fix(test): give slow setup hooks a real timeout budget

bun ignores bunfig.toml's timeout key, and beforeAll/beforeEach hooks do
NOT inherit a test's third-arg timeout — a bare `bun test` gives every
hook the 5000ms default even when all tests in the file declare 30s+.
Measured on bun 1.3.14: a 6s hook dies at ~5001ms with the signature
`(unnamed) [5001ms] ... hook timed out` (the #3545 jsonb-parity CI
failure); both `beforeAll(fn, ms)` and the CLI `--timeout` flag are
enforced hook budgets (kills observed at exactly the configured ms).

Fixes:
- e2e.yml (jsonb-parity, tier1, tier2) and release.yml ran bare
  `bun test`; they now pass --timeout=60000 like every scripts/ runner.
- test/e2e/jsonb-roundtrip.test.ts (the #2339 double-encode guard, which
  only real Postgres can surface) additionally carries per-hook 60s
  budgets so a bare local run can't flake either — same pattern as its
  sibling op-checkpoint-jsonb-parity.test.ts.
- scripts/check-bun-test-timeout.sh: CI guard (run from test.yml's
  verify job) failing any future bare `bun test` in workflows/scripts.
- scripts/run-e2e.sh: correct the comment claiming --timeout is
  per-test-only (it covers hooks; the outer gtimeout exists for
  sync-blocking WASM hangs where no timer can fire).

Proof: with Postgres paused for 6s during setupDB's connect, the
unfixed file fails at 5001.81ms with the exact CI signature; the fixed
file passes the identical condition (5 pass, 6.57s). 396 slow
before-hooks across 362 test files lack per-hook budgets; all of them
run through --timeout-passing invocations after this change, enforced
by the new guard.

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

.github/workflows/e2e.yml

@@ -61,7 +61,10 @@ jobs:
       - name: Run JSONB double-encode parity tests on real Postgres
         env:
           DATABASE_URL: postgresql://postgres:postgres@localhost:5432/gbrain_test
-        run: bun test test/e2e/op-checkpoint-jsonb-parity.test.ts test/e2e/jsonb-roundtrip.test.ts
+        # --timeout also raises bun's 5s default hook budget (beforeAll/afterAll
+        # do NOT inherit a test's third-arg timeout; verified on bun 1.3.x).
+        # Every runner script in scripts/ passes it; bare invocations must too.
+        run: bun test --timeout=60000 test/e2e/op-checkpoint-jsonb-parity.test.ts test/e2e/jsonb-roundtrip.test.ts
 
   tier1:
     name: Tier 1 (Mechanical)
@@ -88,7 +91,7 @@ jobs:
           bun-version: 1.3.13
       - run: bun install
       - name: Run Tier 1 E2E tests
-        run: bun test test/e2e/mechanical.test.ts test/e2e/mcp.test.ts
+        run: bun test --timeout=60000 test/e2e/mechanical.test.ts test/e2e/mcp.test.ts
         env:
           DATABASE_URL: postgresql://postgres:postgres@localhost:5432/gbrain_test
 
@@ -155,7 +158,7 @@ jobs:
           }
           EOF
       - name: Run Tier 2 skill tests
-        run: bun test test/e2e/skills.test.ts test/e2e/zeroentropy-live.test.ts
+        run: bun test --timeout=60000 test/e2e/skills.test.ts test/e2e/zeroentropy-live.test.ts
         env:
           DATABASE_URL: postgresql://postgres:postgres@localhost:5432/gbrain_test
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

.github/workflows/release.yml

@@ -29,7 +29,9 @@ jobs:
         with:
           bun-version: 1.3.13
       - run: bun install
-      - run: bun test
+      # --timeout matches every scripts/ runner and covers hook budgets too
+      # (bunfig.toml's timeout key is ignored by bun; hooks default to 5s).
+      - run: bun test --timeout=60000
       - run: bun run verify
       - run: bun build --compile --target=${{ matrix.target }} --outfile bin/${{ matrix.artifact }} src/cli.ts
       - name: Attest build provenance

.github/workflows/test.yml

@@ -113,6 +113,11 @@ jobs:
           key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
       - run: bun install
       - run: bun run verify
+      # Guard: no bare `bun test` in workflows/scripts — bun ignores
+      # bunfig.toml's timeout, and hooks (beforeAll/afterAll) get the 5s
+      # default regardless of per-test third-arg timeouts. Runs directly
+      # (not via verify's CHECKS array) to avoid a package.json edit.
+      - run: bash scripts/check-bun-test-timeout.sh
 
   serial-tests:
     # *.serial.test.ts at --max-concurrency=1. Lives in its own runner so

scripts/check-bun-test-timeout.sh

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+# CI guard: every `bun test` invocation in workflows and runner scripts must
+# pass an explicit --timeout.
+#
+# Why: bun ignores bunfig.toml's `timeout` key (verified on 1.3.14), so a bare
+# `bun test` gets the 5000ms default for BOTH tests and beforeAll/beforeEach/
+# afterAll/afterEach hooks. Hooks do NOT inherit a test's third-arg timeout —
+# a file whose tests all declare `}, 30_000)` still has a 5s hook budget, and
+# slow setup (Postgres connect + migrations, PGLite cold start) flakes on
+# loaded CI runners with the signature `(unnamed) [5001ms] ... hook timed out`
+# (the #3545 jsonb-parity failure). The CLI --timeout flag is the one measured
+# mechanism that raises the hook budget uniformly; per-hook second-arg
+# timeouts work too but don't scale to ~400 slow hooks.
+#
+# Usage: scripts/check-bun-test-timeout.sh
+# Exit:  0 when clean, 1 when a bare `bun test` invocation is found.
+
+set -euo pipefail
+
+ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
+cd "$ROOT"
+
+# Match executable `bun test` invocations. Exclude comment lines (#, //, *)
+# and lines that already carry --timeout anywhere.
+# Scope: workflows + runner scripts (the surfaces CI executes). package.json
+# script bodies route through scripts/ already; editing it is out of scope here.
+violations="$(grep -rnE '\bbun test\b' .github/workflows scripts 2>/dev/null \
+  | grep -v -- '--timeout' \
+  | grep -vE ':[[:space:]]*(#|//|\*)' \
+  | grep -v 'check-bun-test-timeout' \
+  || true)"
+
+if [ -n "$violations" ]; then
+  echo "FAIL: bare 'bun test' without --timeout (5s default kills slow setup hooks):" >&2
+  echo "$violations" >&2
+  echo "" >&2
+  echo "Add --timeout=60000 (see scripts/run-unit-shard.sh for the convention)." >&2
+  exit 1
+fi
+
+echo "OK: every bun test invocation passes an explicit --timeout."

scripts/run-e2e.sh

@@ -162,8 +162,9 @@ for f in "${files[@]}"; do
   if [ -n "${DATABASE_URL:-}" ]; then
     psql "$DATABASE_URL" -At -c "SELECT pg_terminate_backend(pid) FROM pg_stat_activity WHERE pid != pg_backend_pid() AND datname = current_database()" >/dev/null 2>&1 || true
   fi
-  # Hard outer timeout (180s per file). bun's --timeout is per-test; if a
-  # PGLite WASM call hangs in beforeAll/afterAll, --timeout never fires and
+  # Hard outer timeout (180s per file). bun's --timeout covers tests AND
+  # hooks (measured on 1.3.14), but it's timer-based: a PGLite WASM call
+  # that blocks the event loop synchronously never lets the timer fire and
   # the file wedges indefinitely. gtimeout/timeout SIGKILLs the file so the
   # suite advances. gtimeout (macOS via coreutils) preferred; timeout (Linux)
   # fallback; bare bun (no outer cap) if neither is installed.

src/cli.ts

@@ -9,7 +9,7 @@ installSigchldHandler();
 import { installSignalHandlers as installCleanupSignalHandlers } from './core/process-cleanup.ts';
 installCleanupSignalHandlers();
 
-import { readFileSync, existsSync, unlinkSync } from 'fs';
+import { readFileSync, existsSync, unlinkSync, fstatSync } from 'fs';
 import { spawn } from 'child_process';
 import {
   readUpdateCache,
@@ -55,7 +55,7 @@ export function bigintToStringReplacer(_key: string, value: unknown): unknown {
 }
 
 // CLI-only commands that bypass the operation layer
-export const CLI_ONLY = new Set(['init', 'reinit-pglite', 'upgrade', 'post-upgrade', 'check-update', 'integrations', 'publish', 'check-backlinks', 'lint', 'report', 'import', 'export', 'files', 'embed', 'serve', 'call', 'config', 'doctor', 'migrate', 'eval', 'sync', 'extract', 'extract-conversation-facts', 'enrich', 'features', 'autopilot', 'graph-query', 'jobs', 'agent', 'apply-migrations', 'skillpack-check', 'skillpack', 'resolvers', 'integrity', 'repair-jsonb', 'orphans', 'maintain', 'sources', 'mounts', 'dream', 'check-resolvable', 'routing-eval', 'skillify', 'smoke-test', 'providers', 'storage', 'repos', 'code-def', 'code-refs', 'reindex', 'reindex-code', 'reindex-frontmatter', 'code-callers', 'code-callees', 'reconcile-links', 'frontmatter', 'auth', 'friction', 'claw-test', 'book-mirror', 'takes', 'think', 'salience', 'anomalies', 'calibration', 'transcripts', 'models', 'remote', 'recall', 'forget', 'edges-backfill', 'cache', 'ze-switch', 'retrieval-upgrade', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector']);
+export const CLI_ONLY = new Set(['init', 'reinit-pglite', 'upgrade', 'post-upgrade', 'check-update', 'integrations', 'publish', 'check-backlinks', 'lint', 'report', 'import', 'export', 'files', 'embed', 'serve', 'call', 'config', 'doctor', 'migrate', 'eval', 'sync', 'extract', 'extract-conversation-facts', 'enrich', 'features', 'autopilot', 'graph-query', 'jobs', 'agent', 'apply-migrations', 'skillpack-check', 'skillpack', 'resolvers', 'integrity', 'repair-jsonb', 'orphans', 'maintain', 'sources', 'mounts', 'dream', 'check-resolvable', 'routing-eval', 'skillify', 'smoke-test', 'providers', 'storage', 'repos', 'code-def', 'code-refs', 'reindex', 'reindex-code', 'reindex-frontmatter', 'code-callers', 'code-callees', 'reconcile-links', 'frontmatter', 'auth', 'friction', 'claw-test', 'book-mirror', 'takes', 'think', 'salience', 'anomalies', 'calibration', 'transcripts', 'models', 'remote', 'recall', 'forget', 'edges-backfill', 'cache', 'ze-switch', 'retrieval-upgrade', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector', 'backfill']);
 // CLI-only commands whose handlers print their own --help text. These are
 // excluded from the generic short-circuit so detailed per-command and
 // per-subcommand usage stays reachable.
@@ -344,6 +344,11 @@ async function main() {
   // them out of the engine try/catch is safe and unlocks routing.
   const params = parseOpArgs(op, subArgs);
 
+  // #3513: stdin fill moved out of parseOpArgs so a non-TTY stdin with no
+  // piped input can't block the parse forever — the bounded read leaves the
+  // param unset on timeout and the required-param check below fails fast.
+  await applyStdinParam(op, params);
+
   // v0.27.1 (`gbrain query --image <path>`): swap the `image` param from
   // a filesystem path into base64 bytes + mime. The op accepts base64; the
   // CLI accepts a path. Helper is exported so tests can exercise the
@@ -804,18 +809,99 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
     }
   }
 
-  // Read stdin for content params
+  return params;
+}
+
+/**
+ * #3513: read stdin into an op's stdin-capable param without ever blocking
+ * forever. The old inline `readFileSync(0)` in parseOpArgs assumed non-TTY
+ * implies piped content; a non-TTY stdin with NO input (CI step, cron job,
+ * agent harness holding an unwritten pipe open) blocked the read until kill.
+ *
+ * Strategy by fd kind (fstat):
+ *  - TTY: skip, as before (interactive input is not an op-param source).
+ *  - regular file / /dev/null / anything not a pipe or socket: readFileSync
+ *    returns without blocking (`gbrain put x < file`, `< /dev/null` → '').
+ *  - FIFO/socket: stream-read with a deadline on the FIRST byte only. A real
+ *    pipe (`echo foo | gbrain put x`, heredocs) delivers its first byte
+ *    within milliseconds; once any data arrives the deadline is lifted and
+ *    we read to EOF like readFileSync did (slow producers stay supported).
+ *    An empty-but-closed pipe (`: | gbrain put x`) EOFs immediately → ''.
+ *    A pipe that never delivers a byte times out → param stays unset, so
+ *    the existing required-param usage error fires (fail fast, exit 1).
+ *
+ * GBRAIN_STDIN_TIMEOUT_MS overrides the first-byte deadline (default 5000).
+ * Exported for tests; called by the op dispatch right after parseOpArgs.
+ */
+export async function applyStdinParam(
+  op: Operation,
+  params: Record<string, unknown>,
+): Promise<void> {
+  // Branch shape (stdin hint + missing param + `!process.stdin.isTTY` gate +
+  // 5MB cap) is pinned by the R4 regression test for PR #1325's Windows fix
+  // (test/cycle/regression-pr-wave-r1-r2-r4.test.ts) — keep the spelling.
   if (op.cliHints?.stdin && !params[op.cliHints.stdin] && !process.stdin.isTTY) {
-    const stdinContent = readFileSync(0, 'utf-8');
+    const content = await readStdinBounded();
+    if (content === null) return; // no input arrived — let the required-param check fail fast
     const MAX_STDIN = 5_000_000; // 5MB
-    if (Buffer.byteLength(stdinContent, 'utf-8') > MAX_STDIN) {
+    if (Buffer.byteLength(content, 'utf-8') > MAX_STDIN) {
       console.error(`Error: stdin content exceeds ${MAX_STDIN} bytes. Split into smaller inputs.`);
       process.exit(1);
     }
-    params[op.cliHints.stdin] = stdinContent;
+    params[op.cliHints.stdin] = content;
   }
+}
 
-  return params;
+/** First-byte deadline for pipe/socket stdin (#3513). Env-overridable escape hatch. */
+function stdinFirstByteTimeoutMs(): number {
+  const n = Number(process.env.GBRAIN_STDIN_TIMEOUT_MS);
+  return Number.isFinite(n) && n > 0 ? n : 5000;
+}
+
+/**
+ * Returns the full stdin content, '' for a readable-but-empty stdin, or
+ * null when stdin is a pipe/socket that never delivered a byte within the
+ * first-byte deadline (or the fd is closed/unreadable).
+ */
+export async function readStdinBounded(): Promise<string | null> {
+  let isPipeOrSocket: boolean;
+  try {
+    const st = fstatSync(0);
+    isPipeOrSocket = st.isFIFO() || st.isSocket();
+  } catch {
+    return null; // closed/invalid fd — treat as no input
+  }
+  if (!isPipeOrSocket) {
+    // Regular file redirect, /dev/null, etc. — read returns without blocking.
+    try {
+      return readFileSync(0, 'utf-8');
+    } catch {
+      return null;
+    }
+  }
+  return await new Promise<string | null>((resolve) => {
+    const chunks: Buffer[] = [];
+    let gotData = false;
+    const timer = setTimeout(() => {
+      if (!gotData) {
+        process.stdin.destroy();
+        resolve(null);
+      }
+    }, stdinFirstByteTimeoutMs());
+    const finish = () => {
+      clearTimeout(timer);
+      resolve(Buffer.concat(chunks).toString('utf-8'));
+    };
+    process.stdin.on('data', (c: Buffer) => {
+      if (!gotData) {
+        gotData = true;
+        clearTimeout(timer); // deadline applies to the FIRST byte only
+      }
+      chunks.push(c);
+    });
+    process.stdin.once('end', finish);
+    process.stdin.once('error', finish);
+  });
 }
 
 /**
@@ -872,7 +958,8 @@ export function applyThinClientSourceScope(
   params.source_id = resolved;
 }
 
-async function makeContext(engine: BrainEngine, params: Record<string, unknown>): Promise<OperationContext> {
+// Exported for tests (same import-safety contract as applyThinClientSourceScope).
+export async function makeContext(engine: BrainEngine, params: Record<string, unknown>): Promise<OperationContext> {
   // v0.31.8 (D11): resolve sourceId via the canonical 6-tier chain. Honors
   // --source / GBRAIN_SOURCE / .gbrain-source / path-match / brain default /
   // 'default'. Wrapped in try/catch so a doctor / single-source brain that
@@ -884,16 +971,21 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
   // trusted local boundary) and consumed by federatedSearchScope in
   // operations.ts, which additionally gates on ctx.remote === false.
   let localFederated: string[] | undefined;
+  // params.source is set when a CLI flag was parsed for the op (rare; most
+  // CLI ops don't take --source). Falls through to env/dotfile/path-match.
+  const explicit = (params.source as string | undefined) ?? null;
   try {
     const { resolveSourceWithTier, localFederatedSourceIds } = await import('./core/source-resolver.ts');
-    // params.source is set when a CLI flag was parsed for the op (rare; most
-    // CLI ops don't take --source). Falls through to env/dotfile/path-match.
-    const explicit = (params.source as string | undefined) ?? null;
     const resolved = await resolveSourceWithTier(engine, explicit);
     sourceId = resolved.source_id;
     localFederated = await localFederatedSourceIds(engine, resolved.source_id, resolved.tier);
-  } catch {
-    // Source resolution failed (e.g. sources table doesn't exist on a fresh
+  } catch (err) {
+    // #1712: an EXPLICIT --source that fails to resolve (invalid id, or a
+    // source that doesn't exist) must error loudly — the blanket swallow
+    // turned `--source __all__` and typos into a silent `default` scope,
+    // which is how three bug reports became debugging sessions.
+    if (explicit) throw err;
+    // Ambient resolution failed (e.g. sources table doesn't exist on a fresh
     // pre-init brain). Leave sourceId unset; engine read methods fall through
     // to the cross-source view (D16 back-compat path).
     sourceId = undefined;
@@ -2448,6 +2540,7 @@ TOOLS
   publish <page.md> [--password]     Shareable HTML (strips private data, optional AES-256)
   check-backlinks <check|fix> [dir]  Find/fix missing back-links across brain
   lint <dir|file> [--fix]            Catch LLM artifacts, placeholder dates, bad frontmatter
+  backfill <kind|list>               v0.30.1: run a registered backfill (effective-date, ...)
   orphans [--json] [--count]         Find pages with no inbound wikilinks
   salience [--days N] [--kind P]     v0.29: pages ranked by emotional + activity salience
   anomalies [--since D] [--sigma N]  v0.29: cohort-based statistical anomalies (tag, type)

src/commands/embed.ts

@@ -19,6 +19,26 @@ import {
 } from '../core/pace-mode.ts';
 import { tryAcquireDbLock, type DbLockHandle } from '../core/db-lock.ts';
 import { embedBackfillLockId } from '../core/embed-backfill-lock.ts';
+import { wrapChunkTextsForStoredMode } from '../core/embedding-context.ts';
+import { titleTierCorpusGeneration } from '../core/contextual-retrieval-service.ts';
+import type { Page } from '../core/types.ts';
+
+/**
+ * #3507 — after a plain re-embed fully re-embedded a `per_chunk_synopsis`
+ * page at the title-only tier (see wrapChunkTextsForStoredMode), restamp the
+ * page's CR state to 'title' so `contextual_retrieval_mode` keeps describing
+ * the vectors actually in the column. The reindex sweep restores the synopsis
+ * tier later. No-op for every other mode.
+ */
+export async function restampIfDemotedToTitleTier(
+  engine: BrainEngine,
+  page: Pick<Page, 'contextual_retrieval_mode'> | null | undefined,
+  slug: string,
+  sourceId: string,
+): Promise<void> {
+  if (page?.contextual_retrieval_mode !== 'per_chunk_synopsis') return;
+  await engine.updatePageContextualRetrievalState(slug, sourceId, 'title', titleTierCorpusGeneration());
+}
 
 export interface EmbedOpts {
   /** Embed ALL pages (every chunk). */
@@ -599,7 +619,11 @@ async function embedPage(
     return;
   }
 
