@mastra/memory 1.1.0 → 1.2.0-alpha.0

package/dist/docs/{SOURCE_MAP.json → assets/SOURCE_MAP.json}

@@ -1,59 +1,59 @@
 {
-  "version": "1.1.0",
+  "version": "1.2.0-alpha.0",
   "package": "@mastra/memory",
   "exports": {
     "OBSERVATIONAL_MEMORY_DEFAULTS": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js"
+      "implementation": "dist/chunk-TYVPTNCP.js"
     },
     "OBSERVER_SYSTEM_PROMPT": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js"
+      "implementation": "dist/chunk-TYVPTNCP.js"
     },
     "ObservationalMemory": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js",
-      "line": 1206
+      "implementation": "dist/chunk-TYVPTNCP.js",
+      "line": 1283
     },
     "TokenCounter": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js",
-      "line": 925
+      "implementation": "dist/chunk-TYVPTNCP.js",
+      "line": 957
     },
     "buildObserverPrompt": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js",
-      "line": 644
+      "implementation": "dist/chunk-TYVPTNCP.js",
+      "line": 646
     },
     "buildObserverSystemPrompt": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js",
-      "line": 403
+      "implementation": "dist/chunk-TYVPTNCP.js",
+      "line": 405
     },
     "extractCurrentTask": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js",
-      "line": 725
+      "implementation": "dist/chunk-TYVPTNCP.js",
+      "line": 732
     },
     "formatMessagesForObserver": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js",
-      "line": 490
+      "implementation": "dist/chunk-TYVPTNCP.js",
+      "line": 492
     },
     "hasCurrentTaskSection": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js",
-      "line": 713
+      "implementation": "dist/chunk-TYVPTNCP.js",
+      "line": 720
     },
     "optimizeObservationsForContext": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js",
-      "line": 736
+      "implementation": "dist/chunk-TYVPTNCP.js",
+      "line": 743
     },
     "parseObserverOutput": {
       "types": "dist/processors/index.d.ts",
-      "implementation": "dist/chunk-6TXUWFIU.js",
-      "line": 670
+      "implementation": "dist/chunk-TYVPTNCP.js",
+      "line": 677
     },
     "extractWorkingMemoryContent": {
       "types": "dist/index.d.ts",
@@ -84,7 +84,7 @@
     "processors": {
       "index": "dist/processors/index.js",
       "chunks": [
-        "chunk-6TXUWFIU.js"
+        "chunk-TYVPTNCP.js"
       ]
     }
   }

package/dist/docs/{agents/03-agent-approval.md → references/docs-agents-agent-approval.md}

@@ -1,5 +1,3 @@
-> Learn how to require approvals, suspend tool execution, and automatically resume suspended tools while keeping humans in control of agent workflows.
-
 # Agent Approval
 
 Agents sometimes require the same [human-in-the-loop](https://mastra.ai/docs/workflows/human-in-the-loop) oversight used in workflows when calling tools that handle sensitive operations, like deleting resources or performing running long processes. With agent approval you can suspend a tool call and provide feedback to the user, or approve or decline a tool call based on targeted application conditions.
@@ -12,7 +10,7 @@ Tool call approval can be enabled at the agent level and apply to every tool the
 
 Agent approval uses a snapshot to capture the state of the request. Ensure you've enabled a storage provider in your main Mastra instance. If storage isn't enabled you'll see an error relating to snapshot not found.
 
-```typescript title="src/mastra/index.ts"
+```typescript
 import { Mastra } from "@mastra/core/mastra";
 import { LibSQLStore } from "@mastra/libsql";
 
@@ -117,13 +115,13 @@ if (output.finishReason === "suspended") {
 
 ### Stream vs Generate comparison
 
-| Aspect | `stream()` | `generate()` |
-|--------|-----------|--------------|
-| Response type | Streaming chunks | Complete response |
-| Approval detection | `tool-call-approval` chunk | `finishReason: 'suspended'` |
-| Approve method | `approveToolCall({ runId })` | `approveToolCallGenerate({ runId, toolCallId })` |
-| Decline method | `declineToolCall({ runId })` | `declineToolCallGenerate({ runId, toolCallId })` |
-| Result | Stream to iterate | Full output object |
+| Aspect             | `stream()`                   | `generate()`                                     |
+| ------------------ | ---------------------------- | ------------------------------------------------ |
+| Response type      | Streaming chunks             | Complete response                                |
+| Approval detection | `tool-call-approval` chunk   | `finishReason: 'suspended'`                      |
+| Approve method     | `approveToolCall({ runId })` | `approveToolCallGenerate({ runId, toolCallId })` |
+| Decline method     | `declineToolCall({ runId })` | `declineToolCallGenerate({ runId, toolCallId })` |
+| Result             | Stream to iterate            | Full output object                               |
 
