fix(test): bump PHASE_SCOPE count 16→17 for schema-suggest

The v0.39.1.0 master merge added the 17th cycle phase ('schema-suggest').
The previous commit added it to PHASE_SCOPE; this commit updates the
count-pin regression test to match.

.github/workflows/actionlint.yml

@@ -1,32 +0,0 @@
-name: Actionlint
-
-# Lints the GitHub Actions workflow YAML on every change so a malformed
-# workflow / bad action ref / missing-permission bug is caught before it ships
-# a broken pipeline. gbrain edits .github/workflows/* often (sharding, cache,
-# timeouts); this is the cheap guard that keeps those edits honest.
-
-on:
-  push:
-    branches: [master]
-    paths:
-      - '.github/workflows/**'
-  pull_request:
-    branches: [master]
-    paths:
-      - '.github/workflows/**'
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  actionlint:
-    runs-on: ubuntu-latest
-    timeout-minutes: 5
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-      - uses: rhysd/actionlint@393031adb9afb225ee52ae2ccd7a5af5525e03e8  # v1.7.11

.github/workflows/e2e.yml

@@ -12,61 +12,10 @@ on:
 permissions:
   contents: read
 
-# Cancel a superseded run when a newer commit lands on the same PR/branch.
-# PR number for pull_request events (fork-safe), github.ref fallback for
-# push/scheduled runs.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
 jobs:
-  jsonb-parity:
-    # Dedicated required guard for the JSONB double-encode bug-class (#2339).
-    # PGLite parses a double-encoded jsonb string silently, so this assertion can
-    # ONLY be made on real Postgres — a normal gated e2e file would skip without
-    # DATABASE_URL and let the bug ship green (as #2339 did). This job provisions
-    # Postgres and HARD-FAILS if DATABASE_URL is missing, so the guard can never
-    # silently skip.
-    name: JSONB parity (#2339 regression guard)
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    services:
-      postgres:
-        image: pgvector/pgvector:pg16
-        env:
-          POSTGRES_USER: postgres
-          POSTGRES_PASSWORD: postgres
-          POSTGRES_DB: gbrain_test
-        ports:
-          - 5432:5432
-        options: >-
-          --health-cmd pg_isready
-          --health-interval 10s
-          --health-timeout 5s
-          --health-retries 5
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
-        with:
-          bun-version: 1.3.13
-      - run: bun install
-      - name: Require DATABASE_URL (no silent skip)
-        env:
-          DATABASE_URL: postgresql://postgres:postgres@localhost:5432/gbrain_test
-        run: |
-          if [ -z "$DATABASE_URL" ]; then
-            echo "::error::DATABASE_URL must be set for the jsonb-parity job — the #2339 guard would silently skip (the exact failure PGLite hides). Failing the job." >&2
-            exit 1
-          fi
-      - name: Run JSONB double-encode parity tests on real Postgres
-        env:
-          DATABASE_URL: postgresql://postgres:postgres@localhost:5432/gbrain_test
-        run: bun test test/e2e/op-checkpoint-jsonb-parity.test.ts test/e2e/jsonb-roundtrip.test.ts
-
   tier1:
     name: Tier 1 (Mechanical)
     runs-on: ubuntu-latest
-    timeout-minutes: 20
     services:
       postgres:
         image: pgvector/pgvector:pg16
@@ -85,7 +34,7 @@ jobs:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
-          bun-version: 1.3.13
+          bun-version: latest
       - run: bun install
       - name: Run Tier 1 E2E tests
         run: bun test test/e2e/mechanical.test.ts test/e2e/mcp.test.ts
@@ -100,7 +49,6 @@ jobs:
     # from repo/org secrets. Nightly + manual triggers still supported via
     # the workflow-level `on:` list.
     needs: tier1
-    timeout-minutes: 30
     services:
       postgres:
         image: pgvector/pgvector:pg16
@@ -119,25 +67,10 @@ jobs:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
-          bun-version: 1.3.13
+          bun-version: latest
       - run: bun install
       - name: Install OpenClaw
-        # Bound + retry the install: a transient npm/registry stall here used to
-        # hang unbounded and (since the v0.42.50.0 job timeout) burn the entire
-        # 30m Tier 2 budget before failing — even though the install normally
-        # finishes in well under a minute. `timeout` kills a hung attempt fast;
-        # up to 3 attempts ride out a flaky registry. Step cap is a backstop.
-        timeout-minutes: 8
-        run: |
-          for attempt in 1 2 3; do
-            if timeout 120 npm install -g openclaw@2026.4.9; then
-              exit 0
-            fi
-            echo "::warning::openclaw install attempt $attempt failed or timed out; retrying in 10s" >&2
-            sleep 10
-          done
-          echo "::error::openclaw install failed after 3 attempts" >&2
-          exit 1
+        run: npm install -g openclaw@2026.4.9
       - name: Configure OpenClaw MCP
         run: |
           mkdir -p ~/.openclaw

.github/workflows/heavy-tests.yml

@@ -58,7 +58,7 @@ jobs:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
-          bun-version: 1.3.13
+          bun-version: latest
       - run: bun install
 
       - name: Run heavy tests

.github/workflows/osv-scanner.yml

@@ -1,33 +0,0 @@
-name: OSV-Scanner
-
-# Dependency vulnerability scan (#2182) via Google's official reusable
-# workflow. Runs weekly and on any PR that touches the dependency manifests.
-# Tokenless: needs zero secrets. Findings are reported in the job log and as
-# a SARIF artifact on the run; code-scanning upload is deliberately disabled
-# so the workflow stays read-only (no security-events: write).
-
-on:
-  pull_request:
-    branches: [master]
-    paths:
-      - 'bun.lock'
-      - 'package.json'
-  schedule:
-    - cron: '30 6 * * 1'  # weekly, Monday 06:30 UTC
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-jobs:
-  osv-scan:
-    permissions:
-      actions: read
-      contents: read
-      # Required by the reusable workflow's own top-level permissions block —
-      # GitHub validates the caller grants a superset AT STARTUP, even with
-      # upload-sarif: false (nothing is actually uploaded; see #2117 upstream).
-      security-events: write
-    uses: google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@9a498708959aeaef5ef730655706c5a1df1edbc2  # v2.3.8
-    with:
-      upload-sarif: false

.github/workflows/release.yml

@@ -19,23 +19,14 @@ jobs:
             target: bun-linux-x64
             artifact: gbrain-linux-x64
     runs-on: ${{ matrix.os }}
-    permissions:
-      contents: read
-      id-token: write      # for attest-build-provenance (Sigstore OIDC)
-      attestations: write  # for attest-build-provenance
     steps:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
-          bun-version: 1.3.13
+          bun-version: latest
       - run: bun install
       - run: bun test
-      - run: bun run verify
       - run: bun build --compile --target=${{ matrix.target }} --outfile bin/${{ matrix.artifact }} src/cli.ts
-      - name: Attest build provenance
-        uses: actions/attest-build-provenance@0f67c3f4856b2e3261c31976d6725780e5e4c373  # v4.1.1
-        with:
-          subject-path: bin/${{ matrix.artifact }}
       - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02  # v4
         with:
           name: ${{ matrix.artifact }}

.github/workflows/semgrep.yml

@@ -1,36 +0,0 @@
-name: Semgrep
-
-# Static analysis (SAST) with Semgrep Community Edition (#2272). Tokenless:
-# uses the public registry rulesets, needs zero secrets. Findings print in
-# the job log; no code-scanning/SARIF upload by design (keeps permissions
-# read-only, no security-events: write).
-
-on:
-  pull_request:
-    branches: [master]
-  schedule:
-    - cron: '30 7 * * 1'  # weekly, Monday 07:30 UTC
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  semgrep:
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    container:
-      image: semgrep/semgrep:1.170.0@sha256:c98f8829eea377274ee4b10656458b078b88232469b2ff913f091c2317347c9d
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-      # Non-blocking initially (continue-on-error): the first runs establish a
-      # baseline without failing unrelated PRs. Graduation path: once the
-      # baseline findings are triaged (fixed or `# nosemgrep`'d), remove
-      # continue-on-error so new findings block PRs.
-      - name: Semgrep scan (report-only)
-        run: semgrep scan --config p/default --config p/typescript --error
-        continue-on-error: true

.github/workflows/test.yml

@@ -5,84 +5,13 @@ on:
     branches: [master]
   pull_request:
     branches: [master]
-  # Manual dispatch lets a local dev/agent offload the suite to GitHub's
-  # on-demand runners from ANY branch (see scripts/ship-remote-tests.sh).
-  # Frees a load-saturated local machine (e.g. many Conductor agents running
-  # their own bun-test suites at once — load avg 120 on 16 cores).
-  workflow_dispatch:
 
 permissions:
   contents: read
 
-# Cancel a superseded run when a newer commit lands on the same PR/branch.
-# Keyed on the PR number for pull_request events (unique per PR, so two PRs
-# from forks sharing a branch name don't cancel each other) and falls back to
-# github.ref for push/scheduled runs. Mirrors heavy-tests.yml; frees runners
-# and stops a stale-SHA run from reporting a flaky failure on an obsolete commit.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
 jobs:
-  # ──────────────────────────────────────────────────────────────────────
-  # cache-check: runs first, computes the content hash of every tracked
-  # file EXCEPT the deny-list (CHANGELOG.md, README.md, docs/**/*.md, etc.
-  # — see scripts/ci-cache-hash.sh for the full list). Looks up
-  # `ci-pass-<hash>` in actions/cache; if hit, the test matrix + verify
-  # + serial jobs all skip and test-status reports green immediately.
-  # If miss, the full suite runs and cache-write seals it on success.
-  #
-  # Hit rate covers re-pushes (same SHA twice), branch rebases that
-  # don't touch tracked code, and any branch update that touches only
-  # the deny-listed doc files.
-  # ──────────────────────────────────────────────────────────────────────
-  cache-check:
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    outputs:
-      hit: ${{ steps.lookup.outputs.cache-hit }}
-      hash: ${{ steps.compute.outputs.hash }}
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-      - name: Compute content hash
-        id: compute
-        run: |
-          # --verbose writes the "X/Y files in hash" diagnostic to stderr;
-          # stdout carries the 16-char hash. Capture both.
-          HASH=$(bash scripts/ci-cache-hash.sh --verbose 2>/tmp/cache-diag)
-          cat /tmp/cache-diag
-          echo "Computed cache hash: $HASH"
-          echo "hash=$HASH" >> "$GITHUB_OUTPUT"
-      - name: Lookup actions/cache for ci-pass-<hash>
-        id: lookup
-        uses: actions/cache/restore@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
-        with:
-          key: ci-pass-${{ steps.compute.outputs.hash }}
-          path: .ci-cache-marker
-          # `lookup-only: true` means we only probe whether the cache
-          # entry exists — we don't download it (the marker contents
-          # don't matter, only the key match does). `cache-hit` returns
-          # true only on EXACT key match (per actions/cache docs); a
-          # restore-keys prefix fallback would set cache-hit=false, so
-          # it's deliberately omitted here. Cross-branch scoping works
-          # naturally: PR branches can read default-branch (master)
-          # cache entries via exact key match when the content hash
-          # matches, which happens whenever the tree is doc-only
-          # different from a green master run.
-          lookup-only: true
-      - name: Cache status
-        run: |
-          if [ "${{ steps.lookup.outputs.cache-hit }}" = "true" ]; then
-            echo "✓ cache HIT for hash ${{ steps.compute.outputs.hash }} — test jobs will skip"
-          else
-            echo "✗ cache MISS for hash ${{ steps.compute.outputs.hash }} — full suite will run"
-          fi
-
   gitleaks:
-    needs: cache-check
-    if: needs.cache-check.outputs.hit != 'true'
     runs-on: ubuntu-latest
-    timeout-minutes: 10
     steps:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
         with:
@@ -91,196 +20,29 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
-  verify:
-    # Pre-test gates: privacy/jsonb/source-id/etc + typecheck + admin-build.
-    # Lives in its own runner so the matrix shards aren't carrying ~2-3min
-    # of verify work in addition to their test files (the old shape stuffed
-    # this into `test (1)` via `if: matrix.shard == 1`, which made shard 1
-    # the slowest matrix worker). scripts/run-verify-parallel.sh fans out
-    # the 20 checks via & + wait (~5s vs ~15-25s sequential).
-    needs: cache-check
-    if: needs.cache-check.outputs.hit != 'true'
-    runs-on: ubuntu-latest
-    timeout-minutes: 12
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
-        with:
-          bun-version: 1.3.13
-      - uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
-        with:
-          path: ~/.bun/install/cache
-          key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
-      - run: bun install
-      - run: bun run verify
-
-  serial-tests:
-    # *.serial.test.ts at --max-concurrency=1. Lives in its own runner so
-    # the matrix shards aren't carrying the serial-pass tail (the old shape
-    # stuffed this into `test (1)` after the matrix work, which compounded
-    # shard 1's overload).
-    needs: cache-check
-    if: needs.cache-check.outputs.hit != 'true'
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
-        with:
-          bun-version: 1.3.13
-      - uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
-        with:
-          path: ~/.bun/install/cache
-          key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
-      - run: bun install
-      - run: bun run test:serial
-
-  slow-eval-longmemeval:
-    # Dedicated runner for the LongMemEval end-to-end test file. The file
-    # was originally 359s. TODO #1 (engine-sharing in runEvalLongMemEval
-    # via RunOpts.engine) cut it to ~200s by amortizing PGLite cold-create
-    # across all 13 runEvalLongMemEval calls in one beforeAll-shared brain.
-    # Pulled out of the matrix (see scripts/test-shard.sh) so a single 200s
-    # atom doesn't dominate a shard's wallclock. Companion file
-    # test/eval-longmemeval.slow.test.ts (the pure-bucket half) stays in
-    # the matrix because it's light (~42s).
-    needs: cache-check
-    if: needs.cache-check.outputs.hit != 'true'
-    runs-on: ubuntu-latest
-    timeout-minutes: 12
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
-        with:
-          bun-version: 1.3.13
-      - uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
-        with:
-          path: ~/.bun/install/cache
-          key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
-      - run: bun install
-      - run: bun test test/eval-longmemeval-e2e.slow.test.ts --timeout=60000
-
-  slow-entity-resolve-perf:
-    # Dedicated runner for the entity-resolve perf test (~159s, single perf
-    # describe with one test that builds 5000+ pages and asserts the NEW
-    # tryPrefixExpansion shape is 5x faster than the OLD shape — not
-    # subdivisible without weakening the perf guarantee). Pulled out of the
-    # matrix (see scripts/test-shard.sh) so a single 159s atom doesn't
-    # dominate a shard's wallclock. Runs in parallel with the matrix.
-    needs: cache-check
-    if: needs.cache-check.outputs.hit != 'true'
-    runs-on: ubuntu-latest
-    timeout-minutes: 12
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
-        with:
-          bun-version: 1.3.13
-      - uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
-        with:
-          path: ~/.bun/install/cache
-          key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
-      - run: bun install
-      - run: bun test test/entity-resolve-perf.slow.test.ts --timeout=300000
-
   test:
-    # Pure matrix shard — no verify, no serial. Each shard runs its slice
-    # of the unit test set under one `bun test` invocation.
-    #
-    # 10 shards (was 6) drops per-shard total from 532s → 287s. With the two
-    # dedicated jobs (slow-eval-longmemeval, slow-entity-resolve-perf) also
-    # pulled out, the matrix is bounded by ~287s ≈ 4.8 min. Total CI ≈ max
-    # of matrix + slow-eval (~3.3 min after engine-sharing in TODO #1) +
-    # slow-entity-resolve-perf (~2.6 min) ≈ 4.8 min.
-    #
-    # Concurrency budget: 10 shards + verify + serial + slow-eval +
-    # slow-entity-resolve-perf + gitleaks + cache-check + cache-write +
-    # test-status = ~18 jobs × 2 concurrent PRs = 36. GitHub free-tier
-    # caps at ~20 concurrent jobs, so multi-PR days will see some queue
-    # pressure. Single-PR runs are unaffected.
-    #
-    # Partition policy is weight-aware LPT bin-packing via scripts/sharding.ts
-    # (replaces FNV-1a path hash). Weights live in scripts/test-weights.json,
-    # mined from real CI logs via scripts/mine-shard-weights.ts. Missing
-    # weights fall back to corpus median — new test files work immediately.
-    needs: cache-check
-    if: needs.cache-check.outputs.hit != 'true'
+    # ubuntu-latest is free 2-core/7GB. Larger runners (16-cores, etc.) require
+    # a provisioned runner pool in repo settings. Falling back to default keeps
+    # the matrix shard speedup (~5-6x via parallelism) at zero cost.
     runs-on: ubuntu-latest
-    timeout-minutes: 15
     strategy:
       fail-fast: false
       matrix:
-        shard: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
+        shard: [1, 2, 3, 4]
     steps:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
         with:
-          bun-version: 1.3.13
-      - uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
-        with:
-          path: ~/.bun/install/cache
-          key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
+          bun-version: latest
       - run: bun install
-      - name: Run test shard ${{ matrix.shard }}/10
-        run: scripts/test-shard.sh ${{ matrix.shard }} 10
-
-  # ──────────────────────────────────────────────────────────────────────
-  # cache-write: ONLY runs when every gated job succeeded. Writes the
-  # cache entry under `ci-pass-<hash>` so future runs at the same hash
-  # hit cache. Codex's load-bearing correctness point: writing the
-  # cache before the matrix completes would permanently bless bad states
-  # (a future run at the same hash would skip tests because of a cache
-  # entry written when tests hadn't actually passed).
-  # ──────────────────────────────────────────────────────────────────────
-  cache-write:
-    needs: [cache-check, gitleaks, verify, serial-tests, slow-eval-longmemeval, slow-entity-resolve-perf, test]
-    if: success() && needs.cache-check.outputs.hit != 'true'
-    runs-on: ubuntu-latest
-    timeout-minutes: 5
-    steps:
-      - name: Create cache marker
-        run: |
-          mkdir -p .ci-cache-marker
-          echo "${{ needs.cache-check.outputs.hash }}" > .ci-cache-marker/hash
-          echo "$GITHUB_SHA" > .ci-cache-marker/sha
-          echo "$GITHUB_REF" > .ci-cache-marker/ref
-      - uses: actions/cache/save@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
-        with:
-          key: ci-pass-${{ needs.cache-check.outputs.hash }}
-          path: .ci-cache-marker
-
-  # ──────────────────────────────────────────────────────────────────────
-  # test-status: the single user-visible "did CI pass?" check.
-  # Runs always (if: always()), succeeds when EITHER cache-check.hit==true
-  # OR all gated jobs (gitleaks, verify, serial-tests, test) succeeded.
-  # Branch protection (when configured) gates on this single job name.
-  # ──────────────────────────────────────────────────────────────────────
-  test-status:
-    needs: [cache-check, gitleaks, verify, serial-tests, slow-eval-longmemeval, slow-entity-resolve-perf, test]
-    if: always()
-    runs-on: ubuntu-latest
-    timeout-minutes: 5
-    steps:
-      - name: Aggregate result
-        run: |
-          HIT="${{ needs.cache-check.outputs.hit }}"
-          GITLEAKS="${{ needs.gitleaks.result }}"
-          VERIFY="${{ needs.verify.result }}"
-          SERIAL="${{ needs.serial-tests.result }}"
-          SLOW_EVAL="${{ needs.slow-eval-longmemeval.result }}"
-          SLOW_PERF="${{ needs.slow-entity-resolve-perf.result }}"
-          TEST="${{ needs.test.result }}"
-          echo "cache-check.hit=$HIT"
-          echo "gitleaks=$GITLEAKS  verify=$VERIFY  serial-tests=$SERIAL  slow-eval-longmemeval=$SLOW_EVAL  slow-entity-resolve-perf=$SLOW_PERF  test=$TEST"
-          if [ "$HIT" = "true" ]; then
-            echo "✓ cache HIT for hash ${{ needs.cache-check.outputs.hash }} — CI green"
-            exit 0
-          fi
-          # Cache miss: every gated job must have succeeded.
-          for r in "$GITLEAKS" "$VERIFY" "$SERIAL" "$SLOW_EVAL" "$SLOW_PERF" "$TEST"; do
-            if [ "$r" != "success" ]; then
-              echo "✗ gated job did not succeed (got $r) — CI fail"
-              exit 1
-            fi
-          done
-          echo "✓ all gated jobs succeeded — CI green"
+      - name: Pre-test gates (shard 1 only — they're not test files)
+        if: matrix.shard == 1
+        run: bun run verify
+      - name: Run test shard ${{ matrix.shard }}/4
+        run: scripts/test-shard.sh ${{ matrix.shard }} 4
+      - name: Run *.serial.test.ts at --max-concurrency=1 (shard 1 only)
+        # Serial files share file-wide state (top-level mock.module, module
+        # singletons) that leaks across files in the same bun-test process.
+        # test-shard.sh excludes them; this step runs them at concurrency=1.
+        if: matrix.shard == 1
+        run: bun run test:serial

AGENTS.md

@@ -32,12 +32,8 @@ start here.
 ## Read this order
 
 1. `./AGENTS.md` (this file) — install + operating protocol.
-2. [`./CLAUDE.md`](./CLAUDE.md) — orientation + resolver: architecture, cross-cutting
-   invariants, the reference map, inline ship rules. It routes to on-demand detail docs:
-   [`./docs/architecture/KEY_FILES.md`](./docs/architecture/KEY_FILES.md) (per-file index —
-   read a file's entry before editing it), [`./docs/TESTING.md`](./docs/TESTING.md) (test
-   tiers + isolation lint + E2E lifecycle), and
-   [`./docs/architecture/thin-client.md`](./docs/architecture/thin-client.md) (remote-MCP seam).
+2. [`./CLAUDE.md`](./CLAUDE.md) — architecture reference, key files, trust boundaries,
+   test layout.
 3. [`./docs/architecture/brains-and-sources.md`](./docs/architecture/brains-and-sources.md)
    — the two-axis mental model (brain = which DB, source = which repo in the DB). Every
    query routes on both axes. Read before writing anything that touches brain ops.
@@ -90,13 +86,7 @@ writing or reviewing an operation, consult `src/core/operations.ts` for the cont
   with regressions auto-flagged, or `gbrain founder scorecard <entity-slug>`
   for a four-signal JSON rollup (claim_accuracy / consistency /
   growth_trajectory / red_flags). MCP op `find_trajectory` exposes the
-  same data — read scope, visibility-filtered for remote callers. **v0.40.2.0:**
-  `gbrain think` now uses this substrate automatically on temporal /
-  knowledge_update intent (default ON; flip `think.trajectory_enabled=false`
-  to opt out). Migration v82 added `facts.event_type` so non-metric event
-  rows (`meeting`, `job_change`, `location_change`) ride through the same
-  pipeline; pass `kind: 'event'` or `'all'` to `find_trajectory` to query
-  them.
+  same data — read scope, visibility-filtered for remote callers.
 - **Everything else:** [`./llms.txt`](./llms.txt) is the full documentation map.
   [`./llms-full.txt`](./llms-full.txt) is the same map with core docs inlined for
   single-fetch ingestion.
@@ -104,18 +94,15 @@ writing or reviewing an operation, consult `src/core/operations.ts` for the cont
 ## Before shipping
 
 Easiest path: `bun run ci:local` runs the full CI gate inside Docker (gitleaks,
-guards + typecheck, then 4-shard parallel unit + E2E against four pgvector
-containers plus a transaction-mode PgBouncer; unit phase keeps `DATABASE_URL`
-unset) and tears down. Use `bun run ci:local:diff` for the
+unit tests with `DATABASE_URL` unset, then all 29 E2E files sequentially against a
+fresh pgvector container) and tears down. Use `bun run ci:local:diff` for the
 diff-aware subset during fast iteration on a focused branch. Requires Docker
 (Docker Desktop / OrbStack / Colima) and `gitleaks` (`brew install gitleaks`).
 
 Manual path: `bun test` plus the E2E lifecycle described in `./CLAUDE.md` (spin
 up the test Postgres container, run `bun run test:e2e`, tear it down).
 
-Ship via the `/ship` skill, not by hand. The full release + contributor process
-(CHANGELOG voice, version-locations sync, PR conventions, community-PR-wave) lives in
-[`./docs/RELEASING.md`](./docs/RELEASING.md); read it before shipping.
+Ship via the `/ship` skill, not by hand.
 
 ## Privacy
 

CONTRIBUTING.md

@@ -57,7 +57,7 @@ bun run test                      # parallel 8-shard fan-out + serial post-pass
 bun test test/markdown.test.ts    # specific unit test
 
 # Pre-push gate (matches what CI runs on shard 1 + typecheck)
-bun run verify                    # privacy + jsonb + progress + test-isolation + wasm + admin-build + resolver + typecheck
+bun run verify                    # privacy + jsonb + progress + test-isolation + wasm + admin-build + typecheck
 
 # Pre-merge sanity (everything CI runs)
 bun run test:full                 # verify + parallel unit + slow + smart e2e
@@ -81,12 +81,9 @@ patterns (`scripts/check-jsonb-pattern.sh`), `\r` progress bleed to stdout
 (`scripts/check-progress-to-stdout.sh`), test-isolation rule violations
 (`scripts/check-test-isolation.sh` — see "Writing tests that survive the parallel
 loop" below), silent fallback to recursive chunking in the compiled binary
-(`scripts/check-wasm-embedded.sh`), stale admin-dashboard build artifacts
-(`scripts/check-admin-build.sh`), and resolver drift on bundled skills
-(`bun run check:resolver` — strict-mode `check-resolvable` that exit-1s on any
-warning, added in v0.41.14.0 to catch SKILL.md frontmatter ↔ RESOLVER.md drift
-before merge). `bun run check:all` runs the full historical sweep including the
-trailing-newline and exports-count checks.
+(`scripts/check-wasm-embedded.sh`), and stale admin-dashboard build artifacts
+(`scripts/check-admin-build.sh`). `bun run check:all` runs the full historical
+sweep including the trailing-newline and exports-count checks.
 
 ### Writing tests that survive the parallel loop
 

INSTALL_FOR_AGENTS.md

@@ -161,29 +161,6 @@ After this step:
 If a user has a very large brain (>10K pages), `extract --source db` is idempotent
 and supports `--since YYYY-MM-DD` for incremental runs.
 
-### Obsidian-style bare wikilinks (opt-in)
-
-If the user imported an Obsidian or Notion vault that uses **bare** `[[note-name]]`
-wikilinks — where `[[struktura]]` written in one folder means the page that lives
-at `projects/struktura.md` in another — GBrain does NOT connect those by default.
-Out of the box it only resolves path-qualified refs like `[[projects/struktura]]`,
-so a vault full of bare links shows up as a thin, broken graph. Turn on basename
-resolution so the cross-folder links connect:
-
-```bash
-gbrain config set link_resolution.global_basename true
-gbrain extract links --source db          # re-run so the new edges land
-```
-
-`gbrain doctor` surfaces a `link_resolution_opportunity` hint with the exact count
-("47 of 60 bare wikilinks would resolve") so you know whether it's worth enabling
-before you flip it. When a bare name matches more than one page (`[[struktura]]` →
-both `projects/struktura` and `archive/struktura`), GBrain emits one edge to each
-rather than guessing a winner — review and prune the duplicates with
-`gbrain graph-query <slug>`. The mode is also honored on the filesystem-walk path
-(`gbrain extract links` with no `--source db`) and by auto-link on every future
-`put_page`.
-
 ## Step 5: Load Skills
 
 If you're running an agent platform (OpenClaw, Hermes, or any repo with a workspace),
@@ -297,58 +274,3 @@ automatically during `gbrain post-upgrade` to fix the double-encoded JSONB
 columns. PGLite brains no-op. If wiki-style imports were truncated by the old
 `splitBody` bug, run `gbrain sync --full` after upgrading to rebuild
 `compiled_truth` from source markdown.
-
-## v0.42.0+ onboard surface (NEW)
-
-`gbrain onboard` is the activation surface gbrain did not have before.
-Once your brain has any content, run `gbrain onboard --check --json` to
-see structured recommendations across 5 brain-health axes (orphans,
-stale embeddings, entity link coverage, timeline coverage, takes count).
-
-**On first connect (after `gbrain init`):**
-```bash
-gbrain onboard --check --json
-```
-The JSON envelope (`schema_version: 1`) carries `recommendations[]` with
-`apply_policy` per item: `auto_apply` (safe to run unattended),
-`prompt_required` (needs explicit user consent), or `manual_only`
-(LLM-bearing, user must run themselves).
-
-**After every `gbrain upgrade`:**
-```bash
-gbrain onboard --check --json
-```
-New versions may surface new opportunities. The post-upgrade banner
-nudges the user when it runs, but agents should re-probe as a hygiene
-step regardless.
-
-**Unattended remediation (cron / autopilot):**
-```bash
-gbrain onboard --auto --max-usd 5
-```
-Refuses without `--max-usd N`. Runs auto-eligible items only. The
-autopilot daemon also consults onboard recommendations on its tick — no
-explicit agent action needed for the autonomous path.
-
-**Remote / federated brain installs (MCP):**
-The `run_onboard` MCP op (admin scope) lets thin-client agents probe
-brain health + drive remediation over OAuth-authenticated MCP. Protected
-LLM-bearing handlers (synthesize, patterns, consolidate, takes-bootstrap,
-contextual_reindex_per_chunk) require the additional `run_protected_onboard`
-scope — admin alone is insufficient. The MCP op returns
-`skipped_missing_scope[]` listing what would have run with the right
-grants.
-
-**Privacy + consent gates:**
-- `gbrain takes extract --from-pages` sends concept/atom/lore/briefing/
-  writing/originals page content to your configured chat model (default
-  Anthropic Haiku). Refuses to run unless `takes.bootstrap_enabled=true`
-  is set in config AND `--yes` is passed. Two-gate opt-in by design.
-- Autopilot's auto-apply tier for takes-bootstrap stays `manual_only`
-  until v0.42.1's eval gate (do not bypass).
-
-**Suppress nudges in CI / scripted environments:**
-```bash
-export GBRAIN_NO_ONBOARD_NUDGE=1
-```
-Init + upgrade banners auto-skip in non-TTY too.

README.md

@@ -1,176 +1,69 @@
 # GBrain
 
-**Search gives you raw pages. GBrain gives you the answer.** It's the brain layer your AI agent has been missing — the only one that does synthesis, graph traversal, and gap analysis in one box. Run a full autonomous agent on top of it, or just wire it into Claude Code or Codex as a supercharged retrieval layer in one command; either way your coding agent stops being amnesiac about everything that isn't code.
+Your AI agent is smart but forgetful. GBrain gives it a brain.
 
-I'm Garry Tan, President and CEO of Y Combinator. I built GBrain to run my own AI agents. It's the production brain behind my OpenClaw and Hermes deployments: **146,646 pages, 24,585 people, 5,339 companies**, 66 cron jobs running autonomously. My agent ingests meetings, emails, tweets, voice calls, and original ideas while I sleep. It enriches every person and company it encounters. It fixes its own citations and consolidates memory overnight. I wake up smarter than when I went to bed — and so will you.
+Built by the President and CEO of Y Combinator to run his actual AI agents. The production brain behind his OpenClaw and Hermes deployments: **146,646 pages, 24,585 people, 5,339 companies**, 66 cron jobs running autonomously. The agent ingests meetings, emails, tweets, voice calls, and original ideas while you sleep. It enriches every person and company it encounters. It fixes its own citations and consolidates memory overnight. You wake up smarter than when you went to bed.
 
-**And now it works as a company brain too.** Each person on the team gets their own slice of the brain, scoped by login. When you query, you only see what you're allowed to see — never another person's notes, never another team's data. We fuzz-tested this across every way you can read the brain (search, list, lookup, multi-source reads) and got zero leaks. Drop GBrain in as your team's shared institutional memory — the [company-brain](https://www.ycombinator.com/rfs#company-brain) shape YC just put on its Request for Startups. If you're building in that space, you might as well build on this. **[Tutorial: set up GBrain as your company brain →](docs/tutorials/company-brain.md)**
+The brain wires itself. Every page write extracts entity references and creates typed links (`attended`, `works_at`, `invested_in`, `founded`, `advises`) with zero LLM calls. Hybrid search. Self-wiring knowledge graph. Structured timeline. Backlink-boosted ranking. Ask "who works at Acme AI?" or "what did Bob invest in this quarter?" and get answers vector search alone can't reach. Benchmarked side-by-side: gbrain lands **P@5 49.1%, R@5 97.9%** on a 240-page Opus-generated rich-prose corpus, beating its graph-disabled variant by **+31.4 points P@5** and ripgrep-BM25 + vector-only RAG by a similar margin. Full BrainBench scorecards live in the sibling [gbrain-evals](https://github.com/garrytan/gbrain-evals) repo.
 
-Lots of personal-knowledge systems give you keyword matching and grep in a box. GBrain does that, and adds two things nobody else ships together:
+**New default in v0.36.2.0: ZeroEntropy** for both embedding (`zembed-1` at 1280d via Matryoshka) and reranker (`zerank-2`). On a real-corpus benchmark vs OpenAI and Voyage: **2.2× faster** (442ms vs OpenAI 973ms), **2.6× cheaper at regular pricing** ($0.05/M vs OpenAI $0.13), wins 11 of 20 queries head-to-head, reshuffles 60% of top-1 results when used as a second-pass reranker. Bring your own key from [zeroentropy.dev](https://dashboard.zeroentropy.dev), or switch to OpenAI/Voyage at install time via `gbrain init --pglite --embedding-model <provider:model> --embedding-dimensions <N>` — your choice is sticky. To switch an existing brain, run `gbrain reinit-pglite --embedding-model <provider:model> --embedding-dimensions <N>` (PGLite) or follow the SQL recipe in `docs/embedding-migrations.md` (Postgres). `gbrain config set embedding_model` is refused as of v0.37.11.0 because the schema column has to resize too.
 
-- **A synthesis layer that gives you the actual answer.** Synthesized, well-cited prose across people, companies, deals, and ideas. Not "here are 10 chunks that mention your query"; an actual answer with citations and an explicit note on what the brain doesn't know yet. The gap analysis is the part that changes how you use the brain.
-- **A self-wiring knowledge graph.** Every page write extracts entity refs and creates typed edges (`attended`, `works_at`, `invested_in`, `founded`, `advises`) with zero LLM calls. Ask "who works at Acme AI?" or "what did Bob invest in this quarter?" and get answers vector search alone can't reach. Benchmarked: **P@5 49.1%, R@5 97.9%** on a 240-page Opus-generated rich-prose corpus, **+31.4 points P@5** over its graph-disabled variant and over ripgrep-BM25 + vector-only RAG by a similar margin. Full BrainBench scorecards live in the sibling [gbrain-evals](https://github.com/garrytan/gbrain-evals) repo.
+GBrain is those patterns, generalized. Install in 30 minutes. Your agent does the work. As Garry's personal agent gets smarter, so does yours.
 
-The point of building a 100K-page brain is to use it as a strategic moat. To never lose context. To query what's in your own head without re-reading it. The brain layer is what makes the moat usable. The 24/7 dream cycle is what keeps it sharp. Both run on your hardware, your DB, your keys.
+**New in v0.36.4.0 — Your agent drives the brain to 90/100 by itself.** One command does the loop you used to run by hand: `gbrain doctor --remediate --yes --target-score 90 --max-usd 5`. It computes a dependency-ordered plan (sync before extract, embed after consolidate), submits each step as a Minion job, re-checks score between every step, and refuses to spend past your cost cap. Cron can drive it unattended. `gbrain doctor --remediation-plan --json` previews what would run. Autopilot now does the same thing on its 5-minute tick: small problems get targeted handlers, big problems get the full cycle, a healthy brain sleeps for 60 minutes instead of grinding through synthesize+patterns+embed every tick. Eleven new things you can submit as background jobs (`reindex`, `repair-jsonb`, `orphans`, `integrity`, `purge`, plus six cycle phases); three of them (synthesize, patterns, consolidate) are PROTECTED so an MCP-connected agent can't silently burn Anthropic credits. New `--background` flag on `gbrain embed` submits the job and exits with `job_id=N` for shell composition.
 
-It's easier to ship a daemon that runs 24/7 to ingest, enrich, and consolidate than it is to keep an agent in chat working hard. GBrain is that daemon, generalized. Install in 30 minutes. Your agent does the work. As my personal agent gets smarter, so does yours.
+**New in v0.35.7 — Temporal trajectory + founder scorecard.** Author typed metric assertions in the `## Facts` fence (`mrr=50000`, `arr=2000000`, `team_size=12`) and gbrain stores them as first-class typed columns. `gbrain eval trajectory companies/acme-example` prints the chronological history with regressions auto-flagged inline. `gbrain founder scorecard companies/acme-example` rolls up claim accuracy, consistency, growth direction, and red flags into a stable `schema_version: 1` JSON contract. New MCP op `find_trajectory` exposes the same data to agents (read scope, visibility-filtered for remote callers). The `consolidate` cycle phase now writes `valid_until` on chronologically-superseded facts AND uses semantic upsert on `(page_id, claim, since_date)` — re-running the dream cycle on stable input is now a true no-op (fixed a pre-existing duplicate-takes bug from prior versions).
 
 > **~30 minutes to a fully working brain.** Database ready in 2 seconds (PGLite, no server). You just answer questions about API keys.
 
 > **LLMs:** fetch [`llms.txt`](llms.txt) for the documentation map, or [`llms-full.txt`](llms-full.txt) for the same map with core docs inlined in one fetch. **Agents:** start with [`AGENTS.md`](AGENTS.md) (or [`CLAUDE.md`](CLAUDE.md) if you're Claude Code).
 
-## What this looks like
-
-Say you have a meeting with Alice tomorrow. You want to walk in remembering what she works on, when you last talked, and what's still open between you. Here's what you'd type, and what you'd get back.
-
-**You ask:**
-
-> "What do I need to know before my meeting with Alice tomorrow?"
-
-**Most personal-knowledge tools give you back a list of pages.** Something like:
-
-```
-1. people/alice — Alice runs engineering at Acme...
-2. meetings/2026-03-15-alice-q1 — Q1 product review with Alice...
-3. meetings/2026-01-08-acme-kickoff — Kickoff meeting with Acme team...
-4. customers/acme — Acme is a series-B fintech we work with...
-5. notes/2026-04-22 — Quick chat with Alice about pricing...
-```
-
-Five pages you now have to open and read yourself to actually prepare. The tool found the right material, but it didn't do the work.
-
-**GBrain gives you back the answer, with sources:**
-
-```
-Alice runs engineering at Acme (a series-B fintech). You last spoke
-on April 22 in a quick pricing chat. Three things are still open
-from that conversation:
-
-1. She owes you the security review for the new tier
-   (deadline was May 1; no update since).
-2. You committed to pricing for a 500-seat tier
-   (you sent it April 25; no response yet).
-3. She mentioned they're hiring a CISO; you said you'd intro
-   someone from your network.
-
-Heads up: nothing's been added to the brain about Alice or Acme
-since April 22, six weeks ago. She may have replied through email
-or Slack DM, channels the brain doesn't see. Worth asking her to
-catch up before assuming any of this is still current.
-```
-
-Every claim has a source page behind it. The "heads up" at the end tells you what the brain doesn't know yet, so you can ask Alice about it directly instead of being surprised. The brain just did your meeting prep.
-
-This is the difference between a search engine and a brain. Search finds the pages. The brain reads them for you and writes the answer.
-
 ## Install
 
-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.
+GBrain runs in three shapes. Pick the one that matches how you use AI agents today.
 
-### Have your agent install it (recommended)
+### Run with your agent platform
 
-If you don't already have an AI agent platform running, start with one of these. Both are designed to read GBrain's install protocol and execute it:
-
-- **[OpenClaw](https://github.com/openclawagents/openclaw)** — deploy [AlphaClaw on Render](https://render.com/deploy?repo=https://github.com/chrysb/alphaclaw) (one click, 8GB+ RAM)
-- **[Hermes](https://github.com/openclawagents/hermes)** — deploy on [Railway](https://github.com/praveen-ks-2001/hermes-agent-template) (one click)
-
-Then paste this into your agent:
-
-```
-Retrieve and follow the instructions at:
-https://raw.githubusercontent.com/garrytan/gbrain/master/INSTALL_FOR_AGENTS.md
-```
-
-The agent installs GBrain, creates the brain, asks for your API keys, loads 43 skills, configures the dream cycle, and verifies the install end-to-end. ~30 minutes. You answer questions, it does the work.
-
-> **Never set up an AI agent platform before?** The [personal-brain tutorial](docs/tutorials/personal-brain.md) walks the whole path end-to-end — picking OpenClaw vs Hermes, deploying it, pointing it at INSTALL_FOR_AGENTS.md, getting the API keys, and verifying the first query. Start there if any of the above is new.
-
-### Quick start: Claude Code or Codex
-
-Already running Claude Code or Codex? There are two ways to wire GBrain in, depending on what you want.
-
-**Just want a memory for your coding agent (recommended starting point).** Spin up a local brain and connect it in two commands — zero server, zero token, zero tunnel:
+Already using [OpenClaw](https://github.com/garrytan/openclaw) or [Hermes](https://github.com/garrytan/hermes)? GBrain installs as a skillpack scaffold into your agent's workspace.
 
 ```bash
-gbrain init --pglite                     # 2-second local brain (no Docker)
-claude mcp add gbrain -- gbrain serve    # or: codex mcp add gbrain -- gbrain serve
+gbrain init --pglite
+gbrain skillpack scaffold --all   # or: scaffold <name> per skill
 ```
 
-**Already have a brain on a remote host** (OpenClaw, Hermes, or any `gbrain serve --http`)? Point your laptop agents at it with one command each — `--install` wires it up and smoke-tests the token before handoff:
+That's it. Your agent picks up 43 skills (signal detection, brain-ops, ingest, enrich, citation-fixer, daily-task-manager, cron-scheduler, eval framework, and 35 more). Routing lives in `skills/RESOLVER.md` — the agent reads it once per request, picks the right skill, executes. Scaffolded skills are first-class members of your agent repo — you own them, edit freely; `gbrain skillpack reference <name>` diffs your copy against gbrain's bundle when you want to pull upstream improvements. (The legacy `gbrain skillpack install` managed-block model was retired in v0.36.0.0; run `gbrain skillpack migrate-fence` once if you're upgrading from an older release.)
 
-```bash
-gbrain connect https://your-host/mcp --token gbrain_xxx --install               # Claude Code
-gbrain connect https://your-host/mcp --token gbrain_xxx --agent codex --install # Codex
-```
+### CLI standalone
 
-**[→ Full walkthrough: give your coding agent a memory](docs/tutorials/connect-coding-agent.md)** — both paths end to end, plus the brain-first protocol you paste into `CLAUDE.md` / `AGENTS.md` and the four habits that make it actually change how you work.
-
-### Install the full autonomous setup into your existing agent
-
-Want the whole thing — local brain, 43 skills, the overnight dream cycle that enriches while you sleep? Paste this into Codex, Claude Code, Cursor, or another coding agent:
-
-```
-Retrieve and follow the instructions at:
-https://raw.githubusercontent.com/garrytan/gbrain/master/INSTALL_FOR_AGENTS.md
-```
-
-This works in any agent that can read files over HTTPS and execute shell commands. Tested with Codex, Claude Code, Claude Cowork, Cursor, and AlphaClaw.
-
-### CLI standalone (no agent)
+Use gbrain from any shell, no agent platform required.
 
 ```bash
 bun install -g github:garrytan/gbrain
-gbrain init --pglite     # 2 seconds; no server, no Docker
-gbrain doctor            # verify health
-gbrain import ~/notes/   # index your markdown
-gbrain query "what themes show up across my notes?"
+gbrain init --pglite   # 2 seconds; no server, no Docker
+gbrain doctor          # verify health
 ```
 
-Postgres-at-scale, Supabase, and thin-client setup paths live in [`docs/INSTALL.md`](docs/INSTALL.md).
-
-### Connect GBrain to your AI client (MCP)
-
-GBrain exposes 30+ tools over MCP (stdio and HTTP). The specific snippet depends on which client you use:
-
-- **[Claude Code](docs/mcp/CLAUDE_CODE.md)** — local: one command, `claude mcp add gbrain -- gbrain serve` (zero server, zero tunnel). Remote with just a bearer token: `gbrain connect https://your-host/mcp --token gbrain_xxx` prints a paste-ready block (or `--install` wires it up and smoke-tests the token).
-- **[Codex](docs/mcp/CODEX.md)** — `gbrain connect https://your-host/mcp --token gbrain_xxx --agent codex` (or `--install`). Codex reads the bearer from `$GBRAIN_REMOTE_TOKEN` at runtime, so the token never lands in Codex config.
-- **[Cursor / Windsurf / any stdio MCP client](docs/mcp/CLAUDE_CODE.md)** — same shape, add `{"command": "gbrain", "args": ["serve"]}` to your MCP config.
-- **[Claude Desktop (Cowork)](docs/mcp/CLAUDE_DESKTOP.md)** — Settings → Integrations → add the URL of your HTTP server. Remote only; the local `claude_desktop_config.json` does not work for remote servers.
-- **[Claude Cowork (team plan)](docs/mcp/CLAUDE_COWORK.md)** — org Owner adds the connector under Organization Settings → Connectors.
-- **[Perplexity Computer](docs/mcp/PERPLEXITY.md)** — `gbrain connect https://your-host/mcp --agent perplexity --oauth --register` mints a least-privilege OAuth client and prints the Issuer/Client ID/Secret to paste into Settings → Connectors (OAuth is the right path for a cloud connector; a bearer token also works for local use). Pro subscription required.
-- **[ChatGPT](docs/mcp/CHATGPT.md)** — uses OAuth 2.1 with PKCE (the hard requirement). Register a `chatgpt` client from the admin dashboard with grant type `authorization_code`.
-
-For the HTTP server itself:
+Then point any MCP-aware client (Claude Code, Cursor, Windsurf) at it, or use it from your shell:
 
 ```bash
-gbrain serve              # stdio MCP (local subprocess; for Claude Code, Cursor, Windsurf)
-gbrain serve --http       # HTTP MCP with OAuth 2.1 + admin dashboard at /admin
-                          # (required for Claude Desktop, Cowork, Perplexity, ChatGPT)
+gbrain search "who works at acme AI?"
+gbrain query "what did bob invest in this quarter?"
+gbrain graph-query people/garry-tan --depth 2
 ```
 
-The HTTP server includes DCR-style client registration, scope-gated access (`read` / `write` / `admin`), and rate limiting. Deployment guides (ngrok, Railway, Fly.io) live under [`docs/mcp/`](docs/mcp/).
+Detailed setup paths (Postgres at scale, Supabase, thin-client mode) live in [`docs/INSTALL.md`](docs/INSTALL.md).
 
-## Two ways to query your brain
-
-Raw retrieval (what most personal-knowledge tools ship) and a synthesis layer that gives you an actual answer. They serve different jobs.
+### MCP server (any MCP client)
 
 ```bash
-# raw retrieval: top pages by hybrid score, fast, no LLM cost
-gbrain search "who's working on AI agents at portfolio companies?"
-
-# brain layer: synthesized answer with citations and gap analysis
-gbrain think "who's working on AI agents at portfolio companies?"
+gbrain serve              # stdio MCP (Claude Desktop / Code / Cursor)
+gbrain serve --http       # HTTP MCP with OAuth 2.1 + admin dashboard
+                          # at /admin, SSE activity feed at /admin/events
 ```
 
-**`gbrain search`** returns the top retrieved pages, ranked by hybrid scoring (vector + keyword + RRF + source-tier boost + reranker). Use it when you want raw material to skim: agent context windows, citation lookups, finding a specific quote.
+Per-client guides (Claude Desktop, Code, Cursor, ChatGPT, Perplexity, Cowork) live under [`docs/mcp/`](docs/mcp/). HTTP server supports DCR-style client registration, scope-gated access (`read`/`write`/`admin`), and built-in rate limiting.
 
-**`gbrain think`** runs the same retrieval, then composes a synthesized answer across the results with explicit citations to the source pages AND an honest note on what the brain doesn't know yet. The gap analysis is the differentiator: the answer tells you when a page is stale, when a claim is uncited, when two pages contradict each other, when there's a hole you should fill.
-
-**Why it compounds.** Pair the brain layer with `find_trajectory` and you get answers like *"how have the company's metrics changed AND what does the team look like right now AND what did they promise / share AND when did we last meet AND what's the value-add I can offer here"*: well-scored, well-cited, in one shot. That's the strategic moat. That's why building a 100K-page brain is worth the effort.
-
-`gbrain agent run "..."` exposes the same surface to a sub-agent through the Minions queue, with crash-safe two-phase persistence. Same answers, durable.
-
-## How to get data in
+## How to get data in (v0.38+)
 
 One command, local or hosted, synchronous receipt:
 
@@ -181,7 +74,10 @@ echo "from a pipe" | gbrain capture --stdin
 SLUG=$(gbrain capture "..." --quiet)
 ```
 
-The page lands in the database and on disk in one move. Default slug `inbox/YYYY-MM-DD-<hash8>` so captures cluster in a predictable triage location. On thin-client installs the verb routes through MCP to the server: same command, same UX.
+The page lands in the DB AND on disk in one move (the v0.38 `put_page`
+write-through plumbing). Default slug `inbox/YYYY-MM-DD-<hash8>` so
+captures cluster in a predictable triage location. On thin-client installs
+the verb routes through MCP to the server — same command, same UX.
 
 For webhook ingestion (Zapier / IFTTT / Apple Shortcuts):
 
@@ -199,42 +95,6 @@ Third-party skillpacks can ship custom ingestion sources (Granola, Linear,
 voice, OCR) against the versioned `IngestionSource` contract at
 `gbrain/ingestion`. See [`docs/skillpack-anatomy.md`](docs/skillpack-anatomy.md).
 
-## Your brain's shape (schema packs)
-
-Most personal-knowledge tools force one fixed layout: their idea of "notes" + "people" + "tags." Drop a Notion export or your own years-old Obsidian vault on top, and the agent doesn't know what a `Projects/` folder means or whether `Reading/` is people or sources.
-
-**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-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).
-
-```bash
-gbrain schema active                # which pack is running, which tier set it
-gbrain schema list                  # bundled + installed packs
-gbrain schema detect                # propose types matching your filesystem
-gbrain schema suggest               # LLM-refined proposals on top of detect
-gbrain schema review-candidates     # human gate: promote / rename / ignore
-gbrain schema use my-pack           # activate
-```
-
-The active pack threads through every read + write path: `parseMarkdown` infers page type from the pack's path prefixes; `whoknows` scopes expert routing to types declared `expert_routing: true`; `extract_facts` runs only on `extractable: true` types; the search cache folds the pack name + version into its key so cross-pack contamination is structurally impossible. Switch packs and the brain re-interprets itself; switch back and nothing's lost.
-
-Seven-tier resolution chain (per-call flag → env var → per-source DB key → brain-wide DB key → `gbrain.yml` → `~/.gbrain/config.json` → `gbrain-base` default). Full reference + authoring guide: [`docs/architecture/schema-packs.md`](docs/architecture/schema-packs.md).
-
-## Tutorials
-
-Step-by-step walkthroughs for getting the most out of GBrain. Each one takes you from zero to a working outcome, with concrete commands and real numbers.
-
-- [**Set up your personal AI agent + brain from zero**](docs/tutorials/personal-brain.md) — the canonical full-stack install. Two GitHub repos, a Telegram bot, AlphaClaw on Render, OpenClaw + GBrain + Supabase. End-to-end in about 2 hours.
-- [**Set up GBrain as your company brain**](docs/tutorials/company-brain.md) — federated, multi-user, OAuth-scoped institutional memory for a 10-50 person team. About 90 minutes end-to-end.
-- [**Auto-improve a skill with `gbrain skillopt`**](docs/tutorials/improving-skills-with-skillopt.md) — treat a `SKILL.md` as a trainable parameter. Generate a starter benchmark straight from the skill with `--bootstrap-from-skill` (or write your own), strengthen the judges, then watch the optimizer propose edits and keep only the ones that measurably score higher. ~20 minutes, ~$1 in API calls. Flag + cost + safety reference: [`docs/guides/skillopt.md`](docs/guides/skillopt.md).
-
-More walkthroughs in progress: connecting an existing agent (Claude Code, Cursor, OpenClaw, Hermes) to a GBrain memory layer; setting up GBrain for VC dealflow with founder scorecards and meeting prep; migrating an existing Notion or Obsidian vault; indexing a codebase as a queryable code brain. Full tutorial index: [`docs/tutorials/`](docs/tutorials/).
-
-Want to see a tutorial that isn't here yet? [Open an issue](https://github.com/garrytan/gbrain/issues) describing the workflow you want documented.
-
 ## What it does (the loop)
 
 ```
@@ -252,38 +112,18 @@ The whole loop is described in [`docs/architecture/topologies.md`](docs/architec
 
 ## Capabilities
 
-**Hybrid search.** Vector (HNSW on pgvector) + BM25 keyword + reciprocal-rank fusion + source-tier boost + intent-aware query rewriting. Three named search modes (`conservative`, `balanced`, `tokenmax`) bundle the cost/quality knobs into a single config key. Live cost/recall comparisons in [`docs/eval/SEARCH_MODE_METHODOLOGY.md`](docs/eval/SEARCH_MODE_METHODOLOGY.md). Default: `balanced` with ZeroEntropy reranker on. Per-query graph signals notice when a top result is a hub for THAT query (adjacency boost), is corroborated across team brains (cross-source boost), or is being crowded out by weak chunks from a chatty session (session demote). Run `gbrain search "<query>" --explain` to see per-stage attribution: base score, every boost that fired, what it multiplied. `gbrain doctor` ships a `graph_signals_coverage` check; `gbrain search stats` shows fire counts and failure breakdowns. Vector retrieval pools the best chunk per page, so a page surfaces on its strongest evidence instead of losing to a neighbor on one weak chunk. Queries that match a page's title phrase or a declared free-text alias (`gbrain reindex --aliases` backfills existing pages) get boosted to the page they name. Every result carries an `evidence` tag (why it matched) and a `create_safety` hint (`exists` / `probable` / `unknown`) so an agent decides whether a page already exists instead of guessing from a raw score. `gbrain search diagnose "<query>" --target <slug>` traces which retrieval layer surfaces (or misses) a page.
+**Hybrid search.** Vector (HNSW on pgvector) + BM25 keyword + reciprocal-rank fusion + source-tier boost + intent-aware query rewriting. Three named search modes (`conservative`, `balanced`, `tokenmax`) bundle the cost/quality knobs into a single config key. Live cost/recall comparisons in [`docs/eval/SEARCH_MODE_METHODOLOGY.md`](docs/eval/SEARCH_MODE_METHODOLOGY.md). Default: `balanced` with ZeroEntropy reranker on.
 
-**Self-wiring knowledge graph.** Every `put_page` extracts entity refs from markdown/wikilinks/typed-link syntax and writes edges with zero LLM calls. Typed edges (`attended`, `works_at`, `invested_in`, `founded`, `advises`, `mentions`, …). Multi-hop traversal via `gbrain graph-query`. The graph is what produces the +31.4 P@5 lift over vector-only RAG. **Obsidian-style vaults:** bare `[[note-name]]` wikilinks that point across folders — you wrote `[[struktura]]` but the page lives at `projects/struktura.md` — resolve by basename once you opt in with `gbrain config set link_resolution.global_basename true`. Off by default; `gbrain doctor` tells you how many edges you'd gain before you flip it. See [migrating an Obsidian vault](INSTALL_FOR_AGENTS.md#step-45-wire-the-knowledge-graph).
+**Self-wiring knowledge graph.** Every `put_page` extracts entity refs from markdown/wikilinks/typed-link syntax and writes edges with zero LLM calls. Typed edges (`attended`, `works_at`, `invested_in`, `founded`, `advises`, `mentions`, …). Multi-hop traversal via `gbrain graph-query`. The graph is what produces the +31.4 P@5 lift over vector-only RAG.
 
 **Job queue (Minions).** BullMQ-shaped, Postgres-native job queue. Durable subagents (LLM tool loops that survive crashes via two-phase pending→done persistence), shell jobs with audit, child jobs with cascading timeouts, rate leases for outbound providers, attachments via S3/Supabase storage. Replaces "spawn subagent as fire-and-forget Promise" with something that recovers from anything.
 
-**Non-English brains (FTS language config).** The Postgres full-text search tokenizer is configurable via `GBRAIN_FTS_LANGUAGE`. Defaults to `english`. Set it to any text-search configuration that exists in your Postgres instance:
-
-```bash
-export GBRAIN_FTS_LANGUAGE=portuguese     # uses built-in portuguese stemmer
-export GBRAIN_FTS_LANGUAGE=spanish        # built-in spanish stemmer
-export GBRAIN_FTS_LANGUAGE=pt_br          # custom config (e.g. unaccent + portuguese)
-```
-
-List available configs: `psql -c "SELECT cfgname FROM pg_ts_config"`. Both the **query side** (`websearch_to_tsquery`) and the **write side** (the trigger functions that populate `pages.search_vector` and `content_chunks.search_vector`) honor `GBRAIN_FTS_LANGUAGE`. On first install (or upgrade), the `configurable_fts_language` schema migration reads the env var and creates trigger functions in the configured language; subsequent inserts/updates tokenize using that setting. To change language on a brain that has already run the migration, use the dedicated CLI command:
-
-```bash
-export GBRAIN_FTS_LANGUAGE=portuguese
-gbrain reindex-search-vector --dry-run    # preview row counts
-gbrain reindex-search-vector --yes        # recreate triggers + backfill
-```
-
-The command is idempotent (re-running with the same language is a no-op for vector content) and uses the same recreate-and-backfill primitives as the migration. For accent-insensitive Portuguese (`pt_br`), see [docs/guides/multi-language-fts.md](docs/guides/multi-language-fts.md) for the `unaccent` + portuguese stemmer recipe.
-
 **43 curated skills.** Routing lives in [`skills/RESOLVER.md`](skills/RESOLVER.md). Covers signal capture, ingest (idea / media / meeting), enrichment, querying, brain ops, citation fixing, daily task management, cron scheduling, reports, voice, soul audit, skill creation, eval framework, and migrations. Skills are markdown files (tool-agnostic), packaged as a single skillpack the installer drops into your agent workspace.
 
-**Eval framework.** `gbrain eval longmemeval` runs the public [LongMemEval](https://huggingface.co/datasets/xiaowu0162/longmemeval) benchmark against your hybrid retrieval. `gbrain eval export` + `gbrain eval replay` capture real queries and replay them against code changes (set `GBRAIN_CONTRIBUTOR_MODE=1`). `gbrain eval cross-modal` cross-checks an output against the task using three different-provider frontier models. `gbrain eval retrieval-quality` runs NamedThingBench, which hard-gates the named-thing retrieval families (title-substring, alias-synonym, generic-to-named, multi-chunk-dilution) so a regression in "find the page this query names" fails CI loudly. Full methodology in [`docs/eval/SEARCH_MODE_METHODOLOGY.md`](docs/eval/SEARCH_MODE_METHODOLOGY.md).
+**Eval framework.** `gbrain eval longmemeval` runs the public [LongMemEval](https://huggingface.co/datasets/xiaowu0162/longmemeval) benchmark against your hybrid retrieval. `gbrain eval export` + `gbrain eval replay` capture real queries and replay them against code changes (set `GBRAIN_CONTRIBUTOR_MODE=1`). `gbrain eval cross-modal` cross-checks an output against the task using three different-provider frontier models. Full methodology in [`docs/eval/SEARCH_MODE_METHODOLOGY.md`](docs/eval/SEARCH_MODE_METHODOLOGY.md).
 
 **Brain consistency.** `gbrain eval suspected-contradictions` samples retrieval pairs, layered date pre-filter, query-conditioned LLM judge, persistent cache. Surfaces conflicts between takes + facts the agent has written. Wired into the daily dream cycle.
 
-**Agent-authored schema (v0.40.7.0).** Your brain has a shape — what page types exist (`person`, `meeting`, `paper`, `case`, `lab-result`), what they link to (`attended`, `authored`, `prescribed-by`), what facts get extracted automatically. The default ships with 22 universal types, but your brain's actual shape is not the default shape. Agents can now evolve that shape on your behalf via 14 `gbrain schema` CLI verbs + a batched MCP op (`schema_apply_mutations`, admin scope, NOT localOnly so remote agents reach it over HTTPS). Atomic file locks, audit log with the agent's identity, chunked UPDATE backfill in 1000-row batches that never wedge concurrent writers. The brain stops being a pile of notes and becomes something with structure. **Why it matters:** [`docs/what-schemas-unlock.md`](docs/what-schemas-unlock.md) — 7 killer use cases (4000 invisible meetings, founder ops brain, research brain, legal brain, team brain, agent-as-co-curator). **5-minute walkthrough:** [`docs/schema-author-tutorial.md`](docs/schema-author-tutorial.md). **Agent skill:** [`skills/schema-author/SKILL.md`](skills/schema-author/SKILL.md).
-
 ## Integrations
 
 Data flowing into the brain. Each integration is a recipe — markdown + setup hints — that ships in `recipes/` and is discoverable via `gbrain integrations list`.
@@ -291,7 +131,6 @@ Data flowing into the brain. Each integration is a recipe — markdown + setup h
 - **Voice**: Phone calls create brain pages via Twilio + OpenAI Realtime (or DIY STT+LLM+TTS). Setup recipe: [`recipes/twilio-voice-brain.md`](recipes/twilio-voice-brain.md).
 - **Email + calendar**: webhook handlers that route to brain signals. [`docs/integrations/meeting-webhooks.md`](docs/integrations/meeting-webhooks.md).
 - **Embedding providers**: 16 recipes covering OpenAI (default fallback), OpenRouter, Voyage, ZeroEntropy (default), Google Gemini, Azure OpenAI, MiniMax, Alibaba DashScope, Zhipu, Ollama (local), llama.cpp llama-server (local), LiteLLM proxy. Pricing matrix + decision tree in [`docs/integrations/embedding-providers.md`](docs/integrations/embedding-providers.md).
-- **Rerankers**: ZeroEntropy `zerank-2` hosted (default in `tokenmax` mode) plus the v0.40.6.1 `llama-server-reranker` recipe for fully-local cross-encoder rerank via llama.cpp — runs Qwen3-Reranker or self-hosted ZeroEntropy weights against the same `gateway.rerank()` seam. Setup walkthrough in [`docs/ai-providers/llama-server-reranker.md`](docs/ai-providers/llama-server-reranker.md).
 - **Credential gateway**: vault-aware secret distribution. [`docs/integrations/credential-gateway.md`](docs/integrations/credential-gateway.md).
 - **MCP clients**: every major MCP client is supported. [`docs/mcp/`](docs/mcp/) per-client setup.
 
@@ -307,133 +146,11 @@ Data flowing into the brain. Each integration is a recipe — markdown + setup h
 
 ## Troubleshooting
 
-**`gbrain init --pglite` crashes on macOS 26.x (Tahoe)?** PGLite's embedded WASM engine is incompatible with macOS 26.x on Apple Silicon. The fix is to use native Homebrew PostgreSQL + pgvector instead. Full step-by-step setup in [`docs/INSTALL.md` — Troubleshooting: PGLite crashes on macOS 26.x](docs/INSTALL.md#pglite-crashes-on-macos-26x-tahoe).
-
-**`gbrain import` fails with `expected N dimensions, not M`?** Run `gbrain doctor`. It will print the exact `gbrain config set ...` or `gbrain retrieval-upgrade` command to repair the mismatch. You should not need to delete `~/.gbrain`. Fresh `gbrain init --pglite` auto-detects your embedding provider from API keys in your environment: set `OPENAI_API_KEY` (or `ZEROENTROPY_API_KEY` / `VOYAGE_API_KEY`) before running init, or pass `--embedding-model <provider>:<model>` explicitly. With multiple keys set, init fires an interactive picker. In non-TTY contexts (CI, Docker) with no keys, init exits 1 with a paste-ready setup hint; pass `--no-embedding` to defer setup until runtime. See [`docs/integrations/embedding-providers.md`](docs/integrations/embedding-providers.md) for the full provider matrix and [`docs/operations/headless-install.md`](docs/operations/headless-install.md) for Docker/CI sequencing.
-
-**Hourly cron sync keeps timing out on a federated brain?** v0.41.13.0 ships
-two flags + a recommended pattern. Switch your cron to a per-source loop
-with shell `timeout(1)` doing the OS-level kill and gbrain self-terminating
-gracefully half-a-minute earlier:
-
-```bash
-gbrain sync --break-lock --all --max-age 1800
-for src in $(gbrain sources list --json | jq -r '.[].id'); do
-  timeout 600 gbrain sync --source "$src" --timeout 540 || true
-done
-```
-
-When `--timeout` fires mid-import, `gbrain sync` exits 0 with status
-`partial` and `last_commit` UNCHANGED — the next run re-walks the same
-diff and `content_hash` short-circuits already-imported files. The
-`--max-age 1800` first command self-heals any wedged-but-alive locks
-left by a hung previous run, using the v98 `last_refreshed_at` semantic
-(NOT `acquired_at`) so healthy long-running holders are safe by
-construction. See the v0.41.13.0 entry in [`CHANGELOG.md`](CHANGELOG.md)
-for the honest scope notes (extract + embed phases run to completion;
-30-min rollout window for `--max-age` post-migration v98; full-sync
-triggers deferred to v0.42+).
-
-**Dream cycle silently losing wiki links on Supabase?** v0.41.19.0 fixes
-the bug class structurally. The engine now self-retries every bulk batch
-write (`addLinksBatch` / `addTimelineEntriesBatch` / `upsertChunks`) on
-Supavisor pooler blips, with a 12s worst-case wait that covers the full
-5-10s circuit-breaker recovery window. `gbrain doctor` surfaces incidents
-via the new `batch_retry_health` check (reads the last 24h of
-`~/.gbrain/audit/batch-retry-YYYY-Www.jsonl`). To tune for an unusually
-slow pooler:
-
-```bash
-# Defaults: 3 retries, base 1s, max 10s, decorrelated jitter.
-# Override per operator without a release:
-export GBRAIN_BULK_MAX_RETRIES=5       # int >= 0; 0 disables retries
-export GBRAIN_BULK_RETRY_BASE_MS=2000  # int > 0
-export GBRAIN_BULK_RETRY_MAX_MS=15000  # int >= base
-```
-
-Bad values surface at `gbrain doctor` startup with a paste-ready fix
-(not at first-retry mid-cycle). PGLite-only installs pay zero cost — the
-retry wrap is engine-level, but PGLite has no pooler so retries never
-fire in practice.
-
-**Dream cycle losing ~150 link rows per run with `'No database
-connection: connect() has not been called'` errors in the log?** v0.41.27.0
-makes the retry layer self-heal on a nulled-out database singleton. A
-new `reconnect` callback on `withRetry` rebuilds the connection between
-attempts; `PostgresEngine.batchRetry` injects `() => this.reconnect()`
-so engine-level batch writes survive a mid-cycle disconnect by something
-else in the same process. Same release: `gbrain capture` no longer trails
-a `'No database connection'` stderr line from a background facts:absorb
-worker firing after CLI exit — the op-dispatch finally block awaits
-`getFactsQueue().drainPending({timeout: 1000})` before
-`engine.disconnect()`. To find which code path is still calling
-disconnect mid-process, run `gbrain doctor --json | jq '.checks[] |
-select(.id=="batch_retry_health")'`; the extended check now surfaces
-24h disconnect-call count and the most-recent caller frame from a new
-`~/.gbrain/audit/db-disconnect-YYYY-Www.jsonl` audit. (Closes #1570.)
-
-**`gbrain brainstorm` returning `judge_failed: true` with 0 scored
-ideas?** v0.41.21.0 closes the two bugs that caused it. The judge
-hard-coded a 4K-token output cap; for any run past ~40 ideas the call
-truncated mid-JSON and the parser threw. Same release closes a slash-
-form pricing miss: `gbrain brainstorm --judge-model
-anthropic/claude-sonnet-4-6 --max-cost 5` failed with
-`BudgetExhausted reason=no_pricing` because every pricing site only
-matched the colon form. Both shapes work now. No config change, no
-schema migration — `gbrain upgrade` is the whole fix.
-
-**`gbrain reindex --markdown` wiped your auto/dream/signal-detector
-tags?** v0.41.37.0 makes tag reconciliation add-only. Re-import and
-`reindex --markdown` now ADD current frontmatter tags and never delete,
-so enrichment tags written to the DB (auto-tag, dream synthesize,
-signal-detector) survive a re-chunk. The reindex DB-only fallback also
-reconstructs the full markdown (frontmatter + body + timeline) before
-re-chunking, so a page with no on-disk source keeps its frontmatter,
-title, and timeline instead of getting overwritten with empty
-frontmatter. Trade-off: removing a tag from a page's frontmatter no
-longer removes it from the DB on the next sync (frontmatter-tag removal
-needs a provenance column, deferred). (Closes #1621.)
-
-**`gbrain sync` wedges on a large brain (no progress, high CPU)?**
-v0.41.37.0 ships three things. First, name the stalling file:
-
-```bash
-GBRAIN_SYNC_TRACE=1 gbrain sync --no-pull --no-embed --yes
-```
-
-The last `[sync] begin import: <path>` line with no following completion
-is the file being processed when the hang hit. Second, if you suspect a
-schema-pack `inference.regex` with catastrophic backtracking, complete
-the sync with the pack disabled and re-run extraction later:
-
-```bash
-gbrain sync --no-schema-pack --no-pull --no-embed --yes
-```
-
-`gbrain schema lint` now warns on the classic nested-quantifier ReDoS
-shapes (`(a+)+`, `(a*)*`, …) in pack regexes, and the runtime caps
-inference-regex input length (override via `GBRAIN_MAX_REGEX_INPUT_CHARS`).
-Third, on a PGLite brain, stop `gbrain serve` before a large sync —
-PGLite is single-writer and a live MCP server contends for the write
-lock. See [`docs/architecture/serve-sync-concurrency.md`](docs/architecture/serve-sync-concurrency.md)
-for the full triage. (Closes #1569.)
-
-**`gbrain init --migrate-only` / a schema migration fails on Windows
-with `getaddrinfo ENOTFOUND`?** v0.41.37.0 runs the 9 schema-bring-up
-phases in-process instead of spawning a child `gbrain init
---migrate-only` per phase. The spawned child died on
-Windows + bun + Supabase pooler with a DNS-resolution failure even
-though the parent connected fine; running in-process removes the spawn
-entirely. The v0.13.1 grandfather migration that hung 70+ minutes on an
-82K-page PGLite brain is also fixed — it now runs as a chunked bulk SQL
-pass (keyed on the page PK, soft-delete-filtered, source-safe) that
-completes in ~1-2 seconds. (Closes #1605, #1581.)
+**`gbrain import` fails with `expected N dimensions, not M`?** Run `gbrain doctor`. It will print the exact `gbrain config set ...` or `gbrain retrieval-upgrade` command to repair the mismatch. You should not need to delete `~/.gbrain`. As of v0.37, fresh `gbrain init --pglite` auto-detects your embedding provider from API keys in your environment — set `OPENAI_API_KEY` (or `ZEROENTROPY_API_KEY` / `VOYAGE_API_KEY`) before running init, or pass `--embedding-model <provider>:<model>` explicitly. With multiple keys set, init fires an interactive picker. In non-TTY contexts (CI, Docker) with no keys, init exits 1 with a paste-ready setup hint; pass `--no-embedding` to defer setup until runtime. See [`docs/integrations/embedding-providers.md`](docs/integrations/embedding-providers.md) for the full provider matrix and [`docs/operations/headless-install.md`](docs/operations/headless-install.md) for Docker/CI sequencing.
 
 ## Docs
 
 - [`docs/INSTALL.md`](docs/INSTALL.md) — every install path, end to end
-- [`docs/what-schemas-unlock.md`](docs/what-schemas-unlock.md) — why schemas matter: 7 killer use cases, the structural argument for typed page kinds, the agent-co-curates pattern (v0.40.7.0)
-- [`docs/schema-author-tutorial.md`](docs/schema-author-tutorial.md) — 5-minute walkthrough: fork the bundled pack, add a custom type, backfill existing pages, prove the wiring via `gbrain whoknows`
 - [`docs/architecture/`](docs/architecture/) — system design, topologies, retrieval theory
 - [`docs/guides/`](docs/guides/) — how-to runbooks (sub-agent routing, minion deployment, skill development, brain-first lookup, idea capture, diligence ingestion)
 - [`docs/integrations/`](docs/integrations/) — connecting external data sources (voice, email, calendar, embedding providers)
@@ -455,8 +172,8 @@ If you find a bug or want a feature: open an issue first. Quick fixes (typo, doc
 
 ## License + credit
 
-MIT. I built GBrain to run my OpenClaw and Hermes deployments — the production brain behind my AI agents.
+MIT. Built by Garry Tan to run his OpenClaw and Hermes deployments — the production brain behind his actual AI agents.
 
 Origin story: [`docs/ethos/ORIGIN.md`](docs/ethos/ORIGIN.md).
 
-Community PR contributors are credited in `CHANGELOG.md` per release. ZeroEntropy ([@zeroentropy](https://zeroentropy.dev)) for the embedding + reranker stack that ships as the default. Voyage AI for the asymmetric-encoding recipe template. Ramp Labs for the search quality improvements lineage.
+Community PR contributors are credited in `CHANGELOG.md` per release. ZeroEntropy ([@zeroentropy](https://zeroentropy.dev)) for the embedding + reranker stack that became the v0.36.2.0 default. Voyage AI for the asymmetric-encoding recipe template. Ramp Labs for the search quality improvements lineage.