-  const embeddings = await embedBatch(toEmbed.map(c => c.chunk_text), { abortSignal: signal });
+  // #3507: embed with the page's STORED wrapping convention (title-tier
+  // contextual prefix when the page was embedded wrapped), not raw
+  // chunk_text — otherwise a re-embed silently strips the contextual
+  // prefixes the sync path applied. fenced_code chunks stay unwrapped.
+  const embeddings = await embedBatch(wrapChunkTextsForStoredMode(page, toEmbed), { abortSignal: signal });
   const embeddingMap = new Map<number, Float32Array>();
   for (let j = 0; j < toEmbed.length; j++) {
     embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
@@ -622,6 +646,9 @@ async function embedPage(
   // such a page and then stamps it.
   if (toEmbed.length === chunks.length) {
     await engine.setPageEmbeddingSignature(slug, { sourceId, signature: currentEmbeddingSignature() });
+    // #3507: a fully re-embedded per_chunk_synopsis page landed at the
+    // title tier — keep the stamped mode honest.
+    await restampIfDemotedToTitleTier(engine, page, slug, page.source_id);
   }
   result.embedded += toEmbed.length;
   result.pages_processed++;
@@ -763,7 +790,8 @@ async function embedAll(
     }
 
     try {
-      const embeddings = await embedBatch(toEmbed.map(c => c.chunk_text));
+      // #3507: reproduce the page's stored wrapping convention (see embedPage).
+      const embeddings = await embedBatch(wrapChunkTextsForStoredMode(page, toEmbed));
       // Build a map of new embeddings by chunk_index
       const embeddingMap = new Map<number, Float32Array>();
       for (let j = 0; j < toEmbed.length; j++) {
@@ -785,6 +813,11 @@ async function embedAll(
       await observed(pacer, () =>
         engine.setPageEmbeddingSignature(page.slug, { sourceId: pageSourceId, signature }),
       );
+      // #3507: --all fully re-embeds; a per_chunk_synopsis page landed at
+      // the title tier — keep the stamped mode honest.
+      await observed(pacer, () =>
+        restampIfDemotedToTitleTier(engine, page, page.slug, pageSourceId),
+      );
       result.embedded += toEmbed.length;
     } catch (e: unknown) {
       serr(`\n  Error embedding ${page.slug}: ${e instanceof Error ? e.message : e}`);
@@ -1098,7 +1131,13 @@ async function embedAllStale(
         const keySourceId = stale[0]?.source_id ?? 'default';
         const slug = stale[0].slug;
         try {
-          const embeddings = await embedBatchWithBackoff(stale.map(c => c.chunk_text), { abortSignal: effectiveSignal });
+          // #3507: fetch the page row for its title + stored CR mode so the
+          // re-embed reproduces the page's wrapping convention instead of
+          // silently stripping contextual prefixes — `embed --stale` is the
+          // NORMAL post-model-migration path, so raw-text embedding here
+          // quietly converted whole corpora to the unwrapped convention.
+          const pageRow = await observed(pacer, () => engine.getPage(slug, { sourceId: keySourceId }));
+          const embeddings = await embedBatchWithBackoff(wrapChunkTextsForStoredMode(pageRow, stale), { abortSignal: effectiveSignal });
           // Re-fetch existing chunks and merge to avoid deleting non-stale chunks.
           const existing = await observed(pacer, () => engine.getChunks(slug, { sourceId: keySourceId }));
           const staleIdxToEmbedding = new Map<number, Float32Array>();
@@ -1126,6 +1165,14 @@ async function embedAllStale(
               engine.setPageEmbeddingSignature(slug, { sourceId: keySourceId, signature }),
             );
           }
+          // #3507: a FULLY re-embedded per_chunk_synopsis page landed at the
+          // title tier — keep the stamped mode honest. Partially-stale pages
+          // stay stamped as-is (mixed provenance; reindex sweeps fix them).
+          if (stale.length === existing.length) {
+            await observed(pacer, () =>
+              restampIfDemotedToTitleTier(engine, pageRow, slug, keySourceId),
+            );
+          }
           result.embedded += stale.length;
         } catch (e: unknown) {
           // Budget/abort-fired cancellations are expected on the way out; don't

src/commands/jobs.ts

@@ -233,7 +233,7 @@ USAGE
   gbrain jobs get <id>
   gbrain jobs cancel <id>
   gbrain jobs retry <id>
-  gbrain jobs prune [--older-than 30d]
+  gbrain jobs prune [--older-than 30d] [--dry-run]
   gbrain jobs delete <id>
   gbrain jobs stats
   gbrain jobs smoke
@@ -633,8 +633,15 @@ HANDLER TYPES (built in)
       try { await queue.ensureSchema(); }
       catch (e) { console.error(e instanceof Error ? e.message : String(e)); process.exit(1); }
 
-      const count = await queue.prune({ olderThan: new Date(Date.now() - days * 86400000) });
-      console.log(`Pruned ${count} jobs older than ${days} days.`);
+      // #2712: --dry-run previews the count without deleting. It used to be
+      // silently ignored (the destructive default ran anyway).
+      const dryRun = hasFlag(args, '--dry-run');
+      const count = await queue.prune({ olderThan: new Date(Date.now() - days * 86400000), dryRun });
+      if (dryRun) {
+        console.log(`[dry-run] Would prune ${count} jobs older than ${days} days. Nothing deleted.`);
+      } else {
+        console.log(`Pruned ${count} jobs older than ${days} days.`);
+      }
       break;
     }
 

src/commands/takes.ts

@@ -3,6 +3,7 @@
  *
  * Subcommands:
  *   takes <slug>                          — list takes for a page
+ *   takes list                            — list all active takes (#2079)
  *   takes search "<query>" [--who h]       — keyword search across all takes
  *   takes add <slug> ...flags              — append a take (markdown + DB)
  *   takes update <slug> --row N ...flags   — update mutable fields
@@ -129,11 +130,10 @@ function writeBody(path: string, body: string): void {
 // --- Subcommands ---
 
 async function cmdList(engine: BrainEngine, args: string[]): Promise<void> {
-  const slug = args[0];
-  if (!slug) {
-    console.error('Usage: gbrain takes <slug> [--json]');
-    process.exit(1);
-  }
+  // #2079: slug is optional. `gbrain takes list` (no slug) lists ALL active
+  // takes — CLI parity with the takes_list operation. A leading flag is not
+  // a slug.
+  const slug = args[0] && !args[0].startsWith('-') ? args[0] : undefined;
   const json = flagPresent(args, '--json');
   const holder = flagValue(args, '--who');
   const kind = flagValue(args, '--kind') as string | undefined;
@@ -153,17 +153,19 @@ async function cmdList(engine: BrainEngine, args: string[]): Promise<void> {
     return;
   }
 
+  const scope = slug ?? 'this brain';
   if (takes.length === 0) {
-    console.log(`No takes on ${slug}.`);
+    console.log(`No takes on ${scope}.`);
     return;
   }
-  console.log(`# Takes on ${slug}\n`);
+  console.log(`# Takes on ${scope}\n`);
   for (const t of takes) {
     const tag = t.active ? '' : ' [superseded]';
     const w = Number(t.weight).toFixed(2);
     const since = t.since_date ?? '';
     const src = t.source ? ` — ${t.source}` : '';
-    console.log(`#${t.row_num} [${t.kind} • ${t.holder} • w=${w}${since ? ` • ${since}` : ''}]${tag}\n  ${t.claim}${src}\n`);
+    const where = slug ? '' : `${t.page_slug} `;
+    console.log(`${where}#${t.row_num} [${t.kind} • ${t.holder} • w=${w}${since ? ` • ${since}` : ''}]${tag}\n  ${t.claim}${src}\n`);
   }
 }
 
@@ -555,6 +557,8 @@ export async function runTakes(engine: BrainEngine, args: string[]): Promise<voi
 Subcommands:
   takes <slug> [--json] [--who h] [--kind k] [--sort weight|since_date|created_at] [--expired]
                                           List takes for a page
+  takes list [--json] [--who h] [--kind k] [--sort ...] [--expired]
+                                          List all active takes across the brain (#2079)
   takes search "<query>" [--limit N] [--json]
                                           Keyword search across all takes
   takes add <slug> --claim "..." --kind <fact|take|bet|hunch> --who <holder>
@@ -584,6 +588,9 @@ Common flags:
   const rest = args.slice(1);
 
   switch (sub) {
+    // #2079: `takes list` used to be parsed as page slug "list" and printed
+    // "No takes on list." — reading exactly like an empty takes table.
+    case 'list':        return cmdList(engine, rest);
     case 'search':      return cmdSearch(engine, rest);
     case 'add':         return cmdAdd(engine, rest, await resolveTakesSourceId(engine));
     case 'update':      return cmdUpdate(engine, rest, await resolveTakesSourceId(engine));

src/core/ai/gateway.ts

@@ -642,8 +642,42 @@ function warnRecipesMissingBatchTokens(): void {
   }
 }
 
-/** Reset (for tests). */
-export function resetGateway(): void {
+/**
+ * Test-only reset baseline (#3554). The bunfig preload
+ * (`test/helpers/legacy-embedding-preload.ts`) pins the gateway to the legacy
+ * OpenAI/1536 config at process start, but `resetGateway()` used to wipe that
+ * pin to `_config = null`. The next test file's engine connect then
+ * reconfigured from the SHIPPED default (zembed-1 @ 1280) and every 1536-d
+ * fixture in that file exploded with `expected 1280 dimensions, not 1536` —
+ * a cross-file mine whose placement depended on shard bin-packing.
+ *
+ * When a baseline factory is registered, `resetGateway()` means "back to the
+ * test baseline" instead of "unconfigured": it clears everything as before,
+ * then re-applies the factory's config via `configureGateway()`. A factory
+ * (not a frozen config) so each re-application captures fresh
+ * `process.env`, matching the preload's original `applyLegacy()` semantics.
+ *
+ * Production is untouched: nothing in `src/` calls `resetGateway()` or this
+ * setter, so in production the baseline is never registered and
+ * `resetGateway()` still fully unconfigures. Same `__*ForTests` seam
+ * convention as `__setEmbedTransportForTests` above.
+ */
+let _resetBaseline: (() => AIGatewayConfig) | null = null;
+
+/**
+ * Register (or clear, with `null`) the config factory that `resetGateway()`
+ * re-applies. Called once by the bunfig test preload.
+ *
+ * @internal exported for tests; not part of the public gateway API.
+ */
+export function __setGatewayResetBaselineForTests(
+  factory: (() => AIGatewayConfig) | null,
+): void {
+  _resetBaseline = factory;
+}
+
+/** Clear every piece of module state. Shared by both reset flavors. */
+function clearGatewayState(): void {
   _config = null;
   _modelCache.clear();
   _shrinkState.clear();
@@ -655,6 +689,33 @@ export function resetGateway(): void {
   _extendedModels.clear();
 }
 
+/**
+ * Reset (for tests). Clears all module state (config, model cache, shrink
+ * state, transports, warned recipes, extended models), then — if a test
+ * baseline is registered — re-applies it so the gateway returns to the
+ * process-wide test default instead of an unconfigured limbo (#3554).
+ */
+export function resetGateway(): void {
+  clearGatewayState();
+  // configureGateway re-clears _modelCache/_shrinkState/_extendedModels and
+  // registers the baseline's models; transports are NOT touched by it, so a
+  // stale test transport can never leak back in through this path.
+  if (_resetBaseline) configureGateway(_resetBaseline());
+}
+
+/**
+ * Reset AND stay unconfigured, ignoring any registered baseline. For the
+ * handful of tests that assert genuine no-gateway behavior
+ * (`no_gateway_config` diagnosis, `isAvailable() === false`, graceful
+ * degradation paths). The preload's per-test beforeEach restores the
+ * baseline before the next test, so this cannot leak across tests.
+ *
+ * @internal exported for tests; not part of the public gateway API.
+ */
+export function __unconfigureGatewayForTests(): void {
+  clearGatewayState();
+}
+
 /**
  * Test-only seam. Replaces the function the gateway calls to embed a
  * sub-batch. Pass `null` to restore the real `embedMany` from the AI SDK.

src/core/cjk.ts

@@ -21,12 +21,35 @@ export const CJK_SLUG_CHARS = '一-鿿぀-ゟ゠-ヿ가-힯';
 export const CJK_RANGES_REGEX = new RegExp(`[${CJK_SLUG_CHARS}]`);
 
 /**
- * Page-slug segment grammar (no anchors): alnum-or-CJK lead char, then
- * alnum/CJK/hyphen continuation. Single source for validatePageSlug
- * (operations.ts), SlugRegistry's SLUG_RE, and the dream-cycle
- * SUMMARY_SLUG_RE so every slug validator shares one grammar (#738).
+ * Slug "word" character class (#3417): every script's letters, not just
+ * Latin + CJK. Unicode property escapes — REQUIRES the `u` flag on any
+ * regex composed from this string (without `u`, `\p{Ll}` silently matches
+ * the literal chars `p`, `L`, `l`, `{`, `}`).
+ *
+ *   \p{Ll} lowercase letters (a-z, Cyrillic/Greek lowercase, đ, …)
+ *   \p{Lm} modifier letters
+ *   \p{Lo} caseless-script letters (Hebrew, Arabic, Thai, CJK, Devanagari, …)
+ *   \p{M}  combining marks that survive the Latin accent-strip pass
+ *          (Hebrew niqqud, Arabic harakat, Thai/Devanagari vowel signs)
+ *   \p{N}  numbers (0-9, Arabic-Indic digits, …)
+ *
+ * Uppercase (\p{Lu}/\p{Lt}) is deliberately excluded: slugifySegment()
+ * lowercases before filtering, so validators stay lowercase-canonical.
+ *
+ * Distinct from CJK_SLUG_CHARS above, which also drives the
+ * countCJKAwareWords density heuristic — do NOT merge the two, or slug
+ * grammar changes silently change chunking behavior.
  */
-export const PAGE_SLUG_SEG = `[a-z0-9${CJK_SLUG_CHARS}][a-z0-9${CJK_SLUG_CHARS}\\-]*`;
+export const SLUG_WORD_CHARS = '\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}\\p{N}';
+
+/**
+ * Page-slug segment grammar (no anchors): word-char lead, then word-char or
+ * hyphen continuation. Single source for validatePageSlug (operations.ts),
+ * SlugRegistry's SLUG_RE, and the dream-cycle SUMMARY_SLUG_RE so every slug
+ * validator shares one grammar (#738). Compose with the `u` flag — see
+ * SLUG_WORD_CHARS.
+ */
+export const PAGE_SLUG_SEG = `[${SLUG_WORD_CHARS}][${SLUG_WORD_CHARS}\\-]*`;
 
 export const CJK_SENTENCE_DELIMITERS = ['。', '！', '？']; // 。！？
 export const CJK_CLAUSE_DELIMITERS = ['；', '：', '，', '、']; // ；：，、

src/core/contextual-retrieval-service.ts

@@ -145,6 +145,19 @@ export function computeCorpusGeneration(args: {
   return h.digest('hex').slice(0, 16);
 }
 
+/**
+ * #3507 — the corpus_generation a page lands on when a plain re-embed path
+ * (`embed --stale` and friends) re-embeds a `per_chunk_synopsis` page at the
+ * title-only tier (the D14 fallback tier; synopsis re-generation is a paid
+ * backfill concern). Callers restamp
+ * `updatePageContextualRetrievalState(slug, sourceId, 'title', titleTierCorpusGeneration())`
+ * so the stamped mode keeps describing the vectors actually in the column.
+ * Matches what the inline import path writes for its title-tier pages.
+ */
+export function titleTierCorpusGeneration(): string {
+  return computeCorpusGeneration({ crMode: 'title', haikuModel: DEFAULT_HAIKU_MODEL });
+}
+
 /**
  * Compute source_text_hash for D27 P1-4 cache key composition. The
  * synopsis cache invalidates correctly when adjacent text changes (page

src/core/cycle.ts

@@ -1179,7 +1179,9 @@ async function runPhaseExtractFacts(
         summary: `extract_facts skipped: ${result.legacyRowsPending} legacy v0.31 facts pending fence backfill`,
         details: {
           legacyRowsPending: result.legacyRowsPending,
-          hint: 'gbrain apply-migrations --yes',
+          // A bare `apply-migrations --yes` no-ops once the v0.32.2 ledger
+          // entry is complete; the retry marker is what re-runs Phase B.
+          hint: 'gbrain apply-migrations --force-retry 0.32.2 && gbrain apply-migrations --yes',
           warnings: result.warnings,
         },
       };

src/core/cycle/extract-facts.ts

@@ -26,13 +26,17 @@
  *
  * Empty-fence guard (Codex R2-#7; #2484; #2646): the phase refuses to do
  * its destructive reconciliation pass when genuinely-backfillable legacy
- * rows still exist — `row_num IS NULL` (never fenced) AND `entity_slug`
- * resolves to a live page in this source (so the v0_32_2 migration's
- * Phase B could fence them) AND the row is not soft-expired
- * (`expired_at IS NULL`). Status returns `warn` with a hint to run
- * `gbrain apply-migrations --yes`. Without the guard, an interrupted
- * upgrade where v0_32_2 hasn't run could leave the cycle silently
- * misreporting "0 facts on people/alice" while legacy rows linger.
+ * rows still exist — in THIS run's source only (`source_id = sourceId`;
+ * a pending row in source A must not jam extraction for source B — the
+ * source-isolation invariant) — `row_num IS NULL` (never fenced) AND
+ * `entity_slug` resolves to a live page in this source (so the v0_32_2
+ * migration's Phase B could fence them) AND the row is not soft-expired
+ * (`expired_at IS NULL`). Status returns `warn` with a hint to re-run
+ * the v0.32.2 fence backfill (`apply-migrations --force-retry 0.32.2`
+ * then `--yes` — a bare `--yes` is a no-op once the ledger says
+ * complete). Without the guard, an interrupted upgrade where v0_32_2
+ * hasn't run could leave the cycle silently misreporting "0 facts on
+ * people/alice" while legacy rows linger.
  *
  * The live-page requirement (#2484) is load-bearing: the inline facts
  * writer keeps producing `row_num IS NULL, entity_slug IS NOT NULL`
@@ -225,10 +229,17 @@ export async function runExtractFacts(
   // soft-expires legacy rows rather than deleting them, so counting
   // expired rows would leave the guard permanently stuck with no
   // supported way to drain the backlog.
+  //
+  // Source isolation (#3526): the count is scoped to THIS run's
+  // sourceId. The pre-fix query counted brain-wide, so a single pending
+  // legacy row in any mounted source jammed extract_facts for every
+  // source — a cross-source leak of one source's migration state into
+  // another's cycle (CLAUDE.md source-isolation invariant).
   const legacy = await engine.executeRaw<{ n: string }>(
     `SELECT COUNT(*) AS n
        FROM facts f
-      WHERE f.row_num IS NULL
+      WHERE f.source_id = $1
+        AND f.row_num IS NULL
         AND f.entity_slug IS NOT NULL
         AND f.expired_at IS NULL
         AND EXISTS (
@@ -237,15 +248,25 @@ export async function runExtractFacts(
              AND p.slug = f.entity_slug
              AND p.deleted_at IS NULL
         )`,
+    [sourceId],
   );
   const legacyCount = parseInt(legacy[0]?.n ?? '0', 10);
   result.legacyRowsPending = legacyCount;
   if (legacyCount > 0) {
     result.guardTriggered = true;
+    // Drain advice must actually work: a bare `apply-migrations --yes`
+    // is a no-op once the v0.32.2 ledger entry says complete (the
+    // runner classifies it as already-applied), so the sanctioned
+    // re-run path is the explicit retry marker first. Phase B is
+    // idempotent — it only touches `row_num IS NULL` rows and de-dupes
+    // against the existing fence — so the re-run is safe. Individual
+    // rows can instead be drained through `forget_fact` (soft-expired
+    // rows stop counting).
     result.warnings.push(
-      `extract_facts: ${legacyCount} legacy v0.31 fact rows (entity page present, not yet ` +
-      `fenced) pending fence backfill. Run \`gbrain apply-migrations --yes\` to complete ` +
-      `v0_32_2 before this phase can safely reconcile fence → DB.`,
+      `extract_facts: ${legacyCount} legacy v0.31 fact rows in source "${sourceId}" ` +
+      `(entity page present, not yet fenced) pending fence backfill. Re-run the v0.32.2 ` +
+      `fence backfill: \`gbrain apply-migrations --force-retry 0.32.2\` then ` +
+      `\`gbrain apply-migrations --yes\`. Or drain individual rows via \`forget_fact\`.`,
     );
     return result;
   }

src/core/cycle/synthesize.ts

@@ -48,8 +48,9 @@ import { safeSplitIndex } from '../text-safe.ts';
 import { PAGE_SLUG_SEG } from '../cjk.ts';
 
