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/doctor.ts

@@ -820,10 +820,6 @@ export async function doctorReportRemote(engine: BrainEngine): Promise<DoctorRep
   // v0.42.x (#1794, 4A): pool-budget nudge when GBRAIN_MAX_CONNECTIONS is set.
   checks.push(await checkPoolBudget(engine));
 
-  // #2552: warn when an explicit embed-concurrency override fans out against
-  // a local single-slot embedding endpoint (silent backfill starvation).
-  checks.push(await checkEmbedConcurrency());
-
   // v0.42.7 (#1696): link-extraction lag. Strictly SQL (single indexed COUNT),
   // safe on the thin-client/remote path — remote operators on checkout-less
   // Postgres brains are exactly who can't otherwise see the extraction backlog.
@@ -3819,61 +3815,6 @@ export function computePoolBudgetCheck(
   };
 }
 
-/**
- * #2552: warn when an explicit GBRAIN_EMBED_CONCURRENCY override fans out
- * against a local single-slot embedding endpoint (Ollama / llama-server /
- * localhost base URL). Requests serialize on the one loaded model, so N
- * parallel pages multiply latency xN and can exceed the fetch timeout with
- * no surfaced error — the backfill silently starves. (When the env var is
- * unset, embed auto-caps at LOCAL_EMBED_CONCURRENCY_CAP and this check
- * reports ok.) Pure; exported for tests.
- */
-export function computeEmbedConcurrencyCheck(
-  isLocalEndpoint: boolean,
-  envValue: string | undefined,
-  localCap: number,
-): Check {
-  const name = 'embed_concurrency';
-  if (!isLocalEndpoint) {
-    return { name, status: 'ok', message: 'Embedding endpoint is not a local inference server — cloud concurrency defaults apply.' };
-  }
-  const parsed = envValue ? parseInt(envValue, 10) : NaN;
-  if (envValue && Number.isFinite(parsed) && parsed > localCap) {
-    return {
-      name,
-      status: 'warn',
-      message:
-        `GBRAIN_EMBED_CONCURRENCY=${parsed} against a local embedding endpoint. ` +
-        `Local inference servers serialize requests, so ${parsed} parallel pages multiply ` +
-        `latency x${parsed} and can exceed the fetch timeout — the embed backfill stalls ` +
-        `with no error. Unset GBRAIN_EMBED_CONCURRENCY (auto-caps at ${localCap}) or set it <= ${localCap}.`,
-    };
-  }
-  return {
-    name,
-    status: 'ok',
-    message: `Local embedding endpoint detected; embed concurrency capped at ${envValue ? parsed : localCap}.`,
-  };
-}
-
-/** Thin gateway/env wrapper over `computeEmbedConcurrencyCheck`. */
-export async function checkEmbedConcurrency(): Promise<Check> {
-  try {
-    const { isLocalEmbeddingEndpoint, LOCAL_EMBED_CONCURRENCY_CAP } = await import('../core/ai/gateway.ts');
-    return computeEmbedConcurrencyCheck(
-      isLocalEmbeddingEndpoint(),
-      process.env.GBRAIN_EMBED_CONCURRENCY,
-      LOCAL_EMBED_CONCURRENCY_CAP,
-    );
-  } catch (err) {
-    return {
-      name: 'embed_concurrency',
-      status: 'ok',
-      message: `Skipped (${err instanceof Error ? err.message : String(err)})`,
-    };
-  }
-}
-
 /** Thin env/engine wrapper over `computePoolBudgetCheck`. */
 export async function checkPoolBudget(_engine: BrainEngine): Promise<Check> {
   try {

src/commands/embed.ts

@@ -1,6 +1,5 @@
 import type { BrainEngine } from '../core/engine.ts';
 import { embedBatch, currentEmbeddingSignature } from '../core/embedding.ts';
-import { isLocalEmbeddingEndpoint, LOCAL_EMBED_CONCURRENCY_CAP } from '../core/ai/gateway.ts';
 import type { ChunkInput } from '../core/types.ts';
 import { chunkText } from '../core/chunkers/recursive.ts';
 import { createProgress, type ProgressReporter } from '../core/progress.ts';
@@ -177,31 +176,6 @@ export class EmbeddingDimMismatchError extends Error {
   }
 }
 
