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/autopilot.ts

@@ -686,7 +686,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
       try {
         const { MinionQueue } = await import('../core/minions/queue.ts');
         const { computeRecommendations, embeddingProviderConfigured, HOSTED_EMBED_KEY_CONFIG } = await import('../core/brain-score-recommendations.ts');
-        const { countExtractionLag } = await import('../core/remediation/context.ts');
         const queue = new MinionQueue(engine);
         const slotMs = Math.floor(Date.now() / (baseInterval * 1000)) * baseInterval * 1000;
         const slot = new Date(slotMs).toISOString();
@@ -878,9 +877,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
             return !!(process.env[envVar] || (cfgField ? embedKeyCfg[cfgField] : undefined));
           }),
           hasChatApiKey: !!(process.env.ANTHROPIC_API_KEY || await engine.getConfig('anthropic_api_key')),
-          // Real extraction-lag gate for sync.repo/extract.all — same counter
-          // loadRecommendationContext uses (replaces the health.stale_pages proxy).
-          extractionLagPages: await countExtractionLag(engine),
         };
         // v0.41.18.0 (A5 + A19 + A22, T15): consult onboard recommendations
         // ALONGSIDE doctor's brain-score recommendations. Onboard's 4 new

src/core/brain-score-recommendations.ts

@@ -146,16 +146,6 @@ export interface RecommendationContext {
   chatModel?: string;
   /** Whether the chat provider has a usable API key. */
   hasChatApiKey?: boolean;
-  /**
-   * Count of pages needing link/timeline extraction — the SAME staleness the
-   * `gbrain extract --stale` walk and doctor's `links_extraction_lag` check use
-   * (`engine.countStalePagesForExtraction`). Gates the sync→extract pipeline
-   * (sync.repo / extract.all). Replaces the old `health.stale_pages` gate, which
-   * counted "pages whose updated_at predates their newest timeline entry" — a
-   * proxy that broke when the updated_at-on-timeline-insert trigger was dropped
-   * (migration v10) and never reflected real extraction work.
-   */
-  extractionLagPages?: number;
 }
 
 /** Triage result for one check. */
@@ -202,28 +192,20 @@ export function computeRecommendations(
   const source = ctx.sourceId ?? 'default';
 
   // ---------------------------------------------------------------------
-  // sync.repo + extract.all — the materialization pipeline, gated on the REAL
-  // extraction lag (pages whose link/timeline edges are stale), NOT on the
-  // legacy `health.stale_pages` proxy. `extractionLagPages` comes from the same
-  // counter the `extract --stale` walk + doctor's `links_extraction_lag` use, so
-  // the recommendation can only fire when running extract will actually reduce
-  // it (and clear the rec). See RecommendationContext.extractionLagPages.
-  // sync.repo is the prerequisite: re-sync so pages are current before extract
-  // materializes their edges.
+  // sync.repo — fires when sync hasn't run recently OR pages are stale
   // ---------------------------------------------------------------------
-  const extractionLag = ctx.extractionLagPages ?? 0;
-  if (ctx.repoPath && extractionLag > 0) {
+  if (ctx.repoPath && health.stale_pages > 0) {
     const params = { repoPath: ctx.repoPath, sourceId: ctx.sourceId, noEmbed: true };
     out.push({
       id: 'sync.repo',
       job: 'sync',
       params,
       idempotency_key: idemKey(source, 'sync', params),
-      severity: extractionLag > 50 ? 'high' : 'medium',
-      est_seconds: Math.min(600, 30 + extractionLag * 0.5),
+      severity: health.stale_pages > 50 ? 'high' : 'medium',
+      est_seconds: Math.min(600, 30 + health.stale_pages * 0.5),
       est_usd_cost: 0,  // sync is fs+DB only
       depends_on: [],
-      rationale: `Sync before extracting ${extractionLag} page${extractionLag === 1 ? '' : 's'} with stale link/timeline edges`,
+      rationale: `${health.stale_pages} stale page${health.stale_pages === 1 ? '' : 's'} on disk`,
       status: 'remediable',
     });
   }
@@ -255,7 +237,7 @@ export function computeRecommendations(
       est_seconds: Math.min(3600, 5 + health.missing_embeddings * 0.05),
       est_usd_cost,
       // sync should run first so embed sees fresh pages.
-      depends_on: ctx.repoPath && extractionLag > 0 ? ['sync.repo'] : [],
+      depends_on: ctx.repoPath && health.stale_pages > 0 ? ['sync.repo'] : [],
       rationale: `${health.missing_embeddings} chunk${health.missing_embeddings === 1 ? '' : 's'} invisible to vector search`,
       status: 'remediable',
     });
@@ -285,7 +267,7 @@ export function computeRecommendations(
   // Triggered when sync.repo fires (because sync was set to noEmbed:true,
   // and noExtract:true after T5 lands → extract job is the materializer).
   // ---------------------------------------------------------------------
-  if (ctx.repoPath && extractionLag > 0) {
+  if (ctx.repoPath && health.stale_pages > 0) {
     const params = { mode: 'all', dir: ctx.repoPath };
     out.push({
       id: 'extract.all',
@@ -296,7 +278,7 @@ export function computeRecommendations(
       est_seconds: Math.min(600, 30 + health.page_count * 0.01),
       est_usd_cost: 0,
       depends_on: ['sync.repo'],
-      rationale: `Materialize link + timeline edges for ${extractionLag} page${extractionLag === 1 ? '' : 's'} with stale extraction`,
+      rationale: 'Materialize link + timeline edges from fresh pages',
       status: 'remediable',
     });
   }

