xpltdco/chrysopedia
2
0
Fork 0
Code Issues 2 Pull requests Projects Releases Packages Wiki Activity Actions
chrysopedia/backend/pipeline
History
Exact
jlightner 96491ac70a fix: LLM config, task time limits, base_url, fallback model, debug Redis caching 
- Add BASE_URL setting to config.py, replace hardcoded localhost:8096 in notifications
- Fix LLM_FALLBACK_MODEL default from fyn-llm-agent-chat to qwen2.5:7b
- Fix docker-compose LLM_FALLBACK_MODEL to use env var with correct default
- Add BASE_URL env var to API and worker in docker-compose.yml
- Add soft_time_limit/time_limit to all pipeline stage tasks (prevent stuck workers)
- Cache Redis connection in _is_debug_mode() instead of creating per-call
- Remove duplicate test files in backend/tests/notifications/
2026-04-05 06:01:54 +00:00
..
quality feat: Ran manual chat evaluation against live endpoint, documented qual… 2026-04-04 14:50:44 +00:00
__init__.py fix: restore complete project tree from ub01 canonical state 2026-03-31 02:10:41 +00:00
caption_generator.py feat: Created ASS subtitle generator with karaoke word-by-word highligh… 2026-04-04 11:12:19 +00:00
card_renderer.py feat: Built ffmpeg-based card renderer with concat demuxer pipeline and… 2026-04-04 11:17:38 +00:00
citation_utils.py test: Added BodySection/BodySubSection schema models, changed Synthesiz… 2026-04-03 00:50:30 +00:00
embedding_client.py fix: restore complete project tree from ub01 canonical state 2026-03-31 02:10:41 +00:00
export_fixture.py feat: add pipeline iteration tooling — offline test harness, stage re-runs, chunking inspector 2026-04-02 15:47:46 +00:00
highlight_schemas.py test: Added 3 audio proxy scoring functions, extract_word_timings utili… 2026-04-04 08:05:22 +00:00
highlight_scorer.py test: Added 3 audio proxy scoring functions, extract_word_timings utili… 2026-04-04 08:05:22 +00:00
llm_client.py fix: static 96k max_tokens for all pipeline stages — dynamic estimator was truncating thinking model output 2026-04-03 08:18:28 +00:00
qdrant_client.py feat: Added LightRAG /query/data as primary search engine with file_sou… 2026-04-04 04:44:24 +00:00
schemas.py test: Added BodySection/BodySubSection schema models, changed Synthesiz… 2026-04-03 00:50:30 +00:00
shorts_generator.py feat: Built ffmpeg-based card renderer with concat demuxer pipeline and… 2026-04-04 11:17:38 +00:00
stages.py fix: LLM config, task time limits, base_url, fallback model, debug Redis caching 2026-04-05 06:01:54 +00:00
test_caption_generator.py feat: Created ASS subtitle generator with karaoke word-by-word highligh… 2026-04-04 11:12:19 +00:00
test_card_renderer.py feat: Built ffmpeg-based card renderer with concat demuxer pipeline and… 2026-04-04 11:17:38 +00:00
test_citation_utils.py test: Added BodySection/BodySubSection schema models, changed Synthesiz… 2026-04-03 00:50:30 +00:00
test_compose_pipeline.py test: Added 12 unit tests covering compose prompt construction, branchi… 2026-04-03 01:33:16 +00:00
test_harness.py test: Added compose subcommand with build_compose_prompt(), run_compose… 2026-04-03 01:05:25 +00:00
test_harness_compose.py test: 16 unit tests covering compose prompt XML structure, citation off… 2026-04-03 01:08:41 +00:00
test_harness_v2_format.py test: Updated test_harness.py word-count/section-count logic for list[B… 2026-04-03 00:54:27 +00:00
test_highlight_scorer.py test: Added 3 audio proxy scoring functions, extract_word_timings utili… 2026-04-04 08:05:22 +00:00
test_section_embedding.py feat: Added per-section embedding to stage 6 for v2 technique pages wit… 2026-04-03 02:12:56 +00:00