admin/gbrain
1
0
Fork 0
mirror of https://github.com/garrytan/gbrain.git synced 2026-07-31 04:07:52 +00:00
Code Issues Packages Projects Releases Wiki Activity
425 Commits 567 Branches 1 Tag
c873ce3014439b4ec5a973c4edbec0ecfb261683
Commit Graph
9 Commits
Author SHA1 Message Date
+5
Time AttakcGitHubSinabinathomaskong119maxpetrusenkoagentbrettdaviesivandebotRafael Reisfbal23javieraldapeDavid CarolanMasashi-Ono0611spiky02plateaupsam-717Claude Opus 4.8
 		86962b242b fix(gateway): consolidate tool-loop resume + provider fixes (fix-wave A) (#2820) 
Collector branch superseding the gateway tool-loop duplicate cluster and
adjacent provider fixes. Re-implemented from the best of each PR (deduped by
content, not file-overlap); every fix carries test coverage.

Gateway tool-loop resume (supersedes #1934 #2062 #2065 #2112 #2274 #2487
#2336 #2257 #2499 #2491, test #2063):
- toolLoop now persists the tool-result user turn per round (onToolResultTurn),
  so a resumed subagent job reloads a balanced transcript instead of dangling
  assistant tool-calls that non-Anthropic providers reject with
  AI_MissingToolResultsError.
- runSubagentViaGateway reconciles an already-corrupted transcript on resume:
  it heals every dangling assistant tool-call turn (not just the tail) from the
  settled subagent_tool_executions rows, re-dispatching idempotent-pending
  tools and throwing on non-idempotent, mirroring the legacy Anthropic path.
  Terminal early-return for a transcript that already reached end_turn.
- repairToolPairing() is a last-resort normalization at the chat() boundary
  (from #2336): back-fills error stubs for any assistant tool-call still
  unanswered (partial turns, provider-duplicated/dropped IDs on local models,
  length-truncated batches). No-op on balanced input.
- toModelMessages is Date-safe (Postgres timestamptz -> ISO via a JSON round
  trip at the SDK boundary, never a ::jsonb cast; degrades bigint/circular to a
  string instead of throwing) and drops non-string text blocks reasoning models
  emit that AI SDK v6 rejects (#2488).

Adjacent provider fixes:
- Model-aware default max output tokens: thinking-by-default Claude 5 models get
  headroom (gateway 32000, think 16000) while everything else stays 4096/4000,
  so DeepSeek/OpenAI subagents don't exceed provider caps (#2614 #2806).
- DeepSeek: promote reasoning_content into content when content is empty, via a
  fail-open recipe fetch shim (#2617).
- OpenRouter: map openrouter_api_key (config + env) into OPENROUTER_API_KEY
  through buildGatewayConfig; register agent.use_gateway_loop, zeroentropy and
  openrouter keys in KNOWN_CONFIG_KEYS so `config set` accepts them (#2572,
  config key from #2112).

Preserves JSONB (no JSON.stringify into ::jsonb), engine parity, source
isolation, and trust-boundary invariants. Verified with the gbrain-pr-test-env
consumer matrix (clawlancer/Postgres, gstack + hivemindos/PGLite) baseline-FAIL
-> candidate-PASS on the same repro, plus bun run verify (31/31) and 439
targeted unit + e2e tests.

Co-authored-by: Sinabina <sinabina@Sinabinas-MacBook-Pro-4.local>
Co-authored-by: thomaskong119 <thomaskong119@hotmail.com>
Co-authored-by: maxpetrusenkoagent <max.petrusenko.agent@gmail.com>
Co-authored-by: brettdavies <brettdavies@users.noreply.github.com>
Co-authored-by: ivandebot <187176982+ivandebot@users.noreply.github.com>
Co-authored-by: Rafael Reis <rafael.reis@contabilizei.com.br>
Co-authored-by: fbal23 <fbal.public@gmail.com>
Co-authored-by: javieraldape <javieraldape@users.noreply.github.com>
Co-authored-by: David Carolan <david@joyrestart.com>
Co-authored-by: Masashi-Ono0611 <masashi.ono.0611@gmail.com>
Co-authored-by: spiky02plateau <155588579+spiky02plateau@users.noreply.github.com>
Co-authored-by: psam-717 <mphilannorbah@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-16 16:31:53 -07:00
Time AttakcandGitHub 010847c020 fix(think): enforce source scope across gather (#2200) (#2739) 
Carry the caller's scalar or federated source scope through every think gather stream: hybrid page retrieval, takes keyword/vector retrieval, and graph traversal. Adds source predicates to the takes retrieval methods in both engines. Part of #2200 (the think slice; #2200 stays open as the tracking issue for the remaining by-slug read ops).
 2026-07-13 00:09:27 -07:00
Garry TanGitHubClaude Opus 4.8
 		5911072aec v0.42.4.0 fix: think --model fails loud — slash-form ids + never persist empty synthesis (#1698) (#1736) 
* fix: think --model fails loud on unresolvable model; never persist empty synthesis (#1698)

Slash-form model ids (anthropic/claude-sonnet-4-6) silently degraded to the
no-LLM stub and wrote empty synthesis pages with exit 0 (reporter saw 200).
Three compounding defects, fixed:

- normalizeModelId (src/core/model-id.ts): one shared provider:model normalizer
  replacing 4 colon-only inlines; slash→colon, bare→default, malformed
  leading-separator (:foo) returned unchanged so resolveRecipe throws loud.
- validateModelId + probeChatModel (gateway.ts): shared id-validity + key probe;
  runThink hard-errors on an explicit --model it can't run (no silent degrade).
- synthesisOk + persist-skip (think/index.ts): empty/malformed/empty-JSON
  synthesis is never persisted; --save with no synthesis exits 1.
- auto-think (cycle/auto-think.ts): empty synthesis no longer counts complete or
  advances the cooldown (the autonomous third caller of persistSynthesis).
- hasAnthropicKey consolidated into src/core/ai/anthropic-key.ts (3 copies → 1).

MCP think op sets modelExplicit; saved_slug '' maps to null.

* chore: bump version and changelog (v0.42.4.0)

#1698 think --model fail-loud wave. Also files the P3 follow-up TODO for the
provider-symmetric early gate (D1 accept-as-is).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-01 21:54:13 -07:00
Garry TanGitHubClaude Opus 4.7
 		a19ee8bafe v0.40.2.0 feat: trajectory routing for temporal + knowledge_update (gbrain think + LongMemEval) (#1296) 
* feat(facts): add event_type column + trajectory-format helper (v0.40.2.0 Commit 1)

Substrate work for v0.40.2.0 Track B (trajectory routing for temporal +
knowledge_update). This commit lands the schema + the shared formatter;
think wiring + LongMemEval extractor + intent routing come in Commits 2-4.

Migration v81 (facts_event_type_column):
  ALTER TABLE facts ADD COLUMN event_type TEXT (nullable, metadata-only).
  Lets the v0.35.4 typed-claim substrate carry event-shaped rows
  (event_type='meeting'/'job_change'/'location_change') alongside the
  metric-shaped rows (claim_metric/claim_value etc) it has carried since
  v67. Temporal-reasoning questions ("when did I last meet Marco") need
  the event shape; the metric shape doesn't fit them.

Engine changes (pglite + postgres parity):
  - TrajectoryPoint.event_type: string | null added; projection in both
    findTrajectory SQL paths returns the column.
  - TrajectoryOpts.kind?: 'metric' | 'event' | 'all' added (default 'all').
    Defensive opt that future-proofs filtering once event rows accumulate.
  - Both engines apply the new kind filter at SQL level when set.

Back-compat (codex outside-voice concern):
  Existing callers (founder-scorecard, eval-trajectory) already defensively
  skip metric === null rows in their per-metric math. Event-only rows
  (metric=NULL, event_type='meeting') ride through invisibly to those
  callers — verified by the new regression test that asserts byte-identical
  computeFounderScorecard + computeTrajectoryStats output with and without
  event rows in the input. Both callers now pass kind:'metric' explicitly
  for call-site clarity (no behavior change).

MCP find_trajectory op:
  - event_type added to the wire-shape map.
  - kind param added to the op declaration (enum metric/event/all).

Shared formatter (src/core/trajectory-format.ts, new):
  formatTrajectoryBlock(points, entitySlug, opts) — sibling shape to
  renderTakesBlock + renderChatBlock. Groups by (metric ?? event_type).
  Per-metric cap 20, total cap 100 (prompt-budget guardrail). For
  knowledge_update intent, annotates value-change rows with
  "(superseded prior)" — the explicit signal codex flagged was missing
  from default RRF-ordered retrieval. Promoted to src/core/ so both
  gbrain think (Commit 2) and the LongMemEval harness (Commit 4)
  consume one source of truth.

Prompt-injection coverage (codex Problem 10):
  src/core/think/sanitize.ts INJECTION_PATTERNS extended with three
  new entries — close-trajectory, open-trajectory, xml-attr-inject —
  so adversarial </trajectory> sequences in extracted text get
  escaped before reaching the model. Parity with the existing
  </take> coverage.

Tests (all hermetic, no DATABASE_URL):
  - test/trajectory-format.test.ts (17 cases, all green): grouping,
    caps, sanitization, supersession annotation, determinism,
    provenance, text-cap, adversarial </trajectory> escape.
  - test/engine-parity-event-type.test.ts (6 cases): PGLite round-trip
    of the column + kind filter matrix.
  - test/regressions/v0_40_2_0-trajectory-backcompat.test.ts (4 cases):
    pins the byte-identical-output contract that founder-scorecard's
    per-metric math ignores event rows.
  - test/migrate.test.ts: v81 round-trip verified via existing
    structural assertion harness.
  - 209 tests across 5 impacted suites pass; bun run verify clean
    (17 pre-checks including privacy, jsonb, type, fuzz purity).

Plan: ~/.claude/plans/system-instruction-you-are-working-crystalline-owl.md
GSTACK REVIEW REPORT: CEO + ENG + CODEX CLEARED.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(think): trajectory injection for temporal + knowledge_update (v0.40.2.0 Commit 2)

Wires the v0.40.2.0 substrate (Commit 1's facts.event_type column +
formatTrajectoryBlock) into the production `gbrain think` surface.
Default ON; flip `think.trajectory_enabled=false` to opt out.

New pure modules (zero engine dependency):
  - src/core/think/intent.ts — classifyIntent(question): regex-first
    routing into 'temporal' | 'knowledge_update' | 'other'. KU wins over
    temporal when both match. The 'other' fast path short-circuits with
    zero SQL.
  - src/core/think/entity-extract.ts — extractCandidateEntities() pulls
    high-precision candidates from retrieval slugs (people/, companies/,
    organizations/, deals/) and medium-precision noun phrases from the
    question. Word-level tokenization + stop-word boundaries stitch
    "Blue Bottle" as one candidate while splitting "I last meet Marco"
    correctly. Leading-verb stripper drops "meet", "visit" etc so
    "marco" surfaces cleanly. Cap of 5 per question.

Engine-touching wiring (src/core/think/index.ts):
  - RunThinkOpts gains 4 fields: withTrajectory (default true),
    sourceId, allowedSources, remote.
  - readThinkTrajectoryEnabled() reads the config kill switch; default
    true; survives missing config table on legacy brains.
  - Trajectory orchestration sits between gather and prompt assembly:
    intent classify → extract candidates → per-candidate
    resolveEntitySlugWithSource → skip fallback_slugify → 5s timeout
    Promise.race + 3-wide concurrency cap → formatTrajectoryBlock.
    Any error degrades to "no block" + TRAJECTORY_INJECTION_FAILED
    warning; the think call itself never crashes from trajectory.
  - On success, TRAJECTORY_INJECTED_<N>_POINTS warning records the
    count for downstream telemetry.

Prompt placement (src/core/think/prompt.ts) — Codex Problem 6 fix:
  buildThinkUserMessage's trajectoryBlock slot honors BOTH existing
  orderings — calibration mode inserts trajectory between calibration
  and question; default mode inserts between retrieval and the output
  instruction. NO third ordering is introduced. Empty trajectoryBlock
  skips the "Known trajectory:" header entirely (don't cue the model
  we tried).

Resolution-source signal (src/core/entities/resolve.ts) — Codex Problem 5:
  New companion resolveEntitySlugWithSource() returns
  {slug, source: 'exact_page' | 'fuzzy_match' | 'fallback_slugify'}
  so trajectory routing can skip fallback-only resolutions —
  querying findTrajectory on an invented slug always returns [] and
  wastes a SQL round-trip. The original resolveEntitySlug keeps its
  contract for pre-v0.40 callers.

MCP think op handler (src/core/operations.ts):
  Extracts sourceScopeOpts(ctx) into scalar sourceId + allowedSources
  + remote, threads through to runThink. CLI callers omit (engine
  default source, remote=false). Mirrors the same source-scope
  discipline applied to all other read paths in v0.34.1.0.

Sanitization (Commit 1 already extended INJECTION_PATTERNS for
</trajectory> — consumed here).

Test coverage (all hermetic, no DATABASE_URL, no API keys):
  - test/think-intent.test.ts (14 cases) — temporal, KU, other,
    precedence (KU wins when both match), defensive non-string inputs.
  - test/think-entity-extract.test.ts (10 cases) — retrieved-slug
    source, noun-phrase source, stop-word stripping, leading-verb
    stripping, dedup across sources, 5-candidate cap.
  - test/think-trajectory-injection.test.ts (7 cases against PGLite
    in-memory) — temporal intent injection happy path with superseded-
    prior annotation, "other" intent short-circuit, withTrajectory:
    false bypass, think.trajectory_enabled=false config bypass,
    empty-trajectory skip, engine.findTrajectory throw is caught
    (Promise.allSettled defense), TRAJECTORY_INJECTED warning count.
  - Existing test/think-pipeline.serial.test.ts re-asserted unchanged
    (10 cases — calibration mode parity, gather, sanitization,
    cite-render all intact).

72 tests pass across 7 impacted suites; bun run verify clean (17 pre-
checks). Defaulted on per CEO + Eng D1; kill switch via config.

Plan: ~/.claude/plans/system-instruction-you-are-working-crystalline-owl.md

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(longmemeval): inline Haiku claim extractor + content-hash cache (v0.40.2.0 Commit 3)

Populates the LongMemEval benchmark brain's facts table inline at
import time so Commit 4's intent routing has data to retrieve. Per the
CHANGELOG D1 decision, this is full-haystack preprocessing — disclosed
explicitly in the benchmark output's methodology_note field (Commit 4).

New module src/eval/longmemeval/extract.ts:
  extractAndInsertClaims({engine, client, model, sessionSlug,
                          sessionId, sessionBody, sourceId, aliasMap})
  - Hashes the session body (sha256) for cache lookup.
  - Cache hit → reuses parsed claims (cuts a 3-iteration benchmark
    run from $1.50 to $0.50 when sessions repeat across questions,
    as they do in LongMemEval).
  - Cache miss → one Haiku call. System prompt asks for
    {entity, metric, value, unit, period, event_type, valid_from, text}[]
    JSON. New parseExtractedJsonArray() helper does fence-strip + parse
    (parseModelJSON from cross-modal-eval is shaped for scored objects,
    not arrays — different parser needed here).
  - Per-record validateClaim() drops malformed records (missing
    entity, bad date) silently; the rest land in NewFact rows.
  - Per-question AliasMap (Codex Problem 4 — semantics pinned):
    "Marco" + "Marco Smith" + "marco" in the SAME question collapse
    to one slug via first-mention-wins canonicalization. Across
    questions, the harness creates a fresh map (no leak).
  - Real-page-aware entity resolution via the v0.40.2.0
    resolveEntitySlugWithSource (Commit 2). Slugify-fallback rows
    still insert (we need the data); the resolution_source signal
    is only consulted at trajectory retrieval time (Commit 4).
  - Bulk insert via engine.insertFacts with the
    `gbrain-allow-direct-insert` allow-list comment per the
    check-system-of-record CI guard contract — benchmark brain is
    ephemeral in-memory PGLite, no markdown source-of-truth applies.
  - Fail-open posture: Haiku throw, malformed JSON, insert collision
    all return inserted=0 without throwing. One bad session never
    kills the per-question loop.
  - getCacheStats() exposes hits/misses/size for the per-run stderr
    telemetry Codex Problem 14 asked for (empirical hit-rate
    reporting; the optimistic claim self-verifies).

Substrate plumbing (extends Commit 1):
  - NewFact.event_type?: string | null added in engine.ts so the
    extractor can pass event-shaped rows through to insertFacts.
  - PGLite engine + Postgres engine insertFacts() now persist
    event_type. Param-positional dispatch extended to 20/21 placeholders
    (null-embedding vs embedding-present); tx.unsafe vector cast on
    Postgres path unchanged.

Test coverage (test/longmemeval-extract.test.ts, 13 cases, hermetic):
  - Happy path: typed-claim + event rows both insert with correct
    kind (event_type='meeting' → kind='event'; claim_metric='mrr'
    → kind='fact').
  - Alias map: per-session collapsing ("Marco" + "Marco Smith"),
    cross-session persistence within one question, fresh map per
    question (caller-clears semantics pinned).
  - Content-hash cache: identical body → cache hit, only ONE Haiku
    call across two sessions; different bodies miss; getCacheStats
    reports hits/misses/size.
  - Fail-open: malformed JSON, Haiku throw, empty array output,
    invalid records (missing entity, bad date) — none crash; 0
    inserted in each case.

55 tests pass across 4 impacted suites; bun run verify clean.

Plan: ~/.claude/plans/system-instruction-you-are-working-crystalline-owl.md

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(longmemeval): trajectory intent routing + prompt splice + methodology disclosure (v0.40.2.0 Commit 4)

The final wiring: per-question intent classification + trajectory call
+ block splice into the answer-gen prompt. Plus the methodology
disclosure stamps that close out the Codex D1 contract.

New module src/eval/longmemeval/intent.ts:
  classifyIntent(q): prefers q.question_type from the dataset
  (LongMemEval ships labels like 'temporal-reasoning',
  'knowledge-update', 'single-session-user') before falling back to
  the SHARED regex set imported from src/core/think/intent.ts.
  Single source of truth for the regex — think and longmemeval
  cannot drift.

Harness wiring in src/commands/eval-longmemeval.ts:
  - runEvalLongMemEval() spawns an extractor model via resolveModel
    (tier:'utility' → haiku) when trajectory routing is enabled.
    Calls resetExtractorState() once per benchmark run so the
    content-hash cache + counters start clean.
  - runOneQuestion() creates a FRESH per-question AliasMap (Codex
    Problem 4 — first-mention-wins canonicalization stays scoped to
    one question, never leaks across).
  - Per session: after importFromContent lands, extractAndInsertClaims
    populates the facts table. Fail-open if the Haiku call errors;
    next session keeps going.
  - After hybridSearch returns: classifyIntent(q) routes
    temporal/knowledge_update through extractCandidateEntities (the
    SHARED helper from Commit 2's think/entity-extract) → per-candidate
    findTrajectory with 5s Promise.race timeout → formatTrajectoryBlock.
    First candidate with a non-empty trajectory wins.
  - generateAnswer() splices the trajectory block BEFORE the
    Retrieved sessions block. Empty block (no entity match / no
    points) → no "Known trajectory:" header (don't cue the model
    we tried).
  - JSON envelope gains 5 fields per question when trajectory routing
    is on: intent, trajectory_points, entity_resolved,
    resolution_source, methodology_note. methodology_note also
    written to stderr at run completion.

Resolution-source gate DIVERGES from think (intentional):
  In the think production path, fallback_slugify results are skipped
  because querying invented slugs wastes SQL — production brains have
  canonical pages. In the LongMemEval benchmark, there ARE no
  canonical pages; both the extractor and the lookup go through
  slugify-fallback on the same free-form name, so they cohere on the
  same slug. Applying the think-path gate here would permanently
  block trajectory injection on the benchmark. Comment in
  runOneQuestion documents the divergence.

New CLI flag --no-trajectory:
  Bypasses BOTH the Haiku extractor AND the per-question intent
  routing. Used by the measurement protocol to baseline default-on vs
  no-trajectory across 3 seeds per condition with paired-bootstrap
  CI. Documented in the help text.

New RunOpts fields:
  - extractorClient?: ThinkLLMClient — separate stub from the
    answer-gen client so tests can isolate the two surfaces.
  - extractorModel?: string — model override for the Haiku call.

methodology_note = 'extractor=haiku-preprocess-full-haystack-v1'
stamped on:
  - Every per-question JSON envelope row.
  - Stderr summary at run completion.
This is the Codex D1 contract: the temporal-reasoning delta we
publish is "gbrain + Haiku-preprocess pipeline" vs "gbrain alone",
not directly comparable to LongMemEval's published baselines
without that disclosure.

Extractor cache hit-rate stderr summary (Codex Problem 14):
  '[longmemeval] extractor.cache_hits: 412 / 489 sessions (84.2%,
  cached_bodies=412)' — empirical verification of the optimistic
  hit-rate claim. The optimistic number self-verifies per run.

Test coverage (all hermetic, no API keys):
  - test/longmemeval-intent.test.ts (9 cases) — dataset
    question_type → Intent mapping for all six LongMemEval labels;
    dataset label trumps question-text signal; unknown labels fall
    through to the regex classifier.
  - test/longmemeval-trajectory-routing.test.ts (4 cases) —
    end-to-end through runEvalLongMemEval with both clients stubbed:
    trajectory block lands in answer-gen prompt for temporal
    intent + absent for 'other'; --no-trajectory bypasses extractor
    AND injection AND omits envelope fields; methodology_note
    stamped on every routed row; perf gate preserved (< 10s for
    2-question fixture).

118 tests pass across 11 impacted suites; bun run verify clean.

Wave complete. CHANGELOG draft + measurement plan live in the plan
file. v0.40.2.0 ready for /ship after a real-LLM spot-check run.

Plan: ~/.claude/plans/system-instruction-you-are-working-crystalline-owl.md

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v0.40.2.0)

v0.40.2.0 trajectory routing wave — gbrain think now grounds answers
about temporal/knowledge-update questions in the typed-claim timeline
the brain has been quietly building via the extract_facts cycle phase.
Default ON; flip think.trajectory_enabled=false to opt out.

LongMemEval-side wiring lands the same plumbing in the benchmark
harness with explicit methodology disclosure (extractor=haiku-preprocess-
full-haystack-v1) in the JSON envelope and stderr summary — the published
temporal-reasoning number is "gbrain + Haiku-preprocess" vs "gbrain alone",
not directly comparable to LongMemEval's published baselines without that
disclosure.

Plan: ~/.claude/plans/system-instruction-you-are-working-crystalline-owl.md
3 review passes: CEO + ENG + CODEX all CLEARED.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: sync project docs for v0.40.2.0 trajectory routing

CLAUDE.md, README.md, AGENTS.md extended with the v0.40.2.0 trajectory
routing surface: gbrain think integration (default ON via
think.trajectory_enabled config key), facts.event_type schema column +
TrajectoryPoint.event_type + TrajectoryOpts.kind filter, shared
formatTrajectoryBlock helper in src/core/trajectory-format.ts,
LongMemEval extractor + intent routing + methodology disclosure,
migration v82.

llms-full.txt regenerated to match CLAUDE.md edits (CI test/build-llms
gate).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test: fill v0.40.2.0 unit + e2e gaps (71 new tests across 7 gap areas)

Audit of the trajectory-routing wave's test surface vs the shipped
code surfaced 7 gaps. All filled, all green. Total: 343 tests across
17 impacted suites (was 272 pre-fill).

Gap 1 — Migration v86 structural tests (11 new in test/migrate.test.ts):
  - v86 entry exists with documented name + idempotent
  - exactly one event_type column add to facts
  - IF NOT EXISTS guard
  - column is nullable (no NOT NULL, no DEFAULT regression guard)
  - does NOT create any index (event_type is selectivity-poor)
  - does NOT touch any other table (blast-radius pin)
  - does NOT carry a sqlFor override (engine-shared SQL contract)
  - PGLite round-trip: column exists with right type + nullable
  - event_type INSERT/SELECT round-trip
  - NULL round-trip for legacy + metric-only rows
  - LATEST_VERSION >= 86 contract pin

Gap 2 — resolveEntitySlugWithSource branch coverage (12 new in
test/entity-resolve.test.ts):
  - exact_page branch (full slug, slug-shape match)
  - fuzzy_match branch (Title-cased display name, bare first name via
    prefix expansion)
  - fallback_slugify branch (unseeded name, multi-word non-match
    phrase, accented input)
  - null tail (empty + whitespace)
  - back-compat parity with resolveEntitySlug for both exact_page and
    fallback_slugify branches

Gap 3 — INJECTION_PATTERNS dedicated coverage for new entries (18 new
in test/think-sanitize-trajectory.test.ts):
  - close-trajectory entry registered + matches canonical and
    whitespace/case variations
  - open-trajectory entry registered + matches both no-attr and
    with-attrs forms
  - xml-attr-inject strips entity=/metric=/event_type=/kind=
  - does NOT strip non-trajectory attribute names (class/id/title)
  - combined multi-vector attack: all three patterns fire
  - formatTrajectoryBlock end-to-end with adversarial extractor text:
    one live </trajectory> (the wrapper, not the injection); one
    entity= attribute (the wrapper, not the injection)
  - pattern ordering invariant: new entries land after close-take

Gap 4 — runThink calibration-mode placement contract (3 new in
test/think-trajectory-injection.test.ts):
  - default mode: question → pages → takes → trajectory → instruction
  - calibration mode: pages → takes → calibration → trajectory →
    question → instruction (Codex P6 — no third ordering invented)
  - empty trajectory in calibration mode preserves the existing
    calibration shape (no false-positive cue)

Gap 5 — runThink resolution_source != fallback_slugify gate (1 new
in test/think-trajectory-injection.test.ts):
  - candidate that only matches via fallback_slugify is NOT queried
    (think-path divergence from longmemeval-path which accepts it)

Gap 6 — E2E for runThink trajectory injection (7 new in
test/e2e/think-trajectory-pglite.test.ts):
  - full pipeline lands <trajectory> block in answer-gen prompt
  - knowledge_update intent annotates value-change rows with
    (superseded prior)
  - 'other' intent short-circuits (no block, no SQL)
  - think.trajectory_enabled=false config bypasses entire path
  - empty brain → graceful no-op (no crash, no block)
  - multi-entity deterministic ordering
  - adversarial </trajectory> in seeded fact text is escaped before
    reaching the LLM (end-to-end sanitization gate)

Gap 7 — longmemeval extractor stress + persistence pins (6 new in
test/longmemeval-extract.test.ts):
  - alias map cross-session stress with 12 sessions in one question;
    all 12 rows collapse under ONE entity_slug
  - different entities stay separate across many sessions
  - embedding + embedded_at both NULL on benchmark-inserted rows
    (regression guard against accidental embed-on-write)
  - row_num sequential + source_markdown_slug stamped per session
    (v0.32.2 partial UNIQUE index contract)
  - source field stamped "longmemeval:extractor" (audit-tag pin)
  - cache key invariance: same body hash hits cache across different
    sessionId/slug

bun run verify clean (17 pre-checks). No regressions in any of the
14 non-new impacted suites.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test: exempt facts.event_type from schema-bootstrap-coverage CI guard

The schema-bootstrap-coverage CI guard (test/schema-bootstrap-coverage.test.ts)
enforces that every ALTER TABLE ADD COLUMN in MIGRATIONS is covered by
applyForwardReferenceBootstrap OR by PGLITE_SCHEMA_SQL's CREATE TABLE
bodies OR by COLUMN_EXEMPTIONS.

v0.40.2.0's migration v87 adds facts.event_type but deliberately ships
without a bootstrap probe because:
  - No CREATE INDEX in PGLITE_SCHEMA_SQL references event_type
  - No FK references event_type
  - All existing callers (founder-scorecard, eval-trajectory, gbrain
    think trajectory injection) defensively skip NULL-metric rows in
    per-metric math, so event_type=NULL on pre-v87 brains is invisible
  - Pre-v87 brains land event_type=NULL via the migration ALTER

Exactly mirrors the precedent set by facts.claim_metric / claim_value /
claim_unit / claim_period exemptions (v67 typed-claim columns) which
are exempted for the same structural reason: column-only migration,
no forward-reference index, no downstream filter breaks on old brains.

