fix(search): honor per-call source_id/all_sources in the search op — the #1484 hint's advised retry was silently ignored

The zero-hit CLI hint tells users to retry with --source-id __all__, which
works for `query` (routes through resolveRequestedScope) but the `search`
op had no source_id/all_sources params: the flag parsed into params, nothing
consumed it, and the retry re-ran the same single-source search — an
invisible false negative whose params.source_id also suppressed the hint on
the retry. search now resolves per-call scope through the same canonical
fail-closed resolver as query (local __all__ spans the brain; remote
collapses to the caller's grant; out-of-grant source_id is denied).

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

src/cli.ts

@@ -466,6 +466,11 @@ async function main() {
     const result = JSON.parse(JSON.stringify(rawResult, bigintToStringReplacer));
     const output = formatResult(op.name, result);
     if (output) process.stdout.write(output);
+    // #1484 — invisible-miss hint: a bare query/search that hit zero results
+    // on a multi-source brain tells the user (stderr) which source it
+    // actually searched and how to widen the scope.
+    const hint = await sourceScopeHint(op.name, params, ctx.sourceId, engine, result);
+    if (hint) console.error(hint);
   } catch (e: unknown) {
     // v0.42.20.0 (codex D4): on error, set exitCode + return so the `finally`
     // STILL runs (drains every background-work sink + disconnects). A bare
@@ -837,6 +842,44 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
   };
 }
 
+/**
+ * #1484 — a bare `gbrain query`/`search` silently scopes to the resolved
+ * source (usually 'default'); on a multi-source brain a zero-hit run looks
+ * identical to "the brain doesn't know this" even when the answer lives in
+ * another source. Returns a stderr hint when (a) the op is query/search,
+ * (b) it returned zero results, (c) the caller did NOT scope explicitly
+ * (--source / --source-id / --all-sources), and (d) the brain has >1
+ * registered source. Best-effort: any lookup failure returns null.
+ *
+ * Exported for tests (same import-safety contract as formatResult).
+ */
+export async function sourceScopeHint(
+  opName: string,
+  params: Record<string, unknown>,
+  sourceId: string,
+  engine: BrainEngine,
+  result: unknown,
+): Promise<string | null> {
+  if (opName !== 'query' && opName !== 'search') return null;
+  if (!Array.isArray(result) || result.length > 0) return null;
+  // Explicit scoping (flag tier) = user intent; don't second-guess it.
+  if (params.source || params.source_id || params.all_sources) return null;
+  if (sourceId === '__all__') return null;
+  try {
+    const rows = await engine.executeRaw<{ n: number }>(
+      `SELECT count(*)::int AS n FROM sources`,
+    );
+    const n = Number(rows[0]?.n ?? 0);
+    if (n <= 1) return null;
+    return (
+      `Hint: this brain has ${n} sources; you searched only "${sourceId}". ` +
+      `Retry with --source-id __all__ (all sources) or --source-id <id>.`
+    );
+  } catch {
+    return null; // hint is best-effort; never fail the query over it
+  }
+}
+
 // Exported for tests (same import-safety contract as cliAliases/printOpHelp).
 export function formatResult(opName: string, result: unknown): string {
   switch (opName) {

src/commands/jobs.ts

@@ -2059,8 +2059,6 @@ export async function registerBuiltinHandlers(
         sourceId,
         windowSeconds,
         brainDir: repoPath,
-        // #2750: worker cancel/timeout/lock-loss propagates into the drain.
-        abortSignal: job.signal,
       });
     } catch (e) {
       if (e instanceof LockUnavailableError) {

src/core/ai/gateway.ts

@@ -1000,9 +1000,24 @@ const voyageCompatFetch = (async (input: RequestInfo | URL, init?: RequestInit)
   // Voyage diverges from OpenAI in two places that break the parser:
   //   - `embedding` is a base64 string (SDK schema expects `number[]`)
   //   - `usage` lacks `prompt_tokens` (SDK schema requires it when usage present)
+  //
+  // #1610: read the body ONCE via text() and JSON.parse it. The pre-fix
+  // `await resp.clone().json()` truncated large bodies on bun < 1.1.27
+  // (oven-sh/bun#6348) — the parse threw, the catch fell back to the raw
+  // response, and multi-chunk pages died with "Invalid JSON response".
+  // Every JSON return path below rebuilds the Response so a stale
+  // Content-Length/Content-Encoding header from the original can't lie
+  // about the rewritten body.
+  const bodyText = await resp.text();
+  const rebuild = (body: string) => {
+    const headers = new Headers(resp.headers);
+    headers.delete('content-length');
+    headers.delete('content-encoding');
+    return new Response(body, { status: resp.status, statusText: resp.statusText, headers });
+  };
   try {
-    const json: any = await resp.clone().json();
-    if (!json || typeof json !== 'object') return resp;
+    const json: any = JSON.parse(bodyText);
+    if (!json || typeof json !== 'object') return rebuild(bodyText);
     let modified = false;
     if (Array.isArray(json.data)) {
       for (const item of json.data) {
@@ -1037,22 +1052,19 @@ const voyageCompatFetch = (async (input: RequestInfo | URL, init?: RequestInit)
         : 0;
       modified = true;
     }
-    if (!modified) return resp;
-    return new Response(JSON.stringify(json), {
-      status: resp.status,
-      statusText: resp.statusText,
-      headers: resp.headers,
-    });
+    if (!modified) return rebuild(bodyText);
+    return rebuild(JSON.stringify(json));
   } catch (err) {
     // OOM-cap throws MUST propagate. The catch is here for "Voyage returned
     // JSON I can't reshape" (parse error, unexpected schema) — falling back
-    // to the original response is correct in that case. Letting the
+    // to the original body is correct in that case. Letting the
     // too-large response through here would defeat the entire purpose of
     // Layer 2 (the per-embedding cap that fires when Content-Length wasn't
     // available to Layer 1).
     if (err instanceof VoyageResponseTooLargeError) throw err;
-    // If parsing/transformation fails, fall back to the original response.
-    return resp;
+    // If parsing/transformation fails, pass the original body through
+    // (rebuilt — resp's body stream is already consumed by text()).
+    return rebuild(bodyText);
   }
 }) as unknown as typeof fetch;
 
@@ -1192,9 +1204,21 @@ const zeroEntropyCompatFetch = (async (input: RequestInfo | URL, init?: RequestI
   // validates. Also map usage.total_tokens → prompt_tokens (SDK requires
   // prompt_tokens when `usage` is present — same divergence Voyage hit at
   // gateway.ts:655).
+  //
+  // #1610: read the body ONCE via text() + JSON.parse — `resp.clone().json()`
+  // truncated large bodies on bun < 1.1.27 (oven-sh/bun#6348), so the parse
+  // threw and the catch fell back to the RAW ZE `{results: ...}` shape, which
+  // the AI SDK schema rejects → "Invalid JSON response" on multi-chunk pages.
+  const bodyText = await resp.text();
+  const rebuild = (body: string) => {
+    const headers = new Headers(resp.headers);
+    headers.delete('content-length');
+    headers.delete('content-encoding');
+    return new Response(body, { status: resp.status, statusText: resp.statusText, headers });
+  };
   try {
-    const json: any = await resp.clone().json();
-    if (!json || typeof json !== 'object') return resp;
+    const json: any = JSON.parse(bodyText);
+    if (!json || typeof json !== 'object') return rebuild(bodyText);
     let modified = false;
     if (Array.isArray(json.results) && !Array.isArray(json.data)) {
       // Layer 2 OOM cap — per-embedding size. ZE returns float[] arrays,
@@ -1228,20 +1252,25 @@ const zeroEntropyCompatFetch = (async (input: RequestInfo | URL, init?: RequestI
       // SDK also expects total_tokens; ZE provides it directly.
       modified = true;
     }
-    if (!modified) return resp;
-    return new Response(JSON.stringify(json), {
-      status: resp.status,
-      statusText: resp.statusText,
-      headers: resp.headers,
-    });
+    if (!modified) return rebuild(bodyText);
+    return rebuild(JSON.stringify(json));
   } catch (err) {
     // OOM-cap throws MUST propagate. Voyage's pattern: instanceof check on
     // its own tagged class. Same here — only rethrow our own cap class.
     if (err instanceof ZeroEntropyResponseTooLargeError) throw err;
-    return resp;
+    return rebuild(bodyText);
   }
 }) as unknown as typeof fetch;
 
+/**
+ * Test-only seams (#1610): the compat shims are module-private closures;
+ * exporting them lets tests drive the response-rewrite paths behaviorally
+ * (truncating clone(), stale Content-Length) without a live provider.
+ * Same pattern as __getShrinkStateForTests.
+ */
+export const __voyageCompatFetchForTests = voyageCompatFetch;
+export const __zeroEntropyCompatFetchForTests = zeroEntropyCompatFetch;
+
 /**
  * Generic asymmetric-embedding shim for openai-compatible recipes that
  * ship no compat fetch of their own (llama-server, litellm, ollama, ...).

