Merge branch 'master' into pile/1961-takeover

src/cli.ts

@@ -54,7 +54,7 @@ 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', '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', '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', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector']);
 // 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.
@@ -78,6 +78,8 @@ const CLI_ONLY_SELF_HELP = new Set([
   'capture',
   // v0.42 self-upgrade ships its own usage (flags + the agent-skill story).
   'self-upgrade',
+  // maintain (#3015) prints its own usage block (modes + not-auto-applied list).
+  'maintain',
   // v0.43 (#2095): watch ships WATCH_HELP (flags + the stdin-turn protocol).
   'watch',
   // v0.37 fix wave (Lane D.4 + CDX2-12): sync's --no-embed flag was
@@ -1757,6 +1759,11 @@ async function handleCliOnly(command: string, args: string[]) {
         await runOrphans(engine, args);
         break;
       }
+      case 'maintain': {
+        const { runMaintain } = await import('./commands/maintain.ts');
+        await runMaintain(engine, args);
+        break;
+      }
       // v0.32.7 CJK wave — post-upgrade markdown re-chunk sweep.
       // v0.36 Phase 3 wave — `gbrain reindex --multimodal` re-embeds content_chunks
       // into the unified Voyage multimodal-3 column.

src/commands/embed.ts

@@ -581,7 +581,7 @@ async function embedPage(
   for (let j = 0; j < toEmbed.length; j++) {
     embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
   }
-  const updated: ChunkInput[] = chunks.map(c => ({
+  const updated: ChunkInput[] = chunks.map(c => preserveCodeMetadata(c, {
     chunk_index: c.chunk_index,
     chunk_text: c.chunk_text,
     chunk_source: c.chunk_source,
@@ -605,6 +605,31 @@ async function embedPage(
   slog(`${slug}: embedded ${toEmbed.length} chunks`);
 }
 
+/**
+ * Carry code-chunk metadata (language, symbol_name, symbol_type, line range,
+ * parent scope, doc comment, qualified name) from a loaded Chunk back into a
+ * ChunkInput destined for upsertChunks.
+ *
+ * Issue #769: every re-embed used to strip these fields, and upsertChunks
+ * overwrites (does not COALESCE) the metadata columns from EXCLUDED, so
+ * each pass clobbered code-def's primary index to NULL. Pulling the
+ * preservation into one helper keeps the three re-embed call sites
+ * (embedPage, embedAll non-stale, embedAllStale) in lock-step.
+ */
+function preserveCodeMetadata(loaded: any, base: ChunkInput): ChunkInput {
+  return {
+    ...base,
+    language: loaded.language ?? undefined,
+    symbol_name: loaded.symbol_name ?? undefined,
+    symbol_type: loaded.symbol_type ?? undefined,
+    start_line: loaded.start_line ?? undefined,
+    end_line: loaded.end_line ?? undefined,
+    parent_symbol_path: loaded.parent_symbol_path ?? undefined,
+    doc_comment: loaded.doc_comment ?? undefined,
+    symbol_name_qualified: loaded.symbol_name_qualified ?? undefined,
+  };
+}
+
 async function embedAll(
   engine: BrainEngine,
   staleOnly: boolean,
@@ -717,8 +742,10 @@ async function embedAll(
       for (let j = 0; j < toEmbed.length; j++) {
         embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
       }
-      // Preserve ALL chunks, only update embeddings for stale ones
-      const updated: ChunkInput[] = chunks.map(c => ({
+      // Preserve ALL chunks, only update embeddings for stale ones.
+      // preserveCodeMetadata threads code-chunk metadata (#769) so re-embed
+      // doesn't clobber language/symbol_name/symbol_type to NULL.
+      const updated: ChunkInput[] = chunks.map(c => preserveCodeMetadata(c, {
         chunk_index: c.chunk_index,
         chunk_text: c.chunk_text,
         chunk_source: c.chunk_source,
@@ -1012,7 +1039,10 @@ async function embedAllStale(
           for (let j = 0; j < stale.length; j++) {
             staleIdxToEmbedding.set(stale[j].chunk_index, embeddings[j]);
           }
-          const merged: ChunkInput[] = existing.map(c => ({
+          // preserveCodeMetadata threads code-chunk metadata (#769) so the
+          // autopilot --stale path doesn't clobber language/symbol_name/etc
+          // to NULL on every cycle.
+          const merged: ChunkInput[] = existing.map(c => preserveCodeMetadata(c, {
             chunk_index: c.chunk_index,
             chunk_text: c.chunk_text,
             chunk_source: c.chunk_source,

src/commands/extract.ts

@@ -1651,7 +1651,7 @@ async function extractTimelineFromDB(
  * make re-extraction idempotent). EVERY processed page is stamped, including
  * zero-link pages — they WERE processed.
  */
-async function extractStaleFromDB(
+export async function extractStaleFromDB(
   engine: BrainEngine,
   opts: {
     dryRun: boolean;

