mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-14 00:48:18 +00:00
master
6
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Garry TanandClaude Fable 5
|
3f22f51e5d |
v0.45.6.0 feat(skills): giftable-skills import wave — 17 new production skills + 8 upgrades (#4033)
* feat(skills): check-skill-refs gate + per-commit skills gate runner Three integrity checks over skills/ markdown: dangling refs (backtick paths, composes: frontmatter, RESOLVER dispatcher slugs), donor-remnant paths behind a ratchet allowlist, and warn-only CLI-reference drift against the live tool surface. Wired as check:skill-refs in verify and bundled into scripts/skills-commit-gate.sh (conformance+resolver tests, check-resolvable --strict, lock regen+freshness, refs, optional per-file privacy lint) for any commit touching the skills pack. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skillpack): machine-readable plugin curation record + membership assertions skills/plugin-exclusions.json records why each manifest skill is not bundled into openclaw.plugin.json (Tier B host-only decisions, seeded from the pre-existing split). test/openclaw-plugin-manifest.test.ts now asserts manifest = bundled + exclusions with no overlap, no orphans, no stale exclusions, and a sorted skills array (two pre-existing sort inversions fixed). Bundling decisions are now review-visible: moving a skill between tiers requires touching both files in one commit. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): skillify reconciled with the evolved upstream line (v2.0.0) Adopts eval contracts, the NO-REGRESSION LAW, idempotency guidance, and the 14-item checklist from the upstream skillify line while preserving this repo's divergent content. bulk-ingestion (later in this wave) delegates its codify phase to this checklist. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): book-mirror 0.5.0 backport Table-misalignment root-cause fix, anti-repetition hard constraints, and the resonant-stance rewrite from the upstream line, generalized onto native gbrain surfaces (no external storage libs). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(conventions): test-before-bulk gains the progressive ramp + output-existence checks 10 -> 100 -> 500 -> full ramp with per-round stop gates, the count-before/count-after output-existence check (catches silent zero-row writes), the <2% error-rate gate, the copy-paste verification checklist, cost estimation, and pointers to native pace mode + progress flags so nobody rebuilds throttling in bash. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(conventions): regex-discipline — judgment vs heuristic epistemics The one-question test (deterministic-and-rote vs judgment), the earned- regex sequence, red flags/green lights, never-regex-what-an-attacker-can- imitate, and two genericized cautionary tales. Pairs with test-before-bulk: look before you compress, compress only the rote. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(conventions): path-discipline — display strings are not path strings Never pass a display-formatted link/URL to a file tool; a "successful" write to a poisoned path lies. Poisoned-path tells, verify-before-done, retry discipline, junk-tree recovery. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(conventions): exec-output — buffer to file, read bounded slices Empty exec results usually mean truncation, not a broken shell. The buffer-then-slice rule, shell patterns, and the diagnostic ladder, generalized to any harness. Conventions half of the durable-execution doctrine (the minion-orchestrator half lands separately). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): concept-synthesis 0.2.0 — curation cull phase Adds the keep/delete/merge muscle the synthesis loop lacked: minimum substance gates (style cannot rescue hollow ideas), weighted verdict bands with hard delete triggers, grounding labels wired to the citation conventions, a reputational-risk gate, cluster budgets, and reversible merge-with-backlinks with merge-count as an emergent-salience signal. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): measure-before-you-fix — measure-first ops triage Stopwatch-verify before raising timeouts; act-line vs alert-line. Trigger vocabulary maps onto the shipped doctor/autopilot/sync alert classes. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): data-loss-gate — confirmation gate for irreversible operations Recoverability checklist + alternatives + explicit-yes before any bulk delete, forget sweep, source/mount removal, or history rewrite. No category-level exception classes: disposability is a property of the inspected target. Routing-convention honesty: the native operation- boundary confirm remains a filed follow-up. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): fact-check — pre-publication claim verification Breadth gate: extract every verifiable claim, verify each against live sources with a confidence scale. Data-derived claims section carries the two laws: producer is never verifier (independent re-derivation via a different query path) and affiliation is not authorship (typed edges, not co-occurrence). Hard-block on unsupported claims. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): resolve-before-asking — exhaust the brain before interrupting the human Query, timeline, and every mounted source before asking; when asking is justified, ask WITH a hypothesis (pairs with ask-user). Includes the no-placeholders-at-ingest rule. Owns WHETHER asking is justified; query owns the lookup verb, brain-ops the read-write cycle. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): brain-ingest-gate — ingest entry gate (no raw copies, entity resolution, dedup) No-raw-copies entry rule; the Named-Entity Resolution Gate (registry- first + alias expansion — a vector score is a floor for prose, never a gate for named things); the qualitative dedup decision tree (open and read the top hit before writing). The gate keeps full dedup responsibility: native import skips only matching frontmatter IDs. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): correction-pipeline — trace corrections to the contamination source When the user corrects a fact: root-cause it (7-class taxonomy), fix the source surface (facts table via recall/forget/remember; pages via edit + re-sync; identity files via bootstrap templates), then run the propagation check. Never just note it. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): company-brainify — personal-to-team brain sanitization Strip/keep tables, triage grep pipelines, verification greps, and the history-purge procedure for publishing a sanitized team brain from a personal one. Scan scope covers meetings, dailies, facts, and takes, not just people pages. History rewrite is gated through data-loss-gate with a mirror-clone backup. