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>

docs/tutorials/improving-skills-with-skillopt.md

@@ -233,14 +233,13 @@ keep it or `git checkout` to throw it away. Nothing is committed for you.
 
 **For a skill that ships with gbrain** (anything under the gbrain repo's own
 `skills/`): SkillOpt refuses to overwrite it by default and writes the winner to
-`skills/<name>/skillopt/proposed.md` instead (while keeping `best.md` as the
-optimizer's current-best pointer), so an optimization pass can never silently
-mutate a skill other people depend on. Two ways to handle that:
+`skills/<name>/skillopt/best.md` instead, so an optimization pass can never
+silently mutate a skill other people depend on. Two ways to handle that:
 
 ```bash
 # See the proposed improvement without touching SKILL.md (works for ANY skill):
 gbrain skillopt meeting-prep --split 1:1:1 --no-mutate
-# → writes skills/meeting-prep/skillopt/proposed.md, updates best.md, and prints the proposal path.
+# → writes skills/meeting-prep/skillopt/best.md (the proposed rewrite), prints its path. Copy what you want.
 
 # Actually rewrite a bundled skill (explicit opt-in + an independent held-out set):
 gbrain skillopt brain-ops --split 1:1:1 --allow-mutate-bundled \

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/skillopt/orchestrator.ts

@@ -93,13 +93,7 @@ import { resolveLrSchedule } from './lr-schedule.ts';
 import { preflight, formatPreflightReport } from './preflight.ts';
 import { isRejected, loadRejectedBuffer, makeRejectedEntry, saveRejectedBuffer } from './rejected-buffer.ts';
 import { runReflect, runOneShotRewrite, describeJudges } from './reflect.ts';
-import {
-  acceptCandidate,
-  proposedPath as proposedFilePath,
-  revertAllPending,
-  skillPath,
-  writeProposed,
-} from './version-store.ts';
+import { acceptCandidate, bestPath, revertAllPending, skillPath, writeProposed } from './version-store.ts';
 import { runValidationGate, scoreSkillOnTasks } from './validate-gate.ts';
 import { ROLLOUT_SUCCESS_THRESHOLD } from './types.ts';
 import type { SkillOptOpts, EditOp, RunReceipt, BenchmarkTask } from './types.ts';
@@ -708,9 +702,9 @@ async function runOptimizationLoop(
   // to the catch's assignment values only (it can't prove the async callback ran).
   const finalOutcome = outcome as 'accepted' | 'no_improvement' | 'aborted' | 'errored';
   if (!mutateDecision.mutate && finalOutcome === 'accepted') {
-    // writeProposed() emitted both the best pointer and the stable review
-    // artifact in the accept branch. SKILL.md remains untouched.
-    proposedPath = proposedFilePath(skillsDir, skillName);
+    // best.md was written by writeProposed() in the accept branch (no-mutate
+    // path); it doubles as proposed.md for human review. SKILL.md untouched.
+    proposedPath = bestPath(skillsDir, skillName);
   } else if (mutateDecision.mutate) {
     mutatedSkillFile = finalOutcome === 'accepted';
   }

src/core/skillopt/version-store.ts

@@ -23,7 +23,6 @@
  *
  *   history.json
  *   best.md
- *   proposed.md
  *   versions/
  *     v0001_e1_s1.md
  *     v0002_e1_s2.md
@@ -53,10 +52,6 @@ export function bestPath(skillsDir: string, skillName: string): string {
   return path.join(skilloptDir(skillsDir, skillName), 'best.md');
 }
 
-export function proposedPath(skillsDir: string, skillName: string): string {
-  return path.join(skilloptDir(skillsDir, skillName), 'proposed.md');
-}
-
 export function skillPath(skillsDir: string, skillName: string): string {
   return path.join(skillsDir, skillName, 'SKILL.md');
 }
@@ -176,18 +171,17 @@ export function acceptCandidate(input: AcceptInput): AcceptResult {
 }
 
 /**
- * Write the candidate to both `best.md` and `proposed.md` WITHOUT touching
- * SKILL.md or the history ledger. `best.md` remains the optimizer's current
- * best pointer; `proposed.md` is the stable human-review artifact promised by