src/commands/maintain.ts

@@ -0,0 +1,224 @@
+/**
+ * gbrain maintain — conservative self-healing maintenance.
+ *
+ * This command automates the safe parts of the operator runbook:
+ *   - stale link/timeline extraction
+ *   - stale per-source dream cycles when doctor reports cycle_freshness
+ *
+ * It deliberately does NOT mutate source files, apply schema-pack upgrades, or
+ * invent semantic hub links. Those need review or a separate command with an
+ * auditable proposal surface.
+ */
+
+import { existsSync } from 'fs';
+import type { BrainEngine } from '../core/engine.ts';
+import type { BrainHealth } from '../core/types.ts';
+import { buildChecks, computeDoctorReport, type DoctorReport, type Check } from './doctor.ts';
+import { extractStaleFromDB } from './extract.ts';
+import { runCycle, type CycleReport } from '../core/cycle.ts';
+
+type ActionStatus = 'ok' | 'would_apply' | 'applied' | 'blocked' | 'skipped';
+
+export interface MaintenanceAction {
+  name: string;
+  status: ActionStatus;
+  message: string;
+  details?: Record<string, unknown>;
+}
+
+export interface MaintainOptions {
+  json: boolean;
+  safe: boolean;
+  dryRun: boolean;
+  help: boolean;
+}
+
+export interface MaintainReport {
+  mode: 'dry-run' | 'safe';
+  before: {
+    health: BrainHealth;
+    doctor: DoctorReport;
+  };
+  actions: MaintenanceAction[];
+  after: {
+    health: BrainHealth;
+    doctor: DoctorReport;
+  };
+}
+
+export function parseMaintainArgs(args: string[]): MaintainOptions {
+  const safe = args.includes('--safe');
+  return {
+    json: args.includes('--json'),
+    safe,
+    dryRun: args.includes('--dry-run') || !safe,
+    help: args.includes('--help') || args.includes('-h'),
+  };
+}
+
+export function extractCycleFreshnessSourceIds(checks: Check[]): string[] {
+  const ids = new Set<string>();
+  for (const check of checks) {
+    if (check.name !== 'cycle_freshness' || check.status === 'ok') continue;
+    const re = /Source '([^']+)' last cycled/g;
+    for (const match of check.message.matchAll(re)) {
+      const id = match[1]?.trim();
+      if (id) ids.add(id);
+    }
+  }
+  return [...ids].sort();
+}
+
+async function buildDoctorReport(engine: BrainEngine): Promise<DoctorReport> {
+  const checks = await buildChecks(engine, ['--json', '--scope=brain']);
+  return computeDoctorReport(checks);
+}
+
+async function runStaleExtraction(
+  engine: BrainEngine,
+  beforeHealth: BrainHealth,
+  dryRun: boolean,
+): Promise<MaintenanceAction> {
+  if (beforeHealth.stale_pages <= 0) {
+    return { name: 'extract_stale', status: 'ok', message: 'No stale pages.' };
+  }
+
+  if (dryRun) {
+    return {
+      name: 'extract_stale',
+      status: 'would_apply',
+      message: `Would run DB-backed stale extraction for ${beforeHealth.stale_pages} page(s).`,
+      details: { stale_pages: beforeHealth.stale_pages },
+    };
+  }
+
+  const result = await extractStaleFromDB(engine, {
+    dryRun: false,
+    jsonMode: false,
+    includeFrontmatter: false,
+    catchUp: false,
+  });
+
+  return {
+    name: 'extract_stale',
+    status: 'applied',
+    message: `Processed ${result.pagesProcessed} stale page(s); ${result.staleRemaining} remain.`,
+    details: {
+      links_created: result.linksCreated,
+      timeline_created: result.timelineCreated,
+      pages_processed: result.pagesProcessed,
+      stale_remaining: result.staleRemaining,
+    },
+  };
+}
+
+async function runCycleFreshnessMaintenance(
+  engine: BrainEngine,
+  beforeDoctor: DoctorReport,
+  dryRun: boolean,
+): Promise<MaintenanceAction[]> {
+  const sourceIds = extractCycleFreshnessSourceIds(beforeDoctor.checks);
+  if (sourceIds.length === 0) {
+    return [{ name: 'cycle_freshness', status: 'ok', message: 'All sources cycled recently.' }];
+  }
+
+  if (dryRun) {
+    return sourceIds.map((sourceId) => ({
+      name: 'cycle_freshness',
+      status: 'would_apply',
+      message: `Would run source-scoped dream cycle for ${sourceId}.`,
+      details: { source_id: sourceId },
+    }));
+  }
+
+  const sources = await engine.listAllSources();
+  const actions: MaintenanceAction[] = [];
+
+  for (const sourceId of sourceIds) {
+    const source = sources.find((s) => s.id === sourceId);
+    const localPath = source?.local_path ?? null;
+    const brainDir = localPath && existsSync(localPath) ? localPath : null;
+    const report: CycleReport = await runCycle(engine, {
+      brainDir,
+      dryRun: false,
+      pull: false,
+      sourceId,
+    });
+    actions.push({
+      name: 'cycle_freshness',
+      status: report.status === 'failed' ? 'blocked' : 'applied',
+      message: `Ran source-scoped dream cycle for ${sourceId}: ${report.status}.`,
+      details: {
+        source_id: sourceId,
+        brain_dir: brainDir,
+        cycle_status: report.status,
+        phases: report.phases.map((p) => ({ phase: p.phase, status: p.status })),
+      },
+    });
+  }
+
+  return actions;
+}
+
+export async function runMaintain(engine: BrainEngine, args: string[]): Promise<MaintainReport | void> {
+  const opts = parseMaintainArgs(args);
+  if (opts.help) {
+    console.log(`Usage: gbrain maintain [--safe] [--dry-run] [--json]
+
+Conservative self-healing maintenance.
+
+Modes:
+  --dry-run   Preview safe actions without writes. Default when --safe is absent.
+  --safe      Apply safe actions: stale extraction and source cycle freshness.
+  --json      Emit a structured before/action/after report.
+
+Not auto-applied:
+  source-file frontmatter fixes, schema-pack upgrades, atom-pack changes,
+  semantic hub-link guesses, and destructive cleanup.
+`);
+    return;
+  }
+
+  const beforeHealth = await engine.getHealth();
+  const beforeDoctor = await buildDoctorReport(engine);
+  const actions: MaintenanceAction[] = [];
+
+  actions.push(await runStaleExtraction(engine, beforeHealth, opts.dryRun));
+  actions.push(...await runCycleFreshnessMaintenance(engine, beforeDoctor, opts.dryRun));
+
+  const afterHealth = await engine.getHealth();
+  const afterDoctor = await buildDoctorReport(engine);
+  const report: MaintainReport = {
+    mode: opts.dryRun ? 'dry-run' : 'safe',
+    before: { health: beforeHealth, doctor: beforeDoctor },
+    actions,
+    after: { health: afterHealth, doctor: afterDoctor },
+  };
+
+  if (opts.json) {
+    console.log(JSON.stringify(report, null, 2));
+  } else {
+    printMaintainReport(report);
+  }
+  return report;
+}
+
+function printMaintainReport(report: MaintainReport): void {
+  console.log(`GBrain maintain (${report.mode})`);
+  console.log(
+    `Before: brain_score=${Math.round(report.before.health.brain_score)}/100 ` +
+    `stale=${report.before.health.stale_pages} islands=${report.before.health.orphan_pages} ` +
+    `doctor=${report.before.doctor.status}`,
+  );
+  for (const action of report.actions) {
+    console.log(`  ${action.status}: ${action.name} — ${action.message}`);
+  }
+  console.log(
+    `After:  brain_score=${Math.round(report.after.health.brain_score)}/100 ` +
+    `stale=${report.after.health.stale_pages} islands=${report.after.health.orphan_pages} ` +
+    `doctor=${report.after.doctor.status}`,
+  );
+  if (report.mode === 'dry-run') {
+    console.log('Run `gbrain maintain --safe` to apply safe actions.');
+  }
+}

src/commands/orphans.ts

@@ -15,6 +15,11 @@
 import type { BrainEngine } from '../core/engine.ts';
 import { createProgress, startHeartbeat } from '../core/progress.ts';
 import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
+import {
+  shouldExcludeFromOrphanReporting,
+  loadOrphanPolicyOverrides,
+  type OrphanPolicyOverrides,
+} from '../core/orphan-policy.ts';
 
 // --- Types ---
 
@@ -32,65 +37,14 @@ export interface OrphanResult {
   excluded: number;
 }
 
-// --- Filter constants ---
-
-/** Slug suffixes that are always auto-generated root files */
-const AUTO_SUFFIX_PATTERNS = ['/_index', '/log'];
-
-/** Page slugs that are pseudo-pages by convention */
-const PSEUDO_SLUGS = new Set(['_atlas', '_index', '_stats', '_orphans', '_scratch', 'claude']);
-
-/** Slug segment that marks raw sources */
-const RAW_SEGMENT = '/raw/';
-
-/** Slug prefixes where no inbound links is expected */
-const DENY_PREFIXES = [
-  'output/',
-  'dashboards/',
-  'scripts/',
-  'templates/',
-  'openclaw/config/',
-];
-
-/** First slug segments where no inbound links is expected */
-const FIRST_SEGMENT_EXCLUSIONS = new Set([
-  'scratch',
-  'thoughts',
-  'catalog',
-  'entities',
-  'raw',
-  'atoms',
-  'skills',
-]);
-
 // --- Filter logic ---
 
 /**
  * Returns true if a slug should be excluded from orphan reporting by default.
  * These are pages where having no inbound links is expected / not a content problem.
  */
-export function shouldExclude(slug: string): boolean {
-  // Pseudo-pages (exact match)
-  if (PSEUDO_SLUGS.has(slug)) return true;
-
-  // Auto-generated suffix patterns
-  for (const suffix of AUTO_SUFFIX_PATTERNS) {
-    if (slug.endsWith(suffix)) return true;
-  }
-
-  // Raw source slugs
-  if (slug.includes(RAW_SEGMENT)) return true;
-
-  // Deny-prefix slugs
-  for (const prefix of DENY_PREFIXES) {
-    if (slug.startsWith(prefix)) return true;
-  }
-
-  // First-segment exclusions
-  const firstSegment = slug.split('/')[0];
-  if (FIRST_SEGMENT_EXCLUSIONS.has(firstSegment)) return true;
-
-  return false;
+export function shouldExclude(slug: string, overrides?: OrphanPolicyOverrides): boolean {
+  return shouldExcludeFromOrphanReporting(slug, overrides);
 }
 