Adding facts.event_type to COLUMN_EXEMPTIONS with a brief rationale
comment matching the existing v0.35.6 entry shape.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-22 22:37:15 -07:00
Garry TanGitHubClaude Opus 4.7
 		3a0e1116e7 v0.36.1.0 Hindsight calibration wave: brain learns how you tend to be wrong (#1139) 
* schema: v0.36.0.0 Hindsight calibration tables (migrations v67-v71)

Foundation commit for the Hindsight-inspired calibration wave. Adds four
new tables + one perf index, all source-scoped from day 1 per v0.34.1
discipline:

- calibration_profiles (v67): per-holder LLM-narrative aggregation of
  TakesScorecard data. published BOOL gates E8 cross-brain mount sharing
  (default false). grade_completion REAL surfaces partial-grade state to
  the dashboard. active_bias_tags TEXT[] with GIN index feeds E3 (calibration-
  aware contradictions) and E7 (real-time nudge matching).

- take_proposals (v68): propose_takes phase queue. Idempotency cache via
  (source_id, page_slug, content_hash, prompt_version) unique index mirrors
  the v0.23 dream_verdicts pattern. proposal_run_id supports --rollback by
  run. dedup_against_fence_rows JSONB audit column records what canonical
  takes the LLM was told to dedupe against at proposal time.

- take_grade_cache (v69): grade_takes verdict cache. Composite PK on
  (take_id, prompt_version, judge_model_id, evidence_signature) — prompt
  edits OR evidence changes cleanly invalidate prior verdicts. applied=false
  default + auto-resolve-off-by-default (D17) means every fresh install
  needs operator opt-in before grade verdicts mutate the takes table.

- take_nudge_log (v70): E7 nudge cooldown state. Polymorphic FK — a nudge
  fires on either a canonical take OR a pending proposal (CDX-5 fix). CHECK
  constraint enforces exactly-one-set. channel column lets future routing
  (webhook, admin SPA toast) reuse the same cooldown semantics.

- takes_resolved_at_idx (v71): partial index for the Brier-trend
  aggregation queries. Engine-aware handler — Postgres uses CONCURRENTLY
  to avoid the ShareLock; PGLite uses plain CREATE.

Every table carries wave_version TEXT NOT NULL DEFAULT 'v0.36.0.0' so the
v0.36.0.0 calibration --undo-wave command (lands later in the wave) can
reverse just this wave's writes.

Plan: ~/.claude/plans/system-instruction-you-are-working-rippling-knuth.md
covers the design rationale (D17/D18/D21 + CDX findings).

Schema parity:
- src/schema.sql for fresh Postgres installs
- src/core/pglite-schema.ts for fresh PGLite installs
- src/core/schema-embedded.ts auto-regenerated from schema.sql
- src/core/migrate.ts for upgrade-in-place from older brains

VERSION bumped to 0.36.0.0 for the wave. CHANGELOG entry lands at /ship.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* core: BaseCyclePhase abstract class enforces source-scope + budget contracts

D21 from the eng review. Three new v0.36.0.0 cycle phases (propose_takes,
grade_takes, calibration_profile) share enough structure that the
duplication-vs-abstraction trade tips toward a shared base. Without this
scaffold, source-isolation discipline would drift exactly the way it
drifted in v0.34.1 — except this time across three new surfaces at once.

What this enforces:

1. Phase signature is uniform: run(ctx, opts) → PhaseResult.

2. ctx.sourceId / ctx.auth.allowedSources MUST be threaded through every
   engine call. The base class surfaces a scope() helper that wraps
   sourceScopeOpts(ctx) and is the only sanctioned way to read source-
   scoped data. Forgetting to thread source scope becomes a TypeScript
   compile error, not a runtime leak. Closes the v0.34.1 leak class
   structurally for every new phase.

3. Budget meter wraps run() automatically. Subclass declares budgetUsdKey
   + budgetUsdDefault; base reads the resolved cap from config and creates
   the BudgetMeter. Subclass calls this.checkBudget() before each LLM
   submit; budget-exhausted phase still returns status='ok' (clean abort)
   so the cycle report shows partial completion, not failure.

4. Error envelope is uniform. Thrown errors get caught and converted to
   status='fail' with a phase-specific error.code via the subclass's
   mapErrorCode() hook.

5. Progress reporter integration. Base accepts the reporter via opts;
   subclasses call this.tick() instead of touching the reporter directly,
   so the phase name in the progress stream is always correct.

Tests: 13 cases in test/core/base-phase.test.ts cover source-scope
threading (5 cases including the empty-allowedSources-MUST-NOT-widen-scope
regression), PhaseResult shape including the error envelope path (3
cases), dry-run propagation (2 cases), and budget meter construction
(3 cases including config-key override).

Synthesize.ts / patterns.ts (existing pre-v0.36 phases) deliberately do
NOT retrofit to this base in v0.36.0.0 — too much churn for a refactor
that doesn't pay off until v0.37+. Future phases use this by default.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* cycle: propose_takes phase + take_proposals queue write path (T3)

LLM-based take extraction from markdown prose. Walks pages updated since
last cycle, sends each page's body to a tuned extractor, writes the
extracted gradeable claims to the take_proposals queue. User accepts /
rejects via `gbrain takes propose --review` (lands in Lane C).

Cycle wiring:
  lint → backlinks → sync → synthesize → extract → extract_facts →
    resolve_symbol_edges → patterns → recompute_emotional_weight →
    consolidate → propose_takes (NEW) → grade_takes (NEW; T4) →
    calibration_profile (NEW; T6) → embed → orphans → purge

CyclePhase enum extended with 3 new entries; ALL_PHASES + NEEDS_LOCK_PHASES
updated. All three new phases acquire the cycle lock (writes to
take_proposals / take_grade_cache / calibration_profiles).

Idempotency contract:
  The (source_id, page_slug, content_hash, prompt_version) composite unique
  index on take_proposals means an unchanged page never re-spends LLM
  tokens. Bumping PROPOSE_TAKES_PROMPT_VERSION cleanly invalidates the
  cache so a tuned prompt re-runs proposals on every page. Mirrors the
  v0.23 dream_verdicts pattern.

F2 fence dedup:
  The phase reads the page's existing `<!-- gbrain:takes:begin -->` fence
  (when present) and passes the canonical take rows to the extractor as
  "things you have already captured." Prevents duplicate proposals when
  prose is appended to a page that already has takes. Records the fence
  rows the LLM was told to dedupe against on the take_proposals row for
  audit (dedup_against_fence_rows JSONB).

Auto-resolve posture:
  propose_takes only WRITES proposals to the queue. Nothing in this phase
  mutates the canonical takes table. Operator opt-in via the queue review
  CLI (Lane C) is the only path from queue to canonical fence (D17).

Prompt tuning status (v0.36.0.0 ship state):
  The default extractor prompt is annotated `v0.36.0.0-stub`. The real
  tuned prompt arrives via T19 synthetic corpus build (50 anonymized
  pages, 3-model parallel extraction, user reviews disagreement set,
  F1 ≥ 0.85 on training corpus + F1 ≥ 0.8 on ground-truth holdout).
  Until T19 lands, propose_takes runs but produces best-effort candidates
  the user reviews manually.

Architecture:
  ProposeTakesPhase extends BaseCyclePhase (T2). Inherits source-scope
  threading via scope(), budget metering via this.checkBudget(), error
  envelope wrapping. budgetUsdKey: cycle.propose_takes.budget_usd
  (default $5/cycle). Budget exhaustion mid-page returns status='warn'
  with details.budget_exhausted=true — clean partial-completion semantics.

  Test seam: opts.extractor injection so the phase can run hermetically
  without touching the gateway. defaultExtractor (production path) calls
  gateway.chat with the EXTRACT_TAKES_PROMPT and parses the JSON array
  output via parseExtractorOutput.

  parseExtractorOutput defends against common LLM output sins: markdown
  code fence wrapping, leading prose, single-object instead of array,
  unknown kind values, weight out of [0,1], rows missing claim_text or
  exceeding 500 chars.

Tests: 25 cases in test/propose-takes.test.ts cover the 4 pure helpers
(parseExtractorOutput, contentHash, hasCompleteFence,
extractExistingTakesForDedup) + 7 phase integration scenarios (happy path,
cache hit, fence dedup, extractor failure, empty pages, skipPagesWithFence,
proposal_run_id stability).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* cycle: grade_takes phase + take_grade_cache verdict pipeline (T4)

Walks unresolved takes that are old enough to have outcome data, retrieves
evidence from the brain, asks a judge model to verdict each one. Writes
verdicts to take_grade_cache. Optionally — only when operator has flipped
the opt-in config flag — auto-applies high-confidence verdicts to the
canonical takes table via engine.resolveTake.

Auto-resolve posture (D17 — DISABLED by default):
  On a fresh install, grade_takes runs and writes verdicts to the cache,
  but applied=false on every row. Operator reviews the queue, then flips
  `cycle.grade_takes.auto_resolve.enabled: true` once trust is earned.
  Mirrors the propose_takes review-queue posture: queue exists, mutation
  requires explicit opt-in.

Conservative threshold (D12):
  When auto_resolve.enabled is true, a verdict auto-applies only when
  confidence >= 0.95 (single-judge path). T5 ensemble path lands next,
  tightening this further with 3/3 unanimous requirement.

  'unresolvable' verdict NEVER auto-applies even at confidence=1.0 —
  there's no canonical column for "we tried and there's no evidence yet."

Evidence retrieval status (v0.36.0.0 ship state):
  The default evidence retriever returns an "evidence-retrieval not yet
  wired" placeholder. Most verdicts produced by the stub-judge against
  the stub-evidence will be 'unresolvable'. Real retrieval (hybrid search
  over pages newer than the take's since_date, optionally augmented by a
  gateway web-search recipe in v0.37+) lands as a follow-up. Documented
  limitation per CDX-8 + D17 — the phase ships now so the wiring is real
  and the cache table accumulates verdicts even if early ones are
  conservative.

Cache key:
  Composite primary key on take_grade_cache is
  (take_id, prompt_version, judge_model_id, evidence_signature). Prompt
  edits OR evidence changes OR judge swap cleanly invalidate prior
  verdicts. Mirrors the v0.32.6 eval_contradictions_cache pattern.

  evidence_signature = SHA-256 of (judge_model_id + '|' + evidence_text)
  so identical evidence under a different judge does NOT collide.

Architecture:
  GradeTakesPhase extends BaseCyclePhase. Inherits source-scope threading,
  budget metering (cycle.grade_takes.budget_usd, default $3/cycle), error
  envelope. Test seam: opts.judge + opts.evidenceRetriever injection so
  the phase runs hermetically.

  parseJudgeOutput defends against fence-wrapping, leading prose,
  out-of-range confidence (clamps to [0,1]), invalid verdict labels,
  oversized reasoning (truncated at 400 chars). Returns null on
  unrecoverable parse — caller treats null as "judge_output_parse_failed
  / unresolvable at confidence 0.0" so the row still lands in cache with
  the parse failure surfaced via warnings.

  takeIsOldEnough gates on since_date (default 6 months). Tolerates
  YYYY-MM-DD and YYYY-MM formats. Returns false on null/unparseable
  since_date so takes without dates never get graded (we'd be
  hallucinating temporal context).

Tests: 23 cases covering parseJudgeOutput (7 cases), evidenceSignature
(3), takeIsOldEnough (5), and 8 phase integration scenarios — happy path,
D17 auto-resolve-off default, D12 above-threshold auto-apply, below-
threshold cache-only, unresolvable-NEVER-applies, cache hit, too-recent
gate, judge-throw warning.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* cycle: grade_takes ensemble tiebreaker for borderline verdicts (T5 / E2)

Multi-judge ensemble tiebreaker, additive on top of T4's single-judge
foundation. Reuses gateway.chat as the per-model judge interface; runs
three judges in parallel via Promise.allSettled. Pure aggregation logic
in aggregateEnsemble() — no SQL, no LLM, hermetically testable.

When ensemble fires (T5 trigger band):
  Only when ALL of:
    - opts.useEnsemble === true (default false)
    - opts.ensembleJudges array is non-empty
    - single-model confidence in [0.6, 0.95) (configurable via
      opts.ensembleTriggerBand)
    - single-model verdict !== 'unresolvable'

  Above 0.95 the single judge is already sufficient (T4 path). Below 0.6
  the verdict is clearly review-only — ensemble wouldn't change the
  posture. 'unresolvable' from single-judge means no evidence yet; calling
  three more judges on the same evidence won't manufacture some.

Conservative auto-apply (D12):
  Ensemble verdict auto-applies via engine.resolveTake only when ALL of:
    - autoResolve === true (operator opt-in per D17)
    - ensemble.agreement === 3 (3/3 unanimous)
    - ensemble.minConfidence >= ensembleThreshold (default 0.85)
    - winning verdict !== 'unresolvable'

  Schema-level monotonic-tightening guard for ensembleThreshold lives in
  the takes resolution layer.

Cache identity:
  When ensemble fires, the cache row's judge_model_id becomes
  'ensemble:<modelA>+<modelB>+<modelC>' — a future re-run with different
  ensemble membership doesn't collide with prior verdicts. evidence_signature
  is recomputed because it includes the judge_model_id.

aggregateEnsemble (pure):
  - 3/3 unanimous → agreement=3, minConfidence=min across the three
  - 2/3 majority → agreement=2, minConfidence across the agreeing two
  - 1/1/1 disagreement → tie-break: prefer non-'unresolvable', then
    alphabetical for determinism
  - 'unresolvable' from one model NEVER tips a 2-vote majority toward
    'unresolvable' — by-label tally only counts a model toward its own
    label
  - All three judges failing (allSettled rejected) → verdict='unresolvable'
    with agreement=0; auto-apply path blocked
  - Single judge survives + two fail → agreement=1; the lone verdict wins
    but auto-apply gated by the 3/3 requirement

Tests: 16 cases.
  aggregateEnsemble (6): 3/3, 2/3, 1/1/1, unresolvable-tipping-resistance,
  all-failed, partial-failed-but-survives.
  Phase trigger conditions (5): useEnsemble=false default, useEnsemble=true
  in borderline band, single >= 0.95 skip, single < 0.6 skip, single =
  'unresolvable' skip.
  Phase auto-apply rules (5): 3/3+threshold+autoResolve, 2/3 majority no
  apply, 3/3 below threshold no apply, one ensemble judge throws still
  aggregates from allSettled, empty ensembleJudges falls through to
  single.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* cycle: calibration_profile phase + shared voice gate across surfaces (T6)

The calibration narrative layer. Reads TakesScorecard, asks an LLM to
write 2-4 conversational pattern statements ("right on tactics, late on
macro by 18 months"), passes them through the voice gate, derives active
bias tags, writes the row to calibration_profiles. This is the read-side
that E1 (think anti-bias rewrite), E3 (contradictions join), E6
(dashboard), and E7 (real-time nudges) all consume.

Voice gate (D24 — single function, multiple surfaces):
  ALL five calibration UX surfaces import the same gateVoice() function
  from src/core/calibration/voice-gate.ts. Mode parameter
  ('pattern_statement' | 'nudge' | 'forecast_blurb' | 'dashboard_caption'
  | 'morning_pulse') drives surface-specific tuning via the rubric the
  gate ships to its Haiku judge. NO forked implementations — voice
  rubric drift would defeat the gate.

  Each mode's rubric explicitly forbids preachy / clinical / corporate
  voice; a structural test pins this. Anchors the cross-cutting voice
  rule from /plan-ceo-review D2-D8.

Fallback policy (D11):
  Up to 2 generation attempts (configurable). On both rejects → fall back
  to a hand-written template from src/core/calibration/templates.ts.
  Templates are intentionally short and a little "robotic" — they're the
  safety net, not the destination. voice_gate_passed=false +
  voice_gate_attempts get persisted on the calibration_profiles row so
  the operator can review the failing examples and tune the rubric over
  time. Suppressing the surface silently is NEVER an option — that's how
  voice quality silently degrades.

  parseJudgeOutput defaults to 'academic' on parse failure (NEVER passes
  pass-through) so a Haiku output garble falls through to the template
  rather than letting unverified text reach the user.

calibration_profile phase:
  Extends BaseCyclePhase. Cold-brain skip: <5 resolved takes → no row
  written, no LLM call. Otherwise: scorecard via engine.getScorecard()
  → patterns via voice-gated generator → bias tags via separate
  generator (best-effort; failure logs warning, phase continues).

  The DB INSERT lands in the v67 calibration_profiles row with
  source_id, holder, the patterns, voice gate audit fields, active bias
  tags, and grade_completion (F1 fix — partial-grade state surfaces to
  the dashboard "60% graded" badge).

  Budget gate at $0.50/cycle default (mostly Haiku). Below-budget
  before-LLM-call check returns status='warn' without writing the row.

  Per-domain scorecards are a placeholder for v0.36.0.0 ship state —
  the F12 batchGetTakesScorecards() engine method that powers per-domain
  rendering lands in Lane C alongside the CLI/MCP surface.

Architecture:
  parsePatternStatementsOutput is tolerant of LLM emitting numbered
  lists / bulleted lines despite the prompt asking for plain lines.
  Caps at 4 patterns + drops excessively long lines (>200 chars).

  parseBiasTagsOutput lowercases input + drops non-kebab-case tokens
  (defends against the LLM emitting "Over-Confident Geography" with
  spaces or capitals). Caps at 4 tags.

Tests: 43 cases across two new test files.
  voice-gate.test.ts (24): parseJudgeOutput (7), gateVoice happy path
  (3), fallback path (5), mode parity (2), templates (7).
  calibration-profile.test.ts (19): parsers (10), pickFallbackSlots
  (3), phase integration (6 — cold-brain skip, happy path, voice gate
  fallback, grade_completion plumbed through, bias-tags failure
  non-fatal, source_id scope reaches INSERT).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* cli: gbrain calibration + get_calibration_profile MCP op (T7)

Public-facing read surface for the v0.36.0.0 calibration wave. CLI prints
the active calibration profile; MCP op exposes the same data path for
agents. Mirror of the v0.29 salience/anomalies shape (pure data fn + JSON
formatter + human formatter + thin CLI dispatch).

CLI: `gbrain calibration`
  Flags:
    --holder <id>         specific holder (default 'garry')
    --json                machine output for piping
    --regenerate          run calibration_profile phase now
    --undo-wave <ver>     [placeholder — wires in Lane D / T17]
    ab-report             [placeholder — wires in Lane D / T18]

  Human output:
    Calibration profile — holder: garry, source: default
    Generated: <local timestamp>
    [Note: built on 60% graded — partial completion this cycle.]   (when grade_completion < 0.9)
    [Note: voice gate fell back to template (2 attempts).]         (when voice_gate_passed=false)

    Resolved: 12 takes
    Brier:    0.210 (lower is better)
    Accuracy: 60.0%
    Partial:  10.0%

    Pattern statements:
      • You called early-stage tactics well — 8 of 10 held up.

    Active bias tags: over-confident-geography

  Cold-brain fallback message names the exact dream command to run.

MCP: `get_calibration_profile` (scope: read)
  Param: holder?: string (defaults to 'garry')
  Returns: latest CalibrationProfileRow | null

  Source-scoping via sourceScopeOpts(ctx): scalar source-bound clients see
  only their source; federated_read scopes see the union of allowed sources;
  no source filter when neither is set (CLI default path).

  Throws GBrainError('INVALID_HOLDER') on empty/non-string holder so
  remote callers get a structured error instead of a SQL-shape failure.

Architecture:
  getLatestProfile is the pure data fn — engine + opts → CalibrationProfileRow | null.
  Reused by both the CLI and the MCP op. Source-scoped via the standard
  v0.34.1 spread pattern (scalar sourceId vs sourceIds array).

  formatProfileText is pure — null → cold-brain message, populated → full
  printout. Annotates partial-grade rows and voice-gate-fallback rows so
  the operator sees data-quality status inline.

  parseArgs is exported via __testing for unit coverage. Sub-command
  ('ab-report') vs flag distinction is intentional — keeps the surface
  parallel with `gbrain eval cross-modal` etc.

Tests: 21 cases.
  parseArgs (6 cases): empty, --holder, --json, --regenerate, --undo-wave, ab-report.
  getLatestProfile (5 cases): happy, null, scalar source scope, federated array
    scope, no-source-filter default.
  formatProfileText (5 cases): cold-brain, happy, partial-grade note, voice-fallback
    note, published-to-mounts note.
  getCalibrationProfileOp (5 cases): default holder, scalar source scope,
    federated scope union, returns-null-on-unknown-holder, throws on empty holder.

Lane D follow-ups: --undo-wave (T17) and ab-report (T18) print a clear
"lands in Lane D" stderr line + exit 2; the surfaces exist for early
testers, the implementations land next.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* think: --with-calibration + anti-bias prompt rewrite (T8 / E1, D22)

Optional anti-bias rewrite mode for `gbrain think`. When set, the active
calibration profile gets injected per the D22 placement spec (AFTER
retrieval evidence, BEFORE the user's question). The bias filter applies
to QUESTION FRAMING, not evidence interpretation — matches LLM-as-judge
best practice (bias prompts near end of context perform better).

Default behavior unchanged (R1 regression guard): omitting
--with-calibration produces the v0.28-vintage user-message shape with the
question first, then retrieval. Existing think users see no change.

Two user-message shapes in buildThinkUserMessage:

  Default (no calibration):
    Question: X
    <pages>...</pages>
    <takes>...</takes>
    <graph>...</graph>
    Respond with a single JSON object...

  With calibration (D22):
    <pages>...</pages>
    <takes>...</takes>
    <graph>...</graph>
    <calibration holder="garry">
      Track record: Brier 0.210 (lower is better).
      Active patterns:
        - You called early-stage tactics well — 8 of 10 held up.
      Active bias tags: over-confident-geography
    </calibration>
    Question: X
    Respond...

  Calibration block is built by buildCalibrationBlock (exported for the
  E3 contradictions probe to render the same shape).

System prompt extension (withCalibration:true):
  - Names BOTH the user's PRIOR (default reasoning) AND the COUNTER-PRIOR
    from their hedged-domain self.
  - References active bias tags by name when relevant ("this fits the
    over-confident-geography pattern").
  - Does NOT silently substitute the debiased answer. ALWAYS surfaces
    both priors transparently.
  - Adds a "Calibration" section between Conflicts and Gaps in the
    answer body.

RunThinkOpts extension:
  - withCalibration?: boolean — opt-in
  - calibrationHolder?: string — defaults to 'garry'

  When withCalibration=true and no profile exists, runThink falls back to
  baseline behavior + pushes NO_CALIBRATION_PROFILE to warnings (visible
  to the operator). When the calibration fetch fails, CALIBRATION_FETCH_FAILED
  warning surfaces with the underlying error. Either path keeps think working;
  the calibration loop is enhancement, not requirement.

CLI: `gbrain think "<q>" --with-calibration [--calibration-holder <id>]`

Tests: 11 cases.
  buildThinkSystemPrompt (4 cases): R1 regression — default/false/omitted
  → no anti-bias rules; with calibration → adds PRIOR + COUNTER-PRIOR +
  bias-tag reference; preserves existing hard rules.

  buildCalibrationBlock (3 cases): happy path, null brier omitted (not
  "Brier null"), empty patterns + tags still well-formed.

  buildThinkUserMessage (4 cases): R1 regression — without calibration:
  question first; D22 placement — retrieval → calibration → question →
  instruction; graph + calibration ordering; empty retrieval blocks render
  placeholders without breaking shape.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* contradictions: calibration-profile join (T9 / E3)

Cross-references each contradiction finding against the active calibration
profile. When a contradiction's domain matches an active bias tag (e.g.
"over-confident-geography" or "late-on-macro-tech"), the output gains a
one-line bias context explaining which pattern this fits.

Pure functions only — no DB writes, no LLM calls. The probe runner imports
tagFindingWithCalibration() and applies it to each finding before emitting.
When no profile exists or no tags match, the helper returns null and the
runner emits the unchanged finding (regression R2 — contradictions output
is byte-identical to v0.32.6 when no calibration profile is present).

Match heuristic (v0.36.0.0 ship-state):
  Bias tags are kebab-case axis-then-domain slugs ('over-confident-geography').
  computeDomainHint() extracts a domain hint from the finding's slugs +
  holder + verdict text:
    - wiki/companies/... → hiring | market-timing
    - wiki/people/... → founder-behavior
    - macro / geography / tactics / ai segments in slug → matching tag
  First-match-wins for ordering determinism.

  Match is intentionally fuzzy — the v0.32.6 contradictions probe doesn't
  yet carry structured domain metadata. v0.37+ structured-domain-on-takes
  (Hindsight-style enum) tightens this.

Output:
  Returns { bias_tag: string, context: string } | null.
  Context format: "This contradiction fits your active bias pattern
  \"<tag>\" (Brier 0.31). Verdict: contradiction; severity: medium.
  Consider reviewing both sides through the lens of that pattern."

Tests: 13 cases.
  R2 regression (2): null profile → null tag; empty active_bias_tags → null tag.
  computeDomainHint (5): companies / people / macro / geography / unknown
  paths produce expected hints.
  Match path (4): macro→late-on-macro-tech, geography→over-confident-geography,
  mismatch returns null, first-match-wins with multiple candidate tags.
  buildBiasContextString (2): emits tag+verdict+severity+Brier; omits
  Brier when null (no "Brier null" leak).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* calibration: Brier-trend forecast at write time (T10 / E5)

Pure math layer over existing TakesScorecard data. Zero new LLM cost, zero
new schema. Surfaces the user's historical Brier for the take's
(holder, domain) bucket at write time so they see "your historical Brier
in macro takes is 0.31" before committing the take.

Voice-gate-rendered output:
  The user-facing string goes through gateVoice mode='forecast_blurb' via
  templates.ts (already in T6). This module is the pure data layer; the
  template renders the math into the conversational voice.

v0.36.0.0 ship state:
  Bucket dimension is the DOMAIN (slug-prefix). The conviction-weight
  bucket dimension would need a new engine method
  (engine.batchGetTakeBucketStats per F11) — deferred to v0.37+. Until
  then, forecast = historical Brier in this holder's domain.

  resolveDomainPrefix() keeps slug-prefix-looking domain hints
  ('companies/', 'wiki/macro') and falls back to overall for free-form
  hints ('macro tech', 'geography'). Hindsight-style structured domain
  on takes (CDX-11 mitigation TODO) tightens this in v0.37+.

MIN_BUCKET_N = 5:
  Below this sample size, the forecast returns predicted_brier=null with
  insufficient_data=true. Template renders "Forecast unavailable: only N
  resolved takes at this conviction yet" instead of a noisy estimate.

Architecture:
  computeForecast(input) — pure function, takes scorecards already
  fetched; ideal for tests + reuse across batched paths.
  forecastForTake(engine, input) — convenience wrapper, 1-2 engine
  round-trips (no domain → 1; with domain → 2).
  batchForecast(engine, inputs[]) — memoizes per (holder, domainPrefix);
  N inputs collapse to ≤2*unique_holders unique engine calls. Used by
  the propose-queue review flow (50 candidates → 1-2 scorecard fetches).

Tests: 14 cases.
  computeForecast (4): insufficient_data branch, stable forecast,
    overall fallback, MIN_BUCKET_N export.
  resolveDomainPrefix (5): undefined/empty/whitespace → undefined;
    slug-prefix → kept; free-form → undefined.
  forecastForTake (3): 1-call overall, 2-call domain, free-form fallback.
  batchForecast (2): cache collapse for repeat queries; different holders
    do not collapse.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* calibration: gstack-learnings coupling on incorrect resolutions (T11 / E4)

When the grade_takes phase auto-resolves a take as 'incorrect' or 'partial',
optionally write a learning entry to gstack's per-project learnings.jsonl
so other gstack skills (plan-ceo-review, ship, investigate, ...) can pull
it as context when relevant. The brain teaches every other tool about
the user's track record.

