiveSignal.aborted) return;
-          embedFailures++;
+          recordFailure(result, stale.length, slug, e);
           serr(`\n  Error embedding ${slug}: ${e instanceof Error ? e.message : e}`);
         }
         totalProcessedPages++;
@@ -1231,14 +1334,14 @@ async function embedAllStale(
   // chunks unembedded means those chunks are stuck (a non-transient embed
   // failure), not that we ran out of time. Surface it loudly so it doesn't read
   // as a clean run — re-running won't help until the underlying failure is fixed.
-  if (staleOpts?.catchUp && !effectiveSignal.aborted && embedFailures > 0) {
+  if (staleOpts?.catchUp && !effectiveSignal.aborted && result.failures > 0) {
     const remaining = await engine.countStaleChunks(
       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.`);
+      serr(`\n  [embed] catch-up finished but ${remaining} chunk(s) remain stale after ${result.failures} embed failure(s). These are not embeddable as-is; re-running won't clear them until the underlying error is resolved.`);
     }
   }
 }
@@ -1358,12 +1461,7 @@ export async function embedBatchWithBackoff(
       // If the budget fired we may have been aborted mid-fetch; bubble out.
       if (signal?.aborted) throw e;
       const msg = e instanceof Error ? e.message : String(e);
-      // D4: structured detection first (handles gateway-wrapped errors via
-      // cause chain); message-match as fallback for providers whose wrappers
-      // strip `cause.status`.
-      const isRateLimit = detect429FromCause(e)
-        || /rate.?limit|429/i.test(msg);
-      if (!isRateLimit || attempt === MAX_RATE_LIMIT_RETRIES) throw e;
+      if (!isRateLimitError(e) || attempt === MAX_RATE_LIMIT_RETRIES) throw e;
 
       const delayMs = parseRetryDelayMs(msg);
       serr(`  [rate-limit] attempt ${attempt + 1}/${MAX_RATE_LIMIT_RETRIES}, waiting ${delayMs}ms...`);
@@ -1373,3 +1471,86 @@ export async function embedBatchWithBackoff(
   // Unreachable, but TypeScript needs it.
   return embedBatch(texts);
 }
+
+/**
+ * 429 judgment shared by embedBatchWithBackoff (retry decision) and
+ * embedPageTexts (fan-out decision). D4: structured detection first
+ * (gateway-wrapped errors via cause chain); message-match as fallback for
+ * providers whose wrappers strip `cause.status`.
+ */
+function isRateLimitError(e: unknown): boolean {
+  const msg = e instanceof Error ? e.message : String(e);
+  return detect429FromCause(e) || /rate.?limit|429/i.test(msg);
+}
+
+/** Walk the cause chain (like detect429FromCause) for the first HTTP status. */
+function statusFromCause(e: unknown): number | undefined {
+  let cur: unknown = e;
+  for (let depth = 0; depth < 5 && cur !== undefined && cur !== null; depth++) {
+    const obj = cur as { status?: unknown; statusCode?: unknown; cause?: unknown };
+    if (typeof obj.status === 'number') return obj.status;
+    if (typeof obj.statusCode === 'number') return obj.statusCode;
+    cur = obj.cause;
+  }
+  return undefined;
+}
+
+/**
+ * #3037: embed one page's chunk texts with per-chunk failure isolation.
+ *
+ * All three embed paths used to send a page's chunks in ONE
+ * embedBatch call, so one bad chunk (e.g. an oversized chunk the provider
+ * 400s) left EVERY sibling chunk NULL — an ~8.6x blast radius. This wrapper
+ * tries the batch first (the cheap, common path), and only on a
+ * PERMANENT-looking batch failure retries once per chunk so one bad chunk
+ * costs one chunk.
+ *
+ * Cost bounding — when we do NOT fan out (rethrow instead):
+ *   - 429 / rate limit: embedBatchWithBackoff already retried with backoff;
+ *     fanning out N single-chunk calls would hammer the same limiter N-fold.
+ *   - AITransientError (5xx / network / unknown, per normalizeAIError): the
+ *     batch CONTENT isn't the problem, so isolation can't help — during an
+ *     outage it would just multiply failing calls per page.
+ *   - 401/403 (auth): nothing chunk-specific; every call would fail.
+ * When we DO fan out (permanent request-shaped 4xx like 400/413/422), the
+ * per-chunk pass happens at most ONCE per page per run and re-spends roughly
+ * the same tokens the failed batch would have — bounded, no recursion. A
+ * fresh 429 arising DURING the fan-out still gets the normal backoff (each
+ * single-chunk call goes through embedBatchWithBackoff).
+ *
+ * Throws when nothing could be embedded (total failure — same contract as
+ * the pre-#3037 single batch call). Returns `null` at the index of each
+ * failed chunk otherwise.
+ */
+async function embedPageTexts(
+  texts: string[],
+  opts: EmbedBatchWithBackoffOpts = {},
+): Promise<{ embeddings: (Float32Array | null)[]; failed: number; firstError?: unknown }> {
+  try {
+    return { embeddings: await embedBatchWithBackoff(texts, opts), failed: 0 };
+  } catch (e: unknown) {
+    if (opts.abortSignal?.aborted) throw e; // shutdown, not a chunk problem
+    if (texts.length <= 1) throw e; // nothing to isolate
+    if (isRateLimitError(e) || e instanceof AITransientError) throw e;
+    const status = statusFromCause(e);
+    if (status === 401 || status === 403) throw e;
+
+    const embeddings: (Float32Array | null)[] = [];
+    let failed = 0;
+    let firstError: unknown;
+    for (const t of texts) {
+      try {
+        const single = await embedBatchWithBackoff([t], opts);
+        embeddings.push(single[0] ?? null);
+        if (single[0] === undefined) { failed++; firstError ??= e; }
+      } catch (chunkErr: unknown) {
+        if (opts.abortSignal?.aborted) throw chunkErr;
+        embeddings.push(null);
+        failed++;
+        firstError ??= chunkErr;
+      }
+    }
+    if (failed === texts.length) throw firstError ?? e; // total failure: pre-#3037 contract
+    return { embeddings, failed, firstError };
+  }
+}