-/**
- * #2552: resolve the bulk-embed worker count. Env override or the
- * cloud-tuned default of 20 — but when the operator did NOT set
- * GBRAIN_EMBED_CONCURRENCY and the embedding endpoint is a local inference
- * server (Ollama / llama-server / localhost base URL), cap at
- * LOCAL_EMBED_CONCURRENCY_CAP: 20 parallel pages against a single-slot
- * server serialize on the one loaded model, multiply latency x20 past the
- * fetch timeout, and starve the backfill with no surfaced error. An
- * explicit env value always wins (`gbrain doctor` warns instead).
- * Pacing only ever LOWERS concurrency (Codex P2).
- */
-export function resolveEmbedConcurrency(paceMaxConcurrency?: number): number {
-  const envSet = !!process.env.GBRAIN_EMBED_CONCURRENCY;
-  const base = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
-  let resolved = base;
-  if (!envSet && isLocalEmbeddingEndpoint() && base > LOCAL_EMBED_CONCURRENCY_CAP) {
-    resolved = LOCAL_EMBED_CONCURRENCY_CAP;
-    serr(
-      `[embed] local embedding endpoint detected — capping concurrency at ` +
-      `${LOCAL_EMBED_CONCURRENCY_CAP} (set GBRAIN_EMBED_CONCURRENCY to override)`,
-    );
-  }
-  return paceMaxConcurrency ? Math.min(resolved, paceMaxConcurrency) : resolved;
-}
-
 /**
  * Pre-flight check: read the actual schema column dim and compare to the
  * gateway's resolved dim. Throws `EmbeddingDimMismatchError` on mismatch
@@ -703,8 +677,10 @@ async function embedAll(
   // Paced runs lower this to the resolved cap (the real lever vs pooler-slot
   // starvation); unpaced keeps the env/default 20. Codex P2: only ever LOWER —
   // never raise above an operator's existing env cap.
-  // #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
-  const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
+  const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
+  const CONCURRENCY = staleOpts?.paceMaxConcurrency
+    ? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
+    : BASE_CONCURRENCY;
 
   async function embedOnePage(page: typeof pages[number]) {
     // #1737: bail before doing any work for this page if the run was aborted.
@@ -879,8 +855,10 @@ async function embedAllStale(
   // Paced runs lower concurrency to the resolved cap (E-1: worker count IS the
   // lever on this single pool, no separate permit). Codex P2: pacing only ever
   // LOWERS concurrency — never raise above an operator's existing env cap.
-  // #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
-  const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
+  const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
+  const CONCURRENCY = staleOpts?.paceMaxConcurrency
+    ? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
+    : BASE_CONCURRENCY;
   const pacer = staleOpts?.pacer ?? createNoopPacer();
 
   // D3 + D3a + D8: wall-clock budget. 30 min default; env override.

src/core/ai/gateway.ts

@@ -683,33 +683,6 @@ export function getEmbeddingDimensions(): number {
   return requireConfig().embedding_dimensions ?? DEFAULT_EMBEDDING_DIMENSIONS;
 }
 
-/**
- * #2552: cap for parallel bulk-embed workers against a local inference
- * server. A single-slot Ollama/llama-server serializes requests, so the
- * cloud-tuned 20-worker fan-out multiplies latency x20 and blows past the
- * fetch timeout with no surfaced error (the backfill silently starves).
- */
-export const LOCAL_EMBED_CONCURRENCY_CAP = 2;
-
-/**
- * #2552: true when the configured embedding model routes to a local
- * inference server — the `ollama` / `llama-server` recipes, or any recipe
- * whose base URL was explicitly pointed at localhost. Bulk callers use this
- * to pick CPU-safe concurrency defaults; `gbrain doctor` uses it to warn
- * about an explicit cloud-sized override. Fail-open: unconfigured or
- * unresolvable gateway → false (cloud behavior, the historical default).
- */
-export function isLocalEmbeddingEndpoint(): boolean {
-  try {
-    const { recipe } = resolveRecipe(getEmbeddingModel());
-    if (recipe.id === 'ollama' || recipe.id === 'llama-server') return true;
-    const base = requireConfig().base_urls?.[recipe.id] ?? '';
-    return /\/\/(localhost|127\.0\.0\.1|\[::1\])(:|\/|$)/i.test(base);
-  } catch {
-    return false;
-  }
-}
-
 /**
  * v0.28.11: returns the configured multimodal embedding model when set,
  * or undefined if the brain falls back to `embedding_model` for multimodal

