diff --git a/docs/tutorials/improving-skills-with-skillopt.md b/docs/tutorials/improving-skills-with-skillopt.md index 6c2a7fd53..009cac18d 100644 --- a/docs/tutorials/improving-skills-with-skillopt.md +++ b/docs/tutorials/improving-skills-with-skillopt.md @@ -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//skillopt/best.md` instead, so an optimization pass can never -silently mutate a skill other people depend on. Two ways to handle that: +`skills//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 \ diff --git a/src/core/skillopt/orchestrator.ts b/src/core/skillopt/orchestrator.ts index ffb858a83..99df6e1c4 100644 --- a/src/core/skillopt/orchestrator.ts +++ b/src/core/skillopt/orchestrator.ts @@ -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'; } diff --git a/src/core/skillopt/version-store.ts b/src/core/skillopt/version-store.ts index c723ccd10..ce2eef72a 100644 --- a/src/core/skillopt/version-store.ts +++ b/src/core/skillopt/version-store.ts @@ -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; } /** diff --git a/test/e2e/skillopt-loop.serial.test.ts b/test/e2e/skillopt-loop.serial.test.ts index 5b5038b3d..72cf6ae42 100644 --- a/test/e2e/skillopt-loop.serial.test.ts +++ b/test/e2e/skillopt-loop.serial.test.ts @@ -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'); diff --git a/test/skillopt/version-store.test.ts b/test/skillopt/version-store.test.ts index 736d52611..129aec849 100644 --- a/test/skillopt/version-store.test.ts +++ b/test/skillopt/version-store.test.ts @@ -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);