 /**
@@ -156,6 +110,7 @@ export async function findOrphans(
   let allOrphans: { slug: string; title: string; domain: string | null }[];
   let total: number;
   let excludedAll: number;
+  const overrides = includePseudo ? undefined : await loadOrphanPolicyOverrides(engine);
   try {
     allOrphans = await engine.findOrphanPages(
       sourceIds ? { sourceIds } : sourceId ? { sourceId } : undefined,
@@ -184,7 +139,7 @@ export async function findOrphans(
     total = liveRows.length;
     excludedAll = includePseudo
       ? 0
-      : liveRows.reduce((n, r) => n + (shouldExclude(r.slug) ? 1 : 0), 0);
+      : liveRows.reduce((n, r) => n + (shouldExclude(r.slug, overrides) ? 1 : 0), 0);
   } finally {
     stopHb();
     progress.finish();
@@ -192,7 +147,7 @@ export async function findOrphans(
 
   const filtered = includePseudo
     ? allOrphans
-    : allOrphans.filter(row => !shouldExclude(row.slug));
+    : allOrphans.filter(row => !shouldExclude(row.slug, overrides));
 
   const orphans: OrphanPage[] = filtered.map(row => ({
     slug: row.slug,

src/core/contextual-retrieval-service.ts

@@ -54,6 +54,7 @@ import {
 import {
   generatePerChunkSynopsis,
   SYNOPSIS_PROMPT_VERSION,
+  SYNOPSIS_DOC_MAX_CHARS,
   type GeneratePerChunkSynopsisResult,
 } from './page-summary.ts';
 import {
@@ -103,8 +104,17 @@ function getEmbeddingModelTag(): string {
 export function computeCorpusGeneration(args: {
   crMode: CRMode;
   haikuModel: string;
+  /**
+   * Resolved `SYNOPSIS_DOC_MAX_CHARS` for per_chunk_synopsis runs. When
+   * present, folded into the hash so changes to
+   * `GBRAIN_SYNOPSIS_DOC_MAX_CHARS` invalidate the prior cache cleanly.
+   * Omit for `crMode !== 'per_chunk_synopsis'` — title / none modes
+   * don't consult the cap and the field stays out of the hash for
+   * back-compat with pre-cap embeddings.
+   */
+  synopsisDocMaxChars?: number;
 }): string {
-  return createHash('sha256')
+  const h = createHash('sha256')
     .update(args.crMode)
     .update('|')
     .update(String(SYNOPSIS_PROMPT_VERSION))
@@ -113,9 +123,11 @@ export function computeCorpusGeneration(args: {
     .update('|')
     .update(String(TITLE_WRAPPER_VERSION))
     .update('|')
-    .update(getEmbeddingModelTag())
-    .digest('hex')
-    .slice(0, 16);
+    .update(getEmbeddingModelTag());
+  if (args.synopsisDocMaxChars !== undefined) {
+    h.update('|doc_cap=').update(String(args.synopsisDocMaxChars));
+  }
+  return h.digest('hex').slice(0, 16);
 }
 
 /**
@@ -253,7 +265,11 @@ export async function reembedPageWithContextualRetrieval(
       args.pageSlug,
       args.sourceId,
       resolution.mode,
-      computeCorpusGeneration({ crMode: resolution.mode, haikuModel: args.haikuModel ?? DEFAULT_HAIKU_MODEL }),
+      computeCorpusGeneration({
+        crMode: resolution.mode,
+        haikuModel: args.haikuModel ?? DEFAULT_HAIKU_MODEL,
+        synopsisDocMaxChars: resolution.mode === 'per_chunk_synopsis' ? SYNOPSIS_DOC_MAX_CHARS : undefined,
+      }),
     );
     return { kind: 'skipped', reason: 'no_chunks' };
   }
@@ -282,6 +298,7 @@ export async function reembedPageWithContextualRetrieval(
       const corpus_generation = computeCorpusGeneration({
         crMode: attemptMode,
         haikuModel,
+        synopsisDocMaxChars: attemptMode === 'per_chunk_synopsis' ? SYNOPSIS_DOC_MAX_CHARS : undefined,
       });
 
       // ── PHASE 2: single DB transaction ───────────────────────────

src/core/import-file.ts

@@ -733,6 +733,11 @@ export async function importFromContent(
       : computeCorpusGeneration({
           crMode: effectiveCRMode,
           haikuModel: 'anthropic:claude-haiku-4-5-20251001',
+          // Inline import-file path never uses per_chunk_synopsis (refuses
+          // upstream); pass undefined so the doc-cap field stays out of
+          // the hash here. Per_chunk_synopsis runs through the Minion
+          // backfill handler which threads SYNOPSIS_DOC_MAX_CHARS through
+          // the service layer.
         });
 
   // Transaction wraps all DB writes. Every per-page tx call carries the

src/core/link-extraction.ts

@@ -489,7 +489,22 @@ export async function extractPageLinks(
       // text inside `[[...]]` before any `|`), NOT the display alias
       // (ref.name = match[2]). `[[struktura|the project]]` must resolve
       // `struktura`, not "the project". The display text is for context only.
-      const matches = await resolver.resolveBasenameMatches(ref.slug);
+      //
+      // The literal may be path-qualified (`[[notes/struktura]]`). The FS
+      // path (resolveSlugAll) strips the dirname before its basename lookup,
+      // but this path passed the raw literal to an index keyed by final
+      // segments only — so every slash-containing wikilink outside
+      // DIR_PATTERN silently resolved to nothing. Query by the final
+      // segment, then use the written path as a disambiguation filter
+      // (the analogue of the FS ancestor walk honoring the written path):
+      // a match must end with the literal, so `[[notes/struktura]]` can
+      // resolve to `vault/notes/struktura` but never to `wiki/struktura`.
+      const slashIdx = ref.slug.lastIndexOf('/');
+      const basename = slashIdx === -1 ? ref.slug : ref.slug.slice(slashIdx + 1);
+      let matches = await resolver.resolveBasenameMatches(basename);
+      if (slashIdx !== -1) {
+        matches = matches.filter(m => m === ref.slug || m.endsWith(`/${ref.slug}`));
+      }
       if (matches.length === 0) continue;
       const idx = content.indexOf(ref.slug);
       const context = idx >= 0 ? excerpt(content, idx, 240) : ref.name;

