fix(facts): fold visibility tier into hot-memory meta cache key

trustedFactReads is re-read from config on every stdio tool call, so the
reader's visibility tier can now flip within one server process. The
meta-hook cache key (source, session, allow-list hash) didn't capture it,
so a mid-session opt-out of facts.trust_local_reads could keep serving a
private-inclusive cached payload for the 30s TTL. Compute the visibility
filter before the cache lookup and append the tier to the key, restoring
the header's cross-tier no-bleed invariant.

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

src/commands/doctor.ts

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

src/commands/embed.ts

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

src/core/ai/gateway.ts

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

src/core/ai/recipes/ollama.ts

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

src/core/config.ts

@@ -908,6 +908,10 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
   'facts.extraction_model',
   // #2113: output-token cap for the per-turn facts extractor (default 4000).
   'facts.extraction_max_tokens',
+  // Owner opt-in: let the local stdio MCP pipe read this owner's private facts
+  // (find_trajectory / recall). Default off; HTTP transport ignores it. See
+  // src/core/facts/reader-trust.ts.
+  'facts.trust_local_reads',
   // Dream cycle config
   'dream.synthesize.session_corpus_dir',
   'dream.synthesize.meeting_transcripts_dir',

src/core/doctor-categories.ts

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

src/core/engine.ts

@@ -591,6 +591,8 @@ export interface TrajectoryOpts {
   sourceIds?: string[];
   /** When true, filters to visibility='world' only. Set by MCP layer from ctx.remote. */
   remote?: boolean;
+  /** Owner opt-in: read private facts despite `remote`. See facts/reader-trust.ts. */
+  trustedFactReads?: boolean;
   /** Metric filter. When set, only facts with this canonical metric label participate. */
   metric?: string;
   /**

src/core/facts/meta-hook.ts

@@ -17,6 +17,7 @@
 import type { OperationContext } from './../operations.ts';
 import type { FactRow } from './../engine.ts';
 import { effectiveConfidence } from './decay.ts';
+import { readableFactVisibilities } from './reader-trust.ts';
 
 const DEFAULT_TTL_MS = 30_000;
 const DEFAULT_TOP_K = 10;
@@ -50,7 +51,13 @@ export async function getBrainHotMemoryMeta(
   const sessionId = (ctx as { source_session?: string }).source_session
     ?? null;
   const allowListHash = hashAllowList(ctx.takesHoldersAllowList);
-  const cacheKey = `${sourceId}::${sessionId ?? '_'}::${allowListHash}`;
+  // Visibility tier: untrusted remote → world-only; trusted local +
+  // owner-trusted reads → all rows. Folded into the cache key (the header's
+  // "cache entries don't bleed across tiers" invariant): trustedFactReads is
+  // re-read from config per call, so a mid-session opt-out must not keep
+  // serving a private-inclusive cached payload for the TTL window.
+  const visibility = readableFactVisibilities(ctx);
+  const cacheKey = `${sourceId}::${sessionId ?? '_'}::${allowListHash}::${visibility ? 'world' : 'all'}`;
 
   const ttl = Math.max(1000, opts.ttlMs ?? DEFAULT_TTL_MS);
   const topK = Math.max(1, Math.min(opts.topK ?? DEFAULT_TOP_K, 25));
@@ -61,10 +68,6 @@ export async function getBrainHotMemoryMeta(
     return cached.payload;
   }
 
-  // Build a fresh payload. Visibility tier: remote → world-only;
-  // local → all rows.
-  const visibility = ctx.remote === false ? undefined : ['world'] as ('world' | 'private')[];
-
   let rows: FactRow[] = [];
   if (sessionId) {
     rows = await ctx.engine.listFactsBySession(sourceId, sessionId, {