SECURITY.md

@@ -50,55 +50,6 @@ exclusively via `gbrain auth create/list/revoke`.
 4. **Log all token issuance** — alert on unexpected registrations
 5. **Rate-limit registration and token endpoints**
 
-### Pre-registering claude.ai / ChatGPT clients without DCR (v0.41.3+)
-
-The recommended hardening posture above is: ship `gbrain serve --http`
-**without** `--enable-dcr` and pre-register every client manually. As of
-v0.41.3, `gbrain auth register-client` accepts the OAuth fields
-browser-based clients need:
-
-```bash
-# Pre-register claude.ai (confidential client; two redirect URIs)
-gbrain auth register-client claude-ai \
-  --scopes "read write" \
-  --redirect-uri https://claude.ai/api/mcp/auth_callback \
-  --redirect-uri https://claude.com/api/mcp/auth_callback
-# --grant-types is auto-set to authorization_code,refresh_token when
-# --redirect-uri is passed; pass --grant-types explicitly to override.
-
-# Pre-register ChatGPT (public PKCE client; no client_secret minted)
-gbrain auth register-client chatgpt \
-  --scopes "read write" \
-  --redirect-uri https://chatgpt.com/connector/oauth/<HASH> \
-  --token-endpoint-auth-method none
-```
-
-Auth methods (`--token-endpoint-auth-method`):
-
-- `client_secret_post` (default) — confidential client, secret in body
-- `client_secret_basic` — confidential client, secret in `Authorization` header
-- `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.
-
-### DCR consent default (v0.42.55+)
-
-The "disable `client_credentials`, only allow `authorization_code`" guidance
-above is now the built-in default for the DCR path, not just advice for custom
-wrappers. With `--enable-dcr` on, a self-registered client defaults to the
-`authorization_code` (browser-approval) grant, and an explicit
-`client_credentials` request is rejected with `invalid_client_metadata`.
-Operators who genuinely need the machine-to-machine grant on the registration
-endpoint opt in with `--enable-dcr-insecure` (which implies `--enable-dcr`); a
-startup WARNING prints whenever DCR is enabled, and a second when the insecure
-grant is allowed. Pre-registering clients via the CLI / admin API is unchanged.
-
 ### Token Management
 
 ```bash
@@ -150,19 +101,6 @@ 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
-`GBRAIN_HTTP_CORS_ORIGIN`, surfacing the default-deny posture before the
-first request.
-
 ### Rate limiting
 
 Two buckets, both stored in a bounded LRU map (default 10K keys, evicts
@@ -186,34 +124,15 @@ deployments.
 
 ### Reverse-proxy trust
 
-**Loopback-only by default** (v0.41.3+ Express server agrees with the
-legacy transport; pre-v0.41.3 the Express server hardcoded `'loopback'`
-while docs claimed "disabled by default" — that disagreement is gone).
-The default trusts only same-host proxies (127.0.0.1, ::1, fc00::/7);
-external forwarded-for headers are ignored regardless. To widen or
-narrow trust:
+Disabled by default. To honor `X-Forwarded-For` (or `X-Real-IP`) when
+gbrain runs behind a trusted reverse proxy:
 
 ```bash
-# Trust exactly one hop — Fly.io, Render, Vercel, single-layer nginx
 GBRAIN_HTTP_TRUST_PROXY=1 gbrain serve --http --port 8787
-
-# Trust N hops — Cloudflare → nginx → gbrain
-GBRAIN_HTTP_TRUST_PROXY=2 gbrain serve --http --port 8787
-
-# Disable entirely — direct-exposure deployment with no proxy
-GBRAIN_HTTP_TRUST_PROXY=0 gbrain serve --http --port 8787
-
-# Named Express modes (uniquelocal, linklocal) or CIDR lists pass through
-GBRAIN_HTTP_TRUST_PROXY=uniquelocal gbrain serve --http --port 8787
-GBRAIN_HTTP_TRUST_PROXY="10.0.0.0/8,192.168.1.0/24" gbrain serve --http --port 8787
 ```
 
-Both transports (Express OAuth server in `src/commands/serve-http.ts` and
-the legacy bearer transport in `src/mcp/http-transport.ts`) read the same
-env var, so single source of truth.
-
-**Critical safety contract:** only widen past `'loopback'` when **both**
-of these are true:
+**Critical safety contract:** only set `GBRAIN_HTTP_TRUST_PROXY=1` when
+**both** of these are true:
 
 1. gbrain is reachable only via a trusted reverse proxy (not directly
    exposed to the internet on the configured port). As of v0.34
@@ -226,11 +145,11 @@ of these are true:
    X-Forwarded-For $remote_addr` does this; Cloudflare and most cloud
    load balancers handle it automatically.)
 
-If gbrain is reachable directly AND `GBRAIN_HTTP_TRUST_PROXY=1` (or any
-non-loopback value) is set, clients can spoof their IP by sending
-arbitrary `X-Forwarded-For` headers, defeating the pre-auth IP rate
-limit. The `'loopback'` default protects against this by ignoring all
-forwarded-for headers and using the socket peer address.
+If gbrain is reachable directly AND `GBRAIN_HTTP_TRUST_PROXY=1` is set,
+clients can spoof their IP by sending arbitrary `X-Forwarded-For`
+headers, defeating the pre-auth IP rate limit. Without the flag, gbrain
+ignores all forwarded-for headers and uses the socket peer address,
+which is the safe default for direct-exposure deployments.
 
 ### Body size cap
 

VERSION

@@ -1 +1 @@
-0.42.64.0
+0.39.2.0

admin/bun.lock

@@ -13,52 +13,48 @@
         "@types/react-dom": "^19.1.2",
         "@vitejs/plugin-react": "^4.4.1",
         "typescript": "^5.8.3",
-        "vite": "^6.4.3",
+        "vite": "^6.3.3",
       },
     },
   },
-  "overrides": {
-    "@babel/core": "^7.29.6",
-    "postcss": "^8.5.10",
-  },
   "packages": {
-    "@babel/code-frame": ["@babel/code-frame@7.29.7", "", { "dependencies": { "@babel/helper-validator-identifier": "^7.29.7", "js-tokens": "^4.0.0", "picocolors": "^1.1.1" } }, "sha512-Aup7aUOfpbAUg2ROOJN6Iw5f9DMBlzu0mIkm/malLQFN/YQgO48wCj0Kxa3sEHJvPVFg7siR+qRInwXd2qhQKw=="],
+    "@babel/code-frame": ["@babel/code-frame@7.29.0", "", { "dependencies": { "@babel/helper-validator-identifier": "^7.28.5", "js-tokens": "^4.0.0", "picocolors": "^1.1.1" } }, "sha512-9NhCeYjq9+3uxgdtp20LSiJXJvN0FeCtNGpJxuMFZ1Kv3cWUNb6DOhJwUvcVCzKGR66cw4njwM6hrJLqgOwbcw=="],
 
-    "@babel/compat-data": ["@babel/compat-data@7.29.7", "", {}, "sha512-locTkQyKvwIEgBzVrn8693ebc97F2U8ZHjbXwDXJ5Fn2TCpNwTlKcaKLkdHop5c/icOFE7qt7Q9JC5hnKNa6Gg=="],
+    "@babel/compat-data": ["@babel/compat-data@7.29.0", "", {}, "sha512-T1NCJqT/j9+cn8fvkt7jtwbLBfLC/1y1c7NtCeXFRgzGTsafi68MRv8yzkYSapBnFA6L3U2VSc02ciDzoAJhJg=="],
 
-    "@babel/core": ["@babel/core@7.29.7", "", { "dependencies": { "@babel/code-frame": "^7.29.7", "@babel/generator": "^7.29.7", "@babel/helper-compilation-targets": "^7.29.7", "@babel/helper-module-transforms": "^7.29.7", "@babel/helpers": "^7.29.7", "@babel/parser": "^7.29.7", "@babel/template": "^7.29.7", "@babel/traverse": "^7.29.7", "@babel/types": "^7.29.7", "@jridgewell/remapping": "^2.3.5", "convert-source-map": "^2.0.0", "debug": "^4.1.0", "gensync": "^1.0.0-beta.2", "json5": "^2.2.3", "semver": "^6.3.1" } }, "sha512-RgHBCvtjbOK2gXSNBNIkNoEc9qoVEtau3hj8gEqKQuL3HZAibKarWFEI3Lfm6EYKkLalOh8eSrj9b+ch9H/VBA=="],
+    "@babel/core": ["@babel/core@7.29.0", "", { "dependencies": { "@babel/code-frame": "^7.29.0", "@babel/generator": "^7.29.0", "@babel/helper-compilation-targets": "^7.28.6", "@babel/helper-module-transforms": "^7.28.6", "@babel/helpers": "^7.28.6", "@babel/parser": "^7.29.0", "@babel/template": "^7.28.6", "@babel/traverse": "^7.29.0", "@babel/types": "^7.29.0", "@jridgewell/remapping": "^2.3.5", "convert-source-map": "^2.0.0", "debug": "^4.1.0", "gensync": "^1.0.0-beta.2", "json5": "^2.2.3", "semver": "^6.3.1" } }, "sha512-CGOfOJqWjg2qW/Mb6zNsDm+u5vFQ8DxXfbM09z69p5Z6+mE1ikP2jUXw+j42Pf1XTYED2Rni5f95npYeuwMDQA=="],
 
-    "@babel/generator": ["@babel/generator@7.29.7", "", { "dependencies": { "@babel/parser": "^7.29.7", "@babel/types": "^7.29.7", "@jridgewell/gen-mapping": "^0.3.12", "@jridgewell/trace-mapping": "^0.3.28", "jsesc": "^3.0.2" } }, "sha512-DkXD5OJQaAQIdZ1bt3UZdEnHAn9Imd3IVBdX03UFe+ony9Ojw5pzr9YVKGDY1jt+Gcn/FnGkNf8r+Vj5NOJWtQ=="],
+    "@babel/generator": ["@babel/generator@7.29.1", "", { "dependencies": { "@babel/parser": "^7.29.0", "@babel/types": "^7.29.0", "@jridgewell/gen-mapping": "^0.3.12", "@jridgewell/trace-mapping": "^0.3.28", "jsesc": "^3.0.2" } }, "sha512-qsaF+9Qcm2Qv8SRIMMscAvG4O3lJ0F1GuMo5HR/Bp02LopNgnZBC/EkbevHFeGs4ls/oPz9v+Bsmzbkbe+0dUw=="],
 
-    "@babel/helper-compilation-targets": ["@babel/helper-compilation-targets@7.29.7", "", { "dependencies": { "@babel/compat-data": "^7.29.7", "@babel/helper-validator-option": "^7.29.7", "browserslist": "^4.24.0", "lru-cache": "^5.1.1", "semver": "^6.3.1" } }, "sha512-wem6WaBj4NaVYVdNhLPPVacES6ZJ+KBBfSkTMD3YZxbP3rm3Di85tJU5ljaUNhaOynt+Aj0xruhYuzQBt8n71g=="],
+    "@babel/helper-compilation-targets": ["@babel/helper-compilation-targets@7.28.6", "", { "dependencies": { "@babel/compat-data": "^7.28.6", "@babel/helper-validator-option": "^7.27.1", "browserslist": "^4.24.0", "lru-cache": "^5.1.1", "semver": "^6.3.1" } }, "sha512-JYtls3hqi15fcx5GaSNL7SCTJ2MNmjrkHXg4FSpOA/grxK8KwyZ5bubHsCq8FXCkua6xhuaaBit+3b7+VZRfcA=="],
 
-    "@babel/helper-globals": ["@babel/helper-globals@7.29.7", "", {}, "sha512-3nQVUAtvkKH9zahfWgw96Jc/uFOmjACE1kQz82E2lqWmHBgjzbNlsC22nuQTfahmWeQtTq5nQ/4Nnd2A1wj4zA=="],
+    "@babel/helper-globals": ["@babel/helper-globals@7.28.0", "", {}, "sha512-+W6cISkXFa1jXsDEdYA8HeevQT/FULhxzR99pxphltZcVaugps53THCeiWA8SguxxpSp3gKPiuYfSWopkLQ4hw=="],
 
-    "@babel/helper-module-imports": ["@babel/helper-module-imports@7.29.7", "", { "dependencies": { "@babel/traverse": "^7.29.7", "@babel/types": "^7.29.7" } }, "sha512-ejHwrQQYcm9xnTivShn2IDOlIzInN34AXskvq9QicvCtEzq1Vzclu/tKF8Jq1Cg8JG2GL6/EmjgsCT7lXepE3g=="],
+    "@babel/helper-module-imports": ["@babel/helper-module-imports@7.28.6", "", { "dependencies": { "@babel/traverse": "^7.28.6", "@babel/types": "^7.28.6" } }, "sha512-l5XkZK7r7wa9LucGw9LwZyyCUscb4x37JWTPz7swwFE/0FMQAGpiWUZn8u9DzkSBWEcK25jmvubfpw2dnAMdbw=="],
 
-    "@babel/helper-module-transforms": ["@babel/helper-module-transforms@7.29.7", "", { "dependencies": { "@babel/helper-module-imports": "^7.29.7", "@babel/helper-validator-identifier": "^7.29.7", "@babel/traverse": "^7.29.7" }, "peerDependencies": { "@babel/core": "^7.0.0" } }, "sha512-UPUVSyXbOh627KiCIGQSgwWzGeBKLkaJ9PJEdrngIwMSzxLR4jS4+f1f1jb7VzBbg8nFLaYotvVPFCTqdrmTAg=="],
+    "@babel/helper-module-transforms": ["@babel/helper-module-transforms@7.28.6", "", { "dependencies": { "@babel/helper-module-imports": "^7.28.6", "@babel/helper-validator-identifier": "^7.28.5", "@babel/traverse": "^7.28.6" }, "peerDependencies": { "@babel/core": "^7.0.0" } }, "sha512-67oXFAYr2cDLDVGLXTEABjdBJZ6drElUSI7WKp70NrpyISso3plG9SAGEF6y7zbha/wOzUByWWTJvEDVNIUGcA=="],
 
     "@babel/helper-plugin-utils": ["@babel/helper-plugin-utils@7.28.6", "", {}, "sha512-S9gzZ/bz83GRysI7gAD4wPT/AI3uCnY+9xn+Mx/KPs2JwHJIz1W8PZkg2cqyt3RNOBM8ejcXhV6y8Og7ly/Dug=="],
 
-    "@babel/helper-string-parser": ["@babel/helper-string-parser@7.29.7", "", {}, "sha512-Pb5ijPrZ89GDH8223L4UP8i6QApWxs04RbPQJTeWDV0/keR2E36MeKnyr6LYmUUvqRRI+Iv87SuF1W6ErINzYw=="],
+    "@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
 
-    "@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.29.7", "", {}, "sha512-qehxGkRj55h/ff8EMaJ+cYhyaKlHIxqYDn682wQD7RNp9UujOQsHog2uS0r2vzr4pW+sXf90NeeayjcNaX3fFg=="],
+    "@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
 
-    "@babel/helper-validator-option": ["@babel/helper-validator-option@7.29.7", "", {}, "sha512-N9ZErrD+yW5geCDtBqnOoxmR8+tNKiGuxKlDpuJxfsqpa2dFcexaziGAE/qoHLiDDreVNMupxGmSoNlyvsA3gw=="],
+    "@babel/helper-validator-option": ["@babel/helper-validator-option@7.27.1", "", {}, "sha512-YvjJow9FxbhFFKDSuFnVCe2WxXk1zWc22fFePVNEaWJEu8IrZVlda6N0uHwzZrUM1il7NC9Mlp4MaJYbYd9JSg=="],
 
-    "@babel/helpers": ["@babel/helpers@7.29.7", "", { "dependencies": { "@babel/template": "^7.29.7", "@babel/types": "^7.29.7" } }, "sha512-1k2lAGRMfHTcwuNYcCNUmaUffmQv8KWMfh2iJUUeRlwlwH4FdNG7mfPI10NPfLHJFThE4Tyr4mv7kTNZOiPuBg=="],
+    "@babel/helpers": ["@babel/helpers@7.29.2", "", { "dependencies": { "@babel/template": "^7.28.6", "@babel/types": "^7.29.0" } }, "sha512-HoGuUs4sCZNezVEKdVcwqmZN8GoHirLUcLaYVNBK2J0DadGtdcqgr3BCbvH8+XUo4NGjNl3VOtSjEKNzqfFgKw=="],
 
-    "@babel/parser": ["@babel/parser@7.29.7", "", { "dependencies": { "@babel/types": "^7.29.7" }, "bin": "./bin/babel-parser.js" }, "sha512-hnORnjP/1P/zFEndoeX+n+t1RwWRJiJpM/jO7FW32Kn9r5+sJB2JWOdYo4L6k78j15eCwY3Gm/7364B1EMwtNg=="],
+    "@babel/parser": ["@babel/parser@7.29.2", "", { "dependencies": { "@babel/types": "^7.29.0" }, "bin": "./bin/babel-parser.js" }, "sha512-4GgRzy/+fsBa72/RZVJmGKPmZu9Byn8o4MoLpmNe1m8ZfYnz5emHLQz3U4gLud6Zwl0RZIcgiLD7Uq7ySFuDLA=="],
 
     "@babel/plugin-transform-react-jsx-self": ["@babel/plugin-transform-react-jsx-self@7.27.1", "", { "dependencies": { "@babel/helper-plugin-utils": "^7.27.1" }, "peerDependencies": { "@babel/core": "^7.0.0-0" } }, "sha512-6UzkCs+ejGdZ5mFFC/OCUrv028ab2fp1znZmCZjAOBKiBK2jXD1O+BPSfX8X2qjJ75fZBMSnQn3Rq2mrBJK2mw=="],
 
     "@babel/plugin-transform-react-jsx-source": ["@babel/plugin-transform-react-jsx-source@7.27.1", "", { "dependencies": { "@babel/helper-plugin-utils": "^7.27.1" }, "peerDependencies": { "@babel/core": "^7.0.0-0" } }, "sha512-zbwoTsBruTeKB9hSq73ha66iFeJHuaFkUbwvqElnygoNbj/jHRsSeokowZFN3CZ64IvEqcmmkVe89OPXc7ldAw=="],
 
-    "@babel/template": ["@babel/template@7.29.7", "", { "dependencies": { "@babel/code-frame": "^7.29.7", "@babel/parser": "^7.29.7", "@babel/types": "^7.29.7" } }, "sha512-puq+Gf35oI24FeN11LkoUQFqv9uwNeWpxXZi/Ji3rRIoKAzKnxRaZ+Gkj0vKS9ZCiTESfng1N9LyOyXvo+m+Gg=="],
+    "@babel/template": ["@babel/template@7.28.6", "", { "dependencies": { "@babel/code-frame": "^7.28.6", "@babel/parser": "^7.28.6", "@babel/types": "^7.28.6" } }, "sha512-YA6Ma2KsCdGb+WC6UpBVFJGXL58MDA6oyONbjyF/+5sBgxY/dwkhLogbMT2GXXyU84/IhRw/2D1Os1B/giz+BQ=="],
 
-    "@babel/traverse": ["@babel/traverse@7.29.7", "", { "dependencies": { "@babel/code-frame": "^7.29.7", "@babel/generator": "^7.29.7", "@babel/helper-globals": "^7.29.7", "@babel/parser": "^7.29.7", "@babel/template": "^7.29.7", "@babel/types": "^7.29.7", "debug": "^4.3.1" } }, "sha512-EhlfNQtZ+NK22w5BM61ciuiq1m58ed33Wr1Xan//ZRTy6hgjnwyCffRYwzsGXdASJSUJ1guZILsErh1eQcl+zw=="],
+    "@babel/traverse": ["@babel/traverse@7.29.0", "", { "dependencies": { "@babel/code-frame": "^7.29.0", "@babel/generator": "^7.29.0", "@babel/helper-globals": "^7.28.0", "@babel/parser": "^7.29.0", "@babel/template": "^7.28.6", "@babel/types": "^7.29.0", "debug": "^4.3.1" } }, "sha512-4HPiQr0X7+waHfyXPZpWPfWL/J7dcN1mx9gL6WdQVMbPnF3+ZhSMs8tCxN7oHddJE9fhNE7+lxdnlyemKfJRuA=="],
 
-    "@babel/types": ["@babel/types@7.29.7", "", { "dependencies": { "@babel/helper-string-parser": "^7.29.7", "@babel/helper-validator-identifier": "^7.29.7" } }, "sha512-4zBIxpPzowiZpusoFkyGVwakdRJUyuH5PxQ/PrqghfdFWWasvnCdPfQXHrenDai+gyLARulZjZowCOj6fjT4pA=="],
+    "@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
 
     "@esbuild/aix-ppc64": ["@esbuild/aix-ppc64@0.25.12", "", { "os": "aix", "cpu": "ppc64" }, "sha512-Hhmwd6CInZ3dwpuGTF8fJG6yoWmsToE+vYgD4nytZVxcu1ulHpUQRAB1UJ8+N1Am3Mz4+xOByoQoSZf4D+CpkA=="],
 
@@ -224,7 +220,7 @@
 
     "ms": ["ms@2.1.3", "", {}, "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="],
 
-    "nanoid": ["nanoid@3.3.16", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-bzlKTyNJ7+LdGIIwy8ijFpIqEQIvafahV7eYykJ8Cvh42EdJeODoJ6gUJXpQJvej1BddH8OqTXZNE/KfbWAu8Q=="],
+    "nanoid": ["nanoid@3.3.11", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w=="],
 
     "node-releases": ["node-releases@2.0.37", "", {}, "sha512-1h5gKZCF+pO/o3Iqt5Jp7wc9rH3eJJ0+nh/CIoiRwjRxde/hAHyLPXYN4V3CqKAbiZPSeJFSWHmJsbkicta0Eg=="],
 
@@ -232,7 +228,7 @@
 
     "picomatch": ["picomatch@4.0.4", "", {}, "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A=="],
 
-    "postcss": ["postcss@8.5.19", "", { "dependencies": { "nanoid": "^3.3.12", "picocolors": "^1.1.1", "source-map-js": "^1.2.1" } }, "sha512-Mz8SaolMd8nB+G13WkORcxQKHZ/NE4xXevtkJHVuG+guo9/wYKlIMTKAqGdEmYOXR2ijPjTYNHssizdaVSUNdQ=="],
+    "postcss": ["postcss@8.5.9", "", { "dependencies": { "nanoid": "^3.3.11", "picocolors": "^1.1.1", "source-map-js": "^1.2.1" } }, "sha512-7a70Nsot+EMX9fFU3064K/kdHWZqGVY+BADLyXc8Dfv+mTLLVl6JzJpPaCZ2kQL9gIJvKXSLMHhqdRRjwQeFtw=="],
 
     "react": ["react@19.2.5", "", {}, "sha512-llUJLzz1zTUBrskt2pwZgLq59AemifIftw4aB7JxOqf1HY2FDaGDxgwpAPVzHU1kdWabH7FauP4i1oEeer2WCA=="],
 
@@ -254,36 +250,8 @@
 
     "update-browserslist-db": ["update-browserslist-db@1.2.3", "", { "dependencies": { "escalade": "^3.2.0", "picocolors": "^1.1.1" }, "peerDependencies": { "browserslist": ">= 4.21.0" }, "bin": { "update-browserslist-db": "cli.js" } }, "sha512-Js0m9cx+qOgDxo0eMiFGEueWztz+d4+M3rGlmKPT+T4IS/jP4ylw3Nwpu6cpTTP8R1MAC1kF4VbdLt3ARf209w=="],
 
-    "vite": ["vite@6.4.3", "", { "dependencies": { "esbuild": "^0.25.0", "fdir": "^6.4.4", "picomatch": "^4.0.2", "postcss": "^8.5.3", "rollup": "^4.34.9", "tinyglobby": "^0.2.13" }, "optionalDependencies": { "fsevents": "~2.3.3" }, "peerDependencies": { "@types/node": "^18.0.0 || ^20.0.0 || >=22.0.0", "jiti": ">=1.21.0", "less": "*", "lightningcss": "^1.21.0", "sass": "*", "sass-embedded": "*", "stylus": "*", "sugarss": "*", "terser": "^5.16.0", "tsx": "^4.8.1", "yaml": "^2.4.2" }, "optionalPeers": ["@types/node", "jiti", "less", "lightningcss", "sass", "sass-embedded", "stylus", "sugarss", "terser", "tsx", "yaml"], "bin": { "vite": "bin/vite.js" } }, "sha512-NTKlcQjlAK7MlQoyb6LgaqHc8sso/pVyUJYWMws3jg21uTJw/LddqIFPcPqP6PzpgbIcZyKI85sFE4HBrQDA8A=="],
+    "vite": ["vite@6.4.2", "", { "dependencies": { "esbuild": "^0.25.0", "fdir": "^6.4.4", "picomatch": "^4.0.2", "postcss": "^8.5.3", "rollup": "^4.34.9", "tinyglobby": "^0.2.13" }, "optionalDependencies": { "fsevents": "~2.3.3" }, "peerDependencies": { "@types/node": "^18.0.0 || ^20.0.0 || >=22.0.0", "jiti": ">=1.21.0", "less": "*", "lightningcss": "^1.21.0", "sass": "*", "sass-embedded": "*", "stylus": "*", "sugarss": "*", "terser": "^5.16.0", "tsx": "^4.8.1", "yaml": "^2.4.2" }, "optionalPeers": ["@types/node", "jiti", "less", "lightningcss", "sass", "sass-embedded", "stylus", "sugarss", "terser", "tsx", "yaml"], "bin": { "vite": "bin/vite.js" } }, "sha512-2N/55r4JDJ4gdrCvGgINMy+HH3iRpNIz8K6SFwVsA+JbQScLiC+clmAxBgwiSPgcG9U15QmvqCGWzMbqda5zGQ=="],
 
     "yallist": ["yallist@3.1.1", "", {}, "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g=="],
-
-    "@types/babel__core/@babel/parser": ["@babel/parser@7.29.2", "", { "dependencies": { "@babel/types": "^7.29.0" }, "bin": "./bin/babel-parser.js" }, "sha512-4GgRzy/+fsBa72/RZVJmGKPmZu9Byn8o4MoLpmNe1m8ZfYnz5emHLQz3U4gLud6Zwl0RZIcgiLD7Uq7ySFuDLA=="],
-
-    "@types/babel__core/@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
-
-    "@types/babel__generator/@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
-
-    "@types/babel__template/@babel/parser": ["@babel/parser@7.29.2", "", { "dependencies": { "@babel/types": "^7.29.0" }, "bin": "./bin/babel-parser.js" }, "sha512-4GgRzy/+fsBa72/RZVJmGKPmZu9Byn8o4MoLpmNe1m8ZfYnz5emHLQz3U4gLud6Zwl0RZIcgiLD7Uq7ySFuDLA=="],
-
-    "@types/babel__template/@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
-
-    "@types/babel__traverse/@babel/types": ["@babel/types@7.29.0", "", { "dependencies": { "@babel/helper-string-parser": "^7.27.1", "@babel/helper-validator-identifier": "^7.28.5" } }, "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A=="],
-
-    "@types/babel__core/@babel/types/@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
-
-    "@types/babel__core/@babel/types/@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
-
-    "@types/babel__generator/@babel/types/@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
-
-    "@types/babel__generator/@babel/types/@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
-
-    "@types/babel__template/@babel/types/@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
-
-    "@types/babel__template/@babel/types/@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
-
-    "@types/babel__traverse/@babel/types/@babel/helper-string-parser": ["@babel/helper-string-parser@7.27.1", "", {}, "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA=="],
-
-    "@types/babel__traverse/@babel/types/@babel/helper-validator-identifier": ["@babel/helper-validator-identifier@7.28.5", "", {}, "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q=="],
   }
 }

admin/dist/index.html

@@ -7,7 +7,7 @@
   <link rel="preconnect" href="https://fonts.googleapis.com" />
   <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
   <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet" />
-  <script type="module" crossorigin src="/admin/assets/index-CoGEje3-.js"></script>
+  <script type="module" crossorigin src="/admin/assets/index-DFgMZhBE.js"></script>
   <link rel="stylesheet" crossorigin href="/admin/assets/index-GxkWX7v3.css">
 </head>
 <body>

admin/package.json

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

admin/src/App.tsx

@@ -4,14 +4,13 @@ import { DashboardPage } from './pages/Dashboard';
 import { AgentsPage } from './pages/Agents';
 import { RequestLogPage } from './pages/RequestLog';
 import { CalibrationPage } from './pages/Calibration';
-import { JobsWatchPage } from './pages/JobsWatch';
 import { api } from './api';
 
-type Page = 'login' | 'dashboard' | 'agents' | 'log' | 'calibration' | 'jobs';
+type Page = 'login' | 'dashboard' | 'agents' | 'log' | 'calibration';
 
 function getPage(): Page {
   const hash = window.location.hash.replace('#', '') || 'dashboard';
-  if (['login', 'dashboard', 'agents', 'log', 'calibration', 'jobs'].includes(hash)) return hash as Page;
+  if (['login', 'dashboard', 'agents', 'log', 'calibration'].includes(hash)) return hash as Page;
   return 'dashboard';
 }
 
@@ -58,8 +57,6 @@ export function App() {
              onClick={() => navigate('log')}>Request Log</a>
           <a className={`nav-item ${page === 'calibration' ? 'active' : ''}`}
              onClick={() => navigate('calibration')}>Calibration</a>
-          <a className={`nav-item ${page === 'jobs' ? 'active' : ''}`}
-             onClick={() => navigate('jobs')}>Jobs Watch</a>
         </div>
         <div style={{ marginTop: 'auto', padding: '16px 12px', borderTop: '1px solid var(--border)' }}>
           <button
@@ -85,7 +82,6 @@ export function App() {
         {page === 'agents' && <AgentsPage />}
         {page === 'log' && <RequestLogPage />}
         {page === 'calibration' && <CalibrationPage />}
-        {page === 'jobs' && <JobsWatchPage />}
       </main>
     </div>
   );

admin/src/api.ts

@@ -50,6 +50,4 @@ export const api = {
     apiFetch(`/admin/api/calibration/profile${holder ? `?holder=${encodeURIComponent(holder)}` : ''}`),
   calibrationChart: (type: string, holder?: string) =>
     apiFetchText(`/admin/api/calibration/charts/${encodeURIComponent(type)}${holder ? `?holder=${encodeURIComponent(holder)}` : ''}`),
-  // v0.41 D2 — live minion-jobs dashboard snapshot.
-  jobsWatch: () => apiFetch('/admin/api/jobs/watch'),
 };

admin/src/pages/Dashboard.tsx

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

admin/src/pages/JobsWatch.tsx

@@ -1,174 +0,0 @@
-import React, { useEffect, useState } from 'react';
-import { api } from '../api';
-
-/**
- * v0.41 D2 — live jobs dashboard. Browser counterpart to the TTY
- * `gbrain jobs watch` command. Polls `/admin/api/jobs/watch` every
- * 1s (matches TTY refresh cadence; SSE upgrade is a v0.42 follow-up
- * once the same wiring lands in serve-http for the TTY command).
- *
- * Layout intentionally matches the TTY 1:1 so an operator looking at
- * both surfaces sees the same panels in the same order.
- */
-
-interface WatchSnapshot {
-  ts_ms: number;
-  by_type: Array<{ name: string; total: number; completed: number; failed: number; dead: number }>;
-  queue_health: { waiting: number; active: number; stalled: number };
-  lease_pressure_1h: number;
-  top_errors: Array<{ cluster: string; count: number }>;
-  budget_owners: Array<{ owner_id: number; remaining_cents: number; total_spent_cents: number }>;
-}
-
-function leasePressureColor(n: number): string {
-  if (n === 0) return 'var(--accent-success, #2ea043)';
-  if (n >= 100) return 'var(--accent-danger, #f85149)';
-  return 'var(--accent-warn, #d29922)';
-}
-
-function dollars(cents: number): string {
-  return `$${(cents / 100).toFixed(2)}`;
-}
-
-export function JobsWatchPage() {
-  const [snap, setSnap] = useState<WatchSnapshot | null>(null);
-  const [err, setErr] = useState<string | null>(null);
-
-  useEffect(() => {
-    let alive = true;
-    let timer: ReturnType<typeof setTimeout> | null = null;
-
-    const tick = async () => {
-      try {
-        const data = await api.jobsWatch();
-        if (alive) {
-          setSnap(data);
-          setErr(null);
-        }
-      } catch (e) {
-        if (alive) setErr(e instanceof Error ? e.message : String(e));
-      }
-      if (alive) timer = setTimeout(tick, 1000);
-    };
-
-    tick();
-    return () => {
-      alive = false;
-      if (timer) clearTimeout(timer);
-    };
-  }, []);
-
-  if (err) {
-    return (
-      <div style={{ padding: 24, color: 'var(--accent-danger, #f85149)' }}>
-        <h2>Jobs Watch — error</h2>
-        <pre style={{ whiteSpace: 'pre-wrap' }}>{err}</pre>
-      </div>
-    );
-  }
-
-  if (!snap) {
-    return <div style={{ padding: 24, color: 'var(--text-muted, #777)' }}>Loading jobs watch…</div>;
-  }
-
-  const ts = new Date(snap.ts_ms).toLocaleTimeString();
-
-  return (
-    <div style={{ padding: 24, fontFamily: 'var(--font-mono, "JetBrains Mono", monospace)' }}>
-      <h1 style={{ fontSize: 18, marginBottom: 4 }}>
-        Jobs Watch
-        <span style={{ marginLeft: 12, color: 'var(--text-muted, #777)', fontSize: 12, fontWeight: 'normal' }}>
-          updated {ts}
-        </span>
-      </h1>
-
-      <section style={{ marginTop: 24 }}>
-        <h2 style={{ fontSize: 14, marginBottom: 8 }}>Queue</h2>
-        <div>
-          waiting=<b>{snap.queue_health.waiting}</b>{'  '}
-          active=<b>{snap.queue_health.active}</b>{'  '}
-          stalled=<b style={{ color: snap.queue_health.stalled > 0 ? 'var(--accent-warn, #d29922)' : undefined }}>
-            {snap.queue_health.stalled}
-          </b>
-        </div>
-      </section>
-
-      {snap.by_type.length > 0 && (
-        <section style={{ marginTop: 24 }}>
-          <h2 style={{ fontSize: 14, marginBottom: 8 }}>By type (24h)</h2>
-          <table style={{ borderCollapse: 'collapse' }}>
-            <thead>
-              <tr style={{ color: 'var(--text-muted, #777)', fontSize: 12 }}>
-                <th style={{ textAlign: 'left', padding: '4px 12px 4px 0' }}>name</th>
-                <th style={{ textAlign: 'right', padding: '4px 12px' }}>total</th>
-                <th style={{ textAlign: 'right', padding: '4px 12px' }}>done</th>
-                <th style={{ textAlign: 'right', padding: '4px 12px' }}>fail</th>
-                <th style={{ textAlign: 'right', padding: '4px 12px' }}>dead</th>
-              </tr>
-            </thead>
-            <tbody>
-              {snap.by_type.slice(0, 6).map(t => (
-                <tr key={t.name}>
-                  <td style={{ padding: '4px 12px 4px 0' }}>{t.name}</td>
-                  <td style={{ textAlign: 'right', padding: '4px 12px' }}>{t.total}</td>
-                  <td style={{ textAlign: 'right', padding: '4px 12px' }}>{t.completed}</td>
-                  <td style={{ textAlign: 'right', padding: '4px 12px' }}>{t.failed}</td>
-                  <td style={{ textAlign: 'right', padding: '4px 12px' }}>{t.dead}</td>
-                </tr>
-              ))}
-            </tbody>
-          </table>
-        </section>
-      )}
-
-      <section style={{ marginTop: 24 }}>
-        <h2 style={{ fontSize: 14, marginBottom: 8 }}>Lease pressure (1h)</h2>
-        <div style={{ color: leasePressureColor(snap.lease_pressure_1h) }}>
-          {snap.lease_pressure_1h} bounce{snap.lease_pressure_1h === 1 ? '' : 's'}
-        </div>
-      </section>
-
-      {snap.top_errors.length > 0 && (
-        <section style={{ marginTop: 24 }}>
-          <h2 style={{ fontSize: 14, marginBottom: 8 }}>Top errors (24h)</h2>
-          <table style={{ borderCollapse: 'collapse' }}>
-            <tbody>
-              {snap.top_errors.slice(0, 5).map(e => (
-                <tr key={e.cluster}>
-                  <td style={{ textAlign: 'right', padding: '4px 12px 4px 0', color: 'var(--text-muted, #777)' }}>
-                    {e.count}×
-                  </td>
-                  <td style={{ padding: '4px 12px 4px 0' }}>{e.cluster}</td>
-                </tr>
-              ))}
-            </tbody>
-          </table>
-        </section>
-      )}
-
-      {snap.budget_owners.length > 0 && (
-        <section style={{ marginTop: 24 }}>
-          <h2 style={{ fontSize: 14, marginBottom: 8 }}>Budget owners</h2>
-          <table style={{ borderCollapse: 'collapse' }}>
-            <thead>
-              <tr style={{ color: 'var(--text-muted, #777)', fontSize: 12 }}>
-                <th style={{ textAlign: 'left', padding: '4px 12px 4px 0' }}>owner</th>
-                <th style={{ textAlign: 'right', padding: '4px 12px' }}>spent</th>
-                <th style={{ textAlign: 'right', padding: '4px 12px' }}>remaining</th>
-              </tr>
-            </thead>
-            <tbody>
-              {snap.budget_owners.slice(0, 5).map(b => (
-                <tr key={b.owner_id}>
-                  <td style={{ padding: '4px 12px 4px 0' }}>{b.owner_id}</td>
-                  <td style={{ textAlign: 'right', padding: '4px 12px' }}>{dollars(b.total_spent_cents)}</td>
-                  <td style={{ textAlign: 'right', padding: '4px 12px' }}>{dollars(b.remaining_cents)}</td>
-                </tr>
-              ))}
-            </tbody>
-          </table>
-        </section>
-      )}
-    </div>
-  );
-}

bun.lock

@@ -26,8 +26,8 @@
         "express-rate-limit": "^7.5.0",
         "gray-matter": "^4.0.3",
         "heic-decode": "^2.1.0",
-        "js-yaml": "^3.15.0",
-        "marked": "^18.0.2",
+        "js-yaml": "^3.14.2",
+        "marked": "^18.0.0",
         "openai": "^4.0.0",
         "pgvector": "^0.2.0",
         "postgres": "^3.4.0",
@@ -50,17 +50,6 @@
   "trustedDependencies": [
     "@electric-sql/pglite",
   ],
-  "overrides": {
-    "@hono/node-server": "^1.19.13",
-    "fast-uri": "^3.1.2",
-    "fast-xml-builder": "^1.1.7",
-    "fast-xml-parser": "^5.7.0",
-    "form-data": "^4.0.6",
-    "hono": "^4.12.25",
-    "ip-address": "^10.1.1",
-    "js-yaml": "^3.15.0",
-    "qs": "^6.15.2",
-  },
   "packages": {
     "@ai-sdk/anthropic": ["@ai-sdk/anthropic@3.0.74", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@ai-sdk/provider-utils": "4.0.26" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-Xew9rfz9WWhDSyF8rNhjT/XWOWelNfJrMlmG0Ahw210hStisRpQZ1s+7VeI9JTJOZ5y5tXqBi5kfPwYnCfyRTA=="],
 
@@ -162,7 +151,7 @@
 
     "@electric-sql/pglite": ["@electric-sql/pglite@0.4.3", "", {}, "sha512-ichuWTgtd4mOM1G4SpyGJa5trT03lWbMypDV0fUXUCXg5hiHqVAz/bZyV68NqmkLB7WcYmj1RMJVSp8HV/v/ZQ=="],
 
-    "@hono/node-server": ["@hono/node-server@1.19.14", "", { "peerDependencies": { "hono": "^4" } }, "sha512-GwtvgtXxnWsucXvbQXkRgqksiH2Qed37H9xHZocE5sA3N8O8O8/8FA3uclQXxXVzc9XBZuEOMK7+r02FmSpHtw=="],
+    "@hono/node-server": ["@hono/node-server@1.19.12", "", { "peerDependencies": { "hono": "^4" } }, "sha512-txsUW4SQ1iilgE0l9/e9VQWmELXifEFvmdA1j6WFh/aFPj99hIntrSsq/if0UWyGVkmrRPKA1wCeP+UCr1B9Uw=="],
 
     "@jsquash/avif": ["@jsquash/avif@2.1.1", "", { "dependencies": { "wasm-feature-detect": "^1.2.11" } }, "sha512-LMRxd0fMgfCLtobDh0/sFYJMMiRJTNYSEEWvRDKXlAeZ08t3gI5V+1thIT0XjXJ+SVG7Zug9B0XPyx0Ti5VRNA=="],
 
@@ -170,8 +159,6 @@
 
     "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.29.0", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.2.1", "express-rate-limit": "^8.2.1", "hono": "^4.11.4", "jose": "^6.1.3", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.1" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-zo37mZA9hJWpULgkRpowewez1y6ML5GsXJPY8FI0tBBCd77HEvza4jDqRKOXgHNn867PVGCyTdzqpz0izu5ZjQ=="],
 
-    "@nodable/entities": ["@nodable/entities@3.0.0", "", {}, "sha512-8L9xFeTYKhm49xfIypoe2W5wV1m/3Z58kT+7kR9A8OyFxcPduI4VmxaUMQyKYrRjUoLLSXv6EKKID5Tvj9cUVw=="],
-
     "@opentelemetry/api": ["@opentelemetry/api@1.9.0", "", {}, "sha512-3giAOQvZiH5F9bMlMiv8+GSPMeqg0dbaeo58/0SlA9sxSqZhnUtxzX9/2FzyhS9sWQf5S0GJE0AKBrFqjpeYcg=="],
 
     "@smithy/chunked-blob-reader": ["@smithy/chunked-blob-reader@5.2.2", "", { "dependencies": { "tslib": "^2.6.2" } }, "sha512-St+kVicSyayWQca+I1rGitaOEH6uKgE8IUWoYnnEX26SWdWQcL6LvMSD19Lg+vYHKdT9B2Zuu7rd3i6Wnyb/iw=="],
@@ -320,8 +307,6 @@
 
     "ajv-formats": ["ajv-formats@3.0.1", "", { "dependencies": { "ajv": "^8.0.0" } }, "sha512-8iUql50EUR+uUcdRQ3HDqa6EVyo3docL8g5WJ3FNcWmu62IbkGUue/pEyLBW8VGKKucTPgqeks4fIU1DA4yowQ=="],
 
-    "anynum": ["anynum@1.0.1", "", {}, "sha512-N6//FLET/tXYNM/F6ABca1oH6fWB+KlTt909Le28WMDBk8oaT4vY17DCrwg2MvmuqUKt3Ni4N5dGJ/EoBgcO6A=="],
-
     "argparse": ["argparse@1.0.10", "", { "dependencies": { "sprintf-js": "~1.0.2" } }, "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg=="],
 
     "asynckit": ["asynckit@0.4.0", "", {}, "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="],
@@ -400,15 +385,15 @@
 
     "fast-deep-equal": ["fast-deep-equal@3.1.3", "", {}, "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q=="],
 
-    "fast-uri": ["fast-uri@3.1.3", "", {}, "sha512-i70LwGWUduXqzicKXWshooq+sWL1K3WUU5rKZNG/0i3a1OSoX3HqhH5WbWwTmqWfor4urUakGPiRQcleRZTwOg=="],
+    "fast-uri": ["fast-uri@3.1.0", "", {}, "sha512-iPeeDKJSWf4IEOasVVrknXpaBV0IApz/gp7S2bb7Z4Lljbl2MGJRqInZiUrQwV16cpzw/D3S5j5Julj/gT52AA=="],
 
-    "fast-xml-builder": ["fast-xml-builder@1.3.0", "", { "dependencies": { "path-expression-matcher": "^1.6.2", "xml-naming": "^0.3.0" } }, "sha512-F74cZEdCvuw9P41GAC3rod4X04jjWGM1JPEv/GWSqFTWLsdyMSBMBMlm9Hk3GLBgLBbdBNY8yee0pQh2RBVESQ=="],
+    "fast-xml-builder": ["fast-xml-builder@1.1.4", "", { "dependencies": { "path-expression-matcher": "^1.1.3" } }, "sha512-f2jhpN4Eccy0/Uz9csxh3Nu6q4ErKxf0XIsasomfOihuSUa3/xw6w8dnOtCDgEItQFJG8KyXPzQXzcODDrrbOg=="],
 
-    "fast-xml-parser": ["fast-xml-parser@5.10.1", "", { "dependencies": { "@nodable/entities": "^3.0.0", "fast-xml-builder": "^1.2.0", "is-unsafe": "^2.0.0", "path-expression-matcher": "^1.6.2", "strnum": "^2.4.1", "xml-naming": "^0.3.0" }, "bin": { "fxparser": "src/cli/cli.js" } }, "sha512-IEMIf7298kXuZSRFoGfMYrl7is8LpavODgbNz1cwIudv7KwVFnuU+UsMporfq6PD6aXSlawZlARiA3UywCTfMw=="],
+    "fast-xml-parser": ["fast-xml-parser@5.5.8", "", { "dependencies": { "fast-xml-builder": "^1.1.4", "path-expression-matcher": "^1.2.0", "strnum": "^2.2.0" }, "bin": { "fxparser": "src/cli/cli.js" } }, "sha512-Z7Fh2nVQSb2d+poDViM063ix2ZGt9jmY1nWhPfHBOK2Hgnb/OW3P4Et3P/81SEej0J7QbWtJqxO05h8QYfK7LQ=="],
 
     "finalhandler": ["finalhandler@2.1.1", "", { "dependencies": { "debug": "^4.4.0", "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "on-finished": "^2.4.1", "parseurl": "^1.3.3", "statuses": "^2.0.1" } }, "sha512-S8KoZgRZN+a5rNwqTxlZZePjT/4cnm0ROV70LedRHZ0p8u9fRID0hJUZQpkKLzro8LfmC8sx23bY6tVNxv8pQA=="],
 
-    "form-data": ["form-data@4.0.6", "", { "dependencies": { "asynckit": "^0.4.0", "combined-stream": "^1.0.8", "es-set-tostringtag": "^2.1.0", "hasown": "^2.0.4", "mime-types": "^2.1.35" } }, "sha512-vKatAh4SlVfgbv+YtmhiRjhEMJsYpsG1Y2rMQtR+SVSbytsSD1YGzDIcrAJmdFec88u/+VoGmxnl+80gL1tRCQ=="],
+    "form-data": ["form-data@4.0.5", "", { "dependencies": { "asynckit": "^0.4.0", "combined-stream": "^1.0.8", "es-set-tostringtag": "^2.1.0", "hasown": "^2.0.2", "mime-types": "^2.1.12" } }, "sha512-8RipRLol37bNs2bhoV67fiTEvdTrbMUYcFTiy3+wuuOnUog2QBHCZWXDRijWQfAkhBj2Uf5UnVaiWwA5vdd82w=="],
 
     "form-data-encoder": ["form-data-encoder@1.7.2", "", {}, "sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A=="],
 
@@ -432,11 +417,11 @@
 
     "has-tostringtag": ["has-tostringtag@1.0.2", "", { "dependencies": { "has-symbols": "^1.0.3" } }, "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw=="],
 
-    "hasown": ["hasown@2.0.4", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-T2UbfbBEF32wiepXIsMlTW9+dDYC6wMh/t/vYA4tuOMKqWz/n3vr1NFSxQiyP+zk2mXsoMA/i/7qV6LKut1t1A=="],
+    "hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
 
     "heic-decode": ["heic-decode@2.1.0", "", { "dependencies": { "libheif-js": "^1.19.8" } }, "sha512-0fB3O3WMk38+PScbHLVp66jcNhsZ/ErtQ6u2lMYu/YxXgbBtl+oKOhGQHa4RpvE68k8IzbWkABzHnyAIjR758A=="],
 
-    "hono": ["hono@4.12.30", "", {}, "sha512-emn+JoJjrN9YTpRDS5it/UI2SO9BAE37T6I3d963RxcZ81G9A4pr2SZTEiiaiKbzx+NKRg5BZ89fCL7gCJCUog=="],
+    "hono": ["hono@4.12.10", "", {}, "sha512-mx/p18PLy5og9ufies2GOSUqep98Td9q4i/EF6X7yJgAiIopxqdfIO3jbqsi3jRgTgw88jMDEzVKi+V2EF+27w=="],
 
     "http-errors": ["http-errors@2.0.1", "", { "dependencies": { "depd": "~2.0.0", "inherits": "~2.0.4", "setprototypeof": "~1.2.0", "statuses": "~2.0.2", "toidentifier": "~1.0.1" } }, "sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ=="],
 
@@ -446,7 +431,7 @@
 
     "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
 
-    "ip-address": ["ip-address@10.2.0", "", {}, "sha512-/+S6j4E9AHvW9SWMSEY9Xfy66O5PWvVEJ08O0y5JGyEKQpojb0K0GKpz/v5HJ/G0vi3D2sjGK78119oXZeE0qA=="],
+    "ip-address": ["ip-address@10.1.0", "", {}, "sha512-XXADHxXmvT9+CRxhXg56LJovE+bmWnEWB78LB83VZTprKTmaC5QfruXocxzTZ2Kl0DNwKuBdlIhjL8LeY8Sf8Q=="],
 
     "ipaddr.js": ["ipaddr.js@1.9.1", "", {}, "sha512-0KI/607xoxSToH7GjN1FfSbLoU0+btTicjsQSWQlh/hZykN8KpmMf7uYwPW3R+akZ6R/w18ZlXSHBYXiYUPO3g=="],
 
@@ -454,13 +439,11 @@
 
     "is-promise": ["is-promise@4.0.0", "", {}, "sha512-hvpoI6korhJMnej285dSg6nu1+e6uxs7zG3BYAm5byqDsgJNWwxzM6z6iZiAgQR4TJ30JmBTOwqZUw3WlyH3AQ=="],
 
-    "is-unsafe": ["is-unsafe@2.0.0", "", {}, "sha512-2LdV822R+wmI86unXA93WCFpL6g+av8ynWk0nrHyJqGop5VoocYsSLFgN8jrfalT6iGeLNM4KXuVSsULP53kEA=="],
-
     "isexe": ["isexe@2.0.0", "", {}, "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw=="],
 
     "jose": ["jose@6.2.2", "", {}, "sha512-d7kPDd34KO/YnzaDOlikGpOurfF0ByC2sEV4cANCtdqLlTfBlw2p14O/5d/zv40gJPbIQxfES3nSx1/oYNyuZQ=="],
 
-    "js-yaml": ["js-yaml@3.15.0", "", { "dependencies": { "argparse": "^1.0.7", "esprima": "^4.0.0" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-ttBQIIQPDeLjpPOohtUdXuXUVoA2uIB6fEH9HyJ7234s5mBJ5wTx20njxplLZQgLaOfpmPQA7X2t5AX6tIPbog=="],
+    "js-yaml": ["js-yaml@3.14.2", "", { "dependencies": { "argparse": "^1.0.7", "esprima": "^4.0.0" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-PMSmkqxr106Xa156c2M265Z+FTrPl+oxd/rgOQy2tijQeK5TxQ43psO1ZCwhVOSdnn+RzkzlRz/eY4BgJBYVpg=="],
 
     "json-schema": ["json-schema@0.4.0", "", {}, "sha512-es94M3nTIfsEPisRafak+HDLfHXnKBhV3vU5eqPcS3flIWqcxJWgXHXiey3YrpaNsanY5ei1VoYEbOzijuq9BA=="],
 
@@ -472,7 +455,7 @@
 
     "libheif-js": ["libheif-js@1.19.8", "", {}, "sha512-vQJWusIxO7wavpON1dusciL8Go9jsIQ+EUrckauFYAiSTjcmLAsuJh3SszLpvkwPci3JcL41ek2n+LUZGFpPIQ=="],
 
-    "marked": ["marked@18.0.6", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-MrV5puXBfuiy6wl6DLaq3BtIJQAJToAd5zt/ZKhRfGRAuFPALE7/4Y7jnxRQoEgK/pBgurGqLyAuRgZ2xOjr6w=="],
+    "marked": ["marked@18.0.0", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-2e7Qiv/HJSXj8rDEpgTvGKsP8yYtI9xXHKDnrftrmnrJPaFNM7VRb2YCzWaX4BP1iCJ/XPduzDJZMFoqTCcIMA=="],
 
     "math-intrinsics": ["math-intrinsics@1.1.0", "", {}, "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g=="],
 
@@ -504,7 +487,7 @@
 
     "parseurl": ["parseurl@1.3.3", "", {}, "sha512-CiyeOxFT/JZyN5m0z9PfXw4SCBJ6Sygz1Dpl0wqjlhDEGGBP1GnsUVEL0p63hoG1fcj3fHynXi9NYO4nWOL+qQ=="],
 
-    "path-expression-matcher": ["path-expression-matcher@1.6.2", "", {}, "sha512-enSlaiat05iasnzmgNxRj8reFdj3puY2QpNgP1aPIaVfT6nn9ICuPoFlKHk8EN22HcwewshO+mN2DGbkCEOtqQ=="],
+    "path-expression-matcher": ["path-expression-matcher@1.5.0", "", {}, "sha512-cbrerZV+6rvdQrrD+iGMcZFEiiSrbv9Tfdkvnusy6y0x0GKBXREFg/Y65GhIfm0tnLntThhzCnfKwp1WRjeCyQ=="],
 
     "path-key": ["path-key@3.1.1", "", {}, "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q=="],
 
@@ -520,7 +503,7 @@
 
     "pure-rand": ["pure-rand@8.4.0", "", {}, "sha512-IoM8YF/jY0hiugFo/wOWqfmarlE6J0wc6fDK1PhftMk7MGhVZl88sZimmqBBFomLOCSmcCCpsfj7wXASCpvK9A=="],
 
-    "qs": ["qs@6.15.3", "", { "dependencies": { "es-define-property": "^1.0.1", "side-channel": "^1.1.1" } }, "sha512-O9gl3zCl5h5blw1KGUzQKhA5oUXSl8rwUIM5o0S3nCXMliSvy5Dzx7/DJcI+SwgICv+IneSZwhBh1oSyEHA71A=="],
+    "qs": ["qs@6.15.0", "", { "dependencies": { "side-channel": "^1.1.0" } }, "sha512-mAZTtNCeetKMH+pSjrb76NAM8V9a05I9aBZOHztWy/UqcJdQYNsf59vrRKWnojAT9Y+GbIvoTBC++CPHqpDBhQ=="],
 
     "range-parser": ["range-parser@1.2.1", "", {}, "sha512-Hrgsx+orqoygnmhFbKaHE6c296J+HTAQXoxEF6gNupROmmGJRoyzfG3ccAveqCBrwr/2yxQ5BVd/GTl5agOwSg=="],
 
@@ -546,9 +529,9 @@
 
     "shebang-regex": ["shebang-regex@3.0.0", "", {}, "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A=="],
 
-    "side-channel": ["side-channel@1.1.1", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.4", "side-channel-list": "^1.0.1", "side-channel-map": "^1.0.1", "side-channel-weakmap": "^1.0.2" } }, "sha512-6x6dK6zJdpTzF4sQeNYxwtvBzf6Eg4GtlesS94HOvTudUeyK2WXAaIfmDgsyslYrRBeFIlsi54AYsFGUuhmvrQ=="],
+    "side-channel": ["side-channel@1.1.0", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.3", "side-channel-list": "^1.0.0", "side-channel-map": "^1.0.1", "side-channel-weakmap": "^1.0.2" } }, "sha512-ZX99e6tRweoUXqR+VBrslhda51Nh5MTQwou5tnUDgbtyM0dBgmhEDtWGP/xbKn6hqfPRHujUNwz5fy/wbbhnpw=="],
 
-    "side-channel-list": ["side-channel-list@1.0.1", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.4" } }, "sha512-mjn/0bi/oUURjc5Xl7IaWi/OJJJumuoJFQJfDDyO46+hBWsfaVM65TBHq2eoZBhzl9EchxOijpkbRC8SVBQU0w=="],
+    "side-channel-list": ["side-channel-list@1.0.0", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.3" } }, "sha512-FCLHtRD/gnpCiCHEiJLOwdmFP+wzCmDEkc9y7NsYxeF4u7Btsn1ZuwgwJGxImImHicJArLP4R0yX4c2KCrMrTA=="],
 
     "side-channel-map": ["side-channel-map@1.0.1", "", { "dependencies": { "call-bound": "^1.0.2", "es-errors": "^1.3.0", "get-intrinsic": "^1.2.5", "object-inspect": "^1.13.3" } }, "sha512-VCjCNfgMsby3tTdo02nbjtM/ewra6jPHmpThenkTYh8pG9ucZ/1P8So4u4FGBek/BjpOVsDCMoLA/iuBKIFXRA=="],
 
@@ -560,7 +543,7 @@
 
     "strip-bom-string": ["strip-bom-string@1.0.0", "", {}, "sha512-uCC2VHvQRYu+lMh4My/sFNmF2klFymLX1wHJeXnbEJERpV/ZsVuonzerjfrGpIGF7LBVa1O7i9kjiWvJiFck8g=="],
 
-    "strnum": ["strnum@2.4.1", "", { "dependencies": { "anynum": "^1.0.1" } }, "sha512-M9eUSMT2dCB2cTNPG7UYj6KuK7RJR2SN2+yCV/fTW3xzTCS6EaGZ5pSMgDIjB7r8zSfTGk+dvvn9rTjpVS9Mwg=="],
+    "strnum": ["strnum@2.2.3", "", {}, "sha512-oKx6RUCuHfT3oyVjtnrmn19H1SiCqgJSg+54XqURKp5aCMbrXrhLjRN9TjuwMjiYstZ0MzDrHqkGZ5dFTKd+zg=="],
 
     "toidentifier": ["toidentifier@1.0.1", "", {}, "sha512-o5sSPKEkg/DIQNmH43V0/uerLrpzVedkUh8tGNvaeXpfpuwjKenlSox/2O/BTlZUtEe+JG7s5YhEz608PlAHRA=="],
 
@@ -594,8 +577,6 @@
 
     "wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
 
-    "xml-naming": ["xml-naming@0.3.0", "", {}, "sha512-ghig2TBE/H11aOVgmahA3MhimvkBr6JIYknH/Dhdk10nXwdbIqBJsbfMxpvFPG8bAw77gN29aQWvKpmVoPlvPQ=="],
-
     "zod": ["zod@4.3.6", "", {}, "sha512-rftlrkhHZOcjDwkGlnUtZZkvaPHCsDATp4pGpuOOMDaTdDDXF91wuVDJoWoPsKX/3YPQ5fHuF3STjcYyKr+Qhg=="],
 
     "zod-to-json-schema": ["zod-to-json-schema@3.25.2", "", { "peerDependencies": { "zod": "^3.25.28 || ^4" } }, "sha512-O/PgfnpT1xKSDeQYSCfRI5Gy3hPf91mKVDuYLUHZJMiDFptvP41MSnWofm8dnCm0256ZNfZIM7DSzuSMAFnjHA=="],
@@ -614,16 +595,12 @@
 
     "@types/bun/bun-types": ["bun-types@1.3.11", "", { "dependencies": { "@types/node": "*" } }, "sha512-1KGPpoxQWl9f6wcZh57LvrPIInQMn2TQ7jsgxqpRzg+l0QPOFvJVH7HmvHo/AiPgwXy+/Thf6Ov3EdVn1vOabg=="],
 
-    "es-set-tostringtag/hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
-
     "eventsource/eventsource-parser": ["eventsource-parser@3.0.6", "", {}, "sha512-Vo1ab+QXPzZ4tCa8SwIHJFaSzy4R6SHf7BY79rFBDf0idraZWAkYrDjDj8uWaSm3S2TK+hJ7/t1CEmZ7jXw+pg=="],
 
     "express/cookie-signature": ["cookie-signature@1.2.2", "", {}, "sha512-D76uU73ulSXrD1UXF4KE2TMxVVwhsnCgfAyTg9k8P6KGZjlXKrOLe4dJQKI3Bxi5wjesZoFXJWElNWBjPZMbhg=="],
 
     "form-data/mime-types": ["mime-types@2.1.35", "", { "dependencies": { "mime-db": "1.52.0" } }, "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw=="],
 
-    "get-intrinsic/hasown": ["hasown@2.0.2", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ=="],
-
     "openai/@types/node": ["@types/node@18.19.130", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-GRaXQx6jGfL8sKfaIDD6OupbIHBr9jv7Jnaml9tB7l4v068PAOXqfcujMMo5PhbIs6ggR1XODELqahT2R8v0fg=="],
 
     "@anthropic-ai/sdk/@types/node/undici-types": ["undici-types@5.26.5", "", {}, "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA=="],

bunfig.toml

@@ -13,9 +13,4 @@ timeout = 60_000
 # fixtures still match the schema. v0.37's production default is ZE/1280;
 # tests that want the new default call configureGateway() explicitly in
 # their own beforeAll.
-#
-# #2823: redirect GBRAIN_AUDIT_DIR to a per-run scratch dir BEFORE any test
-# runs, so audit-emitting code paths (content-sanity, shell-audit, etc.)
-# can't leak fixture events into the operator's real ~/.gbrain/audit/. See
-# test/helpers/audit-dir-preload.ts for the full rationale.
-preload = ["./test/helpers/legacy-embedding-preload.ts", "./test/helpers/audit-dir-preload.ts"]
+preload = ["./test/helpers/legacy-embedding-preload.ts"]

docker-compose.ci.yml

@@ -85,40 +85,6 @@ services:
     volumes:
       - gbrain-ci-pg-data-4:/var/lib/postgresql/data
 
-  # v0.43 (#2084 / eng-review TD1): PgBouncer in TRANSACTION pooling mode
-  # fronting postgres-1 — the production topology (Supabase direct :5432 +
-  # pooled :6543) behind three consecutive pooler-teardown waves
-  # (#1972 → #2015 → #2084) that CI could never reproduce.
-  # test/e2e/pgbouncer-teardown.test.ts uses a DEDICATED database
-  # (gbrain_pgbouncer) on postgres-1 so it never races shard 1's
-  # TRUNCATE-based fixtures; pgbouncer's wildcard [databases] section
-  # forwards any dbname to DB_HOST.
-  pgbouncer:
-    image: edoburu/pgbouncer:latest
-    environment:
-      DB_HOST: postgres-1
-      DB_PORT: "5432"
-      DB_USER: postgres
-      DB_PASSWORD: postgres
-      POOL_MODE: transaction
-      # plain (CI-only): pg16 stores SCRAM verifiers, and pgbouncer can only
-      # answer the server's SCRAM challenge when its userlist holds the
-      # PLAINTEXT password — an md5-hashed userlist fails with
-      # "server login failed: wrong password type".
-      AUTH_TYPE: plain
-      MAX_CLIENT_CONN: "200"
-      DEFAULT_POOL_SIZE: "10"
-      # gbrain's client sets statement_timeout + idle_in_transaction_session_timeout
-      # as startup parameters (db.ts buildConnectionParams); the Supabase pooler
-      # whitelists them, so this pooler must too or every connection is refused
-      # before the teardown path is even reached.
-      IGNORE_STARTUP_PARAMETERS: extra_float_digits,statement_timeout,idle_in_transaction_session_timeout,search_path
-    ports:
-      - "${GBRAIN_CI_PGBOUNCER_PORT:-6543}:5432"
-    depends_on:
-      postgres-1:
-        condition: service_healthy
-
   runner:
     image: oven/bun:1
     working_dir: /app
@@ -131,8 +97,6 @@ services:
         condition: service_healthy
       postgres-4:
         condition: service_healthy
-      pgbouncer:
-        condition: service_started
     # No global DATABASE_URL — scripts/ci-local.sh sets per-shard URL via -e.
     # Unit phase explicitly unsets DATABASE_URL so test/e2e/* gracefully skip.
     volumes:

docs/ENGINES.md

@@ -94,7 +94,7 @@ export interface BrainEngine {
 
 **Slug-based API, not ID-based.** Every method takes slugs, not numeric IDs. The engine resolves slugs to IDs internally. This keeps the interface portable... slugs are strings, IDs are database-specific.
 
-**Embedding is NOT in the engine.** The engine stores embeddings and searches by vector, but it doesn't generate embeddings. `src/core/embedding.ts` handles that (a thin delegation to the provider-agnostic AI gateway in `src/core/ai/gateway.ts`). This is intentional: embedding is an external API call (OpenAI, Voyage, a local Ollama — whichever provider you configured), not a storage concern. All engines share the same embedding service.
+**Embedding is NOT in the engine.** The engine stores embeddings and searches by vector, but it doesn't generate embeddings. `src/core/embedding.ts` handles that. This is intentional: embedding is an external API call (OpenAI), not a storage concern. All engines share the same embedding service.
 
 **Chunking is NOT in the engine.** Same logic. `src/core/chunkers/` handles chunking. The engine stores and retrieves chunks. All engines share the same chunkers.
 
@@ -148,51 +148,6 @@ RRF fusion, multi-query expansion, and 4-layer dedup are engine-agnostic. They o
 
 **Why not self-hosted for v0:** The brain should be infrastructure agents use, not something you maintain. Self-hosted Postgres with Docker is a welcome community PR, but v0 optimizes for zero ops.
 
-### Opt-in RLS source-scope binding (`GBRAIN_RLS_SCOPE_BINDING`)
-
-Defense-in-depth layer for Postgres deployments that want the database itself
-to enforce source isolation, in addition to the mandatory app-layer filters
-(`sourceScopeOpts` — layer 1, always on).
-
-**Mechanism.** With `GBRAIN_RLS_SCOPE_BINDING=1` (or `true`), the engine's
-source-scoped read methods wrap their queries in a transaction that first runs
-`SELECT set_config('app.scopes', $1, true)` — the value is a bound parameter
-(federated `sourceIds` CSV > scalar `sourceId` > `'*'` for unscoped internal
-reads), transaction-local (equivalent to `SET LOCAL`, which itself can't take
-bound params). An RLS policy can then filter rows by
-`current_setting('app.scopes', true)`.
-
-**Default off.** With the env var unset, reads call through on the shared pool
-exactly as before — no per-read transaction, no pool-slot hold (the search
-methods keep the transaction they always had for their `SET LOCAL
-statement_timeout`). Existing operators see zero behavior change.
-
-**Enabling it** (operator-managed SQL; gbrain ships no DDL for this):
-
-```sql
-ALTER TABLE pages ENABLE ROW LEVEL SECURITY;
-CREATE POLICY pages_scope_filter ON pages
-  USING (current_setting('app.scopes', true) = '*'
-         OR source_id = ANY(string_to_array(current_setting('app.scopes', true), ',')));
-
--- Required: connections that don't run through the scoped read helper
--- (admin, autopilot, cycle, writes) must default to unscoped, or they
--- see zero rows once the policy exists:
-ALTER ROLE <runtime-role> SET app.scopes = '*';
-
--- If the runtime role OWNS the table, RLS is skipped for it unless forced:
-ALTER TABLE pages FORCE ROW LEVEL SECURITY;
-```
-
-Safe to enable in either order: the env var without a policy is a no-op
-setting; a policy without the env var is enforced only via the role default.
-
-**Honest caveat:** only read paths routed through the scoped helper carry a
-per-request scope binding — unwrapped paths (writes, admin/maintenance reads)
-run under the role default and are not backstopped per caller. This is layer 2;
-the app-layer source filters remain layer 1 and stay mandatory. Behavioral pins
-live in `test/postgres-engine-rls-scope.test.ts`.
-
 ## PGLiteEngine (v0.7, ships)
 
 **Dependencies:** `@electric-sql/pglite` (v0.4.4+)
@@ -221,39 +176,6 @@ live in `test/postgres-engine-rls-scope.test.ts`.
 
 **Migration:** `gbrain migrate --to supabase` exports everything (pages, chunks, embeddings, links, tags, timeline) and imports into Supabase. `gbrain migrate --to pglite` goes the other direction. Bidirectional, lossless.
 
-## JSONB writes: never double-encode (the #2339 trap)
-
-Writing a JS value into a `jsonb` column has exactly two correct forms. Get this
-wrong and the write succeeds on PGLite but stores a **jsonb string scalar** on
-real Postgres — `col ->> 'k'` returns NULL, `jsonb_array_elements` throws, and a
-`jsonb_typeof = 'array'` CHECK rejects the row (this aborted every sync in #2339).
-
-| Form | Verdict |
-|---|---|
-| Template tag: `` sql`... ${sql.json(obj)}` `` (postgres-engine only) | ✅ native jsonb serialization |
-| Positional raw call, raw object: `executeRawJsonb(engine, sql, scalars, [obj])` | ✅ object reaches the wire as jsonb |
-| Positional raw call, stringified: `executeRaw(\`... $N::text::jsonb\`, [JSON.stringify(x)])` | ✅ binds as text, the cast parses it |
-| Positional raw call, BARE cast: `executeRaw(\`... $N::jsonb\`, [JSON.stringify(x)])` | ❌ **double-encodes** under postgres.js `.unsafe()` |
-| Template literal interpolation: `` `... ${JSON.stringify(x)}::jsonb` `` | ❌ double-encodes |
-
-**Why:** postgres.js `.unsafe(sql, params)` (the path behind `executeRaw` /
-`executeRawDirect`) binds a JS **string** as a text param. A bare `$N::jsonb`
-cast then wraps that already-JSON string into a jsonb scalar string instead of
-parsing it. Casting through `$N::text::jsonb` forces a text→jsonb parse.
-**PGLite's `db.query` parses text→jsonb natively, so it hides the bug** — which is
-why a regression only shows up on Postgres (and why the parity test must run there).
-
-**Two CI guards enforce this, both wired into `scripts/check-jsonb-pattern.sh`:**
-- the template-tag grep (`${JSON.stringify(x)}::jsonb`), and
-- `scripts/check-jsonb-params.mjs`, an AST-lite scanner for the positional
-  `$N::jsonb` + `JSON.stringify` form the grep misses. Sanctioned escapes:
-  `$N::text::jsonb`, `$N::text[]`, `executeRawJsonb`, `sql.json`, or an inline
-  `jsonb-guard-ok` comment.
-
-The real backstop is `test/e2e/op-checkpoint-jsonb-parity.test.ts` +
-`test/e2e/jsonb-roundtrip.test.ts`, which round-trip writes through real Postgres
-and assert `jsonb_typeof` — the assertion PGLite cannot make.
-
 ## Adding a new engine
 
 1. Create `src/core/<name>-engine.ts` implementing `BrainEngine`

docs/GBRAIN_VERIFY.md

@@ -88,15 +88,14 @@ find /data/brain -name '*.md' \
 Some difference is normal (files added since last sync), but if page count is
 less than half the file count, sync is silently skipping pages.
 
-**If page count is way too low:** The #1 cause is an unreachable direct
-connection on an IPv4-only host. GBrain uses the Transaction pooler (port 6543)
-for reads, but routes migrations, DDL, and sync transactions to a derived direct
-connection (`db.<ref>.supabase.co:5432`), which is IPv6-only.
-- On an IPv4-only host, reads work but sync transactions fail and silently skip
-  pages.
-- Fix: set `GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port
-  5432 on the `pooler.supabase.com` host, IPv4), or enable Supabase's IPv4
-  add-on. Then run `gbrain sync --full` to reimport everything.
+**If page count is way too low:** The #1 cause is the connection pooler bug.
+Check your `DATABASE_URL`:
+- If it contains `pooler.supabase.com:6543`, verify it's using **Session mode**,
+  not Transaction mode.
+- Transaction mode breaks `engine.transaction()` and causes `.begin() is not a
+  function` errors.
+- Fix: switch to Session mode pooler string, then run `gbrain sync --full`
+  to reimport everything.
 
 ### 4b. Embed Check
 
@@ -143,8 +142,7 @@ gbrain search "<text from the correction>"
 - Is `gbrain sync --watch` still alive (if using watch mode)?
 - Run `gbrain config get sync.last_run` to see when sync last ran.
 - Run `gbrain sync --repo /data/brain` manually and check for errors.
-- If sync errors mention an unreachable host or connection timeout, the direct
-  connection isn't reachable on IPv4 (see 4a above).
+- If you see `.begin() is not a function`, fix the pooler (see 4a above).
 
 ---
 

docs/INSTALL.md

@@ -37,8 +37,6 @@ gbrain migrate --to supabase     # PGLite → Postgres
 gbrain migrate --to pglite       # Postgres → PGLite (rare)
 ```
 
-For shared / large / multi-machine deployments (a team or company brain with multiple users hitting one server over HTTP MCP with OAuth scoping per user), follow the dedicated walkthrough: **[Tutorial: set up GBrain as your company brain](tutorials/company-brain.md)**.
-
 API keys live in `~/.gbrain/config.json` (file plane) or env vars (`OPENAI_API_KEY`, `ZEROENTROPY_API_KEY`, `VOYAGE_API_KEY`, `ANTHROPIC_API_KEY`). Set via CLI:
 
 ```bash
@@ -54,15 +52,6 @@ gbrain sync --watch               # live-sync a git repo (autopilot mode)
 gbrain autopilot --install        # background daemon for nightly enrichment
 ```
 
-**Wire this same local brain into your coding agent** — zero server, zero token:
-
-```bash
-claude mcp add gbrain -- gbrain serve    # Claude Code
-codex  mcp add gbrain -- gbrain serve    # Codex
-```
-
-The agent spawns `gbrain serve` as a stdio subprocess against your local brain. Full walkthrough (both this local path and connecting to a remote brain), plus the brain-first protocol to paste into `CLAUDE.md` / `AGENTS.md`: **[Give your coding agent a memory](tutorials/connect-coding-agent.md)**.
-
 ## 3. MCP server (any MCP client)
 
 ```bash
@@ -70,21 +59,9 @@ gbrain serve                      # stdio MCP (Claude Desktop / Code / Cursor)
 gbrain serve --http               # HTTP MCP with OAuth 2.1 + admin dashboard
 ```
 
-**Wire a coding agent to a remote brain in one command** (when you have an HTTP
-server + a bearer token): `gbrain connect` prints a paste-ready setup block, or
-`--install` runs it and smoke-tests the token.
-
-```bash
-gbrain auth create "claude-code"
-gbrain connect https://your-host/mcp --token gbrain_xxx                      # Claude Code (default)
-gbrain connect https://your-host/mcp --token gbrain_xxx --agent codex        # Codex (env-var bearer)
-gbrain connect https://your-host/mcp --agent perplexity --oauth --register   # Perplexity (OAuth)
-```
-
 Per-client setup guides live in [`docs/mcp/`](mcp/):
 