src/core/ai/recipes/ollama.ts

@@ -29,17 +29,9 @@ export const ollama: Recipe = {
       trust_custom_dims: true, // #2271: local models carry varied native dims
       cost_per_1m_tokens_usd: 0,
       price_last_verified: '2026-04-20',
-      // #2552: Ollama's true batch capacity depends on the locally loaded
-      // model + OLLAMA_NUM_PARALLEL, but the previous `no_batch_cap: true`
-      // meant a whole page went out in ONE request — on a CPU-only box that
-      // multiplies latency past the fetch timeout and the backfill starves
-      // with no surfaced error. Ollama doesn't return a recognizable
-      // token-limit error either, so the recursive-halving safety net never
-      // fires; a conservative static pre-split cap is the only guard.
-      // 4096 tokens x 2 chars/token ~= 8K chars per request (code-dense
-      // pages run ~2 chars/token, not the tiktoken-ish 4).
-      max_batch_tokens: 4096,
-      chars_per_token: 2,
+      // Ollama's batch capacity depends on the locally loaded model + the
+      // OLLAMA_NUM_PARALLEL config; no static cap to declare. v0.32 (#779).
+      no_batch_cap: true,
     },
   },
   setup_hint: 'Install Ollama from https://ollama.ai, then `ollama pull nomic-embed-text` and `ollama serve`.',

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/doctor-categories.ts

@@ -141,7 +141,6 @@ export const OPS_CHECK_NAMES: ReadonlySet<string> = new Set([
   'pgbouncer_prepare',
   'pgvector',
   'pool_budget',
-  'embed_concurrency',
   'progressive_batch_audit_health',
   'queue_health',
   'reranker_health',

src/core/pglite-engine.ts

@@ -56,7 +56,7 @@ import { GBrainError, PAGE_SORT_SQL, ENRICH_ORDER_SQL } from './types.ts';
 import { finalizeLastSeen } from './chronicle/last-seen.ts';
 import { computeAnomaliesFromBuckets } from './cycle/anomaly.ts';
 import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
-import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
+import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
 import {
   normalizeEngineColumn,
   buildVectorCastFragment,
@@ -1591,8 +1591,6 @@ export class PGLiteEngine implements BrainEngine {
     }
 
