New Features
- Built-in Web Search tool: Integrated web search as a built-in Agent tool, reducing decision cost (4f0ea5d)
- Claude Opus 4.6 model support: Added support for Claude Opus 4.6 model (#2661)
- WeCom image recognition: Support image message recognition in WeCom channel (#2667)
Improvements
- Smart context management: Resolved chat context overflow with intelligent context trimming strategy to prevent token limits (cea7fb7, 8acf2db) #2663
- Runtime info dynamic update: Automatic update of timestamps and other runtime info in system prompts via dynamic functions (#2655, #2657)
- Skill prompt optimization: Improved Skill system prompt generation, simplified tool descriptions for better Agent performance (6c21833)
- GLM custom API Base URL: Support custom API Base URL for GLM models (#2660)
- Startup script optimization: Improved
run.shscript interaction and configuration flow (#2656) - Decision step logging: Added Agent decision step logging for debugging (cb303e6)
Bug Fixes
- Scheduler memory loss: Fixed memory loss caused by Scheduler dispatcher (a77a874)
- Empty tool calls & long results: Fixed handling of empty tool calls and excessively long tool results (0542700)
- OpenAI Function Call: Fixed function call compatibility with OpenAI models (158c87a)
- Claude tool name field: Removed extraneous tool name field from Claude model responses (eec10cb)
- MiniMax reasoning: Optimized MiniMax model reasoning content handling, hidden thinking process output (c72cda3, 72b1cac)
- GLM thinking process: Hidden GLM model thinking process display (72b1cac)
- Feishu connection & SSL: Fixed Feishu channel SSL certificate errors and connection issues (229b14b, 8674421)
- model_type validation: Fixed
AttributeErrorcaused by non-stringmodel_type(#2666)