 // Slug grammar from validatePageSlug — shared via PAGE_SLUG_SEG (#738).
-// Used for the orchestrator-written summary index slug.
-const SUMMARY_SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`);
+// Used for the orchestrator-written summary index slug. `u` flag required
+// by PAGE_SLUG_SEG's \p{...} classes (#3417).
+const SUMMARY_SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`, 'u');
 
 // ── Model context budget (D1, D5, D7, D9) ─────────────────────────────
 

src/core/embed-stale.ts

@@ -19,7 +19,8 @@
 
 import type { BrainEngine } from './engine.ts';
 import type { ChunkInput } from './types.ts';
-import { embedBatchWithBackoff } from '../commands/embed.ts';
+import { embedBatchWithBackoff, restampIfDemotedToTitleTier } from '../commands/embed.ts';
+import { wrapChunkTextsForStoredMode } from './embedding-context.ts';
 import { type DbPacer, createNoopPacer, observed } from './db-pacer.ts';
 import { AbortError } from './abort-check.ts';
 
@@ -189,8 +190,15 @@ export async function embedStaleForSource(
       const keySourceId = stale[0]?.source_id ?? sourceId;
       const slug = stale[0].slug;
       try {
+        // #3507: fetch the page row for its title + stored CR mode so the
+        // re-embed reproduces the page's wrapping convention instead of
+        // silently stripping contextual prefixes (mirrors
+        // src/commands/embed.ts:embedAllStale).
+        const pageRow = await observed(pacer, () =>
+          engine.getPage(slug, { sourceId: keySourceId }),
+        );
         const embeddings = await embedFn(
-          stale.map((c) => c.chunk_text),
+          wrapChunkTextsForStoredMode(pageRow, stale),
           { abortSignal: signal },
         );
         const existing = await observed(pacer, () =>
@@ -233,6 +241,13 @@ export async function embedStaleForSource(
             engine.setPageEmbeddingSignature(slug, { sourceId: keySourceId, signature }),
           );
         }
+        // #3507: a FULLY re-embedded per_chunk_synopsis page landed at the
+        // title tier — keep the stamped mode honest (mixed pages stay as-is).
+        if (stale.length === existing.length) {
+          await observed(pacer, () =>
+            restampIfDemotedToTitleTier(engine, pageRow, slug, keySourceId),
+          );
+        }
         result.embedded += stale.length;
         result.pagesProcessed += 1;
       } catch (e: unknown) {

src/core/embedding-context.ts

@@ -186,3 +186,41 @@ export function modeRequiresHaiku(mode: CRMode): boolean {
 export function modeRequiresWrapper(mode: CRMode): boolean {
   return mode !== 'none';
 }
+
+/**
+ * #3507 — build the embedding inputs for a re-embed of EXISTING chunk rows,
+ * reproducing the wrapping convention the page's vectors were originally
+ * built under (recorded in `pages.contextual_retrieval_mode`).
+ *
+ * Used by every plain re-embed path (`embed <slug>`, `embed --all`,
+ * `embed --stale`, the embed-backfill Minion loop). Before this helper those
+ * paths embedded raw `chunk_text`, so any re-embed — including the NORMAL
+ * post-model-migration `embed --stale` — silently replaced context-wrapped
+ * vectors with unwrapped ones, degrading retrieval with no signature change
+ * to show for it.
+ *
+ * Convention rules (embed PRESERVES conventions; changing them is
+ * sync/reindex's job):
+ *   - mode NULL/undefined/'none' → raw chunk_text (status quo).
+ *   - mode 'title'               → title-only prefix (pure string concat).
+ *   - mode 'per_chunk_synopsis'  → title-only prefix. Re-generating Haiku
+ *     synopses is a paid backfill concern; title-only is the service's own
+ *     documented fallback tier (D14). Callers that fully re-embed a page
+ *     this way should restamp the page to 'title' so the column stays
+ *     honest (see contextual-retrieval-service.ts:titleTierCorpusGeneration).
+ *   - `fenced_code` chunks are NEVER wrapped (D20-T4), same as sync.
+ */
+export function wrapChunkTextsForStoredMode(
+  page:
+    | { title?: string | null; contextual_retrieval_mode?: CRMode | null }
+    | null
+    | undefined,
+  chunks: ReadonlyArray<{ chunk_text: string; chunk_source?: string | null }>,
+): string[] {
+  const mode = page?.contextual_retrieval_mode;
+  if (mode == null || !modeRequiresWrapper(mode)) {
+    return chunks.map((c) => c.chunk_text);
+  }
+  const prefix = buildContextualPrefix(page?.title ?? '', null);
+  return chunks.map((c) => wrapChunkForEmbedding(c.chunk_text, prefix, c.chunk_source));
+}

src/core/extract/receipt-writer.ts

@@ -85,11 +85,21 @@ const RUN_ID_SHORT_LEN = 8;
 /**
  * Truncate a run id to the standard 8-char short form used in slug
  * paths. Idempotent — passing an already-short id returns it unchanged.
- * Non-hex / non-alphanumeric chars survive (op-checkpoint ids may
- * include dashes or other separators).
+ * Non-hex / non-alphanumeric chars survive INSIDE the short form
+ * (op-checkpoint ids may include dashes or other separators), but
+ * boundary hyphens are trimmed (#3443): `slugifySegment()` strips
+ * leading/trailing hyphens during repo sync, so a short form like
+ * 'propose-' (from propose-<timestamp> run ids) made the DB receipt
+ * slug and its Git-backed slug disagree — writing the receipt through
+ * to the repo created a normalized sibling instead of materializing
+ * the existing page. Invariant: slugifySegment(shortRunId(x)) ===
+ * shortRunId(x) for slug-safe run ids.
  */
 export function shortRunId(runId: string): string {
-  return runId.slice(0, RUN_ID_SHORT_LEN);
+  // ponytail: truncation-based discrimination is only as good as the run id's
+  // first 8 chars; families that need per-run uniqueness must front-load it.
+  const short = runId.slice(0, RUN_ID_SHORT_LEN).replace(/^-+|-+$/g, '');
+  return short || (runId ? 'run' : '');
 }
 
 /**

src/core/import-file.ts

@@ -1092,8 +1092,8 @@ export async function importFromFile(
         chunks: 0,
         error:
           `Filename "${relativePath}" produces no usable slug. ` +
-          `Add a "slug:" to the frontmatter, or rename the file to use ` +
-          `ASCII / Chinese / Japanese / Korean characters.`,
+          `Add a "slug:" to the frontmatter, or rename the file to include ` +
+          `at least one letter or number (any script).`,
       };
     }
   } else if (parsed.slug !== expectedSlug) {

src/core/minions/handler-timeouts.ts

@@ -43,6 +43,11 @@ export const HANDLER_DEFAULT_TIMEOUT_MS: Readonly<Record<string, number>> = {
   // few writes. Generous 10-min budget (vs the tight null-default) covers a
   // slow gateway without the 30-min loop budget.
   chronicle_extract: TEN_MIN_MS,
+  // #3207 — same shape as chronicle_extract: one page = one LLM extraction
+  // call + a few writes. Was missing from this map, so it inherited the tight
+  // null-default and got dead-lettered mid-generation on slow chat providers
+  // (facts silently lost) — exactly the failure this file exists to prevent.
+  'facts-absorb': TEN_MIN_MS,
   // Per-page contextual reindex jobs process chunks sequentially with one
   // rate-leased LLM synopsis call per chunk; large transcript pages need more
   // than the standard 30-min long-job budget.

src/core/minions/queue.ts

@@ -534,10 +534,21 @@ export class MinionQueue {
   }
 
   /** Prune old jobs in terminal statuses. Returns count of deleted rows. */
-  async prune(opts?: { olderThan?: Date; status?: MinionJobStatus[] }): Promise<number> {
+  async prune(opts?: { olderThan?: Date; status?: MinionJobStatus[]; dryRun?: boolean }): Promise<number> {
     const statuses = opts?.status ?? ['completed', 'dead', 'cancelled'];
     const olderThan = opts?.olderThan ?? new Date(Date.now() - 30 * 86400000);
 
+    // #2712: dryRun counts the would-be-pruned rows without deleting.
+    // Silent-ignoring a safety flag on a delete path is data loss.
+    if (opts?.dryRun) {
+      const rows = await this.engine.executeRaw<{ count: string }>(
+        `SELECT count(*)::text as count FROM minion_jobs
+         WHERE status = ANY($1) AND updated_at < $2`,
+        [statuses, olderThan.toISOString()]
+      );
+      return parseInt(rows[0]?.count ?? '0', 10);
+    }
+
     const rows = await this.engine.executeRaw<{ count: string }>(
       `WITH pruned AS (
          DELETE FROM minion_jobs

src/core/operations.ts

@@ -28,6 +28,7 @@ import { isSearchMode } from './search/mode.ts';
 import { stampEvidence } from './search/evidence.ts';
 import type { SearchResult } from './types.ts';
 import { CJK_SLUG_CHARS, PAGE_SLUG_SEG } from './cjk.ts';
+import { ALL_SOURCES } from './source-id.ts';
 import * as db from './db.ts';
 import { VERSION } from '../version.ts';
 import {
@@ -162,10 +163,11 @@ export function validatePageSlug(slug: string): void {
   if (slug.length > 255) {
     throw new OperationError('invalid_params', 'page_slug exceeds 255 characters');
   }
-  // v0.32.7: CJK ranges (Han / Hiragana / Katakana / Hangul Syllables) allowed
-  // in segments. ASCII shape rules (lead char, hyphen continuation) preserved.
-  if (!new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`, 'i').test(slug)) {
-    throw new OperationError('invalid_params', `Invalid page_slug: ${slug} (allowed: alphanumeric, CJK, hyphens, forward-slash separated segments)`);
+  // #3417: letters/numbers from any script allowed in segments (u flag required
+  // for the \p{...} classes in PAGE_SLUG_SEG). Shape rules (lead char, hyphen
+  // continuation) preserved.
+  if (!new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`, 'iu').test(slug)) {
+    throw new OperationError('invalid_params', `Invalid page_slug: ${slug} (allowed: letters/numbers in any script, hyphens, forward-slash separated segments)`);
   }
 }
 
@@ -486,6 +488,14 @@ export function sourceScopeOpts(ctx: OperationContext): { sourceId?: string; sou
   // value of `[]` MUST NOT widen scope to "all sources" by being interpreted
   // as "no filter."
   if (allowed && allowed.length > 0) return { sourceIds: allowed };
+  // #1712: the __all__ sentinel spans the brain — but ONLY for trusted local
+  // callers (strictly `remote === false`). For remote/untrusted callers the
+  // literal stays as-is: it can never match a real source id (underscores are
+  // rejected at creation), so the read fail-closes to empty rather than
+  // widening past the caller's grant. Do NOT "simplify" this to `{}`.
+  if (ctx.sourceId === ALL_SOURCES) {
+    return ctx.remote === false ? {} : { sourceId: ctx.sourceId };
+  }
   if (ctx.sourceId) return { sourceId: ctx.sourceId };
   return {};
 }
@@ -553,7 +563,7 @@ export function resolveRequestedScope(
   sourceIdParam: string | undefined,
   allSourcesParam = false,
 ): { sourceId?: string; sourceIds?: string[] } {
-  const wantsAll = allSourcesParam || sourceIdParam === '__all__';
+  const wantsAll = allSourcesParam || sourceIdParam === ALL_SOURCES;
   if (wantsAll) {
     return ctx.remote === false ? {} : sourceScopeOpts(ctx);
   }

src/core/output/slug-registry.ts

@@ -72,9 +72,10 @@ export class SlugRegistryError extends Error {
 // SlugRegistry
 // ---------------------------------------------------------------------------
 
-// Shares the page-slug segment grammar (incl. CJK ranges, #738) with
+// Shares the page-slug segment grammar (all scripts, #738/#3417) with
 // validatePageSlug; keeps this site's dir/name shape (>= 2 segments).
-const SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})+$`);
+// `u` flag required by PAGE_SLUG_SEG's \p{...} classes.
+const SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})+$`, 'u');
 
 export class SlugRegistry {
   constructor(private engine: BrainEngine) {}

src/core/pglite-engine.ts

@@ -420,8 +420,10 @@ export class PGLiteEngine implements BrainEngine {
     let model: string = DEFAULT_EMBEDDING_MODEL;
     try {
       const gw = await import('./ai/gateway.ts');
+      // Both accessors THROW when the gateway is unconfigured (they never
+      // return falsy), so the catch below is the only fallback path (#3461).
       dims = gw.getEmbeddingDimensions();
-      model = gw.getEmbeddingModel() || model;
+      model = gw.getEmbeddingModel();
     } catch { /* gateway not configured — use defaults */ }
 
     await this.db.exec(getPGLiteSchema(dims, model));
@@ -979,7 +981,8 @@ export class PGLiteEngine implements BrainEngine {
     const { rows } = await this.db.query(
       `SELECT id, source_id, slug, type, title, compiled_truth, timeline, frontmatter, content_hash, created_at, updated_at, deleted_at,
               effective_date, effective_date_source,
-              source_kind, source_uri, ingested_via, ingested_at
+              source_kind, source_uri, ingested_via, ingested_at,
+              contextual_retrieval_mode
        FROM pages WHERE ${where.join(' AND ')} LIMIT 1`,
       params
     );
@@ -2320,15 +2323,26 @@ export class PGLiteEngine implements BrainEngine {
 
     // Provenance fallback for chunks without an explicit `model`: resolve the
     // gateway's runtime model, not the compile-time DEFAULT_EMBEDDING_MODEL.
-    // See postgres-engine.ts _upsertChunksOnce for the full rationale — pglite
-    // mirrors it for parity.
-    let resolvedModel: string = DEFAULT_EMBEDDING_MODEL;
+    // #3461: getEmbeddingModel() THROWS when unconfigured (never returns
+    // falsy) — on the throw path fall back to the brain's own
+    // `config.embedding_model` row, then the compile-time default as the
+    // last resort. See postgres-engine.ts _upsertChunksOnce for the full
+    // rationale — pglite mirrors it for parity.
+    let resolvedModel: string | null = null;
     try {
       const gw = await import('./ai/gateway.ts');
-      resolvedModel = gw.getEmbeddingModel() || resolvedModel;
+      resolvedModel = gw.getEmbeddingModel();
     } catch {
-      // Gateway unconfigured (unit tests / pre-connect): keep the default.
+      try {
+        const cfg = await this.db.query(
+          `SELECT value FROM config WHERE key = 'embedding_model'`,
+        );
+        resolvedModel = ((cfg.rows[0] as { value?: string } | undefined)?.value) ?? null;
+      } catch {
+        // config table unreadable — fall through to the compile-time default.
+      }
     }
+    if (!resolvedModel) resolvedModel = DEFAULT_EMBEDDING_MODEL;
 
     for (const chunk of chunks) {
       const embeddingStr = chunk.embedding
@@ -2381,6 +2395,9 @@ export class PGLiteEngine implements BrainEngine {
     // Code-chunk metadata columns follow the same chunk_text-gated CASE pattern as `embedding`
     // (#769). Re-chunk trusts EXCLUDED outright; pure re-embed COALESCEs so a caller carrying
     // only embedding-shaped fields doesn't clobber metadata to NULL.
+    //
+    // #3461: `model` mirrors the `embedding` CASE branch-for-branch so the label always
+    // describes whichever vector wins the upsert. See postgres-engine.ts for rationale.
     await this.db.query(
       `INSERT INTO content_chunks ${cols} VALUES ${rowParts.join(', ')}
        ON CONFLICT (page_id, chunk_index) DO UPDATE SET
@@ -2394,7 +2411,14 @@ export class PGLiteEngine implements BrainEngine {
                 THEN EXCLUDED.embedding
            ELSE content_chunks.embedding
          END,
-         model = COALESCE(EXCLUDED.model, content_chunks.model),
+         model = CASE
+           WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.model
+           WHEN content_chunks.embedding IS NULL THEN EXCLUDED.model
+           WHEN EXCLUDED.embedded_at IS NOT NULL
+                AND (content_chunks.embedded_at IS NULL OR EXCLUDED.embedded_at > content_chunks.embedded_at)
+                THEN EXCLUDED.model
+           ELSE content_chunks.model
+         END,
          token_count = EXCLUDED.token_count,
          embedded_at = CASE
            WHEN EXCLUDED.chunk_text != content_chunks.chunk_text AND EXCLUDED.embedding IS NULL THEN NULL
@@ -5308,12 +5332,16 @@ export class PGLiteEngine implements BrainEngine {
     // pages_with_timeline) and v0.10.3 graph layer (link_coverage, timeline_coverage,
     // most_connected). Both coexist: master's brain_score is the composite
     // dashboard, v0.10.3 metrics give entity-page-level granularity.
+    // #1305: every page-scoped count here excludes soft-deleted rows — same
+    // posture as getStats — so brain_score moves when the user deletes pages.
+    // Chunk/link counts stay raw (storage until the purge phase), matching
+    // getStats, and destructive-removal counts elsewhere deliberately stay raw.
     const { rows: [h] } = await this.db.query(`
       WITH entity_pages AS (
-        SELECT id, slug FROM pages WHERE type IN ('entity', 'person', 'company')
+        SELECT id, slug FROM pages WHERE type IN ('entity', 'person', 'company') AND deleted_at IS NULL
       )
       SELECT
-        (SELECT count(*) FROM pages) as page_count,
+        (SELECT count(*) FROM pages WHERE deleted_at IS NULL) as page_count,
         (SELECT count(*) FROM content_chunks WHERE embedded_at IS NOT NULL)::float /
           GREATEST((SELECT count(*) FROM content_chunks), 1)::float as embed_coverage,
         0 as stale_pages,
@@ -5338,7 +5366,7 @@ export class PGLiteEngine implements BrainEngine {
       SELECT p.slug,
              (SELECT count(*) FROM links l WHERE l.from_page_id = p.id OR l.to_page_id = p.id)::int as link_count
       FROM pages p
-      WHERE p.type IN ('entity', 'person', 'company')
+      WHERE p.type IN ('entity', 'person', 'company') AND p.deleted_at IS NULL
       ORDER BY link_count DESC
       LIMIT 5
     `);
@@ -5357,6 +5385,7 @@ export class PGLiteEngine implements BrainEngine {
               AND NOT EXISTS (SELECT 1 FROM links l WHERE l.from_page_id = p.id)) as islanded,
              EXISTS (SELECT 1 FROM timeline_entries te WHERE te.page_id = p.id) as has_timeline
       FROM pages p
+      WHERE p.deleted_at IS NULL
     `);
 