     // v0.20.0 Cathedral II Layer 10 C1/C2: language + symbol-kind filters.
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, innerLimit, limit, offset];
     let extraFilter = '';
     if (opts?.language) {
@@ -1632,7 +1630,6 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const keywordSql =
       `WITH ranked AS (
@@ -1640,14 +1637,14 @@ export class PGLiteEngine implements BrainEngine {
            p.slug, p.id as page_id, p.title, p.type, p.source_id,
            p.effective_date, p.effective_date_source,
            cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-           ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+           ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
            CASE WHEN p.updated_at < (
              SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
            ) THEN true ELSE false END AS stale
          FROM content_chunks cc
          JOIN pages p ON p.id = cc.page_id
          JOIN sources s ON s.id = p.source_id
-         WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
+         WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
            -- v0.27.1: hide image rows from default text-keyword search so
            -- OCR text doesn't drown text-page hits. Image-similarity queries
            -- run a separate vector path on embedding_image.
@@ -1715,10 +1712,7 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, limit, offset];
     let extraFilter = '';
     if (opts?.type) {
@@ -1766,7 +1760,7 @@ export class PGLiteEngine implements BrainEngine {
          COALESCE(rep.chunk_index, 0) as chunk_index,
          COALESCE(rep.chunk_text, '') as chunk_text,
          COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
-         ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+         ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
          CASE WHEN p.updated_at < (
            SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
          ) THEN true ELSE false END AS stale
@@ -1781,7 +1775,7 @@ export class PGLiteEngine implements BrainEngine {
          ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
          LIMIT 1
        ) rep ON true
-       WHERE p.search_vector @@ ${ftsQueryExpr}
+       WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
          ${extraFilter} ${hardExcludeClause} ${visibilityClause}
        ORDER BY score DESC, p.id ASC
        LIMIT $2 OFFSET $3`;
@@ -1968,8 +1962,6 @@ export class PGLiteEngine implements BrainEngine {
       });
     }
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, limit, offset];
     let extraFilter = '';
     if (opts?.language) {
@@ -2004,21 +1996,20 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const { rows } = await this.db.query(
       `SELECT
          p.slug, p.id as page_id, p.title, p.type, p.source_id,
          p.effective_date, p.effective_date_source,
          cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-         ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+         ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
          CASE WHEN p.updated_at < (
            SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
          ) THEN true ELSE false END AS stale
        FROM content_chunks cc
        JOIN pages p ON p.id = cc.page_id
        JOIN sources s ON s.id = p.source_id
-       WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
+       WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
        ORDER BY score DESC
        LIMIT $2 OFFSET $3`,
       params

src/core/postgres-engine.ts

@@ -64,7 +64,7 @@ import { ConnectionManager } from './connection-manager.ts';
 import { logConnectionEvent } from './connection-audit.ts';
 import { validateSlug, contentHash, rowToPage, rowToStalePage, rowToChunk, rowToSearchResult, parseEmbedding, tryParseEmbedding, takeRowToTake, takeHitRowToHit, isUndefinedTableError, warnOncePerProcess } from './utils.ts';
 import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
-import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
+import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
 import { DEFAULT_EMBEDDING_MODEL, DEFAULT_EMBEDDING_DIMENSIONS } from './ai/defaults.ts';
 import { DELETE_BATCH_SIZE } from './engine-constants.ts';
 
@@ -1691,8 +1691,6 @@ export class PostgresEngine implements BrainEngine {
     const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
     const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (type) {
@@ -1763,7 +1761,6 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const rawQuery = `
       WITH ranked_chunks AS (
@@ -1771,11 +1768,11 @@ export class PostgresEngine implements BrainEngine {
           p.slug, p.id as page_id, p.title, p.type, p.source_id,
           p.effective_date, p.effective_date_source,
           cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-          ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score
+          ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score
         FROM content_chunks cc
         JOIN pages p ON p.id = cc.page_id
         JOIN sources s ON s.id = p.source_id
-        WHERE cc.search_vector @@ ${ftsQueryExpr}
+        WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
           ${typeClause}
           ${typesClause}
           ${excludeSlugsClause}
@@ -1866,10 +1863,7 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (opts?.type) {
@@ -1929,7 +1923,7 @@ export class PostgresEngine implements BrainEngine {
         COALESCE(rep.chunk_index, 0) as chunk_index,
         COALESCE(rep.chunk_text, '') as chunk_text,
         COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
-        ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+        ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
         false AS stale
       FROM pages p
       JOIN sources s ON s.id = p.source_id
@@ -1942,7 +1936,7 @@ export class PostgresEngine implements BrainEngine {
         ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
         LIMIT 1
       ) rep ON true
-      WHERE p.search_vector @@ ${ftsQueryExpr}
+      WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
         ${typeClause}
         ${typesClause}
         ${excludeSlugsClause}
@@ -2006,8 +2000,6 @@ export class PostgresEngine implements BrainEngine {
     const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
     const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (type) {
@@ -2068,19 +2060,18 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const rawQuery = `
       SELECT
         p.slug, p.id as page_id, p.title, p.type, p.source_id,
         p.effective_date, p.effective_date_source,
         cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-        ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+        ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
         false AS stale
       FROM content_chunks cc
       JOIN pages p ON p.id = cc.page_id
       JOIN sources s ON s.id = p.source_id
-      WHERE cc.search_vector @@ ${ftsQueryExpr}
+      WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
         ${typeClause}
         ${typesClause}
         ${excludeSlugsClause}

src/core/search/sql-ranking.ts

@@ -251,28 +251,6 @@ export function buildOrFallbackWebsearchQuery(query: string): string | null {
   return tokens.join(' OR ');
 }
 
