- Modified Docker run commands in CI workflows to include the `-direct` flag for enhanced server operation.
- Removed outdated loading status message during sandbox preparation and added new messages for improved user feedback.
- Introduced a loading message for waiting on AI responses, enhancing the user experience during sandbox execution.
- Refactored identity handling in stream processing to streamline message management.
Made-with: Cursor
- Updated Docker run commands in CI workflows to include the `-direct` flag for improved server operation.
- Implemented image existence checks and automatic pulling for sandbox environments, enhancing reliability during initialization.
- Added loading status updates for sandbox operations, providing better feedback during the setup process.
- Refactored lifecycle management to ensure accurate tracking of sandbox states and improved error handling.
Made-with: Cursor
- Introduced a human-readable display name for the sandbox, constructed from the agent and workspace names.
- Updated the BuildIdentifier function to include workspace ID in identifiers for long-running and persistent lifecycles.
- Modified sandbox creation options to incorporate the display name, improving clarity in sandbox management.
- Refactored related tests to ensure compatibility with the new identifier structure and display name integration.
Made-with: Cursor
- Added support for issuing and passing a sandbox token during stream execution in the Assistant.
- Updated StreamRequest to include a Token field for managing user authentication.
- Enhanced ClaudeRunner to set environment variables for the sandbox token and refresh token.
- Refactored SandboxToken structure to clarify its purpose and manage token credentials effectively.
- Modified sandbox management routes to enforce OAuth guard for improved security.
Made-with: Cursor
- Implemented a new endpoint to retrieve the absolute path of a workspace's root directory.
- Enhanced the workspace interface with a GetRoot method to facilitate this functionality.
- Updated the workspace manager to utilize the new method for improved path resolution.
Made-with: Cursor
- Updated the AssistantInfo struct to include new fields: Connector, ConnectorOptions, Modes, DefaultMode, Sandbox, and ComputerFilter for improved assistant configuration.
- Enhanced the loading process to extract Sandbox flag and ComputerFilter from V2 sandbox configuration.
- Refactored GetInfo method to return comprehensive assistant details for better UI integration.
- Introduced new endpoint for workspace options to streamline InputArea selector functionality.
Made-with: Cursor
- Refactored the sandbox initialization process to resolve the connector before obtaining the Computer, allowing for the injection of OPENAI_PROXY_* environment variables.
- Updated the GetComputer and BuildCreateOptions functions to accept an optional connector parameter for improved environment variable management.
- Standardized the VNC configuration by replacing SANDBOX_VNC_ENABLED with VNC_ENABLED across Dockerfiles and related scripts for consistency.
- Enhanced the VNC service startup script to check the new VNC_ENABLED variable, ensuring proper service initialization.
Made-with: Cursor
- 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 fallback mechanism in the GetConnector method to use a default connector if the specified connector is not found.
- Add logging to notify when falling back to the default connector, improving debugging and traceability.
- Update comments for clarity on connector selection priority, ensuring better understanding of the logic flow.
- Introduce a new field for dependencies in the Assistant model to manage external MCP client dependencies with version constraints.
- Implement deep copy functionality for dependencies in the Clone method to ensure integrity during assistant cloning.
- Enhance the Update method to handle dependencies input from data maps, supporting both string and interface types.
- Update the Map method to include dependencies in the serialized output.
- Add comprehensive tests to validate loading, cloning, and mapping of dependencies, ensuring correct behavior across various scenarios.
- 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.
- Implement TestEnsureChatMetadata to verify that metadata, including robot_id, is correctly persisted in chat records.
- Update EnsureChat method to store metadata from the context when creating chat records.
- Introduce TestExecutorGoalsInjection to validate that pre-confirmed goals are injected into executions from TriggerInput.Data.
- Enhance executor logic to handle goal injection and persistence, ensuring accurate execution titles.
- Modify chat filtering to support chat_id_prefix for improved chat retrieval based on robot identifiers.
- Modify the sandbox integration test to load a different assistant configuration, ensuring accurate testing of sandbox capabilities.
- Refactor JSON field parsing in the Xun store to handle both string and byte slice types, improving robustness in data processing and ensuring proper unmarshalling of JSON fields.
- Introduce `Capabilities` and `Sandbox` fields in the Assistant model, allowing for detailed descriptions of assistant capabilities and sandbox configurations.
- Update loading and conversion functions to handle the new fields, ensuring they are correctly parsed and stored.
- Modify filtering and response handling to include the new fields, providing better integration with the API.
- Add comprehensive tests to validate the functionality of the new fields, ensuring they are correctly processed 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.
- Add new indirect dependencies including various Charmbracelet packages for improved UI handling.
- Enhance logging in the Assistant module by adding tool completion and start logging for better traceability of tool calls.
- Modify context handling in the RequestLogger to support a stack-based assistant ID management, improving the logging structure for agent requests.