     const r = h as Record<string, unknown>;

src/core/postgres-engine.ts

@@ -382,8 +382,10 @@ export class PostgresEngine implements BrainEngine {
     let model: string = DEFAULT_EMBEDDING_MODEL;
     try {
       const gw = await import('./ai/gateway.ts');
+      // Both accessors THROW when the gateway is unconfigured (they never
+      // return falsy), so the catch below is the only fallback path (#3461).
       dims = gw.getEmbeddingDimensions();
-      model = gw.getEmbeddingModel() || model;
+      model = gw.getEmbeddingModel();
     } catch { /* gateway not yet configured — use defaults */ }
 
     const sqlText = getPostgresSchema(dims, model);
@@ -1031,7 +1033,8 @@ export class PostgresEngine implements BrainEngine {
       const rows = await tx`
         SELECT id, source_id, slug, type, title, compiled_truth, timeline, frontmatter, content_hash, created_at, updated_at, deleted_at,
                effective_date, effective_date_source,
-               source_kind, source_uri, ingested_via, ingested_at
+               source_kind, source_uri, ingested_via, ingested_at,
+               contextual_retrieval_mode
         FROM pages
         WHERE slug = ${slug} ${sourceCondition} ${deletedCondition}
         LIMIT 1
@@ -2437,14 +2440,28 @@ export class PostgresEngine implements BrainEngine {
     // hardcoded default (e.g. zeroentropyai:zembed-1) onto rows whose vectors
     // were produced by a different, config-resolved model — corrupting the
     // provenance that signature-drift staleness + dim-migration logic trust.
-    // Mirrors the resolve-then-fallback pattern used for schema sizing above.
-    let resolvedModel: string = DEFAULT_EMBEDDING_MODEL;
+    //
+    // #3461: getEmbeddingModel() THROWS when the gateway is unconfigured —
+    // it never returns falsy — so an `||` guard here is dead code and the
+    // catch path used to stamp the compile-time default onto rows whose
+    // vectors came from the config-resolved provider. On the throw path we
+    // now fall back to the brain's own `config.embedding_model` row (kept
+    // current by init / migrate / retrieval-upgrade), which names the model
+    // that actually produced this brain's vectors. The compile-time default
+    // is the LAST resort (fresh brain whose config row doesn't exist yet).
+    let resolvedModel: string | null = null;
     try {
       const gw = await import('./ai/gateway.ts');
-      resolvedModel = gw.getEmbeddingModel() || resolvedModel;
+      resolvedModel = gw.getEmbeddingModel();
     } catch {
-      // Gateway unconfigured (unit tests / pre-connect): keep the default.
+      try {
+        const cfg = await sql`SELECT value FROM config WHERE key = 'embedding_model'`;
+        resolvedModel = (cfg[0]?.value as string | undefined) ?? null;
+      } catch {
+        // config table unreadable — fall through to the compile-time default.
+      }
     }
+    if (!resolvedModel) resolvedModel = DEFAULT_EMBEDDING_MODEL;
 
     for (const chunk of chunks) {
       const embeddingStr = chunk.embedding
@@ -2508,6 +2525,11 @@ export class PostgresEngine implements BrainEngine {
     // pure re-embed (chunk_text unchanged) COALESCEs so a caller that only carries embedding
     // doesn't clobber metadata to NULL. Without this, every embed --stale pass nuked code-def's
     // primary index for thousands of chunks at once.
+    //
+    // #3461: `model` mirrors the `embedding` CASE branch-for-branch — the label must
+    // describe whichever vector WINS the upsert. The old COALESCE(EXCLUDED.model, …)
+    // relabeled preserved (older-model) vectors with the current gateway model on every
+    // partial re-embed, corrupting provenance without changing the vector.
     await sql.unsafe(
       `INSERT INTO content_chunks ${cols} VALUES ${rows.join(', ')}
        ON CONFLICT (page_id, chunk_index) DO UPDATE SET
@@ -2521,7 +2543,14 @@ export class PostgresEngine implements BrainEngine {
                 THEN EXCLUDED.embedding
            ELSE content_chunks.embedding
          END,
-         model = COALESCE(EXCLUDED.model, content_chunks.model),
+         model = CASE
+           WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.model
+           WHEN content_chunks.embedding IS NULL THEN EXCLUDED.model
+           WHEN EXCLUDED.embedded_at IS NOT NULL
+                AND (content_chunks.embedded_at IS NULL OR EXCLUDED.embedded_at > content_chunks.embedded_at)
+                THEN EXCLUDED.model
+           ELSE content_chunks.model
+         END,
          token_count = EXCLUDED.token_count,
          embedded_at = CASE
            WHEN EXCLUDED.chunk_text != content_chunks.chunk_text AND EXCLUDED.embedding IS NULL THEN NULL
@@ -5403,12 +5432,16 @@ export class PostgresEngine implements BrainEngine {
     // no outbound links). The raw islanded list is filtered through the same
     // policy as `gbrain orphans` so convention pages do not count against
     // dashboard health.
+    // #1305: every page-scoped count here excludes soft-deleted rows — same
+    // posture as getStats — so brain_score moves when the user deletes pages.
+    // Chunk/link counts stay raw (storage until the purge phase), matching
+    // getStats, and destructive-removal counts elsewhere deliberately stay raw.
     const [h] = await sql`
       WITH entity_pages AS (
-        SELECT id, slug FROM pages WHERE type IN ('entity', 'person', 'company')
+        SELECT id, slug FROM pages WHERE type IN ('entity', 'person', 'company') AND deleted_at IS NULL
       )
       SELECT
-        (SELECT count(*) FROM pages) as page_count,
+        (SELECT count(*) FROM pages WHERE deleted_at IS NULL) as page_count,
         (SELECT count(*) FROM content_chunks WHERE embedded_at IS NOT NULL)::float /
           GREATEST((SELECT count(*) FROM content_chunks), 1)::float as embed_coverage,
         0 as stale_pages,
@@ -5430,7 +5463,7 @@ export class PostgresEngine implements BrainEngine {
       SELECT p.slug,
              (SELECT count(*) FROM links l WHERE l.from_page_id = p.id OR l.to_page_id = p.id)::int as link_count
       FROM pages p
-      WHERE p.type IN ('entity', 'person', 'company')
+      WHERE p.type IN ('entity', 'person', 'company') AND p.deleted_at IS NULL
       ORDER BY link_count DESC
       LIMIT 5
     `;
@@ -5449,6 +5482,7 @@ export class PostgresEngine implements BrainEngine {
               AND NOT EXISTS (SELECT 1 FROM links l WHERE l.from_page_id = p.id)) as islanded,
              EXISTS (SELECT 1 FROM timeline_entries te WHERE te.page_id = p.id) as has_timeline
       FROM pages p
+      WHERE p.deleted_at IS NULL
     `;
 
     const pageCount = Number(h.page_count);

src/core/source-id.ts

@@ -33,6 +33,17 @@
 
 export const SOURCE_ID_RE = /^[a-z0-9](?:[a-z0-9-]{0,30}[a-z0-9])?$/;
 
+/**
+ * Sentinel meaning "span every source" (#1712). Deliberately NOT a valid
+ * source id (underscores are rejected by SOURCE_ID_RE), so it can never
+ * collide with a real source, be created via `sources add`, or leak into
+ * lock ids / path joins. The resolver's explicit/env tiers pass it through
+ * verbatim; `sourceScopeOpts` translates it to an unscoped read for trusted
+ * local callers and keeps it as an unsatisfiable literal for remote callers
+ * (fail-closed).
+ */
+export const ALL_SOURCES = '__all__';
+
 /** Returns true if the string matches the canonical source_id regex. */
 export function isValidSourceId(s: unknown): s is string {
   return typeof s === 'string' && SOURCE_ID_RE.test(s);

src/core/source-resolver.ts

@@ -17,9 +17,13 @@ import { readFileSync, lstatSync, type Stats } from 'fs';
 import { join, dirname, resolve } from 'path';
 import type { BrainEngine } from './engine.ts';
 import { isSourceFederated } from './sources-load.ts';
-import { SOURCE_ID_RE, isValidSourceId } from './source-id.ts';
+import { SOURCE_ID_RE, isValidSourceId, ALL_SOURCES } from './source-id.ts';
 import { isTrustedDotfile, realpathOrResolve } from './path-confine.ts';
 
+// Re-export so scope-resolution call sites can import the sentinel from
+// either module (#1712).
+export { ALL_SOURCES };
+
 const DOTFILE = '.gbrain-source';
 // Canonical SOURCE_ID_RE imported from `source-id.ts` (single source of truth).
 // Re-exported below as `__testing.SOURCE_ID_RE` for legacy test imports.
@@ -83,8 +87,11 @@ export async function resolveSourceId(
   explicit: string | null | undefined,
   cwd: string = process.cwd(),
 ): Promise<string> {
-  // 1. Explicit flag wins.
+  // 1. Explicit flag wins. The __all__ sentinel passes through verbatim
+  //    (#1712) — it is not a source id, so it skips both the regex and
+  //    assertSourceExists; sourceScopeOpts gives it span-everything semantics.
   if (explicit) {
+    if (explicit === ALL_SOURCES) return ALL_SOURCES;
     if (!SOURCE_ID_RE.test(explicit)) {
       throw new Error(`Invalid --source value "${explicit}". Must match [a-z0-9-]{1,32}.`);
     }
@@ -92,9 +99,10 @@ export async function resolveSourceId(
     return explicit;
   }
 
-  // 2. Env var.
+  // 2. Env var. Same __all__ pass-through (#2140).
   const env = process.env.GBRAIN_SOURCE;
   if (env && env.length > 0) {
+    if (env === ALL_SOURCES) return ALL_SOURCES;
     if (!SOURCE_ID_RE.test(env)) {
       throw new Error(`Invalid GBRAIN_SOURCE value "${env}". Must match [a-z0-9-]{1,32}.`);
     }
@@ -173,6 +181,7 @@ export function resolveSourceIdEngineFree(
   cwd: string = process.cwd(),
 ): string | null {
   if (explicit) {
+    if (explicit === ALL_SOURCES) return ALL_SOURCES; // #1712 sentinel pass-through
     if (!SOURCE_ID_RE.test(explicit)) {
       throw new Error(`Invalid --source value "${explicit}". Must match [a-z0-9-]{1,32}.`);
     }
@@ -180,6 +189,7 @@ export function resolveSourceIdEngineFree(
   }
   const env = process.env.GBRAIN_SOURCE;
   if (env && env.length > 0) {
+    if (env === ALL_SOURCES) return ALL_SOURCES; // #2140 sentinel pass-through
     if (!SOURCE_ID_RE.test(env)) {
       throw new Error(`Invalid GBRAIN_SOURCE value "${env}". Must match [a-z0-9-]{1,32}.`);
     }
@@ -315,8 +325,11 @@ export async function resolveSourceWithTier(
   explicit: string | null | undefined,
   cwd: string = process.cwd(),
 ): Promise<{ source_id: string; tier: SourceTier; detail?: string }> {
-  // 1. Explicit flag wins.
+  // 1. Explicit flag wins. __all__ sentinel passes through verbatim (#1712).
   if (explicit) {
+    if (explicit === ALL_SOURCES) {
+      return { source_id: ALL_SOURCES, tier: 'flag', detail: `--source ${ALL_SOURCES} (spans all sources)` };
+    }
     if (!SOURCE_ID_RE.test(explicit)) {
       throw new Error(`Invalid --source value "${explicit}". Must match [a-z0-9-]{1,32}.`);
     }
@@ -324,9 +337,12 @@ export async function resolveSourceWithTier(
     return { source_id: explicit, tier: 'flag', detail: `--source ${explicit}` };
   }
 
-  // 2. Env var.
+  // 2. Env var. Same __all__ pass-through (#2140).
   const env = process.env.GBRAIN_SOURCE;
   if (env && env.length > 0) {
+    if (env === ALL_SOURCES) {
+      return { source_id: ALL_SOURCES, tier: 'env', detail: `GBRAIN_SOURCE=${ALL_SOURCES} (spans all sources)` };
+    }
     if (!SOURCE_ID_RE.test(env)) {
       throw new Error(`Invalid GBRAIN_SOURCE value "${env}". Must match [a-z0-9-]{1,32}.`);
     }

src/core/sync.ts

@@ -11,7 +11,7 @@
  *   pathToSlug()  →  convert file paths to page slugs
  */
 
-import { CJK_SLUG_CHARS } from './cjk.ts';
+import { SLUG_WORD_CHARS } from './cjk.ts';
 // v0.37.7.0 #1169 submodule-detection helpers. Bottom-of-file already
 // aliases existsSync as `_existsSync` for other purposes; the top-of-file
 // import keeps the pruneDir helper's deps near its callsite.
@@ -396,8 +396,10 @@ export function unsyncableReason(path: string, opts: SyncableOptions = {}): Sync
 
 /**
  * Character class for the lowercase-canonical form of a slug segment after
- * slugifySegment() has run. Lowercase letters, digits, dots, underscores,
- * hyphens. Exposed so adjacent code (e.g. takes-fence holder validation,
+ * slugifySegment() has run. Letters/numbers in any script (lowercase where
+ * the script has case — #3417), dots, underscores, hyphens. Uses \p{...}
+ * classes, so composed regexes need the `u` flag (this one carries it).
+ * Exposed so adjacent code (e.g. takes-fence holder validation,
  * v0.32 EXP-4) can reuse the actual repo slug grammar instead of inventing
  * a stricter parallel one and emitting false-positive warnings on legitimate
  * `companies/acme.io` / `people/foo_bar` slugs (codex review #3).
@@ -405,15 +407,18 @@ export function unsyncableReason(path: string, opts: SyncableOptions = {}): Sync
  * Pattern is the inner character class only (no anchors); callers wrap it
  * in `^...$` or compose it with prefixes like `(?:people|companies)/...`.
  */
-export const SLUG_SEGMENT_PATTERN = new RegExp(`[a-z0-9._\\-${CJK_SLUG_CHARS}]+`);
+export const SLUG_SEGMENT_PATTERN = new RegExp(`[${SLUG_WORD_CHARS}._\\-]+`, 'u');
 
 /**
  * Slugify a single path segment: lowercase, strip special chars, spaces → hyphens.
- * CJK ranges (Han / Hiragana / Katakana / Hangul Syllables) are preserved (v0.32.7).
- * NFC re-normalize after the NFD-strip-accents pass so Hangul Jamo recomposes back
- * into precomposed syllables that fall inside the whitelist.
+ * Letters and numbers from EVERY script are preserved (#3417): previously only
+ * Latin + CJK survived, so Hebrew/Arabic/Cyrillic/Greek/Thai/... filenames
+ * collapsed to empty segments and distinct files silently merged onto one slug.
+ * NFC re-normalize after the NFD-strip-accents pass so Hangul Jamo recomposes
+ * back into precomposed syllables, and so NFD filenames (macOS) and NFC
+ * filenames (Linux/git) of the same name produce the SAME slug.
  */
-const SLUGIFY_KEEP_RE = new RegExp(`[^a-z0-9.\\s_\\-${CJK_SLUG_CHARS}]`, 'g');
+const SLUGIFY_KEEP_RE = new RegExp(`[^${SLUG_WORD_CHARS}.\\s_\\-]`, 'gu');
 
 export function slugifySegment(segment: string): string {
   return segment

src/core/takes-fence.ts

@@ -134,6 +134,7 @@ export const TAKES_FENCE_END   = '<!--- gbrain:takes:end -->';
 import { SLUG_SEGMENT_PATTERN } from './sync.ts';
 export const HOLDER_REGEX = new RegExp(
   `^(?:world|brain|(?:people|companies)/${SLUG_SEGMENT_PATTERN.source}|${SLUG_SEGMENT_PATTERN.source})$`,
+  'u', // required by SLUG_SEGMENT_PATTERN's \p{...} classes (#3417)
 );
 
