fix(dream): deterministic last-writer attribution for colliding slugs

collectChildPutPageSlugs paired each slug to a jobId first-seen over an
unordered result set. When two children collide on a final slug, the pages
row holds the LAST put_page write, so the provenance stamp
(transcript_id/transcript_source/date) could attribute an arbitrary other
transcript. ORDER BY id + last-writer-wins aligns the stamp with the
surviving content; pinned by a collision test.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/commands/extract.ts

@@ -433,10 +433,7 @@ export async function extractLinksFromFile(
       async resolve(name: string, dirHint?: string | string[]): Promise<string | null> {
         if (!name) return null;
         const trimmed = name.trim();
-        // Same broadened slug-shape as makeResolver step 1: accepts
-        // digit-leading folders (`90-people/nicolai`) and nested paths.
-        // Exact Set membership guards it — no false positives.
-        if (/\//.test(trimmed) && /^[a-z0-9][a-z0-9/_-]*$/.test(trimmed) && allSlugs.has(trimmed)) {
+        if (/^[a-z][a-z0-9-]*\/[a-z0-9][a-z0-9-]*$/.test(trimmed) && allSlugs.has(trimmed)) {
           return trimmed;
         }
         const hints = Array.isArray(dirHint) ? dirHint : (dirHint ? [dirHint] : []);
@@ -585,17 +582,6 @@ export interface ExtractOpts {
    * before (single-'default'-source brains unaffected).
    */
   sourceId?: string;
-  /**
-   * v0.42 — also extract frontmatter links on the incremental (slugs) path.
-   * `extractForSlugs` extracts BODY links only by default; set this true to also
-   * parse each changed page's frontmatter so `sources:`/`related:` edges stay fresh
-   * when YAML is edited externally and synced in. Applied PER changed page, so the
-   * incremental walk stays bounded (no switch to a full DB scan). Only honored on
-   * the incremental path (`slugs` defined); the full-walk path already covers
-   * frontmatter via its own dispatch. Gated upstream by the config key
-   * `autopilot.incremental_extract_include_frontmatter` (default off).
-   */
-  includeFrontmatter?: boolean;
 }
 
 /**
@@ -634,7 +620,7 @@ export async function runExtractCore(engine: BrainEngine, opts: ExtractOpts): Pr
       // Nothing changed — skip entirely.
       return result;
     }
-    const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers, opts.signal, opts.sourceId, opts.includeFrontmatter);
+    const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers, opts.signal, opts.sourceId);
     result.links_created = r.links_created;
     result.timeline_entries_created = r.timeline_created;
     result.pages_processed = r.pages;
@@ -1025,11 +1011,6 @@ async function extractForSlugs(
   signal?: AbortSignal,
   // #1747/#1503: stamp resolved brain source id on batch rows (see ExtractOpts.sourceId).
   sourceId?: string,
-  // v0.42: when true, also extract frontmatter links per changed page so
-  // externally-edited YAML (`sources:`/`related:`) stays fresh on the cycle.
-  // Default false preserves the body-only incremental behavior. Gated upstream
-  // by `autopilot.incremental_extract_include_frontmatter`.
-  includeFrontmatter: boolean = false,
 ): Promise<{ links_created: number; timeline_created: number; pages: number }> {
   // Build the full slug set for link resolution (fast: just readdir, no file reads)
   const allFiles = walkMarkdownFiles(brainDir);
@@ -1104,7 +1085,7 @@ async function extractForSlugs(
         const content = readFileSync(fullPath, 'utf-8');
 
         if (doLinks) {
-          const links = await extractLinksFromFile(content, relPath, allSlugs, { globalBasename, includeFrontmatter });
+          const links = await extractLinksFromFile(content, relPath, allSlugs, { globalBasename });
           for (const link of links) {
             if (dryRun) {
               if (!jsonMode) console.log(`  ${link.from_slug} → ${link.to_slug} (${link.link_type})`);

src/core/config.ts

@@ -121,18 +121,6 @@ export interface GBrainConfig {
       /** Daily spend cap (USD); bounds drains/day = floor(cap / ~$0.30). Default 2.0. */
       max_usd_per_day?: number;
     };
-    /**
-     * v0.42 — keep frontmatter links fresh on the incremental cycle. The cycle's
-     * extract phase re-extracts only the slugs a sync changed, but `extractForSlugs`
-     * extracts BODY links only — frontmatter (`sources:`/`related:` etc.) link edges
-     * silently drift stale when a page's YAML is edited externally and synced in.
-     * Set true to also extract frontmatter links per changed page each cycle, keeping
-     * externally-edited YAML edges fresh without a full rescan. Default false
-     * (preserves current behavior). Read via the file/env/DB plane in the cycle's
-     * extract dispatch. Disable/enable with
-     * `gbrain config set autopilot.incremental_extract_include_frontmatter <bool>`.
-     */
-    incremental_extract_include_frontmatter?: boolean;
   };
   eval?: {
     /** false disables capture entirely. Defaults to true. */

src/core/cycle.ts

@@ -996,21 +996,6 @@ async function runPhaseExtract(
 ): Promise<PhaseResult> {
   try {
     const { runExtractCore } = await import('../commands/extract.ts');
-    const { loadConfig } = await import('./config.ts');
-    // Default off: the incremental cycle extracts body links only unless the
-    // operator opts in to keeping externally-edited frontmatter links fresh too.
-    // Both planes, file wins (env > file > DB precedence, per loadConfigWithEngine):
-    // `gbrain config set autopilot.incremental_extract_include_frontmatter true`
-    // writes the DB plane (engine.setConfig), so a file-plane-only read here
-    // would make the documented enable command a silent no-op (#2120 class).
-    const fileVal = loadConfig()?.autopilot?.incremental_extract_include_frontmatter;
-    let includeFrontmatter = fileVal === true;
-    if (fileVal === undefined) {
-      try {
-        includeFrontmatter =
-          (await engine.getConfig('autopilot.incremental_extract_include_frontmatter')) === 'true';
-      } catch { /* config table unreadable → default off */ }
-    }
     // Extract is read-mostly against the filesystem + write to links table.
     // Honor dryRun by skipping with a 'skipped' entry: extract doesn't have
     // a clean dry-run mode today and runCycle should be honest about it.
@@ -1031,7 +1016,6 @@ async function runPhaseExtract(
       slugs: changedSlugs,  // undefined = full walk (first run / manual)
       signal,
       sourceId,
-      includeFrontmatter,  // honored on the incremental (slugs) path only
     });
     const linksCreated = result?.links_created ?? 0;
     const timelineCreated = result?.timeline_entries_created ?? 0;

