fix(cli): honor search --json output (#2042)

`gbrain search <q> --json` silently printed human text: the search/query
ops declare no json param, parseOpArgs dropped the undeclared trailing
flag, and formatResult only emitted human text or --explain output.

Treat --json as a CLI-local boolean formatter flag in parseOpArgs (never
added to the operation contract; MCP validateParams ignores the extra
key on the routed path) and have formatResult's search/query case emit
the raw result array as parseable JSON when set.

Takeover of #2531, rebased onto master (keeps bigintToStringReplacer at
the local-path formatResult call site).

Co-authored-by: javieraldape <javieraldape@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/cli.ts

@@ -464,7 +464,7 @@ async function main() {
     // routed path. Date → ISO string; bigint → string (postgres.js shape);
     // Buffer → object. Microsecond-cost; eliminates a whole drift bug class.
     const result = JSON.parse(JSON.stringify(rawResult, bigintToStringReplacer));
-    const output = formatResult(op.name, result);
+    const output = formatResult(op.name, result, params);
     if (output) process.stdout.write(output);
   } catch (e: unknown) {
     // v0.42.20.0 (codex D4): on error, set exitCode + return so the `finally`
@@ -547,7 +547,7 @@ async function runThinClientRouted(
       signal: sigintController.signal,
     });
     const result = unpackToolResult(raw);
-    const output = formatResult(op.name, result);
+    const output = formatResult(op.name, result, params);
     if (output) process.stdout.write(output);
   } catch (e: unknown) {
     if (e instanceof RemoteMcpError) {
@@ -777,6 +777,10 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
       const paramDef = op.params[key];
       if (paramDef?.type === 'boolean') {
         params[key] = true;
+      } else if (key === 'json') {
+        // Generic operation formatter flag. It is intentionally CLI-local:
+        // do not add it to the operation contract exposed over MCP/tools.
+        params[key] = true;
       } else if (i + 1 < args.length) {
         params[key] = args[++i];
         if (paramDef?.type === 'number') params[key] = Number(params[key]);
@@ -838,7 +842,11 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
 }
 
 // Exported for tests (same import-safety contract as cliAliases/printOpHelp).
-export function formatResult(opName: string, result: unknown): string {
+export function formatResult(
+  opName: string,
+  result: unknown,
+  params: Record<string, unknown> = {},
+): string {
   switch (opName) {
     case 'volunteer_context': {
       const r = result as any;
@@ -877,6 +885,7 @@ export function formatResult(opName: string, result: unknown): string {
     case 'search':
     case 'query': {
       const results = result as any[];
+      if (params.json === true) return JSON.stringify(results, null, 2) + '\n';
       if (results.length === 0) return 'No results.\n';
       // v0.40.4 — --explain switches to per-stage attribution formatter.
       // Reads CliOptions.explain via the module-level singleton.

src/core/ai/recipes/litellm-proxy.ts

@@ -56,36 +56,6 @@ 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>. For rerank: register a rerank model in LiteLLM and set search.reranker.model litellm:<model-name>.',
+  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>.',
 };

test/ai/recipe-litellm-reranker.test.ts

@@ -1,88 +0,0 @@
-/**
- * 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/cli-args.test.ts

@@ -20,5 +20,16 @@ describe('parseOpArgs', () => {
       source_id: 'gstack-code-repo-0e4763c9',
     });
   });
-});
 
+  test('--json is a CLI-local formatter flag for shared operations', () => {
+    const params = parseOpArgs(operationsByName.search, [
+      'needle',
+      '--json',
+    ]);
+
+    expect(params).toEqual({
+      query: 'needle',
+      json: true,
+    });
+  });
+});

test/cli-format-search-json.test.ts

@@ -0,0 +1,28 @@
+import { describe, expect, test } from 'bun:test';
+import { formatResult } from '../src/cli.ts';
+
+describe('formatResult - search/query --json', () => {
+  test('search --json renders the raw result array as parseable JSON', () => {
+    const out = formatResult('search', [
+      {
+        slug: 'docs/example',
+        score: 0.42,
+        chunk_text: 'Example result text',
+      },
+    ], { json: true });
+
+    expect(JSON.parse(out)).toEqual([
+      {
+        slug: 'docs/example',
+        score: 0.42,
+        chunk_text: 'Example result text',
+      },
+    ]);
+  });
+
+  test('query --json keeps empty results machine-readable', () => {
+    const out = formatResult('query', [], { json: true });
+
+    expect(JSON.parse(out)).toEqual([]);
+  });
+});

test/cli-search-dispatch.test.ts

@@ -49,6 +49,15 @@ describe('T5 — gbrain search dispatch', () => {
     });
   });
 
+  test('`search "<freetext>" --json` emits a parseable result array', () => {
+    withHome((home) => {
+      const { stdout, stderr, status } = run(['search', 'zzz-no-such-page-xyz', '--json'], home);
+      expect(status).toBe(0);
+      expect(stderr).not.toContain('Unknown subcommand');
+      expect(JSON.parse(stdout)).toEqual([]);
+    });
+  });
+
   test('`search stats --json` routes to the dashboard', () => {
     withHome((home) => {
       const { stdout, status } = run(['search', 'stats', '--json'], home);