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/extract.ts

@@ -43,7 +43,7 @@ import {
 } from '../core/link-extraction.ts';
 import { createProgress } from '../core/progress.ts';
 import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
-import { pathToSlug, slugifyPath, pruneDir, isSyncable } from '../core/sync.ts';
+import { pathToSlug, pruneDir, isSyncable } from '../core/sync.ts';
 // v0.41.18.0: withRetry + isRetryableConnError + WithRetryOpts moved to
 // src/core/retry.ts as the canonical primitive. Engine methods
 // (addLinksBatch/addTimelineEntriesBatch/upsertChunks) now self-retry via
@@ -269,24 +269,14 @@ export function extractMarkdownLinks(content: string): { name: string; relTarget
 export function resolveSlug(fileDir: string, relTarget: string, allSlugs: Set<string>): string | null {
   const targetNoExt = relTarget.endsWith('.md') ? relTarget.slice(0, -3) : relTarget;
 
-  // Issue #1964: wikilinks carry raw Obsidian paths (`[[llm-wiki/entities/AI 3.0]]`)
-  // but allSlugs holds sync-slugified slugs (`llm-wiki/entities/ai-3.0`). Try the
-  // raw candidate first (back-compat), then the sync-consistent slugified form.
-  const hit = (candidate: string): string | null => {
-    if (allSlugs.has(candidate)) return candidate;
-    const slugified = slugifyPath(candidate);
-    if (slugified !== candidate && allSlugs.has(slugified)) return slugified;
-    return null;
-  };
-
-  const s1 = hit(join(fileDir, targetNoExt));
-  if (s1) return s1;
+  const s1 = join(fileDir, targetNoExt);
+  if (allSlugs.has(s1)) return s1;
 
   const parts = fileDir.split('/').filter(Boolean);
   for (let strip = 1; strip <= parts.length; strip++) {
     const ancestor = parts.slice(0, parts.length - strip).join('/');
-    const candidate = hit(ancestor ? join(ancestor, targetNoExt) : targetNoExt);
-    if (candidate) return candidate;
+    const candidate = ancestor ? join(ancestor, targetNoExt) : targetNoExt;
+    if (allSlugs.has(candidate)) return candidate;
   }
 
   return null;

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/link-extraction.ts

@@ -14,7 +14,6 @@
 import type { BrainEngine } from './engine.ts';
 import type { PageType } from './types.ts';
 import { ensureWellFormed } from './text-safe.ts';
-import { slugifyPath } from './sync.ts';
 
 /**
  * v0.42.7 — link-extraction version stamp. Bump this ISO timestamp whenever the
@@ -483,29 +482,14 @@ export async function extractPageLinks(
     // pre-v0.40.8.2 behavior of dropping bare wikilinks outside
     // DIR_PATTERN.
     if (ref.needsResolution) {
-      if (typeof resolver.resolveBasenameMatches !== 'function') continue;
+      if (!opts.globalBasename || typeof resolver.resolveBasenameMatches !== 'function') {
+        continue;
+      }
       // Issue #972 (codex): resolve by the wikilink TARGET (ref.slug — the
       // text inside `[[...]]` before any `|`), NOT the display alias
       // (ref.name = match[2]). `[[struktura|the project]]` must resolve
       // `struktura`, not "the project". The display text is for context only.
-      //
-      // Issue #1964: a dir-qualified wikilink (`[[llm-wiki/entities/AI 3.0]]`)
-      // carries a raw Obsidian path while page slugs are sync-slugified
-      // (`llm-wiki/entities/ai-3.0`). Slugify the path the same way sync does,
-      // then match by exact slug or path-suffix (wiki-root-relative authoring).
-      // This runs regardless of global_basename — it's dir-qualified, so the
-      // cross-dir false-positive risk the flag guards against doesn't apply.
-      // Mirrors the FS path's resolveSlug ancestor walk. Bare `[[name]]`
-      // wikilinks still require the global_basename flag.
-      let matches: string[] = [];
-      const slugified = ref.slug.includes('/') ? slugifyPath(ref.slug) : '';
-      if (slugified.includes('/')) {
-        const tail = slugified.slice(slugified.lastIndexOf('/') + 1);
-        matches = (await resolver.resolveBasenameMatches(tail))
-          .filter(m => m === slugified || m.endsWith(`/${slugified}`));
-      } else if (opts.globalBasename) {
-        matches = await resolver.resolveBasenameMatches(ref.slug);
-      }
+      const matches = await resolver.resolveBasenameMatches(ref.slug);
       if (matches.length === 0) continue;
       const idx = content.indexOf(ref.slug);
       const context = idx >= 0 ? excerpt(content, idx, 240) : ref.name;

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/extract-fs.test.ts

@@ -389,33 +389,6 @@ describe('resolveSlugAll', () => {
   });
 });
 
