fix(search,embed): normalize / in FTS queries; CPU-safe defaults for local embedding endpoints

Two backlog fixes:

1. Takeover of #2380 (search): Postgres' default text-search parser
   classifies foo/bar as a single file-alias token mapped to the simple
   dictionary, so websearch_to_tsquery produces one un-stemmed lexeme
   that never matches indexed text — slash-containing queries bypassed
   FTS AND semantics (zero primary hits, OR-fallback results only).
   normalizeKeywordQuery() replaces / with whitespace before parse.
   Beyond the original PR: also routes searchTitles through the
   normalizer (the PR only covered the two chunk arms), applies it in
   BOTH engines, and drops the stray node_modules symlink from the diff.

2. Fixes #2552 (embed): cloud-tuned embedding defaults silently wedge
   CPU-only Ollama boxes. The ollama recipe now declares a conservative
   static batch cap (max_batch_tokens 4096 x chars_per_token 2, ~8K
   chars/request) instead of no_batch_cap — Ollama never returns a
   recognizable token-limit error, so the recursive-halving safety net
   can't fire. Bulk embed auto-caps worker fan-out at 2 for local
   endpoints (ollama / llama-server / localhost base URL) unless
   GBRAIN_EMBED_CONCURRENCY is set explicitly, and gbrain doctor grows
   an embed_concurrency check that warns when an explicit override fans
   out against a local endpoint.

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

src/commands/doctor.ts

@@ -820,6 +820,10 @@ 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.
@@ -3815,6 +3819,61 @@ 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

@@ -1,5 +1,6 @@
 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';
@@ -176,6 +177,31 @@ 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
@@ -677,10 +703,8 @@ 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.
-  const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
-  const CONCURRENCY = staleOpts?.paceMaxConcurrency
-    ? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
-    : BASE_CONCURRENCY;
+  // #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
+  const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
 
   async function embedOnePage(page: typeof pages[number]) {
     // #1737: bail before doing any work for this page if the run was aborted.
@@ -855,10 +879,8 @@ 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.
-  const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
-  const CONCURRENCY = staleOpts?.paceMaxConcurrency
-    ? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
-    : BASE_CONCURRENCY;
+  // #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
+  const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
   const pacer = staleOpts?.pacer ?? createNoopPacer();
 
   // D3 + D3a + D8: wall-clock budget. 30 min default; env override.

src/core/ai/gateway.ts

@@ -683,6 +683,33 @@ 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

@@ -29,9 +29,17 @@ 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',
-      // 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,
+      // #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,
     },
   },
   setup_hint: 'Install Ollama from https://ollama.ai, then `ollama pull nomic-embed-text` and `ollama serve`.',

src/core/doctor-categories.ts

@@ -141,6 +141,7 @@ 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

@@ -65,6 +65,7 @@ import {
   EmbeddingColumnNotRegisteredError,
 } from './search/embedding-column.ts';
 import { hasCJK, escapeLikePattern } from './cjk.ts';
+import { normalizeKeywordQuery } from './search/keyword.ts';
 
 type PGLiteDB = PGlite;
 
@@ -1591,7 +1592,11 @@ export class PGLiteEngine implements BrainEngine {
     }
 
     // v0.20.0 Cathedral II Layer 10 C1/C2: language + symbol-kind filters.
-    const params: unknown[] = [query, innerLimit, limit, offset];
+    // Normalize the FTS query so `/` is split into separate words before
+    // websearch_to_tsquery parses it; Postgres' default parser otherwise
+    // treats `foo/bar` as a single `file`-alias token that never matches
+    // indexed text. See normalizeKeywordQuery in ./search/keyword.ts.
+    const params: unknown[] = [normalizeKeywordQuery(query), innerLimit, limit, offset];
     let extraFilter = '';
     if (opts?.language) {
       params.push(opts.language);
@@ -1713,7 +1718,11 @@ export class PGLiteEngine implements BrainEngine {
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
 
-    const params: unknown[] = [query, limit, offset];
+    // Normalize the FTS query so `/` is split into separate words before
+    // websearch_to_tsquery parses it; Postgres' default parser otherwise
+    // treats `foo/bar` as a single `file`-alias token that never matches
+    // indexed text. See normalizeKeywordQuery in ./search/keyword.ts.
+    const params: unknown[] = [normalizeKeywordQuery(query), limit, offset];
     let extraFilter = '';
     if (opts?.type) {
       params.push(opts.type);
@@ -1962,7 +1971,11 @@ export class PGLiteEngine implements BrainEngine {
       });
     }
 
