feat(extract): recognize inline [Source: ..., YYYY-MM-DD] citations as timeline entries (#2524)

* feat(extract): recognize inline [Source: ..., YYYY-MM-DD] citations as timeline entries

gbrain's own quality conventions (skills/conventions/quality.md) require a
dated [Source: ..., YYYY-MM-DD] citation on every brain write, so curated
pages are full of dated evidence — but extractTimelineFromContent only
recognized the timeline-bullet and date-header formats. A page whose dates
all live in citations scored zero timeline coverage in brain_score, and
doctor pointed users at a formatting convention their own citations already
satisfied in spirit.

Format 3 files one entry per citation: date and source from the marker,
summary from the annotated line with citation markers stripped. Lines
already captured by Format 1 are skipped so a timeline bullet carrying its
own citation is not double-filed. Bare citations with no surrounding text
are ignored.

Idempotency is unchanged: persistence already dedupes at the DB layer.

* fix(extract): Format 3 citations also in parseTimelineEntries (db-source + ingest path)

The first commit only taught extractTimelineFromContent (fs-source) the
citation format; the db-source extract and the ingest path parse through
parseTimelineEntries in core/link-extraction.ts, which still could not see
citations. Same rules as the fs parser: bullet-captured lines skipped,
bare citations ignored, invalid calendar dates rejected; the citation
source is preserved in the entry detail.

---------

Co-authored-by: pabloglzg <186649799+pabloglzg@users.noreply.github.com>

src/commands/extract.ts

@@ -494,6 +494,38 @@ export function extractTimelineFromContent(content: string, slug: string): Extra
     entries.push({ slug, date: match[1], source: 'markdown', summary: match[2].trim(), detail: detail || undefined });
   }
 
+  // Format 3: Inline citation — [Source: <source>, YYYY-MM-DD]
+  //
+  // This is the citation convention gbrain's own quality rules require on
+  // every brain write (skills/conventions/quality.md), so dated evidence is
+  // pervasive in curated pages — but until now the extractor could not see
+  // it, and a page whose dates all live in citations scored zero timeline
+  // coverage. The entry's summary is the sentence the citation annotates
+  // (the surrounding line with citation markers stripped).
+  //
+  // Lines already captured by Format 1 are skipped: a timeline bullet often
+  // carries its own [Source: ...] citation, and re-extracting it would file
+  // a duplicate entry under a different (source, summary) shape that the
+  // 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*\|/;
+  for (const line of content.split(/\r?\n/)) {
+    if (bulletLinePattern.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.
+    const summary = line
+      .replace(/\[Source:[^\]]*\]/g, '')
+      .replace(/^[-*>#\s]+/, '')
+      .replace(/\s+/g, ' ')
+      .trim()
+      .slice(0, 300);
+    if (!summary) continue; // a bare citation with no surrounding text is not an event
+    for (const m of lineMatches) {
+      entries.push({ slug, date: m[2], source: m[1].trim().slice(0, 200), summary });
+    }
+  }
+
   return entries;
 }
 

src/core/link-extraction.ts

@@ -1156,6 +1156,31 @@ export function parseTimelineEntries(content: string): TimelineCandidate[] {
     result.push({ date, summary, detail: detailLines.join(' ').trim() });
     i = j;
   }
+
+  // Format 3: inline citation — [Source: <source>, YYYY-MM-DD]. The citation
+  // convention gbrain's own quality rules require on every brain write;
+  // until now this parser (the db-source extract + ingest path) could not
+  // see it, so a page whose dates all live in citations scored zero
+  // timeline coverage. Kept in sync with extractTimelineFromContent's
+  // Format 3 (the fs-source path). Lines already captured by the timeline
+  // 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;
+    const matches = [...line.matchAll(citationRe)];
+    if (matches.length === 0) continue;
+    const summary = line
+      .replace(/\[Source:[^\]]*\]/g, '')
+      .replace(/^[-*>#\s]+/, '')
+      .replace(/\s+/g, ' ')
+      .trim()
+      .slice(0, 300);
+    if (!summary) continue;
+    for (const m of matches) {
+      if (!isValidDate(m[2])) continue;
+      result.push({ date: m[2], summary, detail: `Source: ${m[1].trim().slice(0, 200)}` });
+    }
+  }
   return result;
 }
 

