@mastra/pg 1.8.0-alpha.0 → 1.8.1-alpha.0

package/CHANGELOG.md

@@ -1,5 +1,76 @@
 # @mastra/pg
 
+## 1.8.1-alpha.0
+
+### Patch Changes
+
+- Added dated message boundary delimiters when activating buffered observations for improved cache stability. ([#14367](https://github.com/mastra-ai/mastra/pull/14367))
+
+- Updated dependencies [[`4444280`](https://github.com/mastra-ai/mastra/commit/444428094253e916ec077e66284e685fde67021e), [`dbb879a`](https://github.com/mastra-ai/mastra/commit/dbb879af0b809c668e9b3a9d8bac97d806caa267), [`8de3555`](https://github.com/mastra-ai/mastra/commit/8de355572c6fd838f863a3e7e6fe24d0947b774f)]:
+  - @mastra/core@1.14.0-alpha.2
+
+## 1.8.0
+
+### Minor Changes
+
+- Added `metadataIndexes` option to `createIndex()` for PgVector. This allows creating btree indexes on specific metadata fields in vector tables, significantly improving query performance when filtering by those fields. This is especially impactful for Memory's `memory_messages` table, which filters by `thread_id` and `resource_id` — previously causing sequential scans under load. ([#14034](https://github.com/mastra-ai/mastra/pull/14034))
+
+  **Usage example:**
+
+  ```ts
+  await pgVector.createIndex({
+    indexName: 'my_vectors',
+    dimension: 1536,
+    metadataIndexes: ['thread_id', 'resource_id'],
+  });
+  ```
+
+  Fixes #12109
+
+- Add support for pgvector's `bit` and `sparsevec` vector storage types ([#12815](https://github.com/mastra-ai/mastra/pull/12815))
+
+  You can now store binary and sparse vectors in `@mastra/pg`:
+
+  ```ts
+  // Binary vectors for fast similarity search
+  await db.createIndex({
+    indexName: 'my_binary_index',
+    dimension: 128,
+    metric: 'hamming', // or 'jaccard'
+    vectorType: 'bit',
+  });
+
+  // Sparse vectors for BM25/TF-IDF representations
+  await db.createIndex({
+    indexName: 'my_sparse_index',
+    dimension: 500,
+    metric: 'cosine',
+    vectorType: 'sparsevec',
+  });
+  ```
+
+  What's new:
+  - `vectorType: 'bit'` for binary vectors with `'hamming'` and `'jaccard'` distance metrics
+  - `vectorType: 'sparsevec'` for sparse vectors (cosine, euclidean, dotproduct)
+  - Automatic metric normalization: `bit` defaults to `'hamming'` when no metric is specified
+  - `includeVector` round-trips work correctly for all vector types
+  - Requires pgvector >= 0.7.0
+
+- Added `requestContext` column to the spans table. Request context data from tracing is now persisted alongside other span data. ([#14020](https://github.com/mastra-ai/mastra/pull/14020))
+
+- Added `requestContext` and `requestContextSchema` column support to dataset storage. Dataset items now persist request context alongside input and ground truth data. ([#13938](https://github.com/mastra-ai/mastra/pull/13938))
+
+### Patch Changes
+
+- Added resilient column handling to insert and update operations. Unknown columns in records are now silently dropped instead of causing SQL errors, ensuring forward compatibility when newer domain packages add fields that haven't been migrated yet. ([#14021](https://github.com/mastra-ai/mastra/pull/14021))
+
+  For example, calling `db.insert({ tableName, record: { id: '1', title: 'Hello', futureField: 'value' } })` will silently ignore `futureField` if it doesn't exist in the database table, rather than throwing. The same applies to `update` — unknown fields in the data payload are dropped before building the SQL statement.
+
+- Fixed slow semantic recall in the Postgres storage adapter for large threads. Recall now completes in under 500ms even for threads with 7,000+ messages, down from ~30 seconds. (Fixes #11702) ([#14022](https://github.com/mastra-ai/mastra/pull/14022))
+
