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/migrate-engine.ts

@@ -3,11 +3,7 @@
  *
  * Usage:
  *   gbrain migrate --to supabase [--url <connection_string>]
- *     (--url is persisted to config.json, mode 0600, so the migrated brain
- *      works without env — #1271)
  *   gbrain migrate --to pglite [--path <db_path>]
- *     (an explicit --path destination is bootstrapped with its own
- *      <path>/.gbrain/config.json so GBRAIN_HOME=<path> just works — #1271)
  *   gbrain migrate --to <engine> --force  (overwrite non-empty target)
  */
 
@@ -15,9 +11,9 @@ import { createEngine } from '../core/engine-factory.ts';
 import { loadConfig, saveConfig, toEngineConfig, gbrainPath, effectiveEnvDatabaseUrl, type GBrainConfig } from '../core/config.ts';
 import type { BrainEngine } from '../core/engine.ts';
 import type { EngineConfig } from '../core/types.ts';
-import { writeFileSync, readFileSync, existsSync, unlinkSync, mkdirSync, chmodSync } from 'fs';
+import { writeFileSync, readFileSync, existsSync, unlinkSync } from 'fs';
 import { createHash } from 'crypto';
-import { resolve, join } from 'path';
+import { resolve } from 'path';
 import { createProgress } from '../core/progress.ts';
 import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
 
@@ -63,31 +59,6 @@ export interface MigrateManifest {
   started_at: string;
 }
 
-/**
- * #1271 Finding 1: make an explicit `--to pglite --path P` destination usable
- * as a standalone brain. Writes `P/.gbrain/config.json` (mode 0600, plus a
- * `*` .gitignore) so `GBRAIN_HOME=P` resolves without a manual `gbrain init`.
- * Never clobbers an existing config at the destination. Returns the written
- * config path, or null when skipped.
- */
-export function bootstrapDestinationConfig(dbPath: string): string | null {
-  const abs = resolve(dbPath);
-  const dir = join(abs, '.gbrain');
-  const file = join(dir, 'config.json');
-  if (existsSync(file)) return null;
-  mkdirSync(dir, { recursive: true });
-  const cfg: GBrainConfig = { engine: 'pglite', database_path: abs };
-  writeFileSync(file, JSON.stringify(cfg, null, 2) + '\n', { mode: 0o600 });
-  try { chmodSync(file, 0o600); } catch { /* platform-specific */ }
-  // Same worktree-safety pattern as saveConfig()'s ensureGitignore, scoped
-  // to the destination home. Don't clobber a user-customized .gitignore.
-  const gitignore = join(dir, '.gitignore');
-  if (!existsSync(gitignore)) {
-    writeFileSync(gitignore, '*\n', { mode: 0o600 });
-  }
-  return file;
-}
-
 export function migrationTargetId(config: EngineConfig): string {
   const locator = config.engine === 'postgres'
     ? config.database_url ?? ''
@@ -381,25 +352,6 @@ export async function runMigrateEngine(sourceEngine: BrainEngine, args: string[]
   };
   saveConfig(newConfig);
 
-  // #1271 Finding 2 (by design, but say it out loud): the connection string
-  // is persisted so the migrated brain works without env. Mode 0600.
-  if (opts.targetEngine === 'postgres' && opts.targetUrl) {
-    console.error('Note: the --url connection string (including credentials) is persisted to config.json (mode 0600).');
-  }
-
-  // #1271 Finding 1: an explicit --path destination doubles as a standalone
-  // GBRAIN_HOME. Best-effort — never fail a completed migration over it.
-  if (opts.targetEngine === 'pglite' && opts.targetPath) {
-    try {
-      const written = bootstrapDestinationConfig(opts.targetPath);
-      if (written) {
-        console.log(`Destination bootstrapped: ${written} (usable via GBRAIN_HOME=${resolve(opts.targetPath)})`);
-      }
-    } catch (e) {
-      console.warn(`  WARN could not bootstrap destination config: ${e instanceof Error ? e.message : String(e)}`);
-    }
-  }
-
   // Clean up
   clearManifest();
 

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',
 ]);
 

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/migrate-engine-dest-bootstrap.test.ts

@@ -1,40 +0,0 @@
-import { describe, expect, test } from 'bun:test';
-import { mkdtempSync, mkdirSync, readFileSync, statSync, writeFileSync } from 'fs';
-import { tmpdir } from 'os';
-import { join, resolve } from 'path';
-import { bootstrapDestinationConfig } from '../src/commands/migrate-engine.ts';
-import { loadConfigFileOnly } from '../src/core/config.ts';
-import { withEnv } from './helpers/with-env.ts';
-
-describe('migrate --to pglite destination bootstrap (#1271)', () => {
-  test('writes <path>/.gbrain/config.json so GBRAIN_HOME=<path> resolves a brain', async () => {
-    const dest = mkdtempSync(join(tmpdir(), 'gbrain-dest-'));
-    const written = bootstrapDestinationConfig(dest);
-    const file = join(dest, '.gbrain', 'config.json');
-    expect(written).toBe(file);
-
-    const cfg = JSON.parse(readFileSync(file, 'utf-8'));
-    expect(cfg.engine).toBe('pglite');
-    expect(cfg.database_path).toBe(resolve(dest));
-    expect(statSync(file).mode & 0o777).toBe(0o600);
-    // worktree safety: destination home is git-ignored like saveConfig()'s home
-    expect(readFileSync(join(dest, '.gbrain', '.gitignore'), 'utf-8')).toBe('*\n');
-
-    // The exact failure mode from #1271: config resolution under
-    // GBRAIN_HOME=<path> used to find nothing ("No brain configured").
-    await withEnv({ GBRAIN_HOME: dest }, () => {
-      const loaded = loadConfigFileOnly();
-      expect(loaded?.engine).toBe('pglite');
-      expect(loaded?.database_path).toBe(resolve(dest));
-    });
-  });
-
-  test('never clobbers an existing destination config', () => {
-    const dest = mkdtempSync(join(tmpdir(), 'gbrain-dest-'));
-    mkdirSync(join(dest, '.gbrain'), { recursive: true });
-    writeFileSync(join(dest, '.gbrain', 'config.json'), '{"engine":"postgres"}\n');
-
-    expect(bootstrapDestinationConfig(dest)).toBe(null);
-    expect(JSON.parse(readFileSync(join(dest, '.gbrain', 'config.json'), 'utf-8')).engine).toBe('postgres');
-  });
-});