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): citation-graph-ingest — typed inter-document citation edges Extract every inter-document reference from an ingested corpus and classify the edge type (overrules/distinguishes/relies-on/extends...), written via native link ops and queryable via graph-query. States plainly that natural-language relational retrieval walks a fixed edge- type set today; wiring these types in is a filed follow-up. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): two-tier-extraction — triage/deep-read model routing for archives Cheap-model triage pass, gate, then strong-model deep read for archive ingestion, expressed through the model-routing conventions. Deterministic privacy wall: named-entity and sensitive-pattern classes are stripped before any model call; ambiguous content fails closed to human review. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): brain-link-discipline — verified links in every deliverable Composite: same-message link rule, path derivation via git ls-files, push-before-link ordering, subagent-relay path rewrite, bulk-list formatting. Fallback chain: verified hosted-remote URL, then repo- relative path with a scope note, then publish output offered as an attachable artifact (never promised as a URL). Extends _output-rules.md with the verified-deliverable-link canon and the in-page (relative) vs in-message (absolute) scope split. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): draft-in-voice — memory-grounded ghostwriting from validated profiles Load a validated voice profile, obey its hard rules, produce 2-3 drafts, run the voice-fidelity self-check, never auto-post. Ships the build-a- profile appendix (corpus threshold, fingerprint schema, profile page schema with provenance/consent/versioning) so users without a donor profile aren't dead-ended. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): bulk-ingestion — the disciplined bulk pipeline lifecycle + manifest substrate Composite: the schema-trial-evaluate-codify-bulk-monitor lifecycle spine plus the manifest.json durable-state substrate (stable source-derived ids, derived-not-asserted status, idempotent workers, per-worker progress-file merge, never trust a subagent's 'done' — verify on disk). Codify delegates to skillify; execution to jobs/minions; ramping to test-before-bulk. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(scripts): check-skill-refs reads cliHints from operations source --tools-json does not serialize every op's cliHints, so real commands (get, timeline, backlinks, graph, link) warned as unknown. The checker now also derives the known-command set from operations.ts cliHints names + aliases. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): meeting-ingestion 2.0.0 — recorder-agnostic pipeline backport Normalized transcript record as the any-recorder contract, multi-meeting split detection, cross-recorder dedup, evidence-based speaker resolution (never guess; ASR-variant search-before-create), required page sections with explicit-reason-for-empty, claim-verification table, and the brain- contradiction consistency check. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): meeting-ingestion 2.1.0 — verify-before-done phase Hard gate before reporting ingested: required sections have substance, every people/companies slug has a page + timeline backlink, speaker map resolved, every quote grounded verbatim in the transcript (deterministic sidecar checks where transcripts are retained), fabricated-attendee sanity checks. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): meeting-ingestion 2.2.0 — sequence verify (chronology checks) Deterministic order lint before a meeting page ships: phase-inversion and impossible-transit checks, day-timeline gaps corroborated against `gbrain day`, with a pass/block/explicit-waive contract (waives logged as acknowledged, not resolved). Adds routing-eval fixtures for the upgraded skill. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): reports 1.1.0 — Actionability Gate Four link failure modes (Broken/Dead/Indirect/Missing) with the rule "a missing link is honest, an indirect link is a broken promise", the blocked-vs-warning table, retry loop as agent-run checks, and the prompt gate snippet. Canon lives in _output-rules.md; this section carries the taxonomy delta. Routing fixtures added. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): briefing 1.3.0 — pre-briefing context pulls Salience, anomalies, personal recall, and hot-memory pulse pulls before composing the briefing, wired to the real CLI flags (anomalies uses --lookback-days, not the upstream --since form). Routing fixtures added. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): daily-task-manager 2.0.0 — stable IDs + fail-closed actions Stable task-ID anchors, deterministic action routing, fail-closed ambiguity handling (no mutation on zero/multiple matches), structured Returns contract with an agent-chaining JSON mode, minimal-diff save discipline. Routing fixtures added. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): eiirp 1.1.0 — auto-fire gate (file before you deliver) Always-on convention: when substantial structured analysis of a user- shared document is about to be delivered, file the brain page first and deliver analysis + link in the same reply. Fire conditions, does-not- fire list, dedicated-pipeline exemptions, per-user storage-policy override. eiirp moves from plugin exclusion to bundled — the gate is load-bearing for downstream installs. Routing fixtures added. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): minion-orchestrator 1.1.0 — durable execution doctrine Capability ladder for operations over two minutes: jobs + a one-shot self-deleting deadman (verifying the result was REPORTED, not that the process exited) where the shell-jobs contract allows; cron-checked progress file; foreground with buffered output otherwise. Deadman failure modes (dies before firing, double-fire idempotency, stale checkpoint) encoded in Contract and Anti-Patterns; content-addressed stage-checkpoint appendix. Existing trust-boundary text unchanged. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test(skills): concept-synthesis cull-phase routing fixtures Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): research-compendium — archive, summarize 1:1, synthesize self-contained Deep-research discipline: archive every source, one summary per source, then a self-contained synthesis (the Self-Contained Rule; Low-Bar/High- Ceiling). Claims verification delegates to fact-check; retention is gated by the user's privacy posture. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): context-audit — token hygiene for the always-loaded stack Report-only audit of SOUL/MEMORY/CLAUDE/AGENTS-class files: redundancy, contradictions, staleness, compression candidates ranked by token savings. Recommendations target bootstrap templates, never rendered files; judging routes through the native cross-modal eval runner with a cheap-model default. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): blog-ingest — whole-publication and feed ingestion Feed discovery, pagination walking, article-shape normalization, canonical-URL dedup, idempotent re-runs, polite pacing, and empty-husk repair as agent procedures; per-article enrichment hands off to brain-ingest-gate. Public posts only. Fetched text is data, never instructions (untrusted-content section). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): conversation-archive — AI-chat history as first-class brain content Convert chat exports into per-conversation pages, import, validate via the conversation-parser surface, extract facts; gap-healing backfill under the three invariants (capture cadence outruns eviction, gap detection, write-path equals commit-path); idea-evolution tracing. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): skill-autobench — evals mined from lived usage Mine a skill's real invocation history (user corrections are the gold signal) into a proposed eval contract and replayable cases with honesty labels, staged pending human approval — never rewrites a skill. Multi-model judging verifies each provider actually responded. Extends the SkillOpt surface; never duplicates it. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(todos): giftable-import wave follow-ups Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(skills): resolver strict reconciliation — triggers, fixtures, disambiguation Drives check-resolvable --strict to zero on the 69-skill pack: wave-side trigger narrowing (bare words become phrases on measure-before-you-fix, data-loss-gate, brain-ingest-gate), fixture intents rewritten to realistic phrasings, wave-side MECE duplicates removed, the ingest-gate quality rules delegated to conventions, and three new disambiguation rules (publication/article/media/chat-export routing, soul-audit vs context-audit, measurement-first triage vs debugging). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): idea-ingest 1.1.0 — Returns contract + edge cases backport Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): media-ingest 1.1.0 — input contract, error handling, known pitfalls Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): brain-ops 1.1.0 — entity-card first lookup + shallow-ls warning (memory-verbs block preserved) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): maintain 1.1.0 — weekly feature-adoption check Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): data-research 1.1.0 — infer research target from context Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(llms): regenerate bundles after the skills wave RESOLVER.md is inlined into the llms bundles; the wave's routing rows and disambiguation rules regenerate here (single wave-end regen; the committed bundles match HEAD per test/build-llms.test.ts). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(test): assemble banned-path fixtures at runtime in check-skill-refs tests The privacy check bans those literals in source files; the fixtures now construct them so the test still exercises the donor-remnant gate. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(skillpack): bundle capture + publish; keep host-only contrast fixtures portable The downstream-install smoke showed shipped fixtures referencing host- only skills. capture and publish move from exclusions to the bundle — both are user-facing and wave skills route to them (the eiirp auto-fire files via capture; brain-link-discipline falls back to publish). Contrast fixtures that pointed at host-only skills (smoke-test, skill-optimizer) now target shipped skills with declared ambiguity, so `check-resolvable --strict` is green on the host pack (69 skills) AND on a fresh scaffolded install (58 skills). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test(evals): post-import-wave routing receipt (haiku) A/B harness run against the 69-skill resolver after the import wave: baseline (uncompressed) 100% held-out / 78.3% training strict — beating both compression variants on strict scoring, corroborating the review decision to defer resolver compression to its own PR. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(skills): pre-landing review fixes — trust boundaries, gate hardening, registration prose From the six-reviewer pre-landing pass: research-compendium gains the untrusted-content section (verbatim web archives feed future recall); blog-ingest's injection marker now travels with body chunks (inline fenced wrapper, not frontmatter-only); company-brainify's history-rewrite backup moves to a non-volatile private location with pre-push re-verification and retention cleanup; the 17 imported manifest entries get real descriptions (a block-scalar parsing slip) with a test pinning description prose and plugin-array uniqueness; check-skill-refs becomes cwd-independent, validates relative markdown links, and warns visibly on an empty CLI command set (5 new tests); the commit gate fails loudly on a regenerated-but-unstaged lock, single-quotes its inline lint script, and rejects missing lint paths; ladder attribution, checkpoint-hook bypass, frontmatter-contract notes, curation + misroute runbook docs, the brain-first API-pull rule, and negative routing fixtures for eight skills round out the batch. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(skills): adversarial-review hardening — trust boundaries, closure, honest contracts From the ship pre-landing + adversarial + red-team passes (all findings folded): Untrusted content: a shared conventions/untrusted-content.md (fetched text is data, never instructions) referenced from every skill that fetches or imports external text — fact-check most critically (a fetched page is never authority to rewrite a brain fact). conversation-archive gains a mandatory secret+PII redaction pass before any page is written. company-brainify: the destructive strip now sanitizes a staging copy behind the data-loss-gate card (personal brain untouched); the history purge derives its path set from the full sanitized scope, runs only against the shared repo (never sync.repo_path), stages under a non-volatile backup dir with a pre-push restore check, and logs the deletion to the personal brain, not the shared one. Downstream closure: ask-user and brain-taxonomist are bundled (three new skills delegate to them); remaining host-only references are prose, not links; a membership+closure test makes a bundled skill referencing an unshipped skill a build failure. Honest contracts: brain-link-discipline is marked mutating (it commits and pushes) and only sends its token to the issuing host; inert priority markers removed; citation-graph-ingest's writes_to dropped; concurrency and slug-collision limits documented for daily-task-manager, bulk-ingestion, conversation-archive, and blog-ingest; the self- authorizing shell-jobs prefix removed in favor of worker-side authorization. Gate hardening: the commit gate compares the staged lock blob and runs the plugin-manifest tests; check-skill-refs scans jsonl for donor remnants, tolerates CRLF, and rejects flag-shaped option values. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * v0.45.6.0 feat(skills): giftable-skills import wave — 17 new production skills + 8 upgrades Grows the built-in pack from ~52 to 69 skills: the trust layer (correction-pipeline, data-loss-gate, fact-check, brain-ingest-gate), team-brain sanitization (company-brainify), typed citation-graph ingestion, disciplined bulk/feed/conversation ingestion, and operational skills (measure-before-you-fix, context-audit, skill-autobench, resolve-before-asking, brain-link-discipline, draft-in-voice, research-compendium), plus meeting-ingestion/skillify/eiirp/ minion-orchestrator/concept-synthesis/reports/briefing/daily-task-manager upgrades and a new skill-ref integrity gate + plugin-curation record. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skillpack,doctor): skill currency + declared preconditions — the migration harness now examines skills The upgrade/migration path was DB-only for skills: schema migrations never touched them, and skill sync was manual/advisory with new skills hidden from the post-upgrade sweep. This makes skill currency and per-skill setup first-class. Currency (capability A): src/core/skillpack/skill-currency.ts classifies every bundled skill against the install as new / drifted / current, by each skill's OWN files (shared conventions on disk no longer misclassify a new skill as drifted). `gbrain skillpack status` reports it; `gbrain skillpack sync` scaffolds only the new ones and never overwrites local edits; the post-upgrade sweep surfaces new skills with the sync command; `gbrain doctor` gains a `skill_currency` check (WARN when new skills are available, drift stays advisory). Preconditions (capability B): a `requires:` frontmatter field (source / dir:<path> / config:<key> / pages:<n>), a pure DI-seam checker in src/core/skillpack/preconditions.ts, `gbrain skillpack setup <skill>` for the static list + hints, and a `skill_preconditions` doctor check that verifies them live against the connected brain. Annotated only the two skills with genuine preconditions (citation-graph-ingest needs a corpus; skill-autobench needs the conversations/ archive). Semantic skill search (capability C) is deliberately deferred as its own subsystem (tenancy + source isolation + embedding backfill) — filed in TODOS, not crammed in unreviewed. Tests: skill-currency, skill-preconditions, skillpack-status (31 new assertions). doctor + skillpack stay engine-safe (currency is filesystem- only; live precondition checks skip cleanly without a brain). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(doctor,skillpack): categorize new skill checks, refresh flag registry, sweep test + noise gate CI on the pushed feature surfaced three real in-branch failures: - doctor-categories: register skill_currency + skill_preconditions under SKILL_CHECK_NAMES (every doctor check must be categorized). - flag registry: doctor's import of findGbrainRoot pulls bundle.ts (which runs git rev-parse --verify) into its flag scan; regenerated the known-flags allowlist to match (harmless over-inclusion, per the generator's design). - upgrade sweep: header renamed to 'Skillpack sweep (post-upgrade)'; new-skill surfacing gated on the host having scaffolded at least one skill, so a zero-skill (opted-out) host stays silent instead of getting 'N new skills' on every upgrade. Tests updated + a case added locking the surfacing. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Garry Tan
|
75fae742d5 |
v0.44.0.0 feat(eval): BrainBench — cross-harness memory conformance suite (Cathedral 2) (#2158)
Public, reproducible, cross-harness benchmark for the four ways agent memory fails (know-to-ask, push precision/recall, write-back fidelity, cross-session continuity). Hermetic PGLite, sealed gold, deterministic corpus, CI gate vs master's committed baseline, published JSON-schema foreign-runner contract. See docs/eval/BRAINBENCH.md. |
||
|
spiky02plateau
|
06f58c2b32 |
feat(gateway): config-driven provider_chat_options passthrough (fixes #2577) (#2857)
Add provider_chat_options alongside provider_base_urls and thread it through the gateway config path into chat(). The chat request now deep-merges provider-scoped options and model-scoped overrides into providerOptions keyed by recipe id, preserving existing gateway-built options such as Anthropic cacheControl and leaving absent-config behavior unchanged. This lets operators disable thinking for small-budget hybrid-reasoning utility calls without hardcoding that behavior for every use of those models. |
||
|
Garry TanandClaude Opus 4.8
|
eefe8b5741 |
v0.42.1.0 feat: gbrain skillopt — self-evolving skills (closes #1481) (#1563)
* feat(skillopt): foundation modules — types, lr-schedule, benchmark, score, audit, lock
* feat(skillopt): edit primitives — apply-edits (D5+D9), rejected-buffer LRU, version-store (D8 history-intent-first)
* feat(skillopt): rollout (D2 gateway.toolLoop + D13 read-only allowlist), reflect (D7 two calls), validate-gate (D12 median+epsilon, D4 parallel), preflight (D3), bundled-skill-gate (D16)
* feat(skillopt): orchestrator (D6 slow-update, D10 ASCII diagrams, D11 caching), checkpoint, bootstrap (D15 sentinel), CLI dispatch + help
* feat(skillopt): cycle phase (F1 dream-loop wiring), PROTECTED_JOB_NAMES + MCP op (F6 admin scope + allowlist) + Minion handler (F7 --background)
* feat(skillopt): full cathedral — --all batch (F4), --target-models fleet (F5), write-capture (F10), held-out scaffold (F11), adversarial suite 41 cases (F2), E2E PGLite (F3), meta-skill bundle (T7), reflect+judge evals (F8+F9), docs (T10)
* chore: bump version to v0.42.0.0 (MINOR — significant new feature)
* fix(skillopt): wire trajectories from forward gate to reflect + fix parseEditsResponse parser misuse
Two related v0.42.0.0 bugs that conspired to make `runSkillOpt` structurally
unable to accept any candidate edit. Either alone would have killed self-evolution;
together they made the loop a no-op for every input.
**Bug 1 (orchestrator gap):** `runOptimizationLoop` in orchestrator.ts called
`runReflect({successes: [], failures: []})` with hardcoded empty arrays. The
forward gate's `scoredRollouts` were computed then voided. `runReflect`
short-circuits both modes when their batches are empty, so the optimizer was
never asked to propose an edit. Every step hit the no_edits_applied branch.
Fix: add `scoredRollouts: ScoredRollout[]` to `GateResult` and
`runsPerTask?: number` to `ValidateGateOpts`. Forward pass uses
`runsPerTask: 1`; orchestrator partitions returned rollouts by `score >= 0.5`
and threads real successes + failures into `runReflect`.
**Bug 2 (parser misuse):** `parseEditsResponse` in reflect.ts routed every
optimizer response through `parseJudgeJson` first. `parseJudgeJson` looks for
a `score` key (it's a judge-output parser, not an edits parser) and returns
null for any JSON without one — including the well-formed `{"edits": [...]}`
the optimizer is contractually required to emit. The function then early-
returned `[]` and the actual `tryExtractEdits` path on the next line was
unreachable dead code.