 /**

src/core/utils.ts

@@ -110,6 +110,12 @@ export function rowToPage(row: Record<string, unknown>): Page {
   const sourceUri = row.source_uri === undefined ? undefined : (row.source_uri as string | null);
   const ingestedVia = row.ingested_via === undefined ? undefined : (row.ingested_via as string | null);
   const ingestedAt = readOptionalDate(row.ingested_at);
+  // #3507: the CR tier the page was last embedded under (three-state, same
+  // pattern as the provenance columns above). Re-embed paths (`embed --stale`
+  // and friends) read this to reproduce the page's stored wrapping convention.
+  const contextualRetrievalMode = row.contextual_retrieval_mode === undefined
+    ? undefined
+    : (row.contextual_retrieval_mode as Page['contextual_retrieval_mode']);
   return {
     id: row.id as number,
     slug: row.slug as string,
@@ -135,6 +141,7 @@ export function rowToPage(row: Record<string, unknown>): Page {
     ...(sourceUri !== undefined && { source_uri: sourceUri }),
     ...(ingestedVia !== undefined && { ingested_via: ingestedVia }),
     ...(ingestedAt !== undefined && { ingested_at: ingestedAt }),
+    ...(contextualRetrievalMode !== undefined && { contextual_retrieval_mode: contextualRetrievalMode }),
     // v0.31.12: propagate source_id so downstream callers (embed, reconcile-links)
     // can thread it through getChunks / upsertChunks without defaulting to 'default'.
     // v0.32.8: Page.source_id is required. Every SELECT feeding rowToPage now

test/ai/gateway-reset-baseline.test.ts

@@ -0,0 +1,68 @@
+/**
+ * #3554 — resetGateway() must restore the test baseline, not unconfigure.
+ *
+ * The bunfig preload (test/helpers/legacy-embedding-preload.ts) pins the
+ * gateway to openai:text-embedding-3-large @ 1536 at process start and
+ * registers that config as the reset baseline. Before the fix,
+ * resetGateway() wiped the pin to _config = null; the next file's beforeAll
+ * engine-connect then reconfigured from the SHIPPED default (zembed-1 @
+ * 1280) and every 1536-d fixture in that file failed with
+ * `expected 1280 dimensions, not 1536`. Which file pairs collided depended
+ * on shard bin-packing, so adding ANY test file reshuffled the mines.
+ *
+ * These assertions pin the contract so it cannot silently rot again.
+ */
+import { describe, test, expect, afterEach } from 'bun:test';
+import {
+  configureGateway,
+  resetGateway,
+  __unconfigureGatewayForTests,
+  __setChatTransportForTests,
+  getEmbeddingModel,
+  getEmbeddingDimensions,
+  isAvailable,
+} from '../../src/core/ai/gateway.ts';
+
+afterEach(() => resetGateway());
+
+describe('resetGateway baseline restore (#3554)', () => {
+  test('immediately after resetGateway(), the preload baseline is live', () => {
+    resetGateway();
+    expect(getEmbeddingModel()).toBe('openai:text-embedding-3-large');
+    expect(getEmbeddingDimensions()).toBe(1536);
+  });
+
+  test('resetGateway() overwrites a file-local config back to the baseline', () => {
+    configureGateway({
+      embedding_model: 'zeroentropyai:zembed-1',
+      embedding_dimensions: 1280,
+      env: {},
+    });
+    expect(getEmbeddingDimensions()).toBe(1280);
+    resetGateway();
+    expect(getEmbeddingModel()).toBe('openai:text-embedding-3-large');
+    expect(getEmbeddingDimensions()).toBe(1536);
+  });
+
+  test('resetGateway() still clears test transports (no stale transport leaks back)', () => {
+    __setChatTransportForTests(async () => {
+      throw new Error('should have been cleared');
+    });
+    resetGateway();
+    // Baseline config sets no chat key in a keyless env, but the transport
+    // seam itself must be gone: isAvailable('chat') short-circuits to true
+    // whenever a chat transport is installed, so with a hard-unconfigured
+    // gateway it can only be true if the transport survived the reset.
+    __unconfigureGatewayForTests();
+    expect(isAvailable('chat')).toBe(false);
+  });
+
+  test('__unconfigureGatewayForTests() gives a genuinely unconfigured gateway', () => {
+    __unconfigureGatewayForTests();
+    expect(() => getEmbeddingDimensions()).toThrow(/not configured/);
+    expect(isAvailable('embedding')).toBe(false);
+    // And a plain reset brings the baseline back.
+    resetGateway();
+    expect(getEmbeddingDimensions()).toBe(1536);
+  });
+});

test/ai/gateway.test.ts

@@ -2,6 +2,7 @@ import { describe, test, expect, beforeEach, afterAll } from 'bun:test';
 import {
   configureGateway,
   resetGateway,
+  __unconfigureGatewayForTests,
   isAvailable,
   embed,
   getEmbeddingModel,
@@ -55,6 +56,9 @@ describe('gateway.isAvailable (silent-drop regression surface)', () => {
   beforeEach(() => resetGateway());
 
   test('returns false when gateway not configured', () => {
+    // resetGateway() restores the preload's test baseline (#3554); go
+    // genuinely unconfigured for this one assertion.
+    __unconfigureGatewayForTests();
     expect(isAvailable('embedding')).toBe(false);
   });
 

test/all-sources-sentinel.test.ts

@@ -0,0 +1,176 @@
+/**
+ * #1712 (dupes #2289, #2140) — the `__all__` sentinel must work in EVERY
+ * resolution tier, not just as a per-call `source_id` param.
+ *
+ * The bug: SOURCE_ID_RE forbids underscores, so `--source __all__` and
+ * `GBRAIN_SOURCE=__all__` threw in the resolver; the CLI's makeContext
+ * blanket-caught that and silently fell back to `sourceId: 'default'` —
+ * making the documented span-everything flag STRICTLY NARROWER than passing
+ * no flag at all (the catch also discarded the #2561/#3242 federated
+ * widening). Meanwhile sourceScopeOpts treated a ctx.sourceId of '__all__'
+ * as an unsatisfiable literal.
+ *
+ * Uses the literal '__all__' (not the ALL_SOURCES constant) so these tests
+ * load and run behaviorally against pre-fix trees.
+ */
+import { describe, test, expect } from 'bun:test';
+import { withEnv } from './helpers/with-env.ts';
+import {
+  resolveSourceId,
+  resolveSourceIdEngineFree,
+  resolveSourceWithTier,
+} from '../src/core/source-resolver.ts';
+import {
+  sourceScopeOpts,
+  federatedSearchScope,
+  type OperationContext,
+} from '../src/core/operations.ts';
+import type { BrainEngine } from '../src/core/engine.ts';
+
+// Stub engine: registered sources + no local_path rows + no default config.
+function makeStub(registeredSources: string[]): BrainEngine {
+  return {
+    kind: 'pglite',
+    executeRaw: async <T>(sql: string, params?: unknown[]): Promise<T[]> => {
+      if (sql.includes('SELECT id FROM sources WHERE id = $1')) {
+        const target = params?.[0];
+        return registeredSources.includes(target as string)
+          ? [{ id: target } as unknown as T]
+          : [];
+      }
+      return [];
+    },
+    getConfig: async () => null,
+  } as unknown as BrainEngine;
+}
+
+function ctxOf(overrides: Partial<OperationContext> = {}): OperationContext {
+  return {
+    engine: {} as any,
+    config: {} as any,
+    logger: console as any,
+    dryRun: false,
+    remote: true,
+    sourceId: 'default',
+    ...overrides,
+  };
+}
+
+// ── Resolver tiers pass the sentinel through verbatim ──────────────────
+
+describe('source-resolver — __all__ sentinel pass-through', () => {
+  test('resolveSourceId: explicit --source __all__ resolves (no regex throw, no existence check)', async () => {
+    // '__all__' is deliberately NOT in the registered set — the sentinel
+    // must skip assertSourceExists (it is not a source id).
+    const id = await resolveSourceId(makeStub(['default']), '__all__', '/nonexistent');
+    expect(id).toBe('__all__');
+  });
+
+  test('resolveSourceId: GBRAIN_SOURCE=__all__ resolves (#2140)', async () => {
+    await withEnv({ GBRAIN_SOURCE: '__all__' }, async () => {
+      const id = await resolveSourceId(makeStub(['default']), null, '/nonexistent');
+      expect(id).toBe('__all__');
+    });
+  });
+
+  test('resolveSourceIdEngineFree: explicit + env __all__ (thin-client path)', async () => {
+    expect(resolveSourceIdEngineFree('__all__', '/nonexistent')).toBe('__all__');
+    await withEnv({ GBRAIN_SOURCE: '__all__' }, () => {
+      expect(resolveSourceIdEngineFree(null, '/nonexistent')).toBe('__all__');
+    });
+  });
+
+  test('resolveSourceWithTier: flag and env tiers carry the sentinel', async () => {
+    const flag = await resolveSourceWithTier(makeStub(['default']), '__all__', '/nonexistent');
+    expect(flag).toMatchObject({ source_id: '__all__', tier: 'flag' });
+    await withEnv({ GBRAIN_SOURCE: '__all__' }, async () => {
+      const env = await resolveSourceWithTier(makeStub(['default']), null, '/nonexistent');
+      expect(env).toMatchObject({ source_id: '__all__', tier: 'env' });
+    });
+  });
+
+  test('a genuinely invalid --source still throws (SOURCE_ID_RE not loosened)', async () => {
+    await expect(resolveSourceId(makeStub(['default']), 'my_source', '/nonexistent'))
+      .rejects.toThrow(/Invalid --source/);
+    expect(() => resolveSourceIdEngineFree('my_source', '/nonexistent'))
+      .toThrow(/Invalid --source/);
+  });
+});
+
+// ── sourceScopeOpts — the single read-scope choke point ─────────────────
+
+describe('sourceScopeOpts — __all__ sentinel', () => {
+  test('trusted local (remote === false): spans the whole brain (empty scope)', () => {
+    expect(sourceScopeOpts(ctxOf({ remote: false, sourceId: '__all__' }))).toEqual({});
+  });
+
+  test('remote: keeps the unsatisfiable literal — fail-closed, never widens', () => {
+    expect(sourceScopeOpts(ctxOf({ remote: true, sourceId: '__all__' })))
+      .toEqual({ sourceId: '__all__' });
+  });
+
+  test('anything not strictly remote === false is untrusted (fail-closed)', () => {
+    // undefined / missing remote must behave like remote, per the trust rule.
+    const ctx = ctxOf({ sourceId: '__all__' });
+    (ctx as any).remote = undefined;
+    expect(sourceScopeOpts(ctx)).toEqual({ sourceId: '__all__' });
+  });
+
+  test('a federated grant always wins over the sentinel', () => {
+    const ctx = ctxOf({
+      remote: true,
+      sourceId: '__all__',
+      auth: { token: 't', clientId: 'c', scopes: [], allowedSources: ['a', 'b'] } as any,
+    });
+    expect(sourceScopeOpts(ctx)).toEqual({ sourceIds: ['a', 'b'] });
+  });
+});
+
+// ── Never narrower than passing no flag (#2561 regression shape) ────────
+
+describe('__all__ is never narrower than an unqualified read', () => {
+  test('local __all__ spans the brain even when federated widening exists', () => {
+    // Unqualified read on a federated brain widens to the federated array…
+    const unqualified = ctxOf({
+      remote: false,
+      sourceId: 'default',
+      localFederatedSourceIds: ['default', 'src-a', 'src-b'],
+    });
+    expect(federatedSearchScope(unqualified)).toEqual({
+      sourceIds: ['default', 'src-a', 'src-b'],
+    });
+    // …and __all__ must be a superset of that: the whole brain ({}).
+    const all = ctxOf({ remote: false, sourceId: '__all__' });
+    expect(federatedSearchScope(all)).toEqual({});
+  });
+});
+
+// ── makeContext — explicit --source failures error loudly ───────────────
+
+describe('cli makeContext — no silent default fallback for explicit --source', () => {
+  test('--source __all__ produces ctx.sourceId __all__ (was: silent default)', async () => {
+    const { makeContext } = await import('../src/cli.ts');
+    const ctx = await makeContext(makeStub(['default']), { source: '__all__' });
+    expect(ctx.sourceId).toBe('__all__');
+    expect(ctx.remote).toBe(false);
+  });
+
+  test('an explicit --source that fails to resolve throws instead of becoming default', async () => {
+    const { makeContext } = await import('../src/cli.ts');
+    await expect(makeContext(makeStub(['default']), { source: 'ghost' }))
+      .rejects.toThrow(/not found/);
+    await expect(makeContext(makeStub(['default']), { source: 'my_source' }))
+      .rejects.toThrow(/Invalid --source/);
+  });
+
+  test('ambient resolution failure still falls back silently (pre-init brains)', async () => {
+    const { makeContext } = await import('../src/cli.ts');
+    const broken = {
+      kind: 'pglite',
+      executeRaw: async () => { throw new Error('relation "sources" does not exist'); },
+      getConfig: async () => { throw new Error('relation "config" does not exist'); },
+    } as unknown as BrainEngine;
+    const ctx = await makeContext(broken, {});
+    expect(ctx.sourceId).toBe('default');
+  });
+});

test/brain-durability-hook.serial.test.ts

@@ -11,15 +11,34 @@ import { tmpdir } from 'os';
 import { execFileSync } from 'child_process';
 import { hardenBrainRepo } from '../src/core/brain-repo-durability.ts';
 
+// #2943 root cause: `env: process.env` is REQUIRED here. Bun snapshots
+// process.env at startup, so without it the spawned git — and any post-commit
+// hook it fires — is blind to beforeEach's HOME/GBRAIN_HOME mutations (the
+// same Bun quirk as #2747, see resolveGbrainCliPath in brain-repo-durability).
+// Pre-fix, the hook under test resolved ${GBRAIN_HOME:-$HOME/.gbrain} to the
+// OPERATOR'S REAL ~/.gbrain: it wrote its log lines there (polluting the real
+// brain-push.log on every run), the LOCAL-ONLY test never saw them in the
+// temp log it polls, and the assertion only passed when the scaffolding push
+// from beforeEach (spawned by hardenBrainRepo WITH explicit env) happened to
+// still be in flight, lose the ref race, and retry AFTER the test had pointed
+// origin at the dead path — an accidental, load-dependent signal. That race
+// is the CI flake.
 function git(cwd: string, ...args: string[]): string {
   return execFileSync('git', ['-C', cwd, '-c', 'protocol.file.allow=always', ...args], {
-    stdio: ['ignore', 'pipe', 'pipe'], encoding: 'utf-8',
+    stdio: ['ignore', 'pipe', 'pipe'], encoding: 'utf-8', env: process.env,
   }).trim();
 }
 function originHead(bare: string): string {
   return git(bare, 'rev-parse', 'refs/heads/main');
 }
-async function waitForOrigin(bare: string, expectSha: string, ms = 8000): Promise<boolean> {
+// #2943: 30s poll deadlines (was 8s) for headroom under loaded CI shards —
+// the unreachable-origin path runs ~6 sequential process spawns after the
+// hook detaches. Every hook test also passes an explicit 60_000 third-arg
+// timeout: bun 1.3.14 IGNORES bunfig.toml's `timeout` key, so a bare
+// `bun test` enforces its 5000ms default and killed these tests before the
+// internal deadline could even elapse (the runner scripts pass --timeout
+// explicitly, which is why the inversion only bit direct local runs).
+async function waitForOrigin(bare: string, expectSha: string, ms = 30_000): Promise<boolean> {
   const deadline = Date.now() + ms;
   while (Date.now() < deadline) {
     try { if (originHead(bare) === expectSha) return true; } catch { /* */ }
@@ -28,6 +47,24 @@ async function waitForOrigin(bare: string, expectSha: string, ms = 8000): Promis
   return false;
 }
 
+/** #2943 (index.lock form): hardenBrainRepo installs the post-commit hook
+ * BEFORE committing the scaffolding, so that commit fires the hook and
+ * detaches a background brain_push. If that push loses the ref race against
+ * hardenBrainRepo's own synchronous push, it falls back to `git pull
+ * --rebase`, which takes .git/index.lock — racing the test body's first git
+ * calls ("Unable to create '.../.git/index.lock': File exists"). Wait for the
+ * detached push's terminal log line before handing the repo to the test. */
+async function waitForHookPushSettled(ms = 30_000): Promise<void> {
+  const log = join(process.env.GBRAIN_HOME!, 'brain-push.log');
+  const terminal = /\[push\] (ok|lock-timeout|LOCAL-ONLY)/;
+  const deadline = Date.now() + ms;
+  while (Date.now() < deadline) {
+    if (existsSync(log) && terminal.test(readFileSync(log, 'utf-8'))) return;
+    await new Promise(r => setTimeout(r, 150));
+  }
+  throw new Error(`detached hook push did not settle within ${ms}ms (${log})`);
+}
+
 let root: string, work: string, bare: string;
 let oldHome: string | undefined, oldGbrainHome: string | undefined;
 
@@ -38,14 +75,15 @@ beforeEach(async () => {
   process.env.GBRAIN_HOME = join(process.env.HOME, '.gbrain');
   process.env.GBRAIN_GIT_ALLOW_FILE_TRANSPORT = '1';
   bare = mkdtempSync(join(root, 'origin-')) + '.git';
-  execFileSync('git', ['init', '-q', '--bare', '-b', 'main', bare], { stdio: 'ignore' });
+  execFileSync('git', ['init', '-q', '--bare', '-b', 'main', bare], { stdio: 'ignore', env: process.env });
   work = mkdtempSync(join(root, 'work-'));
-  execFileSync('git', ['-c', 'protocol.file.allow=always', 'clone', '-q', bare, work], { stdio: 'ignore' });
+  execFileSync('git', ['-c', 'protocol.file.allow=always', 'clone', '-q', bare, work], { stdio: 'ignore', env: process.env });
   git(work, 'config', 'user.email', 't@t.t'); git(work, 'config', 'user.name', 'tester');
   writeFileSync(join(work, 'README.md'), 'init\n');
   git(work, 'add', 'README.md'); git(work, 'commit', '-qm', 'init'); git(work, 'push', '-q', 'origin', 'main');
   git(work, 'remote', 'set-head', 'origin', 'main');
   await hardenBrainRepo({ repoPath: work, sourceId: 'wiki', pat: 'ghp_x', installCron: false });
+  await waitForHookPushSettled();
 });
 afterEach(() => {
   if (oldHome === undefined) delete process.env.HOME; else process.env.HOME = oldHome;
@@ -65,7 +103,7 @@ describe('brain-commit-push.sh (D13 guarantee)', () => {
     expect(originHead(bare)).toBe(git(work, 'rev-parse', 'HEAD'));
     // origin actually has the file
     const verify = mkdtempSync(join(root, 'verify-'));
-    execFileSync('git', ['-c', 'protocol.file.allow=always', 'clone', '-q', bare, verify], { stdio: 'ignore' });
+    execFileSync('git', ['-c', 'protocol.file.allow=always', 'clone', '-q', bare, verify], { stdio: 'ignore', env: process.env });
     expect(existsSync(join(verify, 'people', 'alice.md'))).toBe(true);
   });
 
