mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 09:52:22 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
06eeb2890b |
@@ -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 \
|
||||
|
||||
-64
@@ -24,7 +24,6 @@ import type { GBrainConfig } from './core/config.ts';
|
||||
import type { AIGatewayConfig } from './core/ai/types.ts';
|
||||
import type { BrainEngine } from './core/engine.ts';
|
||||
import { operations, OperationError } from './core/operations.ts';
|
||||
import { resolveSourceIdEngineFree } from './core/source-resolver.ts';
|
||||
import { formatVolunteeredPage } from './core/context/volunteer.ts';
|
||||
import type { Operation, OperationContext } from './core/operations.ts';
|
||||
import { shouldForceExitAfterMain, finishCliTeardown, flushThenExit, currentExitCode, setCliExitVerdict } from './core/cli-force-exit.ts';
|
||||
@@ -383,15 +382,6 @@ async function main() {
|
||||
if (op.localOnly) {
|
||||
refuseThinClient(command, cfgPre!.remote_mcp!.mcp_url);
|
||||
}
|
||||
// #2098: the local path resolves --source / GBRAIN_SOURCE / .gbrain-source
|
||||
// inside makeContext (ctx.sourceId), which this route never reaches — so
|
||||
// scope must be mapped onto the op's source_id wire param before the call.
|
||||
try {
|
||||
applyThinClientSourceScope(op, params);
|
||||
} catch (e: unknown) {
|
||||
console.error(e instanceof Error ? e.message : String(e));
|
||||
process.exit(1);
|
||||
}
|
||||
await runThinClientRouted(op, params, cfgPre!, cliOpts);
|
||||
return;
|
||||
}
|
||||
@@ -812,60 +802,6 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
|
||||
return params;
|
||||
}
|
||||
|
||||
/**
|
||||
* #2098: thin-client source scoping. Locally, --source / GBRAIN_SOURCE /
|
||||
* .gbrain-source resolve to ctx.sourceId in makeContext; the thin-client
|
||||
* route short-circuits before that, so `gbrain query --source X` against a
|
||||
* remote brain silently searched unscoped. This runs the engine-free tiers
|
||||
* (flag → env → dotfile; the DB-backed tiers can't run without an engine —
|
||||
* the server's grant scoping covers the rest) and maps the result onto the
|
||||
* op's `source_id` wire param.
|
||||
*
|
||||
* Ops that declare their OWN `source` param (facts add, etc.) are left
|
||||
* untouched — their --source is an op param, not scope. An explicit --source
|
||||
* on an op with no source_id wire param throws (loud beats silent drop);
|
||||
* ambient env/dotfile scope with nowhere to send it is ignored, matching the
|
||||
* pre-fix behavior for non-scopeable ops. Exported for tests.
|
||||
*/
|
||||
// Ops whose `source_id` wire param is NOT read-scope semantics: get_skill's
|
||||
// source_id flips the lookup from host catalog to brain-resident-pack
|
||||
// (getResidentSkillDetail). Ambient env/dotfile scope must never leak into
|
||||
// these; an explicit --source-id still passes through untouched above.
|
||||
const NON_SCOPE_SOURCE_ID_OPS = new Set(['get_skill']);
|
||||
|
||||
export function applyThinClientSourceScope(
|
||||
op: Operation,
|
||||
params: Record<string, unknown>,
|
||||
cwd?: string,
|
||||
): void {
|
||||
if ('source' in op.params) return; // the op owns --source; not a scope flag
|
||||
const explicit = typeof params.source === 'string' && params.source.length > 0
|
||||
? (params.source as string)
|
||||
: null;
|
||||
delete params.source; // never a wire param on these ops — don't leak it
|
||||
// Explicit per-call scope already on the wire wins over ambient tiers.
