fix(doctor): register onboard check names in doctor-categories to stop unknown-check warnings

doctor.ts pushes runAllOnboardChecks results into the checks list, but the
7 onboard check names (embed_staleness, entity_link_coverage,
timeline_coverage, takes_count, dangling_aliases, pack_upgrade_available,
type_proliferation) were never added to doctor-categories.ts, so every
doctor run emitted an 'unknown check name' stderr warn per onboard check.

Registers the 5 data-quality names under BRAIN and the 2 schema-pack names
under META (alphabetical order preserved), and widens the drift-guard test
to scan src/core/onboard/checks.ts alongside src/commands/doctor.ts so
future onboard checks can't drift uncategorized.

Takeover of #1839, rebased onto master (keeps master's timeline_dedup_index).

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

src/commands/onboard.ts

@@ -142,16 +142,12 @@ 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). 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.
+  // summary).
   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/doctor-categories.ts

@@ -35,10 +35,11 @@
  *
  * The doctor renders both side by side.
  *
- * Drift contract: every check name that ships in doctor.ts MUST appear in
+ * Drift contract: every check name that ships through doctor MUST appear in
  * exactly one set below. The drift-guard test in
- * `test/doctor-categories.test.ts` enforces this by reading doctor.ts source
- * via a tagged-string scan and asserting set membership exactly.
+ * `test/doctor-categories.test.ts` enforces this by reading doctor check
+ * emitter sources via a tagged-string scan and asserting set membership
+ * exactly.
  *
  * If you add a new doctor check, you MUST add its name to the appropriate
  * set here. The categorize step in `src/commands/doctor.ts` falls through
@@ -67,12 +68,15 @@ export const BRAIN_CHECK_NAMES: ReadonlySet<string> = new Set([
   'conversation_parser_probe_health',
   'cross_modal_modality_backfill',
   'cycle_freshness',
+  'dangling_aliases',
   'effective_date_health',
+  'embed_staleness',
   'embedding_column_registry',
   'embedding_env_override',
   'embedding_provider',
   'embedding_width_consistency',
   'embeddings',
+  'entity_link_coverage',
   'eval_drift',
   'extract_atoms_backlog',
   'extract_health',
@@ -102,7 +106,9 @@ export const BRAIN_CHECK_NAMES: ReadonlySet<string> = new Set([
   'stub_guard_24h',
   'sync_failures',
   'sync_freshness',
+  'takes_count',
   'takes_weight_grid',
+  'timeline_coverage',
   'unified_multimodal_coverage',
   'voice_gate_health',
 ]);
@@ -170,12 +176,14 @@ export const META_CHECK_NAMES: ReadonlySet<string> = new Set([
   'eval_capture',
   'minions_migration',
   'multi_source_drift',
+  'pack_upgrade_available',
   'schema_pack_active',
   'schema_pack_consistency',
   'schema_pack_source_drift',
   'schema_version',
   'slug_fallback_audit',
   'timeline_dedup_index',
+  'type_proliferation',
   'upgrade_errors',
 ]);
 

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, extraRemediations: allowedExtras },
+      { targetScore, maxUsd },
       {},
     );
 

src/core/remediation/run.ts

@@ -66,10 +66,9 @@ 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, extraRemediations });
+  const initialPlan = await computeRemediationPlan(engine, { targetScore });
   if (initialPlan.target_unreachable) {
     hooks.onTargetUnreachable?.(targetScore, initialPlan.max_reachable_score);
     return {
@@ -88,7 +87,7 @@ export async function runRemediation(
   }
 
   const initialHealth = await engine.getHealth();
-  let recs: RemediationStep[] = computeRecommendations(initialHealth, ctx, extraRemediations)
+  let recs: RemediationStep[] = computeRecommendations(initialHealth, ctx)
     .filter((r) => r.status === 'remediable');
   if (recs.length === 0) {
     hooks.onNothingToDo?.(initialHealth.brain_score, targetScore);
@@ -306,13 +305,7 @@ export async function runRemediation(
       // steps with bumped retry suffix (D1).
       if (recs.length === 0 || stepCount >= maxJobs) break;
       const freshHealth = await engine.getHealth();
-      // 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');
+      recs = computeRecommendations(freshHealth, ctx).filter((r) => r.status === 'remediable');
     }
   };
 

src/core/remediation/types.ts

@@ -63,16 +63,6 @@ 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/doctor-categories.test.ts

