fix(gateway): add chat touchpoint to zhipu recipe so GLM subagents work (#1157)

The zhipu recipe was embedding-only, so models.tier.subagent=zhipu:glm-5.1
threw "does not offer a chat touchpoint" — while the error hint falsely
listed zhipu (and dashscope/minimax, also embedding-only) among providers
with chat.

- zhipu recipe: add a chat touchpoint (glm-5.1 family, supports_tools +
  supports_subagent_loop; no Anthropic-style prompt cache on the
  OpenAI-compat path, so the loop runs with the degraded:no_caching warn).
  openai-compat tier means newer GLM ids pass without a recipe edit.
- capabilities.ts: compute the "Known providers with chat" hint from the
  recipe registry instead of a hardcoded list, so it can never drift into
  naming chat-less providers again.
- Declines the originally requested models.anthropic_compatible_prefixes
  config: v0.38's recipe-driven capability gate already replaced the
  Anthropic-only enforcement, so a recipe chat touchpoint is the whole fix.

Fixes #1157

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

src/commands/embed.ts

@@ -107,14 +107,6 @@ export interface EmbedOpts {
    * runs lock every source in sorted order. dryRun skips it.
    */
   singleFlight?: boolean;
-  /**
-   * #394: suppress human stdout summaries (the `[dry-run] Would embed ...` /
-   * `Embedded N chunks ...` slog lines). Set by structured-output callers —
-   * the cycle's embed phase (dream --json must keep stdout JSON-clean per
-   * docs/progress-events.md) reports counts via its own PhaseResult instead.
-   * Errors/warnings still go to stderr regardless.
-   */
-  quiet?: boolean;
 }
 
 /**
@@ -261,7 +253,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
     for (const s of opts.slugs) {
       if (isAborted(opts.signal)) break; // #1737: stop the per-slug loop on abort
       try {
-        await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal, opts.quiet);
+        await embedPage(engine, s, !!opts.dryRun, result, opts.sourceId, opts.signal);
       } catch (e: unknown) {
         serr(`  Error embedding ${s}: ${e instanceof Error ? e.message : e}`);
       }
@@ -355,7 +347,6 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
         catchUp: opts.catchUp,
         pacer,
         paceMaxConcurrency,
-        quiet: opts.quiet,
       }, opts.signal);
     } finally {
       // E1: surface pacing telemetry (human + structured) when pacing was on.
@@ -385,7 +376,7 @@ export async function runEmbedCore(engine: BrainEngine, opts: EmbedOpts): Promis
     return result;
   }
   if (opts.slug) {
-    await embedPage(engine, opts.slug, !!opts.dryRun, result, opts.sourceId, opts.signal, opts.quiet);
+    await embedPage(engine, opts.slug, !!opts.dryRun, result, opts.sourceId, opts.signal);
     return result;
   }
   throw new Error('No embed target specified. Pass { slug }, { slugs }, { all }, or { stale }.');
@@ -530,7 +521,6 @@ async function embedPage(
   result: EmbedResult,
   sourceId?: string,
   signal?: AbortSignal,
-  quiet?: boolean,
 ) {
   const opts = sourceId ? { sourceId } : undefined;
   const page = await engine.getPage(slug, opts);
@@ -575,7 +565,7 @@ async function embedPage(
   result.skipped += chunks.length - toEmbed.length;
 
   if (toEmbed.length === 0) {
-    if (!quiet) slog(`${slug}: all ${chunks.length} chunks already embedded`);
+    slog(`${slug}: all ${chunks.length} chunks already embedded`);
     result.pages_processed++;
     return;
   }
@@ -612,7 +602,7 @@ async function embedPage(
   }
   result.embedded += toEmbed.length;
   result.pages_processed++;
-  if (!quiet) slog(`${slug}: embedded ${toEmbed.length} chunks`);
+  slog(`${slug}: embedded ${toEmbed.length} chunks`);
 }
 
 async function embedAll(
@@ -630,8 +620,6 @@ async function embedAll(
     pacer?: DbPacer;
     /** Resolved concurrency cap (E-1: the worker count, no separate permit). */
     paceMaxConcurrency?: number;
-    /** #394: suppress human stdout summaries (structured-output callers). */
-    quiet?: boolean;
   },
   signal?: AbortSignal,
 ) {
@@ -775,12 +763,10 @@ async function embedAll(
   });
 
   // Stdout summary preserved for scripts/tests that grep for counts.
-  if (!staleOpts?.quiet) {
-    if (dryRun) {
-      slog(`[dry-run] Would embed ${result.would_embed} chunks across ${pages.length} pages`);
-    } else {
-      slog(`Embedded ${result.embedded} chunks across ${pages.length} pages`);
-    }
+  if (dryRun) {
+    slog(`[dry-run] Would embed ${result.would_embed} chunks across ${pages.length} pages`);
+  } else {
+    slog(`Embedded ${result.embedded} chunks across ${pages.length} pages`);
   }
 }
 
