fix(dream): keep dream --dry-run --json stdout clean of embed summaries (#394)

The cycle's embed phase called runEmbedCore with no output suppression, so
the '[dry-run] Would embed ...' / 'Embedded N chunks ...' slog summaries
landed on stdout ahead of the JSON CycleReport, breaking the documented
stdout-clean-for-JSON contract (docs/progress-events.md).

Adds EmbedOpts.quiet gating the human stdout summary slog sites in
embed.ts (embedPage, embedAll, embedAllStale); the cycle's runPhaseEmbed
sets quiet: true since it reports counts via its own PhaseResult. Errors
and warnings still go to stderr regardless.

Takeover of #854 (same approach, reimplemented on current master — the
original patch predates the slog migration and the widened
embedAll/embedAllStale signatures). Regression test ported from #854.

Co-authored-by: Kage18 <Kage18@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/commands/embed.ts

@@ -107,6 +107,14 @@ export interface EmbedOpts {
    * runs lock every source in sorted order. dryRun skips it.
    */
   singleFlight?: boolean;
+  /**
+   * #394: suppress human stdout summaries (the `[dry-run] Would embed ...` /
+   * `Embedded N chunks ...` slog lines). Set by structured-output callers —
+   * the cycle's embed phase (dream --json must keep stdout JSON-clean per
+   * docs/progress-events.md) reports counts via its own PhaseResult instead.
+   * Errors/warnings still go to stderr regardless.
+   */
+  quiet?: boolean;
 }
 
 /**
@@ -253,7 +261,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
     for (const s of opts.slugs) {
       if (isAborted(opts.signal)) break; // #1737: stop the per-slug loop on abort
       try {
-        await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal);
+        await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal, opts.quiet);
       } catch (e: unknown) {
         serr(`  Error embedding ${s}: ${e instanceof Error ? e.message : e}`);
       }
@@ -347,6 +355,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
         catchUp: opts.catchUp,
         pacer,
         paceMaxConcurrency,
+        quiet: opts.quiet,
       }, opts.signal);
     } finally {
       // E1: surface pacing telemetry (human + structured) when pacing was on.
@@ -376,7 +385,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
     return result;
   }
   if (opts.slug) {
-    await embedPage(engine, opts.slug, !!opts.dryRun, result, opts.sourceId, opts.signal);
+    await embedPage(engine, opts.slug, !!opts.dryRun, result, opts.sourceId, opts.signal, opts.quiet);
     return result;
   }
   throw new Error('No embed target specified. Pass { slug }, { slugs }, { all }, or { stale }.');
@@ -521,6 +530,7 @@ async function embedPage(
   result: EmbedResult,
   sourceId?: string,
   signal?: AbortSignal,
+  quiet?: boolean,
 ) {
   const opts = sourceId ? { sourceId } : undefined;
   const page = await engine.getPage(slug, opts);
@@ -565,7 +575,7 @@ async function embedPage(
   result.skipped += chunks.length - toEmbed.length;
 
   if (toEmbed.length === 0) {
-    slog(`${slug}: all ${chunks.length} chunks already embedded`);
+    if (!quiet) slog(`${slug}: all ${chunks.length} chunks already embedded`);
     result.pages_processed++;
     return;
   }
@@ -602,7 +612,7 @@ async function embedPage(
   }
   result.embedded += toEmbed.length;
   result.pages_processed++;
-  slog(`${slug}: embedded ${toEmbed.length} chunks`);
+  if (!quiet) slog(`${slug}: embedded ${toEmbed.length} chunks`);
 }
 
 async function embedAll(
@@ -620,6 +630,8 @@ async function embedAll(
     pacer?: DbPacer;
     /** Resolved concurrency cap (E-1: the worker count, no separate permit). */
     paceMaxConcurrency?: number;
+    /** #394: suppress human stdout summaries (structured-output callers). */
+    quiet?: boolean;
   },
   signal?: AbortSignal,
 ) {
@@ -763,10 +775,12 @@ async function embedAll(
   });
 
   // Stdout summary preserved for scripts/tests that grep for counts.
-  if (dryRun) {
-    slog(`[dry-run] Would embed ${result.would_embed} chunks across ${pages.length} pages`);
-  } else {
-    slog(`Embedded ${result.embedded} chunks across ${pages.length} pages`);
+  if (!staleOpts?.quiet) {
+    if (dryRun) {
+      slog(`[dry-run] Would embed ${result.would_embed} chunks across ${pages.length} pages`);
+    } else {
+      slog(`Embedded ${result.embedded} chunks across ${pages.length} pages`);
+    }
   }
 }
 