-    const params: unknown[] = [query, limit, offset];
+    // Normalize the FTS query so `/` is split into separate words before
+    // websearch_to_tsquery parses it; Postgres' default parser otherwise
+    // treats `foo/bar` as a single `file`-alias token that never matches
+    // indexed text. See normalizeKeywordQuery in ./search/keyword.ts.
+    const params: unknown[] = [normalizeKeywordQuery(query), limit, offset];
     let extraFilter = '';
     if (opts?.language) {
       params.push(opts.language);

src/core/postgres-engine.ts

@@ -67,6 +67,7 @@ import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.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';
+import { normalizeKeywordQuery } from './search/keyword.ts';
 
 function escapeSqlStringLiteral(value: string): string {
   return value.replace(/'/g, "''");
@@ -1691,7 +1692,11 @@ export class PostgresEngine implements BrainEngine {
     const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
     const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
 
-    const params: unknown[] = [query];
+    // Normalize the FTS query so `/` is split into separate words before
+    // websearch_to_tsquery parses it; Postgres' default parser otherwise
+    // treats `foo/bar` as a single `file`-alias token that never matches
+    // indexed text. See normalizeKeywordQuery in ./search/keyword.ts.
+    const params: unknown[] = [normalizeKeywordQuery(query)];
     let typeClause = '';
     if (type) {
       params.push(type);
@@ -1864,7 +1869,11 @@ export class PostgresEngine implements BrainEngine {
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
 
-    const params: unknown[] = [query];
+    // Normalize the FTS query so `/` is split into separate words before
+    // websearch_to_tsquery parses it; Postgres' default parser otherwise
+    // treats `foo/bar` as a single `file`-alias token that never matches
+    // indexed text. See normalizeKeywordQuery in ./search/keyword.ts.
+    const params: unknown[] = [normalizeKeywordQuery(query)];
     let typeClause = '';
     if (opts?.type) {
       params.push(opts.type);
@@ -2000,7 +2009,11 @@ export class PostgresEngine implements BrainEngine {
     const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
     const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
 
-    const params: unknown[] = [query];
+    // Normalize the FTS query so `/` is split into separate words before
+    // websearch_to_tsquery parses it; Postgres' default parser otherwise
+    // treats `foo/bar` as a single `file`-alias token that never matches
+    // indexed text. See normalizeKeywordQuery in ./search/keyword.ts.
+    const params: unknown[] = [normalizeKeywordQuery(query)];
     let typeClause = '';
     if (type) {
       params.push(type);

src/core/search/keyword.ts

@@ -1,6 +1,20 @@
 import type { BrainEngine } from '../engine.ts';
 import type { SearchResult, SearchOpts } from '../types.ts';
 
+// Postgres' default text-search parser classifies `foo/bar` as a single
+// `file`-alias token. Under the english config that alias maps to the
+// `simple` dictionary, so `websearch_to_tsquery('english', 'foo/bar')`
+// produces the single lexeme `'foo/bar'`. That lexeme never matches indexed
+// text whose `to_tsvector('english', …)` split on the slash, so any query
+// containing `/` silently returns zero FTS hits — e.g. pasting a meeting
+// title like `Author1/Author2 - Topic`. Replacing `/` with whitespace breaks
+// the file-alias token into ordinary `asciiword`s, which then stem and match
+// through the english dictionary the same way a manually-despaced query
+// does. The semantic / vector path is unaffected.
+export function normalizeKeywordQuery(query: string): string {
+  return query.replace(/\//g, ' ').replace(/\s+/g, ' ').trim();
+}
+
 export async function keywordSearch(
   engine: BrainEngine,
   query: string,

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('Ollama, LiteLLM, llama-server all declare no_batch_cap: true', () => {
-    for (const id of ['ollama', 'litellm', 'llama-server']) {
+  test('LiteLLM and llama-server declare no_batch_cap: true', () => {
+    for (const id of ['litellm', 'llama-server']) {
       const r = getRecipe(id);
       expect(r, `${id} not registered`).toBeDefined();
       expect(
@@ -39,6 +39,18 @@ 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/embed-local-endpoint.serial.test.ts

@@ -0,0 +1,118 @@
+/**
+ * #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

@@ -216,6 +216,49 @@ 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('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