src/core/cycle/synthesize.ts

@@ -428,8 +428,13 @@ export async function runPhaseSynthesize(
 
     const queue = new MinionQueue(engine);
     const childIds: number[] = [];
-    /** Map child job_id → chunk metadata for D6 orchestrator-side slug rewrite. */
-    const chunkInfo = new Map<number, { idx: number; hash6: string }>();
+    /**
+     * Map child job_id → transcript metadata. Drives D6 orchestrator-side
+     * slug rewrite for chunked transcripts AND the deterministic frontmatter
+     * stampDreamProvenance merges into each written page. Populated for
+     * every child (single-chunk children carry chunkTotal=1).
+     */
+    const childMeta = new Map<number, ChildMeta>();
     /** Skip reasons for the cycle report (D5 cap hits, D8 legacy-key skips). */
     const skipReports: Array<{ filePath: string; reason: string }> = [];
 
@@ -513,9 +518,14 @@ export async function runPhaseSynthesize(
           { allowProtectedSubmit: true },
         );
         childIds.push(child.id);
-        if (isChunked) {
-          chunkInfo.set(child.id, { idx: i, hash6 });
-        }
+        childMeta.set(child.id, {
+          idx: i,
+          hash6,
+          chunkTotal: chunks.length,
+          transcriptSource: t.transcriptSource,
+          transcriptId: stripContentVersionSuffix(t.basename),
+          inferredDate: t.inferredDate,
+        });
       }
     }
 
@@ -544,14 +554,14 @@ export async function runPhaseSynthesize(
 
     // Collect slugs from put_page tool executions across the children
     // (codex finding #2: deterministic provenance, NOT pages.updated_at).
-    // D6 orchestrator slug rewrite: chunkInfo drives post-hoc rewrite of
+    // D6 orchestrator slug rewrite: childMeta drives post-hoc rewrite of
     // bare-hash slugs to `<hash6>-c<idx>` so chunked siblings can't collide
     // even if Sonnet drops the chunk suffix.
     // v0.32.8: refs carry source_id so reverseWriteRefs picks the correct
     // (source, slug) row. #1586: refs are stamped with the cycle's resolved
     // source (children write there via SubagentHandlerData.source_id).
     const cycleSourceId = opts.sourceId ?? 'default';
-    const writtenRefs = await collectChildPutPageSlugs(engine, childIds, chunkInfo, cycleSourceId);
+    const writtenRefs = await collectChildPutPageSlugs(engine, childIds, childMeta, cycleSourceId);
 
     const summaryDate = opts.date ?? today();
 
@@ -559,7 +569,12 @@ export async function runPhaseSynthesize(
     // of every child-written page BEFORE reverse-rendering, so generated pages
     // are queryable (`frontmatter->>'dream_generated'`) and a later put_page
     // write-through (which re-renders from the DB row) can't erase the stamp.
-    await stampDreamProvenance(engine, writtenRefs, summaryDate);
+    // #2285: the stamp also carries the orchestrator-owned deterministic
+    // frontmatter (transcript_id, transcript_source, transcript_hash, date,
+    // chunk) derived from childMeta — subagent drift on those fields can't
+    // leak, and reverseWriteRefs below re-reads the row so the same fields
+    // land in the on-disk markdown.
+    await stampDreamProvenance(engine, writtenRefs, summaryDate, childMeta);
 