src/commands/eval-cross-modal.ts

@@ -78,7 +78,7 @@ FLAGS:
                            cycle is 3 model calls; verdict aggregates over them.
   --slot-a-model <id>      Override default 'openai:gpt-5.2'.
   --slot-b-model <id>      Override default 'anthropic:claude-opus-4-7'.
-  --slot-c-model <id>      Override default 'google:gemini-1.5-pro'.
+  --slot-c-model <id>      Override default 'deepseek:deepseek-v4-pro'.
   --receipt-dir <path>     Default: gbrainPath('eval-receipts').
   --max-tokens N           Output token budget per call. Default: 4000.
   --json                   Emit final aggregate as JSON to stdout (progress to stderr).

src/commands/extract.ts

@@ -43,7 +43,7 @@ import {
 } from '../core/link-extraction.ts';
 import { createProgress } from '../core/progress.ts';
 import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
-import { pathToSlug, pruneDir, isSyncable } from '../core/sync.ts';
+import { pathToSlug, slugifyPath, pruneDir, isSyncable } from '../core/sync.ts';
 // v0.41.18.0: withRetry + isRetryableConnError + WithRetryOpts moved to
 // src/core/retry.ts as the canonical primitive. Engine methods
 // (addLinksBatch/addTimelineEntriesBatch/upsertChunks) now self-retry via
@@ -269,14 +269,24 @@ export function extractMarkdownLinks(content: string): { name: string; relTarget
 export function resolveSlug(fileDir: string, relTarget: string, allSlugs: Set<string>): string | null {
   const targetNoExt = relTarget.endsWith('.md') ? relTarget.slice(0, -3) : relTarget;
 
-  const s1 = join(fileDir, targetNoExt);
-  if (allSlugs.has(s1)) return s1;
+  // Issue #1964: wikilinks carry raw Obsidian paths (`[[llm-wiki/entities/AI 3.0]]`)
+  // but allSlugs holds sync-slugified slugs (`llm-wiki/entities/ai-3.0`). Try the
+  // raw candidate first (back-compat), then the sync-consistent slugified form.
+  const hit = (candidate: string): string | null => {
+    if (allSlugs.has(candidate)) return candidate;
+    const slugified = slugifyPath(candidate);
+    if (slugified !== candidate && allSlugs.has(slugified)) return slugified;
+    return null;
+  };
+
+  const s1 = hit(join(fileDir, targetNoExt));
+  if (s1) return s1;
 
   const parts = fileDir.split('/').filter(Boolean);
   for (let strip = 1; strip <= parts.length; strip++) {
     const ancestor = parts.slice(0, parts.length - strip).join('/');
-    const candidate = ancestor ? join(ancestor, targetNoExt) : targetNoExt;
-    if (allSlugs.has(candidate)) return candidate;
+    const candidate = hit(ancestor ? join(ancestor, targetNoExt) : targetNoExt);
+    if (candidate) return candidate;
   }
 
