@mastra/memory 1.22.3-alpha.0 → 1.23.0-alpha.2

package/dist/docs/SKILL.md

@@ -3,7 +3,7 @@ name: mastra-memory
 description: Documentation for @mastra/memory. Use when working with @mastra/memory APIs, configuration, or implementation.
 metadata:
   package: "@mastra/memory"
-  version: "1.22.3-alpha.0"
+  version: "1.23.0-alpha.2"
 ---
 
 ## When to use
@@ -35,6 +35,7 @@ Read the individual reference documents for detailed explanations and code examp
 
 - [Reference: Mastra.getMemory()](references/reference-core-getMemory.md) - Documentation for the `Mastra.getMemory()` method in Mastra, which retrieves a registered memory instance by its registry key.
 - [Reference: Mastra.listMemory()](references/reference-core-listMemory.md) - Documentation for the `Mastra.listMemory()` method in Mastra, which returns all registered memory instances.
+- [Memory](references/reference-file-based-agents-memory.md) - Give a file-based agent persistent memory with a memory.ts module.
 - [Reference: Cloned thread utilities](references/reference-memory-clone-utilities.md) - Documentation for utility methods to work with cloned threads in Mastra Memory.
 - [Reference: Memory.cloneThread()](references/reference-memory-cloneThread.md) - Documentation for the `Memory.cloneThread()` method in Mastra, which creates a copy of a conversation thread with all its messages.
 - [Reference: Memory.createThread()](references/reference-memory-createThread.md) - Documentation for the `Memory.createThread()` method in Mastra, which creates a new conversation thread in the memory system.
@@ -42,6 +43,8 @@ Read the individual reference documents for detailed explanations and code examp
 - [Reference: Memory.listThreads()](references/reference-memory-listThreads.md) - Documentation for the `Memory.listThreads()` method in Mastra, which retrieves threads with optional filtering by resourceId and/or metadata.
 - [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: Observational Memory](references/reference-memory-observational-memory.md) - API reference for Observational Memory in Mastra — a three-tier memory system that uses Observer and Reflector agents to maintain long-term memory across conversations.
+- [Reference: summarizeConversation()](references/reference-memory-summarizeConversation.md) - Documentation for the standalone `summarizeConversation()` function in Mastra, which summarizes messages you pass in and extracts structured values from them.
+- [Reference: Memory.summarizeThread()](references/reference-memory-summarizeThread.md) - Documentation for the `Memory.summarizeThread()` method in Mastra, which summarizes a thread's conversation in one shot and extracts structured values from it.
 - [Reference: TokenLimiterProcessor](references/reference-processors-token-limiter-processor.md) - Documentation for the TokenLimiterProcessor in Mastra, which limits the number of tokens in messages.
 - [Reference: Aurora DSQL Storage](references/reference-storage-dsql.md) - Documentation for the Amazon Aurora DSQL storage implementation 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.

