fix(search): match both slash-split and literal slash forms in FTS queries (#2380 review)

Review finding on the normalize-only approach: Postgres' text-search
parser emits the joined file-alias lexeme on the INDEX side too
(to_tsvector('english','acme/widget') -> 'acme/widget'), so replacing
'/' with whitespace in the query made documents containing the literal
slash form (file paths, URLs, pasted titles) unreachable — the split-word
AND pass can't match the joined lexeme and the OR fallback can't either.
Pre-fix, those exact-form queries DID match.

Replace the TS-side normalizeKeywordQuery with buildWebsearchQueryExpr
in sql-ranking.ts (shared by both engines, keeping them in lockstep): a
slash-bearing query now binds the raw text once and matches
(websearch_to_tsquery(translate($1,'/',' ')) || websearch_to_tsquery($1))
— split-word prose AND literal slash forms alike. Slash-free queries keep
the byte-identical single-parse SQL and identical ts_rank.

New regression test pins the literal-slash arm (verified failing under
the normalize-only expression); the two AND-vs-OR slash tests still pass.

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

docs/tutorials/company-brain.md

@@ -223,16 +223,14 @@ export GBRAIN_REMOTE_CLIENT_ID=<Alice's client_id>
 export GBRAIN_REMOTE_CLIENT_SECRET=<Alice's client_secret>
 export GBRAIN_REMOTE_MCP_URL=https://brain.acme-co.com/mcp
 
-gbrain search "performance review"
+gbrain search "performance review" --remote
 ```
 
-(On a thin-client install every shared op routes through the remote MCP server automatically — no flag needed. The env vars select whose credentials the call uses.)
-
 Alice should see results only from `customers` and `shared`. The performance-review notes live in `internal`, which she's not scoped to read. She shouldn't see them.
 
 ```bash
 # Terminal 2, as Bob (export his credentials similarly)
-gbrain search "performance review"
+gbrain search "performance review" --remote
 ```
 
 Bob should see the performance-review notes from `internal`, plus anything related from `shared`. He shouldn't see anything that lives only in `customers`.
@@ -516,7 +514,7 @@ The first sync embeds every page, which takes time. Check `gbrain sources status
 
 ### "I see a page I shouldn't see"
 
-This shouldn't happen, but if you suspect it, run `gbrain search <query> --json` as the constrained client (thin-client install, with the client's `GBRAIN_REMOTE_*` env exported) and inspect the `source_id` field on every returned result. Every row should be in the client's `--federated-read` set. If one isn't, file an issue with the exact slug and source IDs.
+This shouldn't happen, but if you suspect it, run `gbrain search <query> --remote --json` as the constrained client and inspect the `source_id` field on every returned result. Every row should be in the client's `--federated-read` set. If one isn't, file an issue with the exact slug and source IDs.
 
 ### "The synthesized answer is wrong"
 

src/cli.ts

@@ -464,11 +464,7 @@ async function main() {
     // routed path. Date → ISO string; bigint → string (postgres.js shape);
     // Buffer → object. Microsecond-cost; eliminates a whole drift bug class.
     const result = JSON.parse(JSON.stringify(rawResult, bigintToStringReplacer));
-    // #380 pass-through: `--json` (undeclared on most ops, promised by docs)
-    // emits the raw op result instead of the human formatter.
-    const output = params.json === true
-      ? JSON.stringify(result, null, 2) + '\n'
-      : formatResult(op.name, result);
+    const output = formatResult(op.name, result);
     if (output) process.stdout.write(output);
   } catch (e: unknown) {
     // v0.42.20.0 (codex D4): on error, set exitCode + return so the `finally`
@@ -551,10 +547,7 @@ async function runThinClientRouted(
       signal: sigintController.signal,
     });
     const result = unpackToolResult(raw);
-    // #380: same --json seam as the local-engine path (renderer parity).
