mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 09:52:22 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
78cc6d1e84 |
@@ -206,11 +206,7 @@ jobs:
|
||||
needs: cache-check
|
||||
if: needs.cache-check.outputs.hit != 'true'
|
||||
runs-on: ubuntu-latest
|
||||
# 20 (was 15): shard 4 runs ~14.5 min on master (dream.test.ts ~29s/test
|
||||
# dominates it) and hits the 15-min ceiling on slower runners, cancelling
|
||||
# mid-run with 0 test failures. Rebalancing via
|
||||
# scripts/mine-shard-weights.ts is the real fix; this stops the bleeding.
|
||||
timeout-minutes: 20
|
||||
timeout-minutes: 15
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
|
||||
@@ -20,6 +20,14 @@ export const CJK_SLUG_CHARS = '一-鿿-ゟ゠-ヿ가-';
|
||||
|
||||
export const CJK_RANGES_REGEX = new RegExp(`[${CJK_SLUG_CHARS}]`);
|
||||
|
||||
/**
|
||||
* Page-slug segment grammar (no anchors): alnum-or-CJK lead char, then
|
||||
* alnum/CJK/hyphen continuation. Single source for validatePageSlug
|
||||
* (operations.ts), SlugRegistry's SLUG_RE, and the dream-cycle
|
||||
* SUMMARY_SLUG_RE so every slug validator shares one grammar (#738).
|
||||
*/
|
||||
export const PAGE_SLUG_SEG = `[a-z0-9${CJK_SLUG_CHARS}][a-z0-9${CJK_SLUG_CHARS}\\-]*`;
|
||||
|
||||
export const CJK_SENTENCE_DELIMITERS = ['。', '!', '?']; // 。!?
|
||||
export const CJK_CLAUSE_DELIMITERS = [';', ':', ',', '、']; // ;:,、
|
||||
|
||||
|
||||
@@ -43,10 +43,11 @@ import { serializeMarkdown, serializePageToMarkdown } from '../markdown.ts';
|
||||
import type { Page, PageType } from '../types.ts';
|
||||
import { validateSourceId } from '../utils.ts';
|
||||
import { safeSplitIndex } from '../text-safe.ts';
|
||||
import { PAGE_SLUG_SEG } from '../cjk.ts';
|
||||
|
||||
// Slug regex from validatePageSlug — kept in sync.
|
||||
// Slug grammar from validatePageSlug — shared via PAGE_SLUG_SEG (#738).
|
||||
// Used for the orchestrator-written summary index slug.
|
||||
const SUMMARY_SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)*$/;
|
||||
const SUMMARY_SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`);
|
||||
|
||||
// ── Model context budget (D1, D5, D7, D9) ─────────────────────────────
|
||||
|
||||
|
||||
@@ -25,7 +25,7 @@ import { bumpLastRetrievedAt } from './last-retrieved.ts';
|
||||
import { isSearchMode } from './search/mode.ts';
|
||||
import { stampEvidence } from './search/evidence.ts';
|
||||
import type { SearchResult } from './types.ts';
|
||||
import { CJK_SLUG_CHARS } from './cjk.ts';
|
||||
import { CJK_SLUG_CHARS, PAGE_SLUG_SEG } from './cjk.ts';
|
||||
import * as db from './db.ts';
|
||||
import { VERSION } from '../version.ts';
|
||||
import {
|
||||
@@ -162,7 +162,6 @@ export function validatePageSlug(slug: string): void {
|
||||
}
|
||||
// v0.32.7: CJK ranges (Han / Hiragana / Katakana / Hangul Syllables) allowed
|
||||
// in segments. ASCII shape rules (lead char, hyphen continuation) preserved.