src/core/cycle/extract-atoms-drain.ts

@@ -23,10 +23,6 @@
  */
 
 import type { BrainEngine } from '../engine.ts';
-import { anySignal } from '../abort-check.ts';
-
-/** Fresh cleanup budget for the lock release after the window signal fires. */
-const LOCK_RELEASE_GRACE_MS = 5_000;
 
 export interface ExtractAtomsDrainDeps {
   /**
@@ -34,13 +30,13 @@ export interface ExtractAtomsDrainDeps {
    * via `withRefreshingLock`. MUST throw when the lock is held by another
    * process (e.g. `LockUnavailableError`) — the drain lets that propagate so
    * the caller can report `cycle_already_running` and exit, matching the
-   * routine cycle's skip contract. The signal bounds lock acquisition too.
+   * routine cycle's skip contract.
    */
-  withLock: <T>(work: () => Promise<T>, signal: AbortSignal) => Promise<T>;
-  /** Process one batch. The signal fires at the drain wallclock deadline. */
-  runBatch: (signal: AbortSignal) => Promise<{ extracted: number; skipped: number }>;
+  withLock: <T>(work: () => Promise<T>) => Promise<T>;
+  /** Process one bounded batch (rediscovers eligibility). Returns counts. */
+  runBatch: () => Promise<{ extracted: number; skipped: number }>;
   /** Count remaining eligible-but-unextracted pages, or null on query error. */
-  countRemaining: (signal: AbortSignal) => Promise<number | null>;
+  countRemaining: () => Promise<number | null>;
   /** Injectable clock. Production: Date.now. */
   now: () => number;
   /** Optional progress sink (one line per batch). */
@@ -52,8 +48,6 @@ export interface ExtractAtomsDrainOpts {
   windowMs: number;
   /** Hard cap on batches (belt-and-suspenders against a 0-progress loop). Default 1000. */
   maxBatches?: number;
-  /** External caller cancellation (worker timeout / shutdown). */
-  abortSignal?: AbortSignal;
 }
 
 export interface ExtractAtomsDrainResult {
@@ -74,79 +68,35 @@ export async function runExtractAtomsDrain(
   opts: ExtractAtomsDrainOpts,
 ): Promise<ExtractAtomsDrainResult> {
   const maxBatches = opts.maxBatches ?? 1000;
-  const deadline = deps.now() + opts.windowMs;
-  // #2750: the window used to be checked only BETWEEN batches, so one slow
-  // batch (sequential LLM calls) or a hung lock/count/write overran it without
-  // bound (observed window=120s → 282.5s). A real-time deadline signal now
-  // cancels (Postgres) or abandons (PGLite, cooperative) whatever is in
-  // flight; the injected clock still drives loop-boundary checks so the pure
-  // loop stays unit-testable.
-  const signal = anySignal(
-    AbortSignal.timeout(Math.max(1, opts.windowMs)),
-    opts.abortSignal,
-  );
-  const result: ExtractAtomsDrainResult = await deps.withLock(async () => {
+  return deps.withLock(async () => {
+    const deadline = deps.now() + opts.windowMs;
     let extracted = 0;
     let skipped = 0;
     let batches = 0;
     let stopped: ExtractAtomsDrainResult['stopped'] = 'window';
 
-    while (deps.now() < deadline && !signal.aborted) {
+    while (deps.now() < deadline) {
       if (batches >= maxBatches) { stopped = 'max_batches'; break; }
 
-      let before: number | null;
-      try {
-        before = await deps.countRemaining(signal);
-      } catch (err) {
-        if (signal.aborted) break;
-        throw err;
-      }
+      const before = await deps.countRemaining();
       if (before === 0) { stopped = 'drained'; break; }
 
-      // The backlog count consumed the same wallclock budget — re-check so a
-      // slow count can't hand the batch a window that already expired.
-      if (deps.now() >= deadline || signal.aborted) break;
-
-      let r: { extracted: number; skipped: number };
-      try {
-        r = await deps.runBatch(signal);
-      } catch (err) {
-        if (signal.aborted) break;
-        throw err;
-      }
+      const r = await deps.runBatch();
       extracted += r.extracted;
       skipped += r.skipped;
       batches++;
       deps.onBatch?.({ batch: batches, extracted: r.extracted, remaining: before });
 
-      // A deadline abort inside the batch can surface as zero progress;
-      // window exhaustion wins over the generic no_progress label.
-      if (deps.now() >= deadline || signal.aborted) break;
-
       // Stop if a batch made zero forward progress — extraction is failing or
       // everything left is ineligible (e.g. all skipped). Prevents a hot loop
       // that spends budget without draining.
       if (r.extracted === 0 && r.skipped === 0) { stopped = 'no_progress'; break; }
     }
 
-    // After the window elapsed, don't spend more unbounded time on a final
-    // count — report remaining as unknown instead of overrunning further.
-    const windowElapsed = signal.aborted || deps.now() >= deadline;
-    let remaining: number | null = null;
-    if (!windowElapsed) {
-      try {
-        remaining = await deps.countRemaining(signal);
-      } catch (err) {
-        if (!signal.aborted) throw err;
-      }
-    }
+    const remaining = await deps.countRemaining();
     if (remaining === 0) stopped = 'drained';
     return { phase: 'extract_atoms', status: 'ok', extracted, skipped, remaining, batches, stopped };
-  }, signal);
-  // Internal window expiry is a normal partial result. An EXTERNAL abort
-  // (worker cancel/timeout/shutdown) must reject so Minion records the abort.
-  if (opts.abortSignal?.aborted) throw opts.abortSignal.reason;
-  return result;
+  });
 }
 
 // ─── Shared wiring helper (v0.42.x #1685 DECISION 5A) ──────────────────────
@@ -184,8 +134,6 @@ export interface DrainForSourceOpts {
   maxBatches?: number;
   /** Optional per-batch progress sink (stderr line in dream; job progress in the handler). */
   onBatch?: ExtractAtomsDrainDeps['onBatch'];
-  /** Worker cancellation / shutdown signal (Minion `job.signal`). */
-  abortSignal?: AbortSignal;
 }
 
 export async function runExtractAtomsDrainForSource(
@@ -201,17 +149,12 @@ export async function runExtractAtomsDrainForSource(
 
   return runExtractAtomsDrain(
     {
-      withLock: (work, signal) => withRefreshingLock(engine, lockId, work, {
-        ttlMinutes: 5,
-        signal,
-        releaseTimeoutMs: LOCK_RELEASE_GRACE_MS,
-      }),
-      runBatch: async (signal) => {
+      withLock: (work) => withRefreshingLock(engine, lockId, work, { ttlMinutes: 5 }),
+      runBatch: async () => {
         const r = await runPhaseExtractAtoms(engine, {
           sourceId: extractionSourceId,
           dryRun: false,
           brainDir: opts.brainDir,
-          abortSignal: signal,
         });
         const d = (r.details ?? {}) as Record<string, unknown>;
         return {
@@ -219,14 +162,10 @@ export async function runExtractAtomsDrainForSource(
           skipped: Number(d.duplicates_skipped ?? 0),
         };
       },
-      countRemaining: (signal) => countExtractAtomsBacklog(engine, extractionSourceId, signal),
+      countRemaining: () => countExtractAtomsBacklog(engine, extractionSourceId),
       now: Date.now,
       onBatch: opts.onBatch,
     },
-    {
-      windowMs: opts.windowSeconds * 1000,
-      maxBatches: opts.maxBatches,
-      abortSignal: opts.abortSignal,
-    },
+    { windowMs: opts.windowSeconds * 1000, maxBatches: opts.maxBatches },
   );
 }

src/core/cycle/extract-atoms.ts

@@ -58,10 +58,6 @@ import { createHash } from 'crypto';
 import { slugifySegment } from '../sync.ts';
 
 const DEFAULT_BUDGET_USD = 0.3;
-// #2750: fresh wallclock budget for the receipt/rollup bookkeeping writes when
-// the caller's deadline already fired — committed atoms must not lose their
-// cost/receipt trail, but the writes can't be unbounded either.
-const BOOKKEEPING_GRACE_MS = 5_000;
 
 // v0.42+ TODO: read atom_type enum from active pack manifest at runtime.
 const ATOM_TYPES = [
@@ -159,13 +155,6 @@ export interface ExtractAtomsOpts {
    * `heartbeat()` on the passed reporter.
    */
   progress?: ProgressReporter;
-  /**
-   * #2750: caller deadline/cancellation. Forwarded to every gateway call and
-   * DB query/write so the drain window bounds real lifetime, plus a
-   * cooperative between-item check (the PGLite path, where query abort only
-   * abandons the waiter).
-   */
-  abortSignal?: AbortSignal;
 }
 
 interface ExtractedAtom {
@@ -223,7 +212,6 @@ export async function discoverExtractablePages(
   engine: BrainEngine,
   sourceId: string,
   affectedSlugs?: string[],
-  abortSignal?: AbortSignal,
 ): Promise<DiscoveredPage[]> {
   const hasFilter = Array.isArray(affectedSlugs) && affectedSlugs.length > 0;
   const sql = `
@@ -263,16 +251,13 @@ export async function discoverExtractablePages(
       slug: string;
       compiled_truth: string;
       content_hash: string;
-    }>(sql, params, { signal: abortSignal });
+    }>(sql, params);
     return rows.map((r) => ({
       slug: r.slug,
       content: r.compiled_truth,
       contentHash: r.content_hash,
     }));
   } catch (err) {
-    // A deadline abort is not a fail-soft condition — propagate so the
-    // caller stops instead of proceeding with an empty page list.
-    if (abortSignal?.aborted) throw err;
     const msg = err instanceof Error ? err.message : String(err);
     console.error(`[extract_atoms] page-discovery query failed: ${msg}`);
     return []; // fail-soft: transcript path still proceeds
@@ -297,7 +282,6 @@ export async function discoverExtractablePages(
 export async function countExtractAtomsBacklog(
   engine: BrainEngine,
   sourceId?: string,
-  abortSignal?: AbortSignal,
 ): Promise<number | null> {
   try {
     // Two modes: scoped (the phase's per-source `remaining`) vs brain-wide
@@ -337,10 +321,9 @@ export async function countExtractAtomsBacklog(
     const params = scoped
       ? [sourceId, extractableTypes, MIN_PAGE_CHARS_FOR_EXTRACTION]
       : [extractableTypes, MIN_PAGE_CHARS_FOR_EXTRACTION];
-    const rows = await engine.executeRaw<{ cnt: string | number }>(sql, params, { signal: abortSignal });
+    const rows = await engine.executeRaw<{ cnt: string | number }>(sql, params);
     return Number(rows[0]?.cnt ?? 0);
   } catch (err) {
-    if (abortSignal?.aborted) throw err;
     const msg = err instanceof Error ? err.message : String(err);
     console.error(`[extract_atoms] backlog count failed: ${msg}`);
     return null;
@@ -367,7 +350,6 @@ export async function atomsExistingForHashes(
   engine: BrainEngine,
   sourceId: string,
   contentHash16s: string[],
-  abortSignal?: AbortSignal,
 ): Promise<Set<string>> {
   if (contentHash16s.length === 0) return new Set();
   try {
@@ -379,11 +361,9 @@ export async function atomsExistingForHashes(
           AND deleted_at IS NULL
           AND frontmatter->>'source_hash' = ANY($2::text[])`,
       [sourceId, contentHash16s],
-      { signal: abortSignal },
     );
     return new Set(rows.map(r => r.h));
   } catch (err) {
-    if (abortSignal?.aborted) throw err;
     const msg = err instanceof Error ? err.message : String(err);
     console.error(`[extract_atoms] batch idempotency check failed (assuming none extracted): ${msg}`);
     return new Set();
@@ -404,7 +384,6 @@ export async function runPhaseExtractAtoms(
 ): Promise<PhaseResult> {
   const sourceId = opts.sourceId ?? 'default';
   const chat = opts._chat ?? gatewayChat;
-  if (opts.abortSignal?.aborted) throw opts.abortSignal.reason;
 