     // Dual-write: reverse-render each DB row → markdown file.
     const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs, cycleSourceId);
@@ -1095,15 +1110,17 @@ function sanitizeForSlug(s: string): string {
  * fake"): we no longer need detection because the rewrite enforces
  * uniqueness at slug-write time.
  *
- * `chunkInfo` maps child job_id → { chunk_index, hash6 }. Single-chunk
- * children are absent from the map and pass through unchanged.
+ * `childMeta` maps child job_id → per-child transcript metadata. Chunked
+ * children (chunkTotal > 1) get the slug rewrite; single-chunk children
+ * pass through unchanged. Each returned ref carries the job_id that wrote
+ * it so stampDreamProvenance can pair the slug back to its childMeta entry.
  */
 async function collectChildPutPageSlugs(
   engine: BrainEngine,
   childIds: number[],
-  chunkInfo: Map<number, { idx: number; hash6: string }>,
+  childMeta: Map<number, ChildMeta>,
   sourceId = 'default',
-): Promise<Array<{ slug: string; source_id: string }>> {
+): Promise<Array<{ slug: string; source_id: string; jobId: number }>> {
   if (childIds.length === 0) return [];
   // Raw fetch — NO SELECT DISTINCT. Preserves per-child slug duplicates so
   // the orchestrator sees what each child wrote. COALESCE handles both
@@ -1122,16 +1139,73 @@ async function collectChildPutPageSlugs(
        FROM subagent_tool_executions
       WHERE job_id = ANY($1::int[])
         AND tool_name = 'brain_put_page'
-        AND status = 'complete'`,
+        AND status = 'complete'
+      ORDER BY id`,
     [childIds],
   );
-  const rewritten = new Set<string>();
+  const rewritten = new Map<string, number>();
   for (const r of rows) {
     if (typeof r.slug !== 'string' || r.slug.length === 0) continue;
-    const ci = chunkInfo.get(r.job_id);
-    rewritten.add(ci ? rewriteChunkedSlug(r.slug, ci.hash6, ci.idx) : r.slug);
+    const meta = childMeta.get(r.job_id);
+    const finalSlug = meta && meta.chunkTotal > 1
+      ? rewriteChunkedSlug(r.slug, meta.hash6, meta.idx)
+      : r.slug;
+    // Last writer wins, in execution-row order (ORDER BY id): if two children
+    // collide on a final slug, the pages row holds the LAST put_page write, so
+    // the stamp must attribute that child's transcript — not an arbitrary one.
+    rewritten.set(finalSlug, r.job_id);
   }
-  return Array.from(rewritten).sort().map(slug => ({ slug, source_id: sourceId }));
+  return [...rewritten.entries()]
+    .sort(([a], [b]) => a.localeCompare(b))
+    .map(([slug, jobId]) => ({ slug, source_id: sourceId, jobId }));
+}
+
+/**
+ * Per-child orchestrator state. Drives D6 chunked-slug rewrite (idx + hash6)
+ * AND the deterministic frontmatter stampDreamProvenance merges into each
+ * written page. Populated for every child, not just chunked ones.
+ */
+interface ChildMeta {
+  idx: number;
+  hash6: string;
+  chunkTotal: number;
+  transcriptSource: string | null;
+  transcriptId: string;
+  inferredDate: string | null;
+}
+
+/**
+ * Strip the content-version suffix that claude-code-archive appends when a
+ * conversation is edited (`<uuid>--<contentHash>.md`). The session UUID is
+ * the stable transcript identifier; the suffix changes with content. Used to
+ * populate `transcript_id` so edits of the same session collapse to one id.
+ */
+function stripContentVersionSuffix(basename: string): string {
+  return basename.replace(/--[a-f0-9]+$/i, '');
+}
+
+/**
+ * Deterministic frontmatter for one synthesized page (#2285). Every field
+ * here is owned by the orchestrator — the subagent's value for any of these
+ * is overwritten. The subagent retains authority over type / title / tags /
+ * body. `date` feeds the effective-date precedence chain
+ * (src/core/effective-date.ts) so re-imports keep the conversation date even
+ * when sync tools re-stamp file mtimes.
+ */
+function buildDeterministicFrontmatter(
+  meta: ChildMeta,
+  cycleDate: string,
+): Record<string, unknown> {
+  const overrides: Record<string, unknown> = {
+    dream_generated: true,
+    dream_cycle_date: cycleDate,
+    transcript_id: meta.transcriptId,
+    transcript_hash: meta.hash6,
+  };
+  if (meta.transcriptSource) overrides.transcript_source = meta.transcriptSource;
+  if (meta.chunkTotal > 1) overrides.chunk = `${meta.idx + 1}/${meta.chunkTotal}`;
+  if (meta.inferredDate) overrides.date = meta.inferredDate;
+  return overrides;
 }
 
 /**
@@ -1177,12 +1251,19 @@ async function hasLegacySingleChunkCompletion(
  */
 async function stampDreamProvenance(
   engine: BrainEngine,
-  refs: Array<{ slug: string; source_id: string }>,
+  refs: Array<{ slug: string; source_id: string; jobId?: number }>,
   cycleDate: string,
+  childMeta?: Map<number, ChildMeta>,
 ): Promise<void> {
   if (refs.length === 0) return;
   const { executeRawJsonb } = await import('../sql-query.ts');
-  for (const { slug, source_id } of refs) {
+  for (const { slug, source_id, jobId } of refs) {
+    // #2285: when the ref pairs back to a child, the stamp also carries the
+    // orchestrator-owned deterministic frontmatter for that transcript.
+    const meta = jobId !== undefined ? childMeta?.get(jobId) : undefined;
+    const stamp = meta
+      ? buildDeterministicFrontmatter(meta, cycleDate)
+      : { dream_generated: true, dream_cycle_date: cycleDate };
     try {
       await executeRawJsonb(
         engine,
@@ -1190,7 +1271,7 @@ async function stampDreamProvenance(
             SET frontmatter = COALESCE(frontmatter, '{}'::jsonb) || $3::jsonb
           WHERE slug = $1 AND source_id = $2`,
         [slug, source_id],
-        [{ dream_generated: true, dream_cycle_date: cycleDate }],
+        [stamp],
       );
     } catch (e) {
       const msg = e instanceof Error ? e.message : String(e);

src/core/cycle/transcript-discovery.ts

@@ -10,7 +10,7 @@
  */
 
 import { readFileSync, readdirSync, statSync } from 'node:fs';
-import { join, basename } from 'node:path';
+import { join, basename, dirname } from 'node:path';
 import { createHash } from 'node:crypto';
 import { pruneDir } from '../sync.ts';
 
@@ -23,8 +23,22 @@ export interface DiscoveredTranscript {
   content: string;
   /** Filename basename without extension; used as a topic-slug seed. */
   basename: string;
-  /** Inferred date if the basename matches `YYYY-MM-DD...` (or null). */
+  /**
+   * Inferred conversation date (YYYY-MM-DD) or null. Precedence: the
+   * `| First message | <ISO> |` row in the transcript's `## Metadata`
+   * table (stable across mtime-restamping re-syncs) wins; a leading
+   * `YYYY-MM-DD` in the basename is the fallback.
+   */
   inferredDate: string | null;
+  /**
+   * Transcript source archive name, derived from the path's grandparent
+   * directory (the immediate parent of the date directory). For the
+   * canonical layout `<corpus>/<source>/<date>/<id>.md` this yields the
+   * source-name segment — e.g. `claude-code` for the claude-code-archive
+   * output, `meetings` for meeting recordings. Null when the file does
+   * not live under a `<source>/<date>/` pair (ad-hoc inputs).
+   */
+  transcriptSource: string | null;
 }
 
 export interface DiscoverOpts {
@@ -161,6 +175,36 @@ function matchesAnyExclude(text: string, patterns: RegExp[]): boolean {
   return false;
 }
 