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,129 +1,133 @@
 {
-  "version": "1.22.3-alpha.0",
+  "version": "1.23.0-alpha.2",
   "package": "@mastra/memory",
   "exports": {
     "Extractor": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 316
     },
     "ModelByInputTokens": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 1354
     },
     "OBSERVER_SYSTEM_PROMPT": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js"
+      "implementation": "dist/chunk-GHFCSEEP.js"
     },
     "ObservationalMemory": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
-      "line": 27533
+      "implementation": "dist/chunk-GHFCSEEP.js",
+      "line": 27685
     },
     "ObservationalMemoryProcessor": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
-      "line": 30164
+      "implementation": "dist/chunk-GHFCSEEP.js",
+      "line": 30316
     },
     "TokenCounter": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
-      "line": 26858
+      "implementation": "dist/chunk-GHFCSEEP.js",
+      "line": 21467
     },
     "WorkingMemoryExtractor": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
-      "line": 20684
+      "implementation": "dist/chunk-GHFCSEEP.js",
+      "line": 22134
     },
     "buildObserverPrompt": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 4465
     },
     "buildObserverSystemPrompt": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 3732
     },
     "combineObservationGroupRanges": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 1446
     },
     "deriveObservationGroupProvenance": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 1480
     },
     "extractCurrentTask": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 4588
     },
     "formatMessagesForObserver": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 4187
     },
     "getObservationsAsOf": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
-      "line": 30386
+      "implementation": "dist/chunk-GHFCSEEP.js",
+      "line": 30538
     },
     "hasCurrentTaskSection": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 4576
     },
     "injectAnchorIds": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 3287
     },
     "optimizeObservationsForContext": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 4599
     },
     "parseAnchorId": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 3260
     },
     "parseObservationGroups": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 1415
     },
     "parseObserverOutput": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 4479
     },
     "reconcileObservationGroupsFromReflection": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 1504
     },
     "renderObservationGroupsForReflection": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 1460
     },
     "stripEphemeralAnchorIds": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 3317
     },
     "stripObservationGroups": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 1437
     },
+    "summarizeConversation": {
+      "types": "dist/processors/index.d.ts",
+      "implementation": "dist/chunk-GHFCSEEP.js"
+    },
     "wrapInObservationGroup": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
+      "implementation": "dist/chunk-GHFCSEEP.js",
       "line": 1408
     },
     "OBSERVATIONAL_MEMORY_DEFAULTS": {
@@ -144,40 +148,44 @@
     },
     "Memory": {
       "types": "dist/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
-      "line": 22109
+      "implementation": "dist/chunk-GHFCSEEP.js",
+      "line": 23559
     },
     "MessageHistory": {
       "types": "dist/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js"
+      "implementation": "dist/chunk-GHFCSEEP.js"
+    },
+    "SUMMARIZE_THREAD_DEFAULTS": {
+      "types": "dist/index.d.ts",
+      "implementation": "dist/chunk-GHFCSEEP.js"
     },
     "SemanticRecall": {
       "types": "dist/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js"
+      "implementation": "dist/chunk-GHFCSEEP.js"
     },
     "WorkingMemory": {
       "types": "dist/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js"
+      "implementation": "dist/chunk-GHFCSEEP.js"
     },
     "deepMergeWorkingMemory": {
       "types": "dist/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
-      "line": 21748
+      "implementation": "dist/chunk-GHFCSEEP.js",
+      "line": 23198
     },
     "extractWorkingMemoryContent": {
       "types": "dist/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
-      "line": 22064
+      "implementation": "dist/chunk-GHFCSEEP.js",
+      "line": 23514
     },
     "extractWorkingMemoryTags": {
       "types": "dist/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
-      "line": 22032
+      "implementation": "dist/chunk-GHFCSEEP.js",
+      "line": 23482
     },
     "removeWorkingMemoryTags": {
       "types": "dist/index.d.ts",
-      "implementation": "dist/chunk-5PG7DW2T.js",
-      "line": 22045
+      "implementation": "dist/chunk-GHFCSEEP.js",
+      "line": 23495
     },
     "WORKING_MEMORY_STATE_ID": {
       "types": "dist/index.d.ts",
@@ -197,7 +205,7 @@
     "processors": {
       "index": "dist/processors/index.js",
       "chunks": [
-        "chunk-5PG7DW2T.js",
+        "chunk-GHFCSEEP.js",
         "chunk-LSJJAJAF.js"
       ]
     }

package/dist/docs/references/docs-agents-supervisor-agents.md

@@ -428,4 +428,5 @@ Version overrides propagate automatically through delegation. See [Subagent vers
 - [Agent.generate() reference](https://mastra.ai/reference/agents/generate)
 - [Agent approval](https://mastra.ai/docs/agents/agent-approval)
 - [Memory in multi-agent systems](https://mastra.ai/docs/memory/overview)
-- [Concept: Multi-agent systems](https://mastra.ai/guides/concepts/multi-agent-systems)
+- [Concept: Multi-agent systems](https://mastra.ai/guides/concepts/multi-agent-systems)
+- 📹 [Mastra supervisor agents workshop](https://www.youtube.com/watch?v=FNb2fL9WhQg\&t=1872s)

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

@@ -714,4 +714,5 @@ In practical terms, OM replaces both working memory and message history, and has
 - [Memory Overview](https://mastra.ai/docs/memory/overview)
 - [Message History](https://mastra.ai/docs/memory/message-history)
 - [Memory Processors](https://mastra.ai/docs/memory/memory-processors)
-- [Mastra Code](https://code.mastra.ai/): A coding agent using Observational Memory
+- [Mastra Code](https://code.mastra.ai/): A coding agent using Observational Memory
+- 📹 [Mastra processors and Observational Memory workshop](https://www.youtube.com/watch?v=4Vpp7xQYvl0)

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

@@ -15,6 +15,8 @@ If the combined memory exceeds the model's context limit, [memory processors](ht
 
 Memory results will be stored in one or more of your configured [storage providers](https://mastra.ai/docs/storage/overview).
 
+> **📹 Watch:** Watch [Mastra memory concepts](https://www.youtube.com/watch?v=18iIHQtIPmc) for a conceptual overview of the memory layers agents can use.
+
 ## When to use memory
 
 Use memory when your agent needs to maintain multi-turn conversations that reference prior exchanges, recall user preferences or facts from earlier in a session, or build context over time within a conversation thread. Skip memory for single-turn requests where each interaction is independent.

