docs(tutorial): drop dead --remote flag from company-brain search examples

With unknown op flags now a hard error (this PR), the tutorial's
`gbrain search ... --remote` invocations would fail: no code path ever
read a --remote flag — thin-client installs route shared ops through the
remote MCP server automatically. Update the three examples to the
flagless form and explain the automatic routing.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

docs/tutorials/company-brain.md

@@ -223,14 +223,16 @@ 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" --remote
+gbrain search "performance review"
 ```
 
+(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" --remote
+gbrain search "performance review"
 ```
 
 Bob should see the performance-review notes from `internal`, plus anything related from `shared`. He shouldn't see anything that lives only in `customers`.
@@ -514,7 +516,7 @@ 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> --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.
+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.
 
 ### "The synthesized answer is wrong"
 

src/cli.ts

@@ -464,7 +464,11 @@ 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);
+    // #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);
     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 +551,10 @@ async function runThinClientRouted(
       signal: sigintController.signal,
     });
     const result = unpackToolResult(raw);
-    const output = formatResult(op.name, result);
+    // #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);
     if (output) process.stdout.write(output);
   } catch (e: unknown) {
     if (e instanceof RemoteMcpError) {
@@ -757,10 +764,28 @@ 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];
@@ -774,12 +799,42 @@ 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?.type === 'boolean') {
+      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') {
         params[key] = true;
       } else if (i + 1 < args.length) {
         params[key] = args[++i];
-        if (paramDef?.type === 'number') params[key] = Number(params[key]);
+        if (paramDef.type === 'number') params[key] = Number(params[key]);
+      } else {
+        console.error(`Error: ${arg} requires a value.`);
+        process.exit(1);
       }
     } else if (posIdx < positional.length) {
       const key = positional[posIdx++];
@@ -788,10 +843,30 @@ 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);
@@ -808,20 +883,12 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
   // 'default'. Wrapped in try/catch so a doctor / single-source brain that
   // never set up sources still returns 'default' silently.
   let sourceId: string | undefined;
-  // #2561: when the source resolved via a NON-explicit tier (path-match /
-  // brain default / sole-non-default / seed default), unqualified search-shaped
-  // reads span every `config.federated = true` source. Computed here (the
-  // trusted local boundary) and consumed by federatedSearchScope in
-  // operations.ts, which additionally gates on ctx.remote === false.
-  let localFederated: string[] | undefined;
   try {
-    const { resolveSourceWithTier, localFederatedSourceIds } = await import('./core/source-resolver.ts');
+    const { resolveSourceId } = await import('./core/source-resolver.ts');
     // params.source is set when a CLI flag was parsed for the op (rare; most
     // CLI ops don't take --source). Falls through to env/dotfile/path-match.
     const explicit = (params.source as string | undefined) ?? null;
-    const resolved = await resolveSourceWithTier(engine, explicit);
-    sourceId = resolved.source_id;
-    localFederated = await localFederatedSourceIds(engine, resolved.source_id, resolved.tier);
+    sourceId = await resolveSourceId(engine, explicit);
   } catch {
     // Source resolution failed (e.g. sources table doesn't exist on a fresh
     // pre-init brain). Leave sourceId unset; engine read methods fall through
@@ -842,7 +909,6 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
     // table). Matches dispatch.ts's auto-fill so the contract holds across
     // every transport.
     sourceId: sourceId ?? 'default',
-    ...(localFederated ? { localFederatedSourceIds: localFederated } : {}),
   };
 }
 
@@ -2262,6 +2328,10 @@ 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/core/operations.ts

@@ -424,23 +424,6 @@ export interface OperationContext {
    * satisfied even on single-source brains.
    */
   sourceId: string;
-  /**
-   * #2561 — federated read scope for UNQUALIFIED local CLI reads.
-   *
-   * Set ONLY by the local CLI's context builder (src/cli.ts makeContext), and
-   * only when the source resolved via a non-explicit tier (local_path /
-   * brain_default / sole_non_default / seed_default — NOT --source, NOT
-   * GBRAIN_SOURCE, NOT a .gbrain-source dotfile). Contains the resolved
-   * source first, then every other `config.federated = true` source, so an
-   * unqualified `gbrain search "X"` spans federated sources as
-   * docs/guides/multi-source-brains.md promises.
-   *
-   * Consumed exclusively by `federatedSearchScope` and ONLY when
-   * `ctx.remote === false` — a remote caller's scope stays governed by
-   * `ctx.auth.allowedSources` / scalar `ctx.sourceId` (source-isolation
-   * invariant, fail-closed).
-   */
-  localFederatedSourceIds?: string[];
 }
 
