mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
* Wave A: schema + receipts foundation for v0.42 extract operator surfaces
Foundation layer for the pack-driven extractables + receipt-as-brain-memory
+ operator-discoverability cathedral. Five atomic pieces ship together
because their schema + helpers + module dependencies are tight-coupled:
A1. Widen pack manifest's `extractable` from `boolean` to
`boolean | ExtractableSpec`. ExtractableSpec carries prompt_template,
fixture_corpus, eval_dimensions, benchmark_min_recall, and reserves
verifier_path for v0.43+ pack-shipped verifier code (REFUSE at
runtime in v0.42 per plan D-EXTRACT-37). Back-compat: every pre-v0.42
pack with `extractable: true` continues parsing unchanged. Three new
helpers: extractableSpecsFromPack(), getExtractableSpec(),
refuseVerifierPathInV042().
A2. New page type `extract_receipt` in ALL_PAGE_TYPES. Source-boost map
adds `extracts/` prefix at factor 0.3 — receipts surface in search
when extraction-relevant but never dominate user content (D-EXTRACT-42).
A3. New module src/core/extract/receipt-writer.ts (~190 LOC) exporting
writeReceipt(engine, input). Canonical slug shape
extracts/{date}/{kind}/{source_id}/{run_id_short}/round-{N} per
D-EXTRACT-17. Frontmatter belt+suspenders per D-EXTRACT-19: BOTH
type:extract_receipt AND dream_generated:true stamped on every
receipt, regardless of caller, so the eligibility predicate's
anti-loop guards reject the receipt page from any future extraction
sweep (single-flag bypass requires breaking two unrelated checks).
Idempotent on resume — same run_id+round overwrites cleanly.
A4. Migration v104 creates extract_rollup_7d table (per-day rollup of
extract events keyed on kind+source_id+day). Audit JSONL stays the
SOURCE OF TRUTH per F-OUT-19; this table is a best-effort cache for
doctor's <100ms read budget. Per-day rows mean the 7-day window
auto-evicts on every read. v100 was deliberately skipped on master
(renumbered out during a prior wave); v101/v102/v103 also taken;
v104 is the next clean slot.
A5. Doctor `extract_health` check reads extract_rollup_7d for last 7
days and emits per-kind aggregates: cost_7d_usd, eval_pass_count,
eval_fail_count, halt_count, round_completed_count, halt_rate.
3-state: OK when rollup empty (pre-v0.42 brain or fresh init), WARN
when any per-kind halt rate > 10% (top-3 named in message), WARN
when rollup_write_failures > 0 (audit JSONL is SoT but operator
deserves to know the DB cache is degraded). Pre-v104 brains stay
quiet — the missing-table error path is caught and treated as
OK so doctor doesn't warn during the upgrade window.
Tests added:
- test/extractable-spec-widening.test.ts (22 cases) — back-compat with
boolean shape, new struct parsing, verifier_path REFUSE contract.
- test/extract/receipt-writer.test.ts (12 cases) — slug shape, frontmatter
belt+suspenders, idempotent resume, body human-readability.
- test/doctor-extract-health.test.ts (8 cases) — empty rollup OK, halt
rate WARN, rollup_write_failures WARN, 7-day window inclusion at
boundary, multi-kind top-3 message ordering.
Plus the canonical bootstrap-coverage test passes with the new v104
migration cleanly applied through both engines.
Plan: ~/.claude/plans/system-instruction-you-are-working-stateless-dragonfly.md
Wave A scope. Wave B (hook receipts into existing extractors) follows.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* Wave B: hook receipts + rollup row into the 5 shipped extractors
Each LLM-backed extractor surface now records its run in two places when
something actually happened:
1. An extract receipt PAGE at extracts/{date}/{kind}/{source_id}/{run_id_short}/round-{N}
(queryable via gbrain search, citable, surfaces in cross-modal
contradiction probes per the Wave A foundation). Only written when
`total_rows > 0` so no-op runs don't bloat the brain.
2. An UPSERT row in extract_rollup_7d (DB-backed best-effort cache
per F-OUT-19) so the doctor extract_health check from Wave A reads
per-kind aggregates without scanning JSONL.