|
||||
if (params.source_id !== undefined || params.all_sources === true) {
|
||||
if (explicit) {
|
||||
throw new Error('Pass either --source or --source-id/--all-sources, not both.');
|
||||
}
|
||||
return;
|
||||
}
|
||||
const resolved = resolveSourceIdEngineFree(explicit, cwd);
|
||||
if (!resolved) return;
|
||||
if (!('source_id' in op.params) || NON_SCOPE_SOURCE_ID_OPS.has(op.name)) {
|
||||
if (explicit) {
|
||||
const hint = NON_SCOPE_SOURCE_ID_OPS.has(op.name)
|
||||
? `(its source_id parameter is not a scope filter; pass --source-id explicitly if you mean it)`
|
||||
: `(the remote op has no source_id parameter; the server scopes it to your grant)`;
|
||||
throw new Error(
|
||||
`gbrain ${op.cliHints?.name || op.name} does not accept --source on a thin-client install ${hint}.`,
|
||||
);
|
||||
}
|
||||
return; // ambient env/dotfile scope with nowhere to send it
|
||||
}
|
||||
params.source_id = resolved;
|
||||
}
|
||||
|
||||
async function makeContext(engine: BrainEngine, params: Record<string, unknown>): Promise<OperationContext> {
|
||||
// v0.31.8 (D11): resolve sourceId via the canonical 6-tier chain. Honors
|
||||
// --source / GBRAIN_SOURCE / .gbrain-source / path-match / brain default /
|
||||
|
||||
@@ -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';
|
||||
}
|
||||
|
||||
@@ -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;
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -160,33 +160,6 @@ export async function resolveSourceId(
|
||||
return 'default';
|
||||
}
|
||||
|
||||
/**
|
||||
* Engine-free tiers (1-3) of the resolution chain: explicit flag →
|
||||
* GBRAIN_SOURCE env → .gbrain-source dotfile walk. Used by the thin-client
|
||||
* CLI path (#2098), which has no local engine to run tiers 4-6 or
|
||||
* assertSourceExists against — the remote server enforces existence + grant.
|
||||
* Returns null when no engine-free tier fires.
|
||||
*/
|
||||
export function resolveSourceIdEngineFree(
|
||||
explicit: string | null | undefined,
|
||||
cwd: string = process.cwd(),
|
||||
): string | null {
|
||||
if (explicit) {
|
||||
if (!SOURCE_ID_RE.test(explicit)) {
|
||||
throw new Error(`Invalid --source value "${explicit}". Must match [a-z0-9-]{1,32}.`);
|
||||
}
|
||||
return explicit;
|
||||
}
|
||||
const env = process.env.GBRAIN_SOURCE;
|
||||
if (env && env.length > 0) {
|
||||
if (!SOURCE_ID_RE.test(env)) {
|
||||
throw new Error(`Invalid GBRAIN_SOURCE value "${env}". Must match [a-z0-9-]{1,32}.`);
|
||||
}
|
||||
return env;
|
||||
}
|
||||
return readDotfileWalk(cwd);
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the id of the SINGLE registered non-default source with a
|
||||
* local_path, when exactly one such row exists. Returns null when:
|
||||
|
||||
@@ -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');
|
||||
|
||||
@@ -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);
|
||||
|
||||
@@ -1,142 +0,0 @@
|
||||
/**
|
||||
* #2098: thin-client routing dropped --source / GBRAIN_SOURCE / .gbrain-source.
|
||||
*
|
||||
* The local CLI path resolves source scope in makeContext (ctx.sourceId); the
|
||||
* thin-client route short-circuits before that and sent params verbatim, so
|
||||
* `gbrain query --source X` against a remote brain silently searched unscoped
|
||||
* (the server op ignores the unknown `source` key).
|
||||
*
|
||||
* applyThinClientSourceScope runs the engine-free tiers (flag → env → dotfile)
|
||||
* and maps the result onto the op's `source_id` wire param. These tests fail
|
||||
* without the fix (params.source_id stays undefined / params.source leaks).
