- Added locale support in various components, including the Assistant's execution context and agent tools, to improve internationalization.
- Updated the `pickNodeByFilter` function to include a fallback mechanism for host_exec nodes when no container nodes are available.
- Introduced a new `agent_reference` tool for downloading agent source code for read-only study, alongside updates to the `agent_download` tool to restrict downloads to the 'smith' namespace.
- Enhanced documentation and tests to reflect the new functionalities and ensure robust locale extraction and handling.
- Implemented AssistantReloadFunc to enable hot-reloading of assistants after deployment, improving deployment flexibility.
- Enhanced gRPC authProvider to include workspace and sandbox IDs from incoming context metadata, enriching the authentication context.
- Updated tools to support new agent-related functionalities, including listing, downloading, deploying, and connecting agents.
- Expanded system tools documentation to include new agent commands, ensuring comprehensive guidance for users.
- Refactored the initSandboxV2 function to return a structured result, consolidating the runner, computer, configuration, cleanup function, loading message ID, and roles into a single return type.
- Updated the Stream method to utilize the new sandboxV2InitResult structure, improving clarity and reducing complexity in handling sandbox initialization.
- Introduced role management enhancements, allowing for pre-resolved role connectors to be passed through the request, streamlining connector resolution during execution.
- Adjusted various components to support the new roles structure, ensuring consistent handling across the agent's sandbox operations.
- Added logging for connector resolution and role management, improving diagnostics and traceability during sandbox execution.
- Updated .gitignore to include tools/TOOL-REGISTRATION.md for better project organization.
- Skipped tests related to KB/DB search functionality due to temporary unavailability.
- Updated test cases in chat_test.go, search_auth_integration_test.go, search_auto_full_test.go, and others to reflect this change.
- Adjusted search handling in search.go to limit search types to "web" only until KB/DB search is re-enabled.
- 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.
- Introduced a new "Heavy" role in the system configuration, allowing for complex reasoning tasks.
- Updated the initialization and environment resolution functions to handle the new Heavy role appropriately.
- Enhanced tests to validate the integration of the Heavy role, ensuring proper connector resolution and model handling.
- Adjusted OpenAPI settings to reflect the addition of the Heavy role, improving overall system capabilities.
- Integrated logging for connector resolution failures, providing clearer diagnostics during fallback scenarios.
- Simplified connector ID extraction in various components, ensuring accurate handling of model identifiers.
- Updated model configuration to support new parameters and capabilities, improving overall provider management.
- Enhanced OpenAPI settings to reflect changes in model options and connector behavior, ensuring better alignment with upstream API requirements.
- Updated the system configuration to include new role-level defaults for Light, Vision, and Audio connectors.
- Refactored the resolveSystemConnector function to prioritize per-agent overrides, improving connector resolution logic.
- Enhanced LLMConnector integration across various components to streamline settings retrieval and capabilities management.
- Improved error handling and logging for connector-related operations, ensuring better diagnostics and user feedback.
- Replaced 'Voice' with 'Audio' in the system configuration and related tests to better reflect functionality.
- Introduced new methods for role management in the llmprovider, allowing for dynamic retrieval of roles based on user and team context.
- Updated the OpenAPI settings to support new role management endpoints and capabilities.
- Enhanced the handling of API keys in provider management, allowing for optional plain-text retrieval.
- Upgraded several dependencies in go.mod and go.sum, including golang.org/x/crypto, golang.org/x/net, golang.org/x/sys, and google.golang.org/grpc to their latest versions for improved security and performance.
- Updated opentelemetry packages to v1.43.0 and added new indirect dependencies for better observability support.
- Adjusted the handling of execute messages in stream.go to ensure proper persistence based on message status.
- Enhanced command handling in command.go to maintain system prompt constraints during continuation turns.
- Implemented GetWorkspaceID method in the context package to retrieve the workspace ID.
- Updated buildContextVariables to include WORKSPACE_ID in the context variables if available.
- Enhanced buildEnv function to set CTX_WORKSPACE_ID in the environment configuration based on the workspace ID.
- Refactored role connector handling to support multiple connectors in the environment setup.
- Added tests for new role connector functionality and workspace ID integration.
- Introduced Vision and Voice fields in the SystemConfig and System types to support new capabilities.
- Updated resolveEnvStrings function to handle environment variables for Vision and Voice.
- Enhanced unit tests to validate the new Vision and Voice configurations, ensuring correct environment variable resolution.
- Added GetVisionConnector and GetVoiceConnector functions to retrieve connectors for vision and voice capabilities.
