fix(onboard): stop dropping onboard-check remediations on the --apply --auto path

Takeover of #2161. runRemediation ignored onboard-check extras in three
places: the pre-flight plan, the initial recommendation build, and the D7
mid-run recheck that rebuilds recs after every completed step. The --check
path threaded extras correctly, so `gbrain onboard --apply --auto` reported
"Nothing to do" when the only remediable work came from onboard checks —
and even with the first two sites fixed (the original PR diff), any plan
with 2+ steps dropped all remaining extras after step 1 via the recheck.

- Add RemediationOpts.extraRemediations; thread it through the pre-flight
  plan, initial recs, and the mid-run recheck.
- Recheck filters extras to ids not already processed this run: extras
  carry static status:'remediable', so unfiltered threading would resubmit
  completed extras forever.
- Wire the CLI --auto path (onboard.ts) AND the MCP run_onboard auto path
  (operations.ts), which already computed the scope-filtered allowedExtras
  and then dropped it.
- Regression test: extras-only plan on an empty brain runs BOTH extras
  exactly once and terminates (serial file: mock.module queue stub +
  GBRAIN_HOME tmpdir).

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

src/commands/onboard.ts

@@ -142,12 +142,16 @@ export async function runOnboard(engine: BrainEngine, args: string[]): Promise<v
 
   // --auto path: runs through the T2 library orchestrator. Hooks emit CLI
   // progress to stderr; the final result lands as JSON on stdout (or human
-  // summary).
+  // summary). extraRemediations (gathered above from runAllOnboardChecks)
+  // is threaded into the runner so the onboard-check remediations
+  // (extract-ner, extract-timeline-from-meetings, etc.) reach the planner
+  // — the same wiring the --check path uses above.
   const result = await runRemediation(
     engine,
     {
       targetScore,
       maxUsd,
+      extraRemediations,
       // --auto --yes opts into the prompt_required tier too; library
       // doesn't distinguish auto_apply vs prompt_required, it just runs
       // every remediation in the plan. The plan-building side (T12 render)

src/core/context-engine.ts

@@ -453,14 +453,7 @@ function resolveActivity(
  * every `assemble()` call. 1 MB is generous for a human-edited task list. */
 const MAX_TASKS_MD_BYTES = 1_000_000;
 
-/** Extract open tasks from ops/tasks.md Today section.
- *
- * The daily-task-manager skill's documented Output Format uses priority
- * headings (`## P1 — Today`) with plain `- [ ] task` lines; older fixtures
- * used a bare `## Today` heading with bold task names. Accept both so the
- * live-context reader matches the documented writer contract instead of
- * silently surfacing no tasks (#2186).
- */
+/** Extract open tasks from ops/tasks.md "## Today" section. */
 function resolveTodayTasks(workspaceDir: string): string[] {
   try {
     const path = join(workspaceDir, 'ops', 'tasks.md');
@@ -468,18 +461,14 @@ function resolveTodayTasks(workspaceDir: string): string[] {
     // statSync throws if the file doesn't exist; that lands in the outer catch.
     if (statSync(path).size > MAX_TASKS_MD_BYTES) return [];
     const raw = readFileSync(path, 'utf8');
-    const todayMatch = raw.match(/^##\s+(?:P\d\s*[—–-]\s*)?Today\b[\s\S]*?(?=\n##\s|$(?![\s\S]))/m);
+    const todayMatch = raw.match(/## Today[\s\S]*?(?=\n## |$)/);
     if (!todayMatch) return [];
 
     const lines = todayMatch[0].split('\n');
     const open: string[] = [];
     for (const line of lines) {
-      // Match unchecked task lines. Legacy bold form first (extracts just
-      // the task name, dropping trailing metadata), then the documented
-      // plain form (whole line body is the task).
-      const m =
-        line.match(/^\s*-\s*\[ \]\s*\*\*(.+?)\*\*/) ??
-        line.match(/^\s*-\s*\[ \]\s*(.+?)\s*$/);
+      // Match unchecked task lines: - [ ] **task name** ...
+      const m = line.match(/^\s*-\s*\[ \]\s*\*\*(.+?)\*\*/);
       if (m) open.push(sanitizeForPrompt(m[1].trim()));
     }
     return open.slice(0, 5); // cap at 5 to keep prompt lean

src/core/operations.ts

@@ -4957,7 +4957,7 @@ const run_onboard: Operation = {
     // typo, the underlying queue.add would reject. Defense-in-depth.
     const result = await runRemediation(
       ctx.engine,
-      { targetScore, maxUsd },
+      { targetScore, maxUsd, extraRemediations: allowedExtras },
       {},
     );
 

src/core/remediation/run.ts

@@ -66,9 +66,10 @@ export async function runRemediation(
   } = await import('../remediation-checkpoint.ts');
 
   const ctx = await loadRecommendationContext(engine);
+  const extraRemediations = opts.extraRemediations ?? [];
 
