- Replaced the previous node and space management with a channel-based state management system in `manager.go`, enhancing concurrency handling.
- Implemented methods for loading and saving trace updates to disk in `local/driver.go` and `store/driver.go`, allowing for persistent state across sessions.
- Updated subscription handling in `subscription.go` to streamline the process of broadcasting updates to active subscribers.
- Enhanced node and trace status management, including cancellation and completion states, to provide better control over trace execution.
- Adjusted related tests to ensure compatibility with the new state management approach.
- Removed unnecessary blank lines in multiple test files to enhance code clarity and maintainability.
- Adjusted formatting in `subscription.go`, `trace_bench_test.go`, `trace_concurrent_test.go`, `trace_mem_test.go`, `trace_node_test.go`, `trace_space_test.go`, and `trace_subscription_test.go` for consistency.
- Updated benchmark and memory leak detection commands in the Makefile to include both agent and trace components.
- Refactored the manager struct in `manager.go` to support cancellable contexts and added per-space locks for improved concurrency safety.
- Enhanced subscription handling in `subscription.go` to only broadcast updates if there are active subscribers, preventing unnecessary operations.
- Implemented comprehensive disk operations in `local/driver.go` and `store/driver.go` for managing trace nodes, spaces, and logs, including loading, saving, and deleting functionalities.
- Improved README documentation to clarify driver configurations and usage examples for trace management.
- Updated trace ID validation in `TestEnterStack_RootCreation` to ensure it is at least 8 digits long.
- Changed import path for the trace package in `stack.go` for consistency.
- Removed the entire `manager.go`, `node.go`, `space.go`, `subscription.go`, `trace.go`, `local/driver.go`, `store/driver.go`, and related types and events files to streamline the trace package, focusing on essential functionality.
- Introduced a global trace registry to manage active traces with thread-safe access.
- Added support for two storage drivers: Local (file-based) and Store (Gou store).
- Enhanced trace ID generation to include a date prefix and improved uniqueness.
- Implemented functions for creating, loading, and releasing traces, along with checking their existence in both the registry and persistent storage.
- Added functionality to retrieve trace metadata and list active traces, improving trace management capabilities.
- Added a new field to track the current message type (text, thinking, tool_call) in the streamState struct.
- Updated message handling methods to set the current message type appropriately.
- Modified the group end handling to use the tracked message type when sending messages, ensuring accurate type representation.
- Enhanced unit tests to verify the correct handling of group end events and their associated types.
- Changed the Vision field in ModelCapabilities from bool to interface{} to accommodate both boolean values and VisionFormat strings.
- Modified the getConnectorCapabilities function to directly assign the Vision capability based on the updated model configuration, enhancing compatibility with various vision input formats.
- Integrated Claude API keys into GitHub workflows for both unit and PR tests.
- Introduced a new VisionFormat type and constants to manage image input formats.
- Updated ModelCapabilities to support vision input, allowing for flexible handling of image formats.
- Enhanced VisionAdapter to preprocess messages and convert image URLs to base64 format for Claude compatibility.
- Improved OpenAI provider to utilize vision support in message preprocessing, ensuring better integration with vision capabilities.
- Renamed and refactored functions and variables to transition from connector settings to model capabilities, enhancing clarity and consistency.
- Updated the loading mechanism to read model capabilities from `models.yml` instead of `connectors.yml`.
- Adjusted the assistant's global settings to utilize model capabilities, ensuring proper integration with the new configuration structure.
- Enhanced the reasoning adapter to support temperature adjustment based on model capabilities, improving flexibility in handling reasoning parameters.
- 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.
- Removed legacy and audio providers, consolidating functionality into a new architecture that separates API format handling from capability management.
- Updated the OpenAI provider to support capability adapters for tool calls, vision, audio, and reasoning, enhancing modularity and extensibility.
- Introduced a new method for detecting API formats and streamlined the provider selection process.
