3 Commits

Author	SHA1	Message	Date
PR Bot	1b9c5609c9	feat: add MiniMax provider support ... - Add MiniMax model detection and compatibility handling in LLMClient - Handle response_format incompatibility: MiniMax does not support response_format parameter, use prompt engineering for JSON output - Add temperature clamping for MiniMax (must be > 0) - Add robust JSON parsing from LLM responses (parse_json_from_response) - Update simulation_config_generator and oasis_profile_generator for MiniMax compatibility - Add MiniMax configuration examples in .env.example - Add MiniMax documentation in README.md and README-EN.md - Add unit tests for MiniMax compatibility functions Supported models: MiniMax-M2.5, MiniMax-M2.5-highspeed API docs: https://platform.minimax.io/docs/api-reference/text-openai-api	2026-03-12 14:03:07 +08:00
666ghj	985f89f49a	fix: resolve 500 error caused by <think> tags and markdown code fences in content field from reasoning models like MiniMax/GLM	2026-03-06 00:30:31 +08:00
666ghj	08f417f3b7	Introduce Project ID for context management, finalizing the stateful API pipeline from file submission to graph construction.	2025-11-28 17:21:08 +08:00