   // 1a. Get transcripts (test seam OR production discovery).
   //     v0.41.2.1: config loader switched to loadConfigWithEngine() so the
@@ -446,7 +425,7 @@ export async function runPhaseExtractAtoms(
   if (opts._pages !== undefined) {
     pages = opts._pages;
   } else {
-    pages = await discoverExtractablePages(engine, sourceId, opts.affectedSlugs, opts.abortSignal);
+    pages = await discoverExtractablePages(engine, sourceId, opts.affectedSlugs);
   }
 
   // 2. Apply transcript-side source-hash idempotency in ONE batch query
@@ -458,7 +437,7 @@ export async function runPhaseExtractAtoms(
   // Surface a heartbeat before the batch query so even an instant
   // short-circuit shows a sign of life (closes Issue 2 silent-phase pain).
   opts.progress?.heartbeat(`checking existing atoms for ${allHashes16.length} transcripts`);
-  const existingHashes = await atomsExistingForHashes(engine, sourceId, allHashes16, opts.abortSignal);
+  const existingHashes = await atomsExistingForHashes(engine, sourceId, allHashes16);
   for (const t of transcripts) {
     if (existingHashes.has(t.contentHash.slice(0, 16))) {
       duplicatesSkipped++;
@@ -522,7 +501,6 @@ export async function runPhaseExtractAtoms(
   const failures: Array<{ source: string; error: string }> = [];
   let estimatedSpendUsd = 0;
   const budgetCap = DEFAULT_BUDGET_USD;
-  let deadlineAborted = false;
 
   // v0.41.19.0 (T3): throttled yield helper. Fires `opts.yieldDuringPhase`
   // every 30s. Cycle.ts threads `buildYieldDuringPhase(lock, outer)` so
@@ -548,12 +526,6 @@ export async function runPhaseExtractAtoms(
   }
 
   for (const item of work) {
-    // #2750: cooperative between-item abort. Works on every engine — this is
-    // the primary bound on PGLite, where query abort only abandons the waiter.
-    if (opts.abortSignal?.aborted) {
-      deadlineAborted = true;
-      break;
-    }
     await maybeYield();
     if (estimatedSpendUsd >= budgetCap) {
       if (item.kind === 'transcript') transcriptsSkipped++;
@@ -572,22 +544,16 @@ export async function runPhaseExtractAtoms(
           },
         ],
         maxTokens: 2000,
-        abortSignal: opts.abortSignal,
       });
-      // Rough cost estimate — Haiku at ~$0.80/M input + $4/M output.
-      // A completed gateway call is billable even if the deadline fires
-      // immediately afterward, so record usage BEFORE the abort check.
-      estimatedSpendUsd +=
-        (result.usage.input_tokens * 0.8 + result.usage.output_tokens * 4.0) / 1_000_000;
-      if (opts.abortSignal?.aborted) {
-        deadlineAborted = true;
-        break;
-      }
       // Post-await yield: closes the "long LLM call past TTL" hazard
       // codex flagged. The 30s throttle inside maybeYield bounds the
       // actual refresh rate so this is cheap when calls are fast.
       await maybeYield();
 
+      // Rough cost estimate — Haiku at ~$0.80/M input + $4/M output
+      estimatedSpendUsd +=
+        (result.usage.input_tokens * 0.8 + result.usage.output_tokens * 4.0) / 1_000_000;
+
       const atoms = parseAtomsResponse(result.text);
       if (atoms.length === 0) {
         if (item.kind === 'transcript') transcriptsProcessed++;
@@ -626,7 +592,7 @@ export async function runPhaseExtractAtoms(
               },
               timeline: '',
             },
-            { sourceId, signal: opts.abortSignal },
+            { sourceId },
           );
           totalAtomsExtracted++;
         }
@@ -639,11 +605,6 @@ export async function runPhaseExtractAtoms(
       // Reporter rate-limits to ~1 line/sec; safe to tick every iter.
       opts.progress?.tick(1, `${totalAtomsExtracted} atoms / ${duplicatesSkipped} skipped`);
     } catch (err) {
-      // A deadline abort is a partial result, not a per-item failure.
-      if (opts.abortSignal?.aborted) {
-        deadlineAborted = true;
-        break;
-      }
       failures.push({
         source: originLabel,
         error: err instanceof Error ? err.message : String(err),
@@ -654,12 +615,6 @@ export async function runPhaseExtractAtoms(
   // v0.42 Wave B2: write extract receipt + rollup row when the phase
   // actually extracted atoms. Both are best-effort per F-OUT-19 —
   // audit-trail / search-visibility surfaces don't block the phase result.
-  //
-  // #2750: bookkeeping runs on a FRESH short grace signal, never the caller's
-  // work deadline — the deadline may have already fired (partial run) and
-  // committed atoms must not lose their receipt/cost trail; but the writes
-  // stay bounded so the overrun is capped at the grace window.
-  const bookkeepingSignal = opts.dryRun ? undefined : AbortSignal.timeout(BOOKKEEPING_GRACE_MS);
   if (!opts.dryRun && totalAtomsExtracted > 0) {
     const runId = `atoms-${Date.now().toString(36)}-${sourceId.slice(0, 4)}`;
     try {
@@ -674,24 +629,19 @@ export async function runPhaseExtractAtoms(
         summary:
           `Extracted ${totalAtomsExtracted} atoms from ` +
           `${transcriptsProcessed} transcripts + ${pagesProcessed} pages.`,
-      }, { signal: bookkeepingSignal });
+      });
     } catch (err) {
       console.error(`[extract_atoms] receipt write failed: ${(err as Error).message}`);
     }
   }
   if (!opts.dryRun) {
-    try {
-      await upsertExtractRollup(engine, {
-        kind: 'atoms',
-        source_id: sourceId,
-        cost_delta: estimatedSpendUsd,
-        // A deadline-truncated run is not a completed round.
-        round_completed_delta: failures.length === 0 && !deadlineAborted ? 1 : 0,
-        halt_delta: failures.length > 0 ? 1 : 0,
-      }, { signal: bookkeepingSignal });
-    } catch (err) {
-      console.error(`[extract_atoms] rollup write failed: ${(err as Error).message}`);
-    }
+    await upsertExtractRollup(engine, {
+      kind: 'atoms',
+      source_id: sourceId,
+      cost_delta: estimatedSpendUsd,
+      round_completed_delta: failures.length === 0 ? 1 : 0,
+      halt_delta: failures.length > 0 ? 1 : 0,
+    });
   }
 
   return {
@@ -720,7 +670,6 @@ export async function runPhaseExtractAtoms(
       budget_usd: budgetCap,
       source_id: sourceId,
       dry_run: opts.dryRun ?? false,
-      deadline_aborted: deadlineAborted,
     },
   };
 }

src/core/db-lock.ts

@@ -26,8 +26,7 @@ import type { BrainEngine } from './engine.ts';
 
 export interface DbLockHandle {
   id: string;
-  /** Optional signal bounds the release DELETE (deadline-bound callers). */
-  release: (signal?: AbortSignal) => Promise<void>;
+  release: () => Promise<void>;
   refresh: () => Promise<void>;
 }
 
@@ -174,7 +173,6 @@ export async function tryAcquireDbLock(
   engine: BrainEngine,
   lockId: string,
   ttlMinutes: number = DEFAULT_TTL_MINUTES,
-  opts: { signal?: AbortSignal } = {},
 ): Promise<DbLockHandle | null> {
   const pid = process.pid;
   const host = hostname();
@@ -207,26 +205,20 @@ export async function tryAcquireDbLock(
     // `gbrain sync --break-lock --max-age <s>` uses last_refreshed_at (not
     // acquired_at) to identify wedged-but-alive holders without stealing
     // healthy long-running holders that are actively refreshing.
-    // #2750: routed through executeRaw so a deadline-bound caller's signal
-    // can cancel a hung acquire (pool exhaustion). Cancellation is
-    // transactional; in the rare ambiguous-commit case the row's TTL is the
-    // backstop (drain locks use a short 5-minute TTL).
-    const rows = await engine.executeRaw<{ id: string }>(
-      `INSERT INTO gbrain_cycle_locks (id, holder_pid, holder_host, acquired_at, ttl_expires_at, last_refreshed_at)
-       VALUES ($1, $2, $3, NOW(), NOW() + $4::interval, NOW())
-       ON CONFLICT (id) DO UPDATE
-         SET holder_pid = $2,
-             holder_host = $3,
-             acquired_at = NOW(),
-             ttl_expires_at = NOW() + $4::interval,
-             last_refreshed_at = NOW()
-         WHERE gbrain_cycle_locks.ttl_expires_at < NOW()
-           AND (gbrain_cycle_locks.last_refreshed_at IS NULL
-                OR gbrain_cycle_locks.last_refreshed_at < NOW() - $5 * INTERVAL '1 second')
-       RETURNING id`,
-      [lockId, pid, host, ttl, stealGraceSeconds],
-      { signal: opts.signal },
-    );
+    const rows: Array<{ id: string }> = await sql`
+      INSERT INTO gbrain_cycle_locks (id, holder_pid, holder_host, acquired_at, ttl_expires_at, last_refreshed_at)
+      VALUES (${lockId}, ${pid}, ${host}, NOW(), NOW() + ${ttl}::interval, NOW())
+      ON CONFLICT (id) DO UPDATE
+        SET holder_pid = ${pid},
+            holder_host = ${host},
+            acquired_at = NOW(),
+            ttl_expires_at = NOW() + ${ttl}::interval,
+            last_refreshed_at = NOW()
+        WHERE gbrain_cycle_locks.ttl_expires_at < NOW()
+          AND (gbrain_cycle_locks.last_refreshed_at IS NULL
+               OR gbrain_cycle_locks.last_refreshed_at < NOW() - ${stealGraceSeconds} * INTERVAL '1 second')
+      RETURNING id
+    `;
     if (rows.length === 0) return null;
     const deregister = registerCleanup(`db-lock:${lockId}`, async () => {
       await sql`
@@ -249,17 +241,12 @@ export async function tryAcquireDbLock(
           [ttl, lockId, pid],
         );
       },
-      release: async (signal?: AbortSignal) => {
+      release: async () => {
         deregister();
-        // Direct session pool (same rationale as refresh, #1794) + optional
-        // signal so a deadline-bound caller's release can't hang forever on
-        // an exhausted pooler. TTL is the backstop if the DELETE is cancelled.
-        await engine.executeRawDirect(
-          `DELETE FROM gbrain_cycle_locks
-            WHERE id = $1 AND holder_pid = $2`,
-          [lockId, pid],
-          { signal },
-        );
+        await sql`
+          DELETE FROM gbrain_cycle_locks
+          WHERE id = ${lockId} AND holder_pid = ${pid}
+        `;
       },
     };
   }
@@ -316,11 +303,6 @@ export async function tryAcquireDbLock(
   const first = await acquireOnce();
   if (first) return first;
 
