lda
Verified
10dabca241
feat: add opencode browser click challenge harness
- Challenge prompt requiring workflow/deployment/run evidence
- CLI harness (run_opencode_trials.py) for running N agent trials
- Classification: success, workflow_not_used, run_failed, timeout, parse_error, unknown
- 8 unit tests covering build/parse/classify/path logic
- README with usage docs and optional Playwright MCP attachment
- Evidence index and roadmap updated
- Plan archived to historical/
History
..
2026-06-15 02:32:54 +07:00
2026-06-15 00:36:34 +07:00
2026-06-14 18:19:45 +07:00
2026-05-08 21:55:33 +07:00
2026-05-23 22:07:05 +07:00
2026-05-21 06:16:58 +07:00
2026-05-25 15:48:39 +07:00
2026-05-25 15:48:39 +07:00
2026-06-06 15:01:39 +07:00
2026-05-21 14:31:52 +07:00
2026-06-06 15:01:39 +07:00
2026-06-14 00:16:56 +07:00
2026-06-06 15:01:39 +07:00
2026-06-12 09:07:05 +07:00
2026-05-22 00:58:53 +07:00
2026-05-23 22:07:05 +07:00
2026-06-09 17:49:27 +07:00
2026-05-21 06:16:58 +07:00
2026-05-19 03:13:46 +07:00