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

@@ -4,7 +4,7 @@
 
 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)
+> **📹 Watch:** Watch [Mastra semantic recall](https://www.youtube.com/watch?v=UVZtK8cK8xQ\&pp=ygUVbWFzdHJhIHdvcmtpbmcgbWVtb3J5) to see how agents retrieve relevant messages from past conversations.
 
 ## How semantic recall works
 

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

@@ -10,6 +10,8 @@ This is useful for maintaining ongoing state that's always relevant and should a
 
 If you use [Observational Memory](https://mastra.ai/docs/memory/observational-memory), `observationalMemory.observation.manageWorkingMemory` lets OM update working memory for the agent.
 
+> **📹 Watch:** Watch [Mastra working memory](https://www.youtube.com/watch?v=UMy_JHLf1n8\&pp=ygUVbWFzdHJhIHdvcmtpbmcgbWVtb3J5) to see how agents keep persistent user context available across interactions.
+
 Working memory can persist at two different scopes:
 
 - **Resource-scoped** (default): Memory persists across all conversation threads for the same user
@@ -43,9 +45,7 @@ const agent = new Agent({
 
 ## 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)
+Working memory is a block of Markdown text that the agent is able to update over time to store continuously relevant information.
 
 ## Memory persistence scopes
 

package/dist/docs/references/reference-file-based-agents-memory.md

@@ -0,0 +1,58 @@
+> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
+
+# Memory
+
+A file-based agent gets [memory](https://mastra.ai/docs/memory/overview) from a `memory.ts` file that default-exports a [`Memory`](https://mastra.ai/reference/memory/memory-class) instance. Use this page for the file-based convention; use the memory docs for message history, semantic recall, storage, and processors.
+
+Without `memory.ts` or `config.memory`, the agent has no memory by default. Each `generate()` or `stream()` call starts without remembered conversation state unless you pass the prior context yourself.
+
+## Quickstart
+
+Create `memory.ts` next to the agent's `config.ts`:
+
+```typescript
+import { Memory } from '@mastra/memory'
+
+export default new Memory()
+```
+
+The exported instance becomes the agent's `memory`. If your app configures a storage provider on the main Mastra instance, memory data is stored there. See [storage](https://mastra.ai/docs/storage/overview) for more information.
+
+Use the same `resource` and `thread` values when calling the agent to continue a conversation:
+
+```typescript
+const response = await weatherAgent.generate('Remember that I prefer Celsius.', {
+  memory: {
+    resource: 'user-123',
+    thread: 'weather-chat',
+  },
+})
+```
+
+## Configure memory
+
+Pass options to `new Memory()` when the default behavior isn't enough.
+
+```typescript
+import { Memory } from '@mastra/memory'
+
+export default new Memory({
+  options: {
+    lastMessages: 20,
+    workingMemory: {
+      enabled: true,
+      scope: 'resource',
+    },
+  },
+})
+```
+
+Visit the [`Memory` reference](https://mastra.ai/reference/memory/memory-class) for constructor options. Use these pages for related memory features:
+
+- [Storage](https://mastra.ai/docs/storage/overview): configure persistence for memory data.
+- [Semantic recall](https://mastra.ai/docs/memory/semantic-recall): retrieve relevant past messages by semantic meaning.
+- [Memory processors](https://mastra.ai/docs/memory/memory-processors): filter, trim, or transform messages before memory adds them to model context.
+
+## Precedence with config
+
+`config.memory` wins over `memory.ts`. If neither is present, the assembled file-based agent has no memory. See [`config.ts` precedence](https://mastra.ai/reference/file-based-agents/config) for the full merge table.

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

@@ -37,7 +37,7 @@ export const agent = new Agent({
 
 **options** (`MemoryConfig`): Memory configuration options.
 
-**options.lastMessages** (`number | false`): Number of most recent messages to include in context. Set to false to disable loading conversation history into context. Use Number.MAX\_SAFE\_INTEGER to retrieve all messages with no limit. To prevent saving new messages, use the readOnly option instead.
+**options.lastMessages** (`number | false`): Number of most recent messages to include in context. Set to false to disable the message history feature entirely (messages are not loaded into context or saved). Use Number.MAX\_SAFE\_INTEGER to retrieve all messages with no limit. To load messages without saving new ones, use the readOnly option.
 
 **options.readOnly** (`boolean`): When true, prevents memory from saving new messages and provides working memory as read-only context (without the updateWorkingMemory tool). Useful for read-only operations like previews, internal routing agents, or sub agents that should reference but not modify memory.
 

