fix(rerank): classify missing auth before fallback (#2059)

Missing ZEROENTROPY_API_KEY threw AIConfigError from auth resolution, which
rerank.ts recorded as reason 'unknown' — and doctor's reranker_health had no
unknown bucket, so it reported ok while every rerank silently failed open.

- gateway.rerank wraps AIConfigError from applyResolveAuth as
  RerankError(reason: 'auth') before any HTTP call.
- checkRerankerHealth warns on >=3 'unknown' failures in the 7-day window
  (covers historical pre-fix audit rows), with a ZEROENTROPY_API_KEY setup
  hint when the error summary points at a missing key.
- Tests: RerankError(auth) classification, applyReranker fail-open + audit
  reason, doctor warn on repeated unknowns.

Takeover of #2070.

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

docs/tutorials/company-brain.md

@@ -223,16 +223,14 @@ export GBRAIN_REMOTE_CLIENT_ID=<Alice's client_id>
 export GBRAIN_REMOTE_CLIENT_SECRET=<Alice's client_secret>
 export GBRAIN_REMOTE_MCP_URL=https://brain.acme-co.com/mcp
 
-gbrain search "performance review"
+gbrain search "performance review" --remote
 ```
 
-(On a thin-client install every shared op routes through the remote MCP server automatically — no flag needed. The env vars select whose credentials the call uses.)
-
 Alice should see results only from `customers` and `shared`. The performance-review notes live in `internal`, which she's not scoped to read. She shouldn't see them.
 
 ```bash
 # Terminal 2, as Bob (export his credentials similarly)
-gbrain search "performance review"
+gbrain search "performance review" --remote
 ```
 
 Bob should see the performance-review notes from `internal`, plus anything related from `shared`. He shouldn't see anything that lives only in `customers`.
@@ -516,7 +514,7 @@ The first sync embeds every page, which takes time. Check `gbrain sources status
 
 ### "I see a page I shouldn't see"
 
-This shouldn't happen, but if you suspect it, run `gbrain search <query> --json` as the constrained client (thin-client install, with the client's `GBRAIN_REMOTE_*` env exported) and inspect the `source_id` field on every returned result. Every row should be in the client's `--federated-read` set. If one isn't, file an issue with the exact slug and source IDs.
+This shouldn't happen, but if you suspect it, run `gbrain search <query> --remote --json` as the constrained client and inspect the `source_id` field on every returned result. Every row should be in the client's `--federated-read` set. If one isn't, file an issue with the exact slug and source IDs.
 
 ### "The synthesized answer is wrong"
 

src/cli.ts

@@ -464,11 +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));
-    // #380 pass-through: `--json` (undeclared on most ops, promised by docs)
-    // emits the raw op result instead of the human formatter.
-    const output = params.json === true
-      ? JSON.stringify(result, null, 2) + '\n'
-      : formatResult(op.name, result);
+    const output = formatResult(op.name, result);
     if (output) process.stdout.write(output);
   } catch (e: unknown) {
     // v0.42.20.0 (codex D4): on error, set exitCode + return so the `finally`
@@ -551,10 +547,7 @@ async function runThinClientRouted(
       signal: sigintController.signal,
     });
     const result = unpackToolResult(raw);
-    // #380: same --json seam as the local-engine path (renderer parity).