+/**
+ * Content-based conversation date: the `| First message | <ISO timestamp> |`
+ * row claude-code-archive writes into the transcript's `## Metadata` table.
+ * Stable across rsync/Dropbox/Syncthing/B2 re-syncs that re-stamp mtime,
+ * unlike anything derived from file metadata. Returns YYYY-MM-DD or null.
+ */
+const FIRST_MESSAGE_RE = /^\|\s*First message\s*\|\s*(\d{4}-\d{2}-\d{2})/im;
+
+export function inferContentDate(content: string): string | null {
+  const m = FIRST_MESSAGE_RE.exec(content);
+  return m ? m[1] : null;
+}
+
+/**
+ * Derive the archive source name from a transcript path. Returns the basename
+ * of the directory two levels above the file when the immediate parent is a
+ * date directory and the grandparent looks like a source-name slug (lowercase
+ * alphanumeric segments separated by hyphens); otherwise null. This pins the
+ * canonical claude-code-archive layout `<corpus>/<source>/<date>/<id>.md`
+ * without claiming a source for ad-hoc inputs that don't match.
+ */
+export function deriveTranscriptSource(filePath: string): string | null {
+  const parentName = basename(dirname(filePath));
+  if (!/^\d{4}-\d{2}-\d{2}/.test(parentName)) return null;
+  const grandparentName = basename(dirname(dirname(filePath)));
+  if (!grandparentName) return null;
+  if (!/^[a-z0-9]+(-[a-z0-9]+)*$/.test(grandparentName)) return null;
+  return grandparentName;
+}
+
 function listTextFiles(dir: string): string[] {
   // Recursive walk with descent-time pruning (closes codex C12/C13 spec gap).
   // Accepts BOTH .txt and .md per transcript-discovery's domain rules — does
@@ -225,8 +269,11 @@ export function discoverTranscripts(opts: DiscoverOpts): DiscoveredTranscript[]
       const ext = filePath.endsWith('.md') ? '.md' : '.txt';
       const baseName = basename(filePath, ext);
       const dateMatch = DATE_RE.exec(baseName);
-      const inferredDate = dateMatch ? dateMatch[1] : null;
-      if (!isInDateRange(inferredDate, opts)) continue;
+      const filenameDate = dateMatch ? dateMatch[1] : null;
+      // Fast path: date-named files outside the window skip before the read.
+      // ponytail: a date-named file whose content date differs is filtered on
+      // its filename date — acceptable; archive layouts use UUID basenames.
+      if (filenameDate && !isInDateRange(filenameDate, opts)) continue;
 
       let content: string;
       try {
@@ -241,12 +288,17 @@ export function discoverTranscripts(opts: DiscoverOpts): DiscoveredTranscript[]
       }
       if (matchesAnyExclude(content, excludeRes)) continue;
 
+      // Content-metadata date wins (survives mtime restamps); filename next.
+      const inferredDate = inferContentDate(content) ?? filenameDate;
+      if (!isInDateRange(inferredDate, opts)) continue;
+
       results.push({
         filePath,
         contentHash: hashContent(content),
         content,
         basename: baseName,
         inferredDate,
+        transcriptSource: deriveTranscriptSource(filePath),
       });
     }
   }
@@ -290,6 +342,7 @@ export function readSingleTranscript(
     contentHash: hashContent(content),
     content,
     basename: baseName,
-    inferredDate: dateMatch ? dateMatch[1] : null,
+    inferredDate: inferContentDate(content) ?? (dateMatch ? dateMatch[1] : null),
+    transcriptSource: deriveTranscriptSource(filePath),
   };
 }

src/core/link-extraction.ts

@@ -942,17 +942,8 @@ export function makeResolver(
 
       const hints = Array.isArray(dirHint) ? dirHint : (dirHint ? [dirHint] : []);
 
-      // Step 1: already a slug? Try an exact page lookup for any slug-shaped
-      // value (contains '/', slug charset). Broadened beyond the original
-      // single-segment lowercase-leading form (`^[a-z][a-z0-9-]*\/[a-z0-9]...`)
-      // to also accept digit-leading folders (`90-people/nicolai`,
-      // `01-trading/...`) and nested paths (`a/b/c`) — common in PARA-numbered
-      // vaults. This is an EXACT getPage match only — no fuzzy — so it never
-      // produces a false positive; a non-existent slug just falls through to
-      // the steps below. Fixes frontmatter `related: [[dir/slug]]` values
-      // (unwrapped by unwrapWikilink) that name a real page the strict regex
-      // could not reach and whose full-path fuzzy score is below threshold.
-      if (/\//.test(trimmed) && /^[a-z0-9][a-z0-9/_-]*$/.test(trimmed)) {
+      // Step 1: already a slug? (dir/name shape, lowercase, hyphenated)
+      if (/^[a-z][a-z0-9-]*\/[a-z0-9][a-z0-9-]*$/.test(trimmed)) {
         const page = await engine.getPage(trimmed);
         if (page) {
           cache.set(cacheKey, trimmed);
@@ -1012,25 +1003,6 @@ export function makeResolver(
 
 // ─── Frontmatter extractor ──────────────────────────────────────
 
-/**
- * Unwrap an Obsidian `[[wikilink]]` frontmatter value to its bare link
- * target so the resolver (which expects bare titles / dir slugs) can match
- * it. Mainstream Obsidian authors frontmatter links as `related: ["[[Page]]"]`;
- * without this, the resolver treats the brackets as part of the value and a
- * `[[90-people/nicolai]]` is normalized into `90peoplenicolai`, so it never
- * resolves. Strips a trailing `|alias`, `#heading`, or `^block` suffix — the
- * link target only. The regex is anchored to a wholly-wrapped value
- * (`^\s*\[\[…\]\]\s*$`), so bare titles and any value not fully wrapped pass
- * through unchanged and existing behavior is preserved exactly.
- */
-export function unwrapWikilink(value: string): string {
-  const match = /^\s*\[\[(.+?)\]\]\s*$/.exec(value);
-  if (!match) return value;
-  // Take the link target: drop |alias, then #heading / ^block suffixes.
-  const target = match[1].split('|')[0].split('#')[0].split('^')[0];
-  return target.trim();
-}
-
 export interface UnresolvedFrontmatterRef {
   /** The frontmatter field name. */
   field: string;
@@ -1088,12 +1060,7 @@ export async function extractFrontmatterLinks(
         }
         if (!name) continue;   // skip numbers, nulls, malformed objects
 