src/core/orphan-policy.ts

@@ -0,0 +1,116 @@
+/**
+ * Shared orphan-reporting exclusion policy.
+ *
+ * These are pages where "no inbound links" is expected and should not count
+ * against health. Keep this in core so the CLI orphan report and engine health
+ * dashboard cannot drift.
+ *
+ * Defaults are GBrain-wide conventions only. Brain-specific exclusions
+ * (private folder names, one-off fixture slugs) belong in the brain's own
+ * config, not here:
+ *
+ *   gbrain config set orphans.exclude_prefixes "my-private-folder/,archive/"
+ *   gbrain config set orphans.exclude_slugs "some-one-off-page"
+ */
+
+const AUTO_SUFFIX_PATTERNS = ['/_index', '/log'];
+
+const PSEUDO_SLUGS = new Set(['_atlas', '_index', '_stats', '_orphans', '_scratch', 'claude']);
+
+const RAW_SEGMENT = '/raw/';
+
+const DENY_PREFIXES = [
+  'output/',
+  'dashboards/',
+  'scripts/',
+  'templates/',
+  '_templates/',
+  'openclaw/config/',
+  'extracts/',
+];
+
+const FIRST_SEGMENT_EXCLUSIONS = new Set([
+  'scratch',
+  'thoughts',
+  'catalog',
+  'entities',
+  'raw',
+  'atoms',
+  'skills',
+  'dreaming',
+  'daily',
+]);
+
+const ROOT_DATE_SLUG = /^\d{4}-\d{2}-\d{2}(?:-.+)?$/;
+
+function isAgentWorkspaceConvention(slug: string): boolean {
+  if (!slug.startsWith('agents/')) return false;
+  if (slug.includes('/memory/dreaming/')) return true;
+  return /^agents\/[^/]+\/(?:agents|identity|soul|tools|user|heartbeat|dreams|dormant)$/.test(slug);
+}
+
+/** Per-brain additions to the convention defaults (from config). */
+export interface OrphanPolicyOverrides {
+  excludePrefixes?: string[];
+  excludeSlugs?: string[];
+}
+
+/** Config keys for per-brain orphan exclusions (comma-separated values). */
+export const ORPHAN_EXCLUDE_PREFIXES_KEY = 'orphans.exclude_prefixes';
+export const ORPHAN_EXCLUDE_SLUGS_KEY = 'orphans.exclude_slugs';
+
+function parseList(value: string | null): string[] {
+  if (!value) return [];
+  return value.split(',').map(s => s.trim()).filter(Boolean);
+}
+
+/**
+ * Load per-brain orphan exclusions from the brain config table. Callers with
+ * an engine in hand (getHealth, `gbrain orphans`) pass the result as the
+ * second argument to shouldExcludeFromOrphanReporting.
+ */
+export async function loadOrphanPolicyOverrides(
+  engine: { getConfig(key: string): Promise<string | null> },
+): Promise<OrphanPolicyOverrides> {
+  const [prefixes, slugs] = await Promise.all([
+    engine.getConfig(ORPHAN_EXCLUDE_PREFIXES_KEY),
+    engine.getConfig(ORPHAN_EXCLUDE_SLUGS_KEY),
+  ]);
+  return { excludePrefixes: parseList(prefixes), excludeSlugs: parseList(slugs) };
+}
+
+export function shouldExcludeFromOrphanReporting(
+  slug: string,
+  overrides?: OrphanPolicyOverrides,
+): boolean {
+  if (PSEUDO_SLUGS.has(slug)) return true;
+
+  for (const suffix of AUTO_SUFFIX_PATTERNS) {
+    if (slug.endsWith(suffix)) return true;
+  }
+
+  if (slug.includes(RAW_SEGMENT)) return true;
+  if (slug.includes('/daily/')) return true;
+
+  for (const prefix of DENY_PREFIXES) {
+    if (slug.startsWith(prefix)) return true;
+  }
+
+  const firstSegment = slug.split('/')[0];
+  if (FIRST_SEGMENT_EXCLUSIONS.has(firstSegment)) return true;
+
+  if (ROOT_DATE_SLUG.test(slug)) return true;
+
+  if (slug.startsWith('_brain-')) return true;
+
+  if (isAgentWorkspaceConvention(slug)) return true;
+
+  if (overrides) {
+    if (overrides.excludeSlugs?.includes(slug)) return true;
+    for (const prefix of overrides.excludePrefixes ?? []) {
+      if (slug.startsWith(prefix)) return true;
+    }
+  }
+
+  return false;
+}

src/core/page-summary.ts

@@ -44,6 +44,33 @@ const HAIKU_MAX_TOKENS = 200;
 /** Default model when caller doesn't override. Resolves through the gateway. */
 const DEFAULT_SYNOPSIS_MODEL = 'anthropic:claude-haiku-4-5-20251001';
 
+/**
+ * Hard cap on `documentText` length (chars) before send.
+ *
+ * 2026-05-25 fix wave: small local chat models (Gemma 4 E2B, Qwen3 4B) get
+ * dramatically slower on long contexts even with 131K-token windows declared.
+ * A 73K-char page synopsis on Gemma 4 E2B takes 60-120s, exceeding the
+ * worker's default 30s `lockDuration` and tripping `lock-lost` errors.
+ *
+ * Truncate to a budget that fits a small model's effective throughput while
+ * preserving enough document context for the synopsis to be useful. Truncates
+ * the TAIL because the head (title, frontmatter, intro) carries the
+ * document-level anchor the synopsis needs.
+ *
+ * Override per workload via `GBRAIN_SYNOPSIS_DOC_MAX_CHARS`. Default 32768
+ * (~8K tokens at 4 chars/tok) keeps small-model synopsis under ~30s.
+ * Anthropic Haiku is unaffected at this cap; bump higher when running
+ * frontier models if you want richer document anchoring.
+ */
+export const SYNOPSIS_DOC_MAX_CHARS = (() => {
+  const env = process.env.GBRAIN_SYNOPSIS_DOC_MAX_CHARS;
+  if (env && /^\d+$/.test(env)) {
+    const n = parseInt(env, 10);
+    if (n >= 512 && n <= 1_048_576) return n;
+  }
+  return 32768;
+})();
+
 /**
  * Synopsis prompt version. Folded into corpus_generation so prompt edits
  * invalidate prior embeddings via the v0.40.3.0 query_cache.page_generations
@@ -188,11 +215,19 @@ function buildUserPrompt(
   documentText: string,
   chunkText: string,
 ): string {
+  // Tail-truncate `documentText` to `SYNOPSIS_DOC_MAX_CHARS` so small local
+  // chat models don't stall on >100KB pages. Head preserved (title block,
+  // frontmatter, intro paragraphs carry the document-level anchor).
+  let trimmedDoc = documentText;
+  if (documentText.length > SYNOPSIS_DOC_MAX_CHARS) {
+    trimmedDoc = documentText.slice(0, SYNOPSIS_DOC_MAX_CHARS) +
+      `\n\n[... ${documentText.length - SYNOPSIS_DOC_MAX_CHARS} chars truncated for synopsis budget ...]`;
+  }
   return [
     `<page_title>${pageTitle}</page_title>`,
     '',
     '<full_document>',
-    documentText,
+    trimmedDoc,
     '</full_document>',
     '',
     '<chunk>',