-  // #2750: deadline-bound callers prefer an honest busy result over the
-  // best-effort same-host takeover below, whose inspect/delete/retry calls
-  // are not signal-bounded. The initial upsert already reclaims expired locks.
-  if (opts.signal) return null;
-
   // v0.42 (#1780 Gap 3): the lock is held and its TTL hasn't expired (the
   // upsert's ON CONFLICT ... WHERE ttl_expires_at < NOW() returned no row).
   // If the holder is on THIS host, provably dead, and past the grace window,
@@ -814,10 +796,6 @@ export interface WithRefreshingLockOpts {
   ttlMinutes?: number;
   /** Heartbeat-fail threshold in ms — abort if SELECT 1 takes longer. Default 30000. */
   heartbeatTimeoutMs?: number;
-  /** #2750: bound lock acquisition with the caller's deadline signal. */
-  signal?: AbortSignal;
-  /** Fresh cleanup budget for the release DELETE when `signal` is set. Default 5000. */
-  releaseTimeoutMs?: number;
 }
 
 /**
@@ -837,7 +815,7 @@ export async function withRefreshingLock<T>(
   // Refresh 6x per TTL window so a missed tick doesn't expire the lock.
   const refreshIntervalMs = Math.max(15000, (ttlMinutes * 60 * 1000) / 6);
 
-  const handle = await tryAcquireDbLock(engine, lockId, ttlMinutes, { signal: opts.signal });
+  const handle = await tryAcquireDbLock(engine, lockId, ttlMinutes);
   if (!handle) throw new LockUnavailableError(lockId);
 
   let healthOk = true;
@@ -876,13 +854,7 @@ export async function withRefreshingLock<T>(
     return await work();
   } finally {
     clearInterval(interval);
-    // #2750: when the caller is deadline-bound, its work signal may already
-    // have fired — release on a FRESH short grace signal so cleanup neither
-    // inherits the spent deadline nor hangs unbounded. TTL is the backstop.
-    const releaseSignal = opts.signal
-      ? AbortSignal.timeout(opts.releaseTimeoutMs ?? 5_000)
-      : undefined;
-    try { await handle.release(releaseSignal); } catch { /* idempotent; TTL backstop */ }
+    try { await handle.release(); } catch { /* idempotent */ }
     if (!healthOk) {
       // Surface that the heartbeat detected backend trouble — caller can
       // log to the connection-events audit if desired.

src/core/engine.ts

@@ -696,16 +696,8 @@ export interface BrainEngine {
    * is included in the INSERT column list so ON CONFLICT (source_id, slug)
    * DO UPDATE actually targets the intended row instead of fabricating a
    * duplicate at (default, slug). Multi-source brains MUST pass sourceId.
-   *
-   * `opts.signal` (#2750): optional cancellation for deadline-bound writers.
-   * Postgres cancels the in-flight statement; PGLite pre-checks only (query
-   * cancellation is not possible in-process — cooperative abort between calls).
    */
-  putPage(
-    slug: string,
-    page: PageInput,
-    opts?: { sourceId?: string; signal?: AbortSignal },
-  ): Promise<Page>;
+  putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page>;
   /**
    * v0.41.13 (#1309) — identity-based dedup pre-check for the import pipeline.
    *

src/core/extract/receipt-writer.ts

@@ -187,7 +187,6 @@ function buildReceiptFrontmatter(input: ExtractReceiptInput): Record<string, unk
 export async function writeReceipt(
   engine: BrainEngine,
   input: ExtractReceiptInput,
-  opts?: { signal?: AbortSignal },
 ): Promise<{ slug: string; page: Page }> {
   const slug = receiptSlug(input);
   const title = `${input.kind} — ${input.round} — ${input.source_id}`;
@@ -202,7 +201,7 @@ export async function writeReceipt(
       compiled_truth,
       frontmatter,
     },
-    { sourceId: input.source_id, signal: opts?.signal },
+    { sourceId: input.source_id },
   );
 
   return { slug, page };

src/core/extract/rollup-writer.ts

@@ -70,7 +70,6 @@ function today(): string {
 export async function upsertExtractRollup(
   engine: BrainEngine,
   input: RollupUpsertInput,
-  opts?: { signal?: AbortSignal },
 ): Promise<{ ok: boolean; error?: string }> {
   const day = input.day ?? today();
   const cost = input.cost_delta ?? 0;
@@ -97,12 +96,9 @@ export async function upsertExtractRollup(
          rollup_write_failures  = extract_rollup_7d.rollup_write_failures  + EXCLUDED.rollup_write_failures,
          updated_at             = now()`,
       [input.kind, input.source_id, day, cost, halts, evalFails, evalPasses, completed, failures],
-      { signal: opts?.signal },
     );
     return { ok: true };
   } catch (err) {
-    // Signal-bounded callers get the abort surfaced, not a swallowed `ok:false`.
-    if (opts?.signal?.aborted) throw err;
     const msg = (err as Error).message || String(err);
     // Don't spam: log once per process per (kind, day) error class.
     rollupErrorLogOnce(input.kind, day, msg);

src/core/operations.ts

@@ -499,7 +499,7 @@ export function linkReadScopeOpts(ctx: OperationContext): { sourceId?: string; s
  * FAIL-CLOSED: anything not strictly `ctx.remote === false` is untrusted.
  *
  * This is the SINGLE resolver for every read op that accepts a per-call
- * `source_id` / `all_sources` parameter (query, code_callers, code_callees,
+ * `source_id` / `all_sources` parameter (query, search, code_callers, code_callees,
  * get_page, search_by_image, code_blast, code_flow). Inlining the `__all__`
  * branch per handler is the bug class that leaked cross-source reads (#1924,
  * #1371): a remote client could pass `source_id: '__all__'` to opt out of its
@@ -1442,13 +1442,24 @@ const search: Operation = {
     limit: { type: 'number', description: 'Max results (default 20)' },
     offset: { type: 'number', description: 'Skip first N results (for pagination)' },
     mode: { type: 'string', description: 'Search mode (conservative|balanced|tokenmax). Local callers only.' },
+    source_id: {
+      type: 'string',
+      description:
+        "Scope search to a single source. Defaults to OperationContext.sourceId. Pass '__all__' to span every source for trusted local callers; for remote callers '__all__' spans only your granted sources.",
+    },
+    all_sources: { type: 'boolean', description: "Span sources (equivalent to source_id=__all__): every source locally, your grant remotely." },
   },
   handler: async (ctx, p) => {
     const startedAt = Date.now();
     const queryText = p.query as string;
     const limit = (p.limit as number) || 20;
     const offset = (p.offset as number) || 0;
-    const scope = sourceScopeOpts(ctx);
+    // #1484 follow-up: route through the canonical fail-closed resolver so
+    // `--source-id __all__` / `all_sources` behave the same as on `query`
+    // (the zero-hit CLI hint advises exactly that retry). Without a per-call
+    // param, `search` silently ignored --source-id — the retry looked like
+    // a genuine miss.
+    const scope = resolveRequestedScope(ctx, p.source_id as string | undefined, p.all_sources === true);
 
     // T4/D5 — per-call mode honored ONLY for trusted/local callers so a remote
     // OAuth client can't escalate to the costly tokenmax bundle. Local + unknown

src/core/pglite-engine.ts

@@ -1003,15 +1003,7 @@ export class PGLiteEngine implements BrainEngine {
     return { slug: r.slug, id: Number(r.id) };
   }
 
-  async putPage(
-    slug: string,
-    page: PageInput,
-    opts?: { sourceId?: string; signal?: AbortSignal },
-  ): Promise<Page> {
-    // #2750: PGLite is in-process WASM — no query cancellation. Pre-check so
-    // an already-fired deadline skips the write; abort is cooperative
-    // between calls (same posture as executeRaw's documented gap).
-    if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
+  async putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page> {
     slug = validateSlug(slug);
     const hash = page.content_hash || contentHash(page);
     const frontmatter = page.frontmatter || {};

src/core/postgres-engine.ts

@@ -72,32 +72,6 @@ function escapeSqlStringLiteral(value: string): string {
   return value.replace(/'/g, "''");
 }
 
-/**
- * #2750: race a promise against an AbortSignal, detaching the listener once
- * settled (long-lived drain signals are reused across many calls, so a bare
- * Promise.race would leak one listener per call). The abandoned promise keeps
- * running; used only for pool-acquisition waits where that is harmless.
- */
-function waitForSignal<T>(work: Promise<T>, signal?: AbortSignal): Promise<T> {
-  if (!signal) return work;
-  if (signal.aborted) return Promise.reject(new DOMException('aborted', 'AbortError'));
-  return new Promise<T>((resolve, reject) => {
-    let settled = false;
-    const finish = (fn: () => void) => {
-      if (settled) return;
-      settled = true;
-      signal.removeEventListener('abort', onAbort);
-      fn();
-    };
-    const onAbort = () => finish(() => reject(new DOMException('aborted', 'AbortError')));
-    signal.addEventListener('abort', onAbort, { once: true });
-    work.then(
-      (value) => finish(() => resolve(value)),
-      (err) => finish(() => reject(err)),
-    );
-  });
-}
-
 export function getPostgresSchema(
   dims: number = DEFAULT_EMBEDDING_DIMENSIONS,
   model: string = DEFAULT_EMBEDDING_MODEL,
@@ -1087,12 +1061,7 @@ export class PostgresEngine implements BrainEngine {
     });
   }
 