 ## Tool-level approval
 
@@ -231,7 +229,6 @@ const handleResume = async () => {
   }
   process.stdout.write("\n");
 };
-
 ```
 
 ## Automatic tool resumption
@@ -270,8 +267,11 @@ const stream = await agent.stream("What's the weather?", {
 When `autoResumeSuspendedTools` is enabled:
 
 1. A tool suspends execution by calling `suspend()` with a payload (e.g., requesting more information)
+
 2. The suspension is persisted to memory along with the conversation
+
 3. When the user sends their next message on the same thread, the agent:
+
    - Detects the suspended tool from message history
    - Extracts `resumeData` from the user's message based on the tool's `resumeSchema`
    - Automatically resumes the tool with the extracted data
@@ -341,7 +341,7 @@ const handleResume = async () => {
 
 **Conversation flow:**
 
-```
+```text
 User: "What's the weather like?"
 Agent: "What city do you want to know the weather for?"
 
@@ -361,17 +361,17 @@ For automatic tool resumption to work:
 
 ### Manual vs automatic resumption
 
-| Approach | Use case |
-|----------|----------|
-| Manual (`resumeStream()`) | Programmatic control, webhooks, button clicks, external triggers |
+| Approach                               | Use case                                                                 |
+| -------------------------------------- | ------------------------------------------------------------------------ |
+| Manual (`resumeStream()`)              | Programmatic control, webhooks, button clicks, external triggers         |
 | Automatic (`autoResumeSuspendedTools`) | Conversational flows where users provide resume data in natural language |
 
 Both approaches work with the same tool definitions. Automatic resumption triggers only when suspended tools exist in the message history and the user sends a new message on the same thread.
 
 ## Related
 
-- [Using Tools](./using-tools)
-- [Agent Overview](./overview)
-- [Tools Overview](../mcp/overview)
-- [Agent Memory](./agent-memory)
+- [Using Tools](https://mastra.ai/docs/agents/using-tools)
+- [Agent Overview](https://mastra.ai/docs/agents/overview)
+- [Tools Overview](https://mastra.ai/docs/mcp/overview)
+- [Agent Memory](https://mastra.ai/docs/agents/agent-memory)
 - [Request Context](https://mastra.ai/docs/server/request-context)

package/dist/docs/references/docs-agents-agent-memory.md

@@ -0,0 +1,212 @@
+# Agent memory
+
+Agents use memory to maintain context across interactions. LLMs are stateless and don't retain information between calls, so agents need memory to track message history and recall relevant information.
+
+Mastra agents can be configured to store message history, with optional [working memory](https://mastra.ai/docs/memory/working-memory) to maintain recent context, [semantic recall](https://mastra.ai/docs/memory/semantic-recall) to retrieve past messages based on meaning, or [observational memory](https://mastra.ai/docs/memory/observational-memory) for automatic long-term memory that compresses conversations as they grow.
+
+## 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.
+
+## Setting up memory
+
+To enable memory in Mastra, install the `@mastra/memory` package along with a storage provider.
+
+**npm**:
+
+```bash
+npm install @mastra/memory@latest @mastra/libsql@latest
+```
+
+**pnpm**:
+
+```bash
+pnpm add @mastra/memory@latest @mastra/libsql@latest
+```
+
+**Yarn**:
+
+```bash
+yarn add @mastra/memory@latest @mastra/libsql@latest
+```
+
+**Bun**:
+
+```bash
+bun add @mastra/memory@latest @mastra/libsql@latest
+```
+
+## Storage providers
+
+Memory requires a storage provider to persist message history, including user messages and agent responses. For more details on available providers and how storage works in Mastra, see the [Storage](https://mastra.ai/docs/memory/storage) documentation.
+
+## Configuring memory
+
+1. Enable memory by creating a `Memory` instance and passing it to the agent’s `memory` option.
+
+   ```typescript
+   import { Agent } from "@mastra/core/agent";
+   import { Memory } from "@mastra/memory";
+
+   export const memoryAgent = new Agent({
+     id: 'memory-agent',
+     name: 'Memory Agent',
+     memory: new Memory({
+       options: {
+         lastMessages: 20,
+       },
+     }),
+   });
+   ```
+
+   > **Info:** Visit [Memory Class](https://mastra.ai/reference/memory/memory-class) for a full list of configuration options.
+
+2. Add a storage provider to your main Mastra instance to enable memory across all configured agents.
+
+   ```typescript
+   import { Mastra } from "@mastra/core";
+   import { LibSQLStore } from "@mastra/libsql";
+
+   export const mastra = new Mastra({
+     storage: new LibSQLStore({
+       id: 'mastra-storage',
+       url: ":memory:",
+     }),
+   });
+   ```
+
+   > **Info:** Visit [libSQL Storage](https://mastra.ai/reference/storage/libsql) for a full list of configuration options.
+
+Alternatively, add storage directly to an agent’s memory to keep data separate or use different providers per agent.
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+import { Memory } from "@mastra/memory";
+import { LibSQLStore } from "@mastra/libsql";
+
+export const memoryAgent = new Agent({
+  id: 'memory-agent',
+  name: 'Memory Agent',
+  memory: new Memory({
+    storage: new LibSQLStore({