-/**
- * #2380: FTS query expression for slash-bearing queries. Postgres' default
- * text-search parser classifies `foo/bar` as a single `file`-alias lexeme —
- * on BOTH the query side and the index side. So a raw `foo/bar` query only
- * matched documents carrying the identical joined lexeme (literal paths),
- * and a slash-split query only matches documents whose text had the words
- * separated. Neither form alone covers both document shapes; OR the two
- * parses so a slash query matches prose ("foo and bar", stemmed, AND
- * semantics) AND literal slash forms ("src/core/x.ts") alike.
- *
- * Slash-free queries return the plain single-parse expression — byte-
- * identical SQL and identical ts_rank to the historical behavior.
- *
- * `ftsLang` is validated by getFtsLanguage() (safe to interpolate);
- * `param` is a `$N` placeholder, never user text.
- */
-export function buildWebsearchQueryExpr(ftsLang: string, param: string, query: string): string {
-  const plain = `websearch_to_tsquery('${ftsLang}', ${param})`;
-  if (!query.includes('/')) return plain;
-  return `(websearch_to_tsquery('${ftsLang}', translate(${param}, '/', ' ')) || ${plain})`;
-}
-
 // ============================================================
 // v0.29.1 — Recency component SQL builder
 // ============================================================

test/ai/no-batch-cap-suppression.serial.test.ts

@@ -28,8 +28,8 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
     resetGateway();
   });
 
-  test('LiteLLM and llama-server declare no_batch_cap: true', () => {
-    for (const id of ['litellm', 'llama-server']) {
+  test('Ollama, LiteLLM, llama-server all declare no_batch_cap: true', () => {
+    for (const id of ['ollama', 'litellm', 'llama-server']) {
       const r = getRecipe(id);
       expect(r, `${id} not registered`).toBeDefined();
       expect(
@@ -39,18 +39,6 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
     }
   });
 
-  test('#2552: Ollama declares a conservative static batch cap, not no_batch_cap', () => {
-    // A CPU-only Ollama box wedges when a whole page ships in one request;
-    // Ollama never returns a token-limit error so the recursive-halving
-    // safety net can't fire. The pre-split cap is the only guard.
-    const r = getRecipe('ollama');
-    expect(r).toBeDefined();
-    const e = r!.touchpoints.embedding!;
-    expect(e.no_batch_cap).toBeUndefined();
-    expect(e.max_batch_tokens).toBe(4096);
-    expect(e.chars_per_token).toBe(2);
-  });
-
   test('configureGateway does NOT warn for ollama/litellm/llama-server', () => {
     warnSpy.mockClear();
     resetGateway();

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/embed-local-endpoint.serial.test.ts