-        // Accept Obsidian `[[wikilink]]` values in frontmatter link fields by
-        // unwrapping to the bare target before resolution. Bare titles pass
-        // through unchanged; the original `name` is preserved for the
-        // unresolved report and edge context.
-        const linkTarget = unwrapWikilink(name);
-        const resolved = await resolver.resolve(linkTarget, mapping.dirHint);
+        const resolved = await resolver.resolve(name, mapping.dirHint);
         if (!resolved) {
           unresolved.push({ field, name });
           continue;

test/cycle-dream-output-root.test.ts

@@ -26,6 +26,7 @@ const transcript: DiscoveredTranscript = {
   content: 'User: hello world',
   contentHash: 'abcdef0123456789',
   inferredDate: '2026-07-17',
+  transcriptSource: null,
 } as DiscoveredTranscript;
 
 describe('#2415: buildSynthesisPrompt output root', () => {

test/cycle-synthesize-slug-collection.test.ts

@@ -152,3 +152,94 @@ describe('#2569: stampDreamProvenance persists the marker into DB frontmatter',
     await stampDreamProvenance(engine as any, refs, '2026-07-17'); // idempotent
   });
 });
+
+describe('#2285: orchestrator-owned deterministic transcript frontmatter', () => {
+  const meta = {
+    idx: 1,
+    hash6: 'abc123',
+    chunkTotal: 3,
+    transcriptSource: 'claude-code',
+    transcriptId: 'session-uuid',
+    inferredDate: '2026-05-15',
+  };
+
+  test('collectChildPutPageSlugs pairs each ref back to the writing job', async () => {
+    const refs = await collectChildPutPageSlugs(
+      engine as any, [1001], new Map([[1001, { ...meta, chunkTotal: 1 }]]), 'mybrain',
+    );
+    expect(refs.length).toBeGreaterThan(0);
+    for (const r of refs) {
+      expect(r.jobId).toBe(1001);
+      expect(r.source_id).toBe('mybrain'); // #1586: cycle source, never hardcoded 'default'
+    }
+  });
+
+  test('slug collision across children attributes the LAST writer (matches surviving putPage)', async () => {
+    const db = (engine as any).db;
+    // Jobs 1001 then 1002 write the same slug; the pages row would hold
+    // 1002's content (last put_page wins), so the ref must carry jobId 1002.
+    await db.query(
+      `INSERT INTO subagent_tool_executions (job_id, message_idx, tool_use_id, tool_name, status, input)
+       VALUES (1001, 9, 'tool_dup_a', 'brain_put_page', 'complete', $1::jsonb)`,
+      [JSON.stringify({ slug: 'wiki/agents/test/collision', body: 'first' })],
+    );
+    await db.query(
+      `INSERT INTO subagent_tool_executions (job_id, message_idx, tool_use_id, tool_name, status, input)
+       VALUES (1002, 9, 'tool_dup_b', 'brain_put_page', 'complete', $1::jsonb)`,
+      [JSON.stringify({ slug: 'wiki/agents/test/collision', body: 'second' })],
+    );
+    const refs = await collectChildPutPageSlugs(engine as any, [1001, 1002], new Map());
+    const hit = refs.find((r: { slug: string }) => r.slug === 'wiki/agents/test/collision');
+    expect(hit?.jobId).toBe(1002);
+  });
+
+  test('stampDreamProvenance merges the transcript metadata into DB frontmatter', async () => {
+    const slug = 'wiki/originals/ideas/2026-07-17-transcript-meta-abc123';
+    await engine.putPage(slug, {
+      type: 'note',
+      title: 'Meta stamp',
+      compiled_truth: 'body',
+      timeline: '',
+      frontmatter: { keep_me: 'yes', transcript_id: 'subagent-drift' },
+    });
+    await stampDreamProvenance(
+      engine as any,
+      [{ slug, source_id: 'default', jobId: 42 }],
+      '2026-07-17',
+      new Map([[42, meta]]),
+    );
+    const rows = await engine.executeRaw<{ fm: Record<string, unknown> }>(
+      `SELECT frontmatter AS fm FROM pages WHERE slug = $1`, [slug],
+    );
+    const fm = rows[0].fm as Record<string, unknown>;
+    expect(fm.dream_generated).toBe(true);
+    expect(fm.dream_cycle_date).toBe('2026-07-17');
+    expect(fm.transcript_id).toBe('session-uuid'); // orchestrator wins over subagent drift
+    expect(fm.transcript_hash).toBe('abc123');
+    expect(fm.transcript_source).toBe('claude-code');
+    expect(fm.chunk).toBe('2/3');
+    expect(fm.date).toBe('2026-05-15');
+    expect(fm.keep_me).toBe('yes'); // subagent-owned keys survive
+  });
+
+  test('single-chunk children with no inferredDate stamp only the applicable fields', async () => {
+    const slug = 'wiki/originals/ideas/2026-07-17-minimal-meta-abc123';
+    await engine.putPage(slug, {
+      type: 'note', title: 'Minimal', compiled_truth: 'b', timeline: '', frontmatter: {},
+    });
+    await stampDreamProvenance(
+      engine as any,
+      [{ slug, source_id: 'default', jobId: 43 }],
+      '2026-07-17',
+      new Map([[43, { ...meta, chunkTotal: 1, transcriptSource: null, inferredDate: null }]]),
+    );
+    const rows = await engine.executeRaw<{ fm: Record<string, unknown> }>(
+      `SELECT frontmatter AS fm FROM pages WHERE slug = $1`, [slug],
+    );
+    const fm = rows[0].fm as Record<string, unknown>;
+    expect(fm.transcript_id).toBe('session-uuid');
+    expect(fm.chunk).toBeUndefined();
+    expect(fm.transcript_source).toBeUndefined();
+    expect(fm.date).toBeUndefined();
+  });
+});

test/cycle-synthesize.test.ts

@@ -302,6 +302,7 @@ describe('judgeSignificance', () => {
       content: 'A short conversation about something interesting.',
       basename: 'x',
       inferredDate: null,
+      transcriptSource: null,
     };
   }
 