-    const output = params.json === true
-      ? JSON.stringify(result, null, 2) + '\n'
-      : formatResult(op.name, result);
+    const output = formatResult(op.name, result);
     if (output) process.stdout.write(output);
   } catch (e: unknown) {
     if (e instanceof RemoteMcpError) {
@@ -764,28 +757,10 @@ export function resolveQueryImage(
   return { path: imagePath, base64, mime };
 }
 
-/**
- * #380: undeclared flags that are honored DOWNSTREAM of parseOpArgs and must
- * keep passing through when unknown flags become hard errors:
- *   - source     → makeContext's resolveSourceId (the --source axis)
- *   - brain      → the mount/brain routing axis (docs promise the flag)
- *   - dry_run    → makeContext's ctx.dryRun (ops without a declared dry_run)
- *   - json       → raw-JSON output seam (local + thin-client paths)
- */
-const PASSTHROUGH_VALUE_FLAGS = new Set(['source', 'brain']);
-const PASSTHROUGH_BOOL_FLAGS = new Set(['dry_run', 'json']);
-
 export function parseOpArgs(op: Operation, args: string[]): Record<string, unknown> {
   const params: Record<string, unknown> = {};
   const positional = op.cliHints?.positional || [];
   let posIdx = 0;
-  const cliName = op.cliHints?.name || op.name;
-  const MAX_STDIN = 5_000_000; // 5MB cap, shared by stdin and --file
-  // #380: `--file <path>` fills the op's declared stdin param (put's `content`)
-  // from a file. Driven by cliHints.stdin — no per-op hard-coding — and
-  // disabled when the op declares a real `file` param of its own.
-  const fileParam = op.cliHints?.stdin && !op.params.file ? op.cliHints.stdin : undefined;
-  let filePath: string | undefined;
 
   for (let i = 0; i < args.length; i++) {
     const arg = args[i];
@@ -799,42 +774,12 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
         }
       }
       const key = arg.slice(2).replace(/-/g, '_');
-      if (fileParam && key === 'file') {
-        if (i + 1 >= args.length) {
-          console.error(`Error: ${arg} requires a value.`);
-          process.exit(1);
-        }
-        filePath = args[++i];
-        continue;
-      }
       const paramDef = op.params[key];
-      if (!paramDef) {
-        if (PASSTHROUGH_BOOL_FLAGS.has(key)) {
-          params[key] = true;
-          continue;
-        }
-        if (PASSTHROUGH_VALUE_FLAGS.has(key)) {
-          if (i + 1 >= args.length) {
-            console.error(`Error: ${arg} requires a value.`);
-            process.exit(1);
-          }
-          params[key] = args[++i];
-          continue;
-        }
-        // #380: unknown flags were silently swallowed into params, so typos
-        // like `put --file` created empty pages instead of erroring.
-        console.error(`Unknown option for gbrain ${cliName}: ${arg}`);
-        console.error(`Run 'gbrain ${cliName} --help' for valid flags.`);
-        process.exit(1);
-      }
-      if (paramDef.type === 'boolean') {
+      if (paramDef?.type === 'boolean') {
         params[key] = true;
       } else if (i + 1 < args.length) {
         params[key] = args[++i];
-        if (paramDef.type === 'number') params[key] = Number(params[key]);
-      } else {
-        console.error(`Error: ${arg} requires a value.`);
-        process.exit(1);
+        if (paramDef?.type === 'number') params[key] = Number(params[key]);
       }
     } else if (posIdx < positional.length) {
       const key = positional[posIdx++];
@@ -843,30 +788,10 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
     }
   }
 
-  // #380: resolve --file AFTER the loop so --file/--content conflicts are
-  // caught in either order.
-  if (filePath !== undefined && fileParam) {
-    if (params[fileParam] !== undefined) {
-      console.error(`Error: use only one of --file, --${fileParam}, or stdin for gbrain ${cliName}.`);
-      process.exit(1);
-    }
-    let fileContent: string;
-    try {
-      fileContent = readFileSync(filePath, 'utf-8');
-    } catch (e) {
-      console.error(`Error: cannot read --file ${filePath}: ${e instanceof Error ? e.message : String(e)}`);
-      process.exit(1);
-    }
-    if (Buffer.byteLength(fileContent, 'utf-8') > MAX_STDIN) {
-      console.error(`Error: file content exceeds ${MAX_STDIN} bytes. Split into smaller inputs.`);
-      process.exit(1);
-    }
-    params[fileParam] = fileContent;
-  }
-
   // Read stdin for content params
   if (op.cliHints?.stdin && !params[op.cliHints.stdin] && !process.stdin.isTTY) {
     const stdinContent = readFileSync(0, 'utf-8');
+    const MAX_STDIN = 5_000_000; // 5MB
     if (Buffer.byteLength(stdinContent, 'utf-8') > MAX_STDIN) {
       console.error(`Error: stdin content exceeds ${MAX_STDIN} bytes. Split into smaller inputs.`);
       process.exit(1);
@@ -2328,10 +2253,6 @@ export function printOpHelp(op: Operation, invokedName?: string) {
       const prefix = isPos ? `  <${key}>` : `  --${key.replace(/_/g, '-')}`;
       console.log(`${prefix.padEnd(28)} ${def.description || ''}${req}`);
     }
-    // #380: ops that read stdin also accept --file <path> (parseOpArgs).
