- Added a `hashUserID` function to generate a collision-safe hash for user IDs, improving metadata handling.
- Updated the environment setup in `buildEnv` to override `metadata.user_id` with a sanitized value, ensuring compatibility with third-party APIs.
- Enhanced logging for the environment variables to aid in debugging and monitoring.
- Introduced `image_generate` tool for generating images from text prompts, with options for specifying output file paths and image dimensions.
- Updated `image_read` functionality to allow optional provider specification for enhanced image analysis.
- Implemented new `GenerateImage` method in the LLM API for seamless integration of image generation capabilities.
- Enhanced documentation to include detailed usage examples for both image reading and generation tools.
- Updated tests to validate new image generation features and ensure robust functionality across image tools.
- Added `image_read` tool for reading and analyzing images using vision-capable models, with a detailed input schema for image path, prompt, max size, and provider.
- Implemented `ReadImage` function to handle image processing and integration with vision models, returning descriptive text.
- Created comprehensive tests for image resizing, data URI handling, and various input scenarios to ensure robust functionality.
- Updated documentation to include usage examples and parameter descriptions for the new image tools.
- Added support for processing image content in the agent, providing placeholder text when image parsing fails.
- Implemented a fallback mechanism to utilize vision tools for image analysis, improving the handling of image content.
- Updated tests to validate the new image handling behavior, ensuring correct responses when vision support is unavailable.
- Enhanced system prompts to guide users on using the new `image_read` tool for image analysis, improving user experience.
- 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.