   return null;
@@ -349,7 +359,13 @@ function inferTypeByDir(fromDir: string, toDir: string, frontmatter?: Record<str
   const to = toDir.split('/')[0];
   if (from === 'people' && to === 'companies') {
     if (Array.isArray(frontmatter?.founded)) return 'founded';
-    return 'works_at';
+    // #3466: bare people/ -> companies/ adjacency is not evidence of
+    // employment, so it gets the neutral 'mentions' verb instead of
+    // 'works_at'. Real works_at edges still come from the two paths that
+    // read actual evidence: the company:/companies: frontmatter fields
+    // (FRONTMATTER_LINK_MAP) and employment phrasing in prose
+    // (inferLinkType in link-extraction.ts).
+    return 'mentions';
   }
   if (from === 'people' && to === 'deals') return 'involved_in';
   if (from === 'deals' && to === 'companies') return 'deal_for';
@@ -1452,6 +1468,8 @@ async function extractLinksFromDB(
     slugToSources.set(ref.slug, list);
   }
   let processed = 0, created = 0;
+  // #2576: skipped-candidate counter — see extractStaleFromDB's twin.
+  let skippedMissingTarget = 0;
   // v0.42.7 (#1696): pages whose links we extracted this run — stamped after
   // the loop so a manual `gbrain extract links|all --source db` clears the
   // links_extraction_lag doctor signal. Non-dry-run only.
@@ -1508,7 +1526,7 @@ async function extractLinksFromDB(
       // endpoint-validation + from/to source-id picking (null = skip: missing
       // endpoint OR target only in a non-origin/non-default source).
       const resolved = resolveCandidateSources(c, slug, source_id, allSlugs, slugToSources);
-      if (!resolved) continue;
+      if (!resolved) { skippedMissingTarget++; continue; }
       const { fromSlug, fromSourceId, toSourceId } = resolved;
 
       if (dryRunSeen) {
@@ -1565,6 +1583,9 @@ async function extractLinksFromDB(
   if (!jsonMode) {
     const label = dryRun ? '(dry run) would create' : 'created';
     console.log(`Links: ${label} ${created} from ${processed} pages (db source)`);
+    if (skippedMissingTarget > 0) {
+      console.log(`Skipped ${skippedMissingTarget} candidate(s) whose target page doesn't exist (references to non-pages are never persisted).`);
+    }
     if (includeFrontmatter && unresolved.length > 0) {
       // Top-20 preview of unresolvable frontmatter names so the user can
       // see where the graph has holes (codex tension 6.4).
@@ -1710,7 +1731,7 @@ export async function extractStaleFromDB(
     sourceIdFilter?: string;
     catchUp: boolean;
   },
-): Promise<{ linksCreated: number; timelineCreated: number; pagesProcessed: number; staleRemaining: number }> {
+): Promise<{ linksCreated: number; timelineCreated: number; pagesProcessed: number; staleRemaining: number; skippedMissingTarget?: number }> {
   const { dryRun, jsonMode, includeFrontmatter, sourceIdFilter, catchUp } = opts;
   const versionTs = LINK_EXTRACTOR_VERSION_TS;
 
@@ -1762,6 +1783,10 @@ export async function extractStaleFromDB(
   let afterPageId = 0;
   let linksCreated = 0, timelineCreated = 0, pagesProcessed = 0;
   let budgetHit = false;
+  // #2576: candidates whose endpoint pages don't exist are skipped, not
+  // persisted. Counted so a dropped reference is observable in the summary
+  // instead of vanishing silently (the failure mode that hid bug 2).
+  let skippedMissingTarget = 0;
 
   for (;;) {
     const rows = await engine.listStalePagesForExtraction({
@@ -1781,7 +1806,7 @@ export async function extractStaleFromDB(
       );
       for (const c of extracted.candidates) {
         const r = resolveCandidateSources(c, page.slug, page.source_id, allSlugs, slugToSources);
-        if (!r) continue;
+        if (!r) { skippedMissingTarget++; continue; }
         linkRows.push({
           from_slug: r.fromSlug, to_slug: c.targetSlug, link_type: c.linkType,
           context: c.context, link_source: c.linkSource, origin_slug: c.originSlug,
@@ -1842,6 +1867,9 @@ export async function extractStaleFromDB(
 