-  async putPage(
-    slug: string,
-    page: PageInput,
-    opts?: { sourceId?: string; signal?: AbortSignal },
-  ): Promise<Page> {
-    if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
+  async putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page> {
     slug = validateSlug(slug);
     const sql = this.sql;
     const hash = page.content_hash || contentHash(page);
@@ -1127,7 +1096,7 @@ export class PostgresEngine implements BrainEngine {
     const sourceUri = page.source_uri ?? null;
     const ingestedVia = page.ingested_via ?? null;
     const ingestedAt = (sourceKind || sourceUri || ingestedVia) ? new Date() : null;
-    const pending = sql`
+    const rows = await sql`
       INSERT INTO pages (source_id, slug, type, page_kind, title, compiled_truth, timeline, frontmatter, content_hash, updated_at, effective_date, effective_date_source, import_filename, chunker_version, source_path, source_kind, source_uri, ingested_via, ingested_at)
       VALUES (${sourceId}, ${slug}, ${page.type}, ${pageKind}, ${page.title}, ${page.compiled_truth}, ${page.timeline || ''}, ${sql.json(frontmatter as Parameters<typeof sql.json>[0])}, ${hash}, now(), ${effectiveDate}, ${effectiveDateSource}, ${importFilename}, COALESCE(${chunkerVersion}::smallint, ${MARKDOWN_CHUNKER_VERSION}), ${sourcePath}, ${sourceKind}, ${sourceUri}, ${ingestedVia}, ${ingestedAt})
       ON CONFLICT (source_id, slug) DO UPDATE SET
@@ -1150,22 +1119,6 @@ export class PostgresEngine implements BrainEngine {
         ingested_at           = COALESCE(EXCLUDED.ingested_at,           pages.ingested_at)
       RETURNING id, source_id, slug, type, title, compiled_truth, timeline, frontmatter, content_hash, created_at, updated_at, effective_date, effective_date_source, import_filename, source_kind, source_uri, ingested_via, ingested_at
     `;
-    // #2750: cancel the in-flight statement when the caller's deadline fires,
-    // same .cancel() wiring as runUnsafe (postgres.js pending queries).
-    if (opts?.signal) {
-      const signal = opts.signal;
-      const onAbort = () => {
-        try { (pending as unknown as { cancel?: () => void }).cancel?.(); } catch { /* best-effort */ }
-      };
-      signal.addEventListener('abort', onAbort, { once: true });
-      try {
-        const rows = await pending;
-        return rowToPage(rows[0]);
-      } finally {
-        signal.removeEventListener('abort', onAbort);
-      }
-    }
-    const rows = await pending;
     return rowToPage(rows[0]);
   }
 
@@ -5854,16 +5807,11 @@ export class PostgresEngine implements BrainEngine {
     params?: unknown[],
     opts?: { signal?: AbortSignal },
   ): Promise<T[]> {
-    // #2750: an already-fired signal short-circuits BEFORE any pool routing,
-    // and the direct-pool acquisition itself is signal-bounded — under pooler
-    // exhaustion `ddl()` can stall indefinitely, which used to make even a
-    // "bounded" lock release hang past its caller's deadline.
-    if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
     // Inside an open transaction, _sql is the reserved tx connection (set via
     // defineProperty in transaction()); never reroute off it.
     const inTransaction = this._sql !== null && this.connectionManager?.peekReadPool() !== this._sql;
     const conn = (!inTransaction && this.connectionManager?.isDualPoolActive())
-      ? await waitForSignal(this.connectionManager.ddl(), opts?.signal)
+      ? await this.connectionManager.ddl()
       : this.sql;
     return this.runUnsafe<T>(conn, sql, params, opts);
   }

src/core/search/hybrid.ts

@@ -1323,8 +1323,18 @@ export async function hybridSearch(
       if (effectiveModality === 'both' && imageVectorList !== null) {
         vectorLists = [...vectorLists, imageVectorList];
       }
-    } catch {
-      // Embedding failure is non-fatal, fall back to keyword-only
+    } catch (err) {
+      // Embedding/vector failure is non-fatal — fall back to keyword-only —
+      // but say WHY (#1626): this arm only runs when the embedding provider
+      // probed available, so a throw here is a real failure (embed timeout,
+      // transient pooler error on the searchVector fan-out). Pre-fix the bare
+      // catch made a cross-source `--source __all__` run silently collapse to
+      // keyword-only/"No results" with zero diagnostics.
+      warnOncePerProcess(
+        'hybrid-vector-arm-failed',
+        `[gbrain] vector arm failed (fail-open, keyword-only fallback): ` +
+          `${err instanceof Error ? err.message : String(err)}`,
+      );
     }
   }
 

test/ai/compat-fetch-body-read.serial.test.ts

@@ -0,0 +1,115 @@
+/**
+ * #1610 — Voyage/ZeroEntropy compat shims must read the response body ONCE
+ * via text() instead of `resp.clone().json()`.
+ *
+ * On bun < 1.1.27, Response.clone() truncates large bodies (oven-sh/bun#6348):
+ * the clone().json() parse threw, the shim's catch fell back to the ORIGINAL
+ * response — whose wire shape (ZE `{results: ...}`, Voyage base64 embeddings)
+ * the AI SDK's openai-compatible Zod schema rejects — and multi-chunk pages
+ * failed with "Invalid JSON response".
+ *
+ * These tests simulate the truncating clone() and assert the shims still
+ * return the fully rewritten body. They also pin that the rewritten Response
+ * does NOT carry the original (now stale) Content-Length header, which lied
+ * about the rewritten body's size (gateway.ts previously copied
+ * `headers: resp.headers` verbatim).
+ */
+
+import { afterEach, describe, expect, test } from 'bun:test';
+import {
+  __voyageCompatFetchForTests,
+  __zeroEntropyCompatFetchForTests,
+} from '../../src/core/ai/gateway.ts';
+
+const origFetch = globalThis.fetch;
+afterEach(() => {
+  globalThis.fetch = origFetch;
+});
+
+/** Build a Response whose clone() truncates the body (bun < 1.1.27 behavior). */
+function truncatingCloneResponse(body: string): Response {
+  const headers = {
+    'content-type': 'application/json',
+    // Deliberately stale after any rewrite: the original wire body's length.
+    'content-length': String(Buffer.byteLength(body)),
+  };
+  const resp = new Response(body, { status: 200, headers });
+  (resp as any).clone = () =>
+    new Response(body.slice(0, 32), { status: 200, headers });
+  return resp;
+}
+
+describe('voyageCompatFetch — single body read (#1610)', () => {
+  test('rewrites base64 embeddings even when clone() truncates the body', async () => {
+    const floats = new Float32Array([0.5, 0.25, -1]);
+    const b64 = Buffer.from(floats.buffer).toString('base64');
+    const wireBody = JSON.stringify({
+      object: 'list',
+      data: [{ object: 'embedding', embedding: b64, index: 0 }],
+      model: 'voyage-3',
+      usage: { total_tokens: 7 },
+    });
+    globalThis.fetch = (async () => truncatingCloneResponse(wireBody)) as unknown as typeof fetch;
+
+    const out = await __voyageCompatFetchForTests('https://api.voyageai.com/v1/embeddings', {
+      method: 'POST',
+      body: JSON.stringify({ input: ['hello'], model: 'voyage-3' }),
+      headers: { 'content-type': 'application/json' },
+    });
+
+    const json: any = await out.json();
+    expect(Array.from(json.data[0].embedding)).toEqual([0.5, 0.25, -1]);
+    expect(json.usage.prompt_tokens).toBe(7);
+    // Stale Content-Length from the wire body must not survive the rewrite.
+    expect(out.headers.get('content-length')).toBeNull();
+    expect(out.headers.get('content-encoding')).toBeNull();
+  });
+});
+
+describe('zeroEntropyCompatFetch — single body read (#1610)', () => {
+  test('rewrites {results} → {data} even when clone() truncates the body', async () => {
+    const wireBody = JSON.stringify({
+      results: [{ embedding: [0.1, 0.2] }, { embedding: [0.3, 0.4] }],
+      usage: { total_bytes: 42, total_tokens: 9 },
+    });
+    let fetchedUrl = '';
+    globalThis.fetch = (async (url: string | URL | Request) => {
+      fetchedUrl = String(url);
+      return truncatingCloneResponse(wireBody);
+    }) as unknown as typeof fetch;
+
+    const out = await __zeroEntropyCompatFetchForTests('https://api.zeroentropy.dev/v1/embeddings', {
+      method: 'POST',
+      body: JSON.stringify({ input: ['hello'], model: 'zembed-1' }),
+      headers: { 'content-type': 'application/json' },
+    });
+
+    expect(fetchedUrl.endsWith('/v1/models/embed')).toBe(true);
+    const json: any = await out.json();
+    // The AI SDK schema requires {data: [{embedding, index}]} — the raw ZE
+    // {results} fallback is exactly the pre-fix "Invalid JSON response".
+    expect(json.results).toBeUndefined();
+    expect(json.data).toHaveLength(2);
+    expect(json.data[0]).toEqual({ object: 'embedding', embedding: [0.1, 0.2], index: 0 });
+    expect(json.data[1].index).toBe(1);
+    expect(json.usage.prompt_tokens).toBe(9);
+    expect(out.headers.get('content-length')).toBeNull();
+  });
+
+  test('non-JSON body falls back to the original bytes (rebuilt, still readable)', async () => {
+    const wireBody = 'plain text, not json';
+    globalThis.fetch = (async () =>
+      new Response(wireBody, {
+        status: 200,
+        headers: { 'content-type': 'application/json' },
+      })) as unknown as typeof fetch;
+
+    const out = await __zeroEntropyCompatFetchForTests('https://api.zeroentropy.dev/v1/embeddings', {
+      method: 'POST',
+      body: JSON.stringify({ input: ['hello'] }),
+    });
+    // Body was consumed by the shim's single read; the fallback must
+    // rebuild a readable Response rather than return the drained original.
+    expect(await out.text()).toBe(wireBody);
+  });
+});

test/ai/zeroentropy-compat-fetch.test.ts

@@ -98,16 +98,18 @@ describe('zeroEntropyCompatFetch — OOM caps', () => {
     expect(src).toMatch(/MAX_ZEROENTROPY_RESPONSE_BYTES\s*=\s*256\s*\*\s*1024\s*\*\s*1024/);
   });
 
