Claude b122a55657 Address review: keep goals on failure, coerce model list fields ...

- explore dequeues its goal only after the engine call succeeds
- model-supplied list fields go through as_list/str_list, so null or
  string values can't crash a run or turn into per-character tests
- run_ab_eval rejects blank problems before any model call and
  randomizes baseline/treated solver call order
- middleware merges into a leading system message with block content

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YbuVfbQEpaitM5TMjBMzkF

2026-10-23 16:15:50 +00:00

..

__init__.py

Rebuild MuseEngine as an LLM-backed, governed, tested package

2026-10-23 16:03:12 +00:00

conftest.py

Rebuild MuseEngine as an LLM-backed, governed, tested package

2026-10-23 16:03:12 +00:00

test_agent_and_eval.py

Address review: keep goals on failure, coerce model list fields

2026-10-23 16:15:50 +00:00

test_engine.py

Address review: keep goals on failure, coerce model list fields

2026-10-23 16:15:50 +00:00