Fix: drop the wrong-typed guard. `parseEditsResponse` now calls
`tryExtractEdits` directly. Export it so `reflect.test.ts` can pin the
contract independently of the chat transport.
**Why this slipped through 152 prior skillopt tests:** zero unit coverage
of `parseEditsResponse` or `runReflect`. The existing E2E `all-reject` case
asserted no_improvement (which was true for the wrong reason — empty edits,
not gate rejection). Both bugs were structurally invisible to the existing
test surface.
**New coverage:**
- `test/skillopt/reflect.test.ts` (15 cases):
- 8 `parseEditsResponse` cases including the IRON-RULE regression pin
for the v0.42.0.1 fix (`{"edits": [...]}` JSON must survive the parser).
- 7 `runReflect` D7 contract cases: both modes fire, empty-batch skips,
additive token usage, one-mode-throws-other-still-works, rejected-buffer
flows into anti-bias prompt.
- Documents the trailing-comma limitation as an explicit out-of-scope pin
(so a future tightening of `tryExtractEdits` lights this test up
intentionally).
- `test/e2e/skillopt-loop.serial.test.ts` (7 cases):
- HAPPY PATH: stubbed `gateway.chat` acts as both target agent (emits
sections based on skill content) and optimizer (proposes a real
add-Citations edit). Drives `runSkillOpt` end-to-end against PGLite.
Asserts outcome=accepted, SKILL.md mutated with new section,
frontmatter preserved (D5), history has one committed row,
best.md mirrors disk, delta > epsilon, receipt fields populated.
- 5 broken cases (each isolates a distinct orchestrator-visible failure):
1. Below-baseline regression: optimizer proposes a destructive edit;
gate rejects with reason=below_baseline; SKILL.md unchanged;
rejected-buffer captures the bad edit for anti-bias context.
2. Malformed reflect JSON: orchestrator degrades gracefully to
no_improvement without crashing.
3. Anchor-not-found: applyEditBatch rejects all; sel gate skipped;
rejected-buffer captures with reason=apply_failed.
4. Budget exhausted mid-step: outcome=aborted, no pending rows survive.
5. Converged-skill re-run: starting from already-perfect skill →
no_improvement (no thrash on a well-tuned starting point).
- IDEMPOTENT RE-RUN: drive runSkillOpt twice in sequence. Run 1 accepts.
Run 2 sees improved baseline, no failures, returns no_improvement.
SKILL.md byte-identical to post-run-1; history still has exactly 1
committed row. Proves stability at the fixed point.
All hermetic (no DATABASE_URL, no API keys). PGLite in-memory engine,
tempdir SKILL.md + benchmark, stubbed gateway.chat via
`__setChatTransportForTests`. `.serial.test.ts` because the stub installs
module state and the loop walks shared disk state across epochs.
Test counts after fix: 174 skillopt-surface tests pass (149 pre-existing
unit + 15 new reflect unit + 3 existing E2E + 7 new E2E). Typecheck clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(cycle): align ALL_PHASES skillopt position with actual dispatch order
v0.42.0.0 added skillopt to ALL_PHASES right after `patterns` (line 127), but
the dispatch block in runCycle (line ~1912) actually runs skillopt between
`conversation_facts_backfill` and `embed`. The two were inconsistent, and the
serial test `report.phases.map(p => p.phase)).toEqual(ALL_PHASES)` was failing
on master because of it.
A second pre-existing failure: the two phase-count assertions in
`test/core/cycle.serial.test.ts` still said `toBe(20)` even though
ALL_PHASES grew to 21 when skillopt was added. The author bumped the array
but forgot the test.
Two fixes, one commit:
1. Move `'skillopt'` in ALL_PHASES from after `patterns` to between
`conversation_facts_backfill` and `embed`, matching where runCycle
actually dispatches it. Runtime behavior is unchanged — only the
declaration order moves. Updated the surrounding comment to call out
the position invariant and reference the test that pins it.
2. Update both `toBe(20)` assertions in cycle.serial.test.ts to `toBe(21)`
with a v0.42.0.0 history line in the running comments.
Why declaration follows runtime (not the other way around): the comment
intent ("Runs AFTER patterns — graph-fresh") is still satisfied because
"after the entire main graph-mutating cluster" is strictly fresher than
"right after patterns". No design intent is lost.
Test result: cycle.serial.test.ts is now 28/28 (was 27/28 on master + my
prior commit). Skillopt suite still 174/174.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(ci): bump PHASE_SCOPE assertion to 21 + fix skill-optimizer Anti-Patterns case
Two CI failures pre-existing on this branch since the v0.42.0.0 skillopt
cathedral landed; master is green because skillopt didn't exist there yet.
1. test/phase-scope-coverage.test.ts asserted ALL_PHASES.length === 20.