src/core/facts/reader-trust.ts

@@ -0,0 +1,48 @@
+/**
+ * Fact-read visibility trust.
+ *
+ * Fact rows are tagged `private` | `world`. Remote/untrusted callers
+ * (`remote === true`) see only `world` rows — the posture that keeps a
+ * published or HTTP-served brain from leaking private claims to strangers.
+ *
+ * But the stdio MCP server is an unauthenticated LOCAL pipe: on a single-owner
+ * machine the caller IS the owner, yet it still defaults `remote: true` for
+ * safety, so the owner's own agent is denied the owner's own private facts
+ * (e.g. `find_trajectory` returns empty over MCP even though the facts exist).
+ *
+ * `trustedFactReads` is a narrow, READ-ONLY trust elevation, deliberately
+ * DECOUPLED from `remote` so every other remote protection — file_upload
+ * confinement, source isolation, fence stripping, takes-holder scoping — stays
+ * fully in force. The stdio MCP server sets it ONLY when the brain owner opts
+ * in via the `facts.trust_local_reads` config (default off). The HTTP/published
+ * transport never sets it, so a served brain stays world-only regardless.
+ */
+export interface FactReaderTrust {
+  /**
+   * Mirrors OperationContext.remote. FAIL-CLOSED: anything not strictly
+   * `false` is treated as remote/untrusted (CLAUDE.md trust invariant).
+   */
+  remote?: boolean;
+  /** Owner opt-in: this remote caller may read private facts. */
+  trustedFactReads?: boolean;
+}
+
+/**
+ * True when the reader is restricted to `visibility = 'world'` rows.
+ * Fail-closed: an unset/undefined `remote` is untrusted — only an explicit
+ * `remote: false` (trusted local CLI) or an explicit owner opt-in
+ * (`trustedFactReads: true`) reads private rows.
+ */
+export function factsWorldOnly(t: FactReaderTrust): boolean {
+  return t.remote !== false && t.trustedFactReads !== true;
+}
+
+/**
+ * Visibility filter for list-style fact reads: `['world']` when the reader is
+ * world-only, `undefined` (no filter — all rows) when it is trusted.
+ */
+export function readableFactVisibilities(
+  t: FactReaderTrust,
+): ('private' | 'world')[] | undefined {
+  return factsWorldOnly(t) ? ['world'] : undefined;
+}

src/core/operations.ts

@@ -18,6 +18,7 @@ import { captureEvalCandidate, isEvalCaptureEnabled, isEvalScrubEnabled } from '
 import type { HybridSearchMeta } from './types.ts';
 import { extractPageLinks, isAutoLinkEnabled, isAutoTimelineEnabled, isGlobalBasenameEnabled, parseTimelineEntries, makeResolver, type UnresolvedFrontmatterRef } from './link-extraction.ts';
 import { isFactsBackstopEligible } from './facts/eligibility.ts';
+import { readableFactVisibilities } from './facts/reader-trust.ts';
 import { stripTakesFence } from './takes-fence.ts';
 import { stripFactsFence } from './facts-fence.ts';
 import { getContentFlag } from './quarantine.ts';
@@ -332,6 +333,15 @@ export interface OperationContext {
    * remote/untrusted (defense in depth in case the type is bypassed via cast).
    */
   remote: boolean;
+  /**
+   * Owner opt-in (`facts.trust_local_reads`): allow this remote caller to read
+   * `private` facts. A NARROW, read-only trust elevation decoupled from
+   * `remote` — every other remote protection (file confinement, source
+   * isolation, fence stripping, takes scoping) stays in force. Set ONLY by the
+   * stdio MCP server when the config is on; the HTTP transport never sets it.
+   * Consulted via `src/core/facts/reader-trust.ts`.
+   */
+  trustedFactReads?: boolean;
   /**
    * Subagent runtime context (v0.16+). Set by the subagent tool dispatcher when
    * dispatching an op as a tool call from an LLM loop. Used to enforce per-op
@@ -3629,6 +3639,7 @@ const find_trajectory: Operation = {
       entitySlug: p.entity_slug,
       ...scope,
       remote: ctx.remote === true,
+      trustedFactReads: ctx.trustedFactReads === true,
       metric,
       kind,
       since,
@@ -3989,13 +4000,9 @@ const recall: Operation = {
     const includeExpired = p.include_expired === true;
     const grep = typeof p.grep === 'string' ? p.grep.toLowerCase() : null;
 