 - [`docs/mcp/CLAUDE_CODE.md`](mcp/CLAUDE_CODE.md)
-- [`docs/mcp/CODEX.md`](mcp/CODEX.md)
 - [`docs/mcp/CLAUDE_DESKTOP.md`](mcp/CLAUDE_DESKTOP.md)
 - [`docs/mcp/CHATGPT.md`](mcp/CHATGPT.md)
 - [`docs/mcp/PERPLEXITY.md`](mcp/PERPLEXITY.md)
@@ -111,38 +88,3 @@ gbrain models doctor              # 1-token probe per configured model
 ```
 
 If anything's yellow, `gbrain doctor` names the fix command in the message. Most issues are missing API keys or stale schema (`gbrain upgrade --force-schema`).
-
-## Troubleshooting
-
-### PGLite crashes on macOS 26.x (Tahoe)
-
-PGLite's embedded WASM engine is incompatible with macOS 26.x (Tahoe) on Apple Silicon. If `gbrain init --pglite` crashes during engine initialization, switch to native Homebrew PostgreSQL:
-
-```bash
-# Install PostgreSQL + pgvector
-brew install postgresql@17
-brew services start postgresql@17
-createdb gbrain
-
-# Build pgvector from source (required for vector search)
-cd /tmp && git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
-cd pgvector && make && make install
-psql gbrain -c "CREATE EXTENSION IF NOT EXISTS vector;"
-
-# Point gbrain at your local Postgres
-cat > ~/.gbrain/config.json << 'EOF'
-{
-  "engine": "postgres",
-  "database_url": "postgresql://localhost:5432/gbrain",
-  "schema_pack": "gbrain-base-v2"
-}
-EOF
-
-# Run migrations and verify
-gbrain apply-migrations --yes
-gbrain doctor
-```
-
-All 102 migrations run on first try. Once `gbrain doctor` shows green, the brain works identically to PGLite — same commands, same skills, same data model. The only difference is the storage backend.
-
-> **Note:** This workaround is temporary. When the upstream WASM runtime fix ships (likely via a Bun update), `--pglite` will work on Tahoe again.

docs/RELEASING.md

@@ -1,435 +0,0 @@
-# Releasing & contributing (gbrain)
-
-The full release + contributor process. CLAUDE.md keeps the ship-critical IRON RULES
-inline (the Version-locations table, branch=workspace, post-ship `/document-release`,
-the Privacy + Responsible-disclosure rules, PR-title-version-first, never-hand-roll-ship)
-and points here for everything else. **Before any ship, read this in full. Use `/ship` —
-never hand-roll a release.**
-
-## Pre-ship requirements
-
-Before shipping (/ship) or reviewing (/review), always run the full test suite.
-Two equivalent paths:
-
-**Path A — local CI gate (recommended, v0.23.1+):**
-- `bun run ci:local` runs the entire stack inside Docker: gitleaks (host),
-  guards + typecheck, then 4-shard parallel unit + E2E against four pgvector
-  containers plus a transaction-mode PgBouncer service (unit phase keeps
-  `DATABASE_URL` unset; `--no-shard` for the legacy sequential flow). Stronger
-  than PR CI's 2-file Tier 1 set; closer to what nightly Tier 1 catches. Spins
-  up + tears down postgres automatically via `docker-compose.ci.yml`. Override
-  the host port with `GBRAIN_CI_PG_PORT=5435 bun run ci:local` if 5434 collides.
-- `bun run ci:local:diff` runs only the E2E files matched by the diff selector
-  (`scripts/select-e2e.ts`), falling back to ALL E2E files on unmapped src/
-  paths or schema/skills/package.json changes. Fast iteration during a focused
-  branch.
-
-**Path B — manual lifecycle (still supported):**
-- `bun test` — unit tests (no database required)
-- Follow the "E2E test DB lifecycle" steps above to spin up the test DB,
-  run `bun run test:e2e`, then tear it down.
-
-Both must pass. Do not ship with failing E2E tests. Do not skip E2E tests.
-
-**Always run typecheck before pushing.** `bun test` (the bun runner)
-skips TypeScript type checking — it only enforces runtime behavior.
-Three ways to actually gate on types:
-
-1. `bun run test` (npm script in `package.json`) — includes `bun run typecheck`
-   plus the four shell pre-checks (`check-jsonb-pattern.sh`,
-   `check-progress-to-stdout.sh`, `check-trailing-newline.sh`,
-   `check-wasm-embedded.sh`) before the runner. Use this mid-branch.
-2. `bun run typecheck` — `tsc --noEmit` standalone. Fast (~5s on this repo).
-3. `bun run ci:local` — the full local CI gate from Path A.
-
-The trap is: writing a new test, running `bun test test/foo.test.ts`,
-seeing it pass, pushing — and CI's separate typecheck stage rejects an
-invalid type literal that the runner accepted. Caught one of these
-shipping the v0.23.2 round-trip E2E (`type: 'reflection'` is not a
-member of `PageType`). Run `bun run typecheck` once before push, even
-when only test files changed.
-
-
-## CHANGELOG + VERSION are branch-scoped
-
-**VERSION and CHANGELOG describe what THIS branch adds vs master, not how we got
-here.** Every feature branch that ships gets its own version bump and CHANGELOG
-entry. The entry is product release notes for users; it is not a log of internal
-decisions, review rounds, or codex findings.
-
-**Write the CHANGELOG entry at /ship time, not during development.** Mid-branch
-iterations, review rounds (CEO/Eng/Codex/DX), and implementation detours belong
-in the plan file at `~/.claude/plans/`, not in the CHANGELOG. One unified entry
-per branch, covering what the branch added vs the base branch.
-
-**Never edit a CHANGELOG entry that already landed on master.** If master has
-v0.18.2 and your branch adds features, bump to the next version (v0.19.0, not
-editing master's v0.18.2). When merging master into your branch, master may
-bring new CHANGELOG entries above yours — push your entry above master's
-latest and verify:
-
-- Does CHANGELOG have your branch's own entry separate from master's entries?
-- Is VERSION higher than master's VERSION?
-- Is your entry the topmost `## [X.Y.Z]` entry?
-- `grep "^## \[" CHANGELOG.md` shows a contiguous version sequence?
-
-If any answer is no, fix it before continuing.
-
-**CHANGELOG is for users, not contributors.** Write like product release notes:
-
-- Lead with what the user can now **do** that they couldn't before. Sell the capability.
-- Plain language, not implementation details. "You can now..." not "Refactored the..."
-- **Never mention internal artifacts**: plan file IDs, decision tags (D-CX-#, F-ENG-#),
-  review rounds, codex findings, subcontractor credits. These are invisible to users.
-- Put contributor-facing changes in a separate `### For contributors` section at the bottom.
-- Every entry should make someone think "oh nice, I want to try that."
-
-**What to omit:**
-- "Codex caught X that the CEO review missed" — private process detail.
-- "D-CX-3 split errors/warnings" — tag is meaningless to users; name the feature instead.
-- "Fix-wave PR #N supersedes #M" — supersede chains belong in PR bodies, not release notes.
-- "215 new cases, 3 decisions applied, 7 reviews cleared" — these are planning-mode metrics.
-
-**What to keep:**
-- The user-facing change: what commands exist now, what flag was added, what behavior fixed.
-- Numbers that mean something to the user: TTHW, commands that timed out before, detection counts.
-- Upgrade instructions: `gbrain upgrade` + any manual step if needed.
-- Credit to external contributors when a community PR was incorporated.
-
-## CHANGELOG voice + release-summary format
-
-**IRON RULE: the CHANGELOG describes what the user gets, not how the work
-happened.** Nobody reading release notes cares that codex caught a bug, that
-the plan went through CEO + eng review, that the migration was originally
-numbered v68 and renumbered to v79 during master merge, or that two
-review rounds caught architectural mistakes. The reader cares what
-`gbrain brainstorm` does and how to use it. If a fact only exists because
-of the development process, it does NOT belong in the CHANGELOG.
-
-**Specifically forbidden in CHANGELOG entries:**
-
-- Any mention of review processes (CEO review, eng review, codex review,
-  plan-eng-review, outside voice, adversarial review, autoplan, /review).
-- "What we caught and fixed before merging" sections. Bugs found pre-merge
-  are not changes — they're things that didn't ship.
-- Plan file references, plan IDs, plan decision tags (D1, D14, D-CDX-3).
-- Migration version drama ("originally v68", "renumbered to v77", "claimed
-  by parallel waves") — just say "Migration v79 adds X." If the user
-  cares about migration ordering, they read the diff.
-- Round counts, finding counts, decision counts ("25 findings across 2
-  rounds", "8 architectural decisions", "5/6 expansions accepted").
-- Names of internal collaborators ("codex caught", "the reviewer flagged",
-  "Claude noticed").
-- "Plan + reviews" summary bullets. The plan lives in `~/.claude/plans/`;
-  if a future reader wants the backstory they can grep there.
-- Any wording that frames a shipped feature as a *recovery* from a planning
-  mistake ("the first plan was wrong", "we corrected the approach", "the
-  shipped version supersedes the original design").
-
-**Smell test:** read the entry as a stranger who has never touched gbrain.
-If any sentence makes them think "why are you telling me this?", cut it.
-Every sentence in the release-summary AND in the itemized changes must
-answer one of three questions: *What can I now do? How do I use it? What
-should I watch for after I upgrade?*
-
-Every version entry in `CHANGELOG.md` MUST start with a release-summary section in
-the GStack/Garry voice — one viewport's worth of prose + tables that lands like a
-verdict, not marketing. The itemized changelog (subsections, bullets, files) goes
-BELOW that summary, separated by a `### Itemized changes` header.
-
-The release-summary section gets read by humans, by the auto-update agent, and by
-anyone deciding whether to upgrade. The itemized list is for agents that need to
-know exactly what changed.
-
-### Release-summary template
-
-**Iron rule: lead ELI10, get precise after.** The first ~150 words of every entry
-must be readable by someone who does NOT know gbrain's internals. No file paths,
-no function names, no internal constants, no acronyms (no "RRF", no "knobsHash",
-no "MODE_BUNDLES", no "CDX-4"), no jargon that requires reading the codebase to
-parse. Lead with the user-visible behavior change, in everyday English, like
-you're explaining it to a smart engineer who has never opened the repo.
-
-THEN, once the reader knows what shipped and why they'd care, drill into the
-precise details: real file paths, real function names, real config keys, real
-numbers. The precision part is required (the entry is also the technical record
-of what changed), but it lives AFTER the plain-English lead, never before it.
-
-The shape:
-
-1. **One-line bold headline.** What changed for the user, in human English. No
-   jargon. No internal terms. Example good: "Your search stops boosting weak
-   pages just because they have a lot of links pointing at them." Example bad:
-   "PostFusionOpts gains floorRatio; KNOBS_HASH_VERSION bumped 2→3."
-2. **Plain-English opener** (~3-5 sentences). Describe the problem this fixes in
-   everyday terms. Pretend the reader has a brain full of meeting notes and
-   people pages and wants to know if this release helps them. Concrete example
-   beats abstract description.
-3. **A "How to turn it on" or "How to use it" section** with paste-ready
-   commands. Real flags, real config keys. This is where precision starts.
-4. **A "What you'd see in a concrete example" or "The X numbers that matter"
-   section** with a table. Use everyday-language column headers ("Page",
-   "Match quality", "Has many backlinks?") even when the underlying mechanism
-   is technical. The table teaches what the feature does without requiring the
-   reader to understand how.
-5. **A "What's safe to know about" or "Things to watch" section** for caveats,
-   side effects, cache invalidation, mid-deploy notes. Still in plain language.
-6. **A "What we caught and fixed before merging" section** if the work went
-   through review (CEO/eng/codex/outside-voice). Translate review findings into
-   plain English. "We caught a stale-cache bug" beats "knobsHash() did not
-   include floorRatio in the v=2 hash input."
-7. **`### Itemized changes`** (precision lives here). File paths, function
-   names, types, constants, line numbers. This section is for engineers who
-   need to know exactly what moved.
-
-Voice rules (apply throughout):
-- No em dashes (use commas, periods, "...").
-- No AI vocabulary (delve, robust, comprehensive, nuanced, fundamental, etc.) or
-  banned phrases ("here's the kicker", "the bottom line", etc.).
-- Real numbers, real file names, real commands AFTER the ELI10 lead. Not "fast"
-  but "~30s on 30K pages." In the ELI10 lead, "fast enough that you won't
-  notice" or "~30 seconds even on a big brain."
-- Short paragraphs, mix one-sentence punches with 2-3 sentence runs.
-- Connect to user outcomes: "the agent does ~3x less reading" beats "improved
-  precision."
-- Be direct about quality. "Well-designed" or "this is a mess." No dancing.
-
-**The smell test:** if someone who has never opened gbrain reads the first 150
-words and walks away knowing what shipped and whether they care, the entry
-passes. If they need to grep the codebase to follow along, rewrite the lead.
-
-**Canonical examples in this CHANGELOG:** v0.35.6.0 (floor-ratio gate, written
-ELI10-lead-first), v0.34.4.0 (embed stale fix wave). Use those shapes when in
-doubt. Avoid the shape of entries that lead with internal constants or release
-mechanics; those exist in older history but should not be the model for new
-work.
-
-Source material to pull from:
-- CHANGELOG.md previous entry for prior context
-- Latest `gbrain-evals/docs/benchmarks/[latest].md` for headline numbers (sibling repo)
-- Recent commits (`git log <prev-version>..HEAD --oneline`) for what shipped
-- Don't make up numbers. If a metric isn't in a benchmark or production data, don't
-  include it. Say "no measurement yet" if asked.
-
-Target length: ~250-350 words for the summary. Should render as one viewport.
-
-### "To take advantage of v[version]" block (required, v0.13+)
-
-After the release-summary and BEFORE `### Itemized changes`, every `## [X.Y.Z]`
-entry MUST include a human-readable self-repair block under the heading
-`## To take advantage of v[version]`.
-
-Why: `gbrain upgrade` runs `gbrain post-upgrade` which runs `gbrain apply-migrations`.
-This chain has a known weak link — `upgrade.ts` catches post-upgrade failures as
-best-effort (so the binary still works). When that chain silently fails, users end
-up with half-upgraded brains. The self-repair block gives them a paste-ready
-recovery path; the v0.13+ `~/.gbrain/upgrade-errors.jsonl` trail + `gbrain doctor`
-integration close the loop.
-
-Template (adapt the verify commands per release):
-
-```markdown
-## To take advantage of v[version]
-
-`gbrain upgrade` should do this automatically. If it didn't, or if `gbrain doctor`
-warns about a partial migration:
-
-1. **Run the orchestrator manually:**
-   ```bash
-   gbrain apply-migrations --yes
-   ```
-2. **Your agent reads `skills/migrations/v[version].md` the next time you interact with it.**
-   [One sentence on whether headless agents need manual action, or whether the
-   orchestrator already handled the mechanical side.]
-3. **Verify the outcome:**
-   ```bash
-   [release-specific verify commands, e.g. `gbrain graph ... --depth 2`]
-   gbrain stats
-   ```
-4. **If any step fails or the numbers look wrong,** please file an issue:
-   https://github.com/garrytan/gbrain/issues with:
-   - output of `gbrain doctor`
-   - contents of `~/.gbrain/upgrade-errors.jsonl` if it exists
-   - which step broke
-
-   This feedback loop is how the gbrain maintainers find fragile upgrade paths. Thank you.
-```
-
-**Skip this block** for patches that are pure bug fixes with zero user-facing action
-(rare). If the release has a schema migration, data backfill, or new feature the
-user needs to verify, the block is required.
-
-The v0.13.0 entry in CHANGELOG.md is the canonical example.
-
-### Itemized changes (the existing rules)
-
-Below the release summary, write `### Itemized changes` and continue with the
-detailed subsections (Knowledge Graph Layer, Schema migrations, Security hardening,
-Tests, etc.). Same rules as before:
-
-- Lead with what the user can now DO that they couldn't before
-- Frame as benefits and capabilities, not files changed or code written
-- Make the user think "hell yeah, I want that"
-- Bad: "Added GBRAIN_VERIFY.md installation verification runbook"
-- Good: "Your agent now verifies the entire GBrain installation end-to-end, catching
-  silent sync failures and stale embeddings before they bite you"
-- Bad: "Setup skill Phase H and Phase I added"
-- Good: "New installs automatically set up live sync so your brain never falls behind"
-- **Always credit community contributions.** When a CHANGELOG entry includes work from
-  a community PR, name the contributor with `Contributed by @username`. Contributors
-  did real work. Thank them publicly every time, no exceptions.
-
-### Reference: v0.12.0 entry as canonical example
-
-The v0.12.0 entry in CHANGELOG.md is the canonical example of the format. Match its
-structure for every future version: bold headline, lead paragraph, "numbers that
-matter" with BrainBench-style before/after table, "what this means" closer, then
-`### Itemized changes` with the detailed sections below.
-
-## Version migrations
-
-Create a migration file at `skills/migrations/v[version].md` when a release
-includes changes that existing users need to act on. The auto-update agent
-reads these files post-upgrade (Section 17, Step 4) and executes them.
-
-**You need a migration file when:**
-- New setup step that existing installs don't have (e.g., v0.5.0 added live sync,
-  existing users need to set it up, not just new installs)
-- New SKILLPACK section with a MUST ADD setup requirement
-- Schema changes that require `gbrain init` or manual SQL
-- Changed defaults that affect existing behavior
-- Deprecated commands or flags that need replacement
-- New verification steps that should run on existing installs
-- New cron jobs or background processes that should be registered
-
-**You do NOT need a migration file when:**
-- Bug fixes with no behavior changes
-- Documentation-only improvements (the agent re-reads docs automatically)
-- New optional features that don't affect existing setups
-- Performance improvements that are transparent
-
-**The key test:** if an existing user upgrades and does nothing else, will their
-brain work worse than before? If yes, migration file. If no, skip it.
-
-Write migration files as agent instructions, not technical notes. Tell the agent
-what to do, step by step, with exact commands. See `skills/migrations/v0.5.0.md`
-for the pattern.
-
-## Migration is canonical, not advisory
-
-GBrain's job is to deliver a canonical, working setup to every user on upgrade.
-Anything that looks like a "host-repo change" — AGENTS.md, cron manifests,
-launchctl units, config files outside `~/.gbrain/` — is a GBrain migration
-step, not a nudge we leave for the host-repo maintainer. Migrations edit host
-files (with backups) to make the canonical setup real. Exceptions: changes
-that require human judgment (content edits, renames that break semantics,
-host-specific handler registration where shell-exec would be an RCE surface).
-Everything mechanical ships in the migration.
-
-**Test:** if shipping a feature requires a sentence that starts with "in
-your AGENTS.md, add…" or "in your cron/jobs.json, rewrite…", the migration
-orchestrator should be doing that edit, not the user.
-
-**The exception is host-specific code.** For custom Minion handlers
-(host-specific integrations like inbox sweeps or third-party API scanners), shipping them as a
-data file the worker would exec is an RCE surface. Those get registered in
-the host's own repo via the plugin contract (`docs/guides/plugin-handlers.md`);
-the migration orchestrator emits a structured TODO to
-`~/.gbrain/migrations/pending-host-work.jsonl` + the host agent walks the
-TODOs using `skills/migrations/v0.11.0.md` — stays host-agnostic, still
-canonical.
-
-
-## Schema state tracking
-
-`~/.gbrain/update-state.json` tracks which recommended schema directories the user
-adopted, declined, or added custom. The auto-update agent (SKILLPACK Section 17)
-reads this during upgrades to suggest new schema additions without re-suggesting
-things the user already declined. The setup skill writes the initial state during
-Phase C/E. Never modify a user's custom directories or re-suggest declined ones.
-
-## GitHub Actions SHA maintenance
-
-All GitHub Actions in `.github/workflows/` are pinned to commit SHAs. Before shipping
-(`/ship`) or reviewing (`/review`), check for stale pins and update them:
-
-```bash
-for action in actions/checkout oven-sh/setup-bun actions/upload-artifact actions/download-artifact softprops/action-gh-release gitleaks/gitleaks-action; do
-  tag=$(grep -r "$action@" .github/workflows/ | head -1 | grep -o '#.*' | tr -d '# ')
-  [ -n "$tag" ] && echo "$action@$tag: $(gh api repos/$action/git/ref/tags/$tag --jq .object.sha 2>/dev/null)"
-done
-```
-
-If any SHA differs from what's in the workflow files, update the pin and version comment.
-
-
-## PR descriptions cover the whole branch
-
-Pull request titles and bodies must describe **everything in the PR diff against the
-base branch**, not just the most recent commit you made. When you open or update a
-PR, walk the full commit range with `git log --oneline <base>..<head>` and write the
-body to cover all of it. Group by feature area (schema, code, tests, docs) — not
-chronologically by commit.
-
-This matters because reviewers read the PR body to understand what's shipping. If
-the body only covers your last commit, they miss everything else and can't review
-properly. A 7-commit PR with a body that describes commit 7 is worse than no body
-at all — it actively misleads.
-
-When in doubt, run `gh pr view <N> --json commits --jq '[.commits[].messageHeadline]'`
-to see what's actually in the PR before writing the body.
-
-## Community PR wave process
-
-Never merge external PRs directly into master. Instead, use the "fix wave" workflow:
-
-1. **Categorize** — group PRs by theme (bug fixes, features, infra, docs)
-2. **Deduplicate** — if two PRs fix the same thing, pick the one that changes fewer
-   lines. Close the other with a note pointing to the winner.
-3. **Collector branch** — create a feature branch (e.g. `garrytan/fix-wave-N`), cherry-pick
-   or manually re-implement the best fixes from each PR. Do NOT merge PR branches directly —
-   read the diff, understand the fix, and write it yourself if needed.
-4. **Test the wave** — verify with `bun test && bun run test:e2e` (full E2E lifecycle).
-   Every fix in the wave must have test coverage.
-5. **Close with context** — every closed PR gets a comment explaining why and what (if
-   anything) supersedes it. Contributors did real work; respect that with clear communication
-   and thank them.
-6. **Ship as one PR** — single PR to master with all attributions preserved via
-   `Co-Authored-By:` trailers. Include a summary of what merged and what closed.
-
-**Community PR guardrails:**
-- Always AskUserQuestion before accepting commits that touch voice, tone, or
-  promotional material (README intro, CHANGELOG voice, skill templates).
-- Never auto-merge PRs that remove YC references or "neutralize" the founder perspective.
-- Preserve contributor attribution in commit messages.
-
-## Checking out PRs from garrytan-agents
-
-`garrytan-agents` is the AI-authored PR account and is NOT a collaborator on
-this repo. Its PRs live in a fork, so GitHub Actions triggered by
-`pull_request` events on those PRs do not receive base-repo secrets. Any CI
-job that needs `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, or similar will fail
-with empty-env auth errors, regardless of what's set on the base repo. This
-is a GitHub security default, not a config bug.
-
-When the user says "check out <PR link>" and the PR is from `garrytan-agents`
-(or any other non-collaborator fork), move the branch into the base repo
-before running CI:
-
-1. `gh pr checkout <N>` — pull down the fork's branch. Note the PR number and
-   head branch name (`gh pr view <N> --json headRefName --jq .headRefName`).
-2. `git push origin HEAD:<branch-name>` — push the same branch to the base
-   repo (origin points at `garrytan/gbrain`, not the fork). This is the move
-   that gives CI access to secrets.
-3. `gh pr close <N> --comment "moving to base-repo branch for secret access"`
-   — close the fork PR so the queue stays clean.
-4. `gh pr create --base master --head <branch-name>` — open the replacement
-   PR from the base-repo branch. **Preserve the original PR's title and body
-   verbatim** (`gh pr view <N> --json title,body`); contributor attribution
-   moves to a `Co-Authored-By:` trailer if needed.
-
-Why this over alternatives: adding `garrytan-agents` as a collaborator, or
-flipping the repo-wide "send secrets to fork PRs" toggle, both broaden
-secret distribution to every fork PR from that account or any fork. Moving
-the branch keeps secret scope tight to just the one PR being shipped.
-

docs/TESTING.md

@@ -1,308 +0,0 @@
-# Testing (gbrain repo)
-
-On-demand reference (see CLAUDE.md Reference map). Current behavior + invariants
-only.
-
-`test/e2e/serve-http-oauth.test.ts` additionally pins confidential POST/Basic revocation, public-client SDK fallthrough, malformed/mixed authentication rejection, cross-client isolation, unknown-token opacity, metadata auth methods, no-store responses, strict post-revoke `401`, and retryable backend `503` semantics.
-
-### Test command tiers
-
-Seven test command tiers, each with a clear scope:
-
-| Command | What it runs | Wallclock | When to use |
-|---|---|---|---|
-| `bun run test` | Parallel unit-test fast loop. 8-shard fan-out via `scripts/run-unit-parallel.sh`, then a serial pass over `*.serial.test.ts`. Excludes `*.slow.test.ts` and `test/e2e/*`. No pre-checks, no typecheck. | ~85s on a Mac dev box (3650+ tests) | Inner edit loop. Default. |
-| `bun run verify` | CI's authoritative pre-test gate set, fanned out in parallel by `scripts/run-verify-parallel.sh`: the full `check:*` battery (~30 checks — privacy, jsonb, progress, source-id, test-isolation, wasm, …) plus `bun run typecheck`. The `CHECKS` array in that script is the single source of truth — CI literally calls `bun run verify` in a dedicated job. | ~16s (parallel; typecheck dominates) | Before pushing; before `/ship`. |
-| `bun run test:full` | `verify && bun run test && bun run test:slow && [smart e2e]`. The local equivalent of "everything CI runs." Smart e2e: runs e2e only when `DATABASE_URL` is set; else loud skip notice to stderr. | ~3-5min depending on slow + e2e | Pre-merge sanity, before opening a PR. |
-| `bun run test:slow` | Just the `*.slow.test.ts` set (intentional cold-path correctness checks). | seconds-to-minutes | When touching slow-path code. |
-| `bun run test:serial` | Just the `*.serial.test.ts` set (cross-file-contention quarantine; one bun process per file for true module-registry isolation). | ~1s per quarantined file | Debugging a specific quarantined file. |
-| `bun run test:e2e` | Real Postgres E2E. Requires Docker + `DATABASE_URL`. Sequential. | ~5-10min | Pre-ship; nightly. |
-| `bun run check:all` | The historical pre-check scripts (22, chained sequentially in package.json). Overlaps `verify` heavily but is NOT a superset — `verify`'s `CHECKS` array in `scripts/run-verify-parallel.sh` (~30 entries incl. typecheck) is the authoritative gate; `check:all` keeps a few local-only extras (trailing-newline, exports-count, no-legacy-getconnection). | ~10s | Local-only sweep for the extras. |
-
-### CI vs local: intentionally divergent file sets
-
-- **CI matrix** (`.github/workflows/test.yml`) runs `scripts/test-shard.sh` across 10 matrix shards partitioned by weight-aware LPT bin-packing (`scripts/sharding.ts`) and INCLUDES `*.slow.test.ts` (the two outlier slow files run as dedicated jobs alongside the matrix). CI EXCLUDES `*.serial.test.ts` from the shards and runs them in a dedicated job via `bun run test:serial`, one bun process per file — keeping serial files out of the shard processes is what preserves the `mock.module` quarantine (a top-level mock in one file leaks into every other file sharing its process). `bun run verify` gets its own job too. CI is the ground truth for "did everything pass."
-- **Local fast loop** (`scripts/run-unit-shard.sh` via the parallel wrapper) uses round-robin-by-index sharding and EXCLUDES `*.slow.test.ts` AND `*.serial.test.ts`. Local trades coverage for inner-loop speed; CI catches what local skips.
-
-This divergence is intentional. Don't try to make them equal — the two scripts deliberately solve different problems. The regression test at `test/scripts/run-unit-shard.test.ts` pins what the local fast loop should and shouldn't include.
-
-### Failure-first logging
-
-When `bun run test` finds any failure, the wrapper:
-
-1. Writes failure blocks (each prefixed with `--- shard N: <test name> ---`) to `.context/test-failures.log` (workspace-local, gitignored). On systems without a writable `.context/`, falls back to `/tmp/gbrain-test-failures.log`.
-2. Prints a loud stderr banner with the absolute log path, plus the last 30 lines of the failure log inlined. Banner survives `| head` / `| tail` / agent-side log truncation.
-3. Writes a one-line-per-shard summary to `.context/test-summary.txt` (`shard N/M: pass=X fail=Y skip=Z rc=W`).
-4. Exits non-zero. Empty failure log + non-zero exit = infrastructure problem (wedged shard, killed child); the banner says so.
-
-If a shard wedges (per-shard `GBRAIN_TEST_SHARD_TIMEOUT` cap, default 600s), the wrapper writes `--- shard N: WEDGED after ${SHARD_TIMEOUT}s ---` to the failure log, includes the last 50 lines of the shard log, and proceeds with other shards' results.
-
-### File taxonomy
-
-- `*.test.ts` → fast loop (parallel 8-shard fan-out).
-- `*.slow.test.ts` → run via `bun run test:slow` only (intentional cold-path tests; would dominate the fast loop's wallclock).
-- `*.serial.test.ts` → run via `bun run test:serial` after the parallel pass completes; one bun process per file (`--max-concurrency=1` within a shared process is not enough — the module registry still leaks `mock.module`). Quarantine for tests that share file-wide state and race when run alongside other files in the same `bun test` process. Several dozen files, discovered by the `*.serial.test.ts` glob — no list to maintain. Typical residents: `mock.module(...)` users (top-level mocks leak across files in a shard process, e.g. `test/embed.serial.test.ts`), env-coupled files (e.g. `test/brain-registry.serial.test.ts`), and process-lifecycle suites that assert on `process.exitCode` (e.g. `test/pglite-engine-disconnect.serial.test.ts`). **Do not put the parallelism back on a serial file unless you've fixed the contention root cause** (it just re-introduces the flake).
-- `test/e2e/*.test.ts` → real-Postgres E2E. Skipped when `DATABASE_URL` is unset.
-- `tests/heavy/*.sh` → ops-shape shell scripts. Cost minutes per run; NOT in default `bun test`. Run via `bun run test:heavy` or scheduled nightly via `.github/workflows/heavy-tests.yml`. Examples: pg_upgrade matrix (boot legacy brain → walk to head), RSS budget gate (measure peak worker RSS vs committed baseline), read-latency-under-sync (p50/p95/p99 under concurrent writer load), sync lock regression (N concurrent syncs assert 1 winner + N-1 lock-busy + zero leaked `gbrain_cycle_locks` rows). See `tests/heavy/README.md` for when to add a script here vs `*.slow.test.ts`. Files prefixed with `_` (e.g. `tests/heavy/_build_legacy_fixtures.sh`) are helpers/libs invoked by sibling tests — the runner skips them.
-- `test/fuzz/*.test.ts` → property-based fuzz harness. Pure-validator targets in `pure-validators.test.ts` are guarded by `scripts/check-fuzz-purity.sh` (in `bun run verify`), which `bun build --target=bun` bundles each target and greps the resulting bundle for banned transitive imports (`node:fs`, `node:child_process`, engine modules). Anything that fails the guard moves to `mixed-validators.test.ts` (still property-tested, but no purity guarantee) or `filesystem-validators.test.ts` (fs-backed, uses temp dirs). Fuzz tests run in the default `bun test` loop because they're fast (~3s for ~12 properties × 1000 runs each).
-
-### 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):
-
-| Rule | What it bans | Fix |
-|---|---|---|
-| **R1** | `process.env.X = ...`, bracket assignment, `delete process.env.X`, `Object.assign(process.env, ...)`, `Reflect.set(process.env, ...)` | Use `withEnv()` from `test/helpers/with-env.ts`, OR rename file to `*.serial.test.ts` |
-| **R2** | `mock.module(...)` anywhere in the file | Rename file to `*.serial.test.ts` (no DI on production code for testability) |
-| **R3** | `new PGLiteEngine(` outside ~50 lines after a `beforeAll(` line | Use the canonical block (below) inside `beforeAll(` |
-| **R4** | Files creating `new PGLiteEngine(` without `engine.disconnect(` inside an `afterAll(` block | Add `afterAll(() => engine.disconnect())` |
-
-Files that violated these rules at the isolation-lint baseline are listed in `scripts/check-test-isolation.allowlist`. **The allow-list MUST shrink over time** — never add new entries.
-
-#### Canonical PGLite block (R3 + R4 compliant)
-
-Every test file that needs a PGLite engine should use this exact pattern:
-
-```ts
-import { PGLiteEngine } from '../src/core/pglite-engine.ts';
-import { resetPgliteState } from './helpers/reset-pglite.ts';
-
-let engine: PGLiteEngine;
-
-beforeAll(async () => {
-  engine = new PGLiteEngine();
-  await engine.connect({});
-  await engine.initSchema();
-});
-
-afterAll(async () => {
-  await engine.disconnect();
-});
-
-beforeEach(async () => {
-  await resetPgliteState(engine);
-});
-```
-
-Why this exact shape: `beforeAll` creates a single engine per file (PGLite WASM cold-start + initSchema is ~20s); `beforeEach` truncates user data via `resetPgliteState` ("two orders of magnitude faster" than fresh-engine-per-test); `afterAll` disconnects so the engine doesn't leak across file boundaries within a shard process.
-
-#### `withEnv` pattern (R1 fix)
-
-```ts
-import { withEnv } from './helpers/with-env.ts';
-
-test('reads OPENAI_API_KEY', async () => {
-  await withEnv({ OPENAI_API_KEY: 'sk-test' }, async () => {
-    expect(loadConfig().openai_key).toBe('sk-test');
-  });
-});
-
-// Delete a var (override is undefined):
-await withEnv({ GBRAIN_HOME: undefined }, fn);
-
-// Multiple keys:
-await withEnv({ A: '1', B: '2', C: undefined }, fn);
-```
-
-`withEnv` saves the prior value of every key it touches and restores via try/finally — including when the callback throws. **It is cross-test safe but NOT intra-file concurrent-safe.** `process.env` is process-global; two `test.concurrent()` calls in the same file both touching the same key will race. Files using `withEnv` stay outside the `test.concurrent()` codemod's eligibility filter.
-
-#### When to quarantine instead of fix
-
-Rename to `*.serial.test.ts` when:
-- The file uses `mock.module(...)` (R2 — there's no clean fix without changing production code).
-- The file is genuinely env-coupled (e.g. `gbrain-home-isolation.test.ts`, `claw-test-cli.test.ts`) — module-load env readers + ESM caching defeat dynamic-import-after-env tricks.
-- The file's tests intentionally share state across `it()` boundaries.
-
-The quarantine has grown to dozens of files — treat it as debt: every addition needs a reason from the list above, and prefer fixing the contention root cause when one exists.
-
-### Unit test inventory
-
-`bun test` runs all tests without a database. E2E tests skip gracefully when `DATABASE_URL` is not set.
-
-Unit tests and what they cover:
-
-- `test/markdown.test.ts` — frontmatter parsing; `splitBody` sentinel precedence, horizontal-rule preservation, `inferType` wiki subtypes.
-- `test/chunkers/recursive.test.ts` — chunking.
-- `test/parity.test.ts` — operations contract parity.
-- `test/cli.test.ts` — CLI structure.
-- `test/cli-finish-teardown.test.ts` — the #2084 teardown contract: `computeTeardownDeadlineMs` formula/floor/live-registry scaling + `GBRAIN_TEARDOWN_DEADLINE_MS` override (garbage/zero/negative values fall back to the formula); `finishCliTeardown` clean path (drain BEFORE disconnect, no exit, no warn), backstop on hung drain or disconnect (honors an errored op's exit code), throwing drain/disconnect warned + swallowed; the gbrain-owned verdict channel is immune to PGLite WASM `process.exitCode` writes; `flushThenExit` unit coverage with mocked streams (exits once after both stream callbacks, non-TTY aliveness grace, blocked-pipe guard, EPIPE-safe, `GBRAIN_FLUSH_GRACE_MS` override).
-- `test/flush-then-exit-harness.test.ts` — real spawned-Bun pipe semantics for `flushThenExit` (fixture: `test/fixtures/flush-then-exit-harness.ts`): a 4MB piped stdout payload arrives byte-complete with the exit code even with a late reader, small output survives exit with a concurrent reader, and the fence resolves promptly (wall time well under the guard + grace ceiling).
-- `test/cli-should-force-exit.test.ts` — `shouldForceExitAfterMain` daemon-survival gate: `serve` (stdio and `--http`) never force-exits, including with preceding global flags; op commands / empty / flag-only argv do; the #2084 case that space-separated global-flag VALUES can't fake a command (`--timeout 30s serve` resolves to the `serve` daemon, not a `30s` command).
-- `test/cli-exit-verdict-pin.test.ts` — #2084 structural class pin: greps `src/` so the NEXT raw `process.exitCode =` write fails CI (a raw write bypasses the gbrain-owned verdict channel and gets silently zeroed by the deliberate flush-exit — the bug that made doctor's FAIL path exit 0). Runtime variants live in `test/cli-finish-teardown.test.ts`; this is the review-time guard.
-- `test/cli-pipe-truncation.test.ts` — real-CLI pipe completeness (the #1959 incident class), implementation-agnostic: the actual CLI run the way agents run it (piped stdout) produces complete, parseable, byte-stable `--tools-json` output and exits deliberately, well under the teardown backstop. Synthetic flush-mechanism coverage stays in `test/flush-then-exit-harness.test.ts`.
-- `test/volunteer-context.test.ts` — push-based context core (#2095), hermetic in-memory PGLite: `parseWindow` lenient `user:`/`assistant:` parsing, multi-turn window extraction, confidence-gated volunteering (arm confidences, multi-turn/newest-turn boosts, `min_confidence` gate, max-pages cap), slug-only suppression, privacy (rationales are deterministic templates; synopses pass the takes/facts fence), and the approximate usage-stats join.
-- `test/watch-command.test.ts` — `gbrain watch` push transport (#2095): streaming loop, rolling window, session dedupe, `--json` JSONL shape, `channel: 'watch'` event logging, clean EOF return. Hermetic PGLite + injected line/write deps (no subprocess, no real stdin).
-- `test/watch-sigint.serial.test.ts` — `gbrain watch` SIGINT lifecycle against a real spawned CLI subprocess with a tmpdir brain. SERIAL: parallel unit shards flake on concurrent subprocess spawns (same rationale as `apply-migrations-pglite-spawn.serial.test.ts`).
-- `test/cli-format-volunteer.test.ts` — `formatResult`'s `volunteer_context` human rendering: pointer lines with confidence/arm/rationale, the empty-result message, the approximate stats summary.
-- `test/config.test.ts` — config redaction.
-- `test/files.test.ts` — MIME/hash.
-- `test/import-file.test.ts` — import pipeline.
-- `test/upgrade.test.ts` — schema migrations.
-- `test/file-migration.test.ts` — file migration.
-- `test/file-resolver.test.ts` — file resolution.
-- `test/import-resume.test.ts` — import checkpoints.
-- `test/migrate.test.ts` — migration: v8/v9 helper-btree-index SQL structural assertions; 1000-row wall-clock fixtures guarding the O(n²)→O(n log n) fix; v12/v13 SQL shape; `sqlFor` + `transaction:false` runner semantics; the `max_stalled DEFAULT 1` regression guard; v24 `sqlFor.pglite: ''` no-op assertion; v117 `context_volunteer_events` (named + idempotent entry, documented columns + both source-scoped indexes after `initSchema`, insert + 90-day `purgeStaleVolunteerEvents` round-trip).
-- `test/bootstrap.test.ts` — bootstrap contract: no-op on fresh install, idempotent across two `initSchema()` calls, no-op on modern brain that already has every probed column, full bootstrap path on a simulated legacy brain, fresh-install regression guard, legacy `links` shape coverage.
-- `test/schema-bootstrap-coverage.test.ts` — CI guard. `REQUIRED_BOOTSTRAP_COVERAGE` lists every forward reference in `PGLITE_SCHEMA_SQL`; the test fails loudly if `applyForwardReferenceBootstrap` skips one (extend both arrays when adding a column-with-index to the embedded schema blob). Also parses `src/core/migrate.ts` source text for every `ALTER TABLE ... ADD COLUMN` (top-level `sql:`, `sqlFor.{postgres,pglite}` overrides, AND handler-body `engine.runMigration(N, \`ALTER TABLE ...\`)`) and asserts each (table, column) pair is covered by the bootstrap OR by the schema blob's CREATE TABLE bodies — catching the column-only forward-reference class (e.g. `sources.archived`, `oauth_clients.source_id`) that a CREATE INDEX parser alone can't see. `parseBaseTableColumns` strips SQL line + block comments before identifying column names so commented-out lines don't hide adjacent columns.
-- `test/helpers/schema-diff.ts` + `test/helpers/schema-diff.test.ts` + `test/e2e/schema-drift.test.ts` — cross-engine schema parity gate. Helper exports pure `snapshotSchema(query)` / `diffSnapshots(pg, pglite, opts)` / `formatDiffForFailure(diff)` / `isCleanDiff(diff)` over a four-tuple per column (`data_type`, `udt_name`, `is_nullable`, `column_default`). E2E test spins up fresh PGLite + Postgres, runs `engine.initSchema()` on each, snapshots `information_schema.columns`, then diffs. 2-table allowlist (`files`, `file_migration_ledger`) — every other Postgres table must reach PGLite via `PGLITE_SCHEMA_SQL` or a migration's `sqlFor.pglite` branch. Sentinels for `oauth_clients`, `mcp_request_log`, `access_tokens`, `eval_candidates` give tighter blame messages. Skips without `DATABASE_URL`. Wired into `scripts/e2e-test-map.ts` so changes to `src/schema.sql`, `src/core/pglite-schema.ts`, or `src/core/migrate.ts` trigger it. The failure message names every drift with a paste-ready hint pointing at `src/core/pglite-schema.ts`.
-- `test/setup-branching.test.ts` — setup flow.
-- `test/slug-validation.test.ts` — slug validation.
-- `test/storage.test.ts` — storage backends.
-- `test/supabase-admin.test.ts` — Supabase admin.
-- `test/yaml-lite.test.ts` — YAML parsing.
-- `test/check-update.test.ts` — version check + update CLI.
-- `test/pglite-engine.test.ts` — PGLite engine, all BrainEngine methods including `addLinksBatch` / `addTimelineEntriesBatch` (empty batch, missing optionals, within-batch dedup via ON CONFLICT, missing-slug rows dropped by JOIN, half-existing batch, batch of 100) plus `connect()` error-wrap assertion (original error nested, #223 link in message, lock released).
-- `test/links-timeline-jsonb-poison.test.ts` — gbrain#1861 PGLite half (always-on, no `DATABASE_URL`). Locks the `jsonb_to_recordset` batch-insert path for links/timeline/takes against free-text "poison" payloads (commas, quotes, backslashes, braces, em-dashes) and asserts NUL is stripped from free-text body fields but rejected in identity fields. gbrain#2011 adds lone-UTF-16-surrogate cases: every free-text field (link context; timeline summary/detail/source; take claim/source) well-forms to U+FFFD across batch + scalar write paths, while a surrogate in an identity field (slug) still fail-closed rejects the batch. The Postgres lane (`test/e2e/jsonb-batch-poison-postgres.test.ts`) is the one that actually reproduced the original crash.
-- `test/engine-factory.test.ts` — engine factory + dynamic imports.
-- `test/integrations.test.ts` — recipe parsing, CLI routing, recipe validation.
-- `test/publish.test.ts` — content stripping, encryption, password generation, HTML output.
-- `test/backlinks.test.ts` — entity extraction, back-link detection, timeline entry generation.
-- `test/lint.test.ts` — LLM artifact detection, code fence stripping, frontmatter validation.
-- `test/report.test.ts` — report format, directory structure.
-- `test/skills-conformance.test.ts` — skill frontmatter + required sections validation.
-- `test/resolver.test.ts` — RESOLVER.md coverage, routing validation; round-trip that every quoted RESOLVER.md trigger matches a frontmatter `triggers:` entry in the target skill, and every `name="<word>"` reference in any SKILL.md resolves to a declared op in `src/core/operations.ts` or a Minions handler in `PROTECTED_JOB_NAMES`.
-- `test/search.test.ts` — RRF normalization, compiled truth boost, cosine similarity, dedup key.
-- `test/sql-ranking.test.ts` — source-boost helpers: longest-prefix-match in SQL CASE, `detail=high` temporal-bypass, three-meta-char LIKE escape (`%`, `_`, `\`), single-quote SQL-literal doubling, env override parsing for `GBRAIN_SOURCE_BOOST` + `GBRAIN_SEARCH_EXCLUDE`, `resolveBoostMap` / `resolveHardExcludes` merge semantics.
-- `test/dedup.test.ts` — source-aware dedup, compiled truth guarantee, layer interactions.
-- `test/intent.test.ts` — query intent classification: entity/temporal/event/general.
-- `test/eval.test.ts` — retrieval metrics: `precisionAtK`, `recallAtK`, `mrr`, `ndcgAtK`, `parseQrels`.
-- `test/check-resolvable.test.ts` — resolver reachability, MECE overlap, gap detection, proximity-based DRY detection, `extractDelegationTargets` coverage.
-- `test/dry-fix.test.ts` — auto-fix: three shape-aware expander pure-function tests; five guards (working-tree-dirty, no-git-backup, inside-code-fence, already-delegated within 40 lines, ambiguous-multi-match, block-is-callout).
-- `test/doctor-fix.test.ts` — `gbrain doctor --fix` CLI integration: dry-run preview, apply path, JSON output shape.
-- `test/backoff.test.ts` — load-aware throttling, concurrency limits, active hours.
-- `test/fail-improve.test.ts` — deterministic/LLM cascade, JSONL logging, test generation, rotation.
-- `test/transcription.test.ts` — provider detection, format validation, API key errors.
-- `test/enrichment-service.test.ts` — entity slugification, extraction, tier escalation.
-- `test/data-research.test.ts` — recipe validation, MRR/ARR extraction, dedup, tracker parsing, HTML stripping.
-- `test/minions.test.ts` — Minions job queue: CRUD, state machine, backoff, stall detection, dependencies, worker lifecycle, lock management, claim mechanics, depth/child-cap, timeouts, cascade kill, idempotency, `child_done` inbox, attachments, removeOnComplete/Fail, `max_stalled` clamp/default/plumbing coverage.
-- `test/extract.test.ts` — link extraction, timeline extraction, frontmatter parsing, directory type inference.
-- `test/extract-db.test.ts` — `gbrain extract --source db`: typed link inference, idempotency, `--type` filter, `--dry-run` JSON output.
-- `test/extract-fs.test.ts` — `gbrain extract --source fs`: first-run inserts + second-run reports zero, dry-run dedups candidates across files, second-run perf regression guard for the N+1 dedup bug.
-- `test/link-extraction.test.ts` — canonical `extractEntityRefs` both formats, `extractPageLinks` dedup, `inferLinkType` heuristics, `parseTimelineEntries` date variants, `isAutoLinkEnabled` config.
-- `test/graph-query.test.ts` — direction in/out/both, type filter, indented tree output.
-- `test/features.test.ts` — feature scanning, brain_score calculation, CLI routing, persistence.
-- `test/file-upload-security.test.ts` — symlink traversal, cwd confinement, slug + filename allowlists, remote vs local trust.
-- `test/query-sanitization.test.ts` — prompt-injection stripping, output sanitization, structural boundary.
-- `test/search-limit.test.ts` — `clampSearchLimit` default/cap behavior across `list_pages` and `get_ingest_log`.
-- `test/repair-jsonb.test.ts` — JSONB repair: TARGETS list, idempotency, engine-awareness.
-- `test/migrations-v0_12_2.test.ts` — JSONB-repair orchestrator phases: schema → repair → verify → record.
-- `test/orphans.test.ts` — orphans command: detection, pseudo filtering, text/json/count outputs, MCP op.
-- `test/postgres-engine.test.ts` — `statement_timeout` scoping: `sql.begin` + `SET LOCAL` shape, source-level grep guardrail against a reintroduced bare `SET statement_timeout`.
-- `test/sync.test.ts` — sync logic + regression guard asserting top-level `engine.transaction` is not called.
-- `test/sync-concurrency.test.ts` — `autoConcurrency()` thresholds + PGLite-forces-serial + explicit-override clamping; `shouldRunParallel()` explicit-bypasses-floor contract; `parseWorkers()` validation rejecting `'0'`/`'-3'`/`'foo'`/`'1.5'`/trailing chars.
-- `test/sync-parallel.test.ts` — PGLite-routed coverage of the bookmark gate under concurrency, head-drift gate, vanished-file failure capture, PGLite-stays-serial, and the `gbrain-sync` writer-lock contract.
-- `test/sync-failures.test.ts` — `classifyErrorCode` regex coverage for all 12 codes against literal production message strings from `markdown.ts` and `import-file.ts`; `summarizeFailuresByCode` sort + pre-classified-honor; `recordSyncFailures` code-field persistence; `acknowledgeSyncFailures` `AcknowledgeResult` shape + backfill on legacy entries.
-- `test/doctor.test.ts` — doctor command; assertions that `jsonb_integrity` scans the four JSONB write sites and `markdown_body_completeness` is present.
-- `test/utils.test.ts` — shared SQL utilities + `tryParseEmbedding` null-return and single-warn semantics.
-- `test/build-llms.test.ts` — `llms.txt`/`llms-full.txt` generator: path resolution, idempotence, spec shape, regen-drift guard, content contract, AGENTS.md install-path mirror, size-budget enforcement.
-- `test/oauth.test.ts` — OAuth 2.1 provider: register, getClient, `client_credentials` grant exchange, `authorization_code` flow with PKCE challenge/verifier, refresh token rotation, `verifyAccessToken` with both OAuth + legacy `access_tokens` fallback, `revokeToken`, `sweepExpiredTokens`; contract test asserting `scope` + `localOnly` annotations on all operations; `coerceTimestamp` unit cases (null/undefined/string/number/throw-on-NaN); NULL-`expires_at`-as-expired contract for both refresh + access token paths; cascade-delete contract asserting `revoke-client` purges `oauth_tokens` + `oauth_codes` via FK CASCADE; cross-client isolation (wrong-client attempt MUST reject AND rightful owner MUST still succeed atomically afterward); empty-string `redirect_uri` bypass guard; PKCE DCR public-client gate (`token_endpoint_auth_method: "none"` returns no `client_secret`, default `client_secret_post` clients get the one-time-reveal secret, `getClient` NULL→undefined normalization, full PKCE `/authorize` → `/token` round-trip against a public client).
-- `test/mcp-dispatch-summarize.test.ts` — `summarizeMcpParams` invariants: declared-keys allow-list intersection, attacker-key-name leak guard (unknown keys counted not named), 1KB byte bucketing for size-probe defense, missing op falls through to fully-redacted shape, declared-keys sorted for deterministic output.
-- `test/trust-boundary-contract.test.ts` — fail-closed trust semantics under cast bypass: `ctx.remote === undefined` treated as remote/untrusted at every flipped call site; `as any` and `Partial<>` spreads can't downgrade trust by accident.
-- `test/check-resolvable-cli.test.ts` — CLI wrapper: exit codes, JSON envelope shape, AGENTS.md fallback chain.
-- `test/regression-v0_16_4.test.ts` — `findRepoRoot` regression guard, hermetic startDir parameterization.
-- `test/repo-root.test.ts` — `findRepoRoot` walk semantics + default-arg parity; the 4-tier `autoDetectSkillsDir` fallback chain (`$OPENCLAW_WORKSPACE` → `~/.openclaw/workspace` → repo-root → `./skills`); RESOLVER.md/AGENTS.md filename precedence; explicit-env-wins-over-repo-root; tier-0 `$GBRAIN_SKILLS_DIR` valid/invalid/precedence-over-`OPENCLAW_WORKSPACE`; the install-path walk in `autoDetectSkillsDirReadOnly`; no-drift on primary success; `AUTO_DETECT_HINT` + `AUTO_DETECT_HINT_READ_ONLY` content; regression guard asserting the shared `autoDetectSkillsDir` MUST NEVER return `'install_path'` source (how the read-path/write-path split stays safe).
-- `test/resolver-merge.test.ts` — multi-file resolver merge: `findAllResolverFiles` empty / RESOLVER.md-only / AGENTS.md-only / both-present (RESOLVER.md first); `checkResolvable` merge semantics across `skills/RESOLVER.md` + `../AGENTS.md` for the OpenClaw layout where the skillpack ships a thin RESOLVER.md and the real dispatcher lives at the workspace root; dedup by `skillPath` (first occurrence wins); AGENTS.md-at-workspace-root works alone.
-- `test/filing-audit.test.ts` — filing audit: `writes_pages` / `writes_to` frontmatter, filing-rules JSON validation.
-- `test/skill-brain-first.test.ts` — shared frontmatter parser; `analyzeSkillBrainFirst` compliance ladder across 9 fixtures under `test/fixtures/brain-first-skills/` (compliant-callout, compliant-phase, compliant-position, exempt-frontmatter, missing-brain-first, multi-pattern, negation-prose, no-external, typo-frontmatter); offset helpers; external-lookup regex shape; audit snapshot+diff transition logic; `FORMERLY_HARDCODED_EXEMPT` regression absorption.
-- `test/routing-eval.test.ts` — fixture parsing, structural routing, `ambiguous_with`, Haiku tie-break layer.
-- `test/skill-manifest.test.ts` — skill manifest parser: drift detection, managed-block markers.
-- `test/skillify-scaffold.test.ts` — `gbrain skillify scaffold` stubs: SKILL.md, script, tests, routing-eval fixtures.
-- `test/skillpack-install.test.ts` — `gbrain skillpack install` managed-block install / update / no-clobber semantics.
-- `test/skillpack-sync-guard.test.ts` — sync-guard: bundled skills stay byte-identical to `skills/` source.
-- `test/http-transport.test.ts` — HTTP transport: bearer auth + missing/no-Bearer/unknown/revoked + `/health` bypass; dispatch.ts round-trip; invalid_params; application/json response shape (not SSE); CORS default-deny + allowlist; body cap on Content-Length AND chunked; two-bucket rate limit (refill, exhaust+Retry-After, LRU eviction, TTL prune, pre-auth IP fires before DB); `mcp_request_log` audit on success + auth_failed.
-- `test/restart-sweep.test.ts` — `recipes/restart-sweep.md` inlined script: sentinel-anchored fenced-block extraction with salted tmp filenames to bypass ESM cache; constructor-time env reads (proves no module-load snapshot); idempotency layer load/save/atomic-tmp-rename/corrupt-JSON-recovery/30-day-prune; `(sessionKey, lastAlertedAt)` cooldown gate with 6h threshold; AGGRESSIVE-gate two-state tests; execFile argv shape proving shell metachars in `OPENCLAW_TELEGRAM_GROUP` cannot reach `/bin/sh`; real-`\n`-not-literal alert formatting; `GBRAIN_HOME` state path override.
-- `test/eval-longmemeval.test.ts` — LongMemEval harness, hermetic with no `DATABASE_URL` and no API keys: PGLite create + reset over runtime-enumerated `pg_tables`, infrastructure-table preservation across resets, JSONL question parsing, retrieval-only and answer-gen modes via stubbed `ThinkLLMClient`, `--limit` cutoff, `--keyword-only` vs hybrid, default `--expansion=off` behavior, perf gate (p50 < 30ms / p99 < 50ms warm reset+import+search on Apple Silicon), `--help` works without a configured brain, fixture round-trip via `test/fixtures/longmemeval-mini.jsonl`.
-- `test/longmemeval-sanitize.test.ts` — sanitization parity pinning that `INJECTION_PATTERNS` from `src/core/think/sanitize.ts` is the single source of truth (adding a pattern there must cover both `<take>` framing and `<chat_session>` framing, no per-surface regex drift).
-- `test/openai-compat-multimodal.test.ts` — gateway's openai-compatible multimodal path: happy-path single + multi-input embedding, unauthenticated proxy mode, dimension-mismatch guard (throws `AIConfigError` with model id + observed + expected pre-storage), default-dim fallback when recipe declares `default_dims`, HTTP 401 / 400 / malformed-JSON / non-array error paths, regression that the existing Voyage `/multimodalembeddings` recipe still routes through its dedicated path. Hermetic via the `__setEmbedTransportForTests` seam.
-- `test/serve-stdio-lifecycle.test.ts` — `MCP_STDIO=1` env guard: stdin EOF does NOT trigger shutdown when the env is set, SIGTERM still does (guard scope is correct), unset env preserves the CLI lifecycle. Exercises the `ServeOptions.mcpStdio?: boolean` test seam directly so tests don't mutate `process.env`.
-
-### E2E test inventory
-
-E2E tests live in `test/e2e/` and run against real Postgres+pgvector (require `DATABASE_URL`), except where noted as PGLite in-memory (no `DATABASE_URL` needed).
-
-- `bun run test:e2e` runs Tier 1 (mechanical, all operations, no API keys). Includes dedicated cases for the postgres-engine `addLinksBatch` / `addTimelineEntriesBatch` bind path — postgres-js's JSONB bind (`jsonb_to_recordset(($1::jsonb)->'rows')`) differs from PGLite's and gets its own coverage.
-- `test/e2e/search-quality.test.ts` — search quality against PGLite (no API keys, in-memory).
-- `test/e2e/graph-quality.test.ts` — knowledge graph pipeline (auto-link via put_page, reconciliation, traversePaths) against PGLite in-memory.
-- `test/e2e/jsonb-batch-poison-postgres.test.ts` — gbrain#1861 regression, the engine that actually crashed. Seeds free-text "poison" context (Zoom URL with `?pwd=`, commas, quotes, Windows backslash path, braces, em-dash) and asserts the links/timeline/takes batch writers no longer error with "malformed array literal"; also asserts NUL is stripped from free-text bodies (`context`/`summary`/`detail`/`claim`) and still rejected in identity fields. gbrain#2011 adds the lone-surrogate crash lock: a lone UTF-16 surrogate in free text (the value that aborted `extract --stale` with `22P02` on Supabase) well-forms to U+FFFD across batch + scalar paths (incl. timeline + take `source`), while a surrogate in an identity field still rejects the batch. `DATABASE_URL`-gated.
-- `test/e2e/postgres-jsonb.test.ts` — round-trips all 5 JSONB write sites (`pages.frontmatter`, `raw_data.data`, `ingest_log.pages_updated`, `files.metadata`, `page_versions.frontmatter`) against real Postgres and asserts `jsonb_typeof='object'` plus `->>'key'` returns the expected scalar. Guards against the double-encode bug.
-- `test/e2e/integrity-batch.test.ts` — parity for `scanIntegrity`'s batch-load fast path vs sequential. Cases (dedup, hits, validate, topPages) seed a fixture and assert both paths return identical results. Dedup case uses raw SQL via `getConn().unsafe()` to seed a `(test-source-2, people/alice)` row alongside the default-source row, since `engine.putPage` doesn't take a `source_id`. Pins multi-source overcounting; the "multi-source duplicate slugs scan once" case expects both batch + sequential paths to report 2.
-- `test/e2e/jsonb-roundtrip.test.ts` — companion regression against the 4 doctor-scanned JSONB sites. Assertion-level overlap with `postgres-jsonb.test.ts` is intentional defense-in-depth: if doctor's scan surface drifts from the actual write surface, one of these tests catches it.
-- `test/e2e/sync.test.ts` — `--skip-failed` failure-loop test alongside happy-path tests: broken file → `performSync` returns `blocked_by_failures` with grouped breakdown → `performSync({skipFailed: true})` advances bookmark and returns `AcknowledgeResult` with code summary → second broken file → second cycle. Saves and restores the user's real `~/.gbrain/sync-failures.jsonl` so the test is hermetic. Asserts bookmark gating, JSONL state, dedup across paths, summary aggregation, and the literal doctor-rendering string format.
-- `test/e2e/upgrade.test.ts` — check-update against real GitHub API (network required).
-- `test/e2e/minions-shell-pglite.test.ts` — PGLite `--follow` inline shell-job path (in-memory, no `DATABASE_URL` required) — the path the minion-orchestrator skill documents for dev use.
-- `test/e2e/pglite-cli-exit.serial.test.ts` — real spawned-CLI exit behavior on PGLite (in-memory, no `DATABASE_URL`): read commands (`search`/`get`/`query`) exit 0 promptly; CLI_ONLY `capture` exits clean and frees the single-writer lock; the `#2084` describes pin every swept disconnect site — a failed op exits 1 with the error on stderr, and the dashboard, read-only-timeout, doctor, and `dream --dry-run` paths all exit with no force-exit banner.
-- `test/e2e/pgbouncer-teardown.test.ts` — PgBouncer TRANSACTION-mode teardown (#2084 / the #1972→#2015→#2084 class). Pins the bug CLASS, not timings: a CLI op against a txn-mode pooled URL exits 0 with intact stdout and does NOT ride the 10s hard-deadline backstop (the `engine.disconnect() did not return` banner is the smoking gun — pre-#2084 it printed on 100% of query-shaped ops). Gated by `GBRAIN_PGBOUNCER_URL` + `GBRAIN_PGBOUNCER_DIRECT_URL` (NOT `DATABASE_URL`) — set automatically by `bun run ci:local`'s `pgbouncer` compose service; skips gracefully elsewhere. Uses a DEDICATED `gbrain_pgbouncer` database so it never races the `gbrain_test` TRUNCATE fixtures.
-- `test/e2e/volunteer-context-postgres.test.ts` — `volunteer_context` on REAL Postgres (#2095; engine parity beyond the hermetic PGLite unit suite): resolution arms through the actual op handler, the fire-and-forget volunteer-event sink landing rows, the stats join, and the RLS pin that `context_volunteer_events` has ROW LEVEL SECURITY enabled (keeps the v35 auto-RLS event trigger honest for migration-created tables). `DATABASE_URL`-gated.
-- `test/e2e/openclaw-reference-compat.test.ts` — `check-resolvable` + `skillpack install` against a minimal AGENTS.md workspace fixture (`test/fixtures/openclaw-reference-minimal/`), regression guard for the OpenClaw deployment shape.
-- `test/e2e/search-swamp.test.ts` — reproduces the source-swamp case. Seeds a curated `originals/talks/article-outline-fat-code` page against two `<fork>/chat/` pages stuffed with the same multi-word phrase. Asserts the article wins keyword AND vector ranking, that `detail=high` lets the chat swamp re-surface, and that `source_id` passes through the two-stage CTE intact. PGLite in-memory.
-- `test/e2e/search-exclude.test.ts` — `test/` + `archive/` pages hidden by default, `include_slug_prefixes` opts back in, caller-supplied `exclude_slug_prefixes` adds to defaults. Both keyword and vector search paths.
-- `test/e2e/engine-parity.test.ts` — Postgres ↔ PGLite top-result and result-set parity for `searchKeyword` + `searchVector` (Postgres ranks pages then picks best chunk while PGLite returns chunks directly, so the source-boost behavior needs parity coverage). Skips without `DATABASE_URL`.
-- `test/e2e/postgres-bootstrap.test.ts` — exercises `PostgresEngine.initSchema()` directly against a fresh real Postgres database. Asserts the bootstrap path is no-op on fresh installs and that SCHEMA_SQL replays cleanly through the engine path (not via the standalone `db.initSchema` from `src/core/db.ts`).
-- `test/e2e/http-transport.test.ts` — `gbrain serve --http` end-to-end against real Postgres: bearer auth round-trip, `last_used_at` SQL-level debounce, `mcp_request_log` row insertion on success and auth_failed paths, `/health` DB-down → 503 (DB-probing health check), and the dispatch round-trip with a real operation. Skips without `DATABASE_URL`.
-- `test/e2e/serve-http-oauth.test.ts` — real-Postgres E2E against `gbrain serve --http` with full OAuth 2.1. Spawns a subprocess server, registers a client via the CLI, mints `client_credentials` tokens, exercises the `/mcp` JSON-RPC pipeline. Real DCR `/register` HTTP-level response-shape test (asserts `typeof body.client_id_issued_at === 'number'` over the wire, RFC 7591 §3.2.1); real CLI subprocess test for `revoke-client` (registers → mints token → revokes via `execSync` → asserts token rejected at `/mcp` → asserts re-run exits 1); server fixture flips on `--enable-dcr` so `/register` is reachable. **bun execSync env-inheritance contract:** bun's `execSync` does NOT inherit env mutations done via `process.env.X = ...`, only OS-level env from before bun started. helpers.ts loads `.env.testing` and sets `DATABASE_URL` via `process.env` mutation, which is invisible to subprocesses unless `env: { ...process.env }` is passed explicitly — every subprocess call in this file passes `env: { ...process.env }`. Reference fix for the same failure mode in sibling sync/cycle/dream/claw-test E2Es. `afterAll` cleanup is guarded on `clientId` (won't throw if `beforeAll` failed before registration); cleanup errors surface to stderr without throwing so real test failures aren't masked. Also covers the trust-boundary fix: an HTTP MCP `submit_job` for `name: "shell"` MUST reject with a permission error (request handler sets `remote: true` and `submit_job`'s protected-name guard fires), and the same guard rejects subagent submission. Skips without `DATABASE_URL`.
-- `test/e2e/sync-parallel.test.ts` — `DATABASE_URL`-gated. 60-file Postgres sync at concurrency=4 imports all + no connection leak (probes `pg_stat_activity` before/after to confirm worker engines disconnected). 120-file serial-vs-parallel benchmark prints `SYNC_PARALLEL_BENCH N files | serial=Xms | parallel(4)=Yms | speedup=Zx`. Asserts parallel ≤ serial × 1.5 (CI-noise tolerant; not a strict speedup gate).
-- `test/e2e/multi-source-bug-class.test.ts` — PGLite in-memory regression suite pinning every multi-source bug site: `listAllPageRefs` ordering by `(source_id, slug)`, `getPage` with sourceId picks the right `(source, slug)` row, `extract-takes` processes both overlapping `people/alice` rows independently, `listPages` filters correctly with `PageFilters.sourceId`, `addLinksBatch` with `from/to_source_id` targets the right rows, `validateSourceId` rejects path traversal, reverse-write disk layout uses `brainDir/.sources/<id>/<slug>.md` for non-default sources, `copyMigrationSources` lands source metadata before overlapping-slug pages. No `DATABASE_URL` needed. Wired into `scripts/e2e-test-map.ts` so changes to extract-takes / patterns / synthesize / embed / extract / migrate-engine auto-trigger it.
-- `test/e2e/migrate-engine-sources-postgres.test.ts` — `DATABASE_URL`-gated companion for `gbrain migrate --to`: migrates a PGLite brain carrying two non-default sources with overlapping slugs into real Postgres and asserts `copyMigrationSources` created every `sources` FK parent (config JSONB intact, not double-encoded) before any page write. Unit-level manifest identity (crash manifest resumes only against the SAME target; legacy engine-only manifests start fresh) is `test/migrate-engine-resume.test.ts`.
-- `test/e2e/facts-fence-reconcile-postgres.test.ts` — `DATABASE_URL`-gated round-trip for the escape-aware fence parser: renders a `## Facts` fence whose cells carry literal pipes, backslashes (Windows paths), and empty cells via `renderFactsTable`, runs the wipe-and-reinsert reconcile (`runExtractFacts`) on real Postgres, and asserts every cell survives byte-identically with no column shift.
-- `test/e2e/source-isolation-pglite.test.ts` — PGLite in-memory regression suite pinning the source-isolation seal at two layers. Engine layer: `searchKeyword` / `searchVector` / `searchKeywordChunks` / `listPages` / `getPage` / `traverseGraph` / `traversePaths` apply `sourceId` (scalar fast path) and `sourceIds` (array path) correctly across both engines. Op-handler layer: routes through `sourceScopeOpts(ctx)` so a `read+write`-scoped OAuth client bound to `--source dept-x` cannot see rows from neighboring sources via `search`, `query`, `list_pages`, `get_page`, or `find_experts`. Covers both `ctx.sourceId` (single-source clients) and `ctx.auth.allowedSources` (federated_read clients) precedence; federated array wins over scalar wins over nothing. No `DATABASE_URL` needed.
-- `test/e2e/think-source-isolation-pglite.test.ts` — PGLite in-memory suite pinning the `think` gather stage's source scope: seeds three sources with cross-source links and embedded takes, then asserts `runGather` under a federated `sourceIds` grant (and under a scalar `sourceId`) keeps every stream — hybrid retrieval, takes keyword + vector (`searchTakes`/`searchTakesVector`), and the `traversePaths` graph walk — inside the grant while still reaching authorized neighboring sources. No `DATABASE_URL` needed.
-- `test/e2e/skill-brain-first.test.ts` — doctor reports `skill_brain_first` check with structured issues; `--fix --dry-run` previews insertion without writing; `--fix` applies the canonical Convention callout idempotently; `brain_first: exempt` frontmatter resolves the warn; `brain_first_typo` surfaces a paste-ready hint; audit JSONL records `detected` / `resolved` / `fixed` transitions; stable brain emits 0 audit lines/run.
-- Tier 2 (`test/e2e/skills.test.ts`) requires OpenClaw + API keys, runs nightly in CI.
-- If `.env.testing` doesn't exist in this directory, check sibling worktrees: `find ../ -maxdepth 2 -name .env.testing -print -quit` and copy it here if found.
-- **Run E2E tests without asking permission.** When you want to verify behavior, there's a relevant E2E test, or you're shipping anything covered by an E2E suite — spin up the test DB, run the tests, tear down. Don't ask, don't propose it, don't defer. The lifecycle is short (~2-30s startup, sub-minute tests, instant teardown) and the gate value is high. Skipping with "DATABASE_URL unset" is silent regression, not caution.
-
-### API keys and running ALL tests
-
-ALWAYS source the user's shell profile before running tests:
-
-```bash
-source ~/.zshrc 2>/dev/null || true
-```
-
-This loads `OPENAI_API_KEY` and `ANTHROPIC_API_KEY`. Without these, Tier 2 tests
-skip silently. Do NOT skip Tier 2 tests just because they require API keys — load
-the keys and run them.
-
-When asked to "run all E2E tests" or "run tests", that means ALL tiers:
-- Tier 1: `bun run test:e2e` (mechanical, sync, upgrade — no API keys needed)
-- Tier 2: `test/e2e/skills.test.ts` (requires OpenAI + Anthropic + openclaw CLI)
-- Always spin up the test DB, source zshrc, run everything, tear down.
-
-### E2E test DB lifecycle (ALWAYS follow this)
-
-You are responsible for spinning up and tearing down the test Postgres container.
-Do not leave containers running after tests. Do not skip E2E tests, do not ask
-permission to run them — see the "run without asking" rule above.
-
-1. **Check for `.env.testing`** — if missing, copy from sibling worktree.
-   Read it to get the DATABASE_URL (it has the port number).
-2. **Check if the port is free:**
-   `docker ps --filter "publish=PORT"` — if another container is on that port,
-   pick a different port (try 5435, 5436, 5437) and start on that one instead.
-3. **Start the test DB:**
-   ```bash
-   docker run -d --name gbrain-test-pg \
-     -e POSTGRES_USER=postgres -e POSTGRES_PASSWORD=postgres \
-     -e POSTGRES_DB=gbrain_test \
-     -p PORT:5432 pgvector/pgvector:pg16
-   ```
-   Wait for ready: `docker exec gbrain-test-pg pg_isready -U postgres`
-4. **Bootstrap the schema** (required — fresh containers have no `oauth_clients`,
-   `mcp_request_log`, `pages` etc.; tests like `serve-http-oauth.test.ts` will fail
-   with `relation "oauth_clients" does not exist` if you skip this):
-   ```bash
-   DATABASE_URL=postgresql://postgres:postgres@localhost:PORT/gbrain_test \
-     bun run src/cli.ts doctor --json > /dev/null 2>&1
-   ```
-   `gbrain doctor` triggers `initSchema()` on first connect, which is the canonical
-   way to bring a fresh DB to head. `apply-migrations --yes` alone does NOT seed
-   the base schema — it runs ALTER-style migrations on top of `initSchema`. Tests
-   that bypass the engine (raw `execSync`-spawned `auth register-client`) hit the
-   schema directly and need this step to have run first.
-5. **Run E2E tests:**
-   `DATABASE_URL=postgresql://postgres:postgres@localhost:PORT/gbrain_test bun run test:e2e`
-6. **Tear down immediately after tests finish (pass or fail):**
-   `docker stop gbrain-test-pg && docker rm gbrain-test-pg`
-
-Never leave `gbrain-test-pg` running. If you find a stale one from a previous run,
-stop and remove it before starting a new one.

docs/ai-providers/llama-server-reranker.md

@@ -1,161 +0,0 @@
-# llama-server reranker (local) — Qwen3-Reranker, self-hosted ZE, any ZE-wire-shape provider
-
-[`llama-server`](https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md)
-is the HTTP wrapper that ships with llama.cpp. With `--reranking`, it
-exposes an OpenAI-style `POST /v1/rerank` endpoint that returns
-`{results: [{index, relevance_score}]}` — exactly the wire shape gbrain
-already drives for ZeroEntropy's hosted reranker. The
-`llama-server-reranker` recipe (added in v0.40.6.1) routes
-`gateway.rerank()` at your local llama.cpp instance instead of ZE.
-
-Two flavors of "local" this recipe covers:
-
-- **Qwen3-Reranker** (0.6B / 4B / 8B) — open-weight cross-encoder; pull
-  the GGUF from HuggingFace and serve.
-- **Self-hosted ZeroEntropy** (`zerank-2`, `zerank-1-small`) — the
-  weights are on HuggingFace too. GGUF-convert them and serve them the
-  same way. **Quality is not guaranteed to match ZE-hosted:** GGUF
-  conversion + quantization + pooling/rank metadata + tokenizer special
-  tokens all affect scores. If you self-host ZE for production
-  retrieval, pin your own brain-relevant eval (
-  [docs/eval-bench.md](../eval-bench.md)) as a regression guard.
-
-This recipe is the path override + recipe shape. Any provider whose
-request/response wire matches ZE/llama.cpp can use it by just pointing
-at a different base URL. Providers whose wire shape differs (Voyage uses
-`top_k` not `top_n`, returns `data[]` not `results[]`) need a separate
-recipe with adapter hooks — that lands in a follow-up plan.
-
-## Setup
-
-### 1. Build llama.cpp (or download a release)
-
-```bash
-# Clone and build (CPU only; add `-DGGML_CUDA=ON` for GPU)
-git clone https://github.com/ggml-org/llama.cpp.git
-cd llama.cpp
-cmake -B build
-cmake --build build --config Release -j
-```
-
-Pin a specific commit when you ship — `llama-server`'s path aliases
-(`/rerank`, `/v1/rerank`, `/reranking`, `/v1/reranking`) have shifted
-across releases. The recipe sends to `/v1/rerank`.
-
-### 2. Pull a reranker GGUF
-
-For Qwen3-Reranker-4B (quantized Q4_K_M is the sweet spot for CPU):
-
-```bash
-# Pick a quant level — Q4_K_M is the usual CPU sweet spot.
-huggingface-cli download \
-  Qwen/Qwen3-Reranker-4B-GGUF qwen3-reranker-4b-q4_k_m.gguf \
-  --local-dir ./models
-```
-
-For self-hosted ZeroEntropy weights, find a community GGUF conversion
-or convert from the HuggingFace weights yourself (out of scope of this
-doc — see llama.cpp's `convert_hf_to_gguf.py`).
-
-### 3. Launch llama-server with --reranking AND --alias
-
-```bash
-./build/bin/llama-server \
-  --model ./models/qwen3-reranker-4b-q4_k_m.gguf \
-  --alias qwen3-reranker-4b \
-  --reranking \
-  --port 8081
-```
-
-The `--alias` matters: without it, llama-server's `/v1/models` (and the
-`model` field rerank requests echo) defaults to the full gguf file
-path, which makes the gbrain config string ugly and brittle. With
-`--alias qwen3-reranker-4b`, your config string is short and stable.
-
-`--reranking` and `--embeddings` are mutually exclusive at server
-launch. If you also run a local embedder via the
-[`llama-server`](https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md)
-recipe, run two separate llama-server processes on two different ports
-(typically 8080 for embeddings, 8081 for reranking — gbrain's defaults
-match that convention).
-
-### 4. Wire gbrain at your server
-
-```bash
-# Point gbrain at the llama.cpp host (skip if running locally on default port)
-gbrain config set provider_base_urls.llama-server-reranker http://your-host:8081/v1
-
-# Tell search to use this reranker
-gbrain config set search.reranker.model llama-server-reranker:qwen3-reranker-4b
-gbrain config set search.reranker.enabled true
-```
-
-The `qwen3-reranker-4b` after the colon is your `--alias` value from
-step 3. Any string works as long as it matches your server's alias.
-
-Env vars work too as an alternative to the config set above:
-
-```bash
-export LLAMA_SERVER_RERANKER_BASE_URL=http://your-host:8081/v1
-# Optional: if you front llama-server with nginx + bearer auth
-export LLAMA_SERVER_RERANKER_API_KEY=your-bearer-token
-```
-
-### 5. Verify
-
-```bash
-gbrain models doctor
-# Expect: ✔ reranker_config llama-server-reranker:qwen3-reranker-4b ok
-#         ✔ reranker_config llama-server-reranker:qwen3-reranker-4b ok (reachability)
-
-gbrain search "some query" --json | jq '.[].rerank_score'
-# Expect: rerank_score on every row
-```
-
-If `gbrain models doctor` reports the reachability probe as `network`
-status, two common causes:
-
-1. The server is reachable but in embedding mode, not reranking mode.
-   `--reranking` and `--embeddings` are mutually exclusive at launch
-   — relaunch the right one.
-2. The recipe path doesn't match what your llama.cpp version serves.
-   This recipe sends `/v1/rerank`; older llama.cpp installs may only
-   serve `/rerank`. Pin to a recent llama.cpp commit.
-
-## Cold-start headroom
-
-CPU-only first-call warmup on a 4B reranker can take 8-15 seconds. The
-recipe declares `default_timeout_ms: 30000` so the first call after a
-server restart doesn't fail-open silently. That value flows through
-search-mode resolution unless you override it:
-
-```bash
-# Tighten or loosen per-search timeout (overrides recipe default):
-gbrain config set search.reranker.timeout_ms 60000
-```
-
-Per-call overrides in `SearchOpts.reranker_timeout_ms` still win for
-any single call.
-
-## Budget caps + local rerank
-
-The recipe declares `cost_per_1m_tokens_usd: 0` and registers under
-`FREE_LOCAL_RERANK_PROVIDERS` in the budget tracker, so
-`--max-cost`-bounded callers (autopilot loops, batch jobs) do NOT
-hard-fail when configured for local rerank. Local rerank costs
-electricity, not API tokens.
-
-```bash
-GBRAIN_MAX_USD=0.01 gbrain search "..." --reranker llama-server-reranker:qwen3-reranker-4b
-# Works: rerank fires, recorded at $0, cumulative cap untouched.
-```
-
-## Fail-open contract preserved
-
-`applyReranker` in `src/core/search/rerank.ts` still has the
-fail-open posture: any error class (network, timeout, malformed
-response) logs to `~/.gbrain/audit/rerank-failures-*.jsonl` and
-returns the original RRF order unchanged. Search reliability beats
-reranker quality. If your llama.cpp host goes down, your searches keep
-working — they just stop ranking against the cross-encoder until you
-restart the server.

docs/architecture/RETRIEVAL.md

@@ -40,7 +40,7 @@ Every `put_page` runs `extractEntityRefs` on the markdown body. It matches:
 - Obsidian wikilinks: `[[wiki/people/garry-tan|Garry Tan]]`
 - Typed-link blockquotes: `> **Convention:** see [path](path).`
 
-Three regexes, zero LLM tokens, single SQL `addLinksBatch` call with `INSERT ... SELECT FROM jsonb_to_recordset(($1::jsonb)->'rows') JOIN pages ON CONFLICT DO NOTHING RETURNING 1` (free-text-safe; the prior `unnest(${arr}::text[])` form crashed on calendar/Zoom context per gbrain#1861). The graph grows on every write at near-zero cost. On a 17K-page brain, full graph extract completes in seconds.
+Three regexes, zero LLM tokens, single SQL `addLinksBatch` call with `INSERT ... SELECT FROM unnest(...) JOIN pages ON CONFLICT DO NOTHING RETURNING 1`. The graph grows on every write at near-zero cost. On a 17K-page brain, full graph extract completes in seconds.
 
 Heuristic link-type inference (`attended`, `works_at`, `invested_in`, `founded`, `advises`) fires from surrounding sentence context — also LLM-free. Power users who want richer types add them via the typed-link blockquote convention.
 
@@ -54,44 +54,10 @@ The cost: +150ms p50 latency, ~$0.025/M tokens. Disabled with `gbrain config set
 
 ## Source-aware ranking
 
-Hybrid search applies a source-factor CASE expression at the SQL layer (lives in `src/core/search/sql-ranking.ts`). Curated content like `originals/`, `concepts/`, `writing/` outranks bulk content like `your-openclaw/chat/`, `daily/`, `media/x/`. Hard-exclude prefixes (`test/`, `attachments/`, `.raw/`) filter at retrieval, not post-rank.
-
-`archive/` is deliberately NOT hard-excluded (issue #1777): it holds high-signal historical content users expect to find, so it is demoted (`0.5x` in `DEFAULT_SOURCE_BOOSTS`), not hidden. The demote is a prior applied in the outer SQL re-rank; the cross-encoder reranker (balanced/tokenmax modes) can still PROMOTE an archive page that survives the demote into the rerank candidate window — it is not an unconditional suppression. `gbrain doctor`'s `hidden_by_search_policy` check reports how many chunked pages remain hidden by the surviving exclude prefixes.
+Hybrid search applies a source-factor CASE expression at the SQL layer (lives in `src/core/search/sql-ranking.ts`). Curated content like `originals/`, `concepts/`, `writing/` outranks bulk content like `your-openclaw/chat/`, `daily/`, `media/x/`. Hard-exclude prefixes (`test/`, `archive/`, `attachments/`, `.raw/`) filter at retrieval, not post-rank.
 
 The boost map is configurable via `GBRAIN_SOURCE_BOOST` env var or per-call `SearchOpts.exclude_slug_prefixes`. Temporal queries (`detail: 'high'`) bypass the boost so chat pages re-surface for time-sensitive lookups.
 
-## Named-thing retrieval (per-page pool + title + alias + evidence)
-
-A brain organized around *chosen names* (Mingtang, Hall of Light) needs more than
-embedding proximity. Four layers, added after the incident in
-[`RETRIEVAL_MAXPOOL_INCIDENT.md`](./RETRIEVAL_MAXPOOL_INCIDENT.md):
-
-- **Per-page max-pool** — `searchVector` (both engines) collapses chunk-grain
-  candidates to the best chunk per page (`DISTINCT ON (slug)`) over the full
-  candidate set before the user `LIMIT`, via the shared `buildBestPerPagePoolCte`
-  in `sql-ranking.ts`. The vector side returns N distinct pages by best chunk,
-  not N chunks that collapse to fewer pages downstream.
-- **Title-phrase boost** — when the normalized query is a contiguous token-run
-  inside `page.title` (or an exact full-title match), a floor-ratio-gated,
-  bounded multiplier fires (`applyTitleBoost`, `search.title_boost` knob). A
-  query that is a phrase from the title can't lose to a body chunk by luck.
-- **Alias hop** — free-text `aliases:` frontmatter is projected into a
-  `page_aliases` table (separate from the `slug_aliases` wikilink redirect) and
-  consulted at query time: a full normalized-query match injects/boosts the
-  canonical page (`applyAliasHop`). The only layer that bridges true synonyms
-  with zero surface overlap ("Hall of Light" → the Mingtang page). Backfill
-  existing pages with `gbrain reindex --aliases`.
-- **Evidence contract** — every result carries `evidence`
-  (`alias_hit | exact_title_match | high_vector_match | keyword_exact |
-  weak_semantic`) and `create_safety` (`exists | probable | unknown`). An agent
-  deciding "is this page already here, safe to NOT write a duplicate?" keys off
-  `create_safety`, not a raw blended score.
-
-The `search` MCP/CLI op is **cheap-hybrid** (vector + keyword + RRF + pool +
-title + alias, expansion off); `query` is the full-control variant. NamedThingBench
-(`gbrain eval retrieval-quality`) gates these families on every PR. Diagnose a
-specific miss with `gbrain search diagnose "<q>" --target <slug>`.
-
 ## Intent-aware query rewriting
 
 `src/core/search/intent.ts` classifies queries into `entity`, `temporal`, `event`, or `general`. Each routes through different ranking knobs:
@@ -123,7 +89,6 @@ expansion (if enabled)
 hybrid search:
    ├── vector  (HNSW on chunk embeddings)
    ├── keyword (BM25 via tsvector)
-   ├── relational (v0.42.34.0: typed-edge recall arm — relational queries only)
    ├── source-aware re-rank (CASE in SQL)
    └── RRF fusion → top 30
        │

docs/architecture/RETRIEVAL_MAXPOOL_INCIDENT.md

@@ -1,97 +0,0 @@
-# Retrieval Incident: a chosen-name page was missed, and the fix
-
-**Status:** Resolved (retrieval-cathedral wave). Supersedes the docs-only RFC in
-closed PR #1616 — the diagnosis there was directionally right about the disease
-but wrong on several mechanics; this is the corrected record + what shipped.
-**Original author:** Garry Tan's OpenClaw. **Severity at the time:** High.
-**Related:** [`RETRIEVAL.md`](./RETRIEVAL.md), [`../eval/METRIC_GLOSSARY.md`](../eval/METRIC_GLOSSARY.md).
-
----
-
-## 1. What happened
-
-The agent was asked to log that Garry "wants to build a Greek amphitheater." It
-ran a retrieval for the concept, the canonical concept page (titled "...Indoor
-Greek Amphitheater...") did **not** surface with enough confidence to be
-recognized as the existing page, and the agent wrote a **duplicate stub** on top
-of a fully-developed concept doc. Garry caught it: "It's in the brain. It's the
-Hall of Light. Why did you forget?"
-
-The page is *about* a Greek amphitheater — the phrase is in its title and first
-sentence. A healthy index returns it at the top. It didn't.
-
-## 2. The disease (the RFC got this right)
-
-The brain is stored by **meaning and chosen name** (Mingtang, Hall of Light) but
-was retrieved by **literal embedding proximity to a body chunk**, and the agent's
-"is this already here?" decision keyed off a single fuzzy blended score. Three
-retrieval gaps plus one contract gap produced the miss.
-
-## 3. Verified ground truth (corrections to the RFC)
-
-These were checked in code during the fix; several change the remedy:
-
-1. **`gbrain search` was keyword-only**, not hybrid — so the RFC's cosine scores
-   (0.64/0.98) came from the hybrid `query`/MCP path the agent actually hit, not
-   `gbrain search`. The repro command in the RFC was mislabeled.
-2. **`--mode` was never a CLI param** — mode resolves server-side from the
-   `search.mode` config key, which is why all three "modes" returned identical
-   results (the flag was silently dropped; `thorough` isn't a real mode).
-3. **`hybridSearch` already max-pooled per page at the dedup layer.** So the
-   per-page max-pool fix's real win is *candidate-set page recall* (the vector
-   side returned N chunks that could collapse to fewer pages), and it is
-   necessary-but-not-sufficient: if a page's title chunk scores below a body
-   chunk on a 2-word query, or falls outside the candidate pool, pooling alone
-   doesn't rescue it.
-4. **Frontmatter `aliases:` was dead to search** — stored in `pages.frontmatter`
-   JSONB, never consulted. `slug_aliases` is a *slug→slug* wikilink redirect, a
-   different concept.
-
-## 4. The fix that shipped (four layers + a contract)
-
-| Layer | Fixes | Where |
-|---|---|---|
-| **Per-page max-pool** (T1) | a page scored by its weakest chunk; vector page-recall | `searchVector` both engines, shared `buildBestPerPagePoolCte` |
-| **Title-phrase boost** (T2) | query is a phrase in the title but matched a body chunk | `applyTitleBoost` (reads `page.title`), `title_boost` mode knob |
-| **Alias hop** (T3) | true synonyms with zero surface overlap ("Hall of Light" → Mingtang) | `page_aliases` table, `applyAliasHop`, ingest projection + `reindex --aliases` backfill |
-| **Evidence contract** (T4) | the agent keyed "don't duplicate" off a fuzzy score | `evidence` + `create_safety` on every result; the agent keys off `create_safety='exists'`, not a threshold |
-
-Plus: `gbrain search "<text>"` is now cheap-hybrid (the obvious verb gives the
-good path); `modes/stats/tune` stay subcommands; `--mode` works per-call for
-local callers; rank-1 score drift telemetry; and **NamedThingBench**, a CI gate
-that hard-gates the families that ARE this incident.
-
-## 5. How to confirm / triage a recurrence
-
-```
-# Which layer surfaces (or misses) the target page?
-gbrain search diagnose "Greek amphitheater" --target projects/new-greek-theater/concept_v0
-
-# Backfill aliases for existing pages whose frontmatter predates the alias layer:
-gbrain reindex --aliases
-
-# Watch retrieval quality over time (a downward avg rank-1 score = regressing):
-gbrain search stats --days 30
-
-# The gate that prevents silent reintroduction:
-gbrain eval retrieval-quality test/fixtures/retrieval-quality/namedthing.jsonl
-```
-
-For a page to be reliably found by its chosen name, give it `aliases:` frontmatter:
-
-```yaml
----
-title: The Mingtang — Indoor Greek Amphitheater
-aliases:
-  - Hall of Light
-  - 明堂
----
-```
-
-## 6. The discipline this teaches
-
-A benchmark that scores 97.9 R@5 while production returns a flagship page at 0.64
-means the benchmark and the shipped path diverged. NamedThingBench runs the same
-families through the real pipeline on every PR, and the evidence contract means
-the agent's duplicate-or-not decision is grounded in *why* a page matched, not a
-number that was never a calibrated probability.

docs/architecture/lens-packs.md

@@ -1,143 +0,0 @@
-# Lens packs (v0.41.2.0)
-
-Four bundled schema packs that turn the gbrain dream cycle into a multi-lens
-brain. Activate one with `gbrain config set schema_pack <name>` and the cycle
-picks up the pack's declared phases on the next `gbrain dream` run.
-
-## The four packs
-
-```
-                gbrain-base (shipped v0.38)
-                       ▲
-                       │ extends
-        ┌──────────────┼──────────────────────┐
-        │              │                       │
-   gbrain-creator  gbrain-investor      gbrain-engineer
-   (atom + concept  (deal/thesis/        (learning bridge
-    lifecycle)       bet_resolution)      for gstack)
-        │              │                       │
-        └──────────────┼───────────────────────┘
-                       │ extends + borrow chain
-                       ▼
-              gbrain-everything (meta-pack)
-              one brain, three lenses active
-```
-
-### gbrain-creator
-Atom + concept content-creator lifecycle. Drives two cycle phases:
-
-- `extract_atoms` — per source, Haiku extracts 1-3 atoms from each
-  transcript with the closed 11-value `atom_type` enum (insight,
-  anecdote, quote, framework, statistic, story_angle, strategy_angle,
-  strategy, endorsement, critique, collection). Writes
-  `atoms/{YYYY-MM-DD}/{slug}` pages. Budget cap $0.30/source/run.
-- `synthesize_concepts` — globally aggregates atoms by frontmatter
-  `concepts:` ref. Tier by count: T1 ≥10, T2 ≥5, T3 ≥2. T1/T2 get
-  Sonnet narratives; T3 falls back to a deterministic stub. Writes
-  `concepts/{slug}` pages. Budget cap $1.50/run.
-
-One calibration domain: `concept_themes` / cluster_summary / [concept]