   if (!jsonMode) {
     console.log(`Extract --stale: ${linksCreated} link(s) + ${timelineCreated} timeline entr(ies) from ${pagesProcessed} page(s).`);
+    if (skippedMissingTarget > 0) {
+      console.log(`Skipped ${skippedMissingTarget} candidate(s) whose target page doesn't exist (references to non-pages are never persisted).`);
+    }
     if (budgetHit && staleRemaining > 0) {
       console.log(`Time budget reached — ${staleRemaining} page(s) still stale. Re-run 'gbrain extract --stale' (or pass --catch-up) to continue.`);
     }
@@ -1849,9 +1877,10 @@ export async function extractStaleFromDB(
     process.stdout.write(JSON.stringify({
       action: 'extract_stale_done', links_created: linksCreated, timeline_created: timelineCreated,
       pages_processed: pagesProcessed, stale_remaining: staleRemaining, budget_hit: budgetHit,
+      skipped_missing_target: skippedMissingTarget,
     }) + '\n');
   }
-  return { linksCreated, timelineCreated, pagesProcessed, staleRemaining };
+  return { linksCreated, timelineCreated, pagesProcessed, staleRemaining, skippedMissingTarget };
 }
 
 /**

src/commands/features.ts

@@ -42,7 +42,7 @@ interface FeatureScanResult {
 const RECIPE_META = [
   { id: 'email-to-brain', name: 'Email to Brain', secrets: ['GMAIL_APP_PASSWORD'] },
   { id: 'calendar-to-brain', name: 'Calendar Sync', secrets: ['GOOGLE_CALENDAR_API_KEY'] },
-  { id: 'x-to-brain', name: 'X/Twitter to Brain', secrets: ['X_BEARER_TOKEN'] },
+  { id: 'x-to-brain', name: 'X/Twitter to Brain', secrets: ['X_API_BEARER_TOKEN'] },
   { id: 'twilio-voice-brain', name: 'Voice to Brain', secrets: ['TWILIO_AUTH_TOKEN'] },
   { id: 'meeting-sync', name: 'Meeting Sync', secrets: ['CIRCLEBACK_API_KEY'] },
   { id: 'credential-gateway', name: 'Credential Gateway', secrets: ['OAUTH_CLIENT_SECRET'] },

src/commands/files.ts

@@ -16,7 +16,7 @@ interface FileRecord {
   filename: string;
   storage_path: string;
   mime_type: string | null;
-  size_bytes: number;
+  size_bytes: number | bigint | string | null;
   content_hash: string;
   metadata: Record<string, unknown>;
   created_at: string;
@@ -42,6 +42,14 @@ function fileHash(filePath: string): string {
   return createHash('sha256').update(content).digest('hex');
 }
 
+export function formatFileSizeKb(rawSizeBytes: number | bigint | string | null): string {
+  if (rawSizeBytes == null) return '?';
+  const sizeBytes = Number(rawSizeBytes);
+  return Number.isFinite(sizeBytes) && sizeBytes >= 0
+    ? `${Math.round(sizeBytes / 1024)}KB`
+    : '?';
+}
+
 export async function runFiles(engine: BrainEngine, args: string[]) {
   const subcommand = args[0];
 
@@ -116,7 +124,7 @@ async function listFiles(engine: BrainEngine, slug?: string) {
 
   console.log(`${rows.length} file(s):`);
   for (const row of rows) {
-    const size = row.size_bytes ? `${Math.round(Number(row.size_bytes) / 1024)}KB` : '?';
+    const size = formatFileSizeKb(row.size_bytes as FileRecord['size_bytes']);
     console.log(`  ${row.page_slug || '(unlinked)'} / ${row.filename}  [${size}, ${row.mime_type || '?'}]`);
   }
 }

src/commands/import.ts

@@ -78,6 +78,17 @@ export async function runImport(
   const jsonOutput = args.includes('--json');
   const includeGitignored = args.includes('--include-gitignored') || opts.includeGitignored === true;
 
