Compare commits

..
Author SHA1 Message Date
06eeb2890b fix(skillopt): emit proposed.md in no-mutate mode (#2635)
writeProposed now writes both best.md (optimizer's current-best pointer)
and proposed.md (the stable review artifact documented by --no-mutate);
the orchestrator returns the real proposed.md path instead of aliasing
best.md. Fix lands in the shared helper so both accept-branch call sites
are covered.

Takeover of #2719.

Co-authored-by: RerankerGuo <RerankerGuo@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:30:19 -07:00
7 changed files with 54 additions and 120 deletions
@@ -233,13 +233,14 @@ keep it or `git checkout` to throw it away. Nothing is committed for you.
**For a skill that ships with gbrain** (anything under the gbrain repo's own
`skills/`): SkillOpt refuses to overwrite it by default and writes the winner to
`skills/<name>/skillopt/best.md` instead, so an optimization pass can never
silently mutate a skill other people depend on. Two ways to handle that:
`skills/<name>/skillopt/proposed.md` instead (while keeping `best.md` as the
optimizer's current-best pointer), so an optimization pass can never silently
mutate a skill other people depend on. Two ways to handle that:
```bash
# See the proposed improvement without touching SKILL.md (works for ANY skill):
gbrain skillopt meeting-prep --split 1:1:1 --no-mutate
# → writes skills/meeting-prep/skillopt/best.md (the proposed rewrite), prints its path. Copy what you want.
# → writes skills/meeting-prep/skillopt/proposed.md, updates best.md, and prints the proposal path.
# Actually rewrite a bundled skill (explicit opt-in + an independent held-out set):
gbrain skillopt brain-ops --split 1:1:1 --allow-mutate-bundled \
+6 -17
View File
@@ -18,7 +18,6 @@
import type { BrainEngine } from '../engine.ts';
import { loadActivePackBestEffort } from './best-effort.ts';
import type { OperationContext } from '../operations.ts';
import { isUndefinedTableError } from '../utils.ts';
export interface StatsOpts {
/** Single source scope. Omit + omit sourceIds for whole-brain aggregate. */
@@ -165,17 +164,9 @@ async function fetchCountRows(engine: BrainEngine, opts: StatsOpts): Promise<Raw
`;
try {
return await engine.executeRaw<RawCountRow>(sql, params);
} catch (err) {
// ONLY swallow the genuine "pages table doesn't exist yet" case
// (empty / pre-init brain). #2466: the old bare `catch {}` masked
// EVERY error — so any engine-level failure (connection, version
// skew, a query incompatibility) was silently converted to 0 rows,
// printing "Total pages: 0" on a populated brain and cascading into
// false "100% coverage" + a starved `schema suggest`. Surface
// everything that is not a missing-table error so the real failure
// is visible instead of hidden behind a fake zero.
if (isUndefinedTableError(err)) return [];
throw err;
} catch {
// Empty / pre-init brain: pages table may not exist yet.
return [];
}
}
@@ -213,11 +204,9 @@ async function detectDeadPrefixes(
if (cnt === 0) {
hints.push({ type: t.name, prefix });
}
} catch (err) {
// #2466: only skip on the genuine "no pages table yet" case;
// rethrow any other engine error so it isn't silently masked.
if (isUndefinedTableError(err)) continue;
throw err;
} catch {
// Skip on engine error (no pages table yet, etc.).
continue;
}
}
}
+10 -4
View File
@@ -93,7 +93,13 @@ import { resolveLrSchedule } from './lr-schedule.ts';
import { preflight, formatPreflightReport } from './preflight.ts';
import { isRejected, loadRejectedBuffer, makeRejectedEntry, saveRejectedBuffer } from './rejected-buffer.ts';
import { runReflect, runOneShotRewrite, describeJudges } from './reflect.ts';
import { acceptCandidate, bestPath, revertAllPending, skillPath, writeProposed } from './version-store.ts';
import {
acceptCandidate,
proposedPath as proposedFilePath,
revertAllPending,
skillPath,
writeProposed,
} from './version-store.ts';
import { runValidationGate, scoreSkillOnTasks } from './validate-gate.ts';
import { ROLLOUT_SUCCESS_THRESHOLD } from './types.ts';
import type { SkillOptOpts, EditOp, RunReceipt, BenchmarkTask } from './types.ts';
@@ -702,9 +708,9 @@ async function runOptimizationLoop(
// to the catch's assignment values only (it can't prove the async callback ran).
const finalOutcome = outcome as 'accepted' | 'no_improvement' | 'aborted' | 'errored';
if (!mutateDecision.mutate && finalOutcome === 'accepted') {
// best.md was written by writeProposed() in the accept branch (no-mutate
// path); it doubles as proposed.md for human review. SKILL.md untouched.
