Research-Stack/5-Applications/tools-scripts/llm
allaun 551df86e1d fix(lharness): Improve proof extraction to handle LLM response formatting variations
- Extract markdown code blocks first, fallback to manual stripping
- Handle multiple 'by' keyword case variations (:= by, by line starts, etc.)
- Avoid duplicate 'by by' syntax errors on insertion
- Strip trailing whitespace in proof positions
2026-06-27 14:46:56 -05:00
..
deepseek_review_adapter.py initial: sovereign research stack (consolidated, weightless, and lfs-optimized) 2026-05-04 18:11:36 -05:00
deepseek_v4_flash_lean_harness.py fix(lharness): Improve proof extraction to handle LLM response formatting variations 2026-06-27 14:46:56 -05:00
ollama_deepseek_review_emitter.py chore(repo): push local 768-commit branch state onto clean remote baseline 2026-06-15 22:46:50 -05:00
test_emitter_utils.py test(coverage): add 138 unit tests for least-covered modules (#78) 2026-06-14 19:31:16 -05:00
test_ollama_deepseek_review_emitter.py Add verified Ollama DeepSeek review emitter 2026-05-11 23:13:54 -05:00