hai/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-05-14 00:13:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: reduce E2E test flakiness — pre-warm browse, simplify ship, accept multi-skill routing

Browse Source 
Browse E2E: pre-warm Chromium in beforeAll so agent doesn't waste turns on cold
startup. Reduce maxTurns 10→3. Add CI-aware MAX_START_WAIT (8s→30s when CI=true).

Ship E2E: simplify prompt from full /ship workflow to focused VERSION bump +
CHANGELOG + commit + push. Reduce maxTurns 15→8.

Routing E2E: accept multiple valid skills for ambiguous prompts.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-23 20:24:05 -07:00
parent 9dc04020a4
commit b0c7739c93
4 changed files with 18 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
test/skill-routing-e2e.test.ts
View File

@@ -270,7 +270,8 @@ describeE2E('Skill Routing E2E — Developer Journey', () => {
recordRouting(testName, result, expectedSkill, actualSkill);
expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
expect([expectedSkill], `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
const validSkills = ['plan-ceo-review', 'office-hours'];
expect(validSkills, `Expected one of ${validSkills.join('/')} but got ${actualSkill}`).toContain(actualSkill);
} finally {
fs.rmSync(tmpDir, { recursive: true, force: true });
}
@@ -327,7 +328,8 @@ export default app;
recordRouting(testName, result, expectedSkill, actualSkill);
expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
expect([expectedSkill], `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
const validSkills = ['investigate', 'qa'];
expect(validSkills, `Expected one of ${validSkills.join('/')} but got ${actualSkill}`).toContain(actualSkill);
} finally {
fs.rmSync(tmpDir, { recursive: true, force: true });
}
@@ -602,7 +604,8 @@ body { font-family: sans-serif; }
recordRouting(testName, result, expectedSkill, actualSkill);
expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
expect([expectedSkill], `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
const validSkills = ['design-review', 'qa', 'qa-only', 'browse'];
expect(validSkills, `Expected one of ${validSkills.join('/')} but got ${actualSkill}`).toContain(actualSkill);
} finally {
fs.rmSync(tmpDir, { recursive: true, force: true });
}