-    const output = params.json === true
-      ? JSON.stringify(result, null, 2) + '\n'
-      : formatResult(op.name, result);
+    const output = formatResult(op.name, result);
     if (output) process.stdout.write(output);
   } catch (e: unknown) {
     if (e instanceof RemoteMcpError) {
@@ -764,28 +757,10 @@ export function resolveQueryImage(
   return { path: imagePath, base64, mime };
 }
 
-/**
- * #380: undeclared flags that are honored DOWNSTREAM of parseOpArgs and must
- * keep passing through when unknown flags become hard errors:
- *   - source     → makeContext's resolveSourceId (the --source axis)
- *   - brain      → the mount/brain routing axis (docs promise the flag)
- *   - dry_run    → makeContext's ctx.dryRun (ops without a declared dry_run)
- *   - json       → raw-JSON output seam (local + thin-client paths)
- */
-const PASSTHROUGH_VALUE_FLAGS = new Set(['source', 'brain']);
-const PASSTHROUGH_BOOL_FLAGS = new Set(['dry_run', 'json']);
-
 export function parseOpArgs(op: Operation, args: string[]): Record<string, unknown> {
   const params: Record<string, unknown> = {};
   const positional = op.cliHints?.positional || [];
   let posIdx = 0;
-  const cliName = op.cliHints?.name || op.name;
-  const MAX_STDIN = 5_000_000; // 5MB cap, shared by stdin and --file
-  // #380: `--file <path>` fills the op's declared stdin param (put's `content`)
-  // from a file. Driven by cliHints.stdin — no per-op hard-coding — and
-  // disabled when the op declares a real `file` param of its own.
-  const fileParam = op.cliHints?.stdin && !op.params.file ? op.cliHints.stdin : undefined;
-  let filePath: string | undefined;
 
   for (let i = 0; i < args.length; i++) {
     const arg = args[i];
@@ -799,42 +774,12 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
         }
       }
       const key = arg.slice(2).replace(/-/g, '_');
-      if (fileParam && key === 'file') {
-        if (i + 1 >= args.length) {
-          console.error(`Error: ${arg} requires a value.`);
-          process.exit(1);
-        }
-        filePath = args[++i];
-        continue;
-      }
       const paramDef = op.params[key];
-      if (!paramDef) {
-        if (PASSTHROUGH_BOOL_FLAGS.has(key)) {
-          params[key] = true;
-          continue;
-        }
-        if (PASSTHROUGH_VALUE_FLAGS.has(key)) {
-          if (i + 1 >= args.length) {
-            console.error(`Error: ${arg} requires a value.`);
-            process.exit(1);
-          }
-          params[key] = args[++i];
-          continue;
-        }
-        // #380: unknown flags were silently swallowed into params, so typos
-        // like `put --file` created empty pages instead of erroring.
-        console.error(`Unknown option for gbrain ${cliName}: ${arg}`);
-        console.error(`Run 'gbrain ${cliName} --help' for valid flags.`);
-        process.exit(1);
-      }
-      if (paramDef.type === 'boolean') {
+      if (paramDef?.type === 'boolean') {
         params[key] = true;
       } else if (i + 1 < args.length) {
         params[key] = args[++i];
-        if (paramDef.type === 'number') params[key] = Number(params[key]);
-      } else {
-        console.error(`Error: ${arg} requires a value.`);
-        process.exit(1);
+        if (paramDef?.type === 'number') params[key] = Number(params[key]);
       }
     } else if (posIdx < positional.length) {
       const key = positional[posIdx++];
@@ -843,30 +788,10 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
     }
   }
 
-  // #380: resolve --file AFTER the loop so --file/--content conflicts are
-  // caught in either order.