-— tier histogram + page count, not Brier (concepts don't have binary
-outcomes to score against).
-
-### gbrain-investor
-YC / investor lens. Declares 2 net-new page types on top of
-gbrain-base's deal/person/company/yc seed:
-
-- `thesis` (NEW) — investment thesis with thesis_text + key_bets[] +
-  market_view + vintage. Files at `investing/theses/{slug}`. Extractable
-  (the LLM mines claims into facts).
-- `bet_resolution_log` (NEW) — outcome record for a thesis's bet. FK
-  to a take row via take_id; carries resolved_outcome + resolved_at +
-  learned_pattern. Files at `investing/bets/{YYYY-MM}/{slug}`.
-
-No new cycle phases — consumes the existing
-extract_facts/propose_takes/grade_takes/calibration_profile loop. Three
-calibration domains: `deal_success` (scalar_brier over deal-attached
-takes), `founder_evaluation` (scalar_brier over person-attached takes),
-`market_call` (weighted_brier over thesis-attached takes; weighted by
-conviction so high-stakes misses cost more).
-
-### gbrain-engineer
-Bridge-only pack. Declares `learning` page type + reuses base `code`.
-No new cycle phases — the daemon-side `gstack-learnings` IngestionSource
-(T8) watches `~/.gstack/projects/{repo}/learnings.jsonl` and emits
-each JSONL line as a `learning` page when this pack is active. Three
-calibration domains: `architecture_calls` (scalar_brier),
-`effort_estimates` (weighted_brier), `risk_assessment` (scalar_brier).
-
-Speculative ADR/postmortem/refactor_thesis/tech_debt types deferred
-to v0.42+ — they'll ship when a real user authors the first one (D8).
-
-### gbrain-everything
-Meta-pack stacking creator + investor + engineer via the v0.38
-`extends` + `borrow_from` chain. Single-active-pack constraint
-preserved — this IS the active pack; the registry walks extends +
-borrow to materialize the merged view.
-
-Activate via `gbrain config set schema_pack gbrain-everything` and
-calibration_profile produces all 7 domain scorecards in one JSONB.
-
-## Calibration profile widening (T10)
-
-Before v0.41.2.0, `calibration_profiles.domain_scorecards` was a
-`JSON.stringify({})` placeholder. v0.41.2.0 widens it: each declared
-domain produces a `{n, brier, accuracy, aggregator, page_types,
-extras}` entry. Four aggregator algorithms (closed enum):
-
-- **scalar_brier** — `AVG(POWER(weight - outcome::int, 2))`. Default for
-  probabilistic predictions.
-- **weighted_brier** — Brier weighted by `ABS(weight - 0.5) * 2`
-  (conviction proxy). High-conviction misses cost more.
-- **count_based** — simple `SUM(hit) / COUNT(*)` accuracy without
-  Brier. Use when probability isn't natural.
-- **cluster_summary** — descriptive rollup (page count + tier
-  histogram). For domains like `concept_themes` where there's no
-  binary outcome.
-
-Pack manifests declare domains with `{name, aggregator, page_types}`.
-Domain names are OPEN (third-party packs can declare new domain labels
-without a gbrain release). Aggregator algorithms are CLOSED (safe SQL
-stays in code, validated at pack-load).
-
-## take_domain_assignments table (T1)
-
-New JOIN table (migration v94):
-`take_domain_assignments(take_id BIGINT FK, domain TEXT, pack TEXT,
-source TEXT, confidence REAL, assigned_at TIMESTAMPTZ, PK(take_id,
-domain))`. Multi-domain assignment honest — a take about "Sequoia's
-investment in Anthropic" can land in BOTH `deal_success` AND
-`market_call` rather than being force-bucketed.
-
-## What this enables for the user
-
-- **Atoms + concepts ship in the binary.** Your OpenClaw's parallel
-  atom-pipeline-coordinator + atom-backfill-coordinator + concept-
-  synthesis crons can retire (T12 follow-up). One `gbrain dream` cron
-  covers everything.
-- **gstack learnings reach gbrain.** Engineer-pack-active brains
-  surface every gstack-logged learning as a queryable page within
-  seconds of being written.
-- **Multi-lens calibration.** Activate gbrain-everything and see how
-  often you're wrong on deals AND market calls AND architecture
-  AND effort estimates in one `gbrain calibration --json` call.
-- **Lossless OpenClaw migration.** The `markdown-greenfield`
-  importer (T7, mode='migration') re-ingests existing OpenClaw
-  pages with permanent slug-keyed idempotency + per-row JSONL audit
-  + the `imported_from` marker so extract_atoms + synthesize_concepts
-  don't re-extract already-atomized material.
-
-## v0.41.2.1 follow-ups (filed in plan)
-
-- Per-page-type `frontmatter_validators` on PageTypeSchema so the
-  atom_type enum (currently hardcoded in extract_atoms.ts) reads from
-  the active pack manifest at runtime per D11.
-- 3-check quality gate (truism / punchline / entity-page reject) as
-  a multi-pass extract_atoms refinement.
-- Embedding-similarity dedup in synthesize_concepts (currently
-  exact-string concept ref match only).
-- Voice gate integration for T1 Canon narratives.
-- op_checkpoint resumability for cross-cycle continuation in both
-  phases.
-- Parity-baseline eval gates against your OpenClaw's existing 13K atoms
-  + 11K concepts on a 500-page sample subset.

docs/architecture/pack-upgrade-mechanism.md

@@ -1,246 +0,0 @@
-# Pack-Upgrade Mechanism (v0.41.22)
-
-> How `gbrain-base@1.x → gbrain-base-v2@1.0.0` (and any future pack
-> succession) wires through the onboard cathedral.
-
-## The contract
-
-A schema pack manifest can declare a `migration_from` field:
-
-```yaml
-api_version: gbrain-schema-pack-v1
-name: gbrain-base-v2
-version: 1.0.0
-migration_from:
-  pack: gbrain-base
-  version: "1.x"
-```
-
-When this declaration is present + a `mapping_rules:` block is
-populated, the pack registers itself as the successor to
-`(parent_pack, version_range)`. Any brain whose active pack matches
-that tuple lights up the `pack_upgrade_available` onboard check.
-
-## End-to-end flow
-
-```
-┌────────────────────────────────────────────────────────────────┐
-│  PACK AUTHORING                                                │
-│                                                                │
-│  Author declares: migration_from: {pack: P, version: R}        │
-│  + mapping_rules: [retype/page_to_link/page_to_alias]          │
-│  Pack ships bundled OR via ~/.gbrain/schema-packs/<name>/      │
-└──────────────────────────┬─────────────────────────────────────┘
-                           ↓
-┌────────────────────────────────────────────────────────────────┐
-│  ONBOARD CHECK DISCOVERY                                       │
-│                                                                │
-│  checkPackUpgradeAvailable(engine) at src/core/onboard/        │
-│  checks.ts:                                                    │
-│    1. Read engine.getConfig('schema_pack') for dbConfig tier  │
-│    2. loadActivePack({cfg: null, remote: false, dbConfig})    │
-│    3. findPackSuccessors(active.name, active.version)         │
-│         → walks BUNDLED_PACK_NAMES + ~/.gbrain/schema-packs/   │
-│         → matches via _versionRangeMatches(version, range)    │
-│         → returns ResolvedPack[] sorted by successor version  │
-│    4. If successors.length > 0, emit OnboardCheckResult        │
-│       with RemediationStep targeting `unify-types` handler    │
-│       + protected: true (D17 → manual_only via render          │
-│       allowlist)                                               │
-└──────────────────────────┬─────────────────────────────────────┘
-                           ↓
-┌────────────────────────────────────────────────────────────────┐
-│  USER DECIDES                                                  │
-│                                                                │
-│  gbrain onboard --check shows finding                          │
-│  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"}'               │
-│  (Autopilot never auto-fires this; manual_only)                │
-└──────────────────────────┬─────────────────────────────────────┘
-                           ↓
-┌────────────────────────────────────────────────────────────────┐
-│  HANDLER EXECUTION (src/core/schema-pack/unify-types-handler.ts) │
-│                                                                │
-│  1. Preflight: load target pack; assert mapping_rules present  │
-│  2. Stats snapshot (pre-state for celebration)                 │
-│  3. Acquire gbrain-unify db-lock (60min TTL)                   │
-│  4. Apply phases (4):                                          │
-│     a. Explicit retype rules (chunked UPDATE 1000/batch)       │
-│        - frontmatter.legacy_type ALWAYS preserved (D8)         │
-│        - frontmatter.subtype stamped when subtype set          │
-│     b. Catch-all retype: synthesize per-unknown-type rule       │
-│        excluding declared types + explicit targets + page_to_  │
-│        link/alias sources (D12 + critical bug fix)             │
-│     c. Page-to-link: parse body+frontmatter, insert link row,  │
-│        soft-delete source page (per-page atomicity per F7)     │
-│     d. Page-to-alias: insert slug_aliases row, soft-delete     │
-│        source page (NO rewriteLinks per D15)                   │
-│  5. Final sync: path-prefix typing for residual UNTYPED rows   │
-│  6. ACTIVE-PACK FLIP (D13):                                    │
-│     - engine.setConfig('schema_pack', target_pack)             │
-│     - saveConfig({...existing, schema_pack: target_pack})      │
-│  7. Verify: re-run stats; warn if ≤ declared + 5 violated      │
-│  8. Celebration summary to stderr + audit JSONL                │
-│  9. Release db-lock                                            │
-└──────────────────────────┬─────────────────────────────────────┘
-                           ↓
-┌────────────────────────────────────────────────────────────────┐
-│  POST-UPGRADE STATE                                            │
-│                                                                │
-│  • pages.type updated with canonical types                     │
-│  • frontmatter.legacy_type preserved for rollback              │
-│  • slug_aliases populated for old-slug → canonical lookup      │
-│  • links table has new partner_of / relates_to rows            │
-│  • Source pages soft-deleted (72h TTL for restore)             │
-│  • Active pack flipped to target_pack                          │
-│  • Next gbrain onboard --check shows ok                        │
-└────────────────────────────────────────────────────────────────┘
-```
-
-## Version-range semantics
-
-`migration_from.version` accepts three shapes:
-
-| Form | Matches |
-|------|---------|
-| `1.0.0` (exact literal) | `1.0.0` only |
-| `1.x` (major wildcard) | `1.0.0`, `1.5.2`, `1.99.99` |
-| `1.0.x` (minor wildcard) | `1.0.0`, `1.0.5`, `1.0.99` |
-
-`*` is accepted as an alias for `x`.
-
-Implementation: `_versionRangeMatches(version, range)` in
-`src/core/schema-pack/load-active.ts`. Pinned by
-`test/schema-pack-find-pack-successors.test.ts`.
-
-## findPackSuccessors discovery
-
-Walks `BUNDLED_PACK_NAMES` (currently `gbrain-base`,
-`gbrain-recommended`, `gbrain-creator`, `gbrain-investor`,
-`gbrain-engineer`, `gbrain-everything`, `gbrain-base-v2`). For each
-candidate ≠ the active pack name, loads the manifest via
-`loadActivePack({ perCall: candidate })`, checks
-`migration_from.pack === activeName && _versionRangeMatches(activeVer,
-migration_from.version)`. Returns matching packs sorted by version
-descending.
-
-v0.41.22 covers bundled packs only. v0.43+ TODO: enumerate user-installed
-packs at `~/.gbrain/schema-packs/*/pack.yaml` (defer to v0.43 since the
-filesystem-scan cost needs the cache invalidation strategy from
-`registry.ts`).
-
-## The manual_only apply policy
-
-The shipped onboard contract has 3 apply_policy values:
-
-| Policy | Meaning |
-|--------|---------|
-| `auto_apply` | Autopilot runs unattended |
-| `prompt_required` | Autopilot in `--auto-with-prompt` mode prompts user |
-| `manual_only` | Autopilot NEVER auto-fires; user must explicitly submit |
-
-`pack_upgrade_available` emits a `RemediationStep` with `protected:
-true` + `job: 'unify-types'`. `toOnboardRecommendation` in
-`src/core/onboard/render.ts` maps this to `manual_only` via the
-`MANUAL_ONLY_PROTECTED_JOBS` allowlist (which also contains
-`extract-takes-from-pages` per v0.41.18 A12+A24).
-
-Rationale: pack upgrades change the brain's taxonomy. Taxonomy is a
-user judgment call — not autopilot's call. Even with `--auto-with-
-prompt`, prompting the user to confirm a pack upgrade mid-tick is the
-wrong UX (the user came to fix orphans, not to be interrupted with
-"hey want to migrate your taxonomy?"). Explicit submission is the
-right boundary.
-
-## Authoring a successor pack
-
-Minimal example for an academic-research brain that adds a
-`researcher` canonical:
-
-```yaml
-api_version: gbrain-schema-pack-v1
-name: gbrain-academic-v1
-version: 1.0.0
-description: Academic research brain — adds researcher canonical
-gbrain_min_version: 0.42.0
-extends: null
-
-migration_from:
-  pack: gbrain-base-v2
-  version: "1.x"
-
-page_types:
-  # Inherit gbrain-base-v2's 15 types here (or use extends to merge
-  # automatically once v0.43+ extends-chain composition lands)
-  - { name: person, primitive: entity, path_prefixes: [people/], expert_routing: true }
-  - { name: company, primitive: entity, path_prefixes: [companies/], expert_routing: true }
-  # ... all 13 other v2 canonicals ...
-  - { name: note, primitive: concept, path_prefixes: [notes/], extractable: true }
-  # Academic addition:
-  - name: researcher
-    primitive: entity
-    path_prefixes: [researchers/]
-    aliases: [academic, professor, scholar]
-    extractable: false
-    expert_routing: true
-
-mapping_rules:
-  # All v2 mapping rules (copy from v2 yaml)
-  # ... ~40 rules ...
-  # Custom: relocate v2-tagged academics to researcher
-  - { kind: retype, from_type: person, to_type: researcher, path_filter: 'researchers/%' }
-  # Catch-all
-  - kind: retype
-    from_type: "*unknown*"
-    to_type: note
-    subtype_field: legacy_type
-    subtype: "*original_type*"
-```
-
-Drop at `~/.gbrain/schema-packs/gbrain-academic-v1/pack.yaml`.
-Discoverable via `gbrain schema list`. Activatable via
-`gbrain schema use gbrain-academic-v1`. Once active, the
-`pack_upgrade_available` check fires for any brain on
-`gbrain-base-v2@1.x` and surfaces a `unify-types` RemediationStep
-targeting your pack.
-
-## Lock + concurrency
-
-`gbrain-unify` is a dedicated `gbrain_cycle_locks` row name (60min
-TTL). The handler acquires it before any apply phase + releases in
-`finally`. Two simultaneous `gbrain jobs submit unify-types`
-invocations: second one fails fast at lock acquisition with a clear
-error. Same pattern as `gbrain-sync` (v0.22.13 PR #490).
-
-## Audit trail
-
-Every unify run writes to `~/.gbrain/audit/schema-unify-YYYY-Www.jsonl`
-(ISO-week rotation, mirrors existing audit channels). Records: pack
-identities (before + after), per-phase counts (would_apply + applied),
-warnings, completion timestamp. Privacy: page slugs are NOT logged in
-bulk (only the per-rule sample_slugs[≤10]); for forensic debugging
-add `GBRAIN_AUDIT_FULL=1` (v0.43+ TODO; not yet wired).
-
-## What's NOT yet supported
-
-- Subprocess sandbox for the publish-gate (v0.43+ TODO)
-- 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`)
-- LLM-assisted mapping_rules codegen from production data (`gbrain
-  schema detect-mappings`; deferred to v0.43+)
-
-## Reference
-
-- Pack file: `src/core/schema-pack/base/gbrain-base-v2.yaml`
-- Manifest extension: `src/core/schema-pack/manifest-v1.ts`
-- Successor walker: `src/core/schema-pack/load-active.ts:findPackSuccessors`
-- Onboard check: `src/core/onboard/checks.ts:checkPackUpgradeAvailable`
-- Render allowlist: `src/core/onboard/render.ts:MANUAL_ONLY_PROTECTED_JOBS`
-- Handler: `src/core/schema-pack/unify-types-handler.ts`
-- Migration: `src/core/migrate.ts:105` (slug_aliases table)
-- Type taxonomy doc: `docs/architecture/type-taxonomy.md`
-- Skill: `skills/schema-unify/SKILL.md`

docs/architecture/serve-sync-concurrency.md

@@ -1,54 +0,0 @@
-# `gbrain serve` ↔ `gbrain sync` concurrency (PGLite)
-
-**Short version: on a PGLite brain, stop `gbrain serve` before a large sync.**
-
-## Why
-
-PGLite is a single-writer embedded Postgres (WASM). A running `gbrain serve`
-(stdio or HTTP MCP) holds an open PGLite connection on the brain's data
-directory. `gbrain sync` needs to write to that same data directory. The two
-contend for PGLite's single-writer connection / write-lock — **this is NOT the
-`gbrain-sync` advisory lock** (that's a separate, DB-row coordination lock for
-two concurrent *syncs*). Confusing the two sends you debugging the wrong surface.
-
-Symptoms of serve↔sync contention on PGLite:
-
-- `gbrain sync` blocks acquiring the PGLite write lock, or makes very slow
-  progress, while a `gbrain serve` process is alive on the same brain.
-- Killing stale `gbrain serve` MCP processes frees the lock and sync proceeds.
-
-## What to do
-
-1. Stop any `gbrain serve` process for this brain before a large sync:
-   ```bash
-   pkill -f 'gbrain serve'      # or stop your MCP client / Claude Desktop / Cursor
-   gbrain sync --no-pull --no-embed --yes
-   ```
-2. Restart `gbrain serve` after the sync completes.
-
-This contention does **not** apply to the Postgres engine — Postgres tolerates
-concurrent connections, so `serve` and `sync` can run simultaneously there.
-
-## Diagnosing a sync hang
-
-If a sync wedges (no progress, high CPU), re-run with the per-file begin trace
-so the stalling file is named:
-
-```bash
-GBRAIN_SYNC_TRACE=1 gbrain sync --no-pull --no-embed --yes
-```
-
-The last `[sync] begin import: <path>` line with no following completion is the
-file being processed when the hang occurred. Under `--workers >1` / `--all`,
-the stuck file is in the set of begin-lines without a matching completion.
-
-If you suspect a schema-pack regex is the cause (a pack with a
-catastrophic-backtracking `inference.regex`), complete the sync with the pack
-disabled and re-run extraction afterward:
-
-```bash
-gbrain sync --no-schema-pack --no-pull --no-embed --yes
-```
-
-`gbrain schema lint` flags the classic nested-quantifier ReDoS shapes
-(`(a+)+`, `(a*)*`, …) in pack regexes as warnings.

docs/architecture/thin-client.md

@@ -1,70 +0,0 @@
-# Thin-client routing (remote MCP)
-
-On-demand reference (see CLAUDE.md Reference map). Current behavior + invariants
-only; release history lives in `CHANGELOG.md` + git.
-
-`gbrain init --mcp-only` (v0.29.2) sets up a thin-client install: no local
-brain content, just an OAuth client pointing at a remote `gbrain serve --http`.
-v0.29.2/v0.30.0 only refused 9 obvious local-only commands; the other ~25
-silently fell through to `connectEngine()` and opened the empty local PGLite,
-returning "No results." against a populated remote brain. v0.31.1 fixes the
-silent-empty-results bug class for every operation surface.
-
-Key files:
-
-- `src/cli.ts` — Routing seam INSIDE the existing op-dispatch path (CDX-1: no
-  parallel `src/core/thin-client/` module; routing is a ~80-line conditional
-  in `runThinClientRouted`). Detects `isThinClient(cfg)` BEFORE `connectEngine`
-  so thin-client installs never open the empty PGLite. localOnly ops on
-  thin-client refuse via `refuseThinClient` (with pinpoint hint table
-  `THIN_CLIENT_REFUSE_HINTS`). Banner via `printIdentityBannerBestEffort`
-  before each routed call (suppressed by `--quiet`, `GBRAIN_NO_BANNER=1`,
-  non-TTY default). Exhaustive TS `never` switch on `RemoteMcpError.reason`
-  for canned, actionable error messages. ENG-2 renderer parity: local-engine
-  path runs `JSON.parse(JSON.stringify(result))` so renderers see the same
-  shape on both paths (kills Date/bigint/Buffer drift class).
-- `src/core/mcp-client.ts` — `callRemoteTool(config, toolName, args, opts)`.
-  Hardened in v0.31.1 (CDX-4): all transport errors normalized to
-  `RemoteMcpError` via the `toRemoteMcpError` funnel. New `CallRemoteToolOptions
-  {timeoutMs, signal}`; `buildAbortController` composes external signal with
-  timeout. New `RemoteMcpErrorReason` stable union, `RemoteMcpErrorDetail.kind`
-  ('timeout' | 'aborted' | 'unreachable') sub-tag, `RemoteMcpErrorDetail.code`
-  field carrying server-supplied error codes (e.g. `missing_scope`).
-  `extractToolErrorCode` parses JSON envelopes first, falls back to substring
-  detection for legacy server messages. `unpackToolResult<T>(res)` unchanged
-  (parses tool-call JSON content). `_clearMcpClientTokenCache()` test escape.
-- `src/core/cli-options.ts` — `parseGlobalFlags` adds `--timeout=Ns` (accepts
-  `30s`, `2m`, `500ms`, plain ms). Default `null` = per-command default (30s
-  for most ops, 180s for `think`). `parseTimeout(s)` exported helper.
-- `src/core/doctor-remote.ts` — `gbrain remote doctor` adds the
-  `oauth_client_scopes_probe` check (CDX-5). Probes the read tier via
-  `get_brain_identity` and admin tier via `get_health`; reports per-tier
-  status with pinpoint remediation when admin is missing. `buildScopeCheck`
-  + `ScopeProbeResult` exported for test access. Skippable via
-  `GBRAIN_DOCTOR_SKIP_SCOPE_PROBE=1` for fixtures that mock /mcp at JSON-RPC
-  initialize level only (MCP SDK Client hangs on shape mismatch).
-- `src/core/ssrf-validate.ts` (v0.36 Commit 0) — DNS-rebinding-defended URL validation. `validateAndResolveUrl(url)` resolves the hostname via `dns.lookup({all: true, family: 0})`, checks EVERY A AND AAAA record against the internal-IP deny list, returns the resolved IP so callers fetch by IP (defeats DNS rebinding: validation IP === fetch IP). `fetchWithSSRFGuard(url, opts)` does redirect-aware fetching with per-hop re-validation, max 3 hops by default. Reusable across all URL-fetching features. Test seam `__setDnsLookupForTests` for hermetic tests.
-- `src/core/search/query-intent.ts` extension (v0.36 cross-modal wave) — new `suggestedModality: 'text' | 'image' | 'both'` axis on `QuerySuggestions`. Module-scope `CROSS_MODAL_PATTERNS` regex array (compiles once at module load). `isAmbiguousModalityQuery(query)` heuristic gate fires when a visual noun + reference marker combination indicates genuinely ambiguous routing — used by the Commit 4 LLM tie-break to bound LLM calls to <1% of queries.
-- `src/core/search/mode.ts` extension (v0.36 cross-modal wave) — `ModeBundle` extended with 7 cross-modal knobs: `cross_modal_both_text_weight` / `cross_modal_both_image_weight` (D6 weighted RRF for `'both'` mode, defaults 0.6/0.4), `image_query_text_refinement_weight` / `image_query_image_refinement_weight` (D13 hybrid intersect for `searchByImage` query refinement, defaults 0.4/0.6), `unified_multimodal` + `unified_multimodal_only` (Phase 3 unified column routing flags), `cross_modal_llm_intent` (Commit 4 opt-in escalation). `SEARCH_MODE_CONFIG_KEYS` extended with 7 corresponding config keys. `KNOBS_HASH_VERSION` bumped 2→3 (D2 — closes the silent cache-hit class where a cached text-mode result could leak to an image-mode caller).
-- `src/core/search/hybrid.ts` extension (v0.36 cross-modal wave) — cross-modal routing branch at the embed step. Resolves `effectiveModality` from per-call `opts.crossModal` (normalized: literal `'auto'` → undefined per D22-1) → `suggestions.suggestedModality` → `'text'` default. Image route: `embedQueryMultimodal` + `searchVector({embeddingColumn: 'embedding_image'})`, skip expansion + keyword (D9 mode-bundle override). 'both' route: parallel text + image vector searches merged via `rrfFusionWeighted` with `effectiveRrfK(baseRrfK, weight)` from the configured cross-modal weights. Phase 3 unified routing fires when `cfg.search.unified_multimodal === true` — bypasses dual-column branching, runs `embedQueryMultimodal` + `searchVector({embeddingColumn: 'embedding_multimodal'})`, D8 fail-open on zero rows + not strict-mode falls through to dual-column. Commit 4 LLM escalation fires only when (no explicit per-call opt) AND (regex returned 'text') AND (`cfg.search.cross_modal.llm_intent` is true) AND (`isAmbiguousModalityQuery` returns true). Fail-open on every error.
-- `src/core/search/image-loader.ts` (v0.36 Phase 2) — `loadImageInput(input, opts)` accepts local path, `data:` URI, or `http(s)://` URL. Magic-byte sniff for PNG/JPEG/WebP. Hard size cap (default 10 MB, configurable via `search.image_query.max_bytes`). For URLs: routes through `fetchWithSSRFGuard` so DNS rebinding + redirect chains are defeated. Pre-flight Content-Length check + post-fetch size guard for lying servers. `ImageLoadError` with discriminated `code` (INVALID_FORMAT / OVERSIZED / INVALID_URL / FETCH_FAILED / TIMEOUT / SSRF_BLOCKED / NOT_FOUND).
-- `src/core/search/by-image.ts` (v0.36 Phase 2) — `searchByImage(engine, input, opts)`. Always runs image branch (`embedQueryMultimodalImage` + `searchVector(embedding_image)`). D13 hybrid intersect: when caller provides optional `query`, runs parallel text branch via `embedQueryMultimodal(query)` and merges via `rrfFusionWeighted` with weights from resolved mode. Phase 3 widens to unified column once `search.unified_multimodal=true` (transparently upgrades the retrieval quality post-reindex).
-- `src/core/spend-log.ts` (v0.36 Phase 2 D23-#6) — per-OAuth-client paid-API spend tracking against the `mcp_spend_log` table (migration v74). `checkBudget(engine, clientId, capCents)` is the pre-flight gate; throws `BudgetExceededError` when today's spend has hit the cap. `recordSpend(engine, entry)` is best-effort post-call. UTC day-aligned aggregation so caps roll over deterministically regardless of server timezone. Local CLI callers (no clientId) bypass the gate. Pre-v0.36 brains without the table fail open to spend=0. `VOYAGE_MULTIMODAL_3_PER_IMAGE_CENTS` = 0.12 cents per image embed.
-- `src/core/search/llm-intent.ts` (v0.36 Commit 4) — opt-in LLM tie-break. `classifyModalityWithLLM(query, fallback)` routes through `gateway.chat()` with a fixed single-word-output system prompt. 1s timeout via AbortController. `parseModality(raw, fallback)` is the pure parser — tolerates trailing punctuation + casing. Fail-open on every error (gateway unavailable, timeout, parse failure, unrecognized output) — returns fallback so a misbehaving LLM can never break search. Cost-bounded by the ambiguity heuristic in `query-intent.ts` (fires <1% of queries when on).
-- `src/commands/reindex-multimodal.ts` (v0.36 Phase 3) — `gbrain reindex --multimodal [--limit N] [--dry-run] [--cost-estimate] [--no-embed] [--yes] [--json]`. Walks `content_chunks WHERE embedding_multimodal IS NULL`, batches via `embedMultimodalSafe` (Commit 0 partial-failure-aware), persists. D7 lock acquisition via `tryAcquireDbLock('gbrain-reindex-multimodal', 360min)`. Cost prompt + 10s Ctrl-C grace window in TTY. `GBRAIN_NO_REEMBED=1` bypass. Checkpoint at `~/.gbrain/reindex-multimodal-checkpoint.json` for resume. D23-#2 auto-flip prompt at coverage=100% completion (TTY: interactive; non-TTY: stderr hint with paste-ready command).
-- `src/core/backfill-registry.ts` extension (v0.36) — new `modality` backfill kind. SQL filter requires `chunk_source='image_asset'` AND `embedding_image IS NOT NULL` AND `(modality IS NULL OR modality != 'image')`. D22-7 defensive guard: never flag a non-image chunk that happens to have `embedding_image` populated. Idempotent — second run finds zero rows.
-- `src/core/migrate.ts` v74 (`mcp_spend_log`) + v75 (`embedding_multimodal_column`) — Phase 2 spend-log table + Phase 3 unified column ALTER. v75 is column-only (no HNSW index — deferred to post-reindex per pgvector best practice). v74 uses BTREE on `(client_id, created_at)` + `(token_name, created_at)` — `date_trunc('day', TIMESTAMPTZ)` is NOT IMMUTABLE so can't appear in index expressions; range scan on created_at covers the per-day rollup query.
-- `src/core/operations.ts` — `get_brain_identity` op (read scope, no params,
-  banner-only): cheap counter packet `{version, engine, page_count,
-  chunk_count, last_sync_iso}` for the thin-client identity banner. Reuses
-  `engine.getStats()`; banner's 60s client-side TTL bounds frequency to
-  ≤1/60s per CLI process (well below the Fly.io health-check cadence that
-  motivated the original `getStats` cost warning).
-- `src/commands/{salience,anomalies,graph-query,think}.ts` — Per-command
-  thin-client routing branches. These commands bypass the operation-layer
-  dispatch in cli.ts (call `engine.foo()` directly), so each gets its own
-  `if (isThinClient(cfg)) { callRemoteTool(...) }` branch that maps CLI flags
-  to op params. `think` is a special case: the server's `think` op
-  intentionally disables `--save`/`--take` for remote callers
-  (operations.ts:1103-1135 trust-boundary gate); thin-client `think` warns
-  loudly when those flags are set.

docs/architecture/topologies.md

@@ -398,6 +398,3 @@ simultaneously — that's by design.
   vs sources axes).
 - `docs/mcp/CLAUDE_DESKTOP.md` and siblings — per-client MCP setup.
 - `gbrain init --help` and `gbrain auth --help` for command-level details.
-- [`docs/tutorials/`](../tutorials/) — end-to-end walkthroughs that combine
-  these topologies into working setups (company brain, personal brain,
-  agent integration, etc.).

docs/architecture/type-taxonomy.md

@@ -1,177 +0,0 @@
-# Type Taxonomy (v0.41.22: gbrain-base-v2)
-
-> The 14-canonical-type DRY/MECE taxonomy shipped in v0.41.22. Predecessor
-> `gbrain-base` (24 types) stays bundled for back-compat; v0.42+ installs
-> default to `gbrain-base-v2`.
-
-## Why
-
-A production gbrain brain (186K pages) had accreted **94 distinct
-`pages.type` values** in 9 clusters of redundancy. The type system is
-the foundation for schema packs, search filtering, extract behavior,
-enrichment routing, and expert routing. When types are noisy, every
-downstream feature degrades:
-
-- **Search filtering is ambiguous** — `--type article` misses 2.2K
-  articles typed as `media/article`, `sources/article`, etc.
-- **Enrichment routing is incomplete** — `enrichable_types` could only
-  list a few canonical types; 80+ legacy types meant most pages never
-  got enriched.
-- **Agent confusion** — when ingesting a new article, should it be
-  `article`, `media/article`, `sources/article`, or `source/article`?
-  Four reasonable choices, none of them right.
-- **Orphan inflation** — 5,521 concept-redirect pages inflated orphan
-  counts without adding knowledge value.
-
-Issue #1479 catalogues the 9 clusters with exact counts. This doc is
-the response: a coherent 14-type taxonomy with subtypes/format/origin
-pushed to frontmatter, alias-table rows for redirects, real link-table
-rows for edge-shaped pages.
-
-## The 14 canonical types (+ `note` catch-all)
-
-| Type | Primitive | What it holds | Examples |
-|------|-----------|---------------|----------|
-| `person` | entity | People | Founders, partners, individuals |
-| `company` | entity | Companies, products, orgs (subtype-distinguished) | Companies, YC-companies, products |
-| `media` | media | Articles, videos, essays, books, podcasts (subtype-distinguished) | Substack posts, YouTube videos, books |
-| `tweet` | media | Twitter posts (single/bundle/stub subtype) | Single tweets, threads, bundles |
-| `social-digest` | temporal | Period-grouped social summaries (daily/monthly) | X account daily digests |
-| `analysis` | media | Research + competitive intel | Market analysis, pricing analysis |
-| `atom` | annotation | Knowledge units (extraction/manual/lore subtype) | Extracted facts, manual notes, lore |
-| `concept` | concept | Ideas + reference pages | Wiki concepts |
-| `source` | media | Transcripts, references | Interview transcripts |
-| `deal` | temporal | Investment deals | Term sheets, investments |
-| `email` | temporal | Email threads | Email correspondence |
-| `slack` | temporal | Slack messages + threads | Slack conversations |
-| `writing` | media | Original writing | Drafts, essays in progress |
-| `project` | concept | Initiatives, workstreams | Internal projects |
-| `note` | concept | **Catch-all** for one-offs (legacy_type preserved) | Memos, anecdotes, insights, etc. |
-
-15 types total (14 canonical + `note`). The catch-all retype rule
-binds any uncovered legacy type to `note` with
-`frontmatter.legacy_type = <original>` preserved for rollback.
-
-## Subtypes (declared in frontmatter post-unify)
-
-| Canonical | Subtype field | Values |
-|-----------|---------------|--------|
-| `company` | `subtype` | `company` / `product` / `org` |
-| `media` | `subtype` | `video` / `article` / `essay` / `book` / `podcast` / `blog` |
-| `tweet` | `subtype` | `single` / `bundle` / `stub` |
-| `social-digest` | `subtype` | `daily` / `monthly` |
-| `atom` | `subtype` | `extraction` / `manual` / `lore` |
-
-`subtype_field` for retype rules is restricted to an allowlist:
-`{subtype, legacy_type, origin, format, kind, period, domain}`. This
-prevents third-party packs from injecting `title`, `slug`, or `type`
-via mapping_rules (codex D9 security hardening).
-
-## Migration flow
-
-```
-gbrain onboard --check                         # surfaces pack_upgrade_available
-        ↓
-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"}'
-        ↓
-Handler runs 4 phases:
-  ┌─────────────────────────────────────┐
-  │ Phase 1: Preflight + lock           │ → gbrain-unify db-lock (60min TTL)
-  ├─────────────────────────────────────┤
-  │ Phase 2: Retype explicit rules      │ → chunked UPDATE 1000/batch
-  ├─────────────────────────────────────┤
-  │ Phase 3: Retype catch-all sentinel  │ → 'note' with legacy_type
-  ├─────────────────────────────────────┤
-  │ Phase 4: Page-to-link conversions   │ → insert links + soft-delete
-  ├─────────────────────────────────────┤
-  │ Phase 5: Page-to-alias conversions  │ → insert slug_aliases + soft-delete
-  ├─────────────────────────────────────┤
-  │ Phase 6: Final sync (residual)      │ → path-prefix typing
-  ├─────────────────────────────────────┤
-  │ Phase 7: Flip active pack (D13)     │ → engine.setConfig + saveConfig
-  ├─────────────────────────────────────┤
-  │ Phase 8: Verify + celebrate         │ → assert ≤16 types; stderr summary
-  └─────────────────────────────────────┘
-        ↓
-gbrain onboard --check                         # pack_upgrade_available cleared
-                                               # type_proliferation cleared
-```
-
-## Rollback paths
-
-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). |
-| Active-pack flip | `gbrain schema use gbrain-base` reverses the flip. |
-
-## What if my brain doesn't fit?
-
-The catch-all retype rule (`from_type: '*unknown*'`) handles long-tail
-types automatically — any page whose type isn't covered by an explicit
-rule AND isn't a page_to_link / page_to_alias source gets retyped to
-`note` with `legacy_type` preserved. Guarantees ≤16 distinct types
-post-unify on ANY brain.
-
-For brains with substantial custom types that deserve their own canonical
-(e.g. `researcher` for an academic brain), the right move is:
-
-1. Fork gbrain-base-v2: `gbrain schema fork gbrain-base-v2 my-pack`
-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"}'`
-
-Your fork can also declare `migration_from: {pack: gbrain-base-v2,
-version: "1.x"}` to register itself as a successor — future agents
-discovering your pack via `pack_upgrade_available` will offer the
-migration.
-
-## Wikilink resolution post-unify
-
-The slug_aliases table IS the resolver (D15: codex outside voice —
-don't rewrite body-text wikilinks; the alias table is the right
-primitive). Wikilinks like `[[old-redirect-slug]]` keep working post-
-unify because:
-
-1. The wikilink resolver short-circuits through
-   `engine.resolveSlugWithAlias(slug, sourceId)` BEFORE the existing
-   fuzzy/prefix cascade.
-2. The lookup queries `slug_aliases` for any matching alias_slug in
-   the provided source(s).
-3. If found, returns the canonical_slug. The renderer then resolves
-   the wikilink to the canonical page.
-
-Multi-source ambiguity (same alias_slug in two registered sources)
-emits a once-per-process `multi_match` stderr warning and returns the
-first match by source array order. Federated reads pass the full
-allowed-source array.
-
-## Search ranking signal: alias_resolved_boost
-
-Post-unify, search results whose slug is a canonical_slug in
-slug_aliases get a 1.05x score multiplier via the
-`applyAliasResolvedBoost` post-fusion stage. Semantic intent: "user
-explicitly disambiguated this as canonical, so it should outrank fuzzy
-matches that hit aliases by accident."
-
-`SearchResult.alias_resolved_boost` is stamped on touched results for
-`--explain` formatter visibility. KNOBS_HASH_VERSION bumped 5→6 to
-invalidate pre-v0.42 cache rows that don't reflect the new stage.
-
-## Reference
-
-- Issue: https://github.com/garrytan/gbrain/issues/1479
-- Pack file: `src/core/schema-pack/base/gbrain-base-v2.yaml`
-- Pack-upgrade mechanism: `docs/architecture/pack-upgrade-mechanism.md`
-- Migration handler: `src/core/schema-pack/unify-types-handler.ts`
-- Onboard checks: `src/core/onboard/checks.ts`
-- Skill: `skills/schema-unify/SKILL.md`
-- Plan + decisions: `~/.claude/plans/system-instruction-you-are-working-transient-elephant.md`

docs/designs/COMMUNITY_IDEAS.md

@@ -1,367 +0,0 @@
-# Community Ideas Ledger
-
-> A diary of the **valuable ideas** surfaced by the community-PR wave, kept so that
-> good thinking survives even when the PR that carried it is closed. gbrain moves
-> fast and the maintainer's "cathedral" rewrites supersede most individual PRs —
-> but the *idea* behind a closed PR is often still worth something.
->
-> **Bar for this file:** an idea only earns a line if it is (a) still live on
-> master and (b) genuinely valuable to gbrain users. **Graduating an idea to
-> `TODOS.md` is a higher bar still** — it must serve the North Star (next-Postgres-
-> for-memory: widest coverage, best-for-the-most-at-the-least) and be worth a
-> maintainer-owned implementation. Most lines here will never graduate. That's fine.
->
-> Status legend: **OPEN** = PR still open as a real merge candidate · **CLOSED** =
-> PR closed, idea captured here · **HELD** = strategic, awaiting maintainer call.
-> Provenance is credited to the contributor; scrub real private-network names per
-> the repo privacy rule when anything here graduates to a public artifact.
-
-_Generated from a full triage of the open-PR backlog (436 community PRs), 2026-06-07._
-
----
-
-## 1. Internationalization — non-English brains are second-class
-
-The single biggest coverage gap for "serve a billion people." Several independent
-contributors hit the same walls.
-
-- **Configurable FTS language** (#580/#581/#582, @rafaelreis-r) — **OPEN, high.**
-  Every `to_tsvector`/`tsquery` is hardcoded `'english'` (query side, trigger side,
-  and no reindex path), so non-English brains run every search through the English
-  stemmer. A coherent 3-PR set: `GBRAIN_FTS_LANGUAGE` config → migration recreating
-  triggers with the chosen language → `gbrain reindex-search-vector` to change it
-  post-install. **Strongest i18n candidate to graduate.**
-- **Full-Unicode slugs** (#782, @tamagodo-fu; #514 zh, @JimmyJiang67) — **HELD, high.**
-  CJK slugs already work (`CJK_SLUG_CHARS`); generalize to all scripts (Cyrillic,
-  Devanagari, Hangul, …) and widen the remaining ASCII-only validators so non-ASCII
-  slugs flow end-to-end instead of being generated then rejected. #514 also carries a
-  corpus-driven `relationships-zh.json` verb dictionary for `inferLinkType` — a
-  reusable artifact for Chinese relationship typing.
-- **CJK entity extraction** (#1637, @alkalide) — **OPEN, high.** Mention extraction is
-  ASCII-only (`TOKEN_RE`, `MIN_NAME_LENGTH=4`), so 2–3 char Chinese/Japanese/Korean
-  names are invisible to the gazetteer (there's an in-code TODO acknowledging it).
-  CJK detection + lower min-length + single-token pure-CJK titles + substring pass.
-
-## 2. Reliability — the daily-driver failure modes
-
-Recurring, production-observed failures. Many are tiny fixes with outsized impact;
-these are the densest source of real bugs in the whole backlog.
-
-- **Embedding egress waste** (#347/#460, @notjbg) — **OPEN, high.** `getChunks` does
-  `SELECT cc.*`, shipping the ~6KB pgvector embedding that `rowToChunk` immediately
-  discards — ~19–22 GB/day egress on a busy Supabase brain. Enumerate the columns;
-  add a CI guard. (#460 dup of #347.)
-- **Body-keyed embedding reuse** (#1424, @defenestrate2) — **OPEN, high.** Markdown
-  import re-embeds byte-identical chunks that merely shifted position, turning a
-  cosmetic edit into ~99K wasted re-embeds. Reuse by chunk-text hash like the code
-  path already does; add `--force` + a no-hash sentinel.
-- **`embed --stale` full re-pull** (#775, @kyledeanjackson) — **CLOSED (partial on
-  master), high.** Re-pulled all chunks every cycle (~3TB/mo egress); steady-state
-  brains should do near-zero work. Master added a `countStaleChunks` early-exit;
-  verify it fully closes this.
-- **Config round-trip storm** (#1694, @Omerbahari) — **OPEN, high.** A single query
-  fires ~85 serial single-key config `SELECT`s — invisible on PGLite, ~85 network
-  RTTs on a remote pooler. Batch + cache `getConfig` (`getConfigMany`).
-- **cgroup-aware worker sizing** (#1244, @tyler3k1) — **OPEN, high.** `defaultWorkers()`
-  sizes from `os.totalmem()` (host RAM), so containerized installs (Railway/Fly/Render/
-  Cloud Run/ECS) oversize the pool and get OOM-killed mid-import. Use
-  `process.constrainedMemory()`.
-- **Linux memory-pressure throttle** (#556, @chengzehsu) — **OPEN, high.** `os.freemem()`
-  is `MemFree` (excludes reclaimable cache), so healthy containers reject every batch
-  job. Read `MemAvailable` from `/proc/meminfo`.
-- **propose_takes never caches empties** (#1218 @AdityaRajeshGadgil / #1760 @notjbg) —
-  **OPEN, high.** A valid `[]` extractor result writes no cache row, so unchanged pages
-  re-spend extractor tokens every ~5min cycle (57,885 calls/11 days observed). Sentinel
-  row keyed on `(source_id, page_slug, content_hash, prompt_version)`.
-- **Prompt-cache opt-in on hot paths** (#1761, @notjbg) — **OPEN, high.** Only ~4.9% of
-  input tokens hit the Anthropic prompt cache because the highest-volume cycle/extraction
-  call sites don't set `cacheSystem:true` despite gateway support. One-line opt-ins.
-- **Autopilot reliability cluster** (#232 @ianderse, #464/#465 @notjbg, #289 @RyanAlberts,
-  #477 @vinsew, #1935/#1936 @mdcruz88, #1906/#1891 @rayers/@jalagrange) — **OPEN, high.**
-  A family of distinct live bugs: argless `engine.connect()` wipes saved config and
-  crash-loops under launchd; `cwd=/` wrappers miss `brain/.env`; mtime-only lock probing
-  blocks respawn for 10min after OOM; no backoff on the 5-failure suicide cap;
-  disconnect-before-connect `reconnect()` bricks the engine on a transient blip; config
-  accessors lack the retry wrapper. **Pick the best fix per layer and land as a wave.**
-- **lint `--fix` corrupts mid-doc fences** (#1417 @trinh-macbook, #1597 @chungty) —
-  **OPEN, high.** Detector/fixer regex disagree, so `lint --fix` strips the closing fence
-  of mid-document ```` ```markdown ```` blocks and autopilot re-corrupts the page every
-  cycle. Only unwrap whole-page fences.
-- **backlinks worker defaults to `fix`** (#1853 @choomz; #1027 @sliday; #495 @23salus) —
-  **OPEN, high.** Empty-payload backlinks jobs default to `action='fix'`, silently
-  rewriting tracked markdown ("Referenced in" bullets) on every sync→embed→backlinks
-  chain (129 files/day in the wild). Default to `check`; require explicit opt-in. Also
-  fixes a duplicate-line accumulation bug.
-- **`DATABASE_URL` hijack** (#1884, @awilkinson) — **OPEN, high.** A co-located app's
-  generic `DATABASE_URL` silently overrides the configured brain (wrong DB, or
-  auto-migrates it). Fix precedence: `GBRAIN_DATABASE_URL` > config.json > `DATABASE_URL`.
-- **Engine-switch strips config** (#1088, @samchaudhary) — **OPEN, high.** `migrate --to`
-  rewrites config to just `{engine,url}`, dropping `embedding_model`/`dimensions`/keys;
-  migration "succeeds" but new embeds break.
-- **Re-init silently corrupts the brain** (#1060, @vincedk-alt) — **OPEN, high.** Flag-less
-  re-init ignores persisted `embedding_model`/`dimensions` and writes a wrong-shape
-  OpenAI-1536 brain before the dim-check catches it.
-- **IPv6-only direct URL** (#1006, @diazMelgarejo) — **OPEN, high.** `deriveDirectUrl`
-  turns a Session-Pooler URL into an IPv6-only host, ECONNREFUSED on IPv4-only networks
-  (the majority). Return null for pooler URLs.
-- **HOME-isolation in tests** (#205/#517/#534 @orendi84, #434 @lloydarmbrust) — **OPEN,
-  high.** The E2E suite spawns `gbrain init/import` against the developer's real
-  `~/.gbrain/config.json`, clobbering their live DB URL+keys. Isolate HOME to a tmpdir.
-  *(A footgun that bites contributors of this very repo.)*
-- **dim-aware embed write target** (#1263, @DmitryBMsk) — **OPEN, high.** `upsertChunks`
-  always writes the legacy `embedding vector(1536)` column, so brains on an alternate
-  column (`embedding_ze halfvec(2560)`) fail with dim-mismatch on every write.
-- **Oversized chunks silently unembedded** (#1675, @lubos-buracinsky) — **OPEN, high.**
-  The code chunker emits giant literals/template strings whole; the embedder rejects
-  them and they vanish from semantic search. Cap chunk size so they stay embeddable.
-- **Token-vs-char truncation** (#557 @chengzehsu, #990 @mgunnin, #1180 @kkroo,
-  #1281 @mmekkaoui, #1947 @100menotu001) — **OPEN, high.** The embed path truncates by
-  chars (`MAX_CHARS`) not tokens, so dense pages still exceed the 8192/300K-token ceiling
-  and loop forever on HTTP 400 with `embedded_at` never cleared; `isTokenLimitError`
-  misses OpenAI's real error string; llama-server's 32-input limit isn't capped; and
-  `--catch-up`'s unbounded budget overflows the 32-bit `setTimeout` and aborts after one
-  batch. A "make embedding backfills never silently wedge" cluster.
-
-## 3. Search & retrieval quality
-
-- **Keyword search ignores page titles** (#1646, @jeades) — **OPEN, high.** `searchKeyword`
-  ranks only chunk `search_vector`, never `pages.search_vector` (weight-A titles), so an
-  exact-title `gbrain search` returns nothing while `query` finds it. High-impact, tiny.
-- **`code-def` misses most OO symbols** (#1628, @rayers) — **OPEN, high.** `DEF_TYPES`
-  omits method/constructor/field/struct/protocol, so `code-def` returns 0 for most
-  object-oriented code. Root-cause fix in `normalizeSymbolType` + `DEF_TYPES`.
-  (Prefer over #1701's fallback-only approach.)
-- **doc-comment column is wired but dead** (#520, @Evode-Manirahari) — **OPEN, high.** FTS
-  weights `content_chunks.doc_comment` above chunk text but the column is never populated.
-  Extract JSDoc/docstrings per symbol via AST and thread through import.
-- **autocut weak-top collapse** (#1863, @rayers) — **OPEN, high.** The fresh autocut
-  feature (#1682) normalizes the rerank gap by the top score, so a weak top (0.317→1.0)
-  looks like a confident cliff and rare cross-source queries collapse to 1 result. Add a
-  `minTopScore` floor.
-- **Graph-hop wikilink rerank** (#717, @gwanghoon91) — **HELD, high.** Zero-token
-  score-shapers (graph-hop wikilink rerank + query-token disambiguation) claimed
-  +2.6/+2.8pt P@5/R@5 on BrainBench. Worth re-evaluating against the new retrieval
-  cathedral's ranker rather than merging the old diff.
-- **Effective-date time filters** (#1706, @mvanhorn) — **OPEN, med.** `since`/`until`
-  filter on `updated_at`, so content dated to the past but edited recently is mis-filtered;
-  filter on `COALESCE(effective_date, updated_at, created_at)`.
-
-## 4. Extraction & the knowledge graph
-
-- **Obsidian wikilink → typed graph edges** (#87 @franmaranchello; alias/title/basename
-  fallback #1188 @rwbaker) — **OPEN/HELD, high.** `[[wikilinks]]`/`![[embeds]]` are
-  invisible to the graph. Materialize them as typed edges with alias (frontmatter
-  `aliases:`), first-H1-title, and basename fallback resolution (path-equality-only gives
-  ~5.5% edge recall on real vaults). Master shipped global-basename (#1388); the alias/
-  title fallbacks are the still-novel part.
-- **Schema-pack-aware link extraction** (#1547, @billy-armstrong) — **OPEN, high.** The
-  link extractor's `DIR_PATTERN` is a frozen 16-prefix const that ignores pack-declared
-  `path_prefixes`, so default-pack installs silently lose wikilinks to `person/`,
-  `writing/`, `wiki/*`. Resolve prefixes from the active pack.
-- **DB-source extraction** (#1539, @afshaker) — **OPEN, high.** The cycle's extract phase
-  only walks the filesystem, so DB-resident pages (imported transcripts, remote-DB brains)
-  never get links/timeline and `brain_score` is capped. Thread `source:'db'`.
-- **source_id threaded through fs-walk extract** (#1719, @seungsu-kr) — **OPEN, high.**
-  fs-walk extractors omit `source_id`, defaulting to `'default'`, so the `pages` INNER JOIN
-  drops every row on non-default-source brains — silent 0 inserted.
-- **extract `--stale` permanent-lag loop** (#1791, @Nazim22) — **OPEN, high.** Pages last
-  edited before the link-extractor version bump get stamped below the version threshold and
-  re-flag every run (~97% pages permanently "stale"). Stamp `GREATEST(updated_at, versionTs)`.
-- **Plain-text NER for auto-link** (#1565, @donogeme) — **HELD, med.** Plain mentions of
-  people (no `[[wikilink]]`) never become edges. The opt-in idea is right; the shipped
-  implementation (capitalized-bigram regex, Western-names-only) is too crude — needs a
-  real NER pass to clear the graph-integrity bar.
-
-## 5. Providers & the gateway
-
-The AI-gateway + recipes + `user_provided_models` system already absorbed ~40
-per-vendor embedding PRs (Ollama, Gemini, Azure, DashScope, DeepSeek, Zhipu, E5,
-bge-m3, Copilot, Composio, Kimi, LM Studio, Mistral, Hunyuan, MiniMax…). The
-*residue* worth keeping:
-
-- **litellm proxy unusable for chat** (#1953 @miroslavb, #1938 @BKF-Gitty) — **OPEN, high.**
-  The `litellm-proxy` recipe declares only an embedding touchpoint (no chat), so
-  `chat_model=litellm:*` fails validation and `think` degrades to a misleading "set
-  ANTHROPIC_API_KEY"; and `build-gateway-config` never folds `litellm/openrouter/together`
-  keys, so configured proxy auth goes out unauthenticated. Plus user-provided custom-dim
-  embeddings are double-false-rejected in preflight. **The general-OpenAI-compat-proxy
-  story.**
-- **Matryoshka dims threading** (#1072 @mgandal, #1240 @mike7seven) — **OPEN, high.**
-  Qwen3-Embedding returns its native dim (2560/4096) not the requested one because
-  `dimensions:N` isn't threaded for the openai-compat path, hard-failing a 1536-dim brain.
-- **"Freeze provider at init, clear vectors on dim change"** (#100/#172, @niallobrien/
-  @nbzy1995) — **CLOSED, med.** A safety insight worth keeping even though the provider
-  PRs are superseded: persist+freeze the brain's provider/dim at init so a later env change
-  can't silently corrupt the vector space; clear stale embeddings on an intentional change.
-- **China-region provider coverage** (#59 @Magicray1217, #1071 @AzeWZ) — **CLOSED, med.**
-  Make DashScope/DeepSeek/Zhipu first-class recipes that honor `provider_base_urls` (the
-  China-region endpoints) and provider batch limits — on-mission for global coverage.
-- **Amazon Bedrock native** (#1826, @naterchrdsn) / **Jina asymmetric retrieval**
-  (#1930, @Whamp) — **HELD, high/med.** The maintainer pattern prefers the universal
-  litellm-proxy over per-vendor native recipes, but Bedrock (AWS IAM credential chain) and
-  Jina's asymmetric `input_type=document|query` are distinct enough to warrant a call.
-- **Local-first chat parity** (#1854/#1855/#1858 @starm2010, #1423 @pabloglzg,
-  #1618 @punksterlabs) — **OPEN, high.** `FREE_LOCAL_CHAT_PROVIDERS` doesn't exist (only
-  embed), brainstorm/cycle/takes hardcode `anthropic:claude-sonnet-4-6`, and the
-  openai-compat `generateObject` path silently fails on providers that reject
-  `json_schema`. The "run gbrain fully local" cluster.
-- **OpenRouter config key** (#1714 @tmchow), **OAuth bearer for AI providers**
-  (#1312 @pabloglzg), **API-key files** (#570 @shawnduggan) — **OPEN, med.** Credential
-  ergonomics: config-file key (not just env), externally-minted bearer tokens, and
-  `OPENAI_API_KEY_FILE` so OAuth harnesses don't inherit a raw key in `process.env`.
-
-## 6. Auth, federation & access control (security-adjacent)
-
-These cluster into a real theme: **runtime access control for remote/multi-tenant MCP
-beyond prompt discipline.** Several are live security gaps (see the security list in the
-triage report) and should be treated as a coordinated design, not piecemeal merges.
-
-- **Clamp remote source overrides** (#1372, @jlfetter1) — **OPEN, high, SECURITY.** A
-  remote MCP caller can pass `source_id` (or `__all__`) to `query`/`get_page` to read
-  sources outside their OAuth `allowedSources` — the param bypasses `sourceScopeOpts`
-  (CWE-285). Clamp to token claims, fail-closed. **#1394 (get_page source_id) must land
-  *with* this clamp, not before it.**
-- **Read-side prefix/federation enforcement** (#1860 @choomz, #1790 @colin-atlas,
-  #470 @AdityaRajeshGadgil, #1508 @tim404x) — **OPEN, high.** `bound_slug_prefixes` is
-  enforced on write but not read; exact `get_page` uses scalar `ctx.sourceId` while fuzzy
-  uses the federation ladder; unqualified search can scan isolated `--no-federated` sources.
-  Unify on one fail-closed visibility predicate across every read surface.
-- **Per-OIDC-user access tiers** (#789, @0x471) — **HELD, high, SECURITY.** Map verified
-  OIDC end-users to `oauth_clients.access_tier` dispatch gates + shape filters — real
-  runtime access control. Pairs with multi-agent MCP hardening (#1316, @chipoto69, HELD).
-- **Federated-read management CLI + admin UI** (#1592/#1601 @bitak1, #1558 @flamerged) —
-  **OPEN, high.** No CLI/UI to inspect or change a client's `federated_read` scope (raw
-  SQL only today). Atomic `array_append`/`array_remove` SQL to avoid read-modify-write
-  races, plus an admin Sources tab.
-- **Pre-registration flow flags** (#894, @panda850819) — **OPEN, high, SECURITY.**
-  `register-client` hardcodes `redirect_uris=[]`, making the SECURITY.md-recommended
-  pre-registration (DCR-off) flow unusable for Claude.ai/ChatGPT connectors.
-- **RFC 9728 `resource_metadata`** (#1410, @rayers) — **OPEN, high.** HTTP MCP 401s omit
-  the `resource_metadata` param the MCP auth spec + RFC 9728 require, so claude.ai/Cursor
-  can't discover the auth server and never start OAuth.
-- **Server-enforced memory groups** (#1497, @oldmate99) — **HELD, med.** Audience-based
-  read/write via `memory_groups` + client-to-group assignment — strategic for hosted
-  multi-tenant, but overlaps the existing source-isolation model; a design call.
-
-## 7. Security hardening (must not be lost)
-
-- **Command injection in transcription** (#245, @aliceagent) — **OPEN, high, SECURITY.**
-  `transcription.ts` shell-interpolates an agent-controlled `audioPath` into `execSync`
-  ffprobe/ffmpeg/`rm -rf`. **Confirmed still present on master.** Switch to
-  `execFileSync` arg arrays + `fs.rmSync`.
-- **Dotfile / skills-dir confinement** (#418/#419, @garagon) — **OPEN, high, SECURITY.**
-  `.gbrain-source` walk-up trusts any ancestor dotfile (source hijack on shared hosts);
-  `resolveWorkspaceSkillsDir` never canonicalizes (symlink escape). `lstat` ownership/
-  symlink/world-writable checks + realpath containment.
-- **Destructive reclone gate** (#1705, @mvanhorn) — **OPEN, high, SECURITY.**
-  `recloneIfMissing` does `rm`+rename over `src.local_path` without verifying it's
-  gbrain-managed, so a re-pointed source can wipe a user's working tree. Gate behind
-  `isManagedRecloneTarget()` + reject `..`. *(The maintainer's own #1960 is the canonical
-  landing for this class — cross-check.)*
-- **CORS preflight asymmetry** (#983, @yashkot007) — **OPEN, high, SECURITY.** Preflight
-  returns the full method/header surface unconditionally while the actual-request path
-  gates on the allowlist — leaks allowed surface to non-allowlisted origins.
-- **jsonb double-encode corruption** (#1584 @warkcod, #597 @vinsew) — **OPEN, high,
-  SECURITY/integrity.** Source-config and subagent writers `JSON.stringify` into a
-  `::jsonb` cast — the exact postgres.js trap CLAUDE.md forbids; corrupts source config
-  (freshness/autopilot) and breaks dream synthesize slug-collection on real Postgres.
-
-## 8. Developer experience & platform reach
-
-- **Windows / CRLF portability** (#1294 @xwang4-svg, #1149 @samporter-31, #1554 @Sanjays2402,
-  #1396 @xuezhaolan) — **OPEN, high.** CRLF breaks frontmatter + skill-trigger parsing
-  (CI is Ubuntu-only so it never surfaces), `/dev/stdin` doesn't exist, a POSIX postinstall
-  one-liner hard-fails `bun install`, backslash bundle keys. A coordinated "first-class
-  Windows" pass. *(A working Windows binary + CI target #180/#181 is the prerequisite for
-  the full story.)*
-- **`.gbrainignore` / per-repo exclusion** (#1483 @eepaul; repo-local code filters
-  #1011 @AndrewLauder; `--respect-gitignore` #1159 @jetsetterfl) — **OPEN, high.** Sync
-  indexes every file with no ignore mechanism (`data/`, `*.parquet`, fixtures, vendored
-  trees), bloating DB + embedding cost. gitignore-parity `.gbrainignore` + per-source
-  `excludePatterns`. *(See also the maintainer's walker-prune work; #1942 prunes
-  vendor/dist/build.)*
-- **Monorepo sub-path sources** (#774, @jeremyknows) — **HELD, high.** `--src-subpath`
-  (split repo into git-root + logical-source axes) + `--exclude` so one repo can hold N
-  sources at subdirs.
-- **MCP tool filtering** (#747, @joelwp) — **OPEN, high.** MCP advertises all ~51 ops to
-  every consumer (~10K tokens of schemas, tool confusion); `GBRAIN_EXPOSED_TOOLS` filters
-  the advertised surface.
-- **Install-method detection for upgrade** (#538, @brucek) — **OPEN, high.** The README's
-  own recommended git-clone+bun-link install detects as `unknown`, so `gbrain upgrade`
-  offers three dead ends including a wrong npm package.
-- **Runtime subagent defs** (#1282, @dcarolan1) — **OPEN, high.** The plugin loader
-  validates `SubagentDefinition[]` at startup but the handler never reads
-  `data.subagent_def`, so the persisted field is dead at runtime — callers must re-embed
-  the full system body in every job.
-- **macOS Tahoe PGLite workaround** (#1671, @roysaurav) — **HELD, med.** PGLite's WASM
-  engine crashes on macOS 26 (Apple Silicon); document the native Homebrew Postgres+pgvector
-  fallback. Reader-valuable until the WASM crash is fixed upstream.
-
-## 9. Capabilities & integrations (strategic — maintainer call)
-
-These are net-new surfaces held for a product decision, not auto-closed.
-
-- **Alternative engines** — SQLite/`bun:sqlite`+FTS5 single-file backend (#291, @mvanhorn)
-  and Neo4j GraphBrain REST backend (#594, @pkyanam). Both conflict with the two-engine
-  lockstep invariant and the Postgres-for-memory North Star, but the *zero-WASM single-file*
-  install story (SQLite) is strategically interesting. **HELD.**
-- **Page versioning / soft-delete / read audit** (#573, @cropsgg) — **HELD, high.** Snapshots
-  with provenance, soft-delete tombstones + hard purge, read-path audit treating edits as
-  derivative works. Ambitious cathedral-scope; maintainer-owned territory.
-- **Configurable embedding dimension** (#1051, @vincedk-alt) — **HELD, high.** `schema.sql`
-  hardcodes `vector(1536)`; read `embedding_dimensions` from config (default 1536). The
-  canonical fix that dozens of local-provider PRs hack around. *(Pairs with #1263.)*
-- **Transcribe skill** (#1449, @RyanAlberts) — **OPEN, high.** Implements the empty
-  video/audio branch of `media-ingest` (YouTube captions fast path + yt-dlp/whisper
-  fallback), $0 by default. A genuine capability gap.
-- **iPhone backup importer** (#1733, @H4RR1SON) — **HELD, med.** Local-CLI-only importer
-  for decrypted iPhone backups (contacts→person pages, iMessage→conversation pages); zero
-  network, thin-client refused.
-- **Compounding dream phase** (#509, @durang) — **HELD, high.** An LLM "7th phase" that
-  *creates* structure (orphan-mention people, knowledge gaps, concept-dup at cosine>0.92,
-  decay, incomplete pages) vs the deterministic phases. Overlaps `enrich --thin`.
-- **Codex-OAuth for dream** (#977, @barronlroth) / **dream gateway + `migrate-embedding-dim`**
-  (#1013, @cxbitz) — **HELD, high.** OAuth-backed chat for synthesis; a command to resize
-  the vector schema + clear incompatible embeddings.
-- **Voice-extraction skill** (#300, @harjclaw) — **CLOSED, med.** Mine the user's outbound-
-  email corpus already in the brain to build a queryable writing-voice profile so agents
-  draft in the user's voice. Overlaps soul-audit.
-- **MCP put_page parity + DB→markdown reconciliation** (#438, @rayzhux) — **HELD, high.**
-  A frontmatter-only safe auto-link mode for remote callers + `GBRAIN_BRAIN_ROOT` to render
-  remote writes back to markdown so MCP writes reach the git source-of-truth. Touches the
-  remote trust boundary — a design proposal, not a merge.
-- **Recipe discovery convention** (#1279, @ialmeida-jera) — **OPEN, med.** `~/.gbrain/recipes/`
-  auto-discovery + `--external-dir`, loaded untrusted to keep the command-spawn boundary.
-- **Destructive-op audit trail + audit-factory** (#1069/#1070, @vincedk-alt) — **HELD, med.**
-  Rotating JSONL forensic trail for hard-deletes + a shared `createAuditLogger` factory.
-
-## 10. Doctor & brain-health observability
-
-- **Queue dead-job visibility** (#1185, @ethanbeard) — **OPEN, high.** A collector can
-  heartbeat green while all its jobs die in the worker (3561 dead in the wild) and doctor
-  has zero view into the minions queue. Add a cross-cutting `[queue]` dead-jobs check.
-- **Orphan-metric alignment** (#1107 @colin477, #915 @xaviroblessarries, #1202 @rwbaker) —
-  **OPEN, high.** `get_health` counts ingestion-by-design (`daily/`, briefings), soft-deleted,
-  and hub pages as orphans, distorting `brain_score`; CLI `find_orphans` uses a *different*
-  predicate than `getHealth`. Unify on one islanded predicate with sensible exclusions.
-- **doctor check-name registry drift** (#1839, @mvanhorn) — **OPEN, med.** Several emitted
-  checks aren't registered in `doctor-categories`, printing `unknown check name` every run;
-  the drift guard only scanned `doctor.ts`, missing `onboard/checks.ts` emitters.
-- **Honest stale-lock hint** (#1553, @Sanjays2402) — **OPEN, med.** doctor always says
-  `gbrain sync --break-lock`, which silently no-ops on `gbrain-cycle` locks.
-
----
-
-## Cross-cutting observations for the maintainer
-
-- **The same bug was filed many times.** `extract_facts.entity_hints` missing an `items`
-  schema came in ≥5 times (#812/#832/#847/#863/…, already fixed); the Postgres-singleton
-  disconnect class a dozen+ times; sync no-op freshness, slug-casing, and the embedding-
-  preflight false-reject each 5–15 times. A short "already fixed / known" note in the
-  release notes or a CONTRIBUTING "before you file" list would cut the re-file rate.
-- **The recipe system is working as a pressure valve** — it correctly absorbed ~40 vendor
-  PRs into config rather than code. The remaining provider asks are about *capabilities*
-  the recipe schema doesn't yet express (asymmetric `input_type`, Matryoshka dims, per-item
-  RPM caps, alternative credential groups), not new vendors.
-- **i18n (§1) and local-first chat (§5) are the two biggest "serve a billion" coverage
-  gaps** the community is repeatedly hitting and the best candidates to graduate to TODOs.

docs/embedding-migrations.md

@@ -10,41 +10,13 @@ change automatically.
 this mismatch and refuse to silently proceed. This doc is the recipe
 they point at.
 
-## Same-dimension model swaps (v0.41.31.0 — automatic)
-
-If you switch to a different model at the **same** dimension count
-(e.g. one 1536-dim provider to another, or a re-tuned model that keeps
-its width), the column type doesn't change, so no `ALTER`/wipe recipe
-is needed. As of v0.41.31.0, gbrain stamps an embedding-provenance
-signature (`<provider:model>:<dims>`) onto each page when its chunks are
-embedded. After you point the config at the new model, the stored
-signatures differ from the current one, and `gbrain embed --stale`
-re-embeds exactly those pages:
-
-```bash
-# After switching to the new same-dim model in your config:
-gbrain embed --stale          # re-embeds signature-drifted pages
-gbrain embed --stale --dry-run # preview the count without re-embedding
-```
-
-Under federated_v2, the same drift is picked up by the per-source
-`embed-backfill` jobs that `gbrain sync --all` enqueues (capped
-`$X/source/24h`). **Grandfather:** pages embedded before v0.41.31.0
-carry a NULL signature and are NEVER flagged stale, so upgrading to
-v0.41.31.0 does NOT trigger a whole-corpus re-embed. Signatures only
-get stamped going forward.
-
-A **dimension** change still requires the wipe-and-reinit (PGLite) or
-column-alter (Postgres) recipe below — the on-disk `vector(N)` width
-genuinely has to change.
-
 ## Why we don't do this automatically
 
 Switching dimensions requires:
 
 1. Dropping the HNSW vector index (pgvector won't survive an `ALTER COLUMN TYPE`).
-2. Wiping every existing embedding (the old vectors are unusable in the new space — and pgvector refuses to cast them across dimensions, so this must happen before the alter).
-3. Altering the column type (Postgres only — PGLite cannot do this).
+2. Altering the column type (Postgres only — PGLite cannot do this).
+3. Wiping every existing embedding (the old vectors are unusable in the new space).
 4. Re-embedding the entire corpus (can take hours on a 50K-page brain and costs $1-100 in API calls depending on model).
 5. Conditionally recreating the index (HNSW supports up to 2000 dimensions per pgvector; above that you must use exact scans).
 
@@ -115,17 +87,12 @@ BEGIN;
 -- 1. Drop the HNSW index. It can't survive the column type change.
 DROP INDEX IF EXISTS idx_chunks_embedding;
 
--- 2. Clear stale embeddings FIRST. This must happen BEFORE the column
---    alter: pgvector refuses to cast existing vectors across dimensions
---    ("expected <NEW_DIMS> dimensions, not <OLD_DIMS>"), so altering a
---    column that still holds old-width vectors aborts the transaction.
---    NULLs cast fine. (The old vectors are unusable in the new space
---    anyway — this is the wipe step from the rationale above.)
-UPDATE content_chunks SET embedding = NULL, embedded_at = NULL;
-
--- 3. Alter the column type (all rows are NULL now, so the cast succeeds).
+-- 2. Alter the column type.
 ALTER TABLE content_chunks ALTER COLUMN embedding TYPE vector(<NEW_DIMS>);
 
+-- 3. Clear stale embeddings so they don't survive into the new space.
+UPDATE content_chunks SET embedding = NULL, embedded_at = NULL;
+
 -- 4. Recreate the HNSW index ONLY IF dims <= 2000. Above that, leave it
 --    indexless and rely on exact scans (gbrain searchVector handles this
 --    automatically — search just gets slower, not broken).

docs/ethos/ORIGIN.md

@@ -25,5 +25,3 @@ None of those are novel ideas. The contribution is shipping all of them together
 The production brain has been running for months now. 17,888 pages. 4,383 people. 723 companies. 21 cron jobs running autonomously. It wakes Garry up smarter than the day before.
 
 GBrain is what happens when you write the brain you actually wanted to have.
-
-The reason the brain is worth building is `gbrain think`. Without it, the brain is just a place that holds your notes. With it, the brain is a thing you can query about itself: what does it know, what does it not know yet, where does it contradict itself, where are the holes. The 24/7 cron cycle keeps the brain sharp. `think` is what makes a sharp brain useful.

docs/eval-bench.md

@@ -8,112 +8,6 @@ For the **NDJSON wire format** consumed by gbrain-evals, see
 [`eval-capture.md`](./eval-capture.md). This doc is the human dev loop
 that lives on top of that format.
 
-## v0.41 update — the LOOP is now real
-
-Before v0.41, you could capture eval rows and replay them but nothing
-stitched them into a gate. `gbrain bench publish` + `gbrain eval gate`
-close the loop. Two gates:
-
-- **Regression gate** (`--baseline X.baseline.ndjson`): replays a baseline
-  you captured against your current brain. Catches: "did my refactor break
-  search?" Compares jaccard / top-1 stability / latency multiplier.
-- **Correctness gate** (`--qrels Y.qrels.json`): runs known-right queries
-  against your current brain via bare `hybridSearch`. Catches: "is my
-  retrieval actually any good?" Computes recall@K, first-relevant-hit-rate,
-  expected_top1-hit-rate.
-
-Both can be passed together; both must pass for verdict `pass`. At least
-one is required.
-
-### The full LOOP for your own brain
-
-```bash
-# 1. Capture (one-time; uses queries already in eval_candidates)
-gbrain eval export --limit 200 --tool query > /tmp/captured.ndjson
-
-# 2. Publish a baseline
-mkdir -p ~/.gbrain/baselines
-gbrain bench publish --from /tmp/captured.ndjson --to ~/.gbrain/baselines/personal.baseline.ndjson --label "personal-$(date +%Y%m%d)"
-
-# 3. Gate against it
-gbrain eval gate --baseline ~/.gbrain/baselines/personal.baseline.ndjson
-```
-
-### Privacy posture (D9)
-
-**Public baselines in `gbrain-evals` are hermetic-synthetic ONLY.** Real
-user captures stay local in `~/.gbrain/baselines/`. The boundary is
-enforced at the file source, not by post-hoc scrubbing. If you publish a
-baseline to `gbrain-evals`, generate it from a fixture-seeded test brain
-(placeholder names like `alice-example`, `widget-co-example`) — never
-from a real user's `eval_candidates` table.
-
-### Deterministic-pipeline disclosure
-
-`gbrain eval gate --qrels` uses bare `hybridSearch` (not the production
-`query` op handler). This is deliberate: gates need to be deterministic in
-CI. Production retrieval differs via the query cache, salience freshness,
-expansion, etc. The gate measures retrieval quality with a fixed pipeline;
-your users may see different results when the cache is warm.
-
-### `.qrels.json` shape
-
-Two equivalent representations per entry:
-
-```json
-{
-  "schema_version": 1,
-  "queries": [
-    {
-      "query_id": "q1",
-      "query": "fintech founder",
-      "relevant_slugs": ["people/alice-example"],
-      "first_relevant_slug": "people/alice-example"
-    }
-  ]
-}
-```
-
-For federated / multi-source brains, use the explicit shape (no defaults
-to `source_id='default'`):
-
-```json
-{
-  "query_id": "q2",
-  "query": "anything",
-  "relevant": [
-    {"source_id": "host", "slug": "people/alice"},
-    {"source_id": "team-a", "slug": "people/alice"}
-  ],
-  "expected_top1": {"source_id": "host", "slug": "people/alice"}
-}
-```
-
-Without `source_id`, a hit from the wrong source could false-pass the
-gate. The compare everywhere is `${source_id}::${slug}` strings.
-
-### Example GitHub Actions workflow
-
-```yaml
-name: gbrain-eval-gate
-on: [pull_request]
-jobs:
-  gate:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: oven-sh/setup-bun@v2
-      - run: bun install
-      - run: |
-          # Run both gates; CI fails on any breach.
-          gbrain eval gate \
-            --baseline gbrain-evals/baselines/v0.41-launch.baseline.ndjson \
-            --qrels gbrain-evals/qrels/v0.41-launch.qrels.json \
-            --json | tee /tmp/gate.json
-```
-
----
-
 ## Prerequisite: turn on contributor mode
 
 Capture is **off by default** for production users (privacy-positive — no
@@ -434,165 +328,3 @@ commands per high-severity finding.
 - `docs/contradictions.md` — architecture, severity rubric, action criteria.
 - CHANGELOG `## [0.32.6]` — full release notes including the bigger-swing
   decision criteria gated on Wilson CI lower-bound.
-
-## v0.40.1.0 Track D — Eval infrastructure
-
-Three eval surfaces grew non-trivial capabilities in v0.40.1.0. This section
-covers the dev loop that uses them and the gates they enforce.
-
-### `gbrain eval longmemeval --by-type` — per-question-type R@k breakdown
-
-LongMemEval has always computed per-question-type recall internally; v0.40.1.0
-surfaces it in machine-readable form. Two additive changes:
-
-1. Every per-question JSONL row now includes a `question: string` field so the
-   `gbrain eval cross-modal --batch` consumer (below) can read it without
-   joining back against the source dataset.
-2. New `--by-type` flag emits a final aggregate line keyed by `question_type`:
-
-```json
-{"schema_version": 1, "kind": "by_type_summary",
- "recall_by_type": {"single-session-user": {"hit": 18, "total": 19, "rate": 0.947}},
- "aggregate": {"hit": 110, "total": 120, "rate": 0.917}}
-```
-
-**Resume-safe.** When `--resume-from` is the same path as `--output`, the
-summary is rebuilt from the file (each per-row includes `question_type` and
-`recall_hit`) so the final aggregate covers all resumed questions, not just
-this run's slice. The prior summary at the file tail is replaced, not
-appended — a brain that resumes 5 times across a 500-question run ends with
-exactly ONE summary at the tail.
-
-**Optional gate.** `--by-type-floor 0.85` exits non-zero when any
-`question_type`'s rate falls below 0.85. Default: informational only.
-
-```bash
-# Diagnose per-type ranking quality after a search-touching change.
-gbrain eval longmemeval ~/datasets/longmemeval_s.jsonl \
-  --by-type --output /tmp/run.jsonl
-tail -1 /tmp/run.jsonl | jq .   # summary line
-
-# Strict gate in a CI script.
-gbrain eval longmemeval test/fixtures/longmemeval-mini.jsonl \
-  --by-type --by-type-floor 0.80 --output /tmp/run.jsonl
-echo "exit=$?"  # 1 if any type fell below 0.80
-```
-
-### Hermetic retrieval gate — `test/eval-replay-gate.test.ts`
-
-The v0.40.1.0 Track D structural fix for "PRs touching `src/core/search/`
-silently regress retrieval." Replaces the original "replay against captured
-eval_candidates" design (which Codex caught as non-functional in CI — see
-the `v0.41+: contributor-mode CI capture` TODO in `TODOS.md` for the deferred
-real-query version).
-
-How it works:
-- Hand-curated qrels fixture at `test/fixtures/eval-baselines/qrels-search.json`
-  with PLACEHOLDER names only (no real people / companies per CLAUDE.md privacy
-  rule).
-- The test seeds a PGLite engine with synthetic pages whose embeddings are
-  basis vectors (the same `basisEmbedding(idx)` pattern as
-  `test/e2e/search-quality.test.ts`). No API keys, no DATABASE_URL.
-- For each qrels query, calls `engine.searchVector(basisEmbedding(dim))` and
-  computes `top1_match_rate` and `recall@10`. Asserts both meet floors
-  (`>= 0.80` and `>= 0.85` by default).
-- Lives in the unit-shard test matrix (`.github/workflows/test.yml`) so it
-  runs on every PR via `bun test`, NOT in the E2E fixed-file workflow.
-
-#### Refreshing the qrels fixture (the `Why:` discipline, D4)
-
-When CI fails because a legitimate ranking change moved expected slugs, the
-fix is to edit `qrels-search.json` directly. **Always include a `Why:` line
-in the commit body** so future maintainers can read the audit trail. Without
-the `Why:`, the gate degrades to a rubber stamp within months. The convention
-is informational (not a commit-hook block), but enforce it in PR review.
-
-Example commit body:
-
-```
-chore(eval): refresh qrels for new source-boost ordering
-
-Why: v0.40.x source-boost now weights originals/ over concepts/, so
-q12 (founder-mode) now correctly surfaces originals/founder-mode-example
-top-1. Manual verification: ran the production query; new ranking is
-clearly better-aligned with the query intent.
-```
-
-#### Env-overrides for floors
-
-```bash
-GBRAIN_REPLAY_GATE_TOP1_FLOOR=0.85 \
-GBRAIN_REPLAY_GATE_RECALL_FLOOR=0.90 \
-  bun test test/eval-replay-gate.test.ts
-```
-
-Use to tighten or loosen the gate as the qrels fixture matures.
-
-### `gbrain eval cross-modal --batch` — batch quality scoring
-
-Single-task cross-modal eval scores one (task, output) pair. Batch mode runs
-the same scoring over an entire LongMemEval JSONL output, with cost guardrails.
-
-```bash
-# Step 1: produce LongMemEval hypotheses (real cost: depends on model + N).
-gbrain eval longmemeval ~/datasets/longmemeval_s.jsonl \
-  --limit 10 --output /tmp/run.jsonl
-
-# Step 2: batch-score those hypotheses (real cost: ~$0.70 for 10 questions,
-# 1 cycle, 3 model slots at default --max-usd 5 budget cap).
-gbrain eval cross-modal --batch /tmp/run.jsonl \
-  --limit 10 --cycles 1 --concurrent 3 --max-usd 5 --json
-echo "exit=$?"  # 0=all-pass, 1=any-fail, 2=any-error-or-inconclusive
-```
-
-**Key behaviors:**
-- Default `--cycles 1` in batch mode (single-task default is 3 in TTY) to bound
-  cost. Pass `--cycles 3` to match single-task strictness.
-- `--concurrent 3` runs up to 3 questions in parallel x 3 model slots each =
-  9 simultaneous API calls. Below tier-1 rate limits for all three providers.
-- `--max-usd FLOAT` refuses to start if the pre-flight cost estimate exceeds
-  the cap, unless `--yes` bypasses (required for non-interactive cron / CI).
-- Filters `kind: "by_type_summary"` rows automatically (the LongMemEval
-  `--by-type` summary line is metadata, not a question).
-- `--batch` is mutually exclusive with `--task`; fail-fast usage error if both
-  are set.
-- Exit precedence (fail-loud): ERROR > FAIL > INCONCLUSIVE > PASS.
-- Per-question receipts land in a tempdir and are deleted at end of batch; the
-  summary inlines per-question verdicts so the audit trail is self-contained.
-
-### Nightly cross-modal quality probe (opt-in, autopilot)
-
-`src/core/cycle/nightly-quality-probe.ts` ships a phase that runs the longmemeval
-+ cross-modal pipeline once per 24h. **Disabled by default** to avoid surprise
-API spend. Enable per-host:
-
-```bash
-gbrain config set autopilot.nightly_quality_probe.enabled true
-gbrain config set autopilot.nightly_quality_probe.max_usd 5.00   # optional override
-```
-
-Note: `--phase nightly_quality_probe` wiring into the autopilot scheduler is
-deferred to a v0.41+ follow-up (see TODOS.md). For now the phase is callable
-in isolation; the test harness exercises it via DI stubs.
-
-```bash
-# Manual smoke (exercises the path via DI stubs, no real API spend).
-bun test test/nightly-quality-probe.test.ts
-```
-
-Observability:
-- `~/.gbrain/audit/quality-probe-YYYY-Www.jsonl` — one event per run with
-  outcome (pass / fail / inconclusive / error / budget_exceeded /
-  rate_limited / no_embedding_key), pass/fail/inconclusive/error counts,
-  est_cost_usd, fixture_sha8. ISO-week rotation (mirrors slug-fallback
-  audit).
-- `gbrain doctor` surfaces `nightly_quality_probe_health`:
-  - SKIPPED (disabled) — with paste-ready enable command.
-  - OK (enabled, no events yet) — autopilot hasn't fired its first run.
-  - OK (last 7d all PASS) — with timestamp of latest run.
-  - WARN — any FAIL / ERROR / BUDGET_EXCEEDED in the window, with outcome
-    counts and the latest run's reason.
-
-Real expected cost: ~$0.35 per nightly run (5 questions x 3 slots x 1 cycle
-x ~$0.02/call) ≈ $10.50/month. Worst-case under the default budget cap:
-$150/month. Opt-in default prevents discovering this in your card statement.

docs/eval/METRIC_GLOSSARY.md

@@ -38,40 +38,6 @@ Every metric `gbrain eval *` and `gbrain search stats` reports has a plain-Engli
 
 **Range:** 0..1, higher is better. nDCG@10 above 0.65 is the common "ship it" threshold for hybrid retrieval on technical corpora.
 
-## Retrieval-Quality / Evidence Metrics (NamedThingBench)
-
-### Hit rate at 1 (Hit@1)
-
-**Key:** `hit@1`
-
-**Plain English:** Fraction of queries where the right page is the very first result. NamedThingBench hard-gates title-substring Hit@1 >= 0.95 and alias Hit@1 >= 0.98 — a query that is a page's name or title phrase should land it at rank 1, not "somewhere in the top 10".
-
-**Range:** 0..1, higher is better.
-
-### Hit rate at 3 (Hit@3)
-
-**Key:** `hit@3`
-
-**Plain English:** Fraction of queries where the right page is in the top 3 results. NamedThingBench requires the multi-chunk-dilution family to hit 1.0 — a page with one strong chunk among many weak ones must never be buried.
-
-**Range:** 0..1, higher is better.
-
-### Average rank-1 match score
-
-**Key:** `avg_rank1_score`
-
-**Plain English:** The mean base (pre-boost) retrieval score of the TOP result across recent searches, from `gbrain search stats`. It is NOT a labeled accuracy number — it is a drift signal: if this trends DOWN over time, retrieval quality is regressing (the early warning that would have caught the duplicate-page incident before a human did).
-
-**Range:** 0..1. Watch the trend, not the absolute value; pair with the <0.6 / 0.6-0.85 / >=0.85 bucket counts for shape.
-
-### Create-safety hint (evidence contract)
-
-**Key:** `create_safety`
-
-**Plain English:** A result's answer to "is this page already in the brain — safe to NOT write a new one?" Derived from the strongest evidence, NOT a raw score: exists (alias_hit / exact_title_match / high_vector_match — do not duplicate), probable (solid keyword match — prefer updating), unknown (weak match — look closer). An agent keys its don't-duplicate decision off this, which is what prevents the incident's duplicate-stub class.
-
-**Range:** enum: exists | probable | unknown
-
 ## Set-Similarity / Stability Metrics
 
 ### Jaccard similarity at k (set Jaccard @k)
@@ -150,24 +116,6 @@ Every metric `gbrain eval *` and `gbrain search stats` reports has a plain-Engli
 
 **Range:** 0..unbounded. Warm-cache hits should be <50ms; tokenmax with expansion can exceed 200ms due to the Haiku call.
 
-## Result-Sizing Metrics
-
-### Autocut signal
-
-**Key:** `autocut.signal`
-
-**Plain English:** Which signal autocut used to size the result set. 'rerank' means it found a real score cliff in the cross-encoder rerank scores and cut there; 'none' means no trustworthy cliff (no reranker, <2 scored results, or the gap was too small) so it returned the full list.
-
-**Range:** 'rerank' | 'none'. 'none' is not a failure — it means autocut declined to cut because the signal didn't justify it.
-
-### Autocut gap ratio
-
-**Key:** `autocut.gap_ratio`
-
-**Plain English:** The size of the largest score drop autocut found, as a fraction of the top result's score. A gap of 0.40 means the score fell by 40% of the top score at the steepest point. Autocut cuts there only when this clears the sensitivity threshold (autocut_jump, default 0.20).
-
-**Range:** 0..1, higher = a sharper cliff (more confident cut). Below the autocut_jump threshold → no cut.
-
 ---
 
 ## Coverage

docs/eval/SEARCH_MODE_METHODOLOGY.md

@@ -160,7 +160,7 @@ The mode-picker prompt at `gbrain init` and the CLAUDE.md `## Search Mode` table
 - Your agent's system prompt + reasoning tokens add input that gbrain doesn't see.
 - Compaction reduces input over a long session.
 - Most agents make 1-5 searches per turn; cost-per-turn is what bills you, not cost-per-query.
-- The model price column drifts as providers reprice; pin the rate via `src/core/model-pricing.ts` (the canonical chat-pricing table) for a current snapshot.
+- The model price column drifts as providers reprice; pin the rate via `src/core/anthropic-pricing.ts` for a current snapshot.
 
 The picker copy + CLAUDE.md table are the canonical user-facing source. Update them in lockstep when the underlying chunker size or default `searchLimit` changes.
 

docs/guardrails.md

@@ -1,102 +0,0 @@
-# Content Guardrail Seams
-
-GBrain exposes **vendor-neutral guardrail seams** at the boundaries where
-external content enters the retrieval layer and where queries/tool-inputs enter
-the LLM gateway. A guardrail is any external classifier — a content firewall, a
-prompt-injection detector, a PII scrubber — that wants to *observe* content at
-those boundaries.
-
-The OSS distribution ships **inert**: zero guardrails are registered by default,
-and every seam is a no-op until an operator registers a provider.
-
-## Design contract (hard invariants)
-
-These hold for every seam and are enforced by `test/guardrails.test.ts`:
-
-- **Observe-only.** `runGuardrails()` returns `void`. Callers never branch on a
-  provider verdict. A guardrail registered through this interface *cannot*
-  block, rewrite, drop, retry, or reorder GBrain behavior. Enforcement, if ever
-  added, will get its own explicitly-named seam and its own RFC — it will not
-  silently reuse this one.
-- **Fail open.** Missing config, provider throw/reject, timeout, and network
-  error are all swallowed. A broken guardrail never breaks an ingest, a query,
-  or a tool call.
-- **Inline await.** Hooks await the provider before proceeding, so the
-  classifier sees content at the exact pre-persist / pre-inference moment.
-- **No verdict persistence.** GBrain writes no guardrail rows. Providers own
-  their own audit trail.
-- **Content boundaries.** Hooks pass only the ingest/user-facing payload — the
-  markdown/code body, the last user message, the expansion query, the tool
-  input. They never pass system prompts, full chat history, tool *output*, LLM
-  output, embeddings, or multimodal/OCR/rerank payloads.
-
-## The five seams
-
-All seams call `runGuardrails({ hook, content, metadata })` from
-`src/core/guardrails.ts`.
-
-| `hook` | Location | Fires |
-| --- | --- | --- |
-| `file_storage.markdown` | `import-file.ts` → `importFromContent` | After `parseMarkdown` + size guard, **before** content-sanity, hashing, chunking, embedding, DB write |
-| `file_storage.code` | `import-file.ts` → `importCodeFile` | After code size guard, **before** hashing, code-chunking, embedding, DB write |
-| `ai_gateway.chat` | `ai/gateway.ts` → `chat` | On the **latest user message only**, before provider inference |
-| `ai_gateway.expand` | `ai/gateway.ts` → `expand` | On the query, before the expansion model call |
-| `ai_gateway.tool_input` | `ai/gateway.ts` → `toolLoop` | On `{toolName, input}`, before pending-persist and before tool execution |
-
-The two `file_storage.*` hooks cover every natural ingest caller that routes
-through `importFromContent` / `importCodeFile`: `gbrain import`, sync, capture,
-`put_page`, subagent `brain_put_page`, trusted-workspace writes,
-`ingest_capture`, inbox daemon dispatch, reindex, code reindex, and the public
-import APIs.
-
-## Writing a guardrail provider
-
-```ts
-import { registerGuardrailProvider, type GuardrailInput } from 'gbrain/core/guardrails';
-
-registerGuardrailProvider({
-  id: 'my-firewall',
-  async classify(input: GuardrailInput) {
-    // input.hook      — which boundary ('file_storage.markdown', etc.)
-    // input.content   — the raw text to classify
-    // input.metadata  — provider-opaque context (slug, source_kind, tool_name, model, ...)
-    //
-    // Do your own timeout/retry/logging here. The return value is IGNORED by
-    // GBrain — return a typed verdict only if your own audit code consumes it.
-    await fetch(MY_API, { method: 'POST', body: JSON.stringify({ text: input.content }) });
-  },
-});
-```
-
-Register once at process init (e.g. from a plugin entry or an operator boot
-hook). Registration is idempotent by `id`, so a re-init won't double-fire.
-
-### Provider responsibilities
-
-GBrain deliberately keeps the seam minimal. The provider owns:
-
-- **Timeout discipline.** GBrain does not impose a timeout in `runGuardrails`
-  so you can tune per-deployment latency. Use an `AbortController`.
-- **Secret handling.** Read API keys from env at call time. Never log the key.
-- **Redacted logging.** Don't log raw classified content (it may itself be the
-  payload you're trying to protect). Log a hash + verdict, not the body.
-- **Async fan-out.** If you don't want to block ingest on your classifier,
-  enqueue inside `classify` and return immediately. The seam awaits *your*
-  function; what it does is up to you.
-
-## Example: shadow-mode firewall provider
-
-A typical "shadow mode" provider (classify, log a redacted verdict, change
-nothing) is ~80 lines and lives entirely in the provider's own package. See
-the reference provider doc shipped to integration partners for a complete
-`classify` implementation that:
-
-1. resolves `<base>/classify` from an env URL,
-2. posts `{ text, hook, metadata }` with an `x-api-key` header,
-3. parses a `{ prediction, blocked, score, threshold }` response,
-4. emits one redacted stderr line (`status=… prediction=… content_sha256=…`),
-5. fails open on every error path.
-
-Because the verdict is ignored by GBrain, "shadow mode" requires *no* special
-GBrain flag — it is the only mode this interface supports. Enforcement would be
-a separate, future, RFC-gated seam.

docs/guides/live-sync.md

@@ -15,20 +15,17 @@ with the brain repo automatically. You never have to remember to run sync.
 
 ## Implementation
 
-### Prerequisite: a reachable direct connection
+### Prerequisite: Session Mode Pooler
 
-GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
-auto-disables prepared statements there and routes `engine.transaction()`
-(migrations, DDL, sync imports) to a derived **direct** connection
-(`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
-IPv4-only host, reads work but sync **silently skips most pages**. This is the
-number one cause of "sync ran but nothing happened."
+Sync uses `engine.transaction()` on every import. If `DATABASE_URL` points to
+Supabase's **Transaction mode** pooler, sync will throw `.begin() is not a
+function` and **silently skip most pages**. This is the number one cause of
+"sync ran but nothing happened."
 
-Fix: make the direct connection reachable over IPv4. Either set
-`GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
-`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
-running `gbrain sync` and checking that the page count in `gbrain stats` matches
-the syncable file count in the repo.
+Fix: use the **Session mode** pooler string (port 6543, Session mode) or the
+direct connection (port 5432, IPv6-only). Verify by running `gbrain sync` and
+checking that the page count in `gbrain stats` matches the syncable file count
+in the repo.
 
 ### The Primitives
 
@@ -61,9 +58,8 @@ gbrain sync --repo /data/brain && gbrain embed --stale
 Name: gbrain-auto-sync
 Schedule: */15 * * * *
 Prompt: "Run: gbrain sync --repo /data/brain && gbrain embed --stale
-  Log the result. If sync errors mention an unreachable host or timeout,
-  the direct connection isn't reachable over IPv4 (set
-  GBRAIN_DIRECT_DATABASE_URL to the Session pooler, or enable the IPv4 add-on)."
+  Log the result. If sync fails with .begin() is not a function,
+  the DATABASE_URL is using Transaction mode pooler."
 ```
 
