- 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.
- Update the filename logic in convertAttachments to prefer the semantic title from the delivery agent over the raw storage filename.
- Ensure the original file extension is preserved when using the human-readable title, improving clarity for email clients.
- Adjust logging to reflect the updated filename handling for better observability during attachment processing.
- Update DeliveryPayload to use structured types for Content and Preferences, enhancing type safety and readability.
- Modify tests to reflect changes in payload structure, ensuring proper serialization and deserialization of delivery content.
- Implement a new robotHandler for processing delivery events, streamlining the handling of different delivery channels (email, webhook, process).
- Remove the deprecated DeliveryCenter, consolidating delivery logic within the new handler for better maintainability.
- Enhance error handling and logging during delivery processing to improve observability and debugging capabilities.
- Change clock trigger time in tests from 09:00 to 03:33 for more accurate simulation.
- Ensure cleanup of integration robots is performed before each test run to maintain test isolation.
- Stop the manager before assertions to prevent unintended executions during test validation.
- Refactor execution listing to support pagination with `Page` and `PageSize` options, replacing previous `Limit` and `Offset` parameters.
- Introduce `ExcludeStatuses` in execution queries to filter out specific execution statuses.
- Implement streaming interaction methods in the manager, allowing real-time responses from the host agent during interactions.
- Update API endpoints to accommodate new query parameters and enhance interaction capabilities with streaming support.
- Modify tests to ensure coverage for new pagination and streaming functionalities.
- Add `language_model` field to robot data structures for LLM connector overrides.
- Update `AgentCaller` to utilize the robot's language model and include logging capabilities for agent calls.
- Refactor task execution to log task outputs and inputs, improving observability during execution.
- Modify tests to accommodate changes in the runner initialization and ensure proper logging functionality.
- Update multiple test cases in interact_helpers_test.go to include Status and Phase fields in ExecutionRecord, ensuring comprehensive coverage for human-triggered actions.
- Replace direct error handling with require.NoError for improved test reliability and clarity in error reporting during execution store saves.
- Update multiple test cases in interact_helpers_test.go to include TriggerType set to types.TriggerHuman in ExecutionRecord.
- Ensure consistency in testing scenarios involving human-triggered executions, enhancing clarity and coverage in unit tests.
- Rename test folders and commands in the Makefile for consistency, changing references from AI to Agent tests.
- Update GitHub Actions workflows to reflect the new naming conventions for agent and robot tests, ensuring clarity in CI processes.
- Modify test cases to improve readability and maintainability, including renaming test functions for better understanding of their purpose.
- Enhance comments in the Makefile and workflows to provide clearer context on the testing processes and requirements.
- Implement V2 execution model in the standard executor, simplifying task execution to a single call without validation loops.
- Introduce support for resuming suspended executions, allowing for human input during task processing.
- Enhance event handling by pushing task completion and failure events to the event bus for better tracking and integration.
- Update tests to reflect changes in execution flow and ensure robust handling of task statuses and results.
- 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.
- Introduce `resolveEnvStrings` function to handle `$ENV.XXX` references in the agent's DSL settings, ensuring that environment variables are correctly substituted in system and uses fields.
- Enhance `Load` function to call `resolveEnvStrings` during the loading process, improving the configuration handling for agents.
- Add comprehensive unit tests for `resolveEnvStrings` to validate the correct resolution of environment variables across various fields and scenarios, including handling of undefined variables and plain strings.
- Ensure that the implementation maintains existing functionality while enhancing flexibility for environment-based configurations.
- 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.
- Update `CallTool`, `CallTools`, and `CallToolsParallel` methods to pass the context as an additional argument, allowing for proper authorization propagation.
- Modify `buildAuthorizedInfo` to include `TeamID` in the `AuthorizedInfo` struct.
- Improve path resolution in `ResolvePathWithYaoRoot` to prioritize application root before falling back to the current working directory.
- Adjust `LoadContextConfig` to read the context configuration file using the resolved path, enhancing file handling robustness.
- 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.