+  // #3637: under --json, stdout belongs to the JSON document alone. The
+  // informational lines below are useful — they just belong on the other
+  // channel, the same rule progress already follows (CLAUDE.md: "Progress
+  // always writes to stderr. Stdout stays clean for data output (--json
+  // payloads)"). Pre-fix, `import --json` prefixed the payload with
+  // "Found N markdown files", so JSON.parse of stdout failed outright.
+  const info = (msg: string): void => {
+    if (jsonOutput) console.error(msg);
+    else console.log(msg);
+  };
+
   // T7 (D9): refuse cleanly when init persisted the deferred-setup sentinel,
   // unless the user is explicitly skipping embedding via `--no-embed` (in
   // which case the chunks land without vectors and the user can backfill
@@ -225,7 +236,7 @@ export async function runImport(
   if (opts.exclude && opts.exclude.length > 0) {
     const beforeExclude = allFiles.length;
     allFiles = allFiles.filter(abs => !matchesAnyGlob(relative(dir, abs), opts.exclude));
-    console.log(
+    info(
       `Found ${allFiles.length} ${fileTypeLabel} files ` +
       `(${beforeExclude - allFiles.length} excluded by --exclude patterns)`,
     );
@@ -237,7 +248,7 @@ export async function runImport(
       );
     }
   } else {
-    console.log(`Found ${allFiles.length} ${fileTypeLabel} files`);
+    info(`Found ${allFiles.length} ${fileTypeLabel} files`);
   }
 
   // Sort newest-first so date-prefixed brain paths get embedded before older ones.
@@ -253,7 +264,7 @@ export async function runImport(
     const cp = loadCheckpoint(checkpointPath, dir);
     if (cp) {
       for (const p of cp.completedPaths) completed.add(p);
-      console.log(`Resuming from checkpoint: skipping ${completed.size} already-processed files`);
+      info(`Resuming from checkpoint: skipping ${completed.size} already-processed files`);
     }
   }
   const files = resumeFilter(allFiles, dir, completed);
@@ -261,13 +272,19 @@ export async function runImport(
   // Determine actual worker count
   const actualWorkers = workerCount > 1 ? workerCount : 1;
   if (actualWorkers > 1) {
-    console.log(`Using ${actualWorkers} parallel workers`);
+    info(`Using ${actualWorkers} parallel workers`);
   }
 
   let imported = 0;
   let skipped = 0;
   let errors = 0;
   let processed = 0;
+  // Time-based checkpoint floor (see the save site below). Chunking cost scales
+  // with paragraph count, not bytes, so a single reference-style file can take
+  // many minutes; a count-only trigger leaves that work undurable.
+  const CHECKPOINT_MAX_INTERVAL_MS = 120_000;
+  let lastCheckpointMs = Date.now();
+  let lastCheckpointSize = completed.size;
   let chunksCreated = 0;
   const importedSlugs: string[] = [];
   const errorCounts: Record<string, number> = {};
@@ -343,7 +360,17 @@ export async function runImport(
     // Save checkpoint every 100 SUCCESSFUL adds (not every 100 processed).
     // Failed files never enter `completed`, so a flaky file can't push the
     // checkpoint past it — the next run will retry it.
-    if (completed.size > 0 && completed.size % 100 === 0) {
+    // ...and ALSO save on a time interval. On a corpus with an expensive tail
+    // `completed` can advance ~1 file per several minutes, so the next
+    // 100-boundary may be hours away; any kill before it discards every file
+    // since the last boundary and the run can never converge.
+    const nowMs = Date.now();
+    const dueByCount = completed.size > 0 && completed.size % 100 === 0;
+    const dueByTime = completed.size > lastCheckpointSize
+      && nowMs - lastCheckpointMs >= CHECKPOINT_MAX_INTERVAL_MS;
+    if (dueByCount || dueByTime) {
+      lastCheckpointMs = nowMs;
+      lastCheckpointSize = completed.size;
       const cpDir = gbrainPath();
       if (!existsSync(cpDir)) {
         try { const { mkdirSync } = await import('fs'); mkdirSync(cpDir, { recursive: true }); }
@@ -429,13 +456,37 @@ export async function runImport(
     }
   }
 
+  // Final checkpoint save BEFORE the clear/preserve decision below. The
+  // periodic triggers above are gated on a 100-file boundary or an interval,
+  // so a run that ends between them would otherwise leave its tail unsaved.
+  // This must run before clearCheckpoint() so a clean run still ends with no
+  // checkpoint file — it only makes the ERROR path's preserved checkpoint
+  // complete.
+  if (errors > 0 && completed.size > lastCheckpointSize) {
+    try {
+      const cpDir = gbrainPath();
+      if (!existsSync(cpDir)) {
+        const { mkdirSync } = await import('fs');
+        mkdirSync(cpDir, { recursive: true });
+      }
+      saveCheckpoint(checkpointPath, {
+        schema_version: 1,
+        owner: 'gbrain',
+        kind: 'import',
+        dir,
+        completedPaths: Array.from(completed),
+        timestamp: new Date().toISOString(),
+      });
+    } catch { /* non-fatal: the next run simply redoes the tail */ }
+  }
+
   // Clear checkpoint on clean completion. On error, the path-based checkpoint
   // preserves only the successfully-completed paths, so the next run retries
   // failed files automatically (they never entered `completed`).
   if (errors === 0) {
     clearCheckpoint(checkpointPath);
   } else if (existsSync(checkpointPath)) {
-    console.log(`  Checkpoint preserved (${errors} errors). Run again to retry failed files.`);
+    info(`  Checkpoint preserved (${errors} errors). Run again to retry failed files.`);
   }
 
