@mastra/pg 1.35.0 → 1.36.0-alpha.1

package/dist/docs/SKILL.md

@@ -3,7 +3,7 @@ name: mastra-pg
 description: Documentation for @mastra/pg. Use when working with @mastra/pg APIs, configuration, or implementation.
 metadata:
   package: "@mastra/pg"
-  version: "1.35.0"
+  version: "1.36.0-alpha.1"
 ---
 
 ## When to use
@@ -14,18 +14,11 @@ Use this skill whenever you are working with @mastra/pg to obtain the domain-spe
 
 Read the individual reference documents for detailed explanations and code examples.
 
-### Docs
-
-- [Workers](references/docs-deployment-workers.md) - Run Mastra workflow orchestration, schedules, and long-running background tasks in dedicated workers to keep API processes responsive under load.
-- [Semantic recall](references/docs-memory-semantic-recall.md) - Retrieve relevant messages from past Mastra conversations with semantic recall, vector search, embeddings, metadata filters, and configurable storage.
-- [Working memory](references/docs-memory-working-memory.md) - Persist user profiles, preferences, and application data with Mastra working memory using resource- or thread-scoped templates and storage adapters.
-- [Storage](references/docs-storage.md) - Configure Mastra storage to persist memory, workflow state, observability data, evals, schedules, and long-running agent state across restarts.
-
 ### Integrations
 
 - [ClickHouse Managed Postgres](references/integrations-databases-clickhouse-managed-postgres.md) - Store Mastra application data in ClickHouse Managed Postgres with PostgresStore and verified TLS.
 - [DynamoDB](references/integrations-databases-dynamodb.md) - Persist Mastra data in Amazon DynamoDB with a single-table ElectroDB design, configurable indexes, TTL support, credentials, and table initialization.
-- [Neon Postgres](references/integrations-databases-neon.md) - Connect Mastra to Neon Postgres with PostgresStore, pooled production connections, schema initialization, vector search, and Neon agent skills.
+- [Neon Postgres](references/integrations-databases-neon.md) - Connect Mastra to Neon Postgres with PostgresStore, pooled production connections, schema initialization, vector search, and Neon agent skills, and give agents Neon tools through Mastra Connect.
 - [PostgreSQL](references/integrations-databases-postgresql.md) - Persist Mastra application data in PostgreSQL with PostgresStore, configure connections and pools, initialize schemas, and enable observability.
 - [PG](references/integrations-vectors-pg.md) - Run pgvector similarity search inside PostgreSQL from Mastra with HNSW or IVFFlat indexing, metadata filtering, and direct connection pool access.
 
@@ -38,10 +31,6 @@ Read the individual reference documents for detailed explanations and code examp
 - [Chunking and embedding documents](references/reference-rag-chunking-and-embedding.md) - Chunk documents with MDocument, generate embeddings through the AI SDK, and prepare text and metadata for vector storage and RAG retrieval.
 - [Reference: Metadata filters](references/reference-rag-metadata-filters.md) - Mastra provides a unified metadata filtering syntax across all vector stores, based on MongoDB/Sift query syntax.
 - [RAG (Retrieval-Augmented Generation) in Mastra](references/reference-rag-overview.md) - RAG in Mastra helps you enhance LLM outputs by incorporating relevant context from your own data sources, improving accuracy and grounding responses in real information.
-- [Retrieval, semantic search, reranking](references/reference-rag-retrieval.md) - After storing embeddings, you need to retrieve relevant chunks to answer user queries.
-- [Storing embeddings in a vector database](references/reference-rag-vector-databases.md) - After generating embeddings, you need to store them in a database that supports vector similarity search.
-- [Reference: Composite storage](references/reference-storage-composite.md) - MastraCompositeStore can compose storage domains from different providers. Use it when you need different databases for different purposes.
-- [Reference: Storage retention (prune)](references/reference-storage-retention.md) - prune() deletes rows. It caps growth and is safe to run against large tables (batched, bounded, resumable, cancellable).
 - [Reference: createVectorQueryTool()](references/reference-tools-vector-query-tool.md) - The createVectorQueryTool() function creates a tool for semantic search over vector stores.
 
 

