- Modified the TestOwnerPrefixedIDs test to use ScopedKey for provider key generation, ensuring unique keys based on owner context.
- This change enhances the accuracy of tests related to provider management by preventing key collisions during test execution.
- Introduced grpcAuthProvider to adapt gRPC AuthorizedInfo for use in MCP process calls, enabling better authorization handling.
- Updated MCPListTools and MCPCallTool methods to include authorization information in tool calls, improving security and context awareness.
- Refactored fetch functions in webfetch to support Brightdata API endpoint configuration, enhancing flexibility in fetching HTML content.
- Improved fetchHTML and fetchRawHTML methods to prioritize Brightdata when configured, streamlining content retrieval processes.
- Added isHTMLContent utility function to determine response content type, enhancing the robustness of content handling in fetch operations.
- 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.
- Updated the builtinSearch function to delegate search operations to the websearch tool, improving modularity and maintainability.
- Enhanced context handling by passing the agent context to builtinSearch, allowing for user and team identification during searches.
- Added a new DecryptValue function in cloud.go to streamline value decryption, delegating to the existing config.DecryptValue method.
- Updated .gitignore to include tools/README.md for better project organization.
- Introduced ScopedKey function to generate unique provider keys based on owner type (user/team) to prevent key collisions.
- Updated provider creation and management tests to utilize scoped keys, ensuring consistent key handling across different contexts.
- Refactored existing tests to validate the correct generation and retrieval of scoped keys, enhancing overall provider management reliability.
- Adjusted OpenAPI settings to reflect the use of scoped keys in provider operations, improving API consistency.
- Added support for embedding and image generation capabilities in the capabilitiesFromMap function.
- Updated the ToMap method to delegate to the canonical Capabilities.ToMap() method, simplifying the conversion process.
- Enhanced the capabilities handling in various components, including filters for non-chat models in OpenAPI settings.
- Introduced utility functions for filter checking and non-chat model identification, improving overall capabilities management.
- 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 timeout parameter in the TestProcessCall_Timeout_Short test to 1 second to ensure it accurately reflects expected behavior during LLM round-trip execution.
- This change aims to improve the reliability of the test by aligning the timeout with realistic processing times.
- Enhanced the extractConnectorID function to correctly return the connector ID for built-in providers without appending a model, preventing the creation of non-existent composite IDs.
- Improved logic for handling connector IDs based on provider source, ensuring accurate retrieval in various scenarios.
- 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.
- Modified the LLM provider retrieval functions to include an optional parameter for enhanced functionality.
- Updated the handleLLMProviderUpdate and handleLLMProviderTest functions to reflect this change, improving error handling and provider management.
- 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.
- Replaced fmt.Sprintf with net.JoinHostPort for constructing the SMTP address in smtpValidateConnection and smtpSendTestEmail functions, improving address handling and ensuring proper formatting.
- Introduced new endpoints for managing sandbox operations, including GET, PUT, and POST methods for registry and image management.
- Added data structures for sandbox configuration and image details, enhancing the OpenAPI settings to support sandbox functionality.
- Updated Makefile to skip sandbox-related tests in CI, ensuring local execution only.
- Introduced new endpoints for managing MCP servers, including GET, POST, PUT, and DELETE methods for server operations.
- Organized routing under a new /mcp group to enhance endpoint management within the OpenAPI settings.
- Introduced new endpoints for managing SMTP settings, including GET, PUT, and POST methods for retrieving, updating, and testing SMTP configurations.
- Added data structures for SMTP presets and configuration, enhancing the OpenAPI settings to support email functionality.
- Organized routing under a new /smtp group for better endpoint management.
- Introduced new endpoints for managing search providers, including GET, PUT, and POST methods for testing and updating providers.
- Added data structures for search provider configuration, presets, and tool assignments to support the new functionality.
- Enhanced the OpenAPI settings to accommodate the new search-related features.
- Introduced a new preset for Yao Agents in presets.yml, including configuration details such as API URL and capabilities.
- Added new LLM management endpoints in the OpenAPI settings, allowing for CRUD operations on LLM providers and roles.
- Enhanced data structures to support the new LLM functionality, including LLMPageData for aggregated responses.
- Added new endpoints for managing cloud settings under /setting/cloud, including GET, PUT, and POST methods.
- Introduced owner verification logic to ensure only team owners can modify settings, utilizing caching for efficiency.
- Enhanced data structures for cloud settings responses, including CloudRegion and CloudPageData types.
- Refactored existing functions to integrate new owner verification and error handling mechanisms.
- 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.
- Implemented initialization for the Setting Registry during the Load process.
- Added reload functionality to refresh the Setting Registry as needed.
- Enhanced error handling to capture and report issues during initialization and reloading.
- Added initialization for LLM Provider and MCP Client Registries during the Load process.
- Implemented reload functionality for both registries to ensure they are properly refreshed when needed.
- Enhanced error handling to capture and report issues during initialization and reloading of the registries.
- Updated logger methods to respect the new `config.Silent` flag, allowing suppression of console output in development mode.
- Refactored `buildTurnResponse` to utilize a shared `buildTrace` function for improved tool call association.
- Introduced JSON output capabilities in `OutputWriter` for detailed trace and duration reporting.
- Enhanced reporting mechanisms to include trace details in JSON and Markdown formats for better diagnostics.
- Added support for a new `Trace` structure to capture detailed execution information, including tool calls and completion data.
- Introduced `shellQuoteForPlatform` to build shell-safe command strings tailored for Windows and POSIX environments.
- Updated `buildSandboxEnvPrompt` to display the correct environment variable syntax based on the operating system.