-    // Visibility filter: remote callers see world-only unless their token
-    // grants elevated visibility (future-proofing; v0.31 ships world-only
-    // for remote, all for local CLI).
-    const visibility =
-      ctx.remote === false
-        ? undefined
-        : ['world'] as ('private' | 'world')[];
+    // Visibility filter: world-only for untrusted remote callers; all rows for
+    // trusted local CLI and owner-trusted reads (facts.trust_local_reads).
+    const visibility = readableFactVisibilities(ctx);
 
     let rows: Awaited<ReturnType<typeof ctx.engine.listFactsByEntity>> = [];
 

src/core/pglite-engine.ts

@@ -18,6 +18,7 @@ import type {
 } from './engine.ts';
 import { MAX_SEARCH_LIMIT, clampSearchLimit } from './engine.ts';
 import { withRetry, BULK_RETRY_OPTS, resolveBulkRetryOpts, computeNextDelay, type BatchAuditSite } from './retry.ts';
+import { factsWorldOnly } from './facts/reader-trust.ts';
 import { logBatchRetry as auditLogBatchRetry, logBatchExhausted as auditLogBatchExhausted } from './audit/batch-retry-audit.ts';
 import { runMigrations } from './migrate.ts';
 import { PGLITE_SCHEMA_SQL, getPGLiteSchema } from './pglite-schema.ts';
@@ -56,7 +57,7 @@ import { GBrainError, PAGE_SORT_SQL, ENRICH_ORDER_SQL } from './types.ts';
 import { finalizeLastSeen } from './chronicle/last-seen.ts';
 import { computeAnomaliesFromBuckets } from './cycle/anomaly.ts';
 import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
-import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
+import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
 import {
   normalizeEngineColumn,
   buildVectorCastFragment,
@@ -1591,8 +1592,6 @@ export class PGLiteEngine implements BrainEngine {
     }
 
     // v0.20.0 Cathedral II Layer 10 C1/C2: language + symbol-kind filters.
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, innerLimit, limit, offset];
     let extraFilter = '';
     if (opts?.language) {
@@ -1632,7 +1631,6 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const keywordSql =
       `WITH ranked AS (
@@ -1640,14 +1638,14 @@ export class PGLiteEngine implements BrainEngine {
            p.slug, p.id as page_id, p.title, p.type, p.source_id,
            p.effective_date, p.effective_date_source,
            cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-           ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+           ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
            CASE WHEN p.updated_at < (
              SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
            ) THEN true ELSE false END AS stale
          FROM content_chunks cc
          JOIN pages p ON p.id = cc.page_id
          JOIN sources s ON s.id = p.source_id
-         WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
+         WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
            -- v0.27.1: hide image rows from default text-keyword search so
            -- OCR text doesn't drown text-page hits. Image-similarity queries
            -- run a separate vector path on embedding_image.
@@ -1715,10 +1713,7 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, limit, offset];
     let extraFilter = '';
     if (opts?.type) {
@@ -1766,7 +1761,7 @@ export class PGLiteEngine implements BrainEngine {
          COALESCE(rep.chunk_index, 0) as chunk_index,
          COALESCE(rep.chunk_text, '') as chunk_text,
          COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
-         ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+         ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
          CASE WHEN p.updated_at < (
            SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
          ) THEN true ELSE false END AS stale
@@ -1781,7 +1776,7 @@ export class PGLiteEngine implements BrainEngine {
          ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
          LIMIT 1
        ) rep ON true
-       WHERE p.search_vector @@ ${ftsQueryExpr}
+       WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
          ${extraFilter} ${hardExcludeClause} ${visibilityClause}
        ORDER BY score DESC, p.id ASC
        LIMIT $2 OFFSET $3`;
@@ -1968,8 +1963,6 @@ export class PGLiteEngine implements BrainEngine {
       });
     }
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, limit, offset];
     let extraFilter = '';
     if (opts?.language) {
@@ -2004,21 +1997,20 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const { rows } = await this.db.query(
       `SELECT
          p.slug, p.id as page_id, p.title, p.type, p.source_id,
          p.effective_date, p.effective_date_source,
          cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-         ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+         ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
          CASE WHEN p.updated_at < (
            SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
          ) THEN true ELSE false END AS stale
        FROM content_chunks cc
        JOIN pages p ON p.id = cc.page_id
        JOIN sources s ON s.id = p.source_id
-       WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
+       WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
        ORDER BY score DESC
        LIMIT $2 OFFSET $3`,
       params
@@ -4327,7 +4319,10 @@ export class PGLiteEngine implements BrainEngine {
     const useArray = Array.isArray(opts.sourceIds) && opts.sourceIds.length > 0;
     const sourceIds = useArray ? opts.sourceIds! : null;
     const sourceId = opts.sourceId ?? 'default';
-    const remoteFilter = opts.remote === true;
+    // Direct-engine contract: unset `remote` here means a trusted in-process
+    // caller (CLI/tests) — the fail-closed default lives in the op layer, which
+    // always passes explicit booleans. Normalize before the fail-closed helper.
+    const remoteFilter = factsWorldOnly({ remote: opts.remote === true, trustedFactReads: opts.trustedFactReads === true });
 
