@mastra/core 1.7.0 → 1.8.0

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

@@ -0,0 +1,209 @@
+# 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/references/docs-agents-guardrails.md

@@ -0,0 +1,374 @@
+# Guardrails
+
+Agents use processors to apply guardrails to inputs and outputs. They run before or after each interaction, giving you a way to review, transform, or block information as it passes between the user and the agent.
+
+Processors can be configured as:
+
+- **`inputProcessors`**: Applied before messages reach the language model.
+- **`outputProcessors`**: Applied to responses before they're returned to users.
+
+Some processors are _hybrid_, meaning they can be used with either `inputProcessors` or `outputProcessors`, depending on where the logic should be applied.
+
+## When to use processors
+
+Use processors for content moderation, prompt injection prevention, response sanitization, message transformation, and other security-related controls. Mastra provides several built-in input and output processors for common use cases.
+
+## Adding processors to an agent
+
+Import and instantiate the relevant processor class, and pass it to your agent’s configuration using either the `inputProcessors` or `outputProcessors` option:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { ModerationProcessor } from '@mastra/core/processors'
+
+export const moderatedAgent = new Agent({
+  id: 'moderated-agent',
+  name: 'Moderated Agent',
+  instructions: 'You are a helpful assistant',
+  model: 'openai/gpt-5.1',
+  inputProcessors: [
+    new ModerationProcessor({
+      model: 'openrouter/openai/gpt-oss-safeguard-20b',
+      categories: ['hate', 'harassment', 'violence'],
+      threshold: 0.7,
+      strategy: 'block',
+      instructions: 'Detect and flag inappropriate content in user messages',
+    }),
+  ],
+})
+```
+
+## Input processors
+
+Input processors are applied before user messages reach the language model. They are useful for normalization, validation, content moderation, prompt injection detection, and security checks.
+
+### Normalizing user messages
+
+The `UnicodeNormalizer` is an input processor that cleans and normalizes user input by unifying Unicode characters, standardizing whitespace, and removing problematic symbols, allowing the LLM to better understand user messages.
+
+```typescript
+import { UnicodeNormalizer } from '@mastra/core/processors'
+
+export const normalizedAgent = new Agent({
+  id: 'normalized-agent',
+  name: 'Normalized Agent',
+  inputProcessors: [
+    new UnicodeNormalizer({
+      stripControlChars: true,
+      collapseWhitespace: true,
+    }),
+  ],
+})
+```
+
+> **Info:** Visit [UnicodeNormalizer](https://mastra.ai/reference/processors/unicode-normalizer) for a full list of configuration options.
+
+### Preventing prompt injection
+
+The `PromptInjectionDetector` is an input processor that scans user messages for prompt injection, jailbreak attempts, and system override patterns. It uses an LLM to classify risky input and can block or rewrite it before it reaches the model.
+
+```typescript
+import { PromptInjectionDetector } from '@mastra/core/processors'
+
+export const secureAgent = new Agent({
+  id: 'secure-agent',
+  name: 'Secure Agent',
+  inputProcessors: [
+    new PromptInjectionDetector({
+      model: 'openrouter/openai/gpt-oss-safeguard-20b',
+      threshold: 0.8,
+      strategy: 'rewrite',
+      detectionTypes: ['injection', 'jailbreak', 'system-override'],
+    }),
+  ],
+})
+```
+
+> **Info:** Visit [PromptInjectionDetector](https://mastra.ai/reference/processors/prompt-injection-detector) for a full list of configuration options.
+
+### Detecting and translating language
+
+The `LanguageDetector` is an input processor that detects and translates user messages into a target language, enabling multilingual support while maintaining consistent interaction. It uses an LLM to identify the language and perform the translation.
+
+```typescript
+import { LanguageDetector } from '@mastra/core/processors'
+
+export const multilingualAgent = new Agent({
+  id: 'multilingual-agent',
+  name: 'Multilingual Agent',
+  inputProcessors: [
+    new LanguageDetector({
+      model: 'openrouter/openai/gpt-oss-safeguard-20b',
+      targetLanguages: ['English', 'en'],
+      strategy: 'translate',
+      threshold: 0.8,
+    }),
+  ],
+})
+```
+
+> **Info:** Visit [LanguageDetector](https://mastra.ai/reference/processors/language-detector) for a full list of configuration options.
+
+## Output processors
+
+Output processors are applied after the language model generates a response, but before it is returned to the user. They are useful for response optimization, moderation, transformation, and applying safety controls.
+
+### Batching streamed output
+
+The `BatchPartsProcessor` is an output processor that combines multiple stream parts before emitting them to the client. This reduces network overhead and improves the user experience by consolidating small chunks into larger batches.