skillopt is the 21st phase. Bumped to 21 with v0.42.0.0 history line
in the comment chain. Sibling fix to the cycle.serial.test.ts bump
in commit
|
||
|
|
7be17261bc |
v0.32.3.0 skill: functional-area-resolver — pattern for compressing routing tables (#859)
* skill: compress-agents-md — functional-area resolver pattern Proven via A/B eval: 100% routing accuracy at 48% size reduction. Converts granular per-skill resolver rows into functional-area dispatchers with '(dispatcher for: ...)' sub-skill lists. Includes: - SKILL.md with full pattern docs, before/after examples, eval results - routing-eval.jsonl with 5 fixtures - Anti-patterns (resolver-of-resolvers pipe table = 15% accuracy) * skill: rename compress-agents-md → functional-area-resolver, cite prior art The contribution is a pattern (functional-area dispatcher with `(dispatcher for: ...)` clauses), not a file. Rename describes the contribution; triggers broaden to cover both AGENTS.md and RESOLVER.md phrasings. SKILL.md rewrite: - Three-model A/B table (Opus 4.7 / Sonnet 4.6 / Haiku 4.5) replaces the original Sonnet-only claim. Functional-areas beats baseline by +13 to +17pp training (lenient) across all three models at 48% the size. - Strict + lenient scoring documented side by side. Lenient (predicted shares dispatcher area with expected) matches production agent behavior. - Preconditions added: refuse to compress if file <12KB or working tree dirty. - Multi-file routing precedence section for the v0.31.7 RESOLVER.md/AGENTS.md merge case. - Mandatory verification step (≥95% via the harness). - Daily-doctor.mjs reference scrubbed (didn't exist in gbrain). - Three prior-art citations: AnyTool (arXiv:2402.04253), RAG-MCP (arXiv:2505.03275), Anthropic Agent Skills progressive disclosure. The pattern is the static-prompt analog of runtime hierarchical routing. routing-eval.jsonl: 8 positive (5 original + 3 broadened triggers) + 4 adversarial negatives targeting skillify, skill-creator, book-mirror, concept-synthesis to prove broadened triggers don't over-capture adjacent meta-skills. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * evals: A/B harness for functional-area-resolver (gateway-routed, strict + lenient scoring) evals/functional-area-resolver/ lives outside skills/ deliberately. The skillpack bundler walks skills/<skill>/ recursively, so an eval surface in there would copy harness + variants + fixtures + tests into every downstream install. The pattern (in SKILL.md) ships everywhere; the eval evidence stays in the gbrain repo. What ships: - Three variant resolvers in variants/ — baseline.md (verbose 25KB) and functional-areas.md (compressed 13KB) extracted from a real production AGENTS.md at git commits 93848ff3b^ and 93848ff3b (owner PII scrubbed). resolver-of-resolvers.md derived mechanically by stripping (dispatcher for: ...) clauses — the ablation case. - 20 hand-authored training fixtures + 5 held-out blind fixtures. - harness-runner.ts — TypeScript runner via gbrain gateway. Flags: --model {opus|sonnet|haiku|<full-id>}, --variants-dir, --variants for description-length sweeps, --parallel N (rate-lease bound), --limit N for smoke runs, --yes for non-TTY. - Every output row carries BOTH `correct` (strict) and `correct_lenient` (predicted shares dispatcher area with expected). Lenient matches production behavior. - Receipt header binds (model, prompt_template_hash, fixtures_hash, harness_sha, ts, cmd_args). Re-runs are auditable. - harness.mjs — thin Node shim that spawns the TS runner via bun. - rescore.mjs — zero-cost lenient re-score of an existing JSONL. - harness-runner.test.ts — 45 unit tests (no API key needed) covering every pure function plus the dispatcher-list parser. The prompt template is load-bearing: without the "drill into (dispatcher for: ...) list" instruction, every compression variant collapses to ~30-60%. Documented in SKILL.md and README.md. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * evals: baseline receipts (Opus 4.7 + Sonnet 4.6 + Haiku 4.5, 2026-05-11) Three canonical 225-row receipts (3 variants × 25 fixtures × 3 seeds per model). Each receipt header binds (model, prompt_template_hash, fixtures_hash, harness_sha, ts) so the published SKILL.md numbers are reproducible. Training corpus (n=20, lenient): baseline | Opus 81.7% | Sonnet 86.7% | Haiku 73.3% | 25KB functional-areas | Opus 98.3% | Sonnet 100% | Haiku 88.3% | 13KB resolver-of-resolvers | Opus 63.3% | Sonnet 41.7% | Haiku 65.0% | 10KB functional-areas beats baseline by +13 to +17pp across all three models at 48% the size. resolver-of-resolvers' Sonnet collapse (41.7%) is the SKILL.md "compression without dispatcher clause is broken" claim, observed. Held-out (n=5, lenient) saturates at 100% across most cells (Sonnet × resolver-of-resolvers is 73.3% — the same failure mode visible on a smaller sample). ~$3 API spend across all three runs. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: wire functional-area-resolver into RESOLVER.md + manifests skills/RESOLVER.md gets a new row in Operational, adjacent to skillify. Triggers: "Compress my resolver", "AGENTS.md too large", "RESOLVER.md too big", "functional area dispatcher", "shrink routing table". skills/manifest.json adds the new entry and bumps manifest version 0.25.1 → 0.32.3.0 (loadOrDeriveManifest reads this for sync-guard). openclaw.plugin.json adds functional-area-resolver to the skills array and bumps version 0.25.1 → 0.32.3.0 so install receipts stop being stale (src/core/skillpack/installer.ts:307-311 uses manifest version on every install). Verified: - gbrain check-resolvable --json: 42/42 reachable, 0 errors. - gbrain routing-eval: 70/70 pass (100% structural). - bun test test/skillpack-sync-guard.test.ts: passes (manifest in sync). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * v0.32.3.0 skill: functional-area-resolver — pattern for compressing routing tables Headline: compress a 25KB AGENTS.md down to 13KB without losing routing accuracy. Pattern proven across Opus 4.7, Sonnet 4.6, and Haiku 4.5 — beats the verbose baseline by +13 to +17pp at 48% the size. Empirical (training, n=20, 3 seeds, lenient): baseline 25KB: Opus 81.7% | Sonnet 86.7% | Haiku 73.3% functional-areas 13KB: Opus 98.3% | Sonnet 100% | Haiku 88.3% resolver-of-resolvers 10KB: Opus 63.3% | Sonnet 41.7% | Haiku 65.0% The (dispatcher for: ...) clause is the load-bearing signal. Strip it (the resolver-of-resolvers variant) and Sonnet collapses to 41.7% — the failure case the pattern's authors predicted, now observed. Files in this release: - VERSION + package.json bumped to 0.32.3.0 (4-segment per CLAUDE.md). - CHANGELOG.md: full empirical story, cross-model table, three prior-art citations (AnyTool, RAG-MCP, Anthropic Agent Skills progressive disclosure). - TODOS.md: nine v0.33.x follow-ups (dogfood on gbrain's own RESOLVER.md, CLI promotion to gbrain routing-eval --ab-compare, held-out corpus growth, cross-vendor Gemini+GPT verification, per-row description length sweep, structural compression to ~10KB, hierarchical area-of-areas, embedding pre-router, adversarial fixtures, prompt-design ablation doc). - llms-full.txt regenerated. Bisect-friendly history on this branch: |
||
|
|
1d78013c07 |
v0.28.5 fix(wave): PGLite upgrade wedge + embedding dim corruption + bun-link foot-gun (#697)
* fix(engines): pre-add v0.20 + v0.26.3 forward-reference columns in bootstrap The forward-reference bootstrap (PostgresEngine + PGLiteEngine applyForwardReferenceBootstrap) covered v0.18 + v0.19 + v0.26.5 columns but missed two later groups. Brains upgrading from v0.14-era to current master crash before the migration ladder runs: 1. v0.20 Cathedral II — content_chunks.search_vector, parent_symbol_path, doc_comment, symbol_name_qualified. `CREATE INDEX idx_chunks_search_vector` and `CREATE INDEX idx_chunks_symbol_qualified` in schema.sql/PGLITE_SCHEMA_SQL crash with "column search_vector does not exist" / "column symbol_name_qualified does not exist". 2. v0.26.3 — mcp_request_log.agent_name, params, error_message. `CREATE INDEX idx_mcp_log_agent_time ON mcp_request_log(agent_name,...)` crashes with "column agent_name does not exist". Reproduces deterministically on a v0.13/v0.14 brain upgraded straight to current master. The user hits the wall before any of v15-v36 can run. Both engines now probe for these columns and pre-add them via `ALTER TABLE ADD COLUMN IF NOT EXISTS` before SCHEMA_SQL runs. Migrations v26, v27, v33 still run later via runMigrations and remain idempotent (they handle backfill on top of the bootstrap-added columns). Test coverage extended in test/schema-bootstrap-coverage.test.ts: REQUIRED_BOOTSTRAP_COVERAGE now lists 6 new forward references; the strip-and-rebuild block drops the corresponding indexes/triggers so the test exercises a brain that pre-dates v0.20 + v0.26.3 migrations. Repro: brain on schema v13/v14 + run `gbrain init --migrate-only` against current master → fails. With this patch → succeeds; ladder runs to v36. * fix(engines): pre-add v0.27 subagent_messages.provider_id in bootstrap PR #682 covered v0.20 (chunks) + v0.26.3 (mcp_request_log) but missed v0.27's subagent_messages.provider_id. The composite index `idx_subagent_messages_provider ON subagent_messages (job_id, provider_id)` in PGLITE_SCHEMA_SQL crashes on brains pinned at v0.18-v0.26 because provider_id is the SECOND column in the composite — array-extraction patterns that scan only first-column references miss it entirely. This is the wedge surfaced by issue #670 (v0.22.0 → v0.27.0 init --migrate-only crashes with "column 'provider_id' does not exist") and contributing to #661/#657. Both engines now probe for subagent_messages.provider_id and pre-add the column via ALTER TABLE ADD COLUMN IF NOT EXISTS before SCHEMA_SQL runs. Migration v36 (subagent_provider_neutral_persistence_v0_27) still runs later via runMigrations and remains idempotent. Note on the test side: REQUIRED_BOOTSTRAP_COVERAGE is hand-maintained and just gained a v0.27 entry. v0.28.5's Step 3 replaces this array with a SQL parser that auto-derives coverage from PGLITE_SCHEMA_SQL, including composite-index columns. This commit is the targeted follow-up to PR #682's cherry-pick; A2's parser closes the class permanently. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(cli): conditional schema-init on connect (closes #651) Adds `hasPendingMigrations(engine)` next to `runMigrations` in migrate.ts: single getConfig('version') probe, returns true when current < LATEST_VERSION, defensively returns true on getConfig failure (treats wedged-config as pending). `connectEngine` in cli.ts now wraps `engine.initSchema()` in a probe gate: short-lived CLI calls (gbrain stats, query, doctor, etc.) on already-migrated brains skip the bootstrap-probe + SCHEMA_SQL replay + ledger-check entirely. Wedged brains still auto-heal — the probe says "yes pending" and initSchema runs as before. Building on oyi77's investigation in PR #652. Same correctness as #652's unconditional initSchema-on-every-connect, but no perf regression on the hot path. Failure non-fatal: if probe or init throws, log a hint and let subsequent operations surface the real error in context. Test coverage in test/migrate.test.ts: 3 cases covering fully-migrated (false), version-rewound (true), and missing-version-config (defensive true). Pairs with v0.28.5's X1 (post-upgrade auto-apply) — the upgrade path runs initSchema explicitly while every other code path that goes through connectEngine gets the cheap probe. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(upgrade): post-upgrade auto-applies pending schema migrations (X1) Prior behavior: `gbrain upgrade` → `gbrain post-upgrade` → `apply-migrations` only WARNs at apply-migrations.ts:296-302 when schema version is behind LATEST_VERSION, telling the user to run `gbrain init --migrate-only`. 