+- Updated dependencies [[`4f71b43`](https://github.com/mastra-ai/mastra/commit/4f71b436a4a6b8839842d8da47b57b84509af56c), [`a070277`](https://github.com/mastra-ai/mastra/commit/a07027766ce195ba74d0783116d894cbab25d44c), [`b628b91`](https://github.com/mastra-ai/mastra/commit/b628b9128b372c0f54214d902b07279f03443900), [`332c014`](https://github.com/mastra-ai/mastra/commit/332c014e076b81edf7fe45b58205882726415e90), [`6b63153`](https://github.com/mastra-ai/mastra/commit/6b63153878ea841c0f4ce632ba66bb33e57e9c1b), [`4246e34`](https://github.com/mastra-ai/mastra/commit/4246e34cec9c26636d0965942268e6d07c346671), [`b8837ee`](https://github.com/mastra-ai/mastra/commit/b8837ee77e2e84197609762bfabd8b3da326d30c), [`866cc2c`](https://github.com/mastra-ai/mastra/commit/866cc2cb1f0e3b314afab5194f69477fada745d1), [`5d950f7`](https://github.com/mastra-ai/mastra/commit/5d950f7bf426a215a1808f0abef7de5c8336ba1c), [`28c85b1`](https://github.com/mastra-ai/mastra/commit/28c85b184fc32b40f7f160483c982da6d388ecbd), [`e9a08fb`](https://github.com/mastra-ai/mastra/commit/e9a08fbef1ada7e50e961e2f54f55e8c10b4a45c), [`1d0a8a8`](https://github.com/mastra-ai/mastra/commit/1d0a8a8acf33203d5744fc429b090ad8598aa8ed), [`631ffd8`](https://github.com/mastra-ai/mastra/commit/631ffd82fed108648b448b28e6a90e38c5f53bf5), [`6bcbf8a`](https://github.com/mastra-ai/mastra/commit/6bcbf8a6774d5a53b21d61db8a45ce2593ca1616), [`aae2295`](https://github.com/mastra-ai/mastra/commit/aae2295838a2d329ad6640829e87934790ffe5b8), [`aa61f29`](https://github.com/mastra-ai/mastra/commit/aa61f29ff8095ce46a4ae16e46c4d8c79b2b685b), [`7ff3714`](https://github.com/mastra-ai/mastra/commit/7ff37148515439bb3be009a60e02c3e363299760), [`18c3a90`](https://github.com/mastra-ai/mastra/commit/18c3a90c9e48cf69500e308affeb8eba5860b2af), [`41d79a1`](https://github.com/mastra-ai/mastra/commit/41d79a14bd8cb6de1e2565fd0a04786bae2f211b), [`f35487b`](https://github.com/mastra-ai/mastra/commit/f35487bb2d46c636e22aa71d90025613ae38235a), [`6dc2192`](https://github.com/mastra-ai/mastra/commit/6dc21921aef0f0efab15cd0805fa3d18f277a76f), [`eeb3a3f`](https://github.com/mastra-ai/mastra/commit/eeb3a3f43aca10cf49479eed2a84b7d9ecea02ba), [`e673376`](https://github.com/mastra-ai/mastra/commit/e6733763ad1321aa7e5ae15096b9c2104f93b1f3), [`05f8d90`](https://github.com/mastra-ai/mastra/commit/05f8d9009290ce6aa03428b3add635268615db85), [`b2204c9`](https://github.com/mastra-ai/mastra/commit/b2204c98a42848bbfb6f0440f005dc2b6354f1cd), [`a1bf1e3`](https://github.com/mastra-ai/mastra/commit/a1bf1e385ed4c0ef6f11b56c5887442970d127f2), [`b6f647a`](https://github.com/mastra-ai/mastra/commit/b6f647ae2388e091f366581595feb957e37d5b40), [`0c57b8b`](https://github.com/mastra-ai/mastra/commit/0c57b8b0a69a97b5a4ae3f79be6c610f29f3cf7b), [`b081f27`](https://github.com/mastra-ai/mastra/commit/b081f272cf411716e1d6bd72ceac4bcee2657b19), [`4b8da97`](https://github.com/mastra-ai/mastra/commit/4b8da97a5ce306e97869df6c39535d9069e563db), [`0c09eac`](https://github.com/mastra-ai/mastra/commit/0c09eacb1926f64cfdc9ae5c6d63385cf8c9f72c), [`6b9b93d`](https://github.com/mastra-ai/mastra/commit/6b9b93d6f459d1ba6e36f163abf62a085ddb3d64), [`31b6067`](https://github.com/mastra-ai/mastra/commit/31b6067d0cc3ab10e1b29c36147f3b5266bc714a), [`797ac42`](https://github.com/mastra-ai/mastra/commit/797ac4276de231ad2d694d9aeca75980f6cd0419), [`0bc289e`](https://github.com/mastra-ai/mastra/commit/0bc289e2d476bf46c5b91c21969e8d0c6864691c), [`9b75a06`](https://github.com/mastra-ai/mastra/commit/9b75a06e53ebb0b950ba7c1e83a0142047185f46), [`4c3a1b1`](https://github.com/mastra-ai/mastra/commit/4c3a1b122ea083e003d71092f30f3b31680b01c0), [`256df35`](https://github.com/mastra-ai/mastra/commit/256df3571d62beb3ad4971faa432927cc140e603), [`85cc3b3`](https://github.com/mastra-ai/mastra/commit/85cc3b3b6f32ae4b083c26498f50d5b250ba944b), [`97ea28c`](https://github.com/mastra-ai/mastra/commit/97ea28c746e9e4147d56047bbb1c4a92417a3fec), [`d567299`](https://github.com/mastra-ai/mastra/commit/d567299cf81e02bd9d5221d4bc05967d6c224161), [`716ffe6`](https://github.com/mastra-ai/mastra/commit/716ffe68bed81f7c2690bc8581b9e140f7bf1c3d), [`8296332`](https://github.com/mastra-ai/mastra/commit/8296332de21c16e3dfc3d0b2d615720a6dc88f2f), [`4df2116`](https://github.com/mastra-ai/mastra/commit/4df211619dd922c047d396ca41cd7027c8c4c8e7), [`2219c1a`](https://github.com/mastra-ai/mastra/commit/2219c1acbd21da116da877f0036ffb985a9dd5a3), [`17c4145`](https://github.com/mastra-ai/mastra/commit/17c4145166099354545582335b5252bdfdfd908b)]:
+  - @mastra/core@1.11.0
+
 ## 1.8.0-alpha.0
 