test/extract.test.ts

@@ -135,6 +135,56 @@ describe('extractTimelineFromContent', () => {
     const entries = extractTimelineFromContent(content, 'test');
     expect(entries).toHaveLength(1);
   });
+
+  it('extracts inline citation format entries', () => {
+    const content = `Closed the seed round with fund-a leading. [Source: board meeting notes, 2025-04-02]`;
+    const entries = extractTimelineFromContent(content, 'deals/acme-seed');
+    expect(entries).toHaveLength(1);
+    expect(entries[0].date).toBe('2025-04-02');
+    expect(entries[0].source).toBe('board meeting notes');
+    expect(entries[0].summary).toBe('Closed the seed round with fund-a leading.');
+  });
+
+  it('keeps commas inside the citation source', () => {
+    const content = `Alice joined as CTO. [Source: email from alice-example re: offer, signed, 2025-05-10]`;
+    const entries = extractTimelineFromContent(content, 'people/alice-example');
+    expect(entries).toHaveLength(1);
+    expect(entries[0].date).toBe('2025-05-10');
+    expect(entries[0].source).toBe('email from alice-example re: offer, signed');
+  });
+
+  it('extracts one entry per citation when a line carries several', () => {
+    const content = `Both sides confirmed the partnership. [Source: call with widget-co, 2025-06-01] [Source: follow-up email, 2025-06-03]`;
+    const entries = extractTimelineFromContent(content, 'companies/widget-co');
+    expect(entries).toHaveLength(2);
+    expect(entries[0].date).toBe('2025-06-01');
+    expect(entries[1].date).toBe('2025-06-03');
+    expect(entries[0].summary).toBe(entries[1].summary);
+  });
+
+  it('does not double-extract a timeline bullet that carries its own citation', () => {
+    const content = `- **2025-03-18** | Meeting — Discussed partnership [Source: meeting notes, 2025-03-18]`;
+    const entries = extractTimelineFromContent(content, 'test');
+    expect(entries).toHaveLength(1); // Format 1 only
+    expect(entries[0].source).toBe('Meeting');
+  });
+
+  it('skips a bare citation with no surrounding text', () => {
+    const content = `[Source: import batch, 2025-07-01]`;
+    expect(extractTimelineFromContent(content, 'test')).toHaveLength(0);
+  });
+
+  it('ignores citations without a date', () => {
+    const content = `Some claim here. [Source: undated memo]`;
+    expect(extractTimelineFromContent(content, 'test')).toHaveLength(0);
+  });
+
+  it('strips list markers from the citation summary', () => {
+    const content = `- Landed the enterprise pilot with acme-example. [Source: CRM update, 2025-08-15]`;
+    const entries = extractTimelineFromContent(content, 'companies/acme-example');
+    expect(entries).toHaveLength(1);
+    expect(entries[0].summary).toBe('Landed the enterprise pilot with acme-example.');
+  });
 });
 
 describe('walkMarkdownFiles', () => {

test/link-extraction.test.ts

@@ -1265,3 +1265,29 @@ describe("v0.18.0 migration v22 — links_resolution_type", () => {
   });
 });
 
+
+describe('parseTimelineEntries — Format 3: inline [Source: ..., YYYY-MM-DD] citations', () => {
+  test('extracts an entry from a dated citation', () => {
+    const entries = parseTimelineEntries('Closed the seed round. [Source: board notes, 2025-04-02]');
+    expect(entries).toHaveLength(1);
+    expect(entries[0].date).toBe('2025-04-02');
+    expect(entries[0].summary).toBe('Closed the seed round.');
+    expect(entries[0].detail).toBe('Source: board notes');
+  });
+
+  test('keeps commas inside the citation source', () => {
+    const entries = parseTimelineEntries('Alice joined. [Source: email re: offer, signed, 2025-05-10]');
+    expect(entries).toHaveLength(1);
+    expect(entries[0].detail).toBe('Source: email re: offer, signed');
+  });
+
+  test('does not double-extract a timeline bullet carrying its own citation', () => {
+    const entries = parseTimelineEntries('- **2025-03-18** | Meeting notes [Source: notes, 2025-03-18]');
+    expect(entries).toHaveLength(1); // bullet pass only
+  });
+
+  test('skips invalid calendar dates and bare citations', () => {
+    expect(parseTimelineEntries('Claim. [Source: memo, 2026-13-45]')).toHaveLength(0);
+    expect(parseTimelineEntries('[Source: import batch, 2025-07-01]')).toHaveLength(0);
+  });
+});