- Clean up the code for sending the initial ChunkToolCall, improving readability and maintaining alignment with OpenAI's format for tool name resolution.
- Ensure that the chunk count is incremented after sending the tool call data, enhancing the message handling process in the streamWithRetry function.
- Implement functionality to send an initial ChunkToolCall with the event's ID and function name, aligning with OpenAI's format for tool name resolution.
- Enhance message tracking by incrementing the chunk count after sending the tool call data, improving the overall message handling process in the streamWithRetry function.
- Update the `ToMap` function in `capabilities.go` to include the `stt` capability from OpenAI.
- Modify the `convertAnthropicCaps` function to map the `STT` field from Anthropic capabilities.
- Enhance documentation in `llm.go` to describe the new `stt` capability for audio transcription models.
- Update `forceSkipForSubAgent` to respect caller's `skip.output` setting, allowing for silent internal worker agent execution.
- Refactor error handling in `callAgentWithContext` to utilize a new `NewResult` function for consistent result construction.
- Introduce `ProcessCallRequest` structure for improved agent call parameters, including a default timeout constant for process calls.
- 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.
- Added a call to `CloseSafeWriter` in `TestJsValueStreamingWorkflow` to flush all pending async writes before reading the output buffer. This change improves test reliability, particularly on slow CI runners, by preventing potential issues with empty buffers.
- Add calls to `CloseSafeWriter` in `TestJsValueSendVsSendStream` to ensure all pending async writes are flushed before reading the output buffer. This change addresses potential issues with empty buffers on slow CI runners, improving test consistency.
- Include `ANTHROPIC_API_KEY` in both `pr-test.yml` and `unit-test.yml` workflows to support Anthropic API integration.
- Refactor tool call processing in `anthropic.go` to ensure deterministic order by sorting tool call indices before processing, enhancing reliability in tool call execution.
- 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.
- Refactor the `ResolveScript` function to improve the script path resolution strategy, allowing for better handling of assistant directories and module paths.
- Update asset metadata timestamps in `bindata.go` to reflect recent changes, ensuring accurate tracking of file modifications.
- Modify CSS component name formatting in `build.go` and TypeScript component selectors in `index.ts` for consistency in syntax.
- Improve locale handling in `locale.go` by implementing a fallback mechanism for locale file resolution based on language prefixes.
- Normalize locale values in `request.go` to lowercase for consistency across the application.
- Enhance component name sanitization in `utils.go` to replace additional characters, ensuring valid component naming conventions.
- Modify the test for the Claude executor to check for the IPC socket at the new path "/run/yao.sock" instead of the previous "/tmp/yao.sock". This aligns the test with the updated default configuration for the IPC socket path, ensuring consistency across the codebase.
- Modify the expected API URL in the `TestBuildProxyConfig` to include the `/v1` prefix for consistency with the updated URL building logic.
- Remove unnecessary `modified` flags in the `prepareAttachments` method to streamline attachment processing and ensure clarity in the codebase.
This change enhances the accuracy of tests and improves the maintainability of the attachment handling logic.
- Introduce a whitelist mapping for `package.yao` sandbox arguments to corresponding Claude CLI flags, allowing selective argument passing.
- Update `BuildCommandWithContinuation` to iterate over the whitelist and append valid arguments to the Claude CLI command.
This change enhances the flexibility of argument handling in the Claude CLI, ensuring only specified arguments are processed.
- Update `buildAPIURL` function in OpenAI provider to delegate URL construction to `connector.BuildAPIURL`, ensuring consistent URL formatting across the agent LLM and sandbox proxy paths.
- Modify backend URL construction in Claude's `BuildProxyConfig` to utilize the shared `connector.BuildAPIURL` helper, applying the necessary `/v1` prefix for compatibility.
This change enhances code maintainability and consistency in API URL handling across different components.
- Introduce functionality to resolve and manage user-uploaded files in the sandbox environment.
- Implement `prepareAttachments` method to convert attachment URLs to local file paths and handle duplicates.
- Update message processing to replace attachment content with text references, allowing Claude CLI to access files using Read and Bash tools.
