fix: vision tool cannot process videos, clarify image-only capability 3ee1e2c mangubee Claude commited on Jan 13
fix: clarify tool descriptions to prevent LLM selecting vision for YouTube 61ecfdb mangubee Claude commited on Jan 13
fix: YouTubeTranscriptApi.fetch is instance method not class method 92346a5 mangubee Claude commited on Jan 13
fix: youtube transcript API and missing datasets dependency a170083 mangubee Claude commited on Jan 13
fix: remove duplicate huggingface-hub, update tenacity version c9e941b mangubee Claude commited on Jan 13
fix: add youtube_transcript and transcribe_audio to TOOL_FUNCTIONS 40db96d mangubee Claude commited on Jan 13
feat: Phase 1 - YouTube transcript + Whisper audio transcription 38cc8e4 mangubee Claude commited on Jan 13
feat: system error field, calculator fix, target task IDs, course vs GAIA docs 41ac444 mangubee Claude commited on Jan 12
Phase 0-2: HF Vision Integration Complete - Google Gemma 3 Selected 2bb2d3d mangubee Claude commited on Jan 12
Add initial implementation for Phase 0 validation of HF Inference API with vision models 630f609 mangubee commited on Jan 11
Phase 0 Prep: Cache restructure, Vision investigation, HF integration plan 9fb579f mangubee Claude commited on Jan 7
Add UI-based LLM provider selection for cloud testing ac73681 mangubee Claude Sonnet 4.5 commited on Jan 4
Stage 5: Performance optimization - retry logic, Groq integration, improved prompts 5890f66 mangubee Claude Sonnet 4.5 commited on Jan 4
Docs: Update CHANGELOG with correct session date and dev records a98db29 mangubee Claude Sonnet 4.5 commited on Jan 4
Docs: Recover Stage 4 complete documentation structure 06fc271 mangubee Claude Sonnet 4.5 commited on Jan 4
Docs: Update dev log to reflect JSON export implementation ac31506 mangubee Claude Sonnet 4.5 commited on Jan 4