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
11 changed files with 68 additions and 137 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 \
-12
View File
@@ -186,18 +186,6 @@ export function isSourceStale(src: SourceRow, now = Date.now(), floorMin = FULL_
return ageMin >= floorMin;
}
/**
* #2060: count sources past the per-source cycle freshness floor. Consumed
* by autopilot's dispatch decision — a stale source forces the fanout path
* even when the doctor plan is small (score 7094, plan ≤ 3, est < 300s),
* so targeted mode can't leave cycle_freshness stale indefinitely.
* dispatchPerSource's own throttles (skipped_fresh / fanoutMax / failure
* cooldown) bound the resulting work.
*/
export function countStaleSources(sources: SourceRow[], now = Date.now(), floorMin = FULL_CYCLE_FLOOR_MIN): number {
return sources.filter((s) => isSourceStale(s, now, floorMin)).length;
}
/**
* Most recent SUCCESSFUL cycle for a source. Prefers `last_source_cycle_at`
* (per-source phases, written by the split cycle) and falls back to the legacy
+2 -16
View File
@@ -901,27 +901,13 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
const FULL_CYCLE_FLOOR_MIN = 60;
const minutesSinceLastFull = (Date.now() - lastFullCycleAt) / 60000;
// #2060: stale per-source cycle freshness is a dispatch input. Without
// it, a brain sitting at score 7094 with a small targeted plan (≤3
// steps, <300s) stays in targeted mode indefinitely and no per-source
// cycle is ever dispatched — cycle_freshness never advances. A stale
// source forces the fanout path; dispatchPerSource's throttles
// (skipped_fresh / fanoutMax / failure cooldown) bound the work.
// Fail-open to 0: a read failure must not block dispatch.
let staleCycleSources = 0;
try {
const { countStaleSources } = await import('./autopilot-fanout.ts');
staleCycleSources = countStaleSources(await engine.listAllSources({ localPathOnly: true }));
} catch { /* fail-open: freshness is a dispatch hint, not a gate */ }
const shouldFullCycle =
(score >= 95 && plan.length === 0 && minutesSinceLastFull >= FULL_CYCLE_FLOOR_MIN) ||
plan.length > 3 ||
estTotal >= 300 ||
score < 70 ||
staleCycleSources > 0;
score < 70;
const shouldSleep = score >= 95 && plan.length === 0 && minutesSinceLastFull < FULL_CYCLE_FLOOR_MIN && staleCycleSources === 0;
const shouldSleep = score >= 95 && plan.length === 0 && minutesSinceLastFull < FULL_CYCLE_FLOOR_MIN;
if (shouldSleep) {
if (jsonMode) {
+10 -19
View File
@@ -854,10 +854,7 @@ interface SyncPhaseResult extends PhaseResult {
/**
* Resolve the source id for a brain directory by looking up the sources
* table. Returns undefined when no registered source matches (falls back
* to pre-v0.18 global config.sync.* keys) OR when MORE than one source
* claims the path — an ambiguous match must not scope phases or stamp
* last_full_cycle_at for an arbitrarily-picked source (the "freshness
* stamp that lies" this resolution exists to prevent).
* to pre-v0.18 global config.sync.* keys).
*/
async function resolveSourceForDir(
engine: BrainEngine,
@@ -868,10 +865,10 @@ async function resolveSourceForDir(
if (brainDir === null) return undefined;
try {
const rows = await engine.executeRaw<{ id: string }>(
`SELECT id FROM sources WHERE local_path = $1 LIMIT 2`,
`SELECT id FROM sources WHERE local_path = $1 LIMIT 1`,
[brainDir],
);
return rows.length === 1 ? rows[0]!.id : undefined;
return rows[0]?.id;
} catch {
// sources table might not exist on very old brains — fall through.
return undefined;
@@ -2368,23 +2365,17 @@ export async function runCycle(
}
// v0.38 (codex r1 P0-5): persist per-source cycle completion timestamp
// when the cycle ran successfully against a resolvable source. Read by
// autopilot's per-source freshness gate next tick.