-  if (filePath !== undefined && fileParam) {
-    if (params[fileParam] !== undefined) {
-      console.error(`Error: use only one of --file, --${fileParam}, or stdin for gbrain ${cliName}.`);
-      process.exit(1);
-    }
-    let fileContent: string;
-    try {
-      fileContent = readFileSync(filePath, 'utf-8');
-    } catch (e) {
-      console.error(`Error: cannot read --file ${filePath}: ${e instanceof Error ? e.message : String(e)}`);
-      process.exit(1);
-    }
-    if (Buffer.byteLength(fileContent, 'utf-8') > MAX_STDIN) {
-      console.error(`Error: file content exceeds ${MAX_STDIN} bytes. Split into smaller inputs.`);
-      process.exit(1);
-    }
-    params[fileParam] = fileContent;
-  }
-
   // Read stdin for content params
   if (op.cliHints?.stdin && !params[op.cliHints.stdin] && !process.stdin.isTTY) {
     const stdinContent = readFileSync(0, 'utf-8');
+    const MAX_STDIN = 5_000_000; // 5MB
     if (Buffer.byteLength(stdinContent, 'utf-8') > MAX_STDIN) {
       console.error(`Error: stdin content exceeds ${MAX_STDIN} bytes. Split into smaller inputs.`);
       process.exit(1);
@@ -2328,10 +2253,6 @@ export function printOpHelp(op: Operation, invokedName?: string) {
       const prefix = isPos ? `  <${key}>` : `  --${key.replace(/_/g, '-')}`;
       console.log(`${prefix.padEnd(28)} ${def.description || ''}${req}`);
     }
-    // #380: ops that read stdin also accept --file <path> (parseOpArgs).
-    if (op.cliHints?.stdin && !op.params.file) {
-      console.log(`${'  --file <path>'.padEnd(28)} Read ${op.cliHints.stdin} from a file (alternative to --${op.cliHints.stdin} or stdin)`);
-    }
   }
 }
 

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/operations.ts

@@ -769,7 +769,7 @@ const get_page: Operation = {
 
 const put_page: Operation = {
   name: 'put_page',
-  description: 'Write/update a page (markdown with frontmatter). Chunks, embeds, reconciles tags, and (when auto_link/auto_timeline are enabled) extracts + reconciles graph links and timeline entries. On the CLI, `gbrain put SLUG --file PATH` reads content from a file (also `--content` or stdin). For provenance write-through and a binary-NUL guard, prefer `gbrain capture --file PATH --slug SLUG` (v0.39.3.0).',
+  description: 'Write/update a page (markdown with frontmatter). Chunks, embeds, reconciles tags, and (when auto_link/auto_timeline are enabled) extracts + reconciles graph links and timeline entries. For large content on Windows (pipe-buffer limit ~45KB) or any file-as-input workflow, use `gbrain capture --file PATH --slug SLUG` — capture reads the file as a Buffer with a binary-NUL guard and adds provenance write-through (v0.39.3.0).',
   params: {
     slug: { type: 'string', required: true, description: 'Page slug' },
     content: { type: 'string', required: true, description: 'Full markdown content with YAML frontmatter' },
@@ -1384,10 +1384,7 @@ const list_pages: Operation = {
   params: {
     type: { type: 'string', description: 'Filter by page type' },
     tag: { type: 'string', description: 'Filter by tag' },
-    limit: { type: 'number', description: 'Max results (default 50, capped at 100 — use offset to paginate beyond)' },
-    // #2876: the 100-row cap was silent and there was no way past it even
-    // though both engines already support OFFSET on listPages.
-    offset: { type: 'number', description: 'Skip first N results (pagination; pair with limit)' },
+    limit: { type: 'number', description: 'Max results (default 50)' },
     // v0.29 — surface filter that already exists on PageFilters.
     updated_after: {
       type: 'string',
@@ -1418,10 +1415,6 @@ const list_pages: Operation = {
       type: p.type as any,
       tag: p.tag as string,
       limit: clampSearchLimit(p.limit as number | undefined, 50, 100),
-      // #2876: thread pagination through (engines already honor offset).
