feat(ai): add reranker touchpoint to LiteLLM proxy recipe (takeover of #2455)

LiteLLM normalizes Cohere/Voyage/Jina rerank backends to the wire shape
gateway.rerank() already speaks, so a reranker touchpoint on the litellm
recipe makes any proxied rerank model reachable via
`search.reranker.model litellm:<model>` with no adapter.

Repairs from the original PR:
- path is the LEAF '/rerank' (not '/v1/rerank'): LiteLLM serves both
  /rerank and /v1/rerank, and the recipe's setup_hint allows
  LITELLM_BASE_URL with or without the /v1 suffix — pinning '/v1/rerank'
  doubled to /v1/v1/rerank (404) on /v1-suffixed bases.
- setup_hint appends the rerank guidance to master's current line instead
  of replacing it with a stale pre-/v1-suffix version.
- cost_per_1m_tokens_usd stays undefined (pricing-unknown), matching the
  recipe's embedding/chat touchpoints and budget-tracker's deliberate
  litellm exclusion from the free-provider sets (a proxy can front a paid
  provider; the touchpoint field isn't consumed by rerank pricing anyway).

Test drives gateway.rerank()'s real URL builder via the stubbed transport
for both base-URL forms; the /v1-suffixed case fails with the original
PR's path.

Co-authored-by: ozp <ozp@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/litellm-proxy.ts

@@ -56,6 +56,36 @@ export const litellmProxy: Recipe = {
       cost_per_1m_output_usd: undefined,
       price_last_verified: '2026-06-14',
     },
+    // LiteLLM normalizes Cohere / Voyage / Jina / etc. rerank backends to the
+    // same wire shape gbrain's gateway.rerank() already speaks (the
+    // ZeroEntropy/llama.cpp contract):
+    //   { model, query, documents, top_n } → { results: [{ index, relevance_score }] }
+    // So any rerank model the user registers in their LiteLLM config is
+    // reachable via `gbrain config set search.reranker.model litellm:<model>`
+    // with no request/response adapter — same as embeddings ride the proxy.
+    reranker: {
+      models: [], // user-provided; whatever rerank models the proxy serves
+      // No canonical default — the proxy defines its own model ids. The user
+      // sets search.reranker.model explicitly (mirrors the embedding
+      // touchpoint's user_provided_models contract).
+      default_model: '',
+      // The proxied backend bills (Cohere/Voyage/…); pricing-unknown is the
+      // honest state — same stance as this recipe's embedding/chat
+      // touchpoints and budget-tracker's deliberate litellm exclusion from
+      // the free-provider sets.
+      cost_per_1m_tokens_usd: undefined,
+      price_last_verified: '2026-06-27',
+      max_payload_bytes: 5_000_000,
+      // LEAF path only (matches llama-server-reranker's convention). LiteLLM
+      // serves both `/rerank` and `/v1/rerank`, and LITELLM_BASE_URL may be
+      // set with or without the `/v1` suffix (the setup_hint allows both), so
+      // the leaf form yields a valid route either way:
+      //   http://localhost:4000    + /rerank → /rerank        ✓
+      //   http://localhost:4000/v1 + /rerank → /v1/rerank     ✓
+      // Pinning '/v1/rerank' here would double to /v1/v1/rerank → 404 on
+      // /v1-suffixed bases.
+      path: '/rerank',
+    },
   },
-  setup_hint: 'Run LiteLLM (https://docs.litellm.ai) in front of any provider; set LITELLM_BASE_URL (include the /v1 suffix if your proxy serves the OpenAI route there, e.g. http://localhost:4000/v1) + pass --embedding-model litellm:<model> and --embedding-dimensions <N>.',
+  setup_hint: 'Run LiteLLM (https://docs.litellm.ai) in front of any provider; set LITELLM_BASE_URL (include the /v1 suffix if your proxy serves the OpenAI route there, e.g. http://localhost:4000/v1) + pass --embedding-model litellm:<model> and --embedding-dimensions <N>. For rerank: register a rerank model in LiteLLM and set search.reranker.model litellm:<model-name>.',
 };

