mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-14 00:13:05 +08:00
1a4f0c9c15
* fix(learnings): use token-OR matching in gstack-learnings-search --query
Split the query on whitespace into tokens; a learning matches if ANY
token appears as a substring in ANY of key/insight/files. Previously
the whole query was a single substring, so multi-word queries like
"debug investigation" only matched learnings whose insight contained
that exact contiguous phrase, which is usually nothing.
Whitespace-only query falls through to no-query (matches today's no-flag
behavior). Single-word queries behave exactly as before.
Adds test/gstack-learnings-search.test.ts: 3 assertions covering
multi-token, single-token, and no-query backwards compat.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(resolver): parameterized LEARNINGS_SEARCH with shell-injection guard
The {{LEARNINGS_SEARCH}} macro now accepts a query=KEYWORD argument that
gets interpolated as --query "<keyword>" into the generated bash. Empty
value falls through to no-query (principle of least surprise: a stray
{{LEARNINGS_SEARCH:query=}} placeholder gets today's behavior, not a
build failure). Pattern reuses the parameterized-macro parsing from
composition.ts. The 13 templates that don't pass a query stay
byte-identical in their generated SKILL.md output.
Shell-injection guard: the query value is whitelisted to
^[A-Za-z0-9 _-]+$ at gen-skill-docs time. Any \$(), backticks,
semicolons, or quotes throw a loud build error instead of emitting
executable bash. Static template queries are safe by inspection;
this defends against future contributors writing dangerous values.
Adds 5 assertions to test/gen-skill-docs.test.ts covering no-args,
claude+query=foo bar on both cross-project and project-scoped branches,
codex host variant, empty value semantics, and shell-injection payloads
(\$(whoami), backticks, ;, &, ", \\, \$x) throwing build errors.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(skills): task-shaped queries + mid-flow refresh in /investigate /qa /ship
The three long skills now pull learnings keyed to their theme at the
top, then re-pull at phase boundaries as work shifts to new sub-tasks.
Top-of-skill queries (5-6 token unions, token-OR matched):
- investigate: "debug investigation root cause hypothesis bug fix"
- qa: "qa testing bug regression flake fixture"
- ship: "release ship version changelog merge pr"
Mid-flow refresh blocks (concrete keyword recipe + worked examples):
- investigate: between Phase 1 (hypothesis) and Phase 2 (analysis),
keyed to the hypothesis noun. Examples: auth-cookie, session-expiry.
- qa: between Phase 7 (triage) and Phase 8 (fix loop), keyed to the
buggy component name. Examples: checkout-button, signup-form.
- ship: just before Step 12 (VERSION bump), keyed to the headline
feature. Examples: learnings-search, pacing, worktree-ship.
Keyword recipe enforces alphanumeric+hyphen only (no quotes, slashes,
dots, colons) so dynamic queries cannot inject shell metacharacters.
The other 13 short-lived skills keep the bare {{LEARNINGS_SEARCH}} form.
Backwards-compat verified via diff: their generated SKILL.md output is
byte-identical to before this change.
Golden ship fixtures regenerated to match the new ship/SKILL.md output.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* chore: bump version and changelog (v1.33.1.0)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* test: refresh codex+factory ship golden fixtures
Follow-up to 513c9660 — the codex and factory host outputs needed
regeneration too, missed in the initial commit because gen:skill-docs
was only run for the claude host. Now matches gen:skill-docs --host all.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
61 lines
2.5 KiB
TypeScript
61 lines
2.5 KiB
TypeScript
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
import * as os from 'os';
|
|
import { execFileSync } from 'child_process';
|
|
|
|
const ROOT = path.resolve(import.meta.dir, '..');
|
|
const BIN = path.join(ROOT, 'bin', 'gstack-learnings-search');
|
|
|
|
const tmpHome = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-search-test-'));
|
|
const tmpCwd = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-search-cwd-'));
|
|
// gstack-slug derives slug from git remote (none here) → falls back to basename of cwd.
|
|
const slug = path.basename(tmpCwd).replace(/[^a-zA-Z0-9._-]/g, '');
|
|
const projDir = path.join(tmpHome, 'projects', slug);
|
|
|
|
function run(args: string[]): string {
|
|
return execFileSync(BIN, args, {
|
|
env: { ...process.env, GSTACK_HOME: tmpHome },
|
|
cwd: tmpCwd,
|
|
encoding: 'utf-8',
|
|
});
|
|
}
|
|
|
|
beforeAll(() => {
|
|
fs.mkdirSync(projDir, { recursive: true });
|
|
const entries = [
|
|
{ ts: '2026-05-01T00:00:00Z', skill: 'test', type: 'pattern', key: 'foo-pattern', insight: 'A foo-related insight', confidence: 8, source: 'observed', files: [] },
|
|
{ ts: '2026-05-02T00:00:00Z', skill: 'test', type: 'pitfall', key: 'bar-pitfall', insight: 'A bar-related insight', confidence: 8, source: 'observed', files: [] },
|
|
{ ts: '2026-05-03T00:00:00Z', skill: 'test', type: 'pattern', key: 'baz-pattern', insight: 'A baz-related insight', confidence: 8, source: 'observed', files: [] },
|
|
];
|
|
fs.writeFileSync(path.join(projDir, 'learnings.jsonl'), entries.map(e => JSON.stringify(e)).join('\n') + '\n');
|
|
});
|
|
|
|
afterAll(() => {
|
|
fs.rmSync(tmpHome, { recursive: true, force: true });
|
|
fs.rmSync(tmpCwd, { recursive: true, force: true });
|
|
});
|
|
|
|
describe('gstack-learnings-search token-OR query semantics', () => {
|
|
test('multi-token query returns entries matching ANY token', () => {
|
|
const out = run(['--query', 'foo bar']);
|
|
expect(out).toContain('foo-pattern');
|
|
expect(out).toContain('bar-pitfall');
|
|
expect(out).not.toContain('baz-pattern');
|
|
});
|
|
|
|
test('single-token query returns only entries matching that token', () => {
|
|
const out = run(['--query', 'foo']);
|
|
expect(out).toContain('foo-pattern');
|
|
expect(out).not.toContain('bar-pitfall');
|
|
expect(out).not.toContain('baz-pattern');
|
|
});
|
|
|
|
test('no --query flag returns all entries (backwards-compat)', () => {
|
|
const out = run(['--limit', '10']);
|
|
expect(out).toContain('foo-pattern');
|
|
expect(out).toContain('bar-pitfall');
|
|
expect(out).toContain('baz-pattern');
|
|
});
|
|
});
|