@@ -102,7 +140,7 @@ describe('brain-commit-push.sh (D13 guarantee)', () => {
     rmSync(join(work, '.git', 'hooks', 'post-commit'));
     // Advance the remote from a second clone so a pull is genuinely needed.
     const other = mkdtempSync(join(root, 'other-'));
-    execFileSync('git', ['-c', 'protocol.file.allow=always', 'clone', '-q', bare, other], { stdio: 'ignore' });
+    execFileSync('git', ['-c', 'protocol.file.allow=always', 'clone', '-q', bare, other], { stdio: 'ignore', env: process.env });
     git(other, 'config', 'user.email', 'o@o.o'); git(other, 'config', 'user.name', 'other');
     writeFileSync(join(other, 'remote.md'), 'from other\n');
     git(other, 'add', 'remote.md'); git(other, 'commit', '-qm', 'remote change'); git(other, 'push', '-q', 'origin', 'main');
@@ -128,26 +166,26 @@ describe('post-commit hook (D9 local, D7 self-contained)', () => {
     git(work, 'add', 'note.md'); git(work, 'commit', '-qm', 'note'); // fires .git/hooks/post-commit
     const head = git(work, 'rev-parse', 'HEAD');
     expect(await waitForOrigin(bare, head)).toBe(true);
-  });
+  }, 60_000);
 
   test('the hook works even with the committed helper deleted (self-contained)', async () => {
     rmSync(join(work, 'scripts', 'brain-commit-push.sh'));
     git(work, 'add', '-A'); git(work, 'commit', '-qm', 'remove helper');
     const head = git(work, 'rev-parse', 'HEAD');
     expect(await waitForOrigin(bare, head)).toBe(true);
-  });
+  }, 60_000);
 
   test('logs a clear LOCAL-ONLY line when origin is unreachable', async () => {
     git(work, 'remote', 'set-url', 'origin', join(root, 'gone2.git'));
     writeFileSync(join(work, 'orphan.md'), 'o\n');
     git(work, 'add', 'orphan.md'); git(work, 'commit', '-qm', 'orphan');
     const log = join(process.env.GBRAIN_HOME!, 'brain-push.log');
-    const deadline = Date.now() + 8000;
+    const deadline = Date.now() + 30_000;
     let found = false;
     while (Date.now() < deadline) {
       if (existsSync(log) && readFileSync(log, 'utf-8').includes('NEEDS ATTENTION')) { found = true; break; }
       await new Promise(r => setTimeout(r, 150));
     }
     expect(found).toBe(true);
-  });
+  }, 60_000);
 });

test/cli-stdin-hang.test.ts

@@ -0,0 +1,173 @@
+/**
+ * #3513: parseOpArgs' stdin read must never block forever.
+ *
+ * In a non-TTY with no piped input — a CI step, a cron job, an agent
+ * harness that inherits a non-TTY stdin without writing to it — the old
+ * inline `readFileSync(0)` never returned. The fix bounds the read with a
+ * first-byte deadline (pipes/sockets only) and falls through to the
+ * existing required-param usage error on timeout.
+ *
+ * The load-bearing regression test spawns the REAL CLI with a held-open,
+ * never-written pipe: on pre-fix code it hangs until our observation window
+ * kills it; on fixed code it exits 1 with the usage error well inside the
+ * window. The stdin read + required-param check both run BEFORE engine
+ * connect, so no brain/DB is touched.
+ */
+import { describe, expect, test } from 'bun:test';
+import { dirname, join } from 'path';
+
+const REPO = dirname(import.meta.dir);
+const CLI = join(REPO, 'src', 'cli.ts');
+
+interface CliRun {
+  exited: boolean;
+  exitCode: number | null;
+  stderr: string;
+}
+
+/** Narrow Bun's `number | FileSink` stdin union to the pipe sink. */
+function pipeSink(proc: { stdin: unknown }): { write(d: string): unknown; end(): unknown } {
+  const s = proc.stdin;
+  if (!s || typeof s === 'number') throw new Error('expected a piped stdin sink');
+  return s as { write(d: string): unknown; end(): unknown };
+}
+
+/**
+ * Spawn the CLI with the given stdin wiring. `holdPipeOpen` keeps the write
+ * end of the stdin pipe alive without ever writing — the #3513 repro. The
+ * observation window kills the child if it hasn't exited (pre-fix hang).
+ */
+async function runCliWithStdin(
+  args: string[],
+  stdin: 'hold-open' | 'closed-empty' | { data: string } | { file: string },
+  windowMs: number,
+): Promise<CliRun> {
+  const proc = Bun.spawn(['bun', 'run', CLI, ...args], {
+    cwd: REPO,
+    env: { ...process.env, GBRAIN_STDIN_TIMEOUT_MS: '500' },
+    stdin: typeof stdin === 'object' && 'file' in stdin ? Bun.file(stdin.file) : 'pipe',
+    stdout: 'pipe',
+    stderr: 'pipe',
+  });
+  if (typeof stdin === 'object' && 'data' in stdin) {
+    pipeSink(proc).write(stdin.data);
+    await pipeSink(proc).end();
+  } else if (stdin === 'closed-empty') {
+    await pipeSink(proc).end();
+  }
+  // 'hold-open': never write, never close — the CI/cron/agent-harness shape.
+
+  let exited = true;
+  const killer = setTimeout(() => {
+    exited = false;
+    try { proc.kill('SIGKILL'); } catch { /* already dead */ }
+  }, windowMs);
+  const [exitCode, stderr] = await Promise.all([
+    proc.exited,
+    new Response(proc.stderr).text(),
+  ]);
+  clearTimeout(killer);
+  try { pipeSink(proc).end(); } catch { /* hold-open cleanup */ }
+  return { exited, exitCode: exited ? exitCode : null, stderr };
+}
+
+describe('#3513 — stdin-capable op with a non-TTY, never-written stdin', () => {
+  test('exits fast with the usage error instead of blocking forever', async () => {
+    // `put` declares stdin:'content' (required). No inline content, no piped
+    // input → the bounded read times out at 500ms, content stays unset, and
+    // the required-param check prints usage and exits 1. Pre-fix: readFileSync(0)
+    // blocks until the 20s window kills the child.
+    const run = await runCliWithStdin(['put', 'stdin-hang-test-slug'], 'hold-open', 20_000);
+    expect(run.exited).toBe(true); // pre-#3513 this is false: the read never returns
+    expect(run.exitCode).toBe(1);
+    expect(run.stderr).toContain('Usage: gbrain put');
+  }, 30_000);
+
+  test('a genuine pipe with data is still consumed (no hang, no crash)', async () => {
+    // Piped content fills `content`; the missing positional slug then fails
+    // the required check — proving the stream path read stdin and moved on.
+    const run = await runCliWithStdin(['put'], { data: '# hello\n' }, 20_000);
+    expect(run.exited).toBe(true);
+    expect(run.exitCode).toBe(1);
+    expect(run.stderr).toContain('Usage: gbrain put');
+  }, 30_000);
+
+  test('empty-but-real input (`< /dev/null`) does not hang', async () => {
+    const run = await runCliWithStdin(['put'], { file: '/dev/null' }, 20_000);
+    expect(run.exited).toBe(true);
+    expect(run.exitCode).toBe(1);
+  }, 30_000);
+
+  test('an empty pipe that closes immediately does not hang', async () => {
+    const run = await runCliWithStdin(['put'], 'closed-empty', 20_000);
+    expect(run.exited).toBe(true);
+    expect(run.exitCode).toBe(1);
+  }, 30_000);
+});
+
+describe('#3513 — applyStdinParam content preservation (subprocess driver)', () => {
+  // Drive the exported helper in a child process so we control the child's
+  // real fd 0 — bun test's own stdin is not a reliable fixture.
+  const DRIVER = `
+    const { applyStdinParam } = await import(${JSON.stringify(CLI)});
+    const op = { name: 'put', params: { content: { type: 'string', required: true } }, cliHints: { stdin: 'content' } };
+    const params = {};
+    await applyStdinParam(op, params);
+    console.log(JSON.stringify(params));
+    process.exit(0);
+  `;
+
+  async function runDriver(
+    stdin: 'hold-open' | 'closed-empty' | { data: string } | { file: string },
+  ): Promise<{ exited: boolean; params: Record<string, unknown> | null }> {
+    const proc = Bun.spawn(['bun', '-e', DRIVER], {
+      cwd: REPO,
+      env: { ...process.env, GBRAIN_STDIN_TIMEOUT_MS: '500' },
+      stdin: typeof stdin === 'object' && 'file' in stdin ? Bun.file(stdin.file) : 'pipe',
+      stdout: 'pipe',
+      stderr: 'pipe',
+    });
+    if (typeof stdin === 'object' && 'data' in stdin) {
+      pipeSink(proc).write(stdin.data);
+      await pipeSink(proc).end();
+    } else if (stdin === 'closed-empty') {
+      await pipeSink(proc).end();
+    }
+    let exited = true;
+    const killer = setTimeout(() => {
+      exited = false;
+      try { proc.kill('SIGKILL'); } catch { /* already dead */ }
+    }, 20_000);
+    const [stdout] = await Promise.all([new Response(proc.stdout).text(), proc.exited]);
+    clearTimeout(killer);
+    try { pipeSink(proc).end(); } catch { /* hold-open cleanup */ }
+    const line = stdout.trim().split('\n').pop() ?? '';
+    let params: Record<string, unknown> | null = null;
+    try { params = JSON.parse(line); } catch { /* child killed before printing */ }
+    return { exited, params };
+  }
+
+  test('piped data lands in the stdin param verbatim', async () => {
+    const { exited, params } = await runDriver({ data: '---\ntitle: x\n---\nbody' });
+    expect(exited).toBe(true);
+    expect(params?.content).toBe('---\ntitle: x\n---\nbody');
+  }, 30_000);
+
+  test('/dev/null yields empty-string content (readable, empty — pre-fix parity)', async () => {
+    const { exited, params } = await runDriver({ file: '/dev/null' });
+    expect(exited).toBe(true);
+    expect(params?.content).toBe('');
+  }, 30_000);
+
+  test('empty closed pipe yields empty-string content', async () => {
+    const { exited, params } = await runDriver('closed-empty');
+    expect(exited).toBe(true);
+    expect(params?.content).toBe('');
+  }, 30_000);
+
+  test('held-open pipe times out and leaves the param unset', async () => {
+    const { exited, params } = await runDriver('hold-open');
+    expect(exited).toBe(true); // completes inside the window instead of hanging
+    expect(params).toEqual({});
+  }, 30_000);
+});

test/doctor-ze-checks.test.ts

@@ -143,9 +143,10 @@ describe('checkEmbeddingWidthConsistency', () => {
   });
 
   test('gateway unconfigured: skips with ok', async () => {
-    // Reset gateway so requireConfig() throws.
-    const { resetGateway } = await import('../src/core/ai/gateway.ts');
-    resetGateway();
+    // Hard-unconfigure so requireConfig() throws — resetGateway() would
+    // restore the preload's test baseline (#3554).
+    const { __unconfigureGatewayForTests } = await import('../src/core/ai/gateway.ts');
+    __unconfigureGatewayForTests();
     const check = await checkEmbeddingWidthConsistency(engine);
     expect(check.status).toBe('ok');
     expect(check.message).toContain('gateway not configured');

test/e2e/embedding-column-pglite.test.ts

@@ -252,6 +252,87 @@ describe('upsertChunks — model provenance uses gateway-resolved model, not com
 
     resetGateway();
   });
+
+  // #3461: getEmbeddingModel() THROWS when the gateway is unconfigured — it
+  // never returns falsy — so the reland's `|| resolvedModel` guard was dead
+  // code and the catch path still stamped the compile-time default onto rows
+  // whose vectors came from the config-resolved provider. The engine must
+  // fall back to the brain's own `config.embedding_model` row instead.
+  test('#3461: unconfigured gateway falls back to the brain config model, never the compiled default', async () => {
+    await engine.setConfig('embedding_model', 'voyage:voyage-3-large');
+    // The preload's beforeEach re-configures the gateway before every test,
+    // so the reset must happen INSIDE the test body.
+    resetGateway();
+
+    await engine.putPage('docs/provenance-throw-path', {
+      type: 'concept',
+      title: 'Provenance throw-path page',
+      compiled_truth: 'Chunk written while the gateway is unconfigured.',
+    });
+    await engine.upsertChunks('docs/provenance-throw-path', [
+      { chunk_index: 0, chunk_text: 'throw-path provenance chunk', chunk_source: 'compiled_truth' },
+    ]);
+
+    const rows = await engine.executeRaw<{ model: string }>(
+      `SELECT cc.model FROM content_chunks cc
+         JOIN pages p ON p.id = cc.page_id
+        WHERE p.slug = 'docs/provenance-throw-path'`,
+    );
+    expect(rows.length).toBe(1);
+    expect(rows[0].model).toBe('voyage:voyage-3-large');
+
+    // Restore the value initSchema wrote for the rest of the file.
+    await engine.setConfig('embedding_model', 'openai:text-embedding-3-large');
+  });
+
+  // #3461 sibling: on a partial re-upsert that carries NO new embedding (the
+  // exact shape `embed --stale` produces for a page's non-stale chunks), the
+  // preserved vector must KEEP its original model label. The old
+  // COALESCE(EXCLUDED.model, …) relabeled it with the current gateway model.
+  test('#3461: preserved vector keeps its original model label on a no-embedding re-upsert', async () => {
+    configureGateway({
+      embedding_model: 'openai:text-embedding-3-large',
+      embedding_dimensions: 1536,
+      env: { OPENAI_API_KEY: 'sk-test' },
+    });
+
+    await engine.putPage('docs/provenance-preserve', {
+      type: 'concept',
+      title: 'Provenance preserve page',
+      compiled_truth: 'Chunk embedded under model A, re-upserted under model B.',
+    });
+    await engine.upsertChunks('docs/provenance-preserve', [
+      {
+        chunk_index: 0,
+        chunk_text: 'stable chunk text',
+        chunk_source: 'compiled_truth',
+        embedding: new Float32Array(VEC1536_A),
+      },
+    ]);
+
+    // Model swap: the gateway now resolves a different model, and the
+    // re-upsert (same chunk_text) carries no new embedding.
+    configureGateway({
+      embedding_model: 'voyage:voyage-3-large',
+      embedding_dimensions: 1536,
+      env: { VOYAGE_API_KEY: 'test' },
+    });
+    await engine.upsertChunks('docs/provenance-preserve', [
+      { chunk_index: 0, chunk_text: 'stable chunk text', chunk_source: 'compiled_truth' },
+    ]);
+
+    const rows = await engine.executeRaw<{ model: string; has_embedding: boolean }>(
+      `SELECT cc.model, cc.embedding IS NOT NULL AS has_embedding
+         FROM content_chunks cc
+         JOIN pages p ON p.id = cc.page_id
+        WHERE p.slug = 'docs/provenance-preserve'`,
+    );
+    expect(rows.length).toBe(1);
+    expect(rows[0].has_embedding).toBe(true); // vector preserved…
+    expect(rows[0].model).toBe('openai:text-embedding-3-large'); // …and its label still describes it
+
+    resetGateway();
+  });
 });
 
 describe('buildVectorCastFragment — engine SQL composer (D3)', () => {

test/e2e/jsonb-roundtrip.test.ts

@@ -26,8 +26,12 @@ if (skip) {
 }
 
 describeE2E('E2E: JSONB roundtrip — v0.12.1 reliability wave', () => {
-  beforeAll(async () => { await setupDB(); });
-  afterAll(async () => { await teardownDB(); });
+  // 60s hook budget: setupDB runs connect + the full migration chain, which
+  // exceeds bun's default 5s hook timeout on loaded CI runners. Hooks do NOT
+  // inherit a test's third-arg timeout (verified on bun 1.3.14) — they need
+  // their own second-arg budget. Same pattern as op-checkpoint-jsonb-parity.
+  beforeAll(async () => { await setupDB(); }, 60_000);
+  afterAll(async () => { await teardownDB(); }, 60_000);
 
   test('putPage writes frontmatter as object, not double-encoded string', async () => {
     const engine = getEngine();
@@ -69,7 +73,7 @@ describeE2E('E2E: JSONB roundtrip — v0.12.1 reliability wave', () => {
     `;
     expect(row.t).toBe('object');
     expect(row.marker).toBe('rawdata-value');
-  });
+  }, 30_000);
 
   test('logIngest writes pages_updated as array, not double-encoded string', async () => {
     const engine = getEngine();
@@ -91,7 +95,7 @@ describeE2E('E2E: JSONB roundtrip — v0.12.1 reliability wave', () => {
     expect(row.t).toBe('array');
     expect(Number(row.n)).toBe(3);
     expect(row.first).toBe('test/a');
-  });
+  }, 30_000);
 
   // files.ts:254 (uploadRaw's cloud-upload branch) was changed from
   // `${JSON.stringify({...})}::jsonb` to `${sql.json({...})}` in v0.12.1.
@@ -114,7 +118,7 @@ describeE2E('E2E: JSONB roundtrip — v0.12.1 reliability wave', () => {
     expect(row.t).toBe('object');
     expect(row.type).toBe('pdf');
     expect(row.method).toBe('TUS resumable');
-  });
+  }, 30_000);
 
   // Source-level tripwire: if anyone re-introduces the old `${JSON.stringify(x)}::jsonb`
   // pattern for the fixed sites, fail loudly. Greps actual source files per the
@@ -129,5 +133,5 @@ describeE2E('E2E: JSONB roundtrip — v0.12.1 reliability wave', () => {
       const source = await Bun.file(new URL(rel, import.meta.url)).text();
       expect(source.match(bad)?.[0] ?? null).toBeNull();
     }
-  });
+  }, 30_000);
 });

test/e2e/skill-brain-first.test.ts

@@ -81,6 +81,11 @@ function copyFixturesIntoTempWorkspace(): Workspace {
 
 let workspace: Workspace;
 
+// Restore (not delete) after each test: the audit-dir preload sets
+// GBRAIN_AUDIT_DIR once at process start, and deleting it leaks the
+// operator's real ~/.gbrain/audit/ to every later file in the shard.
+const priorAuditDir = process.env.GBRAIN_AUDIT_DIR;
+
 beforeEach(() => {
   workspace = copyFixturesIntoTempWorkspace();
   // Redirect audit dir to the tempdir so the snapshot file doesn't pollute
@@ -89,7 +94,8 @@ beforeEach(() => {
 });
 
 afterEach(() => {
-  delete process.env.GBRAIN_AUDIT_DIR;
+  if (priorAuditDir === undefined) delete process.env.GBRAIN_AUDIT_DIR;
+  else process.env.GBRAIN_AUDIT_DIR = priorAuditDir;
   workspace.cleanup();
 });
 

test/embed-preflight.test.ts

@@ -6,7 +6,11 @@
  * process.env.
  */
 import { describe, test, expect, beforeEach, afterAll } from 'bun:test';
-import { configureGateway, resetGateway } from '../src/core/ai/gateway.ts';
+import {
+  configureGateway,
+  resetGateway,
+  __unconfigureGatewayForTests,
+} from '../src/core/ai/gateway.ts';
 import {
   validateEmbeddingCreds,
   formatEmbeddingCredsError,
@@ -22,18 +26,12 @@ import type { AIGatewayConfig } from '../src/core/ai/types.ts';
 // isAvailable('embedding') check. That's what made facts-backstop-gating
 // fail intermittently (bin-pack-dependent) on CI shard 10.
 //
-// Don't end on a bare resetGateway() either: the NEXT file's beforeAll
-// (often engine.initSchema, which sizes vector columns from ambient gateway
-// state) runs before the legacy-embedding-preload's per-test restore, so a
-// null gateway here would seed 1280-d schemas under 1536-d fixtures.
-// Restore the preload's legacy pin instead.
+// #3554: resetGateway() now restores the preload's legacy pin itself (the
+// preload registers it via __setGatewayResetBaselineForTests), so a bare
+// reset is safe here — the NEXT file's beforeAll sees the 1536-d baseline,
+// not a null gateway that would seed 1280-d schemas under 1536-d fixtures.
 afterAll(() => {
   resetGateway();
-  configureGateway({
-    embedding_model: 'openai:text-embedding-3-large',
-    embedding_dimensions: 1536,
-    env: { ...process.env },
-  });
 });
 
 function baseConfig(overrides: Partial<AIGatewayConfig> = {}): AIGatewayConfig {
@@ -138,7 +136,9 @@ describe('validateEmbeddingCreds', () => {
   });
 
   test('throws no_gateway_config when gateway was not configured', () => {
-    // resetGateway() in beforeEach already cleared _config.
+    // resetGateway() restores the preload's test baseline (#3554), so this
+    // test needs the hard variant to get a genuinely unconfigured gateway.
+    __unconfigureGatewayForTests();
     let caught: unknown;
     try { validateEmbeddingCreds(); } catch (e) { caught = e; }
     expect(caught).toBeInstanceOf(EmbeddingCredentialError);