Config gate (D5 / CDX-17 mitigation):
  `cycle.grade_takes.write_gstack_learnings` defaults FALSE. External
  users may not have gstack installed; the gstack-learnings binary API
  isn't stable yet. Garry's brain flips it true to opt in.

Quality gate:
  Only 'incorrect' and 'partial' verdicts trigger the write. 'correct'
  resolutions are noise (we expected the take to hold up — no learning).
  'unresolvable' has no canonical column. Defense-in-depth runtime guard
  in writeIncorrectResolution() rejects ineligible qualities with
  reason='quality_not_eligible' so a caller misuse never surfaces a
  malformed learning entry.

Auto-apply only:
  Coupling fires only when grade_takes both auto-applies AND the verdict
  is incorrect/partial AND the config flag is enabled. Manual resolutions
  via `gbrain takes resolve` intentionally DO NOT propagate to gstack —
  manual writes already carry operator intent; the calibration loop is
  the noise-prone path that earns coupling.

Namespace:
  Every entry's key starts with 'gbrain:calibration:v0.36.0.0:'. Lane D
  `gbrain calibration --undo-wave v0.36.0.0` (T17) filters on this prefix
  for the optional gstack-scrub step. First active bias tag suffixes the
  key (e.g. 'take-42:over-confident-geography') so future analysis can
  group learnings by bias pattern.

Architecture:
  buildLearningEntry — pure. Truncates claim at 200 chars + ellipsis;
  emits Pattern: line when activeBiasTags present; defaults confidence
  to 0.8 when caller omits it.

  writeIncorrectResolution — async wrapper. Honors config gate; honors
  quality gate; calls the injected writer (or defaultGstackWriter in
  production). Failures are non-fatal: returns
  { written: false, reason: 'write_failed' | 'binary_missing', error }.
  The grade_takes phase logs to result.warnings and continues — gstack
  coupling failure NEVER aborts a cycle.

  defaultGstackWriter — shells out to gstack-learnings-log binary via
  execFileSync. Throws GBrainError('GSTACK_BINARY_NOT_FOUND') when the
  binary isn't on PATH; writeIncorrectResolution classifies that error
  to reason='binary_missing' so the operator sees the install hint
  instead of a generic write_failed.

  Wired into grade-takes.ts after engine.resolveTake() inside the
  auto-apply block. Only fires when shouldApply=true.

Tests: 14 cases.
  buildLearningEntry (7): canonical shape, partial vs incorrect wording,
  bias-tag suffix, no-tag fallback, claim truncation, default confidence,
  no-reasoning omission.
  writeIncorrectResolution (7): config gate, quality gate, happy path,
  writer-throw graceful degrade, binary-missing classification, async
  writer awaited, partial quality writes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* doctor: 4 calibration checks — abandoned/freshness/drift/voice (T12)

Adds the four calibration doctor checks per the eng-review spec.

abandoned_threads:
  Counts active high-conviction takes (weight >= 0.7) older than 12 months
  that have never been superseded. Signal, not error — always status='ok'
  with a count. The hint sends users to `gbrain calibration` for details.

calibration_freshness:
  Warns when the active profile is older than 7 days (configurable via
  the same env-var pattern other freshness checks use). Cold-brain branch
  (no profile yet) returns ok without scolding. Hint points at
  `gbrain calibration --regenerate`.

grade_confidence_drift (CDX-11 mitigation):
  Surfaces the count of auto-applied grade verdicts. Below 30: returns
  "need 30+ for drift detection". At/above 30: returns "drift math
  arrives in v0.37+". The surface is wired; the actual
  confidence-vs-accuracy correlation math is a v0.37+ follow-up once we
  have 30+ auto-applied verdicts to measure against. Closes the CDX-11
  hole structurally — the operator sees the surface even before the math
  is meaningful.

voice_gate_health:
  Tracks voice gate failure rate over the last 7 days. <30% fail rate →
  ok (template fallback is fine in isolation). >=30% → warn with hint
  to review src/core/calibration/voice-gate.ts rubric. Anchors the
  cross-cutting voice rule observability story.

All four checks return status='warn' with a diagnostic message on
engine errors — non-blocking, never throws. Matches the existing doctor
check pattern (see checkSyncFreshness for prior art).

Wired into runDoctor after checkRerankerHealth (the v0.35 cluster), in
the canonical block 10 slot.

Tests: 15 cases. 4 per check (happy path, alt-status, engine-throw
diagnostic, plus boundary tests for the freshness staleness gate at
exactly 7 days and the grade drift gate at 30 applied verdicts).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* calibration: E7 nudge + 14-day cooldown (T13 / D16 F3)

Real-time pattern surfacing when a newly-committed high-conviction take
matches an active bias pattern. Conversational nudge text via the
templates module; 14-day cooldown per (take_id, nudge_pattern) via
take_nudge_log to prevent the feedback loop where each cycle re-fires
the same nudge on the same take.

Threshold gates (D16 F3):
  - holder match (profile.holder === take.holder)
  - conviction-weight > 0.7 (strict greater than)
  - take's slug-derived domain hint matches an active bias tag
    (takeDomainHint — same heuristic as eval-contradictions/calibration-join.ts
    for cross-surface consistency)

Cooldown gate:
  Before firing, probe take_nudge_log for (take_id, nudge_pattern) rows
  with fired_at >= now() - 14 days. Any hit → silently skip. After firing,
  insert a new row with channel='stderr' so the next 14 days are gated.

Feedback-loop prevention:
  User hedges a take in response to a nudge (e.g. weight 0.85 → 0.65).
  Even though the take's `weight` field changed, the cooldown row for
  the over-confident-geography pattern is still there from the original
  fire — so the next cycle's evaluateAndFireNudge() silently skips. The
  user reset path (gbrain takes nudge --reset N) clears the cooldown to
  re-arm.

Output channel (v0.36.0.0 ship state):
  STDERR only. Schema's `channel` column already supports multi-channel
  (webhook, admin SPA toast); routing those is a v0.37+ follow-up.

Architecture:
  evaluateNudgeRule(take, profile) — pure rule check. Returns
  { matched, reason, matchedTag }. No engine call.
  checkCooldown(engine, takeId, pattern) — engine probe, returns boolean.
  recordNudgeFire(engine, opts) — INSERT into take_nudge_log.
  evaluateAndFireNudge(opts) — full pipeline. Returns NudgeDecision.
  resetNudgeCooldown(engine, takeId) — DELETE...RETURNING for the CLI.

  buildNudgeText delegates to templates.ts nudgeTemplate (D24 mode='nudge'
  voice). v0.36.0.0 ship state uses the template directly; LLM-generated
  nudge text via the voice gate lands in v0.37+ when we have production
  examples to tune from.

Tests: 22 cases.
  takeDomainHint (5): companies/people/macro/geography/unrecognized.
  evaluateNudgeRule (6): no_profile, wrong_holder, conviction-at-threshold-
  is-NOT-eligible (strict >), no matching tag, happy match,
  first-match-wins for multiple candidate tags.
  checkCooldown (3): true on row hit, false on no row, cutoff date param
  verifies the 14-day boundary.
  evaluateAndFireNudge (4): happy fire (text contains hush command +
  matched tag), cooldown silent skip (no INSERT, no stderr), no_profile
  short-circuit, below-conviction short-circuit (no cooldown query fired).
  buildNudgeText (2): hush command shape, conviction value embedded.
  resetNudgeCooldown (2): returns count, idempotent on zero rows.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* calibration: E8 team-brain sharing + D18 cross-brain query semantics (T14)

Cross-brain calibration profile resolution per the D18 4-rule contract.
Pins all four cross-brain leak surfaces in dedicated unit tests so future
mount features can't silently regress this security model.

D18 semantics (committed):

  Rule 1 — LOCAL-FIRST ORDERING.
    Query the local brain first. If a profile exists, return it. Do NOT
    also query mounts (avoids stale-mount-overrides-fresh-local).
    Verified: mountResolver is NOT called when local has a hit.

  Rule 2 — MOUNT FALLBACK.
    Only when local has no profile AND canReadMounts=true, walk the
    mounts in priority order. First match wins. Each mount-side row
    must have published=true to be visible (D15 asymmetric opt-in).

  Rule 3 — CROSS-BRAIN ATTRIBUTION.
    Every returned profile carries source_brain_id + from_mount flag.
    Consumers (E1 think rewrite, E3 contradictions, E7 nudge, E6
    dashboard) MUST surface this via attributionSuffix() so the user
    sees which brain answered.

  Rule 4 — SUBAGENT PROHIBITION.
    canReadMountsForCtx() classifier returns FALSE for subagent loops
    without trusted-workspace allowedSlugPrefixes. Closes the
    OAuth-token-to-cross-brain-leak surface — subagents see ONLY their
    local-brain results regardless of which holder they query.

    Exception: trusted cycle phases (synthesize/patterns) pass
    allowedSlugPrefixes set and ARE allowed to read mounts. Pinned in
    the classifier test.

Architecture:
  queryAcrossBrains(localEngine, opts) — pure orchestrator. Composes
  getLatestProfile() from src/commands/calibration.ts. Mount engine
  access is via opts.mountResolver — production wires this to the
  v0.19+ gbrain mounts subsystem; tests inject a stub returning an
  ordered list of mocked engines. Decouples cross-brain LOGIC from
  multi-engine PLUMBING.

  canReadMountsForCtx(ctx) — pure classifier table. Drives the rule-4
  gate. Production callers compose it from OperationContext.

  attributionSuffix(result) — pure formatter. Emits the "(from mounted
  brain: <id>)" suffix when from_mount=true; empty string when local.
  Mandatory for user-visible cross-brain consumers.

Tests: 15 cases pinned to the 4 D18 rules + 4 supplementary structural
checks.
  D18-1: published=false profile on mount stays hidden.
  D18-2/3: subagent context cannot fall back to mounts (2 cases — null
    on local-empty + canReadMounts=false, local hit still returned).
  D18-4: attribution surfaces source_brain_id (3 cases — mount answer
    flag, local answer flag, attributionSuffix formatter).
  Rule 1 local-first ordering (2 cases — mountResolver NOT called on
    local hit, IS called on local empty).
  Mount priority order (3 cases — first published=true wins, all
    published=false returns null, no mounts configured returns null
    without throwing).
  canReadMountsForCtx classifier (4 cases — local CLI true, MCP
    non-subagent true, subagent without trusted-workspace false,
    subagent WITH trusted-workspace true).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* admin: E6 Calibration tab + D23 server-rendered SVG + TD2 contrast bump (T15)

Adds the v0.36.0.0 admin SPA Calibration tab. Per the design review,
the approved variant-B (Linear calm clarity) layout: single-column flow,
generous whitespace, ONE big sparkline as hero, then patterns, then
domain bars, then abandoned threads.

D23 server-rendered SVG architecture:

  src/core/calibration/svg-renderer.ts — pure functions. data → SVG
  string. No DOM, no React, no chart library dep. Inlines the admin
  design tokens (#0a0a0f bg, #3b82f6 accent, etc.) so the SVG is
  visually consistent with the rest of the admin SPA.

  Four chart renderers:
    - renderBrierTrend({ series }) — sparkline w/ baseline reference
      at 0.25 (always-50% baseline)
    - renderDomainBars({ bars }) — horizontal accuracy bars per domain
    - renderAbandonedThreadsCard(threads) — D30/TD4 'revisit now' link
      per row, points at /admin/calibration/revisit/<takeId>
    - renderPatternStatementsCard(statements) — D29/TD3 clickable
      drill-down links per row, point at /admin/calibration/pattern/<i>

  XSS posture: all caller-controlled strings pass through escapeXml().
  Numeric inputs are .toFixed()-coerced. Admin SPA renders via
  dangerouslySetInnerHTML inside a TrustedSVG wrapper component;
  endpoint is gated by requireAdmin middleware.

  /admin/api/calibration/profile — returns the active profile row as JSON.
  /admin/api/calibration/charts/:type — returns image/svg+xml markup
    for type ∈ {brier-trend, domain-bars, pattern-statements,
                abandoned-threads}. Cache-Control: private, max-age=60.

  brier-trend currently renders a single-point series from the active
  profile (the time-series view across calibration_profiles.generated_at
  history is a v0.37 follow-up once we have multiple snapshots).
  abandoned-threads pulls the top 5 abandoned rows via the same SQL the
  doctor check uses.

CalibrationPage React component (admin/src/pages/Calibration.tsx):
  Fetches profile + 4 charts. Loading / error / cold-brain states all
  handled. Layout includes the audit annotations (partial-grade badge,
  voice-gate-fell-back-to-template badge) per the approved mockup.
  TrustedSVG wrapper isolates the dangerouslySetInnerHTML to the SVG
  surface only.

App.tsx nav: added 'calibration' page route + sidebar nav item, hash
routing extended to support #calibration.

TD2 contrast bump:
  admin/src/index.css --text-muted: #555 → #777. Old value was contrast
  4.0 on the #0a0a0f bg — below WCAG AA 4.5 for body text. New value is
  ~5.5, passes AA. Improvement is global across Dashboard, Agents,
  RequestLog, and the new Calibration tab — single-line CSS change with
  ~10x the impact.

admin/dist/ rebuilt via `bun run build` (vite). 36 modules transformed.

Tests: 19 cases in test/svg-renderer.test.ts.
  escapeXml (1): canonical entities.
  renderBrierTrend (6): empty state, polyline for 2+ points, clamp
  beyond yMax, design tokens inlined, XSS safety on date strings,
  text-anchor end on right label.
  renderDomainBars (4): empty state, label/accuracy/n rendering,
  out-of-range accuracy clamp, XSS safety on labels.
  renderAbandonedThreadsCard (4): empty state, row rendering with
  revisit link, claim truncation at 70 chars, custom revisitHref override.
  renderPatternStatementsCard (4): empty state, anchor count matches
  statement count, XSS safety, custom drillHref override.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* recall: calibration footer formatter for morning pulse (T16)

Pure formatter that turns a CalibrationProfileRow + optional abandoned-
threads list into the conversational block the morning pulse will surface:

  Calibration this quarter:
    Brier 0.18 (solid).
    Right on early-stage tactics, late on macro by 18 months.
    Over-confident on team execution; under-calibrated on regulatory risk.

  Threads you opened and never came back to:
    · AI search platform differentiation         (17 months silent)
    · International expansion playbook           (12 months silent)

Cold-brain branch: returns empty string when no profile or < 5 resolved
takes. Caller decides whether to render the block; cold-brain absence
is the cleanest non-event.

Brier trend note maps the absolute value to conversational copy:
  <= 0.10 → "(strong calibration)"
  <= 0.20 → "(solid)"
  <= 0.25 → "(near baseline)"
  > 0.25  → "(worse than always-50% baseline — review your high-conviction calls)"

  v0.36.0.0 ship state has only the current profile snapshot. The
  "was 0.22 90d ago — improving" comparison shape arrives when we
  accumulate generated_at history across multiple cycles.

R3 regression posture:
  This module is the FORMATTER only. Wiring into `gbrain recall`'s text
  output is intentionally NOT in this commit — runRecall's surface
  stays unchanged. v0.37 wires it under --show-calibration (opt-in
  initially, default-on later). For now the formatter is callable from
  the admin tab + custom CLI scripts that want it.

Architecture:
  buildRecallCalibrationFooter(opts) — pure. opts.profile required,
  opts.abandonedThreads optional, opts.threadColumnWidth defaults to 50.

  Caps at 4 patterns + 5 abandoned threads to keep the footer scannable.
  Truncates long abandoned-thread claim text to fit the column width with
  a trailing ellipsis.

Tests: 14 cases.
  Cold-brain branch (3): null profile, < 5 resolved, zero resolved.
  Happy path (7): header + Brier + patterns, trend note ranges (4
  brackets), null brier omits the Brier line but keeps header, caps at
  4 patterns.
  Abandoned threads (4): omit section when none, emit when present,
  cap at 5, truncate long claim with column-width override.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* calibration: --undo-wave reversal command (T17 / D18 CDX-3)

Implements the undo-wave reversal flow. Every new row written by the
v0.36.0.0 calibration wave carries wave_version='v0.36.0.0' so a precise
revert is possible without touching pre-wave data.

CLI surface (replaces the v0.36.0.0 ship-state placeholder):
  gbrain calibration --undo-wave v0.36.0.0 [--dry-run] [--scrub-gstack] [--json]

Reversal scope (4 steps):

  Step 1 — UNSET takes.resolved_* columns for takes auto-applied by this
  wave. Identifies wave-applied takes via take_grade_cache.applied=true
  + wave_version match. Cross-checks resolved_by='gbrain:grade_takes' to
  ensure we're not un-resolving a take a manual `gbrain takes resolve`
  override has since claimed. Manual resolutions persist; only auto-grade
  resolutions revert.

  Step 1b — Mark take_grade_cache rows applied=false post-undo so the
  audit trail shows they WERE applied but this wave was reverted. The
  CDX-11 confidence-drift check filters on applied=true and gets a
  cleaner sample post-undo.

  Step 2 — DELETE FROM calibration_profiles WHERE wave_version = ?.

  Step 3 — DELETE FROM take_nudge_log WHERE wave_version = ?.

  Step 4 — Optional gstack-learnings-prune via the binary, scoped to the
  GSTACK_LEARNING_NAMESPACE prefix. Opt-in via --scrub-gstack. Best-effort:
  binary-missing or failure logs a warning + suggests the manual command;
  the rest of the undo still succeeded.

Dry-run posture:
  --dry-run computes the counts via SELECT COUNT(*) shapes without
  emitting any UPDATE or DELETE. Same UndoWaveResult shape returned so
  operator sees exactly what would be reverted before committing.

  --dry-run intentionally skips the gstack scrub (filesystem write) too;
  ship-state safety call.

Idempotency:
  Re-running --undo-wave on a brain that's already reverted is a no-op.
  Each query filters on wave_version; no matching rows → zero counts.

Architecture:
  undoWave(engine, opts) — async, returns UndoWaveResult. Pure data
  layer; no stderr writes, no process exits. CLI dispatch in
  src/commands/calibration.ts handles printing.

  v0.36.0.0 ship state runs steps 1-3 sequentially (no transaction).
  Partial reversal is recoverable via re-run since each step is
  idempotent on wave_version match. A future enhancement (v0.37+) can
  wrap in engine.transaction once that surface lands in BrainEngine.

Tests: 8 cases in test/undo-wave.test.ts.
  Dry-run posture (1): counts emitted, NO UPDATE/DELETE SQL fired.
  Happy path (3): all 4 steps execute, resolved_by filter scopes UPDATE
  to wave-applied resolutions, custom resolvedByLabel honored.
  Empty wave (2): zero counts when no matching rows, idempotent re-run.
  Wave-version parameter threading (2): supplied version threads
  through all queries, different wave versions don't collide.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* calibration: A/B harness for think + ab-report (T18 / D19 CDX-18)

Structural answer to CDX-18 (anti-bias rewrite may make advice worse).
We don't have to guess whether calibration helps — we measure.

Architecture:
  runAbTrial(input) — calls thinkRunner TWICE on the same question
  (baseline + --with-calibration), surfaces both answers to a
  preferenceResolver, persists the trial to think_ab_results.

  buildAbReport(engine, { days }) — aggregates the table over the last
  N days (default 30). Computes win counts, ties, neither, and a
  with_calibration_win_rate over DECISIVE trials only (excludes
  neither/tie). Flags calibration_net_negative when n >= 20 AND win
  rate < 45%.

  formatAbReport(report, days) — pretty-prints for stdout; emits the
  calibration_net_negative warning block when triggered.

CLI:
  gbrain calibration ab-report [--days N] [--json]
    Reads the table, prints the breakdown. Replaces the v0.36.0.0
    ship-state placeholder in src/commands/calibration.ts.

  gbrain think --ab "<question>"
    Wires into runAbTrial via the dispatch in src/commands/think.ts —
    follow-up commit. This commit lands the harness layer + schema +
    report surface; the --ab flag itself flips on in a one-line wiring
    commit when the runRecall path is ready.

Schema (migration v72 / think_ab_results):
  source_id, wave_version, ran_at, question, baseline_answer,
  with_calibration_answer, preferred (CHECK in {baseline,
  with_calibration, neither, tie}), model_id, notes.

  CHECK constraint enforces preferred enum. Default wave_version
  'v0.36.0.0' stamped so --undo-wave can scrub these too.

  Index on (source_id, ran_at DESC) supports the report's
  "last N days" query.

  schema.sql + pglite-schema.ts both updated for fresh-install parity.
  schema-embedded.ts regenerated via build:schema.

calibration_net_negative threshold (D19):
  Triggers when:
    - decisive_trials (baseline + with_calibration) >= 20
    - with_calibration_win_rate < 0.45 (NOT <= — exact 45% is OK)

  Small-sample guard (n < 20) prevents the warning from firing on
  early data with sampling noise. Confidence-flat threshold (no Wilson
  CI yet) keeps the math simple; v0.37+ adds CI bounds.

Tests: 12 cases in test/think-ab.test.ts.
  runAbTrial (4): both runner calls fire, preferenceResolver receives
    both answers, INSERT row params shape, throws when thinkRunner
    missing.
  buildAbReport (5): zero trials, aggregation, net_negative trigger at
    n>=20 + win<45%, no trigger at n<20 (small-sample guard), no
    trigger at exact 45% boundary.
  formatAbReport (3): zero-state message, decisive-trials breakdown,
    net_negative warning block.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* calibration: pattern drill-down route + revisit-now CLI (TD3 / D29 + TD4 / D30)

TD3 (D29) — clickable pattern drill-down endpoint:
  GET /admin/api/calibration/pattern/:id (requireAdmin)
  Returns the pattern statement at index `id` plus the top 25 resolved
  takes for the holder, sorted by weight desc. v0.36.0.0 ship-state
  approximation: surfaces broad provenance evidence (top resolved
  takes). v0.37+ stores per-pattern source_take_ids[] on a
  calibration_profile_patterns join table so the drill-down shows the
  EXACT takes that drove the pattern.

  Surfaces a `provenance_note` field in the response so the operator
  sees the v0.36.0.0-vs-v0.37 fidelity boundary inline.

  The admin SPA's renderPatternStatementsCard SVG already emits anchor
  tags pointing at /admin/calibration/pattern/<i> (T15 ship state).
  This route makes those anchors clickable — closes the trust loop that
  was the rationale for D29 ("pattern statements without their evidence
  are dressed-up LLM hallucinations").

TD4 (D30) — `gbrain takes revisit <slug>` editor-open action:
  Adds the `revisit` subcommand to gbrain takes. Opens $EDITOR (falling
  back to vi) on the source markdown file for the slug. Appends a
  `<!-- gbrain:revisit -->` cursor marker at the bottom of the page on
  first invocation so the editor opens with intent visible.

  Reads sync.repo_path from config to locate the brain repo. Refuses to
  proceed with a clear error when the repo isn't configured or the page
  doesn't exist.

  spawnSync with stdio:'inherit' so the editor takes the terminal. Exit
  status surfaced on failure.

  The SVG renderer's revisit-now anchor for each abandoned thread row
  emits /admin/calibration/revisit/<takeId>. A small route handler that
  resolves take_id → page_slug then dispatches `gbrain takes revisit`
  via spawn is a v0.37 follow-up — the CLI command exists now so
  developers can wire it directly.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: DESIGN.md — formalize de facto design tokens (TD1)

Promotes the admin SPA's de facto design tokens (landed v0.26.0) to a
canonical DESIGN.md at the repo root. This is the calibration target
for /plan-design-review and /design-review going forward — when a
question is "does this UI fit the system?", the answer is here.

Captures the system as it stands today:

  Voice (5 surfaces, all routed through gateVoice() with mode-specific
  rubrics): pattern_statement, nudge, forecast_blurb, dashboard_caption,
  morning_pulse. Friend-not-doctor; concrete data over abstract metrics;
  no preachy / clinical / corporate language.

  Color tokens: 10 CSS variables from admin/src/index.css inlined into
  the SVG renderer (src/core/calibration/svg-renderer.ts). Dark theme
  is the only theme — admin is an operator tool. WCAG contrast
  documented per token; TD2's #555 → #777 bump on --text-muted noted.

  Typography: Inter for UI, JetBrains Mono for numbers/slugs/data.
  Type scale (18 / 14 / 13 / 12 / 11) documented as de facto, not yet
  formalized.

  Spacing scale: 4 / 8 / 16 / 24 / 32px. Linear-app density.

  Layout: sidebar 200px, max content 720px (text) / 960px (tables).
  No 3-column feature grids, no icons in colored circles, no
  decorative blobs.

  Charts: server-rendered SVG via pure functions in
  src/core/calibration/svg-renderer.ts. XSS posture documented:
  server-side escapeXml on caller-controlled strings, numeric inputs
  .toFixed()-coerced, admin SPA renders via <TrustedSVG> wrapper.

  Interaction patterns: keyboard nav required (J/K/space/u/q on the
  propose-queue), loading/empty/error states ARE features.

  v0.37+ roadmap: type scale formalization, animation tokens, component
  library extraction. Light mode explicitly NOT planned.

The doc is a living target, not a frozen spec. Major changes route
through /plan-design-review per the existing review chain.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* calibration: synthetic corpus scaffold + privacy CI guard (T19 + T20)

T19 — synthetic corpus scaffold for extract-takes prompt tuning.
  test/fixtures/calibration/extract-takes-corpus/ — 5 representative
  pages across 4 genres (essay, people, companies, meetings, decisions).
  v0.36.0.0 ships a SMALL representative corpus as proof of structure;
  the full 50-page training set + 10-page holdout gets generated by the
  operator via `gbrain calibration build-corpus` (v0.37 follow-up
  subcommand) or by hand with the privacy guard catching violations
  either way.

  Privacy contract per D13': every page is SYNTHETIC. None of the
  names/companies/funds/deals/events refer to anything real. Placeholder
  names per CLAUDE.md: alice-example, charlie-example, acme-example,
  widget-co, fund-a/b/c, acme-seed, widget-series-a, meetings/2026-04-03.

  test/fixtures/calibration/README.md spells out the privacy contract,
  generation flow, and what the corpus is (stable regression set for
  the extract-takes prompt) vs is not (real anything).

T20 — privacy CI guard (CDX-14 mitigation).
  scripts/check-synthetic-corpus-privacy.sh greps the corpus for:
    1. Explicit dollar amounts ($50M, $1.2B etc) — would suggest the
       page memorized a real round size.
    2. Out-of-range year references (informational only for v0.36.0.0;
       deferred to a manual review checklist).
    3. Pages that reference ZERO placeholder names — suggests the page
       might be referring to real entities. Essay-genre fixtures
       exempt (they're anonymized PG-style writing by design).

  Wired into `bun run verify` (CI gate) so contributors can't accidentally
  land a synthetic fixture that leaks real-world specificity. The intent
  is fail-fast on accidental leakage; the operator can update the
  allowlist if a generic dollar amount is intentional.

  Closes CDX-14: 'CC reads real brain pages locally, writes nothing
  still risks privacy if any generated synthetic fixture memorizes
  structure-specific facts. Placeholder names are not enough.'

The corpus shipped here is intentionally small but covers the four
core gbrain page genres (essay, people, companies, meetings/decisions).
The v0.37 corpus-build subcommand will fan out to 50 with the operator
spot-checking + the CI guard enforcing the privacy contract.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test: R1-R5 IRON RULE regression inventory (T21)

Per /plan-eng-review D26 IRON RULE: regressions get added to the test
suite as critical requirements, no AskUserQuestion needed. Pins five
regressions identified during the v0.36.0.0 wave's coverage diagram:

  R1: think baseline UNCHANGED when --with-calibration absent.
      Covered structurally by test/think-with-calibration.test.ts plus
      assertion-pinned in this file (default user message: question
      first, then retrieval; system prompt: no anti-bias section).

  R2: contradictions probe output UNCHANGED when no calibration profile.
      Covered structurally by test/eval-contradictions-calibration-join.test.ts
      plus pinned here (null profile → null tag, byte-identical to v0.32.6).

