- Introduced auto-configuration classes for profile, client, agent, and prompt modules.
- Updated README to reflect new modular architecture and configuration properties.
- Added selective enabling/disabling of modules via application properties.
- Refactored existing services and strategies to remove unnecessary Spring annotations.
- Enhanced test configurations to utilize auto-configuration.
- Updated META-INF imports to include new auto-configuration classes.
- Updated model profile to support new cost parameters: costPerCachedInToken and costPerReasoningOutToken.
- Enhanced AgentRequestStatistic to track cached input tokens and reasoning output tokens.
- Modified CompletionStatistics to include cached input tokens and reasoning output tokens.
- Updated AzureAiClient, CachedClient, and other clients to handle new statistics fields.
- Introduced Timings class to capture detailed timing metrics for requests.
- Adjusted Usage class to include input and output token details.
- Updated properties files to include new cost parameters for cached and reasoning tokens.
- Added ModelProfile to the Agent record to allow for more detailed model configurations.
- Updated AgentExecutorService to utilize ModelProfile when fetching clients.
- Modified BaseAgent interface to include a default modelProfile method.
- Adjusted Client interface and implementations to support ModelProfile in conversation and streaming methods.
- Enhanced ClientService to retrieve clients based on ModelProfile.
- Updated CompletionInterceptor to work with ModelProfile instead of ModelCategory.
- Refactored AzureAiClient and other client implementations to handle ModelProfile correctly.
- Changed CachedClient to cache responses based on ModelProfile.
- Updated ModelCategory to a record type for better validation and immutability.
- Enhanced ModelProfile with validation checks for its fields.
- Updated ModelProfileService to support fetching profiles based on ModelCategory.
- Adjusted tests to accommodate changes in Agent and ModelProfile.
- Updated properties files to include category information for model profiles.
- Added AbstractCompletionRequest and AbstractCompletionResponse classes to standardize request and response structures.
- Implemented StreamOptions for streaming responses in chat completions.
- Enhanced ChatCompletionClient and TextCompletionClient to support reasoning content in responses.
- Updated ModelProfile to include reasoning effort and summary details.
- Created GptOssPromptStrategy to handle specific prompt formatting and reasoning extraction.
- Modified existing tests to validate reasoning content in completions.
- Updated configuration properties for reasoning settings in local properties files.
This commit introduces the following changes:
- **BaseAgent:** Added a mechanism to allow consumers to update the AgentContext after post-processing a split. This provides more flexibility for downstream components to react to the processed data.
- **TextAgentResponseHandler:** Introduced a `beforeStream` consumer that allows updating the AgentContext before the stream begins. This enables pre-processing or initialization steps within the response handler. The constructor has been updated to accept this new consumer. Also fixed a bug where the chunkKey and updateKey were not being removed after processing.
These changes enhance the extensibility and configurability of the agent processing pipeline.