New module src/core/extract/rollup-writer.ts (~120 LOC) exports
upsertExtractRollup() with PostgreSQL ON CONFLICT DO UPDATE on the
(kind, source_id, day) PK. Concurrency-safe per F-OUT-14 design.
Failure path is best-effort — bumps rollup_write_failures in the
table itself, stderr-warns once per (kind, day, error-class), and
NEVER fails the parent extraction operation. JSONL remains source
of truth.
Wired into 5 extractors:
- extract-conversation-facts (kind: facts.conversation) — both
success path AND BudgetExhausted halt path write receipt+rollup
so partial runs are still observable.
- extract_atoms cycle phase (kind: atoms)
- synthesize_concepts cycle phase (kind: concepts, source_id: default
because concepts are brain-global)
- propose_takes cycle phase (kind: takes.proposed) — scope-aware
source_id from the read scope.
- extract_facts cycle phase (kind: facts.fence) — deterministic
(no LLM cost) but still records reconcile activity so doctor sees
the cycle is alive.
Receipt frontmatter belt+suspenders (D-EXTRACT-19) reused from
Wave A: every receipt stamps BOTH `type: extract_receipt` AND
`dream_generated: true` so the eligibility predicate's anti-loop
guards reject the receipt page from any future extraction sweep.
Test surgery in test/propose-takes.test.ts — one existing assertion
tightened from "no INSERTs" to "no INSERT INTO take_proposals" so
the new rollup UPSERT doesn't falsely fail the cache-hit case test.
Run regression: 85/85 tests pass across extract-conversation-facts,
extract-atoms-synthesize-concepts, extract-facts-phase, propose-takes.
Plan: ~/.claude/plans/system-instruction-you-are-working-stateless-dragonfly.md
Wave B scope. Wave C (pack-author scaffolding + benchmark) follows.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* Wave C+D: pack-author scaffolding + operator surfaces for v0.42 extract
Wave C: pack-author authoring loop
- scaffold-extractable mutation primitive declares a kind as extractable
on a pack manifest in one verb (wires through updateTypeOnPack from
the v0.41 mutate library); generates 5 placeholder fixtures + a
pack-supplied prompt template stub
- schema CLI wires gbrain schema scaffold-extractable <type> --pack <pack>
- extract benchmark CLI loads a pack's fixture corpus through strict
D-EXTRACT-21 path validation (rejects absolute paths, .. traversal,
null bytes, symlinks resolving outside pack root); v0.42 ships as a
stub reporter (LLM dispatch deferred to Wave E)
Wave D: operator surfaces
- extract status CLI reads extract_rollup_7d for the last 7 days,
sorts by (halt_rate desc, cost desc); kubectl-style right-aligned
table, top-5 + "more rows" hint by default, --verbose shows all;
stable schema_version: 1 JSON envelope for monitoring pipelines
- extract --explain <kind> CLI prints the active pack's resolution
chain: declaration source (pack-declared vs built-in cycle phase),
prompt_template + fixture_corpus paths with existence checks,
eval_dimensions, benchmark_min_recall, and the last 7d rollup
- extract.ts gains a lifecycle-grouped help text (Extraction /
Inspection / Status) per the original D3 plan goal
Tests:
- test/schema-pack/scaffold-extractable.test.ts (15 cases) including
explicit privacy-rule assertions guarding against real-name leakage
- test/extract/benchmark.test.ts (17 cases) covering path validation
rejections + JSONL fixture parsing
- test/extract/status.test.ts (15 cases) over pure aggregation +
formatting
Housekeeping:
- test/extract/receipt-writer.test.ts refactored to the canonical
PGLite block (beforeAll/afterAll/resetPgliteState in beforeEach)
per CLAUDE.md test-isolation R3+R4; runtime drops from ~30s of
99-migration replay per test to <6s for all 12 cases together
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* v0.42.0.0: extract operator surfaces + pack-driven extractables
Bump VERSION + package.json to 0.42.0.0. CHANGELOG entry covers the
three-wave shipped scope (receipts + rollup + doctor check; receipts
hooked into all 5 shipped extractors; pack-author scaffolding +
benchmark stub-reporter; status + --explain dashboards + lifecycle
help). CLAUDE.md Key Files gains a v0.42 cluster annotation. llms.txt
regenerated.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* v0.41.23.0: re-tag from 0.42.0.0 (patch-channel slot, no scope change)
VERSION + package.json + CHANGELOG header + CLAUDE.md cluster annotation
all moved from 0.42.0.0 to 0.41.23.0. Body text updated in-place: every
"v0.42" / "v0.43+" reference inside this entry's release notes now reads
"v0.41.23" or "follow-up release" as appropriate.
