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/commands/doctor.ts

@@ -1551,24 +1551,6 @@ export async function checkRerankerHealth(engine: BrainEngine): Promise<Check> {
       };
     }
 
-    // Historical #2059 rows were logged as `unknown` before missing reranker
-    // auth was classified at the gateway. Surface repeated unknowns instead of
-    // reporting "ok" while every rerank fails open.
-    const unknownFails = failures.filter((f) => f.reason === 'unknown');
-    if (unknownFails.length >= 3) {
-      const setupHint = unknownFails.some((f) => {
-        const summary = String(f.error_summary ?? '');
-        return summary.includes('ZEROENTROPY_API_KEY') || summary.toLowerCase().includes('api key');
-      })
-        ? ' Fix: verify ZEROENTROPY_API_KEY and run `gbrain models doctor`.'
-        : '';
-      return {
-        name: 'reranker_health',
-        status: 'warn',
-        message: `${unknownFails.length} unknown reranker failure(s) in last 7 days.${setupHint}`,
-      };
-    }
-
     return {
       name: 'reranker_health',
       status: 'ok',

src/core/ai/gateway.ts

@@ -3656,15 +3656,7 @@ export async function rerank(input: RerankInput): Promise<RerankResult[]> {
   // whose request/response shape differs from ZE/llama.cpp (e.g. Voyage with
   // `top_k` / `data[]`) needs separate adapter hooks in a follow-up plan.
   const url = `${compat.baseURL.replace(/\/$/, '')}${tp.path ?? '/models/rerank'}`;
-  let auth: { apiKey?: string; headers?: Record<string, string> };
-  try {
-    auth = applyResolveAuth(recipe, cfg, 'reranker');
-  } catch (err) {
-    if (err instanceof AIConfigError) {
-      throw new RerankError(err.message, 'auth');
-    }
-    throw err;
-  }
+  const auth = applyResolveAuth(recipe, cfg, 'reranker');
   // applyResolveAuth returns { apiKey } for Bearer-style auth (SDK's native
   // path) or { headers } for custom-header providers (Azure). v0.37.6.0:
   // recipes can ALSO declare default_headers (attribution etc.) which flow

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>.',
 };

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/rerank.test.ts

@@ -154,28 +154,6 @@ describe('gateway.rerank() — happy path', () => {
 describe('gateway.rerank() — error classification', () => {
   beforeEach(() => configureZE());
 
-  test('missing required reranker API key → RerankError(auth) before HTTP call', async () => {
-    configureGateway({
-      reranker_model: 'zeroentropyai:zerank-2',
-      env: {},
-    });
-    let called = false;
-    __setRerankTransportForTests(async () => {
-      called = true;
-      return mockResp({ results: [{ index: 0, relevance_score: 0.5 }] });
-    });
-
-    try {
-      await rerank({ query: 'q', documents: ['d'] });
-      throw new Error('should have thrown');
-    } catch (err) {
-      expect(err).toBeInstanceOf(RerankError);
-      expect((err as RerankError).reason).toBe('auth');
-      expect((err as Error).message).toContain('ZEROENTROPY_API_KEY');
-      expect(called).toBe(false);
-    }
-  });
-
   test('401 → auth', async () => {
     __setRerankTransportForTests(async () => new Response('Unauthorized', { status: 401 }));
     try {

test/doctor.test.ts

@@ -2,11 +2,6 @@ import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:tes
 import { mkdirSync, rmSync, writeFileSync } from 'fs';
 import { join } from 'path';
 import { tmpdir } from 'os';
-import * as fs from 'node:fs';
-import * as os from 'node:os';
-import * as path from 'node:path';
-import { withEnv } from './helpers/with-env.ts';
-import { logRerankFailure } from '../src/core/rerank-audit.ts';
 
 describe('doctor command', () => {
   test('doctor module exports runDoctor', async () => {
@@ -52,34 +47,6 @@ describe('doctor command', () => {
     expect(check.issues![0].action).toContain('trigger');
   });
 
-  test('reranker_health warns on repeated unknown rerank failures', async () => {
-    const { checkRerankerHealth } = await import('../src/commands/doctor.ts');
-    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-rerank-doctor-'));
-    try {
-      await withEnv({ GBRAIN_AUDIT_DIR: tmpDir }, async () => {
-        for (let i = 0; i < 3; i++) {
-          logRerankFailure({
-            model: 'zeroentropyai:zerank-2',
-            reason: 'unknown',
-            query_hash: `unknown${i}`,
-            doc_count: 30,
-            error_summary: 'ZeroEntropy reranker requires ZEROENTROPY_API_KEY.',
-          });
-        }
-        const check = await checkRerankerHealth({
-          async getConfig(key: string): Promise<string | null> {
-            return key === 'search.reranker.enabled' ? 'true' : null;
-          },
-        } as any);
-        expect(check.status).toBe('warn');
-        expect(check.message).toContain('unknown');
-        expect(check.message).toContain('ZEROENTROPY_API_KEY');
-      });
-    } finally {
-      fs.rmSync(tmpDir, { recursive: true, force: true });
-    }
-  });
-
   test('runDoctor accepts null engine for filesystem-only mode', async () => {
     const { runDoctor } = await import('../src/commands/doctor.ts');
     // runDoctor should accept null engine — it runs filesystem checks only.

test/search/rerank.test.ts

@@ -12,14 +12,9 @@
  */
 
 import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
-import * as fs from 'node:fs';
-import * as os from 'node:os';
-import * as path from 'node:path';
 import { applyReranker, type RerankerOpts } from '../../src/core/search/rerank.ts';
 import { RerankError, type RerankResult } from '../../src/core/ai/gateway.ts';
-import { readRecentRerankFailures } from '../../src/core/rerank-audit.ts';
 import type { SearchResult } from '../../src/core/types.ts';
-import { withEnv } from '../helpers/with-env.ts';
 
 function makeResult(slug: string, score: number, chunk: string): SearchResult {
   return {
@@ -165,36 +160,6 @@ describe('applyReranker — fail-open on every RerankError reason', () => {
     expect(out).toEqual(results);
   });
 
-  test('missing gateway reranker API key fail-opens and audits auth', async () => {
-    const { configureGateway } = await import('../../src/core/ai/gateway.ts');
-    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-rerank-search-'));
-    try {
-      await withEnv({ GBRAIN_AUDIT_DIR: tmpDir }, async () => {
-        configureGateway({
-          reranker_model: 'zeroentropyai:zerank-2',
-          env: {},
-        });
-
-        const results = [makeResult('a', 1.0, 'doc a')];
-        const out = await applyReranker('q', results, {
-          enabled: true,
-          topNIn: 1,
-          topNOut: null,
-          model: 'zeroentropyai:zerank-2',
-        });
-
-        expect(out).toEqual(results);
-        const failures = readRecentRerankFailures(1);
-        expect(failures).toHaveLength(1);
-        expect(failures[0]!.reason).toBe('auth');
-        expect(failures[0]!.error_summary).toContain('ZEROENTROPY_API_KEY');
-      });
-    } finally {
-      fs.rmSync(tmpDir, { recursive: true, force: true });
-      configureGateway({ env: { ZEROENTROPY_API_KEY: 'test-key' } });
-    }
-  });
-
   test('fail-open on non-RerankError throw too', async () => {
     const results = [makeResult('a', 1.0, 'a')];
     const opts: RerankerOpts = {