-    if (op.cliHints?.stdin && !op.params.file) {
-      console.log(`${'  --file <path>'.padEnd(28)} Read ${op.cliHints.stdin} from a file (alternative to --${op.cliHints.stdin} or stdin)`);
-    }
   }
 }
 

src/commands/doctor.ts

@@ -1551,6 +1551,24 @@ 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

@@ -3656,7 +3656,15 @@ 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'}`;
-  const auth = applyResolveAuth(recipe, cfg, 'reranker');
+  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;
+  }
   // 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/operations.ts

@@ -769,7 +769,7 @@ const get_page: Operation = {
 
 const put_page: Operation = {
   name: 'put_page',
-  description: 'Write/update a page (markdown with frontmatter). Chunks, embeds, reconciles tags, and (when auto_link/auto_timeline are enabled) extracts + reconciles graph links and timeline entries. On the CLI, `gbrain put SLUG --file PATH` reads content from a file (also `--content` or stdin). For provenance write-through and a binary-NUL guard, prefer `gbrain capture --file PATH --slug SLUG` (v0.39.3.0).',
+  description: 'Write/update a page (markdown with frontmatter). Chunks, embeds, reconciles tags, and (when auto_link/auto_timeline are enabled) extracts + reconciles graph links and timeline entries. For large content on Windows (pipe-buffer limit ~45KB) or any file-as-input workflow, use `gbrain capture --file PATH --slug SLUG` — capture reads the file as a Buffer with a binary-NUL guard and adds provenance write-through (v0.39.3.0).',
   params: {
     slug: { type: 'string', required: true, description: 'Page slug' },
     content: { type: 'string', required: true, description: 'Full markdown content with YAML frontmatter' },
@@ -1384,10 +1384,7 @@ const list_pages: Operation = {
   params: {
     type: { type: 'string', description: 'Filter by page type' },
     tag: { type: 'string', description: 'Filter by tag' },
-    limit: { type: 'number', description: 'Max results (default 50, capped at 100 — use offset to paginate beyond)' },
-    // #2876: the 100-row cap was silent and there was no way past it even
-    // though both engines already support OFFSET on listPages.
-    offset: { type: 'number', description: 'Skip first N results (pagination; pair with limit)' },
+    limit: { type: 'number', description: 'Max results (default 50)' },
     // v0.29 — surface filter that already exists on PageFilters.
     updated_after: {
       type: 'string',
@@ -1418,10 +1415,6 @@ const list_pages: Operation = {
       type: p.type as any,
       tag: p.tag as string,
       limit: clampSearchLimit(p.limit as number | undefined, 50, 100),
-      // #2876: thread pagination through (engines already honor offset).
-      offset: Number.isFinite(p.offset as number) && (p.offset as number) > 0
-        ? Math.floor(p.offset as number)
-        : undefined,
       includeDeleted: (p.include_deleted as boolean) === true,
       updated_after: typeof p.updated_after === 'string' ? p.updated_after : undefined,
       sort,

test/ai/rerank.test.ts

@@ -154,6 +154,28 @@ 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/cli-args.test.ts

@@ -1,41 +1,8 @@
 import { describe, expect, test } from 'bun:test';
-import { mkdtempSync, rmSync, writeFileSync } from 'fs';
-import { tmpdir } from 'os';
-import { join } from 'path';
 import { parseOpArgs } from '../src/cli.ts';
 import { operationsByName } from '../src/core/operations.ts';
 
 describe('parseOpArgs', () => {
-  // #380: `gbrain put SLUG --file PATH` reads content from the file instead
-  // of silently swallowing the flag and creating an empty page.