 /**
@@ -556,45 +539,6 @@ export function resolveRequestedScope(
   return sourceScopeOpts(ctx);
 }
 
-/**
- * #2561 — source scope for the search-shaped read ops (`search`, `query`).
- *
- * Delegates to `resolveRequestedScope` (the single trust+grant resolver), then
- * widens an UNQUALIFIED trusted-local scalar scope to the CLI-computed
- * federated set (`ctx.localFederatedSourceIds`, resolved source first). This is
- * what makes `sources add --federated` mean something for local search: a
- * federated source participates in unqualified `gbrain search "X"` results.
- *
- * The expansion NEVER applies when:
- *   - the caller is not strictly trusted-local (`ctx.remote !== false`) —
- *     remote scope stays grant-governed (fail-closed source isolation);
- *   - a per-call `source_id` was passed (explicit wins, including `__all__`);
- *   - the resolver already produced a federated array (OAuth grant);
- *   - the CLI resolved the source from an explicit signal (--source / env /
- *     dotfile) — makeContext leaves `localFederatedSourceIds` unset then.
- *
- * Deliberately NOT inside `sourceScopeOpts`: code-intel ops collapse a
- * multi-element scope to an error (`resolveCodeIntelScope`), and non-search
- * reads (get_page, get_links, …) keep their long-standing scalar behavior.
- */
-export function federatedSearchScope(
-  ctx: OperationContext,
-  sourceIdParam?: string,
-): { sourceId?: string; sourceIds?: string[] } {
-  const scope = resolveRequestedScope(ctx, sourceIdParam);
-  if (
-    ctx.remote === false &&
-    sourceIdParam === undefined &&
-    scope.sourceId !== undefined &&
-    scope.sourceIds === undefined &&
-    ctx.localFederatedSourceIds !== undefined &&
-    ctx.localFederatedSourceIds.length > 1
-  ) {
-    return { sourceIds: ctx.localFederatedSourceIds };
-  }
-  return scope;
-}
-
 /**
  * Code-intel adapter for `resolveRequestedScope`. Graph traversal
  * (code_callers/code_callees/code_blast/code_flow) is single-source by design —
@@ -825,7 +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. 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).',
+  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).',
   params: {
     slug: { type: 'string', required: true, description: 'Page slug' },
     content: { type: 'string', required: true, description: 'Full markdown content with YAML frontmatter' },
@@ -1440,7 +1384,10 @@ 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)' },
+    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)' },
     // v0.29 — surface filter that already exists on PageFilters.
     updated_after: {
       type: 'string',
@@ -1471,6 +1418,10 @@ 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,
@@ -1504,8 +1455,7 @@ const search: Operation = {
     const queryText = p.query as string;
     const limit = (p.limit as number) || 20;
     const offset = (p.offset as number) || 0;
-    // #2561: unqualified trusted-local search spans federated sources.
-    const scope = federatedSearchScope(ctx);
+    const scope = sourceScopeOpts(ctx);
 
     // T4/D5 — per-call mode honored ONLY for trusted/local callers so a remote
     // OAuth client can't escalate to the costly tokenmax bundle. Local + unknown
@@ -1667,9 +1617,7 @@ const query: Operation = {
     // is spread into BOTH the image-similarity searchVector path and the text
     // hybridSearch path below, so both honor the same grant.
     const sourceIdParam = typeof p.source_id === 'string' ? p.source_id : undefined;
-    // #2561: unqualified trusted-local query spans federated sources (per-call
-    // source_id / remote grants still resolve through resolveRequestedScope).
-    const querySourceScope = federatedSearchScope(ctx, sourceIdParam);
+    const querySourceScope = resolveRequestedScope(ctx, sourceIdParam);
 
     // v0.27.1: image-similarity branch. Bypasses hybridSearch (which is
     // text-only); embeds the image via embedMultimodal and runs a direct

src/core/source-resolver.ts

@@ -353,45 +353,6 @@ export async function resolveSourceWithTier(
   return { source_id: 'default', tier: 'seed_default' };
 }
 