-  test('Layer 1: Content-Length pre-check before resp.clone().json()', async () => {
+  test('Layer 1: Content-Length pre-check before the body is read', async () => {
     const src = await Bun.file(GATEWAY_PATH).text();
     // Find the zeroEntropyCompatFetch block bounds, then assert ordering
-    // within it (mirroring the voyage cap test pattern).
+    // within it (mirroring the voyage cap test pattern). #1610 moved the
+    // body read from `resp.clone().json()` to a single `resp.text()` (bun
+    // < 1.1.27 truncates clone()d bodies, oven-sh/bun#6348).
     const zeFetchStart = src.indexOf('const zeroEntropyCompatFetch');
     expect(zeFetchStart).toBeGreaterThan(0);
-    const block = src.slice(zeFetchStart, zeFetchStart + 8000);
+    const block = src.slice(zeFetchStart, zeFetchStart + 9000);
 
     const preCheckIdx = block.indexOf("resp.headers.get('content-length')");
-    const jsonParseIdx = block.indexOf('await resp.clone().json()');
+    const jsonParseIdx = block.indexOf('const bodyText = await resp.text()');
     expect(preCheckIdx).toBeGreaterThan(0);
     expect(jsonParseIdx).toBeGreaterThan(0);
     // The pre-check MUST appear before the JSON parse — Voyage's lesson

test/cli-source-scope-hint.test.ts

@@ -0,0 +1,61 @@
+/**
+ * #1484 — invisible-miss hint. A bare `gbrain query` resolves to a single
+ * source (usually 'default'); on a multi-source brain a zero-hit run gave no
+ * signal that the answer might live in another source. sourceScopeHint
+ * returns the stderr hint exactly when: query/search op + zero results +
+ * no explicit scoping param + >1 registered source.
+ */
+
+import { describe, expect, test } from 'bun:test';
+import { sourceScopeHint } from '../src/cli.ts';
+import type { BrainEngine } from '../src/core/engine.ts';
+
+function fakeEngine(sourceCount: number, fail = false): BrainEngine {
+  return {
+    executeRaw: async () => {
+      if (fail) throw new Error('sources table missing');
+      return [{ n: sourceCount }];
+    },
+  } as unknown as BrainEngine;
+}
+
+describe('sourceScopeHint (#1484)', () => {
+  test('fires on a bare zero-hit query against a multi-source brain', async () => {
+    const hint = await sourceScopeHint('query', {}, 'default', fakeEngine(3), []);
+    expect(hint).toContain('3 sources');
+    expect(hint).toContain('"default"');
+    expect(hint).toContain('--source-id __all__');
+  });
+
+  test('fires for search too', async () => {
+    const hint = await sourceScopeHint('search', {}, 'wiki', fakeEngine(2), []);
+    expect(hint).toContain('"wiki"');
+  });
+
+  test('silent when results were found', async () => {
+    expect(await sourceScopeHint('query', {}, 'default', fakeEngine(3), [{ slug: 'a' }])).toBeNull();
+  });
+
+  test('silent when the caller scoped explicitly', async () => {
+    expect(await sourceScopeHint('query', { source_id: 'wiki' }, 'wiki', fakeEngine(3), [])).toBeNull();
+    expect(await sourceScopeHint('query', { source: 'wiki' }, 'wiki', fakeEngine(3), [])).toBeNull();
+    expect(await sourceScopeHint('query', { all_sources: true }, '__all__', fakeEngine(3), [])).toBeNull();
+  });
+
+  test('silent when the resolved scope is already __all__', async () => {
+    expect(await sourceScopeHint('query', {}, '__all__', fakeEngine(3), [])).toBeNull();
+  });
+
+  test('silent on a single-source brain', async () => {
+    expect(await sourceScopeHint('query', {}, 'default', fakeEngine(1), [])).toBeNull();
+  });
+
+  test('silent for non-search ops and non-array results', async () => {
+    expect(await sourceScopeHint('get_stats', {}, 'default', fakeEngine(3), [])).toBeNull();
+    expect(await sourceScopeHint('query', {}, 'default', fakeEngine(3), { rows: [] })).toBeNull();
+  });
+
+  test('best-effort: sources lookup failure returns null, never throws', async () => {
+    expect(await sourceScopeHint('query', {}, 'default', fakeEngine(3, true), [])).toBeNull();
+  });
+});

test/cycle/extract-atoms-synthesize-concepts.test.ts

@@ -17,7 +17,6 @@ import { runPhaseExtractAtoms, parseAtomsResponse } from '../../src/core/cycle/e
 import { runPhaseSynthesizeConcepts } from '../../src/core/cycle/synthesize-concepts.ts';
 import { resetPgliteState } from '../helpers/reset-pglite.ts';
 import type { ChatResult, ChatOpts } from '../../src/core/ai/gateway.ts';
-import type { BrainEngine } from '../../src/core/engine.ts';
 
 let engine: PGLiteEngine;
 
@@ -178,180 +177,6 @@ describe('v0.41 T5: runPhaseExtractAtoms via stubbed chat', () => {
     expect((result.details?.failures as unknown[]).length).toBe(1);
   });
 
-  // ── #2750: caller deadline bounds the phase ────────────────────────────
-
-  test('caller deadline aborts a hung chat before processing the next item', async () => {
-    let calls = 0;
-    const chat = async (opts: ChatOpts) => {
-      calls++;
-      return await new Promise<never>((_resolve, reject) => {
-        const signal = opts.abortSignal;
-        if (!signal) return reject(new Error('missing abort signal'));
-        if (signal.aborted) return reject(signal.reason);
-        signal.addEventListener('abort', () => reject(signal.reason), { once: true });
-      });
-    };
-    const started = Date.now();
-    const result = await runPhaseExtractAtoms(engine, {
-      _transcripts: [
-        { filePath: '/hung.txt', content: 'a', contentHash: 'hung-a' },
-        { filePath: '/never.txt', content: 'b', contentHash: 'hung-b' },
-      ],
-      _pages: [],
-      _chat: chat as typeof import('../../src/core/ai/gateway.ts').chat,
-      abortSignal: AbortSignal.timeout(25),
-    });
-    expect(Date.now() - started).toBeLessThan(2_000);
-    expect(calls).toBe(1);
-    expect(result.status).toBe('ok');
-    expect(result.details?.deadline_aborted).toBe(true);
-    expect(result.details?.atoms_extracted).toBe(0);
-    expect(result.details?.failures).toEqual([]);
-  });
-
-  test('billable chat usage is counted when the deadline fires as the response resolves', async () => {
-    const controller = new AbortController();
-    const chat = async (opts: ChatOpts): Promise<ChatResult> => {
-      controller.abort(new DOMException('deadline', 'TimeoutError'));
-      return stubChat(`[{"title":"late","atom_type":"insight","body":"b"}]`, {
-        input_tokens: 1_000,
-        output_tokens: 500,
-      })(opts);
-    };
-    const result = await runPhaseExtractAtoms(engine, {
-      _transcripts: [{ filePath: '/late.txt', content: 'a', contentHash: 'late' }],
-      _pages: [],
-      _chat: chat,
-      abortSignal: controller.signal,
-    });
-    expect(result.details?.deadline_aborted).toBe(true);
-    expect(Number(result.details?.estimated_spend_usd)).toBeGreaterThan(0);
-    expect(result.details?.atoms_extracted).toBe(0);
-  });
-
-  test('deadline after partial progress still writes receipt and incomplete rollup', async () => {
-    const controller = new AbortController();
-    let calls = 0;
-    let notifySecondChat!: () => void;
-    const secondChatStarted = new Promise<void>((resolve) => { notifySecondChat = resolve; });
-    const chat = async (opts: ChatOpts): Promise<ChatResult> => {
-      calls++;
-      if (calls === 1) {
-        return stubChat(`[{"title":"committed","atom_type":"insight","body":"b"}]`)(opts);
-      }
-      notifySecondChat();
-      return await new Promise<never>((_resolve, reject) => {
-        const signal = opts.abortSignal;
-        if (!signal) return reject(new Error('missing abort signal'));
-        signal.addEventListener('abort', () => reject(signal.reason), { once: true });
-      });
-    };
-
-    const pending = runPhaseExtractAtoms(engine, {
-      _transcripts: [
-        { filePath: '/committed.txt', content: 'a', contentHash: 'committed-a' },
-        { filePath: '/hung.txt', content: 'b', contentHash: 'hung-b' },
-      ],
-      _pages: [],
-      _chat: chat,
-      abortSignal: controller.signal,
-    });
-    await secondChatStarted;
-    controller.abort(new DOMException('deadline', 'TimeoutError'));
-    const result = await pending;
-
-    const atoms = await engine.executeRaw<{ n: number }>(
-      `SELECT COUNT(*)::int AS n FROM pages WHERE type = 'atom'`,
-    );
-    const receipts = await engine.executeRaw<{ n: number }>(
-      `SELECT COUNT(*)::int AS n FROM pages WHERE type = 'extract_receipt'`,
-    );
-    const rollups = await engine.executeRaw<{
-      cost_usd: string | number;
-      round_completed_count: string | number;
-    }>(
-      `SELECT cost_usd, round_completed_count
-         FROM extract_rollup_7d
-        WHERE kind = 'atoms' AND source_id = 'default'`,
-    );
-    expect(result.details?.deadline_aborted).toBe(true);
-    expect(atoms[0].n).toBe(1);
-    expect(receipts[0].n).toBe(1);
-    expect(Number(rollups[0].cost_usd)).toBeGreaterThan(0);
-    expect(Number(rollups[0].round_completed_count)).toBe(0);
-  });
-
-  test('bookkeeping runs on a fresh grace signal, not the fired work deadline', async () => {
-    const controller = new AbortController();
-    let putCalls = 0;
-    let receiptSignal: AbortSignal | undefined;
-    let rollupSignal: AbortSignal | undefined;
-    const signalAwareEngine = {
-      executeRaw: async (sql: string, _params?: unknown[], opts?: { signal?: AbortSignal }) => {
-        if (sql.includes('INSERT INTO extract_rollup_7d')) rollupSignal = opts?.signal;
-        return [];
-      },
-      putPage: async (_slug: string, _page: unknown, opts?: { signal?: AbortSignal }) => {
-        putCalls++;
-        if (putCalls === 1) {
-          // Atom write in flight; the work deadline fires before bookkeeping.
-          controller.abort(new DOMException('work deadline', 'TimeoutError'));
-        } else {
-          receiptSignal = opts?.signal;
-        }
-        return {};
-      },
-    } as unknown as BrainEngine;
-
-    const result = await runPhaseExtractAtoms(signalAwareEngine, {
-      _transcripts: [{ filePath: '/one.txt', content: 'a', contentHash: 'one' }],
-      _pages: [],
-      _chat: stubChat(`[{"title":"one","atom_type":"insight","body":"b"}]`),
-      abortSignal: controller.signal,
-    });
-
-    expect(result.details?.atoms_extracted).toBe(1);
-    expect(putCalls).toBe(2); // atom write + receipt write
-    expect(receiptSignal).toBeDefined();
-    expect(receiptSignal).not.toBe(controller.signal);
-    expect(receiptSignal?.aborted).toBe(false);
-    expect(rollupSignal).toBe(receiptSignal);
-  });
-
-  test('caller deadline cancels a hung atom write and stops the phase', async () => {
-    const controller = new AbortController();
-    let notifyWriteStarted!: () => void;
-    const writeStarted = new Promise<void>((resolve) => { notifyWriteStarted = resolve; });
-    let writeCalls = 0;
-    const signalAwareEngine = {
-      executeRaw: async () => [],
-      putPage: async (_slug: string, _page: unknown, opts?: { signal?: AbortSignal }) => {
-        writeCalls++;
-        notifyWriteStarted();
-        return await new Promise<never>((_resolve, reject) => {
-          const signal = opts?.signal;
-          if (!signal) return reject(new Error('missing abort signal'));
-          if (signal.aborted) return reject(signal.reason);
-          signal.addEventListener('abort', () => reject(signal.reason), { once: true });
-        });
-      },
-    } as unknown as BrainEngine;
-
-    const pending = runPhaseExtractAtoms(signalAwareEngine, {
-      _transcripts: [{ filePath: '/hung-write.txt', content: 'a', contentHash: 'hung-write' }],
-      _pages: [],
-      _chat: stubChat(`[{"title":"hung write","atom_type":"insight","body":"b"}]`),
-      abortSignal: controller.signal,
-    });
-    await writeStarted;
-    controller.abort(new DOMException('deadline', 'TimeoutError'));
-    const result = await pending;
-
-    expect(writeCalls).toBe(1);
-    expect(result.details?.deadline_aborted).toBe(true);
-    expect(result.details?.atoms_extracted).toBe(0);
-  });
-
   // v0.41.2.1 regression case (D9 #14 wording): with _pages:[] and same
   // _transcripts, all PRE-EXISTING PhaseResult.details fields match
   // pre-fix values byte-for-byte. The new fields (pages_processed,