-  test('put --file reads the stdin param (content) from a file', () => {
-    const dir = mkdtempSync(join(tmpdir(), 'gbrain-put-file-'));
-    try {
-      const pagePath = join(dir, 'page.md');
-      writeFileSync(pagePath, '# From file\n\nBody loaded from --file.\n');
-      const params = parseOpArgs(operationsByName.put_page, ['concepts/from-file', '--file', pagePath]);
-      expect(params.slug).toBe('concepts/from-file');
-      expect(params.content).toBe('# From file\n\nBody loaded from --file.\n');
-    } finally {
-      rmSync(dir, { recursive: true, force: true });
-    }
-  });
-
-  // #380 regression guard: undeclared-but-honored flags must keep passing
-  // through when unknown flags become hard errors (--source is read by
-  // makeContext; --json by the output seam; --dry-run by ctx.dryRun).
-  test('pass-through allowlist flags survive on ops that do not declare them', () => {
-    const params = parseOpArgs(operationsByName.get_page, [
-      'people/alice-example', '--source', 'wiki', '--json', '--dry-run',
-    ]);
-    expect(params).toEqual({
-      slug: 'people/alice-example',
-      source: 'wiki',
-      json: true,
-      dry_run: true,
-    });
-  });
-
   test('--no-<boolean> maps to false without consuming the next flag', () => {
     const params = parseOpArgs(operationsByName.query, [
       'freshEmbedSourceScope code source',

test/cli.test.ts

@@ -1,5 +1,5 @@
 import { describe, test, expect } from 'bun:test';
-import { existsSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'fs';
+import { existsSync, mkdtempSync, readFileSync, rmSync } from 'fs';
 import { tmpdir } from 'os';
 import { join } from 'path';
 
@@ -120,76 +120,6 @@ describe('CLI dispatch integration', () => {
     expect(exitCode).toBe(0);
   });
 
-  // #380 / PR #856: put --help documents the --file input path.
-  test('put --help documents --file input', async () => {
-    const proc = Bun.spawn(['bun', 'run', 'src/cli.ts', 'put', '--help'], {
-      cwd: repoRoot,
-      stdout: 'pipe',
-      stderr: 'pipe',
-    });
-    const stdout = await new Response(proc.stdout).text();
-    const exitCode = await proc.exited;
-    expect(stdout).toContain('Usage: gbrain put');
-    expect(stdout).toContain('--file <path>');
-    expect(exitCode).toBe(0);
-  });
-
-  // #380: unknown flags on shared ops are a hard error (previously silently
-  // swallowed into params — `put --file` created empty pages). parseOpArgs
-  // runs BEFORE engine connect, so the error must fire without a brain.