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

@@ -0,0 +1,99 @@
+> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
+
+# summarizeConversation()
+
+The standalone `summarizeConversation()` function summarizes a conversation in one shot. It distills the messages you pass in with the same Observer plumbing that powers [Observational Memory](https://mastra.ai/reference/memory/observational-memory) — without Observational Memory attached to an agent, and without reading from or writing to storage.
+
+Nothing is written back to memory. The summary and extracted values are returned to you (and to each extractor's `onExtracted` hook), so you decide where they go — for example your own database.
+
+Use this when you already have the messages in hand and want explicit control over what gets summarized. To summarize a stored thread by ID instead, use [`Memory.summarizeThread()`](https://mastra.ai/reference/memory/summarizeThread), which loads the messages for you.
+
+## Usage example
+
+```typescript
+import { summarizeConversation } from '@mastra/memory'
+
+const result = await summarizeConversation({
+  model: 'openai/gpt-5-mini',
+  messages,
+  instructions: 'Summarize this voicemail call for the business owner.',
+})
+```
+
+## Parameters
+
+**model** (`string | LanguageModel | DynamicModel`): Model that runs the summarization, such as a router string like '\_\_GATEWAY\_OPENAI\_MODEL\_MINI\_\_'.
+
+**messages** (`MastraDBMessage[]`): The conversation to summarize. When empty, the function returns an empty result without calling the model.
+
+**instructions** (`string`): Extra guidance appended to the summarizer's system prompt, such as what to focus on or who the summary is for.
+
+**extract** (`Extractor[]`): Extractors to run over the conversation. Extractors with a Zod schema run as a follow-up structured output call; schema-less extractors are extracted inline. Each extractor's onExtracted hook fires with the extracted value.
+
+**threadId** (`string`): Thread the conversation belongs to. Defaults to the first threadId found on messages. Passed to extractor contexts.
+
+**resourceId** (`string`): Resource (user) the conversation belongs to. Defaults to the first resourceId found on messages. Passed to extractor contexts.
+
+**memory** (`Memory`): Memory instance forwarded to extractor contexts. Set automatically when called through Memory.summarizeThread().
+
+**mastra** (`Mastra`): Mastra instance used to resolve custom gateway models. Set automatically when called through Memory.summarizeThread().
+
+**requestContext** (`RequestContext`): Request context forwarded to the summarizer model and extractor hooks.
+
+**abortSignal** (`AbortSignal`): Signal to cancel the summarization call.
+
+## Returns
+
+**summary** (`string`): The distilled observations produced from the conversation, in dense bullet form.
+
+**extracted** (`Record<string, unknown>`): Values produced by extract extractors, keyed by extractor slug.
+
+**extractionFailures** (`{ slug: string; error: string }[]`): Extractors that failed to produce a valid value, with the reason. Only present when at least one extractor failed.
+
+**usage** (`{ inputTokens?: number; outputTokens?: number; totalTokens?: number }`): Token usage of the summarization call.
+
+## Extended usage example
+
+The following example summarizes an in-flight voice session from messages the application already holds, and extracts a structured record:
+
+```typescript
+import { summarizeConversation, Extractor } from '@mastra/memory'
+import type { MastraDBMessage } from '@mastra/core/agent'
+import { z } from 'zod'
+import { sessionRecords } from './db'
+
+const sessionSummary = new Extractor({
+  name: 'session-summary',
+  instructions: 'Return a concise summary of the session.',
+  schema: z.object({
+    summary: z.string(),
+    sentiment: z.enum(['positive', 'neutral', 'negative']),
+    followUps: z.array(z.string()),
+  }),
+  metadataKeyPath: false, // don't persist into memory metadata — the hook owns storage
+  onExtracted: async ({ current, threadId }) => {
+    await sessionRecords.upsert({ sessionId: threadId, record: current })
+  },
+})
+
+export async function onSessionEnd(messages: MastraDBMessage[]) {
+  const { summary, extracted, extractionFailures } = await summarizeConversation({
+    model: 'openai/gpt-5-mini',
+    messages,
+    instructions: 'Summarize this support session for the account manager.',
+    extract: [sessionSummary],
+  })
+
+  if (extractionFailures?.length) {
+    console.warn('Some extractors failed', extractionFailures)
+  }
+
+  return { summary, extracted }
+}
+```
+
+### Related
+
+- [.summarizeThread()](https://mastra.ai/reference/memory/summarizeThread)
+- [Memory Class Reference](https://mastra.ai/reference/memory/memory-class)
+- [Observational Memory](https://mastra.ai/reference/memory/observational-memory)

