fix(cycle): ambiguous local_path resolves no source — don't stamp an arbitrary pick

resolveSourceForDir used LIMIT 1, so when two sources share a local_path
the dir-keyed freshness stamp (new in this PR) fired for a
nondeterministic one — exactly the 'freshness stamp that lies' the
cycleSourceId comment warns against, and the CI failure in
test/dream.test.ts ('gbrain dream (no --source) leaves all sources
untouched'). Require exactly one match; ambiguous or no match falls back
to the pre-v0.18 behavior (undefined), same as before this PR for the
no-match case.

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

src/commands/autopilot-fanout.ts

@@ -186,6 +186,18 @@ 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 70–94, 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

src/commands/autopilot.ts

@@ -901,13 +901,27 @@ 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 70–94 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;
+          score < 70 ||
+          staleCycleSources > 0;
 
-        const shouldSleep = score >= 95 && plan.length === 0 && minutesSinceLastFull < FULL_CYCLE_FLOOR_MIN;
+        const shouldSleep = score >= 95 && plan.length === 0 && minutesSinceLastFull < FULL_CYCLE_FLOOR_MIN && staleCycleSources === 0;
 
         if (shouldSleep) {
           if (jsonMode) {

src/core/cycle.ts

@@ -854,7 +854,10 @@ 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).
+ * 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).
  */
 async function resolveSourceForDir(
   engine: BrainEngine,
@@ -865,10 +868,10 @@ 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 1`,
+      `SELECT id FROM sources WHERE local_path = $1 LIMIT 2`,
       [brainDir],
     );
-    return rows[0]?.id;
+    return rows.length === 1 ? rows[0]!.id : undefined;
   } catch {
     // sources table might not exist on very old brains — fall through.
     return undefined;
@@ -2365,17 +2368,23 @@ export async function runCycle(
   }
 
   // v0.38 (codex r1 P0-5): persist per-source cycle completion timestamp
-  // 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)
+  // 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)
   //   - 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 (opts.sourceId && engine && !dryRun && !aborted && (status === 'ok' || status === 'clean' || status === 'partial')) {
+  if (cycleSourceId && 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
@@ -2385,13 +2394,13 @@ 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(opts.sourceId, {
+      await engine.updateSourceConfig(cycleSourceId, {
         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 ${opts.sourceId}: ${e instanceof Error ? e.message : String(e)}`);
+      console.warn(`[cycle] failed to write last_source_cycle_at for source ${cycleSourceId}: ${e instanceof Error ? e.message : String(e)}`);
     }
   }
 

src/core/cycle/synthesize.ts

@@ -428,13 +428,8 @@ export async function runPhaseSynthesize(
 
     const queue = new MinionQueue(engine);
     const childIds: number[] = [];
-    /**
-     * 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>();
+    /** Map child job_id → chunk metadata for D6 orchestrator-side slug rewrite. */
+    const chunkInfo = new Map<number, { idx: number; hash6: string }>();
     /** Skip reasons for the cycle report (D5 cap hits, D8 legacy-key skips). */
     const skipReports: Array<{ filePath: string; reason: string }> = [];
 
@@ -518,14 +513,9 @@ export async function runPhaseSynthesize(
           { allowProtectedSubmit: true },
         );
         childIds.push(child.id);
-        childMeta.set(child.id, {
-          idx: i,
-          hash6,
-          chunkTotal: chunks.length,
-          transcriptSource: t.transcriptSource,
-          transcriptId: stripContentVersionSuffix(t.basename),
-          inferredDate: t.inferredDate,
-        });
+        if (isChunked) {
+          chunkInfo.set(child.id, { idx: i, hash6 });
+        }
       }
     }
 
@@ -554,14 +544,14 @@ 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: childMeta drives post-hoc rewrite of
+    // D6 orchestrator slug rewrite: chunkInfo 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, childMeta, cycleSourceId);
+    const writtenRefs = await collectChildPutPageSlugs(engine, childIds, chunkInfo, cycleSourceId);
 
     const summaryDate = opts.date ?? today();
 
