Max 494c8dc98e Add DeepSeek API configuration and enhance reasoning support in LLM adapters ... - Added DeepSeek API keys and model configurations to the GitHub workflows for both unit and PR tests. - Introduced a new `ReasoningEffort` parameter in the `CompletionOptions` struct to manage reasoning levels for models like o1 and GPT-5. - Updated the `ReasoningAdapter` to handle the new `ReasoningEffort` parameter, ensuring it is stripped if not supported by the model. - Enhanced the OpenAI provider to preprocess options through adapters, improving the handling of reasoning content and ensuring compatibility with DeepSeek R1 reasoning format.		2025-11-17 08:07:20 +08:00
..
adapter.go	Refactor LLM provider architecture to utilize capability adapters	2025-11-17 06:44:20 +08:00
audio.go	Refactor LLM provider architecture to utilize capability adapters	2025-11-17 06:44:20 +08:00
reasoning.go	Add DeepSeek API configuration and enhance reasoning support in LLM adapters	2025-11-17 08:07:20 +08:00
toolcall.go	Add DeepSeek API configuration and enhance reasoning support in LLM adapters	2025-11-17 08:07:20 +08:00
vision.go	Refactor LLM provider architecture to utilize capability adapters	2025-11-17 06:44:20 +08:00