   // Pre-flight ceiling check via the shared plan computation.
-  const initialPlan = await computeRemediationPlan(engine, { targetScore });
+  const initialPlan = await computeRemediationPlan(engine, { targetScore, extraRemediations });
   if (initialPlan.target_unreachable) {
     hooks.onTargetUnreachable?.(targetScore, initialPlan.max_reachable_score);
     return {
@@ -87,7 +88,7 @@ export async function runRemediation(
   }
 
   const initialHealth = await engine.getHealth();
-  let recs: RemediationStep[] = computeRecommendations(initialHealth, ctx)
+  let recs: RemediationStep[] = computeRecommendations(initialHealth, ctx, extraRemediations)
     .filter((r) => r.status === 'remediable');
   if (recs.length === 0) {
     hooks.onNothingToDo?.(initialHealth.brain_score, targetScore);
@@ -305,7 +306,13 @@ export async function runRemediation(
       // steps with bumped retry suffix (D1).
       if (recs.length === 0 || stepCount >= maxJobs) break;
       const freshHealth = await engine.getHealth();
-      recs = computeRecommendations(freshHealth, ctx).filter((r) => r.status === 'remediable');
+      // Extras carry a static status:'remediable' — a fresh health snapshot
+      // never ages them out the way health-derived steps drop. Filter out
+      // ids this run already processed (any terminal status), or the recheck
+      // would resubmit completed extras every iteration, forever.
+      const processedIds = new Set(submitted.map((s) => s.id));
+      const pendingExtras = extraRemediations.filter((r) => !processedIds.has(r.id));
+      recs = computeRecommendations(freshHealth, ctx, pendingExtras).filter((r) => r.status === 'remediable');
     }
   };
 

src/core/remediation/types.ts

@@ -63,6 +63,16 @@ export interface RemediationOpts {
   resumePlanHash?: string;
   /** Whether to attempt resume at all (default false). */
   resume?: boolean;
+  /**
+   * Caller-supplied RemediationStep entries threaded into the planner.
+   * Mirrors RemediationPlanOpts.extraRemediations so onboard's --apply
+   * --auto path (and MCP run_onboard auto modes) forward the same
+   * onboard-check remediations the --check path already passes through
+   * computeRemediationPlan. Without this the runner saw only generic
+   * brain_score remediations and reported "Nothing to do" whenever the
+   * only applicable work was an extra (e.g. extract-ner).
+   */
+  extraRemediations?: RemediationStep[];
 }
 
 /**

test/context-engine.test.ts

@@ -322,28 +322,6 @@ describe('gbrain-context engine', () => {
     expect(result.systemPromptAddition).not.toContain('Something later');
   });
 
-  it('injects documented "## P1 — Today" plain tasks from ops/tasks.md (#2186)', async () => {
-    tmpDir = makeWorkspace({
-      heartbeat: { garryAwake: true },
-      tasks: `# Tasks\n\n## P0 — Urgent\n- [ ] **Escalate outage**\n\n## P1 — Today\n- [ ] Call Alice about launch plan\n- [ ] **Review Bob contract** — due Friday\n- [x] Completed item\n\n## P2 — This Week\n- [ ] Should not surface`,
-    });
-    const engine = createGBrainContextEngine({ workspaceDir: tmpDir });
-
-    const result = await engine.assemble({
-      sessionId: 'test-session',
-      messages: [],
-    });
-
-    expect(result.systemPromptAddition).toContain('Open tasks');
-    expect(result.systemPromptAddition).toContain('Call Alice about launch plan');
-    // Bold form still extracts just the task name, not trailing metadata.
-    expect(result.systemPromptAddition).toContain('Review Bob contract');
-    expect(result.systemPromptAddition).not.toContain('due Friday');
-    expect(result.systemPromptAddition).not.toContain('Escalate outage');
-    expect(result.systemPromptAddition).not.toContain('Completed item');
-    expect(result.systemPromptAddition).not.toContain('Should not surface');
-  });
-
   it('no activity section when calendar is empty and no tasks', async () => {
     tmpDir = makeWorkspace({
       heartbeat: { garryAwake: true },