@@ -1,10 +1,10 @@
 /**
  * Drift guard for src/core/doctor-categories.ts.
  *
- * Reads src/commands/doctor.ts source via a literal-string scan, enumerates
- * every `name: '<...>'` Check name, and asserts each appears in exactly ONE
- * category set. The union of the four sets must equal the discovered names
- * exactly — no orphans, no extras.
+ * Reads doctor check emitter source via a literal-string scan, enumerates every
+ * `name: '<...>'` Check name, and asserts each appears in exactly ONE category
+ * set. The union of the four sets must equal the discovered names exactly —
+ * no orphans, no extras.
  *
  * This is the structural failure the v0.41.19.0 plan-eng-review caught:
  * doctor.ts grows new checks regularly; without this guard, the
@@ -25,26 +25,30 @@ import {
 } from '../src/core/doctor-categories.ts';
 
 const DOCTOR_TS_PATH = join(import.meta.dir, '..', 'src', 'commands', 'doctor.ts');
+const ONBOARD_CHECKS_TS_PATH = join(import.meta.dir, '..', 'src', 'core', 'onboard', 'checks.ts');
+const CHECK_SOURCE_PATHS = [DOCTOR_TS_PATH, ONBOARD_CHECKS_TS_PATH];
 
 function enumerateCheckNames(): Set<string> {
-  const source = readFileSync(DOCTOR_TS_PATH, 'utf-8');
   const names = new Set<string>();
-  // 1) Inline object-literal form: `{ name: 'foo', ... }`.
-  for (const m of source.matchAll(/name:\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
-    names.add(m[1]);
-  }
-  // 2) Helper-function form: `const name = 'foo';` inside a check helper.
-  //    Catches checks like `nightly_quality_probe_health` and
-  //    `conversation_facts_backlog` that build the Check from a captured
-  //    name constant.
-  for (const m of source.matchAll(/const\s+name\s*=\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
-    names.add(m[1]);
+  for (const path of CHECK_SOURCE_PATHS) {
+    const source = readFileSync(path, 'utf-8');
+    // 1) Inline object-literal form: `{ name: 'foo', ... }`.
+    for (const m of source.matchAll(/name:\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
+      names.add(m[1]);
+    }
+    // 2) Helper-function form: `const name = 'foo';` inside a check helper.
+    //    Catches checks like `nightly_quality_probe_health` and
+    //    `conversation_facts_backlog` that build the Check from a captured
+    //    name constant.
+    for (const m of source.matchAll(/const\s+name\s*=\s*['"]([a-z][a-z0-9_]+)['"]/g)) {
+      names.add(m[1]);
+    }
   }
   return names;
 }
 
 describe('doctor-categories drift guard', () => {
-  test('every check name in doctor.ts source belongs to exactly one category set', () => {
+  test('every doctor-emitted check name belongs to exactly one category set', () => {
     const discovered = enumerateCheckNames();
     const allCategorized = new Set<string>([
       ...BRAIN_CHECK_NAMES,
@@ -59,7 +63,7 @@ describe('doctor-categories drift guard', () => {
     }
     if (missing.length > 0) {
       throw new Error(
-        `These check names appear in doctor.ts but are not categorized in ` +
+        `These check names appear in doctor check emitters but are not categorized in ` +
           `src/core/doctor-categories.ts: ${missing.sort().join(', ')}. ` +
           `Add each to BRAIN/SKILL/OPS/META_CHECK_NAMES.`,
       );
@@ -86,7 +90,7 @@ describe('doctor-categories drift guard', () => {
     expect(dupes).toEqual([]);
   });
 
-  test('every categorized name is currently used in doctor.ts source (no stale entries)', () => {
+  test('every categorized name is currently used in doctor check emitters (no stale entries)', () => {
     const discovered = enumerateCheckNames();
     const allCategorized = new Set<string>([
       ...BRAIN_CHECK_NAMES,
@@ -124,6 +128,14 @@ describe('categorizeCheck', () => {
     expect(categorizeCheck('sync_freshness')).toBe('brain');
   });
 
+  test('returns the right category for onboard data-quality check names', () => {
+    expect(categorizeCheck('embed_staleness')).toBe('brain');
+    expect(categorizeCheck('entity_link_coverage')).toBe('brain');
+    expect(categorizeCheck('timeline_coverage')).toBe('brain');
+    expect(categorizeCheck('takes_count')).toBe('brain');
+    expect(categorizeCheck('dangling_aliases')).toBe('brain');
+  });
+
   test('returns the right category for a known skill name', () => {
     expect(categorizeCheck('resolver_health')).toBe('skill');
     expect(categorizeCheck('skill_conformance')).toBe('skill');
@@ -140,6 +152,24 @@ describe('categorizeCheck', () => {
     expect(categorizeCheck('upgrade_errors')).toBe('meta');
   });
 
+  test('returns the right category for onboard schema-pack check names without warning', () => {
+    const originalWrite = process.stderr.write.bind(process.stderr);
+    const captured: string[] = [];
+    (process.stderr as { write: typeof process.stderr.write }).write = ((
+      chunk: string | Uint8Array,
+    ) => {
+      captured.push(typeof chunk === 'string' ? chunk : Buffer.from(chunk).toString());
+      return true;
+    }) as typeof process.stderr.write;
+    try {
+      expect(categorizeCheck('pack_upgrade_available')).toBe('meta');
+      expect(categorizeCheck('type_proliferation')).toBe('meta');
+      expect(captured.filter((c) => c.includes('[doctor-categories]'))).toEqual([]);
+    } finally {
+      (process.stderr as { write: typeof process.stderr.write }).write = originalWrite;
+    }
+  });
+
   test('unknown check name falls through to meta with a stderr warn (once per process)', () => {
     const originalWrite = process.stderr.write.bind(process.stderr);
     const captured: string[] = [];

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

@@ -1,108 +0,0 @@
-// 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',
-    ]);
-  });
-});