- Enhance documentation to inform users about the new attachment handling capabilities.
This change improves the interaction with user-uploaded files, enabling better integration within the Claude CLI environment.
- Ensure the existence of $HOME/.Xauthority for PyAutoGUI/Xlib compatibility.
- Adjust PYTHONPATH to maintain access to user-installed Python packages.
- Explicitly set XAUTHORITY to the correct path for X11 authentication.
- Pass secrets as environment variables for Claude CLI to ensure proper access.
- Refactor VNC image support check to utilize a centralized keyword list for better maintainability.
- Fix ListDir to support BusyBox/Alpine ls by falling back from GNU
--time-style format, resolving CI test failures
- Update parseLS to handle both GNU (epoch) and BusyBox (date string) formats
- Fix claude-proxy streaming: always include usage in message_delta events
to prevent Claude CLI from falling back to non-streaming mode
- Fix claude-proxy non-streaming: ensure usage is always present in responses
- Add paragraph separators between text blocks in Claude executor stream parser
- Translate VNC proxy UI from Chinese to English
- Rename sandbox-claude-playwright to sandbox-claude-browser across
Dockerfiles, build scripts, and documentation
Co-authored-by: Cursor <cursoragent@cursor.com>
- Implement GetSandboxID method to return a mock sandbox ID for testing.
- Add GetVNCUrl method to return an empty string for VNC access in tests.
- Update SandboxExecutor interface to include new methods for sandbox identification and VNC URL retrieval.
- Enhance context creation to set sandbox ID and VNC URL properties in the sandbox instance.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Update start command to check if the current directory is a Yao app root or a subdirectory, providing clearer error messages for users.
- Modify installation logic to handle empty directories more effectively, ensuring the init app is installed only when appropriate.
- Improve welcome message formatting and update links for documentation and community resources.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Replace the existing NanoID generation in generateContextID with UUID for improved uniqueness.
- Update RequestID method to return the context ID directly instead of generating a new NanoID.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Refactor BuildCommand to support session continuation using --continue flag.
- Introduce BuildCommandWithContinuation to handle both initial and continuation requests.
- Add BuildLastUserMessageJSONL for generating JSONL from the last user message in continuation scenarios.
- Enhance Executor to check for existing sessions and adjust command building accordingly.
- Update environment setup to ensure session data is stored correctly for persistence.
Co-authored-by: Cursor <cursoragent@cursor.com>
- 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>
- Send ChunkMessageStart before ChunkText in parseStream
- This initializes stream state (inGroup=true) required for Buffer.AddAssistantMessage
- Only send ChunkMessageEnd if message was started
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>
- Fix missing SystemPrompt field in sandbox executor options conversion
(was causing Claude CLI to be skipped even when prompts were configured)
- Rewrite parseStream to handle Claude CLI stream-json output format:
- system: initialization message
- assistant: message with content array (text, tool_use)
- result: final result with verification string
- Add comprehensive E2E tests via caller for sandbox integration:
- TestSandboxE2E_ClaudeCLIExecution: verify command execution
- TestSandboxE2E_FileCreation: verify file operations
- TestSandboxE2E_HookOnlyMode: verify Claude CLI skip logic
- TestSandboxE2E_StreamingResponse: verify streaming works
- Add real_e2e_test.go for direct Claude CLI execution testing
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>
- Add claude-proxy: lightweight Go proxy to translate between Anthropic
and OpenAI-compatible APIs with full streaming and tool-calling support
- Update Dockerfile to include claude-proxy binary (multi-arch)
- Add auto-start proxy via entrypoint when env vars are set
- Update executor.go to write proxy config and start proxy
- Simplify command.go to use direct Claude CLI with proxy
- Support both docker run -e and config file for proxy settings
Co-authored-by: Cursor <cursoragent@cursor.com>
- Adjusted assertions in the command test to verify the updated command structure, which now begins with "bash" and includes specific flags for executing CCR commands.
- Enhanced the test to ensure the user prompt is correctly included in the command, improving the accuracy of the test verification.
- 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.