+      id: 'mastra-storage',
+      url: ":memory:",
+    }),
+  }),
+});
+```
+
+> **Mastra Cloud Store limitation:** Agent-level storage is not supported when using [Mastra Cloud Store](https://mastra.ai/docs/mastra-cloud/deployment). If you use Mastra Cloud Store, configure storage on the Mastra instance instead. This limitation does not apply if you bring your own database.
+
+## Message history
+
+Include a `memory` object with both `resource` and `thread` to track message history during agent calls.
+
+- `resource`: A stable identifier for the user or entity.
+- `thread`: An ID that isolates a specific conversation or session.
+
+These fields tell the agent where to store and retrieve context, enabling persistent, thread-aware memory across a conversation.
+
+```typescript
+const response = await memoryAgent.generate(
+  "Remember my favorite color is blue.",
+  {
+    memory: {
+      resource: "user-123",
+      thread: "conversation-123",
+    },
+  },
+);
+```
+
+To recall information stored in memory, call the agent with the same `resource` and `thread` values used in the original conversation.
+
+```typescript
+const response = await memoryAgent.generate("What's my favorite color?", {
+  memory: {
+    resource: "user-123",
+    thread: "conversation-123",
+  },
+});
+```
+
+> **Warning:** Each thread has an owner (`resourceId`) that cannot be changed after creation. Avoid reusing the same thread ID for threads with different owners, as this will cause errors when querying.
+
+To learn more about memory see the [Memory](https://mastra.ai/docs/memory/overview) documentation.
+
+## Observational Memory
+
+For long-running conversations, raw message history grows until it fills the context window, degrading agent performance. [Observational Memory](https://mastra.ai/docs/memory/observational-memory) solves this by running background agents that compress old messages into dense observations, keeping the context window small while preserving long-term memory.
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+import { Memory } from "@mastra/memory";
+
+export const memoryAgent = new Agent({
+  id: 'memory-agent',
+  name: 'Memory Agent',
+  memory: new Memory({
+    options: {
+      observationalMemory: true,
+    },
+  }),
+});
+```
+
+Setting `observationalMemory: true` uses `google/gemini-2.5-flash` as the default model for the Observer and Reflector. To use a different model or customize thresholds, pass a config object:
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+import { Memory } from "@mastra/memory";
+
+export const memoryAgent = new Agent({
+  id: 'memory-agent',
+  name: 'Memory Agent',
+  memory: new Memory({
+    options: {
+      observationalMemory: {
+        model: "deepseek/deepseek-reasoner",
+        observation: {
+          messageTokens: 20_000,
+        },
+      },
+    },
+  }),
+});
+```
+
+> **Info:** See [Observational Memory](https://mastra.ai/docs/memory/observational-memory) for details on how observations and reflections work, and [the reference](https://mastra.ai/reference/memory/observational-memory) for all configuration options.
+
+## Using `RequestContext`
+
+Use [RequestContext](https://mastra.ai/docs/server/request-context) to access request-specific values. This lets you conditionally select different memory or storage configurations based on the context of the request.
+
+```typescript
+export type UserTier = {
+  "user-tier": "enterprise" | "pro";
+};
+
+const premiumMemory = new Memory();
+
+const standardMemory = new Memory();
+
+export const memoryAgent = new Agent({
+  id: 'memory-agent',
+  name: 'Memory Agent',
+  memory: ({ requestContext }) => {
+    const userTier = requestContext.get("user-tier") as UserTier["user-tier"];
+
+    return userTier === "enterprise" ? premiumMemory : standardMemory;
+  },
+});
+```
+
+> **Info:** Visit [Request Context](https://mastra.ai/docs/server/request-context) for more information.
+
+## Related
+
+- [Observational Memory](https://mastra.ai/docs/memory/observational-memory)
+- [Working Memory](https://mastra.ai/docs/memory/working-memory)
+- [Semantic Recall](https://mastra.ai/docs/memory/semantic-recall)
+- [Storage](https://mastra.ai/docs/memory/storage)
+- [Request Context](https://mastra.ai/docs/server/request-context)

package/dist/docs/{agents/04-network-approval.md → references/docs-agents-network-approval.md}

@@ -1,14 +1,12 @@
-> Learn how to require approvals, suspend execution, and resume suspended networks while keeping humans in control of agent network workflows.
-
 # Network Approval
 
-Agent networks can require the same [human-in-the-loop](https://mastra.ai/docs/workflows/human-in-the-loop) oversight used in individual agents and workflows. When a tool, sub-agent, or workflow within a network requires approval or suspends execution, the network pauses and emits events that allow your application to collect user input before resuming.
+Agent networks can require the same [human-in-the-loop](https://mastra.ai/docs/workflows/human-in-the-loop) oversight used in individual agents and workflows. When a tool, subagent, or workflow within a network requires approval or suspends execution, the network pauses and emits events that allow your application to collect user input before resuming.
 
