fix(dream): stamp incremental extraction watermark (#2636)

The Dream cycle disables sync's inline extraction and routes changed
slugs through extractForSlugs, which flushed link/timeline batches but
never stamped links_extracted_at — so incrementally extracted pages
stayed permanently visible to `extract --stale` / doctor.

Collect processedRefs per successfully processed page and stamp them
via stampExtracted (best-effort) after both batch flushes, non-dry-run
mode 'all' only. Source-id threading from the original PR #2637 already
landed on master via #1503/#1747, so this rebase carries only the
missing watermark stamp plus regression tests.

Takeover of #2637.

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

src/commands/extract.ts

@@ -1025,6 +1025,10 @@ async function extractForSlugs(
   let linksCreated = 0;
   let timelineCreated = 0;
   let pagesProcessed = 0;
+  // #2636: successfully processed pages get their extraction watermark
+  // stamped after the final flush (mode 'all' only — a partial-mode run
+  // hasn't done the full extraction the watermark asserts).
+  const processedRefs: Array<{ slug: string; source_id: string }> = [];
 
   // Issue #972: read the basename flag once per extract run.
   const globalBasename = await isGlobalBasenameEnabled(engine);
@@ -1113,6 +1117,7 @@ async function extractForSlugs(
         }
 
         pagesProcessed++;
+        if (!dryRun) processedRefs.push({ slug, source_id: sourceId ?? 'default' });
       } catch { /* skip unreadable */ }
       progress.tick(1);
     },
@@ -1120,6 +1125,13 @@ async function extractForSlugs(
 
   await flushLinks();
   await flushTimeline();
+  // #2636: the Dream cycle disables sync's inline extraction and routes
+  // changed slugs through this incremental path — without a stamp here,
+  // those pages never get links_extracted_at and stay permanently visible
+  // to `extract --stale` / doctor. Stamp only after BOTH batches flushed.
+  if (!dryRun && mode === 'all') {
+    await stampExtracted(engine, processedRefs);
+  }
   progress.finish();
 
   if (!jsonMode) {

src/core/config.ts

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

src/core/engine.ts

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

src/core/facts/meta-hook.ts

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

src/core/facts/reader-trust.ts

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

src/core/operations.ts

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

src/core/pglite-engine.ts

@@ -18,7 +18,6 @@ import type {
 } from './engine.ts';
 import { MAX_SEARCH_LIMIT, clampSearchLimit } from './engine.ts';
 import { withRetry, BULK_RETRY_OPTS, resolveBulkRetryOpts, computeNextDelay, type BatchAuditSite } from './retry.ts';
-import { factsWorldOnly } from './facts/reader-trust.ts';
 import { logBatchRetry as auditLogBatchRetry, logBatchExhausted as auditLogBatchExhausted } from './audit/batch-retry-audit.ts';
 import { runMigrations } from './migrate.ts';
 import { PGLITE_SCHEMA_SQL, getPGLiteSchema } from './pglite-schema.ts';
@@ -4319,10 +4318,7 @@ export class PGLiteEngine implements BrainEngine {
     const useArray = Array.isArray(opts.sourceIds) && opts.sourceIds.length > 0;
     const sourceIds = useArray ? opts.sourceIds! : null;
     const sourceId = opts.sourceId ?? 'default';
-    // Direct-engine contract: unset `remote` here means a trusted in-process
-    // caller (CLI/tests) — the fail-closed default lives in the op layer, which
-    // always passes explicit booleans. Normalize before the fail-closed helper.
-    const remoteFilter = factsWorldOnly({ remote: opts.remote === true, trustedFactReads: opts.trustedFactReads === true });
+    const remoteFilter = opts.remote === true;
 
