Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 a42352081c test(extract): pin the version-arm stamp floor with an explicit regression test
The floor in extractStaleFromDB was only covered incidentally — the #1768
test's updated_at (2026-06-02) fell below the bumped VERSION_TS, but its
comment still says the date was chosen to sit ABOVE the watermark. A future
date 'repair' there would silently drop floor coverage. This test pins it
directly: pre-watermark page clears after --stale and stays cleared.
Verified fail-without-fix against master's extract.ts.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:59:09 -07:00
Garry TanandClaude Fable 5 070f4c5678 fix(extract): floor --stale stamp at LINK_EXTRACTOR_VERSION_TS so version bumps don't create permanently-stale pages
The version-ts bump in this PR exposed a latent conflict: extractStaleFromDB
stamps links_extracted_at = the page's read updated_at (#1768 µs fix), but a
page last edited BEFORE the new LINK_EXTRACTOR_VERSION_TS then lands below the
version watermark and the 'links_extracted_at < versionTs' arm re-flags it
stale on every run — an infinite re-extraction loop. Stamp
max(updated_at, versionTs); versionTs is always a past release date, so the
D4 concurrent-edit race guard still holds.

Fixes the test/extract-stale.test.ts CI failure on this branch.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 10:56:38 -07:00
Garry TanandClaude Fable 5 4b2df89935 fix(extract): resolve path-style wikilinks outside DIR_PATTERN + add ops/ to whitelist (#2576 bug 2)
- Add ops to DIR_PATTERN so [[ops/services/...]] wikilinks and bare
  ops/... slug refs are recognized as qualified entity references.
- queryBasenameIndex (the shared basename matcher behind
  resolveBasenameMatches, the FS resolver, and the doctor check) now
  falls back to the path tail when a path-style ref misses — before,
  normalizeBasename stripped slashes into a garbage key that could
  never hit the tail-keyed index.
- Bump LINK_EXTRACTOR_VERSION_TS so extract --stale re-sweeps
  previously-stamped pages with the new extraction logic.

Bugs 1+3 of #2576 are covered by PR #2717 (--stale nullResolver).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:33:45 -07:00
10 changed files with 78 additions and 122 deletions
-12
View File
@@ -186,18 +186,6 @@ export function isSourceStale(src: SourceRow, now = Date.now(), floorMin = FULL_
return ageMin >= floorMin;
}
/**
* #2060: count sources past the per-source cycle freshness floor. Consumed
* by autopilot's dispatch decision — a stale source forces the fanout path
* even when the doctor plan is small (score 7094, plan ≤ 3, est < 300s),
* so targeted mode can't leave cycle_freshness stale indefinitely.
* dispatchPerSource's own throttles (skipped_fresh / fanoutMax / failure
* cooldown) bound the resulting work.
*/
export function countStaleSources(sources: SourceRow[], now = Date.now(), floorMin = FULL_CYCLE_FLOOR_MIN): number {
return sources.filter((s) => isSourceStale(s, now, floorMin)).length;
}
/**
* Most recent SUCCESSFUL cycle for a source. Prefers `last_source_cycle_at`
* (per-source phases, written by the split cycle) and falls back to the legacy
+2 -16
View File
@@ -901,27 +901,13 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
const FULL_CYCLE_FLOOR_MIN = 60;
const minutesSinceLastFull = (Date.now() - lastFullCycleAt) / 60000;
// #2060: stale per-source cycle freshness is a dispatch input. Without
// it, a brain sitting at score 7094 with a small targeted plan (≤3
// steps, <300s) stays in targeted mode indefinitely and no per-source
// cycle is ever dispatched — cycle_freshness never advances. A stale
// source forces the fanout path; dispatchPerSource's throttles
// (skipped_fresh / fanoutMax / failure cooldown) bound the work.