test/embed-stale.serial.test.ts

@@ -277,3 +277,79 @@ describe('embedStaleForSource', () => {
     expect(txtRow.embedded_at).not.toBeNull();
   });
 });
+
+// ────────────────────────────────────────────────────────────────
+// #3507 — re-embed must reproduce the page's STORED contextual-retrieval
+// wrapping convention. Before the fix, every plain re-embed (including the
+// normal post-model-migration `embed --stale`) embedded raw chunk_text,
+// silently replacing context-wrapped vectors with unwrapped ones.
+// ────────────────────────────────────────────────────────────────
+
+describe('contextual-retrieval wrapping on re-embed (#3507)', () => {
+  /** embedFn that records every text it is asked to embed. */
+  function capturingEmbedFn(seen: string[]) {
+    return (texts: string[]): Promise<Float32Array[]> => {
+      seen.push(...texts);
+      return fakeEmbedFn(texts);
+    };
+  }
+
+  async function seedWrappablePage(slug: string, title: string): Promise<void> {
+    await engine.putPage(slug, { type: 'note', title, compiled_truth: 'seeded' });
+    await engine.upsertChunks(slug, [
+      { chunk_index: 0, chunk_text: 'prose chunk about widgets', chunk_source: 'compiled_truth', token_count: 4 },
+      { chunk_index: 1, chunk_text: 'const x = 1;', chunk_source: 'fenced_code', token_count: 4 },
+    ]);
+  }
+
+  test('title-mode page: stale re-embed sends title-wrapped texts; fenced_code stays raw', async () => {
+    await seedWrappablePage('wrapped-page', 'Widget Notes');
+    await engine.updatePageContextualRetrievalState('wrapped-page', 'default', 'title', 'gen-title');
+
+    const seen: string[] = [];
+    const result = await embedStaleForSource(engine, 'default', { embedFn: capturingEmbedFn(seen) });
+    expect(result.embedded).toBe(2);
+
+    expect(seen).toContain('<context>Widget Notes\n</context>\nprose chunk about widgets');
+    expect(seen).toContain('const x = 1;'); // fenced_code is NEVER wrapped (D20-T4)
+
+    // D20-T1: the canonical chunk_text is NOT rewritten — wrapping is embed-input-only.
+    const chunks = await engine.getChunks('wrapped-page');
+    expect(chunks.map((c) => c.chunk_text).sort()).toEqual(['const x = 1;', 'prose chunk about widgets']);
+    // Mode stamp unchanged for title-tier pages.
+    const rows = await engine.executeRaw<{ contextual_retrieval_mode: string }>(
+      `SELECT contextual_retrieval_mode FROM pages WHERE slug = 'wrapped-page'`,
+    );
+    expect(rows[0].contextual_retrieval_mode).toBe('title');
+  });
+
+  test('per_chunk_synopsis page: re-embed applies the title-tier wrapper and restamps honestly', async () => {
+    await seedWrappablePage('synopsis-page', 'Synopsis Notes');
+    await engine.updatePageContextualRetrievalState('synopsis-page', 'default', 'per_chunk_synopsis', 'gen-synopsis');
+
+    const seen: string[] = [];
+    const result = await embedStaleForSource(engine, 'default', { embedFn: capturingEmbedFn(seen) });
+    expect(result.embedded).toBe(2);
+
+    // Synopsis re-generation is a paid backfill concern; the plain re-embed
+    // lands at the title tier (the service's own D14 fallback tier)…
+    expect(seen).toContain('<context>Synopsis Notes\n</context>\nprose chunk about widgets');
+    // …and the stamped mode is updated so it keeps describing the vectors.
+    const rows = await engine.executeRaw<{ contextual_retrieval_mode: string }>(
+      `SELECT contextual_retrieval_mode FROM pages WHERE slug = 'synopsis-page'`,
+    );
+    expect(rows[0].contextual_retrieval_mode).toBe('title');
+  });
+
+  test('unstamped page (NULL mode) embeds raw chunk_text — convention preserved', async () => {
+    await seedWrappablePage('plain-page', 'Plain Notes');
+    // No updatePageContextualRetrievalState call: pre-CR page.
+
+    const seen: string[] = [];
+    const result = await embedStaleForSource(engine, 'default', { embedFn: capturingEmbedFn(seen) });
+    expect(result.embedded).toBe(2);
+
+    expect(seen).toContain('prose chunk about widgets');
+    expect(seen.some((t) => t.startsWith('<context>'))).toBe(false);
+  });
+});

test/embed.serial.test.ts

@@ -907,3 +907,76 @@ describe('runEmbed preserves code-chunk metadata across re-embed (regression for
     expect(metadataOf(upsertChunkArgs![0])).toEqual(metadataOf(fullCodeChunk));
   });
 });
+
+// ────────────────────────────────────────────────────────────────
+// #3507 — `embed --stale` must reproduce the page's STORED
+// contextual-retrieval wrapping convention instead of embedding raw
+// chunk_text (which silently stripped contextual prefixes on every
+// re-embed, including the normal post-model-migration path).
+// ────────────────────────────────────────────────────────────────
+
+describe('embed --stale contextual-retrieval wrapping (#3507)', () => {
+  const wrapChunks = [
+    { chunk_index: 0, chunk_text: 'prose chunk', chunk_source: 'compiled_truth', embedded_at: null, token_count: 1 },
+    { chunk_index: 1, chunk_text: 'const x = 1;', chunk_source: 'fenced_code', embedded_at: null, token_count: 1 },
+  ];
+  const wrapStale = [
+    { slug: 'wrapped', chunk_index: 0, chunk_text: 'prose chunk', chunk_source: 'compiled_truth' as const, model: null, token_count: 1, source_id: 'default', page_id: 1 },
+    { slug: 'wrapped', chunk_index: 1, chunk_text: 'const x = 1;', chunk_source: 'fenced_code' as any, model: null, token_count: 1, source_id: 'default', page_id: 1 },
+  ];
+
+  function wrappingHarness(mode: string | null) {
+    const seen: string[] = [];
+    const restamps: any[][] = [];
+    embedBatchBehavior = async (texts: string[]) => {
+      seen.push(...texts);
+      return texts.map(() => new Float32Array(1536));
+    };
+    const engine = mockEngine({
+      countStaleChunks: async () => 2,
+      listStaleChunks: async () => wrapStale,
+      getPage: async () => ({
+        slug: 'wrapped',
+        title: 'Widget Notes',
+        source_id: 'default',
+        compiled_truth: 'x',
+        timeline: '',
+        contextual_retrieval_mode: mode,
+      }),
+      getChunks: async () => wrapChunks,
+      upsertChunks: async () => {},
+      updatePageContextualRetrievalState: async (...args: any[]) => { restamps.push(args); },
+    });
+    return { engine, seen, restamps };
+  }
+
+  test('title-mode page: stale re-embed wraps prose with the title prefix; fenced_code stays raw', async () => {
+    const { engine, seen, restamps } = wrappingHarness('title');
+    const result = await runEmbedCore(engine, { stale: true });
+    expect(result.embedded).toBe(2);
+    expect(seen).toContain('<context>Widget Notes\n</context>\nprose chunk');
+    expect(seen).toContain('const x = 1;');
+    expect(restamps).toHaveLength(0); // title tier: stamp already honest
+  });
+
+  test('per_chunk_synopsis page: fully re-embedded page restamps to the title tier', async () => {
+    const { engine, seen, restamps } = wrappingHarness('per_chunk_synopsis');
+    const result = await runEmbedCore(engine, { stale: true });
+    expect(result.embedded).toBe(2);
+    expect(seen).toContain('<context>Widget Notes\n</context>\nprose chunk');
+    expect(restamps).toHaveLength(1);
+    const [slug, sourceId, newMode] = restamps[0];
+    expect(slug).toBe('wrapped');
+    expect(sourceId).toBe('default');
+    expect(newMode).toBe('title');
+  });
+
+  test('page with no stored CR mode embeds raw chunk_text (convention preserved)', async () => {
+    const { engine, seen, restamps } = wrappingHarness(null);
+    const result = await runEmbedCore(engine, { stale: true });
+    expect(result.embedded).toBe(2);
+    expect(seen).toContain('prose chunk');
+    expect(seen.some((t) => t.startsWith('<context>'))).toBe(false);
+    expect(restamps).toHaveLength(0);
+  });
+});

test/extract-facts-phase.test.ts

@@ -672,6 +672,51 @@ describe('runExtractFacts — empty-fence guard (Codex R2-#7)', () => {
 });
 
 describe('runExtractFacts — multi-source isolation', () => {
+  test('a pending legacy row in source A does NOT jam extraction for source B (#2646 source-scope)', async () => {
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    await (engine as any).db.query(
+      `INSERT INTO sources (id, name, config) VALUES ('work', 'work', '{}'::jsonb)
+       ON CONFLICT (id) DO NOTHING`,
+    );
+
+    // Source "work": a genuine pending legacy row (row_num NULL, active,
+    // live backing page) — the exact shape that must gate work's cycle.
+    await engine.putPage('people/alice', {
+      title: 'people/alice', type: 'person',
+      compiled_truth: FACT_FENCE(`| 1 | work fence fact | fact | 1.0 | world | high | 2026-01-01 |  | s |  |`),
+      frontmatter: {}, timeline: '',
+    }, { sourceId: 'work' });
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    await (engine as any).db.query(
+      `INSERT INTO facts (source_id, entity_slug, fact, kind, visibility, notability,
+                          valid_from, source, confidence)
+       VALUES ('work', 'people/alice', 'work legacy claim', 'fact', 'private', 'medium',
+               now(), 'mcp:put_page', 1.0)`,
+    );
+
+    // Source "default": clean — no legacy rows, one fenced page.
+    await putPage('people/bob', FACT_FENCE(
+      `| 1 | default fact | fact | 1.0 | world | high | 2026-01-01 |  | s |  |`,
+    ));
+
+    // default's run must NOT be jammed by work's pending backlog.
+    const rDefault = await runExtractFacts(engine, { slugs: ['people/bob'], sourceId: 'default' });
+    expect(rDefault.guardTriggered).toBe(false);
+    expect(rDefault.legacyRowsPending).toBe(0);
+    expect(rDefault.factsInserted).toBe(1);
+
+    // work's own run still gates (discriminator stays sharp).
+    const rWork = await runExtractFacts(engine, { slugs: ['people/alice'], sourceId: 'work' });
+    expect(rWork.guardTriggered).toBe(true);
+    expect(rWork.legacyRowsPending).toBe(1);
+    expect(rWork.factsInserted).toBe(0);
+    // The drain advice must be one that actually re-runs Phase B — a bare
+    // `apply-migrations --yes` no-ops once the ledger says complete.
+    expect(rWork.warnings.some(w => w.includes('--force-retry 0.32.2'))).toBe(true);
+    expect(rWork.warnings.some(w => w.includes('forget_fact'))).toBe(true);
+    expect(rWork.warnings.some(w => w.includes('source "work"'))).toBe(true);
+  });
+
   test('deleteFactsForPage scoping does not affect other sources', async () => {
     // Seed sources work + home.
     // eslint-disable-next-line @typescript-eslint/no-explicit-any

test/extract/receipt-writer.test.ts

@@ -20,6 +20,7 @@ import {
   writeReceipt,
   type ExtractReceiptInput,
 } from '../../src/core/extract/receipt-writer.ts';
+import { slugifySegment } from '../../src/core/sync.ts';
 
 const BASE_INPUT: ExtractReceiptInput = {
   kind: 'facts.conversation',
@@ -81,6 +82,31 @@ describe('shortRunId / dateFromIso — pure helpers', () => {
     expect(shortRunId('op_check_abc')).toBe('op_check');
   });
 
+  // #3443 — a short form ending in '-' (e.g. propose-<timestamp> run ids)
+  // desynced the DB receipt slug from its Git-backed slug: slugifySegment()
+  // strips boundary hyphens during repo sync, so the write-through created a
+  // normalized sibling instead of materializing the existing page.
+  test('shortRunId is canonical under slugifySegment for every receipt-producing run-id family (#3443)', () => {
+    const familyRunIds = [
+      'propose-20260724103000-ab12cd34',           // cycle/propose-takes.ts
+      `atoms-${Date.now().toString(36)}-pers`,     // cycle/extract-atoms.ts
+      `efacts-${Date.now().toString(36)}-pers`,    // cycle/extract-facts.ts
+      `concepts-${Date.now().toString(36)}`,       // cycle/synthesize-concepts.ts
+      `ecf-${Date.now().toString(36)}-pers`,       // extract-conversation-facts.ts
+    ];
+    for (const runId of familyRunIds) {
+      const short = shortRunId(runId);
+      expect(slugifySegment(short)).toBe(short);
+      expect(short.length).toBeGreaterThan(0);
+    }
+  });
+
+  test('shortRunId trims boundary hyphens introduced by truncation', () => {
+    expect(shortRunId('propose-20260724103000-ab12cd34')).toBe('propose');
+    // Pathological all-separator prefix still yields a non-empty segment.
+    expect(shortRunId('--------tail')).toBe('run');
+  });
+
   test('dateFromIso extracts YYYY-MM-DD prefix', () => {
     expect(dateFromIso('2026-05-27T14:30:00Z')).toBe('2026-05-27');
     expect(dateFromIso('2026-05-27T14:30:00.123456Z')).toBe('2026-05-27');

test/foreground-chat-gateway-init.serial.test.ts

@@ -9,7 +9,11 @@ import { afterEach, beforeEach, describe, expect, spyOn, test } from 'bun:test';
 import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs';
 import { tmpdir } from 'node:os';
 import { join } from 'node:path';
-import { isAvailable, resetGateway } from '../src/core/ai/gateway.ts';
+import {
+  __unconfigureGatewayForTests,
+  isAvailable,
+  resetGateway,
+} from '../src/core/ai/gateway.ts';
 import { runExtractConversationFacts } from '../src/commands/extract-conversation-facts.ts';
 import { runEnrich } from '../src/commands/enrich.ts';
 
@@ -27,7 +31,10 @@ beforeEach(() => {
   }));
   process.env.GBRAIN_HOME = home;
   process.env.OPENAI_API_KEY = 'test-key';
-  resetGateway();
+  // Hard-unconfigure: this suite exists to exercise the COLD-gateway path
+  // (#2590), and resetGateway() now restores the preload's test baseline
+  // (#3554), which would make configureGatewayIfUninitialized a no-op.
+  __unconfigureGatewayForTests();
 });
 
 afterEach(() => {

test/health-soft-delete.test.ts

@@ -0,0 +1,123 @@
+/**
+ * #1305 — getHealth() must exclude soft-deleted pages from every
+ * page-scoped count, the same posture getStats() has had since v0.26.5.
+ *
+ * Pre-fix, getHealth counted raw `pages` rows: page_count and orphan_pages
+ * included soft-deleted pages, the entity_pages CTE kept deleted entities in
+ * the link/timeline coverage denominators and in most_connected, and
+ * brain_score therefore never moved when a user soft-deleted pages.
+ *
+ * Boundary (deliberate): chunk- and link-scoped counts (embed_coverage,
+ * missing_embeddings, link_count, dead_links) stay RAW — they occupy storage
+ * until the autopilot purge phase, matching getStats. Destructive-removal
+ * counts (purge paths, #2235) also deliberately count all rows and are
+ * untouched here.
+ *
+ * Runs against PGLite — the fixed SQL shapes are identical in both engines.
+ */
+
+import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:test';
+import { PGLiteEngine } from '../src/core/pglite-engine.ts';
+
+let engine: PGLiteEngine;
+
+beforeAll(async () => {
+  engine = new PGLiteEngine();
+  await engine.connect({});
+  await engine.initSchema();
+}, 60_000);
+
+afterAll(async () => {
+  await engine.disconnect();
+});
+
+beforeEach(async () => {
+  for (const t of ['links', 'content_chunks', 'timeline_entries', 'tags', 'page_versions', 'pages']) {
+    await (engine as any).db.exec(`DELETE FROM ${t}`);
+  }
+});
+
+async function seedNote(slug: string): Promise<void> {
+  await engine.putPage(slug, { type: 'note', title: slug, compiled_truth: `content of ${slug}`, frontmatter: {} });
+}
+
+async function pageId(slug: string): Promise<number> {
+  return (await (engine as any).db.query(`SELECT id FROM pages WHERE slug=$1`, [slug])).rows[0].id;
+}
+
+describe('#1305 — getHealth excludes soft-deleted pages', () => {
+  test('page_count and orphan_pages match getStats after soft-delete (the issue repro)', async () => {
+    for (let i = 0; i < 10; i++) await seedNote(`wiki/note-${i}`);
+    for (let i = 0; i < 6; i++) await engine.softDeletePage(`wiki/note-${i}`);
+
+    const stats = await engine.getStats();
+    const health = await engine.getHealth();
+    expect(stats.page_count).toBe(4);
+    // Pre-fix: 10 (raw rows). getHealth must agree with getStats.
+    expect(health.page_count).toBe(4);
+    // Pre-fix: 10 — deleted pages stayed in the islanded scan.
+    expect(health.orphan_pages).toBe(4);
+  });
+
+  test('brain_score moves when the user soft-deletes the islanded pages', async () => {
+    // 2 connected pages + 8 islanded ones.
+    await seedNote('wiki/hub');
+    await seedNote('wiki/leaf');
+    await (engine as any).db.query(
+      `INSERT INTO links (from_page_id, to_page_id, link_type) VALUES ($1, $2, 'mentions')`,
+      [await pageId('wiki/hub'), await pageId('wiki/leaf')],
+    );
+    for (let i = 0; i < 8; i++) await seedNote(`wiki/clutter-${i}`);
+
+    const before = await engine.getHealth();
+    for (let i = 0; i < 8; i++) await engine.softDeletePage(`wiki/clutter-${i}`);
+    const after = await engine.getHealth();
+
+    // Pre-fix both assertions fail: orphan_pages stayed 8 and brain_score
+    // was byte-identical before/after the delete.
+    expect(after.orphan_pages).toBe(0);
+    expect(after.brain_score).toBeGreaterThan(before.brain_score);
+  });
+
+  test('entity coverage denominators and most_connected exclude deleted entities', async () => {
+    // Live entity: inbound link + timeline entry → full coverage.
+    await engine.putPage('people/alice-example', { type: 'person', title: 'Alice', compiled_truth: 'a person', frontmatter: {} });
+    await engine.putPage('people/bob-example', { type: 'person', title: 'Bob', compiled_truth: 'another person', frontmatter: {} });
+    await seedNote('wiki/mentions-alice');
+    const aliceId = await pageId('people/alice-example');
+    await (engine as any).db.query(
+      `INSERT INTO links (from_page_id, to_page_id, link_type) VALUES ($1, $2, 'mentions')`,
+      [await pageId('wiki/mentions-alice'), aliceId],
+    );
+    await (engine as any).db.query(
+      `INSERT INTO timeline_entries (page_id, date, summary) VALUES ($1, '2026-01-01', 'met alice')`,
+      [aliceId],
+    );
+
+    await engine.softDeletePage('people/bob-example');
+    const h = await engine.getHealth();
+
+    // Pre-fix: bob stayed in the entity_pages CTE → coverage 0.5 each,
+    // and bob appeared in most_connected.
+    expect(h.link_coverage).toBe(1);
+    expect(h.timeline_coverage).toBe(1);
+    expect(h.most_connected.map((c) => c.slug)).not.toContain('people/bob-example');
+  });
+
+  test('chunk storage counts stay raw (the deliberate boundary)', async () => {
+    await seedNote('wiki/kept');
+    await seedNote('wiki/gone');
+    for (const slug of ['wiki/kept', 'wiki/gone']) {
+      await (engine as any).db.query(
+        `INSERT INTO content_chunks (page_id, chunk_index, chunk_text) VALUES ($1, 0, 'chunk')`,
+        [await pageId(slug)],
+      );
+    }
+    await engine.softDeletePage('wiki/gone');
+
+    const h = await engine.getHealth();
+    // Soft-deleted pages' chunks still occupy storage until purge; the
+    // missing_embeddings count keeps seeing them, same as getStats.
+    expect(h.missing_embeddings).toBe(2);
+  });
+});

test/helpers/legacy-embedding-preload.ts

@@ -18,7 +18,11 @@
  * `configureGateway()` explicitly in their own beforeAll, which
  * overwrites this preload.
  */
-import { configureGateway, getEmbeddingDimensions } from '../../src/core/ai/gateway.ts';
+import {
+  configureGateway,
+  getEmbeddingDimensions,
+  __setGatewayResetBaselineForTests,
+} from '../../src/core/ai/gateway.ts';
 import { beforeEach } from 'bun:test';
 
 const LEGACY_CONFIG = {
@@ -26,12 +30,16 @@ const LEGACY_CONFIG = {
   embedding_dimensions: 1536,
 } as const;
 