+
+```typescript
+import { BatchPartsProcessor } from '@mastra/core/processors'
+
+export const batchedAgent = new Agent({
+  id: 'batched-agent',
+  name: 'Batched Agent',
+  outputProcessors: [
+    new BatchPartsProcessor({
+      batchSize: 5,
+      maxWaitTime: 100,
+      emitOnNonText: true,
+    }),
+  ],
+})
+```
+
+> **Info:** Visit [BatchPartsProcessor](https://mastra.ai/reference/processors/batch-parts-processor) for a full list of configuration options.
+
+### Limiting token usage
+
+The `TokenLimiterProcessor` is an output processor that limits the number of tokens in model responses. It helps manage cost and performance by truncating or blocking messages when the limit is exceeded.
+
+```typescript
+import { TokenLimiterProcessor } from '@mastra/core/processors'
+
+export const limitedAgent = new Agent({
+  id: 'limited-agent',
+  name: 'Limited Agent',
+  outputProcessors: [
+    new TokenLimiterProcessor({
+      limit: 1000,
+      strategy: 'truncate',
+      countMode: 'cumulative',
+    }),
+  ],
+})
+```
+
+> **Info:** Visit [TokenLimiterProcessor](https://mastra.ai/reference/processors/token-limiter-processor) for a full list of configuration options.
+
+### Scrubbing system prompts
+
+The `SystemPromptScrubber` is an output processor that detects and redacts system prompts or other internal instructions from model responses. It helps prevent unintended disclosure of prompt content or configuration details that could introduce security risks. It uses an LLM to identify and redact sensitive content based on configured detection types.
+
+```typescript
+import { SystemPromptScrubber } from '@mastra/core/processors'
+
+const scrubbedAgent = new Agent({
+  id: 'scrubbed-agent',
+  name: 'Scrubbed Agent',
+  outputProcessors: [
+    new SystemPromptScrubber({
+      model: 'openrouter/openai/gpt-oss-safeguard-20b',
+      strategy: 'redact',
+      customPatterns: ['system prompt', 'internal instructions'],
+      includeDetections: true,
+      instructions:
+        'Detect and redact system prompts, internal instructions, and security-sensitive content',
+      redactionMethod: 'placeholder',
+      placeholderText: '[REDACTED]',
+    }),
+  ],
+})
+```
+
+> **Info:** Visit [SystemPromptScrubber](https://mastra.ai/reference/processors/system-prompt-scrubber) for a full list of configuration options.
+
+> **Note:** When streaming responses over HTTP, Mastra redacts sensitive request data (system prompts, tool definitions, API keys) from stream chunks at the server level by default. See [Stream data redaction](https://mastra.ai/docs/server/mastra-server) for details.
+
+## Hybrid processors
+
+Hybrid processors can be applied either before messages are sent to the language model or before responses are returned to the user. They are useful for tasks like content moderation and PII redaction.
+
+### Moderating input and output
+
+The `ModerationProcessor` is a hybrid processor that detects inappropriate or harmful content across categories like hate, harassment, and violence. It can be used to moderate either user input or model output, depending on where it's applied. It uses an LLM to classify the message and can block or rewrite it based on your configuration.
+
+```typescript
+import { ModerationProcessor } from '@mastra/core/processors'
+
+export const moderatedAgent = new Agent({
+  id: 'moderated-agent',
+  name: 'Moderated Agent',
+  inputProcessors: [
+    new ModerationProcessor({
+      model: 'openrouter/openai/gpt-oss-safeguard-20b',
+      threshold: 0.7,
+      strategy: 'block',
+      categories: ['hate', 'harassment', 'violence'],
+    }),
+  ],
+  outputProcessors: [new ModerationProcessor()],
+})
+```
+
+> **Info:** Visit [ModerationProcessor](https://mastra.ai/reference/processors/moderation-processor) for a full list of configuration options.
+
+### Detecting and redacting PII
+
+The `PIIDetector` is a hybrid processor that detects and removes personally identifiable information such as emails, phone numbers, and credit cards. It can redact either user input or model output, depending on where it's applied. It uses an LLM to identify sensitive content based on configured detection types.
+
+```typescript
+import { PIIDetector } from '@mastra/core/processors'
+
+export const privateAgent = new Agent({
+  id: 'private-agent',
+  name: 'Private Agent',
+  inputProcessors: [
+    new PIIDetector({
+      model: 'openrouter/openai/gpt-oss-safeguard-20b',
+      threshold: 0.6,
+      strategy: 'redact',
+      redactionMethod: 'mask',
+      detectionTypes: ['email', 'phone', 'credit-card'],
+      instructions: 'Detect and mask personally identifiable information.',
+    }),
+  ],
+  outputProcessors: [new PIIDetector()],
+})
+```
+
+> **Info:** Visit [PIIDetector](https://mastra.ai/reference/processors/pii-detector) for a full list of configuration options.
