- 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 functionality to the Assistant's Stream method to execute auto search if enabled, enhancing the search capabilities based on user configuration.
- Introduced helper methods for determining auto search eligibility, executing the search, and injecting search context into messages.
- Updated DESIGN.md to reflect the new auto search logic, including detailed descriptions of the new methods and their integration points within the search process.
- Introduced a new search object in the context to expose search methods (Web, KB, DB, All, Any, Race) for JavaScript integration.
- Implemented individual search methods with argument validation and error handling, improving the robustness of the API.
- Updated the JSAPI implementation to utilize the new search object, ensuring seamless interaction with the search functionalities.
- Enhanced documentation in DESIGN.md to reflect the new V8 binding methods and their usage, providing clear guidance for developers.
- Added initialization for the Search JSAPI factory in the Assistant module to streamline search operations.
- Updated the DESIGN.md to reflect the new architecture of the search module, including detailed descriptions of the keyword extraction and QueryDSL generation processes.
- Enhanced the interfaces for keyword extraction to require context, improving flexibility for different extraction modes.
- Revised directory structures in the documentation to clarify the organization of search-related components, ensuring comprehensive guidance for developers.
- Added logging for hook start and completion in the Assistant's Stream method to improve traceability during execution.
- Refactored the AgentGetterFunc to utilize the caller package, enhancing modularity and reducing circular dependencies.
- Updated the CallAgent function to check for the initialized AgentGetterFunc from the caller package, ensuring proper agent loading.
- Enhanced the Search handler to support an optional context parameter, improving flexibility for agent mode operations.
- Refined the agentSearch function to delegate search requests to a new AgentProvider, streamlining the search process.
- Updated DESIGN.md to reflect changes in search modes and the integration of the caller package, ensuring comprehensive documentation.
- Introduced a new search configuration structure, allowing for detailed settings for web, knowledge base, database, citation, and weights.
- Updated the `Assistant` model to include a `Search` field, enabling assistant-specific search configurations.
- Enhanced the loading and merging logic for search configurations, ensuring global defaults can be overridden by assistant-specific settings.
- Added comprehensive tests for loading, saving, and updating assistants with search configurations, verifying the integrity of search settings.
- Updated documentation in DESIGN.md to reflect the new search configuration hierarchy and usage, clarifying the interaction between global and assistant-level settings.
- Modified the test case in agent_next_test.go to use a deterministic sub-scenario, reducing flakiness in tests caused by unpredictable LLM responses.
- Enhanced DESIGN.md to clarify the structure and organization of the search module, including detailed descriptions of new types, interfaces, and configuration options.
- Updated the documentation to reflect changes in the citation system, source weighting, and the overall architecture of the search module, ensuring consistency and better understanding for developers.
- Updated the TestHistoryLoading function to clarify role filtering, ensuring only user and assistant messages are included in the history.
- Adjusted message creation timestamps for consistency in test scenarios.
- Removed deprecated context creation methods to streamline context management and improve code clarity.
- Enhanced logging levels in context management for better traceability and debugging.
- 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 `GetInfo` method in the Assistant struct to return basic assistant information with optional locale support for internationalization.
- Implemented `GetInfoByIDs` function to retrieve information for multiple assistants based on their IDs, enhancing batch processing capabilities.
- Updated chat buffer management to include a mode parameter, allowing for dynamic switching between chat and task modes.
- Enhanced message handling to store and retrieve the mode associated with each message, improving context tracking during chat sessions.
- Revised tests to validate the new functionalities, ensuring accurate retrieval of assistant information and proper mode management in chat operations.
- Updated the `ChatBuffer` to support streaming messages, allowing for content to be appended and finalized with `SendStream` and `End` methods.
- Modified the `AddAssistantMessage` method to include a message ID, improving message tracking and retrieval.
- Implemented new methods for appending content to streaming messages and completing them, ensuring accurate message storage and event handling.
- Revised tests to validate the new streaming functionality and ensure proper integration with existing message handling processes.
- Updated `CHAT_STORAGE_DESIGN.md` to reflect changes in message storage and indexing, including unique constraints for message IDs within requests.
- Enhanced chat buffer and message handling to support dynamic connector switching, allowing users to change the connector during a chat session.
- Updated the `ChatBuffer` and `BufferedMessage` structures to include a `connector` field, enabling tracking of the connector used for each message.
- Modified the `EnsureChat` method to skip chat creation when history is disabled, improving chat session management.
- Revised tests to validate the new connector functionality, ensuring accurate message retrieval and connector state management.
- Updated `CHAT_STORAGE_DESIGN.md` to reflect the addition of the `last_connector` field in chat metadata and message structures.
- 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.
- Added functionality to load Knowledge Base (KB) configuration from `agent/kb.yml`, allowing dynamic settings for chat sessions.
- Introduced `initKBConfig` function to read and parse KB settings, integrating them into the Assistant's initialization process.
- Enhanced the Assistant's conversation initialization to prepare KB collections asynchronously, improving performance during chat interactions.