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-litellm-reranker.test.ts

@@ -0,0 +1,88 @@
+/**
+ * litellm-proxy reranker touchpoint smoke.
+ *
+ * Sibling of recipe-llama-server-reranker.test.ts. Pins the reranker
+ * touchpoint on the LiteLLM proxy recipe so:
+ *  - the touchpoint exists with the LEAF '/rerank' path (LiteLLM serves both
+ *    /rerank and /v1/rerank, so the leaf form is valid whether or not the
+ *    user's LITELLM_BASE_URL carries the /v1 suffix the setup_hint allows)
+ *  - a /v1-suffixed base URL does NOT produce /v1/v1/rerank (the original
+ *    community PR pinned '/v1/rerank' which 404s on /v1-suffixed bases)
+ *  - models: [] (user-provided; proxy defines the model ids)
+ *  - pricing stays undefined (proxy can front a paid provider — same honest
+ *    pricing-unknown stance as the embedding/chat touchpoints)
+ *
+ * The gateway.rerank() URL tests drive the real URL builder via the stubbed
+ * transport (same seam as test/ai/rerank.test.ts).
+ */
+
+import { describe, expect, test, afterEach } from 'bun:test';
+import { getRecipe } from '../../src/core/ai/recipes/index.ts';
+import {
+  configureGateway,
+  resetGateway,
+  rerank,
+  __setRerankTransportForTests,
+} from '../../src/core/ai/gateway.ts';
+
+afterEach(() => {
+  __setRerankTransportForTests(null);
+  resetGateway();
+});
+
+describe('recipe: litellm reranker touchpoint', () => {
+  test('declares reranker touchpoint with leaf /rerank path', () => {
+    const r = getRecipe('litellm')!;
+    const tp = r.touchpoints.reranker;
+    expect(tp).toBeDefined();
+    expect(tp!.path).toBe('/rerank');
+    expect(tp!.max_payload_bytes).toBe(5_000_000);
+  });
+
+  test('reranker touchpoint uses empty models[] for user-provided model ids', () => {
+    const r = getRecipe('litellm')!;
+    expect(r.touchpoints.reranker!.models).toEqual([]);
+  });
+
+  test('pricing stays undefined — proxy can front a paid provider', () => {
+    const r = getRecipe('litellm')!;
+    expect(r.touchpoints.reranker!.cost_per_1m_tokens_usd).toBeUndefined();
+  });
+
+  test('setup_hint keeps the /v1-suffix guidance AND mentions rerank', () => {
+    const r = getRecipe('litellm')!;
+    expect(r.setup_hint).toMatch(/\/v1 suffix/);
+    expect(r.setup_hint).toMatch(/search\.reranker\.model litellm:/);
+  });
+});
+
+describe('gateway.rerank() URL via litellm recipe', () => {
+  async function capturedRerankUrl(baseUrl?: string): Promise<string> {
+    configureGateway({
+      reranker_model: 'litellm:my-reranker',
+      env: {},
+      ...(baseUrl ? { base_urls: { litellm: baseUrl } } : {}),
+    });
+    let capturedUrl = '';
+    __setRerankTransportForTests(async (url) => {
+      capturedUrl = url;
+      return new Response(
+        JSON.stringify({ results: [{ index: 0, relevance_score: 0.9 }] }),
+        { status: 200, headers: { 'content-type': 'application/json' } },
+      );
+    });
+    await rerank({ query: 'q', documents: ['d'] });
+    return capturedUrl;
+  }
+
+  test('default base (no /v1 suffix) → /rerank', async () => {
+    const url = await capturedRerankUrl();
+    expect(url).toBe('http://localhost:4000/rerank');
+  });
+
+  test('/v1-suffixed base → /v1/rerank, NOT /v1/v1/rerank', async () => {
+    const url = await capturedRerankUrl('http://localhost:4000/v1');
+    expect(url).toBe('http://localhost:4000/v1/rerank');
+    expect(url).not.toContain('/v1/v1/');
+  });
+});

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