- Added support for tool loop processing when tool call responses are present and sandbox mode is disabled, improving the assistant's ability to handle complex tool interactions.
- Implemented fallback delegation to a loop fallback mechanism in case of tool loop execution failure, enhancing robustness in error scenarios.
- Updated the assistant message structure to include reasoning content, providing better context for generated responses.
- Enhanced error logging in tool call execution to include detailed content, improving diagnostics for tool call failures.
- Updated system configuration to include a new loop fallback agent, expanding the assistant's capabilities.
- Implemented V2 sandbox initialization in the assistant loading process, allowing for standalone sandbox.yao configuration.
- Added support for V2 sandbox execution paths in the Assistant's Stream method, differentiating between V1 and V2 sandboxes.
- Introduced comprehensive tests for V2 sandbox configurations, ensuring correct loading and execution behavior.
- Updated the context and types to accommodate V2 sandbox features, including system information and workspace management.
Made-with: Cursor
- Introduce a new method to control the maximum number of history messages loaded, prioritizing user-defined options over store settings.
- Update the history loading logic to filter out non-semantic message types and convert tool call and action messages into historical summaries for better context.
- Refactor the message conversion functions to handle different formats and ensure clarity in the historical context provided to the LLM.
- Add comprehensive tests to validate the new behavior and ensure accurate message handling in various scenarios.
- Remove the `LoadModelCapabilities` test and associated model capabilities initialization from the agent, streamlining the loading process.
- Update the LLM provider implementations to utilize a unified `Capabilities` structure, replacing references to `openai.Capabilities` with `llm.Capabilities`.
- Enhance capability retrieval methods to simplify the extraction of connector capabilities, ensuring compatibility across different LLM providers.
- Clean up unused functions and variables related to model capabilities, improving code maintainability.
- Added steps to pull necessary Docker images for sandbox testing in both CI workflows.
- Updated the AI test execution to utilize sandbox configurations, ensuring proper environment setup.
- Introduced sandbox initialization in the Assistant's Stream method, allowing for execution of coding agents like Claude and Cursor.
- Enhanced context management to support sandbox execution, improving flexibility in handling agent operations.
- Introduced mechanisms to handle agent-to-agent (A2A) calls, including automatic history skipping for forked calls and proper source tracking.
- Enhanced context management with the addition of ForkParentInfo to facilitate child stack creation without race conditions.
- Updated JSAPI methods to ensure correct handling of sub-agent calls, maintaining output isolation and preventing history pollution.
- Improved documentation to clarify the behavior of A2A calls and context management in concurrent scenarios.
- Added initialization for the Agent JSAPI factory to support ctx.agent.* methods, improving agent interaction capabilities.
- Introduced a new agent object in the JSAPI context for calling other agents, enhancing modularity.
- Implemented an OnMessage callback in the context options to handle messages sent via ctx.Send(), allowing for more flexible message processing.
- Added support for parsing various file types (PDF, DOCX, PPTX) in the content processing pipeline, allowing for more flexible content extraction.
- Implemented a new method to convert file attachments to raw text when content parsing is skipped, improving performance for internal calls.
- Introduced loading message suppression for image processing to enhance user experience during PDF analysis.
- Updated the PDF handler to cache processed text and manage loading messages effectively, ensuring smoother interactions during content retrieval.
- Enhanced error handling and logging for PDF processing, improving traceability and debugging capabilities.
- Updated the BuildContent method to utilize content parsing with improved error handling and context injection, enhancing the processing of user input.
- Refactored the loadMap function to support multiple search configuration types, improving flexibility in handling search settings.
- Enhanced the shouldAutoSearch method to include a check for search disabling via context metadata, allowing for more granular control over search behavior.
- Updated the getMergedSearchUses method to prioritize options.Uses, ensuring that search configurations can be dynamically adjusted based on provided options.
- Removed deprecated audio and excel handling code, streamlining the content processing package and improving maintainability.
- Introduced delegation functionality in the Create hook, allowing agents to route requests to sub-agents without invoking LLM processing.
- Updated the HookCreateResponse structure to include a Delegate field, enabling immediate delegation to another agent.
- Enhanced the Stream method to handle delegation responses, ensuring proper stream closure and error handling for delegated agents.
- Improved logging for delegation actions to facilitate debugging and traceability in agent interactions.
- Added support for tool call responses in the agent's response structure, allowing for better handling of tool execution results.
- Updated the `TurnResult` and `TurnResponse` types to include full agent responses, including tool call details and next hook data.