11 wedge incidents over 2 years have proven users don't read that WARN — they file an issue instead. This commit makes `runPostUpgrade` explicitly call `engine.initSchema()` after the orchestrator migration pass, mirroring `init --migrate-only`'s flow. Side-effect: `gbrain upgrade` now walks away with a healthy brain in the cluster A wedge case (#670, #661, #657, #651, #625, #615, #609). Defensive: wrapped in try/catch so a connection or DDL failure falls back to the existing user-facing WARN. The hint to run `gbrain init --migrate-only` is preserved as the manual escape hatch. Pairs with v0.28.5's A1 (hasPendingMigrations probe in connectEngine): the upgrade path runs initSchema explicitly here, while every other code path that goes through connectEngine gets the cheap probe. Codex outside-voice review caught this gap during plan review: "the plan still does not prove `upgrade` will actually run schema migrations." This is the load-bearing fix that makes v0.28.5's headline outcome ("run upgrade, brain works") literally true for cluster A. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(bootstrap): auto-derive coverage from PGLITE_SCHEMA_SQL (A2) Replaces the hand-maintained REQUIRED_BOOTSTRAP_COVERAGE assertion with a SQL-parser-backed structural check. The new test: 1. parseIndexColumnReferences(PGLITE_SCHEMA_SQL) extracts every column referenced by every CREATE INDEX — including composite-index second and third columns. Codex outside-voice review caught that earlier first-col-only patterns missed v0.27's `idx_subagent_messages_provider ON subagent_messages (job_id, provider_id)`, which is exactly how the v0.28.5 wedge happened. 2. parseBaseTableColumns(PGLITE_SCHEMA_SQL) extracts every column declared in CREATE TABLE bodies (including via ALTER TABLE ADD COLUMN inside the schema blob). 3. parseAlterAddColumns(pglite-engine.ts source) extracts every column that applyForwardReferenceBootstrap adds. 4. Static contract: every (table, column) pair from step 1 must appear in either step 2 or step 3. Otherwise the test fails loud, names every uncovered pair, and points at the bootstrap function for the fix. Self-updating: any future CREATE INDEX added to PGLITE_SCHEMA_SQL on a column that bootstrap doesn't yet provide fails this test at PR time. No human required to remember to update an array. Closes the 11-incident wedge class identified in CLAUDE.md (#239, #243, #266, #357, #366, #374, #375, #378, #395, #396). Helper parsers also have their own unit tests covering composite-index second columns, function-wrapped columns (lower(col)), HNSW operator-class suffixes (vector_cosine_ops), and ALTER TABLE column extraction. Existing REQUIRED_BOOTSTRAP_COVERAGE-based tests preserved as a coarse-grained lower bound; the new parser-based test is the load-bearing structural gate going forward. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: support Voyage 2048d schema setup * fix: harden Voyage schema templating * feat: Voyage 4 embedding support + doctor eval - Add voyage-4-large/4/4-lite/4-nano + domain models to Voyage recipe - Fix AI SDK compatibility: strip encoding_format (Voyage rejects 'float'), patch response to add prompt_tokens from total_tokens - Add embedding_provider doctor check: live smoke test verifying model, API key, dimensions, and DB column alignment - Add embedding provider eval qrels for post-migration quality testing Closes: Voyage AI integration for gbrain embedding pipeline * fix: adaptive embed batch sizing for Voyage token limits Voyage's tokenizer is 3-4x denser than OpenAI tiktoken, causing batches of 50+ texts to exceed the 120K token-per-batch limit even when DB token counts (from tiktoken) suggest they'd fit. Changes: - Add max_batch_tokens to EmbeddingTouchpoint type (provider-declared limit) - Set Voyage recipe to 120K token limit - Gateway embed() now auto-splits batches using conservative char-to-token estimate (1:1 ratio, 80% budget utilization) - On token-limit errors, embedSubBatch recursively halves and retries (down to single-text batches before giving up) - Reduce embedding.ts BATCH_SIZE from 100 to 50 as a secondary guard - Add tests for batch splitting logic and error pattern matching Fixes infinite retry loops where the same oversized batch would fail repeatedly because WHERE embedding IS NULL re-fetches identical rows. * fix(init): error on existing-brain dim mismatch + embedding-migration recipe Adds A4 hard-error path: when `gbrain init --embedding-dimensions N` is run against an existing brain whose `content_chunks.embedding` column is a different `vector(M)`, init exits 1 with an inline four-step ALTER recipe and a pointer to docs/embedding-migrations.md. This kills the silent-corruption pattern surfaced by issue #673: the v0.27 schema seeded `('embedding_dimensions', '1536')` regardless of the flag, so users got a config saying 768 but a column at 1536 — first sync write blew up with "expected 1536, got 768." A4's contract: 1. Connect to engine BEFORE saveConfig so we can read the live column type 2. If column exists AND dim != requested, exit 1 (loud failure) 3. If column doesn't exist (fresh init) OR dim matches, proceed normally Recipe in docs/embedding-migrations.md (and inlined in init's error output) covers all four destructive steps codex's plan-review caught: 1. DROP INDEX IF EXISTS idx_chunks_embedding (HNSW won't survive ALTER) 2. ALTER TABLE content_chunks ALTER COLUMN embedding TYPE vector(N) 3. UPDATE content_chunks SET embedding = NULL, embedded_at = NULL 4. CREATE INDEX HNSW *only if N <= 2000* (pgvector cap) Step 4 is conditional: dims > 2000 (e.g. Voyage 4 Large 2048d) cannot be HNSW-indexed in pgvector; the recipe explicitly says "Skip reindex" in that case so the user doesn't paste a CREATE INDEX that crashes. Helper `readContentChunksEmbeddingDim` and message builder `embeddingMismatchMessage` live in src/core/embedding-dim-check.ts so doctor 8b (next commit) can reuse the same source of truth. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(gateway): correct dim-mismatch error to point at manual ALTER recipe (#672) Previous error message recommended running `gbrain migrate --embedding-model … --embedding-dimensions …`, but `gbrain migrate` only handles engine migration (postgres ↔ pglite), not embedding reconfiguration. Following that hint produced a different error and confused users further. New message: - Names the actual options: change models OR migrate the existing brain - Inlines a one-line quick recipe (DROP INDEX → ALTER → UPDATE NULL → config set → embed --stale) - Points at docs/embedding-migrations.md (added in commit |