@insforge/mcp 1.2.6-memory.0 → 1.2.6-memory.1

package/dist/{chunk-742PFYYV.js → chunk-4SZSV7IV.js}

@@ -2270,110 +2270,107 @@ To: Your current project directory
       }
     })
   );
-  const memoryEnabled = process.env.MEMORY_ENABLED === "true";
-  if (memoryEnabled) {
-    registerTool(
+  registerTool(
+    "store-conversation",
+    "Store a conversation with messages for semantic similarity search. Messages are embedded using pgvector for later retrieval.",
+    {
+      apiKey: z23.string().optional().describe("API key for authentication (optional if provided via --api_key)"),
+      title: z23.string().optional().describe("Optional title for the conversation"),
+      metadata: z23.record(z23.unknown()).optional().describe("Optional metadata to associate with the conversation"),
+      messages: z23.array(
+        z23.object({
+          role: z23.enum(["user", "assistant", "system", "tool"]).describe("Message role"),
+          content: z23.string().describe("Message content"),
+          metadata: z23.record(z23.unknown()).optional().describe("Optional message metadata")
+        })
+      ).min(1).describe("Array of messages to store"),
+      embeddingModel: z23.string().optional().describe("Embedding model to use (uses project default if not specified)")
+    },
+    withUsageTracking(
       "store-conversation",
-      "Store a conversation with messages for semantic similarity search. Messages are embedded using pgvector for later retrieval.",
-      {
-        apiKey: z23.string().optional().describe("API key for authentication (optional if provided via --api_key)"),
-        title: z23.string().optional().describe("Optional title for the conversation"),
-        metadata: z23.record(z23.unknown()).optional().describe("Optional metadata to associate with the conversation"),
-        messages: z23.array(
-          z23.object({
-            role: z23.enum(["user", "assistant", "system", "tool"]).describe("Message role"),
-            content: z23.string().describe("Message content"),
-            metadata: z23.record(z23.unknown()).optional().describe("Optional message metadata")
-          })
-        ).min(1).describe("Array of messages to store"),
-        embeddingModel: z23.string().optional().describe("Embedding model to use (uses project default if not specified)")
-      },
-      withUsageTracking(
-        "store-conversation",
-        async ({ apiKey, title, metadata, messages, embeddingModel }) => {
-          try {
-            const actualApiKey = getApiKey(apiKey);
-            const response = await fetch2(`${API_BASE_URL}/api/memory/conversations`, {
-              method: "POST",
-              headers: {
-                "x-api-key": actualApiKey,
-                "Content-Type": "application/json"
-              },
-              body: JSON.stringify({ title, metadata, messages, embeddingModel })
-            });
-            const result = await handleApiResponse(response);
-            return await addBackgroundContext({
-              content: [
-                {
-                  type: "text",
-                  text: formatSuccessMessage("Conversation stored successfully", result)
-                }
-              ]
-            });
-          } catch (error) {
-            const errMsg = error instanceof Error ? error.message : "Unknown error occurred";
-            return {
-              content: [
-                {
-                  type: "text",
-                  text: `Error storing conversation: ${errMsg}`
-                }
-              ],
-              isError: true
-            };
-          }
+      async ({ apiKey, title, metadata, messages, embeddingModel }) => {
+        try {
+          const actualApiKey = getApiKey(apiKey);
+          const response = await fetch2(`${API_BASE_URL}/api/memory/conversations`, {
+            method: "POST",
+            headers: {
+              "x-api-key": actualApiKey,
+              "Content-Type": "application/json"
+            },
+            body: JSON.stringify({ title, metadata, messages, embeddingModel })
+          });
+          const result = await handleApiResponse(response);
+          return await addBackgroundContext({
+            content: [
+              {
+                type: "text",
+                text: formatSuccessMessage("Conversation stored successfully", result)
+              }
+            ]
+          });
+        } catch (error) {
+          const errMsg = error instanceof Error ? error.message : "Unknown error occurred";
+          return {
+            content: [
+              {
+                type: "text",
+                text: `Error storing conversation: ${errMsg}`
+              }
+            ],
+            isError: true
+          };
         }
-      )
-    );
-    registerTool(
+      }
+    )
+  );
+  registerTool(
+    "search-conversations",
+    "Search for conversations by semantic similarity using pgvector. Returns conversations ranked by relevance to the query.",
+    {
