- Update EmbeddingRequest DTO to support more flexible input types
- Add input parsing method to handle various input formats
- Implement ConvertEmbeddingRequest for multiple channel adaptors
- Remove relayMode parameter from EmbeddingHelper
- Add input validation for embedding requests
- Simplify embedding request conversion for different channels
- Add `Prefix` and `ReasoningContent` fields to Message struct
- Add getter and setter methods for `Prefix`
- Make `ToolCall.ID` field optional (fix#749)
The issue was caused by the `omitempty` tag in the Go struct, which prevented the `temperature` field from being included in the JSON output when it was set to 0.
Signed-off-by: Butui Hu <hot123tea123@gmail.com>
- Add file data DTO for structured file handling
- Implement file decoder service
- Update Claude and Gemini relay channels to handle various file types
- Reorganize worker service to cf_worker for clarity
- Update token counter and image service for new file types
- Refactored ParseToolCalls, SetToolCalls, IsStringContent, and ParseContent methods in the Message struct to use pointer receivers, improving efficiency and consistency in handling mutable state.
- Enhanced code readability and maintainability by ensuring all relevant methods operate on the pointer receiver, aligning with Go best practices.
- Changed the SetToolCalls method to use a pointer receiver for the Message struct, allowing for modifications to the original instance.
- This change improves the method's efficiency and aligns with Go best practices for mutating struct methods.
- Changed the type of ToolCalls in the Message struct from `any` to `json.RawMessage` for better type safety and clarity.
- Introduced ParseToolCalls and SetToolCalls methods to handle ToolCalls more effectively, improving code readability and maintainability.
- Updated the ParseContent method to work with the new MediaContent type instead of MediaMessage, enhancing the structure of content parsing.
- Refactored Gemini relay functions to utilize the new ToolCalls handling methods, streamlining the integration with OpenAI and Gemini systems.
