agentbee / src

Commit History

  1. fix: correct author name formatting in multiple files

    e7b4937

  1. Enhance YouTube video processing with transcript and frame analysis modes⁠

    f1b095a

  1. refactor: rename runtime folders with underscore prefix⁠

    mangubee +1: Claude
    04ece4c
  2. feat: consolidate LLM logs to single session file⁠

    mangubee +1: Claude
    a0fa418
  3. feat: add Chain of Thought for LLM synthesis debugging⁠

    mangubee +1: Claude
    c64957b
  4. fix: close parenthesis in execute_node error handling⁠

    mangubee +1: Claude
    9c1dff0
  5. feat: standardize logging with console + file separation⁠

    mangubee +1: Claude
    fa82033
  6. refactor: compress console logs for clarity⁠

    mangubee +1: Claude
    fed2514
  7. feat: export LLM synthesis context to cache for debugging⁠

    mangubee +1: Claude
    86bc1db
  8. debug: log full transcript content for debugging⁠

    mangubee +1: Claude
    4496081
  9. feat: add transcript caching and upgrade synthesis model⁠

    mangubee +1: Claude
    b68b317
  10. debug: log full transcript content for debugging⁠

    mangubee +1: Claude
    a1d5de5
  11. fix: vision tool cannot process videos, clarify image-only capability⁠

    mangubee +1: Claude
    3ee1e2c
  12. fix: clarify tool descriptions to prevent LLM selecting vision for YouTube⁠

    mangubee +1: Claude
    61ecfdb
  13. fix: typo WISPER_MODEL -> WHISPER_MODEL in audio.py⁠

    mangubee +1: Claude
    7bb1d7c
  14. fix: YouTubeTranscriptApi.fetch is instance method not class method⁠

    mangubee +1: Claude
    92346a5
  15. fix: youtube transcript API and missing datasets dependency⁠

    mangubee +1: Claude
    a170083
  16. fix: add youtube_transcript and transcribe_audio to TOOL_FUNCTIONS⁠

    mangubee +1: Claude
    40db96d
  17. feat: Phase 1 - YouTube transcript + Whisper audio transcription⁠

    mangubee +1: Claude
    38cc8e4

  1. feat: system error field, calculator fix, target task IDs, course vs GAIA docs⁠

    mangubee +1: Claude
    41ac444
  2. Phase 0-2: HF Vision Integration Complete - Google Gemma 3 Selected⁠

    mangubee +1: Claude
    2bb2d3d

  1. Update Groq model to openai/gpt-oss-120b

    44d1862
  2. Add Groundtruth Answer Column

    dc583a7
  3. Integrate benchmark dataset with results from HF as groundtruth

    9fb23b8
  4. Fix: Read LLM provider config at runtime for UI updates

    91f84b2
  5. Add UI-based LLM provider selection for cloud testing⁠

    mangubee +1: Claude Sonnet 4.5
    ac73681
  6. Groq Model Update

    6e73cae
  7. Stage 5: Performance optimization - retry logic, Groq integration, improved prompts⁠

    mangubee +1: Claude Sonnet 4.5
    5890f66

  1. Fix: Tool name consistency across TOOLS registry and TOOL_FUNCTIONS⁠

    mangubee +1: Claude Sonnet 4.5
    59f3cce
  2. Feat: Add HuggingFace Inference API as free LLM fallback tier⁠

    mangubee +1: Claude Sonnet 4.5
    4eed151

  1. Fix: Make LLM provider configurable (Gemini primary, Claude fallback)⁠

    mangubee +1: Claude Sonnet 4.5
    bbc52c6
  2. Stage 3: Core Logic Implementation - LLM Integration⁠

    mangubee +1: Claude Sonnet 4.5
    4c0b7eb
  3. Move test files from tests/ to test/ folder per project standard⁠

    8e48c56
  4. Stage 2: Implement tool development with retry logic and error handling⁠

    mangubee +1: Claude Sonnet 4.5
    1041734

  1. Stage 1: Foundation Setup - LangGraph agent with isolated environment⁠

    bd73133