|
||||
const PAGE_SLUG_SEG = `[a-z0-9${CJK_SLUG_CHARS}][a-z0-9${CJK_SLUG_CHARS}\\-]*`;
|
||||
if (!new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`, 'i').test(slug)) {
|
||||
throw new OperationError('invalid_params', `Invalid page_slug: ${slug} (allowed: alphanumeric, CJK, hyphens, forward-slash separated segments)`);
|
||||
}
|
||||
|
||||
@@ -17,6 +17,7 @@
|
||||
|
||||
import type { BrainEngine } from '../engine.ts';
|
||||
import type { PageType } from '../types.ts';
|
||||
import { PAGE_SLUG_SEG } from '../cjk.ts';
|
||||
|
||||
export interface CreateSlugInput {
|
||||
/**
|
||||
@@ -71,7 +72,9 @@ export class SlugRegistryError extends Error {
|
||||
// SlugRegistry
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
const SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)+$/;
|
||||
// Shares the page-slug segment grammar (incl. CJK ranges, #738) with
|
||||
// validatePageSlug; keeps this site's dir/name shape (>= 2 segments).
|
||||
const SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})+$`);
|
||||
|
||||
export class SlugRegistry {
|
||||
constructor(private engine: BrainEngine) {}
|
||||
|
||||
@@ -23,15 +23,6 @@
|
||||
* hold conventions and shared rule files, not skills. Files like
|
||||
* `_brain-filing-rules.md` live at the root and are not considered
|
||||
* skills by either loader.
|
||||
*
|
||||
* ClawHub-installed workspace skills (#1767): a skill dir carrying
|
||||
* `.clawhub/origin.json` is an externally-managed runtime integration
|
||||
* (e.g. an email or catalog skill), not a gbrain-routable skill. The
|
||||
* derive path SKIPS those so `gbrain doctor` resolver_health doesn't
|
||||
* hard-fail on them — UNLESS the skill's SKILL.md frontmatter declares
|
||||
* `triggers:`, which is the explicit opt-in to gbrain routing (and the
|
||||
* same surface that makes it reachable). An explicit manifest.json that
|
||||
* lists a ClawHub skill also keeps strict checking (verbatim path).
|
||||
*/
|
||||
|
||||
import { existsSync, readFileSync, readdirSync, statSync } from 'fs';
|
||||
@@ -69,27 +60,9 @@ function parseSkillName(skillMdPath: string): string | null {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Does the SKILL.md frontmatter declare a `triggers:` key? A ClawHub-
|
||||
* installed skill that ships gbrain `triggers:` has explicitly opted in
|
||||
* to gbrain routing and gets full resolver checks (#1767).
|
||||
*/
|
||||
function declaresTriggers(skillMdPath: string): boolean {
|
||||
try {
|
||||
const content = readFileSync(skillMdPath, 'utf-8');
|
||||
const fmMatch = content.match(/^---\n([\s\S]*?)\n---/);
|
||||
if (!fmMatch) return false;
|
||||
return /^triggers:/m.test(fmMatch[1]);
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Walk skillsDir, return every `<skillsDir>/<dir>/SKILL.md` as a
|
||||
* ManifestEntry. Dotfile and underscore-prefixed dirs are skipped, as
|
||||
* are ClawHub-installed external skills that haven't opted in to gbrain
|
||||
* routing via `triggers:` frontmatter (#1767).
|
||||
* ManifestEntry. Dotfile and underscore-prefixed dirs are skipped.
|
||||
*/
|
||||
function deriveManifest(skillsDir: string): ManifestEntry[] {
|
||||
const out: ManifestEntry[] = [];
|
||||
@@ -120,12 +93,6 @@ function deriveManifest(skillsDir: string): ManifestEntry[] {
|
||||
const skillMd = join(subdirAbs, 'SKILL.md');
|
||||
if (!existsSync(skillMd)) continue;
|
||||
|
||||
// ClawHub-installed external skill (#1767): skip unless it opts in
|
||||
// to gbrain routing by declaring `triggers:` in its frontmatter.