  R3: takes resolution flow works when grade_takes phase disabled.
      Pinned import-surface coupling: takes-resolution.ts has zero
      dependency on grade_takes module. If a future refactor accidentally
      couples them, this test fails to compile.

  R4: search/list_pages/get_page work identically through new source_id paths.
      Marker test referencing existing v0.34.1 source-isolation suite at
      test/source-isolation-pglite.test.ts. v0.36.0.0 does NOT modify
      those code paths; the existing tests catch any accidental coupling.

  R5: existing search modes (conservative/balanced/tokenmax) unaffected.
      Marker test referencing existing test/search-mode.test.ts. The
      calibration code DOES NOT IMPORT from src/core/search/mode.ts.

Plus an inventory test that confirms all 5 regressions have an
'addressed' status — fail-loud if a future contributor removes a
guard without updating the inventory.

7 tests total. Pure functions, no engine, hermetic.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: v0.36.0.0 CHANGELOG + CLAUDE.md anchors + calibration convention skill

CHANGELOG entry: the user-facing release notes. Leads with the headline
("the brain learns how you tend to be wrong, then argues against your
blind spots on every advice call"), 5 'what you can now do' bullets in
GStack voice, itemized changes by lane, and the 'To take advantage of
v0.36.0.0' upgrade checklist per the CLAUDE.md required-block contract.

CLAUDE.md anchors: new 'v0.36.0.0 Hindsight calibration wave (key files
cluster)' block inserted before the v0.31.1 thin-client section. 23 new
files / extensions annotated with one-paragraph descriptions each,
linking back to the convention skill at skills/conventions/calibration.md
for the agent-facing rules.

skills/conventions/calibration.md: the agent-facing convention skill.
Tells future contributors which calibration touchpoint applies to
their task — voice gate? BaseCyclePhase? source-scope thread? doctor
warning? cross-brain query rules? auto-resolve threshold posture? Test
seam patterns. Bug class to avoid (the v0.34.1 source-isolation leak
shape).

Version trio (per CLAUDE.md mandatory audit):
  VERSION:     0.36.0.0
  package.json: 0.36.0.0
  CHANGELOG:   ## [0.36.0.0] - 2026-05-17

llms.txt + llms-full.txt regenerated via `bun run build:llms` after
the CLAUDE.md edit (per the explicit CLAUDE.md mandate "Any CLAUDE.md
edit MUST be followed by `bun run build:llms`"). The `test/build-llms.test.ts`
guard runs in CI shard 1; the committed bundles are checked against
fresh generator output.

bun run verify is clean. typecheck clean. Privacy CI guard passes
(0 violations across 6 corpus pages). All ready for /ship.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* cycle: wire propose_takes / grade_takes / calibration_profile into runCycle (T-fix)

The three new v0.36.0.0 phases were declared in CyclePhase / ALL_PHASES /
NEEDS_LOCK_PHASES but the runCycle orchestrator never dispatched them.
ALL_PHASES advertised them, gbrain dream --phase propose_takes accepted
them, but `gbrain dream` (default) silently skipped all three.

Adds a single dispatch block between consolidate and embed that:
  - builds an OperationContext on the fly (trusted-workspace caller,
    remote: false, sourceId resolved via the same helper sync uses)
  - dispatches the three phases in the order ALL_PHASES declares
  - records the same skipped-phase shape (no_database) when engine is null

Pinned by test/core/cycle.serial.test.ts "default: all 6 phases run in
order" which was already failing against ALL_PHASES (the test name lags
the actual phase count; left as-is since renaming churns history).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* calibration: expand synthetic corpus + add hand-labeled ground-truth (T19)

Adds 8 new synthetic pages modeled on the genre mix observed in the
real brain (concepts-with-timeline, meeting-notes, daily-journal,
people-pages, essays). Companion .gradeable-claims.json files carry
hand-labeled answer keys — what a tuned propose_takes prompt SHOULD
extract per page. Closes the F1 gate gap from the plan's T19/D19:

  Training corpus (test/fixtures/calibration/extract-takes-corpus/):
    + concept-startup-market-dynamics.md     (10 claims)
    + meeting-2026-04-10-fundraise-fund-a.md (6 claims)
    + daily-2026-04-15.md                    (5 claims)

  Blind holdout (test/fixtures/calibration/holdout/):
    + concept-founder-execution.md           (6 claims, F1 >= 0.80)
    + daily-2026-04-18.md                    (4 claims, F1 >= 0.80)
    + meeting-2026-04-17-hiring-charlie.md   (5 claims, F1 >= 0.80)
    + essay-on-conviction.md                 (7 claims, F1 >= 0.80)
    + people-bob-example.md                  (5 claims, F1 >= 0.80)

Privacy:
  - No real-brain content read into any committed artifact. Pages
    written from scratch using the canonical placeholder set
    (alice-example, charlie-example, bob-example, acme-example,
    widget-co, fund-a/b/c). Real-name grep confirms zero leakage:
    wintermute, garrytan, paul-graham, sam-altman, etc. → 0 hits.
  - scripts/check-synthetic-corpus-privacy.sh passes: 0 violations
    across 14 pages (was 6).

Genre fidelity:
  - concept-with-timeline pages mirror the dated-assertion structure
    real brain uses (verb framing varies: "argues / predicts / I
    think / I bet / strong conviction / moderate conviction").
  - meeting-notes pages carry both prose claims (extracted via
    hedging language) and explicit ## Takes sections.
  - daily-journal pages test probabilistic framing ("75/25 in favor",
    "call it ~0.5") and self-tagged conviction values.
  - essay-on-conviction is the meta-page that names the author's
    own bias patterns — primary signal for calibration_profile.
  - people pages test claim-about-third-party extraction.

Each JSON ground-truth lists per-claim:
  - claim_text + kind (prediction|judgment|bet) + domain
  - conviction (0..1)
  - since_date
  - rationale (why this claim is gradeable + how a tuned prompt
    should infer conviction from the prose)

This is the corpus that gates the T19 prompt-tune iteration:
  - F1 >= 0.85 on training (10+6+5 = 21 claims across 3 pages
    plus the existing 5 fixtures already shipped)
  - F1 >= 0.80 on holdout (27 claims across 5 pages)

Plan reference: ~/.claude/plans/system-instruction-you-are-working-rippling-knuth.md
Privacy gate: scripts/check-synthetic-corpus-privacy.sh (wired into bun run verify).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* calibration: tune propose_takes prompt against synthetic corpus (cat15 F1 0.92+)

The v0.36.1.0 ship state shipped propose_takes with a stub prompt that
the docs flagged as "tune via T19 corpus build before relying on
propose_takes in production." T19's corpus was built in commit 69a71c9d
(14 synthetic pages + 48 hand-labeled claims). The matching gbrain-evals
cat15 runner validates extraction quality against that corpus.

This commit back-ports the tuned prompt validated by cat15's first live
run:

  training avg F1: 0.952  (target 0.85, +10 points)
  holdout  avg F1: 0.922  (target 0.80, +12 points)
  train-holdout gap: 0.03 (well below 0.10 overfitting threshold)
  8/8 probes pass their individual F1 targets

Per-genre F1 floor: 0.80 (people-pages, the hardest genre). Concept-
with-timeline and meeting-notes genres scored at 1.00 on holdout pages.

The tuned prompt design changes vs the stub:
  - Worked example list seeds the "gradeable claim" notion so the model
    doesn't drift into pure-fact extraction.
  - NOT-gradeable list catches the most common over-extraction modes
    (pure facts, direct quotes, restatements).
  - Conviction inference rules anchored to specific hedging language
    so the model produces consistent weight values.
  - kind enum narrowed to 'prediction' | 'judgment' | 'bet' — the v1
    stub's 4-tag enum bled into noise classification on the corpus.

PROPOSE_TAKES_PROMPT_VERSION bumped 'v0.36.1.0-stub' → 'v0.36.1.0-tuned-cat15'.
The bump invalidates the take_proposals idempotency cache so existing
proposal rows stay as audit history but the next cycle re-extracts
against the new prompt — exactly the design contract this version
field is for.

Re-tuning protocol: run cat15 in gbrain-evals against the fixtures
BEFORE bumping the version string. The train-holdout gap should stay
< 0.10. If a future tune drops below the cat15 gate, revert.

Source of evidence:
  - cat15 runner: ~/git/gbrain-evals/eval/runner/cat15-propose-takes.ts
  - Fixture corpus: test/fixtures/calibration/ (this repo, commit 69a71c9d)
  - Live run dumps: ~/git/gbrain-evals/eval/reports/cat15-propose-takes/*.json

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: link cat14/cat15 benchmark report from CHANGELOG + README

Adds the "Validated by published benchmarks" subsection to the v0.36.1.0
CHANGELOG entry and a "Calibration loop" section to the README's
"Receipts on the evals" surface. Both link to the new benchmark report
at gbrain-evals/docs/benchmarks/2026-05-18-brainbench-cat14-cat15-calibration.md.

CHANGELOG: also updates the propose_takes bullet to reflect that the
v0.36.1.0 ship state now includes the tuned 'v0.36.1.0-tuned-cat15'
prompt (back-ported in 04dbab44), not the v1 stub the original entry
described.

README: adds a Calibration loop entry to the receipts table sitting
between source-aware ranking and prompt compression. Frames the cat14
+ cat15 numbers as "first published benchmark for AI memory systems
that reason about user track records" — honest SOTA framing since
Hindsight introduced the concept without quantified evaluation.

llms.txt + llms-full.txt regenerated.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: fix benchmark-report links — gbrain-evals uses main not master

7 links to gbrain-evals/blob/master/docs/benchmarks/ were broken — the
gbrain-evals repo uses 'main' as its default branch, not 'master'.
Surfaced when I checked that the new cat14/cat15 link resolved post-PR-9
merge. Turned out 4 pre-existing links to longmemeval, brainbench-v0.20,
brainbench-cat13b-source-swamp, and comparison-systems were all broken
for the same reason — I just added a fifth by following the same wrong
pattern.

Sweep: gbrain-evals/blob/master/ → gbrain-evals/blob/main/ across both
README.md (5 links) and CHANGELOG.md (2 links).

llms.txt + llms-full.txt regenerated.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-18 19:34:44 -07:00
Garry TanGitHubClaude Opus 4.7
 		4446e9f9d2 v0.35.5.0 fix wave: bootstrap + orphans + think MCP + worktree + walker (#1111) 
* fix(bootstrap): extend probes for files/oauth_clients/sources.archived* + add MIGRATIONS introspection guard

Adds 7 new forward-reference probes to applyForwardReferenceBootstrap on
both engines, closes the column-only forward-ref class via a new
MIGRATIONS-source introspection contract test.

New probes:
- files.source_id + files.page_id (v18 forward refs)
- oauth_clients.source_id + oauth_clients.federated_read (v60+v61+v65)
- sources.archived + archived_at + archive_expires_at (v34 promoted from JSONB)

The sources.archived* columns are the codex-flagged class: they're added
inline in v34's CREATE TABLE definition but `CREATE TABLE IF NOT EXISTS
sources` is a no-op on pre-v34 brains, so downstream visibility filters
(search/list_pages) trip on old brains. needsPagesBootstrap now folds
archive columns into its CREATE TABLE so pre-v0.18 brains get a v34-shape
sources in one go; needsSourcesArchive then only fires on the pre-v34
case (sources exists, archive cols don't).

Closes the structural bug class via test/helpers/extract-added-columns.ts:
reads src/core/migrate.ts as text and extracts every ALTER TABLE ADD
COLUMN. The new contract test asserts every (table, column) pair is
covered by EITHER the bootstrap's ALTER TABLE statements, the bootstrap's
CREATE TABLE definitions, OR the schema blob's CREATE TABLE bodies. The
column-only class (no index, no FK; just an inline CREATE TABLE column
the schema blob can't add to existing tables) is now caught at PR time.

Source-text introspection catches all three migration shapes uniformly:
- top-level `sql:` field
- `sqlFor.postgres` / `sqlFor.pglite` overrides
- handler-body `engine.runMigration(N, \`ALTER TABLE ...\`)` (v34 shape)

Pre-existing parseBaseTableColumns parser bug fixed: now strips `--` line
comments and `/* ... */` blocks before identifying column names. Without
this, a column preceded by a comment was silently dropped. Catches
pages.page_kind and others that were silently uncovered.

13 columns added by migrations but not in PGLITE_SCHEMA_SQL are exempted
with a unified rationale: they have no schema-blob forward reference;
migration handles all upgrade paths cleanly. Refreshing the schema blob
is a separate concern.

Issues closed: #1018 (v60 oauth_clients), #974 (files.source_id/page_id),
#820 (v0.13.0 migration files.page_id cascade); pre-empts the
sources.archived class before any pre-v34 brain trips on it.

Tests:
- 9 cases in test/schema-bootstrap-coverage.test.ts (5 existing + 4 new)
- helper-level unit tests cover SQL shape variants (IF NOT EXISTS,
  quoted identifiers, ALTER TABLE IF EXISTS ONLY, multi-statement)
- planted-bug regression verifies the gate actually catches new uncovered
  columns

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(orphans): filter soft-deleted pages on both candidate and link-source sides

Closes #1021. The v0.26.5 soft-delete invariant requires that
findOrphanPages exclude both:
  1. Candidate pages that are themselves soft-deleted
  2. Inbound links from soft-deleted source pages

Pre-fix, findOrphanPages had no deleted_at filter at all. Soft-deleted
pages with no inbound links were counted as orphans (inflating counts).
Pre-codex-tension-D11, only the candidate-side filter was planned.
Codex C11 caught the second case: a live page that has ONE inbound link
from a soft-deleted source page was hidden from orphan results — the
link still existed in the links table, the EXISTS subquery saw it, the
page looked "linked." Now the inner JOIN on pages enforces
src.deleted_at IS NULL.

Three regression tests pin the contract:
- soft-deleted page with no inbound → NOT orphan
- live page with ONLY inbound link from soft-deleted source → IS orphan
- live page with live inbound → NOT orphan (smoke check that the new
  filters don't break unchanged behavior)

Engine parity: same SQL shape on both Postgres and PGLite engines.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(think): route runThink through gateway.chat adapter (closes #952)

Pre-fix, runThink instantiated `new Anthropic()` directly and read
ANTHROPIC_API_KEY from process.env. Claude Desktop's stdio MCP launch
doesn't inherit shell env, so `gbrain config set anthropic_api_key sk-...`
(writes to ~/.gbrain/config.json) never reached the SDK and every MCP
think call degraded to "no LLM available."

The adapter routes through gateway.chat() — the canonical seam per
CLAUDE.md. Gateway reads the API key from gbrain config OR env, picks
up prompt caching, rate-leases, retry, and the test seam
(__setChatTransportForTests) that v0.31.12 established.

Per plan-eng-review D10 (cross-model tension with codex C7+C8+C9+C10),
four spec points landed:

  1. Drop `new Anthropic()` direct path entirely. Every non-stub LLM
     call from runThink routes through gateway.

  2. Real availability check (NOT a false-positive `getChatModel()`
     truthy). `tryBuildGatewayClient` probes both the recipe (resolveRecipe
     throws AIConfigError on unknown providers) AND the API key (reads
     process.env + loadConfig at the gbrain config layer for parity with
     gateway's own auth resolution). Returns null on miss; runThink takes
     the graceful "no LLM available" early-return preserving the legacy
     NO_ANTHROPIC_API_KEY warning signal.

  3. Model-id normalization. resolveModel returns bare anthropic ids
     (claude-opus-4-7); gateway.chat needs provider:model. Adapter
     auto-prefixes anthropic: when the id is bare. Provider:model strings
     pass through unchanged.

  4. Response-shape conversion. ChatResult → Anthropic.Message via
     chatResultToMessage. mapStopReason translates gateway's
     provider-neutral stop reasons (end / length / tool_calls / refusal /
     content_filter / other) to Anthropic's stop_reason ('end_turn' /
     'max_tokens' / 'tool_use'); refusal/content_filter/other fall through
     to end_turn (no Anthropic equivalent). Usage tokens pass through.

`opts.client` injection preserved (test seam — see ThinkLLMClient).
`opts.stubResponse` preserved (pure-test escape).

Tests:
  - test/think-gateway-adapter.test.ts (9 cases): response shape, stop
    reason mapping, model-id normalization (bare + prefixed), provider
    unknown returns null, ANTHROPIC_API_KEY absent returns null
    (regression for legacy graceful degradation), hasAnthropicKey reads
    process.env correctly. Uses withEnv per the test-isolation contract.
  - test/think-pipeline.serial.test.ts (17 existing cases): unchanged;
    the graceful-degradation case at line 213 still produces the
    NO_ANTHROPIC_API_KEY warning because tryBuildGatewayClient returns
    null when no key is configured, taking the legacy early-return path.

Closes #952.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(sync): distinguish git worktree from submodule via path-segment match (closes #889)

Pre-fix, `manageGitignore` treated every `.git`-as-file as a submodule
and skipped gitignore management. Both submodules AND worktrees use
`.git` as a file (not a directory), so the legacy
`statSync.isFile()` check couldn't discriminate. Worktrees got
misclassified as submodules and their .gitignore wasn't managed.

Per plan-eng-review D4 (chose path-segment match over absolute-vs-
relative path heuristic): the gitdir path contains:
  - `/modules/<name>` for submodules (skip — managed by parent repo)
  - `/worktrees/<name>` for worktrees (MANAGE — first-class repo)

Both are documented Git internal layouts, stable across all 4
{relative, absolute} × {modules, worktrees} combinations including the
absorbed-submodule edge case from `git submodule absorbgitdirs` (where
the submodule's gitdir flips to an absolute path).

Malformed `.git` file (no `gitdir:` prefix, IO error) → MANAGE, preserving
the pre-#889 catch{} fail-closed-toward-managing semantics.

Tests (5 new + 1 regression renamed):
  - REGRESSION: submodule relative gitdir/modules/ → skip (D49 contract)
  - absorbed submodule absolute gitdir/modules/ → skip (edge case)
  - CRITICAL: worktree absolute gitdir/worktrees/ → MANAGE (closes #889)
  - worktree relative gitdir/worktrees/ → MANAGE
  - malformed .git file → MANAGE (preserves catch behavior)
  - regular .git directory → MANAGE (existing smoke)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(walkers): pruneDir helper + descent-time exclusion + transcript predicate (closes #923, #202)

Per plan-eng-review D12 (cross-model tension with codex C12+C13), three
structural changes:

1. Extract `pruneDir(name)` helper in src/core/sync.ts. Returns false for
   directory names walkers must NEVER descend into: `node_modules` (latent
   bug — no leading dot), dot-prefix dirs (`.git`, `.obsidian`, `.raw`,
   `.cache`, etc.), `ops`, and `*.raw` sidecar dirs (gbrain convention —
   `people/pedro.raw/` holds raw source for pedro.md). Walkers consult it
   at descent time BEFORE recursion, saving the IO cost of walking entire
   vendor / hidden / sidecar subtrees only to filter them at file-emit time.

2. `isSyncable` itself gains the same exclusion set (via pruneDir on each
   path segment). Closes the latent bug where node_modules markdown files
   slipped through: `node_modules/some-pkg/README.md` returned true pre-fix
   because the legacy dot-prefix check only blocked `.node_modules` (with
   a leading dot), not the actual `node_modules`. CRITICAL regression test
   in test/sync.test.ts pins the contract per IRON RULE.

3. Two walkers rewritten to use pruneDir at descent + per-walker file
   predicate at emit:
   - `walkMarkdownFiles` (src/commands/extract.ts): pruneDir + isSyncable
     ({strategy:'markdown'}). Pre-fix this walker had ONLY an ad-hoc
     dot-prefix exclusion and didn't call isSyncable at all — descended
     into node_modules, emitted markdown files from there, ignored README/
     ops/.raw filters.
   - `listTextFiles` (src/core/cycle/transcript-discovery.ts): pruneDir +
     own .txt/.md predicate. DOES NOT use isSyncable({strategy:'markdown'})
     because transcripts accept .txt and don't share markdown sync's
     README/ops exclusions (codex C12). Also made RECURSIVE — pre-fix
     it walked only the top dir, so transcripts in `corpus/2026/` were
     invisible (codex C14 — descent-time pruning is the right shape but
     the test would have passed vacuously on a non-recursive walker).

Verified blast radius before adding node_modules: every existing
isSyncable caller (sync.ts:558-561 sync filter, frontmatter.ts:264 validate,
brain-writer.ts:305 reverse-write, import.ts:454 import filter) wants
node_modules excluded — this is a latent-bug fix, not a behavior change
for any legitimate caller.

Tests:
- 7 new isSyncable cases including the node_modules CRITICAL regression
- 6 new pruneDir cases (node_modules, dot-prefix, ops, *.raw, content
  dirs that should pass, empty-string default)
- Existing extract.test.ts + extract-fs.test.ts unchanged and passing

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs(todos): file v0.36.x follow-ups for runThink rewrite + Supabase bootstrap parity

Two follow-up TODOs filed during the v0.36 dreamy-thompson wave:

1. runThink full rewrite (D5+D7 from plan-eng-review): drop the
   ThinkLLMClient indirection now that v0.36 routes through gateway.chat.
   12+ tests need migration to __setChatTransportForTests. Blocked by
   this wave landing.

2. Supabase parity test for applyForwardReferenceBootstrap (codex C6
   residual): real Docker Postgres E2E catches schema correctness but
   not Supabase pooler/direct-pool routing. The probe uses this.sql but
   PostgresEngine.initSchema chooses a DDL connection; the divergence
   has caused multiple historical wedges (#699, #820 lineage).

Both entries include full context per the CLAUDE.md TODOS-format spec
(what, why, pros, cons, blocked-by, plan reference).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(bootstrap): thread DDL connection through applyForwardReferenceBootstrap

Codex adversarial review during /ship caught a P1: initSchema selected a
DDL connection, took pg_advisory_lock(42) on it, but
applyForwardReferenceBootstrap used `this.sql` (the instance pool) inside.
Bootstrap probes ran outside the lock scope on a different connection.

Failure mode: two concurrent gbrain instances could BOTH enter the
bootstrap block on Supabase transaction-pooler setups because the
advisory lock was held on a different connection than the one running
ALTER TABLE. The pooler's statement_timeout could also kill the probes
mid-flight without affecting the lock-holder, leaving an inconsistent
schema state.

Fix: applyForwardReferenceBootstrap now accepts an optional connection
parameter. initSchema passes the DDL conn (the one holding the lock).
this.sql remains the fallback for any unit-test path that calls bootstrap
directly. PGLite engine doesn't need this change — single connection,
no pooler.

This was pre-existing (every prior probe used this.sql), but the v0.36
wave is explicitly about fixing the Supabase upgrade-wedge class. Codex's
position was correct: don't ship the wave with the underlying connection
mismatch still there. The Supabase parity TEST FIXTURE follow-up remains
on TODOS.md (test infra needed to PROVE the fix works under real pooler
topology), but the bug itself is closed.

15/15 bootstrap tests pass. Typecheck clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v0.35.5.0)

Six-correctness-fix wave: bootstrap forward-ref class (4 issues + 1 pre-empt),
orphans soft-delete leak (both sides), runThink → gateway.chat adapter,
git worktree vs submodule discriminator, walker pruneDir + descent-time
exclusion, plus a Codex-P1 catch during /ship that threaded the DDL
connection through applyForwardReferenceBootstrap.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: update CLAUDE.md for v0.35.5.0 backend correctness wave

Fold v0.35.5.0 file-level annotations into CLAUDE.md:
- postgres-engine.ts + pglite-engine.ts: 7 new applyForwardReferenceBootstrap
  probes (files.source_id/page_id, oauth_clients.source_id/federated_read,
  sources.archived/archived_at/archive_expires_at) + DDL connection threading
- test/schema-bootstrap-coverage.test.ts: new MIGRATIONS-source introspection
  guard + parseBaseTableColumns comment-stripping fix
- src/core/sync.ts: new pruneDir helper + manageGitignore worktree
  discriminator
- src/core/think/index.ts (new entry): runThink gateway adapter for MCP
  stdio key resolution
- src/core/operations.ts (new entry): findOrphanPages soft-delete filter

Regenerate llms-full.txt via bun run build:llms.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-17 14:02:45 -07:00
Garry TanGitHubClaude Opus 4.7garrytan-agents
 		29961811a4 v0.31.12 fix: canonical Anthropic model IDs + tier routing surface + gbrain models CLI (#844) 
* fix: canonical Anthropic model IDs + reverse alias + Opus 4.7 pricing

Replace claude-sonnet-4-6-20250929 with claude-sonnet-4-6 everywhere it
appears as a model ID. Starting with Claude 4.6, Anthropic API IDs are
dateless and pinned — the date suffix was carried forward from Sonnet 4.5
by mistake, producing a phantom ID that 404'd on every call.

Production impact in v0.31.6: isAvailable("chat") returned false in every
code path that loaded the recipe's model list, and extractFactsFromTurn
silently returned []. The headline real-time facts extraction feature
was a no-op on the happy path.

- gateway.ts:46 DEFAULT_CHAT_MODEL -> anthropic:claude-sonnet-4-6
- recipes/anthropic.ts: chat + expansion model lists drop date suffix;
  remove wrong-direction alias (claude-sonnet-4-6 -> -20250929);
  add reverse alias (-20250929 -> claude-sonnet-4-6) so stale user
  configs in models.dream.synthesize etc. keep working
- facts/extract.ts: routes through resolveModel; both fallbacks corrected
- anthropic-pricing.ts: Opus 4.7 corrected $15/$75 -> $5/$25 per
  Anthropic docs (the $15/$75 was Opus 4.0 pricing)
- cross-modal-eval/runner.ts: PRICING now reads from ANTHROPIC_PRICING
  for Anthropic models instead of duplicating the map (single source of
  truth — fixes the drift trap that motivated this whole patch)

Tests: cherry-pick PR #830's test/anthropic-model-ids.test.ts verbatim
(6 recipe-shape guardrails). Update gateway-chat tests to assert reverse
alias resolves correctly. Update budget-meter test for new Opus pricing.

Co-Authored-By: garrytan-agents <garrytan-agents@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat: model tier system + recipe-models merge + async reconfigure hook

Add 4-tier model routing (utility/reasoning/deep/subagent) so users can
swap defaults with one config key. Each tier maps to a class of work;
override globally via models.default or per-tier via models.tier.<tier>.

Codex flagged three real architecture issues in the v0.31.12 plan review;
this commit addresses each.

F3 — sync/async timing of configureGateway:
  - buildGatewayConfig stays synchronous (pre-engine-connect callers
    keep working)
  - New reconfigureGatewayWithEngine(engine) async function re-resolves
    expansion + chat defaults through resolveModel after engine.connect()
  - cli.ts wires the re-stamp into the post-connect path

F4/F5 — softening assertTouchpoint was too broad:
  - Earlier plan was to flip native-recipe validation from throw to warn,
    affecting gateway.chat AND gateway.expand AND gateway.embed
  - Instead: per-gateway-instance recipe-models merge. assertTouchpoint
    gets an optional extendedModels Set; when the user opted into a model
    via config, it bypasses the throw. Source-code typos still fail fast.
  - Existing contract test (test/ai/gateway-chat.test.ts:106) preserved

Tier defaults are TIER_DEFAULTS in model-config.ts. Resolution chain
inserts at step 5 (between models.default and env var). Each existing
resolveModel call site gains a tier: arg — think (deep), cycle/synthesize
(reasoning + utility for verdict), patterns/drift (reasoning), auto-think
(deep), facts/extract (reasoning).

Plus 10 new tests pinning tier precedence, subagent-tier fallback when
models.default is non-Anthropic, and the F6 alias-chain conflict case.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat: subagent runtime enforcement for non-Anthropic models (3 layers)

The subagent loop uses Anthropic's Messages API with prompt caching on
system + tools. OpenAI/Google have different shapes. Setting
models.default = openai:gpt-5.5 and routing the subagent there silently
breaks the loop.

Codex F1+F2+F13 in the v0.31.12 plan review pointed out that "warn at
doctor" wasn't enough — handlers/subagent.ts:148 still did
`const model = data.model ?? DEFAULT_MODEL` and called Anthropic directly,
so a job submitted with data.model = openai:gpt-5.5 bypassed any tier
logic and failed at runtime with a confusing provider error.