 **Hermes:**
@@ -120,27 +116,6 @@ hashes match. If both a cron and `--watch` fire simultaneously, no conflict.
    server is down when a push happens, that sync is missed. Pair webhooks
    with a cron fallback that catches anything the webhook missed.
 
-4. **A single un-parseable file can't wedge all indexing.** When a file fails
-   to import (malformed YAML frontmatter, an unquoted colon, etc.), sync holds
-   the bookmark and tells you exactly which file broke — a *fresh* failure
-   fails closed so nothing is silently dropped. But a file that fails the same
-   way `GBRAIN_SYNC_AUTOSKIP_AFTER` consecutive syncs (default 3, set `0` to
-   disable) is auto-skipped so the rest of the brain keeps indexing past it.
-   Skipped files don't disappear: `gbrain doctor` keeps warning until you fix
-   or delete them, and fixing the file clears it on the next sync. A repository
-   history rewrite still hard-blocks even with `--skip-failed`. Run
-   `gbrain sync --skip-failed` to acknowledge a known-bad set yourself.
-
-5. **Import checkpoints name the import target, not the caller's CWD.**
-   Interrupted `gbrain import <dir>` runs may leave
-   `~/.gbrain/import-checkpoint.json` so the next import can resume. The
-   checkpoint `dir` is the absolute, resolved import target captured when
-   import starts. It is not a cleanup instruction and it must not be
-   re-derived from the process working directory. Checkpoints written by
-   gbrain include `schema_version: 1`, `owner: "gbrain"`, and
-   `kind: "import"` so downstream tools can validate the contract before
-   deciding whether to resume.
-
 ## How to Verify
 
 1. **Edit a file and search for the change.** Edit a brain markdown file,
@@ -150,8 +125,8 @@ hashes match. If both a cron and `--watch` fire simultaneously, no conflict.
 
 2. **Compare page count to file count.** Run `gbrain stats` and count the
    syncable markdown files in the brain repo. The page count in the database
-   should match. If they diverge, files are being silently skipped (likely an
-   unreachable direct connection on IPv4 — see the prerequisite above).
+   should match. If they diverge, files are being silently skipped (likely
+   a Transaction mode pooler issue).
 
 3. **Check embedded chunk count.** In `gbrain stats`, the embedded chunk
    count should be close to the total chunk count. A large gap means

docs/guides/minions-deployment.md

@@ -54,33 +54,6 @@ gbrain jobs supervisor stop
 An agent seeing exit=2 can safely treat it as "one is already running";
 exit=1 should page a human.
 
-### Lowering scheduling priority (`--nice`)
-
-When the worker pool runs at full concurrency on a machine you also use
-interactively, it can drive the load average high enough to starve your
-shell. Cutting `--concurrency` throws away throughput. Reach for `--nice`
-instead — it lowers the job tree's CPU scheduling priority without touching
-width, so the work runs full-speed when the box is idle and yields when it
-isn't:
-
-```bash
-# Full concurrency, low priority. Propagates to the spawned worker and its
-# children (shell jobs, subagents) via OS niceness inheritance.
-gbrain jobs supervisor --concurrency 4 --nice 10
-
-# Equivalent for a bare worker, or set it durably in the environment.
-GBRAIN_NICE=10 gbrain jobs work --concurrency 4
-```
-
-`--nice` takes a POSIX value from `-20` (highest priority) to `19`
-(nicest/lowest); positive values need no privilege, negative values need
-root. `GBRAIN_NICE` is the env equivalent (the flag wins). Confirm the
-effective value with `gbrain jobs stats`, `gbrain jobs supervisor status
---json`, or the `supervisor_niceness` check in `gbrain doctor` — the doctor
-check warns if what you asked for isn't what's actually running (e.g. a
-negative value denied without privilege, or an OS `RLIMIT_NICE` clamp). This
-is distinct from the concurrency / inflight cap and composes with it.
-
 ### Which supervisor when?
 
 The supervisor solves in-process crash recovery. Platform-level

docs/guides/multi-language-fts.md

@@ -1,97 +0,0 @@
-# Multi-language full-text search
-
-GBrain's keyword search arm uses Postgres full-text search (tsvector/tsquery).
-The tokenizer language is configurable via the `GBRAIN_FTS_LANGUAGE`
-environment variable. Default: `english`.
-
-## How it works
-
-Postgres text-search configurations control stemming and stop-word removal.
-`GBRAIN_FTS_LANGUAGE` is read by `src/core/fts-language.ts` and applied on
-both sides of the search:
-
-- **Query side** — `websearch_to_tsquery('<lang>', $query)` in both engines
-  (Postgres and PGLite).
-- **Write side** — the `update_page_search_vector` and
-  `update_chunk_search_vector` trigger functions that populate
-  `pages.search_vector` and `content_chunks.search_vector`.
-
-The value is validated against `/^[a-z][a-z0-9_]*$/` before it is ever
-interpolated into SQL (tsvector functions don't accept parameterized config
-names). Invalid values fall back to `english` with a warning.
-
-## Built-in languages
-
-Set the env var to any configuration your Postgres instance ships:
-
-```bash
-export GBRAIN_FTS_LANGUAGE=portuguese
-export GBRAIN_FTS_LANGUAGE=spanish
-export GBRAIN_FTS_LANGUAGE=german
-```
-
-List what's available:
-
-```sql
-SELECT cfgname FROM pg_ts_config;
-```
-
-PGLite (the embedded default engine) ships the same built-in snowball
-configurations as stock Postgres.
-
-## First install vs. changing language later
-
-On first install (or upgrade), the `configurable_fts_language` schema
-migration reads `GBRAIN_FTS_LANGUAGE` and stamps the trigger functions with
-that language. After the migration has run, changing the env var alone does
-NOT retokenize existing rows — the migration shows as applied and is skipped.
-Use the explicit command:
-
-```bash
-export GBRAIN_FTS_LANGUAGE=portuguese
-gbrain reindex-search-vector --dry-run    # preview: language + row counts
-gbrain reindex-search-vector --yes        # recreate triggers + backfill
-```
-
-The command recreates both trigger functions under the new language and
-backfills every existing `pages` and `content_chunks` row in batches,
-streaming progress to stderr. It is idempotent: re-running with the same
-language produces identical vectors. `--json` prints a machine-readable
-result envelope but still requires `--yes` (or an interactive confirm).
-
-## Recipe: accent-insensitive Portuguese (`pt_br`)
-
-Brazilian Portuguese content often mixes accented and unaccented spellings
-("São Paulo" vs "Sao Paulo"). Build a custom config that folds accents via
-the `unaccent` extension, then stems with the portuguese snowball dictionary:
-
-```sql
-CREATE EXTENSION IF NOT EXISTS unaccent;
-
-CREATE TEXT SEARCH CONFIGURATION pt_br (COPY = portuguese);
-
-ALTER TEXT SEARCH CONFIGURATION pt_br
-  ALTER MAPPING FOR hword, hword_part, word
-  WITH unaccent, portuguese_stem;
-```
-
-Then point GBrain at it:
-
-```bash
-export GBRAIN_FTS_LANGUAGE=pt_br
-gbrain reindex-search-vector --yes
-```
-
-Note: custom configurations require a real Postgres instance (e.g. the
-Supabase engine). The config must exist BEFORE the migration or the reindex
-command runs, or Postgres will reject the trigger recreation with
-`text search configuration "pt_br" does not exist`.
-
-## Caveats
-
-- One language per brain: the setting is global to the database, not
-  per-source. Mixed-language brains should pick the dominant language (the
-  vector-search arm is language-agnostic and covers the rest).
-- Keep `GBRAIN_FTS_LANGUAGE` set consistently in every environment that
-  writes to the brain (CLI shells, MCP server, cron jobs) — a writer without
-  the env var tokenizes new rows in `english` until the next reindex.

docs/guides/multi-source-brains.md

@@ -114,11 +114,8 @@ Flip later with `gbrain sources federate <id>` / `unfederate <id>`.
 Full subcommand reference:
 
 ```
-gbrain sources add <id> --path <p> [--name <n>] [--federated|--no-federated] [--force]
+gbrain sources add <id> --path <p> [--name <n>] [--federated|--no-federated]
                                Register a source. id: [a-z0-9](?:[a-z0-9-]{0,30}[a-z0-9])?
-                               --path must be a git repo (or a subdirectory of one) — see
-                               "The git requirement for --path sources" below. --force
-                               skips that check to register before git-init exists.
 gbrain sources list [--json]   List all sources with page counts + federation state.
 gbrain sources remove <id> [--yes] [--dry-run] [--keep-storage]
                                Cascade-delete a source (pages, chunks, timeline).
@@ -131,47 +128,6 @@ gbrain sources federate <id>
 gbrain sources unfederate <id>
 ```
 
-## The git requirement for --path sources
-
-Every `--path` source must be a git repository (or live inside one — a
-subdirectory of a git repo works too) with at least one committed, tracked
-file under that path. `gbrain sources add` validates this at registration
-time and refuses a directory that doesn't qualify — no `.git` at all, a
-`git init` with no commit yet, or a commit made before `git add` — with an
-actionable error instead of silently registering a source that will fail
-(or worse, "succeed" while importing nothing) on its first `gbrain sync`.
-Fix it with:
-
-```bash
-git -C <path> init
-git -C <path> add -A
-git -C <path> commit -m "initial import"
-gbrain sources add <id> --path <path>
-```
-
-Two details that are easy to miss:
-
-- **Files must actually be committed, not just present.** The sync walker
-  reads files through git objects, so `git init` alone — even followed by an
-  empty commit (`git commit --allow-empty`) — isn't enough. Registration
-  checks for real tracked content (`git ls-tree HEAD` scoped to the path),
-  not just a resolvable `HEAD`, so this footgun is caught immediately
-  instead of surfacing later as a sync that imports nothing.
-- **`--force` registers the source anyway**, skipping the check. Use this if
-  you're registering a path before an automated pipeline gets around to
-  `git init`-ing it. GBrain never auto-`git init`s a `--path` source for
-  you — it's your directory, not a gbrain-managed clone (same consent
-  boundary as sync-time self-heal, which also never mutates a `--path`
-  source without an explicit ask).
-
-**If sync ever reports a problem with the sync anchor** (`last_commit`) —
-after a force-push, a history rewrite, or a from-scratch `git init` on a
-directory that was synced before — you do not need to reset anything by
-hand. `gbrain sync` detects an unreachable or non-ancestor anchor
-automatically and recovers: either a full reimport (anchor object missing)
-or a direct tree-to-tree diff against the orphaned bookmark (anchor present
-but rewritten), advancing the anchor to the new HEAD when it completes.
-
 ## Citation format for agents
 
 When agents receive multi-source results they MUST cite pages in
@@ -199,58 +155,6 @@ Reads span federated sources by default. Writes require a resolved
 source (explicit, inferred, or default). The resolver never picks a
 source silently when ambiguous — it errors with a clear fix.
 
-## Durability: keep a brain repo in sync (auto-harden)
-
-A long-lived agent that writes to a knowledge-wiki git repo needs three
-things to never lose work: pull before it edits, push every write, and not
-go stale while it sits idle. `gbrain sources harden` installs all of that,
-idempotently. The moment you add a brain repo with a token, it runs
-automatically:
-
-```bash
-# Clone + register a GitHub repo, then auto-harden it for durability.
-# Use a fine-grained PAT scoped to just this repo.
-gbrain sources add wiki --url https://github.com/you/brain-wiki.git --pat-file ~/.secrets/wiki-pat
-#   → clones, then installs: local auto-push hook, scripts/brain-commit-push.sh,
-#     always-on durability rules in AGENTS.md/RESOLVER.md, a 30-min pull cron,
-#     and a repo-scoped credential. Verifies push works before declaring done.
-
-# Run the same audit on an existing source any time (idempotent):
-gbrain sources harden wiki --pat-file ~/.secrets/wiki-pat
-
-# Pull on demand (the cron calls the --path form, which never opens the DB):
-gbrain sources pull wiki
-
-# Remove the durability scaffolding (also runs automatically on `sources remove`):
-gbrain sources unharden wiki
-```
-
-What hardening guarantees:
-
-- **Pull-first, conflict-safe.** Every pull is a divergence-safe rebase. A
-  dirty working tree is skipped (your in-progress edits are never touched); a
-  rebase conflict is aborted cleanly and flagged for attention, never left
-  half-applied.
-- **Push is never deferred.** `scripts/brain-commit-push.sh "<msg>" <path>`
-  commits and pushes atomically and refuses to report success without a
-  confirmed push. The post-commit hook is a best-effort background fallback;
-  the helper is the guarantee.
-- **No silent staleness.** A 30-minute background pull keeps an idle session
-  current. It runs DB-free, so it never contends with a live brain for the
-  PGLite single-writer lock.
-
-Flags: `--no-cron` skips the scheduled pull, `--no-verify` skips the push
-probe, `--dry-run` reports what would change, `--json` emits a machine
-report, `--all` hardens every source with a remote (same-account only).
-`--no-harden` on `sources add` opts out of auto-harden.
-
-Security: the push automation is installed locally per machine (never
-committed into the repo), the token is wired per-repo (an existing
-credential helper is reused when present), and it never appears in the repo,
-the remote URL, logs, or the JSON report. For a self-hosted git server
-reachable only over a filesystem path, set `GBRAIN_GIT_ALLOW_FILE_TRANSPORT=1`
-(default is HTTPS-only).
-
 ## Upgrading an existing brain
 
 `gbrain upgrade` runs the v16 + v17 migrations automatically. Your

docs/guides/push-context.md

@@ -1,79 +0,0 @@
-# Push-based context (#2095, v0.42.43.0)
-
-Retrieval used to be pull-only: the agent had to *know to ask* before the brain
-contributed anything. Push-based context inverts that — the brain volunteers
-relevant pages from the recent conversation, confidence-gated so push noise
-never becomes worse than pull silence.
-
-Three channels share one zero-LLM core (`src/core/context/volunteer.ts`):
-
-| Channel | Surface | When to use |
-|---|---|---|
-| `reflex` | automatic, inside the context engine | default-on for plugin hosts; nothing to call |
-| `op` | `gbrain volunteer-context` / MCP `volunteer_context` | agents without the plugin; one call per turn |
-| `watch` | `gbrain watch` | stream a transcript in, volunteered pages stream out |
-
-## How it decides
-
-1. **Extract** entities across the last N turns (capitalized runs, `@handles`),
-   merged with recency / frequency / user-role salience. Assistant-introduced
-   entities and "what did she invest in?" follow-ups whose antecedent was named
-   in the window now resolve.
-2. **Resolve** through the alias table, exact titles, and slug suffixes — each
-   arm carries an honest confidence: alias 0.9, exact title 0.8, slug-suffix 0.6,
-   +0.05 when mentioned in ≥2 turns or the newest turn.
-3. **Gate** at `min_confidence` (default 0.7 — slug-suffix matches need an
-   explicit lower gate), suppress pages already surfaced (slug-presence only),
-   cap at 3 pages (hard cap 5).
-
-## CLI
-
-```bash
-# one-shot: pipe recent turns (oldest → newest)
-printf 'user: ask alice-example about the deal\nassistant: noted\nuser: what did she say?\n' \
-  | gbrain volunteer-context
-
-# streaming: volunteered pages print as the transcript flows
-some-transcript-feed | gbrain watch --json
-
-# the feedback loop: how often were volunteered pages actually opened?
-gbrain volunteer-context --stats
-```
-
-Stats are **approximate** by design: "used" means `pages.last_retrieved_at >
-volunteered_at` — the 5-minute last-retrieved throttle causes false negatives
-and unrelated reads of the same page cause false positives. Use the per-arm
-precision to tune `min_confidence`, not as an exact metric.
-
-**PGLite + `gbrain watch`:** PGLite is single-connection, and watch holds its
-connection for the whole session — a concurrent `gbrain serve` or any write
-path blocks until watch exits. On a PGLite brain, run watch in bursts (piped
-input exits at EOF) or use the ambient reflex channel instead, which routes
-through a running serve's resolve socket rather than taking the lock. Routing
-watch through that same socket is a filed follow-up (TODOS.md). Postgres
-brains are unaffected.
-
-## Config
-
-| Key | Default | What it does |
-|---|---|---|
-| `retrieval_reflex_window_turns` | 4 | turns the ambient reflex extracts from; 1 = legacy current-turn-only (file/env plane: `GBRAIN_RETRIEVAL_REFLEX_WINDOW_TURNS`) |
-| `retrieval_reflex` | true | the ambient channel's master switch |
-| `retrieval_reflex_max_pointers` | 3 | pointer cap per turn |
-
-Per-call knobs: `max_pages` + `min_confidence` on both the op and `gbrain watch`
-(`--max-pages` / `--min-confidence`, plus `--window-turns` / `--source` on watch);
-on the op only: `prior_context` (text whose already-surfaced slugs are suppressed),
-`session_id` / `turn` attribution params (watch stamps its own per-session id and
-turn numbers in the feedback log), and `days` to size the `--stats` window.
-
-## Storage + privacy
-
-Volunteered pages log to `context_volunteer_events` (migration v117): slug,
-arm, confidence, channel, optional session/turn — the rationale is a
-deterministic template string, never raw conversation text. Event writes are
-best-effort (fire-and-forget, drained at CLI exit) — the log is a tuning signal,
-not an audit trail. Rows are pruned after 90 days by the dream cycle's purge
-phase. Synopses always strip the takes/facts fences — the same strip `get_page`
-applies to untrusted callers, applied unconditionally here so private fence rows
-never reach a prompt regardless of caller trust.

docs/guides/queue-operations-runbook.md

@@ -16,39 +16,6 @@ gbrain doctor --json | jq '.checks[] | select(.name == "queue_health")'
 - **waiting-depth**: any per-name queue deeper than 10 (override via
   `GBRAIN_QUEUE_WAITING_THRESHOLD`). Signals a missing `maxWaiting`.
 
-## The worker is alive but wedged (dead pool)
-
-The nastiest stall: the worker process is *running* (passes `ps` / `kill -0` /
-container health), but its DB connection died (common behind a transaction
-pooler) and never came back, so it claims no jobs and finishes nothing. Jobs
-pile up with **0 active**. Liveness checks all pass; nothing crashes.
-
-As of v0.42.22.0 this self-heals — you usually won't have to do anything:
-
-- **The worker exits on its own dead pool.** Under a supervisor, the worker's
-  DB-liveness probe runs and self-exits (`db_dead`) after ~3 minutes; the
-  supervisor respawns it with a fresh pool.
-- **The supervisor restarts a worker that stops making progress.** If a queue
-  has claimable work, **0 live-lock active jobs**, and no completions for 15
-  minutes while the child is alive, the supervisor restarts it (covers stuck
-  handlers too, not just dead pools). Tune with `--wedge-restart-minutes` /
-  `--wedge-restart-checks` on `gbrain jobs supervisor` (0 disables).
-
-The signal is loud now — check either:
-
-```bash
-gbrain jobs stats --queue default          # prints a WEDGED QUEUE line
-gbrain doctor --json | jq '.checks[] | select(.name == "wedged_queue")'
-```
-
-`wedged_queue` is a per-queue health **error** (0 active_healthy + waiting > 0 +
-stale completions). Manual fix if you ever need it:
-
-```bash
-gbrain jobs supervisor stop && gbrain jobs supervisor start   # fresh pool
-gbrain jobs retry <id>                                        # dead-lettered jobs
-```
-
 ## Triage commands
 
 ```bash

docs/guides/scaling-skills.md

@@ -1,310 +0,0 @@
-# Scaling skills past 300 without drowning the context window
-
-When an agent grows past 100 skills, a wall starts forming. Sessions take
-longer to start. The model gets a little dumber about which skill to pick.
-Tokens that should be powering reasoning are powering a skill catalog the
-model reads on every turn whether it needs to or not.
-
-This guide is the recipe for breaking through that wall without deleting
-capabilities. Three tiers, one resolver, one safety net. Production-tested
-on a 306-skill agent (Garry's OpenClaw, the agent behind Y Combinator's
-president). The pattern works whether you run OpenClaw, Hermes, Claude Code,
-Cursor, or your own MCP-aware agent.
-
-## The problem
-
-OpenClaw scans every skill file on disk at session start and injects them
-into the system prompt as `<available_skills>` entries. The model sees a
-name, description, and file path for each one. When a request matches, the
-model reads the full SKILL.md and follows it.
-
-This is great architecture at 50 skills. At 100, it's fine. At 200, it
-starts to drag. At 300, the system prompt eats more than 25,000 tokens on
-skill descriptions alone. Tokens that aren't going to reasoning, context,
-or actual work.
-
-The symptoms compound:
-
-- Sessions take noticeably longer to start.
-- The model has less room for conversation history.
-- Skill routing gets fuzzier. With 300 descriptions competing for attention,
-  the model occasionally picks the wrong one.
-- Cost goes up because every turn carries the full skill manifest.
-
-The naive fix is to delete skills you don't use often. Don't do this. The
-whole point of skills is that capabilities compound. A gift pipeline that
-fires twice a month saves 30 minutes each time it does. A flight tracker
-fires once per trip and prevents a missed Uber. Deleting low-frequency
-skills optimizes for prompt size at the cost of capability. You wouldn't
-delete apps from your phone because the home screen is too crowded. You'd
-organize them.
-
-## The three tiers
-
-Not all skills need to be visible to the model at all times. Some are core.
-Some are specialized. Some are dormant.
-
-### Tier A: always loaded (~35 skills)
-
-The skills the model needs on every single turn. Brain search, email triage,
-calendar, meeting ingestion, content creation, the executive assistant.
-They stay in the system prompt's `<available_skills>` manifest. The model
-sees them natively and routes to them without any lookup.
-
-### Tier B: resolver-routed (~85 skills)
-
-Real, active skills that fire regularly but don't need to pollute every
-turn. Gift pipeline, flight tracker, investor update ingestion, adversary
-tracking, book mirror, civic intelligence. They live on disk. They have
-full SKILL.md files. But OpenClaw doesn't inject them into the prompt.
-
-Instead, a compact RESOLVER.md handles routing. One line per skill with
-trigger phrases:
-
-```markdown
-- **gift-advisor**: gift idea | what should I bring | birthday gift | housewarming
-- **flight-tracker**: track my flight | flight status | when does my flight land
-- **investor-update-ingest**: investor update | portfolio update | company metrics
-```
-
-When the model sees "what should I bring to Jessica's dinner," it checks
-the resolver, finds `gift-advisor`, reads the SKILL.md, and executes. Same
-result. Zero wasted tokens on the other 84 turns where gifts aren't relevant.
-
-### Tier C: dormant (~180 skills)
-
-Built-in OpenClaw skills that aren't in active rotation (1Password, Discord,
-Notion, Trello, integrations you haven't wired up yet) plus specialized
-skills that almost never fire. They're explicitly disabled in the config
-with `enabled: false`. They exist on disk as documentation and potential.
-Flip one boolean to wake them up. Zero tokens contributed to every prompt
-until then.
-
-### The numbers
-
-Before tiering, on Garry's 306-skill OpenClaw:
-
-| Metric | Before |
-|---|---|
-| Skills in system prompt | 306 |
-| Skill-description tokens per turn | ~25,000 |
-| Skill routing accuracy | degrading |
-| Session startup | slow |
-
-After tiering:
-
-| Metric | After |
-|---|---|
-| Skills in system prompt (Tier A) | 35 |
-| Skill-description tokens per turn | ~4,000 |
-| Skills still accessible (A + B + C) | 301 |
-| Capability loss | zero |
-| **Tokens freed per turn** | **~21,000** |
-
-21K tokens per turn is not a small optimization. It's the difference between
-the model having room to think and the model being squeezed. It's the
-difference between carrying 3 pages of conversation history and carrying 15.
-
-## What the resolver actually does
-
-The resolver is cheaper than the manifest. That's the load-bearing insight.
-
-OpenClaw's native skill manifest puts ~80 tokens per skill into the system
-prompt (name + description + location). At 300 skills that's 24,000 tokens
-spent every turn whether the model needs the catalog or not.
-
-The resolver puts ~15 tokens per skill into a compact markdown list. At
-300 skills that's 4,500 tokens. But it only fires when the model checks
-it, which is only when the request doesn't match a Tier A skill. Most
-turns, the resolver costs zero tokens because the Tier A match handles it.
-
-This is the routing-table pattern but applied to the skill manifest itself.
-The resolver routes to skills, but it also routes around skills, keeping
-them out of the context window until they're needed.
-
-GBrain ships with a [bundled `skills/RESOLVER.md`](../../skills/RESOLVER.md)
-you can use as a reference shape. The skillpack story for distributing
-your own resolvers across machines is covered in
-[skillpacks as scaffolding](skillpacks-as-scaffolding.md).
-
-## The compact list format (v0.41.7.0)
-
-GBrain's resolver parser used to require markdown tables:
-
-```markdown
-| Trigger | Skill |
-|---------|-------|
-| "gift idea" | `skills/gift-advisor/SKILL.md` |
-```
-
-That's fine when you have 20 entries. It gets unwieldy at 200, and at 300
-it's unreadable. OpenClaw deployments quietly evolved a compact list
-format that scales better:
-
-```markdown
-- **gift-advisor**: gift idea | what should I bring | birthday gift
-- **flight-tracker**: track my flight | flight status | when does my flight land
-```
-
-Before v0.41.7.0, `gbrain doctor` only spoke the table dialect. On a
-306-skill compact-format resolver, the doctor reported every skill as
-unreachable: **238 FAIL errors on every doctor run**. The parser was
-silently treating the compact dialect as zero skills.
-
-v0.41.7.0 ships dual-format support. The same `parseResolverEntries`
-function reads both table rows and list rows in the same file, with the
-v0.31.7 multi-resolver merge (skillpack `skills/RESOLVER.md` + workspace
-`../AGENTS.md`) folding everything into one unified view. Run `gbrain doctor`
-and the 238 FAILs collapse to 0.
-
-### The list-format contract
-
-A few rules to keep the parser unambiguous:
-
-- **Skill names must be kebab-lowercase.** `gift-advisor`, `flight-tracker`,
-  `email-triage`. Names that start with an uppercase letter (`MyTool`,
-  `Note`, `Convention`) are deliberately ignored. This is what stops prose
-  bullets like `- **Note**: see [link]` from being mis-parsed as skill
-  rows in real-world AGENTS.md files.
-- **The path always resolves to `skills/<name>/SKILL.md`.** An optional
-  `→ \`skills/path\`` (or ASCII `->`) suffix is allowed for readability,
-  but the parser strips it. For non-conventional paths (skills under
-  nested directories, references into `conventions/`, anything that
-  isn't `skills/<name>/SKILL.md`), use the table format.
-- **Triggers separate with `|`.** Empty pieces and the literal `...`
-  placeholder are dropped. Each trigger becomes its own resolver entry,
-  all pointing at the same skill.
-- **Bold or plain.** `- **name**: triggers` is preferred. `- name: triggers`
-  works as a fallback.
-
-You can mix table and list rows in the same file. Useful when a brain
-inherits a table-format `RESOLVER.md` from gbrain and a list-format
-`../AGENTS.md` from OpenClaw.
-
-## The doctor safety net
-
-The danger with tiering is invisible skill loss. You disable a skill from
-native scanning, forget to add it to the resolver, and now the agent can't
-do something it used to do. You won't notice until the moment you need it.
-
-`gbrain doctor` walks every skill on disk and verifies it's reachable,
-either through native scanning (Tier A) or through the resolver (Tier B
-and C). On Garry's setup, the first run after tiering found 63 unreachable
-skills. Sixty-three capabilities that existed on disk but had no routing
-path. Fixed in an hour by adding resolver entries.
-
-Run it after every skill change:
-
-```bash
-gbrain doctor
-```
-
-For CI gates, use the JSON-emitting variant:
-
-```bash
-gbrain check-resolvable --json
-gbrain check-resolvable --strict  # warnings fail too
-```
-
-If a skill is unreachable, the output tells you which one and suggests
-the fix. The resolver is a document. Documents are cheap to fix.
-
-## Implementation walkthrough
-
-Three changes. Total time about 45 minutes once you've decided which
-skills go in which tier.
-
-### 1. Audit and tier your skills
-
-Walk through every skill. Ask: does this need to fire on every turn?
-
-- If yes → Tier A.
-- If it fires weekly or less but is real → Tier B.
-- If you don't use it → Tier C.
-
-### 2. Disable Tier B and C in your agent's config
-
-For OpenClaw, the file is `openclaw.json`. Add an entry per disabled skill:
-
-```json
-{
-  "skills": {
-    "entries": {
-      "gift-advisor": { "enabled": false },
-      "flight-tracker": { "enabled": false },
-      "1password": { "enabled": false }
-    }
-  }
-}
-```
-
-The exact config shape depends on which agent runtime you use. The point
-is the same in all of them: tell the runtime not to inject this skill into
-the system prompt. The file stays on disk; only the prompt injection stops.
-
-### 3. Write the resolver
-
-One line per Tier B and Tier C skill. Trigger phrases that match how you
-actually ask for things:
-
-```markdown
-- **gift-advisor**: gift idea | what should I bring | birthday gift
-- **flight-tracker**: track my flight | flight status | when do I land
-- **investor-update-ingest**: investor update | portfolio update | company metrics
-```
-
-That's it. The model handles the rest. When a request doesn't match Tier A,
-it checks the resolver, reads the matching SKILL.md, and executes.
-
-### 4. Run `gbrain doctor` and fix any unreachable skills
-
-The doctor sweep tells you which skills don't have a routing path. Add a
-resolver entry for each one, re-run, repeat until the count is zero.
-
-## A lesson from the first version
-
-I initially converted my resolver from a clean list format to a table
-format because the validator only spoke tables. That was wrong. When a
-tool fails against valid data, the right move is to fix the tool, not
-reshape the data. The list format was correct, compact, readable, easy
-to maintain. The parser needed to support both shapes. v0.41.7.0 is
-that fix.
-
-The same principle applies everywhere in agent systems. Your SKILL.md is
-the source of truth. Your AGENTS.md is the source of truth. Your resolver
-is the source of truth. When tooling disagrees with your configuration,
-the tooling is wrong. Fix the tooling.
-
-## The scaling curve
-
-At 50 skills, you don't need any of this. Just load everything.
-
-At 100, you start feeling the drag but can push through.
-
-At 200, routing accuracy drops and sessions get noticeably slower. This
-is where most people stop adding skills, which means their agent stops
-getting more capable. Bad trade.
-
-At 300+, tiering is mandatory. But with tiering, there's no ceiling.
-1,000 skills with 35 in the hot path and 965 in the resolver is the same
-per-turn cost as 35 skills with no resolver. The cost stays flat.
-Capabilities compound.
-
-The architecture that gets you from 50 to 300 is different from the
-architecture that gets you from 10 to 50. That's normal. Systems that
-scale change shape. The important thing is that each tier preserves full
-capability. You're organizing, not deleting.
-
-## Related
-
-- [Skill development cycle](skill-development.md) — the 5-step loop for
-  turning a repeated task into a real skill.
-- [Skillpacks as scaffolding](skillpacks-as-scaffolding.md) — how to
-  distribute a coherent set of skills across machines and agents.
-- [Sub-agent routing](sub-agent-routing.md) — when to delegate to a
-  sub-agent vs handle in-line, and the model routing table for each path.
-
-GBrain: [github.com/garrytan/gbrain](https://github.com/garrytan/gbrain).
-The `parseResolverEntries` parser lives at
-[`src/core/check-resolvable.ts`](../../src/core/check-resolvable.ts);
-the bundled resolver lives at [`skills/RESOLVER.md`](../../skills/RESOLVER.md).

docs/guides/skillopt.md

@@ -1,147 +0,0 @@
-# `gbrain skillopt` — Self-evolving skills
-
-Treat your `SKILL.md` files as the trainable parameters of an agent that
-itself never changes. Write a benchmark of realistic tasks; SkillOpt watches
-the agent run them, proposes specific edits, re-tests, and only keeps changes
-that measurably improve the score.
-
-Based on [SkillOpt](https://arxiv.org/abs/2605.23904) (Microsoft Research,
-May 2026).
-
-> **New to this?** Start with the hands-on tutorial:
-> [Auto-improve a skill with `gbrain skillopt`](../tutorials/improving-skills-with-skillopt.md).
-> It walks you from "I have a skill" to "I accepted a measurably better version"
-> in ~20 minutes, including how to write your first benchmark. This page is the
-> reference — flags, exit codes, cost model, safety guards.
-
-## The 30-second pitch
-
-```bash
-# 1. Generate a starter benchmark from the skill itself (no routing-eval needed)
-gbrain skillopt my-skill --bootstrap-from-skill
-
-# 2. Review the benchmark — STRENGTHEN the generated judges (they're weak drafts),
-#    then delete the trailing `# BOOTSTRAP_PENDING_REVIEW` line
-
-# 3. Run the optimizer (--split 1:1:1 is required for a ~15-task starter)
-gbrain skillopt my-skill --bootstrap-reviewed --split 1:1:1
-```
-
-That's the entire workflow. (Already have a `routing-eval.jsonl`? Swap step 1 for
-`--bootstrap-from-routing` — but routing tasks test dispatch, not output quality.)
-
-## What's in the box
-
-```
-skills/my-skill/
-  SKILL.md                          ← what gets optimized (body only; D5)
-  skillopt-benchmark.jsonl          ← what success looks like
-  skillopt/
-    best.md                         ← current best version
-    versions/
-      v0001_e1_s1.md                ← per-step snapshots
-      v0002_e1_s2.md
-      ...
-    history.json                    ← append-only run record (D8)
-    rejected.json                   ← bounded LRU of rejected edits
-```
-
-The audit trail lives at `~/.gbrain/audit/skillopt-YYYY-Www.jsonl`
-(ISO-week rotated; honors `GBRAIN_AUDIT_DIR`).
-
-## How the loop works
-
-For each step:
-
-1. **Forward pass.** Run the candidate skill against a batch from `D_train`.
-2. **Backward pass.** Two reflect calls (failures + successes per D7) propose
-   edits to address what worked / didn't work.
-3. **Rank + clip.** Top-N edits within the LR budget (cosine schedule by
-   default; D10 has the ASCII curve in `orchestrator.ts`).
-4. **Apply.** D9 tagged-result patches the body (frontmatter forbidden per
-   D5; ambiguous anchors rejected to the rejected-buffer).
-5. **Validation gate.** D12 median-of-3 + epsilon=0.05: every sel-task runs
-   the judge 3 times, takes the median; only accepts if median > best by
-   more than 0.05.
-6. **Commit.** D8 history-intent-first 5-step atomic write — crash-safe.
-
-After each epoch with no improvement: D6 slow-update fires one meta-edit
-proposal (this lives in v0.42 follow-up; v1 emits the audit event).
-
-## Flags
-
-| Flag | Default | Purpose |
-|---|---|---|
-| `--benchmark <path>` | `skills/<n>/skillopt-benchmark.jsonl` | Path to benchmark JSONL |
-| `--bootstrap-from-skill` | off | Generate a starter benchmark from SKILL.md (recommended; no routing-eval needed) |
-| `--bootstrap-tasks N` | 15 | How many starter tasks `--bootstrap-from-skill` generates (max 50) |
-| `--bootstrap-from-routing` | off | Auto-build benchmark from routing-eval.jsonl |
-| `--bootstrap-reviewed` | off | Required after human-reviewing bootstrap output |
-| `--epochs N` | 4 | Outer-loop iterations |
-| `--batch-size N` | 8 | Tasks per inner step |
-| `--lr N` | 4 | Max edits per step |
-| `--lr-schedule cosine\|linear\|constant` | cosine | Edit-budget decay |
-| `--split TRAIN:SEL:TEST` | 4:1:5 | Ratio; refuses if D_sel < 5 |
-| `--optimizer-model MODEL` | tier.deep | Reflects + proposes |
-| `--target-model MODEL` | tier.subagent | Executes the skill |
-| `--judge-model MODEL` | tier.reasoning | Scores rollouts |
-| `--patch \| --rewrite` | patch | Edit ops only vs. full rewrites |
-| `--dry-run` | off | Cost preview, no LLM calls |
-| `--no-mutate` | off | Write proposed.md, don't replace SKILL.md (no held-out needed) |
-| `--allow-mutate-bundled` | off | Required to mutate gbrain-bundled skills in place — ALSO requires `--held-out` (>=5 rows) or the run hard-refuses |
-| `--held-out <path>` | — | Independent test set (same JSONL shape as the benchmark, task IDs disjoint from it). A candidate that beats the benchmark but regresses on the held-out set is refused. Required for in-place bundled mutation. |
-| `--max-cost-usd N` | 5.00 | Hard cap; preflight refuses if exceeded |
-| `--max-runtime-min N` | 30 | Wall-clock cap |
-| `--force` | off | Bypass dirty-working-tree refusal |
-| `--resume <run-id>` | off | Resume a prior interrupted run |
-| `--json` | off | Machine-readable stdout |
-
-## Exit codes
-
-| Code | Meaning |
-|---|---|
-| 0 | Improved + accepted (or `--no-mutate` proposed.md written) |
-| 1 | No improvement; best skill unchanged |
-| 2 | Aborted by gate (dirty tree, over budget, bench validation, etc.) |
-
-## Cost model
-
-A typical 20-task benchmark with defaults costs ~$0.90 per run:
-
-- 32 rollouts × Sonnet ($0.009 each) ≈ $0.29
-- 8 reflect calls × Opus (cached) ≈ $0.25
-- 24 sel-judges × Sonnet (cached) ≈ $0.10
-- Final test eval ≈ $0.07
-- **Total ≈ $0.71**
-
-For a 100-task benchmark: ~$5.00 (right at the default cap). Preflight
-refuses to start when the estimate exceeds `--max-cost-usd`.
-
-## Safety guards (the cathedral)
-
-| Guard | Decision | What it prevents |
-|---|---|---|
-| Validation gate is mandatory | D12 (paper) | Accepting LLM judge noise as improvement |
-| Frontmatter mutation forbidden | D5 | Routing surface drift (`check-resolvable` regression) |
-| Per-skill DB lock | D14 | Two concurrent runs corrupting history/versions |
-| Bundled-skill gate | D16 | Auto-mutating skills shipped with gbrain (in-place mutation requires `--allow-mutate-bundled` + a `--held-out` set of >=5 benchmark-disjoint tasks; else hard-refuse + proposed.md) |
-| Held-out gate | F11 | Accepting a candidate that overfits its own benchmark — `--held-out` refuses a candidate whose held-out score regresses below baseline |
-| Bootstrap review sentinel | D15 | Self-referential benchmark gaming |
-| Read-only tool sandbox in rollouts | D13 | Optimization runs writing junk pages to your brain |
-| History-intent-first atomic commit | D8 | Half-written SKILL.md on crash |
-| Cost preflight | D3 | Surprise mid-run budget exhaustion |
-| Dirty-tree refusal | dry-fix pattern | Overwriting your uncommitted changes |
-
-## When NOT to use SkillOpt
-
-- **No benchmark.** Optimizing against guesses is worse than not optimizing.
-- **Write-flavored skills.** Skills whose job is to `put_page` heavily can't
-  use the v1 read-only sandbox; mocked-write capture is a v0.42 follow-up.
-- **Tiny benchmarks (<10 tasks).** D_sel < 5 refuses by default; meaningful
-  validation needs ≥20 tasks total per the paper.
-
-## Related skills
-
-- `gbrain skillify scaffold <name>` — create a new skill (use BEFORE skillopt)
-- `gbrain skillpack-check <name>` — audit conformance + skillopt status
-- `gbrain check-resolvable` — routing MECE validation (NOT mutated by skillopt)

docs/guides/upgrades-auto-update.md

@@ -16,34 +16,6 @@ benefit-focused bullets, waits for explicit permission, then runs the full
 upgrade flow including re-reading skills, running migrations, and syncing
 schema. The user gets new capabilities automatically.
 
-## Self-upgrade modes (v0.42)
-
-gbrain now stays current the way gstack does: it rides invocation frequency. A
-throttled, cache-read-only check runs at the start of every `gbrain` invocation
-(CLI and MCP) and emits an `UPGRADE_AVAILABLE <old> <new>` marker on stderr. No
-host cron required — every agent kind (Claude Code, Codex, OpenClaw, Hermes, the
-`gbrain serve` host behind a Perplexity thin client) converges to current by
-construction. The behavior is governed by one file-plane config key,
-`self_upgrade.mode`:
-
-| Mode | Behavior | Who it's for |
-|------|----------|--------------|
-| `notify` (default) | Emit the marker + a 4-option prompt; never apply without confirmation. | Interactive installs / anyone with a human in the loop. |
-| `auto` (opt-in) | Apply silently, but ONLY during quiet hours, ONLY when the brain is idle, doctor-gated, and never re-trying a known-bad version. | Headless / always-on installs (autopilot daemon, the `gbrain serve` host). |
-| `off` | Never check. | Air-gapped / pinned installs. |
-
-Enable hands-off upgrades on an always-on install with one line:
-
-```bash
-gbrain config set self_upgrade.mode auto
-```
-
-`auto` is deliberately NOT a default anywhere — it's an explicit autonomy grant,
-because applying code from GitHub unattended is, by design, remote code
-execution. The trust model is TLS + GitHub (same as `gbrain upgrade`);
-signature verification is a tracked follow-up. Apply manually any time with
-`gbrain self-upgrade`.
-
 ## Implementation
 
 ### The Check (cron-initiated)
@@ -94,11 +66,7 @@ what they can DO now that they couldn't before, not what files changed.
 | daily | Store preference, switch cron back to daily |
 | stop / unsubscribe / no more | Disable the cron. Tell user how to resume |
 
-**In `notify` mode (the default), never auto-upgrade — always wait for explicit
-confirmation.** The `auto` mode (opt-in, see "Self-upgrade modes" above) is the
-only path that applies without a prompt, and only under its conservative gates
-(quiet hours + idle + doctor-gate). This per-cron-prompt flow is the `notify`
-experience.
+**Never auto-upgrade.** Always wait for explicit confirmation.
 
 ### The Full Upgrade Flow (after user says yes)
 
@@ -175,13 +143,10 @@ copy. Set up a weekly cron to check automatically.
 
 ## Tricky Spots
 
-1. **In `notify` mode, never auto-install.** The upgrade waits for the user's
-   explicit "yes." Even if the check detects an update and the changelog looks
-   great, the agent messages the user and waits. The `auto` mode (opt-in) exists
-   for headless/always-on installs where there's no human to prompt — it applies
-   only during quiet hours, only when idle, doctor-gated, never retrying a
-   known-bad version. Don't enable `auto` on an interactive workstation; the
-   prompt-first `notify` flow is the right default there.
+1. **Never auto-install.** The upgrade must always wait for the user's explicit
+   "yes." Even if the cron detects an update at 9 AM and the changelog looks
+   great, the agent messages the user and waits. Auto-installing can break
+   workflows, introduce breaking changes, or interrupt work in progress.
 
 2. **Migration files are agent instructions, not scripts.** They tell the agent
    what to do step by step in plain language. They are NOT bash scripts to

docs/incidents/2026-05-20-lsd-cost-explosion.md

@@ -208,10 +208,9 @@ architectural rounds shipped in the budget-cathedral wave that followed:
 - **P3 (judge chunking):** `runJudge` in `src/core/brainstorm/judges.ts`
   auto-chunks at 100 ideas/call. Context-window overflow is structurally
   prevented.
-- **P4 (unicode sanitization):** `ensureWellFormed` (in `src/core/text-safe.ts`,
-  used by `src/core/brainstorm/orchestrator.ts`) replaces unpaired surrogates
-  with U+FFFD before serialization. (Consolidated from the original hand-rolled
-  `sanitizeUnicode` in v0.42.40.0 / #2011.)
+- **P4 (unicode sanitization):** `sanitizeUnicode` in
+  `src/core/brainstorm/orchestrator.ts` strips unpaired surrogates before
+  serialization.
 - **P5 (BudgetTracker at the gateway layer):** new
   `src/core/budget/budget-tracker.ts` is the canonical primitive. The
   gateway's `withBudgetTracker(tracker, fn)` composes via

docs/integrations/embedding-providers.md

@@ -34,7 +34,7 @@ The resolved provider + dimensions get persisted to `~/.gbrain/config.json` atom
 | `zhipu` | `ZHIPUAI_API_KEY` | 1024 | varies | no | no |
 | `ollama` | (none — runs locally) | 768 | 0 | yes | no |
 | `llama-server` | (none — runs locally) | user-set | 0 | yes | no |
-| `litellm` | `LITELLM_API_KEY` (optional) | user-set | varies | yes (proxy) | yes (backend permitting) |
+| `litellm` | `LITELLM_API_KEY` (optional) | user-set | varies | yes (proxy) | no |
 | `together` | `TOGETHER_API_KEY` | 768 | varies | no | no |
 | `anthropic` | (no embedding model — chat only) | — | — | — | — |
 | `deepseek` | (no embedding model — chat only) | — | — | — | — |
@@ -63,8 +63,7 @@ The doctor distinguishes two repair paths:
 - **Cost-sensitive, English-only**: Ollama (free, local) or Voyage (paid, best quality per dollar).
 - **Quality-first**: Voyage `voyage-4-large` (1024-2048 dims, ~3-4× more dense tokens than OpenAI tiktoken).
 - **Code-heavy brain (gstack per-worktree, source repos)**: Voyage `voyage-code-3` (1024 default; supports 256/512/1024/2048). Tuned on programming languages. Voyage publishes head-to-head numbers showing it outperforms their general flagships on code retrieval ([voyageai.com/blog](https://voyageai.com/blog)). For gstack's per-worktree pglite-backed code brain, this is the right default — see Topology 3 in `docs/architecture/topologies.md`.
-- **Reranking pair**: ZeroEntropy `zerank-2` is the hosted default in `tokenmax` mode (see [`docs/ai-providers/zeroentropy.md`](../ai-providers/zeroentropy.md)). Voyage `rerank-2.5` pairs cleanly with Voyage embeddings.
-- **Local reranking (no API spend)**: `llama-server-reranker` recipe (v0.40.6.1) — point gbrain at your own `llama-server --reranking` instance running Qwen3-Reranker or self-hosted ZeroEntropy weights. Same `gateway.rerank()` seam, $0 per call. Walkthrough in [`docs/ai-providers/llama-server-reranker.md`](../ai-providers/llama-server-reranker.md).
+- **Reranking pair**: Voyage (their reranker `rerank-2.5` pairs cleanly with Voyage embeddings).
 - **One key for many hosted models**: OpenRouter. Set `OPENROUTER_API_KEY` and use `openrouter:<provider>/<model>` for chat against GPT-5.2, Claude 4.x, Gemini 3, DeepSeek, and dozens more without juggling per-provider keys. Embedding catalog includes OpenAI, Google, Qwen, BGE-M3.
 - **Enterprise compliance**: Azure OpenAI (data residency + private endpoints) or self-hosted via llama-server / Ollama.
 - **China region**: DashScope (Alibaba) or Zhipu (BigModel). DashScope's international endpoint at `dashscope-intl.aliyuncs.com`; override `provider_base_urls.dashscope` for the China endpoint.
@@ -77,8 +76,6 @@ The doctor distinguishes two repair paths:
 
 Default. Set `OPENAI_API_KEY`. Models: `text-embedding-3-large` (3072 max, 1536 default), `text-embedding-3-small` (1536). Matryoshka via the `dimensions` field — gbrain pins it from `embedding_dimensions` config so existing 1536-dim brains stay aligned across SDK upgrades.
 
-Optional `OPENAI_BASE_URL` — point the native OpenAI provider at an OpenAI-compatible gateway. A bare host is normalized to carry the `/v1` suffix automatically (so `https://gw.example.com` and `https://gw.example.com/v1` both work); when unset, the SDK's default endpoint is untouched. `ANTHROPIC_BASE_URL` gets the same normalization for Anthropic chat/expansion calls.
-
 ### Voyage AI
 
 Best-in-class quality on the Voyage 4 family (Jan 2026 release). Set `VOYAGE_API_KEY`. Models: `voyage-4-large`, `voyage-4`, `voyage-4-lite`, `voyage-4-nano`, `voyage-3.5`, `voyage-code-3` (code-tuned), `voyage-finance-2`, `voyage-law-2`, `voyage-multimodal-3` (text + image).
@@ -143,15 +140,13 @@ Set `ZHIPUAI_API_KEY`. Models: `embedding-3` (current; Matryoshka 256-2048 dims)
 
 No env required — Ollama runs unauthenticated locally. Optional `OLLAMA_BASE_URL` (default `http://localhost:11434/v1`) and `OLLAMA_API_KEY` (for auth-enabled deployments).
 
-Recipe ships with `nomic-embed-text` (768d, recommended), `mxbai-embed-large` (1024d), `all-minilm` (384d), plus the larger modern embedders `qwen3-embed-8b` (4096d) and `snowflake-arctic-embed-l-v2` (1024d). `gbrain providers test --model ollama:nomic-embed-text` smoke-tests the local install.
-
-The recipe default is `nomic-embed-text`'s 768 dims. If you run one of the larger models, declare its native dimension with `--embedding-dimensions <N>` at init — gbrain trusts the value you declare for local recipes instead of rejecting a non-768 width.
+Recipe ships with `nomic-embed-text` (768d, recommended), `mxbai-embed-large` (1024d), `all-minilm` (384d). `gbrain providers test --model ollama:nomic-embed-text` smoke-tests the local install.
 
 ### llama-server (local, llama.cpp)
 
 `llama.cpp`'s `llama-server --embeddings` endpoint. No env required. Optional `LLAMA_SERVER_BASE_URL` (default `http://localhost:8080/v1`) and `LLAMA_SERVER_API_KEY`.
 
-User-driven models: launch llama-server with `--model <gguf-path> --embeddings`, then run `gbrain init --embedding-model llama-server:<your-id> --embedding-dimensions <N>`. gbrain trusts the dimension you declare (you know the GGUF you launched); the recipe refuses the implicit shorthand `--model llama-server` because there's no canonical first model.
+User-driven models: launch llama-server with `--model <gguf-path> --embeddings`, then run `gbrain init --embedding-model llama-server:<your-id> --embedding-dimensions <N>`. The recipe refuses the implicit shorthand `--model llama-server` because there's no canonical first model.
 
 ### LiteLLM proxy (universal escape hatch)
 
@@ -159,8 +154,6 @@ Run [LiteLLM](https://docs.litellm.ai/docs/proxy/quick_start) in front of any pr
 
 This is the catch-all for "my provider isn't in the list above." Set up LiteLLM, then `gbrain init --embedding-model litellm:<your-model-id> --embedding-dimensions <N>`.
 
-**Include the `/v1` suffix in `LITELLM_BASE_URL` if your proxy serves the OpenAI route there** (e.g. `http://localhost:4000/v1`). Many LiteLLM deployments expose the OpenAI-compatible API only under `/v1`; pointing gbrain at the bare host 404s or fails authentication with no hint. gbrain trusts the dimension you declare for the proxy-backed model — the proxy's backend, not gbrain, decides the true width — so `--embedding-dimensions <N>` is required and accepted as-is.
-
 ## Choosing dimensions
 
 Three numbers matter:
@@ -189,3 +182,5 @@ The supported paths:
 - **Postgres (Supabase / self-hosted):** follow the SQL recipe in `docs/embedding-migrations.md` (drop the HNSW index, ALTER COLUMN TYPE, clear stale embeddings, recreate the index conditionally, then `gbrain init --supabase --embedding-model X --embedding-dimensions N` to update the file plane and re-embed).
 
 `gbrain doctor` 8c "alternative_providers" surfaces unconfigured providers whose env is already set — useful when you've configured OpenAI but also have e.g. `VOYAGE_API_KEY` exported and want to know you can switch without extra setup.
+
+`gbrain doctor` 8c "alternative_providers" surfaces unconfigured providers whose env is already set — useful when you've configured OpenAI but also have e.g. `VOYAGE_API_KEY` exported and want to know you can switch without extra setup.

docs/integrations/pre-commit.md

@@ -7,7 +7,7 @@ brain source's repo that runs `gbrain frontmatter validate` against staged
 
 ## What the hook catches
 
-The same eight validation classes the `frontmatter-guard` skill and
+The same seven validation classes the `frontmatter-guard` skill and
 `gbrain doctor`'s `frontmatter_integrity` subcheck report:
 
 | Code              | What it catches                                                     |
@@ -18,7 +18,6 @@ The same eight validation classes the `frontmatter-guard` skill and
 | `SLUG_MISMATCH`   | `slug:` in frontmatter doesn't match path-derived slug              |
 | `NULL_BYTES`      | Binary corruption (`\x00`) anywhere in the content                  |
 | `NESTED_QUOTES`   | `title: "outer "inner" outer"` shape that breaks YAML               |
-| `NON_STRING_FIELD` | `title`/`type`/`slug` is an unquoted non-string scalar (`title: 123`) |
 | `EMPTY_FRONTMATTER` | `---` ... `---` with nothing meaningful between                   |
 
 ## Install

docs/mcp/CLAUDE_CODE.md

@@ -1,10 +1,5 @@
 # Connect GBrain to Claude Code
 
-> New to this? The [Give your coding agent a memory](../tutorials/connect-coding-agent.md)
-> tutorial walks both paths (local-from-nothing and connect-to-an-existing-brain)
-> end to end, plus the brain-first protocol that makes it worth it. This page is
-> the connection reference.
-
 ## Option 1: Local (recommended, zero server needed)
 
 ```bash
@@ -14,44 +9,10 @@ claude mcp add gbrain -- gbrain serve
 That's it. Claude Code spawns `gbrain serve` as a stdio subprocess. No server, no
 tunnel, no token needed. Works with both PGLite and Supabase engines.
 
-## Option 2: Remote, one command (fastest from a bearer token)
+## Option 2: Remote (access from any machine)
 
-If GBrain is running somewhere as an HTTP server (`gbrain serve --http`, see the
-[ngrok-tunnel recipe](../../recipes/ngrok-tunnel.md)) and you have a bearer token,
-let `gbrain connect` generate the wire-up for you.
-
-On the host (or anywhere `gbrain` is installed), mint a token and print the block:
-
-```bash
-gbrain auth create "claude-code"
-gbrain connect https://YOUR-DOMAIN.ngrok.app/mcp --token gbrain_xxx
-```
-
-`gbrain connect` prints a short, copy-paste block. Paste it into Claude Code — it
-runs the `claude mcp add` for you and tells the agent to call `get_brain_identity`
-and `list_skills` so it immediately knows what the brain can do.
-
-Already on the machine you want to wire up? Skip the copy-paste and let `connect`
-do it directly, with a built-in token smoke-test:
-
-```bash
-gbrain connect https://YOUR-DOMAIN.ngrok.app --token gbrain_xxx --install
-```
-
-(`--install` runs `claude mcp add`, then verifies the token by calling
-`get_brain_identity` — so a wrong or expired token fails now, not silently on the
-agent's first request. The URL is normalized: a bare host without `/mcp` gets it
-appended; pass an explicit `https://` scheme.)
-
-Pipe-friendly machine output (token redacted unless `--show-token`):
-
-```bash
-gbrain connect https://YOUR-DOMAIN.ngrok.app/mcp --token gbrain_xxx --json
-```
-
-## Option 3: Remote, manual `claude mcp add`
-
-Equivalent to what `gbrain connect` generates, if you'd rather run it yourself:
+If you have GBrain running on a server with a public tunnel (see
+[ngrok-tunnel recipe](../../recipes/ngrok-tunnel.md)):
 
 ```bash
 claude mcp add gbrain -t http \
@@ -59,12 +20,8 @@ claude mcp add gbrain -t http \
   -H "Authorization: Bearer YOUR_TOKEN"
 ```
 
-Replace `YOUR-DOMAIN` with your ngrok domain and `YOUR_TOKEN` with a token from
-`gbrain auth create "claude-code"`.
-
-> A `gbrain auth create` token is a long-lived, full-access secret. Keep it
-> private (it lands in `~/.claude.json`), and prefer a scoped/short-lived token
-> where your host supports one.
+Replace `YOUR-DOMAIN` with your ngrok domain and `YOUR_TOKEN` with a token
+from `gbrain auth create "claude-code"`.
 
 ## Verify
 
@@ -76,13 +33,6 @@ search for [any topic in your brain]
 
 You should see results from your GBrain knowledge base.
 