 ### Minor Changes

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: "1.8.0-alpha.0"
+  version: "1.8.1-alpha.0"
 ---
 
 ## When to use
@@ -16,25 +16,25 @@ Read the individual reference documents for detailed explanations and code examp
 
 ### Docs
 
-- [Semantic Recall](references/docs-memory-semantic-recall.md) - Learn how to use semantic recall in Mastra to retrieve relevant messages from past conversations using vector search and embeddings.
-- [Storage](references/docs-memory-storage.md) - Configure storage for Mastra's memory system to persist conversations, workflows, and traces.
-- [Working Memory](references/docs-memory-working-memory.md) - Learn how to configure working memory in Mastra to store persistent user data, preferences.
+- [Semantic recall](references/docs-memory-semantic-recall.md) - Learn how to use semantic recall in Mastra to retrieve relevant messages from past conversations using vector search and embeddings.
+- [Storage](references/docs-memory-storage.md) - Configure storage for Mastra to persist conversations and other runtime state.
+- [Working memory](references/docs-memory-working-memory.md) - Learn how to configure working memory in Mastra to store persistent user data, preferences.
 - [RAG (Retrieval-Augmented Generation) in Mastra](references/docs-rag-overview.md) - Overview of Retrieval-Augmented Generation (RAG) in Mastra, detailing its capabilities for enhancing LLM outputs with relevant context.
-- [Retrieval, Semantic Search, Reranking](references/docs-rag-retrieval.md) - Guide on retrieval processes in Mastra's RAG systems, including semantic search, filtering, and re-ranking.
-- [Storing Embeddings in A Vector Database](references/docs-rag-vector-databases.md) - Guide on vector storage options in Mastra, including embedded and dedicated vector databases for similarity search.
+- [Retrieval, semantic search, reranking](references/docs-rag-retrieval.md) - Guide on retrieval processes in Mastra's RAG systems, including semantic search, filtering, and re-ranking.
+- [Storing embeddings in a vector database](references/docs-rag-vector-databases.md) - Guide on vector storage options in Mastra, including embedded and dedicated vector databases for similarity search.
 
