Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 303bbfb0b8 fix(extract): mirror plain-bullet Format 4 in parseTimelineEntries (db-source parity)
extractTimelineFromContent (fs-source) and parseTimelineEntries
(db-source extract + put_page auto_timeline) are documented as
kept-in-sync; adding Format 4 to only the fs parser left brain-authored
plain bullets invisible on the write path and `extract --source db`.
Same skip in the citation pass so a plain bullet carrying its own
[Source: ...] files exactly one entry on the db path too.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:22:44 -07:00
9efe229eee fix(extract): recognize plain-bullet timeline format as Format 4 (takeover of #1896)
Rebase of #1896 onto master: since it was opened, #2524 landed an
inline-citation arm as Format 3 at the same insertion point, so the
plain-bullet arm now lands as Format 4 and the citation loop's skip is
extended to plain-bullet lines — a plain bullet carrying its own
[Source: ...] citation (the shape quality.md mandates) files exactly
one entry instead of double-counting.

Co-authored-by: ElliotDrel <ElliotDrel@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:20:05 -07:00
10 changed files with 113 additions and 121 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) {
+18 -1
View File
@@ -509,8 +509,12 @@ export function extractTimelineFromContent(content: string, slug: string): Extra
// DB-level uniqueness cannot collapse.
const citationPattern = /\[Source:\s*([^\]]+?),\s*(\d{4}-\d{2}-\d{2})\s*\]/g;
const bulletLinePattern = /^-\s+\*\*\d{4}-\d{2}-\d{2}\*\*\s*\|/;
// Lines captured by Format 4 (plain bullet) are skipped for the same
// reason: quality.md mandates a trailing [Source: ...] on those bullets,
// and re-extracting the citation would double-count the event.
const plainBulletLinePattern = /^-\s+\d{4}-\d{2}-\d{2}\s*[—–-]/;
for (const line of content.split(/\r?\n/)) {
if (bulletLinePattern.test(line)) continue;
if (bulletLinePattern.test(line) || plainBulletLinePattern.test(line)) continue;
const lineMatches = [...line.matchAll(citationPattern)];
if (lineMatches.length === 0) continue;
// Strip every citation marker from the line to leave the annotated text.
@@ -526,6 +530,19 @@ export function extractTimelineFromContent(content: string, slug: string): Extra
}
}
// Format 4: Plain bullet — - YYYY-MM-DD — Summary
// This is the format gbrain's own enrich skill writes (no bold, no source
// pipe). Without it, every brain-authored timeline entry is invisible to
// extraction and timeline_coverage stays at 0%. Anchored at line start so a
// date inside a summary/link cannot start a spurious entry; a bold Format-1
// line (`- **…**`) cannot match here (a `*` follows the bullet, not a
// digit), and the citation loop above skips these lines, so a plain bullet
// carrying its own [Source: ...] files exactly one entry.
const plainBulletPattern = /^-\s+(\d{4}-\d{2}-\d{2})\s*[—–-]\s*(.+)$/gm;
while ((match = plainBulletPattern.exec(content)) !== null) {
entries.push({ slug, date: match[1], source: 'markdown', summary: match[2].trim() });
}
return entries;
}
+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}: ${e instanceof Error ? e.message : String(e)}`);
}
}
+8 -3
View File
@@ -1103,6 +1103,11 @@ export interface TimelineCandidate {
// Match: `- **YYYY-MM-DD** | summary` or `- **YYYY-MM-DD** -- summary`
// or `- **YYYY-MM-DD** - summary` or just `**YYYY-MM-DD** | summary`.
const TIMELINE_LINE_RE = /^\s*-?\s*\*\*(\d{4}-\d{2}-\d{2})\*\*\s*[|\-–—]+\s*(.+?)\s*$/;
// Plain bullet: `- YYYY-MM-DD — summary` (no bold, no source pipe). Kept in
// sync with extractTimelineFromContent's Format 4 (the fs-source path).
// Anchored flush-left so a date inside an indented continuation line cannot
// start a spurious entry.
const PLAIN_TIMELINE_LINE_RE = /^-\s+(\d{4}-\d{2}-\d{2})\s*[—–-]\s*(.+?)\s*$/;
/**
* Parse timeline entries from content. Looks at:
@@ -1119,7 +1124,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
let i = 0;
while (i < lines.length) {
const m = TIMELINE_LINE_RE.exec(lines[i]);
const m = TIMELINE_LINE_RE.exec(lines[i]) ?? PLAIN_TIMELINE_LINE_RE.exec(lines[i]);
if (!m) {
i++;
continue;
@@ -1136,7 +1141,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
let j = i + 1;
while (j < lines.length) {
const next = lines[j];
if (TIMELINE_LINE_RE.test(next)) break;
if (TIMELINE_LINE_RE.test(next) || PLAIN_TIMELINE_LINE_RE.test(next)) break;
if (/^#{1,6}\s/.test(next)) break;
if (next.trim().length === 0 && detailLines.length === 0) {
// skip leading blank line; if we hit a blank after detail content
@@ -1166,7 +1171,7 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
// bullet pass are skipped (a bullet often carries its own citation).
