- 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
Separate DeepSeek from ChatGPTBot into its own module (models/deepseek/) with dedicated deepseek_api_key and deepseek_api_base config fields, avoiding config conflicts when switching between providers. Backward compatible with old users who configured DeepSeek via open_ai_api_key/open_ai_api_base through automatic fallback.
Made-with: Cursor
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.
- Rename ZHIPU_AI bot type from glm-4 to zhipu to avoid confusion with model names
- Add bot_type persistence in web config to fix provider dropdown resetting on refresh
- Change OpenAI provider key to chatGPT to match bot_factory routing
- Add DEEPSEEK constant and route it to ChatGPTBot (OpenAI-compatible API)
- Keep backward compatibility for legacy bot_type glm-4 in bot_factory
- Fix re.sub bad escape error on Windows paths by using lambda replacement
- Remove unused pydantic import in minimax_bot.py
Made-with: Cursor
Replace all direct openai.error.* usages with the openai_compat
compatibility layer to support openai>=1.0.
Affected files:
- models/chatgpt/chat_gpt_bot.py: fix isinstance checks (RateLimitError, Timeout, APIError, APIConnectionError)
- models/openai/open_ai_bot.py: replace import + fix isinstance checks
- models/ali/ali_qwen_bot.py: replace import + fix isinstance checks
- models/modelscope/modelscope_bot.py: remove unused openai.error import
The openai_compat layer (models/openai/openai_compat.py) already
handles both openai<1.0 and openai>=1.0 gracefully. This completes
the migration started in the existing PR #2688.
The code was directly importing openai.error which fails with openai>=1.0.
The project already has an openai_compat.py compatibility layer that handles
both old (<1.0) and new (>=1.0) OpenAI SDK versions.
This commit updates chat_gpt_bot.py to use the compatibility layer.
Related: #2687
- 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