proposedPath = bestPath(skillsDir, skillName);
// writeProposed() emitted both the best pointer and the stable review
// artifact in the accept branch. SKILL.md remains untouched.
proposedPath = proposedFilePath(skillsDir, skillName);
} else if (mutateDecision.mutate) {
mutatedSkillFile = finalOutcome === 'accepted';
}
+15 -9
View File
@@ -23,6 +23,7 @@
*
* history.json
* best.md
* proposed.md
* versions/
* v0001_e1_s1.md
* v0002_e1_s2.md
@@ -52,6 +53,10 @@ export function bestPath(skillsDir: string, skillName: string): string {
return path.join(skilloptDir(skillsDir, skillName), 'best.md');
}
export function proposedPath(skillsDir: string, skillName: string): string {
return path.join(skilloptDir(skillsDir, skillName), 'proposed.md');
}
export function skillPath(skillsDir: string, skillName: string): string {
return path.join(skillsDir, skillName, 'SKILL.md');
}
@@ -171,17 +176,18 @@ export function acceptCandidate(input: AcceptInput): AcceptResult {
}
/**
* Write the candidate to `best.md` (which doubles as `proposed.md`) WITHOUT
* touching SKILL.md or the history ledger. Used by the `--no-mutate` /
* bundled-without-allow paths: the optimizer found a better candidate but the
* caller opted out of in-place mutation, so we surface it for human review.
* Returns the path written. Atomic (.tmp + rename).
* Write the candidate to both `best.md` and `proposed.md` WITHOUT touching
* SKILL.md or the history ledger. `best.md` remains the optimizer's current
* best pointer; `proposed.md` is the stable human-review artifact promised by
* `--no-mutate`. Returns the proposal path. Each write is atomic (.tmp + rename).
*/
export function writeProposed(skillsDir: string, skillName: string, candidateText: string): string {
const p = bestPath(skillsDir, skillName);
fs.mkdirSync(path.dirname(p), { recursive: true });
atomicWrite(p, candidateText);
return p;
const best = bestPath(skillsDir, skillName);
const proposed = proposedPath(skillsDir, skillName);
fs.mkdirSync(path.dirname(best), { recursive: true });
atomicWrite(best, candidateText);
atomicWrite(proposed, candidateText);
return proposed;
}
/**
+4 -4
View File
@@ -39,6 +39,7 @@ import { runSkillOpt } from '../../src/core/skillopt/orchestrator.ts';
import {
bestPath,
loadHistory,
proposedPath,
skillPath,
} from '../../src/core/skillopt/version-store.ts';
import { loadRejectedBuffer } from '../../src/core/skillopt/rejected-buffer.ts';
@@ -741,7 +742,7 @@ describe('skillopt T3 — F11 held-out gate, ablation opts, no-DB-pollution', ()
} finally { fixture.cleanup(); }
});
test('--no-mutate writes proposed.md (best.md), leaves SKILL.md untouched', async () => {
test('--no-mutate writes proposed.md and best.md, leaves SKILL.md untouched', async () => {
const fixture = setupFixture(SKILL_PEOPLE_ONLY, CITATIONS_BENCHMARK);
try {
installStub({
@@ -753,10 +754,9 @@ describe('skillopt T3 — F11 held-out gate, ablation opts, no-DB-pollution', ()
const result = await runOnce(fixture, { noMutate: true });
expect(result.outcome).toBe('accepted');
expect(result.mutatedSkillFile).toBe(false);
expect(result.proposedPath).toBeDefined();
// proposed.md (best.md) exists and carries the improvement.
expect(fs.existsSync(result.proposedPath!)).toBe(true);
expect(result.proposedPath).toBe(proposedPath(fixture.skillsDir, SKILL));
expect(fs.readFileSync(result.proposedPath!, 'utf8')).toContain('## Citations');
expect(fs.readFileSync(bestPath(fixture.skillsDir, SKILL), 'utf8')).toContain('## Citations');
// SKILL.md on disk is UNCHANGED (still People-only).
const skill = fs.readFileSync(skillPath(fixture.skillsDir, SKILL), 'utf8');
expect(skill).not.toContain('## Citations');
-83
View File
@@ -222,89 +222,6 @@ describe('runStatsCore — JSON envelope shape', () => {
});
});
describe('runStatsCore — #2466 catch-narrowing (real count + error surfacing)', () => {
// #2466: `gbrain schema stats` reported "Total pages: 0" on a populated
// PGLite brain. The bug was a bare `catch {}` in fetchCountRows (and a
// sibling in detectDeadPrefixes) that converted ANY engine error into 0
// rows. The COUNT query itself is valid on PGLite (proven below), so the
// regression pins two things: (a) a populated brain reports the real,
// non-zero count through the full runStatsCore path; (b) a non-missing-
// table engine error is rethrown, not masked into a fake zero.