+      apiKey: z23.string().optional().describe("API key for authentication (optional if provided via --api_key)"),
+      query: z23.string().describe("Search query to find similar conversations"),
+      limit: z23.number().int().positive().max(100).optional().default(10).describe("Maximum number of results to return (default: 10)"),
+      threshold: z23.number().min(0).max(1).optional().default(0).describe("Minimum similarity threshold 0-1 (default: 0)"),
+      metadataFilter: z23.record(z23.unknown()).optional().describe("Filter conversations by metadata (JSONB containment)"),
+      embeddingModel: z23.string().optional().describe("Embedding model for the query (uses project default if not specified)")
+    },
+    withUsageTracking(
       "search-conversations",
-      "Search for conversations by semantic similarity using pgvector. Returns conversations ranked by relevance to the query.",
-      {
-        apiKey: z23.string().optional().describe("API key for authentication (optional if provided via --api_key)"),
-        query: z23.string().describe("Search query to find similar conversations"),
-        limit: z23.number().int().positive().max(100).optional().default(10).describe("Maximum number of results to return (default: 10)"),
-        threshold: z23.number().min(0).max(1).optional().default(0).describe("Minimum similarity threshold 0-1 (default: 0)"),
-        metadataFilter: z23.record(z23.unknown()).optional().describe("Filter conversations by metadata (JSONB containment)"),
-        embeddingModel: z23.string().optional().describe("Embedding model for the query (uses project default if not specified)")
-      },
-      withUsageTracking(
-        "search-conversations",
-        async ({ apiKey, query, limit, threshold, metadataFilter, embeddingModel }) => {
-          try {
-            const actualApiKey = getApiKey(apiKey);
-            const response = await fetch2(`${API_BASE_URL}/api/memory/search`, {
-              method: "POST",
-              headers: {
-                "x-api-key": actualApiKey,
-                "Content-Type": "application/json"
-              },
-              body: JSON.stringify({ query, limit, threshold, metadataFilter, embeddingModel })
-            });
-            const result = await handleApiResponse(response);
-            return await addBackgroundContext({
-              content: [
-                {
-                  type: "text",
-                  text: formatSuccessMessage("Conversation search completed", result)
-                }
-              ]
-            });
-          } catch (error) {
-            const errMsg = error instanceof Error ? error.message : "Unknown error occurred";
-            return {
-              content: [
-                {
-                  type: "text",
-                  text: `Error searching conversations: ${errMsg}`
-                }
-              ],
-              isError: true
-            };
-          }
+      async ({ apiKey, query, limit, threshold, metadataFilter, embeddingModel }) => {
+        try {
+          const actualApiKey = getApiKey(apiKey);
+          const response = await fetch2(`${API_BASE_URL}/api/memory/search`, {
+            method: "POST",
+            headers: {
+              "x-api-key": actualApiKey,
+              "Content-Type": "application/json"
+            },
+            body: JSON.stringify({ query, limit, threshold, metadataFilter, embeddingModel })
+          });
+          const result = await handleApiResponse(response);
+          return await addBackgroundContext({
+            content: [
+              {
+                type: "text",
+                text: formatSuccessMessage("Conversation search completed", result)
+              }
+            ]
+          });
+        } catch (error) {
+          const errMsg = error instanceof Error ? error.message : "Unknown error occurred";
+          return {
+            content: [
+              {
+                type: "text",
+                text: `Error searching conversations: ${errMsg}`
+              }
+            ],
+            isError: true
+          };
         }
-      )
-    );
-  }
+      }
+    )
+  );
   return {
     apiKey: GLOBAL_API_KEY,
     apiBaseUrl: API_BASE_URL,

package/dist/http-server.js

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 import {
   registerInsforgeTools
-} from "./chunk-742PFYYV.js";
+} from "./chunk-4SZSV7IV.js";
 
 // src/http/server.ts
 import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";

package/dist/index.js

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 import {
   registerInsforgeTools
-} from "./chunk-742PFYYV.js";
+} from "./chunk-4SZSV7IV.js";
 
 // src/stdio/index.ts
 import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@insforge/mcp",
-  "version": "1.2.6-memory.0",
+  "version": "1.2.6-memory.1",
   "description": "MCP (Model Context Protocol) server for Insforge backend-as-a-service",
   "mcpName": "io.github.InsForge/insforge-mcp",
   "type": "module",