 ## Storage
 
 Network approval uses snapshots to capture execution state. Ensure you've enabled a storage provider in your Mastra instance. If storage isn't enabled you'll see an error relating to snapshot not found.
 
-```typescript title="src/mastra/index.ts"
+```typescript
 import { Mastra } from "@mastra/core/mastra";
 import { LibSQLStore } from "@mastra/libsql";
 
@@ -37,7 +35,7 @@ let runId: string;
 for await (const chunk of stream) {
   runId = stream.runId;
   // if the requirApproval is in a tool inside a subAgent or the subAgent has requireToolApproval set to true
-  if (chunk.type === "agent-execution-approval") { 
+  if (chunk.type === "agent-execution-approval") {
     console.log("Tool requires approval:", chunk.payload);
   }
 
@@ -199,8 +197,11 @@ const stream = await routingAgent.network("Process this request", {
 When `autoResumeSuspendedTools` is enabled:
 
 1. A primitive suspends execution by calling `suspend()` with a payload
+
 2. The suspension is persisted to memory along with the conversation
+
 3. When the user sends their next message on the same thread, the network:
+
    - Detects the suspended primitive from message history
    - Extracts `resumeData` from the user's message based on the tool's `resumeSchema`
    - Automatically resumes the primitive with the extracted data
@@ -241,7 +242,7 @@ for await (const chunk of resumedStream) {
 
 **Conversation flow:**
 
-```
+```text
 User: "Delete the old records"
 Agent: "Please confirm: delete old records"
 
@@ -259,16 +260,16 @@ For automatic tool resumption to work:
 
 ### Manual vs automatic resumption
 
-| Approach | Use case |
-|----------|----------|
-| Manual (`resumeNetwork()`) | Programmatic control, webhooks, button clicks, external triggers |
+| Approach                               | Use case                                                                 |
+| -------------------------------------- | ------------------------------------------------------------------------ |
+| Manual (`resumeNetwork()`)             | Programmatic control, webhooks, button clicks, external triggers         |
 | Automatic (`autoResumeSuspendedTools`) | Conversational flows where users provide resume data in natural language |
 
 Both approaches work with the same tool definitions. Automatic resumption triggers only when suspended tools exist in the message history and the user sends a new message on the same thread.
 
 ## Related
 
-- [Agent Networks](./networks)
-- [Agent Approval](./agent-approval)
+- [Agent Networks](https://mastra.ai/docs/agents/networks)
+- [Agent Approval](https://mastra.ai/docs/agents/agent-approval)
 - [Human-in-the-Loop](https://mastra.ai/docs/workflows/human-in-the-loop)
-- [Agent Memory](./agent-memory)
+- [Agent Memory](https://mastra.ai/docs/agents/agent-memory)

package/dist/docs/{agents/02-networks.md → references/docs-agents-networks.md}

@@ -1,8 +1,6 @@
-> Learn how to coordinate multiple agents, workflows, and tools using agent networks for complex, non-deterministic task execution.
-
 # Agent Networks
 
-Agent networks in Mastra coordinate multiple agents, workflows, and tools to handle tasks that aren't clearly defined upfront but can be inferred from the user's message or context. A top-level **routing agent** (a Mastra agent with other agents, workflows, and tools configured) uses an LLM to interpret the request and decide which primitives (sub-agents, workflows, or tools) to call, in what order, and with what data.
+Agent networks in Mastra coordinate multiple agents, workflows, and tools to handle tasks that aren't clearly defined upfront but can be inferred from the user's message or context. A top-level **routing agent** (a Mastra agent with other agents, workflows, and tools configured) uses an LLM to interpret the request and decide which primitives (subagents, workflows, or tools) to call, in what order, and with what data.
 
 ## When to use networks
 
@@ -18,9 +16,9 @@ Mastra agent networks operate using these principles:
 
 ## Creating an agent network
 
-An agent network is built around a top-level routing agent that delegates tasks to agents, workflows, and tools defined in its configuration. Memory is configured on the routing agent using the `memory` option, and `instructions` define the agent's routing behavior.
+An agent network is built around a top-level routing agent that delegates tasks to subagents, workflows, and tools defined in its configuration. Memory is configured on the routing agent using the `memory` option, and `instructions` define the agent's routing behavior.
 
-```typescript {22-23,26,29} title="src/mastra/agents/routing-agent.ts"
+```typescript
 import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
 import { LibSQLStore } from "@mastra/libsql";
@@ -66,9 +64,9 @@ When configuring a Mastra agent network, each primitive (agent, workflow, or too
 
 #### Agent descriptions
 
-Each agent in a network should include a clear `description` that explains what the agent does.
+Each subagent in a network should include a clear `description` that explains what the agent does.
 
-```typescript title="src/mastra/agents/research-agent.ts"
+```typescript
 export const researchAgent = new Agent({
   id: "research-agent",
   name: "Research Agent",
@@ -78,7 +76,7 @@ export const researchAgent = new Agent({
 });
 ```
 