@@ -415,6 +416,7 @@ describe('judgeSignificance — UTF-16 safety (v0.41.13)', () => {
       content,
       basename: 'long',
       inferredDate: null,
+      transcriptSource: null,
     };
   }
 

test/cycle/synthesize-gateway-adapter.test.ts

@@ -45,6 +45,7 @@ const FIXTURE_TRANSCRIPT: DiscoveredTranscript = {
   content: 'Synthetic transcript content for gateway-adapter parity tests.',
   contentHash: 'sha-fixture-1',
   inferredDate: '2026-05-24',
+  transcriptSource: null,
 };
 
 describe('makeJudgeClient — construction-time provider probe', () => {

test/cycle/transcript-discovery-metadata.test.ts

@@ -0,0 +1,109 @@
+/**
+ * #2285 — transcript metadata discovery.
+ *
+ * Pins the two discovery-side additions:
+ *   1. `transcriptSource` — derived from the `<source>/<date>/<file>` path
+ *      layout; null for ad-hoc inputs that don't match.
+ *   2. Content-based date inference — the `| First message | <ISO> |` row in
+ *      the transcript's `## Metadata` table wins over the filename-regex
+ *      date (stable across mtime-restamping re-syncs); filename is the
+ *      fallback.
+ *
+ * Pure filesystem; no engine, no LLM.
+ */
+
+import { describe, test, expect, beforeEach, afterEach } from 'bun:test';
+import { mkdtempSync, rmSync, writeFileSync, mkdirSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join, dirname } from 'node:path';
+import {
+  discoverTranscripts,
+  readSingleTranscript,
+  deriveTranscriptSource,
+  inferContentDate,
+} from '../../src/core/cycle/transcript-discovery.ts';
+
+let tmpDir: string;
+
+beforeEach(() => {
+  tmpDir = mkdtempSync(join(tmpdir(), 'gbrain-transcript-meta-'));
+});
+
+afterEach(() => {
+  rmSync(tmpDir, { recursive: true, force: true });
+});
+
+function write(relPath: string, body: string): string {
+  const full = join(tmpDir, relPath);
+  mkdirSync(dirname(full), { recursive: true });
+  writeFileSync(full, body);
+  return full;
+}
+
+const FILLER = 'User: hello world. '.repeat(200);
+const METADATA_BLOCK =
+  '## Metadata\n\n| Key | Value |\n| --- | --- |\n| First message | 2026-05-15T03:51:11.584Z |\n\n';
+
+describe('deriveTranscriptSource', () => {
+  test('extracts the source slug from <source>/<date>/<file> layout', () => {
+    expect(deriveTranscriptSource('/corpus/claude-code/2026-06-12/abc.md')).toBe('claude-code');
+    expect(deriveTranscriptSource('/corpus/voice-notes/2026-06-12/xyz.md')).toBe('voice-notes');
+  });
+
+  test('null when the parent dir is not a date dir or grandparent is not a slug', () => {
+    expect(deriveTranscriptSource('/corpus/flat-file.md')).toBeNull();
+    expect(deriveTranscriptSource('/corpus/claude-code/not-a-date/abc.md')).toBeNull();
+    expect(deriveTranscriptSource('/corpus/Not A Slug/2026-06-12/abc.md')).toBeNull();
+  });
+});
+
+describe('inferContentDate', () => {
+  test('parses the | First message | row', () => {
+    expect(inferContentDate(METADATA_BLOCK)).toBe('2026-05-15');
+  });
+  test('null when absent', () => {
+    expect(inferContentDate(FILLER)).toBeNull();
+  });
+});
+
+describe('discoverTranscripts — transcriptSource + date cascade', () => {
+  test('populates transcriptSource per file; null for flat files', () => {
+    write('claude-code/2026-06-12/aaaa.md', FILLER);
+    write('2026-06-12-flat.md', FILLER);
+    const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
+    const byBase = new Map(out.map(t => [t.basename, t.transcriptSource]));
+    expect(byBase.get('aaaa')).toBe('claude-code');
+    expect(byBase.get('2026-06-12-flat')).toBeNull();
+  });
+
+  test('content First-message date wins over the filename date', () => {
+    write('2026-01-01-named.md', METADATA_BLOCK + FILLER);
+    const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
+    expect(out).toHaveLength(1);
+    expect(out[0].inferredDate).toBe('2026-05-15');
+  });
+
+  test('filename date remains the fallback when content has no metadata row', () => {
+    write('2026-01-01-named.md', FILLER);
+    const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
+    expect(out[0].inferredDate).toBe('2026-01-01');
+  });
+
+  test('date filter matches on the content date for UUID-named transcripts', () => {
+    write('claude-code/2026-05-15/uuid-basename.md', METADATA_BLOCK + FILLER);
+    const hit = discoverTranscripts({ corpusDir: tmpDir, minChars: 100, date: '2026-05-15' });
+    expect(hit).toHaveLength(1);
+    const miss = discoverTranscripts({ corpusDir: tmpDir, minChars: 100, date: '2026-05-16' });
+    expect(miss).toHaveLength(0);
+  });
+});
+
+describe('readSingleTranscript — same metadata surface', () => {
+  test('carries transcriptSource and prefers the content date', () => {
+    const p = write('claude-code/2026-05-15/2026-01-01-single.md', METADATA_BLOCK + FILLER);
+    const t = readSingleTranscript(p, { minChars: 100 });
+    expect(t).not.toBeNull();
+    expect(t!.transcriptSource).toBe('claude-code');
+    expect(t!.inferredDate).toBe('2026-05-15');
+  });
+});

test/extract-incremental.test.ts

@@ -191,37 +191,3 @@ describe('runExtractCore — incremental cycle path (#417)', () => {
     expect(result.links_created).toBeGreaterThan(0);
   });
 });
-describe('runExtractCore — incremental frontmatter gate (includeFrontmatter)', () => {
-  // alice has a `source:` frontmatter edge but NO body links. The incremental
-  // path extracts body links only by default, so the frontmatter edge is the
-  // sole signal that distinguishes the gate off vs on.
-  const aliceFm = '---\nsource: companies/acme-example\n---\n# alice';
-
-  test('9. default (flag omitted) does NOT extract frontmatter links on the incremental path', async () => {
-    await seedPage('companies/acme-example', '# acme');
-    await seedPage('people/alice-example', aliceFm);
-    const result = await runExtractCore(engine as unknown as BrainEngine, {
-      mode: 'all',
-      dir: tempDir,
-      slugs: ['people/alice-example'],
-    });
-    // alice's only potential edge is her frontmatter `source:`; with the gate off
-    // it must not be extracted (preserves the body-only incremental behavior).
-    expect(result.pages_processed).toBe(1);
-    expect(result.links_created).toBe(0);
-  });
-
-  test('10. includeFrontmatter: true extracts the frontmatter link on the incremental path', async () => {
-    await seedPage('companies/acme-example', '# acme');
-    await seedPage('people/alice-example', aliceFm);
-    const result = await runExtractCore(engine as unknown as BrainEngine, {
-      mode: 'all',
-      dir: tempDir,
-      slugs: ['people/alice-example'],
-      includeFrontmatter: true,
-    });
-    // Same page, gate on → the `source:` frontmatter edge is now extracted.
-    expect(result.pages_processed).toBe(1);
-    expect(result.links_created).toBeGreaterThan(0);
-  });
-});