src/core/pglite-engine.ts

@@ -57,6 +57,8 @@ import { finalizeLastSeen } from './chronicle/last-seen.ts';
 import { computeAnomaliesFromBuckets } from './cycle/anomaly.ts';
 import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
 import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
+import { shouldExcludeFromOrphanReporting, loadOrphanPolicyOverrides } from './orphan-policy.ts';
+import { LINK_EXTRACTOR_VERSION_TS } from './link-extraction.ts';
 import {
   normalizeEngineColumn,
   buildVectorCastFragment,
@@ -2322,6 +2324,10 @@ export class PGLiteEngine implements BrainEngine {
     // v0.40.3.0 D24 NULL→non-NULL race fix mirrors postgres-engine.ts. Two writers
     // racing on the same chunk previously raced last-write-wins; the fix lets the
     // fresher `embedded_at` win in the text-unchanged branch.
+    //
+    // 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.
     await this.db.query(
       `INSERT INTO content_chunks ${cols} VALUES ${rowParts.join(', ')}
        ON CONFLICT (page_id, chunk_index) DO UPDATE SET
@@ -2345,14 +2351,14 @@ export class PGLiteEngine implements BrainEngine {
                 THEN EXCLUDED.embedded_at
            ELSE content_chunks.embedded_at
          END,
-         language = EXCLUDED.language,
-         symbol_name = EXCLUDED.symbol_name,
-         symbol_type = EXCLUDED.symbol_type,
-         start_line = EXCLUDED.start_line,
-         end_line = EXCLUDED.end_line,
-         parent_symbol_path = EXCLUDED.parent_symbol_path,
-         doc_comment = EXCLUDED.doc_comment,
-         symbol_name_qualified = EXCLUDED.symbol_name_qualified,
+         language = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.language ELSE COALESCE(EXCLUDED.language, content_chunks.language) END,
+         symbol_name = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.symbol_name ELSE COALESCE(EXCLUDED.symbol_name, content_chunks.symbol_name) END,
+         symbol_type = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.symbol_type ELSE COALESCE(EXCLUDED.symbol_type, content_chunks.symbol_type) END,
+         start_line = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.start_line ELSE COALESCE(EXCLUDED.start_line, content_chunks.start_line) END,
+         end_line = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.end_line ELSE COALESCE(EXCLUDED.end_line, content_chunks.end_line) END,
+         parent_symbol_path = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.parent_symbol_path ELSE COALESCE(EXCLUDED.parent_symbol_path, content_chunks.parent_symbol_path) END,
+         doc_comment = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.doc_comment ELSE COALESCE(EXCLUDED.doc_comment, content_chunks.doc_comment) END,
+         symbol_name_qualified = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.symbol_name_qualified ELSE COALESCE(EXCLUDED.symbol_name_qualified, content_chunks.symbol_name_qualified) END,
          modality = EXCLUDED.modality,
          embedding_image = COALESCE(EXCLUDED.embedding_image, content_chunks.embedding_image)`,
       params
@@ -5207,15 +5213,10 @@ export class PGLiteEngine implements BrainEngine {
         (SELECT count(*) FROM pages) 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,
-        (SELECT count(*) FROM pages p
-         WHERE p.updated_at < (SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id)
-        ) as stale_pages,
-        -- Bug 11 — orphan = islanded (no inbound AND no outbound).
-        -- See BrainHealth.orphan_pages docstring; docs updated to match this.
-        (SELECT count(*) FROM pages p
-         WHERE NOT EXISTS (SELECT 1 FROM links l WHERE l.to_page_id = p.id)
-           AND NOT EXISTS (SELECT 1 FROM links l WHERE l.from_page_id = p.id)
-        ) as orphan_pages,
+        0 as stale_pages,
+        -- Bug 11 — orphan = islanded (no inbound AND no outbound). The raw
+        -- list is filtered in TS using the shared orphan-reporting policy.
+        0 as orphan_pages,
         (SELECT count(*) FROM links l
          WHERE NOT EXISTS (SELECT 1 FROM pages p WHERE p.id = l.to_page_id)
         ) as dead_links,
@@ -5240,10 +5241,20 @@ export class PGLiteEngine implements BrainEngine {
       LIMIT 5
     `);
 
+    const { rows: islandedRows } = await this.db.query(`
+      SELECT p.slug
+      FROM pages p
+      WHERE NOT EXISTS (SELECT 1 FROM links l WHERE l.to_page_id = p.id)
+        AND NOT EXISTS (SELECT 1 FROM links l WHERE l.from_page_id = p.id)
+    `);
+
     const r = h as Record<string, unknown>;
     const pageCount = Number(r.page_count);
     const embedCoverage = Number(r.embed_coverage);
-    const orphanPages = Number(r.orphan_pages);
+    const stalePages = await this.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS });
+    const orphanOverrides = await loadOrphanPolicyOverrides(this);
+    const orphanPages = (islandedRows as { slug: string }[])
+      .filter(row => !shouldExcludeFromOrphanReporting(row.slug, orphanOverrides)).length;
     const deadLinks = Number(r.dead_links);
     const linkCount = Number(r.link_count);
     const pagesWithTimeline = Number(r.pages_with_timeline);
@@ -5271,7 +5282,7 @@ export class PGLiteEngine implements BrainEngine {
     return {
       page_count: pageCount,
       embed_coverage: embedCoverage,
-      stale_pages: Number(r.stale_pages),
+      stale_pages: stalePages,
       orphan_pages: orphanPages,
       missing_embeddings: Number(r.missing_embeddings),
       brain_score: brainScore,

src/core/postgres-engine.ts

@@ -67,6 +67,8 @@ import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
 import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
 import { DEFAULT_EMBEDDING_MODEL, DEFAULT_EMBEDDING_DIMENSIONS } from './ai/defaults.ts';
 import { DELETE_BATCH_SIZE } from './engine-constants.ts';
+import { shouldExcludeFromOrphanReporting, loadOrphanPolicyOverrides } from './orphan-policy.ts';
+import { LINK_EXTRACTOR_VERSION_TS } from './link-extraction.ts';
 
 function escapeSqlStringLiteral(value: string): string {
   return value.replace(/'/g, "''");
@@ -2473,6 +2475,13 @@ export class PostgresEngine implements BrainEngine {
     //   - new is fresher (embedded_at > existing.embedded_at) → take new
     //   - otherwise → keep existing (slower writer with stale embedding loses)
     // Mirrored in pglite-engine.ts; pinned by test/e2e/concurrent-embed-race.test.ts.
+    //
+    // Code-chunk metadata columns (language / symbol_name / symbol_type / line range /
+    // parent_symbol_path / doc_comment / symbol_name_qualified) follow the SAME chunk_text-gated
+    // CASE pattern as `embedding` (#769). Re-chunk (chunk_text changed) trusts EXCLUDED outright;
+    // 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.
     await sql.unsafe(
       `INSERT INTO content_chunks ${cols} VALUES ${rows.join(', ')}
        ON CONFLICT (page_id, chunk_index) DO UPDATE SET
@@ -2496,14 +2505,14 @@ export class PostgresEngine implements BrainEngine {
                 THEN EXCLUDED.embedded_at
            ELSE content_chunks.embedded_at
          END,
-         language = EXCLUDED.language,
-         symbol_name = EXCLUDED.symbol_name,
-         symbol_type = EXCLUDED.symbol_type,
-         start_line = EXCLUDED.start_line,
-         end_line = EXCLUDED.end_line,
-         parent_symbol_path = EXCLUDED.parent_symbol_path,
-         doc_comment = EXCLUDED.doc_comment,
-         symbol_name_qualified = EXCLUDED.symbol_name_qualified,
+         language = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.language ELSE COALESCE(EXCLUDED.language, content_chunks.language) END,
+         symbol_name = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.symbol_name ELSE COALESCE(EXCLUDED.symbol_name, content_chunks.symbol_name) END,
+         symbol_type = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.symbol_type ELSE COALESCE(EXCLUDED.symbol_type, content_chunks.symbol_type) END,
+         start_line = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.start_line ELSE COALESCE(EXCLUDED.start_line, content_chunks.start_line) END,
+         end_line = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.end_line ELSE COALESCE(EXCLUDED.end_line, content_chunks.end_line) END,
+         parent_symbol_path = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.parent_symbol_path ELSE COALESCE(EXCLUDED.parent_symbol_path, content_chunks.parent_symbol_path) END,
+         doc_comment = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.doc_comment ELSE COALESCE(EXCLUDED.doc_comment, content_chunks.doc_comment) END,
+         symbol_name_qualified = CASE WHEN EXCLUDED.chunk_text != content_chunks.chunk_text THEN EXCLUDED.symbol_name_qualified ELSE COALESCE(EXCLUDED.symbol_name_qualified, content_chunks.symbol_name_qualified) END,
          modality = EXCLUDED.modality,
          embedding_image = COALESCE(EXCLUDED.embedding_image, content_chunks.embedding_image)`,
       params as Parameters<typeof sql.unsafe>[1],
@@ -5313,11 +5322,9 @@ export class PostgresEngine implements BrainEngine {
   async getHealth(): Promise<BrainHealth> {
     const sql = this.sql;
     // Bug 11 doc-drift fix — orphan_pages means "islanded" (no inbound AND
-    // no outbound links), aligning both engines with the user-facing
-    // definition. The type comment previously said "no inbound" but the
-    // SQL required both — docs now match code so users can trust the
-    // number. A hub page that links out to many but has no back-references
-    // is working as intended, not an orphan.
+    // 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.
     const [h] = await sql`
       WITH entity_pages AS (
         SELECT id, slug FROM pages WHERE type IN ('person', 'company')
@@ -5326,13 +5333,8 @@ export class PostgresEngine implements BrainEngine {
         (SELECT count(*) FROM pages) 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,
-        (SELECT count(*) FROM pages p
-         WHERE p.updated_at < (SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id)
-        ) as stale_pages,
-        (SELECT count(*) FROM pages p
-         WHERE NOT EXISTS (SELECT 1 FROM links l WHERE l.to_page_id = p.id)
-           AND NOT EXISTS (SELECT 1 FROM links l WHERE l.from_page_id = p.id)
-        ) as orphan_pages,
+        0 as stale_pages,
+        0 as orphan_pages,
         (SELECT count(*) FROM links l
          WHERE NOT EXISTS (SELECT 1 FROM pages p WHERE p.id = l.to_page_id)
         ) as dead_links,
@@ -5356,9 +5358,18 @@ export class PostgresEngine implements BrainEngine {
       LIMIT 5
     `;
 