 ### Reference
 
-- [Reference: Memory Class](references/reference-memory-memory-class.md) - Documentation for the `Memory` class in Mastra, which provides a robust system for managing conversation history and thread-based message storage.
-- [Reference: Message History Processor](references/reference-processors-message-history-processor.md) - Documentation for the MessageHistory processor in Mastra, which handles retrieval and persistence of conversation history.
-- [Reference: Semantic Recall Processor](references/reference-processors-semantic-recall-processor.md) - Documentation for the SemanticRecall processor in Mastra, which enables semantic search over conversation history using vector embeddings.
-- [Reference: Working Memory Processor](references/reference-processors-working-memory-processor.md) - Documentation for the WorkingMemory processor in Mastra, which injects persistent user/context data as system instructions.
-- [Reference: Metadata Filters](references/reference-rag-metadata-filters.md) - Documentation for metadata filtering capabilities in Mastra, which allow for precise querying of vector search results across different vector stores.
-- [Reference: Composite Storage](references/reference-storage-composite.md) - Documentation for combining multiple storage backends in Mastra.
-- [Reference: DynamoDB Storage](references/reference-storage-dynamodb.md) - Documentation for the DynamoDB storage implementation in Mastra, using a single-table design with ElectroDB.
-- [Reference: PostgreSQL Storage](references/reference-storage-postgresql.md) - Documentation for the PostgreSQL storage implementation in Mastra.
+- [Reference: Memory class](references/reference-memory-memory-class.md) - Documentation for the `Memory` class in Mastra, which provides a robust system for managing conversation history and thread-based message storage.
+- [Reference: MessageHistory](references/reference-processors-message-history-processor.md) - Documentation for the MessageHistory processor in Mastra, which handles retrieval and persistence of conversation history.
+- [Reference: SemanticRecall](references/reference-processors-semantic-recall-processor.md) - Documentation for the SemanticRecall processor in Mastra, which enables semantic search over conversation history using vector embeddings.
+- [Reference: WorkingMemory](references/reference-processors-working-memory-processor.md) - Documentation for the WorkingMemory processor in Mastra, which injects persistent user/context data as system instructions.
+- [Reference: Metadata filters](references/reference-rag-metadata-filters.md) - Documentation for metadata filtering capabilities in Mastra, which allow for precise querying of vector search results across different vector stores.
+- [Reference: Composite storage](references/reference-storage-composite.md) - Documentation for combining multiple storage backends in Mastra.
+- [Reference: DynamoDB storage](references/reference-storage-dynamodb.md) - Documentation for the DynamoDB storage implementation in Mastra, using a single-table design with ElectroDB.
+- [Reference: PostgreSQL storage](references/reference-storage-postgresql.md) - Documentation for the PostgreSQL storage implementation in Mastra.
 - [Reference: createVectorQueryTool()](references/reference-tools-vector-query-tool.md) - Documentation for the Vector Query Tool in Mastra, which facilitates semantic search over vector stores with filtering and reranking capabilities.
-- [Reference: PG Vector Store](references/reference-vectors-pg.md) - Documentation for the PgVector class in Mastra, which provides vector search using PostgreSQL with pgvector extension.
+- [Reference: PG vector store](references/reference-vectors-pg.md) - Documentation for the PgVector class in Mastra, which provides vector search using PostgreSQL with pgvector extension.
 
 
 Read [assets/SOURCE_MAP.json](assets/SOURCE_MAP.json) for source code references.

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.8.0-alpha.0",
+  "version": "1.8.1-alpha.0",
   "package": "@mastra/pg",
   "exports": {},
   "modules": {}

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

@@ -1,10 +1,10 @@
-# Semantic Recall
+# Semantic recall
 
 If you ask your friend what they did last weekend, they will search in their memory for events associated with "last weekend" and then tell you what they did. That's sort of like how semantic recall works in Mastra.
 
 > **Watch 📹:** What semantic recall is, how it works, and how to configure it in Mastra → [YouTube (5 minutes)](https://youtu.be/UVZtK8cK8xQ)
 
-## How Semantic Recall Works
+## How semantic recall works
 
 Semantic recall is RAG-based search that helps agents maintain context across longer interactions when messages are no longer within [recent message history](https://mastra.ai/docs/memory/message-history).
 
@@ -16,7 +16,7 @@ When it's enabled, new messages are used to query a vector DB for semantically s
 
 After getting a response from the LLM, all new messages (user, assistant, and tool calls/results) are inserted into the vector DB to be recalled in later interactions.
 