     // Build SQL dynamically. PGLite uses $N positional params; we
     // assemble the WHERE clauses + params array in tandem to keep them

src/core/postgres-engine.ts

@@ -14,6 +14,7 @@ import type {
   SourceRow,
 } from './engine.ts';
 import { withRetry, BULK_RETRY_OPTS, resolveBulkRetryOpts, computeNextDelay, type BatchAuditSite } from './retry.ts';
+import { factsWorldOnly } from './facts/reader-trust.ts';
 import { logBatchRetry as auditLogBatchRetry, logBatchExhausted as auditLogBatchExhausted } from './audit/batch-retry-audit.ts';
 import type {
   DomainBankSampleOpts, CorpusSampleOpts, DomainBankRow,
@@ -64,7 +65,7 @@ import { ConnectionManager } from './connection-manager.ts';
 import { logConnectionEvent } from './connection-audit.ts';
 import { validateSlug, contentHash, rowToPage, rowToStalePage, rowToChunk, rowToSearchResult, parseEmbedding, tryParseEmbedding, takeRowToTake, takeHitRowToHit, isUndefinedTableError, warnOncePerProcess } from './utils.ts';
 import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
-import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
+import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
 import { DEFAULT_EMBEDDING_MODEL, DEFAULT_EMBEDDING_DIMENSIONS } from './ai/defaults.ts';
 import { DELETE_BATCH_SIZE } from './engine-constants.ts';
 