   const totalTime = ((Date.now() - startTime) / 1000).toFixed(1);

src/commands/integrations.ts

@@ -23,7 +23,8 @@ import matter from 'gray-matter';
 import { readFileSync, existsSync, writeFileSync, mkdirSync, readdirSync } from 'fs';
 import { join, basename } from 'path';
 import { homedir } from 'os';
-import { gbrainPath } from '../core/config.ts';
+import { gbrainPath, loadConfig } from '../core/config.ts';
+import { buildGatewayConfig } from '../core/ai/build-gateway-config.ts';
 import { execSync } from 'child_process';
 
 // --- Types ---
@@ -54,6 +55,13 @@ interface RecipeFrontmatter {
   health_checks: HealthCheck[];
   setup_time: string;
   cost_estimate?: string;
+  /**
+   * Repo-relative dirs (slug prefixes, trailing '/') this recipe's collector
+   * writes files to. Ground truth for the `db_only_collector_collision`
+   * doctor check (issue #2788): output inside a db_only path is silently
+   * skipped by sync and import (auto-gitignored).
+   */
+  output_paths: string[];
 }
 
 interface ParsedRecipe {
@@ -105,7 +113,20 @@ interface AnyOfCheck {
   checks: HealthCheck[];
 }
 
-type HealthCheck = string | HttpCheck | EnvExistsCheck | CommandCheck | AnyOfCheck;
+/**
+ * Staleness-aware check type (issue #2787, reported by @alexputici). All
+ * other types are point-in-time — a sense whose gateway is up and env vars
+ * are set passes forever even when zero data flows. This one reads the
+ * integration's heartbeat file and FAILS when the newest event is older
+ * than the declared cadence (`max_age`, e.g. "48h", "2d", "90m").
+ */
+interface HeartbeatMaxAgeCheck {
+  type: 'heartbeat_max_age';
+  max_age: string;
+  label?: string;
+}
+
+type HealthCheck = string | HttpCheck | EnvExistsCheck | CommandCheck | AnyOfCheck | HeartbeatMaxAgeCheck;
 
 interface CheckResult {
   integration: string;
@@ -122,9 +143,48 @@ export function isUnsafeHealthCheck(check: string): boolean {
   return /[;&|`$(){}\\<>\n]/.test(check);
 }
 
-/** Expand $VAR references with process.env values */
+/**
+ * Env view for secret resolution (#2789): apply the same config.json→env
+ * folding the runtime applies via buildGatewayConfig, so a credential stored
+ * only in ~/.gbrain/config.json — which powers a perfectly healthy
+ * integration — is not reported [missing] by show/status. process.env still
+ * wins for non-empty values (buildGatewayConfig spreads it last, dropping
+ * only ''/undefined entries). Falls back to bare process.env before
+ * `gbrain init` (no config file yet). Mirrors the #2728 fix on the
+ * providers command.
+ */
+export function secretEnv(): Record<string, string | undefined> {
+  try {
+    const cfg = loadConfig();
+    if (cfg) return buildGatewayConfig(cfg).env;
+  } catch { /* integrations must keep working pre-init — fall through */ }
+  return process.env;
+}
+
+/**
+ * Parse a heartbeat_max_age duration string ("30s", "90m", "48h", "2d")
+ * into milliseconds. Returns null on anything unparseable.
+ */
+export function parseMaxAge(s: string): number | null {
+  const m = /^(\d+(?:\.\d+)?)\s*(s|m|h|d)$/i.exec(String(s).trim());
+  if (!m) return null;
+  const n = Number(m[1]);
+  if (!Number.isFinite(n) || n <= 0) return null;
+  const unit = { s: 1_000, m: 60_000, h: 3_600_000, d: 86_400_000 }[m[2].toLowerCase() as 's' | 'm' | 'h' | 'd'];
+  return n * unit;
+}
+
+/** Human-readable age for heartbeat_max_age output ("3d", "17h", "42m"). */
+function formatAge(ms: number): string {
+  if (ms >= 86_400_000) return `${Math.floor(ms / 86_400_000)}d`;
+  if (ms >= 3_600_000) return `${Math.floor(ms / 3_600_000)}h`;
+  return `${Math.max(0, Math.floor(ms / 60_000))}m`;
+}
+
+/** Expand $VAR references with gateway-env (config-folded) values */
 export function expandVars(s: string): string {
-  return s.replace(/\$([A-Z_][A-Z0-9_]*)/g, (_, name) => process.env[name] || '');
+  const env = secretEnv();
+  return s.replace(/\$([A-Z_][A-Z0-9_]*)/g, (_, name) => env[name] || '');
 }
 