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,6 +1,162 @@
 {
-  "version": "1.35.0",
+  "version": "1.36.0-alpha.1",
   "package": "@mastra/pg",
-  "exports": {},
+  "exports": {
+    "AgentsPG": {
+      "types": "dist/storage/domains/agents/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 4366
+    },
+    "BackgroundTasksPG": {
+      "types": "dist/storage/domains/background-tasks/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 5297
+    },
+    "BlobsPG": {
+      "types": "dist/storage/domains/blobs/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 5688
+    },
+    "ChannelsPG": {
+      "types": "dist/storage/domains/channels/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 5790
+    },
+    "DatasetsPG": {
+      "types": "dist/storage/domains/datasets/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 6032
+    },
+    "ExperimentsPG": {
+      "types": "dist/storage/domains/experiments/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 7289
+    },
+    "FavoritesPG": {
+      "types": "dist/storage/domains/favorites/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 8261
+    },
+    "KnowledgePG": {
+      "types": "dist/storage/domains/knowledge/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 10139
+    },
+    "MCPClientsPG": {
+      "types": "dist/storage/domains/mcp-clients/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 10296
+    },
+    "MCPServersPG": {
+      "types": "dist/storage/domains/mcp-servers/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 10865
+    },
+    "MemoryPG": {
+      "types": "dist/storage/domains/memory/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 11653
+    },
+    "NotificationsPG": {
+      "types": "dist/storage/domains/notifications/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 14464
+    },
+    "ObservabilityPG": {
+      "types": "dist/storage/domains/observability/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 14886
+    },
+    "ObservabilityStoragePostgresVNext": {
+      "types": "dist/storage/domains/observability/v-next/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 21805
+    },
+    "PGVECTOR_PROMPT": {
+      "types": "dist/vector/prompt.d.ts",
+      "implementation": "dist/index.js",
+      "line": 28475
+    },
+    "PgFactoryStorage": {
+      "types": "dist/storage/factory-storage.d.ts",
+      "implementation": "dist/index.js",
+      "line": 27961
+    },
+    "PgVector": {
+      "types": "dist/vector/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 593
+    },
+    "PoolAdapter": {
+      "types": "dist/storage/client.d.ts",
+      "implementation": "dist/index.js",
+      "line": 2069
+    },
+    "PostgresStore": {
+      "types": "dist/storage/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 28176
+    },
+    "PostgresStoreVNext": {
+      "types": "dist/storage/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 28394
+    },
+    "PromptBlocksPG": {
+      "types": "dist/storage/domains/prompt-blocks/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 22250
+    },
+    "SchedulesPG": {
+      "types": "dist/storage/domains/schedules/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 22877
+    },
+    "ScorerDefinitionsPG": {
+      "types": "dist/storage/domains/scorer-definitions/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 23198
+    },
+    "ScoresPG": {
+      "types": "dist/storage/domains/scores/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 23821
+    },
+    "SkillsPG": {
+      "types": "dist/storage/domains/skills/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 24264
+    },
+    "ThreadStatePG": {
+      "types": "dist/storage/domains/thread-state/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 24955
+    },
+    "ToolProviderConnectionsPG": {
+      "types": "dist/storage/domains/tool-provider-connections/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 25129
+    },
+    "WorkflowDefinitionsPG": {
+      "types": "dist/storage/domains/workflow-definitions/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 25393
+    },
+    "WorkflowsPG": {
+      "types": "dist/storage/domains/workflows/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 25776
+    },
+    "WorkspacesPG": {
+      "types": "dist/storage/domains/workspaces/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 27061
+    },
+    "exportSchemas": {
+      "types": "dist/storage/index.d.ts",
+      "implementation": "dist/index.js",
+      "line": 28143
+    }
+  },
   "modules": {}
 }

package/dist/docs/references/integrations-databases-neon.md

@@ -6,6 +6,8 @@
 
 [Neon](https://neon.com) is a managed PostgreSQL service. Mastra connects to Neon through [`PostgresStore`](https://mastra.ai/integrations/databases/postgresql), which uses the Node.js `pg` driver. Neon doesn't require a separate Mastra storage package.
 
+You can also give an agent tools to manage Neon projects and branches, run SQL, and apply schema migrations through [Mastra Connect](#connect).
+
 ## Quickstart
 