// Fail-open to 0: a read failure must not block dispatch.
let staleCycleSources = 0;
try {
const { countStaleSources } = await import('./autopilot-fanout.ts');
staleCycleSources = countStaleSources(await engine.listAllSources({ localPathOnly: true }));
} catch { /* fail-open: freshness is a dispatch hint, not a gate */ }
const shouldFullCycle =
(score >= 95 && plan.length === 0 && minutesSinceLastFull >= FULL_CYCLE_FLOOR_MIN) ||
plan.length > 3 ||
estTotal >= 300 ||
score < 70 ||
staleCycleSources > 0;
score < 70;
const shouldSleep = score >= 95 && plan.length === 0 && minutesSinceLastFull < FULL_CYCLE_FLOOR_MIN && staleCycleSources === 0;
const shouldSleep = score >= 95 && plan.length === 0 && minutesSinceLastFull < FULL_CYCLE_FLOOR_MIN;
if (shouldSleep) {
if (jsonMode) {
+9 -1
View File
@@ -1743,7 +1743,15 @@ async function extractStaleFromDB(
// `page.updated_at.toISOString()` — the JS Date is ms-truncated, so the
// µs-precision DB updated_at stayed strictly greater and the page never
// cleared on Postgres. Stamping the exact value makes them equal.
processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: page.updated_at_iso });
//
// Version-arm floor: a page last edited BEFORE LINK_EXTRACTOR_VERSION_TS
// would otherwise be stamped below the version watermark and stay
// permanently stale (`links_extracted_at < versionTs` re-fires every run).
// Stamp max(updated_at, versionTs) — versionTs is always a past release
// date, so a concurrent edit's now() still exceeds the stamp and D4 holds.
// Tie at ms precision picks updated_at_iso (its µs ≥ versionTs's .000000).
const stampTs = new Date(page.updated_at_iso) >= new Date(versionTs) ? page.updated_at_iso : versionTs;
processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: stampTs });
}
// Flush NON-swallowing (CDX-4): a throw here propagates out of the sweep so
+10 -19
View File
@@ -854,10 +854,7 @@ interface SyncPhaseResult extends PhaseResult {
/**
* Resolve the source id for a brain directory by looking up the sources
* table. Returns undefined when no registered source matches (falls back
* to pre-v0.18 global config.sync.* keys) OR when MORE than one source
* claims the path — an ambiguous match must not scope phases or stamp
* last_full_cycle_at for an arbitrarily-picked source (the "freshness
* stamp that lies" this resolution exists to prevent).
* to pre-v0.18 global config.sync.* keys).
*/
async function resolveSourceForDir(
engine: BrainEngine,
@@ -868,10 +865,10 @@ async function resolveSourceForDir(
if (brainDir === null) return undefined;
try {
const rows = await engine.executeRaw<{ id: string }>(
`SELECT id FROM sources WHERE local_path = $1 LIMIT 2`,
`SELECT id FROM sources WHERE local_path = $1 LIMIT 1`,
[brainDir],
);
return rows.length === 1 ? rows[0]!.id : undefined;
return rows[0]?.id;
} catch {
// sources table might not exist on very old brains — fall through.
return undefined;
@@ -2368,23 +2365,17 @@ export async function runCycle(
}
// v0.38 (codex r1 P0-5): persist per-source cycle completion timestamp
// when the cycle ran successfully against a resolvable source. Read by
// autopilot's per-source freshness gate next tick.
//
// #1993: keyed off `cycleSourceId` (opts.sourceId ?? the source resolved
// from brainDir) — the SAME id the cycle locked + scoped its phases to —
// NOT raw opts.sourceId. The autopilot's inline cycle sets brainDir but
// passes no explicit sourceId, so keying off opts.sourceId alone never
// advanced last_full_cycle_at and cycle_freshness stayed stale even while
// the autopilot cycled every interval. Skipped when:
// - no source resolves (engine null, or no checkout AND no opts.sourceId)
// when the cycle ran successfully against an explicit source. Read by
// autopilot's per-source freshness gate next tick. Skipped when:
// - opts.sourceId is unset (legacy callers — autopilot still here)
// - engine is null (no-DB path)
// - status is 'failed' or 'skipped' (don't mark a non-run as fresh)
// - dryRun (writes are out of scope)
//
// Best-effort: a write failure does NOT change the CycleReport status.