@@ -1,118 +0,0 @@
-/**
- * #2552: cloud-tuned embedding defaults silently wedge CPU-only local
- * endpoints (Ollama). Three-part fix under test:
- *
- *  1. `isLocalEmbeddingEndpoint()` — gateway helper detecting local
- *     inference servers (ollama / llama-server recipes, localhost base URL).
- *  2. `resolveEmbedConcurrency()` — embed auto-caps the 20-worker fan-out
- *     at LOCAL_EMBED_CONCURRENCY_CAP for local endpoints unless the
- *     operator set GBRAIN_EMBED_CONCURRENCY explicitly.
- *  3. `computeEmbedConcurrencyCheck()` — doctor warns when an explicit env
- *     override fans out against a local endpoint.
- *
- * Serial: mutates process.env and the module-global gateway config.
- */
-
-import { afterAll, afterEach, describe, expect, test } from 'bun:test';
-import {
-  configureGateway,
-  resetGateway,
-  isLocalEmbeddingEndpoint,
-  LOCAL_EMBED_CONCURRENCY_CAP,
-} from '../src/core/ai/gateway.ts';
-import { resolveEmbedConcurrency } from '../src/commands/embed.ts';
-import { computeEmbedConcurrencyCheck } from '../src/commands/doctor.ts';
-
-const SAVED_ENV = process.env.GBRAIN_EMBED_CONCURRENCY;
-
-afterEach(() => {
-  resetGateway();
-  if (SAVED_ENV === undefined) delete process.env.GBRAIN_EMBED_CONCURRENCY;
-  else process.env.GBRAIN_EMBED_CONCURRENCY = SAVED_ENV;
-});
-
-afterAll(() => {
-  resetGateway();
-});
-
-describe('#2552 isLocalEmbeddingEndpoint', () => {
-  test('false when the gateway is not configured (fail-open to cloud behavior)', () => {
-    resetGateway();
-    expect(isLocalEmbeddingEndpoint()).toBe(false);
-  });
-
-  test('true for the ollama recipe', () => {
-    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
-    expect(isLocalEmbeddingEndpoint()).toBe(true);
-  });
-
-  test('true for the llama-server recipe', () => {
-    configureGateway({ embedding_model: 'llama-server:my-gguf', env: {} });
-    expect(isLocalEmbeddingEndpoint()).toBe(true);
-  });
-
-  test('false for a cloud recipe', () => {
-    configureGateway({
-      embedding_model: 'openai:text-embedding-3-small',
-      env: { OPENAI_API_KEY: 'fake' },
-    });
-    expect(isLocalEmbeddingEndpoint()).toBe(false);
-  });
-
-  test('true when a cloud recipe base URL is explicitly pointed at localhost', () => {
-    configureGateway({
-      embedding_model: 'openai:text-embedding-3-small',
-      env: { OPENAI_API_KEY: 'fake' },
-      base_urls: { openai: 'http://localhost:8080/v1' },
-    });
-    expect(isLocalEmbeddingEndpoint()).toBe(true);
-  });
-});
-
-describe('#2552 resolveEmbedConcurrency', () => {
-  test('caps at LOCAL_EMBED_CONCURRENCY_CAP for a local endpoint when env is unset', () => {
-    delete process.env.GBRAIN_EMBED_CONCURRENCY;
-    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
-    expect(resolveEmbedConcurrency()).toBe(LOCAL_EMBED_CONCURRENCY_CAP);
-  });
-
-  test('explicit env override always wins, even against a local endpoint', () => {
-    process.env.GBRAIN_EMBED_CONCURRENCY = '10';
-    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
-    expect(resolveEmbedConcurrency()).toBe(10);
-  });
-
-  test('cloud endpoints keep the historical default of 20', () => {
-    delete process.env.GBRAIN_EMBED_CONCURRENCY;
-    configureGateway({ env: { OPENAI_API_KEY: 'fake' } });
-    expect(resolveEmbedConcurrency()).toBe(20);
-  });
-
-  test('pacing only ever lowers concurrency', () => {
-    delete process.env.GBRAIN_EMBED_CONCURRENCY;
-    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
-    expect(resolveEmbedConcurrency(1)).toBe(1);
-    expect(resolveEmbedConcurrency(16)).toBe(LOCAL_EMBED_CONCURRENCY_CAP);
-  });
-});
-
-describe('#2552 computeEmbedConcurrencyCheck (doctor)', () => {
-  test('ok for non-local endpoints', () => {
-    expect(computeEmbedConcurrencyCheck(false, '20', 2).status).toBe('ok');
-  });
-
-  test('warn when an explicit override exceeds the local cap', () => {
-    const check = computeEmbedConcurrencyCheck(true, '20', 2);
-    expect(check.status).toBe('warn');
-    expect(check.message).toContain('GBRAIN_EMBED_CONCURRENCY=20');
-  });
-
-  test('ok when env is unset against a local endpoint (auto-cap applies)', () => {
-    expect(computeEmbedConcurrencyCheck(true, undefined, 2).status).toBe('ok');
-  });
-
-  test('ok when the override is at or under the cap', () => {
-    expect(computeEmbedConcurrencyCheck(true, '2', 2).status).toBe('ok');
-    expect(computeEmbedConcurrencyCheck(true, '1', 2).status).toBe('ok');
-  });
-});

test/pglite-engine.test.ts

@@ -216,67 +216,6 @@ describe('PGLiteEngine: Search', () => {
     expect(results.length).toBe(0);
   });
 