 Create a Neon project, then copy its [pooled connection string](https://neon.com/docs/connect/connect-from-any-app) into `DATABASE_URL`.
@@ -219,4 +221,38 @@ const vector = new PgVector({
 })
 ```
 
-Setting `disableInit: true` prevents the runtime process from creating or changing the extension, tables and indexes.
+Setting `disableInit: true` prevents the runtime process from creating or changing the extension, tables and indexes.
+
+## Connect
+
+Before you start, complete the [Connect setup](https://mastra.ai/docs/mastra-platform/connect) to install `@mastra/connect` and configure your platform project.
+
+### Agent tools
+
+Give agents tools from Neon's hosted Model Context Protocol (MCP) server to manage projects and branches, run SQL, and plan and apply schema migrations in Neon.
+
+Connect an account with the `neon-mcp` provider ID. Run this command from the directory that contains your `.env` file:
+
+```bash
+mastra connect add neon-mcp
+```
+
+Then pass [`tools()`](https://mastra.ai/reference/connect/tools) to the agent and select the provider:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { tools } from '@mastra/connect'
+
+export const neonMcpAgent = new Agent({
+  id: 'neon-mcp-agent',
+  name: 'Neon agent',
+  instructions:
+    'You help people manage projects and branches, run SQL, and plan and apply schema migrations in Neon.',
+  model: '__GATEWAY_OPENAI_MODEL_LUNA__',
+  tools: tools({ providers: ['neon-mcp'] }),
+})
+```
+
+Mastra discovers Neon's tools from its MCP server when the agent runs. The available tools depend on the server and the connected account, not on your `@mastra/connect` version. Tool keys start with `neon-mcp_`.
+
+To see which tools Neon provides, read the [Neon MCP server](https://neon.com/docs/ai/neon-mcp-server) documentation. To require approval before a call runs, see [MCP providers](https://mastra.ai/reference/connect/tools) in the `tools()` reference.

package/dist/docs/references/integrations-databases-postgresql.md

@@ -243,6 +243,52 @@ const thread = await memoryStore?.getThreadById({ threadId: '...' })
 
 > **Warning:** If `init()` isn't called, tables won't be created and storage operations will fail silently or throw errors.
 
+### Managed PostgreSQL and connection poolers
+
+`PostgresStore` connects to managed PostgreSQL providers with the connection string they give you. No provider-specific package is required.
+
+`init()` runs all schema changes on a single connection, so it works through transaction-mode connection poolers such as PgBouncer. You can use the provider's pooled connection string and let Mastra create the schema on startup.
+
+#### Separate schema initialization
+
+If the runtime database role can't create tables or indexes, run `init()` once during deployment with a role that can:
+
+```typescript
+import { PostgresStore } from '@mastra/pg'
+
+const storage = new PostgresStore({
+  id: 'pg-storage-init',
+  connectionString: process.env.DATABASE_ADMIN_URL,
+})
+
+try {
+  await storage.init()
+  // Only needed if the application uses Knowledge
+  await storage.initKnowledge()
+} finally {
+  await storage.close()
+}
+```
+
+The runtime role needs read and write access to the tables this script creates. See [PostgreSQL privileges](https://www.postgresql.org/docs/current/ddl-priv.html).
+
+Then set `disableInit: true` on the runtime store so it skips schema creation:
+
+```typescript
+import { Mastra } from '@mastra/core'
+import { PostgresStore } from '@mastra/pg'
+
+export const mastra = new Mastra({
+  storage: new PostgresStore({
+    id: 'pg-storage',
+    connectionString: process.env.DATABASE_URL,
+    disableInit: true,
+  }),
+})
+```
+
+`disableInit: true` also makes explicit `init()` calls a no-op, so leave it off the store in the deployment script.
+
 ### Using an Existing Pool
 
 If you already have a `pg.Pool` in your application (e.g., shared with an ORM or for Row Level Security), you can pass it directly to `PostgresStore`:

package/dist/docs/references/reference-processors-message-history-processor.md

@@ -33,7 +33,7 @@ const processor = new MessageHistory({
 
 **processInput** (`(args: { messages: MastraDBMessage[]; messageList: MessageList; abort: (reason?: string) => never; tracingContext?: TracingContext; requestContext?: RequestContext }) => Promise<MessageList | MastraDBMessage[]>`): Fetches historical messages from storage and adds them to the message list
 
-**processOutputResult** (`(args: { messages: MastraDBMessage[]; messageList: MessageList; abort: (reason?: string) => never; tracingContext?: TracingContext; requestContext?: RequestContext }) => Promise<MessageList>`): Persists new messages (user input and assistant response) to storage, excluding system messages
+**processOutputResult** (`(args: { messages: MastraDBMessage[]; messageList: MessageList; abort: (reason?: string) => never; tracingContext?: TracingContext; requestContext?: RequestContext; result?: OutputResult }) => Promise<MessageList>`): Persists new messages (user input and assistant response) to storage, excluding system messages
 
 ## Extended usage example
 

package/dist/docs/references/reference-processors-semantic-recall-processor.md

@@ -4,7 +4,7 @@
 
 # SemanticRecall
 
-The `SemanticRecall` is a **hybrid processor** that enables semantic search over conversation history using vector embeddings. On input, it performs semantic search to find relevant historical messages. On output, it creates embeddings for new messages to enable future semantic retrieval.
+The `SemanticRecall` is a **hybrid processor** that enables semantic search over conversation history using vector embeddings. On input, it performs semantic search to find relevant historical messages. On output, it creates embeddings for new messages to enable future semantic retrieval. With a self-embedding vector store and no `embedder`, it sends the message text to the store, which creates the embeddings.
 
 ## Usage example
 

package/dist/docs/references/reference-tools-vector-query-tool.md

@@ -88,14 +88,14 @@ The tool returns an object with:
 ```typescript
 {
   id: string;         // Unique chunk/document identifier
-  metadata: any;      // All metadata fields (document ID, etc.)
-  vector: number[];   // Embedding vector (if available)
+  metadata?: any;     // All metadata fields (document ID, etc.)
+  vector: number[];   // Embedding vector, or [] when unavailable
   score: number;      // Similarity score for this retrieval
   document: string;   // Full chunk/document text (if available)
 }
 ```
 
-`document` is only populated by vector stores whose `query()` returns document content, such as Chroma, Elasticsearch, LanceDB, and MongoDB. For other stores, such as PgVector, it's an empty string. Read the chunk text from `sources[i].metadata.text` (or whichever metadata key you stored it under).
+`document` is only populated by vector stores whose `query()` returns document content, such as Chroma, Elasticsearch, LanceDB, and MongoDB. For other stores, such as PgVector, it's an empty string. Read the chunk text from `sources[i].metadata?.text` (or whichever metadata key you stored it under). `metadata` is `undefined` when the store returns no metadata for a result.
 
 ## Default tool description