update forget implementation in mcp (supermemoryai#773)

### TL;DR

Enhanced the `forgetMemory` method to try exact content matching first, then fall back to semantic search with a high similarity threshold for more precise memory deletion.

### What changed?

The `forgetMemory` method now uses a two-step approach: first attempting exact content matching via the API, and if that fails with a 404, falling back to semantic search with a similarity threshold of 0.85. The search method also accepts an optional threshold parameter. Error messages now distinguish between exact matches and semantic matches, including similarity scores in the response.

### How to test?

1. Call `forgetMemory` with the exact content of an existing memory to verify direct deletion
2. Call `forgetMemory` with similar but not identical content to test the semantic search fallback
3. Call `forgetMemory` with completely unrelated content to verify the "no matching memory found" response
4. Verify that success messages indicate whether deletion used exact matching or semantic matching with similarity scores

### Why make this change?

This approach provides more precise memory deletion by prioritizing exact matches while still offering a fallback for similar content. The high similarity threshold (0.85) ensures that only very similar memories are deleted when exact matches aren't found, reducing the risk of accidentally deleting unrelated memories.

Author: sohamd22

apps/mcp/src/client.ts

@@ -154,18 +154,39 @@ export class SupermemoryClient {
 		}
 	}
 
-	// Delete/forget memory by searching first
+	// Delete/forget memory - try exact match first, then semantic search
 	async forgetMemory(
 		content: string,
 	): Promise<{ success: boolean; message: string; containerTag: string }> {
 		try {
-			// First search for the memory
-			const searchResult = await this.search(content, 5)
+			// Try exact content matching first
+			try {
+				const result = await this.client.memories.forget({
+					content: content,
+					containerTag: this.containerTag,
+				})
+
+				return {
+					success: true,
+					message: `Successfully forgot memory (exact match) with ID: ${result.id}`,
+					containerTag: this.containerTag,
+				}
+			} catch (error: any) {
+				// If not 404, it's a real error - re-throw it
+				if (error?.status !== 404) {
+					throw error
+				}
+				// Otherwise continue to semantic search fallback
+			}
+
+			// Fallback to semantic search if exact match fails
+			const SIMILARITY_THRESHOLD = 0.85 // High threshold - only very similar memories
+			const searchResult = await this.search(content, 5, SIMILARITY_THRESHOLD)
 
 			if (searchResult.results.length === 0) {
 				return {
 					success: false,
-					message: "No matching memory found to forget.",
+					message: `No matching memory found to forget. Tried exact match and semantic search with similarity threshold ${SIMILARITY_THRESHOLD}.`,
 					containerTag: this.containerTag,
 				}
 			}
@@ -176,10 +197,12 @@ export class SupermemoryClient {
 				return {
 					success: false,
 					message:
-						"No matching memory found to forget (only document chunks matched).",
+						"No matching memory found to forget (only document chunks matched in semantic search).",
 					containerTag: this.containerTag,
 				}
 			}
+
+			// Delete using the ID from semantic search
 			await this.client.memories.forget({
 				id: memoryToDelete.id,
 				containerTag: this.containerTag,
@@ -189,7 +212,7 @@ export class SupermemoryClient {
 				getMemoryText(memoryToDelete) || memoryToDelete.content || ""
 			return {
 				success: true,
-				message: `Forgot: "${limitByChars(memoryText, 100)}"`,
+				message: `Forgot similar memory (semantic match, similarity: ${memoryToDelete.similarity.toFixed(2)}): "${limitByChars(memoryText, 100)}"`,
 				containerTag: this.containerTag,
 			}
 		} catch (error) {
@@ -198,13 +221,14 @@ export class SupermemoryClient {
 	}
 
 	// Search memories using SDK
-	async search(query: string, limit = 10): Promise<SearchResult> {
+	async search(query: string, limit = 10, threshold?: number): Promise<SearchResult> {
 		try {
 			const result = await this.client.search.memories({
 				q: query,
 				limit,
 				containerTag: this.containerTag,
 				searchMode: "hybrid",
+				threshold, // Optional threshold parameter
 			})
 
 			// Normalize and limit response size — preserve memory vs chunk distinction