@@ -816,8 +802,6 @@ async function embedAllStale(
     pacer?: DbPacer;
     /** Resolved concurrency cap (E-1: the worker count, no separate permit). */
     paceMaxConcurrency?: number;
-    /** #394: suppress human stdout summaries (structured-output callers). */
-    quiet?: boolean;
   },
   signature?: string,
   externalSignal?: AbortSignal,
@@ -835,7 +819,7 @@ async function embedAllStale(
       signature,
       ...(sourceId && { sourceId }),
     });
-    if (invalidated > 0 && !staleOpts?.quiet) {
+    if (invalidated > 0) {
       slog(`[embed] invalidated ${invalidated} chunk(s) embedded under a prior model signature`);
     }
   }
@@ -846,12 +830,10 @@ async function embedAllStale(
     dryRun && signature ? { ...sourceOpt, signature } : sourceOpt,
   );
   if (staleCount === 0) {
-    if (!staleOpts?.quiet) {
-      if (dryRun) {
-        slog('[dry-run] Would embed 0 chunks (0 stale found)');
-      } else {
-        slog('Embedded 0 chunks (0 stale found)');
-      }
+    if (dryRun) {
+      slog('[dry-run] Would embed 0 chunks (0 stale found)');
+    } else {
+      slog('Embedded 0 chunks (0 stale found)');
     }
     return;
   }
@@ -860,7 +842,7 @@ async function embedAllStale(
     result.would_embed += staleCount;
     result.total_chunks += staleCount;
     if (onProgress) onProgress(1, 1, 0);
-    if (!staleOpts?.quiet) slog(`[dry-run] Would embed ${staleCount} stale chunks`);
+    slog(`[dry-run] Would embed ${staleCount} stale chunks`);
     return;
   }
 
@@ -1100,7 +1082,7 @@ async function embedAllStale(
     if (budgetTimer) clearTimeout(budgetTimer);
   }
 
-  if (!staleOpts?.quiet) slog(`Embedded ${result.embedded} chunks across ${totalProcessedPages} pages`);
+  slog(`Embedded ${result.embedded} chunks across ${totalProcessedPages} pages`);
 
   // #1946 (OV2a): a catch-up pass that completed without being aborted but left
   // chunks unembedded means those chunks are stuck (a non-transient embed

src/core/ai/capabilities.ts

@@ -22,6 +22,7 @@
  */
 
 import { resolveRecipe } from './model-resolver.ts';
+import { listRecipes } from './recipes/index.ts';
 import { AIConfigError } from './errors.ts';
 
 export interface ProviderCapabilities {
@@ -77,7 +78,10 @@ export function getProviderCapabilities(modelString: string): ProviderCapabiliti
   if (!chat) {
     throw new AIConfigError(
       `Provider "${recipe.id}" does not offer a chat touchpoint.`,
-      `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.`,
+      // 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.`,
     );
   }
 

src/core/ai/recipes/zhipu.ts

@@ -1,9 +1,10 @@
 import type { Recipe } from '../types.ts';
 
 /**
- * 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).
+ * 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).
  *
  * embedding-3 at 2048 dims exceeds pgvector's HNSW cap of 2000 — those
  * brains fall back to exact vector scans (see
@@ -25,6 +26,20 @@ 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,
@@ -36,5 +51,5 @@ export const zhipu: Recipe = {
     },
   },
   setup_hint:
-    'Get an API key at https://open.bigmodel.cn/, then `export ZHIPUAI_API_KEY=...`',
+    'Get an API key at https://open.bigmodel.cn/, then `export ZHIPUAI_API_KEY=...`. Chat/subagent: use `zhipu:glm-5.1`.',
 };

src/core/cycle.ts

@@ -1214,9 +1214,7 @@ async function runPhaseEmbed(engine: BrainEngine, dryRun: boolean, signal?: Abor
     // 10-15 min one) bails within a batch instead of running to completion
     // after the job was killed — which left gbrain_cycle_locks held and
     // wedged every subsequent autopilot cycle.
-    // #394: quiet — the cycle reports embed counts via its own PhaseResult;
-    // raw `[dry-run] Would embed ...` stdout lines would corrupt `dream --json`.
-    const result = await runEmbedCore(engine, { stale: true, dryRun, signal, quiet: true });
+    const result = await runEmbedCore(engine, { stale: true, dryRun, signal });
     const embeddedCount = dryRun ? result.would_embed : result.embedded;
     return {
       phase: 'embed',

test/ai/recipe-zhipu.test.ts

@@ -69,6 +69,45 @@ 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/dream.test.ts

@@ -292,33 +292,6 @@ describe('runDream — output format', () => {
     expect(parsed).toHaveProperty('totals');
   });
 
-  // #394 / takeover of #854: the embed phase's `[dry-run] Would embed ...`
-  // summary must not leak onto stdout ahead of the JSON CycleReport.
-  test('--dry-run --json emits only JSON even when embed has stale chunks', async () => {
-    await engine.putPage('concepts/testing', {
-      type: 'concept',
-      title: 'Testing',
-      compiled_truth: 'Testing keeps JSON contracts honest.',
-      timeline: '',
-    });
-    await engine.upsertChunks('concepts/testing', [
-      { chunk_index: 0, chunk_text: 'Testing keeps JSON contracts honest.', chunk_source: 'compiled_truth' },
-    ]);
-
-    const lines: string[] = [];
-    const logSpy = spyOn(console, 'log').mockImplementation((msg: string) => { lines.push(String(msg)); });
-    await runDream(engine, ['--dir', repo, '--phase', 'embed', '--dry-run', '--json']);
-    logSpy.mockRestore();
-
-    const output = lines.join('\n');
-    expect(output.trimStart().startsWith('{')).toBe(true);
-    const parsed = JSON.parse(output);
-    expect(parsed.schema_version).toBe('1');
-    expect(parsed.phases[0].phase).toBe('embed');
-    // The stale chunk was still counted in the structured report.
-    expect(parsed.phases[0].details.would_embed).toBe(1);
-  });
-
   test('human output for clean status mentions "Brain is healthy"', async () => {
     const lines: string[] = [];
     const logSpy = spyOn(console, 'log').mockImplementation((msg: string) => { lines.push(String(msg)); });