@@ -1691,8 +1692,6 @@ export class PostgresEngine implements BrainEngine {
     const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
     const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (type) {
@@ -1763,7 +1762,6 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const rawQuery = `
       WITH ranked_chunks AS (
@@ -1771,11 +1769,11 @@ export class PostgresEngine implements BrainEngine {
           p.slug, p.id as page_id, p.title, p.type, p.source_id,
           p.effective_date, p.effective_date_source,
           cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-          ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score
+          ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score
         FROM content_chunks cc
         JOIN pages p ON p.id = cc.page_id
         JOIN sources s ON s.id = p.source_id
-        WHERE cc.search_vector @@ ${ftsQueryExpr}
+        WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
           ${typeClause}
           ${typesClause}
           ${excludeSlugsClause}
@@ -1866,10 +1864,7 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (opts?.type) {
@@ -1929,7 +1924,7 @@ export class PostgresEngine implements BrainEngine {
         COALESCE(rep.chunk_index, 0) as chunk_index,
         COALESCE(rep.chunk_text, '') as chunk_text,
         COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
-        ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+        ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
         false AS stale
       FROM pages p
       JOIN sources s ON s.id = p.source_id
@@ -1942,7 +1937,7 @@ export class PostgresEngine implements BrainEngine {
         ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
         LIMIT 1
       ) rep ON true
-      WHERE p.search_vector @@ ${ftsQueryExpr}
+      WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
         ${typeClause}
         ${typesClause}
         ${excludeSlugsClause}
@@ -2006,8 +2001,6 @@ export class PostgresEngine implements BrainEngine {
     const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
     const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (type) {
@@ -2068,19 +2061,18 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const rawQuery = `
       SELECT
         p.slug, p.id as page_id, p.title, p.type, p.source_id,
         p.effective_date, p.effective_date_source,
         cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-        ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+        ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
         false AS stale
       FROM content_chunks cc
       JOIN pages p ON p.id = cc.page_id
       JOIN sources s ON s.id = p.source_id
-      WHERE cc.search_vector @@ ${ftsQueryExpr}
+      WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
         ${typeClause}
         ${typesClause}
         ${excludeSlugsClause}
@@ -4541,7 +4533,10 @@ export class PostgresEngine implements BrainEngine {
     const useArray = Array.isArray(opts.sourceIds) && opts.sourceIds.length > 0;
     const sourceIds = useArray ? opts.sourceIds! : null;
     const sourceId = opts.sourceId ?? 'default';
-    const remoteFilter = opts.remote === true;
+    // Direct-engine contract: unset `remote` here means a trusted in-process
+    // caller (CLI/tests) — the fail-closed default lives in the op layer, which
+    // always passes explicit booleans. Normalize before the fail-closed helper.
+    const remoteFilter = factsWorldOnly({ remote: opts.remote === true, trustedFactReads: opts.trustedFactReads === true });
 
     // Source-scope predicate: array path (federated) wins over scalar.
     // Engine.ts contract: returns chronological points; regressions +

src/core/search/sql-ranking.ts

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

src/mcp/dispatch.ts

@@ -30,6 +30,13 @@ export interface ToolResult {
 export interface DispatchOpts {
   /** Defaults to true (remote/untrusted). Local CLI callers (`gbrain call`) pass false. */
   remote?: boolean;
+  /**
+   * Owner opt-in (`facts.trust_local_reads`): let this remote caller read
+   * `private` facts. Set ONLY by the stdio MCP server; the HTTP transport
+   * leaves it unset so a served brain stays world-only. See
+   * `src/core/facts/reader-trust.ts`.
+   */
+  trustedFactReads?: boolean;
   /** Override the default stderr logger (e.g. CLI uses console.* directly). */
   logger?: OperationContext['logger'];
   /**
@@ -203,6 +210,7 @@ export function buildOperationContext(
     logger: opts.logger || stderrLogger,
     dryRun: !!params.dry_run,
     remote: opts.remote ?? true,
+    trustedFactReads: opts.trustedFactReads === true,
     takesHoldersAllowList: opts.takesHoldersAllowList,
     // v0.34 D4: sourceId is REQUIRED at the type level. Auto-fill 'default'
     // for single-source brains and any caller who didn't resolve a sourceId.

src/mcp/server.ts

@@ -35,6 +35,16 @@ export async function startMcpServer(engine: BrainEngine) {
   // shape and cast through `any` (the SDK accepts it via the ServerResult union).
   server.setRequestHandler(CallToolRequestSchema, async (request: any): Promise<any> => {
     const { name, arguments: params } = request.params;
+    // Owner opt-in: the stdio pipe is local + unauthenticated, so on a
+    // single-owner machine its caller is the owner. When facts.trust_local_reads
+    // is on, let fact reads (find_trajectory / recall) see this owner's own
+    // private facts. Narrow + read-only — every other remote protection stays
+    // on (remote stays true). HTTP transport never sets this. Best-effort: a
+    // config read blip falls back to the safe world-only default.
+    let trustedFactReads = false;
+    try {
+      trustedFactReads = (await engine.getConfig('facts.trust_local_reads')) === 'true';
+    } catch { /* keep world-only default */ }
     // v0.28: stdio MCP has no per-token auth (local pipe). Default the
     // takes-holder allow-list to ['world'] so agent-facing callers don't
     // see private hunches via takes_list / takes_search / query. Operators
@@ -42,6 +52,7 @@ export async function startMcpServer(engine: BrainEngine) {
     // `gbrain call <op>` (sets remote=false in src/cli.ts).
     return dispatchToolCall(engine, name, params, {
       remote: true,
+      trustedFactReads,
       takesHoldersAllowList: ['world'],
       // v0.31: source defaults to 'default' for stdio (no per-token scope).
       // Operators who want a different source on stdio MCP should set