- Introduced NanoToTime and TimeToNano functions for converting between UnixNano and time.Time, improving clarity and consistency in timestamp management.
- Updated Assistant model to utilize the new utility functions for created_at and updated_at fields.
- Refactored Xun store methods to ensure UTC compatibility for timestamp serialization across different database drivers.
- Added unit tests for the new conversion functions to validate their correctness and behavior.
Modified the initSandboxV2 function to return a per-request copy of the SandboxConfig, ensuring that concurrent requests to the same assistant have their own mutable configuration. Updated related logging and cleanup processes to utilize the new configuration structure. Additionally, introduced a DefaultOneShotMaxAge constant to manage the lifecycle of OneShot containers more effectively.
- Renamed ClaudeRunner to Runner for consistency across the codebase, aligning with the sandbox Runner interface.
- Updated buildCommand and Stream methods to utilize AssistantID directly from StreamRequest, improving clarity and reducing dependency on Config.
- Modified tests to reflect the changes in runner instantiation and argument handling, ensuring compatibility with the new Runner structure.
- Enhanced environment variable setup in buildEnv to include WORKDIR, streamlining the execution context for the runner.
- Updated logging in various methods to include detailed traces for better monitoring of execution flow, including assistantID and chatID.
- Improved context management by ensuring proper release of resources and tracking of execution durations in agent calls.
- Added heartbeat logging in the Claude parser to monitor stream processing and prevent potential issues with long-running tasks.
- Refined the .gitignore file to exclude additional markdown files in the sandbox directory.
- Enhanced the extractSandboxVersion function to support multiple input types, including *sandboxTypes.SandboxConfig and map[string]any, for better flexibility in version retrieval.
- Simplified the version extraction process, ensuring consistent handling of sandbox configurations.
- Added support for sandbox configuration in the LoadPath function, allowing for better management of sandbox settings.
- Updated tests to validate the retrieval of assistant tags with type filters, ensuring accurate responses for both assistant and robot types.
- Enhanced the assistant model to differentiate between sandbox versions, improving the handling of sandbox data in the database.
- Improved API responses to include computer filter details for V2 sandboxes, enhancing the information returned to clients.
- Removed the RegisterProxyConfigs function and its related logic from the sandbox initialization, simplifying the setup process.
- Updated the GetComputer function to handle connector configuration injection directly within the ClaudeRunner.Stream method, ensuring a more cohesive approach to configuration management.
- Introduced a new injectA2OConfig function to push connector configurations to the a2o proxy, enhancing flexibility and error handling.
- Improved logging for connector configuration injection to provide better traceability during execution.
- Introduced a new sandboxV2StreamParams struct to group parameters for the executeSandboxV2Stream function, improving code clarity and maintainability.
- Updated the GetComputer function to handle connector configuration injection via the a2o proxy, removing the need for direct connector parameters.
- Enhanced the executeSandboxV2Stream function to utilize the new parameters struct, simplifying the function signature and improving readability.
- Implemented RegisterProxyConfigs to inject OpenAI-compatible connector configurations into the a2o proxy, ensuring proper environment setup for sandbox execution.
- Refactored BuildCreateOptions to remove direct connector handling, aligning with the new configuration injection approach.
- Added detailed trace logging in the Assistant's Stream function to capture computer and workspace information.
- Replaced fmt.Printf statements with kunlog.Trace in the Telegram polling adapter for consistent logging.
- Updated sandbox lifecycle management functions to utilize kunlog for logging workspace and node resolution details.
- Enhanced error handling in the Claude parser with trace logging for JSON unmarshal and scanner errors.
- Improved file handling logging in the workspace API to provide clearer insights into file read operations.
- Added support for "execute" message type to track tool execution observations within the sandbox environment.
- Implemented handling for execute messages in the stream processing, allowing for real-time updates on tool execution status.
- Enhanced the stream parser to manage the lifecycle of execute messages, including merging input and output data.
- Updated the stream handler to accommodate new message types, improving overall message processing capabilities.
- Refactored related tests to ensure coverage for the new execute message functionality, enhancing reliability.
- Updated the sandbox initialization to resolve both the assistant directory and skills subdirectory, improving directory management.
- Modified the RunPrepareSteps function signature to include an assistantDir parameter, allowing for better handling of file copy operations.
- Adjusted all relevant calls to RunPrepareSteps across the codebase to accommodate the new parameter, ensuring consistency in execution.
- Enhanced test cases to reflect the updated function signature, improving coverage and reliability of the sandbox preparation process.
- 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.