-  // Regression (#2380): queries containing `/` used to bypass FTS AND
-  // semantics. Postgres' default text-search parser classifies `foo/bar` as
-  // a `file`-alias token mapped to the `simple` dictionary, so it became a
-  // single un-stemmed lexeme `'foo/bar'` that never matches indexed text —
-  // the primary FTS pass returned 0 and the OR fallback took over, matching
-  // pages that contain EITHER term. searchKeyword/searchTitles now normalize
-  // `/` to whitespace before websearch_to_tsquery parses, so the primary
-  // AND pass matches directly.
-  test('searchKeyword: slash query matches with AND semantics, not OR fallback', async () => {
-    // Decoy shares only ONE of the two query terms ('enterprise').
-    await engine.putPage('concepts/enterprise-pricing', {
-      type: 'concept', title: 'Widget Pricing',
-      compiled_truth: 'Enterprise pricing for widgets.',
-    });
-    await engine.upsertChunks('concepts/enterprise-pricing', [
-      { chunk_index: 0, chunk_text: 'Enterprise pricing for widgets', chunk_source: 'compiled_truth' },
-    ]);
-
-    // Both terms co-occur only in the novamind chunk. Pre-fix this returned
-    // BOTH pages (primary pass zero-hit → OR fallback); post-fix the primary
-    // AND pass returns exactly the co-occurrence page.
-    const results = await engine.searchKeyword('NovaMind/enterprise');
-    expect(results.length).toBe(1);
-    expect(results[0].slug).toBe('companies/novamind');
-  });
-
-  test('searchTitles: slash query matches with AND semantics, not OR fallback', async () => {
-    await engine.putPage('companies/novamind-enterprise', {
-      type: 'company', title: 'NovaMind Enterprise Platform',
-      compiled_truth: 'Placeholder body.',
-    });
-    await engine.putPage('guides/enterprise-sales', {
-      type: 'concept', title: 'Enterprise Sales Guide',
-      compiled_truth: 'Placeholder body.',
-    });
-
-    // Pre-fix: `NovaMind/Enterprise` parsed as one file-alias lexeme → the
-    // primary title pass returned 0 and the OR fallback matched BOTH titles.
-    const results = await engine.searchTitles('NovaMind/Enterprise');
-    expect(results.length).toBe(1);
-    expect(results[0].slug).toBe('companies/novamind-enterprise');
-  });
-
-  test('searchKeyword: slash query still matches the literal slash form (file paths)', async () => {
-    // The INDEX side also emits the joined file-alias lexeme for literal
-    // `foo/bar` text, so a query normalized to split words alone would go
-    // blind to documents containing the literal slash form (paths, URLs).
-    // buildWebsearchQueryExpr ORs both parses; this pins the raw arm.
-    await engine.putPage('runbooks/widget-deploy', {
-      type: 'concept', title: 'Widget Deploy Runbook',
-      compiled_truth: 'Runbook for the acme/widget deployment pipeline.',
-    });
-    await engine.upsertChunks('runbooks/widget-deploy', [
-      { chunk_index: 0, chunk_text: 'Runbook for the acme/widget deployment pipeline', chunk_source: 'compiled_truth' },
-    ]);
-
-    const results = await engine.searchKeyword('acme/widget');
-    expect(results.length).toBe(1);
-    expect(results[0].slug).toBe('runbooks/widget-deploy');
-  });
-
   test('tsvector trigger populates search_vector on insert', async () => {
     // Verify the PL/pgSQL trigger fires and content_chunks.search_vector is
     // populated from chunk_text. v0.20.0 Cathedral II Layer 3 moved FTS from

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 () => {