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/commands/extract.ts

@@ -1025,10 +1025,6 @@ async function extractForSlugs(
   let linksCreated = 0;
   let timelineCreated = 0;
   let pagesProcessed = 0;
-  // #2636: successfully processed pages get their extraction watermark
-  // stamped after the final flush (mode 'all' only — a partial-mode run
-  // hasn't done the full extraction the watermark asserts).
-  const processedRefs: Array<{ slug: string; source_id: string }> = [];
 
   // Issue #972: read the basename flag once per extract run.
   const globalBasename = await isGlobalBasenameEnabled(engine);
@@ -1117,7 +1113,6 @@ async function extractForSlugs(
         }
 
         pagesProcessed++;
-        if (!dryRun) processedRefs.push({ slug, source_id: sourceId ?? 'default' });
       } catch { /* skip unreadable */ }
       progress.tick(1);
     },
@@ -1125,13 +1120,6 @@ async function extractForSlugs(
 
   await flushLinks();
   await flushTimeline();
-  // #2636: the Dream cycle disables sync's inline extraction and routes
-  // changed slugs through this incremental path — without a stamp here,
-  // those pages never get links_extracted_at and stay permanently visible
-  // to `extract --stale` / doctor. Stamp only after BOTH batches flushed.
-  if (!dryRun && mode === 'all') {
-    await stampExtracted(engine, processedRefs);
-  }
   progress.finish();
 
   if (!jsonMode) {

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',

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/extract-incremental.test.ts

@@ -60,51 +60,6 @@ async function seedPage(slug: string, body: string): Promise<void> {
 }
 
 describe('runExtractCore — incremental cycle path (#417)', () => {
-  test('Dream incremental all-mode stamps the source-scoped extraction watermark (#2636)', async () => {
-    await engine.executeRaw(
-      `INSERT INTO sources (id, name, local_path) VALUES ($1, $2, $3)`,
-      ['repo-a', 'repo-a', tempDir],
-    );
-    await engine.putPage('people/alice-example', {
-      type: 'person',
-      title: 'alice-example',
-      compiled_truth: '# alice',
-      timeline: '',
-      frontmatter: {},
-      content_hash: 'h',
-    }, { sourceId: 'repo-a' });
-    writeFileSync(join(tempDir, 'people/alice-example.md'), '# alice');
-
-    await runExtractCore(engine as unknown as BrainEngine, {
-      mode: 'all',
-      dir: tempDir,
-      slugs: ['people/alice-example'],
-      sourceId: 'repo-a',
-    });
-
-    const rows = await engine.executeRaw<{ links_extracted_at: string | null }>(
-      `SELECT links_extracted_at FROM pages WHERE slug = $1 AND source_id = $2`,
-      ['people/alice-example', 'repo-a'],
-    );
-    expect(rows[0]?.links_extracted_at).not.toBeNull();
-    expect(await engine.countStalePagesForExtraction({ sourceId: 'repo-a' })).toBe(0);
-  });
-
-  test('Dream incremental dry-run does NOT stamp the watermark', async () => {
-    await seedPage('people/alice-example', '# alice');
-    await runExtractCore(engine as unknown as BrainEngine, {
-      mode: 'all',
-      dir: tempDir,
-      slugs: ['people/alice-example'],
-      dryRun: true,
-    });
-    const rows = await engine.executeRaw<{ links_extracted_at: string | null }>(
-      `SELECT links_extracted_at FROM pages WHERE slug = $1`,
-      ['people/alice-example'],
-    );
-    expect(rows[0]?.links_extracted_at ?? null).toBeNull();
-  });
-
   test('1. slugs: [] returns immediately with zero counts (early-return path)', async () => {
     await seedPage('people/alice-example', '# alice');
     const result = await runExtractCore(engine as unknown as BrainEngine, {