// The cost of writing the wrong timestamp post-failure is higher than
// the cost of missing a successful write (next cycle will redo work).
if (cycleSourceId && engine && !dryRun && !aborted && (status === 'ok' || status === 'clean' || status === 'partial')) {
if (opts.sourceId && engine && !dryRun && !aborted && (status === 'ok' || status === 'clean' || status === 'partial')) {
try {
const nowIso = new Date().toISOString();
// #2194 fix #3 (the cycle split): `last_source_cycle_at` is the NEW gate
@@ -2394,13 +2385,13 @@ export async function runCycle(
// phases (those gate on autopilot.last_global_at), so writing it on a
// source-only cycle does not re-introduce the freshness poisoning codex
// flagged in the rejected skip-based design.
await engine.updateSourceConfig(cycleSourceId, {
await engine.updateSourceConfig(opts.sourceId, {
last_source_cycle_at: nowIso,
last_full_cycle_at: nowIso,
});
} catch (e) {
// Best-effort; cycle already succeeded by the time we get here.
console.warn(`[cycle] failed to write last_source_cycle_at for source ${cycleSourceId}: ${e instanceof Error ? e.message : String(e)}`);
console.warn(`[cycle] failed to write last_source_cycle_at for source ${opts.sourceId}: ${e instanceof Error ? e.message : String(e)}`);
}
}
+13 -4
View File
@@ -28,7 +28,7 @@ import { ensureWellFormed } from './text-safe.ts';
* OR updated_at > links_extracted_at`. It is an ISO-8601 string (NOT a number) —
* the column is TIMESTAMPTZ and the predicate binds it as `::timestamptz`.
*/
export const LINK_EXTRACTOR_VERSION_TS = '2026-05-31T00:00:00Z';
export const LINK_EXTRACTOR_VERSION_TS = '2026-07-21T00:00:00Z';
// ─── Entity references ──────────────────────────────────────────
@@ -80,10 +80,10 @@ export type LinkResolutionType = 'qualified' | 'unqualified';
* Directory prefix whitelist. These are the top-level slug dirs the extractor
* recognizes as entity references. Upstream canonical + our extensions:
* - Gbrain canonical: people, companies, meetings, concepts, deal, civic, project, source, media, yc, projects
* - Our domain extensions: tech, finance, personal, openclaw (domain-organized wikis)
* - Our domain extensions: tech, finance, personal, openclaw, ops (domain-organized wikis)
* - Our entity prefix: entities (we kept some legacy entities/projects/ pages)
*/
const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities)';
const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities|ops)';
/**
* Match `[Name](path)` markdown links pointing to entity directories.
@@ -865,7 +865,16 @@ export function queryBasenameIndex(idx: Map<string, string[]>, name: string): st
if (!name || typeof name !== 'string') return [];
const trimmed = name.trim();
if (!trimmed) return [];
const hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
let hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
// Issue #2576 bug 2: path-style refs (`runbooks/2026-05-01-x`) from dirs
// outside DIR_PATTERN reach here, but normalizeBasename strips slashes
// into a garbage key (`runbooks2026-05-01-x`) that can never hit the
// tail-keyed index. Fall back to the path tail so qualified refs resolve
// by basename like everything else.
if (!hit && trimmed.includes('/')) {
const tail = trimmed.slice(trimmed.lastIndexOf('/') + 1).trim();
if (tail) hit = idx.get(tail) ?? idx.get(tail.toLowerCase()) ?? idx.get(normalizeBasename(tail));
}
return hit ? [...hit].sort(basenameSort) : [];
}
-14
View File
@@ -54,20 +54,6 @@ describe('autopilot.ts ↔ dispatchPerSource wiring', () => {
expect(AUTOPILOT_SRC).toMatch(/lastFullCycleAt\s*=\s*Date\.now\(\)/);
});
test('stale per-source cycle freshness is a shouldFullCycle input (#2060)', () => {
// Targeted mode (score 7094, plan ≤3, est <300s) must not be able to
// starve per-source cycle dispatch: a stale source (per countStaleSources
// over listAllSources) forces the fanout path, and the sleep gate must
// not fire while stale sources exist. Without these terms, cycle
// freshness never advances for a brain that always lands in targeted mode.
