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execution state tracking (moved to agent coordination) - Remove PlanningEnabledAppendix and ExecutionStatus enum (superseded by agent architecture) - Add comprehensive integration tests for agent workflows This architecture provides better separation of concerns, clearer agent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.
23 lines
No EOL
925 B
TypeScript
23 lines
No EOL
925 B
TypeScript
import { AIFunction } from "Enums/AIFunction";
|
|
import type { IAIFunctionDefinition } from "../IAIFunctionDefinition";
|
|
|
|
export const Replan: IAIFunctionDefinition = {
|
|
name: AIFunction.Replan,
|
|
description: `Signals that the current plan needs to be revised before execution can continue.
|
|
|
|
- A planned step fails and you need an alternative approach
|
|
- Execution reveals the original plan was based on incorrect assumptions
|
|
- The user provides new information mid-execution
|
|
- You've completed part of the plan but the remaining steps are no longer valid
|
|
- Do NOT use this if the failure is unrecoverable or if the goal is no longer achievable.`,
|
|
parameters: {
|
|
type: "object",
|
|
properties: {
|
|
context: {
|
|
type: "string",
|
|
description: "Explain why replanning is needed. Include what went wrong or changed and be specific about the issue encountered.",
|
|
}
|
|
},
|
|
required: ["context"]
|
|
}
|
|
} |