- Change _exit_with_config_error return type to NoReturn for clarity
- Replace exit() with raise SystemExit() for better testability
- Remove unreachable return statement after error exit
Remove .env.example and move LLM provider settings, base URLs, and model options to a centralized config.json file. Update default_config.py, openai_client.py, and cli/utils.py to load configuration from this file, improving maintainability and reducing hardcoded values across the codebase.
Add effort parameter (high/medium/low) for Claude 4.5+ and 4.6 models,
consistent with OpenAI reasoning_effort and Google thinking_level.
Also add content normalization for Anthropic responses.
- OpenAI: add GPT-5.4, GPT-5.4 Pro; remove o-series and legacy GPT-4o
- Anthropic: add Claude Opus 4.6, Sonnet 4.6; remove legacy 4.1/4.0/3.x
- Google: add Gemini 3.1 Pro, 3.1 Flash Lite; remove deprecated
gemini-3-pro-preview and Gemini 2.0 series
- xAI: clean up model list to match current API
- Simplify UnifiedChatOpenAI GPT-5 temperature handling
- Add missing tradingagents/__init__.py (fixes pip install building)
- Added support for running CLI and Ollama server via Docker
- Introduced tests for local embeddings model and standalone Docker setup
- Enabled conditional Ollama server launch via LLM_PROVIDER
Maytekin
Yijia Xiao
Yijia-Xiao
CadeYu
Max Wong
Geeta Chauhan
Edward Sun
maxer137