-## Quick Start
+## Quick start
 
 Semantic recall is enabled by default, so if you give your agent memory it will be included:
 
@@ -28,12 +28,12 @@ const agent = new Agent({
   id: 'support-agent',
   name: 'SupportAgent',
   instructions: 'You are a helpful support agent.',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   memory: new Memory(),
 })
 ```
 
-## Using the recall() Method
+## Using the `recall()` method
 
 While `listMessages` retrieves messages by thread ID with basic pagination, [`recall()`](https://mastra.ai/reference/memory/recall) adds support for **semantic search**. When you need to find messages by meaning rather than recency, use `recall()` with a `vectorSearchString`:
 
@@ -182,7 +182,7 @@ const agent = new Agent({
 })
 ```
 
-### Using FastEmbed (Local)
+### Using FastEmbed (local)
 
 To use FastEmbed (a local embedding model), install `@mastra/fastembed`:
 
@@ -224,7 +224,7 @@ const agent = new Agent({
 })
 ```
 
-## PostgreSQL Index Optimization
+## 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.
 
@@ -283,6 +283,6 @@ You might want to disable semantic recall in scenarios like:
 - When message history provides sufficient context for the current conversation.
 - In performance-sensitive applications, like realtime two-way audio, where the added latency of creating embeddings and running vector queries is noticeable.
 
-## Viewing Recalled Messages
+## Viewing recalled messages
 
 When tracing is enabled, any messages retrieved via semantic recall will appear in the agent's trace output, alongside recent message history (if configured).

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

@@ -1,6 +1,6 @@
 # Storage
 
-For agents to remember previous interactions, Mastra needs a database. Use a storage adapter for one of the [supported databases](#supported-providers) and pass it to your Mastra instance.
+For agents to remember previous interactions, Mastra needs a storage adapter. Use one of the [supported providers](#supported-providers) and pass it to your Mastra instance.
 
 ```typescript
 import { Mastra } from '@mastra/core'
@@ -24,7 +24,7 @@ export const mastra = new Mastra({
 
 This configures instance-level storage, which all agents share by default. You can also configure [agent-level storage](#agent-level-storage) for isolated data boundaries.
 
-Mastra automatically creates the necessary tables on first interaction. See the [core schema](https://mastra.ai/reference/storage/overview) for details on what gets created, including tables for messages, threads, resources, workflows, traces, and evaluation datasets.
+Mastra automatically initializes the necessary storage structures on first interaction. See [Storage Overview](https://mastra.ai/reference/storage/overview) for domain coverage and the schema used by the built-in database-backed domains.
 
 ## Supported providers
 
@@ -35,7 +35,7 @@ Each provider page includes installation instructions, configuration parameters,
 - [MongoDB](https://mastra.ai/reference/storage/mongodb)
 - [Upstash](https://mastra.ai/reference/storage/upstash)
 - [Cloudflare D1](https://mastra.ai/reference/storage/cloudflare-d1)
-- [Cloudflare Durable Objects](https://mastra.ai/reference/storage/cloudflare)
+- [Cloudflare KV & Durable Objects](https://mastra.ai/reference/storage/cloudflare)
 - [Convex](https://mastra.ai/reference/storage/convex)
 - [DynamoDB](https://mastra.ai/reference/storage/dynamodb)
 - [LanceDB](https://mastra.ai/reference/storage/lance)
@@ -49,7 +49,7 @@ Storage can be configured at the instance level (shared by all agents) or at the
 
 ### Instance-level storage
 
-Add storage to your Mastra instance so all agents, workflows, observability traces and scores share the same memory provider:
+Add storage to your Mastra instance so all agents, workflows, observability traces, and scores share the same storage backend:
 
 ```typescript
 import { Mastra } from '@mastra/core'
@@ -71,7 +71,7 @@ This is useful when all primitives share the same storage backend and have simil
 
 #### Composite storage
 
-[Composite storage](https://mastra.ai/reference/storage/composite) is an alternative way to configure instance-level storage. Use `MastraCompositeStore` to set the `memory` domain (and any other [domains](https://mastra.ai/reference/storage/composite) you need) to different storage providers.
+[Composite storage](https://mastra.ai/reference/storage/composite) is an alternative way to configure instance-level storage. Use `MastraCompositeStore` to route `memory` and any other [supported domains](https://mastra.ai/reference/storage/composite) to different storage providers.
 
 ```typescript
 import { Mastra } from '@mastra/core'
@@ -180,7 +180,7 @@ export const agent = new Agent({
   memory: new Memory({
     options: {
       generateTitle: {
-        model: 'openai/gpt-4o-mini',
+        model: 'openai/gpt-5-mini',
         instructions: 'Generate a 1 word title',
       },
     },

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

@@ -13,7 +13,7 @@ Working memory can persist at two different scopes:
 
 **Important:** Switching between scopes means the agent won't see memory from the other scope - thread-scoped memory is completely separate from resource-scoped memory.
 