+    const islandedRows = await sql<{ slug: string }[]>`
+      SELECT p.slug
+      FROM pages p
+      WHERE NOT EXISTS (SELECT 1 FROM links l WHERE l.to_page_id = p.id)
+        AND NOT EXISTS (SELECT 1 FROM links l WHERE l.from_page_id = p.id)
+    `;
+
     const pageCount = Number(h.page_count);
     const embedCoverage = Number(h.embed_coverage);
-    const orphanPages = Number(h.orphan_pages);
+    const stalePages = await this.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS });
+    const orphanOverrides = await loadOrphanPolicyOverrides(this);
+    const orphanPages = islandedRows.filter(row => !shouldExcludeFromOrphanReporting(row.slug, orphanOverrides)).length;
     const deadLinks = Number(h.dead_links);
     const linkCount = Number(h.link_count);
     const pagesWithTimeline = Number(h.pages_with_timeline);
@@ -5386,7 +5397,7 @@ export class PostgresEngine implements BrainEngine {
     return {
       page_count: pageCount,
       embed_coverage: embedCoverage,
-      stale_pages: Number(h.stale_pages),
+      stale_pages: stalePages,
       orphan_pages: orphanPages,
       missing_embeddings: Number(h.missing_embeddings),
       brain_score: brainScore,

test/e2e/global-basename-pglite.test.ts

@@ -172,6 +172,59 @@ describe('issue #972 — DB-source (gbrain extract links --source db)', () => {
     expect(strk!.link_type).toBe('wikilink_basename');
   });
 
+  test('flag ON → path-qualified wikilink outside DIR_PATTERN resolves via DB path', async () => {
+    // `[[notes/struktura]]` — `notes` is not in DIR_PATTERN, so the ref
+    // reaches the generic pass with its dirname intact. Regression: the DB
+    // path queried the basename index with the raw literal (which is keyed
+    // by final segments only), so path-qualified wikilinks outside
+    // DIR_PATTERN silently produced zero edges while the FS path resolved
+    // the identical content.
+    await engine.putPage('notes/struktura', {
+      type: 'concept' as any, title: 'Struktura Notes',
+      compiled_truth: '', timeline: '',
+    });
+    await engine.putPage('concepts/knowledge-graph', {
+      type: 'concept', title: 'Knowledge Graph',
+      compiled_truth: 'Background in [[notes/struktura]].', timeline: '',
+    });
+    await engine.setConfig('link_resolution.global_basename', 'true');
+
+    await runExtract(engine, ['links', '--source', 'db']);
+
+    const outLinks = await engine.getLinks('concepts/knowledge-graph');
+    const strk = outLinks.find(l => l.to_slug === 'notes/struktura');
+    expect(strk).toBeDefined();
+    expect(strk!.link_type).toBe('wikilink_basename');
+    expect(strk!.link_source).toBe('wikilink-resolved');
+  });
+
+  test('path-qualified wikilink never attaches to a basename-only sibling', async () => {
+    // Both notes/struktura and wiki/struktura exist. The author wrote
+    // `[[notes/struktura]]` — the written path must exclude wiki/struktura
+    // (a bare `[[struktura]]` would legitimately match both).
+    await engine.putPage('notes/struktura', {
+      type: 'concept' as any, title: 'Struktura Notes',
+      compiled_truth: '', timeline: '',
+    });
+    await engine.putPage('wiki/struktura', {
+      type: 'concept' as any, title: 'Struktura Wiki',
+      compiled_truth: '', timeline: '',
+    });
+    await engine.putPage('concepts/x', {
+      type: 'concept', title: 'X',
+      compiled_truth: 'See [[notes/struktura]].', timeline: '',
+    });
+    await engine.setConfig('link_resolution.global_basename', 'true');
+
+    await runExtract(engine, ['links', '--source', 'db']);
+
+    const outLinks = await engine.getLinks('concepts/x');
+    const basenameLinks = outLinks
+      .filter(l => l.link_type === 'wikilink_basename')
+      .map(l => l.to_slug);
+    expect(basenameLinks).toEqual(['notes/struktura']);
+  });
+
   test('flag OFF → no basename edges via DB path (back-compat)', async () => {
     await engine.putPage('projects/struktura', {
       type: 'project', title: 'Struktura',