test/extract.test.ts

@@ -76,18 +76,6 @@ describe('extractLinksFromFile', () => {
     }
   });
 
-  it('resolves wrapped [[wikilink]] digit-leading slug-path in frontmatter (fs resolver, broadened step 1)', async () => {
-    // Same bug class as makeResolver step 1 (#1983): the fs resolver's strict
-    // `^[a-z]…` slug regex rejected digit-leading / nested paths, so a PARA-vault
-    // `related: "[[90-people/nicolai]]"` never resolved even though the page exists.
-    const content = '---\nrelated: "[[90-people/nicolai]]"\ntype: concept\n---\nContent.';
-    const allSlugs = new Set(['wiki/note', '90-people/nicolai']);
-    const links = await extractLinksFromFile(content, 'wiki/note.md', allSlugs, { includeFrontmatter: true });
-    const related = links.filter(l => l.link_type === 'related_to');
-    expect(related).toHaveLength(1);
-    expect(related[0].to_slug).toBe('90-people/nicolai');
-  });
-
   it('frontmatter extraction is default OFF (back-compat)', async () => {
     // Without includeFrontmatter, fs-source no longer auto-extracts frontmatter.
     // Matches db-source behavior. User opts in with --include-frontmatter flag.

test/link-extraction.test.ts

@@ -9,7 +9,6 @@ import {
   parseTimelineEntries,
   isAutoLinkEnabled,
   FRONTMATTER_LINK_MAP,
-  unwrapWikilink,
   type SlugResolver,
 } from '../src/core/link-extraction.ts';
 import type { BrainEngine } from '../src/core/engine.ts';
@@ -1292,175 +1291,3 @@ describe('parseTimelineEntries — Format 3: inline [Source: ..., YYYY-MM-DD] ci
     expect(parseTimelineEntries('[Source: import batch, 2025-07-01]')).toHaveLength(0);
   });
 });
-// ─── Frontmatter [[wikilink]] + slug-path resolution ──────────────────────
-// Mainstream Obsidian authors frontmatter links as `related: ["[[Page]]"]`,
-// and PARA-numbered vaults use digit-leading / nested slug paths like
-// `[[90-people/nicolai]]`. Both were silently dropped: brackets were treated
-// as part of the value and the step-1 slug regex (`^[a-z]…`) rejected
-// digit-leading / nested paths, while full-path fuzzy scored below threshold.
-// Fix: unwrapWikilink() before resolution + an exact getPage() for any
-// slug-shaped value (exact-match only → no false positives).
-
-describe('unwrapWikilink', () => {
-  test('wrapped title → bare title', () => {
-    expect(unwrapWikilink('[[Monday Range]]')).toBe('Monday Range');
-  });
-  test('wrapped slug-path (digit-leading folder) → bare slug', () => {
-    expect(unwrapWikilink('[[90-people/nicolai]]')).toBe('90-people/nicolai');
-  });
-  test('wrapped nested slug-path → bare slug', () => {
-    expect(unwrapWikilink('[[01-trading/wiki/strategies/opening-range-breakout]]'))
-      .toBe('01-trading/wiki/strategies/opening-range-breakout');
-  });
-  test('strips |alias', () => {
-    expect(unwrapWikilink('[[90-people/nicolai|Nicolai]]')).toBe('90-people/nicolai');
-  });
-  test('strips #heading', () => {
-    expect(unwrapWikilink('[[Page#Section]]')).toBe('Page');
-  });
-  test('strips ^block', () => {
-    expect(unwrapWikilink('[[Page^abc123]]')).toBe('Page');
-  });
-  test('surrounding whitespace tolerated', () => {
-    expect(unwrapWikilink('  [[Page]]  ')).toBe('Page');
-  });
-  test('bare title passes through unchanged', () => {
-    expect(unwrapWikilink('Monday Range')).toBe('Monday Range');
-  });
-  test('bare slug passes through unchanged', () => {
-    expect(unwrapWikilink('90-people/nicolai')).toBe('90-people/nicolai');
-  });
-  test('partially-wrapped value is NOT unwrapped (anchored)', () => {
-    // Not a wholly-wrapped value → left intact so existing behavior is exact.
-    expect(unwrapWikilink('see [[Page]] for detail')).toBe('see [[Page]] for detail');
-  });
-});
-
-describe('makeResolver — slug-path exact getPage (step 1 broadened)', () => {
-  function fakeEngine(
-    slugs: string[],
-    fuzzyMap: Map<string, { slug: string; similarity: number }> = new Map(),
-  ): BrainEngine {
-    const lookup = new Set(slugs);
-    return {
-      async getPage(slug: string) { return lookup.has(slug) ? { slug } as any : null; },
-      async findByTitleFuzzy(name: string) { return fuzzyMap.get(name) ?? null; },
-      async searchKeyword() { return []; },
-    } as unknown as BrainEngine;
-  }
-
-  test('digit-leading folder slug resolves via exact getPage', async () => {
-    const r = makeResolver(fakeEngine(['90-people/nicolai']));
-    expect(await r.resolve('90-people/nicolai')).toBe('90-people/nicolai');
-  });
-
-  test('nested (>2 segment) slug resolves via exact getPage', async () => {
-    const r = makeResolver(fakeEngine(['01-trading/wiki/strategies/opening-range-breakout']));
-    expect(await r.resolve('01-trading/wiki/strategies/opening-range-breakout'))
-      .toBe('01-trading/wiki/strategies/opening-range-breakout');
-  });
-
-  test('regression: single-segment lowercase slug still resolves', async () => {
-    const r = makeResolver(fakeEngine(['people/pedro']));
-    expect(await r.resolve('people/pedro')).toBe('people/pedro');
-  });
-
-  test('exact-only: slug-shaped value with no matching page falls through (no false positive)', async () => {
-    // `90-people/ghost` is slug-shaped but absent → step-1 getPage misses,
-    // no fuzzy hit → null. Never invents an edge.
-    const r = makeResolver(fakeEngine(['90-people/nicolai']));