|
||||
*/
|
||||
|
||||
import { describe, test, expect } from 'bun:test';
|
||||
import { mkdtempSync, rmSync, writeFileSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
import { tmpdir } from 'os';
|
||||
import { applyThinClientSourceScope, parseOpArgs } from '../src/cli.ts';
|
||||
import { operationsByName } from '../src/core/operations.ts';
|
||||
import { withEnv } from './helpers/with-env.ts';
|
||||
|
||||
const queryOp = operationsByName.query;
|
||||
|
||||
describe('applyThinClientSourceScope (#2098)', () => {
|
||||
test('--source maps onto the query op wire param source_id', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const params = parseOpArgs(queryOp, ['find things', '--source', 'wiki']);
|
||||
expect(params.source).toBe('wiki'); // pre-fix state: wrong key
|
||||
applyThinClientSourceScope(queryOp, params, '/');
|
||||
expect(params.source_id).toBe('wiki');
|
||||
expect('source' in params).toBe(false); // never leaks the unknown key
|
||||
});
|
||||
});
|
||||
|
||||
test('GBRAIN_SOURCE env tier fires when no flag is passed', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
|
||||
const params = parseOpArgs(queryOp, ['find things']);
|
||||
applyThinClientSourceScope(queryOp, params, '/');
|
||||
expect(params.source_id).toBe('gstack');
|
||||
});
|
||||
});
|
||||
|
||||
test('.gbrain-source dotfile tier fires when flag and env are absent', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const tmp = mkdtempSync(join(tmpdir(), 'gbrain-thin-scope-'));
|
||||
try {
|
||||
writeFileSync(join(tmp, '.gbrain-source'), 'essays\n');
|
||||
const params = parseOpArgs(queryOp, ['find things']);
|
||||
applyThinClientSourceScope(queryOp, params, tmp);
|
||||
expect(params.source_id).toBe('essays');
|
||||
} finally {
|
||||
rmSync(tmp, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
test('explicit --source-id on the wire wins over ambient env scope', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
|
||||
const params = parseOpArgs(queryOp, ['find things', '--source-id', 'wiki']);
|
||||
applyThinClientSourceScope(queryOp, params, '/');
|
||||
expect(params.source_id).toBe('wiki');
|
||||
});
|
||||
});
|
||||
|
||||
test('--source together with --source-id is rejected loudly', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const params = parseOpArgs(queryOp, ['q', '--source', 'a', '--source-id', 'b']);
|
||||
expect(() => applyThinClientSourceScope(queryOp, params, '/')).toThrow(/not both/);
|
||||
});
|
||||
});
|
||||
|
||||
test('invalid --source value is rejected loudly', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const params = parseOpArgs(queryOp, ['q', '--source', 'Bad_Value!']);
|
||||
expect(() => applyThinClientSourceScope(queryOp, params, '/')).toThrow(/Invalid --source/);
|
||||
});
|
||||
});
|
||||
|
||||
test('--source on an op with no source_id wire param errors instead of silently dropping', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const op = operationsByName.add_tag;
|
||||
expect('source_id' in op.params).toBe(false);
|
||||
const params = { slug: 'x', tag: 'y', source: 'wiki' };
|
||||
expect(() => applyThinClientSourceScope(op, params, '/')).toThrow(/--source/);
|
||||
});
|
||||
});
|
||||
|
||||
test('ambient env scope on an op with no source_id wire param is ignored (no throw)', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: 'wiki' }, () => {
|
||||
const op = operationsByName.add_tag;
|
||||
const params: Record<string, unknown> = { slug: 'x', tag: 'y' };
|
||||
applyThinClientSourceScope(op, params, '/');
|
||||
expect(params.source_id).toBeUndefined();
|
||||
});
|
||||
});
|
||||
|
||||
test('ops that declare their OWN source param are left untouched', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const op = operationsByName.put_raw_data;
|
||||
expect('source' in op.params).toBe(true);
|
||||
const params: Record<string, unknown> = { slug: 'x', source: 'crustdata', data: {} };
|
||||
applyThinClientSourceScope(op, params, '/');
|
||||
expect(params.source).toBe('crustdata');
|
||||
expect(params.source_id).toBeUndefined();
|
||||
});
|
||||
});
|
||||
|
||||
test('get_skill: ambient scope never leaks into its non-scope source_id param', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: 'wiki' }, () => {
|
||||
const op = operationsByName.get_skill;
|
||||
expect('source_id' in op.params).toBe(true); // has the param, but it is a mode switch
|
||||
const params: Record<string, unknown> = { name: 'ingest' };
|
||||
applyThinClientSourceScope(op, params, '/');
|
||||
expect(params.source_id).toBeUndefined(); // would flip host catalog → brain-pack lookup
|
||||
});
|
||||
});
|
||||
|
||||
test('get_skill: explicit --source errors instead of masquerading as --source-id', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const op = operationsByName.get_skill;
|
||||
const params: Record<string, unknown> = { name: 'ingest', source: 'wiki' };
|
||||
expect(() => applyThinClientSourceScope(op, params, '/')).toThrow(/--source-id/);
|
||||
});
|
||||
});
|
||||
|
||||
test('get_skill: explicit --source-id passes through untouched', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
|
||||
const op = operationsByName.get_skill;
|
||||
const params: Record<string, unknown> = { name: 'ingest', source_id: 'wiki' };
|
||||
applyThinClientSourceScope(op, params, '/');
|
||||
expect(params.source_id).toBe('wiki');
|
||||
});
|
||||
});
|
||||
|
||||
test('no scope from any tier leaves params unchanged', async () => {
|
||||
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
|
||||
const params = parseOpArgs(queryOp, ['find things']);
|
||||
applyThinClientSourceScope(queryOp, params, '/');
|
||||
expect(params.source_id).toBeUndefined();
|
||||
});
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user