- Implement event service integration for better trace management and debugging capabilities.
- Add a new `MergeMetadata` function in the `Context` struct to allow merging of caller-provided metadata into the context, enabling sub-agent hooks to access this information.
- Update the `Stream` method in the `Assistant` to utilize the new metadata merging functionality, enhancing the context management for sub-agents.
- Eliminate the `openai` field from the `Assistant` struct and its initialization in the `initialize` method, streamlining the Assistant's internal structure.
- This change simplifies the codebase by removing unnecessary dependencies on the OpenAI API, enhancing maintainability.
- Add handling for Anthropic connector types in the sandbox, allowing direct connections without a proxy.
- Enhance capability retrieval to support both OpenAI and Anthropic formats, ensuring a unified interface.
- Update the executor and command logic to differentiate between OpenAI and Anthropic configurations, streamlining environment setup.
- Modify the provider selection logic to accommodate Anthropic capabilities, improving flexibility in LLM provider management.
- Refactor API detection to include Anthropic, ensuring accurate identification of connector types.
- Implement secure config file location (/tmp/.yao/proxy.json) instead of user-visible /workspace/
- Add generic options map support for backend-specific parameters (e.g., thinking for Volcengine GLM-4.7)
- Add secrets support for passing sensitive env vars (e.g., GITHUB_TOKEN) to sandbox container
- Remove excessive debug logs, keep critical ones with log.Printf("[Sandbox]...")
- Fix test assertions for system prompt passing via CLI args instead of env var
- Update i18n messages for sandbox loading states
Co-authored-by: Cursor <cursoragent@cursor.com>
- Fix Claude CLI output parsing: only extract content from final
assistant message (with stop_reason) to avoid duplicate content
- Remove trailing "..." from sandbox loading message
Co-authored-by: Cursor <cursoragent@cursor.com>
- Update TestClaudeCommandBuilding to expect new command format
- Rename TestClaudeCCRConfigBuilding to TestClaudeProxyConfigBuilding
- Update assertions for claude-proxy env vars instead of CCR
- Apply gofmt formatting to proxy/types.go
Co-authored-by: Cursor <cursoragent@cursor.com>
- Add --input-format stream-json, --output-format stream-json, --verbose flags
- Use heredoc to pass messages via stdin (no CLI length limit)
- Add BuildInputJSONL function for message conversion
- Add shouldSkipClaudeCLI logic to skip when no prompts/skills/mcp
- Update executor to conditionally start claude-proxy only when needed
- Add SystemPrompt field to Options for skip logic
- Add E2E tests for skip mode and command building
- Fix tests to reflect new command structure
Co-authored-by: Cursor <cursoragent@cursor.com>
- Modified the command verification in the sandbox integration test to assert the new command structure, which now starts with "bash" and includes specific arguments for executing CCR commands.
- Enhanced assertions to check for the presence of required command components, improving the robustness of the test.
- Added functionality to build and manage MCP configuration for sandbox environments, allowing for dynamic tool execution.
- Enhanced the Assistant's Stream method to skip MCP tool calls in sandbox mode, with internal handling by Claude CLI.
- Introduced unit tests for MCP configuration building and skills directory resolution, ensuring robust integration.
- Updated sandbox manager to create IPC sessions and manage tool exposure dynamically, improving interaction with external agents.
- Enhanced documentation to reflect new features and integration points for MCP and skills within the sandbox.
- Updated the sandbox integration test to verify JSON fields using snake_case for CCR configuration.
- Added detailed documentation for the sandbox API, including properties, methods, and use cases for file operations and command execution.
- Enhanced context API documentation to include sandbox operations, improving clarity on available features when sandbox is configured.
- 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.
- Updated `logrus` dependency from v1.9.3 to v1.9.4 and `golang.org/x/sys` from v0.38.0 to v0.40.0 for improved functionality and security.
- Introduced a `Fork` method in the agent context to create child contexts for concurrent agent and LLM calls, preventing race conditions on shared state during batch operations.
- Enhanced the `Orchestrator` methods to utilize forked contexts, ensuring independent execution of agent calls without interference.
- 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 a new `RobotPrompt` field in the `Uses` struct to allow for custom robot system prompts.
- Updated the `Load` function to initialize `RobotPrompt` with a default value if not provided.
- Modified the `SystemConfig` struct to include a connector for the new `RobotPrompt` agent.
- Enhanced the asset binding to include new files related to the `robot_prompt` assistant.
- Updated related documentation and tests to reflect the addition of the `RobotPrompt` functionality.
- Removed dependency on KB configuration in tests, as KB collections are now created during user login.
- Updated test cases to reflect new initialization scenarios, ensuring they handle various conditions gracefully.
- Renamed test functions for clarity, emphasizing the focus on initialization rather than collection creation.