expect(AUTOPILOT_SRC).toMatch(/countStaleSources/);
const fullCycleDeclIdx = AUTOPILOT_SRC.indexOf('const shouldFullCycle');
expect(fullCycleDeclIdx).toBeGreaterThan(-1);
const decl = AUTOPILOT_SRC.slice(fullCycleDeclIdx, fullCycleDeclIdx + 700);
expect(decl).toMatch(/staleCycleSources\s*>\s*0/);
expect(decl).toMatch(/const shouldSleep[^;]*staleCycleSources\s*===\s*0/);
});
test('does NOT regress to the single-job dispatch on the full-cycle path', () => {
// Pre-PR: the shouldFullCycle branch did:
// const job = await queue.add('autopilot-cycle', { repoPath }, {
-18
View File
@@ -14,7 +14,6 @@ import { describe, test, expect } from 'bun:test';
import {
readLastFullCycleAt,
isSourceStale,
countStaleSources,
selectSourcesForDispatch,
resolveFanoutMax,
dispatchPerSource,
@@ -75,23 +74,6 @@ describe('isSourceStale', () => {
});
});
describe('countStaleSources (#2060 dispatch-decision input)', () => {
const NOW = Date.parse('2026-05-22T12:00:00.000Z');
test('counts never-cycled + past-floor sources, ignores fresh', () => {
const sources = [
src('never-cycled'), // stale (null)
src('old', new Date(NOW - 2 * 60 * 60_000).toISOString()), // stale (2h)
src('fresh', new Date(NOW - 30 * 60_000).toISOString()), // fresh (30min)
];
expect(countStaleSources(sources, NOW)).toBe(2);
});
test('returns 0 for all-fresh and for empty list', () => {
const fresh = src('a', new Date(NOW - 10 * 60_000).toISOString());
expect(countStaleSources([fresh], NOW)).toBe(0);
expect(countStaleSources([], NOW)).toBe(0);
});
});
describe('selectSourcesForDispatch', () => {
const NOW = Date.parse('2026-05-22T12:00:00.000Z');
const fresh = (id: string, agoMin: number) =>
+8 -38
View File
@@ -3,10 +3,8 @@
* cycles. Closes codex round-1 P0-5 (write site for last_full_cycle_at
* was unspecified pre-PR).
*
* Conditions for write (keyed off `cycleSourceId` = opts.sourceId ?? the
* source resolved from brainDir, so the autopilot's inline cycle — brainDir
* set, no explicit sourceId — also advances the timestamp, #1993):
* - a source resolves (explicit sourceId, or brainDir matches a source)
* Conditions for write:
* - opts.sourceId is set (legacy callers without sourceId skip the write)
* - engine is non-null (no-DB path skips)
* - status is 'ok' | 'clean' | 'partial' (failed/skipped don't mark fresh)
* - dryRun is false
@@ -92,45 +90,17 @@ describe('runCycle last_full_cycle_at exit hook', () => {
});
});
test('no explicit sourceId but brainDir resolves a source → writes the resolved source timestamp', async () => {
test('legacy caller (no sourceId) does NOT write any source timestamp', async () => {
await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
// The autopilot's inline cycle sets brainDir but passes no sourceId.
// runCycle resolves the source from brainDir (local_path match) into
// cycleSourceId and stamps last_full_cycle_at for it — otherwise
// cycle_freshness reports the brain stale even while the autopilot
// cycles every interval (#1993).
await seedSource('resolved-from-dir'); // local_path = brainDir
expect(await readLastFullCycleAt('resolved-from-dir')).toBeNull();
const t0 = Date.now();
const report = await runCycle(engine, {
brainDir,
phases: ['lint'],
});
expect(['ok', 'clean']).toContain(report.status);
const after = await readLastFullCycleAt('resolved-from-dir');
expect(after).not.toBeNull();
expect(new Date(after!).getTime()).toBeGreaterThanOrEqual(t0);
});
});
test('no sourceId and brainDir matches no source → does not write', async () => {
await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
// A source exists but its local_path does NOT match brainDir, so
// resolveSourceForDir returns undefined, cycleSourceId is undefined,
// and no per-source timestamp is written.