test/extract-atoms-drain.test.ts

@@ -43,135 +43,26 @@ describe('runExtractAtomsDrain (issue #1678)', () => {
     expect(batches).toBe(3);
   });
 
-  it('stops at the wallclock window; remaining is unknown (no post-window count)', async () => {
-    // Each batch consumes 60ms of the 100ms window: two batches fit, the
-    // third boundary check sees 120 ≥ 100 and stops. #2750: after the window
-    // elapses the final countRemaining is SKIPPED (it would overrun the
-    // window), so remaining reports null.
-    let now = 0;
+  it('stops at the wallclock window with remaining > 0', async () => {
+    // SYNC stepping clock: now() #1 sets deadline (0+100=100); the while-check
+    // then sees 50, 50 (two batches), then 999999 → past deadline → stop.
+    const times = [0, 50, 50, 999_999];
+    let ti = 0;
+    const now = () => times[Math.min(ti++, times.length - 1)];
     const result = await runExtractAtomsDrain(
       {
         withLock: passThroughLock,
         countRemaining: async () => 5, // never drains
-        runBatch: async () => {
-          now += 60;
-          return { extracted: 1, skipped: 0 };
-        },
-        now: () => now,
+        runBatch: async () => ({ extracted: 1, skipped: 0 }),
+        now,
       },
       { windowMs: 100 },
     );
     expect(result.stopped).toBe('window');
-    expect(result.remaining).toBeNull();
+    expect(result.remaining).toBe(5);
     expect(result.batches).toBe(2);
   });
 
-  it('passes one drain-level deadline signal into count and batch', async () => {
-    const seen: AbortSignal[] = [];
-    const controller = new AbortController();
-    let now = 0;
-    const result = await runExtractAtomsDrain(
-      {
-        withLock: passThroughLock,
-        countRemaining: async (signal) => {
-          seen.push(signal);
-          return 5;
-        },
-        runBatch: async (signal) => {
-          seen.push(signal);
-          now = 100;
-          return { extracted: 1, skipped: 0 };
-        },
-        now: () => now,
-      },
-      { windowMs: 100, abortSignal: controller.signal },
-    );
-    expect(result.stopped).toBe('window');
-    expect(result.batches).toBe(1);
-    expect(seen.length).toBe(2);
-    expect(seen[0]).toBe(seen[1]);
-    // Combined (timeout + external) signal, not the raw external one.
-    expect(seen[0]).not.toBe(controller.signal);
-  });
-
-  it('aborts a hung backlog count at the window deadline and releases the lock', async () => {
-    let released = false;
-    const result = await runExtractAtomsDrain(
-      {
-        withLock: async (work) => {
-          try { return await work(); }
-          finally { released = true; }
-        },
-        // Hangs until the drain's real-time deadline signal fires (10ms).
-        countRemaining: (signal) => new Promise((_resolve, reject) => {
-          signal.addEventListener('abort', () => reject(signal.reason), { once: true });
-        }),
-        runBatch: async () => ({ extracted: 0, skipped: 0 }),
-        now: () => 0, // injected clock never advances — the SIGNAL must save us
-      },
-      { windowMs: 10 },
-    );
-    expect(result.stopped).toBe('window');
-    expect(result.remaining).toBeNull();
-    expect(released).toBe(true);
-  });
-
-  it('rethrows external cancellation after releasing the lock', async () => {
-    const controller = new AbortController();
-    let released = false;
-    const pending = runExtractAtomsDrain(
-      {
-        withLock: async (work) => {
-          try { return await work(); }
-          finally { released = true; }
-        },
-        countRemaining: (signal) => new Promise((_resolve, reject) => {
-          signal.addEventListener('abort', () => reject(signal.reason), { once: true });
-        }),
-        runBatch: async () => ({ extracted: 0, skipped: 0 }),
-        now: () => 0,
-      },
-      { windowMs: 1_000_000, abortSignal: controller.signal },
-    );
-    controller.abort(new DOMException('worker timeout', 'AbortError'));
-    await expect(pending).rejects.toThrow('worker timeout');
-    expect(released).toBe(true);
-  });
-
-  it('classifies a deadline-exhausted zero-progress batch as window, not no_progress', async () => {
-    let now = 0;
-    const result = await runExtractAtomsDrain(
-      {
-        withLock: passThroughLock,
-        countRemaining: async () => 5,
-        runBatch: async () => {
-          now = 100; // batch consumed the whole window and returned nothing
-          return { extracted: 0, skipped: 0 };
-        },
-        now: () => now,
-      },
-      { windowMs: 100 },
-    );
-    expect(result.stopped).toBe('window');
-    expect(result.batches).toBe(1);
-  });
-
-  it('bounds a hung lock acquisition with the drain deadline signal', async () => {
-    const started = Date.now();
-    await expect(runExtractAtomsDrain(
-      {
-        withLock: (_work, signal) => new Promise((_resolve, reject) => {
-          signal.addEventListener('abort', () => reject(signal.reason), { once: true });
-        }),
-        countRemaining: async () => 1,
-        runBatch: async () => ({ extracted: 0, skipped: 0 }),
-        now: Date.now,
-      },
-      { windowMs: 10 },
-    )).rejects.toThrow();
-    expect(Date.now() - started).toBeLessThan(1_000);
-  });
-
   it('stops on a zero-progress batch (no hot loop)', async () => {
     let batches = 0;
     const result = await runExtractAtomsDrain(
@@ -242,17 +133,4 @@ describe('shared wiring helper holds the cycle lock (5A)', () => {
     expect(src).toContain('cycleLockIdFor(opts.sourceId)');
     expect(src).toContain('withRefreshingLock(engine, lockId');
   });
-
-  // #2750: the deadline signal must reach the phase, the backlog count, AND
-  // the lock wrapper — and the transcript path (brainDir) must stay wired
-  // exactly as the routine callers expect (PR #2752 takeover reverted its
-  // unsanctioned transcript-suppression scope change).
-  it('threads the drain deadline signal through phase, count, and lock', () => {
-    const jobsSrc = readFileSync(join(import.meta.dir, '../src/commands/jobs.ts'), 'utf8');
-    expect(src).toContain('abortSignal: signal');
-    expect(src).toContain('countExtractAtomsBacklog(engine, extractionSourceId, signal)');
-    expect(src).toContain('brainDir: opts.brainDir');
-    expect(src).not.toContain('_transcripts');
-    expect(jobsSrc).toContain('abortSignal: job.signal');
-  });
 });

test/fixtures/supervisor-runner.ts

@@ -24,18 +24,15 @@ import type { BrainEngine } from '../../src/core/engine.ts';
 // Mock engine: healthCheck() calls engine.executeRaw; return empty rows so
 // the query path exercises without needing Postgres.
 //
-// #1849: start() acquires the queue-scoped DB singleton lock via
-// tryAcquireDbLock. #2750 routed the acquire upsert through engine.executeRaw
-// (signal-boundable) and release through engine.executeRawDirect, so the
-// stub returns a single row from the lock upsert (length 1 → acquired) and
-// empty rows everywhere else. Each spawned runner is a fresh process, so
-// there's no cross-test lock state to clean up.
+// #1849: start() now acquires the queue-scoped DB singleton lock via
+// tryAcquireDbLock, which uses the postgres `sql` tagged-template escape hatch.
+// The stub returns a single row from every call so acquire succeeds (length 1
+// → acquired) and refresh/release are no-ops. Each spawned runner is a fresh
+// process, so there's no cross-test lock state to clean up.
 const sqlStub = (..._args: unknown[]) => Promise.resolve([{ id: 'supervisor-lock' }]);
 const mockEngine: Partial<BrainEngine> = {
   kind: 'postgres' as const,
-  executeRaw: async (query: string) =>
-    query.includes('gbrain_cycle_locks') ? [{ id: 'supervisor-lock' }] : [],
-  executeRawDirect: async () => [],
+  executeRaw: async () => [],
   sql: sqlStub,
 } as unknown as BrainEngine;
 