- Improved dynamic test execution by ensuring consistent chat session state across turns, enhancing the overall testing framework's capabilities.
- Enhanced documentation in README.md to reflect changes in response structure and dynamic testing output format.
- Replaced all instances of `ctx.Space` with `ctx.Memory.Context` in the context management code, ensuring a more structured approach to handling temporary request-scoped data.
- Updated related test cases to reflect the changes in context memory usage, enhancing the reliability and clarity of tests.
- Removed the deprecated `Space` references and adjusted comments and documentation to align with the new memory management strategy.
- Updated the search handling to incorporate keyword extraction with weights, improving the relevance of search results.
- Refactored the `shouldAutoSearch` method to return a `SearchIntent` struct, allowing for more nuanced control over search execution based on context.
- Enhanced the `buildSearchRequests` function to utilize extracted keywords, optimizing search queries based on user input.
- Improved the handling of search types and conditions, ensuring that the system can dynamically adjust search behavior based on intent and configuration.
- Updated documentation and prompts to reflect changes in keyword extraction and search intent classification, providing clearer guidelines for usage.
- Added support for a new `Metadata` field in the `Options` struct to allow passing custom data to hooks, enhancing flexibility in context management.
- Updated the `ToMap` and `OptionsFromMap` methods to include serialization and deserialization of the `Metadata` field.
- Enhanced the test case structure to include an `Options` field, allowing for per-test-case configuration, including metadata and skip options.
- Updated documentation to reflect the new `options` and `metadata` fields, providing clear examples for users on how to utilize these features in test cases.
- Updated the `shouldAutoSearch` method to include additional parameters for improved intent detection, allowing for better decision-making on whether to execute auto search.
- Introduced a new `checkSearchIntent` method to utilize the `__yao.needsearch` agent for determining the necessity of a search based on user input.
- Implemented a `ClearExcept` method in the cache to selectively clear non-system agents while preserving essential system agents during cache management.
- Updated the `LoadBuiltIn` function to maintain system agents in the cache, ensuring they remain available for use.
- Enhanced test coverage for loading system agents and validating search intent detection, ensuring robustness in the assistant's search capabilities.
- Revised localization files to include new messages for search intent feedback, improving user experience during search operations.
- Updated the executeAutoSearch method to include an optional parameter for Skip.Keyword, allowing for conditional keyword extraction during web searches.
- Implemented logic to extract keywords only when configured and not skipped, improving search query optimization.
- Modified the Assistant's Stream method to pass options to executeAutoSearch, ensuring seamless integration of the new functionality.
- Updated DESIGN.md to document the changes in keyword extraction logic and its impact on the search process.
- Added a new method to set store settings during assistant initialization, allowing for configuration of storage parameters such as MaxSize and TTL.
- Updated context creation methods to streamline the setup process, ensuring that essential fields are populated consistently across various test contexts.
- Revised tests to validate the new initialization behavior and context management, ensuring proper handling of assistant settings and context properties.
- Introduced methods for initializing and managing a chat buffer, allowing for efficient storage of user inputs and assistant messages during chat sessions.
- Added functionality to track execution steps, including beginning and completing steps, with support for capturing space snapshots and handling errors.
- Enhanced the FlushBuffer method to save buffered messages and steps to the database, ensuring data integrity and recovery capabilities.
- Updated the Stream method to integrate buffer management, ensuring proper handling of chat sessions and message storage.
- Added comprehensive tests to validate buffer initialization, user input handling, and step tracking functionalities.
- Updated the Vision function and associated handlers to accept a forceUses parameter, allowing explicit control over the use of external tools regardless of model capabilities.
- Modified the Assistant's BuildContent method to set the AssistantID in the context for better file tracking.
- Enhanced the applyCreateResponseOptions method to merge and prioritize Uses and ForceUses configurations from the createResponse.
- Added comprehensive tests to validate the adjustment of Uses and ForceUses configurations through hooks, ensuring correct application in content processing.
- Updated the Stream, BuildContent, and LLM execution methods to accept an Options parameter, allowing for more flexible context handling.
- Removed debug print statements to clean up the code and improve readability.
- Enhanced locale handling in the loadMap function to automatically inject assistant name and description into all locales, ensuring better localization support.
- Introduced output skipping functionality in context options to manage internal A2A calls more effectively.
- Improved output writer resolution logic to prioritize context settings, enhancing output management during agent calls.
- Updated the Assistant methods to accept an Options parameter, enhancing flexibility in context management.
- Removed the Connector field from the context and related structures, transitioning to a more streamlined options-based approach.
