mirror of
https://github.com/andy-stack/vaultkeeper-ai.git
synced 2026-07-22 16:30:27 +00:00
ab9ee08281
Restructure the AI workflow from a single-agent model to a specialized multi-agent system with distinct roles: - Add AgentType enum (Main, Orchestration, Planning, Execution) to define agent specializations - Replace AIControllerService and AIFunctionService with modular agent classes in Services/AIServices/: - MainAgent: Handles user interaction and delegates to orchestration - OrchestrationAgent: Coordinates plan execution and step-by-step workflow - PlanningAgent: Creates and revises execution plans - ExecutionAgent: Executes individual plan steps - AIController: Base class providing common agent loop functionality - Create specialized prompts (OrchestrationPrompt, ExecutionPrompt) for agent-specific behavior - Add OrchestrationResult type to communicate workflow control decisions (continue, abort, replan) - Introduce agent-specific function scoping: - ExecuteWorkflow for main agent - CompleteTask for execution agent - CompleteStep/Replan/CancelPlan for orchestration agent - SubmitPlan/AskUserQuestionPlanning for planning agent - Update BaseAIClass to use agentType property instead of isPlanningAgent boolean for model selection - Simplify ExecutionPlan and ExecutionStep types by removing execution state tracking (moved to agent coordination) - Remove PlanningEnabledAppendix and ExecutionStatus enum (superseded by agent architecture) - Add comprehensive integration tests for agent workflows This architecture provides better separation of concerns, clearer agent responsibilities, and more robust plan execution with explicit orchestration control flow.
29 lines
No EOL
1.1 KiB
TypeScript
29 lines
No EOL
1.1 KiB
TypeScript
import { AIFunction } from "Enums/AIFunction";
|
|
import type { IAIFunctionDefinition } from "../IAIFunctionDefinition";
|
|
|
|
export const CancelPlan: IAIFunctionDefinition = {
|
|
name: AIFunction.CancelPlan,
|
|
description: `Terminates the current plan execution immediately and returns control to the main conversation loop.
|
|
|
|
Use this function when plan execution cannot or should not continue.
|
|
|
|
Call this function when:
|
|
- The user has explicitly requested to stop, cancel, or terminate the current operation
|
|
- An insurmountable condition prevents continuation (e.g., required files don't exist,
|
|
incompatible vault state)
|
|
- Persistent errors occur with no viable workaround
|
|
- The task has grown beyond the original plan's boundaries (scope creep)
|
|
|
|
Do NOT use this function:
|
|
- When a replan would be more appropriate`,
|
|
parameters: {
|
|
type: "object",
|
|
properties: {
|
|
context: {
|
|
type: "string",
|
|
description: "Explain why cancellation is being chosen, including what went wrong, what conditions prevented continuation, or why the task cannot proceed as planned.",
|
|
}
|
|
},
|
|
required: ["context"]
|
|
}
|
|
} |