const citationRe = /\[Source:\s*([^\]]+?),\s*(\d{4}-\d{2}-\d{2})\s*\]/g;
for (const line of lines) {
if (TIMELINE_LINE_RE.test(line)) continue;
if (TIMELINE_LINE_RE.test(line) || PLAIN_TIMELINE_LINE_RE.test(line)) continue;
const matches = [...line.matchAll(citationRe)];
if (matches.length === 0) continue;
const summary = line
-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();
});
});
+43
View File
@@ -185,6 +185,49 @@ describe('extractTimelineFromContent', () => {
expect(entries).toHaveLength(1);
expect(entries[0].summary).toBe('Landed the enterprise pilot with acme-example.');
});
// Format 4: the plain bullet `- YYYY-MM-DD — Summary` that gbrain's own
// enrich skill writes. Before this was supported, every brain-authored
// timeline entry was invisible and timeline_coverage was stuck at 0%.
it('extracts plain bullet format (- YYYY-MM-DD — Summary)', () => {
const content = `## Timeline\n- 2026-06-01 — Catch-up call with alice-example; intros offered.`;
const entries = extractTimelineFromContent(content, 'people/alice-example');
expect(entries).toHaveLength(1);
expect(entries[0].date).toBe('2026-06-01');
expect(entries[0].source).toBe('markdown');
expect(entries[0].summary).toBe('Catch-up call with alice-example; intros offered.');
});
it('files exactly one entry for a plain bullet that carries its own citation', () => {
// quality.md mandates this shape; it must not double-count via the
// citation arm (Format 3) AND the plain-bullet arm (Format 4).
const content = `- 2026-05-31 — Confirmed full name. [Source: User, 2026-05-31]`;
const entries = extractTimelineFromContent(content, 'people/charlie-example');
expect(entries).toHaveLength(1);
expect(entries[0].date).toBe('2026-05-31');
expect(entries[0].source).toBe('markdown');
expect(entries[0].summary).toContain('Confirmed full name.');
});
it('does not double-count bold (Format 1) lines as plain bullets', () => {
const content = `- **2025-03-18** | Meeting — Discussed partnership`;
const entries = extractTimelineFromContent(content, 'test');
expect(entries).toHaveLength(1);
expect(entries[0].source).toBe('Meeting');
});
it('does not start a spurious entry from a date inside a summary', () => {
const content = `- 2026-06-01 — See [meeting](meetings/2026-06-01).`;
const entries = extractTimelineFromContent(content, 'people/alice-example');
expect(entries).toHaveLength(1);
expect(entries[0].date).toBe('2026-06-01');
});
it('handles en dash and hyphen separators in plain bullets', () => {
const content = `- 2026-06-01 First\n- 2026-06-02 - Second`;
const entries = extractTimelineFromContent(content, 'test');
expect(entries).toHaveLength(2);
});
});
describe('walkMarkdownFiles', () => {
+24
View File
@@ -720,6 +720,30 @@ More prose here.
const entries = parseTimelineEntries(content);
expect(entries.length).toBe(2);
});
// Plain bullet (extract.ts Format 4 parity — the db-source path must see
// the same entries as the fs-source path).
test('parses plain bullet: - YYYY-MM-DD — summary', () => {
const entries = parseTimelineEntries('## Timeline\n- 2026-06-01 — Catch-up call with alice-example');
expect(entries.length).toBe(1);
expect(entries[0].date).toBe('2026-06-01');
expect(entries[0].summary).toBe('Catch-up call with alice-example');
});
test('files exactly one entry for a plain bullet carrying its own citation', () => {
const entries = parseTimelineEntries('- 2026-05-31 — Confirmed full name. [Source: User, 2026-05-31]');
expect(entries.length).toBe(1);
expect(entries[0].date).toBe('2026-05-31');
});
test('skips invalid dates in plain bullets', () => {
expect(parseTimelineEntries('- 2026-13-45 — Bad date').length).toBe(0);
});
test('does not double-count a bold bullet as a plain bullet', () => {
const entries = parseTimelineEntries('- **2026-01-15** | Met with Alice');
expect(entries.length).toBe(1);
});
});
// ─── isAutoLinkEnabled ─────────────────────────────────────────