- Updated tests to verify the correct loading and application of KB settings, ensuring robust integration with the Assistant's functionality.
- Refactored metadata handling for KB collections to include additional fields for improved context management during chat sessions.
- Added ExecuteWithAuthorized method to the Script struct, allowing scripts to be executed with user authorization information.
- Updated existing Execute method to utilize ExecuteWithAuthorized for improved authorization handling.
- Enhanced script execution tests to verify behavior with and without authorized information, ensuring accurate context management.
- Implemented authorized information conversion to a map for easier integration with runtime environments.
- Refactored context handling in script execution to ensure authorized data is correctly passed and utilized.
- Added permission validation in the Assistant's Stream method to ensure user authorization before processing input messages.
- Introduced conversation initialization within the Stream method to prepare the context for chat interactions.
- Removed the history.go file, which previously contained a placeholder method for handling chat history, streamlining the Assistant's codebase.
- Updated the Knowledge Base API integration in collection management, ensuring all collection operations utilize the new API structure for improved consistency and error handling.
- Added a new GetDel method to the space object, allowing retrieval and immediate deletion of a key's value, enhancing one-time use data handling.
- Updated the JS API to include tests for GetDel functionality, ensuring correct behavior for existing and non-existent keys, as well as complex data structures.
- Removed debug print statements from the Assistant's initializeCapabilities method for cleaner code.
- 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.
- Added tests to verify the presence and correctness of authorized and metadata fields in MCP tool context passing.
- Updated MCP tool context tests to include user and tenant ID assertions, ensuring accurate context validation.
- Enhanced JS API to handle authorized and metadata fields, including tests for nil scenarios, improving robustness and clarity in context management.
- Added tests to verify that agent context is correctly passed to MCP tools during single and parallel calls.
- Updated the MCP client methods to accept agent context as an additional argument, enhancing the context management during tool execution.
- Improved test coverage for context handling, ensuring that context data is accurately received and validated in tool responses.
- Updated cache tests to use the testify assertion library for improved readability and maintainability.
- Added new tests for cache operations including basic functionality, LRU eviction, removal, clearing, and concurrent access.
- Enhanced the cache implementation to unregister scripts upon removal and clearing, ensuring proper resource management.
- Introduced an `All` method to retrieve all assistants in the cache, improving accessibility of cached items.
- Streamlined the script registration and unregistration process within the Assistant struct, enhancing script management.
- Updated the script loading process to load both hook scripts and other scripts from the src directory, improving organization and clarity.
- Introduced a new `Scripts` field in the Assistant struct to store additional scripts, enhancing the flexibility of script management.
- Removed deprecated script loading functions and streamlined the loading logic to ensure better maintainability and performance.
- Adjusted the handling of timestamps for script updates, ensuring accurate tracking of script modifications.
- Replaced all instances of `Script` with `HookScript` in the Assistant and related files to improve clarity and consistency in naming.
- Updated method calls in the Stream, Create, and Next hooks to utilize the new `HookScript` field.
- Adjusted tests and benchmarks to reflect the changes in script handling, ensuring all functionalities remain intact and operational.
- Enhanced the load and initialization processes to accommodate the new HookScript structure, streamlining the assistant's script management.
- 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.
- Changed the `Optional` field in `ConnectorOptions` from a boolean to a pointer to allow for nil values, enhancing flexibility in option handling.
- Updated tests in `load_test.go`, `convert_test.go`, and `assistant_test.go` to reflect the new pointer type for `Optional`, ensuring proper assertions and error handling.
- Added new test cases to validate behavior when `Optional` is nil or false, improving test coverage and robustness of the ConnectorOptions functionality.
- Enhanced the `loadMap` function to include handling for `modes` and `default_mode` fields, allowing for flexible operational modes and a specified primary mode.
- Introduced a new `DB` field in the Assistant model to support database configuration, improving data management capabilities.
- Implemented the `ToModes` conversion function to facilitate various input types for modes, ensuring robust handling and validation.
- Added comprehensive tests for the `ToModes` function to validate its functionality across different input scenarios, enhancing overall reliability.
- Updated relevant methods to ensure consistent integration of the new fields and functionalities within the Assistant model.
- Replaced the deprecated getConnectorCapabilities method with a unified capability getter in the Assistant model, improving capability retrieval logic.
- Added a new API endpoint to retrieve essential assistant information, including fields like id, name, avatar, and connector options, enhancing the assistant's data accessibility.
- Updated the LLM management to support filtering by capabilities, allowing for more flexible provider listings based on user-defined models.
- Improved overall structure and clarity in the assistant's capabilities and API responses, ensuring better maintainability and usability.
- Introduced `modes` field to support multiple operational modes for the assistant, allowing for flexible functionality (e.g., chat, task).
- Added `default_mode` field to specify the primary mode of operation for the assistant.
- Updated the `Map`, `Clone`, and `Update` methods to handle the new fields appropriately.
- Enhanced the `ToAssistantModel` conversion function to include the new fields.
- Added tests to validate the integration and functionality of modes and default mode within the assistant model.