Three layers of enforcement, defense in depth:

Layer 1 (queue.ts:add) — submit-time guard. When name === 'subagent'
and data.model is set, validate the provider. Non-Anthropic rejects
before the job enters the queue.

Layer 2 (handlers/subagent.ts) — tier-resolution fallback. The handler
routes through resolveModel({ tier: 'subagent' }). If the chain resolves
to a non-Anthropic provider (via models.default or models.tier.subagent),
the resolver warns + falls back to TIER_DEFAULTS.subagent
(claude-sonnet-4-6).

Layer 3 (doctor.ts:checkSubagentProvider) — surfacing layer. Warns when
models.tier.subagent or models.default is explicitly set to a
non-Anthropic provider, with a paste-ready fix command. Lets users see
config drift before submitting a job.

Tests: 3 new cases in test/agent-cli.test.ts asserting the queue-level
guard rejects non-Anthropic data.model. Existing test/subagent-handler
suite still passes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat: gbrain models CLI + doctor probe + silent-no-op regression test

New gbrain models CLI gives the agent and user visibility into routing.
Read mode prints the tier table, current overrides, per-task config,
and aliases with source-of-truth attribution per row. Doctor subcommand
fires a 1-token probe to each configured chat/expansion model and
classifies failures (model_not_found / auth / rate_limit / network /
unknown) so config-time invalid IDs surface without waiting for a
production call that silently degrades.

Per Codex F11 — no specific dollar cost claim in either the help text
or the CHANGELOG (providers have minimum-output billing and prompt-cache
rounding that vary). Probe is opt-in (gbrain doctor --probe-models),
never auto-runs. --skip=<provider> narrows the matrix for cost-sensitive
operators.

Per Codex F7+F8+F15 (the structural regression gap): new
test/facts-extract-silent-no-op.test.ts is THE regression test for the
bug class that motivated v0.31.12. Five cases including the smoking-gun:
when chat IS available, extractFactsFromTurn MUST actually call the chat
transport, not silently return []. Uses the gateway's
__setChatTransportForTests seam so it runs in every shard with no API key.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v0.31.12)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: document v0.31.12 model tier system + gbrain models CLI

Add CLAUDE.md Key Files annotations for the v0.31.12 work:
src/core/model-config.ts (tier system + isAnthropicProvider + TIER_DEFAULTS),
src/core/ai/model-resolver.ts (assertTouchpoint extendedModels arg),
src/core/ai/gateway.ts (reconfigureGatewayWithEngine + extended-models registry),
src/core/minions/queue.ts (subagent submit-time guard, layer 1 of 3),
src/commands/models.ts (new gbrain models CLI + doctor probe),
src/commands/doctor.ts (subagent_provider check, layer 3 of 3),
src/core/ai/recipes/anthropic.ts (canonical model IDs + reverse alias),
src/core/anthropic-pricing.ts (Opus 4.7 corrected to \$5/\$25).

Add CLAUDE.md commands section for gbrain models + gbrain models doctor
+ power-user config recipes. Add README.md command-table rows for the
same. Regenerate llms-full.txt so the bundled docs stay in sync.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: scrub --probe-models reference (flag not actually wired)

The v0.31.12 CHANGELOG and skills/conventions/model-routing.md both
referenced `gbrain doctor --probe-models` as an integrated probe entry
point. The flag was never implemented — only `gbrain models doctor`
landed as the probe surface. Caught by /document-release subagent.

Drop the references rather than wire an untested flag at the last minute.
The probe is reachable via `gbrain models doctor`; users who want it
in doctor's output run that command separately.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: garrytan-agents <garrytan-agents@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-10 20:06:31 -07:00
Garry TanGitHubClaude Opus 4.7
 		bca993e09f v0.28.12 feat: LongMemEval benchmark harness (#606) 
* v0.28 schema: takes + synthesis_evidence (v31) + access_tokens.permissions (v32)

Migration v31 adds the takes table (typed/weighted/attributed claims) and
synthesis_evidence (provenance for `gbrain think` outputs). Page-scoped via
page_id FK (slug isn't unique alone in v0.18+ multi-source). HNSW partial
index on embedding for active rows. ON DELETE CASCADE on synthesis_evidence
so deleting a source take cascades the provenance row.

Migration v32 adds access_tokens.permissions JSONB with safe-default
backfill (`{"takes_holders":["world"]}`). Default keeps non-world holders
hidden from MCP-bound tokens until the operator explicitly grants access
via the v0.28 auth permissions CLI.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 engine: addTakesBatch, listTakes, searchTakes/Vector, supersede, resolve, synthesis_evidence

Extends BrainEngine with the takes domain object. Both engines implement the
same surface; PGLite uses manual `$N` placeholders, Postgres uses postgres-js
unnest() — same shape as addLinksBatch and addTimelineEntriesBatch.

Methods:
- addTakesBatch (upsert via ON CONFLICT (page_id, row_num) DO UPDATE)
- listTakes (filter by holder/kind/active/resolved, takesHoldersAllowList
  for MCP-bound calls, sortBy weight/since_date/created_at)
- searchTakes / searchTakesVector (pg_trgm + cosine; honor allow-list)
- countStaleTakes / listStaleTakes (mirror countStaleChunks pattern;
  embedding column intentionally omitted from listStale payload)
- updateTake (mutable fields only; throws TAKE_ROW_NOT_FOUND)
- supersedeTake (transactional: insert new at next row_num, mark old
  active=false, set superseded_by; throws TAKE_RESOLVED_IMMUTABLE on
  resolved bets)
- resolveTake (sets resolved_*; throws TAKE_ALREADY_RESOLVED on re-resolve;
  resolution is immutable per Codex P1 #13 fold)
- addSynthesisEvidence (provenance persist; ON CONFLICT DO NOTHING)
- getTakeEmbeddings (parallel to getEmbeddingsByChunkIds)

Types live in src/core/engine.ts adjacent to LinkBatchInput. Page-scoped
via page_id (slug not unique in v0.18+ multi-source). PageType gains
'synthesis'. takeRowToTake mapper in utils.ts handles Date → ISO string
normalization.

Tests: test/takes-engine.test.ts — 16 cases against PGLite covering
upsert/list/filter/search happy paths, takesHoldersAllowList isolation,
the four invariant errors (TAKE_ROW_NOT_FOUND, TAKES_WEIGHT_CLAMPED,
TAKE_RESOLVED_IMMUTABLE, TAKE_ALREADY_RESOLVED), supersede flow, resolve
metadata round-trip, FK CASCADE on synthesis_evidence when source take
deletes. All pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 model-config: unified resolveModel with 6-tier precedence + alias resolution

Replaces every hardcoded `claude-*-X` and per-phase `dream.<phase>.model`
config key with a single resolver. Hierarchy:

  1. CLI flag (--model)
  2. New-key config (e.g. models.dream.synthesize)
  3. Old-key config (deprecated dream.synthesize.model, dream.patterns.model)
     — read with stderr deprecation warning, one-per-process
  4. Global default (models.default)
  5. Env var (GBRAIN_MODEL or caller-supplied)
  6. Hardcoded fallback

Aliases (`opus`, `sonnet`, `haiku`, `gemini`, `gpt`) resolve at the end so
any tier can use a short name. User-defined `models.aliases.<name>` config
overrides built-ins. Cycle-safe (depth 2 break). Unknown alias passes
through unchanged so users can pass full provider IDs without registering.

When new-key + old-key are BOTH set (Codex P1 #11 fix), new-key wins and
stderr warns "deprecated config X ignored; Y is set and wins". When only
old-key is set, it's honored with a softer "rename to Y before v0.30"
warning. Both warnings emit once per (key, process) — a Set memo prevents
log spam in long-running daemons.

Migrated call sites: synthesize.ts (model + verdictModel), patterns.ts
(model). subagent.ts and search/expansion.ts to be migrated later in v0.28
(staying compatible until then).

Tests: test/model-config.test.ts — 11 cases pinning the 6-tier ordering,
alias resolution + cycle break, deprecated-key warning emit-once, and
unknown-alias pass-through. All pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 takes-fence: parser/renderer/upserter + chunker strip (privacy P0 fix)

src/core/takes-fence.ts — pure functions for the fenced markdown surface:
- parseTakesFence(body) — extracts ParsedTake[] from `<!--- gbrain:takes:begin/end -->`
  blocks. Strict on canonical form, lenient on hand-edits with warnings
  (TAKES_FENCE_UNBALANCED, TAKES_TABLE_MALFORMED, TAKES_ROW_NUM_COLLISION).
  Strikethrough `~~claim~~` → active=false; date ranges `since → until`
  split into sinceDate/untilDate.
- renderTakesFence(takes) — round-trip safe with parseTakesFence.
- upsertTakeRow(body, row) — append-only per CEO-D6 + eng-D9. Creates a
  fresh `## Takes` section if no fence present. row_num is monotonic
  (max + 1, never gap-filled — keeps cross-page refs and synthesis_evidence
  stable forever).
- supersedeRow(body, oldRow, replacement) — strikes through old row's claim
  AND appends the new row at end. Both rows preserved in markdown for
  git-blame archaeology.
- stripTakesFence(body) — removes the fenced block entirely. Used by the
  chunker so takes content lives ONLY in the takes table.

Codex P0 #3 fix: src/core/chunkers/recursive.ts now calls stripTakesFence()
before computing chunk boundaries. Without this, page chunks would contain
the rendered takes table and the per-token MCP allow-list would be
bypassed at the index layer (token bound to takes_holders=['world'] would
see garry's hunches via page hits). Doctor's takes_fence_chunk_leak check
(plan-side) asserts no chunk contains the begin marker.

Tests: 15 cases covering canonical parse, strikethrough, date range, fence
unbalanced detection, malformed-row skip + warning, row_num collision
detection, round-trip render, append-only upsert into existing fence,
fresh-section creation, monotonic row_num under hand-edit gaps, supersede
flow, stripTakesFence verifying takes content removed AND surrounding
prose preserved. Existing chunker tests still pass (15 + 15 = 30).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 page-lock: PID-liveness file lock for atomic markdown read-modify-write

src/core/page-lock.ts — per-page file lock at
~/.gbrain/page-locks/<sha256-of-slug>.lock so two concurrent `gbrain takes
add` calls or `takes seed --refresh` from autopilot can't race on the
same `<slug>.md` read-modify-write. Eng-review fold: reuses the v0.17
cycle.lock pattern (mtime + PID liveness) but per-slug.

Differences from cycle.ts's lock:
- SHA-256 of slug for safe filenames (slashes, unicode, etc.)
- Same-pid + fresh mtime = LIVE (cycle.ts assumes one lock per process and
  reclaims same-pid; page-lock allows concurrent locks for DIFFERENT slugs
  in one process). mtime expiry still rescues post-crash leftovers.
- 5-min TTL (vs cycle's 30 min — page edits are short)
- `withPageLock(slug, fn)` convenience wrapper with default 30s timeout

API:
- acquirePageLock(slug, opts) → handle | null (poll-with-timeout)
- handle.refresh() / handle.release() (idempotent — only releases if pid matches)
- withPageLock(slug, fn, opts) — acquire + run + release-in-finally

Tests: 10 cases — fresh acquire, live holder returns null, stale-mtime
reclaim, dead-PID reclaim, refresh updates timestamp, foreign-pid release
is no-op, withPageLock callback runs and releases on success/failure,
timeout-throws when held, SHA-256 filename safety for slashes/unicode.
All pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 extract-takes: dual-path phase (fs|db) + since/until_date as TEXT

src/core/cycle/extract-takes.ts — new phase that materializes the takes
table from fenced markdown blocks. Two paths mirror src/commands/extract.ts:

- extractTakesFromFs: walk *.md under repoPath, parse fences, batch upsert
- extractTakesFromDb: iterate engine.getAllSlugs(), parse each page's
  compiled_truth+timeline, batch upsert (mutation-immune snapshot iteration)

Single dispatcher extractTakes(opts) routes by source. Honors:
- slugs filter for incremental re-extract (pipes from sync→extract)
- dryRun: count would-be upserts, write nothing
- rebuild: DELETE FROM takes WHERE page_id = $1 before re-insert (clean
  slate when markdown is canonical and DB has drifted)

Schema fix: since_date/until_date were DATE in the original v31 migration.
Spec uses partial dates ('2017-01', '2026-04-29 → 2026-06') that Postgres
DATE rejects. Changed to TEXT in both the Postgres and PGLite blocks so
parser-rendered ranges round-trip cleanly. Loses the ability to do
date-range arithmetic in SQL, but date math on opinion timelines is
out of scope for v0.28 anyway. utils.ts dateOrNull now annotated as
v0.28 TEXT-aware.

Migration v31 has not been deployed yet (this branch is the v0.28 release
candidate), so the type swap is free. No data migration needed.

Tests: test/extract-takes.test.ts — 5 cases against PGLite covering full
walk + fence-skip on no-fence pages, takes-table populated post-extract,
incremental slugs filter, dry-run no-write, rebuild=true clears + re-inserts
ad-hoc rows. test/takes-engine.test.ts (16), test/takes-fence.test.ts (15)
all still pass — 36/36 takes tests green.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 takes CLI: list, search, add, update, supersede, resolve

src/commands/takes.ts — surfaces the engine methods + takes-fence library
through a single `gbrain takes <subcommand>` entrypoint:

  takes <slug>                          list with filters + sort
  takes search "<query>"                pg_trgm keyword search across all takes
  takes add <slug> --claim ... ...      append (markdown + DB, atomic via lock)
  takes update <slug> --row N ...       mutable-fields update (markdown + DB)
  takes supersede <slug> --row N ...    strikethrough old + append new
  takes resolve <slug> --row N --outcome  record bet resolution (immutable)

Markdown is canonical. Every mutate command:
  1. acquires the per-page file lock (withPageLock)
  2. re-reads the .md file
  3. applies the edit via takes-fence (upsertTakeRow / supersedeRow)
  4. writes the .md file back
  5. mirrors to the DB via the engine method
  6. releases the lock (auto via finally)

Resolve currently writes only to DB — surfacing resolved_* in the markdown
table is deferred to v0.29 (the takes-fence renderer's column set is
fixed at # | claim | kind | who | weight | since | source per spec).

Wired into src/cli.ts dispatch + CLI_ONLY allowlist. Help text follows the
project convention (orphans/embed/extract pattern). --dir flag overrides
sync.repo_path config when working outside the configured brain.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 MCP + auth: takes_list / takes_search / think ops + per-token allow-list

OperationContext gains takesHoldersAllowList — server-side filter for
takes.holder field threaded from access_tokens.permissions through dispatch
into the engine SQL. Closes Codex P0 #3 at the dispatch layer (chunker
strip already closed the page-content side in the previous commit).

src/core/operations.ts — three new ops:
- takes_list: lists takes with holder/kind/active/resolved filters; honors
  ctx.takesHoldersAllowList for MCP-bound calls
- takes_search: pg_trgm keyword search; honors allow-list
- think: op surface registered (returns not_implemented envelope until
  Lane D's pipeline lands). Remote callers cannot save/take per Codex P1 #7.

src/mcp/dispatch.ts — DispatchOpts.takesHoldersAllowList threads into
buildOperationContext.

src/mcp/http-transport.ts — validateToken now reads
access_tokens.permissions.takes_holders, defaults to ['world'] when the
column is absent or malformed (default-deny on private hunches).
auth.takesHoldersAllowList passed to dispatchToolCall.

src/mcp/server.ts (stdio) — defaults to takesHoldersAllowList: ['world']
since stdio has no per-token auth. Operators wanting full visibility use
`gbrain call <op>` directly (sets remote=false).

src/commands/auth.ts — `gbrain auth create <name> --takes-holders w,g,b`
flag persists the per-token list; new `auth permissions <name>
set-takes-holders <list>` updates an existing token.

Tests: test/takes-mcp-allowlist.test.ts — 8 cases against PGLite proving
the threading: local-CLI sees all holders, ['world'] returns only public,
['world','garry'] returns 2/3, no-overlap returns empty (no fallback),
search honors allow-list, remote save/take on think rejected with
not_implemented envelope.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28.0: ship-prep — VERSION, CHANGELOG, migration orchestrator, skill

Closes the v0.28 ship-prep cycle. Bumps VERSION + package.json + bun.lock
to 0.28.0. v0_28_0 migration orchestrator runs three idempotent phases on
upgrade:

- Schema verify: asserts schema_version >= 32 (migrations v31 + v32 already
  applied by the schema runner during gbrain upgrade); fails clean if not.
- Backfill takes: inline runs `extractTakes(engine, { source: 'db' })` so
  any pre-existing fenced takes tables in markdown populate the takes
  index. Idempotent; ON CONFLICT DO UPDATE keeps the table in sync.
- Re-chunk TODO: queues a pending-host-work entry asking the host agent
  to re-import pages with takes content so the v0.28 chunker-strip rule
  (Codex P0 #3 fix) applies retroactively. Pages imported under v0.28+
  already have takes content stripped from chunks at index time; this
  TODO catches up legacy pages.

skills/migrations/v0.28.0.md — agent-readable upgrade guide. Walks
through doctor verification, deprecated-key migration, MCP token
visibility configuration, and a "try the takes layer" smoke test.

CHANGELOG.md — v0.28.0 release-summary in the GStack voice (no AI
vocabulary, no em dashes, real numbers from git diff stat) + the
mandatory "To take advantage of v0.28.0" block + itemized changes by
subsystem (schema, engine, markdown surface, model config, MCP+auth,
CLI, tests, accepted risks).

Final test sweep: 65/65 v0.28 tests pass across 6 files. typecheck clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 think pipeline: gather → sanitize → synthesize → cite-render → CLI

src/core/think/sanitize.ts — prompt-injection defense for take claims:
14 jailbreak patterns (ignore-prior, role-jailbreak, close-take tag,
DAN, system-prompt overrides, eval-shell hooks) plus structural framing
(takes wrapped in <take id="..."> tags the model is told to treat as
DATA). Length-cap at 500 chars. Renders evidence blocks for the prompt.

src/core/think/prompt.ts — system prompt + structured-output schema.
Hard rules: cite every claim, mark hunches/low-weight explicitly,
surface conflicts (never silently pick), surface gaps. JSON schema
with answer + citations[] + gaps[]. Prompt adapts to anchor / time
window / save flag.

src/core/think/cite-render.ts — structured citations + regex fallback
(Codex P1 #4 fold). normalizeStructuredCitations validates the model's
structured output; parseInlineCitations is the body-scan fallback when
the model omits the structured field. resolveCitations dispatches and
records CITATIONS_REGEX_FALLBACK warning when used.

src/core/think/gather.ts — 4-stream parallel retrieval:
  1. hybridSearch (pages, existing primitive)
  2. searchTakes (keyword, pg_trgm)
  3. searchTakesVector (vector, when embedQuestion fn supplied)
  4. traversePaths (graph, when --anchor set)
RRF fusion (k=60). Each stream wrapped in try/catch — partial gather
beats no synthesis. Honors takesHoldersAllowList for MCP-bound calls.

src/core/think/index.ts — runThink orchestrator + persistSynthesis:
INTENT (regex classify) → GATHER → render evidence blocks → resolveModel
('models.think' → 'models.default' → GBRAIN_MODEL → opus) → LLM call
(injectable client) → JSON parse with code-fence + fallback strip →
resolveCitations → ThinkResult. persistSynthesis writes a synthesis
page + synthesis_evidence rows (page_id resolved per slug; page-level
citations skip evidence). Degrades gracefully without ANTHROPIC_API_KEY.
Round-loop scaffolding in place (rounds=1 only path exercised in v0.28).

src/commands/think.ts — `gbrain think "<question>"` CLI. Flag parsing
strips --anchor, --rounds, --save, --take, --model, --since, --until,
--json. Local CLI = remote=false, so save/take honored. Human-readable
output by default; --json for agent consumption.

operations.ts — `think` op now calls runThink (was a not_implemented
stub). Remote callers can't save/take per Codex P1 #7. Returns full
ThinkResult plus saved_slug + evidence_inserted.

cli.ts — wired into dispatch + CLI_ONLY allowlist.

Tests: test/think-pipeline.test.ts — 18 cases against PGLite covering
sanitize patterns, structural rendering, citation parsing (structured +
regex fallback + dedup + invalid-slug rejection), gather streams +
allow-list filter, full pipeline with stub client, malformed-LLM
fallback path, no-API-key graceful degradation, persistSynthesis writes
page + evidence rows. All pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 dream phases: auto-think + drift + budget meter (Codex P1 #10 fold)

src/core/anthropic-pricing.ts — USD/1M-tokens map for Claude 4.7 family
plus older aliases. estimateMaxCostUsd returns null on unpriced models so
the meter caller can warn-once and bypass the gate.

src/core/cycle/budget-meter.ts — cumulative cost ledger. Each submit
estimates max-cost from (model + estimatedInputTokens + maxOutputTokens),
accumulates per-cycle, refuses next submit when projected > cap. Codex
P1 #10 fold: non-Anthropic models (gemini, gpt) bypass with one stderr
warn per process and `unpriced=true` on the result. Budget=0 disables
the gate. Audit trail at ~/.gbrain/audit/dream-budget-YYYY-Www.jsonl.

src/core/cycle/auto-think.ts — auto_think dream phase. Reads
dream.auto_think.{enabled,questions,max_per_cycle,budget,cooldown_days,
auto_commit}. Iterates configured questions through runThink with the
BudgetMeter pre-checking each submit. Cooldown timestamp written ONLY on
success (matches v0.23 synthesize pattern — retries after partial
failures pick back up). When auto_commit=true, persists synthesis pages
via persistSynthesis. Default-disabled.

src/core/cycle/drift.ts — drift dream phase scaffold. Reads
dream.drift.{enabled,lookback_days,budget,auto_update}. Surfaces takes
in the soft band (weight 0.3-0.85, unresolved) that have recent timeline
evidence on the same page. v0.28 ships the orchestration; the LLM judge
that proposes weight adjustments lands in v0.29. modelId + meter wired
now so the ledger captures gate state for callers that opt in.

Tests:
- test/budget-meter.test.ts (7 cases) — pricing-map coverage, allow path,
  cumulative-deny, budget=0 disabled, unpriced bypass+warn-once, ledger
  captures all events, ISO-week filename branch.
- test/auto-think-phase.test.ts (9 cases) — auto_think enable/skip,
  questions empty, success → cooldown ts written, cooldown blocks rerun,
  budget exhausted → partial. drift not_enabled, soft-band candidate
  detection, complete + dry-run paths.

All pass. Typecheck clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 e2e Postgres: takes engine + extract + MCP allow-list (12 cases)

test/e2e/takes-postgres.test.ts — full v0.28 takes pipeline against real
Postgres (gated on DATABASE_URL). 12 cases:
- addTakesBatch upsert via unnest() bind path (Postgres-specific)
- listTakes filters: holder, kind, sort=weight, takesHoldersAllowList
- searchTakes pg_trgm + allow-list filter
- supersedeTake transactional path (BEGIN/COMMIT semantics)
- resolveTake immutability — second resolve throws TAKE_ALREADY_RESOLVED
- synthesis_evidence FK CASCADE on take delete
- countStaleTakes + listStaleTakes filter active+null
- extractTakesFromDb populates takes from fenced markdown
- MCP dispatch with takesHoldersAllowList=['world'] returns only world
- MCP dispatch local-CLI path returns all holders
- MCP dispatch takes_search honors allow-list
- think op forces remote_persisted_blocked even for save+take

postgres-engine.ts: addTakesBatch boolean[] serialization fix.
postgres-js auto-detects element type from JS arrays; for booleans it
mis-detects as scalar. Cast through text[] (`'true' | 'false'`) then
SQL-cast to boolean[] — same pattern other batch methods rely on for
type-stable bind shapes.

test/e2e/helpers.ts: setupDB now (a) tolerates non-existent tables in
TRUNCATE (for fresh DBs where v31 hasn't yet created takes/synthesis_evidence)
and (b) calls engine.initSchema() to actually run migrations.

test/takes-mcp-allowlist.test.ts: updated 2 think-op cases to match
Lane D's landed pipeline. They previously asserted not_implemented
envelopes; now they assert remote_persisted_blocked + NO_ANTHROPIC_API_KEY
graceful-degrade behavior.

Run: DATABASE_URL=postgres://localhost:5435/gbrain_test bun test test/e2e/takes-postgres.test.ts
Result: 12/12 pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 dream phases: local DreamPhaseResult type (avoid premature CyclePhase enum extension)

cycle.ts's PhaseResult is shaped {phase, status, summary, details} with a
narrow PhaseStatus enum ('ok'|'warn'|'fail'|'skipped') and CyclePhase enum
that doesn't yet include 'auto_think'/'drift'. The phases ship standalone
in v0.28 (cycle.ts dispatcher integration is v0.28.x); using PhaseResult
forced premature enum extension.

Introduces DreamPhaseResult exported from auto-think.ts:
  { name: 'auto_think'|'drift'; status: 'complete'|'partial'|'failed'|'skipped';
    detail: string; totals?: Record<string,number>; duration_ms: number }

drift.ts re-exports the same type. When v0.28.x wires the dispatcher, the
adapter at the call site can map DreamPhaseResult → PhaseResult cleanly.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 e2e: access_tokens.permissions JSONB end-to-end (5 cases)

test/e2e/auth-permissions.test.ts — closes the v0.28 token-allow-list
verification loop against real Postgres. Exercises:

- Migration v32 default backfill: new tokens created without a permissions
  column get {takes_holders: ["world"]} via the schema DEFAULT clause.
- Explicit ["world","garry"] → dispatch.takes_list filters to those
  holders only; brain hunches stay hidden from this token.
- ["world"] default-deny token → takes_search hits filtered to public claims.
- {} permissions row (operator tampered) gracefully defaults to ["world"]
  via the HTTP transport's validateToken parsing.
- revoked_at IS NOT NULL → token excluded from active token query.

Avoids the postgres-js JSONB double-encode trap (CLAUDE.md memory): pass
the object directly to executeRaw, no JSON.stringify, no ::jsonb cast.

All 5 pass against pgvector/pgvector:pg16 on port 5435. Combined v0.28
test sweep: 116/116 across 11 files.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 e2e: chunker takes-strip integration test (Codex P0 #3 verification)

test/e2e/chunker-takes-strip.test.ts — verifies the chunker actually
strips fenced takes content end-to-end through the import pipeline.
This is the Codex P0 #3 fix's verification path: takes content lives
ONLY in the takes table for retrieval, never duplicated in
content_chunks where the per-token MCP allow-list cannot reach.

5 cases:
- chunkText (unit) output never contains TAKES_FENCE_BEGIN/END markers
- chunkText output never contains fenced claim text
- chunkText output retains non-fence prose (no over-stripping)
- importFromContent end-to-end: imported page has chunks but none
  contain fenced content
- takes_fence_chunk_leak doctor invariant: zero rows globally where
  chunk_text matches `<!--- gbrain:takes:%`

Final v0.28 test sweep:
  121 pass, 0 fail, 336 expect() calls, 12 files
  Coverage: schema migrations, engine methods (PGLite + Postgres),
  takes-fence parser, page-lock, extract phase, takes CLI engine
  surface, model config 6-tier resolver, MCP+auth allow-list,
  think pipeline (gather + sanitize + cite-render + synthesize),
  auto-think + drift + budget meter, JSONB end-to-end, chunker
  strip integration. ~95% of v0.28 surface area covered.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix CI: apply-migrations skippedFuture arrays + http-transport SQL mock

Two CI failures from PR #563:

test/apply-migrations.test.ts (2 fails) — `buildPlan` tests assert exact
skippedFuture arrays at fixed installed-version stamps. Adding v0.28.0 to
the migration registry means it shows up in skippedFuture when the test
runs at installed=0.11.1 / installed=0.12.0. Append '0.28.0' to both
hardcoded arrays.

test/http-transport.test.ts (8 fails) — the FakeEngine mock string-prefix
matches `SELECT id, name FROM access_tokens` to return a row. v0.28's
validateToken now selects `SELECT id, name, permissions FROM access_tokens`
to read the per-token takes_holders allow-list. Mock returned [] on the
new query → validateToken treated every token as invalid → 401.