- * `--no-mutate`. Returns the proposal path. Each write is atomic (.tmp + rename).
+ * Write the candidate to `best.md` (which doubles as `proposed.md`) WITHOUT
+ * touching SKILL.md or the history ledger. Used by the `--no-mutate` /
+ * bundled-without-allow paths: the optimizer found a better candidate but the
+ * caller opted out of in-place mutation, so we surface it for human review.
+ * Returns the path written. Atomic (.tmp + rename).
  */
 export function writeProposed(skillsDir: string, skillName: string, candidateText: string): string {
-  const best = bestPath(skillsDir, skillName);
-  const proposed = proposedPath(skillsDir, skillName);
-  fs.mkdirSync(path.dirname(best), { recursive: true });
-  atomicWrite(best, candidateText);
-  atomicWrite(proposed, candidateText);
-  return proposed;
+  const p = bestPath(skillsDir, skillName);
+  fs.mkdirSync(path.dirname(p), { recursive: true });
+  atomicWrite(p, candidateText);
+  return p;
 }
 
 /**

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/e2e/skillopt-loop.serial.test.ts

@@ -39,7 +39,6 @@ import { runSkillOpt } from '../../src/core/skillopt/orchestrator.ts';
 import {
   bestPath,
   loadHistory,
-  proposedPath,
   skillPath,
 } from '../../src/core/skillopt/version-store.ts';
 import { loadRejectedBuffer } from '../../src/core/skillopt/rejected-buffer.ts';
@@ -742,7 +741,7 @@ describe('skillopt T3 — F11 held-out gate, ablation opts, no-DB-pollution', ()
     } finally { fixture.cleanup(); }
   });
 
-  test('--no-mutate writes proposed.md and best.md, leaves SKILL.md untouched', async () => {
+  test('--no-mutate writes proposed.md (best.md), leaves SKILL.md untouched', async () => {
     const fixture = setupFixture(SKILL_PEOPLE_ONLY, CITATIONS_BENCHMARK);
     try {
       installStub({
@@ -754,9 +753,10 @@ describe('skillopt T3 — F11 held-out gate, ablation opts, no-DB-pollution', ()
           const result = await runOnce(fixture, { noMutate: true });
           expect(result.outcome).toBe('accepted');
           expect(result.mutatedSkillFile).toBe(false);
-          expect(result.proposedPath).toBe(proposedPath(fixture.skillsDir, SKILL));
+          expect(result.proposedPath).toBeDefined();
+          // proposed.md (best.md) exists and carries the improvement.
+          expect(fs.existsSync(result.proposedPath!)).toBe(true);
           expect(fs.readFileSync(result.proposedPath!, 'utf8')).toContain('## Citations');
-          expect(fs.readFileSync(bestPath(fixture.skillsDir, SKILL), 'utf8')).toContain('## Citations');
           // SKILL.md on disk is UNCHANGED (still People-only).
           const skill = fs.readFileSync(skillPath(fixture.skillsDir, SKILL), 'utf8');
           expect(skill).not.toContain('## Citations');

test/skillopt/version-store.test.ts

@@ -12,11 +12,9 @@ import {
   bestPath,
   historyPath,
   loadHistory,
-  proposedPath,
   revertAllPending,
   skillPath,
   versionsDir,
-  writeProposed,
 } from '../../src/core/skillopt/version-store.ts';
 
 let tmpDir: string;
@@ -81,19 +79,6 @@ describe('acceptCandidate (D8 two-phase commit)', () => {
   });
 });
 
-describe('writeProposed', () => {
-  test('writes distinct best and proposed artifacts without mutating SKILL.md (#2635)', () => {
-    const candidate = '---\nname: test\n---\nproposed body\n';
-
-    const written = writeProposed(tmpDir, SKILL, candidate);
-
-    expect(written).toBe(proposedPath(tmpDir, SKILL));
-    expect(fs.readFileSync(bestPath(tmpDir, SKILL), 'utf8')).toBe(candidate);
-    expect(fs.readFileSync(proposedPath(tmpDir, SKILL), 'utf8')).toBe(candidate);
-    expect(fs.readFileSync(skillPath(tmpDir, SKILL), 'utf8')).toContain('baseline body');
-  });
-});
-
 describe('revertAllPending (D8 crash recovery)', () => {
   test('no-op when no pending rows', () => {
     const reverted = revertAllPending(tmpDir, SKILL);