Refactor skill handling and improve runtime trace capabilities
- 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.
This commit is contained in:
@@ -41,7 +41,7 @@ func (c *toolCatalog) resolveForRun(req *Request) (*registry.ToolSet, error) {
|
||||
AIAgent: req.AIAgent,
|
||||
AIConfig: req.AIConfig,
|
||||
UserMessage: req.UserMessage,
|
||||
AllowedToolCodes: c.resolveAllowedToolCodes(req.AIAgent, req.SelectedSkill),
|
||||
AllowedToolCodes: c.parseAgentAllowedToolCodes(req.AIAgent),
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user