markitect-main/markitect/llm
tegwick 5ede1de4b8 fix(pipeline): retry on 0-entity response, save raw debug, improve template
- SourcePipeline: retry split_entities stage once when 0 entity delimiters
  are found (free-tier models intermittently return short non-formatted
  responses); save raw LLM response to <stage>-raw.md alongside prompts
- Return None (pause pipeline) rather than writing empty view file when
  no entities found after max retries
- _http.py: wrap json.JSONDecodeError in LLMAPIError with body preview
- extract-entities.md: add explicit H2-heading format example to Output
  Format section to prevent models from using inline "Section:" format

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-19 14:26:28 +01:00
..
__init__.py feat(llm): add embedding adapter with cache and similarity utils (S1.3) 2026-02-19 01:22:21 +01:00
_http.py fix(pipeline): retry on 0-entity response, save raw debug, improve template 2026-02-19 14:26:28 +01:00
_token_estimator.py feat(llm): add LLM integration module with OpenRouter and Claude Code adapters 2026-02-11 01:17:58 +01:00
claude_code.py feat(llm): add LLM integration module with OpenRouter and Claude Code adapters 2026-02-11 01:17:58 +01:00
config.py feat(llm): add LLM integration module with OpenRouter and Claude Code adapters 2026-02-11 01:17:58 +01:00
embedding_adapter.py feat(llm): add embedding adapter with cache and similarity utils (S1.3) 2026-02-19 01:22:21 +01:00
embedding_cache.py feat(llm): add embedding adapter with cache and similarity utils (S1.3) 2026-02-19 01:22:21 +01:00
embedding_factory.py feat(llm): add embedding adapter with cache and similarity utils (S1.3) 2026-02-19 01:22:21 +01:00
embedding_openai.py feat(llm): add embedding adapter with cache and similarity utils (S1.3) 2026-02-19 01:22:21 +01:00
exceptions.py feat(llm): add LLM integration module with OpenRouter and Claude Code adapters 2026-02-11 01:17:58 +01:00
factory.py feat(llm): add OpenAI adapter, entity archive policy, process chapters 5-7 2026-02-11 23:39:44 +01:00
gemini.py feat(llm): add Gemini adapter and process book-1-chapter-05 2026-02-11 22:54:37 +01:00
openai.py feat(llm): add OpenAI adapter, entity archive policy, process chapters 5-7 2026-02-11 23:39:44 +01:00
openrouter.py feat(llm): add LLM integration module with OpenRouter and Claude Code adapters 2026-02-11 01:17:58 +01:00
similarity.py feat(llm): add embedding adapter with cache and similarity utils (S1.3) 2026-02-19 01:22:21 +01:00
toml_config.py feat(llm): add llm-default and llm-preference commands, switch hardcoded default to gemini 2026-02-13 16:35:44 +01:00