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,

src/core/remediation/context.ts

@@ -8,7 +8,6 @@
 
 import type { BrainEngine } from '../engine.ts';
 import type { RecommendationContext } from '../brain-score-recommendations.ts';
-import { LINK_EXTRACTOR_VERSION_TS } from '../link-extraction.ts';
 
 // Re-export so consumers can `import { RecommendationContext } from '../remediation'`
 // — the canonical RecommendationContext type still lives in
@@ -69,29 +68,5 @@ export async function loadRecommendationContext(
     embeddingDimensions,
     embeddingProviderConfigured: embeddingConfigured,
     hasChatApiKey: !!(process.env.ANTHROPIC_API_KEY || fileCfg?.anthropic_api_key),
-    extractionLagPages: await countExtractionLag(engine),
   };
 }
-
-/**
- * Real extraction-lag count — the SAME staleness `gbrain extract --stale`
- * processes (engine.countStalePagesForExtraction with
- * versionTs=LINK_EXTRACTOR_VERSION_TS, matching doctor's links_extraction_lag
- * check — without versionTs, pages stamped before an extractor version bump
- * would lag for doctor/extract but never trip this gate). Drives the
- * sync→extract recommendation pipeline; replaces the legacy
- * `health.stale_pages` proxy that no longer reflected real extraction work
- * after the v10 trigger drop.
- *
- * Shared by loadRecommendationContext AND the D7 per-step recheck in
- * runRemediation — the recheck MUST refresh this gate alongside getHealth,
- * or a completed extract step keeps re-firing off the frozen initial count.
- */
-export async function countExtractionLag(engine: BrainEngine): Promise<number> {
-  try {
-    return await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS });
-  } catch {
-    /* counter unavailable (very old brain / mid-migration) — treat as 0 */
-    return 0;
-  }
-}

src/core/remediation/run.ts

@@ -16,7 +16,7 @@ import {
   computeRecommendations,
 } from '../brain-score-recommendations.ts';
 import type { RemediationStep } from '../remediation-step.ts';
-import { countExtractionLag, loadRecommendationContext } from './context.ts';
+import { loadRecommendationContext } from './context.ts';
 import { computeRemediationPlan } from './plan.ts';
 import type {
   RemediationHooks,
@@ -65,7 +65,7 @@ export async function runRemediation(
     clearRemediationCheckpoint,
   } = await import('../remediation-checkpoint.ts');
 
-  let ctx = await loadRecommendationContext(engine);
+  const ctx = await loadRecommendationContext(engine);
 
   // Pre-flight ceiling check via the shared plan computation.
   const initialPlan = await computeRemediationPlan(engine, { targetScore });
@@ -305,11 +305,6 @@ export async function runRemediation(
       // steps with bumped retry suffix (D1).
       if (recs.length === 0 || stepCount >= maxJobs) break;
       const freshHealth = await engine.getHealth();
-      // Refresh the extraction-lag gate alongside health: ctx was loaded once
-      // before the loop, and a completed sync/extract step is exactly what
-      // drives the count down. Reusing the frozen initial count would re-fire
-      // sync.repo/extract.all every recheck until maxJobs.
-      ctx = { ...ctx, extractionLagPages: await countExtractionLag(engine) };
       recs = computeRecommendations(freshHealth, ctx).filter((r) => r.status === 'remediable');
     }
   };

src/core/types.ts

@@ -1423,15 +1423,6 @@ export interface BrainStats {
 export interface BrainHealth {
   page_count: number;
   embed_coverage: number;
-  /**
-   * LEGACY proxy: count of pages whose `updated_at` predates their newest
-   * timeline entry. This bumped meaningfully only while a trigger updated
-   * `pages.updated_at` on timeline insert; that trigger was dropped in
-   * migration v10, so the metric no longer reflects real "needs work" state.
-   * NO LONGER gates remediations — the sync→extract pipeline now gates on
-   * `RecommendationContext.extractionLagPages` (the real extraction-lag from
-   * `countStalePagesForExtraction`). Retained for the CLI health line + back-compat.
-   */
   stale_pages: number;
   /**
    * Islanded pages — zero inbound AND zero outbound links. A hub page

test/brain-score-recommendations.test.ts

@@ -119,12 +119,13 @@ describe('computeRecommendations', () => {
     expect(recs.find((r) => r.id === 'embed.stale')).toBeUndefined();
   });
 
