mirror of
https://github.com/val1813/kwcode.git
synced 2026-09-03 06:34:30 +08:00
核心思路:32B模型无法有效整合raw pytest输出,工程把反馈解析成 LLM最容易理解的形式(结构化诊断句),同时加入执行反馈内循环、 docstring注入、批次拆解等机制提升通过率。 9项改动: 1. generate_diagnosis() 结构化诊断句 2. _run_execution_feedback() 内循环 3. usage_finder.py 调用关系注入 4. _extract_docstrings() + _inject_docstrings() 5. _maybe_create_missing_module() LLM生成缺失模块 6. _run_whole_file_refactor() 批次拆解 7. _build_retry_hint() delta反馈 8. _clean_code_output() 格式清理(已覆盖) 9. _inject_skill_context() SKILL.md注入 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
12 lines
102 B
Plaintext
12 lines
102 B
Plaintext
__pycache__/
|
|
*.pyc
|
|
*.pyo
|
|
*.egg-info/
|
|
dist/
|
|
build/
|
|
.pytest_cache/
|
|
test_project/
|
|
.eggs/
|
|
.DS_Store
|
|
logs/
|