-## Quick Start
+## Quick start
 
 Here's a minimal example of setting up an agent with working memory:
 
@@ -26,7 +26,7 @@ const agent = new Agent({
   id: 'personal-assistant',
   name: 'PersonalAssistant',
   instructions: 'You are a helpful personal assistant.',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   memory: new Memory({
     options: {
       workingMemory: {
@@ -37,13 +37,13 @@ const agent = new Agent({
 })
 ```
 
-## How it Works
+## How it works
 
 Working memory is a block of Markdown text that the agent is able to update over time to store continuously relevant information:
 
 [YouTube video player](https://www.youtube-nocookie.com/embed/UMy_JHLf1n8)
 
-## Memory Persistence Scopes
+## Memory persistence scopes
 
 Working memory can operate in two different scopes, allowing you to choose how memory persists across conversations:
 
@@ -117,7 +117,7 @@ const memory = new Memory({
 - Temporary or session-specific information
 - Workflows where each thread needs working memory but threads are ephemeral and not related to each other
 
-## Storage Adapter Support
+## Storage adapter support
 
 Resource-scoped working memory requires specific storage adapters that support the `mastra_resources` table:
 
@@ -128,7 +128,7 @@ Resource-scoped working memory requires specific storage adapters that support t
 - **Upstash** (`@mastra/upstash`)
 - **MongoDB** (`@mastra/mongodb`)
 
-## Custom Templates
+## Custom templates
 
 Templates guide the agent on what information to track and update in working memory. While a default template is used if none is provided, you'll typically want to define a custom template tailored to your agent's specific use case to ensure it remembers the most relevant information.
 
@@ -142,7 +142,7 @@ const memory = new Memory({
       template: `
 # User Profile
 
-## Personal Info
+## Personal info
 
 - Name:
 - Location:
@@ -156,7 +156,7 @@ const memory = new Memory({
   - [Deadline 1]: [Date]
   - [Deadline 2]: [Date]
 
-## Session State
+## Session state
 
 - Last Task Discussed:
 - Open Questions:
@@ -168,7 +168,7 @@ const memory = new Memory({
 })
 ```
 
-## Designing Effective Templates
+## Designing effective templates
 
 A well-structured template keeps the information straightforward for the agent to parse and update. Treat the template as a short form that you want the assistant to keep up to date.
 
@@ -206,7 +206,7 @@ const paragraphMemory = new Memory({
 })
 ```
 
-## Structured Working Memory
+## Structured working memory
 
 Working memory can also be defined using a structured schema instead of a Markdown template. This allows you to specify the exact fields and types that should be tracked, using a [Zod](https://zod.dev/) schema. When using a schema, the agent will see and update working memory as a JSON object matching your schema.
 
@@ -265,20 +265,20 @@ Schema-based working memory uses **merge semantics**, meaning the agent only nee
 - **Set a field to `null` to delete it:** This explicitly removes the field from memory
 - **Arrays are replaced entirely:** When an array field is provided, it replaces the existing array (arrays aren't merged element-by-element)
 
-## Choosing Between Template and Schema
+## Choosing between template and schema
 
 - Use a **template** (Markdown) if you want the agent to maintain memory as a free-form text block, such as a user profile or scratchpad. Templates use **replace semantics** — the agent must provide the complete memory content on each update.
 - Use a **schema** if you need structured, type-safe data that can be validated and programmatically accessed as JSON. Schemas use **merge semantics** — the agent only provides fields to update, and existing fields are preserved.
 - Only one mode can be active at a time: setting both `template` and `schema` isn't supported.
 
-## Example: Multi-step Retention
+## Example: Multi-step retention
 
 Below is a simplified view of how the `User Profile` template updates across a short user conversation:
 
 ```nohighlight
 # User Profile
 
-## Personal Info
+## Personal info
 
 - Name:
 - Location:
@@ -303,7 +303,7 @@ The agent can now refer to `Sam` or `Berlin` in later responses without requesti
 
 If your agent isn't properly updating working memory when you expect it to, you can add system instructions on _how_ and _when_ to use this template in your agent's `instructions` setting.
 