-  test('extraction lag + dead links produce sync + backlinks + extract', () => {
+  test('stale pages + dead links produce sync + backlinks + extract', () => {
     const health = makeHealth({
+      stale_pages: 25,
       dead_links: 8,
       brain_score: 70,
     });
-    const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 25 });
+    const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
     const ids = recs.map((r) => r.id);
     expect(ids).toContain('sync.repo');
     expect(ids).toContain('backlinks.fix');
@@ -132,17 +133,18 @@ describe('computeRecommendations', () => {
   });
 
   test('extract.all depends on sync.repo (D14: stable ids)', () => {
-    const health = makeHealth();
-    const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 10 });
+    const health = makeHealth({ stale_pages: 10 });
+    const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
     const extract = recs.find((r) => r.id === 'extract.all');
     expect(extract?.depends_on).toContain('sync.repo');
   });
 
-  test('embed.stale depends on sync.repo when extraction also needed', () => {
+  test('embed.stale depends on sync.repo when sync also needed', () => {
     const health = makeHealth({
+      stale_pages: 10,
       missing_embeddings: 100,
     });
-    const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 10 });
+    const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
     const embed = recs.find((r) => r.id === 'embed.stale');
     expect(embed?.depends_on).toContain('sync.repo');
   });
@@ -157,9 +159,9 @@ describe('computeRecommendations', () => {
   test('severity ordering: critical before high before medium', () => {
     const health = makeHealth({
       missing_embeddings: 100,  // critical
+      stale_pages: 80,          // high
     });
-    // extractionLagPages > 50 → sync.repo fires at 'high' severity.
-    const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 80 });
+    const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
     const critIdx = recs.findIndex((r) => r.severity === 'critical');
     const highIdx = recs.findIndex((r) => r.severity === 'high');
     expect(critIdx).toBeLessThan(highIdx);
@@ -168,10 +170,11 @@ describe('computeRecommendations', () => {
   // D6 #5 — THE critical regression test for the agent contract.
   test('D6 #5: determinism — same input twice produces identical output', () => {
     const health = makeHealth({
+      stale_pages: 10,
       missing_embeddings: 50,
       dead_links: 3,
     });
-    const ctx = { repoPath: '/brain', embeddingProviderConfigured: true, sourceId: 'default', extractionLagPages: 10 };
+    const ctx = { repoPath: '/brain', embeddingProviderConfigured: true, sourceId: 'default' };
     const run1 = computeRecommendations(health, ctx);
     const run2 = computeRecommendations(health, ctx);
     expect(JSON.stringify(run1)).toBe(JSON.stringify(run2));

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/remediation-context-extraction-lag.test.ts

@@ -1,62 +0,0 @@
-// test/remediation-context-extraction-lag.test.ts
-//
-// Pins the v-next fix: the sync→extract remediation pipeline gates on REAL
-// extraction lag, not the legacy `health.stale_pages` proxy (which counted
-// "updated_at predates newest timeline entry" — meaningless after the v10
-// trigger drop). loadRecommendationContext now populates `extractionLagPages`
-// from `engine.countStalePagesForExtraction` — the SAME counter the
-// `gbrain extract --stale` walk and doctor's `links_extraction_lag` use — so a
-// recommendation can only fire when running extract will actually reduce it.
-
-import { afterAll, beforeAll, describe, expect, it } from 'bun:test';
-import { PGLiteEngine } from '../src/core/pglite-engine.ts';
-import { loadRecommendationContext } from '../src/core/remediation/context.ts';
-
-let engine: PGLiteEngine;
-
-beforeAll(async () => {
-  engine = new PGLiteEngine();
-  await engine.connect({});
-  await engine.initSchema();
-});
-
-afterAll(async () => {
-  await engine.disconnect();
-});
-
-describe('loadRecommendationContext — extractionLagPages wiring', () => {
-  it('is 0 on an empty brain (nothing to extract)', async () => {
-    const ctx = await loadRecommendationContext(engine);
-    expect(ctx.extractionLagPages).toBe(0);
-  });
-
-  it('reflects the real extraction-lag count once a page needs extraction', async () => {
-    // A freshly-imported page has links_extracted_at = NULL, which the canonical
-    // countStalePagesForExtraction predicate counts as stale-for-extraction.
-    await engine.putPage('p0', {
-      title: 'p0',
-      type: 'note' as never,
-      compiled_truth: 'body that is long enough to pass any minimum-length guards in the codebase',
-      timeline: '',
-      frontmatter: {},
-      source_path: 'p0.md',
-    });
-    const ctx = await loadRecommendationContext(engine);
-    expect(ctx.extractionLagPages).toBeGreaterThan(0);
-  });
-
-  it('counts pages stamped before LINK_EXTRACTOR_VERSION_TS (version-bump arm)', async () => {
-    // Backdate p0 so BOTH the NULL arm and the updated_at arm are quiet:
-    // updated_at < links_extracted_at, but links_extracted_at predates the
-    // extractor version stamp. doctor's links_extraction_lag and
-    // `extract --stale` both count this page; the remediation gate must too.
-    await engine.executeRaw(
-      `UPDATE pages SET updated_at = '2020-01-01T00:00:00Z'::timestamptz,
-                        links_extracted_at = '2020-01-02T00:00:00Z'::timestamptz
-        WHERE slug = 'p0'`,
-      [],
-    );
-    const ctx = await loadRecommendationContext(engine);
-    expect(ctx.extractionLagPages).toBeGreaterThan(0);
-  });
-});