test/remediation-run-extras.serial.test.ts

@@ -0,0 +1,108 @@
+// test/remediation-run-extras.serial.test.ts
+// Regression for PR #2161 takeover: `gbrain onboard --apply --auto` dropped
+// onboard-check extraRemediations. Two distinct halves of the bug:
+//   1. runRemediation built the pre-flight plan + initial recs WITHOUT the
+//      extras, so an extras-only plan reported "Nothing to do".
+//   2. The D7 mid-run recheck rebuilt recs WITHOUT the extras after every
+//      completed step, so with 2+ plannable steps all remaining extras were
+//      dropped after step 1. The recheck must also filter out extras this
+//      run already processed — extras carry static status:'remediable', so
+//      unfiltered threading would resubmit completed extras forever.
+//
+// SERIAL: mock.module (queue + wait-for-completion stubs, R2) + GBRAIN_HOME
+// env mutation so checkpoint files land in a tmpdir, not ~/.gbrain.
+
+import { describe, expect, test, beforeAll, afterAll, mock } from 'bun:test';
+import { mkdtempSync, rmSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { PGLiteEngine } from '../src/core/pglite-engine.ts';
+import { makeRemediationStep } from '../src/core/remediation-step.ts';
+
+// Stub the Minion queue: every submitted job is immediately 'completed'.
+// runRemediation only calls queue.add + waitForCompletion(queue, id).
+let nextJobId = 1;
+const submittedJobs: Array<{ name: string }> = [];
+mock.module('../src/core/minions/queue.ts', () => ({
+  MinionQueue: class {
+    async add(name: string) {
+      submittedJobs.push({ name });
+      return { id: nextJobId++, status: 'completed' };
+    }
+  },
+}));
+mock.module('../src/core/minions/wait-for-completion.ts', () => ({
+  waitForCompletion: async () => ({ status: 'completed' }),
+}));
+
+let engine: PGLiteEngine;
+let home: string;
+const prevHome = process.env.GBRAIN_HOME;
+
+beforeAll(async () => {
+  home = mkdtempSync(join(tmpdir(), 'gbrain-remextras-'));
+  process.env.GBRAIN_HOME = home;
+  engine = new PGLiteEngine();
+  await engine.connect({});
+  await engine.initSchema();
+}, 120_000);
+
+afterAll(async () => {
+  await engine.disconnect();
+  if (prevHome === undefined) delete process.env.GBRAIN_HOME;
+  else process.env.GBRAIN_HOME = prevHome;
+  rmSync(home, { recursive: true, force: true });
+});
+
+function extra(id: string, job: string) {
+  return makeRemediationStep({
+    id,
+    job,
+    params: {},
+    severity: 'medium',
+    est_seconds: 5,
+    est_usd_cost: 0,
+    rationale: 'synthetic onboard-check extra',
+    status: 'remediable',
+  });
+}
+
+describe('runRemediation extraRemediations threading', () => {
+  test('extras-only plan runs BOTH extras and terminates (no Nothing-to-do, no resubmit loop)', async () => {
+    // Empty PGLite brain → zero health-derived recommendations. Without the
+    // fix, half 1 makes this run return submitted: [] via onNothingToDo.
+    // With only half 1 (the original PR #2161 diff), the mid-run recheck
+    // drops the second extra after step 1 — submitted has 1 entry, not 2.
+    const { runRemediation } = await import('../src/core/remediation/run.ts');
+    let nothingToDo = false;
+    const result = await runRemediation(
+      engine,
+      {
+        targetScore: 1,
+        extraRemediations: [
+          extra('onboard.extract_ner', 'extract-ner'),
+          extra('onboard.extract_timeline', 'extract-timeline-from-meetings'),
+        ],
+        // Safety bound: an unfiltered recheck would resubmit completed
+        // extras forever; maxJobs turns that regression into a fast fail
+        // (extra count > 1 below) instead of a hung test.
+        maxJobs: 5,
+      },
+      { onNothingToDo: () => { nothingToDo = true; } },
+    );
+
+    expect(nothingToDo).toBe(false);
+    const ids = result.submitted.map((s) => s.id);
+    expect(ids).toContain('onboard.extract_ner');
+    expect(ids).toContain('onboard.extract_timeline');
+    // Each extra ran exactly once — the recheck must not re-plan extras the
+    // run already processed.
+    expect(ids.filter((i) => i === 'onboard.extract_ner').length).toBe(1);
+    expect(ids.filter((i) => i === 'onboard.extract_timeline').length).toBe(1);
+    expect(result.submitted.every((s) => s.status === 'completed')).toBe(true);
+    expect(submittedJobs.map((j) => j.name).sort()).toEqual([
+      'extract-ner',
+      'extract-timeline-from-meetings',
+    ]);
+  });
+});