search_long_term_memories

Retrieve relevant long-term memories from conversation history to maintain context and enable serendipitous recall.

Instructions

Search and activate relevant long-term memories based on current conversation context. Returns activated memories (whose triggers evaluated to true) and random memories for serendipity.

Input Schema

TableJSON Schema

Name	Required	Description
`messages`	Yes	Recent conversation messages
`conversation_id`	Yes	Current conversation ID
`participants`	No	Optional participants information

Implementation Reference

src/tools/long-term-tools.js:196-223 (handler)

The handler function that implements the core logic of the 'search_long_term_memories' tool. It processes input arguments to create context and invokes the LongTermMemoryManager to search and activate memories.

handler: async (args) => {
  try {
    const context = {
      messages: args.messages,
      conversation_id: args.conversation_id,
      participants: args.participants || {}
    };

    const results = await memoryManager.searchAndActivateMemories(context);

    const formatMemory = (mem) => ({
      name: mem.name,
      prompt: mem.prompt,
      createdAt: mem.createdAt.toISOString(),
      updatedAt: mem.updatedAt?.toISOString()
    });

    return {
      activated: results.activated.map(formatMemory),
      random: results.random.map(formatMemory),
      totalMemories: memoryManager.getMemories().length,
      formattedText: memoryManager.formatActivatedMemories(results.activated, results.random)
    };
  } catch (error) {
    return {
      error: error.message
    };
  }

src/tools/long-term-tools.js:188-195 (schema)

Zod input schema defining the expected parameters for the search_long_term_memories tool: recent messages, conversation ID, and optional participants.

inputSchema: z.object({
  messages: z.array(z.object({
    role: z.enum(['user', 'assistant', 'system']),
    content: z.string()
  })).describe('Recent conversation messages'),
  conversation_id: z.string().describe('Current conversation ID'),
  participants: z.object({}).passthrough().optional().describe('Optional participants information')
}),

src/tools/long-term-tools.js:185-225 (registration)

The complete tool definition object for 'search_long_term_memories' within the createLongTermTools function, which registers the tool by including it in the returned array of MCP tools.

{
  name: 'search_long_term_memories',
  description: 'Search and activate relevant long-term memories based on current conversation context. Returns activated memories (whose triggers evaluated to true) and random memories for serendipity.',
  inputSchema: z.object({
    messages: z.array(z.object({
      role: z.enum(['user', 'assistant', 'system']),
      content: z.string()
    })).describe('Recent conversation messages'),
    conversation_id: z.string().describe('Current conversation ID'),
    participants: z.object({}).passthrough().optional().describe('Optional participants information')
  }),
  handler: async (args) => {
    try {
      const context = {
        messages: args.messages,
        conversation_id: args.conversation_id,
        participants: args.participants || {}
      };

      const results = await memoryManager.searchAndActivateMemories(context);

      const formatMemory = (mem) => ({
        name: mem.name,
        prompt: mem.prompt,
        createdAt: mem.createdAt.toISOString(),
        updatedAt: mem.updatedAt?.toISOString()
      });

      return {
        activated: results.activated.map(formatMemory),
        random: results.random.map(formatMemory),
        totalMemories: memoryManager.getMemories().length,
        formattedText: memoryManager.formatActivatedMemories(results.activated, results.random)
      };
    } catch (error) {
      return {
        error: error.message
      };
    }
  }
},

Memory MCP Server