- Add call_vision method to all bot implementations (DashScope, Claude,
Gemini, ZhipuAI, MiniMax, Doubao, Moonshot, OpenAICompatibleBot)
using each vendor's native multimodal API format
- Remove call_with_tools/call_vision from Bot base class to fix MRO
shadowing issue with OpenAICompatibleBot mixin
- Refactor vision tool provider resolution: MainModel → other configured
models (auto-discovered) → OpenAI → LinkAI, with automatic fallback
- Return actual model name used in call_vision responses
- Sync config.json API keys to .env bidirectionally on startup
- Fix bot instance cache to detect bot_type/use_linkai config changes
- Add SSE reconnection support for web console
- Preserve image path hints in Gemini text for correct vision tool calls
- Update docs/tools/vision.mdx
api_key and api_base were refactored to @property but model was not
migrated, causing AttributeError: 'GoogleGeminiBot' object has no
attribute 'model' when using any Gemini model.
- parse [图片: path] markers in text and convert to Gemini inlineData parts
- unify reply path via call_with_tools to reuse multimodal conversion
- keep legacy safety behavior (BLOCK_NONE) and restore safety ratings logging on empty response
- add multimodal request image-part count log for debugging
