AGI MCP Server

Instructions

Implementation Reference

• src/memory-manager.js:726-774 (handler)

  The core handler function that performs the consolidation: creates a new semantic memory, establishes consolidation relationships, marks originals as consolidated, and logs the event in a database transaction.

  async consolidateWorkingMemory(workingMemoryIds, consolidatedContent, consolidatedEmbedding) {
    try {
      const result = await this.db.transaction(async (tx) => {
        // Create consolidated memory
        const [consolidatedMemory] = await tx
          .insert(schema.memories)
          .values({
            type: 'semantic',
            content: consolidatedContent,
            embedding: consolidatedEmbedding,
            importance: 0.8,
            status: 'active'
          })
          .returning();
  
        const consolidatedId = consolidatedMemory.id;
  
        // Create relationships from working memories to consolidated memory
        for (const workingId of workingMemoryIds) {
          await tx.insert(schema.memoryRelationships).values({
            fromMemoryId: workingId,
            toMemoryId: consolidatedId,
            relationshipType: 'consolidation',
            strength: 1.0
          });
  
          // Mark working memory as consolidated
          await tx
            .update(schema.memories)
            .set({ status: 'consolidated' })
            .where(eq(schema.memories.id, workingId));
        }
  
        // Record consolidation event
        await tx.insert(schema.memoryChanges).values({
          memoryId: consolidatedId,
          changeType: 'consolidation',
          newValue: { source_memories: workingMemoryIds }
        });
  
        return consolidatedMemory;
      });
  
      return result;
    } catch (error) {
      console.warn('Memory consolidation failed:', error.message);
      throw error;
    }
  }

• src/tools/memory-tools.js:271-292 (schema)

  Tool schema definition including input validation structure for the consolidate_working_memory tool.

  name: "consolidate_working_memory",
  description: "Consolidate multiple working memories into a single semantic memory",
  inputSchema: {
    type: "object",
    properties: {
      working_memory_ids: {
        type: "array",
        items: { type: "string" },
        description: "Array of working memory UUIDs to consolidate"
      },
      consolidated_content: {
        type: "string",
        description: "Content for the consolidated memory"
      },
      consolidated_embedding: {
        type: "array",
        items: { type: "number" },
        description: "Embedding for the consolidated memory"
      }
    },
    required: ["working_memory_ids", "consolidated_content", "consolidated_embedding"]
  }

• mcp.js:626-632 (registration)

  MCP server tool call handler registration: switch case that dispatches the tool call to the memoryManager's consolidateWorkingMemory method and formats the response.

  case "consolidate_working_memory":
    const consolidatedMemory = await memoryManager.consolidateWorkingMemory(
      args.working_memory_ids,
      args.consolidated_content,
      args.consolidated_embedding
    );
    return { content: [{ type: "text", text: JSON.stringify(consolidatedMemory, null, 2) }] };

• mcp.js:297-318 (schema)

  Tool schema provided in MCP server's listTools response for client validation.

  name: "consolidate_working_memory",
  description: "Consolidate multiple working memories into a single semantic memory",
  inputSchema: {
    type: "object",
    properties: {
      working_memory_ids: {
        type: "array",
        items: { type: "string" },
        description: "Array of working memory UUIDs to consolidate"
      },
      consolidated_content: {
        type: "string",
        description: "Content for the consolidated memory"
      },
      consolidated_embedding: {
        type: "array",
        items: { type: "number" },
        description: "Embedding for the consolidated memory"
      }
    },
    required: ["working_memory_ids", "consolidated_content", "consolidated_embedding"]
  }