-  test('unknown shared-op flags fail before DB connection', async () => {
-    const home = mkdtempSync(join(tmpdir(), 'gbrain-cli-unknown-flag-'));
-    try {
-      const proc = Bun.spawn(['bun', 'run', 'src/cli.ts', 'get', 'people/alice', '--bogus'], {
-        cwd: repoRoot,
-        stdout: 'pipe',
-        stderr: 'pipe',
-        env: isolatedEnv(home),
-      });
-      const stderr = await new Response(proc.stderr).text();
-      const exitCode = await proc.exited;
-      expect(stderr).toContain('Unknown option for gbrain get: --bogus');
-      expect(stderr).not.toContain('No brain configured');
-      expect(exitCode).toBe(1);
-    } finally {
-      rmSync(home, { recursive: true, force: true });
-    }
-  });
-
-  test('put rejects combining --file and --content', async () => {
-    const home = mkdtempSync(join(tmpdir(), 'gbrain-cli-put-conflict-'));
-    try {
-      const pagePath = join(home, 'page.md');
-      writeFileSync(pagePath, 'file body\n');
-      const proc = Bun.spawn(
-        ['bun', 'run', 'src/cli.ts', 'put', 'a/b', '--content', 'inline', '--file', pagePath],
-        { cwd: repoRoot, stdout: 'pipe', stderr: 'pipe', env: isolatedEnv(home) },
-      );
-      const stderr = await new Response(proc.stderr).text();
-      const exitCode = await proc.exited;
-      expect(stderr).toContain('use only one of --file, --content, or stdin');
-      expect(exitCode).toBe(1);
-    } finally {
-      rmSync(home, { recursive: true, force: true });
-    }
-  });
-
-  test('put --file with a missing path errors instead of writing an empty page', async () => {
-    const home = mkdtempSync(join(tmpdir(), 'gbrain-cli-put-missing-file-'));
-    try {
-      const proc = Bun.spawn(
-        ['bun', 'run', 'src/cli.ts', 'put', 'a/b', '--file', join(home, 'nope.md')],
-        { cwd: repoRoot, stdout: 'pipe', stderr: 'pipe', env: isolatedEnv(home) },
-      );
-      const stderr = await new Response(proc.stderr).text();
-      const exitCode = await proc.exited;
-      expect(stderr).toContain('cannot read --file');
-      expect(exitCode).toBe(1);
-    } finally {
-      rmSync(home, { recursive: true, force: true });
-    }
-  });
-
   test('upgrade --help prints usage without running upgrade', async () => {
     const proc = Bun.spawn(['bun', 'run', 'src/cli.ts', 'upgrade', '--help'], {
       cwd: repoRoot,

test/doctor.test.ts

@@ -2,6 +2,11 @@ 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 () => {
@@ -47,6 +52,34 @@ 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/list-pages-offset.test.ts

@@ -1,55 +0,0 @@
-import { describe, test, expect } from 'bun:test';
-import { operationsByName } from '../src/core/operations.ts';
-
-/**
- * #2876: `gbrain list --limit` silently clamped at 100 with no pagination.
- * list_pages now declares `offset` (both engines already supported it on
- * PageFilters) and the limit description discloses the 100-row cap.
- */
-describe('list_pages pagination (#2876)', () => {
-  const listPagesOp = operationsByName.list_pages;
-
-  function makeCtx(captured: unknown[]) {
-    return {
-      engine: {
-        listPages: async (filters: unknown) => {
-          captured.push(filters);
-          return [];
-        },
-      },
-      config: { engine: 'pglite' },
-      logger: { info() {}, warn() {}, error() {} },
-      dryRun: false,
-      remote: false,
-      sourceId: 'default',
-    } as any;
-  }
-
-  test('declares offset param and discloses the 100-row cap on limit', () => {
-    expect(listPagesOp.params.offset).toBeDefined();
-    expect(listPagesOp.params.offset.type).toBe('number');
-    expect(listPagesOp.params.limit.description).toContain('100');
-  });
-
-  test('threads offset through to engine.listPages', async () => {
-    const captured: any[] = [];
-    await listPagesOp.handler(makeCtx(captured), { limit: 10, offset: 30 });
-    expect(captured[0].offset).toBe(30);
-    expect(captured[0].limit).toBe(10);
-  });
-
-  test('drops negative, non-finite, and zero offsets', async () => {
-    const captured: any[] = [];
-    const ctx = makeCtx(captured);
-    await listPagesOp.handler(ctx, { offset: -5 });
-    await listPagesOp.handler(ctx, { offset: Infinity });
-    await listPagesOp.handler(ctx, { offset: 0 });
-    for (const f of captured) expect(f.offset).toBeUndefined();
-  });
-
-  test('floors fractional offsets', async () => {
-    const captured: any[] = [];
-    await listPagesOp.handler(makeCtx(captured), { offset: 7.9 });
-    expect(captured[0].offset).toBe(7);
-  });
-});

test/search/rerank.test.ts

@@ -12,9 +12,14 @@
  */
 
 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 {
@@ -160,6 +165,36 @@ 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 = {