+
+## Applying multiple processors
+
+You can apply multiple processors by listing them in the `inputProcessors` or `outputProcessors` array. They run in sequence, with each processor receiving the output of the one before it.
+
+A typical order might be:
+
+1. **Normalization**: Standardize input format (`UnicodeNormalizer`).
+2. **Security checks**: Detect threats or sensitive content (`PromptInjectionDetector`, `PIIDetector`).
+3. **Filtering**: Block or transform messages (`ModerationProcessor`).
+
+The order affects behavior, so arrange processors to suit your goals.
+
+```typescript
+import {
+  UnicodeNormalizer,
+  ModerationProcessor,
+  PromptInjectionDetector,
+  PIIDetector,
+} from '@mastra/core/processors'
+
+export const testAgent = new Agent({
+  id: 'test-agent',
+  name: 'Test Agent',
+  inputProcessors: [
+    new UnicodeNormalizer(),
+    new PromptInjectionDetector(),
+    new PIIDetector(),
+    new ModerationProcessor(),
+  ],
+})
+```
+
+## Processor strategies
+
+Many of the built-in processors support a `strategy` parameter that controls how they handle flagged input or output. Supported values may include: `block`, `warn`, `detect`, or `redact`.
+
+Most strategies allow the request to continue without interruption. When `block` is used, the processor calls its internal `abort()` function, which immediately stops the request and prevents any subsequent processors from running.
+
+```typescript
+import { PIIDetector } from '@mastra/core/processors'
+
+export const privateAgent = new Agent({
+  id: 'private-agent',
+  name: 'Private Agent',
+  inputProcessors: [
+    new PIIDetector({
+      strategy: 'block',
+    }),
+  ],
+})
+```
+
+### Handling blocked requests
+
+When a processor blocks a request, the agent will still return successfully without throwing an error. To handle blocked requests, check for `tripwire` in the response.
+
+For example, if an agent uses the `PIIDetector` with `strategy: "block"` and the request includes a credit card number, it will be blocked and the response will include tripwire information.
+
+#### `.generate()` example
+
+```typescript
+const result = await agent.generate('Is this credit card number valid?: 4543 1374 5089 4332')
+
+if (result.tripwire) {
+  console.error('Blocked:', result.tripwire.reason)
+  console.error('Processor:', result.tripwire.processorId)
+  // Optional: check if retry was requested
+  console.error('Retry requested:', result.tripwire.retry)
+  // Optional: access additional metadata
+  console.error('Metadata:', result.tripwire.metadata)
+}
+```
+
+#### `.stream()` example
+
+```typescript
+const stream = await agent.stream('Is this credit card number valid?: 4543 1374 5089 4332')
+
+for await (const chunk of stream.fullStream) {
+  if (chunk.type === 'tripwire') {
+    console.error('Blocked:', chunk.payload.reason)
+    console.error('Processor:', chunk.payload.processorId)
+  }
+}
+```
+
+In this case, the `reason` indicates that a credit card number was detected:
+
+```text
+PII detected. Types: credit-card
+```
+
+### Requesting retries
+
+Processors can request that the LLM retry its response with feedback. This is useful for implementing quality checks:
+
+```typescript
+export class QualityChecker implements Processor {
+  id = 'quality-checker'
+
+  async processOutputStep({ text, abort, retryCount }) {
+    const score = await evaluateQuality(text)
+
+    if (score < 0.7 && retryCount < 3) {
+      // Request retry with feedback for the LLM
+      abort('Response quality too low. Please be more specific.', {
+        retry: true,
+        metadata: { score },
+      })
+    }
+
+    return []
+  }
+}
+```
+
+The `abort()` function accepts an optional second parameter with:
+
+- `retry: true` - Request the LLM retry the step
+- `metadata: unknown` - Attach additional data for debugging/logging
+
+Use `retryCount` to track retry attempts and prevent infinite loops.
+
+## Custom processors
+
+If the built-in processors don’t cover your needs, you can create your own by extending the `Processor` class.
+
+Available examples:
+
+- [Message Length Limiter](https://github.com/mastra-ai/mastra/tree/main/examples/processors-message-length-limiter)
+- [Response Length Limiter](https://github.com/mastra-ai/mastra/tree/main/examples/processors-response-length-limiter)
+- [Response Validator](https://github.com/mastra-ai/mastra/tree/main/examples/processors-response-validator)