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 ${MAX_STDIN} bytes. Split into smaller inputs.`);
       process.exit(1);
@@ -2253,6 +2328,10 @@ export function printOpHelp(op: Operation, invokedName?: string) {
       const prefix = isPos ? `  <${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/commands/extract.ts

@@ -1743,15 +1743,7 @@ async function extractStaleFromDB(
       // `page.updated_at.toISOString()` — the JS Date is ms-truncated, so the
       // µs-precision DB updated_at stayed strictly greater and the page never
       // cleared on Postgres. Stamping the exact value makes them equal.
-      //
-      // Version-arm floor: a page last edited BEFORE LINK_EXTRACTOR_VERSION_TS
-      // would otherwise be stamped below the version watermark and stay
-      // permanently stale (`links_extracted_at < versionTs` re-fires every run).
-      // Stamp max(updated_at, versionTs) — versionTs is always a past release
-      // date, so a concurrent edit's now() still exceeds the stamp and D4 holds.
-      // Tie at ms precision picks updated_at_iso (its µs ≥ versionTs's .000000).
-      const stampTs = new Date(page.updated_at_iso) >= new Date(versionTs) ? page.updated_at_iso : versionTs;
-      processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: stampTs });
+      processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: page.updated_at_iso });
     }
 
     // Flush NON-swallowing (CDX-4): a throw here propagates out of the sweep so

src/core/link-extraction.ts

@@ -28,7 +28,7 @@ import { ensureWellFormed } from './text-safe.ts';
  * OR updated_at > links_extracted_at`. It is an ISO-8601 string (NOT a number) —
  * the column is TIMESTAMPTZ and the predicate binds it as `::timestamptz`.
  */
-export const LINK_EXTRACTOR_VERSION_TS = '2026-07-21T00:00:00Z';
+export const LINK_EXTRACTOR_VERSION_TS = '2026-05-31T00:00:00Z';
 
 // ─── Entity references ──────────────────────────────────────────
 
@@ -80,10 +80,10 @@ export type LinkResolutionType = 'qualified' | 'unqualified';
  * Directory prefix whitelist. These are the top-level slug dirs the extractor
  * recognizes as entity references. Upstream canonical + our extensions:
  *   - Gbrain canonical: people, companies, meetings, concepts, deal, civic, project, source, media, yc, projects
- *   - Our domain extensions: tech, finance, personal, openclaw, ops (domain-organized wikis)
+ *   - Our domain extensions: tech, finance, personal, openclaw (domain-organized wikis)
  *   - Our entity prefix: entities (we kept some legacy entities/projects/ pages)
  */
-const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities|ops)';
+const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities)';
 
 /**
  * Match `[Name](path)` markdown links pointing to entity directories.
@@ -865,16 +865,7 @@ export function queryBasenameIndex(idx: Map<string, string[]>, name: string): st
   if (!name || typeof name !== 'string') return [];
   const trimmed = name.trim();
   if (!trimmed) return [];
-  let hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
-  // Issue #2576 bug 2: path-style refs (`runbooks/2026-05-01-x`) from dirs
-  // outside DIR_PATTERN reach here, but normalizeBasename strips slashes
-  // into a garbage key (`runbooks2026-05-01-x`) that can never hit the
-  // tail-keyed index. Fall back to the path tail so qualified refs resolve
-  // by basename like everything else.
-  if (!hit && trimmed.includes('/')) {
-    const tail = trimmed.slice(trimmed.lastIndexOf('/') + 1).trim();
-    if (tail) hit = idx.get(tail) ?? idx.get(tail.toLowerCase()) ?? idx.get(normalizeBasename(tail));
-  }
+  const hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
   return hit ? [...hit].sort(basenameSort) : [];
 }
 

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. 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' },
@@ -1384,7 +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',
@@ -1415,6 +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,

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/extract-stale.test.ts

@@ -209,24 +209,6 @@ describe('gbrain extract --stale', () => {
     expect(usRows[0]?.eq).toBe(true);
   });
 
-  test('version-arm floor: page edited BEFORE LINK_EXTRACTOR_VERSION_TS clears after --stale (issue #2576 bug 3)', async () => {
-    // A page whose updated_at predates the version watermark used to be
-    // stamped at its updated_at (< versionTs), so the version arm re-fired
-    // every run — permanently stale. The sweep now floors the stamp at
-    // versionTs. (The #1768 test above also covers this since the v0.42.x
-    // VERSION_TS bump moved its date below the watermark, but this pins the
-    // behavior explicitly so a date "repair" there can't drop coverage.)
-    await engine.putPage('people/alice', personPage('Alice'));
-    await engine.executeRaw(`UPDATE pages SET updated_at = '2000-01-01T00:00:00Z' WHERE slug = 'people/alice'`);
-    expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(1);
-
-    await runExtract(engine, ['--stale']);
-    // Pre-floor this stayed 1 forever (stamp < versionTs → version arm re-fires).
-    expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
-    await runExtract(engine, ['--stale']);
-    expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
-  });
-
   test('CDX-4 (D2): a link-flush throw aborts the sweep and leaves pages UNSTAMPED', async () => {
     await engine.putPage('people/alice', personPage('Alice'));
     await engine.putPage('companies/acme', companyPage('Acme', '[Alice](people/alice) founded [Acme](companies/acme).'));

test/link-extraction.test.ts

@@ -140,15 +140,6 @@ describe('extractEntityRefs', () => {
     expect(wikiRefs[0].needsResolution).toBe(true);
   });
 
-  test('recognizes ops/ qualified wikilinks (issue #2576 bug 2)', () => {
-    // `ops` was missing from DIR_PATTERN, so [[ops/...]] fell through to
-    // the generic 2c pass (needsResolution) instead of being a real ref.
-    const refs = extractEntityRefs('Deployed via [[ops/services/pointer-agent]].');
-    expect(refs.length).toBe(1);
-    expect(refs[0].slug).toBe('ops/services/pointer-agent');
-    expect(refs[0].needsResolution).toBeUndefined();
-  });
-
   test('skips qualified-syntax tokens (those belong to 2a)', () => {
     // [[wiki:topics/ai]] looks like 2a's qualified shape — even though
     // it wouldn't satisfy DIR_PATTERN, 2c must not claim it either
@@ -1078,15 +1069,6 @@ describe('makeResolver — fallback chain', () => {
     ]);
   });
 
-  test('resolveBasenameMatches: path-style ref falls back to the tail (issue #2576 bug 2)', async () => {
-    // normalizeBasename strips slashes, so `runbooks/2026-05-01-pointer-agent`
-    // used to normalize to a garbage key that never hit the tail-keyed index.
-    const engine = makeFakeEngineWithSlugs(['ops/changes/2026-05-01-pointer-agent']);
-    const r = makeResolver(engine);
-    expect(await r.resolveBasenameMatches!('runbooks/2026-05-01-pointer-agent'))
-      .toEqual(['ops/changes/2026-05-01-pointer-agent']);
-  });
-
   test('resolveBasenameMatches: case-insensitive fallback', async () => {
     const engine = makeFakeEngineWithSlugs(['companies/fast-weigh']);
     const r = makeResolver(engine);

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);
+  });
+});