Commit History

  1. feat: setup progress bar for analysis action and swap batch/settings tabs

    397d321
  2. extend provider-specific prompt caching to analysis path

    Ayona
    e8ea072
  3. refactor prompt assembly for provider-specific caching

    Ayona
    240f6e7
  4. feat: Add thinking parameters to Analysis mode and update models list in README

    0b3ee40
  5. handoff: align help and trim debug leakage

    Ayona
    8f359a6

  1. feat: Allow default analysis model in PrecedentAnalysisWorkflow if not specified

    028f33a

  1. feat: Add support for GPT-5.3 Chat Latest model in configuration and reasoning parameters

    8571f1b

  1. feat: Enhance OpenAI reasoning capabilities with configurable parameters

    b2f09af
  2. Support output_config effort parameter for Claude Adaptive Thinking

    86d1da5
  3. Re-enable extended thinking for Claude Haiku 4.5 models

    28552c9
  4. Fix Anthropic thinking mode configuration logic

    09efcd1

  1. feat: Enhance interactivity of Gradio interface and improve handling of empty response in PrecedentAnalysisWorkflow

    59a8fbf
  2. feat: Update system prompt structure to include cache control in LLMAnalyzer and generate_legal_position functions

    d0c3228
  3. feat: Optimize caching for Anthropic and OpenAI prompts, restructure prompt variables for efficiency

    b434018

  1. feat: Add debug prompt logging functionality with environment variable support

    0c2542b

  1. feat: Оновлення UI для GPT-5.2 та додавання контролю MaxTokens

    a765e3e

  1. feat: Інтеграція GPT-5.2 з підтримкою reasoning⁠

    492b465

  1. Add diagnostic logging and raw httpx connectivity test for OpenAI API

    98f5eca
  2. Disable HTTP/2 in httpx client for OpenAI and DeepSeek to avoid 421 Misdirected Request errors and ensure consistent connections in HF Spaces

    381cd06
  3. Refactor httpx client usage for OpenAI and DeepSeek: implement context management to prevent socket leaks and improve error logging

    3e63a13
  4. Fix OpenAI/DeepSeek HF Spaces connectivity: use custom httpx.Client to handle asyncio conflicts

    60a364a
  5. Enhance API key debugging: add length and prefix display for OPENAI_API_KEY; update provider availability checks to use os.getenv for real-time state

    71df805
  6. Enhance provider management: normalize response keys, add availability checks, and improve Gradio interface for AI providers

    a09e8cb
  7. Revert httpx.Client customization: use default OpenAI SDK settings for async compatibility in HF Spaces

    5c25abd
  8. Fix persistent Connection Errors for OpenAI/DeepSeek: disable HTTP/2 and use robust httpx client

    48ae0da
  9. Fix Connection error for OpenAI and DeepSeek: add retry logic and increase timeout to 120s

    2ef2be1
  10. Improve DeepSeek compatibility (R1/reasoner support) and fix lint errors in main.py

    558b73f
  11. Fix OpenAI gpt-4.1 API parameters: role 'developer', max_completion_tokens, and reasoning effort support; update max_tokens in default config

    39e57fa

  1. Increase max_tokens for all models in generation settings to enhance response capacity

    a3e169a
  2. Add JSON extraction utility and enhance analysis methods for better error handling

    59fabbc
  3. Add placeholders for court decision text and comment in legal position prompt

    d814828
  4. Clean deployment without large index files

    461adca