-/**
- * #2561 — compute the federated read scope for an UNQUALIFIED local CLI call.
- *
- * `sources add --federated` promises that a `config.federated = true` source
- * "participates in unqualified `gbrain search` results"
- * (docs/guides/multi-source-brains.md). This helper turns that promise into a
- * scope: given the resolved source and WHICH tier resolved it, return
- * `[resolvedSource, ...other federated source ids]` — or `undefined` when the
- * expansion must not apply:
- *
- *   - explicit tiers (`flag` / `env` / `dotfile`): the user named a source;
- *     scalar scope stands (that IS the qualified case);
- *   - no other federated source exists: keep the scalar fast path unchanged.
- *
- * Archived sources are excluded (same rationale as pickSoleNonDefaultSource);
- * the archived column is v34+, so fall back to the un-archived query on older
- * brains. Callers put the result on `OperationContext.localFederatedSourceIds`
- * — consumed only by `federatedSearchScope` and only when `remote === false`.
- */
-export async function localFederatedSourceIds(
-  engine: BrainEngine,
-  sourceId: string,
-  tier: SourceTier,
-): Promise<string[] | undefined> {
-  if (tier === 'flag' || tier === 'env' || tier === 'dotfile') return undefined;
-  let rows: Array<{ id: string }>;
-  try {
-    rows = await engine.executeRaw<{ id: string }>(
-      `SELECT id FROM sources WHERE config->>'federated' = 'true' AND archived = false ORDER BY id`,
-    );
-  } catch {
-    rows = await engine.executeRaw<{ id: string }>(
-      `SELECT id FROM sources WHERE config->>'federated' = 'true' ORDER BY id`,
-    );
-  }
-  const ids = [sourceId, ...rows.map((r) => r.id).filter((id) => id !== sourceId)];
-  return ids.length > 1 ? ids : undefined;
-}
-
 /** Exposed for tests. */
 export const __testing = {
   readDotfileWalk,

test/cli-args.test.ts

@@ -1,8 +1,41 @@
 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 } from 'fs';
+import { existsSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'fs';
 import { tmpdir } from 'os';
 import { join } from 'path';
 
@@ -120,6 +120,76 @@ 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/list-pages-offset.test.ts

@@ -0,0 +1,55 @@
+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/local-federated-search-scope.test.ts