-function applyLegacy() {
-  configureGateway({
+function legacyGatewayConfig() {
+  return {
     embedding_model: LEGACY_CONFIG.embedding_model,
     embedding_dimensions: LEGACY_CONFIG.embedding_dimensions,
     env: { ...process.env },
-  });
+  };
+}
+
+function applyLegacy() {
+  configureGateway(legacyGatewayConfig());
 }
 
 if (process.env.GBRAIN_DEBUG_PRELOAD === '1') {
@@ -41,6 +49,16 @@ if (process.env.GBRAIN_DEBUG_PRELOAD === '1') {
 // Initial application — covers tests that don't reset the gateway.
 applyLegacy();
 
+// #3554: make resetGateway() mean "back to this baseline" instead of
+// "unconfigured". Without this, a file whose teardown calls resetGateway()
+// leaves _config = null; the NEXT file's beforeAll engine-connect then
+// reconfigures from the shipped default (zembed-1 @ 1280) BEFORE the
+// beforeEach below can fire, and the 1280-sized schema rejects the file's
+// 1536-d fixtures. Which file pairs collide depends on shard bin-packing,
+// so adding any test file reshuffles the mines. A factory (not a frozen
+// config) so each re-application captures fresh process.env.
+__setGatewayResetBaselineForTests(legacyGatewayConfig);
+
 // Per-test re-application — handles tests that call `resetGateway()`
 // in their setup/teardown. Bun's preload allows registering global
 // hooks; this fires before every test in every file in the shard.

test/import-file.test.ts

@@ -522,7 +522,7 @@ just content.
     const result = await importFile(engine, filePath, '🌟🚀.md', { noEmbed: true });
     expect(result.status).toBe('skipped');
     expect(result.error).toContain('no usable slug');
-    expect(result.error).toContain('ASCII / Chinese / Japanese / Korean');
+    expect(result.error).toContain('at least one letter or number (any script)');
     expect((engine as any)._calls.length).toBe(0);
   });
 

test/llm-intent-escalation.test.ts

@@ -15,6 +15,7 @@ import {
 } from '../src/core/search/llm-intent.ts';
 import {
   __setChatTransportForTests,
+  __unconfigureGatewayForTests,
   configureGateway,
   resetGateway,
 } from '../src/core/ai/gateway.ts';
@@ -122,7 +123,9 @@ describe('classifyModalityWithLLM — fail-open', () => {
   });
 
   test('Gateway not configured → returns fallback', async () => {
-    resetGateway();
+    // Hard-unconfigure: resetGateway() would restore the preload's test
+    // baseline (#3554), whose {...process.env} could make chat available.
+    __unconfigureGatewayForTests();
     // No configureGateway called → isAvailable('chat') returns false.
     expect(await classifyModalityWithLLM('q', 'text')).toBe('text');
   });

test/minions-shell.test.ts

@@ -282,12 +282,19 @@ describe('shell-audit: computeAuditFilename', () => {
 
 describe('shell-audit: write', () => {
   let tmpDir: string;
+  // #3554-sibling: the audit-dir preload sets GBRAIN_AUDIT_DIR once at
+  // process start; deleting it here (instead of restoring) let every file
+  // AFTER this one in the shard write audit fixtures to the operator's
+  // real ~/.gbrain/audit/ — and failed audit-dir-preload.test.ts whenever
+  // bin-packing placed it later in the shard. Restore the prior value.
+  const priorAuditDir = process.env.GBRAIN_AUDIT_DIR;
   beforeEach(() => {
     tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'shell-audit-test-'));
     process.env.GBRAIN_AUDIT_DIR = tmpDir;
   });
   afterAll(() => {
-    delete process.env.GBRAIN_AUDIT_DIR;
+    if (priorAuditDir === undefined) delete process.env.GBRAIN_AUDIT_DIR;
+    else process.env.GBRAIN_AUDIT_DIR = priorAuditDir;
   });
 
   test('GBRAIN_AUDIT_DIR env override resolves to the custom dir', () => {

test/minions.test.ts

@@ -354,6 +354,15 @@ describe('MinionQueue: #1737 per-handler default timeout', () => {
     expect(sub.timeout_ms).toBe(30 * 60 * 1000);
   });
 
+  // #3207 — facts-absorb is one LLM extraction call per page (same shape as
+  // chronicle_extract) but was missing from HANDLER_DEFAULT_TIMEOUT_MS, so it
+  // inherited the tight null-default wall-clock and was dead-lettered
+  // mid-generation on slow chat providers (facts silently lost).
+  test('facts-absorb gets the 10-min LLM-extraction default (#3207)', async () => {
+    const job = await queue.add('facts-absorb', { slug: 'people/alice-example' });
+    expect(job.timeout_ms).toBe(10 * 60 * 1000);
+  });
+
   test('contextual per-chunk reindex gets the 60-min default', async () => {
     const job = await queue.add('contextual_reindex_per_chunk', { page_slug: 'large-transcript' }, undefined, {
       allowProtectedSubmit: true,
@@ -709,6 +718,26 @@ describe('MinionQueue: Prune', () => {
     const count = await queue.prune({ olderThan: new Date(Date.now() + 86400000) }); // future date = prune everything old enough
     expect(count).toBe(1); // only the cancelled one
   });
+
+  // #2712: --dry-run used to be silently ignored — the destructive default
+  // ran and deleted rows while the operator believed they were previewing.
+  test('dryRun counts prunable jobs without deleting', async () => {
+    const job1 = await queue.add('sync', {});
+    await queue.cancelJob(job1.id); // terminal → prunable
+
+    const wouldPrune = await queue.prune({ olderThan: new Date(Date.now() + 86400000), dryRun: true });
+    expect(wouldPrune).toBe(1);
+
+    // The row must still exist after a dry run.
+    const stillThere = await queue.getJob(job1.id);
+    expect(stillThere).not.toBeNull();
+    expect(stillThere!.status).toBe('cancelled');
+
+    // A real prune afterwards actually deletes it.
+    const pruned = await queue.prune({ olderThan: new Date(Date.now() + 86400000) });
+    expect(pruned).toBe(1);
+    expect(await queue.getJob(job1.id)).toBeNull();
+  });
 });
 
 // --- Stats (1 test) ---

test/reconcile-links-cli-reachability.test.ts

@@ -19,3 +19,23 @@ describe('CLI_ONLY command reachability (#2900)', () => {
     expect(CLI_ONLY.has('reconcile-links')).toBe(true);
   });
 });
+
+// #3224 — same drift class: `backfill` has a full `case 'backfill'` handler
+// (cli.ts, dispatching to commands/backfill.ts) but was missing from CLI_ONLY,
+// so every invocation hit the generic "Unknown command" branch.
+describe('CLI_ONLY command reachability (#3224)', () => {
+  test('`backfill` is in CLI_ONLY so dispatch reaches its handler', () => {
+    expect(CLI_ONLY.has('backfill')).toBe(true);
+  });
+
+  test('`gbrain backfill --help` is dispatched, not rejected as unknown', () => {
+    const { spawnSync } = require('node:child_process') as typeof import('node:child_process');
+    const result = spawnSync('bun', ['run', 'src/cli.ts', 'backfill', '--help'], {
+      cwd: process.cwd(),
+      encoding: 'utf8',
+      env: { ...process.env, GBRAIN_HOME: '/tmp/gbrain-test-backfill-nonexistent' },
+    });
+    expect(result.stderr ?? '').not.toContain('Unknown command');
+    expect(result.status).toBe(0);
+  });
+});

test/slug-unicode-scripts.test.ts

@@ -0,0 +1,115 @@
+import { describe, test, expect } from 'bun:test';
+import { slugifySegment, slugifyPath } from '../src/core/sync.ts';
+import { validatePageSlug } from '../src/core/operations.ts';
+import { isValidHolder } from '../src/core/takes-fence.ts';
+
+/**
+ * #3417 — silent data loss for non-Latin, non-CJK scripts.
+ *
+ * Pre-fix, slugifySegment stripped every character outside [a-z0-9._-] + CJK,
+ * so whole filenames in Hebrew / Arabic / Cyrillic / Greek / Thai collapsed to
+ * empty segments. Distinct files then mapped to the SAME slug (their shared
+ * directory prefix) and last-writer-wins overwrote each other with `import`
+ * reporting 0 errors.
+ *
+ * Every assertion here is behavioral (input → output), so this file FAILS on
+ * pre-fix master and passes with the Unicode-property-escape grammar.
+ */
+
+describe('#3417: non-Latin scripts survive slugification', () => {
+  // The six script families from the issue, before/after.
+  const cases: Array<[string, string, string]> = [
+    ['Hebrew', 'notes/רשימת קניות.md', 'notes/רשימת-קניות'],
+    ['Arabic', 'notes/قائمة المهام.md', 'notes/قائمة-المهام'],
+    ['Cyrillic', 'notes/Список задач.md', 'notes/список-задач'],
+    // Greek: tonos marks decompose to U+0301 under NFD and are stripped by the
+    // same combining-accent pass that turns café → cafe. Consistent, stable.
+    ['Greek', 'notes/Λίστα εργασιών.md', 'notes/λιστα-εργασιων'],
+    ['Thai', 'notes/รายการซื้อของ.md', 'notes/รายการซื้อของ'],
+    ['Hebrew + digits', 'notes/תוכנית עבודה 2026.md', 'notes/תוכנית-עבודה-2026'],
+  ];
+
+  for (const [name, input, expected] of cases) {
+    test(`${name}: ${input} → ${expected}`, () => {
+      expect(slugifyPath(input)).toBe(expected);
+    });
+  }
+
+  test('distinct same-directory files no longer collapse onto one slug', () => {
+    // Pre-fix ALL of these slugified to "notes" — one page, last writer wins.
+    const slugs = [
+      slugifyPath('notes/רשימת קניות.md'),
+      slugifyPath('notes/قائمة المهام.md'),
+      slugifyPath('notes/Список задач.md'),
+      slugifyPath('notes/Λίστα εργασιών.md'),
+      slugifyPath('notes/รายการซื้อของ.md'),
+    ];
+    expect(new Set(slugs).size).toBe(slugs.length);
+    for (const s of slugs) expect(s).not.toBe('notes');
+  });
+
+  test('emitted slugs are ACCEPTED by validatePageSlug (three-grammar coherence)', () => {
+    // The trap: fixing only sync.ts makes sync emit slugs put_page rejects.
+    for (const [, input] of cases) {
+      const slug = slugifyPath(input);
+      expect(() => validatePageSlug(slug)).not.toThrow();
+    }
+  });
+
+  test('takes-fence holder grammar accepts non-Latin slugs', () => {
+    expect(isValidHolder('people/גארי-כהן')).toBe(true);
+    expect(isValidHolder('companies/شركة-مثال')).toBe(true);
+    // Uppercase still rejected (lowercase-canonical contract preserved).
+    expect(isValidHolder('people/Garry-Tan')).toBe(false);
+  });
+});
+
+describe('#3417: normalization — NFD (macOS) and NFC (git/Linux) converge', () => {
+  test('Hebrew NFD filename produces the same slug as NFC', () => {
+    const nfc = 'notes/רשימת קניות.md'.normalize('NFC');
+    const nfd = 'notes/רשימת קניות.md'.normalize('NFD');
+    expect(slugifyPath(nfd)).toBe(slugifyPath(nfc));
+  });
+
+  test('Vietnamese NFD filename produces the same slug as NFC', () => {
+    const nfc = 'notes/người dùng.md'.normalize('NFC');
+    const nfd = 'notes/người dùng.md'.normalize('NFD');
+    expect(slugifyPath(nfd)).toBe(slugifyPath(nfc));
+  });
+});
+
+describe('#3417: regressions — existing behavior unchanged', () => {
+  test('ASCII kebab-casing, lowercasing, dots, underscores', () => {
+    expect(slugifyPath('notes/Shopping List.md')).toBe('notes/shopping-list');
+    expect(slugifyPath('notes/v1.0.0.md')).toBe('notes/v1.0.0');
+    expect(slugifySegment('my_file_name')).toBe('my_file_name');
+    expect(slugifySegment('notes (march 2024)')).toBe('notes-march-2024');
+  });
+
+  test('Latin accents still strip (café → cafe)', () => {
+    expect(slugifySegment('café résumé')).toBe('cafe-resume');
+  });
+
+  test('CJK still preserved', () => {
+    expect(slugifyPath('notes/购物清单.md')).toBe('notes/购物清单');
+    expect(slugifyPath('inbox/品牌圣经.md')).toBe('inbox/品牌圣经');
+    expect(slugifySegment('한글테스트'.normalize('NFD'))).toBe('한글테스트');
+  });
+
+  test('all-symbol input still collapses to empty (frontmatter-fallback path intact)', () => {
+    expect(slugifySegment('!!!')).toBe('');
+    expect(slugifySegment('🎉🎉')).toBe('');
+  });
+
+  test('control chars, RTL override, punctuation still stripped', () => {
+    expect(slugifySegment('evil‮gnp')).toBe('evilgnp');
+    expect(slugifySegment('a\u0000b')).toBe('ab');
+  });
+
+  test('validatePageSlug still rejects traversal, backslash, RTL override, uppercase-only weirdness', () => {
+    expect(() => validatePageSlug('../etc/passwd')).toThrow();
+    expect(() => validatePageSlug('notes\\file')).toThrow();
+    expect(() => validatePageSlug('notes/‮evil')).toThrow();
+    expect(() => validatePageSlug('notes/a\u0007b')).toThrow();
+  });
+});

test/slug-validation.test.ts

@@ -259,10 +259,10 @@ describe('SLUG_SEGMENT_PATTERN (v0.32.7)', () => {
     expect(SLUG_SEGMENT_PATTERN.test('icp-理想客户画像')).toBe(true);
   });
 
-  test('REGRESSION: rejects non-CJK Unicode (Vietnamese)', () => {
-    // Scope is CJK only; Vietnamese with combining diacritics stays rejected
-    // until we widen to Unicode property escapes in v0.33+.
-    const result = 'người-dùng'.match(new RegExp(`^${SLUG_SEGMENT_PATTERN.source}$`));
-    expect(result).toBeNull();
+  test('accepts non-CJK Unicode (Vietnamese) since the #3417 all-script widening', () => {
+    // Pre-#3417 this was rejected (scope was CJK only). The grammar now uses
+    // Unicode property escapes, so đ/ư/etc. are valid slug characters.
+    const result = 'người-dùng'.match(new RegExp(`^${SLUG_SEGMENT_PATTERN.source}$`, 'u'));
+    expect(result).not.toBeNull();
   });
 });

test/takes-list-subcommand.test.ts

@@ -0,0 +1,76 @@
+/**
+ * #2079 — `gbrain takes list` used to parse "list" as a PAGE SLUG: cmdList
+ * looked up a page named "list" and printed "No takes on list." even when the
+ * brain held many takes — reading exactly like an empty takes table, so
+ * agents concluded there were no takes and moved on.
+ *
+ * Fix: `list` is a real subcommand (CLI parity with the takes_list op).
+ * Bare `takes <slug>` still lists per-page.
+ */
+
+import { afterAll, beforeAll, describe, expect, test } from 'bun:test';
+import { PGLiteEngine } from '../src/core/pglite-engine.ts';
+import { runTakes } from '../src/commands/takes.ts';
+
+let engine: PGLiteEngine;
+
+async function captureStdout(fn: () => Promise<void>): Promise<string> {
+  const lines: string[] = [];
+  const orig = console.log;
+  console.log = (...args: unknown[]) => { lines.push(args.join(' ')); };
+  try {
+    await fn();
+  } finally {
+    console.log = orig;
+  }
+  return lines.join('\n');
+}
+
+beforeAll(async () => {
+  engine = new PGLiteEngine();
+  await engine.connect({});
+  await engine.initSchema();
+  await engine.putPage('companies/acme-example', {
+    type: 'company',
+    title: 'Acme Example',
+    compiled_truth: 'Acme Example is a test company.',
+  });
+  const [row] = await engine.executeRaw<{ id: number }>(
+    `SELECT id FROM pages WHERE slug = 'companies/acme-example'`,
+  );
+  await engine.addTakesBatch([{
+    page_id: row.id,
+    row_num: 1,
+    claim: 'Acme will ship the widget by Q3.',
+    kind: 'bet',
+    holder: 'self',
+    weight: 0.7,
+  }]);
+});
+
+afterAll(async () => {
+  await engine.disconnect();
+});
+
+describe('gbrain takes list (#2079)', () => {
+  test('`takes list` lists all takes instead of slug-ifying "list"', async () => {
+    const out = await captureStdout(() => runTakes(engine, ['list']));
+    expect(out).not.toContain('No takes on list.');
+    expect(out).toContain('Acme will ship the widget by Q3.');
+    expect(out).toContain('companies/acme-example');
+  });
+
+  test('`takes list --json` returns the full take rows', async () => {
+    const out = await captureStdout(() => runTakes(engine, ['list', '--json']));
+    const parsed = JSON.parse(out);
+    expect(Array.isArray(parsed)).toBe(true);
+    expect(parsed.length).toBe(1);
+    expect(parsed[0].claim).toContain('Acme will ship');
+  });
+
+  test('per-page form still works: `takes <slug>`', async () => {
+    const out = await captureStdout(() => runTakes(engine, ['companies/acme-example']));
+    expect(out).toContain('# Takes on companies/acme-example');
+    expect(out).toContain('Acme will ship the widget by Q3.');
+  });
+});

test/v0_37_fix_wave.serial.test.ts

@@ -55,24 +55,20 @@ describe('v0.37 Lane A — defaults sweep', () => {
   test('A.5: embedding-column registry builtin defaults to ZE/1280 on empty config + gateway', async () => {
     // The registry's resolution chain is cfg > gateway > DEFAULT. With
     // no cfg AND no gateway, it should fall through to the canonical
-    // default (ZE/1280). Reset gateway first to exercise that path.
-    const { resetGateway } = await import('../src/core/ai/gateway.ts');
+    // default (ZE/1280). Hard-unconfigure first to exercise that path —
+    // resetGateway() would restore the preload's 1536 baseline (#3554).
+    const { __unconfigureGatewayForTests, resetGateway } = await import('../src/core/ai/gateway.ts');
     const { getEmbeddingColumnRegistry } = await import('../src/core/search/embedding-column.ts');
-    resetGateway();
+    __unconfigureGatewayForTests();
     try {
       const reg = getEmbeddingColumnRegistry({ engine: 'pglite' } as any);
       expect(reg['embedding']).toBeDefined();
       expect(reg['embedding'].provider).toBe('zeroentropyai:zembed-1');
       expect(reg['embedding'].dimensions).toBe(1280);
     } finally {
-      // Re-apply legacy preload defaults so the rest of the file's tests
-      // (and subsequent files in this shard) see a configured gateway.
-      const { configureGateway } = await import('../src/core/ai/gateway.ts');
-      configureGateway({
-        embedding_model: 'openai:text-embedding-3-large',
-        embedding_dimensions: 1536,
-        env: { ...process.env },
-      });
+      // Restore the preload's legacy baseline so the rest of the file's
+      // tests (and subsequent files in this shard) see a configured gateway.
+      resetGateway();
     }
   });