Fix: mock now matches both query shapes. validTokens row gets a default
`{takes_holders: ['world']}` permission injected when caller didn't
supply one (mirrors the migration v33 column DEFAULT). Updated
FakeEngineConfig type to allow tests to pass explicit permissions.

Verification:
  bun test test/apply-migrations.test.ts → 18/18 pass
  bun test test/http-transport.test.ts   → 24/24 pass
  bun run typecheck                       → clean

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix CI: add scope annotations to v0.28 ops (takes_list/takes_search/think)

test/oauth.test.ts enforces an invariant from master's v0.26 OAuth landing:
every Operation must have `scope: 'read' | 'write' | 'admin'`, and any op
flagged `mutating: true` must be 'write' or 'admin'. My v0.28 ops were added
before master shipped v0.26 + the new invariant; the merge surfaced the gap.

Annotations:
- takes_list   → read
- takes_search → read
- think        → write (mutating: true; --save persists synthesis page)

Verification:
  bun test test/oauth.test.ts → 42/42 pass
  bun run typecheck            → clean

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(v0.28.1): export INJECTION_PATTERNS for shared sanitization

The same pattern set protects takes from prompt-injection (think/sanitize.ts)
and now retrieved chat content in the LongMemEval harness. One source of
truth for both surfaces; adding a new pattern in this file automatically
covers benchmarks too.

Existing consumers (sanitizeTakeForPrompt, renderTakesBlock) keep working
unchanged. Verified via test/think-pipeline.test.ts (18 pass, 0 fail).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(v0.28.1): longmemeval harness — reset-in-place over in-memory PGLite

One in-memory PGLiteEngine per benchmark run; TRUNCATE between questions
with runtime-enumerated tables via pg_tables so future schema migrations
don't silently leak across questions. Infrastructure tables (sources,
config, gbrain_cycle_locks, subagent_rate_leases) preserved across resets
so initSchema-seeded rows like sources.'default' survive (FK target for
pages.source_id).

Files:
- src/eval/longmemeval/harness.ts: createBenchmarkBrain + resetTables +
  withBenchmarkBrain. ~50 lines, no class wrapper.
- src/eval/longmemeval/adapter.ts: pure haystackToPages() converter.
  Slug prefix `chat/` (verified non-matching against DEFAULT_SOURCE_BOOSTS).
- src/eval/longmemeval/sanitize.ts: re-uses INJECTION_PATTERNS from
  think/sanitize.ts; wraps each session in <chat_session id date> tags;
  4000-char cap.
- test/longmemeval-sanitize.test.ts: 12 cases pinning the F8 contract.

Hermetic: no DATABASE_URL, no API keys.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(v0.28.1): gbrain eval longmemeval CLI command

Run the LongMemEval public benchmark against gbrain's hybrid retrieval.
Dataset is a positional path (download from xiaowu0162/longmemeval on HF).
Per-question loop wraps everything in try/catch; one bad question doesn't
kill the run, error JSONL line emitted instead.

Wiring:
- src/cli.ts: pre-dispatch bypass for `eval longmemeval` so the user's
  ~/.gbrain brain is never opened. Hermeticity gate verified: --help works
  on machines with no gbrain config.
- src/commands/eval-longmemeval.ts: arg parsing, JSONL emit (LF + UTF-8
  pinned), hybridSearch with optional expandQuery from search/expansion.ts,
  resolveModel from model-config.ts (6-tier chain), ThinkLLMClient injection
  seam from think/index.ts, structural <chat_session> framing.
- test/eval-longmemeval.test.ts: 12 cases covering harness lifecycle,
  reset clears all tables, schema-migration robustness, p50/p99 speed gate
  (warm reset+import+search target <500ms), adapter shape, source-boost
  regression guard, end-to-end with stubbed LLM, JSONL format guard,
  per-question failure handling.
- test/fixtures/longmemeval-mini.jsonl: 5 hand-authored questions with
  keyword-friendly overlap so --keyword-only works in CI.

Speed: warm reset+import 5 pages+search p50=25.9ms p99=30.3ms locally.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(v0.28.1): bump VERSION + CHANGELOG

VERSION + package.json synchronized at 0.28.1. CHANGELOG entry uses the
release-summary voice + "To take advantage of v0.28.1" block per CLAUDE.md.

Sequential release on garrytan/v0.28-release; lands after v0.28.0.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: surface v0.28.1 LongMemEval CLI across project docs

- README.md: add EVAL section to Commands reference (eval --qrels, export,
  prune, replay, longmemeval); add v0.28.1 announce paragraph next to the
  v0.25.0 BrainBench-Real intro.
- CLAUDE.md: add Key files entry for src/eval/longmemeval/ +
  src/commands/eval-longmemeval.ts; add "Key commands added in v0.28.1"
  subsection (mirrors the v0.26.5 / v0.25.0 pattern); inventory
  test/eval-longmemeval.test.ts + test/longmemeval-sanitize.test.ts under
  the unit-test list.
- docs/eval-bench.md: cross-link from the "What it actually does" section
  to LongMemEval as the third evaluation axis (public benchmark,
  ground-truth labels, full QA pipeline); append "Public benchmarks:
  LongMemEval (v0.28.1)" section with architecture, flags table, and
  perf numbers.
- CONTRIBUTING.md: append a paragraph after the eval-replay block pointing
  contributors at gbrain eval longmemeval for public-benchmark coverage.
- AGENTS.md: extend the existing eval-retrieval bullet with a one-line
  mention of gbrain eval longmemeval.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28.2 feat: remote-source MCP + scope hierarchy + whoami (#690)

* refactor(core): extract SSRF helpers from integrations.ts to core/url-safety.ts

src/core/git-remote.ts (next commit) needs isInternalUrl etc. but importing
from src/commands/ would invert the layering boundary (no existing
src/core/ file imports from src/commands/). Extract the SSRF helpers
(parseOctet, hostnameToOctets, isPrivateIpv4, isInternalUrl) into a new
src/core/url-safety.ts and have integrations.ts re-export for backward
compat. test/integrations.test.ts continues to pass without changes (110
existing tests, 214 expects).

Why this matters for v0.28: the upcoming sources --url feature reuses
this SSRF gate for git-clone URL validation. Codex review caught that
re-rolling weaker URL classification would regress on the IPv6/v4-mapped/
metadata/CGNAT bypass forms that integrations.ts already handles.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(core): add git-remote module — SSRF-defensive clone/pull + state probe

New src/core/git-remote.ts (~210 lines) for v0.28's remote-source feature:

- GIT_SSRF_FLAGS exported const: -c http.followRedirects=false,
  -c protocol.file.allow=never, -c protocol.ext.allow=never,
  --no-recurse-submodules. Single source of truth shared by cloneRepo
  and pullRepo so a future flag added to one path lands on both.
  Closes the SSRF surfaces codex flagged: DNS rebinding via redirects,
  .gitmodules as a second-fetch surface, file:// scheme in remotes.

- parseRemoteUrl: https-only, rejects embedded credentials and path
  traversal, delegates internal-target classification to isInternalUrl
  from url-safety.ts (covers RFC1918, link-local, loopback, IPv6, CGNAT
  100.64/10, metadata hostnames, hex/octal/single-int bypass forms).
  GBRAIN_ALLOW_PRIVATE_REMOTES=1 escape hatch with stderr warning is
  needed for self-hosted git over Tailscale (CGNAT trips the gate).

- cloneRepo: --depth=1 default (full clone via depth: 0); refuses
  non-empty destDirs; spawns git via execFileSync (no shell injection)
  with GIT_TERMINAL_PROMPT=0 + askpass=/bin/false to prevent credential
  prompts. timeoutMs default 600s.

- pullRepo: -C path + GIT_SSRF_FLAGS + pull --ff-only, same env confine.

- validateRepoState: 6-state decision tree (missing | not-a-dir |
  no-git | corrupted | url-drift | healthy). Used by performSync's
  re-clone branch to recover from rmd clone dirs and refuse syncs on
  url-drift or corruption.

test/git-remote.test.ts (304 lines, 32 tests): GIT_SSRF_FLAGS exact
shape, all parseRemoteUrl rejection cases including dedicated CGNAT
100.64/10 with/without GBRAIN_ALLOW_PRIVATE_REMOTES (codex T3 case),
fake-git harness for argv assertions on cloneRepo/pullRepo, all 6
validateRepoState branches.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(core): add scope hierarchy + ALLOWED_SCOPES allowlist

New src/core/scope.ts (~120 lines) for v0.28's scoped MCP feature.

Hierarchy:
  - admin implies all (escape hatch)
  - write implies read
  - sources_admin and users_admin are siblings (different axes —
    sources-mgmt vs user-account-mgmt; neither implies the other)

Exported:
  - hasScope(grantedScopes, requiredScope): the canonical scope check.
    Replaces exact-string-match at three call sites in upcoming commits
    (serve-http.ts:673, oauth-provider.ts:365 F3 refresh, oauth-provider.ts:498
    token issuance). Without this rewrite, an admin-grant token would
    fail to refresh down to sources_admin (codex finding).
  - ALLOWED_SCOPES set + ALLOWED_SCOPES_LIST sorted array (deterministic
    for OAuth metadata wire format and drift-check output).
  - assertAllowedScopes / InvalidScopeError: registration-time gate so
    tokens with bogus scope strings (read flying-unicorn) get rejected
    with RFC 6749 §5.2 invalid_scope at auth.ts:296 + DCR /register +
    registerClientManual. Today's behavior accepts any string silently.
  - parseScopeString: space-separated wire format → array.

Forward-compat: hasScope ignores unknown granted scopes rather than
throwing, so pre-allowlist tokens with weird scope strings continue
working without crashes (registration is the gate, runtime is best-effort).

test/scope.test.ts (178 lines, 35 tests): hierarchy table including
all-implies for admin, sibling non-implication of *_admin scopes,
write→read but not the reverse, F3 refresh-token subset semantics
under hasScope, ALLOWED_SCOPES_LIST sorted-pinning, allowlist
rejection cases, parseScopeString edge cases (undefined/null/empty).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* build(admin): scope-constants mirror + drift CI for src/core/scope.ts

The admin React SPA's tsconfig.json scopes include: ['src'] to admin/src/,
so it cannot directly import ../../src/core/scope.ts. The plan considered
widening the include or generating a single source of truth; both options
either couple the SPA to the gbrain monorepo or add a build step. Eng
review picked the boring choice: hand-maintained mirror at
admin/src/lib/scope-constants.ts plus a CI drift check.

Files:
  - admin/src/lib/scope-constants.ts: hand-maintained ALLOWED_SCOPES_LIST
    duplicate, sorted alphabetically to match src/core/scope.ts.
  - scripts/check-admin-scope-drift.sh: extracts the list from each file
    via awk, normalizes via tr/sort, diffs. Exits 0 on match, 1 on drift
    (with full breakdown of which scopes diverged), 2 on internal error.
    Tested both passing and corrupted paths.
  - package.json: wires check:admin-scope-drift into both `verify` and
    `check:all` so any update to src/core/scope.ts that forgets the
    admin-side mirror fails the build.

The Agents.tsx scope-checkbox sites (5 hardcoded locations) get updated
in a later commit to import from this constants file.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(oauth): hasScope hierarchy + ALLOWED_SCOPES allowlist at registration

Switch three call sites in oauth-provider.ts from exact-string-match to
hasScope() so the v0.28 sources_admin and users_admin scopes — and the
admin-implies-all + write-implies-read hierarchy in src/core/scope.ts —
work end to end:

- F3 refresh-token subset enforcement at line 365: previously rejected
  admin → sources_admin refresh because exact-match treated them as
  unrelated scopes. gstack /setup-gbrain Path 4 needs admin tokens to
  refresh down to least-privilege sources_admin scope; this fix lands
  that path.

- Token issuance intersection at line 498 (client_credentials grant):
  same hasScope swap so a client whose stored grant is `admin` can mint
  tokens including any implied scope.

- registerClient (DCR /register) and registerClientManual: validate
  every scope string against ALLOWED_SCOPES via assertAllowedScopes.
  Pre-fix the system silently accepted `--scopes "read flying-unicorn"`
  and persisted the bogus string in oauth_clients.scope. Post-fix the
  caller gets RFC 6749 §5.2 invalid_scope. Existing rows with
  pre-allowlist scopes keep working (allowlist gates registration only).

Tests amended in test/oauth.test.ts:
- T1 (eng-review): admin grant CAN refresh down to sources_admin
- T1 sibling: write grant CANNOT refresh up to sources_admin
- ALLOWED_SCOPES allowlist coverage (manual + DCR paths, all 5 valid)
- Scope-annotation contract tests widened to accept the v0.28 union

62 OAuth tests pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(serve-http): hasScope at /mcp + advertise full ALLOWED_SCOPES

Two changes against src/commands/serve-http.ts:

- Line 195: scopesSupported on the mcpAuthRouter options switches from the
  hardcoded ['read','write','admin'] to Array.from(ALLOWED_SCOPES_LIST).
  Without this, /.well-known/oauth-authorization-server keeps reporting
  the old triple, so MCP clients (Claude Desktop, ChatGPT, Perplexity)
  cannot discover the v0.28 sources_admin and users_admin scopes via
  standard discovery — they would have to be pre-configured out of band.

- Line 673: request-time scope check on /mcp swaps
  authInfo.scopes.includes(requiredScope) for hasScope(...). This was
  the most-cited codex finding: without it, sources_admin tokens could
  not even satisfy a `read`-scoped op (sources_admin doesn't include
  the literal string "read"). hasScope routes through the hierarchy
  table in src/core/scope.ts so admin implies all and write implies
  read at the gate too.

T2 amendment in test/e2e/serve-http-oauth.test.ts: assert
/.well-known/oauth-authorization-server includes all 5 scopes in
scopes_supported. Pre-v0.28 the list was hardcoded to ['read','write',
'admin'] and this assertion would have failed. (The test is
Postgres-gated; runs under bun run test:e2e with DATABASE_URL set.)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(core): sources-ops module — atomic clone + symlink-safe cleanup

src/core/sources-ops.ts (~470 lines): pure async functions extracted from
src/commands/sources.ts so the CLI handlers and the new MCP ops share
one implementation.

addSource: D3 atomicity contract from the eng review.
  1. Validate id (matches existing SOURCE_ID_RE).
  2. Q4 pre-flight SELECT — fail loudly with structured `source_id_taken`
     before any clone work. Pre-fix the existing CLI used INSERT…ON
     CONFLICT DO NOTHING which silently no-op'd; with clone-first that
     would orphan the temp dir.
  3. parseRemoteUrl gate (delegates to isInternalUrl from url-safety.ts).
  4. Clone into $GBRAIN_HOME/clones/.tmp/<id>-<rand>/ via the new
     git-remote helpers.
  5. INSERT row with local_path=<final clone dir>, config.remote_url=<url>.
  6. fs.renameSync(tmp/, final/). Rollback on either-side failure unlinks
     the temp dir; rename-failed path also DELETEs the just-INSERTed row
     best-effort.

removeSource: clone-cleanup with realpath+lstat confinement matching
validateUploadPath() shape at src/core/operations.ts:61. String startsWith
is symlink-unsafe and would let $GBRAIN_HOME/clones/<id> → /etc resolve
out of the confine. Two defenses layered:
  - isPathContained (realpath-resolves both sides + parent-with-sep
    string check) rejects symlinks whose target falls outside the
    confine.
  - lstat-then-isSymbolicLink check refuses symlinks whose realpath
    happens to land back inside the confine (defense in depth).

getSourceStatus: returns clone_state via validateRepoState (the 6-state
decision tree from git-remote.ts). Lets a remote MCP caller diagnose
"healthy | missing | not-a-dir | no-git | url-drift | corrupted" without
SSH access to the brain host. listSources additionally exposes
remote_url so callers can see which sources are auto-managed.

recloneIfMissing: T4 follow-up for `gbrain sources restore` after the
clone dir was autopurged — re-clones via the same temp + rename
atomicity contract. Idempotent (returns false when clone is already
healthy).

test/sources-ops.test.ts (~470 lines, 24 tests): pre-flight collision
(Q4), happy paths for both --path and --url, all four D3 rollback paths
(clone-fail before INSERT, INSERT-fail after clone, rename-fail
post-INSERT, atomic temp-dir cleanup), symlink-target-OUTSIDE-clones
(realpath confinement), symlink-target-INSIDE-clones (lstat-check),
removeSource refuses to delete user-supplied paths, refuses "default"
source, getSourceStatus clone_state branches, T4 recloneIfMissing
recovery + idempotent + no-op for path-only sources, isPathContained
unit tests covering subtree / outside / symlink-escape / fail-closed.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(operations): whoami + sources_{add,list,remove,status} MCP ops

Five new ops in src/core/operations.ts auto-flow through src/mcp/tool-defs.ts
so MCP clients (Claude Desktop, ChatGPT, Perplexity, OpenClaw) get them via
standard tools/list discovery — no SDK or transport code changes needed.

Operation.scope union widened to add 'sources_admin' and 'users_admin' (the
v0.28 hierarchy from src/core/scope.ts).

whoami (scope: read): introspect calling identity over MCP.
  - Returns `{transport: 'oauth', client_id, client_name, scopes, expires_at}`
    for OAuth clients (clientId starts with gbrain_cl_).
  - Returns `{transport: 'legacy', token_name, scopes, expires_at: null}`
    for grandfathered access_tokens.
  - Returns `{transport: 'local', scopes: []}` when ctx.remote === false.
    Empty scopes (NOT ['read','write','admin']) is the D2 decision —
    returning OAuth-shaped scopes for local callers would resurrect the
    v0.26.9 footgun where code conditionally trusted on
    `auth.scopes.includes('admin')` instead of `ctx.remote === false`.
  - Q3 fail-closed: throws unknown_transport when remote=true AND auth is
    missing OR ctx.remote is the literal `undefined` (cast bypass guard).
    A future transport that forgets to thread auth doesn't get a free
    pass.

sources_add (sources_admin, mutating): register a source by --path
  (existing v0.17 behavior) or --url (v0.28 federated remote-clone path).
  Calls into addSource from sources-ops.ts which owns the temp-dir +
  rename atomicity.

sources_list (read): list registered sources with page counts, federated
  flag, and remote_url. The remote_url field is new — lets a remote MCP
  caller see which sources are auto-managed.

sources_remove (sources_admin, mutating): cascade-delete a source +
  symlink-safe clone cleanup. Requires confirm_destructive: true when the
  source has data.

sources_status (read): per-source diagnostic returning clone_state
  ('healthy' | 'missing' | 'not-a-dir' | 'no-git' | 'url-drift' |
  'corrupted' | 'not-applicable') — lets a remote MCP caller diagnose a
  busted clone without SSH access to the brain host.

test/whoami.test.ts (9 tests): pinned transport-detection for all four
return shapes including Q3 fail-closed throw under both auth=undefined
and remote=undefined cast-bypass paths.

test/sources-mcp.test.ts (16 tests): op-metadata pins (scope, mutating,
localOnly), functional handler shape against PGLite, hasScope-driven
scope-enforcement smoke test simulating the serve-http.ts:673 gate
(read-only token rejected for sources_add; sources_admin token allowed;
admin token allowed for everything; gstack /setup-gbrain Path 4 token
covers all 4 ops), SSRF gate at the op layer.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(sync): re-clone fallback when clone is missing/no-git/corrupted

src/commands/sync.ts gets a v0.28-aware front-half. When the source has
config.remote_url, performSync calls validateRepoState before the existing
fast-forward pull path:

  - 'healthy'    → fall through to existing pull (unchanged)
  - 'missing'    → loud stderr "auto-recovery: re-cloning <id>", then
  'no-git'         recloneIfMissing handles the temp-dir + rename. Sync
  'not-a-dir'      continues from the freshly-cloned head.
  - 'corrupted'  → throw with structured hint pointing at sources remove
                   + add (no syncing wrong state).
  - 'url-drift'  → throw with hint pointing at the (deferred) sources
                   rebase-clone command.

Closes the operator-confidence gap: rm -rf $GBRAIN_HOME/clones/<id>/ no
longer breaks future syncs. The next sync sees the missing dir and
recovers via the recorded URL.

src/core/operations.ts: extend ErrorCode with 'unknown_transport' so
whoami's Q3 fail-closed path types check.

test/sources-resync-recovery.test.ts (12 tests): full validateRepoState
state matrix exercised under fake-git, recloneIfMissing recovery from
each degraded state, idempotent on healthy clones, the sync.ts:320
integration path that drives the recovery.

test/sources-ops.test.ts + test/sources-mcp.test.ts: drop the
GBRAIN_PGLITE_SNAPSHOT-disable line so these tests stop forcing cold
init across the parallel-shard runner. With snapshot allowed, init time
drops from 6+s to ~50ms and parallel runs stay under the 5s hook
timeout.

test/sources-mcp.test.ts: tighten scope literal-type so tsc keeps the
union narrow.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(cli): sources add --url + restore re-clone, thin-wrapper refactor

src/commands/sources.ts now delegates the data-mutation work to
src/core/sources-ops.ts (added in the previous commit). The CLI handler
parses argv, calls into addSource, and formats output.

Two new flags on `gbrain sources add`:
  - `--url <https-url>` : federated remote-clone path (clone + INSERT +
    rename, atomic rollback on failure).
  - `--clone-dir <path>` : override the default
    $GBRAIN_HOME/clones/<id>/ destination.

Validation rejects mutually-exclusive `--url` + `--path`. Errors from
the ops layer (SourceOpError) propagate through the CLI's standard
error wrapper in src/cli.ts so existing tests that assert throw shape
keep passing.

`gbrain sources restore <id>` (T4 from eng review): if the source has a
remote_url AND the on-disk clone was autopurged, call recloneIfMissing
before declaring success. Clone errors print a WARN with recovery
hints rather than failing the restore — the DB row is what restore
guarantees; the clone is best-effort.

54 sources-related tests pass (existing test/sources.test.ts +
sources-ops + sources-mcp).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(doctor,cycle): orphan-clones surface + autopilot purge phase (P1)

addSource's atomicity contract uses a temp dir that gets renamed to the
final clone path. If the process is SIGKILL'd between clone-finish and
rename, the temp dir orphans on disk. Without sweeping these, a brain
server accumulates gigabytes over months of failed `sources add --url`
attempts.

Two layers:

1. `gbrain doctor` now surfaces stale entries. A new orphan_clones check
   walks $GBRAIN_HOME/clones/.tmp/, names anything older than 24h, and
   prints a warn with disk-byte estimate. Operators see the leak before
   `df` complains.

2. The autopilot cycle's existing `purge` phase grows a substep that
   nukes .tmp/ entries past the same 72h TTL the page-soft-delete purge
   uses. Operator behavior stays uniform across all soft-delete-style
   surfaces.

Both layers are filesystem-only (no DB). On a brain that never used
--url cloning, both are no-ops.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* build(admin): scope checkboxes source from scope-constants mirror + dist

admin/src/pages/Agents.tsx Register Client modal:
  - useState default sources from ALLOWED_SCOPES_LIST (defaulting `read`
    to true, others false; unchanged UX for the common case).
  - Scope checkbox map iterates ALLOWED_SCOPES_LIST instead of the old
    hardcoded ['read','write','admin'].

Without this commit, even with the v0.28.1 server-side scope hierarchy,
operators registering an OAuth client from the admin UI cannot tick the
new sources_admin / users_admin scopes — defeats the whole gstack
/setup-gbrain Path 4 unblock.

The drift-check CI gate (scripts/check-admin-scope-drift.sh) ensures
this list stays in sync with src/core/scope.ts going forward.

admin/dist/* rebuilt via `cd admin && bun run build`. Old hash bundle
removed; new bundle (224.96 kB / 68.70 kB gzip).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: v0.28.1 — remote-source MCP + scope hierarchy + whoami

VERSION + package.json: bump to 0.28.1 (per CLAUDE.md branch-scoped
versioning rule — this branch adds substantial new features on top of
v0.28.0).

CHANGELOG.md: new top-level entry for v0.28.1 in the gstack/Garry voice
(no AI vocabulary, no em dashes, real numbers + commands). Lead
paragraph names what the user can now do that they couldn't before.
"Numbers that matter" table calls out the +5 MCP ops, +2 OAuth scopes,
and the 4-to-0 SSH-step number for gstack /setup-gbrain Path 4. "What
this means for you" closer ties the work to the operator workflow shift.
"To take advantage of v0.28.1" block has paste-ready upgrade commands
including the admin SPA rebuild step. Itemized changes section
describes the architecture cleanly without exposing scope-string
internals to public attack-surface enumeration (per CLAUDE.md
responsible-disclosure rule).

TODOS.md: file 6 follow-ups under a new "Remote-source MCP follow-ups
(v0.28.1)" section: token rotation, migration introspection in
get_health, Accept-header friendliness, sources rebase-clone for
URL-drift recovery, --filter=blob:none partial-clone option, and the
chunker_version PGLite-schema parity codex caught.

README.md: short subsection under the existing sources CLI listing
that names the new --url flag and what auto-recovery does. Capability
framing (no scope-string enumeration).

llms.txt + llms-full.txt: regenerated via `bun run build:llms` so the
documentation bundle reflects the v0.28.1 entry. The build-llms
generator's drift check passes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(e2e): sources-remote-mcp — full gstack /setup-gbrain Path 4 round-trip

Spins up `gbrain serve --http` against real Postgres with a fake-git binary
in PATH (so `git clone` is exercised end-to-end without network), registers
two OAuth clients (sources_admin + read-only), mints tokens, calls the new
v0.28.1 MCP ops via /mcp, and asserts the gstack /setup-gbrain Path 4 flow
works end to end.

12 tests cover the full lifecycle:
- whoami over HTTP MCP returns transport=oauth + the right scopes
- /.well-known/oauth-authorization-server advertises all 5 scopes
- sources_add: clone fires, INSERT lands, row carries config.remote_url
- sources_status: clone_state=healthy after add
- sources_list: surfaces remote_url for the new source
- SSRF rejection: sources_add with RFC1918 URL fails at parseRemoteUrl gate
- Scope enforcement: read-only token gets insufficient_scope on sources_add
- Read-only token CAN call sources_list (read-scoped op)
- ALLOWED_SCOPES allowlist: CLI register-client rejects bogus scope
- Recovery: rm clone dir + sources_status reports clone_state=missing
- sources_remove: cascades + cleans up the auto-managed clone dir

Subprocess env threading replicates the v0.26.2 bun execSync inheritance
pattern — bun does NOT inherit process.env mutations, so every CLI
subprocess call passes env: { ...process.env } explicitly.

Cleanup contract mirrors test/e2e/serve-http-oauth.test.ts: revoke any
clients we registered, force-kill the server subprocess on SIGTERM
timeout, surface cleanup failures to stderr without throwing so real
test failures aren't masked.

The base table list in helpers.ts (ALL_TABLES) doesn't include sources
or oauth_clients, so this test explicitly truncates them in beforeAll
to avoid Q4 pre-flight collisions on re-run.

Skipped gracefully when DATABASE_URL is unset.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix: codex adversarial review — confine remote sources_admin + close SSRF gaps

Pre-ship adversarial review (codex exec) caught five issues. Four ship in
this commit; the fifth (DNS rebinding) is filed as v0.28.x follow-up.

CRITICAL — `sources_admin` tokens over HTTP MCP could plant content at any
host path. The MCP op exposed `path` and `clone_dir` to remote callers; the
op layer trusted them verbatim, then auto-recovery's rm -rf on degraded
state turned that into arbitrary delete primitives. src/core/operations.ts
sources_add handler now drops both fields when ctx.remote !== false. Local
CLI keeps the override (operator trust). Loud logger.warn when a remote
caller tries — visible in the SSE feed without leaking values.