//
// #1993: keyed off `cycleSourceId` (opts.sourceId ?? the source resolved
// from brainDir) — the SAME id the cycle locked + scoped its phases to —
// NOT raw opts.sourceId. The autopilot's inline cycle sets brainDir but
// passes no explicit sourceId, so keying off opts.sourceId alone never
// advanced last_full_cycle_at and cycle_freshness stayed stale even while
// the autopilot cycled every interval. Skipped when:
// - no source resolves (engine null, or no checkout AND no opts.sourceId)
// when the cycle ran successfully against an explicit source. Read by
// autopilot's per-source freshness gate next tick. Skipped when:
// - opts.sourceId is unset (legacy callers — autopilot still here)
// - engine is null (no-DB path)
// - status is 'failed' or 'skipped' (don't mark a non-run as fresh)
// - dryRun (writes are out of scope)
//
// Best-effort: a write failure does NOT change the CycleReport status.
// The cost of writing the wrong timestamp post-failure is higher than
// the cost of missing a successful write (next cycle will redo work).
if (cycleSourceId && engine && !dryRun && !aborted && (status === 'ok' || status === 'clean' || status === 'partial')) {
if (opts.sourceId && engine && !dryRun && !aborted && (status === 'ok' || status === 'clean' || status === 'partial')) {
try {
const nowIso = new Date().toISOString();
// #2194 fix #3 (the cycle split): `last_source_cycle_at` is the NEW gate
@@ -2394,13 +2385,13 @@ export async function runCycle(
// phases (those gate on autopilot.last_global_at), so writing it on a
// source-only cycle does not re-introduce the freshness poisoning codex
// flagged in the rejected skip-based design.
await engine.updateSourceConfig(cycleSourceId, {
await engine.updateSourceConfig(opts.sourceId, {
last_source_cycle_at: nowIso,
last_full_cycle_at: nowIso,
});
} catch (e) {
// Best-effort; cycle already succeeded by the time we get here.
console.warn(`[cycle] failed to write last_source_cycle_at for source ${cycleSourceId}: ${e instanceof Error ? e.message : String(e)}`);
console.warn(`[cycle] failed to write last_source_cycle_at for source ${opts.sourceId}: ${e instanceof Error ? e.message : String(e)}`);
}
}
+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;
}
/**
-14
View File
@@ -54,20 +54,6 @@ describe('autopilot.ts ↔ dispatchPerSource wiring', () => {
expect(AUTOPILOT_SRC).toMatch(/lastFullCycleAt\s*=\s*Date\.now\(\)/);
});
test('stale per-source cycle freshness is a shouldFullCycle input (#2060)', () => {
// Targeted mode (score 7094, plan ≤3, est <300s) must not be able to
// starve per-source cycle dispatch: a stale source (per countStaleSources
// over listAllSources) forces the fanout path, and the sleep gate must
// not fire while stale sources exist. Without these terms, cycle
// freshness never advances for a brain that always lands in targeted mode.
