Commit graph

29 commits

Author SHA1 Message Date
Max
2bd2a37c4b Implement VNC support in Sandbox V2 tests and enhance Docker test image
- Add new test cases for VNC URL generation and connection in `box_attach_test.go`, ensuring proper functionality of VNC features.
- Update the Docker test image to include VNC desktop components, enhancing the testing environment for graphical applications.
- Modify the entrypoint script to start a virtual framebuffer and VNC server, allowing for remote desktop access during tests.
- Increase the test timeout in the Makefile to accommodate longer-running VNC tests.

These changes improve the testing framework for Sandbox V2 by integrating VNC capabilities, facilitating better testing of graphical applications.
2026-03-05 15:07:53 +08:00
Max
dfb33681f9 Implement Sandbox V2 support in the Yao SDK
- Add new gRPC endpoint for Heartbeat in the Yao service, enabling communication with the sandbox.
- Update Makefile to include a dedicated unit test target for Sandbox V2, ensuring proper testing of new features.
- Enhance CI workflows to incorporate Sandbox V2 tests, allowing for dual-mode testing (local and remote) with Docker.
- Modify .gitignore to exclude specific Docker files while allowing shell scripts for Sandbox V2.
- Update documentation in DESIGN.md to reflect the new architecture and capabilities of the Sandbox V2.

These changes enhance the Yao SDK's functionality, providing improved support for sandbox operations and testing.
2026-03-05 13:21:09 +08:00
Max
6e68efaba3 Implement gRPC support in the Yao SDK
- Add gRPC server configuration to the application, allowing for gRPC communication.
- Introduce new Makefile targets for gRPC unit testing and proto code generation.
- Update CI workflows to include gRPC tests with SQLite as the transport layer.
- Refactor the sandbox design to support multi-node capabilities and improve isolation.
- Enhance the service layer to facilitate internal request forwarding for gRPC APIs.

This commit lays the groundwork for integrating gRPC into the Yao SDK, improving performance and scalability.
2026-03-04 13:17:48 +08:00
Max
add0424576 Refactor session cleanup logic to ensure single execution and improve resource management
- Replace direct cleanup calls in the Close method with a sync.Once mechanism to guarantee that cleanup runs only once.
- Remove the cleanup method and integrate its functionality into the Close method, streamlining resource management.
- Update the serve method to call Close for cleanup, enhancing clarity and consistency in session termination.
2026-02-26 15:35:47 +08:00
Max
a372a56cf0 Update IPC socket path in tests to match configuration change
- 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.
2026-02-09 00:07:48 +08:00
Max
6f50cf139a Update container IPC socket path in default configuration
- Change the ContainerIPCSocket path from "/tmp/yao.sock" to "/run/yao.sock" to align with system conventions for IPC sockets.

This change improves the configuration's compatibility with standard practices for inter-process communication.
2026-02-08 22:12:31 +08:00
Max
ac926b4233 Enhance container configuration for VNC images
- Add support for increasing the shared memory size (/dev/shm) for Chrome rendering in VNC images, setting it to a quarter of MaxMemory with a minimum of 256MB.
- This change addresses Chrome renderer/GPU process crashes by ensuring adequate memory allocation for namespace-based process isolation.
2026-02-08 20:30:04 +08:00
Max
ce4864cfde Enhance sandbox environment setup for VNC and Python compatibility
- 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.
2026-02-06 19:38:22 +08:00
Max
95cdf7961c Add Chrome support to sandbox module and update documentation
- Introduce a new Chrome image for the sandbox, enabling VNC access with real Chrome and CDP support (amd64 only).
- Update README to reflect the addition of the Chrome image and its build instructions.
- Modify build script to include a dedicated build process for the Chrome image.
- Enhance .gitignore to exclude the new Chrome plan file.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-06 17:48:49 +08:00
Max
28363b973e Fix sandbox compatibility, claude-proxy streaming, and rename playwright to browser
- 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>
2026-02-06 12:31:07 +08:00
Max
0a965c383d Add sandbox ID and VNC URL methods to sandbox executor
- 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>
2026-02-05 21:46:07 +08:00
Max
55164c5665 Enhance VNC sandbox images with Yao branding and sudo support
- Add passwordless sudo for sandbox user in playwright and desktop images
- Configure Yao branding for Fluxbox (CUI dark theme, centered logo)
- Configure Yao branding for XFCE (panel icons, wallpaper, workspace shortcut)
- Add D-Bus support for XFCE desktop environment
- Add dynamic wallpaper generation with configurable resolution and logo size
- Hide Fluxbox toolbar for cleaner Playwright automation view
- Create chromium wrapper script using Playwright's bundled browser
- Add feh and imagemagick for wallpaper management in Fluxbox
- Update .gitignore for config scripts and TODO file