 // --- SSRF Protection ---
@@ -249,7 +309,7 @@ export async function executeHealthCheck(
     }
 
     case 'env_exists': {
-      const val = process.env[check.name];
+      const val = secretEnv()[check.name];
       return {
         ...base,
         status: val ? 'ok' : 'fail',
@@ -279,6 +339,29 @@ export async function executeHealthCheck(
       }
     }
 
+    case 'heartbeat_max_age': {
+      // No embedded gate: reads only the local heartbeat file — no exec, no
+      // network. Safe for user-provided recipes.
+      const maxMs = parseMaxAge(check.max_age);
+      if (maxMs === null) {
+        return { ...base, status: 'fail', output: `${check.label || 'heartbeat_max_age'}: invalid max_age '${check.max_age}' (use e.g. 90m, 48h, 2d)` };
+      }
+      const entries = readHeartbeat(integrationId);
+      if (entries.length === 0) {
+        return { ...base, status: 'fail', output: `${check.label || 'heartbeat'}: no heartbeat events in the last 30 days (expected activity within ${check.max_age}) — the sense has stopped producing data` };
+      }
+      let newest = 0;
+      for (const e of entries) {
+        const t = new Date(e.ts).getTime();
+        if (Number.isFinite(t) && t > newest) newest = t;
+      }
+      const ageMs = Date.now() - newest;
+      if (ageMs > maxMs) {
+        return { ...base, status: 'fail', output: `${check.label || 'heartbeat'}: last event ${formatAge(ageMs)} ago exceeds max_age ${check.max_age} — the sense has stopped producing data` };
+      }
+      return { ...base, status: 'ok', output: `${check.label || 'heartbeat'}: last event ${formatAge(ageMs)} ago (within ${check.max_age})` };
+    }
+
     case 'any_of': {
       for (const sub of check.checks) {
         const result = await executeHealthCheck(sub, integrationId, isEmbedded);
@@ -320,6 +403,7 @@ export function parseRecipe(content: string, filename: string): ParsedRecipe | n
         health_checks: (data.health_checks || []) as HealthCheck[],
         setup_time: data.setup_time || 'unknown',
         cost_estimate: data.cost_estimate,
+        output_paths: Array.isArray(data.output_paths) ? data.output_paths.map(String) : [],
       },
       body: body.trim(),
       filename,
@@ -383,6 +467,25 @@ function loadAllRecipes(): ParsedRecipe[] {
   return recipes;
 }
 
+/**
+ * Output paths of every CONFIGURED recipe (secrets present — the collector
+ * can actually be running). Ground truth for the
+ * `db_only_collector_collision` doctor check and the sync-time warning
+ * (issue #2788). Unconfigured recipes are skipped: a collector that can't
+ * run can't silently die.
+ */
+export function getConfiguredCollectorOutputs(): Array<{ id: string; output_path: string }> {
+  const out: Array<{ id: string; output_path: string }> = [];
+  for (const r of loadAllRecipes()) {
+    if (r.frontmatter.output_paths.length === 0) continue;
+    if (getStatus(r) === 'available') continue;
+    for (const p of r.frontmatter.output_paths) {
+      out.push({ id: r.frontmatter.id, output_path: p });
+    }
+  }
+  return out;
+}
+
 function findRecipe(id: string): ParsedRecipe | null {
   const recipes = loadAllRecipes();
   const exact = recipes.find(r => r.frontmatter.id === id);
@@ -457,11 +560,12 @@ function readHeartbeat(id: string): HeartbeatEntry[] {
 