|
||||
if (existsSync(join(subdirAbs, '.clawhub', 'origin.json')) && !declaresTriggers(skillMd)) {
|
||||
continue;
|
||||
}
|
||||
|
||||
const frontmatterName = parseSkillName(skillMd);
|
||||
const name = frontmatterName && frontmatterName !== '' ? frontmatterName : entry;
|
||||
out.push({ name, path: `${entry}/SKILL.md` });
|
||||
|
||||
@@ -382,35 +382,6 @@ describe("DRY detection — checkResolvable", () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe("#1767 — ClawHub workspace skills are not resolver-required", () => {
|
||||
let dir: string;
|
||||
afterEachCleanup(() => dir && rmSync(dir, { recursive: true, force: true }));
|
||||
|
||||
test("ClawHub skill without gbrain metadata produces no unreachable/mece_gap", () => {
|
||||
dir = mkdtempSync(join(tmpdir(), "gbrain-clawhub-"));
|
||||
// Native gbrain skill: routable via frontmatter triggers. No manifest.json
|
||||
// (the OpenClaw derive path from the issue repro).
|
||||
mkdirSync(join(dir, "query"), { recursive: true });
|
||||
writeFileSync(
|
||||
join(dir, "query", "SKILL.md"),
|
||||
`---\nname: query\ndescription: test\ntriggers:\n - "what do we know"\n---\n\n# query\n`
|
||||
);
|
||||
// ClawHub-installed integration: no triggers, no resolver row.
|
||||
mkdirSync(join(dir, "agentmail", ".clawhub"), { recursive: true });
|
||||
writeFileSync(
|
||||
join(dir, "agentmail", ".clawhub", "origin.json"),
|
||||
JSON.stringify({ registry: "https://clawhub.ai", slug: "agentmail" })
|
||||
);
|
||||
writeFileSync(join(dir, "agentmail", "SKILL.md"), `---\nname: agentmail\ndescription: email integration\n---\n\n# agentmail\n`);
|
||||
|
||||
const report = checkResolvable(dir);
|
||||
const agentmailIssues = report.issues.filter(i => i.skill === "agentmail");
|
||||
expect(agentmailIssues).toEqual([]);
|
||||
expect(report.ok).toBe(true);
|
||||
expect(report.summary.total_skills).toBe(1);
|
||||
});
|
||||
});
|
||||
|
||||
describe("v0.22.4 regression — actual repo skills/ has 0 errors", () => {
|
||||
test("repo skills/ pass check-resolvable cleanly (zero errors AND zero warnings)", () => {
|
||||
// The v0.22.4 (Part A) contract was zero warnings AND zero errors.
|
||||
|
||||
@@ -86,6 +86,12 @@ describe('#2415: loadOutputRoot validation + patterns gather scope', () => {
|
||||
expect(await loadOutputRoot(engine)).toBe('wiki');
|
||||
});
|
||||
|
||||
test('CJK root passes the slug grammar (#738)', async () => {
|
||||
await engine.setConfig('dream.synthesize.output_root', '知识/笔记');
|
||||
expect(await loadOutputRoot(engine)).toBe('知识/笔记');
|
||||
await engine.setConfig('dream.synthesize.output_root', '');
|
||||
});
|
||||
|
||||
test('patterns phase gathers reflections under the configured root', async () => {
|
||||
await engine.setConfig('dream.synthesize.output_root', 'notes');
|
||||
for (let i = 0; i < 3; i++) {
|
||||
|
||||
@@ -166,55 +166,6 @@ describe('loadOrDeriveManifest', () => {
|
||||
expect(r.skills.map(s => s.name)).toEqual(['apple', 'mango', 'zebra']);
|
||||
});
|
||||
|
||||
// #1767 — ClawHub-installed workspace skills are external integrations,
|
||||
// not gbrain-routable skills. The derive path skips them unless they
|
||||
// opt in via `triggers:` frontmatter.