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-05 18:23:15 +08:00
Max
69058787f9 Add VNC remote desktop support for sandbox containers
- Add VNC-enabled Docker images (playwright, desktop) with Xvfb, x11vnc, noVNC
- Implement VNC proxy service for WebSocket-based VNC access
- Add API endpoints: /sandbox/{id}/vnc, /vnc/client, /vnc/ws
- Support dynamic VNC port mapping for Docker Desktop (macOS/Windows)
- Add YAO_SANDBOX_VNC_PORT_MAPPING config option for local development
- Update build.sh to support building VNC images
- Include design document and updated README

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-05 14:45:54 +08:00
Max
702b743de7 Implement continuation support for Claude CLI commands
- 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>
2026-02-01 13:07:18 +08:00
Max
d78b4ea54a Refactor container file operations for improved performance
- Update ReadFile method to read directly from the host's bind-mounted workspace instead of using Docker's CopyFromContainer, enhancing performance.
- Introduce containerPathToHost method to convert container paths to host paths, ensuring proper access to bind-mounted directories.
- Simplify idle container cleanup logic by storing the idle time in a variable for better readability.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-01 11:24:47 +08:00
Max
8a138ced41 Remove remaining demux debug logs
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-01-31 23:13:43 +08:00
Max
ea8be6c287 Add secure proxy configuration with options and secrets support
- 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>
2026-01-31 22:46:48 +08:00
Max
019b606b13 Fix sandbox integration tests for claude-proxy architecture
- 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>
2026-01-31 14:36:01 +08:00
Max
3d16a9de77 Replace CCR with claude-proxy for Claude sandbox
- 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>
2026-01-31 12:44:29 +08:00
Max
c1e92b726d Implement MCP Configuration and Tool Integration for Sandbox
- 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.
2026-01-30 19:57:31 +08:00
Max
cd5cf32a20 Enhance Sandbox Integration and CI Workflow for AI Tests
- 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.
2026-01-30 17:41:06 +08:00
Max
f265aee974 Update Dockerfiles to Use Ubuntu 24.04 and Enhance Package Installation
- Updated base Dockerfile to use Ubuntu 24.04 LTS, ensuring long-term support until April 2029.
- Improved package installation in the base image by adding essential tools and utilities, including jq, vim, and network tools.
- Modified the Claude Dockerfile to reflect the new base image and updated Python version to 3.12.
- Added installation for Claude Code Router (CCR) and created an entrypoint script for CCR daemon mode, enhancing functionality for third-party LLM support.
2026-01-30 12:28:03 +08:00
Max
b40cea6887 Enhance Sandbox Configuration for CI and Testing
- Updated CI workflows to set the YAO_SANDBOX_CONTAINER_USER environment variable, ensuring proper user permissions during sandbox tests.
- Modified the Config struct to include ContainerUser, allowing for user specification in container execution.
- Improved test setup in config_test.go to clear conflicting environment variables, enhancing test reliability.
- Refactored manager_test.go to utilize the new getContainerUser function for consistent user handling across tests.
2026-01-29 20:13:40 +08:00
Max
68fd1919c0 Enhance Sandbox Test Configuration and Directory Management
- Added environment variables for YAO_SANDBOX_WORKSPACE and YAO_SANDBOX_IPC in the CI workflows to improve sandbox test configuration.
- Refactored test directory management in manager_test.go to utilize the new getTestDirs function, allowing for better handling of workspace and IPC directories, whether using environment variables or temporary directories.
- Improved cleanup logic to ensure temporary directories are removed only when created, enhancing test reliability.
2026-01-29 20:03:08 +08:00
Max
0394727f29 Enhance Config and Manager for Container Path Management
- Added ContainerWorkDir and ContainerIPCSocket fields to the Config struct for better container path configuration.
- Updated DefaultConfig to initialize new fields with default values.
- Modified the Manager to apply defaults for container paths and utilize them in container creation and execution methods, improving flexibility and reliability in container management.
2026-01-29 19:53:30 +08:00
Max
1ece4b0f48 Refactor Exec Method to Enhance Container Execution and Output Handling
- Implemented a readiness check to ensure the container is running before executing commands, improving reliability.
- Updated the method to create an exec instance and attach to it, allowing for better management of command execution.
- Enhanced output handling by reading from the exec response, ensuring context-aware output retrieval.
- Added logic to wait for exec completion and retrieve the exit code, improving feedback on command execution status.
2026-01-29 19:44:47 +08:00
Max
08e7ed36a3 Implement Container Readiness Check in Manager
- Added a loop in the ensureRunning method to wait for the Docker container to be in a running state before proceeding, enhancing reliability in container management.
- Included error handling for container inspection to ensure proper feedback in case of failures during the readiness check.
2026-01-29 19:38:03 +08:00
Max
55e43a7edd Enhance Exec Method with Context-Aware Output Handling and Timeout Verification
- Updated the Exec method to read output with context awareness, allowing for better error handling during command execution.
- Modified the TestExecWithTimeout to ensure it correctly verifies timeout behavior and measures execution duration, improving test reliability.
- Added logic to create parent directories in WriteFile method, ensuring proper file handling within containers.
2026-01-29 19:31:19 +08:00
Max
d4bed4f277 feat(sandbox): add persistent Docker sandbox for external CLI agents 2026-01-29 19:23:50 +08:00