-// ─── issue #1964: cross-directory wikilinks — slug/path mismatch ──────────
-
-describe('issue #1964: raw Obsidian wikilink paths resolve to sync-slugified slugs', () => {
-  test('resolveSlug slugifies the candidate (sync-consistent), no flag needed', () => {
-    const all = new Set(['llm-wiki/entities/ai-3.0']);
-    // Wikilink literal `[[llm-wiki/entities/AI 3.0]]` — spaces + uppercase.
-    expect(resolveSlug('llm-wiki/notes', 'llm-wiki/entities/AI 3.0.md', all))
-      .toBe('llm-wiki/entities/ai-3.0');
-  });
-
-  test('resolveSlug slugifies raw (unslugified) fileDir too', () => {
-    const all = new Set(['llm-wiki/entities/ai-3.0']);
-    // fileDir comes from dirname(relPath) — the raw on-disk directory.
-    expect(resolveSlug('LLM Wiki/Notes', 'entities/AI 3.0.md', all))
-      .toBe('llm-wiki/entities/ai-3.0');
-  });
-
-  test('extractLinksFromFile resolves cross-directory wikilink with flag OFF as a typed edge', async () => {
-    const allSlugs = new Set(['llm-wiki/entities/ai-3.0', 'llm-wiki/notes/roadmap']);
-    const content = '---\ntitle: Roadmap\ntype: concept\n---\n\nSee [[llm-wiki/entities/AI 3.0]].\n';
-    const links = await extractLinksFromFile(content, 'llm-wiki/notes/roadmap.md', allSlugs);
-    expect(links.map(l => l.to_slug)).toEqual(['llm-wiki/entities/ai-3.0']);
-    // Dir-qualified path resolution is exact, NOT the basename fallback.
-    expect(links[0].link_type).not.toBe('wikilink_basename');
-  });
-});
-
 describe('issue #972 repro: bare wikilinks resolve when flag is on', () => {
   // End-to-end: reproduces the issue's exact repro inside a tempdir +
   // PGLite, then asserts edge count under both flag states.

test/link-extraction.test.ts

@@ -9,8 +9,6 @@ import {
   parseTimelineEntries,
   isAutoLinkEnabled,
   FRONTMATTER_LINK_MAP,
-  buildBasenameIndex,
-  queryBasenameIndex,
   type SlugResolver,
 } from '../src/core/link-extraction.ts';
 import type { BrainEngine } from '../src/core/engine.ts';
@@ -426,46 +424,6 @@ describe('extractPageLinks', () => {
     expect(strk!.linkType).toBe('wikilink_basename');
   });
 
-  // ─── issue #1964: dir-qualified wikilinks with raw Obsidian paths ────────
-
-  test('#1964: dir-qualified wikilink resolves via sync-consistent slugification (flag OFF)', async () => {
-    // `[[llm-wiki/entities/AI 3.0]]` is a raw Obsidian path; the page slug
-    // is the sync-slugified `llm-wiki/entities/ai-3.0`. Must resolve WITHOUT
-    // global_basename (it's dir-qualified) and must NOT leak to a same-tail
-    // page in a different directory.
-    const resolver: SlugResolver = {
-      resolve: async () => null,
-      resolveBasenameMatches: async (name) =>
-        name === 'ai-3.0' ? ['other/ai-3.0', 'llm-wiki/entities/ai-3.0'] : [],
-    };
-    const { candidates } = await extractPageLinks(
-      'llm-wiki/notes/roadmap',
-      'See [[llm-wiki/entities/AI 3.0]] for the model.',
-      {}, 'concept', resolver,
-      // opts.globalBasename omitted (= false) — path is dir-qualified
-    );
-    expect(candidates.map(c => c.targetSlug)).toEqual(['llm-wiki/entities/ai-3.0']);
-    expect(candidates[0].linkType).toBe('wikilink_basename');
-    expect(candidates[0].linkSource).toBe('wikilink-resolved');
-  });
-
-  test('#1964: path-suffix match resolves wiki-root-relative paths against a real index', async () => {
-    // Author writes `[[llm-wiki/entities/AI 3.0]]` but the brain nests the
-    // wiki under a vault dir. Suffix match rescues it; queried through the
-    // REAL basename index so the tail-key lookup is exercised end to end.
-    const idx = buildBasenameIndex(['vault/llm-wiki/entities/ai-3.0', 'people/ai-3.0']);
-    const resolver: SlugResolver = {
-      resolve: async () => null,
-      resolveBasenameMatches: async (name) => queryBasenameIndex(idx, name),
-    };
-    const { candidates } = await extractPageLinks(
-      'vault/llm-wiki/notes/roadmap',
-      'See [[llm-wiki/entities/AI 3.0]].',
-      {}, 'concept', resolver,
-    );
-    expect(candidates.map(c => c.targetSlug)).toEqual(['vault/llm-wiki/entities/ai-3.0']);
-  });
-
   test('opts.skipFrontmatter suppresses the frontmatter pass', async () => {
     // Real resolver shape that WOULD resolve frontmatter source: too,
     // but skipFrontmatter blocks the path entirely.

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',
+    ]);
+  });
+});