-## Setting Initial Working Memory
+## Setting initial working memory
 
 While agents typically update working memory through the `updateWorkingMemory` tool, you can also set initial working memory programmatically when creating or updating threads. This is useful for injecting user data (like their name, preferences, or other info) that you want available to the agent without passing it in every request.
 
@@ -372,7 +372,7 @@ await memory.updateWorkingMemory({
 })
 ```
 
-## Read-Only Working Memory
+## Read-only working memory
 
 In some scenarios, you may want an agent to have access to working memory data without the ability to modify it. This is useful for:
 

package/dist/docs/references/docs-rag-overview.md

@@ -59,11 +59,11 @@ console.log('Similar chunks:', results)
 
 This example shows the essentials: initialize a document, create chunks, generate embeddings, store them, and query for similar content.
 
-## Document Processing
+## Document processing
 
 The basic building block of RAG is document processing. Documents can be chunked using various strategies (recursive, sliding window, etc.) and enriched with metadata. See the [chunking and embedding doc](https://mastra.ai/docs/rag/chunking-and-embedding).
 
-## Vector Storage
+## Vector storage
 
 Mastra supports multiple vector stores for embedding persistence and similarity search, including pgvector, Pinecone, Qdrant, and MongoDB. See the [vector database doc](https://mastra.ai/docs/rag/vector-databases).
 

package/dist/docs/references/docs-rag-retrieval.md

@@ -1,10 +1,10 @@
-# Retrieval in RAG Systems
+# Retrieval in RAG systems
 
 After storing embeddings, you need to retrieve relevant chunks to answer user queries.
 
 Mastra provides flexible retrieval options with support for semantic search, filtering, and re-ranking.
 
-## How Retrieval Works
+## How retrieval works
 
 1. The user's query is converted to an embedding using the same model used for document embeddings
 2. This embedding is compared to stored embeddings using vector similarity
@@ -14,7 +14,7 @@ Mastra provides flexible retrieval options with support for semantic search, fil
 - Re-ranked for better relevance
 - Processed through a knowledge graph
 
-## Basic Retrieval
+## Basic retrieval
 
 The simplest approach is direct semantic search. This method uses vector similarity to find chunks that are semantically similar to the query:
 
@@ -63,7 +63,7 @@ Results include both the text content and a similarity score:
 ]
 ```
 
-## Advanced Retrieval options
+## Advanced retrieval options
 
 ### Metadata Filtering
 
@@ -272,7 +272,7 @@ import { PGVECTOR_PROMPT } from '@mastra/pg'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${PGVECTOR_PROMPT}
@@ -289,7 +289,7 @@ import { PINECONE_PROMPT } from '@mastra/pinecone'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${PINECONE_PROMPT}
@@ -306,7 +306,7 @@ import { QDRANT_PROMPT } from '@mastra/qdrant'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${QDRANT_PROMPT}
@@ -323,7 +323,7 @@ import { CHROMA_PROMPT } from '@mastra/chroma'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${CHROMA_PROMPT}
@@ -340,7 +340,7 @@ import { ASTRA_PROMPT } from '@mastra/astra'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${ASTRA_PROMPT}
@@ -357,7 +357,7 @@ import { LIBSQL_PROMPT } from '@mastra/libsql'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${LIBSQL_PROMPT}
@@ -374,7 +374,7 @@ import { UPSTASH_PROMPT } from '@mastra/upstash'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${UPSTASH_PROMPT}
@@ -391,7 +391,7 @@ import { VECTORIZE_PROMPT } from '@mastra/vectorize'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${VECTORIZE_PROMPT}
@@ -408,7 +408,7 @@ import { MONGODB_PROMPT } from '@mastra/mongodb'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${MONGODB_PROMPT}
@@ -425,7 +425,7 @@ import { OPENSEARCH_PROMPT } from '@mastra/opensearch'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${OPENSEARCH_PROMPT}
@@ -442,7 +442,7 @@ import { S3VECTORS_PROMPT } from '@mastra/s3vectors'
 export const ragAgent = new Agent({
   id: 'rag-agent',
   name: 'RAG Agent',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${S3VECTORS_PROMPT}
@@ -472,7 +472,7 @@ const initialResults = await pgVector.query({
 })
 
 // Create a relevance scorer
-const relevanceProvider = new MastraAgentRelevanceScorer('relevance-scorer', 'openai/gpt-5.1')
+const relevanceProvider = new MastraAgentRelevanceScorer('relevance-scorer', 'openai/gpt-5.4')
 
 // Re-rank the results
 const rerankedResults = await rerank({

package/dist/docs/references/docs-rag-vector-databases.md

@@ -1,8 +1,8 @@
-# Storing Embeddings in A Vector Database
+# Storing embeddings in a vector database
 
 After generating embeddings, you need to store them in a database that supports vector similarity search. Mastra provides a consistent interface for storing and querying embeddings across various vector databases.
 