test/remediation-run-d7-refresh.serial.test.ts

@@ -1,81 +0,0 @@
-// test/remediation-run-d7-refresh.serial.test.ts
-//
-// Pins the D7-recheck half of the extraction-lag gate fix: runRemediation
-// loads RecommendationContext ONCE before the step loop, and the per-step
-// recheck (D7) must REFRESH ctx.extractionLagPages alongside getHealth.
-// Without the refresh, a completed sync/extract step keeps re-firing off
-// the frozen initial count — the plan never converges and the loop burns
-// steps until maxJobs.
-//
-// SERIAL (R2): uses top-level mock.module for the minion queue +
-// wait-for-completion so no real worker is needed — mocks leak across
-// files in a shard process, so this file must run in its own process.
-
-import { describe, expect, mock, test } from 'bun:test';
-
-// The fake brain: sync.repo clears the extraction lag when it "runs"
-// (today's sync materializes link/timeline edges; extract.all is the
-// explicit re-materializer). The frozen-ctx bug makes runRemediation
-// ignore that and resubmit sync.repo on every D7 recheck.
-let extractionLag = 25;
-const submittedJobs: string[] = [];
-
-mock.module('../src/core/minions/queue.ts', () => ({
-  MinionQueue: class {
-    constructor(_engine: unknown) {}
-    async add(job: string): Promise<{ id: number }> {
-      submittedJobs.push(job);
-      if (job === 'sync' || job === 'extract') extractionLag = 0;
-      return { id: submittedJobs.length };
-    }
-  },
-}));
-
-mock.module('../src/core/minions/wait-for-completion.ts', () => ({
-  waitForCompletion: async () => ({ status: 'completed' }),
-}));
-
-const health = () => ({
-  page_count: 100,
-  embed_coverage: 1.0,
-  stale_pages: 0, // legacy proxy stays 0 — the real counter drives the gate
-  orphan_pages: 0,
-  missing_embeddings: 0,
-  brain_score: 70,
-  dead_links: 0,
-  link_coverage: 1.0,
-  timeline_coverage: 1.0,
-  most_connected: [],
-  embed_coverage_score: 35,
-  link_density_score: 25,
-  timeline_coverage_score: 15,
-  no_orphans_score: 15,
-  no_dead_links_score: 10,
-});
-
-const fakeEngine = {
-  kind: 'pglite' as const,
-  getHealth: async () => health(),
-  getConfig: async (key: string) =>
-    key === 'sync.repo_path' ? '/tmp/brain-example' : null,
-  countStalePagesForExtraction: async () => extractionLag,
-};
-
-describe('runRemediation D7 recheck — extraction-lag gate refresh', () => {
-  test('a completed materializer step clears the gate; the pipeline is not resubmitted', async () => {
-    const { runRemediation } = await import('../src/core/remediation/run.ts');
-    const result = await runRemediation(
-      // Only the methods the orchestrator touches are needed.
-      fakeEngine as never,
-      { targetScore: 0, maxJobs: 6 },
-    );
-    // Frozen-ctx bug: extractionLagPages stays 25 forever, so every D7
-    // recheck re-introduces the sync/extract pipeline and the loop burns
-    // all 6 maxJobs. With the refresh, the plan converges after the first
-    // completed step: no step id is ever submitted twice.
-    const ids = result.submitted.map((s) => s.id);
-    expect(new Set(ids).size).toBe(ids.length);
-    expect(submittedJobs.length).toBeLessThan(3);
-    expect(extractionLag).toBe(0);
-  });
-});