root/fusion
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(FN-1984): enrich chat and heartbeat prompts with agent context

Browse Source 
- Add agent memory support to instruction resolution and introduce/export buildAgentChatPrompt for identity-aware prompt assembly with optional project memory
- Wire ChatManager to AgentStore so chat sessions can enrich system prompts per agent and include recent conversation context in prompt payloads
- Update server chat wiring to provide an AgentStore for prompt enrichment and keep graceful fallback behavior when agent context is unavailable
- Enrich HeartbeatMonitor system prompts with resolved agent instructions/ratings while preserving base-prompt fallback paths
- Expand dashboard and engine tests to cover prompt enrichment, fallback behavior, conversation context assembly, and AgentStore route mocks
This commit is contained in:
Fusion
2026-04-17 02:19:54 -07:00
committed by gsxdsm
parent 0873e3f788
commit a5a65e86fd
11 changed files with 431 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
packages/dashboard/src/server.ts
View File

@@ -4,7 +4,7 @@ import { join, dirname } from "node:path";
import { existsSync } from "node:fs";
import { fileURLToPath } from "node:url";
import type { Task, TaskStore, MergeResult, AutomationStore, RoutineStore, CentralCore, MessageStore } from "@fusion/core";
import { ChatStore } from "@fusion/core";
import { AgentStore, ChatStore } from "@fusion/core";
import type { AuthStorageLike, ModelRegistryLike } from "./routes.js";
import { createApiRoutes } from "./routes.js";
import { createSSE } from "./sse.js";
@@ -603,8 +603,11 @@ export function createServer(store: TaskStore, options?: ServerOptions): ReturnT
// Create ChatStore for chat session management
const chatStore = options?.chatStore ?? new ChatStore(store.getFusionDir(), store.getDatabase());
// Create AgentStore for chat prompt enrichment (lazy-initialized inside ChatManager)
const chatAgentStore = new AgentStore({ rootDir: store.getFusionDir() });
// Create ChatManager for AI chat message handling
const chatManager = options?.chatManager ?? new ChatManager(chatStore, store.getRootDir());
const chatManager = options?.chatManager ?? new ChatManager(chatStore, store.getRootDir(), chatAgentStore);
const runAiSessionCleanup = (maxAgeMs: number, source: "initial" | "scheduled") => {
const result = aiSessionStore.cleanupStaleSessions(maxAgeMs);