@@ -569,12 +559,7 @@ 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.
-    // #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);
+    await stampDreamProvenance(engine, writtenRefs, summaryDate);
 
     // Dual-write: reverse-render each DB row → markdown file.
     const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs, cycleSourceId);
@@ -1110,17 +1095,15 @@ function sanitizeForSlug(s: string): string {
  * fake"): we no longer need detection because the rewrite enforces
  * uniqueness at slug-write time.
  *
- * `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.
+ * `chunkInfo` maps child job_id → { chunk_index, hash6 }. Single-chunk
+ * children are absent from the map and pass through unchanged.
  */
 async function collectChildPutPageSlugs(
   engine: BrainEngine,
   childIds: number[],
-  childMeta: Map<number, ChildMeta>,
+  chunkInfo: Map<number, { idx: number; hash6: string }>,
   sourceId = 'default',
-): Promise<Array<{ slug: string; source_id: string; jobId: number }>> {
+): Promise<Array<{ slug: string; source_id: string }>> {
   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
@@ -1139,73 +1122,16 @@ async function collectChildPutPageSlugs(
        FROM subagent_tool_executions
       WHERE job_id = ANY($1::int[])
         AND tool_name = 'brain_put_page'
-        AND status = 'complete'
-      ORDER BY id`,
+        AND status = 'complete'`,
     [childIds],
   );
-  const rewritten = new Map<string, number>();
+  const rewritten = new Set<string>();
   for (const r of rows) {
     if (typeof r.slug !== 'string' || r.slug.length === 0) continue;
-    const meta = childMeta.get(r.job_id);
-    const finalSlug = meta && meta.chunkTotal > 1
-      ? rewriteChunkedSlug(r.slug, meta.hash6, meta.idx)
-      : r.slug;
-    // Last writer wins, in execution-row order (ORDER BY id): if two children
-    // collide on a final slug, the pages row holds the LAST put_page write, so
-    // the stamp must attribute that child's transcript — not an arbitrary one.
-    rewritten.set(finalSlug, r.job_id);
+    const ci = chunkInfo.get(r.job_id);
+    rewritten.add(ci ? rewriteChunkedSlug(r.slug, ci.hash6, ci.idx) : r.slug);
   }
-  return [...rewritten.entries()]
-    .sort(([a], [b]) => a.localeCompare(b))
-    .map(([slug, jobId]) => ({ slug, source_id: sourceId, jobId }));
-}
-
-/**
- * Per-child orchestrator state. Drives D6 chunked-slug rewrite (idx + hash6)
- * AND the deterministic frontmatter stampDreamProvenance merges into each
- * written page. Populated for every child, not just chunked ones.
- */
-interface ChildMeta {
-  idx: number;
-  hash6: string;
-  chunkTotal: number;
-  transcriptSource: string | null;
-  transcriptId: string;
-  inferredDate: string | null;
-}
-
-/**
- * Strip the content-version suffix that claude-code-archive appends when a
- * conversation is edited (`<uuid>--<contentHash>.md`). The session UUID is
- * the stable transcript identifier; the suffix changes with content. Used to
- * populate `transcript_id` so edits of the same session collapse to one id.
- */
-function stripContentVersionSuffix(basename: string): string {
-  return basename.replace(/--[a-f0-9]+$/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;
+  return Array.from(rewritten).sort().map(slug => ({ slug, source_id: sourceId }));
 }
 
 /**
@@ -1251,19 +1177,12 @@ async function hasLegacySingleChunkCompletion(
  */
 async function stampDreamProvenance(
   engine: BrainEngine,
-  refs: Array<{ slug: string; source_id: string; jobId?: number }>,
+  refs: Array<{ slug: string; source_id: string }>,
   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, 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 };
+  for (const { slug, source_id } of refs) {
     try {
       await executeRawJsonb(
         engine,
@@ -1271,7 +1190,7 @@ async function stampDreamProvenance(
             SET frontmatter = COALESCE(frontmatter, '{}'::jsonb) || $3::jsonb
           WHERE slug = $1 AND source_id = $2`,
         [slug, source_id],
-        [stamp],
+        [{ dream_generated: true, dream_cycle_date: cycleDate }],
       );
     } 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, dirname } from 'node:path';
+import { join, basename } from 'node:path';
 import { createHash } from 'node:crypto';
 import { pruneDir } from '../sync.ts';
 