- Introduced a new `Database` type to encapsulate database models and options.
- Updated the `Assistant` model to include a `DB` field for database configuration.
- Enhanced the `Map`, `Clone`, and `Update` methods to handle the new `DB` field appropriately.
- Implemented the `ToDatabase` conversion function to support various input types for database initialization.
- Added comprehensive tests to validate the integration of the database functionality within the assistant model.
- Updated relevant fields and methods to ensure consistent handling of the new database configuration.
- Introduced GetStorage function for testing purposes, allowing retrieval of the current storage instance.
- Enhanced loadSource function to load scripts from the source field if present, improving assistant initialization.
- Updated comments for clarity on TypeScript handling in loadSource, ensuring better understanding of script loading mechanics.
- 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.
- Added methods to set and retrieve global prompts, enhancing the assistant's capabilities.
- Updated the assistant's message building process to include global prompts, ensuring context-aware parsing.
- Introduced tests to validate the integration and functionality of global prompts within the assistant.
- Improved context variable handling for prompt parsing, supporting dynamic content generation.
- Introduced the `disable_global_prompts` field in the Assistant model to control the usage of global prompts.
- Updated the Load and Get methods to initialize and retrieve global prompts from the configuration.
- Refactored tests to validate the new global prompts functionality and ensure proper loading and context handling.
- Improved the overall structure and clarity of the assistant's capabilities and configurations.
- Removed the GetByConnector method from the Assistant model to streamline the retrieval process.
- Introduced new fields for connector options and prompt presets, allowing for more flexible configurations.
- Updated the Map method to include additional fields such as connector options and prompt presets.
- Enhanced the Clone method to support deep copying of new fields.
- Improved the Update method to handle updates for the new source, connector options, and prompt presets fields.
- Refactored tests to ensure comprehensive coverage of the new functionalities and maintain clarity in the assistant structure.
- Enhanced the getConnectorCapabilities method to prioritize model capabilities and connector settings, improving capability retrieval logic.
- Deprecated the tools field in the Assistant model, transitioning to MCP for tool management, and updated related methods accordingly.
- Introduced new fields for connector options and prompt presets in the Assistant model, allowing for more flexible configurations.
- Updated the GetAssistant method to support field selection, improving data retrieval efficiency and flexibility.
- Refactored tests and documentation to reflect changes in the assistant structure and capabilities, ensuring clarity and maintainability.
- 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.
- Implemented traceLLMFail method to mark LLM requests as failed in the trace context.
- Updated executeLLMStream and executeLLMForToolRetry methods to call traceLLMFail on errors, enhancing error tracking and debugging capabilities.
- Improved overall error handling in LLM execution flows, ensuring failures are properly logged in the trace.
- Updated handleToolCall method to parse tool call delta data from OpenAI, improving the handling of single and multiple tool calls.
- Implemented dynamic delta actions ("append" for arguments, "merge" for static fields) to optimize message sending.
- Enhanced message structure to include appropriate DeltaAction and DeltaPath for better frontend integration.
- Improved error handling during JSON parsing to ensure robustness in tool call processing.
- Simplified context management by directly passing the existing context to the delegated assistant's Stream method, ensuring proper stack tracing.
- Updated comments to clarify the delegation process and the relationship between parent and delegated assistants, enhancing code readability.
- 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.
- Added error handling and logging for completion node creation in the traceAgentCompletion method, improving traceability of failures.
- Introduced a new replaceMethod in the context to allow message content replacement, enhancing message management capabilities.
- Updated documentation for sendMethod and replaceMethod to clarify usage and return values, improving developer experience.
- Updated the traceAgentOutput method to be deprecated in favor of the new traceAgentCompletion method, which creates a dedicated completion node for reporting final outputs.
- Enhanced the i18n messages to include labels and descriptions for the new agent completion functionality, improving localization support.
- Removed debug logging related to MCP tools from the buildCompletionOptions method to streamline the code and improve 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.
- Added detailed debug logging throughout the Stream method to trace execution flow and tool call results, improving visibility during runtime.
- Implemented error tracing with the new traceAgentFail method to capture failures in agent nodes, enhancing error handling.
- Updated MCP tools debugging to provide insights into tool application and validation processes, aiding in troubleshooting.
- Refactored output handling in traceAgentOutput for better clarity and consistency in response management.
- Renamed methods in ToolCallResult from ServerID to Server and ToolName to Tool for improved clarity and consistency.
- Updated i18n messages in builtin.go to remove redundant context, simplifying the label and description for the assistant's streaming process.
- Enhanced the Stream method to include a retry mechanism for tool calls, allowing for up to three attempts in case of errors.
- Introduced detailed logging for each retry attempt, improving traceability and debugging capabilities.
- Added a new method, buildToolRetryMessages, to construct messages for LLM retries, ensuring proper context is maintained.
- Updated the executeLLMForToolRetry method to handle streaming output during retries, providing real-time feedback to users.
- Improved error handling to differentiate between retryable and non-retryable errors, enhancing the robustness of tool call executions.