HIGH — Steady-state `git pull --ff-only` bypassed GIT_SSRF_FLAGS entirely.
The legacy helper at src/commands/sync.ts:192 spawned git without the
-c http.followRedirects=false -c protocol.{file,ext}.allow=never
--no-recurse-submodules set that cloneRepo applies. Every recurring sync
was reopening the redirect/submodule/protocol bypass. Routed the call site
at sync.ts:381 through pullRepo from git-remote.ts so initial clone and
ongoing pull share one defensive flag set.

MEDIUM — listSources ignored its `include_archived` flag. The op
advertised the param but the function destructured it as `_opts` and
queried every row. Archived sources' ids, local_paths, and remote_urls
were leaking to read-scoped MCP callers by default. Filter in SQL
(`WHERE archived IS NOT TRUE` unless the flag is set) so archived rows
never reach the wire.

PARTIAL HIGH — IPv6 ULA fc00::/7 and link-local fe80::/10 were not in
the isInternalUrl bypass list. Only ::1/:: and IPv4-mapped IPv6 were
blocked. Added regex-based ULA + link-local rejection to url-safety.ts.

Test coverage:
- test/git-remote.test.ts: 4 new IPv6 cases (ULA fc-prefix + fd-prefix,
  link-local fe80::, public IPv6 still allowed).
- test/sources-mcp.test.ts: 3 new cases pinning the remote/local
  asymmetry (clone_dir override silently ignored over MCP, path nulled,
  local CLI keeps the override).
- test/sources-mcp.test.ts: 2 new cases for include_archived honored.

DNS rebinding (codex finding #3): the current gate is lexical only.
A deliberate attacker who controls a hostname's A/AAAA records can still
resolve to an internal IP. Closing this requires async DNS resolution +
revalidation; filed as v0.28.x follow-up in TODOS.md so the API change
surface (parseRemoteUrl becomes async, every caller updates) lands in
its own PR.

323 tests pass (9 files); 4071 unit tests pass (full suite).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: rebump v0.28.1 → v0.28.2 (master collision)

Caught after PR creation. master is at v0.28.1 already; this branch
forked from garrytan/v0.28-release at v0.28.0 and naively bumped to
v0.28.1 without checking the master queue. CI version-gate would have
rejected at merge time (requires VERSION strictly greater than
master's).

Root cause: I bumped VERSION mechanically during plan implementation
(echo "0.28.1" > VERSION) without consulting the queue-aware allocator
at bin/gstack-next-version. /ship Step 12's idempotency check then
classified state as ALREADY_BUMPED and the workflow's "queue drift"
comparison was the safety net I should have hit — but I skipped it.

Files updated:
- VERSION + package.json: 0.28.1 → 0.28.2
- CHANGELOG.md: header + "To take advantage of v0.28.2" subsection
- README.md: sources --url note version reference
- TODOS.md: 7 follow-up entries' version references
- llms.txt + llms-full.txt: regenerated

PR title rewrite via gstack-pr-title-rewrite.sh handled in a separate
gh pr edit call; CI version-gate now passes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(todos): close longmemeval-publication, file 4 follow-up TODOs

Full 500-question 4-adapter LongMemEval _s benchmark landed at
github.com/garrytan/gbrain-evals#main:ced01f0. gbrain-hybrid 97.60% R@5,
+1.0pt over MemPal raw 96.6%. Replacing the now-stale "needs full run"
TODO with closure + 4 grounded follow-ups:

  1. Timeline-aware retrieval signal for temporal-reasoning questions
     (P2 — closes the only category we lose to MemPal-raw)
  2. Per-question batch consolidation for ~10x cold-cache speedup
     (P3 — makes daily benchmark CI gate practical)
  3. LongMemEval _m split run (P3 — differentiated, not yet published
     by MemPal)
  4. Cheaper-embedding-model recipe (P4 — recall-cost tradeoff curve)

Each TODO has the standard What/Why/Pros/Cons/Context/Depends-on shape per
the gbrain TODOS-format convention.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(llms): regenerate llms-full.txt to match merged CLAUDE.md

CI test/build-llms.test.ts asserts the committed llms.txt/llms-full.txt
are byte-for-byte identical to what scripts/build-llms.ts produces. The
master merge brought in v0.28.9/v0.28.10/v0.28.11 + multimodal embedding
notes that updated CLAUDE.md; the bundle was stale.

No content changes. Pure regeneration via `bun run build:llms`.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs(changelog): rewrite v0.28.12 entry — lead with the LongMemEval result

Old entry buried the headline ("LongMemEval lands in the box…") under
process detail (hermetic CI test count, 25.9ms p50, schema-table
runtime enumeration). The reader cares what gbrain DOES — not how we
plumbed the harness.

New entry leads with the actual number — 97.60% R@5 on the public
LongMemEval _s split, beating MemPalace raw by 1.0pt — followed by
the per-category win table that proves gbrain ties or beats MemPal in
5 of 6 question types and shows the +7.1pt assistant-voice lift.

Links to the full gbrain-evals report (97.60% headline + full
methodology + reproducible runner) so curious readers can dig deeper.

Two honest findings published in plain text: vector-only is
essentially tied with hybrid at K=5, and query expansion via Haiku is
a clean null result on this dataset. Better to publish the null than
hide it.

Reproduction block updated to match the actual gbrain-evals workflow
(clone + bun install + dataset download + bash batch runner). The
prior "download / run / hand to evaluate_qa.py" block stayed for the
in-tree CLI path.

Regenerated llms-full.txt to keep the build-llms regen-drift guard
green.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-07 19:49:46 -07:00
Garry TanGitHubClaude Opus 4.7
 		b325f28239 v0.28.6 feat: takes + think + unified model config + per-token MCP allow-list (#563) 
* v0.28 schema: takes + synthesis_evidence (v31) + access_tokens.permissions (v32)

Migration v31 adds the takes table (typed/weighted/attributed claims) and
synthesis_evidence (provenance for `gbrain think` outputs). Page-scoped via
page_id FK (slug isn't unique alone in v0.18+ multi-source). HNSW partial
index on embedding for active rows. ON DELETE CASCADE on synthesis_evidence
so deleting a source take cascades the provenance row.

Migration v32 adds access_tokens.permissions JSONB with safe-default
backfill (`{"takes_holders":["world"]}`). Default keeps non-world holders
hidden from MCP-bound tokens until the operator explicitly grants access
via the v0.28 auth permissions CLI.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 engine: addTakesBatch, listTakes, searchTakes/Vector, supersede, resolve, synthesis_evidence

Extends BrainEngine with the takes domain object. Both engines implement the
same surface; PGLite uses manual `$N` placeholders, Postgres uses postgres-js
unnest() — same shape as addLinksBatch and addTimelineEntriesBatch.

Methods:
- addTakesBatch (upsert via ON CONFLICT (page_id, row_num) DO UPDATE)
- listTakes (filter by holder/kind/active/resolved, takesHoldersAllowList
  for MCP-bound calls, sortBy weight/since_date/created_at)
- searchTakes / searchTakesVector (pg_trgm + cosine; honor allow-list)
- countStaleTakes / listStaleTakes (mirror countStaleChunks pattern;
  embedding column intentionally omitted from listStale payload)
- updateTake (mutable fields only; throws TAKE_ROW_NOT_FOUND)
- supersedeTake (transactional: insert new at next row_num, mark old
  active=false, set superseded_by; throws TAKE_RESOLVED_IMMUTABLE on
  resolved bets)
- resolveTake (sets resolved_*; throws TAKE_ALREADY_RESOLVED on re-resolve;
  resolution is immutable per Codex P1 #13 fold)
- addSynthesisEvidence (provenance persist; ON CONFLICT DO NOTHING)
- getTakeEmbeddings (parallel to getEmbeddingsByChunkIds)

Types live in src/core/engine.ts adjacent to LinkBatchInput. Page-scoped
via page_id (slug not unique in v0.18+ multi-source). PageType gains
'synthesis'. takeRowToTake mapper in utils.ts handles Date → ISO string
normalization.

Tests: test/takes-engine.test.ts — 16 cases against PGLite covering
upsert/list/filter/search happy paths, takesHoldersAllowList isolation,
the four invariant errors (TAKE_ROW_NOT_FOUND, TAKES_WEIGHT_CLAMPED,
TAKE_RESOLVED_IMMUTABLE, TAKE_ALREADY_RESOLVED), supersede flow, resolve
metadata round-trip, FK CASCADE on synthesis_evidence when source take
deletes. All pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 model-config: unified resolveModel with 6-tier precedence + alias resolution

Replaces every hardcoded `claude-*-X` and per-phase `dream.<phase>.model`
config key with a single resolver. Hierarchy:

  1. CLI flag (--model)
  2. New-key config (e.g. models.dream.synthesize)
  3. Old-key config (deprecated dream.synthesize.model, dream.patterns.model)
     — read with stderr deprecation warning, one-per-process
  4. Global default (models.default)
  5. Env var (GBRAIN_MODEL or caller-supplied)
  6. Hardcoded fallback

Aliases (`opus`, `sonnet`, `haiku`, `gemini`, `gpt`) resolve at the end so
any tier can use a short name. User-defined `models.aliases.<name>` config
overrides built-ins. Cycle-safe (depth 2 break). Unknown alias passes
through unchanged so users can pass full provider IDs without registering.

When new-key + old-key are BOTH set (Codex P1 #11 fix), new-key wins and
stderr warns "deprecated config X ignored; Y is set and wins". When only
old-key is set, it's honored with a softer "rename to Y before v0.30"
warning. Both warnings emit once per (key, process) — a Set memo prevents
log spam in long-running daemons.

Migrated call sites: synthesize.ts (model + verdictModel), patterns.ts
(model). subagent.ts and search/expansion.ts to be migrated later in v0.28
(staying compatible until then).

Tests: test/model-config.test.ts — 11 cases pinning the 6-tier ordering,
alias resolution + cycle break, deprecated-key warning emit-once, and
unknown-alias pass-through. All pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 takes-fence: parser/renderer/upserter + chunker strip (privacy P0 fix)

src/core/takes-fence.ts — pure functions for the fenced markdown surface:
- parseTakesFence(body) — extracts ParsedTake[] from `<!--- gbrain:takes:begin/end -->`
  blocks. Strict on canonical form, lenient on hand-edits with warnings
  (TAKES_FENCE_UNBALANCED, TAKES_TABLE_MALFORMED, TAKES_ROW_NUM_COLLISION).
  Strikethrough `~~claim~~` → active=false; date ranges `since → until`
  split into sinceDate/untilDate.
- renderTakesFence(takes) — round-trip safe with parseTakesFence.
- upsertTakeRow(body, row) — append-only per CEO-D6 + eng-D9. Creates a
  fresh `## Takes` section if no fence present. row_num is monotonic
  (max + 1, never gap-filled — keeps cross-page refs and synthesis_evidence
  stable forever).
- supersedeRow(body, oldRow, replacement) — strikes through old row's claim
  AND appends the new row at end. Both rows preserved in markdown for
  git-blame archaeology.
- stripTakesFence(body) — removes the fenced block entirely. Used by the
  chunker so takes content lives ONLY in the takes table.

Codex P0 #3 fix: src/core/chunkers/recursive.ts now calls stripTakesFence()
before computing chunk boundaries. Without this, page chunks would contain
the rendered takes table and the per-token MCP allow-list would be
bypassed at the index layer (token bound to takes_holders=['world'] would
see garry's hunches via page hits). Doctor's takes_fence_chunk_leak check
(plan-side) asserts no chunk contains the begin marker.

Tests: 15 cases covering canonical parse, strikethrough, date range, fence
unbalanced detection, malformed-row skip + warning, row_num collision
detection, round-trip render, append-only upsert into existing fence,
fresh-section creation, monotonic row_num under hand-edit gaps, supersede
flow, stripTakesFence verifying takes content removed AND surrounding
prose preserved. Existing chunker tests still pass (15 + 15 = 30).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 page-lock: PID-liveness file lock for atomic markdown read-modify-write

src/core/page-lock.ts — per-page file lock at
~/.gbrain/page-locks/<sha256-of-slug>.lock so two concurrent `gbrain takes
add` calls or `takes seed --refresh` from autopilot can't race on the
same `<slug>.md` read-modify-write. Eng-review fold: reuses the v0.17
cycle.lock pattern (mtime + PID liveness) but per-slug.

Differences from cycle.ts's lock:
- SHA-256 of slug for safe filenames (slashes, unicode, etc.)
- Same-pid + fresh mtime = LIVE (cycle.ts assumes one lock per process and
  reclaims same-pid; page-lock allows concurrent locks for DIFFERENT slugs
  in one process). mtime expiry still rescues post-crash leftovers.
- 5-min TTL (vs cycle's 30 min — page edits are short)
- `withPageLock(slug, fn)` convenience wrapper with default 30s timeout

API:
- acquirePageLock(slug, opts) → handle | null (poll-with-timeout)
- handle.refresh() / handle.release() (idempotent — only releases if pid matches)
- withPageLock(slug, fn, opts) — acquire + run + release-in-finally

Tests: 10 cases — fresh acquire, live holder returns null, stale-mtime
reclaim, dead-PID reclaim, refresh updates timestamp, foreign-pid release
is no-op, withPageLock callback runs and releases on success/failure,
timeout-throws when held, SHA-256 filename safety for slashes/unicode.
All pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 extract-takes: dual-path phase (fs|db) + since/until_date as TEXT

src/core/cycle/extract-takes.ts — new phase that materializes the takes
table from fenced markdown blocks. Two paths mirror src/commands/extract.ts:

- extractTakesFromFs: walk *.md under repoPath, parse fences, batch upsert
- extractTakesFromDb: iterate engine.getAllSlugs(), parse each page's
  compiled_truth+timeline, batch upsert (mutation-immune snapshot iteration)

Single dispatcher extractTakes(opts) routes by source. Honors:
- slugs filter for incremental re-extract (pipes from sync→extract)
- dryRun: count would-be upserts, write nothing
- rebuild: DELETE FROM takes WHERE page_id = $1 before re-insert (clean
  slate when markdown is canonical and DB has drifted)

Schema fix: since_date/until_date were DATE in the original v31 migration.
Spec uses partial dates ('2017-01', '2026-04-29 → 2026-06') that Postgres
DATE rejects. Changed to TEXT in both the Postgres and PGLite blocks so
parser-rendered ranges round-trip cleanly. Loses the ability to do
date-range arithmetic in SQL, but date math on opinion timelines is
out of scope for v0.28 anyway. utils.ts dateOrNull now annotated as
v0.28 TEXT-aware.

Migration v31 has not been deployed yet (this branch is the v0.28 release
candidate), so the type swap is free. No data migration needed.

Tests: test/extract-takes.test.ts — 5 cases against PGLite covering full
walk + fence-skip on no-fence pages, takes-table populated post-extract,
incremental slugs filter, dry-run no-write, rebuild=true clears + re-inserts
ad-hoc rows. test/takes-engine.test.ts (16), test/takes-fence.test.ts (15)
all still pass — 36/36 takes tests green.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 takes CLI: list, search, add, update, supersede, resolve

src/commands/takes.ts — surfaces the engine methods + takes-fence library
through a single `gbrain takes <subcommand>` entrypoint:

  takes <slug>                          list with filters + sort
  takes search "<query>"                pg_trgm keyword search across all takes
  takes add <slug> --claim ... ...      append (markdown + DB, atomic via lock)
  takes update <slug> --row N ...       mutable-fields update (markdown + DB)
  takes supersede <slug> --row N ...    strikethrough old + append new
  takes resolve <slug> --row N --outcome  record bet resolution (immutable)

Markdown is canonical. Every mutate command:
  1. acquires the per-page file lock (withPageLock)
  2. re-reads the .md file
  3. applies the edit via takes-fence (upsertTakeRow / supersedeRow)
  4. writes the .md file back
  5. mirrors to the DB via the engine method
  6. releases the lock (auto via finally)

Resolve currently writes only to DB — surfacing resolved_* in the markdown
table is deferred to v0.29 (the takes-fence renderer's column set is
fixed at # | claim | kind | who | weight | since | source per spec).

Wired into src/cli.ts dispatch + CLI_ONLY allowlist. Help text follows the
project convention (orphans/embed/extract pattern). --dir flag overrides
sync.repo_path config when working outside the configured brain.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 MCP + auth: takes_list / takes_search / think ops + per-token allow-list

OperationContext gains takesHoldersAllowList — server-side filter for
takes.holder field threaded from access_tokens.permissions through dispatch
into the engine SQL. Closes Codex P0 #3 at the dispatch layer (chunker
strip already closed the page-content side in the previous commit).

src/core/operations.ts — three new ops:
- takes_list: lists takes with holder/kind/active/resolved filters; honors
  ctx.takesHoldersAllowList for MCP-bound calls
- takes_search: pg_trgm keyword search; honors allow-list
- think: op surface registered (returns not_implemented envelope until
  Lane D's pipeline lands). Remote callers cannot save/take per Codex P1 #7.

src/mcp/dispatch.ts — DispatchOpts.takesHoldersAllowList threads into
buildOperationContext.

src/mcp/http-transport.ts — validateToken now reads
access_tokens.permissions.takes_holders, defaults to ['world'] when the
column is absent or malformed (default-deny on private hunches).
auth.takesHoldersAllowList passed to dispatchToolCall.

src/mcp/server.ts (stdio) — defaults to takesHoldersAllowList: ['world']
since stdio has no per-token auth. Operators wanting full visibility use
`gbrain call <op>` directly (sets remote=false).

src/commands/auth.ts — `gbrain auth create <name> --takes-holders w,g,b`
flag persists the per-token list; new `auth permissions <name>
set-takes-holders <list>` updates an existing token.

Tests: test/takes-mcp-allowlist.test.ts — 8 cases against PGLite proving
the threading: local-CLI sees all holders, ['world'] returns only public,
['world','garry'] returns 2/3, no-overlap returns empty (no fallback),
search honors allow-list, remote save/take on think rejected with
not_implemented envelope.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28.0: ship-prep — VERSION, CHANGELOG, migration orchestrator, skill

Closes the v0.28 ship-prep cycle. Bumps VERSION + package.json + bun.lock
to 0.28.0. v0_28_0 migration orchestrator runs three idempotent phases on
upgrade:

- Schema verify: asserts schema_version >= 32 (migrations v31 + v32 already
  applied by the schema runner during gbrain upgrade); fails clean if not.
- Backfill takes: inline runs `extractTakes(engine, { source: 'db' })` so
  any pre-existing fenced takes tables in markdown populate the takes
  index. Idempotent; ON CONFLICT DO UPDATE keeps the table in sync.
- Re-chunk TODO: queues a pending-host-work entry asking the host agent
  to re-import pages with takes content so the v0.28 chunker-strip rule
  (Codex P0 #3 fix) applies retroactively. Pages imported under v0.28+
  already have takes content stripped from chunks at index time; this
  TODO catches up legacy pages.

skills/migrations/v0.28.0.md — agent-readable upgrade guide. Walks
through doctor verification, deprecated-key migration, MCP token
visibility configuration, and a "try the takes layer" smoke test.

CHANGELOG.md — v0.28.0 release-summary in the GStack voice (no AI
vocabulary, no em dashes, real numbers from git diff stat) + the
mandatory "To take advantage of v0.28.0" block + itemized changes by
subsystem (schema, engine, markdown surface, model config, MCP+auth,
CLI, tests, accepted risks).

Final test sweep: 65/65 v0.28 tests pass across 6 files. typecheck clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 think pipeline: gather → sanitize → synthesize → cite-render → CLI

src/core/think/sanitize.ts — prompt-injection defense for take claims:
14 jailbreak patterns (ignore-prior, role-jailbreak, close-take tag,
DAN, system-prompt overrides, eval-shell hooks) plus structural framing
(takes wrapped in <take id="..."> tags the model is told to treat as
DATA). Length-cap at 500 chars. Renders evidence blocks for the prompt.

src/core/think/prompt.ts — system prompt + structured-output schema.
Hard rules: cite every claim, mark hunches/low-weight explicitly,
surface conflicts (never silently pick), surface gaps. JSON schema
with answer + citations[] + gaps[]. Prompt adapts to anchor / time
window / save flag.

src/core/think/cite-render.ts — structured citations + regex fallback
(Codex P1 #4 fold). normalizeStructuredCitations validates the model's
structured output; parseInlineCitations is the body-scan fallback when
the model omits the structured field. resolveCitations dispatches and
records CITATIONS_REGEX_FALLBACK warning when used.

src/core/think/gather.ts — 4-stream parallel retrieval:
  1. hybridSearch (pages, existing primitive)
  2. searchTakes (keyword, pg_trgm)
  3. searchTakesVector (vector, when embedQuestion fn supplied)
  4. traversePaths (graph, when --anchor set)
RRF fusion (k=60). Each stream wrapped in try/catch — partial gather
beats no synthesis. Honors takesHoldersAllowList for MCP-bound calls.

src/core/think/index.ts — runThink orchestrator + persistSynthesis:
INTENT (regex classify) → GATHER → render evidence blocks → resolveModel
('models.think' → 'models.default' → GBRAIN_MODEL → opus) → LLM call
(injectable client) → JSON parse with code-fence + fallback strip →
resolveCitations → ThinkResult. persistSynthesis writes a synthesis
page + synthesis_evidence rows (page_id resolved per slug; page-level
citations skip evidence). Degrades gracefully without ANTHROPIC_API_KEY.
Round-loop scaffolding in place (rounds=1 only path exercised in v0.28).

src/commands/think.ts — `gbrain think "<question>"` CLI. Flag parsing
strips --anchor, --rounds, --save, --take, --model, --since, --until,
--json. Local CLI = remote=false, so save/take honored. Human-readable
output by default; --json for agent consumption.

operations.ts — `think` op now calls runThink (was a not_implemented
stub). Remote callers can't save/take per Codex P1 #7. Returns full
ThinkResult plus saved_slug + evidence_inserted.

cli.ts — wired into dispatch + CLI_ONLY allowlist.

Tests: test/think-pipeline.test.ts — 18 cases against PGLite covering
sanitize patterns, structural rendering, citation parsing (structured +
regex fallback + dedup + invalid-slug rejection), gather streams +
allow-list filter, full pipeline with stub client, malformed-LLM
fallback path, no-API-key graceful degradation, persistSynthesis writes
page + evidence rows. All pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 dream phases: auto-think + drift + budget meter (Codex P1 #10 fold)

src/core/anthropic-pricing.ts — USD/1M-tokens map for Claude 4.7 family
plus older aliases. estimateMaxCostUsd returns null on unpriced models so
the meter caller can warn-once and bypass the gate.

src/core/cycle/budget-meter.ts — cumulative cost ledger. Each submit
estimates max-cost from (model + estimatedInputTokens + maxOutputTokens),
accumulates per-cycle, refuses next submit when projected > cap. Codex
P1 #10 fold: non-Anthropic models (gemini, gpt) bypass with one stderr
warn per process and `unpriced=true` on the result. Budget=0 disables
the gate. Audit trail at ~/.gbrain/audit/dream-budget-YYYY-Www.jsonl.

src/core/cycle/auto-think.ts — auto_think dream phase. Reads
dream.auto_think.{enabled,questions,max_per_cycle,budget,cooldown_days,
auto_commit}. Iterates configured questions through runThink with the
BudgetMeter pre-checking each submit. Cooldown timestamp written ONLY on
success (matches v0.23 synthesize pattern — retries after partial
failures pick back up). When auto_commit=true, persists synthesis pages
via persistSynthesis. Default-disabled.

src/core/cycle/drift.ts — drift dream phase scaffold. Reads
dream.drift.{enabled,lookback_days,budget,auto_update}. Surfaces takes
in the soft band (weight 0.3-0.85, unresolved) that have recent timeline
evidence on the same page. v0.28 ships the orchestration; the LLM judge
that proposes weight adjustments lands in v0.29. modelId + meter wired
now so the ledger captures gate state for callers that opt in.

Tests:
- test/budget-meter.test.ts (7 cases) — pricing-map coverage, allow path,
  cumulative-deny, budget=0 disabled, unpriced bypass+warn-once, ledger
  captures all events, ISO-week filename branch.
- test/auto-think-phase.test.ts (9 cases) — auto_think enable/skip,
  questions empty, success → cooldown ts written, cooldown blocks rerun,
  budget exhausted → partial. drift not_enabled, soft-band candidate
  detection, complete + dry-run paths.

All pass. Typecheck clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 e2e Postgres: takes engine + extract + MCP allow-list (12 cases)

test/e2e/takes-postgres.test.ts — full v0.28 takes pipeline against real
Postgres (gated on DATABASE_URL). 12 cases:
- addTakesBatch upsert via unnest() bind path (Postgres-specific)
- listTakes filters: holder, kind, sort=weight, takesHoldersAllowList
- searchTakes pg_trgm + allow-list filter
- supersedeTake transactional path (BEGIN/COMMIT semantics)
- resolveTake immutability — second resolve throws TAKE_ALREADY_RESOLVED
- synthesis_evidence FK CASCADE on take delete
- countStaleTakes + listStaleTakes filter active+null
- extractTakesFromDb populates takes from fenced markdown
- MCP dispatch with takesHoldersAllowList=['world'] returns only world
- MCP dispatch local-CLI path returns all holders
- MCP dispatch takes_search honors allow-list
- think op forces remote_persisted_blocked even for save+take

postgres-engine.ts: addTakesBatch boolean[] serialization fix.
postgres-js auto-detects element type from JS arrays; for booleans it
mis-detects as scalar. Cast through text[] (`'true' | 'false'`) then
SQL-cast to boolean[] — same pattern other batch methods rely on for
type-stable bind shapes.

test/e2e/helpers.ts: setupDB now (a) tolerates non-existent tables in
TRUNCATE (for fresh DBs where v31 hasn't yet created takes/synthesis_evidence)
and (b) calls engine.initSchema() to actually run migrations.

test/takes-mcp-allowlist.test.ts: updated 2 think-op cases to match
Lane D's landed pipeline. They previously asserted not_implemented
envelopes; now they assert remote_persisted_blocked + NO_ANTHROPIC_API_KEY
graceful-degrade behavior.

Run: DATABASE_URL=postgres://localhost:5435/gbrain_test bun test test/e2e/takes-postgres.test.ts
Result: 12/12 pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 dream phases: local DreamPhaseResult type (avoid premature CyclePhase enum extension)

cycle.ts's PhaseResult is shaped {phase, status, summary, details} with a
narrow PhaseStatus enum ('ok'|'warn'|'fail'|'skipped') and CyclePhase enum
that doesn't yet include 'auto_think'/'drift'. The phases ship standalone
in v0.28 (cycle.ts dispatcher integration is v0.28.x); using PhaseResult
forced premature enum extension.

Introduces DreamPhaseResult exported from auto-think.ts:
  { name: 'auto_think'|'drift'; status: 'complete'|'partial'|'failed'|'skipped';
    detail: string; totals?: Record<string,number>; duration_ms: number }

drift.ts re-exports the same type. When v0.28.x wires the dispatcher, the
adapter at the call site can map DreamPhaseResult → PhaseResult cleanly.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 e2e: access_tokens.permissions JSONB end-to-end (5 cases)

test/e2e/auth-permissions.test.ts — closes the v0.28 token-allow-list
verification loop against real Postgres. Exercises:

- Migration v32 default backfill: new tokens created without a permissions
  column get {takes_holders: ["world"]} via the schema DEFAULT clause.
- Explicit ["world","garry"] → dispatch.takes_list filters to those
  holders only; brain hunches stay hidden from this token.
- ["world"] default-deny token → takes_search hits filtered to public claims.
- {} permissions row (operator tampered) gracefully defaults to ["world"]
  via the HTTP transport's validateToken parsing.
- revoked_at IS NOT NULL → token excluded from active token query.

Avoids the postgres-js JSONB double-encode trap (CLAUDE.md memory): pass
the object directly to executeRaw, no JSON.stringify, no ::jsonb cast.

All 5 pass against pgvector/pgvector:pg16 on port 5435. Combined v0.28
test sweep: 116/116 across 11 files.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28 e2e: chunker takes-strip integration test (Codex P0 #3 verification)

test/e2e/chunker-takes-strip.test.ts — verifies the chunker actually
strips fenced takes content end-to-end through the import pipeline.
This is the Codex P0 #3 fix's verification path: takes content lives
ONLY in the takes table for retrieval, never duplicated in
content_chunks where the per-token MCP allow-list cannot reach.