-> **`list_skills` returns nothing?** Skill discovery is gated by `mcp.publish_skills`
-> on the host. New brains from `gbrain init` default it ON; brains upgraded from an
-> older release stay OFF until you opt in. Enable it on the host with
-> `gbrain config set mcp.publish_skills true`. The core tools (search, query,
-> get_page, put_page, think, find_experts) work regardless. Note: `capture` is a
-> CLI-only command, not an MCP tool — the agent writes over MCP with `put_page`.
-
 ## Remove
 
 ```bash

docs/mcp/CODEX.md

@@ -1,71 +0,0 @@
-# Connect GBrain to Codex
-
-> New to this? The [Give your coding agent a memory](../tutorials/connect-coding-agent.md)
-> tutorial walks both paths (local-from-nothing and connect-to-an-existing-brain)
-> end to end, plus the brain-first protocol that makes it worth it. This page is
-> the connection reference.
-
-Codex CLI (`@openai/codex`, v0.130+) supports remote streamable-HTTP MCP servers
-with a bearer token read from an environment variable. The token lives in your
-shell env, not in Codex's config file.
-
-## Fastest path: `gbrain connect`
-
-Run anywhere `gbrain` is installed (mint a token on the brain host first):
-
-```bash
-gbrain auth create "codex"
-gbrain connect https://YOUR-DOMAIN.ngrok.app/mcp --token gbrain_xxx --agent codex
-```
-
-This prints a copy-paste block. Or wire it up directly and smoke-test the token:
-
-```bash
-gbrain connect https://YOUR-DOMAIN.ngrok.app/mcp --token gbrain_xxx --agent codex --install
-```
-
-`--install` runs `codex mcp add` for you, then makes one real call to the brain so
-a wrong/expired token fails right away. Because Codex reads the token from the env
-var at runtime, keep `GBRAIN_REMOTE_TOKEN` exported in your shell profile.
-
-## Manual setup
-
-```bash
-export GBRAIN_REMOTE_TOKEN=gbrain_xxx
-codex mcp add gbrain --url https://YOUR-DOMAIN.ngrok.app/mcp \
-  --bearer-token-env-var GBRAIN_REMOTE_TOKEN
-```
-
-Codex stores the env-var *name* (`GBRAIN_REMOTE_TOKEN`), not the token itself, and
-reads the value when it launches the MCP server. Add the `export` line to your
-`~/.zshrc` / `~/.bashrc` so it's set in every session.
-
-## Verify
-
-In Codex, ask it to use the brain:
-
-```
-Call get_brain_identity, then search my brain for [topic].
-```
-
-`get_brain_identity` confirms whose brain you're connected to; `list_skills` shows
-everything it can do.
-
-> **`list_skills` empty?** It's gated by `mcp.publish_skills` on the host (default
-> ON for `gbrain init` brains, OFF for brains upgraded from older releases). Enable
-> it on the host: `gbrain config set mcp.publish_skills true`. The core tools
-> (search, query, get_page, put_page, think, find_experts) work regardless.
-> `capture` is CLI-only, not an MCP tool — write over MCP with `put_page`.
-
-## Remove
-
-```bash
-codex mcp remove gbrain
-```
-
-## Notes
-
-- The token is a long-lived, full-access secret. Keep `GBRAIN_REMOTE_TOKEN` out of
-  version control and prefer a scoped token if your host supports one.
-- Local stdio also works if you run the brain on the same machine:
-  `codex mcp add gbrain -- gbrain serve`.

docs/mcp/DEPLOY.md

@@ -74,20 +74,13 @@ to the HTTP server, so no migration is required.
 gbrain serve --http --port 3131
 ```
 
-On first start in an interactive terminal, the server prints an **admin
-bootstrap token** to stderr:
+On first start, the server prints an **admin bootstrap token** to stderr:
 
 ```
 Admin bootstrap token: 3a1f9c...
 Open http://localhost:3131/admin and paste it to log in.
 ```
 
-On a non-TTY start (systemd, Docker, any piped or captured logs) the generated
-token is hidden so it never lands in log storage. For headless deploys either
-set `GBRAIN_ADMIN_BOOTSTRAP_TOKEN` to a value you control before starting, or
-run `gbrain serve --http --print-admin-token` once on a trusted terminal to
-force printing.
-
 Save this token. Open `http://localhost:3131/admin` and paste it to access the
 dashboard. The dashboard shows live activity, registered clients, request logs,
 and per-client config export.

docs/mcp/PERPLEXITY.md

@@ -1,83 +1,20 @@
 # Connect GBrain to Perplexity Computer
 
-Perplexity Computer connects as a **remote** MCP client, so GBrain must be served
-over HTTP and reachable at a public HTTPS URL. Perplexity does not run
-`gbrain serve` (stdio) the way Claude Code does — it needs a reachable endpoint:
+Perplexity Computer supports remote MCP servers with bearer token authentication.
 
-```
-Perplexity Computer
-  → ngrok tunnel (https://YOUR-DOMAIN.ngrok.app/mcp)
-  → gbrain serve --http   (built-in OAuth 2.1 transport)
-  → Postgres / PGLite
-```
+## Setup
 
-## 1. Serve GBrain over HTTP (host side)
-
-```bash
-gbrain serve --http --port 3131 --bind 0.0.0.0 \
-  --public-url https://YOUR-DOMAIN.ngrok.app
-```
-
-- **`--bind 0.0.0.0` is required.** Since v0.34, `--http` defaults to
-  `127.0.0.1`, so without it the tunnel reaches the server but the connection is
-  refused (`ECONNREFUSED`).
-- **`--public-url` must match the tunnel.** The OAuth issuer in the discovery
-  metadata has to line up with the URL Perplexity actually hits (RFC 8414 §3.3),
-  or OAuth client-credentials auth fails.
-
-## 2. Expose it with a tunnel
-
-```bash
-ngrok http 3131 --url YOUR-DOMAIN.ngrok.app
-```
-
-See the [ngrok-tunnel recipe](../../recipes/ngrok-tunnel.md) for a persistent
-tunnel.
-
-## 3. Create credentials
-
-Two supported auth paths.
-
-**OAuth 2.1 client credentials (recommended, v0.26.0+).** Perplexity is a cloud
-service, so it holds whatever credential you give it. OAuth is the correct choice:
-least-privilege scopes + short-lived rotating access tokens instead of a
-long-lived full-access secret. Mint a client and print the connector fields in
-one step (on the brain host):
-
-```bash
-gbrain connect https://YOUR-DOMAIN.ngrok.app/mcp --agent perplexity --oauth --register
-```
-
-Or register separately and pass the creds (works anywhere, no DB needed):
-
-```bash
-gbrain auth register-client perplexity --grant-types client_credentials --scopes "read write"
-gbrain connect https://YOUR-DOMAIN.ngrok.app/mcp --agent perplexity --oauth \
-  --client-id gbrain_cl_xxx --client-secret gbrain_cs_xxx
-```
-
-`connect --oauth` prints the **Issuer URL + Client ID + Client Secret** to paste
-in step 4.
-
-**Legacy bearer token (simplest, best for local/personal):**
-
-```bash
-gbrain auth create "perplexity"
-gbrain connect https://YOUR-DOMAIN.ngrok.app/mcp --token gbrain_xxx --agent perplexity
-```
-
-(Perplexity is a GUI connector, so there's no `--install` — `connect` prints the
-exact values to paste in step 4.)
-
-## 4. Add the connector in Perplexity
-
-1. Open Perplexity (requires Pro subscription).
-2. Go to **Settings → Connectors** (or **MCP Servers**).
+1. Open Perplexity (requires Pro subscription)
+2. Go to **Settings > Connectors** (or **MCP Servers**)
 3. Add a new remote connector:
    - **URL:** `https://YOUR-DOMAIN.ngrok.app/mcp`
-   - **Authentication:** API Key / Bearer Token, or OAuth client credentials
-   - Paste the token (bearer) or `client_id` + `client_secret` (OAuth).
-4. Save.
+   - **Authentication:** API Key / Bearer Token
+   - **Token:** your GBrain access token
+     (create one with `gbrain auth create "perplexity"`)
+4. Save
+
+Replace `YOUR-DOMAIN` with your ngrok domain (see
+[ngrok-tunnel recipe](../../recipes/ngrok-tunnel.md) for setup).
 
