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/ai/capabilities.ts

@@ -22,7 +22,6 @@
  */
 
 import { resolveRecipe } from './model-resolver.ts';
-import { listRecipes } from './recipes/index.ts';
 import { AIConfigError } from './errors.ts';
 
 export interface ProviderCapabilities {
@@ -78,10 +77,7 @@ export function getProviderCapabilities(modelString: string): ProviderCapabiliti
   if (!chat) {
     throw new AIConfigError(
       `Provider "${recipe.id}" does not offer a chat touchpoint.`,
-      // Computed from the registry so the hint can't drift into listing
-      // chat-less providers (the pre-fix list falsely included embedding-only
-      // recipes, sending users in circles — #1157).
-      `Known providers with chat: ${listRecipes().filter(r => r.touchpoints.chat).map(r => r.id).join(', ')}. Pick one for models.tier.subagent.`,
+      `Known providers with chat: openai, anthropic, google, openrouter, litellm-proxy, deepseek, groq, together, azure-openai, dashscope, minimax, zhipu, ollama, llama-server. Pick one for models.tier.subagent.`,
     );
   }
 

src/core/ai/recipes/zhipu.ts

@@ -1,10 +1,9 @@
 import type { Recipe } from '../types.ts';
 
 /**
- * Zhipu AI (智谱AI) BigModel Open Platform. OpenAI-compatible /embeddings and
- * /chat/completions endpoints at open.bigmodel.cn. Hosts embedding-2 (1024d),
- * embedding-3 (Matryoshka up to 2048d), and the GLM chat family (glm-5.1 etc.)
- * with native tool calling — usable for models.tier.subagent (#1157).
+ * Zhipu AI (智谱AI) BigModel Open Platform. OpenAI-compatible /embeddings
+ * endpoint at open.bigmodel.cn. Hosts embedding-2 (1024d) and embedding-3
+ * (Matryoshka up to 2048d).
  *
  * embedding-3 at 2048 dims exceeds pgvector's HNSW cap of 2000 — those
  * brains fall back to exact vector scans (see
@@ -26,20 +25,6 @@ export const zhipu: Recipe = {
     setup_url: 'https://open.bigmodel.cn/',
   },
   touchpoints: {
-    chat: {
-      // Informational list (openai-compat tier: assertTouchpoint doesn't
-      // enforce it), so newer GLM ids pass without a recipe edit.
-      models: ['glm-5.1', 'glm-4.6', 'glm-4.5'],
-      supports_tools: true,
-      // gbrain-side stable tool ids (v0.38 D11) decoupled the loop from
-      // Anthropic response formats; GLM tool calling is stable through the
-      // OpenAI-compat path, same as deepseek/groq.
-      supports_subagent_loop: true,
-      // Anthropic-style cache_control markers are not honored on the
-      // OpenAI-compat path — the loop runs hot (degraded:no_caching warn).
-      supports_prompt_cache: false,
-      max_context_tokens: 128000,
-    },
     embedding: {
       models: ['embedding-3', 'embedding-2'],
       default_dims: 1024,
@@ -51,5 +36,5 @@ export const zhipu: Recipe = {
     },
   },
   setup_hint:
-    'Get an API key at https://open.bigmodel.cn/, then `export ZHIPUAI_API_KEY=...`. Chat/subagent: use `zhipu:glm-5.1`.',
+    'Get an API key at https://open.bigmodel.cn/, then `export ZHIPUAI_API_KEY=...`',
 };

test/ai/recipe-zhipu.test.ts

@@ -69,45 +69,6 @@ describe('recipe: zhipu', () => {
     expect(sql.toLowerCase()).toContain('hnsw');
   });
 
-  test('chat touchpoint declares GLM models with tool + subagent-loop support (#1157)', () => {
-    const r = getRecipe('zhipu')!;
-    expect(r.touchpoints.chat).toBeDefined();
-    expect(r.touchpoints.chat!.models).toContain('glm-5.1');
-    expect(r.touchpoints.chat!.supports_tools).toBe(true);
-    expect(r.touchpoints.chat!.supports_subagent_loop).toBe(true);
-    expect(r.touchpoints.chat!.supports_prompt_cache).toBe(false);
-  });
-
-  test('zhipu:glm-5.1 passes the subagent capability gate (degraded:no_caching, not refused)', async () => {
-    // Pre-fix: getProviderCapabilities threw "does not offer a chat touchpoint"
-    // and classifyCapabilities returned 'unknown' → subagent submit refused.
-    const { getProviderCapabilities, classifyCapabilities } =
-      await import('../../src/core/ai/capabilities.ts');
-    const caps = getProviderCapabilities('zhipu:glm-5.1');
-    expect(caps.supportsToolCalling).toBe(true);
-    expect(classifyCapabilities('zhipu:glm-5.1')).toBe('degraded:no_caching');
-  });
-
-  test('no-chat-touchpoint error hint lists only providers that actually have chat', async () => {
-    // The hint is computed from the registry; every provider it names must
-    // really carry a chat touchpoint (pre-fix it hardcoded zhipu/dashscope/
-    // minimax, all embedding-only at the time).
-    const { getProviderCapabilities } = await import('../../src/core/ai/capabilities.ts');
-    const { listRecipes } = await import('../../src/core/ai/recipes/index.ts');
-    let hint = '';
-    try {
-      getProviderCapabilities('voyage:voyage-3');
-      throw new Error('expected AIConfigError for embedding-only provider');
-    } catch (e) {
-      hint = (e as { fix?: string }).fix ?? String(e);
-    }
-    const listed = hint.match(/chat: ([^.]+)\./)?.[1]?.split(', ') ?? [];
-    expect(listed.length).toBeGreaterThan(0);
-    const withChat = new Set(listRecipes().filter(r => r.touchpoints.chat).map(r => r.id));
-    for (const id of listed) expect(withChat.has(id)).toBe(true);
-    expect(listed).toContain('zhipu');
-  });
-
   test('dimsProviderOptions threads dimensions for embedding-3 (Matryoshka)', async () => {
     // Codex finding #1: Zhipu embedding-3 is Matryoshka 256-2048. Without
     // `dimensions` on the wire, user-selected non-default dims are

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, {