@@ -23,22 +23,8 @@ export interface DiscoveredTranscript {
   content: string;
   /** Filename basename without extension; used as a topic-slug seed. */
   basename: string;
-  /**
-   * 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.
-   */
+  /** Inferred date if the basename matches `YYYY-MM-DD...` (or null). */
   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 {
@@ -175,36 +161,6 @@ 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
@@ -269,11 +225,8 @@ 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 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;
+      const inferredDate = dateMatch ? dateMatch[1] : null;
+      if (!isInDateRange(inferredDate, opts)) continue;
 
       let content: string;
       try {
@@ -288,17 +241,12 @@ 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),
       });
     }
   }
@@ -342,7 +290,6 @@ export function readSingleTranscript(
     contentHash: hashContent(content),
     content,
     basename: baseName,
-    inferredDate: inferContentDate(content) ?? (dateMatch ? dateMatch[1] : null),
-    transcriptSource: deriveTranscriptSource(filePath),
+    inferredDate: dateMatch ? dateMatch[1] : null,
   };
 }

test/autopilot-fanout-wiring.test.ts

@@ -54,6 +54,20 @@ 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 70–94, 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 }, {

test/autopilot-fanout.test.ts

@@ -14,6 +14,7 @@ import { describe, test, expect } from 'bun:test';
 import {
   readLastFullCycleAt,
   isSourceStale,
+  countStaleSources,
   selectSourcesForDispatch,
   resolveFanoutMax,
   dispatchPerSource,
@@ -74,6 +75,23 @@ 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) =>

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

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

test/cycle-last-full-cycle-at.test.ts

@@ -3,8 +3,10 @@
  * cycles. Closes codex round-1 P0-5 (write site for last_full_cycle_at
  * was unspecified pre-PR).
  *
- * Conditions for write:
- *   - opts.sourceId is set (legacy callers without sourceId skip the write)
+ * 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)
  *   - engine is non-null (no-DB path skips)
  *   - status is 'ok' | 'clean' | 'partial' (failed/skipped don't mark fresh)
  *   - dryRun is false
@@ -90,17 +92,45 @@ describe('runCycle last_full_cycle_at exit hook', () => {
     });
   });
 
-  test('legacy caller (no sourceId) does NOT write any source timestamp', async () => {
+  test('no explicit sourceId but brainDir resolves a source → writes the resolved source timestamp', async () => {
     await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
-      await seedSource('default-like');
-      // No sourceId passed; should remain untouched.
+      // 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 runCycle(engine, {
         brainDir,
         phases: ['lint'],
       });
-      // No per-source write happens; default source's config stays empty.
-      const after = await readLastFullCycleAt('default-like');
-      expect(after).toBeNull();
+      expect(await readLastFullCycleAt('unmatched')).toBeNull();
     });
   });
 

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

@@ -152,94 +152,3 @@ 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

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

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

@@ -45,7 +45,6 @@ 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

@@ -1,109 +0,0 @@
-/**
- * #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/progress.test.ts

@@ -216,21 +216,17 @@ 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, 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).
+    // Baseline: one handler already installed by prior tests in this file.
     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 NET leaked live entries.
+    // After 50 reporter lifecycles, still exactly one handler and zero leaked live entries.
     expect(__signalHandlerInstalledForTest()).toBe(installedBefore || true);
-    expect(__liveReporterCountForTest()).toBe(liveBefore);
+    expect(__liveReporterCountForTest()).toBe(0);
   });
 
   test('startHeartbeat() fires heartbeats and stop() clears', async () => {