Same scope shipping — the three-wave extract operator surface stays
intact. Just lands in the patch-channel queue (.20/.21/.23 free; .22 is
PR #1542's type-unification cathedral) instead of the minor-channel bump.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: add extract_receipt to gbrain-base.yaml page_types (CI parity gate)
CI shard 5 caught the drift: test/regressions/gbrain-base-equivalence.test.ts
asserts every ALL_PAGE_TYPES seed has a matching page_type entry in the
gbrain-base.yaml pack. Wave A added `extract_receipt` to ALL_PAGE_TYPES
but didn't seed it in the base pack manifest.
Adds the entry under the `annotation` primitive with `extracts/` path
prefix (matches the source-boost demote site) and `extractable: false`
(receipts are written by the framework, never extracted from). Comment
documents the belt+suspenders D-EXTRACT-19 invariant so future readers
understand why receipts carry both `dream_generated: true` AND
`type: extract_receipt`.
Closes the CI gate without changing runtime behavior — the pack-aware
read paths already had the prefix demote wired in src/core/search/source-boost.ts.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: bump gbrain-base page-type count 24→25 in schema-cli test
CI shard 4 caught the second drift from the same root cause as the
prior parity-gate fix: v0.41.23's `extract_receipt` addition bumped
gbrain-base.yaml from 24 to 25 page types. The schema-cli smoke test
was pinned at 24 (the count after v0.41.11.0 added `conversation` +
`atom`); update to 25 and note v0.41.23's contribution alongside the
prior version stamp.
Verified hermetic: running test/schema-cli.test.ts with a clean
GBRAIN_HOME tempdir produces 12/12 pass (the local-machine 'schema
active' fail is from a real ~/.gbrain pinning gbrain-base-v2; not a
shipped-code issue, doesn't repro on CI).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(test): pack-locator stub leak between shard 6 test files
CI shard 6 caught three flaky failures in test/onboard-pack-upgrade-checks.test.ts:
- checkPackUpgradeAvailable > fires on gbrain-base brain with gbrain-base-v2
- checkPackUpgradeAvailable > manual_only routing via render.ts allowlist (D17)
- checkTypeProliferation > warns when distinct types exceed declared+5
Root cause: test/schema-pack-sync.test.ts calls
`__setPackLocatorForTests(...)` to stub the disk-loader, but doesn't
restore in afterAll. Bun's CI shard 6 loads multiple test files into
one process; when sync.test.ts runs before onboard-pack-upgrade-checks.test.ts,
the stubbed locator persists at module scope. `loadActivePack` for
gbrain-base / gbrain-base-v2 then returns null and:
- findPackSuccessors returns [] → status='ok' instead of 'warn' (F1+F2)
- declared falls back to 15 → fail threshold becomes 30, 32 > 30 → 'fail'
instead of 'warn' (F3)
Local single-file runs pass because the locator starts at its default.
Two-layer fix:
1. test/schema-pack-sync.test.ts afterAll calls
`_resetPackLocatorForTests()` to undo the mutation (the canonical
fix at the source).
2. test/onboard-pack-upgrade-checks.test.ts beforeEach calls the same
reset (defense-in-depth against any future test file in the shard
that forgets to restore).
Reproduced locally: running the three shard-6 schema-pack files together
fails 3 tests pre-fix and passes 30/30 post-fix. Full shard 6 sweep
(77 files, 1232 tests) now green; bun run verify still 28/28.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(test): pglite-engine — dim-agnostic chunk-embedding test data
CI shard 6 caught two flaky failures in test/pglite-engine.test.ts:
- PGLiteEngine: Chunks > getChunksWithEmbeddings returns embedding data
- PGLiteEngine: stale chunk pagination > countStaleChunks counts chunks
with NULL embedding only
Both failed with `expected 1280 dimensions, not 1536` at the upsert site.