     // Build SQL dynamically. PGLite uses $N positional params; we
     // assemble the WHERE clauses + params array in tandem to keep them

src/core/postgres-engine.ts

@@ -14,7 +14,6 @@ import type {
   SourceRow,
 } from './engine.ts';
 import { withRetry, BULK_RETRY_OPTS, resolveBulkRetryOpts, computeNextDelay, type BatchAuditSite } from './retry.ts';
-import { factsWorldOnly } from './facts/reader-trust.ts';
 import { logBatchRetry as auditLogBatchRetry, logBatchExhausted as auditLogBatchExhausted } from './audit/batch-retry-audit.ts';
 import type {
   DomainBankSampleOpts, CorpusSampleOpts, DomainBankRow,
@@ -4533,10 +4532,7 @@ export class PostgresEngine implements BrainEngine {
     const useArray = Array.isArray(opts.sourceIds) && opts.sourceIds.length > 0;
     const sourceIds = useArray ? opts.sourceIds! : null;
     const sourceId = opts.sourceId ?? 'default';
-    // Direct-engine contract: unset `remote` here means a trusted in-process
-    // caller (CLI/tests) — the fail-closed default lives in the op layer, which
-    // always passes explicit booleans. Normalize before the fail-closed helper.
-    const remoteFilter = factsWorldOnly({ remote: opts.remote === true, trustedFactReads: opts.trustedFactReads === true });
+    const remoteFilter = opts.remote === true;
 
     // Source-scope predicate: array path (federated) wins over scalar.
     // Engine.ts contract: returns chronological points; regressions +

src/mcp/dispatch.ts

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

src/mcp/server.ts

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

test/engine-find-trajectory.test.ts

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

test/extract-incremental.test.ts

@@ -60,6 +60,51 @@ async function seedPage(slug: string, body: string): Promise<void> {
 }
 
 describe('runExtractCore — incremental cycle path (#417)', () => {
+  test('Dream incremental all-mode stamps the source-scoped extraction watermark (#2636)', async () => {
+    await engine.executeRaw(
+      `INSERT INTO sources (id, name, local_path) VALUES ($1, $2, $3)`,
+      ['repo-a', 'repo-a', tempDir],
+    );
+    await engine.putPage('people/alice-example', {
+      type: 'person',
+      title: 'alice-example',
+      compiled_truth: '# alice',
+      timeline: '',
+      frontmatter: {},
+      content_hash: 'h',
+    }, { sourceId: 'repo-a' });
+    writeFileSync(join(tempDir, 'people/alice-example.md'), '# alice');
+
+    await runExtractCore(engine as unknown as BrainEngine, {
+      mode: 'all',
+      dir: tempDir,
+      slugs: ['people/alice-example'],
+      sourceId: 'repo-a',
+    });
+
+    const rows = await engine.executeRaw<{ links_extracted_at: string | null }>(
+      `SELECT links_extracted_at FROM pages WHERE slug = $1 AND source_id = $2`,
+      ['people/alice-example', 'repo-a'],
+    );
+    expect(rows[0]?.links_extracted_at).not.toBeNull();
+    expect(await engine.countStalePagesForExtraction({ sourceId: 'repo-a' })).toBe(0);
+  });
+
+  test('Dream incremental dry-run does NOT stamp the watermark', async () => {
+    await seedPage('people/alice-example', '# alice');
+    await runExtractCore(engine as unknown as BrainEngine, {
+      mode: 'all',
+      dir: tempDir,
+      slugs: ['people/alice-example'],
+      dryRun: true,
+    });
+    const rows = await engine.executeRaw<{ links_extracted_at: string | null }>(
+      `SELECT links_extracted_at FROM pages WHERE slug = $1`,
+      ['people/alice-example'],
+    );
+    expect(rows[0]?.links_extracted_at ?? null).toBeNull();
+  });
+
   test('1. slugs: [] returns immediately with zero counts (early-return path)', async () => {
     await seedPage('people/alice-example', '# alice');
     const result = await runExtractCore(engine as unknown as BrainEngine, {

test/facts-reader-trust.test.ts

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