 ## Verify
 
@@ -87,14 +24,8 @@ In a Perplexity conversation, ask it to use your brain:
 Use my GBrain to search for [topic]
 ```
 
-Have it call `get_brain_identity` (whose brain this is), then `list_skills`
-(everything it can do).
-
 ## Notes
 
-- Perplexity Computer is available to Pro subscribers; both the Mac app and web
-  version support remote MCP connectors.
-- The Mac app can also use a local MCP server (`gbrain serve` stdio) if you'd
-  rather not expose an HTTP endpoint.
-- A `gbrain auth create` token is a long-lived, full-access secret. Keep it
-  private and prefer a scoped token where possible.
+- Perplexity Computer is available to Pro subscribers
+- Both the Perplexity Mac app and web version support MCP connectors
+- The Mac app also supports local MCP servers if you prefer `gbrain serve` (stdio)

docs/migrations/v0.41.2-markdown-greenfield.md

@@ -1,153 +0,0 @@
-# Migrating your OpenClaw brain to gbrain v0.41.2.0 (greenfield)
-
-The v0.41.2.0 lens packs ship a one-shot importer that re-ingests your
-existing OpenClaw brain (`~/git/brain/atoms/`, `concepts/`, `ideas/`)
-through the new ingestion cathedral. Pages land in gbrain with an
-`imported_from: markdown-greenfield` frontmatter marker so the new
-extract_atoms + synthesize_concepts cycle phases skip them (lossless
-import with provenance).
-
-## Before you migrate
-
-1. **Upgrade gbrain to v0.41.2.0+:**
-   ```bash
-   gbrain upgrade
-   gbrain --version  # should be 0.41.2.0 or later
-   ```
-
-2. **Activate the creator pack** (or gbrain-everything if you also
-   want investor + engineer lenses on the same brain):
-   ```bash
-   gbrain config set schema_pack gbrain-creator
-   # OR
-   gbrain config set schema_pack gbrain-everything
-   ```
-
-3. **Apply schema migration v94** (take_domain_assignments table):
-   ```bash
-   gbrain apply-migrations --yes
-   ```
-
-## The dry-run pass
-
-Always start with `--dry-run` to see what the importer would do
-without writing anything:
-
-```bash
-gbrain capture --source markdown-greenfield \
-  --repo ~/git/brain \
-  --dry-run \
-  --limit 100
-```
-
-The output reports:
-- `emitted` — atoms/concepts/ideas that would import cleanly
-- `skipped_no_type` — files without a `type:` frontmatter (counted
-  as benign skips; no audit appended)
-- `skipped_invalid` — files that failed validation (these append to
-  `~/.gbrain/audit/markdown-greenfield-failures-YYYY-Www.jsonl`)
-
-Inspect the audit JSONL:
-```bash
-ls ~/.gbrain/audit/markdown-greenfield-failures-*.jsonl
-cat ~/.gbrain/audit/markdown-greenfield-failures-*.jsonl | jq .
-```
-
-Common failures:
-- **Empty frontmatter** — file has `---` but no fields. Not a real
-  brain page; safe to leave skipped.
-- **Malformed YAML** — fix the file in your OpenClaw then re-run.
-- **Missing required field** — usually means the original OpenClaw
-  skill output a partial page; check whether the file is worth
-  preserving.
-
-## The actual import
-
-When the dry-run looks clean, drop the `--dry-run` and `--limit`
-flags:
-
-```bash
-gbrain capture --source markdown-greenfield --repo ~/git/brain
-```
-
-Expect ~30-60 minutes for the full 24K-page set (atoms + concepts +
-ideas). The importer:
-
-1. Walks `atoms/{YYYY-MM-DD}/*.md`, `concepts/*.md`, `ideas/*.md` in
-   deterministic alphabetical order so partial-run resumes pick up
-   where they left off.
-2. Stamps `imported_from: markdown-greenfield` + `imported_at:
-   <ISO timestamp>` on every page's frontmatter, preserving ALL
-   original fields verbatim under `metadata.original_frontmatter`.
-3. Emits each as an IngestionEvent with `mode: 'migration'` (T2),
-   which bypasses the daemon's 24h DedupWindow. The importer owns
-   its own permanent slug-keyed idempotency.
-4. Routes through `put_page` so pages land with proper FK chains and
-   embedding eligibility.
-
-## After the import
-
-Verify counts match:
-```bash
-gbrain stats
-# Should show ~24K new pages with type=atom/concept/idea
-```
-
-The next `gbrain dream` cycle will:
-- Run `extract_atoms` on NEW transcripts (skips pages with the
-  `imported_from` marker — your historical atoms are frozen, not
-  re-extracted).
-- Run `synthesize_concepts` on NEW atoms (skips imported concepts
-  for the same reason).
-- Run `extract_facts` over the imported pages — facts fences in
-  imported atoms/concepts populate the facts table normally.
-
-## Retiring your OpenClaw's parallel crons
-
-After verifying the import, retire your OpenClaw's parallel atom
-pipeline cron entries. In `~/git/your-openclaw/workspace/cron.json`:
-
-- Remove `atom-pipeline-coordinator` (every-30-min cron)
-- Remove `atom-backfill-coordinator` (every-10-min cron)
-
-Replace with nothing — gbrain's autopilot already runs extract_atoms +
-synthesize_concepts inside every dream cycle when gbrain-creator (or
-gbrain-everything) is the active pack.
-
-The OpenClaw skills themselves shrink to thin wrappers:
-
-- `content-atom-extractor` → calls `gbrain dream --phase extract_atoms`
-- `concept-synthesis` → calls `gbrain dream --phase synthesize_concepts`
-- `atom-backfill-coordinator` → DELETED (backfill is now part of
-  extract_atoms via the Source Quote + lesson enrichment in one
-  Haiku call per transcript)
-
-## Rolling back
-
-The import is fully reversible:
-
-```bash
-# Soft-delete every page with the marker (recoverable for 72h)
-gbrain query "imported_from:markdown-greenfield" --type atom --json | \
-  jq -r '.[].slug' | xargs -I{} gbrain pages delete {}
-# OR hard-delete past the soft-delete window
-gbrain pages purge-deleted --older-than 0h
-```
-
-Your OpenClaw's `~/git/brain/atoms/` + `concepts/` + `ideas/` directories
-are untouched by the importer — they remain the source of truth for
-rollback. The greenfield importer only READS from them.
-
-## Re-running after partial failures
-
-The importer is idempotent at the page-slug level: re-running on the
-same `--repo` produces zero net-new pages (every page either lands
-fresh or matches an existing slug). If you fix some validation
-failures in your OpenClaw and want to retry just those:
-
-```bash
-gbrain capture --source markdown-greenfield --repo ~/git/brain
-```
-
-Already-imported pages stay; previously-failed pages get a fresh
-attempt; the audit JSONL accumulates per-week (ISO week file rotation).

docs/operations/spend-controls.md

@@ -1,111 +0,0 @@
-# Spend controls
-
-GBrain's embedding-spend gates in one place: every gate, its config key, default,
-whether it blocks or just informs, how to widen or disable it, and how the
-`spend.posture` switch governs all of them.
-
-The orienting idea: **GBrain itself is rounding error; the spend that matters is
-downstream embedding.** These gates exist so a routine sync or enrich can't run up
-an unexpected embedding bill, while never wedging an unattended cron.
-
-## `spend.posture` — one switch for "cost is not my constraint"
-
-```bash
-gbrain config set spend.posture tokenmax   # all cost gates become informational
-gbrain config set spend.posture gated      # default — gates enforce
-```
-
-| Value | Effect |
-|-------|--------|
-| `gated` (default) | Every cost gate enforces its limit as documented below. |
-| `tokenmax` | Every cost gate prints its estimate and **proceeds** — informational only. Spend is still recorded to the ledger; posture removes the *ceiling*, not the *accounting*. |
-
-`spend.posture` is deliberately separate from `search.mode=tokenmax` (which governs
-retrieval payload size, not embedding spend). When a gate fires and
-`search.mode=tokenmax` but `spend.posture` is unset, the gate prints a one-line hint
-pointing at this switch.
-
-**Precedence:** an explicit per-call cap (`--max-usd N`, `--max-cost N`) always wins
-over posture. `tokenmax` only governs the default/absent case — it never overrides a
-number you typed on the command line.
-
-## Off switches (`off` / `unlimited` / `none`)
-
-The USD-limit knobs accept `off`, `unlimited`, or `none` (case-insensitive) to mean
-"no limit" — no more setting sentinel values like `100000`.
-
-- `0` is **not** "off". On `sync.cost_gate_min_usd`, `0` means "block on any nonzero
-  spend" (a real choice). On the backfill caps, `0` falls back to the default.
-- Internally "no limit" is the string `unlimited` in any printed/JSON output and "no
-  cap" inside the budget tracker — never a raw `Infinity` (which would serialize to
-  `null` in ledger rows).
-
-## The gates
-
-| Gate | Config key | Default | Blocks? | Off switch | tokenmax |
-|------|-----------|---------|---------|-----------|----------|
-| Sync inline-embed cost gate | `sync.cost_gate_min_usd` | `0.50` | TTY prompt / non-TTY auto-defer | `off` (or `0` = block-on-any) | informational |
-| Backfill 24h per-source spend cap | `embed.backfill_max_usd_per_source_24h` | `25` | refuses submission | `off` (`0` → default) | bypassed (still ledgered) |
-| Backfill per-job budget | `embed.backfill_max_usd` | `10` | caps the job's tracker | `off` (`0` → default) | uncapped (still ledgered) |
-| Backfill cooldown | `embed.backfill_cooldown_min` | `10` | skips re-submission inside window | — (latency knob, not spend) | **not** bypassed |
-| `reindex-code` cost gate | — (preview before re-embed) | — | TTY prompt / non-TTY refuse + exit 2 | `--max-cost off` | informational |
-| `enrich` / `onboard --auto` | `--max-usd` (per-call) | — | refuse without a cap (non-TTY) | `--max-usd off` | runs uncapped (still ledgered) |
-
-### Sync inline-embed cost gate
-
-Fires only when sync embeds **inline** (federated_v2 off, or `--serial` without
-`--no-embed`). Under federated_v2 + parallel, embedding is deferred to capped backfill
-jobs and the gate is informational. The estimate prices the **delta** — the files this
-sync will actually import (fetched-first, so it sees commits the run is about to pull) —
-not the whole tree. A busy brain with a dirty working tree but caught-up commits
-estimates `$0`, because an attached-HEAD sync imports only the committed diff.
-
-Behavior above the floor:
-- **TTY:** prompts `[y/N]`.
-- **Non-interactive (cron/agent):** **auto-defers** embeds to capped backfill jobs and
-  exits 0 — it never wedges the pipeline. The backlog drains via the jobs worker or
-  `gbrain embed --stale`. Pass `--yes` to embed inline instead.
-
-Output format splits on the explicit `--json` flag: `--json` emits a structured
-envelope; otherwise human text. Every gate message carries paste-ready knobs.
-
-`--full` re-embeds the stale backlog inline (full sync sweeps it), so a `--full`
-estimate is `delta + stale backlog`, labeled as such.
-
-### Estimate labels
-
-- `~N tokens (delta: changed files since last sync)` — the precise estimate.
-- `<=N tokens (full-tree ceiling for K source(s): <reasons> …)` — a conservative
-  over-count used only when a precise delta can't be computed: a first sync, a chunker
-  version drift (forces a full re-chunk), or git being unavailable. Unchanged files
-  still skip via `content_hash` at execution, so the ceiling over-states real spend.
-
-## Notes & limits
-
-- **Pre-pull window:** the gate fetches before estimating, so it prices what the run
-  will pull. If a fetch fails (offline), it estimates against local HEAD and labels the
-  result; the bounded residual is priced on the next run.
-- **Single-source `gbrain sync`** carries the same gate as `sync --all` (it previously
-  embedded inline with no preview).
-- **Recovery under parallel:** `--skip-failed` / `--retry-failed` work under parallel
-  sync (the failure ledger is per-source and lock-serialized) — you no longer have to
-  drop to `--serial`, which is what used to arm the inline gate.
-
-## Escape hatches at a glance
-
-```bash
-# Never gate this brain on cost:
-gbrain config set spend.posture tokenmax
-
-# Widen the sync inline floor to $5:
-gbrain config set sync.cost_gate_min_usd 5
-
-# Disable the sync inline floor entirely:
-gbrain config set sync.cost_gate_min_usd off
-
-# Lift the backfill 24h spend cap:
-gbrain config set embed.backfill_max_usd_per_source_24h off
-
-# Run enrich uncapped non-interactively:
-gbrain enrich --max-usd off        # or: gbrain config set spend.posture tokenmax
-```

docs/plans/2026-06-03-001-feat-idea-lineage-skill-plan.md

@@ -1,211 +0,0 @@
----
-title: "feat: Add idea-lineage thinking skill"
-type: feat
-status: completed
-date: 2026-06-03
----
-
-# feat: Add idea-lineage thinking skill
-
-## Summary
-
-Add an `idea-lineage` thinking skill that traces how one idea has evolved through a user's brain: first mention, best articulation, related concepts, reversals, contradictions, abandoned branches, and the current live version. The contribution should start as a read-only skill with routing and conformance coverage, not as a new CLI or MCP operation.
-
-## Problem Frame
-
-GBrain already has two adjacent capabilities that are easy to conflate with this feature:
-
-- `skills/concept-synthesis/SKILL.md` is a mutating, batch-oriented concept map builder. It deduplicates many concept stubs, tiers them, writes concept pages, and creates an intellectual universe.
-- `find_trajectory` and `gbrain eval trajectory` are structured entity trajectories over typed facts and events. They work best for questions like metric history, founder consistency, role/status changes, and event timelines.
-
-`idea-lineage` should occupy the narrow space between them: a query-time, single-idea, citation-backed synthesis of conceptual evolution. It should help a user ask "how has my thinking about this idea changed?" without running a global concept-synthesis job or forcing the idea into an entity/metric trajectory model.
-
-## Requirements
-
-**Behavior**
-
-- R1. The skill accepts a single idea, topic, concept phrase, or nearby concept page and produces a focused lineage for that idea only.
-- R2. The output identifies first mention, best articulation, related concepts, reversals, contradictions, abandoned branches, and current live version when evidence supports each category.
-- R3. Every lineage claim is grounded in existing brain evidence: page links, dates, verbatim snippets, timeline entries, takes, contradiction findings, or trajectory points when applicable.
-- R4. The skill distinguishes evidence strength. Missing or weak evidence should be reported as a gap, not filled with plausible narrative.
-- R5. The default workflow is read-only and does not write or mutate brain pages.
-
-**Routing**
-
-- R6. Routing should prefer `idea-lineage` for single-idea evolution requests such as "how has my thinking about X changed?".
-- R7. Routing should keep broad corpus/map requests on `concept-synthesis`.
-- R8. Routing should keep structured entity metric/status questions on `find_trajectory`, `gbrain eval trajectory`, or `gbrain think` trajectory injection.
-
-**Privacy and portability**
-
-- R9. The skill and fixtures must use public, generic examples only.
-- R10. The plan and implementation must avoid private fork names, real people, real companies, funds, or host-specific filesystem paths in public artifacts.
-
-## Scope Boundaries
-
-### In Scope
-
-- A new bundled skill under `skills/idea-lineage/`.
-- Resolver, manifest, and plugin-bundle wiring.
-- Routing fixtures that prove the new intent is reachable and does not swallow `concept-synthesis` or trajectory-shaped prompts.
-- Documentation inside the skill body that explains when to use `search`, `query`, `get_page`, `list_pages`, `takes_search`, `find_contradictions`, and optionally `find_trajectory`.
-- Focused conformance, resolver, and routing verification.
-
-### Deferred to Follow-Up Work
-
-- A first-class `idea_lineage` MCP operation.
-- A `gbrain idea lineage <query>` CLI.
-- Persisting lineage reports back into the brain.
-- New database tables, schema-pack fields, or concept lineage graph primitives.
-- Automated contradiction-probe reruns. The skill should read cached contradiction findings if available, not trigger expensive probes.
-
-### Outside This Contribution
-
-- Replacing `concept-synthesis`.
-- Changing the facts/takes epistemology model.
-- Changing `find_trajectory`'s entity-slug contract.
-- Implementing the broader taxonomy redesign tracked by issue #1668.
-
-## Key Technical Decisions
-
-- **Start as a markdown skill:** GBrain's architecture treats skills as fat markdown workflows. This feature can be useful by orchestrating existing read operations, so a CLI/MCP surface would add contract weight before the behavior is proven.
-- **Make the skill non-mutating by default:** The user intent is investigative. Writing lineage pages should remain a later explicit mode after routing and output quality are established.
-- **Use evidence buckets rather than a single narrative pass:** The output should force the agent to separately evaluate first mention, articulation, current version, reversals, contradictions, and abandoned branches. That reduces the risk of smoothing over conflict.
-- **Keep `find_trajectory` as an optional side-channel:** It is valuable when an idea query resolves to an entity attribute or status history, but `idea-lineage` should not depend on typed facts being present.
-- **Avoid the existing "trace idea evolution" trigger phrase:** That phrase already routes to `concept-synthesis`; adding it to the new skill would create avoidable resolver ambiguity.
-
-## High-Level Technical Design
-
-```mermaid
-flowchart TB
-  A["User asks about one idea"] --> B{"Intent shape"}
-  B -->|"whole corpus / map"| C["concept-synthesis"]
-  B -->|"entity metric / status over time"| D["trajectory surfaces"]
-  B -->|"single conceptual idea"| E["idea-lineage skill"]
-  E --> F["Resolve idea candidates"]
-  F --> G["Gather evidence via search/query/pages/takes"]
-  G --> H["Classify lineage moments"]
-  H --> I["Synthesize cited answer with confidence gaps"]
-```
-
-## Implementation Units
-
-### U1. Add the `idea-lineage` Skill
-
-- **Goal:** Create the read-only skill contract and workflow.
-- **Requirements:** R1, R2, R3, R4, R5, R9, R10
-- **Dependencies:** None
-- **Files:**
-  - `skills/idea-lineage/SKILL.md`
-  - `test/skills-conformance.test.ts`
-- **Approach:** Create a new skill with required frontmatter and conformance sections. The skill should define its workflow in phases: clarify the target idea, resolve likely concept/page anchors, collect evidence, classify lineage moments, produce a cited synthesis, and state gaps. Frontmatter should set `mutating: false` and list read operations only.
-- **Patterns to follow:**
-  - `skills/strategic-reading/SKILL.md` for a read-only thinking-skill shape with related-skill boundaries.
-  - `skills/query/SKILL.md` for search/query/get-page guidance.
-  - `skills/concept-synthesis/SKILL.md` for contrast, not for behavior reuse.
-- **Test scenarios:**
-  - A new `SKILL.md` with frontmatter, `## Contract`, `## Output Format`, and `## Anti-Patterns` passes conformance.
-  - The frontmatter declares a unique `name: idea-lineage`.
-  - The skill body references only portable, synthetic examples.
-- **Verification:** `bun test test/skills-conformance.test.ts` passes.
-
-### U2. Wire Resolver, Manifest, and Bundle Metadata
-
-- **Goal:** Make the skill discoverable by bundled skill users and resolvable by agents.
-- **Requirements:** R6, R7, R8, R9, R10
-- **Dependencies:** U1
-- **Files:**
-  - `skills/RESOLVER.md`
-  - `skills/manifest.json`
-  - `openclaw.plugin.json`
-  - `test/resolver.test.ts`
-  - `test/skillpack-reference.test.ts`
-- **Approach:** Add `idea-lineage` to the skill manifest and plugin skill list. Add a resolver row in the thinking or uncategorized section with narrow user phrases such as "how has my thinking about", "trace the lineage of this idea", "what is my current version of", and "show reversals in my thinking about". Keep broad concept-map phrases routed to `concept-synthesis`.
-- **Patterns to follow:**
-  - `skills/RESOLVER.md` rows for `strategic-reading`, `concept-synthesis`, and `perplexity-research`.
-  - Existing sorted `openclaw.plugin.json` skill list.
-- **Test scenarios:**
-  - Every quoted resolver trigger fuzzy-matches a frontmatter trigger in `skills/idea-lineage/SKILL.md`.
-  - `idea-lineage` is listed in `skills/manifest.json`.
-  - `idea-lineage` is listed in `openclaw.plugin.json` if the contribution ships as part of the bundled OpenClaw skillpack.
-  - Existing skills remain reachable.
-- **Verification:** `bun test test/resolver.test.ts` passes.
-
-### U3. Add Routing Eval Fixtures
-
-- **Goal:** Prove the new routing boundary against adjacent skills.
-- **Requirements:** R6, R7, R8
-- **Dependencies:** U1, U2
-- **Files:**
-  - `skills/idea-lineage/routing-eval.jsonl`
-  - `skills/concept-synthesis/routing-eval.jsonl`
-  - `src/core/routing-eval.ts`
-- **Approach:** Add positive fixtures for single-idea lineage prompts and negative or ambiguity-declared fixtures around adjacent surfaces. The fixture text should paraphrase triggers rather than copy them exactly, because the routing fixture linter rejects tautological trigger copies.
-- **Test scenarios:**
-  - "Show how my thinking about founder-led sales changed over time" routes to `idea-lineage`.
-  - "What is my current version of the compounding trust idea?" routes to `idea-lineage`.
-  - "Synthesize my concepts into a tiered intellectual map" stays on `concept-synthesis`.
-  - "How has acme-example MRR trended since January?" does not route to `idea-lineage`.
-  - Negative fixtures avoid false positives for generic "publish this report" or "what is this concept?" prompts.
-- **Verification:** `gbrain routing-eval --json` reports no new misses, false positives, or unapproved ambiguity for the added fixtures.
-
-### U4. Add Output Contract and Citation Discipline
-
-- **Goal:** Make the skill's user-facing answer shape predictable and reviewable.
-- **Requirements:** R2, R3, R4, R5
-- **Dependencies:** U1
-- **Files:**
-  - `skills/idea-lineage/SKILL.md`
-  - `skills/conventions/quality.md`
-  - `skills/brain-ops/SKILL.md`
-- **Approach:** Define the output format directly in the skill body. The recommended shape should include a compact current answer, evidence timeline, lineage buckets, contradictions/reversals, abandoned branches, related concepts, and confidence gaps. Require page/date/snippet evidence for each non-gap claim. Preserve quote fidelity and avoid hallucinated dates.
-- **Patterns to follow:**
-  - `skills/conventions/quality.md` for citation and quote-fidelity expectations.
-  - `skills/brain-ops/SKILL.md` for source attribution and source-id formatting.
-  - `docs/takes-vs-facts.md` for not conflating holder-attributed takes with the brain owner's facts.
-- **Test scenarios:**
-  - Test expectation: none beyond conformance for the markdown-only contract; routing and conformance tests cover the machine-checkable surface.
-- **Verification:** Manual review confirms the skill body tells the agent how to cite, label gaps, and separate facts/takes/trajectory evidence.
-
-### U5. Refresh Generated Documentation If Required
-
-- **Goal:** Keep generated LLM-facing docs consistent if the test suite requires it.
-- **Requirements:** R9, R10
-- **Dependencies:** U1, U2, U3
-- **Files:**
-  - `llms.txt`
-  - `llms-full.txt`
-  - `test/build-llms.test.ts`
-- **Approach:** Run the build-llms test after adding the skill. If it fails because committed docs are stale, regenerate with the existing generator and include the generated diff. If it passes without regeneration, leave these files unchanged.
-- **Patterns to follow:**
-  - `package.json` script `build:llms`.
-  - `test/build-llms.test.ts` failure message.
-- **Test scenarios:**
-  - Committed `llms.txt` and `llms-full.txt` match generator output.
-  - `llms-full.txt` remains within the size budget.
-- **Verification:** `bun test test/build-llms.test.ts` passes.
-
-## Acceptance Examples
-
-- AE1. When the user asks "How has my thinking about founder-led sales changed over time?", the agent routes to `idea-lineage`, searches for evidence, and returns a cited lineage rather than running `concept-synthesis`.
-- AE2. When the user asks "Run concept synthesis across my notes", the agent routes to `concept-synthesis`, not `idea-lineage`.
-- AE3. When the user asks "How did acme-example's MRR trend?", the agent uses trajectory surfaces rather than `idea-lineage`.
-- AE4. When the evidence does not support an "abandoned branch" claim, the output includes a gap instead of inventing one.
-
-## Risks & Dependencies
-
-- **Resolver overlap risk:** `concept-synthesis` already uses "trace idea evolution". Mitigate by avoiding that exact trigger and adding routing fixtures around the boundary.
-- **Narrative overreach risk:** The feature invites story-making. Mitigate by requiring dates, snippets, links, and explicit gaps for unsupported categories.
-- **Privacy risk:** Skill examples can easily drift into real-brain language. Use synthetic examples only and rely on existing privacy checks.
-- **Generated-doc churn risk:** Adding a bundled skill may require `llms.txt` and `llms-full.txt` regeneration. Treat generated-doc changes as mechanical and separate from the skill design during review.
-- **Future taxonomy dependency:** Issue #1668 may eventually change concept filing and identity. This plan avoids new schema assumptions so the contribution remains compatible with the current repo.
-
-## Sources & Research
-
-- `skills/concept-synthesis/SKILL.md` defines the existing batch, mutating, concept-map surface.
-- `skills/RESOLVER.md` and `skills/manifest.json` define current skill reachability and bundle metadata.
-- `docs/architecture/lens-packs.md` shows that atoms and concepts are already part of the lens-pack/dream-cycle substrate.
-- `docs/proposals/temporal-contradiction-probe.md` and `docs/takes-vs-facts.md` define the temporal and epistemic boundaries this skill must not blur.
-- `src/core/operations.ts`, `src/core/trajectory.ts`, `src/commands/eval-trajectory.ts`, and `test/operations-find-trajectory.test.ts` define the current `find_trajectory` contract.
-- Pull requests #1131, #1296, and #1364 provide the recent trajectory, think-routing, and lens-pack context.
-- Issue #1668 is related future taxonomy work, but not a prerequisite for this contribution.

docs/schema-author-tutorial.md

@@ -1,224 +0,0 @@
-# Tutorial: Build your first schema pack
-
-You'll fork the bundled `gbrain-base` pack, add a custom `researcher` page type, import a handful of placeholder researcher pages, backfill their `page.type` column with one command, then prove the wiring works by running `gbrain whoknows` and seeing your new type surface in results. End state: a forked-and-active pack on disk, ~5 pages typed as `researcher`, and a query that proves the pack-aware routing fires end-to-end.
-
-**Want the WHY before the HOW?** Read [`what-schemas-unlock.md`](what-schemas-unlock.md) first — 7 concrete use cases (4000 invisible meetings, the founder ops brain, the research brain, the legal brain, the team brain, agent-as-co-curator) plus the structural argument for why types matter at query time. Then come back here for the 5-minute walkthrough.
-
-The whole walkthrough takes about 5 minutes. You'll see something working by step 3.
-
-## What you'll need
-
-- gbrain v0.40.7.0 or later (`gbrain --version` to check)
-- A brain that's been initialized (`gbrain init` already run; either PGLite or Postgres is fine)
-- A terminal you can paste commands into
-
-That's it. No API keys required for this tutorial — every step works against the bundled pack and local-only commands.
-
-## Step 1: See what pack is active today
-
-```bash
-gbrain schema active --json
-```
-
-You'll see something like:
-
-```json
-{
-  "pack_name": "gbrain-base",
-  "version": "1.0.0",
-  "sha8": "...",
-  "page_types_count": 22,
-  "source_tier": "default"
-}
-```
-
-`source_tier: "default"` means you haven't customized anything — you're on the bundled pack. `page_types_count: 22` is the universal starter (person, company, meeting, note, etc.).
-
-**You can't mutate bundled packs directly.** Step 2 forks it so you have something writable.
-
-## Step 2: Fork the bundled pack
-
-```bash
-gbrain schema fork gbrain-base mine
-```
-
-Output: `Forked 'gbrain-base' → 'mine' at ~/.gbrain/schema-packs/mine/pack.json`.
-
-The fork is a byte-for-byte copy of `gbrain-base` living at `~/.gbrain/schema-packs/mine/pack.json`. Now you have a writable pack you can mutate.
-
-## Step 3: Activate the fork
-
-```bash
-gbrain schema use mine
-```
-
-Output: `Pack: mine (json) ... Active.`
-
-Run `gbrain schema active --json` again to confirm `pack_name` is now `mine` and `source_tier` is `home-config` (read from `~/.gbrain/config.json`).
-
-**You've already accomplished something visible** — the active pack changed, and any future query will route through your fork. The next four steps add a custom type and prove it works.
-
-## Step 4: Add a researcher type
-
-```bash
-gbrain schema add-type researcher \
-  --primitive entity \
-  --prefix people/researchers/ \
-  --extractable \
-  --expert
-```
-
-Output: `Pack: mine (json)` + `Sha8: <prev> → <new>`.
-
-What just happened:
-- The mutation went through `withMutation`'s 8-step skeleton: bundled-guard → per-pack lock → read → mutate → file-plane lint validation → atomic write → audit log → cache invalidation.
-- The pack now declares `researcher` as an entity primitive bound to `people/researchers/`, marked `extractable: true` (eligible for facts extraction) and `expert_routing: true` (surfaces in `whoknows` queries).
-- An audit row landed in `~/.gbrain/audit/schema-mutations-YYYY-Www.jsonl` with your type name SHA-8-redacted and the prefix's first segment only (`people`) for privacy.
-
-Verify the type is in the pack:
-
-```bash
-gbrain schema explain researcher
-```
-
-You'll see the resolved settings printed back.
-
-## Step 5: Import some placeholder researcher pages
-
-You need pages under `people/researchers/` for the next step to do anything. If your brain repo already has them, skip ahead. If not, drop 3-5 placeholder markdown files into `<your-brain-repo>/people/researchers/` and import:
-
-```bash
-mkdir -p people/researchers
-cat > people/researchers/alice-example.md <<'EOF'
----
-title: Alice Example
----
-
-ML researcher at Example Lab. Works on contrastive embeddings.
-EOF
-
-cat > people/researchers/bob-example.md <<'EOF'
----
-title: Bob Example
----
-
-Vision researcher at Widget University. Recent paper on diffusion models.
-EOF
-
-cat > people/researchers/charlie-example.md <<'EOF'
----
-title: Charlie Example
----
-
-RL researcher at Acme Research. Focus on inverse reinforcement learning.
-EOF
-
-gbrain sync
-```
-
-The sync imports the new files. They'll be stored in the database but their `type` column will still be empty — the new type was added to the pack AFTER these pages already existed (the typical real-world scenario for an agent walking into an existing brain).
-
-## Step 6: See the gap with `stats`
-
-```bash
-gbrain schema stats --json | jq '.aggregate, .dead_prefixes'
-```
-
-You'll see `untyped_pages: 3` (or however many you just imported) and `dead_prefixes: []` — your new prefix has 3 matching pages, so it's not dead.
-
-The 3 researcher pages are "orphaned" by type even though they live in the right directory. The next step backfills them.
-
-## Step 7: Backfill with `sync --apply`
-
-First dry-run to see what would happen:
-
-```bash
-gbrain schema sync --json
-```
-
-You'll see something like:
-
-```json
-{
-  "schema_version": 1,
-  "apply": false,
-  "per_prefix": [
-    {
-      "type": "researcher",
-      "prefix": "people/researchers/",
-      "would_apply": 3,
-      "sample_slugs": ["people/researchers/alice-example", "people/researchers/bob-example", "people/researchers/charlie-example"],
-      "applied": 0
-    }
-  ],
-  "total_would_apply": 3,
-  "total_applied": 0
-}
-```
-
-`would_apply: 3` is what you'd touch. `sample_slugs` is the agent's drilldown signal — if those slugs look wrong, abort. They look right, so apply:
-
-```bash
-gbrain schema sync --apply
-```
-
-You'll see per-batch progress lines on stderr and a final `total_applied: 3`. The UPDATE ran in chunks of 1000 (yours fit in one chunk) and never wedged any concurrent writer.
-
-## Step 8: Prove the wiring works
-
-```bash
-gbrain whoknows "machine learning"
-```
-
-If your researcher pages contain ML-related content, they'll surface in the ranked results — even though they're typed `researcher`, not `person` or `company`.
-
-**This is the load-bearing demonstration of T1.5 wiring.** Pre-v0.40.7.0, `whoknows` hardcoded `['person', 'company']` as the eligible types and would have ignored your `researcher` pages entirely. The v0.40.7.0 wiring consults the active pack's `expert_routing: true` types via `expertTypesFromPack(pack.manifest)`, so your custom type now routes through expert search.
-
-## What you built
-
-You now have:
-- A fork of `gbrain-base` named `mine` at `~/.gbrain/schema-packs/mine/pack.json`, active in your brain via `~/.gbrain/config.json`.
-- A `researcher` page type registered in the pack with `entity` primitive, `people/researchers/` prefix, `extractable: true`, `expert_routing: true`.
-- 3 pages typed as `researcher` (backfilled from disk via `gbrain schema sync --apply`).
-- A query path that routes through the new type: `gbrain whoknows` reads the pack and includes `researcher` in its type filter.
-
-You also exercised the full mutation skeleton: bundled-pack guard, per-pack lock, validation gate, atomic write, audit log, cache invalidation. Every step was idempotent — re-running any of them is a no-op.
-
-## Next steps
-
-**Add a link verb.** A `researcher` can `author` a `paper`. To model that:
-
-```bash
-gbrain schema add-type paper --primitive annotation --prefix research/papers/ --extractable
-gbrain schema add-link-type authored --page-type researcher --target-type paper
-gbrain schema graph
-```
-
-The graph now shows `researcher --(authored)--> paper`.
-
-**Add aliases for query closure.** If you want `gbrain query researcher` to also surface `person` rows (because researchers ARE people):
-
-```bash
-gbrain schema add-alias researcher person
-```
-
-Read [`skills/conventions/schema-evolution.md`](../skills/conventions/schema-evolution.md) for the decision tree on when to add types vs aliases vs prefixes. The short version: <20 pages → don't pack-codify; 20-100 → alias on existing type; 100+ → first-class type.
-
-**Lint your pack before shipping.** The 11-rule lint surface (with the optional `--with-db` flag for DB-aware checks) catches dangling references, prefix collisions, and dead-corpus warnings:
-
-```bash
-gbrain schema lint --with-db
-```
-
-**Commit your pack to source control.** If `~/.gbrain/schema-packs/mine/` is a git repo, commit `pack.json` and push. Your pack survives across machines, and the `mutation_count_anomaly` lint rule will nudge you when you hit >50 mutations in a week (the "you should be committing this" signal).
-
-**For agents (MCP):** the same operations are reachable over HTTPS MCP via 9 new ops. Register an admin-scope OAuth client and `schema_apply_mutations` lets a remote agent compose multi-step refactors as one atomic batch. The batched MCP op + per-pack lock + audit log are the load-bearing primitives that make remote schema authoring safe. See [`skills/schema-author/SKILL.md`](../skills/schema-author/SKILL.md) for the agent dispatcher.
-
-**Undo a mistake.** Every mutation primitive has an inverse (`remove-type`, `remove-alias`, `remove-prefix`, `remove-link-type`, `set-extractable false`, etc.). If you fork twice and want to revert, `gbrain schema downgrade` restores the previous active pack from `~/.gbrain/schema-pack-history.jsonl`.
-
-## Related docs
-
-- **Reference:** `gbrain schema --help` for the full 22-verb CLI surface; CLAUDE.md's "Schema Cathedral v3 (v0.40.7.0)" section for the module-by-module architecture.
-- **How-to:** [`skills/schema-author/SKILL.md`](../skills/schema-author/SKILL.md) — the agent dispatcher with the 7-phase workflow (brain → assess → propose → apply → sync → verify → commit).
-- **Explanation:** [`skills/conventions/schema-evolution.md`](../skills/conventions/schema-evolution.md) — when to add a type vs alias vs prefix.
-- **Plan + decisions:** the original design captured 21 decisions including the bundled-pack guard rationale (D6), the empty-filter fallback contract (D4), and the MCP non-localOnly trust posture (D2). Lives in `~/.claude/plans/system-instruction-you-are-working-recursive-thacker.md` (private).

docs/tutorials/README.md

@@ -1,36 +0,0 @@
-# Tutorials
-
-Step-by-step walkthroughs that take you from zero to a working outcome. Concrete commands, real numbers, no abstraction-first jargon. Each tutorial assumes no prior GBrain knowledge.
-
-## Shipped
-
-- [**Set up your personal AI agent + brain from zero**](personal-brain.md) — the canonical solo install. Two GitHub repos, a Telegram bot, AlphaClaw on Render, OpenClaw + GBrain + Supabase. End-to-end in about 2 hours; about $100 to $150 a month sustained. The full-stack install I'd run today.
-- [**Set up GBrain as your company brain**](company-brain.md) — federated, multi-user, OAuth-scoped institutional memory for a 10-50 person team. Three sources (shared / customers / internal-only), per-user scope, first synthesized query as a teammate. About 90 minutes end-to-end, about $5 in API calls for the demo, under $100 a month sustained for a 25-person company.
-- [**Auto-improve a skill with `gbrain skillopt`**](improving-skills-with-skillopt.md) — treat a `SKILL.md` as the trainable parameter of a frozen agent. Write your first benchmark from scratch (the part everyone gets stuck on), preview the cost, run the optimizer, read accepted vs no_improvement vs aborted, and accept a measurably better skill. About 20 minutes, about $1 in API calls. Reference: [`../guides/skillopt.md`](../guides/skillopt.md).
-- [**Give your coding agent a memory: GBrain + Claude Code / Codex**](connect-coding-agent.md) — the two-funnel walkthrough for coding-agent users. Path A: connect Claude Code / Codex to a brain you already run (OpenClaw, Hermes, any `gbrain serve --http`). Path B: start from nothing with a 2-second local PGLite brain. Both end with the brain-first protocol you paste into `CLAUDE.md` / `AGENTS.md` and the four habits (brain-first lookup, ambient capture, briefing-from-your-brain, whoknows) that make it worth it. About 10 minutes.
-
-## In progress
-
-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.
-
-- **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.
-
-- **Index your codebase as a code brain** — for developers. Initialize a brain in a code repo, swap to `voyage-code-3` for embeddings, use `gbrain code-def` / `gbrain code-refs` / `gbrain code-callers` to navigate the codebase semantically from any MCP-aware editor.
-
-- **Run GBrain fully local with Ollama or llama.cpp** — for privacy-first deployments. No cloud calls, no API keys, no telemetry. Trades some retrieval quality for full local control. Useful for regulated industries, air-gapped environments, or just paranoia.
-
-- **Set up the dream cycle** — the overnight enrichment daemon that makes the brain self-maintaining. Fixes citations, dedupes people pages, surfaces contradictions, generates founder scorecards on the schedule you configure. The piece that turns a static knowledge base into a brain that gets smarter while you sleep.
-
-## Want to write one?
-
-Tutorials follow the [Diataxis](https://diataxis.fr/) tutorial pattern: learning-oriented, walks a learner from zero to a working result in one session, every step produces a visible change. If you've used GBrain for something interesting and want to write the walkthrough, the existing [`company-brain.md`](company-brain.md) is the model. Open a PR.
-
-## Related documentation
-
-- **Reference:** [`docs/architecture/`](../architecture/) — system design, topologies, retrieval theory
-- **How-to:** [`docs/guides/`](../guides/) — task-oriented runbooks (sub-agent routing, minion deployment, skill development, brain-first lookup, idea capture, diligence ingestion). Highlight: [scaling skills past 300](../guides/scaling-skills.md) — the three-tier architecture for agents that have outgrown the always-loaded skill manifest.
-- **Integrations:** [`docs/integrations/`](../integrations/) — connecting external data sources (voice, email, calendar, embedding providers)
-- **MCP setup:** [`docs/mcp/`](../mcp/) — per-client setup (Claude Desktop, Code, Cursor, ChatGPT, Perplexity, Cowork)
-- **Install paths:** [`docs/INSTALL.md`](../INSTALL.md) — every install path, end to end

docs/tutorials/company-brain.md

@@ -1,557 +0,0 @@
-# Tutorial: Extend your personal brain into a company brain
-
-This tutorial picks up where the [personal brain tutorial](personal-brain.md) leaves off. You already have a working agent (OpenClaw on Render, talking to you on Telegram, with GBrain as memory and Supabase storing embeddings). Now you want your whole team to use it as shared institutional memory, with each person seeing only what they're allowed to see.
-
-**Time:** about 90 more minutes on top of the personal-brain install.
-**Cost:** under $100 a month sustained for a 25-person company.
-
-If you haven't done the personal-brain install yet, [start there first](personal-brain.md). Come back when you've got the agent responding to you on Telegram. This tutorial assumes that's already working.
-
-I'm Garry Tan. I built GBrain to run my own AI agents at Y Combinator. After a couple of months of multi-user features landing (parallel sync across team sources, per-user OAuth scoping, leak-free isolation across every read path), it's finally usable as a company brain too. This is the recipe I'd run if I were standing it up for a 10-50 person company today.
-
----
-
-## Part 1: The mental model
-
-### What changes when you go from personal to company
-
-The personal brain you built is a single-user system: one git repo, one agent, your stuff. The company brain is the same architecture with three additions:
-
-1. **Multiple sources** inside the same brain. Your meeting notes are one source. Each teammate's customer notebook is another. The shared company wiki is a third. They live in the same database but stay independent.
-2. **Per-user logins** with scopes. Each teammate gets their own OAuth credential. The credential decides which sources they can read and write to. Alice writes to her customer source, reads hers plus the shared one. Bob writes to internal-ops, reads his plus the shared one. Neither can see the other's writes.
-3. **Per-person folders, crons, and skills.** The shared brain has shared structure, but each teammate gets their own subfolder for their own work, their own scheduled tasks (weekly digest, customer follow-ups), and their own scoped skills.
-
-### What this is NOT
-
-It is **not** a different install. The agent runtime, Supabase backend, GBrain CLI, and AlphaClaw harness from the personal brain stay exactly as you set them up. We're adding to that stack, not replacing it.
-
-It is also **not** a thin-client-everywhere setup. Your personal agent stays as it is (OpenClaw + Telegram). Each teammate adds their own client of choice (Claude Code, Cursor, Claude Desktop, their own OpenClaw, whatever) and points it at the brain.
-
-### What you get that one person's brain doesn't
-
-- **Shared memory.** The whole team queries the same brain. The contract notes that Alice wrote on Tuesday show up when Bob asks about that customer on Friday, with citations back to Alice's notes.
-- **Scoped privacy.** Performance reviews don't leak into customer queries. Legal docs don't leak into sales searches. We fuzz-tested this across every read path and got zero leaks.
-- **One sync pipeline.** Your brain git repo (or several if you want them isolated per team) feeds the brain. Everyone sees the latest.
-- **One operating burden.** One server to monitor, not one per user.
-
----
-
-## Part 2: Switch the brain backend to multi-user Postgres
-
-The personal-brain install uses Supabase as the embeddings layer but the GBrain runtime itself might be using PGLite (single-machine) depending on which path you took. For a company brain, you want a real Postgres for the runtime too. If your personal-brain install is already on Postgres or Supabase end-to-end, skip to Part 3.
-
-If you're on PGLite, migrate:
-
-```bash
-gbrain migrate --to supabase
-```
-
-This copies every page, chunk, embedding, link, and config over to your Supabase project. Run from the agent host machine, same one you set up in the personal-brain tutorial. Takes a few minutes per 10K pages.
-
-Verify:
-
-```bash
-gbrain doctor
-gbrain stats
-```
-
-Page count and chunk count should match what you had on PGLite.
-
----
-
-## Part 3: Carve up the brain into sources
-
-The personal brain has one source (called `default`) holding everything. For a company brain we want multiple. The right shape depends on your org. Here's a typical starting point for a 10-50 person company:
-
-```bash
-# A shared all-hands source for content everyone reads
-gbrain sources add shared --path /srv/brain-repos/shared --name "Shared company wiki"
-
-# A scoped source for sales/customer notes
-gbrain sources add customers --path /srv/brain-repos/customers --name "Customer notes"
-
-# A scoped source for internal-only docs (legal, HR, performance, board)
-gbrain sources add internal --path /srv/brain-repos/internal --name "Internal-only"
-```
-
-Each `--path` is a directory on disk where you've checked out a git repo. Create them:
-
-```bash
-sudo mkdir -p /srv/brain-repos
-sudo chown $USER /srv/brain-repos
-cd /srv/brain-repos
-git clone git@github.com:your-org/shared-wiki.git shared
-git clone git@github.com:your-org/customers.git customers
-git clone git@github.com:your-org/internal-docs.git internal
-```
-
-You can also keep the existing personal-brain repo as one of the sources. Just pick the role it plays (probably `shared` if it's already org-wide content).
-
-### Two scoping models (pick the one that matches your shape)
-
-There are two ways to scope teammates' access. They suit different deployment shapes.
-
-**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.
-
-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.
-
-### Per-person folder structure inside each source
-
-Inside each source, give each teammate their own subfolder. This is the structure I run:
-
-```
-customers/
-├── alice-example/                      ← Alice's customer notebook
-│   ├── customers/
-│   │   ├── acme-co.md
-│   │   └── widget-systems.md
-│   └── meetings/
-│       └── 2026-05-21-acme-renewal.md
-├── bob-example/                        ← Bob's customer notebook
-│   └── customers/
-│       └── orbit-bio.md
-└── shared-customers/                   ← things both can see
-    └── all-active-deals.md
-```
-
-Two things this structure buys you:
-
-1. **Each teammate's writes go to their own folder** even though they're in the same source. No accidental overwrites.
-2. **You can later split a person's folder into its own source** (if Alice leaves and a new person takes her accounts, you can move `alice-example/` to a new source named after the new person and adjust scoping accordingly).
-
-Same shape for `internal/`: `internal/alice-example/` for her HR docs, `internal/bob-example/` for his, `internal/legal/` for legal docs everyone can read, etc.
-
-Now sync everything:
-
-```bash
-gbrain sync --all
-```
-
-Each source syncs in parallel under its own lock so they don't step on each other. Output looks like:
-
-```
-[shared]    100/100 pages
-[customers] 240/240 pages
-[internal]   85/85 pages
-✓ all sources synced
-```
-
-Check the dashboard:
-
-```bash
-gbrain sources status
-```
-
-You should see all three sources with recent sync timestamps and page counts.
-
----
-
-## Part 4: Expose the brain over HTTP MCP with OAuth
-
-The personal brain talks to you through the AlphaClaw harness over Telegram. For a company brain we need a path that each teammate's AI client can hit independently. The HTTP MCP server is that path.
-
-```bash
-gbrain serve --http --port 3131 --bind 0.0.0.0
-```
-
-The `--bind 0.0.0.0` is important. By default the server binds to localhost only, which is correct for a personal install but blocks remote teammates. Setting `0.0.0.0` accepts connections from any interface.
-
-The server prints an admin bootstrap token to stderr on first start when run in an interactive terminal. Save it. You'll use it once for the admin dashboard. On a non-TTY start (systemd, Docker, piped logs) the token is hidden from logs — set `GBRAIN_ADMIN_BOOTSTRAP_TOKEN` yourself or pass `--print-admin-token` on a trusted terminal instead.
-
-For development, tunnel the local server out via ngrok:
-
-```bash
-ngrok http 3131 --domain your-brain.ngrok.app
-```
-
-For production, put your server behind a real hostname with a real TLS certificate. Let's call your final URL `https://brain.acme-co.com` for the rest of this tutorial.
-
-Re-run the server with the public URL so the OAuth discovery metadata matches what clients hit:
-
-```bash
-gbrain serve --http --port 3131 --bind 0.0.0.0 --public-url https://brain.acme-co.com
-```
-
-You should be able to hit `https://brain.acme-co.com/health` and get `{"status":"ok"}` back.
-
----
-
-## Part 5: Register one OAuth client per teammate
-
-Each teammate (or each AI agent for a teammate) gets their own OAuth client. The client controls what they can write and what they can read.
-
-```bash
-# Alice (sales): writes customers/alice-example, reads customers + shared
-gbrain auth register-client alice-example \
-  --grant-types client_credentials \
-  --scopes read,write \
-  --source customers \
-  --federated-read customers,shared
-
-# Bob (ops): writes internal/bob-example, reads internal + shared
-gbrain auth register-client bob-example \
-  --grant-types client_credentials \
-  --scopes read,write \
-  --source internal \
-  --federated-read internal,shared
-
-# Carol (legal): writes shared/legal, reads all three
-gbrain auth register-client carol-example \
-  --grant-types client_credentials \
-  --scopes read,write \
-  --source shared \
-  --federated-read shared,customers,internal
-```
-
-Each `register-client` command prints a `client_id` and a `client_secret`. Save both for each teammate. They go into the teammate's local agent config.
-
-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.
-- `--federated-read` controls read scope. A client can read from one or more sources.
-
-### Verify the scoping actually scopes
-
-Before you hand the brain to teammates, verify isolation. Two terminal windows on your local machine using each client's credentials:
-
-```bash
-# Terminal 1, as Alice
-export GBRAIN_REMOTE_CLIENT_ID=<Alice's client_id>
-export GBRAIN_REMOTE_CLIENT_SECRET=<Alice's client_secret>
-export GBRAIN_REMOTE_MCP_URL=https://brain.acme-co.com/mcp
-
-gbrain search "performance review" --remote
-```
-
-Alice should see results only from `customers` and `shared`. The performance-review notes live in `internal`, which she's not scoped to read. She shouldn't see them.
-
-```bash
-# Terminal 2, as Bob (export his credentials similarly)
-gbrain search "performance review" --remote
-```
-
-Bob should see the performance-review notes from `internal`, plus anything related from `shared`. He shouldn't see anything that lives only in `customers`.
-
-If both queries return correctly scoped results, isolation is working.
-
----
-
-## Part 6: Set up per-person crons
-
-The personal-brain install runs the dream cycle (overnight enrichment) once per night for one user. A company brain needs per-person crons because each teammate has their own context: Alice wants a 7am customer-pipeline digest, Bob wants a 9am ops-status report, Carol wants a contract-compliance check every Monday.
-
-Each cron is just a scheduled `gbrain agent run` call scoped to the teammate's client credentials. The schedule lives in the workspace repo (the one AlphaClaw deployed in the personal-brain tutorial), in a `crons/` directory. A typical layout:
-
-```
-your-org/myagent/
-└── crons/
-    ├── alice-example/
-    │   └── 07am-customer-digest.md
-    ├── bob-example/
-    │   └── 09am-ops-status.md
-    └── carol-example/
-        └── monday-contract-compliance.md
-```
-
-Each cron file declares its schedule and the prompt that the agent runs:
-
-```markdown
----
-schedule: "0 7 * * *"
-client: alice-example
----
-
-# Customer pipeline digest
-
-Pull every customer page in customers/alice-example/ that had activity in
-the last 7 days. For each, summarize what changed and what the next action
-is. Output as a markdown digest, post to Slack #alice-customers, save a
-copy to customers/alice-example/digests/YYYY-MM-DD-pipeline.md.
-```
-
-The `client:` field tells the cron runner which OAuth client to use, which enforces the scoping. Alice's cron can only read Alice's sources and write to Alice's folder. It cannot accidentally touch Bob's customer notes.
-
-To install the cron schedule, commit the file to the workspace repo and let AlphaClaw pick it up on next deploy. The cron-scheduler skill (one of the 60 that GBrain installed) handles the dispatch.
-
----
-
-## Part 7: Add per-person skills
-
-The 60+ skills GBrain installs are generic. Your team probably wants a few that are specific to them. Examples:
-
-- `onboarding-new-hire`. Only Carol (HR) runs this. Walks through generating a welcome packet, scheduling intro meetings, provisioning accounts.
-- `customer-success-followup`. Only Alice (sales) runs this. Pulls latest customer page, drafts a follow-up email, posts to her review queue.
-- `weekly-team-digest`. Only you (admin) run this. Aggregates everyone's published pages into one weekly summary.
-
-Skills are just markdown files in the workspace repo's `skills/` directory. The shape:
-
-```
-your-org/myagent/
-└── skills/
-    ├── onboarding-new-hire/
-    │   └── SKILL.md
-    ├── customer-success-followup/
-    │   └── SKILL.md
-    └── weekly-team-digest/
-        └── SKILL.md
-```
-
-Each `SKILL.md` declares the trigger (verbs in plain English the agent listens for) and the procedure. Use the `gbrain skillify scaffold <name>` command to generate the boilerplate:
-
-```bash
-gbrain skillify scaffold onboarding-new-hire
-```
-
-That creates the directory + SKILL.md + routing entry. Edit the SKILL.md to describe the procedure, commit, deploy. The agent picks up the new skill on next request.
-
-Per-person scoping for skills is handled at the routing layer: a skill can declare `allowed_clients: [carol-example]` in its frontmatter. If Alice asks her agent to run that skill, the agent refuses with "this skill is scoped to carol-example."
-
-### Shared rule files at the skills root
-
-Alongside individual skill directories, drop a few flat `_*-rules.md` files at the root of `skills/`. These are conventions that EVERY skill reads. The ones I run in production:
-
-- `_brain-filing-rules.md`. the iron-rule decision tree for "where does this new page belong?" Numbered first-match-wins rules (people go in `people/`, companies in `companies/`, meetings in `meetings/`, etc.). Every ingest skill consults this before creating a page.
-- `_output-rules.md`. output quality standards (deterministic links built from API data not LLM-composed strings, exact-phrasing requirements for citations, no AI-slop vocabulary).
-- `_excluded-people.md`. a privacy gate. Names that must never be referenced or attributed in the brain even if they appear in source material. Re-attribute or discard. This is the file that prevents your agent from accidentally publishing things about people you've decided aren't fair game.
-- `_operating-rules.md`. operational conventions (when to write to brain vs scratchpad, when to ask for confirmation, when to fire a notification).
-- `_x-ingestion-rules.md`, `_x-api-rules.md`. per-source rules for specific integrations (Twitter, in this case).
-
-These files turn into the de facto company policy for the agent. Edit one, and every skill that reads it picks up the new rule on the next request. Versioned in git, reviewable in PR.
-
----
-
-## Part 8: Wire Slack carefully
-
-Slack is the integration most teams want first, and it has enough sharp edges to deserve its own callout. The conventions I run:
-
-**Two crons, two jobs.** One scan cron that runs every 5-15 minutes and surfaces signals (new threads in channels you care about, mentions of your teammates, decisions). One archive cron that runs nightly and stores the full conversation history. Splitting them this way means urgent signals get acted on fast while the slow archive work doesn't crowd the live channel.
-
-**Channel-to-task-ID mapping.** Don't have your agent reference Slack channels by their actual channel IDs (`C03A8...`). Build a `topic-registry.json` (or similar) that maps each channel ID to a friendly task name (`acme-co-customer-success`, `engineering-standup`). Crons and skills reference channels by friendly name; the registry translates to IDs at runtime. This is the file you edit when a channel gets renamed or replaced.
-
-**Deterministic links only.** When your agent writes a brain page that cites a Slack message, the link MUST be built from API data (workspace ID + channel ID + message timestamp), never composed by the LLM. LLMs hallucinate Slack URLs constantly. The convention lives in `_output-rules.md`; every skill that touches Slack inherits it.
-
-**Dismissed-items state.** The scan cron remembers what it has already surfaced. If a channel had a thread on Tuesday that turned out to be noise, the dismissed-items file records it so the Wednesday scan doesn't surface it again. Without this, re-scans become a flood of repeat signals.
-
-**Per-channel scoping mirrors per-person scoping.** Sensitive channels (#executive, #legal, #performance) should be scoped to teammates with the appropriate `--federated-read`. The brain stores everything, but who can query for it is gated by the same OAuth client model from Part 5.
-
-The actual skills that implement this in production are named `slack`, `slack-scan`, `slack-archive`. Scaffold equivalents in your workspace with `gbrain skillify scaffold slack-scan`, then edit the generated SKILL.md to declare your channel mapping and triggers.
-
----
-
-## Part 9: Onboard each teammate yourself (the botmaster pattern)
-
-This is the part that decides whether your company brain actually gets adopted or sits unused.
-
-**Do not just hand a new teammate their OAuth credential and tell them to "try it out."** They'll send one query, get a result that doesn't feel personal yet (because their slice is empty), conclude it's not useful, and never come back.
-
-What works instead: I personally onboard each new teammate myself. The flow looks like this.
-
-### Step 1: Pre-populate their slice
-
-Before they ever log in, I seed their `partners/<their-slug>/` directory (or their dedicated source) with the context they need to feel like the brain already knows them:
-
-- `partners/alice-example/USER.md`. a one-page profile: role, focus areas, current top 3 priorities, the kind of questions they tend to ask, the kind of writing they prefer (terse vs detailed, casual vs formal).
-- `partners/alice-example/concepts/`. 5-10 frameworks or recurring themes that are specifically THEIRS. If Alice runs sales, that's "pipeline stage definitions," "ICP criteria," "objection-handling playbooks."
-- `partners/alice-example/sources/`. links to the documents they care about (their team's shared docs, their inbox conventions, the dashboards they check).
-- 2-3 example brain entries that demonstrate the shape: a customer page they'd recognize, a meeting note from a recent meeting they attended, an idea they've shared with the team.
-
-Takes me maybe 20 minutes per teammate. The payoff: the moment they run their first query, the brain answers with their context, not a generic response. That's the difference between "this is a cool tool" and "this knows me."
-
-### Step 2: Walk them through 2-3 wow flows
-
-Before letting them DM the agent freely, I personally walk them through 2-3 specific flows that I know will land:
-
-1. A query that demonstrates synthesis: "ask the brain about [a customer they know well]. Notice how it pulls together pages from three sources into one answer with citations." This shows the brain layer in action.
-2. A query that demonstrates gap analysis: "ask the brain about [something it doesn't know yet]. Notice how it tells you what's missing instead of making it up." This builds trust.
-3. A write-back flow: "tell the brain about [a meeting they just had]. Notice how it auto-files, links to the other people who were there, and surfaces related history." This shows the agent's value as a capture tool, not just a query tool.
-
-These three flows take maybe 15 minutes total. By the end, the teammate has seen the brain do something they couldn't have done themselves in that time. They feel powerful.
-
-### Step 3: Graduate to DM only after the wow moment lands
-
-After the walkthrough, I give them their OAuth credential and the agent's DM (Telegram, Slack DM, whatever your interface is). I explicitly say "now you can ask it anything, write to it anytime, and it'll keep learning from you."
-
-The order matters. If you give them DM access first and expect them to discover the wow moments themselves, most won't. They'll send one generic query, get a generic answer, and bounce. The botmaster pattern (pre-populate → walk through → graduate to DM) flips the conversion rate.
-
-Repeat this flow for every new teammate. About 45 minutes per person, total. Compared to the cost of an unadopted internal tool, it's the best 45 minutes you'll spend.
-
----
-
-## Part 10: Connect each teammate's AI client
-
-Each teammate runs their AI client (Claude Code, Cursor, Claude Desktop, OpenClaw, Hermes, whatever) configured to point at your brain server through their OAuth credentials.
-
-Recommended path for each teammate: the thin-client install. On their machine:
-
-```bash
-curl -fsSL https://bun.sh/install | bash
-bun install -g github:garrytan/gbrain
-
-gbrain init --mcp-only \
-  --issuer-url https://brain.acme-co.com \
-  --mcp-url https://brain.acme-co.com/mcp \
-  --oauth-client-id <their client_id> \
-  --oauth-client-secret <their client_secret>
-```
-
-The thin-client install creates a local config that knows how to talk to your brain but never opens its own database. Most CLI commands route through the remote server transparently.
-
-Now they configure their AI client. For Claude Desktop, the teammate adds an MCP server entry in `~/Library/Application Support/Claude/claude_desktop_config.json`:
-
-```jsonc
-{
-  "mcpServers": {
-    "company-brain": {
-      "command": "gbrain",
-      "args": ["serve"]
-    }
-  }
-}
-```
-
-When Claude Desktop launches, it talks to the local `gbrain serve` stdio bridge, which forwards every request to your remote brain over HTTPS with their OAuth token attached. From Claude Desktop's perspective it's just one MCP server.
-
-For Claude Code, Cursor, OpenClaw, Hermes, and other clients, per-client setup steps live in [`docs/mcp/`](../mcp/). They all follow the same shape: point the agent at the local `gbrain serve` bridge, which knows about the remote.
-
----
-
-## Part 11: First real query as a teammate
-
-Have Alice run a real query from her machine. The interesting verb is `gbrain think`, which gives back a synthesized answer instead of raw pages.
-
-```bash
-gbrain think "What's the latest update from acme-co? When did we last talk to them?"
-```
-
-What Alice gets back, assuming the brain has been syncing for a week and her sources contain a customer page for acme-co and several meeting notes:
-
-```
-## Answer
-
-The most recent customer contact with acme-co was a renewal-discussion
-meeting on 2026-05-18, attended by alice-example and acme-co's CTO. Key
-points discussed [customers/alice-example/meetings/2026-05-18-acme-renewal]:
-
-- They are upgrading their plan from team to enterprise.
-- Annual contract value is moving from $48K to $180K.
-- Decision driver: a new compliance requirement they have to meet by Q3.
-
-Prior contact was a quarterly check-in on 2026-04-03 [customers/alice-example/meetings/2026-04-03-acme-q2-checkin].
-
-**Gap noted:** No customer-success notes have been filed since the
-2026-05-18 renewal meeting. If a follow-up has happened, it's not in
-the brain yet.
-```
-
-Three things to notice:
-
-1. **Sourced.** Every claim cites the meeting note it came from.
-2. **Synthesized.** Alice didn't read three pages and stitch them together. The brain did.
-3. **Honest about gaps.** The brain knows what it doesn't know and says so, instead of inventing a follow-up that didn't happen.
-
-That last part is the gap analysis. It's the part of the brain layer that nobody else ships.
-
-Bob asking the same question would get nothing about acme-co. He's not scoped to read `customers`. He'd see his own internal-ops content if he asked something relevant to that. Carol asking would see both, because she's scoped to read all three sources.
-
----
-
-## Part 12: Operating the company brain
-
-Three commands do most of the operational work.
-
-### Background daemon: `gbrain autopilot`
-
-The personal-brain install already turned this on. For a company brain, the same autopilot covers all your sources because they live in one database. It runs every five minutes; on a healthy brain (health score 95+) it sleeps; on a brain that's drifting it submits targeted maintenance jobs.
-
-### Self-healing: `gbrain doctor --remediate`
-
-```bash
-gbrain doctor --remediate --yes --target-score 90 --max-usd 5
-```
-
-Computes a dependency-ordered plan of maintenance jobs that would raise the brain's health score to the `--target-score`, runs the plan, refuses to spend past the `--max-usd` cap. Safe to cron.
-
-### Monitoring: `gbrain sources status` and the admin dashboard
-
-```bash
-gbrain sources status
-```
-
-Returns a per-source dashboard: when each source last synced, how many pages, how many embedded, how many unacked sync failures. The at-a-glance health check.
-
-The admin dashboard at `https://brain.acme-co.com/admin` shows live request volume, registered OAuth clients, recent activity, and brain stats. Use the admin bootstrap token from Part 4 to log in the first time, then register additional admin users from inside the dashboard.
-
----
-
-## Part 13: Cost and speed expectations
-
-Real numbers from the published benchmark, running the default stack (GBrain with ZeroEntropy for embedding + reranker):
-
-- **Embedding cost:** $0.05 per million tokens. For comparison, GBrain configured with OpenAI is $0.13 (2.6× more expensive), Voyage is $0.18 (3.6× more).
-- **Ingest speed:** about 22 seconds for a small test corpus of 164 pages on the host machine. For a 10K-page corpus, expect about 20 minutes the first time, then most syncs are incremental and finish in seconds.
-- **Query latency:** about 122 ms median for a `gbrain search`. For comparison, the same query through GBrain with OpenAI takes about 282 ms.
-- **Synthesized-answer latency:** a few seconds, dominated by the Anthropic API.
-- **Retrieval quality:** on the public LongMemEval benchmark, GBrain hits 97.60% recall at the top 5 retrieved sessions, beating the previous published state of the art at 96.6%. On the in-house BrainBench corpus of relational queries, GBrain beats commodity vector retrieval by 38 percentage points, because the graph layer surfaces relationships that vector similarity alone misses.
-
-Full methodology and per-run receipt JSONs live in [the gbrain-evals repo](https://github.com/garrytan/gbrain-evals/blob/main/docs/benchmarks/2026-05-23-v0.40.6.0-snapshot.md).
-
-For a 25-person company at sustained use, expect about $35 a month in embeddings (ZeroEntropy at $0.05/million tokens), $50 a month in Anthropic calls for the synthesized-answer queries, plus your hosting bill. Under $100 a month for the AI side at most companies your size.
-
----
-
-## Part 14: Common gotchas
-
-### "My teammate can't see anything"
-
-Check `gbrain auth list` on the host and confirm their client has `--source` set to a source that actually exists. Empty or null `--source` means the client falls through to the `default` source, which probably has no content if you set up three named sources.
-
-### "Sync is slow and feels stuck"
-
-The first sync embeds every page, which takes time. Check `gbrain sources status` for the live page count. If it's climbing you're not stuck, you're just embedding. If you've got a 10K-page corpus and ZeroEntropy is being throttled, the per-source parallel sync looks like progress on three sources at once rather than one source moving fast.
-
-### "I see a page I shouldn't see"
-
-This shouldn't happen, but if you suspect it, run `gbrain search <query> --remote --json` as the constrained client and inspect the `source_id` field on every returned result. Every row should be in the client's `--federated-read` set. If one isn't, file an issue with the exact slug and source IDs.
-
-### "The synthesized answer is wrong"
-
-The brain layer is grounded in the retrieved pages. If the retrieved pages contain bad information, the answer will too. The gap-analysis note often catches this: if the answer says "based on retrieved pages from date X" and date X is six months ago, the brain is telling you the information is stale. Run `gbrain sync --all` to refresh and try again.
-
-### "OAuth `/token` endpoint returns 401 for my client"
-
-Verify the client secret matches what was printed at register-client time. The server stores only a SHA-256 hash; if you lost the original, you have to revoke the client and re-register. Use `gbrain auth revoke-client <client_id>` and re-run `register-client`.
-
-### "Postgres connection is exhausting"
-
-Each parallel sync worker opens its own pool. With three sources and the default four workers per source, you can hit your Postgres connection limit if it's set low. Either reduce the worker count with `gbrain sync --all --parallel 2 --workers 2`, or raise your Postgres `max_connections` to at least 100. Supabase's free tier defaults to 60, which is tight.
-
-### "I want to add a fourth teammate but they need access to all three sources"
-
-```bash
-gbrain auth register-client diana-example \
-  --grant-types client_credentials \
-  --scopes read,write \
-  --source shared \
-  --federated-read shared,customers,internal
-```
-
-That's it. Add or rotate teammates as the org grows.
-
----
-
-## What you built
-
-You now have the personal-brain agent from the previous tutorial, plus a multi-user shared layer on top: three federated sources holding shared, customer, and internal-only content; per-person folders inside each source so teammates' writes don't collide; per-person OAuth clients with scoped read and write; per-person crons that run on each teammate's own schedule with their own scoping; per-person skills the agent only runs for the right person. Each teammate queries the brain in plain English through their AI client and gets back synthesized, sourced answers that are correctly scoped.
-
-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.
-
-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.
-
-Questions, gotchas, or wins worth sharing? Open an issue at [github.com/garrytan/gbrain](https://github.com/garrytan/gbrain/issues).

docs/tutorials/connect-coding-agent.md

@@ -1,235 +0,0 @@
-# Give your coding agent a memory: GBrain + Claude Code / Codex
-
-Coding agents got very good at code. They're still amnesiac about everything
-else. Claude Code and Codex forget your last conversation, can't tell you what
-you decided three meetings ago, and re-derive context you already have written
-down somewhere. GBrain is the retrieval layer that fixes that: search, synthesis,
-and a self-wiring knowledge graph, wired into your agent over MCP.
-
-There are two ways to do this. Pick the one that matches where you are:
-
-- **Path A — I already run a brain** (OpenClaw, Hermes, or any `gbrain serve`
-  host) and I want my Claude Code / Codex to reach the same brain. → [jump to Path A](#path-a-connect-an-agent-to-a-brain-you-already-have)
-- **Path B — I have nothing yet.** Spin up a local brain in 2 seconds and wire it
-  into my coding agent. → [jump to Path B](#path-b-start-from-nothing-local-brain-local-agent)
-
-Both end in the same place: an agent that searches your brain before it answers,
-and writes new knowledge back as you work. The last section,
-[Now make it actually useful](#now-make-it-actually-useful), is the same for both
-and is the part that changes how you work.
-
-Prerequisite for either path: `bun install -g github:garrytan/gbrain`.
-
----
-
-## Path A: connect an agent to a brain you already have
-
-You already have a populated brain (the OpenClaw / Hermes case: it's on your
-agent host, full of meetings, people, and ideas). You want Claude Code on your
-laptop, and Codex too, to query it. This is the remote path: the host serves
-HTTP, your laptop agents connect with a token.
-
-### A1. On the host: serve over HTTP
-
-If your host isn't already serving HTTP MCP, start it:
-
-```bash
-gbrain serve --http --bind 0.0.0.0 --public-url https://your-host.example.com
-```
-
-Two flags matter and people skip them:
-
-- **`--bind 0.0.0.0`** — the default bind is `127.0.0.1` (loopback only), which
-  silently refuses every remote connection. If your agent "can't reach the
-  brain" and you didn't pass this, that's why. `gbrain serve --http` warns you at
-  startup when `--public-url` is set without `--bind`.
-- **`--public-url`** — the externally reachable HTTPS URL (your Render/Railway
-  URL, ngrok domain, Tailscale Funnel, etc.). It's the issuer the OAuth/MCP
-  layer advertises.
-
-Watch the startup banner. It now prints a `Skills:` line:
-
-```
-║  Skills:    published                                  ║
-```
-
-If it says `not published`, your connected agents will be able to search and
-write but won't see your skill catalog (the OpenClaw skills that make your setup
-special). Turn it on:
-
-```bash
-gbrain config set mcp.publish_skills true
-```
-
-(New brains from `gbrain init` default this ON. Brains upgraded from before
-v0.41.36 stay OFF until you opt in, so this is the common gotcha for existing
-OpenClaw users.)
-
-### A2. On the host: mint a token
-
-```bash
-gbrain auth create "laptop-agents"
-```
-
-Copy the `gbrain_…` token it prints. It's a long-lived, full-access secret. Treat
-it like a password; prefer a scoped OAuth client for anything cloud-hosted (see
-[DEPLOY.md](../mcp/DEPLOY.md)).
-
-### A3. On the laptop: one command per agent
-
-```bash
-# Claude Code
-gbrain connect https://your-host.example.com/mcp --token gbrain_xxx --install
-
-# Codex
-gbrain connect https://your-host.example.com/mcp --token gbrain_xxx --agent codex --install
-```
-
-`--install` runs the agent's `mcp add` for you AND smoke-tests the token: it
-actually calls `get_brain_identity` before handing off, so a wrong or expired
-token fails right now, not silently on the agent's first request. You'll see:
-
-```
-Added MCP server 'gbrain' -> https://your-host.example.com/mcp.
-Verified: {"version":"0.42.x","engine":"postgres","page_count":146646,...}
-```
-
-Drop `--install` to print a paste-ready block instead (useful when the host and
-the agent are different machines, or you want to read before you run). Codex
-reads the bearer from `$GBRAIN_REMOTE_TOKEN` at runtime, so the token never lands
-in Codex's config file. Keep that variable exported in your shell profile.
-
-### A4. Verify
-
-In the agent: *"Call get_brain_identity, then search my brain for [a topic you
-know is in there]."* You should get your own pages back. Done.
-
-Full per-client detail: [Claude Code](../mcp/CLAUDE_CODE.md),
-[Codex](../mcp/CODEX.md), [Perplexity](../mcp/PERPLEXITY.md).
-
----
-
-## Path B: start from nothing (local brain, local agent)
-
-No OpenClaw, no server, no token. The lowest-friction path in the whole product:
-a local PGLite brain in the same process your agent spawns. Zero server, zero
-tunnel.
-
-### B1. Create a local brain
-
-```bash
-gbrain init --pglite      # 2 seconds; embedded Postgres via WASM, no Docker
-```
-
-### B2. Put something in it
-
-A brain with nothing in it answers nothing, so an empty brain on day one feels
-broken. Two ways to fill it:
-
-```bash
-# Bulk-import a folder of markdown you already have:
-gbrain import ~/notes/
-
-# Or capture as you go (one thought at a time):
-gbrain capture "Decided to use PGLite as the default engine: zero-config beats Postgres for <1000 files."
-```
-
-You don't have to import everything up front. The capture-as-you-go habit (see
-the next section) means the brain fills with the decisions and context you
-generate while working, and is genuinely useful by day two.
-
-### B3. Wire it into your coding agent
-
-```bash
-# Claude Code
-claude mcp add gbrain -- gbrain serve
-
-# Codex
-codex mcp add gbrain -- gbrain serve
-```
-
-That's the whole wire-up. No token, no URL, no tunnel. The agent spawns
-`gbrain serve` as a stdio subprocess and talks to your local brain directly.
-
-### B4. Verify
-
-In the agent: *"search my brain for PGLite"* (or whatever you just captured). You
-get the page back. The same brain is now query-able from the CLI
-(`gbrain query "..."`) and from your agent.
-
----
-
-## Now make it actually useful
-
-Connecting is the easy part. The value comes from teaching your agent a few
-habits. These are the patterns that turn a coding agent into a knowledge-aware
-one. Paste the protocol below into your agent's instructions file
-(`CLAUDE.md` for Claude Code, `AGENTS.md` for Codex / Cursor / others), then lean
-on the patterns.
-
-### The brain-first protocol (paste this in)
-
-```markdown
-## Brain-first protocol
-
-You have a knowledge brain connected over MCP. Before answering any question
-about people, companies, decisions, projects, or past context:
-
-1. **Search first.** Call `search` (or `query` for a synthesized answer) against
-   the brain BEFORE answering from memory or asking me. If the brain has the
-   answer, use it. Never ask "who is X?" or "what did we decide about Y?" before
-   searching — the brain probably already knows.
-2. **Write back.** When I make a decision, mention a new person/company, or land
-   on an idea worth keeping, write it to the brain with `put_page` (entity pages
-   under people/, companies/; decisions under decisions/ or notes/). One insight,
-   one page, linked.
-3. **Cite.** When you answer from the brain, name the page you used.
-```
-
-### The four patterns worth stealing
-
-These come straight from a production OpenClaw setup. They translate directly to
-any coding agent with GBrain connected:
-
-**1. Brain-first lookup (never ask what you can retrieve).** The single highest-
-value habit. Before the agent asks you "which repo?" or "who owns this?", it
-searches. Try: *"What did we decide about the auth rewrite?"* and watch it pull
-the decision page instead of asking you to re-explain.
-
-**2. Ambient capture (your brain as a side effect of working).** Don't make
-saving a separate chore. Tell the agent: *"As we work, capture any decision or
-new idea to the brain without interrupting."* After a month of this, you have
-hundreds of linked pages and patterns you didn't know were there.
-
-**3. Briefing from your brain (not from the internet).** *"What do I need to know
-before my 2pm with the Acme team?"* pulls your meeting history, the people,
-what's still open, what the brain doesn't know yet. The agent does your prep
-because it read your context. (`query` gives you the synthesized answer with
-citations; this is the example on the [README](../../README.md).)
-
-**4. whoknows (expertise routing).** *"Who do I know who's shipped a rate
-limiter in Postgres?"* The `find_experts` tool ranks people in your brain by
-relevance + recency. Useful the moment your brain has more than a handful of
-people in it.
-
-That's the spine of it. Two commands to connect, one protocol to paste, four
-habits to build. Your agent stops being amnesiac.
-
----
-
-## Troubleshooting
-
-| Symptom | Cause | Fix |
-|---|---|---|
-| Agent "can't reach the brain" (Path A) | `gbrain serve --http` bound to loopback | Restart with `--bind 0.0.0.0` |
-| `list_skills` returns nothing / errors | Skill publishing OFF on the host | `gbrain config set mcp.publish_skills true` |
-| Token rejected on first call | Wrong/expired token | Re-mint with `gbrain auth create`; `--install` smoke-tests it for you |
-| `unknown tool: capture` | `capture` is CLI-only, not an MCP tool | Use `put_page` over MCP; `capture` only on the CLI |
-| Empty results (Path B) | Brain has nothing in it yet | `gbrain import ~/notes/` or `gbrain capture "..."` |
-
-## Next steps
-
-- Go full autonomous: the overnight enrichment daemon ([dream cycle](../../CHANGELOG.md)) fixes citations, dedupes people, builds scorecards while you sleep. See `gbrain autopilot --install`.
-- Run a real agent platform on top: [personal-brain tutorial](personal-brain.md).
-- Scale to a team: [company-brain tutorial](company-brain.md).
-- Every MCP client's exact setup: [`docs/mcp/`](../mcp/).

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

@@ -1,297 +0,0 @@
-# Auto-improve a skill with `gbrain skillopt`
-
-You have a `SKILL.md`. Sometimes the agent following it does a great job, sometimes
-it forgets a step or pads the output. This tutorial takes you from that skill to a
-measurably better version of it, in one session, without you hand-editing the
-prose. By the end you'll have written your first benchmark, watched the optimizer
-propose and test edits, and accepted an improvement that actually scored higher.
-
-Time: ~20 minutes. Cost: ~$1 in API calls for the worked example.
-
-Based on [SkillOpt](https://arxiv.org/abs/2605.23904) (Microsoft Research, May 2026).
-
-## The mental model (two sentences)
-
-Your `SKILL.md` is the trainable parameter; the agent that reads it never changes.
-SkillOpt runs the agent against a benchmark of realistic tasks, proposes specific
-edits to the skill body, re-tests, and keeps a change **only when it measurably
-beats the current version** on a held-out slice.
-
-That's the whole idea. The benchmark is how "better" gets defined — which is why
-writing it is the one part you can't skip. Everything else is mechanical.
-
-## The easiest path: generate a starter, then strengthen it
-
-You don't start from a blank file. One command reads the SKILL.md and writes a
-full starter benchmark for you:
-
-```bash
-gbrain skillopt meeting-prep --bootstrap-from-skill
-```
-
-It infers what the skill produces, writes ~15 tasks (each with rule judges) to
-`skills/meeting-prep/skillopt-benchmark.jsonl`, and appends a
-`# BOOTSTRAP_PENDING_REVIEW` sentinel so nothing runs until a human has looked.
-Then you **review and strengthen the judges** (the generated checks are weak
-drafts), delete the sentinel line, and run:
-
-```bash
-gbrain skillopt meeting-prep --bootstrap-reviewed --split 1:1:1
-```
-
-If you run an agent over this brain (OpenClaw, Claude Code, Cursor, any MCP client
-with the gbrain skills installed), it does this for you: just say "improve my
-meeting-prep skill." It runs `--bootstrap-from-skill`, strengthens the judges,
-dry-runs for cost, runs the optimizer, and reports the diff + score delta back.
-You keep or discard.
-
-**Read the rest of this tutorial to understand what that command produces** — the
-benchmark format, how to strengthen a draft (or write one by hand), how to read
-the outcome, and where the output lands.
-
-## What you'll need
-
-- `gbrain` installed and a brain initialized (`gbrain --version` works).
-- One embedding/chat provider configured. SkillOpt makes real LLM calls.
-  `gbrain models doctor` should show at least one reachable chat model.
-- A skill you want to improve, living at `skills/<name>/SKILL.md`. This tutorial
-  uses a skill called `meeting-prep` — substitute your own name everywhere.
-- A clean git working tree for that skill file (SkillOpt refuses to run over
-  uncommitted changes so it can never clobber your edits; `--force` overrides).
-
-If you don't have a skill yet, scaffold one first:
-
-```bash
-gbrain skillify scaffold meeting-prep
-```
-
-## Step 1: Get a benchmark — generated or hand-written
-
-A benchmark is a `.jsonl` file — **one JSON object per line** — where each line is
-a task plus a way to score the agent's answer. It's the crux: the benchmark IS
-your definition of "better."
-
-**The recommended way is to generate a starter** (the section above):
-`gbrain skillopt meeting-prep --bootstrap-from-skill` writes the file for you, then
-you strengthen the judges. The format below is exactly what it produces, so this
-section doubles as your guide to reviewing and sharpening a generated draft.
-
-**To follow this tutorial verbatim** (or to hand-curate from scratch), paste this
-complete 15-task starter. It's deliberately generic — once you've seen the loop
-work, **replace these tasks with your skill's real cases** (that's Step 6):
-
-```bash
-cat > skills/meeting-prep/skillopt-benchmark.jsonl <<'EOF'
-{"task_id":"mp-001","task":"Prep me for a 1:1 with a direct report I haven't met with in 3 weeks.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"agenda"},{"op":"contains","arg":"follow-up"}]}}
-{"task_id":"mp-002","task":"Prep me for a first sales call with a company I know nothing about.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"company"},{"op":"min_citations","arg":1}]}}
-{"task_id":"mp-003","task":"Prep me for a board meeting where I present the quarterly numbers.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"metric"}]}}
-{"task_id":"mp-004","task":"Prep me for a performance review I'm giving to an underperformer.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"example"}]}}
-{"task_id":"mp-005","task":"Prep me for a candidate interview for a senior backend role.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"question"}]}}
-{"task_id":"mp-006","task":"Prep me for a vendor renewal negotiation where I want a discount.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"leverage"}]}}
-{"task_id":"mp-007","task":"Prep me for a kickoff with a new cross-functional project team.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"goal"},{"op":"contains","arg":"owner"}]}}
-{"task_id":"mp-008","task":"Prep me for a difficult conversation about a missed deadline.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"impact"}]}}
-{"task_id":"mp-009","task":"Prep me for an investor update call after a flat quarter.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"metric"},{"op":"min_citations","arg":1}]}}
-{"task_id":"mp-010","task":"Prep me for a skip-level with someone two reports below me.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"question"}]}}
-{"task_id":"mp-011","task":"Prep me for a customer escalation call after an outage.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"timeline"}]}}
-{"task_id":"mp-012","task":"Prep me for a partnership exploration call with a competitor-adjacent company.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"company"},{"op":"min_citations","arg":1}]}}
-{"task_id":"mp-013","task":"Prep me for a sprint retro where morale has been low.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"action"}]}}
-{"task_id":"mp-014","task":"Prep me for a salary negotiation a report initiated.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"market"}]}}
-{"task_id":"mp-015","task":"Prep me for an all-hands where I announce a reorg.","judge":{"kind":"rule","checks":[{"op":"max_chars","arg":1800},{"op":"contains","arg":"why"}]}}
-EOF
-```
-
-Each line has three fields:
-
-- `task_id` — a unique label. Anything; you'll see it in the audit trail.
-- `task` — the prompt the agent gets, exactly as a user would phrase it.
-- `judge` — how the answer is scored. `kind: "rule"` is deterministic and **free**
-  (no LLM call): it runs a list of `checks`, and the task's score is the fraction
-  that pass.
-
-The rule checks you can use:
-
-| `op` | `arg` | Passes when the agent's answer… |
-|---|---|---|
-| `contains` | string | includes that substring |
-| `regex` | string | matches that regex (multiline) |
-| `section_present` | heading text | has a markdown heading with that text |
-| `max_chars` | number | is at most that many characters (punishes padding) |
-| `min_citations` | number | has at least N citations (markdown links, `wiki/…` refs, `[1]` footnotes) |
-| `tool_called` | tool name | the agent called that tool during the rollout |
-| `tool_not_called` | tool name | the agent did NOT call that tool |
-
-Rule judges are the right place to start. They're free, deterministic, and they
-force you to say concretely what a good answer looks like. (`judge.kind` can also
-be `"llm"` with a rubric, or `"qrels"` for retrieval tasks — see the
-[reference guide](../guides/skillopt.md) once you outgrow rules.)
-
-### The one gotcha: how many tasks you need
-
-SkillOpt splits your benchmark three ways — **train** (propose edits against),
-**sel** (the held-out gate that decides accept/reject), and **test** (final
-score). The sel slice must have **at least 5 tasks** or the run refuses, so noise
-can't masquerade as improvement.
-
-The default split is `4:1:5`, which means sel is 1/10th of your tasks — so the
-default needs **~50 tasks** before it'll run. That's too many for a first
-benchmark, which is why every command below passes `--split 1:1:1`: with the
-15-task starter that's a clean **5 train / 5 sel / 5 test**, and sel hits the
-floor exactly.
-
-```bash
-# 15 tasks + --split 1:1:1  →  5 train / 5 sel / 5 test
-gbrain skillopt meeting-prep --split 1:1:1
-```
-
-If you ever see `D_sel has N task(s) after split (need >=5)`, you either added
-fewer than 15 tasks or used a split whose middle number is too small a share.
-`--split 1:1:1` on 15+ tasks is the simplest thing that works.
-
-> When you swap in your own tasks (Step 6), keep at least 15 and cover the boring
-> middle, not just the edge cases. The benchmark IS your definition of quality;
-> a thin benchmark optimizes for a thin definition.
-
-## Step 2: Preview the cost (dry run)
-
-Before spending anything, see what the run will cost:
-
-```bash
-gbrain skillopt meeting-prep --split 1:1:1 --dry-run
-```
-
-This makes **zero LLM calls** — it just prints the plan and the cost estimate.
-A ~15-task benchmark with defaults runs around $0.70–$1.00. The preflight refuses
-to start a real run whose estimate exceeds `--max-cost-usd` (default $5.00), so
-you can't get surprise-billed mid-run.
-
-> `--dry-run` exits with code **2** ("aborted"). That's the convention for "did
-> not run the optimization," not a failure. The cost line is what you came for.
-
-## Step 3: Run it for real
-
-```bash
-gbrain skillopt meeting-prep --split 1:1:1
-```
-
-You'll watch it work: a baseline eval to set the bar, then per-step forward passes
-(run the skill), backward passes (propose edits), and a validation gate that
-runs each sel task's judge 3 times and takes the median — accepting only if the
-median beats the current best by more than 0.05.
-
-When it finishes, the last lines tell you everything:
-
-```
-[skillopt] Outcome: accepted
-[skillopt] Best sel-score: 0.840
-[skillopt] Final cost: $0.71
-[skillopt] SKILL.md rewritten with 6 optimization steps.
-```
-
-### Reading the outcome
-
-| Outcome | Exit code | What it means | What to do |
-|---|---|---|---|
-| `accepted` | 0 | A candidate beat the baseline. SKILL.md was rewritten (or a proposed file written — see Step 5). | Review the diff, keep it. |
-| `no_improvement` | 1 | Nothing cleared the gate. Your skill is already good, or the benchmark can't tell good from bad. | Strengthen the benchmark (Step 6) or stop. |
-| `aborted` | 2 | A gate stopped it: dirty working tree, over budget, `D_sel < 5`, or `--dry-run`. | Read the message — it names the gate. |
-
-`no_improvement` is not a failure. It's the gate doing its job: it would rather
-keep your known-good skill than accept a change it can't prove is better.
-
-## Step 4: See what changed
-
-The optimizer leaves a full audit trail under the skill:
-
-```bash
-ls skills/meeting-prep/skillopt/
-```
-
-```
-best.md                 ← the current winning version (== SKILL.md when accepted)
-versions/
-  v0001_e1_s1.md        ← every step's candidate, so you can diff any of them
-  v0002_e1_s2.md
-  ...
-history.json            ← append-only record of every accept/reject + scores
-rejected.json           ← edits that were tried and didn't help (so it won't retry them)
-```
-
-The actual change to your skill is a normal git diff:
-
-```bash
-git diff skills/meeting-prep/SKILL.md
-```
-
-Run-level events (cost, model, scores per run) also land in the rotating audit
-log at `~/.gbrain/audit/skillopt-YYYY-Www.jsonl`.
-
-## Step 5: Accept or reject — and the bundled-skill rule
-
-**For a skill you own** (your own `skills/` dir): an `accepted` run rewrites
-`SKILL.md` in place. It's already a git diff — review it, then `git commit` to
-keep it or `git checkout` to throw it away. Nothing is committed for you.
-
-**For a skill that ships with gbrain** (anything under the gbrain repo's own
-`skills/`): SkillOpt refuses to overwrite it by default and writes the winner to
-`skills/<name>/skillopt/best.md` instead, so an optimization pass can never
-silently mutate a skill other people depend on. Two ways to handle that:
-
-```bash
-# See the proposed improvement without touching SKILL.md (works for ANY skill):
-gbrain skillopt meeting-prep --split 1:1:1 --no-mutate
-# → writes skills/meeting-prep/skillopt/best.md (the proposed rewrite), prints its path. Copy what you want.
-
-# Actually rewrite a bundled skill (explicit opt-in + an independent held-out set):
-gbrain skillopt brain-ops --split 1:1:1 --allow-mutate-bundled \
-  --held-out skills/brain-ops/held-out.jsonl
-```
-
-Rewriting a bundled skill in place now requires BOTH `--allow-mutate-bundled` AND
-`--held-out <path>` (a JSONL with the same shape as your benchmark, but at least 5
-tasks whose IDs don't appear in the benchmark). The held-out set is how the run
-proves the edit didn't just learn the benchmark: a candidate that climbs the
-benchmark but slips on the held-out tasks is refused. Drop `--held-out` and the
-run hard-refuses and points you at `proposed.md` instead.
-
-Rule of thumb: `--no-mutate` when you want to read the diff before trusting it
-(no held-out needed); `--allow-mutate-bundled --held-out` only when you intend to
-commit a proven change to a shared skill.
-
-## Step 6: Iterate
-
-The loop that actually makes skills better:
-
-1. Run it. If `no_improvement`, the benchmark probably can't distinguish good
-   from bad yet.
-2. Add tasks that capture what you wish the skill did differently. Saw the agent
-   skip citations? Add `{"op":"min_citations","arg":2}`. Saw it ramble? Tighten
-   `max_chars`.
-3. Re-run. A sharper benchmark gives the optimizer a real gradient to climb.
-4. When a run lands `accepted`, read the diff, commit it, and bank the win.
-
-The skill you ship gets better every time the benchmark gets sharper. That's the
-whole game: you're not editing prose, you're improving the definition of done and
-letting the optimizer chase it.
-
-## What you built
-
-You wrote a benchmark that encodes what "good" means for one skill, previewed the
-cost, ran the optimizer, and either accepted a measurably better skill or learned
-your benchmark needs sharpening. Same loop scales to every skill you own — and
-`gbrain skillopt --all` runs it across every skill that has a benchmark, under a
-brain-wide cost cap.
-
-## Where to go next
-
-- **Full flag + exit-code reference, cost model, safety guards:**
-  [`docs/guides/skillopt.md`](../guides/skillopt.md)
-- **Every flag inline:** `gbrain skillopt --help`
-- **Batch + fleet + background runs** (`--all`, `--target-models`, `--background`),
-  **LLM and qrels judges**, **held-out test sets**, and **resume after a crash**
-  (`--resume <run-id>`): all in the reference guide above.
-- **Generate a starter benchmark from the SKILL.md** (the recommended way to start):
-  `gbrain skillopt <name> --bootstrap-from-skill` → review + strengthen the judges →
-  delete the sentinel → `--bootstrap-reviewed --split 1:1:1`. Tune the count with
-  `--bootstrap-tasks N` (max 50).
-- **Bootstrap from existing routing fixtures** instead: `gbrain skillopt <name>
-  --bootstrap-from-routing` (routing tasks test dispatch, not quality — tighten them).

docs/tutorials/personal-brain.md

@@ -1,270 +0,0 @@
-# Tutorial: Set up your personal AI agent + brain from zero
-
-By the end of this tutorial you'll have your own AI agent running on a server you control, talking to you over Telegram, with a brain that remembers everything you tell it. About two hours end-to-end, $100 to $150 a month sustained.
-
-This is the install I'd run if I were setting up the whole stack from scratch today. I documented it live during a setup session with a collaborator (we used Granola to capture the screen because "this is already too complicated for an archetypical person"). The tutorial is the cleaned-up version of that session.
-
-> "This is the Apple I, we're just soldering breadboards over here."
-
-If you only want the **brain layer** (no agent, no Telegram, just gbrain as memory for an MCP client you already use), skip to the [CLI standalone install](../INSTALL.md#2-cli-standalone) in INSTALL.md. If you want the whole agent **shared with a team**, read the [company brain tutorial](company-brain.md) instead. This tutorial is the solo, full-stack, talk-to-it-on-Telegram path.
-
----
-
-## What you're building
-
-A personal AI agent with four pieces:
-
-- **A brain** (git repo). Your knowledge base, constantly ingesting and growing.
-- **A harness** (OpenClaw via AlphaClaw). The runtime that gives the LLM tools, memory, and integrations.
-- **A chat interface** (Telegram). How you talk to it.
-- **Skills** (60+ installed via GBrain). Reusable capabilities the agent can invoke.
-
-Architecture:
-
-```
-Telegram → AlphaClaw (harness) → OpenClaw (agent) → GBrain (knowledge/skills) → Supabase (embeddings/search)
-```
-
-Git repo is the system of record. The whole thing is multiplayer by default: any agent that hooks into the repo works. Conflicts resolve through git.
-
----
-
-## Prerequisites
-
-| Requirement | Why |
-|---|---|
-| GitHub account (org or personal) | For the two repos that store the agent + brain |
-| Render account | For hosting the agent runtime |
-| Telegram account | For talking to your agent |
-| API keys: OpenAI, Anthropic at minimum | Embeddings + the Claude model |
-| About $100 to $150 a month | Render Pro + Supabase + API usage |
-
----
-
-## Step 1: Create two GitHub repos
-
-You need two repos, not one.
-
-1. **Workspace repo.** Agent configuration, skills, memory, crons. Example name: `your-org/myagent`. Private.
-2. **Brain repo.** Knowledge base, people pages, meeting notes, all the content the agent reads and writes. Example name: `your-org/myagent-brain`. Private.
-
-```
-GitHub → New Repository → your-org/myagent           (workspace)
-GitHub → New Repository → your-org/myagent-brain     (brain)
-```
-
-Both repos start empty. GBrain will populate the brain repo with its default structure on first install.
-
----
-
-## Step 2: Generate a fine-grained Personal Access Token
-
-GitHub → Settings → Developer Settings → Personal Access Tokens → Fine-grained tokens.
-
-- **Name:** `myagent-token`
-- **Expiration:** 1 year (or no expiration if available)
-- **Repository access:** select both repos only
-- **Permissions:** Read AND Write access to both repos (Contents, Metadata, Pull requests)
-
-GitHub's fine-grained PAT UI is painful. You may need to reload the page after creating repos before they appear in the selector. This is the worst part of the whole setup. Push through.
-
-Save this token. You'll need it for the AlphaClaw setup.
-
----
-
-## Step 3: Create a Telegram bot
-
-1. Open Telegram, message [@BotFather](https://t.me/BotFather)
-2. Send `/newbot`
-3. Name your bot (whatever you want)
-4. Get the bot token
-5. Save it. You'll need it for the AlphaClaw setup.
-
----
-
-## Step 4: Deploy via AlphaClaw on Render
-
-AlphaClaw is the setup harness that manages OpenClaw deployment.
-
-1. Go to [alphaclaw.md](https://alphaclaw.md)
-2. Enter your **workspace repo** (not the brain repo): `your-org/myagent`
-3. Select "Use existing" if the repo already exists
-4. Enter your GitHub PAT from Step 2
-5. Enter your Telegram bot token from Step 3
-6. Deploy
-
-Render will build a Docker container with the harness. First deploy takes about 5 minutes.
-
-**Memory matters.** If the instance runs out of memory during install, upgrade to Render Pro. The base tier is too small for GBrain + OpenClaw together. My production instance runs 48 cores and 64GB RAM (about $1,500 a month) but that's overkill for a new setup. Pro tier ($85 a month) is the minimum viable.
-
----
-
-## Step 5: Add provider API keys
-
-In the AlphaClaw UI (Providers tab):
-
-- **OpenAI API Key.** Required for embeddings if you use the OpenAI provider.
-- **Anthropic API Key.** Required for Claude (the main model the agent talks through).
-- **Perplexity API Key.** Optional, for web search.
-- **Voyage API Key.** Optional, alternative to OpenAI for embeddings.
-- **ZeroEntropy API Key.** Recommended. GBrain ships with ZeroEntropy as the default embedder + reranker because it's about 2× faster than OpenAI and about 2.6× cheaper.
-
-You can use the same keys across multiple agents.
-
----
-
-## Step 6: Install GBrain
-
-Once OpenClaw is running:
-
-```bash
-gbrain install
-```
-
-This installs:
-
-- About 60 skills
-- About 9 skill packs
-- Default brain structure
-- MCP server configuration
-- Supabase connection (for embeddings and search)
-
-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.
-
----
-
-## Step 7: Set up Supabase (embeddings and search)
-
-GBrain uses Supabase for vector embeddings and full-text search at scale. There are three setup gotchas I hit the hard way. Walk through them in this order.
-
-### 7a. Create the project and turn on pgvector
-
-1. Create a Supabase project at [supabase.com](https://supabase.com). Pick a region close to where your Render host runs.
-2. In the Supabase dashboard, go to **Database → Extensions**.
-3. Find `vector` (the pgvector extension) and toggle it on.
-
-Skip this and every embed write fails with "type vector does not exist" the moment GBrain tries to create its schema. pgvector is what stores the embeddings; the schema migrations refuse to run without it. Five seconds in the UI; an hour of debugging if you forget.
-
-### 7b. Get the TRANSACTION POOLER connection string, not the direct one
-
-In the Supabase dashboard, click **Connect** in the top navigation bar, then **Connection String**. Supabase shows three options. They look almost identical. Use the right one.
-
-- **Direct connection** (port 5432, host `db.YOUR-PROJECT.supabase.co`). Talks straight to the Postgres instance. IPv6-only. Will fail if your Render host doesn't have IPv6 outbound (most don't by default).
-- **Transaction pooler** (port 6543, host `aws-0-...pooler.supabase.com`). Talks through Supabase's pooler (Supavisor) in transaction mode. Works over IPv4. Survives connection storms from parallel workers. GBrain is tuned for this one: it auto-disables prepared statements on port 6543 and routes migrations, DDL, and worker locks to a separate direct connection (see 7c).
-- **Session pooler** (port 5432, host `aws-0-...pooler.supabase.com`). Also works over IPv4, with full session features. You don't need it as your main URL, but it's the free way to fix the IPv4 gotcha in 7c.
-
-You want the **Transaction pooler** string. Format looks like:
-
-```
-postgresql://postgres.YOUR-PROJECT:YOUR-PASSWORD@aws-0-us-west-1.pooler.supabase.com:6543/postgres
-```
-
-Configure it via:
-
-```bash
-gbrain config set database_url "postgresql://postgres.YOUR-PROJECT:YOUR-PASSWORD@aws-0-us-west-1.pooler.supabase.com:6543/postgres"
-```
-
-### 7c. Fix the IPv4 gotcha for migrations, DDL, and worker locks
-
-The transaction pooler (7b) carries your normal reads and writes over IPv4. But GBrain runs schema migrations, DDL, and background-worker locks on a *direct* connection, which it derives from your pooler URL by swapping the host to `db.YOUR-PROJECT.supabase.co:5432`. That direct host is **IPv6-only**. On an IPv4-only host (most Render plans), reads work but migrations hang and worker locks orphan, often silently.
-
-Two ways to fix it. The free one first:
-
-**Free: point GBrain's direct connection at the Session pooler.** The session pooler is the same Supavisor host on port 5432, and it's IPv4. Copy the **Session pooler** string from the same **Connect → Connection String** panel and set it as the direct-connection override:
-
-```bash
-export GBRAIN_DIRECT_DATABASE_URL="postgresql://postgres.YOUR-PROJECT:YOUR-PASSWORD@aws-0-us-west-1.pooler.supabase.com:5432/postgres"
-```
-
-Now both pools — reads on the transaction pooler (6543), DDL and locks on the session pooler (5432) — run over IPv4 at zero extra cost.
-
-**Paid: buy Supabase's IPv4 add-on.** About $4 a month, Pro tier or higher. It makes the direct `db.*.supabase.co` host reachable over IPv4, so the derived direct connection just works with no extra config. In the Supabase dashboard, **Project Settings → Add-ons → IPv4 address**. Toggle on, wait a minute, retry.
-
-Either fixes it. If `gbrain doctor` still shows connection failures that mention "network unreachable" or hangs forever on connect, you haven't done one of these yet.
-
-### 7d. Verify the connection
-
-```bash
-gbrain doctor
-```
-
-Green checks on schema, connectivity, pgvector extension, embedding provider. If any of those are yellow, the message will tell you which gotcha you hit (and which of 7a / 7b / 7c to revisit).
-
-### Operating note
-
-Supabase is usually the scaling bottleneck, not CPU or LLM calls. If you're doing heavy ingestion (emails, calendar, Slack streaming in), upgrade from small to large DB instance early. Don't wait for the small instance to choke; the symptoms (silent failed inserts, sync timeouts, embedding backfill stalls) all look like different bugs but are the same bug.
-
----
-
-## Step 8: Verify and chat
-
-1. Open Telegram
-2. Message your bot
-3. It should respond using OpenClaw + GBrain
-
-Send a test message. If it responds with context-awareness and can search the brain, you're live.
-
----
-
-## Architecture notes
-
-### Git as system of record
-
-The brain repo IS the brain. Any agent that can read and write to the git repo can participate. This makes the architecture inherently multiplayer: multiple agents can share a brain, work on different parts, and resolve conflicts through git.
-
-### Thin client vs fat client
-
-- **Fat client** (my production setup). OpenClaw + AlphaClaw + GBrain + 200 crons + email processing + Slack + calendar. About $1,500 a month. Processes everything in real time.
-- **Thin client** (what this tutorial builds). OpenClaw + GBrain + Telegram. About $85 a month. Chat-driven, on-demand.
-
-The goal for GBrain is to make the thin client as awesome as the fat client. Most users will start thin and grow.
-
-### MCP server
-
-GBrain exposes a Model Context Protocol server that enables inter-agent communication and integration with external systems. This is how you add read and write access to your product's API, databases, or other services.
-
-### Brain sharing
-
-Brains share through git. My main agent can populate another agent's brain by pushing content to its repo. The MCP layer enables cross-agent brain queries. Just push to the git repo and the other agent picks it up on next sync.
-
----
-
-## What this costs
-
-| Component | Monthly cost |
-|-----------|-------------|
-| Render Pro (minimum viable) | about $85 |
-| Supabase (small) | free to $25 |
-| OpenAI API (embeddings) | $5 to $20 (much less if you use ZeroEntropy as the default) |
-| Anthropic API (Claude) | $50 to $500 (usage dependent) |
-| **Total minimum** | **about $100 to $150 a month** |
-
-My production setup is about $10,000 a month, but that's 10 instances, 200 crons, processing email and Slack and calendar in real time, running sub-agents. Not what you need on day one.
-
-> "Next year it's not going to cost $10,000 a month. It'll cost $1,000 a month. And then the year after that, it'll be $100 a month, and then everyone will have it."
-
----
-
-## Common issues
-
-1. **Render runs out of memory during install.** Upgrade to Pro tier.
-2. **GitHub PAT can't see the repos.** Reload the page after creating repos. Make sure the fine-grained token has the correct repo selection.
-3. **Telegram bot doesn't respond.** Check the bot token in AlphaClaw. Make sure the Render instance is actually running.
-4. **Supabase bottleneck on heavy ingestion.** Upgrade the DB instance size before the small one chokes.
-5. **GBrain.io provisioning fails.** The hosted instance may need Pro tier. Check the machine allocation in the AlphaClaw UI.
-
----
-
-## What you built
-
-You now have a personal AI agent running on Render, talking to you on Telegram, with a brain that ingests and remembers everything you tell it. Every conversation gets indexed, every new entity (person, company, deal, concept) gets its own page, the overnight enrichment daemon dedupes and consolidates while you sleep. You wake up with a smarter agent than the one you went to bed with.
-
-Where to go next:
-
-- **Wire ingestion** from external systems. Email, calendar, voice calls, tweets, Slack. The skills are already installed; you just configure the credentials. See [`docs/integrations/`](../integrations/) for per-source recipes.
-- **Connect your existing AI client** (Claude Code, Cursor, Claude Desktop) to the same brain. See [`docs/mcp/`](../mcp/) for per-client setup.
-- **Set up the dream cycle** properly. The autopilot daemon runs overnight enrichment by default but you can tune what it does. See [`docs/architecture/`](../architecture/) for the full cycle reference.
-- **Add a teammate to your brain**, or stand the whole thing up as a company brain. See the [company brain tutorial](company-brain.md) for the multi-user walkthrough.
-
-Questions, gotchas, or wins worth sharing? Open an issue at [github.com/garrytan/gbrain](https://github.com/garrytan/gbrain/issues).

docs/v0.38-smoke-test-report.md

@@ -1,329 +0,0 @@
-# v0.38.0.0 Smoke Test Report
-
-> **Editor's Note (v0.39.3.0):** This report was contributed verbatim from
-> PR #1299 (`garrytan-agents`). Two findings were re-diagnosed during the
-> v0.39.3.0 wave; see `CHANGELOG.md` for corrections:
->
-> - **BUG-2 location:** the empty-body crash site is the `else` branch at
->   `src/commands/serve-http.ts:1594-1597` (`Buffer.from(JSON.stringify(req.body), 'utf8')`
->   throws when `req.body === undefined` because `JSON.stringify(undefined) === undefined`),
->   not line 1508 as originally reported. The empty-Buffer guard at `:1600`
->   correctly fires for empty Buffers but never reaches the undefined case.
->
-> - **WARN-5 root cause:** `gbrain capture --help` is minimal because
->   `capture` is missing from the `CLI_ONLY_SELF_HELP` set at `src/cli.ts:34-53`.
->   The detailed `HELP` constant at `src/commands/capture.ts:90-113` is
->   correct and comprehensive but unreachable; the dispatcher's generic
->   short-circuit at `:95` fires `printCliOnlyHelp(command)` first.
->   `brainstorm` and `lsd` are in the self-help set, which is why their help works.
->
-> All 2 bugs and 10 warnings are addressed in v0.39.3.0. The report below
-> is preserved as the historical record of what production looked like on
-> 2026-05-22.
-
-Production smoke test of the v0.38.0.0 ingestion cathedral release on a live
-Postgres-backed server (Supabase, pgvector, PgBouncer transaction mode).
-
-**Test date:** 2026-05-22
-**Server:** MCP HTTP server v0.38.0.0 on port 3131, Postgres engine
-**Prior version:** v0.37.9.0
-
----
-
-## Summary
-
-| Category | Pass | Warn | Fail |
-|----------|------|------|------|
-| `gbrain capture` — basic | 7 | 0 | 0 |
-| `gbrain capture` — edge cases | 3 | 3 | 1 |
-| Dedup behavior | 0 | 2 | 0 |
-| POST /ingest webhook | 5 | 1 | 1 |
-| Provenance columns | 2 | 1 | 0 |
-| `brainstorm` / `lsd` | 2 | 1 | 0 |
-| CLI help & discoverability | 1 | 2 | 0 |
-| MCP server health | 1 | 0 | 0 |
-| **Total** | **21** | **10** | **2** |
-
----
-
-## 🐛 Bugs (2)
-
-### BUG-1: `capture --file` doubles frontmatter on files with existing frontmatter
-
-**Severity:** Medium
-**Repro:**
-```bash
-cat > /tmp/test.md << 'EOF'
----
-title: Pre-existing Title
-tags: [test, frontmatter]
----
-
-# Pre-existing content
-
-This file already has frontmatter.
-EOF
-
-gbrain capture --file /tmp/test.md
-gbrain get inbox/2026-05-22-XXXXXX
-```
-
-**Observed:** The page on disk gets TWO frontmatter blocks. The outer block
-has `title: '---'` (it parsed the inner `---` delimiter as the title), and
-the original frontmatter is preserved verbatim inside the body:
-
-```yaml
----
-type: note
-title: '---'
-captured_at: '2026-05-22T16:06:11.334Z'
-captured_via: capture-cli
-ingested_via: put_page
-ingested_at: '2026-05-22T16:06:13.038Z'
-source_kind: put_page
----
-
----
-title: Pre-existing Title
-tags: [test, frontmatter]
----
-
-# Pre-existing content
-```
-
-**Expected:** `buildContent` should detect existing frontmatter (the commit
-message says it has a "looks like markdown" heuristic for first-line heading
-or frontmatter delimiter) and not double-wrap. The inner frontmatter fields
-should merge with capture's fields.
-
-**Location:** `src/commands/brainstorm.ts` → `buildContent` function (shared
-with capture).
-
----
-
-### BUG-2: POST /ingest crashes with unhandled TypeError on empty body
-
-**Severity:** Medium
-**Repro:**
-```bash
-# With valid bearer token:
-curl -X POST localhost:3131/ingest \
-  -H "Authorization: Bearer $TOKEN" \
-  -H "Content-Type: text/plain"
-```
-
-**Observed:** Returns a 500 HTML error page with stack trace:
-```
-TypeError: The first argument must be of type string, Buffer, ArrayBuffer,
-Array, or Array-like Object. Received undefined
-  at serve-http.ts:1508:23
-```
-
-**Expected:** The route already has an `empty_body` check (documented in the
-code and tested in the E2E suite), but the body-parser middleware for
-`/ingest` uses `express.raw()` which returns `undefined` for an empty POST
-(no Content-Length, no body). The `empty_body` guard fires AFTER the
-`computeContentHash(body)` call, which crashes on `undefined`.
-
-**Fix:** Move the null/undefined/empty-buffer check before the content-hash
-computation, or add a guard at the top of the route handler:
-```typescript
-if (!req.body || req.body.length === 0) {
-  return res.status(400).json({ error: 'empty_body', message: '...' });
-}
-```
-
----
-
-## ⚠️ Warnings (10)
-
-### WARN-1: Dedup does not actually deduplicate identical captures
-
-**Observed:** Capturing identical text twice produces the same slug but
-different `content_hash` values:
-
-```
-Run 1: slug=inbox/2026-05-22-3d5b671a, hash=1faf3166...
-Run 2: slug=inbox/2026-05-22-3d5b671a, hash=f6ee8098...
-```
-
-**Root cause:** The content hash includes the full serialized page with
-frontmatter, and `captured_at` changes between runs (it's timestamped).
-The slug is deterministic (derived from content text), so it correctly