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

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

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

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

test/engine-find-trajectory.test.ts

@@ -165,6 +165,22 @@ describe('findTrajectory — visibility filter (D-CDX-1 / R6)', () => {
     const all = await engine.findTrajectory({ entitySlug: 'traj-vis-default' });
     expect(all.length).toBe(2);
   });
+
+  test('remote=true + trustedFactReads bypasses world-only (owner-trusted reads)', async () => {
+    await insertTyped({ entity_slug: 'traj-vis-trusted', metric: 'mrr', value: 50000, visibility: 'private', valid_from: new Date('2026-01-15') });
+    await insertTyped({ entity_slug: 'traj-vis-trusted', metric: 'mrr', value: 99999, visibility: 'world',   valid_from: new Date('2026-04-12') });
+
+    // Untrusted remote: world only.
+    const untrusted = await engine.findTrajectory({ entitySlug: 'traj-vis-trusted', remote: true });
+    expect(untrusted.length).toBe(1);
+    expect(untrusted[0].value).toBe(99999);
+
+    // Owner-trusted remote: sees the private point too. remote stays true — only
+    // fact-read visibility is elevated.
+    const trusted = await engine.findTrajectory({ entitySlug: 'traj-vis-trusted', remote: true, trustedFactReads: true });
+    expect(trusted.length).toBe(2);
+    expect(trusted.map(p => p.value).sort((a, b) => (a! - b!))).toEqual([50000, 99999]);
+  });
 });
 
 describe('findTrajectory — metric + since + until filters', () => {

test/facts-reader-trust.test.ts

@@ -0,0 +1,43 @@
+import { describe, test, expect } from 'bun:test';
+import {
+  factsWorldOnly,
+  readableFactVisibilities,
+} from '../src/core/facts/reader-trust.ts';
+
+describe('factsWorldOnly', () => {
+  test('FAIL-CLOSED: unset remote is untrusted (world-only)', () => {
+    expect(factsWorldOnly({})).toBe(true);
+    expect(factsWorldOnly({ remote: undefined })).toBe(true);
+    expect(factsWorldOnly({ trustedFactReads: false })).toBe(true);
+  });
+
+  test('explicit remote=false (trusted local CLI) sees all', () => {
+    expect(factsWorldOnly({ remote: false })).toBe(false);
+    expect(factsWorldOnly({ remote: false, trustedFactReads: false })).toBe(false);
+  });
+
+  test('untrusted remote callers are world-only', () => {
+    expect(factsWorldOnly({ remote: true })).toBe(true);
+    expect(factsWorldOnly({ remote: true, trustedFactReads: false })).toBe(true);
+  });
+
+  test('owner-trusted remote reads bypass the world-only filter', () => {
+    expect(factsWorldOnly({ remote: true, trustedFactReads: true })).toBe(false);
+  });
+
+  test('trustedFactReads is a no-op for an already-trusted local caller', () => {
+    expect(factsWorldOnly({ remote: false, trustedFactReads: true })).toBe(false);
+  });
+});
+
+describe('readableFactVisibilities', () => {
+  test("world-only readers get the ['world'] filter (incl. unset remote)", () => {
+    expect(readableFactVisibilities({ remote: true })).toEqual(['world']);
+    expect(readableFactVisibilities({})).toEqual(['world']);
+  });
+
+  test('trusted readers get undefined (no filter — all rows)', () => {
+    expect(readableFactVisibilities({ remote: false })).toBeUndefined();
+    expect(readableFactVisibilities({ remote: true, trustedFactReads: true })).toBeUndefined();
+  });
+});

test/pglite-engine.test.ts

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