expect(AUTOPILOT_SRC).toMatch(/countStaleSources/);
const fullCycleDeclIdx = AUTOPILOT_SRC.indexOf('const shouldFullCycle');
expect(fullCycleDeclIdx).toBeGreaterThan(-1);
const decl = AUTOPILOT_SRC.slice(fullCycleDeclIdx, fullCycleDeclIdx + 700);
expect(decl).toMatch(/staleCycleSources\s*>\s*0/);
expect(decl).toMatch(/const shouldSleep[^;]*staleCycleSources\s*===\s*0/);
});
test('does NOT regress to the single-job dispatch on the full-cycle path', () => {
// Pre-PR: the shouldFullCycle branch did:
// const job = await queue.add('autopilot-cycle', { repoPath }, {
-18
View File
@@ -14,7 +14,6 @@ import { describe, test, expect } from 'bun:test';
import {
readLastFullCycleAt,
isSourceStale,
countStaleSources,
selectSourcesForDispatch,
resolveFanoutMax,
dispatchPerSource,
@@ -75,23 +74,6 @@ describe('isSourceStale', () => {
});
});
describe('countStaleSources (#2060 dispatch-decision input)', () => {
const NOW = Date.parse('2026-05-22T12:00:00.000Z');
test('counts never-cycled + past-floor sources, ignores fresh', () => {
const sources = [
src('never-cycled'), // stale (null)
src('old', new Date(NOW - 2 * 60 * 60_000).toISOString()), // stale (2h)
src('fresh', new Date(NOW - 30 * 60_000).toISOString()), // fresh (30min)
];
expect(countStaleSources(sources, NOW)).toBe(2);
});
test('returns 0 for all-fresh and for empty list', () => {
const fresh = src('a', new Date(NOW - 10 * 60_000).toISOString());
expect(countStaleSources([fresh], NOW)).toBe(0);
expect(countStaleSources([], NOW)).toBe(0);
});
});
describe('selectSourcesForDispatch', () => {
const NOW = Date.parse('2026-05-22T12:00:00.000Z');
const fresh = (id: string, agoMin: number) =>
+8 -38
View File
@@ -3,10 +3,8 @@
* cycles. Closes codex round-1 P0-5 (write site for last_full_cycle_at
* was unspecified pre-PR).
*
* Conditions for write (keyed off `cycleSourceId` = opts.sourceId ?? the
* source resolved from brainDir, so the autopilot's inline cycle — brainDir
* set, no explicit sourceId — also advances the timestamp, #1993):
* - a source resolves (explicit sourceId, or brainDir matches a source)
* Conditions for write:
* - opts.sourceId is set (legacy callers without sourceId skip the write)
* - engine is non-null (no-DB path skips)
* - status is 'ok' | 'clean' | 'partial' (failed/skipped don't mark fresh)
* - dryRun is false
@@ -92,45 +90,17 @@ describe('runCycle last_full_cycle_at exit hook', () => {
});
});
test('no explicit sourceId but brainDir resolves a source → writes the resolved source timestamp', async () => {
test('legacy caller (no sourceId) does NOT write any source timestamp', async () => {
await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
// The autopilot's inline cycle sets brainDir but passes no sourceId.
// runCycle resolves the source from brainDir (local_path match) into
// cycleSourceId and stamps last_full_cycle_at for it — otherwise
// cycle_freshness reports the brain stale even while the autopilot
// cycles every interval (#1993).
await seedSource('resolved-from-dir'); // local_path = brainDir
expect(await readLastFullCycleAt('resolved-from-dir')).toBeNull();
const t0 = Date.now();
const report = await runCycle(engine, {
brainDir,
phases: ['lint'],
});
expect(['ok', 'clean']).toContain(report.status);
const after = await readLastFullCycleAt('resolved-from-dir');
expect(after).not.toBeNull();
expect(new Date(after!).getTime()).toBeGreaterThanOrEqual(t0);
});
});
test('no sourceId and brainDir matches no source → does not write', async () => {
await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
// A source exists but its local_path does NOT match brainDir, so
// resolveSourceForDir returns undefined, cycleSourceId is undefined,
// and no per-source timestamp is written.
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config, archived, created_at)
VALUES ('unmatched', 'unmatched', '/no/such/repo', '{}'::jsonb, false, NOW())
ON CONFLICT (id) DO UPDATE SET local_path = EXCLUDED.local_path`,
[],
);
await seedSource('default-like');
// No sourceId passed; should remain untouched.
await runCycle(engine, {
brainDir,
phases: ['lint'],
});
expect(await readLastFullCycleAt('unmatched')).toBeNull();
// No per-source write happens; default source's config stays empty.
const after = await readLastFullCycleAt('default-like');
expect(after).toBeNull();
});
});
+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');
+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);