chore: ensure that extra parameters are discarded

Voyage will reject all requests with extra parameters

Author: kmruiz

src/common/search/embeddingsProvider.ts

@@ -27,14 +27,33 @@ export const zVoyageModels = z
     .enum(["voyage-3-large", "voyage-3.5", "voyage-3.5-lite", "voyage-code-3"])
     .default("voyage-3-large");
 
+// Zod does not undestand JS boxed numbers (like Int32) as integer literals,
+// so we preprocess them to unwrap them so Zod understands them.
+function unboxNumber(v: unknown): number {
+    if (v && typeof v === "object" && typeof v.valueOf === "function") {
+        const n = Number(v.valueOf());
+        if (!Number.isNaN(n)) return n;
+    }
+    return v as number;
+}
+
 export const zVoyageEmbeddingParameters = z.object({
     outputDimension: z
-        .union([z.literal(256), z.literal(512), z.literal(1024), z.literal(2048), z.literal(4096)])
+        .preprocess(
+            unboxNumber,
+            z.union([z.literal(256), z.literal(512), z.literal(1024), z.literal(2048), z.literal(4096)])
+        )
         .optional()
         .default(1024),
-    outputDType: z.enum(["float", "int8", "uint8", "binary", "ubinary"]).optional().default("float"),
+    outputDtype: z.enum(["float", "int8", "uint8", "binary", "ubinary"]).optional().default("float"),
 });
 
+const zVoyageAPIParameters = zVoyageEmbeddingParameters
+    .extend({
+        inputType: z.enum(["query", "document"]),
+    })
+    .strip();
+
 type VoyageModels = z.infer<typeof zVoyageModels>;
 type VoyageEmbeddingParameters = z.infer<typeof zVoyageEmbeddingParameters> & EmbeddingParameters;
 
@@ -62,11 +81,15 @@ class VoyageEmbeddingsProvider implements EmbeddingsProvider<VoyageModels, Voyag
         content: EmbeddingsInput[],
         parameters: VoyageEmbeddingParameters
     ): Promise<Embeddings[]> {
+        // This ensures that if we receive any random parameter from the outside (agent or us)
+        // it's stripped before sending it to Voyage, as Voyage will reject the request on
+        // a single unknown parameter.
+        const voyage = zVoyageAPIParameters.parse(parameters);
         const model = this.voyage.textEmbeddingModel(modelId);
         const { embeddings } = await embedMany({
             model,
             values: content,
-            providerOptions: { voyage: parameters },
+            providerOptions: { voyage },
         });
 
         return embeddings;

src/tools/mongodb/read/aggregate.ts

@@ -65,7 +65,7 @@ export const AggregateArgs = {
 ### Usage Rules for \`$vectorSearch\`
 - **Unset embeddings:**  
   Unless the user explicitly requests the embeddings, add an \`$unset\` stage **at the end of the pipeline** to remove the embedding field and avoid context limits. **The $unset stage in this situation is mandatory**.
-- **Prefiltering:**
+- **Pre-filtering:**
 If the user requests additional filtering, include filters in \`$vectorSearch.filter\` only for pre-filter fields in the vector index.
     NEVER include fields in $vectorSearch.filter that are not part of the vector index.
 - **Post-filtering:**

tests/integration/tools/mongodb/read/aggregate.test.ts

@@ -32,7 +32,7 @@ describeWithMongoDB("aggregate tool", (integration) => {
 ### Usage Rules for \`$vectorSearch\`
 - **Unset embeddings:**  
   Unless the user explicitly requests the embeddings, add an \`$unset\` stage **at the end of the pipeline** to remove the embedding field and avoid context limits. **The $unset stage in this situation is mandatory**.
-- **Prefiltering:**
+- **Pre-filtering:**
 If the user requests additional filtering, include filters in \`$vectorSearch.filter\` only for pre-filter fields in the vector index.
     NEVER include fields in $vectorSearch.filter that are not part of the vector index.
 - **Post-filtering:**

tests/unit/common/search/vectorSearchEmbeddingsManager.test.ts

@@ -396,7 +396,7 @@ describe("VectorSearchEmbeddingsManager", () => {
             collection: "mycoll",
             path: "embedding_field",
             rawValues: ["oops"],
-            embeddingParameters: { model: "voyage-3-large", outputDimension: 1024, outputDType: "float" } as const,
+            embeddingParameters: { model: "voyage-3-large", outputDimension: 1024, outputDtype: "float" } as const,
             inputType: "query" as const,
         };