 // --- Secret Checking ---
 
-function checkSecrets(secrets: RecipeSecret[]): { set: string[]; missing: RecipeSecret[] } {
+export function checkSecrets(secrets: RecipeSecret[]): { set: string[]; missing: RecipeSecret[] } {
   const set: string[] = [];
   const missing: RecipeSecret[] = [];
+  const env = secretEnv();
   for (const s of secrets) {
-    if (process.env[s.name]) {
+    if (env[s.name]) {
       set.push(s.name);
     } else {
       missing.push(s);
@@ -607,8 +711,9 @@ function cmdShow(args: string[]): void {
   if (f.requires.length > 0) console.log(`Requires:   ${f.requires.join(', ')}`);
 
   console.log('\nSecrets needed:');
+  const env = secretEnv();
   for (const s of f.secrets) {
-    const isSet = process.env[s.name] ? '  [set]' : '  [missing]';
+    const isSet = env[s.name] ? '  [set]' : '  [missing]';
     console.log(`  ${s.name}${isSet}`);
     console.log(`    ${s.description}`);
     console.log(`    Get it: ${s.where}`);

src/commands/integrity.ts

@@ -12,7 +12,7 @@
  * Subcommands:
  *   gbrain integrity check              Read-only report to stdout
  *   gbrain integrity auto               Three-bucket repair with confidence
- *   gbrain integrity --dry-run          Same as auto, no writes
+ *   gbrain integrity auto --dry-run     Same as auto, no writes
  *
  * Three-bucket confidence (contract with x_handle_to_tweet resolver):
  *   >= 0.8 → auto-repair through BrainWriter transaction
@@ -449,6 +449,7 @@ async function cmdAuto(args: string[]): Promise<void> {
   let bucketReview = 0;
   let bucketSkip = 0;
   let bucketErr = 0;
+  let bucketDeadLink = 0;
   let pagesProcessed = 0;
 
   const { createProgress } = await import('../core/progress.ts');
@@ -549,7 +550,13 @@ async function cmdAuto(args: string[]): Promise<void> {
                 hit: { slug, line: hit.line, rawLine: hit.url, phrase: 'dead-link' },
                 reason: `dead link: ${result.value.reason ?? 'unknown'}`,
               });
-              bucketReview++;
+              // Dead links have no confidence score and are never written to
+              // the review file (appendReview() is only called from the
+              // bare-tweet path above) — they land in the skip log via
+              // logSkip() a few lines up. Count them separately so the
+              // printed "Review queue" total only ever reflects what's
+              // actually in ~/.gbrain/integrity-review.md.
+              bucketDeadLink++;
             }
           } catch {
             /* transient; don't fail the run */
@@ -568,6 +575,7 @@ async function cmdAuto(args: string[]): Promise<void> {
     console.log(`Review queue (≥${reviewLower} <${confidenceThreshold}): ${bucketReview}`);
     console.log(`Skipped (<${reviewLower}): ${bucketSkip}`);
     if (bucketErr > 0) console.log(`Resolver errors: ${bucketErr}`);
+    if (bucketDeadLink > 0) console.log(`Dead links surfaced (see skipped log): ${bucketDeadLink}`);
     console.log(`\nReview queue: ${getReviewFile()}`);
     console.log(`Skipped log:  ${getLogFile()}`);
     console.log(`Progress:     ${getProgressFile()}`);

src/commands/jobs.ts

@@ -2194,8 +2194,9 @@ export async function registerBuiltinHandlers(
   // migration that retypes 25K+ pages, creates alias rows, converts edge-
   // shaped pages to link rows, AND flips the active pack at end of run.
   // manual_only via src/core/onboard/render.ts:MANUAL_ONLY_PROTECTED_JOBS.
-  // Operator path: `gbrain jobs submit unify-types --allow-protected --params
-  // '{"target_pack":"gbrain-base-v2"}'`.
+  // Dry-run preview: `gbrain jobs submit unify-types --allow-protected
+  // --params '{"target_pack":"gbrain-base-v2"}'`; apply with
+  // '{"target_pack":"gbrain-base-v2","apply":true}'.
   worker.register('unify-types', async (job) => {
     const { runUnifyTypes } = await import('../core/schema-pack/unify-types-handler.ts');
     const data = (job.data ?? {}) as {
@@ -2213,7 +2214,11 @@ export async function registerBuiltinHandlers(
     } as unknown as import('../core/operations.ts').OperationContext;
     return await runUnifyTypes(ctx, {
       target_pack: data.target_pack,
-      apply: data.apply ?? true,
+      // #1575: default matches the handler interface's "Default false
+      // (dry-run)" — a destructive one-shot migration must be opted into
+      // with apply:true (the onboard remediation + the printed migration
+      // command both carry it explicitly).
+      apply: data.apply ?? false,
       sourceId: data.sourceId,
       onProgress: (msg: string) => {
         job.updateProgress({ phase: 'unify-types', message: msg }).catch(() => {});