test/hybrid-vector-arm-warn.serial.test.ts

@@ -0,0 +1,77 @@
+/**
+ * #1626 — hybridSearch's text-vector arm must not fail DARK.
+ *
+ * The arm only runs when the embedding provider probed available, so a throw
+ * inside it (embed timeout, transient pooler error on searchVector) is a real
+ * failure. Pre-fix, a bare `catch {}` swallowed it and the run silently
+ * collapsed to keyword-only — under `--source __all__` on a strained pooler
+ * that read as a non-deterministic "No results". The fix logs the swallowed
+ * reason via warnOncePerProcess while keeping the keyword fallback.
+ */
+
+import { afterAll, beforeAll, describe, expect, test } from 'bun:test';
+import { PGLiteEngine } from '../src/core/pglite-engine.ts';
+import { hybridSearch } from '../src/core/search/hybrid.ts';
+import {
+  __setEmbedTransportForTests,
+  configureGateway,
+  resetGateway,
+} from '../src/core/ai/gateway.ts';
+import { _resetWarnOnceForTests } from '../src/core/utils.ts';
+
+let engine: PGLiteEngine;
+const origWarn = console.warn;
+
+beforeAll(async () => {
+  // Pin the gateway to OpenAI with a stub key (put-page-provenance pattern):
+  // embed() runs instantiateEmbedding — which requires OPENAI_API_KEY — BEFORE
+  // the stubbed transport is reached. Without this, a keyless CI environment
+  // throws the config error instead of the transport's, and the assertion on
+  // the swallowed reason fails. The key never leaves the process.
+  configureGateway({
+    embedding_model: 'openai:text-embedding-3-large',
+    embedding_dimensions: 1536,
+    env: { ...process.env, OPENAI_API_KEY: process.env.OPENAI_API_KEY || 'sk-test-stub' },
+  });
+  engine = new PGLiteEngine();
+  await engine.connect({});
+  await engine.initSchema();
+  await engine.putPage('people/alice-example', {
+    type: 'person',
+    title: 'Alice Example',
+    compiled_truth: 'Alice Example is a test person for the vector-arm warn test.',
+  });
+});
+
+afterAll(async () => {
+  console.warn = origWarn;
+  __setEmbedTransportForTests(null);
+  resetGateway();
+  await engine.disconnect();
+});
+
+describe('hybridSearch vector-arm failure telemetry (#1626)', () => {
+  test('embed failure logs the swallowed reason and falls back to keyword', async () => {
+    _resetWarnOnceForTests();
+    // Installing a transport makes isAvailable('embedding') true (test-seam
+    // fast path), so the vector arm RUNS — and then throws.
+    __setEmbedTransportForTests(() => {
+      throw new Error('pooler exploded mid-fanout');
+    });
+    const warnings: string[] = [];
+    console.warn = (...args: unknown[]) => {
+      warnings.push(args.map(String).join(' '));
+    };
+    try {
+      const results = await hybridSearch(engine, 'alice');
+      // Keyword fallback still returns results — fail-open preserved.
+      expect(results.some((r) => r.slug === 'people/alice-example')).toBe(true);
+    } finally {
+      console.warn = origWarn;
+      __setEmbedTransportForTests(null);
+    }
+    const armWarnings = warnings.filter((w) => w.includes('vector arm failed'));
+    expect(armWarnings).toHaveLength(1);
+    expect(armWarnings[0]).toContain('pooler exploded mid-fanout');
+  });
+});

test/postgres-execute-raw-direct.test.ts

@@ -98,39 +98,14 @@ describe('PostgresEngine.executeRawDirect — routing decision (PR #1816)', () =
   });
 
   test('already-aborted signal short-circuits with AbortError before routing the query', async () => {
-    let unsafeCalls = 0;
-    let ddlCalls = 0;
-    const readConn: FakeSql = { unsafe: async () => { unsafeCalls++; return []; } };
+    const readConn = fakeSql('read');
     const directConn = fakeSql('direct');
     const engine = makeEngine({ dualPoolActive: true, readConn, directConn });
-    const e = engine as unknown as { connectionManager: { ddl: () => Promise<FakeSql> } };
-    e.connectionManager.ddl = async () => { ddlCalls++; return directConn; };
 
     const ac = new AbortController();
     ac.abort();
     await expect(
       engine.executeRawDirect('UPDATE minion_jobs SET x=1', [], { signal: ac.signal }),
     ).rejects.toThrow(/abort/i);
-    // #2750: short-circuits BEFORE pool routing — no ddl(), no unsafe().
-    expect(ddlCalls).toBe(0);
-    expect(unsafeCalls).toBe(0);
-  });
-
-  test('#2750: signal bounds a stalled direct-pool acquisition before unsafe starts', async () => {
-    let unsafeCalls = 0;
-    const readConn: FakeSql = { unsafe: async () => { unsafeCalls++; return []; } };
-    const directConn = fakeSql('direct');
-    const engine = makeEngine({ dualPoolActive: true, readConn, directConn });
-    const e = engine as unknown as { connectionManager: { ddl: () => Promise<FakeSql> } };
-    e.connectionManager.ddl = () => new Promise<FakeSql>(() => {}); // pooler exhausted: never resolves
-
-    const started = Date.now();
-    await expect(engine.executeRawDirect(
-      'DELETE FROM gbrain_cycle_locks',
-      [],
-      { signal: AbortSignal.timeout(10) },
-    )).rejects.toThrow(/abort/i);
-    expect(Date.now() - started).toBeLessThan(1_000);
-    expect(unsafeCalls).toBe(0);
   });
 });

test/search-op-source-scope.test.ts

@@ -0,0 +1,87 @@
+/**
+ * #1484 follow-up — the `search` op must honor per-call `source_id` /
+ * `all_sources` through the canonical fail-closed resolver
+ * (resolveRequestedScope), exactly like `query` does.
+ *
+ * Pre-fix, `search` had no source_id param at all: the zero-hit CLI hint
+ * advised "retry with --source-id __all__", the flag parsed into params,
+ * NOTHING consumed it, and the retry silently re-ran the same single-source
+ * search — an invisible false negative (and the retry's params.source_id
+ * suppressed the hint, so the user got no second warning).
+ */
+
+import { describe, expect, test } from 'bun:test';
+import { operationsByName } from '../src/core/operations.ts';
+import type { OperationContext } from '../src/core/operations.ts';
+import type { BrainEngine } from '../src/core/engine.ts';
+
+const searchOp = operationsByName['search'];
+
+/** Fake engine: keyword-only config so the handler's scope goes straight to
+ *  searchKeyword, where we capture the opts it was called with. */
+function makeCtx(remote: boolean, allowedSources?: string[]) {
+  const captured: { opts?: Record<string, unknown> } = {};
+  const engine = {
+    getConfig: async (key: string) => (key === 'search.mcp_keyword_only' ? 'true' : null),
+    searchKeyword: async (_q: string, opts: Record<string, unknown>) => {
+      captured.opts = opts;
+      return [];
+    },
+  } as unknown as BrainEngine;
+  const ctx = {
+    engine,
+    config: { engine: 'pglite' },
+    logger: { info: () => {}, warn: () => {}, error: () => {} },
+    dryRun: false,
+    remote,
+    sourceId: 'default',
+    ...(allowedSources ? { auth: { allowedSources } } : {}),
+  } as unknown as OperationContext;
+  return { ctx, captured };
+}
+
+describe('search op per-call source scope (#1484 follow-up)', () => {
+  test('op declares source_id + all_sources params (the CLI hint advises them)', () => {
+    expect(searchOp.params.source_id).toBeDefined();
+    expect(searchOp.params.all_sources).toBeDefined();
+  });
+
+  test('default: scopes to ctx.sourceId', async () => {
+    const { ctx, captured } = makeCtx(false);
+    await searchOp.handler(ctx, { query: 'x' });
+    expect(captured.opts?.sourceId).toBe('default');
+  });
+
+  test("local + source_id '__all__' spans the whole brain (no source filter)", async () => {
+    const { ctx, captured } = makeCtx(false);
+    await searchOp.handler(ctx, { query: 'x', source_id: '__all__' });
+    expect(captured.opts?.sourceId).toBeUndefined();
+    expect(captured.opts?.sourceIds).toBeUndefined();
+  });
+
+  test('local + all_sources=true spans the whole brain', async () => {
+    const { ctx, captured } = makeCtx(false);
+    await searchOp.handler(ctx, { query: 'x', all_sources: true });
+    expect(captured.opts?.sourceId).toBeUndefined();
+    expect(captured.opts?.sourceIds).toBeUndefined();
+  });
+
+  test('explicit source_id wins over ctx.sourceId', async () => {
+    const { ctx, captured } = makeCtx(false);
+    await searchOp.handler(ctx, { query: 'x', source_id: 'wiki' });
+    expect(captured.opts?.sourceId).toBe('wiki');
+  });
+
+  test("remote + '__all__' collapses to the caller's grant (fail-closed)", async () => {
+    const { ctx, captured } = makeCtx(true, ['wiki', 'essays']);
+    await searchOp.handler(ctx, { query: 'x', source_id: '__all__' });
+    expect(captured.opts?.sourceIds).toEqual(['wiki', 'essays']);
+  });
+
+  test('remote + out-of-grant source_id is denied', async () => {
+    const { ctx } = makeCtx(true, ['wiki']);
+    await expect(searchOp.handler(ctx, { query: 'x', source_id: 'secrets' })).rejects.toThrow(
+      /outside your granted sources/,
+    );
+  });
+});

test/voyage-response-cap.test.ts

@@ -34,7 +34,7 @@ describe('v0.31.8 — voyage Content-Length pre-check + per-item cap', () => {
     expect(source).toMatch(/MAX_VOYAGE_RESPONSE_BYTES\s*=\s*256\s*\*\s*1024\s*\*\s*1024/);
   });
 
-  test('Layer 1: Content-Length pre-check fires BEFORE resp.clone().json() (D10 OOM defense)', async () => {
+  test('Layer 1: Content-Length pre-check fires BEFORE the body is read (D10 OOM defense)', async () => {
     const source = await Bun.file(new URL('../src/core/ai/gateway.ts', import.meta.url)).text();
     // Anchor relative to the post-fetch handler block. The function declaration
     // contains an OUTBOUND request body section earlier; we want to verify
@@ -47,8 +47,10 @@ describe('v0.31.8 — voyage Content-Length pre-check + per-item cap', () => {
     // doesn't pin to comment text.
     const preCheckIdx = inboundBlock.indexOf("resp.headers.get('content-length')");
     // Use the full lvalue assignment so the match doesn't accidentally hit
-    // comment text that mentions `await resp.clone().json()` for context.
-    const jsonParseIdx = inboundBlock.indexOf('const json: any = await resp.clone().json()');
+    // comment text that mentions the body read for context. (#1610 moved the
+    // read from `resp.clone().json()` to a single `resp.text()` — bun <
+    // 1.1.27 truncates clone()d bodies, oven-sh/bun#6348.)
+    const jsonParseIdx = inboundBlock.indexOf('const bodyText = await resp.text()');
     expect(preCheckIdx).toBeGreaterThan(0);
     expect(jsonParseIdx).toBeGreaterThan(0);
     // The pre-check MUST appear before the JSON parse — otherwise the OOM