-      offset: Number.isFinite(p.offset as number) && (p.offset as number) > 0
-        ? Math.floor(p.offset as number)
-        : undefined,
       includeDeleted: (p.include_deleted as boolean) === true,
       updated_after: typeof p.updated_after === 'string' ? p.updated_after : undefined,
       sort,

src/core/pglite-engine.ts

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

src/core/postgres-engine.ts

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

src/core/search/sql-ranking.ts

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

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

@@ -28,8 +28,8 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
     resetGateway();
   });
 
-  test('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/cli-args.test.ts

@@ -1,41 +1,8 @@
 import { describe, expect, test } from 'bun:test';
-import { mkdtempSync, rmSync, writeFileSync } from 'fs';
-import { tmpdir } from 'os';
-import { join } from 'path';
 import { parseOpArgs } from '../src/cli.ts';
 import { operationsByName } from '../src/core/operations.ts';
 
 describe('parseOpArgs', () => {
-  // #380: `gbrain put SLUG --file PATH` reads content from the file instead
-  // of silently swallowing the flag and creating an empty page.
-  test('put --file reads the stdin param (content) from a file', () => {
-    const dir = mkdtempSync(join(tmpdir(), 'gbrain-put-file-'));
-    try {
-      const pagePath = join(dir, 'page.md');
-      writeFileSync(pagePath, '# From file\n\nBody loaded from --file.\n');
-      const params = parseOpArgs(operationsByName.put_page, ['concepts/from-file', '--file', pagePath]);
-      expect(params.slug).toBe('concepts/from-file');
-      expect(params.content).toBe('# From file\n\nBody loaded from --file.\n');
-    } finally {
-      rmSync(dir, { recursive: true, force: true });
-    }
-  });
-
-  // #380 regression guard: undeclared-but-honored flags must keep passing
-  // through when unknown flags become hard errors (--source is read by
-  // makeContext; --json by the output seam; --dry-run by ctx.dryRun).
-  test('pass-through allowlist flags survive on ops that do not declare them', () => {
-    const params = parseOpArgs(operationsByName.get_page, [
-      'people/alice-example', '--source', 'wiki', '--json', '--dry-run',
-    ]);
-    expect(params).toEqual({
-      slug: 'people/alice-example',
-      source: 'wiki',
-      json: true,
-      dry_run: true,
-    });
-  });
-
   test('--no-<boolean> maps to false without consuming the next flag', () => {
     const params = parseOpArgs(operationsByName.query, [
       'freshEmbedSourceScope code source',

test/cli.test.ts

@@ -1,5 +1,5 @@
 import { describe, test, expect } from 'bun:test';
-import { existsSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'fs';
+import { existsSync, mkdtempSync, readFileSync, rmSync } from 'fs';
 import { tmpdir } from 'os';
 import { join } from 'path';
 
@@ -120,76 +120,6 @@ describe('CLI dispatch integration', () => {
     expect(exitCode).toBe(0);
   });
 
-  // #380 / PR #856: put --help documents the --file input path.
-  test('put --help documents --file input', async () => {
-    const proc = Bun.spawn(['bun', 'run', 'src/cli.ts', 'put', '--help'], {
-      cwd: repoRoot,
-      stdout: 'pipe',
-      stderr: 'pipe',
-    });
-    const stdout = await new Response(proc.stdout).text();
-    const exitCode = await proc.exited;
-    expect(stdout).toContain('Usage: gbrain put');
-    expect(stdout).toContain('--file <path>');
-    expect(exitCode).toBe(0);
-  });
-
-  // #380: unknown flags on shared ops are a hard error (previously silently
-  // swallowed into params — `put --file` created empty pages). parseOpArgs
-  // runs BEFORE engine connect, so the error must fire without a brain.