-```typescript title="src/mastra/agents/writing-agent.ts"
+```typescript
 export const writingAgent = new Agent({
   id: "writing-agent",
   name: "Writing Agent",
@@ -92,7 +90,7 @@ export const writingAgent = new Agent({
 
 Workflows in a network should include a `description` to explain their purpose, along with `inputSchema` and `outputSchema` to describe the expected data.
 
-```typescript title="src/mastra/workflows/city-workflow.ts"
+```typescript
 export const cityWorkflow = createWorkflow({
   id: "city-workflow",
   description: `This workflow handles city-specific research tasks.
@@ -112,7 +110,7 @@ export const cityWorkflow = createWorkflow({
 
 Tools in a network should include a `description` to explain their purpose, along with `inputSchema` and `outputSchema` to describe the expected data.
 
-```typescript title="src/mastra/tools/weather-tool.ts"
+```typescript
 export const weatherTool = createTool({
   id: "weather-tool",
   description: ` Retrieves current weather information using the wttr.in API.
@@ -286,7 +284,7 @@ const final = await stream.object;
 
 ## Related
 
-- [Agent Memory](./agent-memory)
-- [Workflows Overview](../workflows/overview)
+- [Agent Memory](https://mastra.ai/docs/agents/agent-memory)
+- [Workflows Overview](https://mastra.ai/docs/workflows/overview)
 - [Request Context](https://mastra.ai/docs/server/request-context)
 - [Supervisor example](https://github.com/mastra-ai/mastra/tree/main/examples/supervisor-agent)

package/dist/docs/{memory/06-memory-processors.md → references/docs-memory-memory-processors.md}

@@ -1,5 +1,3 @@
-> Learn how to use memory processors in Mastra to filter, trim, and transform messages before they
-
 # Memory Processors
 
 Memory processors transform and filter messages as they pass through an agent with memory enabled. They manage context window limits, remove unnecessary content, and optimize the information sent to the language model.
@@ -200,7 +198,7 @@ Understanding the execution order is important when combining guardrails with me
 
 ### Input Processors
 
-```
+```text
 [Memory Processors] → [Your inputProcessors]
 ```
 
@@ -211,7 +209,7 @@ This means memory loads message history before your processors can validate or f
 
 ### Output Processors
 
-```
+```text
 [Your outputProcessors] → [Memory Processors]
 ```
 
@@ -302,10 +300,10 @@ const agent = new Agent({
 
 ### Summary
 
-| Guardrail Type | When it runs | If it aborts |
-| -------------- | ------------ | ------------ |
-| Input | After memory loads history | LLM not called, nothing saved |
-| Output | Before memory saves | Nothing saved to storage |
+| Guardrail Type | When it runs               | If it aborts                  |
+| -------------- | -------------------------- | ----------------------------- |
+| Input          | After memory loads history | LLM not called, nothing saved |
+| Output         | Before memory saves        | Nothing saved to storage      |
 
 Both scenarios are safe - guardrails prevent inappropriate content from being persisted to memory