@mastra/mongodb 1.23.2-alpha.0 → 1.24.0

package/dist/docs/SKILL.md

@@ -3,7 +3,7 @@ name: mastra-mongodb
 description: Documentation for @mastra/mongodb. Use when working with @mastra/mongodb APIs, configuration, or implementation.
 metadata:
   package: "@mastra/mongodb"
-  version: "1.23.2-alpha.0"
+  version: "1.24.0"
 ---
 
 ## When to use

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.23.2-alpha.0",
+  "version": "1.24.0",
   "package": "@mastra/mongodb",
   "exports": {},
   "modules": {}

package/dist/docs/references/docs-memory-semantic-recall.md

@@ -403,6 +403,28 @@ Memory uses a single embedder for both storing and recalling messages, so pick o
 
 Multilingual E5 produces 1024-dimensional vectors. Your vector index must be created with matching dimensions, and E5 vectors can't be mixed with vectors from another embedder in the same index.
 
+FastEmbed models embed at most 512 tokens per input (roughly 2,000 to 2,500 characters of English text). Longer inputs are truncated, so text past the limit doesn't affect the embedding and can't be found by semantic recall. The AI SDK v3 FastEmbed models return a warning when this happens. The legacy v1 and v2 models don't. If you embed long documents with FastEmbed, chunk them to fit the window, for example with `maxSize: 1500` in `MDocument.chunk()`.
+
+### Setting the embedding dimension
+
+To name the vector index, Memory needs the embedder's output dimension. By default it finds the dimension by embedding a short probe string the first time semantic recall is set up, once per `Memory` instance. If you already know the dimension, set `embeddingDimension`. Memory then skips the probe, so startup makes no embedding call and doesn't depend on the embedding provider being reachable:
+
+```ts
+import { Memory } from '@mastra/memory'
+
+const memory = new Memory({
+  embedder: 'openai/text-embedding-3-small',
+  embeddingDimension: 1536,
+  options: {
+    semanticRecall: true,
+  },
+})
+```
+
+The index name is the same whether the dimension is configured or probed, so existing indexes keep working.
+
+The value must match the vectors the embedder returns. Memory compares it with the first real embedding, and on a mismatch it throws a `MASTRA_MEMORY_EMBEDDING_DIMENSION_MISMATCH` error naming both values before creating or querying any index. Update `embeddingDimension` whenever you change the embedding model or its output dimension.
+
 ## PostgreSQL index optimization
 
 When using PostgreSQL as your vector store, you can optimize semantic recall performance by configuring the vector index. This is particularly important for large-scale deployments with thousands of messages.

package/dist/docs/references/docs-memory-working-memory.md

@@ -217,7 +217,7 @@ const paragraphMemory = new Memory({
 
 Working memory can also be defined using a structured schema instead of a Markdown template. A [Standard JSON Schema](https://standardschema.dev/json-schema) ([Zod](https://zod.dev/), [Valibot](https://valibot.dev/), [ArkType](https://arktype.io/), etc.). When using a schema, the agent will see and update working memory as a JSON object matching your schema.
 
-**Requirement:** You must specify either `template` or `schema`, but not both.
+You can specify either `template` or `schema`, but not both. If you omit both, Mastra uses the default working memory template.
 