|
||||
it('skips ClawHub-origin skills without triggers frontmatter (#1767)', () => {
|
||||
const dir = scratch();
|
||||
writeSkill(dir, 'query', 'query');
|
||||
writeSkill(dir, 'agentmail', 'agentmail');
|
||||
mkdirSync(join(dir, 'agentmail', '.clawhub'), { recursive: true });
|
||||
writeFileSync(
|
||||
join(dir, 'agentmail', '.clawhub', 'origin.json'),
|
||||
JSON.stringify({ registry: 'https://clawhub.ai', slug: 'agentmail' })
|
||||
);
|
||||
const r = loadOrDeriveManifest(dir);
|
||||
expect(r.derived).toBe(true);
|
||||
expect(r.skills.map(s => s.name)).toEqual(['query']);
|
||||
});
|
||||
|
||||
it('includes ClawHub-origin skills that opt in via triggers frontmatter (#1767)', () => {
|
||||
const dir = scratch();
|
||||
writeSkill(dir, 'agentmail', 'agentmail');
|
||||
mkdirSync(join(dir, 'agentmail', '.clawhub'), { recursive: true });
|
||||
writeFileSync(
|
||||
join(dir, 'agentmail', '.clawhub', 'origin.json'),
|
||||
JSON.stringify({ registry: 'https://clawhub.ai', slug: 'agentmail' })
|
||||
);
|
||||
writeFileSync(
|
||||
join(dir, 'agentmail', 'SKILL.md'),
|
||||
`---\nname: agentmail\ndescription: test\ntriggers:\n - "send email"\n---\n\n# agentmail\n`
|
||||
);
|
||||
const r = loadOrDeriveManifest(dir);
|
||||
expect(r.derived).toBe(true);
|
||||
expect(r.skills.map(s => s.name)).toEqual(['agentmail']);
|
||||
});
|
||||
|
||||
it('keeps ClawHub-origin skills listed in an explicit manifest.json (#1767)', () => {
|
||||
// Explicit manifest.json is a deliberate declaration — strict checking stays.
|
||||
const dir = scratch();
|
||||
writeSkill(dir, 'agentmail', 'agentmail');
|
||||
mkdirSync(join(dir, 'agentmail', '.clawhub'), { recursive: true });
|
||||
writeFileSync(
|
||||
join(dir, 'agentmail', '.clawhub', 'origin.json'),
|
||||
JSON.stringify({ registry: 'https://clawhub.ai', slug: 'agentmail' })
|
||||
);
|
||||
writeManifest(dir, { skills: [{ name: 'agentmail', path: 'agentmail/SKILL.md' }] });
|
||||
const r = loadOrDeriveManifest(dir);
|
||||
expect(r.derived).toBe(false);
|
||||
expect(r.skills.map(s => s.name)).toEqual(['agentmail']);
|
||||
});
|
||||
|
||||
it('treats dirs without SKILL.md as not-a-skill', () => {
|
||||
const dir = scratch();
|
||||
writeSkill(dir, 'query', 'query');
|
||||
|
||||
@@ -203,6 +203,17 @@ describe('SlugRegistry', () => {
|
||||
})).rejects.toThrow(SlugRegistryError);
|
||||
});
|
||||
|
||||
test('create accepts CJK slugs (#738)', async () => {
|
||||
const reg = new SlugRegistry(engine);
|
||||
const r = await reg.create({
|
||||
desiredSlug: '知识/品牌圣经',
|
||||
displayName: '品牌圣经',
|
||||
type: 'note',
|
||||
});
|
||||
expect(r.slug).toBe('知识/品牌圣经');
|
||||
expect(r.exact).toBe(true);
|
||||
});
|
||||
|
||||
test('create throws on invalid slug', async () => {
|
||||
const reg = new SlugRegistry(engine);
|
||||
await expect(reg.create({
|
||||
|
||||
Reference in New Issue
Block a user