6 Commits

Author	SHA1	Message	Date
zhayujie	26693acc3f	feat(vision): prioritize main model for image recognition with multi-provider fallback ... - 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	2026-04-11 19:46:11 +08:00
zhayujie	eda82bac92	fix: gemini tool call bug	2026-03-11 02:04:09 +08:00
zhayujie	4e32f67eeb	fix: validate tool_call_id pairing #2690	2026-03-10 14:52:07 +08:00
zhayujie	0542700f90	fix: issues with empty tool calls and handling excessively long tool results	2026-02-07 20:25:05 +08:00
zhayujie	158c87ab8b	fix: openai function call	2026-02-04 15:42:43 +08:00
zhayujie	4a1fae3cb4	chore: the bot directory was changed to models	2026-02-01 15:21:28 +08:00