mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-07 05:56:41 +02:00
test: add e2e and LLM eval tests for SKILL.md setup block
- 3 Agent SDK e2e tests: happy path, NEEDS_SETUP, non-git-repo - LLM eval: setup block clarity + actionability >= 4 - New error pattern: 'no such file or directory.*browse' These tests catch the exact failure mode where agents can't discover the browse binary via SKILL.md instructions.
This commit is contained in:
@@ -23,6 +23,7 @@ const BROWSE_ERROR_PATTERNS = [
|
||||
/Exit code 1/,
|
||||
/ERROR: browse binary not found/,
|
||||
/Server failed to start/,
|
||||
/no such file or directory.*browse/i,
|
||||
];
|
||||
|
||||
export async function runSkillTest(options: {
|
||||
|
||||
Reference in New Issue
Block a user