- Removed the synchronous preparation of the knowledge base (KB) collection from the InitializeConversation method, now initializing it asynchronously after user login.
- Introduced a new method, GetDocumentsContent, to retrieve content for multiple documents by their IDs, supporting text-based files and improving document handling.
- Updated the API interface to include the new GetDocumentsContent method, enhancing the document management capabilities.
- Enhanced locale handling in the login context to support user preferences during KB collection creation.
- Added logic to skip internal message types ("tool_call", "loading", "action", "event") during LLM context conversion to prevent confusion, while retaining "error" messages for troubleshooting purposes.
- Improved clarity in the handling of message types to ensure only relevant content is processed for LLM interactions.
- 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.
- Removed unnecessary semicolon in the buildStandardResponse method, aligning with Go's idiomatic style.
- Improved code readability by ensuring consistent formatting in the handling of the NextResponse variable.
- Updated the buildStandardResponse method to assign the NextResponse to a variable only if it is not nil, improving code clarity and preventing potential nil pointer dereferences.
- This change enhances the robustness of the response building process in the Assistant's delegation handling.
- Updated the Stream method to include options for handling message history and context more effectively, ensuring original messages are preserved for autoSearch and delegation.
- Introduced a new buildContextMessage function to consolidate conversation context, filtering out system messages and limiting to the last five user messages for efficiency.
- Enhanced content processing by adding a convertToContentParts function to handle different content formats, improving compatibility with historical data.
- Improved logging and error handling in the executeLLMStream method to ensure clarity in LLM request tracing and response handling.
- Added new utility functions for extracting text content and building context messages, enhancing overall code clarity and maintainability.
- Updated the BufferUserInput method to ensure only the root stack buffers user input, preventing duplication in delegated agents.
- Added comments in the Stream and processNextResponse methods to clarify that user input is already buffered by the root agent, allowing delegated agents to skip this step.
- Improved code clarity and maintainability by documenting delegation behavior in the context of user input handling.
- 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_called` and `tool_result` assertions in the Asserter, allowing for validation of tool execution and arguments.
- Introduced methods to check if specific tools were called and to validate their results against expected patterns.
- Updated the `README.md` to include detailed documentation on new assertion types, including usage examples and value formats.
- Enhanced the dynamic runner to set the response for tool-related assertions, improving the overall testing framework's capabilities.
- 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.
- Increased the allowed memory growth threshold per iteration in the memory leak tests from 15KB to 20KB to accommodate higher memory usage observed in business scenarios and standard mode operations.
- Updated comments to reflect the rationale behind the new threshold and to clarify expected memory behavior during tests, ensuring better understanding and accuracy in leak detection.
- 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.
- Removed hardcoded collection IDs in `search_auth_integration_test.go` and replaced them with dynamically generated IDs to ensure uniqueness during test runs.
- Simplified the setup and cleanup processes by introducing the `authTestCollections` struct, which manages the lifecycle of test collections.
- Updated test cases to utilize the new collection management approach, enhancing test reliability and reducing potential conflicts during parallel execution.
- Updated the cleanup process in `cleanupAuthCollections` to include a waiting mechanism for Qdrant to fully process deletions, improving reliability of test setups.
- Removed unnecessary sleep calls and added logging to warn if collections still exist after cleanup, ensuring better visibility during test execution.
- Refactored comments for clarity regarding the cleanup process in both `TestAuthSearchSetup` and `ensureAuthTestData` functions.
- Introduced a new script testing mode to allow testing of agent handler scripts (hooks, tools, etc.) using a Go-like interface, enabling better unit testing of TypeScript/JavaScript code.
- Enhanced the `LoadScripts` function to skip test files during script loading, ensuring only relevant scripts are processed.
- Refactored the test context creation to support custom context configurations via a JSON file, allowing for flexible authorization and metadata management during tests.
- Updated the test runner to handle script tests, including the ability to filter tests using regex patterns and manage custom context data.
- Improved documentation to include details on script testing usage, input formats, and available assertions, enhancing developer experience and clarity.
- Removed redundant test environment initialization code and replaced it with a streamlined approach using `testutils.Prepare` for better clarity and maintainability.
- Introduced utility functions `ensureAuthTestData` and `createAuthTestData` to manage the setup of test collections and documents, ensuring that necessary data is available for tests.
- Updated multiple test cases to utilize the new data initialization methods, improving test reliability and reducing setup complexity.
- Renamed functions for consistency and clarity, changing `buildDBAuthWheres` to `BuildDBAuthWheres` and `filterKBCollectionsByAuth` to `FilterKBCollectionsByAuth`.
- Enhanced test cases to utilize the updated function names, ensuring proper authorization checks in the search functionality.
- Improved test environment initialization to streamline setup processes and ensure robust testing of authorization logic.
- Verified that search results adhere to authorization constraints, ensuring only accessible collections are queried based on user permissions.