- Adjusted various tests to accommodate the new options handling, ensuring comprehensive coverage of the updated functionality.
- Enhanced the Create and Next hooks to return options alongside responses, improving the overall usability of the API.
- Cleaned up deprecated fields and improved context initialization for better maintainability.
- Added support for converting extended types (file, data) to standard LLM types (text, image_url, input_audio) in the Stream method.
- Introduced a new agentCallerWrapper to facilitate agent calls from the content package.
- Implemented ThreadID management for nested agent calls to improve concurrent stream identification.
- Enhanced message handling to include metadata for message_start and message_end events, allowing for better tracking of message states.
- Removed deprecated vision capability checks from the Assistant initialization process, streamlining the codebase.
- Added new content types (file, data) to the context types for improved message content handling.
- Introduced prompt preset selection and global prompt disabling features in the assistant's message building process.
- Updated the `buildSystemPrompts` method to prioritize prompt presets and manage global prompt settings based on context and hook responses.
- Added new fields to the `HookCreateResponse` struct for prompt configuration, allowing for dynamic adjustments during message processing.
- Refactored tests to validate the integration of prompt presets and global prompt controls, ensuring robust functionality and context-aware behavior.
- Updated the model capabilities throughout the agent to utilize the new gouOpenAI.Capabilities struct instead of the previous ModelCapabilities.
- Adjusted related methods and types to ensure compatibility with the new capabilities structure, enhancing clarity and maintainability.
- Improved context handling and message processing by directly integrating OpenAI capabilities, streamlining the overall architecture.
- Introduced a new messageMetadataStore type for managing message and block metadata with thread-safe operations.
- Added methods for setting, getting, and updating message and block metadata, enhancing concurrency handling.
- Removed redundant metadata store implementation from types.go, centralizing functionality in message.go for improved organization.
- Added EndBlock method to explicitly mark the end of a message block, sending a block_end event.
- Updated message handling to include lifecycle events for message start and end, improving tracking and management of message durations.
- Enhanced message metadata structure to support chunk counting and message types, facilitating better message operations.
- Improved JSAPI documentation to include new lifecycle management features, clarifying usage for developers.
- Removed deprecated API and vision components, streamlining the agent's architecture.
- Updated the Load function to utilize a new agentDSL variable, enhancing the management of assistant capabilities.
- Enhanced context handling by introducing a message metadata store for thread-safe operations, improving message tracking and management.
- Refactored context methods to eliminate deprecated fields, ensuring cleaner and more maintainable code.
- Improved documentation and comments throughout the codebase to clarify changes and enhance developer understanding.
- Introduced recordMessageMetadata and getMessageMetadata methods to manage metadata for sent messages, enabling BlockID and ThreadID inheritance in delta operations.
- Implemented new methods (Append, Merge, Set) in the context to enhance message management capabilities, allowing for more flexible message updates.
- Updated the Send method to automatically manage BlockID and ThreadID for delta operations, improving message handling consistency.
- Enhanced JSAPI documentation to reflect new methods and usage patterns, improving developer experience and clarity.
- Updated the Stream method to return a flexible final response, accommodating both standard and Next hook responses.
- Introduced NextProcessContext to encapsulate context for processing Next hook responses, enhancing clarity and maintainability.
- Removed deprecated Done and Failback hooks, streamlining the hook management process.
- Enhanced error handling and logging for improved traceability during streaming operations.
- Introduced a new test case for MCP hook overrides in build_mcp_test.go, validating that hooks can successfully modify MCP server configurations.
- Updated the applyMCPTools and buildMCPTools methods to prioritize hook-provided MCP servers over assistant configurations, enhancing flexibility in tool management.
- Enhanced the HookCreateResponse struct to include MCPServers, allowing hooks to specify server configurations for requests.
- Improved error handling and logging throughout the MCP tool application process, ensuring better traceability and debugging capabilities.
- Updated message structures to replace 'StreamStartData' and 'StreamEndData' with 'EventStreamStartData' and 'EventStreamEndData' for better clarity and consistency.
- Introduced 'EventMessageStartData' and 'EventMessageEndData' to represent individual message lifecycle events, enhancing the granularity of message tracking.
- Refactored the 'streamState' and 'groupTracker' to utilize the new message structures, improving the organization and handling of streaming events.
- Enhanced the context management by integrating an ID generator for unique message identifiers, facilitating better tracking of message sequences.
- Updated documentation and tests to reflect the new message structures and ensure proper functionality across the system.
