Based on the git diff showing extensive package-lock.json changes and modifications to the agent system prompt and configuration, here's the commit message:

``` feat: add AI SDK dependencies and refine agent voice interaction config - Add @ai-sdk packages for enhanced AI capabilities - Install Deepgram SDK, livekit-client, and werift for voice/WebRTC - Expand agent system prompt with multi-tool workflows and Claude Code interaction patterns - Adjust VAD timing (1.2s silence threshold) and turn detection for better voice UX - Switch TTS to inworld/inworld-tts-1 with Olivia voice - Configure interruption timing (0.2s detection, no word requirement) - Add comprehensive guidelines for conversational responses vs structured output - Document plan mode triggers and Claude response type handling 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> ```
2025-10-19 15:41:42 +02:00
parent dabcf63ebc
commit 40b199e329
44 changed files with 12183 additions and 1715 deletions
@@ -0,0 +1,173 @@
+import { v4 as uuidv4 } from 'uuid';
+import { getSystemPrompt } from './system-prompt.js';
+import { streamLLM, type Message } from './llm-openai.js';
+import type { VoiceAssistantWebSocketServer } from '../websocket-server.js';
+
+interface ConversationContext {
+  id: string;
+  messages: Message[];
+  createdAt: Date;
+  lastActivity: Date;
+}
+
+/**
+ * Store active conversations (in-memory for now)
+ * In production, this could be persisted to a database
+ */
+const conversations = new Map<string, ConversationContext>();
+
+/**
+ * Create a new conversation with system prompt
+ */
+export function createConversation(): string {
+  const id = uuidv4();
+  conversations.set(id, {
+    id,
+    messages: [{ role: 'system', content: getSystemPrompt() }],
+    createdAt: new Date(),
+    lastActivity: new Date(),
+  });
+  return id;
+}
+
+/**
+ * Get conversation by ID
+ */
+export function getConversation(id: string): ConversationContext | null {
+  return conversations.get(id) || null;
+}
+
+/**
+ * Process user message through the LLM orchestrator
+ * Handles streaming, tool calls, and WebSocket broadcasting
+ */
+export async function processUserMessage(params: {
+  conversationId: string;
+  message: string;
+  wsServer?: VoiceAssistantWebSocketServer;
+  enableTTS?: boolean;
+}): Promise<string> {
+  const conversation = conversations.get(params.conversationId);
+  if (!conversation) {
+    throw new Error('Conversation not found');
+  }
+
+  // Add user message to context
+  conversation.messages.push({
+    role: 'user',
+    content: params.message,
+  });
+  conversation.lastActivity = new Date();
+
+  // Broadcast user message to WebSocket clients
+  if (params.wsServer) {
+    params.wsServer.broadcastActivityLog({
+      id: uuidv4(),
+      timestamp: new Date(),
+      type: 'transcript',
+      content: params.message,
+    });
+  }
+
+  let assistantResponse = '';
+
+  try {
+    // Stream LLM response with tool execution
+    assistantResponse = await streamLLM({
+      messages: conversation.messages,
+      onChunk: (chunk) => {
+        // Broadcast streaming chunks to WebSocket
+        if (params.wsServer) {
+          params.wsServer.broadcast({
+            type: 'assistant_chunk',
+            payload: { chunk },
+          });
+        }
+      },
+      onToolCall: (toolName, args) => {
+        // Broadcast tool call to WebSocket
+        if (params.wsServer) {
+          params.wsServer.broadcastActivityLog({
+            id: uuidv4(),
+            timestamp: new Date(),
+            type: 'tool_call',
+            content: `Calling ${toolName}`,
+            metadata: { toolName, arguments: args },
+          });
+        }
+      },
+      onToolResult: (toolName, result) => {
+        // Broadcast tool result to WebSocket
+        if (params.wsServer) {
+          params.wsServer.broadcastActivityLog({
+            id: uuidv4(),
+            timestamp: new Date(),
+            type: 'tool_result',
+            content: `Tool ${toolName} completed`,
+            metadata: { toolName, result },
+          });
+        }
+      },
+      onFinish: (fullText) => {
+        // Broadcast complete assistant response
+        if (params.wsServer) {
+          params.wsServer.broadcastActivityLog({
+            id: uuidv4(),
+            timestamp: new Date(),
+            type: 'assistant',
+            content: fullText,
+          });
+        }
+      },
+    });
+
+    // Add assistant response to context
+    conversation.messages.push({
+      role: 'assistant',
+      content: assistantResponse,
+    });
+  } catch (error: any) {
+    // Broadcast error to WebSocket
+    if (params.wsServer) {
+      params.wsServer.broadcastActivityLog({
+        id: uuidv4(),
+        timestamp: new Date(),
+        type: 'error',
+        content: `Error: ${error.message}`,
+      });
+    }
+    throw error;
+  }
+
+  return assistantResponse;
+}
+
+/**
+ * Clean up old conversations (call periodically)
+ */
+export function cleanupConversations(maxAgeMinutes: number = 60): void {
+  const now = new Date();
+  for (const [id, conv] of conversations.entries()) {
+    const ageMinutes = (now.getTime() - conv.lastActivity.getTime()) / (1000 * 60);
+    if (ageMinutes > maxAgeMinutes) {
+      conversations.delete(id);
+    }
+  }
+}
+
+/**
+ * Get conversation statistics
+ */
+export function getConversationStats(): {
+  total: number;
+  conversations: Array<{ id: string; messageCount: number; lastActivity: Date }>;
+} {
+  return {
+    total: conversations.size,
+    conversations: Array.from(conversations.values()).map((conv) => ({
+      id: conv.id,
+      messageCount: conv.messages.length,
+      lastActivity: conv.lastActivity,
+    })),
+  };
+}