-    expect(await r.resolve('90-people/ghost')).toBeNull();
-  });
-
-  test('non-slug value still routes to fuzzy', async () => {
-    const r = makeResolver(fakeEngine(
-      ['01-trading/monday-range'],
-      new Map([['Monday Range', { slug: '01-trading/monday-range', similarity: 1 }]]),
-    ));
-    expect(await r.resolve('Monday Range')).toBe('01-trading/monday-range');
-  });
-});
-
-describe('extractFrontmatterLinks — [[wikilink]] related: values (end-to-end)', () => {
-  function fakeEngine(
-    slugs: string[],
-    fuzzyMap: Map<string, { slug: string; similarity: number }> = new Map(),
-  ): BrainEngine {
-    const lookup = new Set(slugs);
-    return {
-      async getPage(slug: string) { return lookup.has(slug) ? { slug } as any : null; },
-      async findByTitleFuzzy(name: string) { return fuzzyMap.get(name) ?? null; },
-      async searchKeyword() { return []; },
-    } as unknown as BrainEngine;
-  }
-
-  test('wrapped slug-path related: resolves (the core win)', async () => {
-    const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
-    const { candidates, unresolved } = await extractFrontmatterLinks(
-      'wiki/originals/ideas/note', 'note' as never,
-      { related: '[[90-people/nicolai]]' }, resolver,
-    );
-    expect(unresolved).toHaveLength(0);
-    expect(candidates).toHaveLength(1);
-    expect(candidates[0]).toMatchObject({
-      fromSlug: 'wiki/originals/ideas/note',
-      targetSlug: '90-people/nicolai',
-      linkType: 'related_to',
-      linkSource: 'frontmatter',
-    });
-  });
-
-  test('wrapped nested slug-path related: resolves', async () => {
-    const resolver = makeResolver(fakeEngine(['01-trading/wiki/strategies/opening-range-breakout']));
-    const { candidates } = await extractFrontmatterLinks(
-      'wiki/note', 'note' as never,
-      { related: ['[[01-trading/wiki/strategies/opening-range-breakout]]'] }, resolver,
-    );
-    expect(candidates).toHaveLength(1);
-    expect(candidates[0].targetSlug).toBe('01-trading/wiki/strategies/opening-range-breakout');
-  });
-
-  test('wrapped value with |alias resolves to the target', async () => {
-    const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
-    const { candidates } = await extractFrontmatterLinks(
-      'wiki/note', 'note' as never,
-      { related: '[[90-people/nicolai|Nicolai]]' }, resolver,
-    );
-    expect(candidates).toHaveLength(1);
-    expect(candidates[0].targetSlug).toBe('90-people/nicolai');
-  });
-
-  test('regression: bare slug related: still resolves', async () => {
-    const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
-    const { candidates } = await extractFrontmatterLinks(
-      'wiki/note', 'note' as never,
-      { related: '90-people/nicolai' }, resolver,
-    );
-    expect(candidates).toHaveLength(1);
-    expect(candidates[0].targetSlug).toBe('90-people/nicolai');
-  });
-
-  test('regression: wrapped title resolves via fuzzy (brackets harmless)', async () => {
-    const resolver = makeResolver(fakeEngine(
-      ['01-trading/monday-range'],
-      new Map([['Monday Range', { slug: '01-trading/monday-range', similarity: 1 }]]),
-    ));
-    const { candidates } = await extractFrontmatterLinks(
-      'wiki/note', 'note' as never,
-      { related: '[[Monday Range]]' }, resolver,
-    );
-    expect(candidates).toHaveLength(1);
-    expect(candidates[0].targetSlug).toBe('01-trading/monday-range');
-  });
-
-  test('unknown wrapped slug → unresolved (no crash), original value preserved', async () => {
-    const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
-    const { candidates, unresolved } = await extractFrontmatterLinks(
-      'wiki/note', 'note' as never,
-      { related: '[[99-archive/does-not-exist]]' }, resolver,
-    );
-    expect(candidates).toHaveLength(0);
-    expect(unresolved).toHaveLength(1);
-    expect(unresolved[0]).toEqual({ field: 'related', name: '[[99-archive/does-not-exist]]' });
-  });
-});

test/progress.test.ts

@@ -216,17 +216,21 @@ describe('progress reporter', () => {
   });
 
   test('only one process-level signal handler installed across many reporters', () => {
-    // Baseline: one handler already installed by prior tests in this file.
+    // Baseline: one handler already installed by prior tests in this file, and
+    // possibly live reporters from OTHER test files sharing this bun process
+    // (shard composition is not this test's invariant — assert the delta, not
+    // an absolute zero, or shard reshuffles make this fail spuriously).
     const installedBefore = __signalHandlerInstalledForTest();
+    const liveBefore = __liveReporterCountForTest();
     const { stream } = sink(false);
     for (let i = 0; i < 50; i++) {
       const p = createProgress({ mode: 'json', stream, minIntervalMs: 0, minItems: 1 });
       p.start(`phase_${i}`, 1);
       p.finish();
     }
-    // After 50 reporter lifecycles, still exactly one handler and zero leaked live entries.
+    // After 50 reporter lifecycles, still exactly one handler and zero NET leaked live entries.
     expect(__signalHandlerInstalledForTest()).toBe(installedBefore || true);
-    expect(__liveReporterCountForTest()).toBe(0);
+    expect(__liveReporterCountForTest()).toBe(liveBefore);
   });
 
   test('startHeartbeat() fires heartbeats and stop() clears', async () => {