fix(import): fall back to body H1 for title when frontmatter lacks title: (#2446)

Title precedence is now frontmatter title: > body's first ATX H1 > the
slug/filename-humanized fallback. Slug-based imports (contacts, calendar)
carry a correct # Heading but no frontmatter title; without the H1 fallback
they got junk titles humanized from the slug. The H1 scan skips h2+ and
lines inside fenced code blocks, and strips closed-ATX trailing hashes.

Takeover of #2495.

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

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=...`',
 };

src/core/markdown.ts

@@ -135,7 +135,16 @@ export function parseMarkdown(
   const type = coerceFrontmatterString(frontmatter.type) || (
     opts?.activePack ? inferTypeFromPack(filePath, opts.activePack) : inferType(filePath)
   );
-  const title = coerceFrontmatterString(frontmatter.title).trim() || inferTitle(filePath);
+  // #2446: title precedence is frontmatter `title:` > the body's first H1 >
+  // the slug/filename-humanized fallback. Slug-based imports (contacts,
+  // calendar) write a correct `# Heading` but no frontmatter title; without
+  // the H1 fallback they get junk titles humanized from the slug
+  // (`Contact 20170928 5 John Defalco`), which also breaks anything keyed on
+  // the title (e.g. the by-mention gazetteer's first-token bucketing).
+  const title =
+    coerceFrontmatterString(frontmatter.title).trim() ||
+    inferTitleFromBody(body) ||
+    inferTitle(filePath);
   const tags = extractTags(frontmatter);
   const slug = coerceFrontmatterString(frontmatter.slug) || inferSlug(filePath);
 
@@ -602,6 +611,31 @@ function inferTypeWithPrefixes(
   return 'concept';
 }
 
+/**
+ * #2446: derive a title from the body's first ATX H1 (`# Heading`).
+ *
+ * Returns the trimmed heading text with the leading `# ` and any decorative
+ * trailing `#` run stripped, or '' if the body has no H1. Only a SINGLE leading
+ * `#` matches — `##`+ (h2 and deeper) are skipped — and lines inside a fenced
+ * code block (```/~~~) are ignored so a `# comment` in a shell snippet can't be
+ * mistaken for the page title.
+ */
+function inferTitleFromBody(body: string): string {
+  let inFence = false;
+  for (const raw of body.split('\n')) {
+    const fence = /^\s*(`{3,}|~{3,})/.exec(raw);
+    if (fence) {
+      inFence = !inFence;
+      continue;
+    }
+    if (inFence) continue;
+    // Exactly one leading `#`, then whitespace, then the heading text.
+    const m = /^#(?!#)\s+(.+?)\s*$/.exec(raw);
+    if (m) return m[1].replace(/\s+#+\s*$/, '').trim();
+  }
+  return '';
+}
+
 function inferTitle(filePath?: string): string {
   if (!filePath) return 'Untitled';
 

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/markdown.test.ts

@@ -343,3 +343,47 @@ describe('issue #1939 — non-string frontmatter coercion', () => {
     expect(parsed.title).toBe('A Normal Title');
   });
 });
+
+// issue #2446 — when frontmatter has no `title:`, prefer the body's first H1
+// over the slug/filename-humanized fallback. Slug-based imports (contacts,
+// calendar) carry a correct `# Heading` but no frontmatter title; humanizing
+// the slug leaks date/id tokens and loses casing (`Defalco` vs `DeFalco`).
+describe('issue #2446 — body H1 fallback for missing frontmatter title', () => {
+  test('no frontmatter title uses the body H1, not the slug-humanized junk', () => {
+    const md = '---\ntype: person\n---\n\n# John DeFalco\n\nNotes about John.\n';
+    const parsed = parseMarkdown(md, 'people/contact-20170928-5-john-defalco.md');
+    expect(parsed.title).toBe('John DeFalco');
+    // The slug-derived junk title must NOT win.
+    expect(parsed.title).not.toBe('Contact 20170928 5 John Defalco');
+  });
+
+  test('no frontmatter title and no H1 falls back to the inferred slug title', () => {
+    const md = '---\ntype: note\n---\n\njust body prose, no heading\n';
+    const parsed = parseMarkdown(md, 'people/alice-example.md');
+    expect(parsed.title).toBe('Alice Example');
+  });
+
+  test('frontmatter title wins over a body H1 (no regression)', () => {
+    const md = '---\ntitle: Frontmatter Wins\n---\n\n# Body Heading\n\nbody\n';
+    const parsed = parseMarkdown(md, 'people/some-slug.md');
+    expect(parsed.title).toBe('Frontmatter Wins');
+  });
+
+  test('h2 is not treated as the title; first real H1 is used', () => {
+    const md = '---\ntype: note\n---\n\n## Subsection First\n\n# The Real Title\n\nbody\n';
+    const parsed = parseMarkdown(md, 'notes/x.md');
+    expect(parsed.title).toBe('The Real Title');
+  });
+
+  test('a # inside a fenced code block is not mistaken for the title', () => {
+    const md = '---\ntype: note\n---\n\n```sh\n# this is a shell comment, not a heading\n```\n\n# Actual Heading\n';
+    const parsed = parseMarkdown(md, 'notes/x.md');
+    expect(parsed.title).toBe('Actual Heading');
+  });
+
+  test('trailing closing hashes are stripped from the H1', () => {
+    const md = '---\ntype: note\n---\n\n# Closed ATX Heading #\n\nbody\n';
+    const parsed = parseMarkdown(md, 'notes/x.md');
+    expect(parsed.title).toBe('Closed ATX Heading');
+  });
+});