Remove Agent Desk users, roles, login sessions, tokens, and local permission persistence. Expose the backend as an embeddable ai-agent module with host-provided subject lookup and operation authorization callbacks, and complete the frontend/backend repository split.
- Removed runtime mode handling from AIAgentConfigWorkbench and related components.
- Updated tests to reflect changes in AI Agent policy copy and configuration.
- Changed terminology from "workflow" to "revision" in various components and API responses.
- Simplified agent binding logic in channel editing.
- Cleaned up unused variables and types related to runtime modes.
- Updated localization files for consistency with new terminology.
- Updated labels in the AI Agents dashboard for clarity, changing "流程状态" to "Playbook 状态" and "未发布流程" to "未发布 Playbook".
- Introduced AI Agent rollout percentage management in channel editing, allowing users to set and rollback rollout percentages.
- Added new API endpoints for rolling back AI Agent rollout and fetching agent run metrics.
- Implemented new UI components for displaying agent run details, including status, duration, and input/output tokens.
- Enhanced type definitions for AdminChannel and AIAgent to include rollout percentages and runtime modes.
- Updated navigation to include a section for agent runs.
- Added new translations for agent run features in both English and Chinese.
- Deleted tool_filter_middleware_test.go and tool_helpers.go as they are no longer needed.
- Removed associated test cases in tool_helpers_test.go.
- Refactored knowledge retriever logic by moving it to a new file and updating imports.
- Introduced tooling package for tool result reduction logic.
- Updated traces package to include new trace types and structures.
- Adjusted executor and tool search tool to reflect new package structure.
- Updated import paths in multiple service files to reflect the new agent-desk module.
- Added a new configuration file for agent-desk in the Docker setup.
- Updated runtime configuration to use __CS_AI_AGENT_WIDGET_CONFIG__ instead of __CS_AGENT_WIDGET_CONFIG__.
- Changed message types in support host bridge from "cs-agent" to "cs-ai-agent".
- Minified SDK script updated to reflect new AI agent naming conventions.
- Adjusted scrollbar styles in main.scss to use .cs-ai-agent-scrollbar instead of .cs-agent-scrollbar.
- Removed the selectSkill method from prepareService and adjusted related logic in the Run method of Service.
- Updated tool catalog to parse agent allowed tool codes directly.
- Simplified Request and RunInput structures by removing unnecessary fields.
- Enhanced the RuntimeTraceCollector to manage skill activation and visibility.
- Introduced a new databaseSkillBackend to manage skill definitions and their metadata.
- Added tests for skill backend functionalities to ensure correct behavior.
- Updated various factory methods to accommodate changes in skill handling.
- Improved documentation and descriptions for better clarity.
- Replaced the existing runtime executor with a new eino package for better modularity.
- Updated Service struct to use the new RuntimeExecutor from eino.
- Adjusted Run and Resume methods to accommodate changes in input types and execution logic.
- Introduced new types in the eino package to align with the previous executor's functionality.
- Refactored tooling preparation logic to streamline tool definitions and improve clarity.
- Added new context builders and event consumers to enhance runtime event handling.
- Removed legacy executor code and ensured all references are updated to the new eino package.
t