- Updated the Load function and API handlers to replace 'Use' with 'Uses' for assistant configuration, enhancing consistency across the codebase.
- Modified related structures and functions to reflect the new naming convention, ensuring better alignment with the intended functionality.
- Added a new Skip struct to manage request skip configurations, improving request handling flexibility.
- Implemented tests for the GetSkip function to validate skip parameter extraction from both request body and query parameters.
- Updated the Response struct to include ContextID, RequestID, ChatID, and AssistantID for better traceability and context management.
- Modified the Stream method to return the new fields in the response, enhancing the output for client interactions.
- Added ContextID and ChatID to the StreamStartData struct to improve event tracking during streaming requests.
- Refactored the Stream method to retrieve connector capabilities early, allowing output adapters to utilize them effectively.
- Introduced a new Info method in the Assistant to provide structured assistant information, enhancing context accessibility.
- Updated StreamStartData to include additional fields such as ChatID and Assistant info for better event tracking.
- Improved error handling in the Stream method to ensure robust management of connector retrieval failures.
- Enhanced internationalization support for stream event messages, providing localized output for different clients.
- Added an interrupt controller to manage user interrupts during streaming operations.
- Introduced methods for registering and unregistering contexts in a global registry to facilitate interrupt handling.
- Enhanced the Assistant's Stream method to check for force interrupts and handle them appropriately.
- Updated context creation to include unique IDs for better identification during interrupts.
- Implemented logic for graceful and force interrupts, allowing for flexible response to user signals.
- Introduced a trace manager in the context struct for lazy initialization and management of trace operations.
- Implemented the Trace method in the context to facilitate trace object creation and management within JavaScript.
- Enhanced configuration options for trace drivers, including defaults for local and store drivers, and added path and prefix settings.
- Updated related tests to verify the functionality of the new trace management features.
- 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.
- Introduced a new test context creation function to streamline test setup for assistant operations.
- Refactored context structure to replace the deprecated 'Data' field with 'Metadata', improving clarity and consistency.
- Updated various methods to utilize the new 'Metadata' field, ensuring proper handling of request metadata across the system.
- Adjusted tests to reflect changes in metadata handling, enhancing validation of context fields in JavaScript integration.
- Updated the Create method in the Script type to return a structured HookCreateResponse instead of the previous ResponseHookCreate.
- Enhanced the getHookCreateResponse method to handle various response scenarios, including nil and undefined results.
- Refactored context types to introduce the new HookCreateResponse structure, which includes fields for messages, audio configuration, generation parameters, and metadata.
- Adjusted related methods in the Assistant to ensure compatibility with the new response structure.
- Updated the Stream method to return a structured response, including create, done, and completion hooks.
- Introduced new methods for managing message history and building LLM requests, enhancing modularity.
- Refactored the Script type to utilize a new hook structure, improving code organization.
- Removed the obsolete hooks file to streamline the codebase.
- Enhanced context types with additional fields for better integration with LLM models.
- Updated Stream and Run methods in the Assistant to use pointer receivers for context, enhancing performance and clarity.
- Introduced stack management in context handling, including initialization and cleanup of stack references.
- Enhanced the Release method in Context to ensure proper cleanup of resources, including stacks and writer references.
- Added new stack status constants and validation to improve traceability and error handling in agent operations.
- Removed the obsolete JavaScript API file to streamline the codebase.
- Removed commented-out methods from the API interface in assistant types to enhance code cleanliness.
- Introduced a new Response type in context types, ensuring compatibility with the OpenAI API.
- Renamed and restructured the TestNewOpenAPI function to TestGetCompletionRequest for clarity.
- Updated test cases to validate completion requests using a structured request body instead of query parameters.
- Enhanced error handling and assertions to ensure comprehensive coverage of various scenarios, including metadata handling and expected outputs.
- Removed the obsolete openapi_chat_test.go file to streamline the test suite.
- Deleted obsolete agent API files (agent.go, api.go, api_test.go, types.go) to streamline the codebase.
- Refactored the agent loading logic to initialize the API instance correctly, ensuring proper integration with the new structure.
- Updated context handling to improve clarity and maintainability across the agent's functionality.
- Enhanced error handling and cache management in the agent's initialization process.
- Updated context creation in handleChat, handleGenerateTitle, and handleGeneratePrompts to use the request context, improving context management.
- Commented out unused context settings for assistant ID, silent mode, history visibility, and client type to streamline the code.
- Refactored context handling in assistant methods to enhance clarity and maintainability.
- Removed deprecated functions and cleaned up the context structure for better performance and readability.