test/embed.serial.test.ts

@@ -803,3 +803,107 @@ describe('embedAllStale --source threading (D7)', () => {
     expect((firstCallOpts as { sourceId?: string }).sourceId).toBe('media-corpus');
   });
 });
+
+// ────────────────────────────────────────────────────────────────
+// Code metadata preservation across re-embed (regression for #769)
+// ────────────────────────────────────────────────────────────────
+//
+// gbrain v0.30.1 and earlier silently clobbered code-chunk metadata
+// (language, symbol_name, symbol_type, start_line, end_line,
+// parent_symbol_path, doc_comment, symbol_name_qualified) on every
+// re-embed pass. The chunker populated those columns at import time,
+// but embed.ts loaded chunks via getChunks then mapped them to a
+// stripped ChunkInput carrying only 5 fields. upsertChunks then
+// OVERWROTE (not COALESCEd) the metadata columns from EXCLUDED, so
+// re-embed wiped them to NULL. End result on a real brain: 4875 code
+// pages, 47866 chunks, all with NULL language/symbol_name/symbol_type;
+// code-def returned 0 hits across every indexed repo.
+//
+// All three runEmbed paths (--stale autopilot, --all, --slugs) must
+// thread metadata through the re-upsert. Tests below assert that the
+// engine.upsertChunks call carries the same metadata it loaded.
+
+describe('runEmbed preserves code-chunk metadata across re-embed (regression for #769)', () => {
+  const fullCodeChunk = {
+    chunk_index: 0,
+    chunk_text: '[Java] foo/Bar.java:10-20 method baz',
+    chunk_source: 'compiled_truth' as const,
+    embedded_at: null,
+    token_count: 12,
+    language: 'java',
+    symbol_name: 'baz',
+    symbol_type: 'function',
+    start_line: 10,
+    end_line: 20,
+    parent_symbol_path: ['Bar'],
+    doc_comment: 'does the thing',
+    symbol_name_qualified: 'Bar.baz',
+  };
+
+  function metadataOf(chunk: any) {
+    return {
+      language: chunk.language,
+      symbol_name: chunk.symbol_name,
+      symbol_type: chunk.symbol_type,
+      start_line: chunk.start_line,
+      end_line: chunk.end_line,
+      parent_symbol_path: chunk.parent_symbol_path,
+      doc_comment: chunk.doc_comment,
+      symbol_name_qualified: chunk.symbol_name_qualified,
+    };
+  }
+
+  test('--stale (autopilot path) carries code metadata into upsertChunks', async () => {
+    const stale = [{
+      slug: 'code-page',
+      chunk_index: 0,
+      chunk_text: fullCodeChunk.chunk_text,
+      chunk_source: 'compiled_truth',
+      model: null,
+      token_count: 12,
+    }];
+    let upsertChunkArgs: any[] | null = null;
+    const engine = mockEngine({
+      countStaleChunks: async () => 1,
+      listStaleChunks: async () => stale,
+      getChunks: async () => [fullCodeChunk],
+      upsertChunks: async (_slug: string, chunks: any[]) => { upsertChunkArgs = chunks; },
+    });
+
+    await runEmbed(engine, ['--stale']);
+
+    expect(upsertChunkArgs).not.toBeNull();
+    expect(upsertChunkArgs!).toHaveLength(1);
+    expect(metadataOf(upsertChunkArgs![0])).toEqual(metadataOf(fullCodeChunk));
+  });
+
+  test('--all (full re-embed) carries code metadata into upsertChunks', async () => {
+    let upsertChunkArgs: any[] | null = null;
+    const engine = mockEngine({
+      listPages: async () => [{ slug: 'code-page' }],
+      getChunks: async () => [fullCodeChunk],
+      upsertChunks: async (_slug: string, chunks: any[]) => { upsertChunkArgs = chunks; },
+    });
+
+    await runEmbed(engine, ['--all']);
+
+    expect(upsertChunkArgs).not.toBeNull();
+    expect(upsertChunkArgs!).toHaveLength(1);
+    expect(metadataOf(upsertChunkArgs![0])).toEqual(metadataOf(fullCodeChunk));
+  });
+
+  test('--slugs (per-page embed) carries code metadata into upsertChunks', async () => {
+    let upsertChunkArgs: any[] | null = null;
+    const engine = mockEngine({
+      getPage: async () => ({ slug: 'code-page', compiled_truth: 'x', timeline: '' }),
+      getChunks: async () => [fullCodeChunk],
+      upsertChunks: async (_slug: string, chunks: any[]) => { upsertChunkArgs = chunks; },
+    });
+
+    await runEmbed(engine, ['--slugs', 'code-page']);
+
+    expect(upsertChunkArgs).not.toBeNull();
+    expect(upsertChunkArgs!).toHaveLength(1);
+    expect(metadataOf(upsertChunkArgs![0])).toEqual(metadataOf(fullCodeChunk));
+  });
+});

test/link-extraction.test.ts

@@ -403,6 +403,77 @@ describe('extractPageLinks', () => {
     expect(candidates).toEqual([]);
   });
 
+  test('path-qualified wikilink outside DIR_PATTERN queries by final segment', async () => {
+    // `[[notes/struktura]]` (dir not in DIR_PATTERN) falls to the generic
+    // pass. The resolver's basename index is keyed by final path segments,
+    // so the lookup must strip the dirname — mirroring the FS path
+    // (resolveSlugAll). Regression: the raw literal was passed through,
+    // which never matched, so these links silently dropped.
+    const seen: string[] = [];
+    const resolver: SlugResolver = {
+      resolve: async () => null,
+      resolveBasenameMatches: async (name) => {
+        seen.push(name);
+        return name === 'struktura' ? ['notes/struktura'] : [];
+      },
+    };
+    const { candidates } = await extractPageLinks(
+      'concepts/x', 'See [[notes/struktura]].',
+      {}, 'concept', resolver, { globalBasename: true },
+    );
+    expect(seen).toContain('struktura');
+    expect(seen).not.toContain('notes/struktura');
+    expect(candidates.map(c => c.targetSlug)).toEqual(['notes/struktura']);
+    expect(candidates[0].linkType).toBe('wikilink_basename');
+    expect(candidates[0].linkSource).toBe('wikilink-resolved');
+  });
+
+  test('path-qualified wikilink keeps only matches ending with the written path', async () => {
+    // The written path disambiguates: `[[notes/struktura]]` must never
+    // attach to `wiki/struktura` even though both share the basename.
+    const resolver: SlugResolver = {
+      resolve: async () => null,
+      resolveBasenameMatches: async (name) =>
+        name === 'struktura' ? ['notes/struktura', 'wiki/struktura'] : [],
+    };
+    const { candidates } = await extractPageLinks(
+      'concepts/x', 'See [[notes/struktura]].',
+      {}, 'concept', resolver, { globalBasename: true },
+    );
+    expect(candidates.map(c => c.targetSlug)).toEqual(['notes/struktura']);
+  });
+
+  test('path-qualified wikilink matches a deeper real slug by path suffix', async () => {
+    // The page lives at vault/notes/struktura; the author wrote the shorter
+    // tail `[[notes/struktura]]`. Suffix matching connects them, while the
+    // basename-only sibling `wiki/struktura` stays excluded.
+    const resolver: SlugResolver = {
+      resolve: async () => null,
+      resolveBasenameMatches: async (name) =>
+        name === 'struktura' ? ['vault/notes/struktura', 'wiki/struktura'] : [],
+    };
+    const { candidates } = await extractPageLinks(
+      'concepts/x', 'See [[notes/struktura]].',
+      {}, 'concept', resolver, { globalBasename: true },
+    );
+    expect(candidates.map(c => c.targetSlug)).toEqual(['vault/notes/struktura']);
+  });
+
+  test('path-qualified self-link is dropped like the bare form', async () => {
+    // `[[notes/struktura]]` written on notes/struktura itself must not
+    // produce a self-loop (same guard as the bare `[[own-tail]]` case).
+    const resolver: SlugResolver = {
+      resolve: async () => null,
+      resolveBasenameMatches: async (name) =>
+        name === 'struktura' ? ['notes/struktura'] : [],
+    };
+    const { candidates } = await extractPageLinks(
+      'notes/struktura', 'See [[notes/struktura]].',
+      {}, 'concept', resolver, { globalBasename: true },
+    );
+    expect(candidates).toEqual([]);
+  });
+
   test('bare wikilink resolution does not interfere with DIR_PATTERN wikilinks', async () => {
     // 2b refs (people/alice) take the verb-inferred type;
     // 2c refs (struktura) take wikilink_basename. Same call.

