- Introduced handlers for the new /setting/* endpoints in the OpenAPI module.
- Updated import statements to include the new setting package for better organization.
- Enhanced routing capabilities to support the new settings functionality.
- Updated database configuration to include PostgreSQL 14.0 in CI workflows.
- Enhanced JSON null detection in the Xun store to support PostgreSQL dialect.
- Refactored time conversion utilities to handle multiple database formats, including PostgreSQL.
- Improved cleanup logic in the DataCleaner to ensure proper order of operations for referential integrity.
- Added utility functions for converting between Unix timestamps and database timestamps.
- 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.
- Updated agent context to ensure locale is propagated correctly, defaulting to "en" when no locale is provided. This change enhances internationalization support and ensures consistent behavior across different contexts.
- Adjusted test assertions to reflect the updated execution trigger logic for times mode robots, allowing for a maximum of 2 triggers instead of 1.
- Renamed ListRobots function to ListAllRobots for clarity and consistency across the codebase.
- Updated related API endpoints and tests to reflect the new function name.
- Improved caching logic to ensure both autonomous and non-autonomous robots are loaded correctly.
- Enhanced filtering and pagination capabilities within the ListAllRobots function.
- Added new test cases to validate the updated functionality and ensure robust performance.
- Upgraded google.golang.org/grpc from v1.78.0 to v1.79.3 for improved performance and features.
- Updated golang.org/x/oauth2 from v0.32.0 to v0.34.0 to incorporate the latest enhancements and fixes.
- Added agent/robot/ROBOT-WATCHER-IMPROVEMENT.md to .gitignore to prevent tracking of specific improvement documentation.
- 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
Server lifecycle:
- Introduce service.Service to manage HTTP + gRPC startup/shutdown
- Fix gRPC mutex deadlock in StartServer when port is occupied
- Add GracefulStop with 5s timeout before forced Stop in grpc.go
- Pre-check HTTP and gRPC port availability in cmd/start.go
- Print gRPC server address in startup access-points block
gRPC client refactor:
- Move token manager and client from tai/grpc/ to grpc/client/
- Add backward-compatible aliases in tai/yao.go and tai/token.go
- Update cmd/run.go to import grpc/client directly (no tai dependency)
Sandbox v2 docker migration:
- Delete sandbox/v2/docker/ (moved to tai repo)
- Update sandbox/docker/build.sh hint to point to tai repo
- Clean up .gitignore entries for removed docker directory
- Temporarily disable SandboxV2Test and BenchmarkSandboxV2 in CI
(docker images need rebuild after tai repo migration)
Tai integration:
- Add direct-mode registration API handlers in tai/api/
- Add heartbeat handler and token management wrappers
- Update tai/registry and tai/tunnel for latest protocol
- Replace yao-grpc references with tai call in docs
Made-with: Cursor
- 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.
- Add K8s sandbox implementation (sandbox/k8s.go) using client-go
- Extend tai.New() to support K8s runtime via Tai proxy
- Remove containerd support, fix default port assignment bug
- Update CI workflows to spin up k3d cluster and route K8s tests
through Tai proxy for full end-to-end coverage
- Make test ports configurable via environment variables
Made-with: Cursor
- Introduce new MCP and Robot command groups in the CLI, allowing for better organization of package management commands.
- Add corresponding command descriptions for MCP and Robot functionalities to improve user guidance.
- Update the agent command group to include additional commands for enhanced agent management.
- Modify .gitignore to exclude specific design markdown files from version control.
- Add environment variable for test application path in GitHub workflows to streamline testing setup.
- Update .gitignore to exclude registry data files.
- Modify Makefile to include new unit-test-registry target for running tests against the Yao Registry service.
- Add comprehensive Registry Client SDK tests in GitHub workflows, ensuring proper setup and execution of tests with Docker service dependencies.
- Implement steps for user creation, service restart, and test execution, along with reporting results back to the pull request.
- Add Telegram integration support by introducing a dispatcher for handling Telegram events and messages.
- Implement event notifications for robot configuration changes (creation, update, deletion) to facilitate integration with external services.
- Refactor the robot initialization process to load robots into cache and start the dispatcher, improving the overall system setup.
- Update the delivery event structure to include additional metadata for better context during message handling.
- Enhance logging capabilities for better observability during robot execution and event processing.