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

@@ -0,0 +1,93 @@
+> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
+
+# Memory.summarizeThread()
+
+The `.summarizeThread()` method summarizes a thread's conversation in one shot. It loads the thread's messages from storage and distills them with the same Observer plumbing that powers [Observational Memory](https://mastra.ai/reference/memory/observational-memory) — as a standalone call, without Observational Memory attached to an agent.
+
+Messages load page-by-page starting from the newest, bounded by `lastMessages` and `maxInputTokens`, so summarizing a long thread doesn't read its entire history from storage.
+
+Nothing is written back to memory. The summary and extracted values are returned to you (and to each extractor's `onExtracted` hook), so you decide where they go — for example your own database.
+
+Use this when a session ends and you want a summary or structured extraction of the whole conversation, such as a voice call at hang-up. To summarize messages you already have in hand (without loading them from a thread), use the standalone [`summarizeConversation()`](https://mastra.ai/reference/memory/summarizeConversation) function instead — it takes the same options with `messages` in place of `threadId`.
+
+## Usage example
+
+```typescript
+const result = await memory.summarizeThread({
+  model: 'openai/gpt-5-mini',
+  threadId: 'thread-123',
+  instructions: 'Summarize this voicemail call for the business owner.',
+})
+```
+
+## Parameters
+
+**threadId** (`string`): The unique identifier of the thread to summarize.
+
+**model** (`string | LanguageModel | DynamicModel`): Model that runs the summarization, such as a router string like '\_\_GATEWAY\_OPENAI\_MODEL\_MINI\_\_'.
+
+**resourceId** (`string`): ID of the resource that owns the thread. If provided, validates thread ownership. Also passed to extractor contexts.
+
+**lastMessages** (`number`): Only summarize the last N messages of the thread. By default the whole thread is loaded, bounded by maxInputTokens.
+
+**maxInputTokens** (`number`): Stop loading older messages once the collected messages exceed this estimated token count. The newest message is always included. (Default: `1000000`)
+
+**instructions** (`string`): Extra guidance appended to the summarizer's system prompt, such as what to focus on or who the summary is for.
+
+**extract** (`Extractor[]`): Extractors to run over the conversation. Extractors with a Zod schema run as a follow-up structured output call; schema-less extractors are extracted inline. Each extractor's onExtracted hook fires with the extracted value.
+
+**requestContext** (`RequestContext`): Request context forwarded to the summarizer model and extractor hooks.
+
+**abortSignal** (`AbortSignal`): Signal to cancel the summarization call.
+
+## Returns
+
+**summary** (`string`): The distilled observations produced from the conversation, in dense bullet form.
+
+**extracted** (`Record<string, unknown>`): Values produced by extract extractors, keyed by extractor slug.
+
+**extractionFailures** (`{ slug: string; error: string }[]`): Extractors that failed to produce a valid value, with the reason. Only present when at least one extractor failed.
+
+**usage** (`{ inputTokens?: number; outputTokens?: number; totalTokens?: number }`): Token usage of the summarization call.
+
+## Extended usage example
+
+The following example summarizes a finished voice call and stores a structured record in the application's own database:
+
+```typescript
+import { Extractor } from '@mastra/memory'
+import { z } from 'zod'
+import { memory } from './mastra/memory'
+import { callRecords } from './db'
+
+const callSummary = new Extractor({
+  name: 'call-summary',
+  instructions: 'Return a concise summary of the call.',
+  schema: z.object({
+    summary: z.string(),
+    sentiment: z.enum(['positive', 'neutral', 'negative']),
+    requestedServices: z.array(z.string()),
+  }),
+  metadataKeyPath: false, // don't persist into memory metadata — the hook owns storage
+  onExtracted: async ({ current, threadId, resourceId }) => {
+    await callRecords.upsert({ callId: threadId, callerId: resourceId, record: current })
+  },
+})
+
+export async function onCallEnd(threadId: string, resourceId: string) {
+  await memory.summarizeThread({
+    model: 'openai/gpt-5-mini',
+    threadId,
+    resourceId,
+    instructions: 'Summarize this voicemail call for the business owner.',
+    extract: [callSummary],
+  })
+}
+```
+
+### Related
+
+- [summarizeConversation()](https://mastra.ai/reference/memory/summarizeConversation)
+- [Memory Class Reference](https://mastra.ai/reference/memory/memory-class)
+- [Observational Memory](https://mastra.ai/reference/memory/observational-memory)
+- [.recall()](https://mastra.ai/reference/memory/recall)