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config, archived, created_at)
VALUES ('unmatched', 'unmatched', '/no/such/repo', '{}'::jsonb, false, NOW())
ON CONFLICT (id) DO UPDATE SET local_path = EXCLUDED.local_path`,
[],
);
await seedSource('default-like');
// No sourceId passed; should remain untouched.
await runCycle(engine, {
brainDir,
phases: ['lint'],
});
expect(await readLastFullCycleAt('unmatched')).toBeNull();
// No per-source write happens; default source's config stays empty.
const after = await readLastFullCycleAt('default-like');
expect(after).toBeNull();
});
});
+18
View File
@@ -209,6 +209,24 @@ describe('gbrain extract --stale', () => {
expect(usRows[0]?.eq).toBe(true);
});
test('version-arm floor: page edited BEFORE LINK_EXTRACTOR_VERSION_TS clears after --stale (issue #2576 bug 3)', async () => {
// A page whose updated_at predates the version watermark used to be
// stamped at its updated_at (< versionTs), so the version arm re-fired
// every run — permanently stale. The sweep now floors the stamp at
// versionTs. (The #1768 test above also covers this since the v0.42.x
// VERSION_TS bump moved its date below the watermark, but this pins the
// behavior explicitly so a date "repair" there can't drop coverage.)
await engine.putPage('people/alice', personPage('Alice'));
await engine.executeRaw(`UPDATE pages SET updated_at = '2000-01-01T00:00:00Z' WHERE slug = 'people/alice'`);
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(1);
await runExtract(engine, ['--stale']);
// Pre-floor this stayed 1 forever (stamp < versionTs → version arm re-fires).
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
await runExtract(engine, ['--stale']);
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
});
test('CDX-4 (D2): a link-flush throw aborts the sweep and leaves pages UNSTAMPED', async () => {
await engine.putPage('people/alice', personPage('Alice'));
await engine.putPage('companies/acme', companyPage('Acme', '[Alice](people/alice) founded [Acme](companies/acme).'));
+18
View File
@@ -140,6 +140,15 @@ describe('extractEntityRefs', () => {
expect(wikiRefs[0].needsResolution).toBe(true);
});
test('recognizes ops/ qualified wikilinks (issue #2576 bug 2)', () => {
// `ops` was missing from DIR_PATTERN, so [[ops/...]] fell through to
// the generic 2c pass (needsResolution) instead of being a real ref.
const refs = extractEntityRefs('Deployed via [[ops/services/pointer-agent]].');
expect(refs.length).toBe(1);
expect(refs[0].slug).toBe('ops/services/pointer-agent');
expect(refs[0].needsResolution).toBeUndefined();
});
test('skips qualified-syntax tokens (those belong to 2a)', () => {
// [[wiki:topics/ai]] looks like 2a's qualified shape — even though
// it wouldn't satisfy DIR_PATTERN, 2c must not claim it either
@@ -1069,6 +1078,15 @@ describe('makeResolver — fallback chain', () => {
]);
});
test('resolveBasenameMatches: path-style ref falls back to the tail (issue #2576 bug 2)', async () => {
// normalizeBasename strips slashes, so `runbooks/2026-05-01-pointer-agent`
// used to normalize to a garbage key that never hit the tail-keyed index.
const engine = makeFakeEngineWithSlugs(['ops/changes/2026-05-01-pointer-agent']);
const r = makeResolver(engine);
expect(await r.resolveBasenameMatches!('runbooks/2026-05-01-pointer-agent'))
.toEqual(['ops/changes/2026-05-01-pointer-agent']);
});
test('resolveBasenameMatches: case-insensitive fallback', async () => {
const engine = makeFakeEngineWithSlugs(['companies/fast-weigh']);
const r = makeResolver(engine);