-## Supported Databases
+## Supported databases
 
 **MongoDB**:
 
@@ -234,7 +234,7 @@ await store.upsert({
 })
 ```
 
-**ElasticSearch**:
+**Elasticsearch**:
 
 ```ts
 import { ElasticSearchVector } from '@mastra/elasticsearch'
@@ -337,7 +337,7 @@ await store.upsert({
 })
 ```
 
-## Using Vector Storage
+## Using vector storage
 
 Once initialized, all vector stores share the same interface for creating indexes, upserting embeddings, and querying.
 
@@ -355,9 +355,9 @@ await store.createIndex({
 
 The dimension size must match the output dimension of your chosen embedding model. Common dimension sizes are:
 
-- OpenAI text-embedding-3-small: 1536 dimensions (or custom, e.g., 256)
-- Cohere embed-multilingual-v3: 1024 dimensions
-- Google gemini-embedding-001: 768 dimensions (or custom)
+- `OpenAI text-embedding-3-small`: 1536 dimensions (or custom, e.g., 256)
+- `Cohere embed-multilingual-v3`: 1024 dimensions
+- `Google gemini-embedding-001`: 768 dimensions (or custom)
 
 > **Warning:** Index dimensions can't be changed after creation. To use a different model, delete and recreate the index with the new dimension size.
 
@@ -490,7 +490,7 @@ Index names must:
 - Example: `My_Index` is not valid (contains uppercase letters)
 - Example: `_myindex` is not valid (begins with underscore)
 
-**ElasticSearch**:
+**Elasticsearch**:
 
 Index names must:
 
@@ -543,7 +543,7 @@ The upsert operation:
 - Creates new vectors if they don't exist
 - Automatically handles batching for large datasets
 
-## Adding Metadata
+## Adding metadata
 
 Vector stores support rich metadata (any JSON-serializable fields) for filtering and organization. Since metadata is stored with no fixed schema, use consistent field naming to avoid unexpected query results.
 
@@ -581,7 +581,7 @@ Key metadata considerations:
 - Only include fields you plan to filter or sort by - extra fields add overhead
 - Add timestamps (e.g., 'createdAt', 'lastUpdated') to track content freshness
 
-## Deleting Vectors
+## Deleting vectors
 
 When building RAG applications, you often need to clean up stale vectors when documents are deleted or updated. Mastra provides the `deleteVectors` method that supports deleting vectors by metadata filters, making it straightforward to remove all embeddings associated with a specific document.
 
@@ -637,7 +637,7 @@ await store.deleteVectors({
 })
 ```
 
-## Best Practices
+## Best practices
 
 - Create indexes before bulk insertions
 - Use batch operations for large insertions (the upsert method handles batching automatically)

package/dist/docs/references/reference-memory-memory-class.md

@@ -1,4 +1,4 @@
-# Memory Class
+# Memory class
 
 The `Memory` class provides a robust system for managing conversation history and thread-based message storage in Mastra. It enables persistent storage of conversations, semantic search capabilities, and efficient message retrieval. You must configure a storage provider for conversation history, and if you enable semantic recall you will also need to provide a vector store and embedder.
 
@@ -11,7 +11,7 @@ import { Agent } from '@mastra/core/agent'
 export const agent = new Agent({
   name: 'test-agent',
   instructions: 'You are an agent with memory.',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   memory: new Memory({
     options: {
       workingMemory: {
@@ -60,7 +60,7 @@ import { LibSQLStore, LibSQLVector } from '@mastra/libsql'
 export const agent = new Agent({
   name: 'test-agent',
   instructions: 'You are an agent with memory.',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   memory: new Memory({
     storage: new LibSQLStore({
       id: 'test-agent-storage',
@@ -97,7 +97,7 @@ import { PgStore, PgVector } from '@mastra/pg'
 export const agent = new Agent({
   name: 'pg-agent',
   instructions: 'You are an agent with optimized PostgreSQL memory.',
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   memory: new Memory({
     storage: new PgStore({
       id: 'pg-agent-storage',