- Refactored the command copying logic in the runner to use platform-aware commands for copying custom OpenCode tools.
- Removed outdated test scenarios related to the vision connector, streamlining the test suite.
- Implemented two new test scenarios: one to verify that read.ts is not copied when no vision connector is present, and another to confirm that it is copied when a vision connector is configured.
- Updated the runner logic to conditionally copy custom tools into the OpenCode global config directory based on the presence of a vision connector in the configuration.
- Registered new "opencode" and "opencode/cli" runners in the sandbox initialization.
- Updated the `runExecStep` function to use the computer's working directory and set the HOME environment variable.
- Refactored attachment processing in the Claude package to delegate to shared functionality, improving code maintainability.
- Removed the workflow_dispatch trigger from both release workflows to enforce tag-based releases.
- Added a mechanism to wait for draft releases before uploading assets, ensuring all necessary files are present.
- Implemented asset upload to GitHub releases and conditional publishing based on asset completeness.
- Enhanced SHA256 checksum generation for both production and development binaries.
- Updated testConnectorID comment and model version in TestAnthropicStreamRetry to reflect the latest model (Claude Haiku 4.5).
- Added Test command to the SUI command set with associated flags for improved testing capabilities.
- Updated the spdystream dependency version from v0.5.0 to v0.5.1 in go.mod and go.sum files.
- Modified testConnectorID comment to reflect the updated model version (Claude Haiku 3.5).
- Updated model version in TestAnthropicStreamRetry to use "claude-3-5-haiku-20241022".
Implement yao doc process list/inspect/validate and yao doc runtime
list/inspect/validate commands. Validate uses engine addressing logic
(process.Of) and checks dynamic-ID group registries (model, store, fs,
task, schedule) to verify resources actually exist.
- cmd/doc/: CLI command tree with process and runtime subcommands
- cmd/root.go: wire docCmd into rootCmd
- 27 process doc.yml + doc.go pairs across yao packages
- cmd/doc/doc_test.go: integration tests
Made-with: Cursor
- Implemented GinTokenLogin function to handle POST requests for token-based login.
- Allows users to authenticate using a pre-signed access token, returning session cookies and user info.
- Updated user routes to include the new /token/login endpoint for public access.
- Changed the label for the desktop app in both English and Chinese README files to "Yao Desktop" for consistency and improved branding.
- Ensured that the visual elements align with the updated terminology across both language versions.
- Removed unnecessary separators in the English and Chinese README files for a cleaner presentation.
- Ensured consistent formatting across both language versions to enhance readability.
- Revised the English README to reflect the new branding and features of Yao as an AI runtime for building applications.
- Enhanced the structure and content of the README, including quick links, how it works, and features sections.
- Updated the Chinese README to align with the changes made in the English version, ensuring consistency across languages.
- Improved visual elements and descriptions to better convey the functionality and purpose of Yao.
- Updated the notarization workflow to correctly reference the "Release macOS" workflow.
- Enhanced version and run ID resolution logic to ensure accurate detection from the latest release or inputs.
- Improved asset verification process on R2 with a retry mechanism to handle potential delays in asset availability.
- Removed the deprecated unified release workflow, streamlining the release process for macOS and Linux.
- Adjusted CDN update prerequisites to reflect the new workflow structure.
- Simplified version detection logic in the notarization workflow to prioritize the latest GitHub release.
- Enhanced error handling for cases where version or run ID cannot be determined.
- Updated the release workflow to ensure consistent version extraction from the upstream branch or fallback to the latest release.
- Changed default R2_BUCKET from 'get-yaoapps' to 'releases' for better alignment with asset management.
- Updated asset prefix paths in multiple workflows to remove 'releases/' prefix, ensuring uniformity in asset retrieval.
- Enhanced localization in command outputs to reflect updated CDN URLs for better user experience.
- Updated the notarization workflow to automatically resolve version and run ID from the latest release or inputs.
- Added a finalize job to verify assets on R2 and trigger CDN updates after notarization.
- Improved the release workflow to upload binaries to R2 with enhanced error handling and asset verification.
- Refactored upgrade command to support CDN fallback for version resolution, improving update reliability.
- Enhanced localization in the command output for better user experience.
- Added DeviceClientID and DeviceClientSecret fields to the Provider struct for Device Flow (RFC 8628) support.
- Introduced new types and methods for handling Device Authorization and Token requests/responses.
- Updated API routes to include endpoints for initiating Device Flow and polling for tokens.
- Enhanced loadProviders function to process new device-related environment variables.
- Added Size field to represent the file size in bytes.
- Introduced ContentType field to specify the MIME type of the attachment.
- Updated API endpoint to support bundling multiple files into a ZIP archive.
- 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.
- Replaced chunkRecord with recordedEvent to simplify event recording.
- Introduced activeToolID to manage the currently streaming tool, allowing for better state handling during parsing.
- Enhanced closeStreamingTool and suspendStreamingTool methods for improved tool message management.
- Updated parsing logic to handle multiple concurrent tool calls more effectively.
- Added utility functions for extracting message groups and properties from recorded events.
After tai sandbox containers start as root with dynamic UID mapping,
docker exec defaults to root. Add User field to ExecOptions and
hardcode "sandbox" in Box.Exec/Stream to ensure commands run as the
correct user.
Made-with: Cursor
- 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.
- Upgraded AWS SDK for Go v2 and its related packages in go.mod and go.sum to improve compatibility and access to new features.
- Updated session management logic in the Runner to ensure proper handling of chat sessions.
- Added new unit tests for keyword search functionality in the Assistant model, enhancing search capabilities across locales.
- Refactored JSON handling in the Assistant package to streamline options configuration.