it('reports the real non-zero count on a populated PGLite brain (no false 0)', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
// Seed a realistic mix: typed, untyped, multiple types — like the
// 169-page brain in the bug report (scaled down).
for (let i = 0; i < 12; i++) {
const type = i % 3 === 0 ? '' : (i % 3 === 1 ? 'person' : 'company');
await seedPage(`notes/p${i}`, { type, sourcePath: `notes/p${i}.md` });
}
const result = await runStatsCore(ctxOf());
// The core regression: NOT zero.
expect(result.aggregate.total_pages).toBe(12);
expect(result.aggregate.typed_pages).toBe(8);
expect(result.aggregate.untyped_pages).toBe(4);
// And coverage is the honest ratio, not the vacuous 1.0 a 0/0 prints.
expect(result.aggregate.coverage).not.toBe(1.0);
});
});
it('fetchCountRows rethrows a non-missing-table engine error instead of masking it as 0 pages', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
// No pack → detectDeadPrefixes is skipped, isolating the throw to the
// fetchCountRows catch we narrowed. The count query (the GROUP BY one)
// throws a column-level error (SQLSTATE 42703) — the exact class the
// old bare `catch {}` swallowed into 0 rows; everything else succeeds.
__setPackLocatorForTests(() => null);
const boom = Object.assign(new Error('column "type" does not exist'), { code: '42703' });
const stubEngine = {
executeRaw: async (sql: string) => {
if (/GROUP BY source_id/.test(sql)) throw boom; // the fetchCountRows query
return [];
},
} as unknown as PGLiteEngine;
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
await expect(runStatsCore(ctx)).rejects.toThrow('column "type" does not exist');
});
});
it('fetchCountRows still degrades to empty (no throw) on a genuine missing pages table', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
// Pre-init brain shape: the count query hits a missing pages table
// (SQLSTATE 42P01). This is the ONLY case the narrowed catch swallows.
__setPackLocatorForTests(() => null);
const missing = Object.assign(new Error('relation "pages" does not exist'), { code: '42P01' });
const stubEngine = {
executeRaw: async (sql: string) => {
if (/GROUP BY source_id/.test(sql)) throw missing;
return [];
},
} as unknown as PGLiteEngine;
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
const result = await runStatsCore(ctx);
expect(result.aggregate.total_pages).toBe(0);
expect(result.per_source).toEqual([]);
});
});
it('detectDeadPrefixes rethrows a non-missing-table error (sibling catch)', async () => {
await withEnv({ GBRAIN_HOME: tmpDir, GBRAIN_SCHEMA_PACK: 'tiny' }, async () => {
seedTinyPack('tiny', [{ name: 'person', prefix: 'people/' }]);
// fetchCountRows (the GROUP BY query) succeeds → []; the per-prefix
// dead-prefix LIKE query then throws a non-missing-table error, which
// must surface through the narrowed sibling catch.
const stubEngine = {
executeRaw: async (sql: string) => {
if (/GROUP BY source_id/.test(sql)) return []; // count query: empty brain, fine
throw Object.assign(new Error('division by zero'), { code: '22012' }); // the LIKE query
},
} as unknown as PGLiteEngine;
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
await expect(runStatsCore(ctx)).rejects.toThrow('division by zero');
});
});
});
describe('runStatsCore — type/untyped split', () => {
it('treats empty-string type as untyped (not its own bucket)', async () => {
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
+15
View File
@@ -12,9 +12,11 @@ import {
bestPath,
historyPath,
loadHistory,
proposedPath,
revertAllPending,
skillPath,
versionsDir,
writeProposed,
} from '../../src/core/skillopt/version-store.ts';
let tmpDir: string;
@@ -79,6 +81,19 @@ describe('acceptCandidate (D8 two-phase commit)', () => {
});
});
describe('writeProposed', () => {
test('writes distinct best and proposed artifacts without mutating SKILL.md (#2635)', () => {
const candidate = '---\nname: test\n---\nproposed body\n';
const written = writeProposed(tmpDir, SKILL, candidate);
expect(written).toBe(proposedPath(tmpDir, SKILL));
expect(fs.readFileSync(bestPath(tmpDir, SKILL), 'utf8')).toBe(candidate);
expect(fs.readFileSync(proposedPath(tmpDir, SKILL), 'utf8')).toBe(candidate);
expect(fs.readFileSync(skillPath(tmpDir, SKILL), 'utf8')).toContain('baseline body');
});
});
describe('revertAllPending (D8 crash recovery)', () => {
test('no-op when no pending rows', () => {
const reverted = revertAllPending(tmpDir, SKILL);