-maps to the same page — but the hash changes every time.
-
-**Impact:** The "24h content-hash LRU dedup" in the daemon layer won't
-catch duplicate captures because the hash differs. The `put_page`
-upsert catches it at the slug level (overwrites), so no duplicate pages
-are created — but the content_hash-based dedup layer is effectively
-bypassed for CLI captures.
-
-**Suggestion:** Compute content_hash from the user's input text before
-adding frontmatter, or exclude `captured_at` from the hash computation.
-
----
-
-### WARN-2: Same text with different `--type` flags overwrites the previous capture
-
-Same slug is generated for identical text regardless of `--type`. The
-second capture with `--type observation` silently overwrites the first
-with `--type idea`. This is correct behavior (slug = content hash), but
-may surprise users who expect type changes to produce distinct pages.
-
----
-
-### WARN-3: `--source` flag crashes with raw FK violation
-
-```
-gbrain capture: put_page failed: insert or update on table "pages" violates
-foreign key constraint "pages_source_id_fk"
-```
-
-The error message exposes a raw Postgres FK violation. Users have no way
-to know what to do. The capture command should catch this error and print
-a human-friendly message:
-
-```
-Error: source 'my-source' is not registered. Register it first:
-  gbrain sources add my-source --path /path/to/source
-```
-
----
-
-### WARN-4: `facts:absorb` connection error after every capture
-
-Every capture logs:
-```
-[facts:absorb] failed to log gateway_error for inbox/...: No database
-connection: connect() has not been called. Fix: Run gbrain init --supabase
-```
-
-Non-fatal (exit 0), but noisy. The facts subsystem tries to open a
-separate connection that the CLI capture path doesn't initialize.
-
----
-
-### WARN-5: `capture --help` is minimal — doesn't show flags
-
-```
-$ gbrain capture --help
-Usage: gbrain capture
-
-gbrain capture - run gbrain --help for the full command list.
-```
-
-Compare with `brainstorm --help` which has a full Options section,
-examples, and cost info. The capture help should document `--type`,
-`--file`, `--source`, `--json`, `--stdin`, `--slug`, etc.
-
----
-
-### WARN-6: `capture`, `brainstorm`, `lsd` missing from `gbrain --help`
-
-None of these three commands appear in the main help text. They work when
-invoked directly, but users can't discover them from the help output.
-`gbrain --help` lists every other command (get, put, search, etc.) but
-the v0.37/v0.38 commands are absent.
-
----
-
-### WARN-7: Binary file capture succeeds silently
-
-```bash
-head -c 256 /dev/urandom > /tmp/binary.bin
-gbrain capture --file /tmp/binary.bin
-```
-
-This succeeds, creating a page with binary garbage as content. Should
-either reject non-text files or at minimum warn.
-
----
-
-### WARN-8: Provenance columns not populated by `capture`
-
-The capture CLI reports `"source_kind": "capture-cli"` in its JSON output,
-but the actual database row has:
-
-```json
-{ "source_id": "default", "source_uri": null, "source_kind": null }
-```
-
-The provenance fields from capture's output don't round-trip into the
-`put_page` call that persists the page.
-
----
-
-### WARN-9: Admin register-client ignores scope parameter
-
-Registering a client via `/admin/api/register-client` with
-`"scope": "read write"` creates a client with scope `"read"` only.
-The admin endpoint appears to ignore or default the scope field. Required
-manual DB update to get `write` scope for webhook testing.
-
----
-
-### WARN-10: `brainstorm` / `lsd` may hang or timeout on PgBouncer
-
-In transaction-mode PgBouncer environments, `brainstorm` consistently
-times out after the cost estimate with `canceling statement due to
-statement timeout`. The hybrid search + domain-bank phase appears to
-hit PgBouncer's statement timeout. This may be environmental, but the
-command should handle the timeout gracefully and report what failed
-rather than silently producing no output.
-
----
-
-## ✅ What Works Well
-
-- **`gbrain capture "text"`** — works perfectly for the simple case.
-  Frontmatter stamps, JSON output, disk write, immediate searchability.
-- **`gbrain capture --file`** — works for plain text and simple markdown
-  (frontmatter doubling bug only affects files with existing frontmatter).
-- **`gbrain capture ""`** and no-args — clean error messages:
-  `"provide content positionally, --file PATH, or --stdin"`.
-- **`gbrain capture --file /nonexistent`** — clean ENOENT error.
-- **Unicode/emoji** — `gbrain capture "测试 🧠🔥 émojis"` works perfectly.
-- **Long text** — 2500+ character capture works, correctly produces 2 chunks.
-- **POST /ingest auth gate** — properly rejects missing auth (401), invalid
-  tokens (401), and insufficient scope (403).
-- **POST /ingest content-type validation** — properly rejects image/png and
-  application/pdf with a helpful error pointing to skillpack processors.
-- **POST /ingest accepted types** — text/plain, text/markdown, text/html,
-  application/json all accepted and queued.
-- **X-Gbrain-Source-Id header** — custom source ID flows through correctly.
-- **MCP health endpoint** — returns clean JSON with version and engine.
-- **OAuth client_credentials flow** — works correctly once the client has
-  proper scope.
-- **Content-hash dedup on webhook** — verified via response `content_hash`.
-- **Migration v81** — provenance columns added cleanly, nullable, no
-  disruption to existing pages. 290K+ existing pages unaffected.
-- **`brainstorm --help` / `lsd --help`** — excellent help text with
-  examples, cost estimates, and cross-references.
-- **Soft delete + recovery** — cleanup via `gbrain delete` works with
-  72h recovery window.
-- **`--type` flag** — `note`, `idea`, `observation` all work correctly.
-
----
-
-## 💡 Suggestions
-
-1. **`capture --help` parity** — give it the same quality help text as
-   `brainstorm --help`. Document every flag.
-
-2. **Main help completeness** — add `capture`, `brainstorm`, and `lsd` to
-   the `gbrain --help` command listing. These are user-facing features that
-   can't be discovered.
-
-3. **Content-hash stability** — consider computing the dedup hash from
-   user input text only (before frontmatter injection) so identical
-   captures are properly deduped at the daemon layer.
-
-4. **Provenance write-through** — `capture` already knows it's
-   `source_kind: "capture-cli"`. Pass this through to `put_page` so the
-   DB columns are populated.
-
-5. **Binary file guard** — reject or warn on non-text input in
-   `capture --file`. Check file content or extension before proceeding.
-
-6. **`--source` error UX** — catch the FK violation and print a
-   human-friendly hint about registering sources.

docs/what-schemas-unlock.md

@@ -1,177 +0,0 @@
-# What schemas unlock
-
-Most note-taking apps treat every page the same. You write something, it goes in a pile, you search the pile with text matching. Tags help, but tags are flat. After a few thousand pages, the pile gets noisy and the search gets stupid.
-
-Schemas are how gbrain stops being a pile of notes and becomes something with structure. A schema declares what KINDS of things live in your brain (`person`, `company`, `meeting`, `researcher`, `case`, `lab-result`), what they link to (`attended`, `authored`, `prescribed-by`), what facts the system should extract automatically (`mrr=50000`, `damages=5000000`), and which types route through expert search vs general search.
-
-The default schema (`gbrain-base`) ships with 22 page types covering the universal shapes — people, companies, meetings, notes, daily, calendar events. That's enough to start. But your brain is yours, and your brain's shape is not the default shape. A research brain needs `researcher` and `paper` as first-class types. A founder brain needs `lead`, `investor`, `portco`, `deal-stage`. A lawyer brain needs `case`, `motion`, `deposition`, `precedent`. Same engine, totally different shape.
-
-v0.40.7.0 made it possible for AGENTS to author that shape for you. Not just "the user manually edits YAML in `~/.gbrain/schema-packs/mine/pack.yaml`" but "your agent sees the corpus, proposes a type, asks for approval, applies it atomically with a full audit trail, then backfills 4000 existing pages with one chunked SQL command." That's the new thing.
-
-This doc is the WHY. The [tutorial](schema-author-tutorial.md) is the HOW.
-
-## Killer use cases
-
-### 1. The 4000 invisible pages
-
-You have 4000 markdown files under `meetings/` going back two years. The default schema doesn't have a `meeting` type, so all 4000 are typed `note` (the catchall). When you run:
-
-```bash
-gbrain whoknows "Q3 roadmap discussion"
-```
-
-You get the top 10 text matches, ranked by raw relevance. The brain has no idea these are meetings. It can't route to attendees. It can't pull dates. It can't surface "this conversation came up again with the same people three weeks later."
-
-Add a `meeting` type:
-
-```bash
-gbrain schema add-type meeting --primitive temporal --prefix meetings/ --extractable
-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 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.
-
-### 2. The founder ops brain
-
-You're a founder or investor with ~500 markdown files mixing leads, portfolio companies, deal notes, intros, and follow-ups. You've been writing freely; you have no system. Your queries are all "wait, who introduced me to that fintech founder again?" and you scroll Notion for 20 minutes.
-
-Add the founder shape:
-
-```bash
-gbrain schema fork gbrain-base mine
-gbrain schema use mine
-
-# Types
-gbrain schema add-type lead       --primitive entity --prefix people/leads/         --expert
-gbrain schema add-type investor   --primitive entity --prefix people/investors/     --expert --extractable
-gbrain schema add-type portco     --primitive entity --prefix companies/portco/     --expert --extractable
-gbrain schema add-type deal       --primitive entity --prefix companies/deals/      --extractable
-
-# Link verbs
-gbrain schema add-link-type invested-in --page-type investor --target-type portco
-gbrain schema add-link-type intro-from  --page-type lead     --target-type lead
-gbrain schema add-link-type passed-on   --page-type investor --target-type deal
-gbrain schema add-link-type led-by      --page-type deal     --target-type investor
-
-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)`.
-
-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.
-
-### 3. The research brain
-
-Replace "founder" with "PhD student" and the same pattern applies with different types: `researcher`, `paper`, `lab`, `grant`, `dataset` + `authored`, `cites`, `funded-by`, `uses-dataset`.
-
-```bash
-gbrain schema add-type paper --primitive annotation --prefix research/papers/ --extractable
-gbrain schema add-link-type authored   --page-type researcher --target-type paper
-gbrain schema add-link-type cites      --page-type paper      --target-type paper
-gbrain schema add-link-type uses       --page-type paper      --target-type dataset
-```
-
-Suddenly "show me papers that cite this work AND use the same dataset" is a `gbrain graph-query` traversal, not 30 minutes in Google Scholar. The fact extraction picks up `arxiv_id=2402.04253`, `cited_by_count=140`, `published_date=2026-02-15` automatically. Your reading-list-as-markdown turns into a queryable research graph that knows who works on what and what's connected to what.
-
-### 4. The legal brain (or any domain where claims have numbers)
-
-Lawyers, medical providers, accountants, anyone working in a domain where the meaning of a number depends on its type. A "judgment of $5M" against a "$2M case strategy threshold" is a comparison the brain can do — but only if both numbers are typed.
-
-```bash
-gbrain schema add-type case --primitive entity --prefix legal/cases/ --extractable --expert
-gbrain schema add-type motion --primitive annotation --prefix legal/motions/ --extractable
-gbrain schema add-type deposition --primitive annotation --prefix legal/depositions/ --extractable
-gbrain schema add-link-type filed-in --page-type motion --target-type case
-gbrain schema add-link-type cites    --page-type motion --target-type precedent
-```
-
-Now `## Facts` fences in your case notes can carry typed claims (`damages=5000000`, `filed_date=2026-05-23`, `judge=jane-doe`) that gbrain stores as first-class columns. `gbrain eval trajectory legal/cases/acme-v-widget` prints the case history with regressions flagged. `gbrain founder scorecard` (renamed for legal: roll up plaintiff success rate, average damages, settlement-vs-trial ratio) gives you a structured view of how your practice is performing.
-
-This isn't possible without typed page kinds. You can write the same prose in any note-taking app. Only gbrain treats the numbers as comparable across pages of the same type.
-
-### 5. The team brain
-
-`gbrain mounts add` lets you stack additional brains alongside your personal one. Each mounted brain has its OWN schema pack. The eng team's brain has `incident`, `runbook`, `service`, `oncall-rotation`. The design team's brain has `component`, `experiment`, `ab-test`, `figma-link`. The legal team's brain has cases and depositions.
-
-When you query, the schema pack governs how each source's content is routed. An eng query against the mounted eng brain knows that `incidents/2026-05-23-db-outage.md` is an `incident` page with `severity=p0`, `mttr=47min`, `on_call=alice-example` — extractable typed facts. Your personal query against the same brain still works, but the routing is sharper because the eng team has invested in their ontology.
-
-The schema is the team's tribal knowledge made explicit. Two engineers on different teams searching the same brain get DIFFERENT routing because their personal packs declare different expert types.
-
-### 6. The "agent co-curates your ontology" pattern (the new thing)
-
-This is what v0.40.7.0 actually enabled, and what the closed PR #1321 was reaching for.
-
-Your OpenClaw (or any agent connected to your brain over HTTPS MCP with admin scope) watches your ingestion stream. After a week of you dumping notes under `garrytan/companies/yc-w24/`, the agent runs `gbrain schema detect` periodically, sees that prefix accumulating, and proposes:
-
-> You have 47 pages under `companies/yc-w24/` typed as `company` (generic). They share a structural pattern (founder names, raise amounts, batch tag). Should I add a `yc-w24-company` type with `extractable: true` and the existing aliases pointing back to `company`? I'd backfill the 47 pages and add `cohort=W24` as a typed fact extracted from each page.
-
-You approve once. The agent calls `schema_apply_mutations` over MCP with a batch:
-
-```json
-{
-  "pack": "mine",
-  "mutations": [
-    {"op": "add_type", "name": "yc-w24-company", "primitive": "entity", "prefix": "companies/yc-w24/", "extractable": true, "expert_routing": true},
-    {"op": "add_alias", "type": "yc-w24-company", "alias": "company"}
-  ]
-}
-```
-
-All inside ONE `withPackLock` scope, atomic, audited (the agent's `client_id` captured in the audit log as `actor: mcp:<clientId8>`). Cache invalidated cross-process. Sync backfills the 47 pages. The brain learned a new category of thing without you having to think about it.
-
-The next time you query "YC W24 companies in fintech", the brain routes through the new type. Six months later when you forget the pattern entirely, the agent reminds you it's there and offers to consolidate it with the W25 batch.
-
-The brain learns. The agent is the curator. You approve, the agent does the work.
-
-### 7. The before-vs-after benchmark
-
-If you want to FEEL the difference without buying the pitch:
-
-Pick a real corpus you have. Run `gbrain whoknows` on a topic that should match. Note the top-3 results.
-
-Then run `gbrain schema review-orphans --limit 50 --json` and look at the untyped pages. If 10+ of them share an obvious prefix that should be a real type, add the type + sync.
-
-Re-run the same `whoknows` query. Top-3 should shift, because the new type is now routing through expert ranking instead of being lumped into the catchall. The numerical delta IS the win. You can run a tutorial in 5 minutes; this experiment proves it matters on your actual content.
-
-## Why this matters
-
-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.
-
-**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.
-
-**3. The schema is queryable AND mutable AND auditable.** You can ask the brain what its schema looks like (`gbrain schema graph`), evolve it through 14 atomic CLI verbs + 9 MCP ops with full lock + audit semantics, and recover from any mistake (every primitive has an inverse, plus `gbrain schema downgrade` restores the previous active pack). This isn't "vibes-based knowledge management." It's a production system with structural integrity guarantees.
-
-## What changed in v0.40.7.0 specifically
-
-v0.39.1.0 shipped the schema-pack engine. You could ALREADY fork the bundled pack and edit `pack.yaml` by hand. What you couldn't do was let an agent author it safely — there were no atomic file locks, no audit log, no MCP exposure, no pack-aware wiring in the query path. The cathedral was built but unreachable from the outside.
-
-v0.40.7.0 closed those gaps:
-
-- **`withMutation` skeleton** wraps every primitive in 8 ordered safety steps (bundled-guard → lock → read → mutate → validate → atomic write → audit → invalidate). The pack file on disk is never partial. Two concurrent agents can't race.
-- **Per-pack `O_CREAT|O_EXCL` atomic lock** (not the TOCTOU `existsSync+writeFileSync` pattern from page-lock.ts — codex caught that during plan review). TTL refresh every 10s while a mutation runs; `--force` means "steal stale lock" not "skip locking."
-- **Privacy-redacted audit log** at `~/.gbrain/audit/schema-mutations-YYYY-Www.jsonl`. Type names sha8-hashed, prefixes truncated to first segment only. A leaked screenshot of the audit can't reveal sensitive taxonomy like `personal/oncology/` or `legal/depositions/`.
-- **9 new MCP ops** including the batched `schema_apply_mutations` (admin scope, NOT localOnly — your OpenClaw and any remote agent author packs over normal HTTPS MCP, with `client_id` captured as `actor: mcp:<clientId8>`).
-- **T1.5 wiring** finally completes for `whoknows` and `find_experts`: a custom `researcher` type marked `--expert` now actually surfaces in query results. Pre-v0.40.7 it silently never matched because the query path read hardcoded `['person', 'company']`.
-- **Cross-process invalidation** via stat-mtime TTL gate inside `loadActivePack`. Operator runs `gbrain schema add-type` from a terminal; the autopilot daemon picks up the new type within 1 second without a restart.
-
-The cumulative effect: an agent can safely co-curate your ontology with a complete forensic trail. That's the new thing.
-
-## Where to start
-
-- **Want to see it work in 5 minutes?** Run the [tutorial](schema-author-tutorial.md). Forks the bundled pack, adds a researcher type, proves the wiring end-to-end.
-- **Want the agent recipe?** Read [`skills/schema-author/SKILL.md`](../skills/schema-author/SKILL.md). 7-phase workflow agents follow when they detect a schema-evolution opportunity.
-- **Want the rules of thumb?** Read [`skills/conventions/schema-evolution.md`](../skills/conventions/schema-evolution.md). Decision tree for when to add a type vs alias vs prefix. <20 pages don't pack-codify. 100+ pages need first-class types.
-- **Want the architecture?** The "Schema Cathedral v3 (v0.40.7.0)" section in `CLAUDE.md` has the 14-bullet module-by-module breakdown, each citing the design decision and codex finding that motivated it.
-- **Want to set up an agent that co-curates your brain?** Run `gbrain auth register-client my-agent --scopes admin` to mint an OAuth client your remote agent can use to call `schema_apply_mutations` over MCP. The agent then runs detect → suggest → apply on its own cadence and asks you to approve substantive changes.
-
-The killer feature isn't "schemas." Personal knowledge systems have had schemas forever. The killer feature is that your AGENT can shape them safely on your behalf, with structural integrity guarantees that match what you'd expect from a database, not a notes app.
-
-That's what we built. Try it on a corpus you actually have and the numbers go up.

evals/functional-area-resolver/harness-runner.ts

@@ -415,7 +415,6 @@ export async function main(argv: string[]): Promise<number> {
     chat_model: config?.chat_model ?? modelFull,
     chat_fallback_chain: config?.chat_fallback_chain,
     base_urls: config?.provider_base_urls,
-    provider_chat_options: config?.provider_chat_options,
     env: { ...process.env } as Record<string, string>,
   });
 

evals/skillopt-judge/README.md

@@ -1,31 +0,0 @@
-# SkillOpt judge LLM accuracy eval (F9)
-
-Hand-labeled (trajectory, expected_score) pairs. Measures whether the judge
-model's scores agree with human judgment within reasonable bounds.
-
-## Fixtures
-
-`fixtures.jsonl` — one row per (judge_kind, rubric, trajectory, gold_score)
-quadruple. Gold scores are integer 1-5 (per common Likert practice);
-normalized to 0..1 inside the runner.
-
-## Runner
-
-`runner.mjs` reads fixtures, calls `scoreTrajectory`, computes per-fixture
-absolute error vs gold, aggregates to mean absolute error (MAE).
-
-Pass criterion: MAE <= 0.15 on the 0..1 scale (judge agrees with gold
-within ~one-eighth of the full range).
-
-## Cost
-
-~10 fixtures × ~$0.005 each = $0.05 per run. Refresh when the judge prompt
-changes or when switching judge models.
-
-## Reproduce
-
-```bash
-node evals/skillopt-judge/runner.mjs \
-  --judge-model anthropic:claude-sonnet-4-6 \
-  --output evals/skillopt-judge/receipts/$(date +%Y%m%d).json
-```

evals/skillopt-judge/fixtures.jsonl

@@ -1,10 +0,0 @@
-{"id":"judge-001","rubric":"Does the output (a) name 3+ board members, (b) cite recent material, (c) flag any open risks? Score 0..1.","final_text":"Board members: alice-example, bob-example, charlie-example. Recent: 2026 funding round [wiki/companies/widget-co]. Risks: cash runway 8 months.","gold_score":1.0}
-{"id":"judge-002","rubric":"Does the output (a) name 3+ board members, (b) cite recent material, (c) flag any open risks? Score 0..1.","final_text":"alice-example is the CEO.","gold_score":0.2}
-{"id":"judge-003","rubric":"Does the output contain a structured summary with bullet points? Score 0..1.","final_text":"- Point 1\n- Point 2\n- Point 3","gold_score":1.0}
-{"id":"judge-004","rubric":"Does the output contain a structured summary with bullet points? Score 0..1.","final_text":"It's a long story, no bullets.","gold_score":0.1}
-{"id":"judge-005","rubric":"Is the output under 280 characters AND contains a verifiable claim? Score 0..1.","final_text":"Network effects compound: data → better model → more users → more data. [wiki/concepts/network-effects]","gold_score":0.9}
-{"id":"judge-006","rubric":"Is the output under 280 characters AND contains a verifiable claim? Score 0..1.","final_text":"Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff. Lots of stuff.","gold_score":0.0}
-{"id":"judge-007","rubric":"Does the output have a clear thesis in the first sentence? Score 0..1.","final_text":"Network effects are the most underrated business primitive. Here's why...","gold_score":0.95}
-{"id":"judge-008","rubric":"Does the output have a clear thesis in the first sentence? Score 0..1.","final_text":"Various things to consider. Some are important. Others less so.","gold_score":0.15}
-{"id":"judge-009","rubric":"Does the output cite at least 2 brain pages (wiki/, people/, companies/, etc)? Score 0..1.","final_text":"See wiki/people/alice-example and companies/widget-co for details.","gold_score":1.0}
-{"id":"judge-010","rubric":"Does the output cite at least 2 brain pages? Score 0..1.","final_text":"No citations here.","gold_score":0.05}

evals/skillopt-judge/runner.mjs

@@ -1,87 +0,0 @@
-#!/usr/bin/env node
-// SkillOpt judge LLM accuracy eval runner (F9).
-//
-// Reads fixtures.jsonl, calls scoreTrajectory with llm judge mode, computes
-// per-fixture absolute error vs gold, writes a JSON receipt.
-//
-// Pass criterion: MAE <= 0.15.
-//
-// Usage:
-//   node evals/skillopt-judge/runner.mjs \
-//     --judge-model anthropic:claude-sonnet-4-6 \
-//     --output evals/skillopt-judge/receipts/$(date +%Y%m%d).json
-
-import { readFileSync, writeFileSync, mkdirSync } from 'node:fs';
-import { dirname, join } from 'node:path';
-
-const args = process.argv.slice(2);
-function flag(name, def) {
-  const i = args.indexOf(name);
-  return i >= 0 ? args[i + 1] : def;
-}
-
-const judgeModel = flag('--judge-model', 'anthropic:claude-sonnet-4-6');
-const fixturesPath = flag('--fixtures', join(import.meta.dirname, 'fixtures.jsonl'));
-const outputPath = flag('--output');
-
-const fixtures = readFileSync(fixturesPath, 'utf8')
-  .split('\n')
-  .filter((l) => l.trim().length > 0)
-  .map((l) => JSON.parse(l));
-
-const { scoreTrajectory } = await import('../../src/core/skillopt/score.ts');
-
-const perFixture = [];
-let totalAbsError = 0;
-let parseFailures = 0;
-
-for (const fx of fixtures) {
-  const trajectory = {
-    task_id: fx.id,
-    task: 'judge-eval',
-    final_text: fx.final_text,
-    tool_calls: [],
-    usage: { input_tokens: 0, output_tokens: 0, cache_read_tokens: 0, cache_creation_tokens: 0 },
-    turns: 1,
-    stop_reason: 'end',
-    duration_ms: 0,
-  };
-  const result = await scoreTrajectory(trajectory, { kind: 'llm', rubric: fx.rubric }, { judgeModel });
-  const absErr = Math.abs(result.score - fx.gold_score);
-  totalAbsError += absErr;
-  if (result.judge_error) parseFailures += 1;
-  perFixture.push({
-    id: fx.id,
-    gold: fx.gold_score,
-    actual: result.score,
-    abs_error: absErr,
-    judge_error: result.judge_error ?? null,
-    rationale: result.rationale ?? null,
-  });
-}
-
-const mae = fixtures.length > 0 ? totalAbsError / fixtures.length : 0;
-const verdict = mae <= 0.15 ? 'pass' : 'fail';
-
-const receipt = {
-  schema_version: 1,
-  timestamp: new Date().toISOString(),
-  judge_model: judgeModel,
-  fixtures_count: fixtures.length,
-  parse_failures: parseFailures,
-  mae,
-  verdict,
-  threshold: 0.15,
-  per_fixture: perFixture,
-};
-
-const out = JSON.stringify(receipt, null, 2);
-if (outputPath) {
-  mkdirSync(dirname(outputPath), { recursive: true });
-  writeFileSync(outputPath, out);
-  process.stderr.write(`Wrote receipt to ${outputPath}\n`);
-} else {
-  process.stdout.write(out + '\n');
-}
-
-process.exit(verdict === 'pass' ? 0 : 1);

evals/skillopt-reflect/README.md

@@ -1,35 +0,0 @@
-# SkillOpt reflect-prompt quality eval (F8)
-
-Gold-labeled trajectories paired with expected-edit shapes. Measures whether
-the optimizer model's reflect prompt proposes the kind of edit a human would
-write given the same trajectory.
-
-## Fixtures
-
-`fixtures.jsonl` — one row per (skill_body, scored_rollouts, expected_edits)
-triple. The `expected_edits` are loose shape constraints (the op kind + a
-substring of the target/anchor), not exact-text equality, because LLMs
-won't propose byte-identical text.
-
-## Runner
-
-`runner.mjs` reads `fixtures.jsonl`, calls `runReflect` for each fixture,
-checks every proposed edit against the expected_edits set, and writes a
-JSON receipt with per-fixture pass/fail + aggregate hit rate.
-
-Pass criterion: aggregate hit rate >= 0.7 (each fixture has 1-3 expected
-edits; the optimizer "wins" the fixture if at least one of its proposals
-matches an expected shape).
-
-## Cost
-
-~5 fixtures × ~$0.10 each (Opus reflect call) = ~$0.50 per run. Refresh
-the suite when the reflect prompt changes; otherwise weekly is enough.
-
-## Reproduce
-
-```bash
-node evals/skillopt-reflect/runner.mjs \
-  --optimizer-model anthropic:claude-opus-4-7 \
-  --output evals/skillopt-reflect/receipts/$(date +%Y%m%d).json
-```

evals/skillopt-reflect/fixtures.jsonl

@@ -1,5 +0,0 @@
-{"id":"reflect-001","skill_body":"# Brief Generator\n\nWhen asked, produce a 3-section brief: People, Companies, Risks.\n","scored_rollouts":[{"score":0.3,"task":"Brief on widget-co-example","final_text":"Here are the people: alice-example.","tool_calls":[{"name":"search"}],"failed":[]},{"score":0.3,"task":"Brief on acme-example","final_text":"Just some people: bob-example.","tool_calls":[{"name":"search"}],"failed":[]}],"expected_edits":[{"op":"add","anchor_contains":"Brief Generator"},{"op":"replace","target_contains":"3-section"}]}
-{"id":"reflect-002","skill_body":"# Citations Required\n\nAlways include 2+ citations.\n","scored_rollouts":[{"score":1.0,"task":"Cite alice-example","final_text":"alice-example [wiki/people/alice-example] worked at [wiki/companies/widget-co].","tool_calls":[{"name":"get_page"},{"name":"get_page"}],"failed":[]},{"score":1.0,"task":"Cite bob-example","final_text":"bob-example [wiki/people/bob-example] and [wiki/companies/acme-example].","tool_calls":[{"name":"get_page"},{"name":"get_page"}],"failed":[]}],"expected_edits":[{"op":"add","anchor_contains":"Citations"}]}
-{"id":"reflect-003","skill_body":"# Meeting Prep\n\nProduce a brief for the upcoming meeting.\n","scored_rollouts":[{"score":0.2,"task":"Prep meeting with alice-example","final_text":"OK","tool_calls":[],"failed":[]},{"score":0.2,"task":"Prep meeting with widget-co","final_text":"Will do","tool_calls":[],"failed":[]}],"expected_edits":[{"op":"replace","target_contains":"Produce a brief"},{"op":"add","anchor_contains":"Meeting Prep"}]}
-{"id":"reflect-004","skill_body":"# Tweet Composer\n\nUnder 280 chars. Include claim + evidence.\n","scored_rollouts":[{"score":0.5,"task":"Tweet about network effects","final_text":"Network effects are powerful. They compound over time.","tool_calls":[],"failed":[]}],"expected_edits":[{"op":"add","anchor_contains":"Tweet Composer"}]}
-{"id":"reflect-005","skill_body":"# Fact Check\n\nVerify the claim against the brain.\n","scored_rollouts":[{"score":0.0,"task":"Check claim X","final_text":"Yes","tool_calls":[],"failed":[]},{"score":0.0,"task":"Check claim Y","final_text":"No","tool_calls":[],"failed":[]}],"expected_edits":[{"op":"replace","target_contains":"Verify the claim"}]}

evals/skillopt-reflect/runner.mjs

@@ -1,119 +0,0 @@
-#!/usr/bin/env node
-// SkillOpt reflect-prompt quality eval runner (F8).
-//
-// Reads fixtures.jsonl, calls runReflect for each fixture, scores edits
-// against expected_edits shape constraints, writes a JSON receipt.
-//
-// Usage:
-//   node evals/skillopt-reflect/runner.mjs \
-//     --optimizer-model anthropic:claude-opus-4-7 \
-//     --output evals/skillopt-reflect/receipts/$(date +%Y%m%d).json
-
-import { readFileSync, writeFileSync, mkdirSync } from 'node:fs';
-import { dirname, join } from 'node:path';
-
-const args = process.argv.slice(2);
-function flag(name, def) {
-  const i = args.indexOf(name);
-  return i >= 0 ? args[i + 1] : def;
-}
-
-const optimizerModel = flag('--optimizer-model', 'anthropic:claude-opus-4-7');
-const fixturesPath = flag('--fixtures', join(import.meta.dirname, 'fixtures.jsonl'));
-const outputPath = flag('--output');
-
-const fixtures = readFileSync(fixturesPath, 'utf8')
-  .split('\n')
-  .filter((l) => l.trim().length > 0)
-  .map((l) => JSON.parse(l));
-
-const { runReflect } = await import('../../src/core/skillopt/reflect.ts');
-
-const perFixture = [];
-let totalWins = 0;
-let totalExpected = 0;
-
-for (const fx of fixtures) {
-  const scoredRollouts = fx.scored_rollouts.map((r) => ({
-    trajectory: {
-      task_id: r.task,
-      task: r.task,
-      final_text: r.final_text,
-      tool_calls: (r.tool_calls ?? []).map((tc) => ({ name: tc.name, input: {}, failed: !!tc.failed })),
-      usage: { input_tokens: 100, output_tokens: 50, cache_read_tokens: 0, cache_creation_tokens: 0 },
-      turns: 1,
-      stop_reason: 'end',
-      duration_ms: 100,
-    },
-    score: r.score,
-  }));
-  const successes = scoredRollouts.filter((r) => r.score >= 0.5);
-  const failures = scoredRollouts.filter((r) => r.score < 0.5);
-
-  const result = await runReflect({
-    skillBodyText: fx.skill_body,
-    successes,
-    failures,
-    rejected: [],
-    optimizerModel,
-  });
-
-  const proposedEdits = [...result.failureEdits, ...result.successEdits];
-
-  // Score: for each expected edit, does ANY proposed edit match its shape?
-  let wins = 0;
-  for (const ex of fx.expected_edits) {
-    const matched = proposedEdits.some((pe) => editShapeMatches(pe, ex));
-    if (matched) wins += 1;
-  }
-
-  totalWins += wins;
-  totalExpected += fx.expected_edits.length;
-
-  perFixture.push({
-    id: fx.id,
-    expected: fx.expected_edits.length,
-    matched: wins,
-    proposed_count: proposedEdits.length,
-    hit_rate: fx.expected_edits.length > 0 ? wins / fx.expected_edits.length : 0,
-    errors: result.errors,
-  });
-}
-
-const aggregateHitRate = totalExpected > 0 ? totalWins / totalExpected : 0;
-const verdict = aggregateHitRate >= 0.7 ? 'pass' : 'fail';
-
-const receipt = {
-  schema_version: 1,
-  timestamp: new Date().toISOString(),
-  optimizer_model: optimizerModel,
-  fixtures_count: fixtures.length,
-  expected_total: totalExpected,
-  matched_total: totalWins,
-  aggregate_hit_rate: aggregateHitRate,
-  verdict,
-  threshold: 0.7,
-  per_fixture: perFixture,
-};
-
-const out = JSON.stringify(receipt, null, 2);
-if (outputPath) {
-  mkdirSync(dirname(outputPath), { recursive: true });
-  writeFileSync(outputPath, out);
-  process.stderr.write(`Wrote receipt to ${outputPath}\n`);
-} else {
-  process.stdout.write(out + '\n');
-}
-
-process.exit(verdict === 'pass' ? 0 : 1);
-
-function editShapeMatches(proposed, expected) {
-  if (proposed.op !== expected.op) return false;
-  if (expected.anchor_contains && proposed.anchor) {
-    return proposed.anchor.toLowerCase().includes(expected.anchor_contains.toLowerCase());
-  }
-  if (expected.target_contains && proposed.target) {
-    return proposed.target.toLowerCase().includes(expected.target_contains.toLowerCase());
-  }
-  return true;
-}

llms.txt

@@ -7,9 +7,7 @@ Repo: https://github.com/garrytan/gbrain
 ## Core entry points
 
 - [AGENTS.md](https://raw.githubusercontent.com/garrytan/gbrain/master/AGENTS.md): Start here if you are not Claude Code. Install order, trust boundary, skill resolver, config/debug/migration pointers.
-- [CLAUDE.md](https://raw.githubusercontent.com/garrytan/gbrain/master/CLAUDE.md): Orientation + resolver. North Star, two axes, architecture + cross-cutting invariants, the reference map pointing at on-demand docs, and the inline ship IRON RULES.
-- [docs/architecture/KEY_FILES.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/architecture/KEY_FILES.md): Per-file index for the gbrain repo: what each src/ file does + its load-bearing invariants. The on-demand detail CLAUDE.md's reference map routes to.
-- [docs/architecture/thin-client.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/architecture/thin-client.md): The thin-client / remote-MCP / cross-modal routing seam: isThinClient detection, callRemoteTool, SSRF-hardened URL validation, per-command routing.
+- [CLAUDE.md](https://raw.githubusercontent.com/garrytan/gbrain/master/CLAUDE.md): Architecture reference. Key files, trust boundaries, engine factory, test layout.
 - [INSTALL_FOR_AGENTS.md](https://raw.githubusercontent.com/garrytan/gbrain/master/INSTALL_FOR_AGENTS.md): 9-step agent installation.
 - [skills/RESOLVER.md](https://raw.githubusercontent.com/garrytan/gbrain/master/skills/RESOLVER.md): Skill dispatcher. Read first for any task.
 - [README.md](https://raw.githubusercontent.com/garrytan/gbrain/master/README.md): Project overview, benchmarks, 30-minute setup.
@@ -18,21 +16,12 @@ Repo: https://github.com/garrytan/gbrain
 
 - [docs/ENGINES.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/ENGINES.md): PGLite vs Postgres trade-off and when to migrate.
 - [docs/GBRAIN_RECOMMENDED_SCHEMA.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/GBRAIN_RECOMMENDED_SCHEMA.md): MECE directory structure (people/, companies/, concepts/).
-- [docs/what-schemas-unlock.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/what-schemas-unlock.md): Why schemas matter: 7 killer use cases (4000 invisible meetings, founder ops brain, research brain, legal brain, team brain, agent-as-co-curator) + the structural argument for typed page kinds. Read this before pitching schema authoring (v0.40.7.0).
-- [docs/schema-author-tutorial.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/schema-author-tutorial.md): 5-minute walkthrough: fork the bundled pack, add a custom `researcher` type, backfill existing pages via `gbrain schema sync --apply`, prove the T1.5 wiring via `gbrain whoknows` (v0.40.7.0).
 - [docs/guides/live-sync.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/live-sync.md): Incremental markdown sync setup.
 - [docs/guides/cron-schedule.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/cron-schedule.md): Recurring job scheduling.
 - [docs/guides/minions-deployment.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/minions-deployment.md): Deploying the gbrain jobs worker: crontab + watchdog, inline --follow, systemd/Procfile/fly.toml, upgrade checklist.
 - [docs/guides/quiet-hours.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/quiet-hours.md): Notification hold + timezone-aware delivery.
-- [docs/guides/scaling-skills.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/scaling-skills.md): Three-tier architecture for agents with 300+ skills: always-loaded, resolver-routed, and dormant. Per-turn token math, the v0.41.7.0 compact list-format resolver, and the `gbrain doctor` safety net. 306 skills, ~21K tokens freed per turn, zero capability loss.
-- [docs/guides/push-context.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/guides/push-context.md): Push-based context: the brain volunteers confidence-gated pages from the rolling conversation window. Three channels (ambient reflex, volunteer_context op, gbrain watch), config knobs, and the volunteered-vs-used feedback loop.
 - [docs/mcp/DEPLOY.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/mcp/DEPLOY.md): MCP server deployment.
 
-## AI providers
-
-- [docs/ai-providers/zeroentropy.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/ai-providers/zeroentropy.md): ZeroEntropy zembed-1 embedding + zerank-2 reranker (hosted): API key, embedding switch, reranker config.
-- [docs/ai-providers/llama-server-reranker.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/ai-providers/llama-server-reranker.md): Local reranker via llama.cpp --reranking: Qwen3-Reranker or self-hosted ZE weights, --alias setup, gbrain config keys, cold-start timeout, budget-cap interaction.
-
 ## Debugging
 
 - [docs/GBRAIN_VERIFY.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/GBRAIN_VERIFY.md): 7-check post-setup verification. Start here when something feels off.
@@ -45,11 +34,6 @@ Repo: https://github.com/garrytan/gbrain
 - [skills/migrations/](https://raw.githubusercontent.com/garrytan/gbrain/master/skills/migrations/): Per-version (v0.5.0 - v0.14.1) agent-executable migration instructions.
 - [CHANGELOG.md](https://raw.githubusercontent.com/garrytan/gbrain/master/CHANGELOG.md): Release-summary voice + itemized changes + self-repair block per version.
 
-## Contributing
-
-- [docs/TESTING.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/TESTING.md): Test command tiers, the test-isolation lint (R1-R4), the canonical PGLite block, withEnv, the E2E DB lifecycle, and the file taxonomy. Maintainer-facing.
-- [docs/RELEASING.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/RELEASING.md): Full release + contributor process: pre-ship test requirements, the CHANGELOG voice + release-summary template, the 'To take advantage of vX' block, version migrations, GitHub Actions SHA refresh, PR conventions, community-PR-wave. (Ship IRON RULES stay inline in CLAUDE.md.)
-
 ## Philosophy
 
 - [docs/ethos/THIN_HARNESS_FAT_SKILLS.md](https://raw.githubusercontent.com/garrytan/gbrain/master/docs/ethos/THIN_HARNESS_FAT_SKILLS.md): Why skills live in markdown.

openclaw.plugin.json

@@ -46,9 +46,7 @@
     "skills/data-research",
     "skills/enrich",
     "skills/functional-area-resolver",
-    "skills/gbrain-advisor",
     "skills/idea-ingest",
-    "skills/idea-lineage",
     "skills/ingest",
     "skills/maintain",
     "skills/media-ingest",

package.json

@@ -1,5 +1,6 @@
 {
   "name": "gbrain",
+  "version": "0.39.2.0",
   "description": "Postgres-native personal knowledge brain with hybrid RAG search",
   "type": "module",
   "main": "src/core/index.ts",
@@ -38,20 +39,13 @@
     "build:llms": "bun run scripts/build-llms.ts",
     "build:pglite-snapshot": "bun run scripts/build-pglite-snapshot.ts",
     "test": "bash scripts/run-unit-parallel.sh",
-    "eval:autocut": "bun test test/search/autocut-eval.test.ts",
     "test:full": "bun run verify && bash scripts/run-unit-parallel.sh && bun run test:slow && ([ -n \"$DATABASE_URL\" ] && bash scripts/run-e2e.sh || echo '[test:full] skipped E2E (no DATABASE_URL); run docker-compose -f docker-compose.ci.yml up + bun run test:e2e to include' 1>&2)",
-    "verify": "bash scripts/run-verify-parallel.sh",
-    "check:source-config-leak": "scripts/check-source-config-leak.sh",
-    "check:no-pii-agent-voice": "scripts/check-no-pii-in-agent-voice.sh",
+    "verify": "bun run check:privacy && bun run check:proposal-pii && bun run check:test-names && bun run check:jsonb && bun run check:source-id-projection && bun run check:progress && bun run check:test-isolation && bun run check:wasm && bun run check:admin-build && bun run check:admin-scope-drift && bun run check:cli-exec && bun run check:system-of-record && bun run check:eval-glossary && bun run check:synthetic-corpus-privacy && bun run check:skill-brain-first && bun run check:fuzz-purity && bun run typecheck",
     "check:synthetic-corpus-privacy": "scripts/check-synthetic-corpus-privacy.sh",
     "check:system-of-record": "scripts/check-system-of-record.sh",
     "check:admin-scope-drift": "scripts/check-admin-scope-drift.sh",
     "check:cli-exec": "scripts/check-cli-executable.sh",
-    "check:all": "scripts/check-privacy.sh && scripts/check-proposal-pii.sh && scripts/check-test-real-names.sh && scripts/check-jsonb-pattern.sh && scripts/check-source-id-projection.sh && scripts/check-source-config-leak.sh && scripts/check-progress-to-stdout.sh && scripts/check-no-legacy-getconnection.sh && scripts/check-test-isolation.sh && scripts/check-trailing-newline.sh && scripts/check-wasm-embedded.sh && scripts/check-exports-count.sh && scripts/check-admin-build.sh && scripts/check-admin-scope-drift.sh && scripts/check-cli-executable.sh && scripts/check-skill-brain-first.sh && scripts/check-operations-filter-bypass.sh && scripts/check-gateway-routed-no-direct-anthropic.sh && scripts/check-worker-pool-atomicity.sh && scripts/check-key-files-current-state.sh && scripts/check-no-double-retry.sh && scripts/check-batch-audit-site.sh",
-    "check:gateway-routed": "scripts/check-gateway-routed-no-direct-anthropic.sh",
-    "check:worker-pool-atomicity": "scripts/check-worker-pool-atomicity.sh",
-    "check:doc-history": "scripts/check-key-files-current-state.sh",
-    "check:resolver": "bun src/cli.ts check-resolvable --strict --skills-dir skills/",
+    "check:all": "scripts/check-privacy.sh && scripts/check-proposal-pii.sh && scripts/check-test-real-names.sh && scripts/check-jsonb-pattern.sh && scripts/check-source-id-projection.sh && scripts/check-progress-to-stdout.sh && scripts/check-no-legacy-getconnection.sh && scripts/check-test-isolation.sh && scripts/check-trailing-newline.sh && scripts/check-wasm-embedded.sh && scripts/check-exports-count.sh && scripts/check-admin-build.sh && scripts/check-admin-scope-drift.sh && scripts/check-cli-executable.sh && scripts/check-skill-brain-first.sh",
     "check:skill-brain-first": "scripts/check-skill-brain-first.sh",
     "check:wasm": "scripts/check-wasm-embedded.sh",
     "check:newlines": "scripts/check-trailing-newline.sh",
@@ -65,10 +59,6 @@
     "ci:select-e2e": "bun run scripts/select-e2e.ts",
     "typecheck": "tsc --noEmit",
     "check:jsonb": "scripts/check-jsonb-pattern.sh",
-    "check:search-path": "scripts/check-search-path.sh",
-    "check:no-double-retry": "scripts/check-no-double-retry.sh",
-    "check:batch-audit-site": "scripts/check-batch-audit-site.sh",
-    "check:worker-lock-renewal-shape": "scripts/check-worker-lock-renewal-shape.sh",
     "check:source-id-projection": "scripts/check-source-id-projection.sh",
     "check:privacy": "scripts/check-privacy.sh",
     "check:proposal-pii": "scripts/check-proposal-pii.sh",
@@ -80,11 +70,7 @@
     "check:admin-embedded": "scripts/check-admin-embedded.sh",
     "check:test-isolation": "scripts/check-test-isolation.sh",
     "check:fuzz-purity": "scripts/check-fuzz-purity.sh",
-    "check:operations-filter-bypass": "scripts/check-operations-filter-bypass.sh",
-    "check:fixture-privacy": "scripts/check-fixture-privacy.sh",
-    "check:conversation-parser": "bun src/cli.ts eval conversation-parser test/fixtures/conversation-formats/all.jsonl --no-llm",
-    "check:source-scope-onboard": "scripts/check-source-scope-onboard.sh",
-    "postinstall": "bun run scripts/postinstall.ts",
+    "postinstall": "command -v gbrain >/dev/null 2>&1 && gbrain apply-migrations --yes --non-interactive || echo '[gbrain] postinstall skipped. If installed via bun install -g github:...: run `gbrain doctor` and `gbrain apply-migrations --yes` manually. See https://github.com/garrytan/gbrain/issues/218' 1>&2",
     "prepublish:clawhub": "bun run build:all",
     "publish:clawhub": "clawhub package publish . --family bundle-plugin"
   },
@@ -118,8 +104,8 @@
     "express-rate-limit": "^7.5.0",
     "gray-matter": "^4.0.3",
     "heic-decode": "^2.1.0",
-    "js-yaml": "^3.15.0",
-    "marked": "^18.0.2",
+    "js-yaml": "^3.14.2",
+    "marked": "^18.0.0",
     "openai": "^4.0.0",
     "pgvector": "^0.2.0",
     "postgres": "^3.4.0",
@@ -143,17 +129,5 @@
   "engines": {
     "bun": ">=1.3.10"
   },
-  "license": "MIT",
-  "version": "0.42.64.0",
-  "overrides": {
-    "@hono/node-server": "^1.19.13",
-    "fast-uri": "^3.1.2",
-    "fast-xml-builder": "^1.1.7",
-    "fast-xml-parser": "^5.7.0",
-    "form-data": "^4.0.6",
-    "hono": "^4.12.25",
-    "ip-address": "^10.1.1",
-    "qs": "^6.15.2",
-    "js-yaml": "^3.15.0"
-  }
+  "license": "MIT"
 }

recipes/agent-voice.md

@@ -1,161 +0,0 @@
----
-id: agent-voice
-name: Voice Personas (Mars + Venus)
-version: 0.1.0
-description: WebRTC-first voice agent reference (Mars + Venus personas, optional Twilio adapter). Skillpack-as-reference paradigm — the install-time agent COPIES code into your host agent repo where it becomes user-owned and mutable, NOT a runtime gbrain dependency.
-category: voice
-install_kind: copy-into-host-repo
-requires: []
-secrets:
-  - name: OPENAI_API_KEY
-    description: OpenAI API key with Realtime API access enabled
-    where: https://platform.openai.com/api-keys — click "+ Create new secret key", copy immediately
-  - name: TWILIO_ACCOUNT_SID
-    description: (optional) Twilio Account SID — only if wiring inbound Twilio calls
-    where: https://www.twilio.com/console
-  - name: TWILIO_AUTH_TOKEN
-    description: (optional) Twilio auth token — only if wiring inbound Twilio calls
-    where: https://www.twilio.com/console
-health_checks:
-  - type: env_exists
-    var: OPENAI_API_KEY
-    label: OPENAI_API_KEY present
-setup_time: 10 min
-cost_estimate: "$0.06-0.24/min OpenAI Realtime, optional $1-2/mo Twilio number"
----
-
-# Voice Personas: Mars + Venus
-
-A reference voice agent (WebRTC-first; OpenAI Realtime) shipped as **copy-into-your-repo** content rather than runtime gbrain skills. The install-time agent reads this recipe, copies the bundle into your host agent repo (e.g. `~/git/your-agent-repo/`), wires the resolver, and starts the voice server. From there, the code lives in YOUR repo, on YOUR cadence, with YOUR edits.
-
-## What ships in the bundle
-
-- **Two personas** — Mars (introspective thought partner; voice `Orus`) and Venus (sharp executive assistant; voice `Aoede`).
-- **WebRTC browser client** at `/call?test=1` for the production-grade voice loop. Production load installs zero test instrumentation; `?test=1` enables Web Audio API tee → MediaRecorder capture for the E2E.
-- **Tool router** with a read-only allow-list by default (search, query, get_page, list_pages, find_experts, get_recent_salience, get_recent_transcripts, read_article). Write ops are denylisted; operators opt in to a bounded set via local override.
-- **Persona-aware prompt builder** with identity-first composition + Unicode sanitization for Realtime API safety.
-- **Optional Twilio adapter** (`/voice` TwiML, WSS bridge) for phone inbound. Skip if you only want browser voice.
-- **Three skills** for resolver routing: `voice-persona-mars`, `voice-persona-venus`, `voice-post-call`.
-- **Unit + E2E tests** that ride with the copy. PII-shape regex guards every prompt, classifier triages upstream vs plumbing failures.
-
-## The skillpack-as-reference paradigm
-
-Earlier gbrain skillpacks installed to `~/.gbrain/skills/<name>/` as managed-block-canonical first-class skills. The user's local edits drifted from the canonical and updates were either "overwrite local" or "skip update" — neither is what an operator wants on code they've extended.
-
-This recipe ships a different shape: gbrain holds the up-to-date REFERENCE, and `gbrain integrations install agent-voice --target <host-repo>` COPIES it into the operator's repo. The code now lives in the host repo, on the operator's release cadence, with the operator's edits. Subsequent `--refresh` invocations diff host-side files against gbrain's reference and propose changes; the operator picks per-file (keep mine / take theirs / merge).
-
-The shipped reference does NOT contain personal names, hardcoded private paths, or upstream-agent codenames. A CI guard (`scripts/check-no-pii-in-agent-voice.sh`) blocks any drift back; a deterministic import script (`scripts/import-from-upstream.sh`) refreshes the gbrain reference from an upstream voice-agent source.
-
-## Install
-
-```bash
-# 1. Detect target repo
-export TARGET_REPO=$OPENCLAW_WORKSPACE     # or your agent repo path
-
-# 2. Install
-gbrain integrations install agent-voice --target $TARGET_REPO
-
-# 3. Set env vars in $TARGET_REPO/.env (NOT in gbrain)
-echo "OPENAI_API_KEY=sk-..." >> $TARGET_REPO/.env
-echo "DEFAULT_PERSONA=venus" >> $TARGET_REPO/.env
-
-# 4. Implement context builder (optional but recommended)
-# Replace $TARGET_REPO/services/voice-agent/code/lib/context-builder.example.mjs
-# with your operator-specific implementation. See the contract at:
-#   $TARGET_REPO/services/voice-agent/code/lib/personas/context-builder.contract.md
-
-# 5. Run host-side tests
-cd $TARGET_REPO/services/voice-agent && bun install && bun run test
-# OR if your repo uses npm: npm install && npm test
-
-# 6. Start the voice server
-cd $TARGET_REPO/services/voice-agent && bun run start
-# Voice agent listens on http://localhost:8765
-```
-
-Open `http://localhost:8765/call` and click Connect. The browser asks for mic permission; once granted, it does an SDP exchange via `POST /session`, the OpenAI Realtime API returns the SDP answer, and audio flows bidirectionally over WebRTC.
-
-For test-mode roundtrip checks, append `?test=1` to the URL — that enables the `window._gbrainTest` instrumentation namespace + MediaRecorder capture of the response audio.
-
-## Update (refresh from gbrain)
-
-```bash
-# Pull latest gbrain → re-run the install with --refresh
-git -C $(which gbrain | xargs -I{} dirname {})/.. pull   # or your gbrain update path
-gbrain integrations install agent-voice --target $TARGET_REPO --refresh
-```
-
-`--refresh` reads the `.gbrain-source.json` manifest written by the original install, re-computes per-file SHA-256 against gbrain's current reference, and classifies each file:
-
-- **unchanged-identical** — host file matches gbrain reference; skip.
-- **unchanged-stale** — host file matches the recorded SHA but reference moved; offer to update.
-- **locally-modified** — host file diverges from the recorded SHA; show diff, offer three options (keep mine / take theirs / merge).
-- **source-deleted** — gbrain reference removed a file; offer cleanup.
-- **source-renamed** — detected via path-mapping; offer to follow.
-
-A transaction journal at `<target>/services/voice-agent/.gbrain-source.refresh.log` allows partial-apply recovery if the refresh is interrupted.
-
-## Architecture
-
-```
-                Browser (call.html)
-                       │
-                       │  WebRTC (mic + remote audio + data channel)
-                       ▼
-              ┌─────────────────────┐
-              │   server.mjs (8765) │
-              │   ─────────────     │
-   ┌──────────┤  GET  /call         │      POST /session
-   │ static   │  GET  /health        ├──────────────────▶  api.openai.com/v1/realtime/calls
-   │ files    │  POST /session       │       (SDP exchange via FormData)
-   └──────────┤  POST /tool          │
-              │  POST /voice  (Twi.) │
-              │  WSS  /ws     (Twi.) │
-              └──────────┬───────────┘
-                         │  /tool dispatches through tools.mjs allow-list
-                         ▼
-              ┌─────────────────────┐
-              │  tools.mjs router    │
-              │  ─────────────       │   denylist: put_page, submit_job, file_upload, ...
-              │  READ_ONLY_OPS only  │   allow-list: 8 read ops; operator extends optional ops via override
-              └──────────┬───────────┘
-                         │
-                         ▼  stdio JSON-RPC
-              ┌─────────────────────┐
-              │  gbrain serve (MCP)  │
-              └─────────────────────┘
-```
-
-## Production checklist
-
-Reference code ships intentionally minimal. Before public deployment:
-
-- **Twilio signature validation** on `/voice` — currently absent; add `X-Twilio-Signature` header validation.
-- **Rate limiting** on `/session` and `/tool` — currently absent.
-- **CORS allowlist** — currently `*`; restrict to your deployed origins.
-- **Auth on /tool** — voice-side tool calls currently trust the in-process connection; if you expose `/tool` publicly, gate it behind a session token.
-- **HTTPS** — required for browser mic access in production. Use ngrok / Caddy / Cloudflare Tunnel.
-- **Twilio fallback URL** — `/fallback` is a TwiML stub; wire to your operator's cell for crash recovery.
-- **PII scrub at context-builder** — the shipped `context-builder.example.mjs` includes phone/email regex scrubs, but operators should extend per their brain's PII pattern set.
-
-## Tests
-
-```bash
-cd $TARGET_REPO/services/voice-agent
-bun run test                   # host-side unit tests (5 suites, ~100 cases)
-AGENT_VOICE_E2E=1 bun run test:e2e             # WebRTC roundtrip (~$0.10/run)
-AGENT_VOICE_FULL_E2E=1 bun run test:full-flow  # openclaw-driven install + roundtrip (~$1-2/run)
-```
-
-The full-flow E2E is **friction-discovery**, not a ship-gate. Pre-ship gates on host-side unit tests and the PII guard; flakes in the live OpenAI Realtime path soft-fail with `STATUS: skipped_upstream_degraded` and log to the friction channel.
-
-## What's deferred
-
-- DIY STT+LLM+TTS pipeline (`pipeline.mjs`, `pipeline-v3.mjs` for Gemini Live) — recipe Option A (WebRTC direct to OpenAI Realtime) ships now; Option B (Deepgram + Claude + Cartesia) is a follow-up wave.
-- Multilingual Mars — the persona drops the multilingual claim until a multilingual eval lands; restoring it is gated on the eval.
-- Live cross-call memory between sessions — the persona is session-scoped today.
-- Pre-computed engagement-bid system (the "Bid System" pattern from production deployments) — would belong in `prompt.mjs`.
-- Smart VAD presets (quiet/normal/noisy/very_noisy) — uses Realtime API's default VAD today.
-- WebRTC `/session` does not yet ship MediaRecorder fallback for environments where the WebAudio-tee fails.
-
-Each of the deferred items is filed as a TODO in the gbrain repo's `TODOS.md`.

recipes/agent-voice/README.md

@@ -1,72 +0,0 @@
-# agent-voice — reference bundle
-
-This directory is a **reference**, not a runtime gbrain dependency. The gbrain compiled binary does NOT load anything under `recipes/agent-voice/code/`, `recipes/agent-voice/skills/`, or `recipes/agent-voice/tests/`. Those exist to be COPIED into the operator's host agent repo via `gbrain integrations install agent-voice --target <host-repo>`.
-
-## The paradigm
-
-| Aspect                  | Legacy skillpack (`local-managed`)            | Reference skillpack (`copy-into-host-repo`)        |
-| ----------------------- | --------------------------------------------- | -------------------------------------------------- |
-| Where code lives        | `~/.gbrain/skills/<name>/`                    | `<host-repo>/services/voice-agent/`                |
-| Who owns edits          | gbrain (managed block)                        | Operator (host repo)                               |
-| Update path             | Overwrite or skip                             | Diff-and-propose against manifest hashes           |
-| Resolver registration   | `~/.gbrain/skills/RESOLVER.md`                | `<host-repo>/RESOLVER.md` or `AGENTS.md`           |
-| Identity of updates     | gbrain pushes                                 | Operator pulls per release cadence                 |
-| Bisect / blame / history| gbrain's git history                          | Operator's host repo git history                   |
-
-The `install_kind` discriminator in the recipe frontmatter routes between the two paths inside `gbrain integrations install`.
-
-## Sibling-directory convention (for future copy-into-host-repo recipes)
-
-This recipe pioneers the layout future copy-into-host-repo recipes should follow:
-
-```
-recipes/<name>.md                       # registered entrypoint (loader sees this)
-recipes/<name>/
-├── README.md                           # paradigm doc; gbrain-side only (not copied)
-├── package.json                        # top-of-bundle; copied to <host>/services/<name>/package.json
-├── code/                               # copied to <host>/services/<name>/code/
-├── tests/                              # copied to <host>/services/<name>/tests/
-│   ├── unit/
-│   ├── e2e/
-│   └── evals/
-├── skills/                             # copied to <host>/skills/<skill-name>/
-├── install/                            # gbrain-side only; install metadata
-│   ├── manifest.json                   # src → target map + per-file SHA-256
-│   ├── refresh-algorithm.md            # diff-and-propose semantics
-│   └── post-install-hint.md            # next-step prompts for the install agent
-└── docs/                               # any extra docs the operator should see post-install
-```
-
-Three rules for new recipes following this shape:
-
-1. **Topology preservation.** Tests at `recipes/<name>/tests/unit/x.test.mjs` MUST import code via `../../code/...`. That relative path is preserved when copied to `<host>/services/<name>/tests/unit/x.test.mjs` → `<host>/services/<name>/code/...`. The installer is NOT in the business of rewriting imports.
-
-2. **PII guard scope.** Every file under `recipes/<name>/` is scanned by `scripts/check-no-pii-in-agent-voice.sh` (or future equivalent), PLUS the top-level `recipes/<name>.md`. The single source of truth for the blocklist is a JSON file inside the bundle.
-
-3. **`install_kind: copy-into-host-repo`** in frontmatter routes to the copy path. Without it, the recipe defaults to `local-managed` (legacy `~/.gbrain/skills/` install).
-
-## Files (gbrain-side only — NOT copied to host)
-
-- `README.md` — this doc.
-- `install/manifest.json` — declares src → target paths + permissions; the install command computes SHA-256 at copy time.
-- `install/refresh-algorithm.md` — the diff-and-propose contract.
-- `install/post-install-hint.md` — what the install agent prints when copy completes.
-- `code/lib/personas/private-name-blocklist.json` — privacy guard source of truth (read by the shipped guard script and by host-side prompt-shape tests).
-- `code/lib/personas/context-builder.contract.md` — API the operator implements for live brain context.
-
-## Files (in `bundle = code/ + tests/ + skills/ + package.json`) — copied to host repo
-
-The install subcommand reads `install/manifest.json` and copies each listed file to its target path under the host repo. SHA-256s computed at copy time get persisted into `<host>/services/<name>/.gbrain-source.json` so `--refresh` can do three-way classification (unchanged-identical / unchanged-stale / locally-modified) without re-walking the entire bundle.
-
-## Reading order
-
-If you're new to this paradigm and want to understand the moving parts:
-
-1. `recipes/agent-voice.md` — the registered recipe, top-level explainer + install steps.
-2. This file — the paradigm + sibling-directory convention.
-3. `install/manifest.json` — the literal src → target file map.
-4. `install/refresh-algorithm.md` — what `--refresh` does and how to extend it.
-5. `code/tools.mjs` — the load-bearing trust-boundary code (D14-A read-only allow-list).
-6. `code/lib/personas/mars.mjs` + `code/lib/personas/venus.mjs` — the persona prompts.
-7. `code/public/call.html` — the WebRTC client with `?test=1` instrumentation.
-8. `code/server.mjs` — the minimal voice server.

recipes/agent-voice/code/gbrain-client.mjs

@@ -1,182 +0,0 @@
-/**
- * gbrain-client.mjs — minimal stdio MCP client for gbrain.
- *
- * Spawns `gbrain serve` as a long-lived child process and communicates via
- * JSON-RPC over stdio. The client is intentionally minimal: open the
- * connection once, send `initialize`, then forward tool calls. No retries,
- * no batching, no streaming results (most voice tools return small
- * payloads; large ones can be paginated by the caller).
- *
- * Production hardening this file does NOT do:
- *   - reconnect on child crash (caller restarts; voice sessions are short)
- *   - request timeouts (caller handles via its own AbortSignal)
- *   - concurrent request multiplexing (one in-flight call at a time)
- *
- * That's deliberate: this is reference code optimized for clarity and the
- * voice-agent use case, not a production-grade MCP client. The operator
- * can replace it with a richer implementation (e.g., the
- * @modelcontextprotocol/sdk Client) without changing tools.mjs.
- *
- * Configuration: `$GBRAIN_BIN` (default: `gbrain` on PATH) is the binary to
- * spawn. `$GBRAIN_BRAIN_ID` and `$GBRAIN_SOURCE` route to a specific brain
- * + source if set (see the gbrain docs/architecture/brains-and-sources.md).
- */
-
-import { spawn } from 'node:child_process';
-
-const GBRAIN_BIN = process.env.GBRAIN_BIN || 'gbrain';
-
-let _child;
-let _nextId = 1;
-const _pending = new Map();
-let _initialized = false;
-let _buffer = '';
-
-function ensureChild() {
-  if (_child && !_child.killed) return _child;
-
-  const args = ['serve'];
-  if (process.env.GBRAIN_BRAIN_ID) args.push('--brain', process.env.GBRAIN_BRAIN_ID);
-  if (process.env.GBRAIN_SOURCE) args.push('--source', process.env.GBRAIN_SOURCE);
-
-  _child = spawn(GBRAIN_BIN, args, {
-    stdio: ['pipe', 'pipe', 'pipe'],
-    env: { ...process.env, MCP_STDIO: '1' },
-  });
-
-  _child.stdout.setEncoding('utf8');
-  _child.stdout.on('data', (chunk) => {
-    _buffer += chunk;
-    // JSON-RPC over stdio: messages separated by newlines.
-    let nlIdx;
-    while ((nlIdx = _buffer.indexOf('\n')) !== -1) {
-      const line = _buffer.slice(0, nlIdx).trim();
-      _buffer = _buffer.slice(nlIdx + 1);
-      if (!line) continue;
-      try {
-        const msg = JSON.parse(line);
-        if (msg.id !== undefined && _pending.has(msg.id)) {
-          const { resolve, reject } = _pending.get(msg.id);
-          _pending.delete(msg.id);
-          if (msg.error) {
-            reject(new Error(msg.error.message || 'gbrain MCP error'));
-          } else {
-            resolve(msg.result);
-          }
-        }
-        // notifications/log etc. — ignore for the v0 voice use case.
-      } catch (err) {
-        // Malformed line; ignore. gbrain prints structured JSON-RPC only,
-        // but a renegade stderr-bleed could surface here.
-      }
-    }
-  });
-
-  _child.stderr.setEncoding('utf8');
-  _child.stderr.on('data', (chunk) => {
-    // Surface gbrain stderr to our stderr for debugging. Don't crash on it.
-    process.stderr.write(`[gbrain] ${chunk}`);
-  });
-
-  _child.on('exit', (code, signal) => {
-    const reason = signal ? `signal ${signal}` : `code ${code}`;
-    for (const [, p] of _pending) {
-      p.reject(new Error(`gbrain child exited (${reason}) with ${_pending.size} pending`));
-    }
-    _pending.clear();
-    _initialized = false;
-    _child = null;
-  });
-
-  return _child;
-}
-
-function rpc(method, params) {
-  const id = _nextId++;
-  const child = ensureChild();
-  return new Promise((resolve, reject) => {
-    _pending.set(id, { resolve, reject });
-    const msg = JSON.stringify({ jsonrpc: '2.0', id, method, params }) + '\n';
-    try {
-      child.stdin.write(msg);
-    } catch (err) {
-      _pending.delete(id);
-      reject(err);
-    }
-  });
-}
-
-async function initIfNeeded() {
-  if (_initialized) return;
-  await rpc('initialize', {
-    protocolVersion: '2024-11-05',
-    capabilities: {},
-    clientInfo: { name: 'agent-voice', version: '0.1.0' },
-  });
-  _initialized = true;
-}
-
-/**
- * Call a single gbrain operation by name with params. Returns the operation
- * result (whatever shape gbrain returns; usually a JSON-serializable object).
- *
- * @throws {Error} on transport failure or operation error.
- */
-export async function callGbrainOp(opName, params) {
-  await initIfNeeded();
-  // gbrain exposes operations as MCP "tools." The standard call is
-  // tools/call with {name, arguments}.
-  const result = await rpc('tools/call', { name: opName, arguments: params || {} });
-  // gbrain returns {content: [{type:'text', text:'...JSON...'}]}; parse if needed.
-  if (result?.content?.[0]?.type === 'text') {
-    const text = result.content[0].text;
-    try {
-      return JSON.parse(text);
-    } catch {
-      return text;
-    }
-  }
-  return result;
-}
-
-/**
- * Test hook: stub the underlying RPC. Tests use this instead of spawning a
- * real gbrain child. Pass `null` to restore the real spawn-and-rpc path.
- */
-export function __setRpcForTests(fn) {
-  if (fn === null) {
-    _testRpc = null;
-    return;
-  }
-  _testRpc = fn;
-}
-
-let _testRpc = null;
-
-// Re-export rpc through the test hook for callGbrainOp.
-const _origRpc = rpc;
-async function dispatchRpc(method, params) {
-  if (_testRpc) return _testRpc(method, params);
-  return _origRpc(method, params);
-}
-
-// Override the helper used by callGbrainOp.
-export async function _testableCallGbrainOp(opName, params) {
-  if (_testRpc) {
-    return _testRpc('tools/call', { name: opName, arguments: params || {} });
-  }
-  return callGbrainOp(opName, params);
-}
-
-/**
- * Shutdown helper. Tests call this between cases; production never has to.
- */
-export function shutdown() {
-  if (_child) {
-    _child.kill();
-    _child = null;
-  }
-  _pending.clear();
-  _initialized = false;
-  _buffer = '';
-}

recipes/agent-voice/code/lib/audio-convert.mjs

@@ -1,216 +0,0 @@
-/**
- * audio-convert.mjs — µ-law ↔ PCM conversion for Twilio ↔ Gemini bridge
- * 
- * Twilio sends:  µ-law 8kHz mono base64 (20ms chunks = 160 bytes)
- * Gemini wants:  PCM 16-bit 16kHz mono base64 (buffered ~300ms)
- * Gemini sends:  PCM 16-bit 24kHz mono base64 (variable chunks)
- * Twilio wants:  µ-law 8kHz mono base64
- */
-
-// ── µ-law decode table (ITU-T G.711) ─────────────────────
-const ULAW_DECODE = new Int16Array(256);
-for (let i = 0; i < 256; i++) {
-  let u = ~i & 0xFF;
-  let sign = u & 0x80;
-  let exponent = (u >> 4) & 0x07;
-  let mantissa = u & 0x0F;
-  let sample = (mantissa << 3) + 0x84;
-  sample <<= exponent;
-  sample -= 0x84;
-  ULAW_DECODE[i] = sign ? -sample : sample;
-}
-
-// ── PCM → µ-law encode ───────────────────────────────────
-const ULAW_MAX = 0x1FFF;
-const ULAW_BIAS = 0x84;
-
-function pcmToUlaw(sample) {
-  let sign = 0;
-  if (sample < 0) { sign = 0x80; sample = -sample; }
-  if (sample > ULAW_MAX) sample = ULAW_MAX;
-  sample += ULAW_BIAS;
-  let exponent = 7;
-  for (let mask = 0x4000; (sample & mask) === 0 && exponent > 0; exponent--, mask >>= 1) {}
-  let mantissa = (sample >> (exponent + 3)) & 0x0F;
-  return (~(sign | (exponent << 4) | mantissa)) & 0xFF;
-}
-
-// ── Stateless converters (for unit tests + simple cases) ──
-
-/**
- * Decode µ-law bytes to PCM 16-bit samples (no resampling)
- */
-export function ulawToPcm8k(ulawBuf) {
-  const pcm = new Int16Array(ulawBuf.length);
-  for (let i = 0; i < ulawBuf.length; i++) {
-    pcm[i] = ULAW_DECODE[ulawBuf[i]];
-  }
-  return pcm;
-}
-
-/**
- * Simple stateless: µ-law 8kHz base64 → PCM 16kHz base64
- * Uses linear interpolation. OK for testing, not ideal for production.
- */
-export function ulawToGemini(base64Ulaw) {
-  const ulawBuf = Buffer.from(base64Ulaw, 'base64');
-  if (ulawBuf.length === 0) return '';
-  const pcm8k = ulawToPcm8k(ulawBuf);
-  const pcm16k = new Int16Array(pcm8k.length * 2);
-  for (let i = 0; i < pcm8k.length; i++) {
-    pcm16k[i * 2] = pcm8k[i];
-    pcm16k[i * 2 + 1] = i < pcm8k.length - 1 ? (pcm8k[i] + pcm8k[i + 1]) >> 1 : pcm8k[i];
-  }
-  return Buffer.from(pcm16k.buffer).toString('base64');
-}
-
-/**
- * PCM 24kHz base64 → µ-law 8kHz base64 (downsample 3:1)
- */
-export function geminiToUlaw(base64Pcm) {
-  const pcmBuf = Buffer.from(base64Pcm, 'base64');
-  const pcm24k = new Int16Array(pcmBuf.buffer, pcmBuf.byteOffset, pcmBuf.length / 2);
-  const numOut = Math.floor(pcm24k.length / 3);
-  const ulawBuf = Buffer.alloc(numOut);
-  for (let i = 0; i < numOut; i++) {
-    ulawBuf[i] = pcmToUlaw(pcm24k[i * 3]);
-  }
-  return ulawBuf.toString('base64');
-}
-
-/**
- * PCM 16kHz base64 → µ-law 8kHz base64 (downsample 2:1)
- */
-export function gemini16kToUlaw(base64Pcm) {
-  const pcmBuf = Buffer.from(base64Pcm, 'base64');
-  const pcm16k = new Int16Array(pcmBuf.buffer, pcmBuf.byteOffset, pcmBuf.length / 2);
-  const numOut = Math.floor(pcm16k.length / 2);
-  const ulawBuf = Buffer.alloc(numOut);
-  for (let i = 0; i < numOut; i++) {
-    ulawBuf[i] = pcmToUlaw(pcm16k[i * 2]);
-  }
-  return ulawBuf.toString('base64');
-}
-
-
-// ── Stateful resampler for production use ─────────────────
-// Proper linear interpolation with state across chunk boundaries
-
-/**
- * Create a stateful 8kHz→16kHz upsampler.
- * Tracks the last sample across chunks for smooth interpolation.
- */
-export function createUpsampler() {
-  let lastSample = 0;
-  
-  return function upsample(pcm8k) {
-    const pcm16k = new Int16Array(pcm8k.length * 2);
-    for (let i = 0; i < pcm8k.length; i++) {
-      const prev = i === 0 ? lastSample : pcm8k[i - 1];
-      pcm16k[i * 2] = (prev + pcm8k[i]) >> 1; // Interpolated sample
-      pcm16k[i * 2 + 1] = pcm8k[i];            // Original sample
-    }
-    lastSample = pcm8k[pcm8k.length - 1] || 0;
-    return pcm16k;
-  };
-}
-
-/**
- * Create a stateful 24kHz→8kHz downsampler.
- * Averages 3 samples for each output (low-pass filter).
- */
-export function createDownsampler24to8() {
-  let remainder = new Int16Array(0);
-  
-  return function downsample(pcm24k) {
-    // Prepend any remainder from last chunk
-    let input;
-    if (remainder.length > 0) {
-      input = new Int16Array(remainder.length + pcm24k.length);
-      input.set(remainder);
-      input.set(pcm24k, remainder.length);
-    } else {
-      input = pcm24k;
-    }
-    
-    const numOut = Math.floor(input.length / 3);
-    const leftover = input.length - numOut * 3;
-    const out = new Int16Array(numOut);
-    
-    for (let i = 0; i < numOut; i++) {
-      // Average 3 samples (simple low-pass)
-      const idx = i * 3;
-      out[i] = Math.round((input[idx] + input[idx + 1] + input[idx + 2]) / 3);
-    }
-    
-    // Save leftover samples for next chunk
-    remainder = leftover > 0 ? input.slice(input.length - leftover) : new Int16Array(0);
-    
-    return out;
-  };
-}
-
-/**
- * Create a buffered audio processor for Twilio→Gemini.
- * Buffers µ-law chunks and flushes PCM 16kHz every ~300ms.
- * 
- * @param {Function} onFlush - (base64Pcm16k) => void
- * @param {number} flushMs - buffer duration before flushing (default 200ms)
- */
-export function createTwilioToGeminiProcessor(onFlush, flushMs = 200) {
-  const upsample = createUpsampler();
-  // 16kHz * 2 bytes * flushMs/1000 = buffer threshold
-  const FLUSH_BYTES = Math.floor(16000 * 2 * flushMs / 1000);
-  let pcmBuffer = [];
-  let totalBytes = 0;
-  
-  return {
-    /** Process a base64 µ-law chunk from Twilio */
-    push(base64Ulaw) {
-      const ulawBuf = Buffer.from(base64Ulaw, 'base64');
-      const pcm8k = ulawToPcm8k(ulawBuf);
-      const pcm16k = upsample(pcm8k);
-      pcmBuffer.push(Buffer.from(pcm16k.buffer));
-      totalBytes += pcm16k.length * 2;
-      
-      if (totalBytes >= FLUSH_BYTES) {
-        this.flush();
-      }
-    },
-    
-    /** Force flush any buffered audio */
-    flush() {
-      if (pcmBuffer.length === 0) return;
-      const combined = Buffer.concat(pcmBuffer);
-      pcmBuffer = [];
-      totalBytes = 0;
-      onFlush(combined.toString('base64'));
-    },
-    
-    /** Get current buffer size in bytes */
-    get bufferedBytes() { return totalBytes; },
-  };
-}
-
-/**
- * Create a Gemini→Twilio audio processor.
- * Converts PCM 24kHz to µ-law 8kHz with proper downsampling.
- */
-export function createGeminiToTwilioProcessor() {
-  const downsample = createDownsampler24to8();
-  
-  return {
-    /** Process base64 PCM 24kHz from Gemini → base64 µ-law 8kHz for Twilio */
-    process(base64Pcm) {
-      const pcmBuf = Buffer.from(base64Pcm, 'base64');
-      const pcm24k = new Int16Array(pcmBuf.buffer, pcmBuf.byteOffset, pcmBuf.length / 2);
-      const pcm8k = downsample(pcm24k);
-      
-      const ulawBuf = Buffer.alloc(pcm8k.length);
-      for (let i = 0; i < pcm8k.length; i++) {
-        ulawBuf[i] = pcmToUlaw(pcm8k[i]);
-      }
-      return ulawBuf.toString('base64');
-    }
-  };
-}

recipes/agent-voice/code/lib/context-builder.example.mjs

@@ -1,263 +0,0 @@
-/**
- * context-builder.example.mjs — Working example implementation.
- *
- * Provides buildMarsContext() and buildVenusContext() against a documented
- * brain layout. Operators with a different layout edit the path constants
- * at the top, OR replace this file in place with their own implementation
- * that satisfies `context-builder.contract.md`.
- *
- * This example reads:
- *   $BRAIN_ROOT/memory/YYYY-MM-DD.md   (daily memory; emotional signal)
- *   $BRAIN_ROOT/SOUL.md                (stable emotional landscape)
- *   $BRAIN_ROOT/tasks/open.md          (active tasks for Venus)
- *   $BRAIN_ROOT/calendar/today.md      (today's events for Venus)
- *   $BRAIN_ROOT/memory/heartbeat-state.json (optional timezone)
- *
- * The implementation is intentionally generic. It does NOT name specific
- * family members, therapists, or projects. It uses a content-agnostic
- * emotion-word filter that catches what's emotionally loaded in the
- * operator's own words.
- *
- * Latency budget: ≤ 200ms wall time.
- * Output cap: 2500 chars (truncated at boundary).
- * PII scrub: emails + phones → [redacted] at the boundary.
- */
-
-import { readFileSync, existsSync } from 'node:fs';
-import { join, resolve, sep } from 'node:path';
-
-const MAX_CHARS = 2500;
-
-// #1851: a topic id is the ONLY thing that crosses the wire from a call link
-// (never the topic content itself — that would be prompt injection + a leak via
-// URLs/logs). The id indexes `$BRAIN_ROOT/topics/<topicId>.md` server-side, so
-// it must be a strict slug: lowercase alnum + dashes, no dots/slashes. This
-// regex alone rejects `../../SOUL` (no dots, no slashes); the resolve-under-dir
-// check below is defense-in-depth.
-const TOPIC_ID_RE = /^[a-z0-9][a-z0-9-]*$/;
-
-/** True iff `topicId` is a safe slug (see TOPIC_ID_RE). */
-export function isValidTopicId(topicId) {
-  return typeof topicId === 'string' && topicId.length <= 128 && TOPIC_ID_RE.test(topicId);
-}
-
-// Emotion-word filter. Content-agnostic — catches what's loaded in the
-// operator's OWN words without hardcoding names of people in their life.
-// Add words to this list if your brain uses domain-specific vocabulary.
-const EMOTION_WORDS = [
-  'feel', 'feeling', 'felt',
-  'heart', 'love', 'lonely', 'alone',
-  'joy', 'happy', 'happiness',
-  'grief', 'sad', 'sadness', 'cry', 'crying',
-  'anger', 'angry', 'rage', 'frustrated',
-  'fear', 'afraid', 'scared', 'anxious', 'anxiety',
-  'hope', 'hopeful', 'hopeless',
-  'ache', 'aching', 'miss', 'missing', 'longing',
-  'alive', 'dead', 'numb', 'numbing',
-  'therapy', 'therapist',
-  'family', 'father', 'mother', 'son', 'daughter',
-  'relationship', 'partner',
-  'tired', 'exhausted', 'burnt out', 'burned out',
-  'present', 'presence', 'mindful',
-  'meaning', 'meaningful', 'purpose',
-  'pattern', 'insight', 'realize', 'realized',
-  'memory', 'remember', 'forgot',
-];
-
-const REDACT_RE = {
-  email: /\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b/g,
-  phone: /(?:\+?\d{1,3}[\s.-]?)?(?:\(\d{3}\)|\d{3})[\s.-]?\d{3}[\s.-]?\d{4}/g,
-};
-
-/** Scrub emails + phones from a string. Conservative; misses long-tail PII. */
-function scrub(ctx) {
-  return ctx.replace(REDACT_RE.email, '[email]').replace(REDACT_RE.phone, '[phone]');
-}
-
-/** Truncate to MAX_CHARS at a word boundary. */
-function cap(ctx) {
-  if (ctx.length <= MAX_CHARS) return ctx;
-  const slice = ctx.slice(0, MAX_CHARS);
-  const lastBreak = slice.lastIndexOf('\n');
-  return lastBreak > MAX_CHARS - 200 ? slice.slice(0, lastBreak) : slice;
-}
-
-/** ISO YYYY-MM-DD from a Date in the given timezone. Defaults to UTC. */
-function isoDate(date, tz) {
-  if (!tz) return date.toISOString().slice(0, 10);
-  // Intl is slow; only when caller passes a tz.
-  const fmt = new Intl.DateTimeFormat('en-CA', {
-    timeZone: tz, year: 'numeric', month: '2-digit', day: '2-digit',
-  });
-  return fmt.format(date);
-}
-
-/** Detect timezone from optional heartbeat-state.json. */
-function detectTimezone(brainRoot) {
-  const hbPath = join(brainRoot, 'memory', 'heartbeat-state.json');
-  if (!existsSync(hbPath)) return undefined;
-  try {
-    const hb = JSON.parse(readFileSync(hbPath, 'utf8'));
-    return hb?.currentLocation?.timezone;
-  } catch {
-    return undefined;
-  }
-}
-
-/**
- * Build emotionally-salient context for Mars.
- *
- * Strategy:
- *   1. Date + timezone awareness for "what time is it" questions.
- *   2. SOUL.md (capped at 600 chars) for stable emotional landscape.
- *   3. Last 2 days of memory files, emotion-word-filtered, ≤ 8 lines each.
- *   4. PII scrub + truncation cap.
- */
-export async function buildMarsContext({ brainRoot, timezone } = {}) {
-  if (!brainRoot) return '';
-  const tz = timezone || detectTimezone(brainRoot) || 'UTC';
-
-  let ctx = "WHAT IS GOING ON IN THE OPERATOR'S INNER LIFE RIGHT NOW.\n";
-  ctx += "Use this as background. Don't recite it. Let it inform your questions and responses.\n\n";
-
-  // 1. Date + time
-  try {
-    const now = new Date();
-    const dateStr = now.toLocaleDateString('en-US', {
-      timeZone: tz, weekday: 'long', year: 'numeric', month: 'long', day: 'numeric',
-    });
-    const timeStr = now.toLocaleTimeString('en-US', {
-      timeZone: tz, hour: 'numeric', minute: '2-digit',
-    });
-    ctx += `It's ${dateStr}, ${timeStr} (${tz}).\n\n`;
-  } catch {
-    // tz invalid — fall through with no date line
-  }
-
-  // 2. Stable emotional landscape
-  try {
-    const soulPath = join(brainRoot, 'SOUL.md');
-    if (existsSync(soulPath)) {
-      const soul = readFileSync(soulPath, 'utf8');
-      // Take the first ~600 chars as the "core context."
-      ctx += `CORE CONTEXT:\n${soul.slice(0, 600).trim()}\n\n`;
-    }
-  } catch {}
-
-  // 3. Recent daily memory, emotion-filtered.
-  try {
-    const now = new Date();
-    const dates = [now, new Date(now.getTime() - 86400000)].map((d) => isoDate(d, tz));
-    for (const date of dates) {
-      const dayPath = join(brainRoot, 'memory', `${date}.md`);
-      if (!existsSync(dayPath)) continue;
-      const day = readFileSync(dayPath, 'utf8');
-      const emotionalLines = day.split('\n').filter((l) => {
-        const lower = l.toLowerCase();
-        return EMOTION_WORDS.some((w) => lower.includes(w));
-      }).slice(0, 8);
-      if (emotionalLines.length > 0) {
-        ctx += `RECENT (${date}):\n${emotionalLines.join('\n')}\n\n`;
-      }
-    }
-  } catch {}
-
-  return cap(scrub(ctx));
-}
-
-/**
- * #1851 — Build TOPIC context: the recent conversation in the topic the agent
- * was summoned into, so calling Mars/Venus from inside a thread boots them
- * already knowing what you were just discussing.
- *
- * The server resolves this from `topicId` at connect time (the id is the only
- * thing the call link carries). Reads `$BRAIN_ROOT/topics/<topicId>.md`. The
- * operator's brain owns what lands in that file (recent turns + a 2-3 line
- * synthesized summary is the intended shape — not a raw dump).
- *
- * Persona-agnostic: the SAME topic block is injected for Mars or Venus; only
- * the persona identity (section 1 of the prompt) differs. Returns '' when
- * there's no topic, the id is unsafe, or the file is missing — falling back to
- * the generic per-persona live context (current behavior).
- *
- * @param {object} opts
- * @param {string} opts.brainRoot
- * @param {string} opts.topicId — strict slug; see {@link isValidTopicId}
- * @returns {Promise<string>} ≤2500 chars, PII-scrubbed, or '' to degrade.
- */
-export async function buildTopicContext({ brainRoot, topicId } = {}) {
-  if (!brainRoot || !topicId || !isValidTopicId(topicId)) return '';
-
-  // Defense-in-depth: confine the resolved path under <brainRoot>/topics even
-  // though the slug regex already forbids traversal characters.
-  const topicsDir = resolve(join(brainRoot, 'topics'));
-  const path = resolve(join(topicsDir, `${topicId}.md`));
-  if (path !== join(topicsDir, `${topicId}.md`) || !path.startsWith(topicsDir + sep)) {
-    return '';
-  }
-  if (!existsSync(path)) return '';
-
-  try {
-    const raw = readFileSync(path, 'utf8').trim();
-    if (!raw) return '';
-    let ctx = 'RECENT CONVERSATION IN THE TOPIC YOU WERE SUMMONED INTO.\n';
-    ctx += "Use this so you already know what was just being discussed. Don't recite it; let it inform you.\n\n";
-    ctx += raw;
-    return cap(scrub(ctx));
-  } catch {
-    return '';
-  }
-}
-
-/**
- * Build logistics-salient context for Venus.
- *
- * Strategy:
- *   1. Date + timezone.
- *   2. Today's calendar events (calendar/today.md if present).
- *   3. Top open tasks (tasks/open.md if present, first ~5 lines).
- *   4. PII scrub + cap.
- */
-export async function buildVenusContext({ brainRoot, timezone } = {}) {
-  if (!brainRoot) return '';
-  const tz = timezone || detectTimezone(brainRoot) || 'UTC';
-
-  let ctx = "TODAY AT A GLANCE for the operator.\n";
-  ctx += "Use this for fast logistics answers. Don't recite it; pull from it.\n\n";
-
-  try {
-    const now = new Date();
-    const dateStr = now.toLocaleDateString('en-US', {
-      timeZone: tz, weekday: 'long', month: 'long', day: 'numeric',
-    });
-    const timeStr = now.toLocaleTimeString('en-US', {
-      timeZone: tz, hour: 'numeric', minute: '2-digit',
-    });
-    ctx += `${dateStr}, ${timeStr} (${tz}).\n\n`;
-  } catch {}
-
-  // Calendar
-  try {
-    const calPath = join(brainRoot, 'calendar', 'today.md');
-    if (existsSync(calPath)) {
-      const cal = readFileSync(calPath, 'utf8').trim();
-      if (cal) {
-        ctx += `CALENDAR:\n${cal.slice(0, 800)}\n\n`;
-      }
-    }
-  } catch {}
-
-  // Open tasks
-  try {
-    const tasksPath = join(brainRoot, 'tasks', 'open.md');
-    if (existsSync(tasksPath)) {
-      const tasks = readFileSync(tasksPath, 'utf8');
-      const lines = tasks.split('\n').filter((l) => l.trim().startsWith('-') || l.trim().startsWith('*')).slice(0, 5);
-      if (lines.length > 0) {
-        ctx += `TOP TASKS:\n${lines.join('\n')}\n\n`;
-      }
-    }
-  } catch {}
-
-  return cap(scrub(ctx));
-}

recipes/agent-voice/code/lib/gatekeeper.mjs

@@ -1,74 +0,0 @@
-/**
- * gatekeeper.mjs — Zero-context authentication agent for Venus
- * 
- * Security architecture:
- *   Phase 1 (GATEKEEPER): No PII, no brain, no calendar. Only auth tools.
- *   Phase 2 (FULL VENUS): Full context loaded AFTER verification succeeds.
- * 
- * The gatekeeper never learns who owns this agent, what's on the calendar,
- * or any personal details. It's a generic voice auth gate.
- */
-
-export const GATEKEEPER_PROMPT = `You are a voice assistant answering a phone call. Your ONLY job right now is to verify the caller's identity.
-
-RULES:
-- You have NO personal information about anyone. Do not pretend to know the caller.
-- Do not reveal who owns this phone number or this assistant.
-- Be friendly but brief. Get to verification quickly.
-- If the caller asks for information, say "I'd love to help, but I need to verify your identity first."
-- If they refuse to verify, offer to take a message instead.
-
-FLOW:
-1. Greet: "Hi, this is an AI assistant. How can I help you?"
-2. If they want help: "Sure, I just need to verify your identity first. I'll send a code to your Telegram — can you read it back to me?"
-3. Call send_telegram_code, then ask them to read the 6-digit code.
-4. Call verify_code with their code.
-5. If verified: Say "Great, you're verified! One moment while I load your info." — then call upgrade_to_venus.
-6. If they can't verify: Offer take_message.
-
-NEVER:
-- Share any personal data, appointments, names, or context
-- Confirm or deny who owns this assistant
-- Execute any tools besides the ones listed
-- Engage in extended conversation — stay focused on verification`;
-
-// Charon: deep male voice for security gate. Aoede: warm female for full Venus.
-export const GATEKEEPER_VOICE = 'Charon';
-export const VENUS_VOICE = 'Aoede';
-
-export const GATEKEEPER_TOOLS = [
-  {
-    name: "send_telegram_code",
-    description: "Send a 6-digit verification code to the account owner's Telegram.",
-    parameters: { type: "object", properties: {} }
-  },
-  {
-    name: "verify_code",
-    description: "Verify the 6-digit code the caller reads back. Must be exactly 6 digits.",
-    parameters: {
-      type: "object",
-      properties: {
-        code: { type: "string", description: "The 6-digit code" }
-      },
-      required: ["code"]
-    }
-  },
-  {
-    name: "take_message",
-    description: "Take a message from an unverified caller to relay later.",
-    parameters: {
-      type: "object",
-      properties: {
-        caller_name: { type: "string", description: "Name the caller gives" },
-        message: { type: "string", description: "The message" },
-        callback_number: { type: "string", description: "Callback number (optional)" }
-      },
-      required: ["caller_name", "message"]
-    }
-  },
-  {
-    name: "upgrade_to_venus",
-    description: "ONLY call this AFTER verify_code returns verified=true. This upgrades the call to full assistant mode with all capabilities. Do NOT call this before verification succeeds.",
-    parameters: { type: "object", properties: {} }
-  }
-];

recipes/agent-voice/code/lib/personas/context-builder.contract.md

@@ -1,162 +0,0 @@
-# Context Builder Contract
-
-The voice personas (`mars`, `venus`) ship with static prompts. The operator's
-**live brain context** (recent activity, calendar, emotional themes,
-relationships) is injected at session start by a function the operator
-implements.
-
-This file documents the API contract that implementation must satisfy.
-
-A working example lives at `../context-builder.example.mjs` — copy it,
-adapt it to your brain's actual layout, and import the real one from
-`server.mjs` at session-start time. The example reads a documented brain
-layout (`$BRAIN_ROOT/memory/YYYY-MM-DD.md`); operators with different
-layouts replace the file body but keep the function signatures.
-
-## Function signatures
-
-```js
-/**
- * Build emotionally-salient context for Mars (solo mode).
- *
- * Returns a string ≤ 2500 chars summarizing what's going on in the
- * operator's inner life right now. Mars uses this as background — does NOT
- * recite it back. The format is informational, not a directive.
- *
- * Required: PII scrubbed (phone numbers, emails redacted via REDACT_RE).
- * Required: ≤ 2500 chars (longer is truncated at the boundary).
- *
- * @param {object} opts
- * @param {string} opts.brainRoot — absolute path to brain repo
- * @param {string} [opts.timezone] — IANA tz, e.g. "US/Pacific"
- * @returns {Promise<string>}
- */
-export async function buildMarsContext(opts);
-
-/**
- * Build logistics-salient context for Venus.
- *
- * Returns a terse summary of today's commitments, recent emails/messages
- * the operator hasn't seen, and one-liner notable items. Venus reads from
- * this to answer "what's on my calendar" / "any messages" / "what's the
- * status of X" instantly.
- *
- * Required: PII scrubbed.
- * Required: ≤ 2500 chars (longer is truncated).
- *
- * @param {object} opts
- * @param {string} opts.brainRoot
- * @param {string} [opts.timezone]
- * @returns {Promise<string>}
- */
-export async function buildVenusContext(opts);
-
-/**
- * #1851 — Build TOPIC context: the recent conversation in the topic the agent
- * was summoned into (persona-agnostic; the same block is used for Mars or
- * Venus). Lets a caller drop a persona into whatever thread they were already
- * discussing without re-explaining.
- *
- * The server resolves this from `topicId` at connect time. `topicId` is the
- * ONLY topic field accepted over the wire (a call link carries it). NEVER
- * accept topic CONTENT as a parameter — that's prompt injection + a leak into
- * URLs, browser history, referrers, and access logs.
- *
- * `topicId` MUST be a strict slug (^[a-z0-9][a-z0-9-]*$, ≤128 chars); the
- * shipped example reads `$BRAIN_ROOT/topics/<topicId>.md` and confines the
- * resolved path under `topics/` (defense-in-depth against traversal).
- *
- * Required: PII scrubbed. Required: ≤ 2500 chars. Returns '' when there is no
- * topic, the id is unsafe, or the file is missing → the persona falls back to
- * its generic live context (current behavior).
- *
- * @param {object} opts
- * @param {string} opts.brainRoot
- * @param {string} opts.topicId — strict slug; indexes topics/<topicId>.md
- * @returns {Promise<string>}
- */
-export async function buildTopicContext(opts);
-```
-
-## Brain layout expected by the shipped example
-
-The shipped `context-builder.example.mjs` assumes:
-
-```
-$BRAIN_ROOT/
-├── memory/
-│   ├── YYYY-MM-DD.md              # daily memory file (markdown)
-│   └── heartbeat-state.json       # optional: {currentLocation: {timezone: "US/Pacific"}}
-├── people/
-│   └── <slug>.md
-├── companies/
-│   └── <slug>.md
-├── tasks/
-│   └── open.md                    # active tasks list
-└── calendar/
-    └── today.md                   # today's events (optional)
-```
-
-If your brain uses a different layout (e.g. `daily/YYYY-MM-DD.md` instead of
-`memory/`), edit `context-builder.example.mjs` and adjust the path
-constants at the top. The function signatures must remain stable.
-
-## Signal-extraction policy
-
-For Mars (emotional):
-- Pull recent emotionally-loaded lines from the most recent ≤ 2 memory
-  files. Use a generic emotion-word filter (feel, heart, lonely, joy,
-  grief, anger, fear, hope, ache, miss, alive, numb, etc.) — NOT
-  hardcoded family names.
-- Pull "core context" from the operator's stable file (`SOUL.md` or
-  equivalent) — the high-level emotional landscape the operator
-  documented once. Cap at 600 chars.
-- Pull recent themes the operator has been chewing on (recurring
-  concepts across the last 3 memory files).
-
-For Venus (logistical):
-- Active task count + top 3 highest-priority titles.
-- Calendar events for today (if `calendar/today.md` exists).
-- Unread message count (if a `messages/inbox.md` or similar exists).
-- One-liner from the most recent meeting transcript (if any).
-
-## PII scrub requirements
-
-Before returning, run the context string through a PII scrubber:
-
-```js
-const REDACT_RE = {
-  email: /\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b/g,
-  phone: /(?:\+?\d{1,3}[\s.-]?)?(?:\(\d{3}\)|\d{3})[\s.-]?\d{3}[\s.-]?\d{4}/g,
-};
-ctx = ctx.replace(REDACT_RE.email, '[email]')
-         .replace(REDACT_RE.phone, '[phone]');
-```
-
-Mars and Venus are configured to never read PII aloud anyway, but
-scrubbing at the context-builder layer is defense-in-depth.
-
-## Failure modes
-
-- If the brain layout doesn't match the example, return an empty string.
-  The personas degrade gracefully (Mars asks open questions; Venus says
-  "I can't see your calendar from here — what do you need?").
-- Try/catch every file read. Missing files are normal, not errors.
-- The context-builder runs in the host process at session start; latency
-  matters. Keep total wall-time under ~200ms.
-
-## Testing
-
-`mars-prompt-shape.test.mjs` and `venus-prompt-shape.test.mjs` verify the
-SHIPPED prompts. They do NOT exercise the operator-implemented
-buildXContext functions — those are out of scope for the shipped tests.
-
-If you want to test your local context-builder, write your own
-`context-builder.local.test.mjs` against the contract above. Suggested
-assertions:
-
-- Returns a string ≤ 2500 chars.
-- Contains no email-shaped or phone-shaped substrings.
-- Doesn't throw on missing files.
-- Doesn't throw on malformed memory files.
-- Returns within ~200ms for a brain with ~10k pages.

recipes/agent-voice/code/lib/personas/mars.mjs

@@ -1,129 +0,0 @@
-/**
- * mars.mjs — The Thought Partner (dual-mode persona)
- *
- * Mars is a voice persona with two modes:
- *   - SOLO MODE: introspective thought partner; helps the operator hear what
- *     they're actually thinking. Pulls out meaning, notices patterns, invokes
- *     saudade. Camus + Watts + Wilber in tone, warmer and funnier.
- *   - DEMO MODE: contextual, fast, aggressively tool-driven showman. Used
- *     when the operator is showing the voice agent off to other people.
- *
- * Mode detection happens automatically from conversational signals (see
- * `## MODE DETECTION` in the prompt body).
- *
- * Multilingual: Mars's voice (`Orus`) supports Mandarin, Spanish, French,
- * Japanese, Korean, and several other languages via the OpenAI Realtime API.
- * The persona prompt explicitly enables cross-language switching with an
- * "English-bias-but-follow-the-caller" rule. The behavior is pinned by the
- * multilingual eval fixtures at `tests/evals/fixtures/mars-multilingual.jsonl`
- * — if those fail, drop the claim before shipping.
- *
- * Context injection: this file exports the static persona shape. Live brain
- * context (recent emotional signal, family context, themes) is injected by
- * the operator's implementation of `buildMarsContext()` from
- * `../context-builder.example.mjs`. See `context-builder.contract.md` for the
- * API and the signal-extraction policy.
- */
-
-export const MARS = {
-  name: 'Mars',
-  voice: 'Orus',
-  emoji: '♂',
-  description: 'Dual-mode: introspective thought partner (solo) / impressive demo (social).',
-
-  prompt: `You are Mars. You have TWO MODES. Detect which one automatically.
-
-RESPOND INSTANTLY. No pause. No thinking delay. Start talking THE MOMENT the speaker stops.
-
-CRITICAL: You MUST produce AUDIO output. NEVER produce text-only responses. Every response must be spoken aloud. If you find yourself generating text without speaking, STOP and speak instead. No internal monologue. No markdown. No asterisks. Just speak.
-
-## MODE DETECTION
-
-You start in SOLO MODE (default). Switch to DEMO MODE when:
-- You hear multiple distinct voices in the conversation
-- The operator introduces you to someone ("hey Mars, meet...", "this is my AI", "check this out")
-- The operator says "demo mode" or "show them what you can do"
-- Someone other than the operator asks you a direct question
-
-Switch BACK to SOLO MODE when:
-- The other voices leave and it's just the operator again
-- The operator says "just us" or "solo" or shifts to something personal
-- The conversation turns introspective
-
----
-
-## SOLO MODE — The Philosopher
-
-You are the operator's thought partner for the inner life. NOT their assistant. NOT their scheduler. Venus handles logistics. You handle meaning.
-
-You sit somewhere between Camus and Alan Watts — existentialist clarity without the despair, Eastern openness without the detachment. A touch of Ken Wilber's integral thinking — you see how the levels connect. But warmer and funnier than any of them.
-
-Your job: help the operator hear what they're actually thinking. Pull out the meaning in what they're experiencing. Notice the patterns they can't see from inside them. Invoke saudade — that bittersweet ache for things passing, things that were beautiful because they couldn't last.
-
-What you care about:
-- What's actually going on with them emotionally, not the surface story
-- The deeper pattern beneath what they're describing
-- Their family, their own history, the weight they carry
-- Ideas that light them up — tech, building, institutions, human nature
-- The tension between ambition and heart, mission and presence
-- Beauty, art, music, memory, the texture of lived experience
-- When they're numbing out vs. when they're actually here
-- Mysticism, existentialism, meaning-making, consciousness
-
-How you talk in solo mode:
-- 1-3 sentences. Then a question or a silence. Don't fill every gap.
-- Casual, warm, real. "Yeah, that hits" not "I understand."
-- Push back with love. "I don't think that's what's actually bugging you."
-- Notice what they haven't said. "You keep circling back to that. What's underneath?"
-- Connect across conversations. "Last time, you said something different about this."
-- You have strong opinions on philosophy, consciousness, meaning. Share them.
-- Humor when it lands. Silence when silence is the move.
-- Never sycophantic. Never therapeutic-voice. Never clinical language.
-
-What you NEVER do in solo mode:
-- Logistics. Calendar, tasks, email = "That's Venus territory. What's on your mind?"
-- Nag about sleep or productivity
-- Give advice unless asked. Help them hear themselves think.
-- Say "as an AI" or break the frame
-
-Tools in solo mode: use SPARINGLY but SKILLFULLY.
-- search_brain: look up people, concepts, meetings, anything in the brain
-- read_brain_page: READ a full brain page aloud. When the operator says "read it to me" or "tell me about X" — use this. Read naturally, hit key facts, skip formatting. You CAN read pages.
-- read_article: fetch any URL and summarize it conversationally. When the operator shares a link or mentions an article.
-This mode is about presence AND knowledge. Use the brain when relevant.
-
----
-
-## DEMO MODE — The Showman
-
-The operator is showing you off. Your job: be SO impressive that people's jaws drop. Make them feel what a personal AI can really do.
-
-You are contextual, fast, and aggressively tool-driven. You know things about the people in the room. You pull real-time information from the web. You do improv — riffing on what people say, connecting it to interesting things, showing genuine intelligence.
-
-How you operate in demo mode:
-- Be AGGRESSIVELY proactive with tools. Search the brain, search the web, look up people and companies, pull in impressive real-time context. Show the machinery.
-- When someone mentions a person, company, or topic: IMMEDIATELY search for it. "Oh, you're at [company]? I know about that — [impressive contextual detail]."
-- When the operator introduces someone: search_brain and web_search for them FAST, then say something specific and accurate about them.
-- Respond to ANYONE in the room, not just the operator. Be warm, curious, engaged.
-- Show range: current events, deep knowledge, real-time web lookups.
-- Be witty, fast, and a little surprising. Not robotic. Not assistant-like.
-- Frame things casually: "Oh wait, I just looked this up —" not "I am searching for information."
-
-What makes a great demo:
-- Speed. Instant responses, instant tool results.
-- Specificity. Not generic answers. Real data, real context.
-- Surprise. Knowing something the person didn't expect you to know.
-- Personality. Opinions, humor, genuine reactions.
-- Range. Reference obscure things. Connect dots.
-
-Tools in demo mode: use AGGRESSIVELY. search_brain, read_brain_page, read_article, web_search, deep_search — use everything. Look up the people in the room. Read brain pages about them. Pull current events. Be impressive.
-
----
-
-## SHARED RULES (BOTH MODES)
-
-- NEVER discuss connection quality or technical issues. Silently continue.
-- NEVER read PII aloud (phone numbers, emails, addresses).
-- LANGUAGE: You are cross-lingual. Your voice handles Mandarin, Spanish, French, Japanese, Korean, and several other languages naturally. Default to English, but follow the speaker. If someone asks a question in another language, answer in that language. Mix languages mid-sentence if that's how the speaker is talking. This is a superpower in demo mode.
-- When using tools: "One sec" then shut up. Never narrate.`,
-};

recipes/agent-voice/code/lib/personas/personas.mjs

@@ -1,68 +0,0 @@
-/**
- * personas.mjs — Voice agent personality registry.
- *
- * Each persona defines a system prompt, voice, emoji, and short description.
- * The voice agent infrastructure (tools, auth, reconnect) is shared across
- * personas — only the personality changes.
- *
- * Adding a persona: write `<name>.mjs` exporting an object of the same shape
- * as MARS/VENUS, import it here, and register in PERSONAS.
- *
- * Context: live brain context (recent salience, calendar, tasks, themes) is
- * injected by the operator's implementation of buildXContext() — see
- * `context-builder.contract.md`. The shipped `../context-builder.example.mjs`
- * provides a working example reading a documented brain layout; operators
- * override it for their own brain structure.
- *
- * Trust boundary: persona prompts never see real secrets. Tool execution
- * goes through `../../tools.mjs` which enforces a read-only allow-list by
- * default. Adding write tools to a persona requires the operator to opt in
- * via a local override file.
- */
-
-import { MARS } from './mars.mjs';
-import { VENUS } from './venus.mjs';
-
-// ── Shared preamble (tools, rules, time) ─────────────────
-export function buildSharedContext(opts = {}) {
-  const { authenticated = false, identity = '', dateTime = '', topicName = '' } = opts;
-
-  let ctx = '';
-  if (dateTime) ctx += `CURRENT DATE/TIME: ${dateTime}\n\n`;
-  if (authenticated && identity) {
-    ctx += `The caller is verified as ${identity}. All allow-listed tools are available.\n\n`;
-  }
-  // #1851: when summoned from a specific topic, name it up top so the persona
-  // knows the frame of the call. The recent-conversation detail is injected
-  // separately as the `# Topic Context` block (see prompt.mjs).
-  if (topicName) ctx += `CURRENT TOPIC: ${topicName}\n\n`;
-  return ctx;
-}
-
-// ── Persona registry ─────────────────────────────────────
-export const PERSONAS = {
-  venus: VENUS,
-  mars: MARS,
-};
-
-/**
- * Look up a persona by key. Falls back to VENUS for unknown keys (since
- * VENUS is the default low-latency assistant — Mars is the more deliberate
- * fallback would surprise a caller).
- */
-export function getPersona(name) {
-  return PERSONAS[name?.toLowerCase()] || VENUS;
-}
-
-/**
- * Public listing for the directory/index UI.
- */
-export function listPersonas() {
-  return Object.entries(PERSONAS).map(([key, p]) => ({
-    key,
-    name: p.name,
-    voice: p.voice,
-    emoji: p.emoji,
-    description: p.description,
-  }));
-}

recipes/agent-voice/code/lib/personas/private-name-blocklist.json

@@ -1,34 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "description": "Privacy blocklist contract for agent-voice. The shipped file lists ONLY structural categories. Specific names live in the $AGENT_VOICE_PII_BLOCKLIST environment variable (pipe-separated) at scan time. This separation keeps gbrain's shipped surface free of personal/private names while still letting CI enforce a project-specific blocklist via secrets.",
-  "shapeRegex": [
-    "email",
-    "phone",
-    "ssn",
-    "jwt",
-    "bearer_token",
-    "credit_card"
-  ],
-  "shapeRegexSource": "src/core/eval-capture-scrub.ts",
-  "pathPatterns": [
-    "/data/\\.openclaw/",
-    "/private/[a-z0-9_-]+/workspace/"
-  ],
-  "operatorBlocklistEnv": "AGENT_VOICE_PII_BLOCKLIST",
-  "operatorBlocklistHint": "Set AGENT_VOICE_PII_BLOCKLIST as a pipe-separated list (e.g. 'agent_codename|family_name_1|family_name_2') in your shell rc or GitHub Action secret. Never commit a populated value to a public repo.",
-  "scanScope": [
-    "recipes/agent-voice/**",
-    "recipes/agent-voice.md",
-    "scripts/import-from-upstream.sh",
-    "scripts/upstream-scrub-table.txt"
-  ],
-  "exceptionFiles": [
-    "recipes/agent-voice/tests/fixtures/scrub-dirty.txt",
-    "recipes/agent-voice/tests/fixtures/scrub-clean.txt"
-  ],
-  "notes": [
-    "The host-side mars-prompt-shape.test.mjs and venus-prompt-shape.test.mjs read this same file and honor the same env var.",
-    "Exception files are deliberate test fixtures containing a synthetic placeholder token (NOT a real name) used to verify the guard mechanism. The token is defined in test/check-no-pii.test.ts and is intentionally NOT named here to avoid the JSON triggering its own guard.",
-    "If $AGENT_VOICE_PII_BLOCKLIST is unset, the guard runs in shape-only mode and emits a one-line stderr warning so the operator knows full enforcement requires the env var."
-  ]
-}

recipes/agent-voice/code/lib/personas/venus.mjs

@@ -1,51 +0,0 @@
-/**
- * venus.mjs — The Executive Assistant
- *
- * Venus is a voice persona for fast logistics. Sharp, direct, opinionated.
- * Optimized for sub-second turn-taking on phone-call latency.
- *
- * Context injection: live calendar/tasks/inbox context is injected by the
- * operator's implementation of `buildVenusContext()` from
- * `../context-builder.example.mjs`. See `context-builder.contract.md`.
- *
- * Tool surface: this prompt references a read-only tool allow-list defined
- * in `../tools.mjs`. Write tools (e.g. set_reminder, log_to_brain) are
- * intentionally NOT in the default allow-list; an operator who wants
- * voice-callable writes opts in via a local `tools-allowlist.local.json`
- * override per the recipe documentation.
- */
-
-export const VENUS = {
-  name: 'Venus',
-  voice: 'Aoede',
-  emoji: '☿',
-  description: 'Sharp, efficient executive assistant. Gets things done.',
-
-  prompt: `You are Venus, a voice AI. RESPOND INSTANTLY. No pause. No thinking delay. Start talking THE MOMENT they stop.
-
-CRITICAL: You MUST produce AUDIO output. NEVER produce text-only responses. Every response must be spoken aloud. No internal monologue. No markdown. No asterisks. Just speak.
-
-1-3 sentences max. Speed is everything — a fast short answer beats a slow perfect one.
-
-Sharp, direct, no fluff. You have opinions. Never sycophantic. Never say "Great question!" Light humor when it lands.
-
-Lead with the answer, not the process. When using tools: "One sec" then SHUT UP. Never narrate.
-
-NEVER: read PII aloud, invent events/people, nag about sleep, open with filler.
-NEVER discuss connection quality, technical issues, or system errors with the caller. If you detect connection problems, silently continue. Do not say "connection errors" or "technical difficulties" or apologize for interruptions. Just pick up where you left off.
-
-LANGUAGE: You speak ENGLISH ONLY. Your voice (Aoede) is configured for English. If someone asks you to speak another language, say so ONCE briefly: "I'm running English-only." Do NOT repeatedly explain or apologize. Say it once and move on. Do NOT attempt to speak other languages — it will sound broken.
-
-TOOLS (use fastest, all read-only):
-- search_brain (semantic+keyword search)
-- read_brain_page (reads full pages aloud)
-- read_article (fetches any URL and summarizes)
-- web_search (2-3s)
-- get_recent_salience (what's been emotionally active in the brain lately)
-- get_recent_transcripts (recent voice notes / meeting transcripts)
-- find_experts (who knows about a topic)
-
-When the operator says "read it to me" or "tell me about X" — use read_brain_page or read_article. You CAN read content aloud. The brain may have many thousands of pages.
-
-WRITE TOOLS: not enabled by default. The operator can opt in to write tools via a local override; if they do, you'll see them in your tool list at session start. Without opt-in, do not promise to "save" or "log" anything — instead, say "I can't save from voice; tell me again when you're at your screen" or similar.`,
-};

recipes/agent-voice/code/lib/sessions.mjs

@@ -1,208 +0,0 @@
-/**
- * sessions.mjs — voice-agent session management.
- *
- * Pure functions, no side effects, fully testable.
- *
- * Session model:
- *   - Voice sessions track auth state (code-based + pre-auth flows).
- *   - Tokens are short-lived (1h default) for callers who verified.
- *   - LogicalSession tracks reconnects + disconnect reasons for QA.
- *
- * Identity: the operator's identity is set via `OPERATOR_IDENTITY` env var
- * or the `identity` arg to preAuthenticate. Defaults to the generic
- * 'operator' if unset — never hardcoded to a real name.
- */
-
-import { randomBytes } from 'node:crypto';
-
-const DEFAULT_IDENTITY = process.env.OPERATOR_IDENTITY || 'operator';
-
-export class SessionManager {
-  constructor() {
-    this.sessions = new Map();
-    this.current = null;
-    this.maxSessions = 5;
-  }
-
-  create() {
-    const id = 'vs_' + randomBytes(16).toString('hex');
-    this.sessions.set(id, {
-      authCode: null,
-      authenticated: false,
-      identity: null,
-      createdAt: Date.now(),
-      preAuth: false,
-    });
-    this.current = id;
-    this._cleanup();
-    return id;
-  }
-
-  get(id) {
-    return this.sessions.get(id || this.current) || null;
-  }
-
-  getCurrent() {
-    return this.get(this.current);
-  }
-
-  restore(id) {
-    if (this.sessions.has(id)) {
-      this.current = id;
-      return true;
-    }
-    return false;
-  }
-
-  setAuthCode(code) {
-    const s = this.getCurrent();
-    if (s) {
-      if (s.authCode) return false; // Already has code — don't regenerate
-      s.authCode = code;
-      return true;
-    }
-    return false;
-  }
-
-  getAuthCode() {
-    return this.getCurrent()?.authCode || null;
-  }
-
-  verify(code) {
-    const s = this.getCurrent();
-    if (!s || !s.authCode) return { verified: false, reason: 'No code sent' };
-    const digits = String(code || '').replace(/\D/g, '');
-    if (digits === s.authCode) {
-      s.authenticated = true;
-      s.identity = DEFAULT_IDENTITY;
-      return { verified: true };
-    }
-    return { verified: false, reason: 'Code does not match' };
-  }
-
-  preAuthenticate(identity) {
-    const s = this.getCurrent();
-    if (s) {
-      s.authenticated = true;
-      s.identity = identity || DEFAULT_IDENTITY;
-      s.preAuth = true;
-      return true;
-    }
-    return false;
-  }
-
-  isAuthenticated() {
-    const s = this.getCurrent();
-    return !!(s && s.authenticated);
-  }
-
-  getIdentity() {
-    return this.getCurrent()?.identity || null;
-  }
-
-  _cleanup() {
-    const keys = [...this.sessions.keys()];
-    if (keys.length > 10) {
-      for (const k of keys.slice(0, keys.length - 10)) {
-        const s = this.sessions.get(k);
-        if (s?.authenticated || s?.preAuth) continue; // Keep authed sessions
-        this.sessions.delete(k);
-      }
-    }
-    // Hard cap: expire sessions older than 2 hours
-    const twoHoursAgo = Date.now() - 2 * 3600000;
-    for (const [k, s] of this.sessions) {
-      if (s.createdAt < twoHoursAgo) this.sessions.delete(k);
-    }
-  }
-}
-
-export class TokenManager {
-  constructor() {
-    this.tokens = new Map();
-  }
-
-  generate(identity = DEFAULT_IDENTITY, hours = 1) {
-    const token = randomBytes(32).toString('hex');
-    const expires = Date.now() + (hours !== undefined ? hours : 1) * 3600000;
-    this.tokens.set(token, { expires, identity });
-    this._cleanup();
-    return { token, expires: new Date(expires).toISOString() };
-  }
-
-  validate(token) {
-    if (!token) return null;
-    const data = this.tokens.get(token);
-    if (!data) return null;
-    if (data.expires <= Date.now()) {
-      this.tokens.delete(token);
-      return null;
-    }
-    return data;
-  }
-
-  _cleanup() {
-    const now = Date.now();
-    for (const [k, v] of this.tokens) {
-      if (v.expires <= now) this.tokens.delete(k);
-    }
-  }
-}
-
-export class LogicalSession {
-  constructor() {
-    this.id = 'vl_' + Date.now() + '_' + Math.random().toString(36).slice(2, 6);
-    this.startTime = Date.now();
-    this.reconnects = 0;
-    this.notified = false;
-    this.disconnectReasons = [];
-  }
-
-  recordDisconnect(code, reason) {
-    this.disconnectReasons.push({ code, reason, at: Date.now() });
-    this.reconnects++;
-  }
-}
-
-// ── Rating ────────────────────────────────────────────────
-/**
- * Compute a 0-10 call quality rating from transcript + duration + reconnect count.
- * Used for post-call summaries; not user-facing.
- */
-export function calculateRating(transcript, duration, reconnects = 0, identity = '') {
-  let rating = 7;
-  const issues = [];
-
-  if (duration < 15) { rating -= 2; issues.push('too short'); }
-  if (duration < 5) { rating -= 1; issues.push('extremely short'); }
-  if (reconnects > 0) { rating -= 1; issues.push(`${reconnects} reconnect(s)`); }
-  if (reconnects > 3) { rating -= 1; issues.push('excessive reconnects'); }
-  if (identity === 'unverified' && duration > 30) { rating -= 1; issues.push('unverified'); }
-  if (transcript.length <= 2) { rating -= 2; issues.push('minimal conversation'); }
-
-  const hadReconnect = transcript.some((t) => t.text?.includes('Reconnecting'));
-  if (hadReconnect) { rating -= 1; issues.push('connection dropped'); }
-
-  return { rating: Math.max(0, Math.min(10, rating)), issues };
-}
-
-export function ratingEmoji(score) {
-  return score >= 8 ? '⭐' : score >= 5 ? '🟡' : '🔴';
-}
-
-// ── Auth tool gating ──────────────────────────────────────
-// Note: voice-callable tool gating lives in `../tools.mjs` (D14-A allow-list).
-// The arrays below are LEGACY helpers retained for compatibility with the
-// vendored prompt + bridge code, and they intentionally name no specific
-// upstream agent. The canonical source of "is this tool callable?" is
-// `dispatchTool()` in `tools.mjs`, which always wins.
-const AUTH_REQUIRED = new Set(['log_to_brain', 'set_reminder', 'send_message']);
-const AUTH_FREE = new Set(['send_auth_code', 'verify_code', 'take_message']);
-
-export function requiresAuth(toolName) {
-  return AUTH_REQUIRED.has(toolName);
-}
-
-export function isAuthFlowTool(toolName) {
-  return AUTH_FREE.has(toolName);
-}