@@ -802,6 +816,8 @@ async function embedAllStale(
     pacer?: DbPacer;
     /** Resolved concurrency cap (E-1: the worker count, no separate permit). */
     paceMaxConcurrency?: number;
+    /** #394: suppress human stdout summaries (structured-output callers). */
+    quiet?: boolean;
   },
   signature?: string,
   externalSignal?: AbortSignal,
@@ -819,7 +835,7 @@ async function embedAllStale(
       signature,
       ...(sourceId && { sourceId }),
     });
-    if (invalidated > 0) {
+    if (invalidated > 0 && !staleOpts?.quiet) {
       slog(`[embed] invalidated ${invalidated} chunk(s) embedded under a prior model signature`);
     }
   }
@@ -830,10 +846,12 @@ async function embedAllStale(
     dryRun && signature ? { ...sourceOpt, signature } : sourceOpt,
   );
   if (staleCount === 0) {
-    if (dryRun) {
-      slog('[dry-run] Would embed 0 chunks (0 stale found)');
-    } else {
-      slog('Embedded 0 chunks (0 stale found)');
+    if (!staleOpts?.quiet) {
+      if (dryRun) {
+        slog('[dry-run] Would embed 0 chunks (0 stale found)');
+      } else {
+        slog('Embedded 0 chunks (0 stale found)');
+      }
     }
     return;
   }
@@ -842,7 +860,7 @@ async function embedAllStale(
     result.would_embed += staleCount;
     result.total_chunks += staleCount;
     if (onProgress) onProgress(1, 1, 0);
-    slog(`[dry-run] Would embed ${staleCount} stale chunks`);
+    if (!staleOpts?.quiet) slog(`[dry-run] Would embed ${staleCount} stale chunks`);
     return;
   }
 
@@ -1082,7 +1100,7 @@ async function embedAllStale(
     if (budgetTimer) clearTimeout(budgetTimer);
   }
 
-  slog(`Embedded ${result.embedded} chunks across ${totalProcessedPages} pages`);
+  if (!staleOpts?.quiet) slog(`Embedded ${result.embedded} chunks across ${totalProcessedPages} pages`);
 
   // #1946 (OV2a): a catch-up pass that completed without being aborted but left
   // chunks unembedded means those chunks are stuck (a non-transient embed

src/core/cycle.ts

@@ -1214,7 +1214,9 @@ async function runPhaseEmbed(engine: BrainEngine, dryRun: boolean, signal?: Abor
     // 10-15 min one) bails within a batch instead of running to completion
     // after the job was killed — which left gbrain_cycle_locks held and
     // wedged every subsequent autopilot cycle.
-    const result = await runEmbedCore(engine, { stale: true, dryRun, signal });
+    // #394: quiet — the cycle reports embed counts via its own PhaseResult;
+    // raw `[dry-run] Would embed ...` stdout lines would corrupt `dream --json`.
+    const result = await runEmbedCore(engine, { stale: true, dryRun, signal, quiet: true });
     const embeddedCount = dryRun ? result.would_embed : result.embedded;
     return {
       phase: 'embed',

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/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-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/dream.test.ts

@@ -292,6 +292,33 @@ describe('runDream — output format', () => {
     expect(parsed).toHaveProperty('totals');
   });
 
+  // #394 / takeover of #854: the embed phase's `[dry-run] Would embed ...`
+  // summary must not leak onto stdout ahead of the JSON CycleReport.
+  test('--dry-run --json emits only JSON even when embed has stale chunks', async () => {
+    await engine.putPage('concepts/testing', {
+      type: 'concept',
+      title: 'Testing',
+      compiled_truth: 'Testing keeps JSON contracts honest.',
+      timeline: '',
+    });
+    await engine.upsertChunks('concepts/testing', [
+      { chunk_index: 0, chunk_text: 'Testing keeps JSON contracts honest.', chunk_source: 'compiled_truth' },
+    ]);
+
+    const lines: string[] = [];
+    const logSpy = spyOn(console, 'log').mockImplementation((msg: string) => { lines.push(String(msg)); });
+    await runDream(engine, ['--dir', repo, '--phase', 'embed', '--dry-run', '--json']);
+    logSpy.mockRestore();
+
+    const output = lines.join('\n');
+    expect(output.trimStart().startsWith('{')).toBe(true);
+    const parsed = JSON.parse(output);
+    expect(parsed.schema_version).toBe('1');
+    expect(parsed.phases[0].phase).toBe('embed');
+    // The stale chunk was still counted in the structured report.
+    expect(parsed.phases[0].details.would_embed).toBe(1);
+  });
+
   test('human output for clean status mentions "Brain is healthy"', async () => {
     const lines: string[] = [];
     const logSpy = spyOn(console, 'log').mockImplementation((msg: string) => { lines.push(String(msg)); });

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 () => {