- Added locale support in various components, including the Assistant's execution context and agent tools, to improve internationalization.
- Updated the `pickNodeByFilter` function to include a fallback mechanism for host_exec nodes when no container nodes are available.
- Introduced a new `agent_reference` tool for downloading agent source code for read-only study, alongside updates to the `agent_download` tool to restrict downloads to the 'smith' namespace.
- Enhanced documentation and tests to reflect the new functionalities and ensure robust locale extraction and handling.
- Implemented AssistantReloadFunc to enable hot-reloading of assistants after deployment, improving deployment flexibility.
- Enhanced gRPC authProvider to include workspace and sandbox IDs from incoming context metadata, enriching the authentication context.
- Updated tools to support new agent-related functionalities, including listing, downloading, deploying, and connecting agents.
- Expanded system tools documentation to include new agent commands, ensuring comprehensive guidance for users.
- 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.
- 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.
- 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.