@@ -1,154 +0,0 @@
-/**
- * #2561 — sources.config.federated participates in UNQUALIFIED local CLI
- * search/query.
- *
- * Pre-fix: the local CLI always emitted a scalar `{sourceId}` scope (required
- * field, auto-filled 'default'), so a source registered with
- * `gbrain sources add --federated` was invisible to an unqualified
- * `gbrain search "X"` — contradicting docs/guides/multi-source-brains.md
- * ("Source participates in unqualified `gbrain search` results").
- *
- * Fix: the CLI context builder computes `ctx.localFederatedSourceIds`
- * (resolved source + every other federated source) whenever the source
- * resolved via a NON-explicit tier; `federatedSearchScope` widens the scalar
- * scope to that set for the `search` / `query` ops — trusted-local only
- * (`ctx.remote === false`), never for remote callers, never when a per-call
- * `source_id` or an explicit --source/env/dotfile was given.
- */
-import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
-import { PGLiteEngine } from '../src/core/pglite-engine.ts';
-import { localFederatedSourceIds } from '../src/core/source-resolver.ts';
-import {
-  federatedSearchScope,
-  operations,
-  type OperationContext,
-} from '../src/core/operations.ts';
-
-let engine: PGLiteEngine;
-const search = operations.find((o) => o.name === 'search')!;
-
-function ctxOf(overrides: Partial<OperationContext> = {}): OperationContext {
-  return {
-    engine: engine as any,
-    config: {} as any,
-    logger: console as any,
-    dryRun: false,
-    remote: false,
-    sourceId: 'default',
-    ...overrides,
-  };
-}
-
-beforeAll(async () => {
-  engine = new PGLiteEngine();
-  await engine.connect({});
-  await engine.initSchema();
-  // Seeded 'default' source is federated=true. Add:
-  //   wiki    — federated (must join unqualified search)
-  //   private — NOT federated (must stay invisible unless explicitly named)
-  //   oldnews — federated but archived (must stay excluded)
-  await engine.executeRaw(
-    `INSERT INTO sources (id, name, local_path, config) VALUES ('wiki', 'wiki', '/tmp/wiki', '{"federated": true}'::jsonb)`,
-  );
-  await engine.executeRaw(
-    `INSERT INTO sources (id, name, local_path, config) VALUES ('private', 'private', '/tmp/private', '{}'::jsonb)`,
-  );
-  await engine.executeRaw(
-    `INSERT INTO sources (id, name, local_path, config, archived) VALUES ('oldnews', 'oldnews', '/tmp/oldnews', '{"federated": true}'::jsonb, true)`,
-  );
-  const pages: Array<[slug: string, sourceId: string, where: string]> = [
-    ['notes/home', 'default', 'default'],
-    ['wiki/topic', 'wiki', 'wiki'],
-    ['private/topic', 'private', 'private'],
-    ['old/topic', 'oldnews', 'oldnews'],
-  ];
-  for (const [slug, sourceId, where] of pages) {
-    await engine.putPage(slug, {
-      type: 'note', title: `Topic in ${where}`, compiled_truth: `the zebra telescope in ${where}`, frontmatter: {},
-    }, { sourceId });
-    await engine.upsertChunks(slug, [
-      { chunk_index: 0, chunk_text: `the zebra telescope in ${where}`, chunk_source: 'compiled_truth' },
-    ], { sourceId });
-  }
-  // Keyword-only search path: no embedding provider needed in tests.
-  await engine.setConfig('search.mcp_keyword_only', 'true');
-}, 60_000);
-
-afterAll(async () => {
-  if (engine) await engine.disconnect();
-}, 60_000);
-
-describe('localFederatedSourceIds — CLI-side scope computation', () => {
-  test('non-explicit tier: resolved source first, then other federated, archived excluded', async () => {
-    expect(await localFederatedSourceIds(engine, 'default', 'seed_default')).toEqual(['default', 'wiki']);
-  });
-
-  test('non-federated resolved source still joins its own scope', async () => {
-    expect(await localFederatedSourceIds(engine, 'private', 'brain_default')).toEqual(['private', 'default', 'wiki']);
-  });
-
-  test('explicit tiers (--source / env / dotfile) never expand', async () => {
-    expect(await localFederatedSourceIds(engine, 'default', 'flag')).toBeUndefined();
-    expect(await localFederatedSourceIds(engine, 'default', 'env')).toBeUndefined();
-    expect(await localFederatedSourceIds(engine, 'default', 'dotfile')).toBeUndefined();
-  });
-
-  test('single federated source (the resolved one) keeps the scalar fast path', async () => {
-    const solo = { executeRaw: async () => [{ id: 'default' }] } as any;
-    expect(await localFederatedSourceIds(solo, 'default', 'seed_default')).toBeUndefined();
-  });
-});
-
-describe('federatedSearchScope — trust + explicitness matrix', () => {
-  test('trusted local + unqualified widens to the federated set', () => {
-    const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
-    expect(federatedSearchScope(ctx)).toEqual({ sourceIds: ['default', 'wiki'] });
-  });
-
-  test('remote caller NEVER widens (fail-closed), even if the field is set', () => {
-    const ctx = ctxOf({ remote: true, localFederatedSourceIds: ['default', 'wiki'] });
-    expect(federatedSearchScope(ctx)).toEqual({ sourceId: 'default' });
-  });
-
-  test('per-call source_id wins over the federated set', () => {
-    const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
-    expect(federatedSearchScope(ctx, 'wiki')).toEqual({ sourceId: 'wiki' });
-  });
-
-  test('per-call __all__ keeps the whole-brain semantics for trusted local', () => {
-    const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
-    expect(federatedSearchScope(ctx, '__all__')).toEqual({});
-  });
-
-  test('a federated OAuth grant wins over the local set', () => {
-    const ctx = ctxOf({
-      localFederatedSourceIds: ['default', 'wiki'],
-      auth: { allowedSources: ['a', 'b'] } as OperationContext['auth'],
-    });
-    expect(federatedSearchScope(ctx)).toEqual({ sourceIds: ['a', 'b'] });
-  });
-
-  test('no local federated set → unchanged scalar scope', () => {
-    expect(federatedSearchScope(ctxOf())).toEqual({ sourceId: 'default' });
-  });
-});
-
-describe('search op — unqualified local search spans federated sources', () => {
-  test('federated source results appear; non-federated + archived stay invisible', async () => {
-    const ctx = ctxOf({
-      localFederatedSourceIds: await localFederatedSourceIds(engine, 'default', 'seed_default'),
-    });
-    const results = (await search.handler(ctx, { query: 'zebra telescope' })) as Array<{ slug: string }>;
-    const slugs = results.map((r) => r.slug);
-    expect(slugs).toContain('notes/home');
-    expect(slugs).toContain('wiki/topic'); // pre-#2561 this was missing
-    expect(slugs).not.toContain('private/topic');
-    expect(slugs).not.toContain('old/topic');
-  });
-
-  test('explicit source resolution (no federated set on ctx) stays single-source', async () => {
-    const results = (await search.handler(ctxOf(), { query: 'zebra telescope' })) as Array<{ slug: string }>;
-    const slugs = results.map((r) => r.slug);
-    expect(slugs).toEqual(['notes/home']);
-  });
-});