Root cause: pglite-engine.ts:287 initSchema() reads embedding dim from
gw.getEmbeddingDimensions() if the gateway is configured (potentially
left in that state by another shard-6 test file in the same bun process),
falling back to DEFAULT_EMBEDDING_DIMENSIONS otherwise — which is 1280
since v0.36+ when the ZE default landed (zeroentropyai:zembed-1).
Pre-v0.36 defaults were OpenAI's 1536; my test data was pinned to that
stale literal.
The two outcomes that pass:
- gateway happens to be configured for 1536-dim (e.g. master shard 6
run 26515999465 — these tests passed at 20ms + 24ms with no
"dimensions" error)
- gateway happens to be configured for 1280-dim AND test data is 1280
The outcome that fails:
- gateway configured for 1280-dim AND test data hardcoded to 1536
Fix: capture the actual column width after initSchema (probe
pg_attribute.atttypmod for content_chunks.embedding) and use that
captured `CHUNK_EMBED_DIM` constant at the three Float32Array sites.
Test data now matches whatever width the column was created at,
regardless of which shard-6 file ran first.
Local repro: full shard 6 (77 files, 1232 tests, ~6min) green; this
file standalone (100 tests) green; bun run verify 28/28.
Broader pattern: 9 other test files use the same Float32Array(1536)
literal. None land in shard 6 today (so they don't flake), but the
fix shape here can be lifted into a shared helper if the bug class
surfaces elsewhere — filed as a v0.42+ follow-up rather than a
preemptive sweep, since each file's setup shape is slightly different.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
129 lines
5.2 KiB
TypeScript
129 lines
5.2 KiB
TypeScript
/**
|
|
* v0.42 — Per-day extract-event rollup writer (best-effort cache).
|
|
*
|
|
* Sister module to receipt-writer.ts. Where receipts are first-class
|
|
* brain pages (long-term audit trail), the rollup table is a fast-read
|
|
* cache the doctor `extract_health` check reads to keep latency under
|
|
* 100ms regardless of audit volume.
|
|
*
|
|
* F-OUT-19 dual-write posture:
|
|
* - JSONL audit (~/.gbrain/audit/...) is the SOURCE OF TRUTH
|
|
* (forensic, append-only, crash-safe).
|
|
* - This DB rollup is BEST-EFFORT. Failures bump a counter
|
|
* (rollup_write_failures) inside the table itself and stderr-warn;
|
|
* they NEVER fail the parent extraction operation.
|
|
* - When persistent failures accumulate (>10/hr per future doctor
|
|
* rule), an auto-rebuild from JSONL self-heals the cache.
|
|
*
|
|
* Schema (migration v106):
|
|
* extract_rollup_7d (kind, source_id, day, cost_usd, halt_count,
|
|
* eval_fail_count, eval_pass_count,
|
|
* round_completed_count, rollup_write_failures,
|
|
* updated_at, PK(kind, source_id, day))
|
|
*
|
|
* Concurrency: PostgreSQL INSERT ... ON CONFLICT DO UPDATE is
|
|
* concurrency-safe for the per-(kind, source_id, day) PK. Multiple
|
|
* parallel extractions on the same day land cleanly without a lock
|
|
* (UPSERT is atomic per row).
|
|
*/
|
|
|
|
import type { BrainEngine } from '../engine.ts';
|
|
|
|
/**
|
|
* One UPSERT increments per audit event. All counters default to 0 so
|
|
* callers only specify the deltas they care about (e.g. a round-completed
|
|
* event passes round_completed_delta=1; an eval-fail event passes
|
|
* eval_fail_delta=1; a halt event passes halt_delta=1). cost_delta is the
|
|
* cumulative cost ADD for the period this event represents.
