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/backlinks.ts

@@ -5,8 +5,8 @@
  * checks if back-links exist, and optionally creates them.
  *
  * Usage:
- *   gbrain check-backlinks check [dir] [--dir <brain-dir>] # report missing back-links
- *   gbrain check-backlinks fix [dir] [--dir <brain-dir>]   # create missing back-links
+ *   gbrain check-backlinks check [--dir <brain-dir>]     # report missing back-links
+ *   gbrain check-backlinks fix [--dir <brain-dir>]        # create missing back-links
  *   gbrain check-backlinks fix --dry-run                  # preview fixes
  */
 
@@ -201,40 +201,6 @@ export interface BacklinksResult {
   dryRun: boolean;
 }
 
-export interface ParsedBacklinksArgs {
-  subcommand: string | undefined;
-  brainDir: string;
-  dryRun: boolean;
-}
-
-export function parseBacklinksArgs(args: string[]): ParsedBacklinksArgs {
-  const subcommand = args[0];
-  const dryRun = args.includes('--dry-run');
-  const dirIdx = args.indexOf('--dir');
-  const flagDir = dirIdx >= 0 && args[dirIdx + 1] && !args[dirIdx + 1].startsWith('--')
-    ? args[dirIdx + 1]
-    : undefined;
-
-  let positionalDir: string | undefined;
-  for (let i = 1; i < args.length; i++) {
-    const arg = args[i];
-    if (arg === '--dir') {
-      i++;
-      continue;
-    }
-    if (arg === '--dry-run') continue;
-    if (arg.startsWith('--')) continue;
-    positionalDir = arg;
-    break;
-  }
-
-  return {
-    subcommand,
-    brainDir: flagDir ?? positionalDir ?? '.',
-    dryRun,
-  };
-}
-
 /**
  * Library-level backlinks check/fix. Throws on validation errors; returns a
  * structured result so Minions handlers + autopilot-cycle can surface counts.
@@ -270,14 +236,16 @@ export async function runBacklinksCore(opts: BacklinksOpts): Promise<BacklinksRe
 }
 
 export async function runBacklinks(args: string[]) {
-  const { subcommand, brainDir, dryRun } = parseBacklinksArgs(args);
+  const subcommand = args[0];
+  const dirIdx = args.indexOf('--dir');
+  const brainDir = dirIdx >= 0 ? args[dirIdx + 1] : '.';
+  const dryRun = args.includes('--dry-run');
 
   if (!subcommand || !['check', 'fix'].includes(subcommand)) {
-    console.error('Usage: gbrain check-backlinks <check|fix> [dir] [--dir <brain-dir>] [--dry-run]');
+    console.error('Usage: gbrain check-backlinks <check|fix> [--dir <brain-dir>] [--dry-run]');
     console.error('  check    Report missing back-links');
     console.error('  fix      Create missing back-links (appends to Timeline)');
-    console.error('  dir      Brain directory (default: current directory)');
-    console.error('  --dir    Brain directory override');
+    console.error('  --dir    Brain directory (default: current directory)');
     console.error('  --dry-run  Preview fixes without writing');
     process.exit(1);
   }

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/backlinks.test.ts

@@ -4,7 +4,6 @@ import {
   extractPageTitle,
   hasBacklink,
   buildBacklinkEntry,
-  parseBacklinksArgs,
 } from '../src/commands/backlinks.ts';
 
 describe('extractEntityRefs', () => {
@@ -105,26 +104,3 @@ describe('findBacklinkGaps dedupe (v0.36.x #967 regression)', () => {
     }
   });
 });
-
-describe('parseBacklinksArgs', () => {
-  test('uses positional dir for check and fix subcommands', () => {
-    expect(parseBacklinksArgs(['check', '/tmp/brain']).brainDir).toBe('/tmp/brain');
-    expect(parseBacklinksArgs(['fix', '/tmp/brain']).brainDir).toBe('/tmp/brain');
-  });
-
-  test('defaults to cwd when no dir given', () => {
-    expect(parseBacklinksArgs(['check']).brainDir).toBe('.');
-  });
-
-  test('--dir overrides positional dir and preserves dry-run', () => {
-    const parsed = parseBacklinksArgs(['fix', '/tmp/ignored', '--dir', '/tmp/brain', '--dry-run']);
-    expect(parsed.subcommand).toBe('fix');
-    expect(parsed.brainDir).toBe('/tmp/brain');
-    expect(parsed.dryRun).toBe(true);
-  });
-
-  test('--dir missing its value falls back to positional dir', () => {
-    expect(parseBacklinksArgs(['check', '/tmp/brain', '--dir']).brainDir).toBe('/tmp/brain');
-    expect(parseBacklinksArgs(['check', '--dir', '--dry-run']).brainDir).toBe('.');
-  });
-});