 ### Example: Schema-Based Working Memory
 

package/dist/index.cjs

@@ -10,7 +10,7 @@ let _mastra_core_agent = require("@mastra/core/agent");
 let _mastra_core_evals = require("@mastra/core/evals");
 let _mastra_core_storage_domains_skills = require("@mastra/core/storage/domains/skills");
 //#region package.json
-var version = "1.23.2-alpha.0";
+var version = "1.24.0";
 //#endregion
 //#region src/vector/filter.ts
 /**
@@ -42,13 +42,15 @@ var MongoDBFilterTranslator = class extends _mastra_core_vector_filter.BaseFilte
 		return Object.fromEntries(translatedEntries);
 	}
 	translateOperatorValue(operator, value) {
-		if (this.isLogicalOperator(operator)) if (operator === "$not") {
-			if (typeof value !== "object" || value === null || Array.isArray(value)) throw new Error("$not operator requires an object");
-			if (this.isEmpty(value)) throw new Error("$not operator cannot be empty");
-			return this.translateNode(value);
-		} else {
-			if (!Array.isArray(value)) throw new Error(`Value for logical operator ${operator} must be an array`);
-			return value.map((item) => this.translateNode(item));
+		if (this.isLogicalOperator(operator)) {
+			if (operator === "$not") {
+				if (typeof value !== "object" || value === null || Array.isArray(value)) throw new Error("$not operator requires an object");
+				if (this.isEmpty(value)) throw new Error("$not operator cannot be empty");
+				return this.translateNode(value);
+			} else {
+				if (!Array.isArray(value)) throw new Error(`Value for logical operator ${operator} must be an array`);
+				return value.map((item) => this.translateNode(item));
+			}
 		}
 		if (this.isBasicOperator(operator) || this.isNumericOperator(operator)) {
 			if (value instanceof Date) return value.toISOString();
@@ -1532,17 +1534,19 @@ var MongoDBVector = class MongoDBVector extends _mastra_core_vector.MastraVector
 		if (Array.isArray(filter)) return filter.map((item) => this.transformMetadataFilter(item, metadataMode));
 		if (metadataMode === "document") {
 			const transformed = {};
-			for (const [key, value] of Object.entries(filter)) if (key.startsWith("$")) if (Array.isArray(value)) transformed[key] = value.map((item) => this.transformMetadataFilter(item, metadataMode));
-			else if (typeof value === "object" && value !== null) transformed[key] = this.transformMetadataFilter(value, metadataMode);
-			else transformed[key] = value;
-			else transformed[key] = value;
+			for (const [key, value] of Object.entries(filter)) if (key.startsWith("$")) {
+				if (Array.isArray(value)) transformed[key] = value.map((item) => this.transformMetadataFilter(item, metadataMode));
+				else if (typeof value === "object" && value !== null) transformed[key] = this.transformMetadataFilter(value, metadataMode);
+				else transformed[key] = value;
+			} else transformed[key] = value;
 			return transformed;
 		}
 		const transformed = {};
-		for (const [key, value] of Object.entries(filter)) if (key.startsWith("$")) if (Array.isArray(value)) transformed[key] = value.map((item) => this.transformMetadataFilter(item, metadataMode));
-		else if (typeof value === "object" && value !== null) transformed[key] = this.transformMetadataFilter(value, metadataMode);
-		else transformed[key] = value;
-		else if (key.startsWith("metadata.")) transformed[key] = value;
+		for (const [key, value] of Object.entries(filter)) if (key.startsWith("$")) {
+			if (Array.isArray(value)) transformed[key] = value.map((item) => this.transformMetadataFilter(item, metadataMode));
+			else if (typeof value === "object" && value !== null) transformed[key] = this.transformMetadataFilter(value, metadataMode);
+			else transformed[key] = value;
+		} else if (key.startsWith("metadata.")) transformed[key] = value;
 		else if (this.isMetadataField(key)) transformed[`metadata.${key}`] = value;
 		else transformed[key] = value;
 		return transformed;
@@ -3211,6 +3215,7 @@ var MongoDBDatasetsStorage = class extends _mastra_core_storage.DatasetsStorage
 			const { page, perPage: perPageInput } = args.pagination;
 			const collection = await this.getCollection(_mastra_core_storage.TABLE_DATASETS);
 			const filter = {};
+			if (args.filters?.datasetIds !== void 0) filter.id = { $in: args.filters.datasetIds };
 			if (args.filters?.organizationId !== void 0) filter.organizationId = args.filters.organizationId;
 			if (args.filters?.projectId !== void 0) filter.projectId = args.filters.projectId;
 			if (args.filters?.candidateKey !== void 0) filter.candidateKey = args.filters.candidateKey;
@@ -9576,15 +9581,13 @@ MIGRATION REQUIRED: Duplicate spans detected in ${_mastra_core_storage.TABLE_SPA
 							error: null
 						});
 						break;
-					case _mastra_core_storage.TraceStatus.SUCCESS:
-						andConditions.push({
-							endedAt: {
-								$exists: true,
-								$ne: null
-							},
-							error: null
-						});
-						break;
+					case _mastra_core_storage.TraceStatus.SUCCESS: andConditions.push({
+						endedAt: {
+							$exists: true,
+							$ne: null
+						},
+						error: null
+					});
 				}
 			}
 			if (andConditions.length) mongoFilter.$and = andConditions;
@@ -12366,8 +12369,10 @@ var WorkflowsStorageMongoDB = class WorkflowsStorageMongoDB extends _mastra_core
 			if (options.workflowName) query["workflow_name"] = options.workflowName;
 			if (options.status) query["snapshot.status"] = options.status;
 			if (options.fromDate) query["createdAt"] = { $gte: options.fromDate };
-			if (options.toDate) if (query["createdAt"]) query["createdAt"].$lte = options.toDate;
-			else query["createdAt"] = { $lte: options.toDate };
+			if (options.toDate) {
+				if (query["createdAt"]) query["createdAt"].$lte = options.toDate;
+				else query["createdAt"] = { $lte: options.toDate };
+			}
 			if (options.resourceId) query["resourceId"] = options.resourceId;
 			const collection = await this.getCollection(_mastra_core_storage.TABLE_WORKFLOW_SNAPSHOT);
 			let total = 0;