|
|
*/
|
|
export interface RollupUpsertInput {
|
|
kind: string;
|
|
source_id: string;
|
|
/** ISO YYYY-MM-DD. Defaults to today (UTC) if omitted. */
|
|
day?: string;
|
|
cost_delta?: number;
|
|
halt_delta?: number;
|
|
eval_fail_delta?: number;
|
|
eval_pass_delta?: number;
|
|
round_completed_delta?: number;
|
|
/** Increment rollup_write_failures inside the table (used by the
|
|
* self-healing path that records its own write failures forensically). */
|
|
failure_delta?: number;
|
|
}
|
|
|
|
function today(): string {
|
|
// ISO YYYY-MM-DD in UTC. Matches Postgres CURRENT_DATE behavior for
|
|
// UTC servers; for local-time servers there's a slight drift at midnight
|
|
// but rollup is best-effort cache so the drift is acceptable.
|
|
return new Date().toISOString().slice(0, 10);
|
|
}
|
|
|
|
/**
|
|
* UPSERT one rollup event. Best-effort: catches all errors, logs to
|
|
* stderr once per (kind, day, error-class) so it doesn't spam, returns
|
|
* a boolean indicating success.
|
|
*
|
|
* Caller composes multiple deltas in one call (round_completed + cost
|
|
* together is typical) so the rollup row is one UPSERT per audit event,
|
|
* not N UPSERTs.
|
|
*/
|
|
export async function upsertExtractRollup(
|
|
engine: BrainEngine,
|
|
input: RollupUpsertInput,
|
|
): Promise<{ ok: boolean; error?: string }> {
|
|
const day = input.day ?? today();
|
|
const cost = input.cost_delta ?? 0;
|
|
const halts = input.halt_delta ?? 0;
|
|
const evalFails = input.eval_fail_delta ?? 0;
|
|
const evalPasses = input.eval_pass_delta ?? 0;
|
|
const completed = input.round_completed_delta ?? 0;
|
|
const failures = input.failure_delta ?? 0;
|
|
|
|
try {
|
|
await engine.executeRaw(
|
|
`INSERT INTO extract_rollup_7d (
|
|
kind, source_id, day,
|
|
cost_usd, halt_count, eval_fail_count, eval_pass_count,
|
|
round_completed_count, rollup_write_failures, updated_at
|
|
)
|
|
VALUES ($1, $2, $3::date, $4, $5, $6, $7, $8, $9, now())
|
|
ON CONFLICT (kind, source_id, day) DO UPDATE SET
|
|
cost_usd = extract_rollup_7d.cost_usd + EXCLUDED.cost_usd,
|
|
halt_count = extract_rollup_7d.halt_count + EXCLUDED.halt_count,
|
|
eval_fail_count = extract_rollup_7d.eval_fail_count + EXCLUDED.eval_fail_count,
|
|
eval_pass_count = extract_rollup_7d.eval_pass_count + EXCLUDED.eval_pass_count,
|
|
round_completed_count = extract_rollup_7d.round_completed_count + EXCLUDED.round_completed_count,
|
|
rollup_write_failures = extract_rollup_7d.rollup_write_failures + EXCLUDED.rollup_write_failures,
|
|
updated_at = now()`,
|
|
[input.kind, input.source_id, day, cost, halts, evalFails, evalPasses, completed, failures],
|
|
);
|
|
return { ok: true };
|
|
} catch (err) {
|
|
const msg = (err as Error).message || String(err);
|
|
// Don't spam: log once per process per (kind, day) error class.
|
|
rollupErrorLogOnce(input.kind, day, msg);
|
|
return { ok: false, error: msg };
|
|
}
|
|
}
|
|
|
|
const _loggedRollupErrors = new Set<string>();
|
|
function rollupErrorLogOnce(kind: string, day: string, msg: string): void {
|
|
// Classify by error first 80 chars to dedupe "lock timeout" vs
|
|
// "connection refused" but not by exact text.
|
|
const klass = msg.slice(0, 80);
|
|
const key = `${kind}|${day}|${klass}`;
|
|
if (_loggedRollupErrors.has(key)) return;
|
|
_loggedRollupErrors.add(key);
|
|
console.error(
|
|
`[extract-rollup] write failed (best-effort; audit JSONL remains source of truth): ${msg}`,
|
|
);
|
|
}
|
|
|
|
/**
|
|
* Test seam: clear the logged-errors set so repeated test invocations
|
|
* surface stderr each time.
|
|
*/
|
|
export function _resetRollupErrorLogForTests(): void {
|
|
_loggedRollupErrors.clear();
|
|
}
|