-  test('unknown shared-op flags fail before DB connection', async () => {
-    const home = mkdtempSync(join(tmpdir(), 'gbrain-cli-unknown-flag-'));
-    try {
-      const proc = Bun.spawn(['bun', 'run', 'src/cli.ts', 'get', 'people/alice', '--bogus'], {
-        cwd: repoRoot,
-        stdout: 'pipe',
-        stderr: 'pipe',
-        env: isolatedEnv(home),
-      });
-      const stderr = await new Response(proc.stderr).text();
-      const exitCode = await proc.exited;
-      expect(stderr).toContain('Unknown option for gbrain get: --bogus');
-      expect(stderr).not.toContain('No brain configured');
-      expect(exitCode).toBe(1);
-    } finally {
-      rmSync(home, { recursive: true, force: true });
-    }
-  });
-
-  test('put rejects combining --file and --content', async () => {
-    const home = mkdtempSync(join(tmpdir(), 'gbrain-cli-put-conflict-'));
-    try {
-      const pagePath = join(home, 'page.md');
-      writeFileSync(pagePath, 'file body\n');
-      const proc = Bun.spawn(
-        ['bun', 'run', 'src/cli.ts', 'put', 'a/b', '--content', 'inline', '--file', pagePath],
-        { cwd: repoRoot, stdout: 'pipe', stderr: 'pipe', env: isolatedEnv(home) },
-      );
-      const stderr = await new Response(proc.stderr).text();
-      const exitCode = await proc.exited;
-      expect(stderr).toContain('use only one of --file, --content, or stdin');
-      expect(exitCode).toBe(1);
-    } finally {
-      rmSync(home, { recursive: true, force: true });
-    }
-  });
-
-  test('put --file with a missing path errors instead of writing an empty page', async () => {
-    const home = mkdtempSync(join(tmpdir(), 'gbrain-cli-put-missing-file-'));
-    try {
-      const proc = Bun.spawn(
-        ['bun', 'run', 'src/cli.ts', 'put', 'a/b', '--file', join(home, 'nope.md')],
-        { cwd: repoRoot, stdout: 'pipe', stderr: 'pipe', env: isolatedEnv(home) },
-      );
-      const stderr = await new Response(proc.stderr).text();
-      const exitCode = await proc.exited;
-      expect(stderr).toContain('cannot read --file');
-      expect(exitCode).toBe(1);
-    } finally {
-      rmSync(home, { recursive: true, force: true });
-    }
-  });
-
   test('upgrade --help prints usage without running upgrade', async () => {
     const proc = Bun.spawn(['bun', 'run', 'src/cli.ts', 'upgrade', '--help'], {
       cwd: repoRoot,

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/list-pages-offset.test.ts

@@ -1,55 +0,0 @@
-import { describe, test, expect } from 'bun:test';
-import { operationsByName } from '../src/core/operations.ts';
-
-/**
- * #2876: `gbrain list --limit` silently clamped at 100 with no pagination.
- * list_pages now declares `offset` (both engines already supported it on
- * PageFilters) and the limit description discloses the 100-row cap.
- */
-describe('list_pages pagination (#2876)', () => {
-  const listPagesOp = operationsByName.list_pages;
-
-  function makeCtx(captured: unknown[]) {
-    return {
-      engine: {
-        listPages: async (filters: unknown) => {
-          captured.push(filters);
-          return [];
-        },
-      },
-      config: { engine: 'pglite' },
-      logger: { info() {}, warn() {}, error() {} },
-      dryRun: false,
-      remote: false,
-      sourceId: 'default',
-    } as any;
-  }
-
-  test('declares offset param and discloses the 100-row cap on limit', () => {
-    expect(listPagesOp.params.offset).toBeDefined();
-    expect(listPagesOp.params.offset.type).toBe('number');
-    expect(listPagesOp.params.limit.description).toContain('100');
-  });
-
-  test('threads offset through to engine.listPages', async () => {
-    const captured: any[] = [];
-    await listPagesOp.handler(makeCtx(captured), { limit: 10, offset: 30 });
-    expect(captured[0].offset).toBe(30);
-    expect(captured[0].limit).toBe(10);
-  });
-
-  test('drops negative, non-finite, and zero offsets', async () => {
-    const captured: any[] = [];
-    const ctx = makeCtx(captured);
-    await listPagesOp.handler(ctx, { offset: -5 });
-    await listPagesOp.handler(ctx, { offset: Infinity });
-    await listPagesOp.handler(ctx, { offset: 0 });
-    for (const f of captured) expect(f.offset).toBeUndefined();
-  });
-
-  test('floors fractional offsets', async () => {
-    const captured: any[] = [];
-    await listPagesOp.handler(makeCtx(captured), { offset: 7.9 });
-    expect(captured[0].offset).toBe(7);
-  });
-});

test/pglite-engine.test.ts

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