- Enhanced documentation to reflect the new architecture and clarify provider capabilities and usage.
- Added logic to ignore "done" messages that are not delta updates, ensuring that final confirmation messages are not sent to OpenAI clients, which rely on finish_reason instead.
- Added support for lifecycle event messages, including a new event type for tracking stream states (e.g., stream_start, stream_end).
- Introduced a NewEventMessage function to create event messages with structured properties.
- Updated the output package to include event messages in the built-in types, ensuring compatibility with CUI clients while remaining silent for OpenAI clients.
- Enhanced the DefaultStreamHandler to utilize event messages for better lifecycle tracking during streaming operations.
- Improved error handling and logging in the OpenAI provider to capture and report streaming errors effectively.
- Implemented a state management system for handling different streaming chunk types, including stream start, group start, text, thinking, tool calls, metadata, errors, and stream end.
- Introduced a new Send method in the context to facilitate message sending to the client.
- Enhanced the output package with message sending capabilities, including support for message groups and flushing.
- Improved error handling and message ID generation for better streaming reliability and user feedback.
- Added context cancellation handling in the OpenAI provider's Stream and Post methods, allowing for graceful termination of operations when the context is cancelled.
- Implemented a new test, TestOpenAIStreamContextCancellation, to validate that streaming respects context cancellation, ensuring proper error handling and event emission during cancellation scenarios.
- Refactored context usage in existing methods to improve consistency and reliability in handling context across streaming operations.
- Removed unnecessary blank lines in the TestOpenAIStreamLifecycleEvents function to improve code readability.
- Adjusted log formatting for group_end event to ensure consistent output during test execution.
- Added support for stream lifecycle events including stream_start, stream_end, group_start, and group_end.
- Introduced new data structures for handling lifecycle event data, enhancing communication of stream boundaries and metadata.
- Updated the OpenAI provider to track and emit these events during streaming operations, improving UI/UX capabilities.
- Added tests to validate the correct emission and order of lifecycle events during streaming.
- Introduced TestOpenAIJSONMode and TestOpenAIJSONModePost to validate JSON response formatting for streaming and non-streaming requests.
- Added TestOpenAIJSONSchema and TestOpenAIJSONSchemaPost to ensure compliance with strict JSON schema validation.
- Enhanced request body construction in the OpenAI provider to support JSON schema details in response formats.
- Added message preprocessing in the base provider to filter unsupported content types (vision and audio) based on model capabilities.
- Introduced new methods in the OpenAI provider for handling streaming and non-streaming requests with retry logic and tool call validation.
- Enhanced request body building to support various options and improved error handling for API interactions.
- Implemented validation for tool call arguments against JSON schemas, ensuring compliance with expected formats.
- Upgraded Go version to 1.25 and updated several dependencies, including `testify` to v1.11.1 and added new indirect dependencies for JSON schema validation.
- Refactored the assistant's context management to utilize a new `context.Uses` structure, improving the handling of vision, audio, search, and fetch configurations.
- Enhanced the assistant's request building process to support new response formats, including JSON schema validation, ensuring better integration with various tools and services.
- Added global uses configuration to the assistant, allowing for centralized management of vision, audio, search, and fetch settings.
- Updated the Assistant struct and related methods to support the new Uses configuration, improving flexibility in assistant operations.
- Refactored the Stream method to utilize the new CompletionResponse type, enhancing response handling.
- Introduced new methods for building requests and managing capabilities, streamlining the assistant's interaction with various connectors.
- Refactored the Makefile to include new benchmark and memory leak detection tests, improving test coverage.
- Introduced context adjustments in the Create method, allowing hooks to modify context fields such as AssistantID, Connector, Locale, Theme, Route, and Metadata.
- Added a new test scenario to validate context field adjustments, ensuring proper updates during assistant operations.
- Updated test preparation to support optional V8 mode configuration for improved performance during benchmarks.