- 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 unit test commands in the Makefile to include additional skip patterns for memory leak tests, improving test coverage and accuracy.
- Expand benchmark and memory leak detection to include the event module, ensuring comprehensive testing across all components.
- Add new design and TODO documentation files for the event module to facilitate future development.
- Add external tool inspection functionality in the engine, allowing detection of tools like FFmpeg, PDF converters, and Docker.
- Update the `inspect` command to include detected tools in the output.
- Remove the studio configuration from the application, simplifying the configuration structure and related code.
- Clean up unused studio-related code in various files, including login processing and configuration management.
- 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>
- 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>
- 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>
- Update Makefile to include new production and UPX build targets for optimized binaries.
- Add BUILDOPTIONS constant to share/const.go for tracking build configurations.
- Modify version command to display build options.
- Update Dockerfile to install UPX for compression during builds.
- Add release and prod targets to streamline artifact creation.
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>
- 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>
- Added `UPGRADE_PLAN.md` to .gitignore to exclude the new upgrade plan documentation from version control.
- Revised TODO_V2.md to include a detailed implementation plan for the Agent Test Framework, outlining phases for before/after scripts, agent-driven assertions, and dynamic mode features.
- Improved overall documentation clarity to facilitate understanding of upcoming enhancements and tasks within the framework.
- Added MULTI_TURN_DESIGN.md to .gitignore to prevent tracking of design documents in the test directory.
- Refactored the LoadWithRoot function in config.go for improved readability by adjusting indentation for the absolute path resolution logic.
- Introduced a MongoDB service in both `pr-test.yml` and `unit-test.yml` workflows to facilitate database testing.
- Configured MongoDB with environment variables for root username, password, and database name, enhancing test environment setup.
- Updated `.gitignore` to exclude job logs for search agents, ensuring cleaner repository management.
- 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.
- Added context release calls in multiple test cases to ensure proper resource cleanup and prevent memory leaks.
- Updated performance thresholds in memory leak tests, increasing acceptable growth per iteration from 10KB to 15KB to account for overhead.
- Improved validation checks in stress tests to ensure response integrity and metadata accuracy, enhancing overall test robustness.
- Refactored performance report for clarity, consolidating key metrics and findings for better readability.
- Added null handling for input in the I18n Parse method to prevent errors with nil values.
- Refactored string parsing logic into a separate method for improved clarity and maintainability.
- Updated assistant translation logic to streamline the application of i18n translations for various fields, including name, description, and prompts.
- Introduced new tests to validate the retrieval of assistants with locale-specific translations, ensuring correct behavior across different languages.
- Enhanced the GetHistoryWithFilter method to maintain consistent silent message filtering and pagination logic.
- Refactored the ACL enforcement process to include a comprehensive chain of permission checks for clients, users, teams, and members.
- Introduced data access constraints (OwnerOnly, TeamOnly) to enhance access control based on endpoint requirements.
- Updated the Error struct to include the stage of permission checks where failures occur, improving error reporting.
- Enhanced scope management with wildcard matching capabilities and added checks for restricted scopes.
- Implemented tests to validate the enforcement logic and ensure correct handling of data access constraints.
- Updated the OAuth guard to set authorized information in the context using the new authorized package.
- Refactored the GetAuthorizedInfo function to utilize the authorized.GetInfo method, improving clarity and maintainability.
- Enhanced the ACL implementation by adding scope resolution logic in the Enforce method, ensuring proper access control based on user roles and scopes.
- Improved error handling and logging during ACL operations, providing better insights into access decisions.
- Added "permission": true to the option field in user, user_role, user_type, user_oauth_account, and dsl models, enhancing permission management capabilities.
- This change ensures consistency across user-related models and improves the overall functionality of the user management system.
- Added new system models for assistant, attachment, audit, chat, config, dsl, history, and kb with metadata including tags, built-in status, read-only attributes, and sort order.
- Refactored the model loading process to include a dedicated function for loading system models, improving organization and maintainability.
- Updated the application loading logic to set a default prefix for system tables, ensuring consistent naming conventions.
- Improved error handling during model loading and migration processes for better reliability.
- Added backup entries for bindata.go and const.go in .gitignore to prevent accidental commits.
- Refactored Makefile to streamline CUI commit retrieval and ensure consistent versioning in artifact generation.
- Implemented backup and restoration of bindata.go and const.go during the release process for better safety.