5 cases:
- chunkText (unit) output never contains TAKES_FENCE_BEGIN/END markers
- chunkText output never contains fenced claim text
- chunkText output retains non-fence prose (no over-stripping)
- importFromContent end-to-end: imported page has chunks but none
  contain fenced content
- takes_fence_chunk_leak doctor invariant: zero rows globally where
  chunk_text matches `<!--- gbrain:takes:%`

Final v0.28 test sweep:
  121 pass, 0 fail, 336 expect() calls, 12 files
  Coverage: schema migrations, engine methods (PGLite + Postgres),
  takes-fence parser, page-lock, extract phase, takes CLI engine
  surface, model config 6-tier resolver, MCP+auth allow-list,
  think pipeline (gather + sanitize + cite-render + synthesize),
  auto-think + drift + budget meter, JSONB end-to-end, chunker
  strip integration. ~95% of v0.28 surface area covered.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix CI: apply-migrations skippedFuture arrays + http-transport SQL mock

Two CI failures from PR #563:

test/apply-migrations.test.ts (2 fails) — `buildPlan` tests assert exact
skippedFuture arrays at fixed installed-version stamps. Adding v0.28.0 to
the migration registry means it shows up in skippedFuture when the test
runs at installed=0.11.1 / installed=0.12.0. Append '0.28.0' to both
hardcoded arrays.

test/http-transport.test.ts (8 fails) — the FakeEngine mock string-prefix
matches `SELECT id, name FROM access_tokens` to return a row. v0.28's
validateToken now selects `SELECT id, name, permissions FROM access_tokens`
to read the per-token takes_holders allow-list. Mock returned [] on the
new query → validateToken treated every token as invalid → 401.

Fix: mock now matches both query shapes. validTokens row gets a default
`{takes_holders: ['world']}` permission injected when caller didn't
supply one (mirrors the migration v33 column DEFAULT). Updated
FakeEngineConfig type to allow tests to pass explicit permissions.

Verification:
  bun test test/apply-migrations.test.ts → 18/18 pass
  bun test test/http-transport.test.ts   → 24/24 pass
  bun run typecheck                       → clean

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix CI: add scope annotations to v0.28 ops (takes_list/takes_search/think)

test/oauth.test.ts enforces an invariant from master's v0.26 OAuth landing:
every Operation must have `scope: 'read' | 'write' | 'admin'`, and any op
flagged `mutating: true` must be 'write' or 'admin'. My v0.28 ops were added
before master shipped v0.26 + the new invariant; the merge surfaced the gap.

Annotations:
- takes_list   → read
- takes_search → read
- think        → write (mutating: true; --save persists synthesis page)

Verification:
  bun test test/oauth.test.ts → 42/42 pass
  bun run typecheck            → clean

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v0.28.2 feat: remote-source MCP + scope hierarchy + whoami (#690)

* refactor(core): extract SSRF helpers from integrations.ts to core/url-safety.ts

src/core/git-remote.ts (next commit) needs isInternalUrl etc. but importing
from src/commands/ would invert the layering boundary (no existing
src/core/ file imports from src/commands/). Extract the SSRF helpers
(parseOctet, hostnameToOctets, isPrivateIpv4, isInternalUrl) into a new
src/core/url-safety.ts and have integrations.ts re-export for backward
compat. test/integrations.test.ts continues to pass without changes (110
existing tests, 214 expects).

Why this matters for v0.28: the upcoming sources --url feature reuses
this SSRF gate for git-clone URL validation. Codex review caught that
re-rolling weaker URL classification would regress on the IPv6/v4-mapped/
metadata/CGNAT bypass forms that integrations.ts already handles.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(core): add git-remote module — SSRF-defensive clone/pull + state probe

New src/core/git-remote.ts (~210 lines) for v0.28's remote-source feature:

- GIT_SSRF_FLAGS exported const: -c http.followRedirects=false,
  -c protocol.file.allow=never, -c protocol.ext.allow=never,
  --no-recurse-submodules. Single source of truth shared by cloneRepo
  and pullRepo so a future flag added to one path lands on both.
  Closes the SSRF surfaces codex flagged: DNS rebinding via redirects,
  .gitmodules as a second-fetch surface, file:// scheme in remotes.

- parseRemoteUrl: https-only, rejects embedded credentials and path
  traversal, delegates internal-target classification to isInternalUrl
  from url-safety.ts (covers RFC1918, link-local, loopback, IPv6, CGNAT
  100.64/10, metadata hostnames, hex/octal/single-int bypass forms).
  GBRAIN_ALLOW_PRIVATE_REMOTES=1 escape hatch with stderr warning is
  needed for self-hosted git over Tailscale (CGNAT trips the gate).

- cloneRepo: --depth=1 default (full clone via depth: 0); refuses
  non-empty destDirs; spawns git via execFileSync (no shell injection)
  with GIT_TERMINAL_PROMPT=0 + askpass=/bin/false to prevent credential
  prompts. timeoutMs default 600s.

- pullRepo: -C path + GIT_SSRF_FLAGS + pull --ff-only, same env confine.

- validateRepoState: 6-state decision tree (missing | not-a-dir |
  no-git | corrupted | url-drift | healthy). Used by performSync's
  re-clone branch to recover from rmd clone dirs and refuse syncs on
  url-drift or corruption.

test/git-remote.test.ts (304 lines, 32 tests): GIT_SSRF_FLAGS exact
shape, all parseRemoteUrl rejection cases including dedicated CGNAT
100.64/10 with/without GBRAIN_ALLOW_PRIVATE_REMOTES (codex T3 case),
fake-git harness for argv assertions on cloneRepo/pullRepo, all 6
validateRepoState branches.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(core): add scope hierarchy + ALLOWED_SCOPES allowlist

New src/core/scope.ts (~120 lines) for v0.28's scoped MCP feature.

Hierarchy:
  - admin implies all (escape hatch)
  - write implies read
  - sources_admin and users_admin are siblings (different axes —
    sources-mgmt vs user-account-mgmt; neither implies the other)

Exported:
  - hasScope(grantedScopes, requiredScope): the canonical scope check.
    Replaces exact-string-match at three call sites in upcoming commits
    (serve-http.ts:673, oauth-provider.ts:365 F3 refresh, oauth-provider.ts:498
    token issuance). Without this rewrite, an admin-grant token would
    fail to refresh down to sources_admin (codex finding).
  - ALLOWED_SCOPES set + ALLOWED_SCOPES_LIST sorted array (deterministic
    for OAuth metadata wire format and drift-check output).
  - assertAllowedScopes / InvalidScopeError: registration-time gate so
    tokens with bogus scope strings (read flying-unicorn) get rejected
    with RFC 6749 §5.2 invalid_scope at auth.ts:296 + DCR /register +
    registerClientManual. Today's behavior accepts any string silently.
  - parseScopeString: space-separated wire format → array.

Forward-compat: hasScope ignores unknown granted scopes rather than
throwing, so pre-allowlist tokens with weird scope strings continue
working without crashes (registration is the gate, runtime is best-effort).

test/scope.test.ts (178 lines, 35 tests): hierarchy table including
all-implies for admin, sibling non-implication of *_admin scopes,
write→read but not the reverse, F3 refresh-token subset semantics
under hasScope, ALLOWED_SCOPES_LIST sorted-pinning, allowlist
rejection cases, parseScopeString edge cases (undefined/null/empty).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* build(admin): scope-constants mirror + drift CI for src/core/scope.ts

The admin React SPA's tsconfig.json scopes include: ['src'] to admin/src/,
so it cannot directly import ../../src/core/scope.ts. The plan considered
widening the include or generating a single source of truth; both options
either couple the SPA to the gbrain monorepo or add a build step. Eng
review picked the boring choice: hand-maintained mirror at
admin/src/lib/scope-constants.ts plus a CI drift check.

Files:
  - admin/src/lib/scope-constants.ts: hand-maintained ALLOWED_SCOPES_LIST
    duplicate, sorted alphabetically to match src/core/scope.ts.
  - scripts/check-admin-scope-drift.sh: extracts the list from each file
    via awk, normalizes via tr/sort, diffs. Exits 0 on match, 1 on drift
    (with full breakdown of which scopes diverged), 2 on internal error.
    Tested both passing and corrupted paths.
  - package.json: wires check:admin-scope-drift into both `verify` and
    `check:all` so any update to src/core/scope.ts that forgets the
    admin-side mirror fails the build.

The Agents.tsx scope-checkbox sites (5 hardcoded locations) get updated
in a later commit to import from this constants file.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(oauth): hasScope hierarchy + ALLOWED_SCOPES allowlist at registration

Switch three call sites in oauth-provider.ts from exact-string-match to
hasScope() so the v0.28 sources_admin and users_admin scopes — and the
admin-implies-all + write-implies-read hierarchy in src/core/scope.ts —
work end to end:

- F3 refresh-token subset enforcement at line 365: previously rejected
  admin → sources_admin refresh because exact-match treated them as
  unrelated scopes. gstack /setup-gbrain Path 4 needs admin tokens to
  refresh down to least-privilege sources_admin scope; this fix lands
  that path.

- Token issuance intersection at line 498 (client_credentials grant):
  same hasScope swap so a client whose stored grant is `admin` can mint
  tokens including any implied scope.

- registerClient (DCR /register) and registerClientManual: validate
  every scope string against ALLOWED_SCOPES via assertAllowedScopes.
  Pre-fix the system silently accepted `--scopes "read flying-unicorn"`
  and persisted the bogus string in oauth_clients.scope. Post-fix the
  caller gets RFC 6749 §5.2 invalid_scope. Existing rows with
  pre-allowlist scopes keep working (allowlist gates registration only).

Tests amended in test/oauth.test.ts:
- T1 (eng-review): admin grant CAN refresh down to sources_admin
- T1 sibling: write grant CANNOT refresh up to sources_admin
- ALLOWED_SCOPES allowlist coverage (manual + DCR paths, all 5 valid)
- Scope-annotation contract tests widened to accept the v0.28 union

62 OAuth tests pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(serve-http): hasScope at /mcp + advertise full ALLOWED_SCOPES

Two changes against src/commands/serve-http.ts:

- Line 195: scopesSupported on the mcpAuthRouter options switches from the
  hardcoded ['read','write','admin'] to Array.from(ALLOWED_SCOPES_LIST).
  Without this, /.well-known/oauth-authorization-server keeps reporting
  the old triple, so MCP clients (Claude Desktop, ChatGPT, Perplexity)
  cannot discover the v0.28 sources_admin and users_admin scopes via
  standard discovery — they would have to be pre-configured out of band.

- Line 673: request-time scope check on /mcp swaps
  authInfo.scopes.includes(requiredScope) for hasScope(...). This was
  the most-cited codex finding: without it, sources_admin tokens could
  not even satisfy a `read`-scoped op (sources_admin doesn't include
  the literal string "read"). hasScope routes through the hierarchy
  table in src/core/scope.ts so admin implies all and write implies
  read at the gate too.

T2 amendment in test/e2e/serve-http-oauth.test.ts: assert
/.well-known/oauth-authorization-server includes all 5 scopes in
scopes_supported. Pre-v0.28 the list was hardcoded to ['read','write',
'admin'] and this assertion would have failed. (The test is
Postgres-gated; runs under bun run test:e2e with DATABASE_URL set.)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(core): sources-ops module — atomic clone + symlink-safe cleanup

src/core/sources-ops.ts (~470 lines): pure async functions extracted from
src/commands/sources.ts so the CLI handlers and the new MCP ops share
one implementation.

addSource: D3 atomicity contract from the eng review.
  1. Validate id (matches existing SOURCE_ID_RE).
  2. Q4 pre-flight SELECT — fail loudly with structured `source_id_taken`
     before any clone work. Pre-fix the existing CLI used INSERT…ON
     CONFLICT DO NOTHING which silently no-op'd; with clone-first that
     would orphan the temp dir.
  3. parseRemoteUrl gate (delegates to isInternalUrl from url-safety.ts).
  4. Clone into $GBRAIN_HOME/clones/.tmp/<id>-<rand>/ via the new
     git-remote helpers.
  5. INSERT row with local_path=<final clone dir>, config.remote_url=<url>.
  6. fs.renameSync(tmp/, final/). Rollback on either-side failure unlinks
     the temp dir; rename-failed path also DELETEs the just-INSERTed row
     best-effort.

removeSource: clone-cleanup with realpath+lstat confinement matching
validateUploadPath() shape at src/core/operations.ts:61. String startsWith
is symlink-unsafe and would let $GBRAIN_HOME/clones/<id> → /etc resolve
out of the confine. Two defenses layered:
  - isPathContained (realpath-resolves both sides + parent-with-sep
    string check) rejects symlinks whose target falls outside the
    confine.
  - lstat-then-isSymbolicLink check refuses symlinks whose realpath
    happens to land back inside the confine (defense in depth).

getSourceStatus: returns clone_state via validateRepoState (the 6-state
decision tree from git-remote.ts). Lets a remote MCP caller diagnose
"healthy | missing | not-a-dir | no-git | url-drift | corrupted" without
SSH access to the brain host. listSources additionally exposes
remote_url so callers can see which sources are auto-managed.

recloneIfMissing: T4 follow-up for `gbrain sources restore` after the
clone dir was autopurged — re-clones via the same temp + rename
atomicity contract. Idempotent (returns false when clone is already
healthy).

test/sources-ops.test.ts (~470 lines, 24 tests): pre-flight collision
(Q4), happy paths for both --path and --url, all four D3 rollback paths
(clone-fail before INSERT, INSERT-fail after clone, rename-fail
post-INSERT, atomic temp-dir cleanup), symlink-target-OUTSIDE-clones
(realpath confinement), symlink-target-INSIDE-clones (lstat-check),
removeSource refuses to delete user-supplied paths, refuses "default"
source, getSourceStatus clone_state branches, T4 recloneIfMissing
recovery + idempotent + no-op for path-only sources, isPathContained
unit tests covering subtree / outside / symlink-escape / fail-closed.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(operations): whoami + sources_{add,list,remove,status} MCP ops

Five new ops in src/core/operations.ts auto-flow through src/mcp/tool-defs.ts
so MCP clients (Claude Desktop, ChatGPT, Perplexity, OpenClaw) get them via
standard tools/list discovery — no SDK or transport code changes needed.

Operation.scope union widened to add 'sources_admin' and 'users_admin' (the
v0.28 hierarchy from src/core/scope.ts).

whoami (scope: read): introspect calling identity over MCP.
  - Returns `{transport: 'oauth', client_id, client_name, scopes, expires_at}`
    for OAuth clients (clientId starts with gbrain_cl_).
  - Returns `{transport: 'legacy', token_name, scopes, expires_at: null}`
    for grandfathered access_tokens.
  - Returns `{transport: 'local', scopes: []}` when ctx.remote === false.
    Empty scopes (NOT ['read','write','admin']) is the D2 decision —
    returning OAuth-shaped scopes for local callers would resurrect the
    v0.26.9 footgun where code conditionally trusted on
    `auth.scopes.includes('admin')` instead of `ctx.remote === false`.
  - Q3 fail-closed: throws unknown_transport when remote=true AND auth is
    missing OR ctx.remote is the literal `undefined` (cast bypass guard).
    A future transport that forgets to thread auth doesn't get a free
    pass.

sources_add (sources_admin, mutating): register a source by --path
  (existing v0.17 behavior) or --url (v0.28 federated remote-clone path).
  Calls into addSource from sources-ops.ts which owns the temp-dir +
  rename atomicity.

sources_list (read): list registered sources with page counts, federated
  flag, and remote_url. The remote_url field is new — lets a remote MCP
  caller see which sources are auto-managed.

sources_remove (sources_admin, mutating): cascade-delete a source +
  symlink-safe clone cleanup. Requires confirm_destructive: true when the
  source has data.

sources_status (read): per-source diagnostic returning clone_state
  ('healthy' | 'missing' | 'not-a-dir' | 'no-git' | 'url-drift' |
  'corrupted' | 'not-applicable') — lets a remote MCP caller diagnose a
  busted clone without SSH access to the brain host.

test/whoami.test.ts (9 tests): pinned transport-detection for all four
return shapes including Q3 fail-closed throw under both auth=undefined
and remote=undefined cast-bypass paths.

test/sources-mcp.test.ts (16 tests): op-metadata pins (scope, mutating,
localOnly), functional handler shape against PGLite, hasScope-driven
scope-enforcement smoke test simulating the serve-http.ts:673 gate
(read-only token rejected for sources_add; sources_admin token allowed;
admin token allowed for everything; gstack /setup-gbrain Path 4 token
covers all 4 ops), SSRF gate at the op layer.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(sync): re-clone fallback when clone is missing/no-git/corrupted

src/commands/sync.ts gets a v0.28-aware front-half. When the source has
config.remote_url, performSync calls validateRepoState before the existing
fast-forward pull path:

  - 'healthy'    → fall through to existing pull (unchanged)
  - 'missing'    → loud stderr "auto-recovery: re-cloning <id>", then
  'no-git'         recloneIfMissing handles the temp-dir + rename. Sync
  'not-a-dir'      continues from the freshly-cloned head.
  - 'corrupted'  → throw with structured hint pointing at sources remove
                   + add (no syncing wrong state).
  - 'url-drift'  → throw with hint pointing at the (deferred) sources
                   rebase-clone command.

Closes the operator-confidence gap: rm -rf $GBRAIN_HOME/clones/<id>/ no
longer breaks future syncs. The next sync sees the missing dir and
recovers via the recorded URL.

src/core/operations.ts: extend ErrorCode with 'unknown_transport' so
whoami's Q3 fail-closed path types check.

test/sources-resync-recovery.test.ts (12 tests): full validateRepoState
state matrix exercised under fake-git, recloneIfMissing recovery from
each degraded state, idempotent on healthy clones, the sync.ts:320
integration path that drives the recovery.

test/sources-ops.test.ts + test/sources-mcp.test.ts: drop the
GBRAIN_PGLITE_SNAPSHOT-disable line so these tests stop forcing cold
init across the parallel-shard runner. With snapshot allowed, init time
drops from 6+s to ~50ms and parallel runs stay under the 5s hook
timeout.

test/sources-mcp.test.ts: tighten scope literal-type so tsc keeps the
union narrow.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(cli): sources add --url + restore re-clone, thin-wrapper refactor

src/commands/sources.ts now delegates the data-mutation work to
src/core/sources-ops.ts (added in the previous commit). The CLI handler
parses argv, calls into addSource, and formats output.

Two new flags on `gbrain sources add`:
  - `--url <https-url>` : federated remote-clone path (clone + INSERT +
    rename, atomic rollback on failure).
  - `--clone-dir <path>` : override the default
    $GBRAIN_HOME/clones/<id>/ destination.

Validation rejects mutually-exclusive `--url` + `--path`. Errors from
the ops layer (SourceOpError) propagate through the CLI's standard
error wrapper in src/cli.ts so existing tests that assert throw shape
keep passing.

`gbrain sources restore <id>` (T4 from eng review): if the source has a
remote_url AND the on-disk clone was autopurged, call recloneIfMissing
before declaring success. Clone errors print a WARN with recovery
hints rather than failing the restore — the DB row is what restore
guarantees; the clone is best-effort.

54 sources-related tests pass (existing test/sources.test.ts +
sources-ops + sources-mcp).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(doctor,cycle): orphan-clones surface + autopilot purge phase (P1)

addSource's atomicity contract uses a temp dir that gets renamed to the
final clone path. If the process is SIGKILL'd between clone-finish and
rename, the temp dir orphans on disk. Without sweeping these, a brain
server accumulates gigabytes over months of failed `sources add --url`
attempts.

Two layers:

1. `gbrain doctor` now surfaces stale entries. A new orphan_clones check
   walks $GBRAIN_HOME/clones/.tmp/, names anything older than 24h, and
   prints a warn with disk-byte estimate. Operators see the leak before
   `df` complains.

2. The autopilot cycle's existing `purge` phase grows a substep that
   nukes .tmp/ entries past the same 72h TTL the page-soft-delete purge
   uses. Operator behavior stays uniform across all soft-delete-style
   surfaces.

Both layers are filesystem-only (no DB). On a brain that never used
--url cloning, both are no-ops.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* build(admin): scope checkboxes source from scope-constants mirror + dist

admin/src/pages/Agents.tsx Register Client modal:
  - useState default sources from ALLOWED_SCOPES_LIST (defaulting `read`
    to true, others false; unchanged UX for the common case).
  - Scope checkbox map iterates ALLOWED_SCOPES_LIST instead of the old
    hardcoded ['read','write','admin'].

Without this commit, even with the v0.28.1 server-side scope hierarchy,
operators registering an OAuth client from the admin UI cannot tick the
new sources_admin / users_admin scopes — defeats the whole gstack
/setup-gbrain Path 4 unblock.

The drift-check CI gate (scripts/check-admin-scope-drift.sh) ensures
this list stays in sync with src/core/scope.ts going forward.

admin/dist/* rebuilt via `cd admin && bun run build`. Old hash bundle
removed; new bundle (224.96 kB / 68.70 kB gzip).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: v0.28.1 — remote-source MCP + scope hierarchy + whoami

VERSION + package.json: bump to 0.28.1 (per CLAUDE.md branch-scoped
versioning rule — this branch adds substantial new features on top of
v0.28.0).

CHANGELOG.md: new top-level entry for v0.28.1 in the gstack/Garry voice
(no AI vocabulary, no em dashes, real numbers + commands). Lead
paragraph names what the user can now do that they couldn't before.
"Numbers that matter" table calls out the +5 MCP ops, +2 OAuth scopes,
and the 4-to-0 SSH-step number for gstack /setup-gbrain Path 4. "What
this means for you" closer ties the work to the operator workflow shift.
"To take advantage of v0.28.1" block has paste-ready upgrade commands
including the admin SPA rebuild step. Itemized changes section
describes the architecture cleanly without exposing scope-string
internals to public attack-surface enumeration (per CLAUDE.md
responsible-disclosure rule).

TODOS.md: file 6 follow-ups under a new "Remote-source MCP follow-ups
(v0.28.1)" section: token rotation, migration introspection in
get_health, Accept-header friendliness, sources rebase-clone for
URL-drift recovery, --filter=blob:none partial-clone option, and the
chunker_version PGLite-schema parity codex caught.

README.md: short subsection under the existing sources CLI listing
that names the new --url flag and what auto-recovery does. Capability
framing (no scope-string enumeration).

llms.txt + llms-full.txt: regenerated via `bun run build:llms` so the
documentation bundle reflects the v0.28.1 entry. The build-llms
generator's drift check passes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(e2e): sources-remote-mcp — full gstack /setup-gbrain Path 4 round-trip

Spins up `gbrain serve --http` against real Postgres with a fake-git binary
in PATH (so `git clone` is exercised end-to-end without network), registers
two OAuth clients (sources_admin + read-only), mints tokens, calls the new
v0.28.1 MCP ops via /mcp, and asserts the gstack /setup-gbrain Path 4 flow
works end to end.

12 tests cover the full lifecycle:
- whoami over HTTP MCP returns transport=oauth + the right scopes
- /.well-known/oauth-authorization-server advertises all 5 scopes
- sources_add: clone fires, INSERT lands, row carries config.remote_url
- sources_status: clone_state=healthy after add
- sources_list: surfaces remote_url for the new source
- SSRF rejection: sources_add with RFC1918 URL fails at parseRemoteUrl gate
- Scope enforcement: read-only token gets insufficient_scope on sources_add
- Read-only token CAN call sources_list (read-scoped op)
- ALLOWED_SCOPES allowlist: CLI register-client rejects bogus scope
- Recovery: rm clone dir + sources_status reports clone_state=missing
- sources_remove: cascades + cleans up the auto-managed clone dir

Subprocess env threading replicates the v0.26.2 bun execSync inheritance
pattern — bun does NOT inherit process.env mutations, so every CLI
subprocess call passes env: { ...process.env } explicitly.

Cleanup contract mirrors test/e2e/serve-http-oauth.test.ts: revoke any
clients we registered, force-kill the server subprocess on SIGTERM
timeout, surface cleanup failures to stderr without throwing so real
test failures aren't masked.

The base table list in helpers.ts (ALL_TABLES) doesn't include sources
or oauth_clients, so this test explicitly truncates them in beforeAll
to avoid Q4 pre-flight collisions on re-run.

Skipped gracefully when DATABASE_URL is unset.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix: codex adversarial review — confine remote sources_admin + close SSRF gaps

Pre-ship adversarial review (codex exec) caught five issues. Four ship in
this commit; the fifth (DNS rebinding) is filed as v0.28.x follow-up.

CRITICAL — `sources_admin` tokens over HTTP MCP could plant content at any
host path. The MCP op exposed `path` and `clone_dir` to remote callers; the
op layer trusted them verbatim, then auto-recovery's rm -rf on degraded
state turned that into arbitrary delete primitives. src/core/operations.ts
sources_add handler now drops both fields when ctx.remote !== false. Local
CLI keeps the override (operator trust). Loud logger.warn when a remote
caller tries — visible in the SSE feed without leaking values.

HIGH — Steady-state `git pull --ff-only` bypassed GIT_SSRF_FLAGS entirely.
The legacy helper at src/commands/sync.ts:192 spawned git without the
-c http.followRedirects=false -c protocol.{file,ext}.allow=never
--no-recurse-submodules set that cloneRepo applies. Every recurring sync
was reopening the redirect/submodule/protocol bypass. Routed the call site
at sync.ts:381 through pullRepo from git-remote.ts so initial clone and
ongoing pull share one defensive flag set.

MEDIUM — listSources ignored its `include_archived` flag. The op
advertised the param but the function destructured it as `_opts` and
queried every row. Archived sources' ids, local_paths, and remote_urls
were leaking to read-scoped MCP callers by default. Filter in SQL
(`WHERE archived IS NOT TRUE` unless the flag is set) so archived rows
never reach the wire.

PARTIAL HIGH — IPv6 ULA fc00::/7 and link-local fe80::/10 were not in
the isInternalUrl bypass list. Only ::1/:: and IPv4-mapped IPv6 were
blocked. Added regex-based ULA + link-local rejection to url-safety.ts.

Test coverage:
- test/git-remote.test.ts: 4 new IPv6 cases (ULA fc-prefix + fd-prefix,
  link-local fe80::, public IPv6 still allowed).
- test/sources-mcp.test.ts: 3 new cases pinning the remote/local
  asymmetry (clone_dir override silently ignored over MCP, path nulled,
  local CLI keeps the override).
- test/sources-mcp.test.ts: 2 new cases for include_archived honored.

DNS rebinding (codex finding #3): the current gate is lexical only.
A deliberate attacker who controls a hostname's A/AAAA records can still
resolve to an internal IP. Closing this requires async DNS resolution +
revalidation; filed as v0.28.x follow-up in TODOS.md so the API change
surface (parseRemoteUrl becomes async, every caller updates) lands in
its own PR.

323 tests pass (9 files); 4071 unit tests pass (full suite).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: rebump v0.28.1 → v0.28.2 (master collision)

Caught after PR creation. master is at v0.28.1 already; this branch
forked from garrytan/v0.28-release at v0.28.0 and naively bumped to
v0.28.1 without checking the master queue. CI version-gate would have
rejected at merge time (requires VERSION strictly greater than
master's).

Root cause: I bumped VERSION mechanically during plan implementation
(echo "0.28.1" > VERSION) without consulting the queue-aware allocator
at bin/gstack-next-version. /ship Step 12's idempotency check then
classified state as ALREADY_BUMPED and the workflow's "queue drift"
comparison was the safety net I should have hit — but I skipped it.

Files updated:
- VERSION + package.json: 0.28.1 → 0.28.2
- CHANGELOG.md: header + "To take advantage of v0.28.2" subsection
- README.md: sources --url note version reference
- TODOS.md: 7 follow-up entries' version references
- llms.txt + llms-full.txt: regenerated

PR title rewrite via gstack-pr-title-rewrite.sh handled in a separate
gh pr edit call; CI version-gate now passes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-06 21:14:34 -07:00