test/maintain.test.ts

@@ -0,0 +1,62 @@
+import { describe, expect, test } from 'bun:test';
+import {
+  extractCycleFreshnessSourceIds,
+  parseMaintainArgs,
+} from '../src/commands/maintain.ts';
+import type { Check } from '../src/commands/doctor.ts';
+
+describe('maintain args', () => {
+  test('defaults to dry-run unless --safe is explicit', () => {
+    expect(parseMaintainArgs([])).toMatchObject({
+      safe: false,
+      dryRun: true,
+      json: false,
+    });
+  });
+
+  test('--safe enables mutating safe mode', () => {
+    expect(parseMaintainArgs(['--safe', '--json'])).toMatchObject({
+      safe: true,
+      dryRun: false,
+      json: true,
+    });
+  });
+
+  test('--dry-run wins over --safe', () => {
+    expect(parseMaintainArgs(['--safe', '--dry-run'])).toMatchObject({
+      safe: true,
+      dryRun: true,
+    });
+  });
+});
+
+describe('cycle freshness source extraction', () => {
+  test('extracts stale source ids from doctor messages', () => {
+    const checks: Check[] = [
+      {
+        name: 'cycle_freshness',
+        status: 'fail',
+        message: "Source 'brain-sync-remote-teffur' last cycled 40h ago. Run `gbrain dream --source <id>`.",
+      },
+      {
+        name: 'cycle_freshness',
+        status: 'fail',
+        message: "Source 'wiki' last cycled 25h ago. Source 'wiki' last cycled 25h ago.",
+      },
+    ];
+
+    expect(extractCycleFreshnessSourceIds(checks)).toEqual([
+      'brain-sync-remote-teffur',
+      'wiki',
+    ]);
+  });
+
+  test('ignores ok and unrelated checks', () => {
+    const checks: Check[] = [
+      { name: 'cycle_freshness', status: 'ok', message: "Source 'fresh' last cycled recently." },
+      { name: 'frontmatter_integrity', status: 'warn', message: "Source 'wiki' has frontmatter issues." },
+    ];
+
+    expect(extractCycleFreshnessSourceIds(checks)).toEqual([]);
+  });
+});

test/orphans-pure-fn.test.ts

@@ -186,11 +186,67 @@ describe('shouldExclude — orphan filter regression (preserve curation)', () =>
     expect(shouldExclude('entities/anonymous')).toBe(true);
     expect(shouldExclude('atoms/fact-123')).toBe(true);
     expect(shouldExclude('skills/gbrain-operations')).toBe(true);
+    expect(shouldExclude('dreaming/light/2026-07-20')).toBe(true);
+    expect(shouldExclude('daily/2026-07-20')).toBe(true);
+    expect(shouldExclude('agent-openclaw/daily/2026-07-20')).toBe(true);
+  });
+
+  test('workspace convention slugs are excluded', () => {
+    expect(shouldExclude('_brain-conventions')).toBe(true);
+    expect(shouldExclude('_templates/decision')).toBe(true);
+    expect(shouldExclude('extracts/2026-06-30/takes.proposed/round-single')).toBe(true);
+    expect(shouldExclude('2026-07-20')).toBe(true);
+    expect(shouldExclude('2026-07-20-qa-sweep')).toBe(true);
+    expect(shouldExclude('agents/arya/identity')).toBe(true);
+    expect(shouldExclude('agents/arya/memory/dreaming/deep/2026-07-20')).toBe(true);
   });
 
   test('regular slugs are NOT excluded', () => {
     expect(shouldExclude('people/alice')).toBe(false);
     expect(shouldExclude('companies/acme')).toBe(false);
     expect(shouldExclude('writing/post-1')).toBe(false);
+    expect(shouldExclude('agents/arya/qa-reports/launch-review')).toBe(false);
+  });
+});
+
+describe('getHealth orphan_pages uses shared exclusion policy', () => {
+  test('excluded convention islands do not count against health', async () => {
+    await engine.putPage('_templates/decision', {
+      type: 'template', title: 'Decision', compiled_truth: 'template', timeline: '', frontmatter: {},
+    });
+    await engine.putPage('skills/arya/source-check', {
+      type: 'concept', title: 'Skill', compiled_truth: 'skill', timeline: '', frontmatter: {},
+    });
+    await engine.putPage('agents/arya/identity', {
+      type: 'note', title: 'Identity', compiled_truth: 'identity', timeline: '', frontmatter: {},
+    });
+    await engine.putPage('people/alice', {
+      type: 'person', title: 'Alice', compiled_truth: 'real island', timeline: '', frontmatter: {},
+    });
+
+    const health = await engine.getHealth();
+
+    expect(health.orphan_pages).toBe(1);
+  });
+
+  test('per-brain config overrides (orphans.exclude_*) also apply to health', async () => {
+    await engine.putPage('my-private-folder/secret-ref', {
+      type: 'note', title: 'Ref', compiled_truth: 'ref', timeline: '', frontmatter: {},
+    });
+    await engine.putPage('one-off-fixture-page', {
+      type: 'note', title: 'Fixture', compiled_truth: 'fixture', timeline: '', frontmatter: {},
+    });
+    await engine.putPage('people/alice', {
+      type: 'person', title: 'Alice', compiled_truth: 'real island', timeline: '', frontmatter: {},
+    });
+
+    expect((await engine.getHealth()).orphan_pages).toBe(3);
+
+    await engine.setConfig('orphans.exclude_prefixes', 'my-private-folder/');
+    await engine.setConfig('orphans.exclude_slugs', 'one-off-fixture-page');
+    expect((await engine.getHealth()).orphan_pages).toBe(1);
+
+    await engine.unsetConfig('orphans.exclude_prefixes');
+    await engine.unsetConfig('orphans.exclude_slugs');
   });
 });

test/orphans.test.ts

@@ -66,6 +66,10 @@ describe('shouldExclude', () => {
     expect(shouldExclude('templates/meeting-note')).toBe(true);
   });
 
+  test('excludes deny-prefix: _templates/', () => {
+    expect(shouldExclude('_templates/meeting-note')).toBe(true);
+  });
+
   test('excludes deny-prefix: openclaw/config/', () => {
     expect(shouldExclude('openclaw/config/agent')).toBe(true);
   });
@@ -86,10 +90,44 @@ describe('shouldExclude', () => {
     expect(shouldExclude('entities/product-hunt')).toBe(true);
   });
 
+  test('excludes first-segment: skills, dreaming, and daily', () => {
+    expect(shouldExclude('skills/arya/source-check')).toBe(true);
+    expect(shouldExclude('dreaming/light/2026-07-20')).toBe(true);
+    expect(shouldExclude('daily/2026-07-20')).toBe(true);
+    expect(shouldExclude('agent-openclaw/daily/2026-07-20')).toBe(true);
+  });
+
+  test('excludes root date logs and agent workspace conventions', () => {
+    expect(shouldExclude('_brain-conventions')).toBe(true);
+    expect(shouldExclude('2026-07-20')).toBe(true);
+    expect(shouldExclude('2026-07-20-qa-sweep')).toBe(true);
+    expect(shouldExclude('agents/arya/identity')).toBe(true);
+    expect(shouldExclude('agents/arya/memory/dreaming/deep/2026-07-20')).toBe(true);
+  });
+
+  test('excludes generated extracts', () => {
+    expect(shouldExclude('extracts/2026-06-30/takes.proposed/round-single')).toBe(true);
+  });
+
+  test('brain-specific exclusions come from config overrides, not global defaults', () => {
+    // No baked-in defaults for these:
+    expect(shouldExclude('my-private-folder/some-secret-ref.md')).toBe(false);
+    expect(shouldExclude('one-off-fixture-page')).toBe(false);
+    // The per-brain config plane (orphans.exclude_prefixes / exclude_slugs):
+    const overrides = {
+      excludePrefixes: ['my-private-folder/'],
+      excludeSlugs: ['one-off-fixture-page'],
+    };
+    expect(shouldExclude('my-private-folder/some-secret-ref.md', overrides)).toBe(true);
+    expect(shouldExclude('one-off-fixture-page', overrides)).toBe(true);
+    expect(shouldExclude('people/jane-doe', overrides)).toBe(false);
+  });
+
   test('does NOT exclude a normal content page', () => {
     expect(shouldExclude('companies/acme')).toBe(false);
     expect(shouldExclude('people/jane-doe')).toBe(false);
     expect(shouldExclude('projects/gbrain')).toBe(false);
+    expect(shouldExclude('agents/arya/qa-reports/launch-review')).toBe(false);
   });
 
   test('does NOT exclude a page ending with log-like text that is not /log', () => {