@mastra/mcp-docs-server 1.2.3-alpha.9 → 1.2.3

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

@@ -163,6 +163,120 @@ OM uses fast local token estimation for this thresholding work. Text is estimate
 
 The Observer can also see attachments in the history it reviews. OM keeps readable placeholders like `[Image #1: reference-board.png]` or `[File #1: floorplan.pdf]` in the transcript for readability, and forwards the actual attachment parts alongside the text. Image-like `file` parts are upgraded to image inputs for the Observer when possible, while non-image attachments are forwarded as file parts with normalized token counting. This applies to both normal thread observation and batched resource-scope observation.
 
+### Extractors
+
+Use extractors when you want OM to persist specific values alongside observations. Built-in values such as **current task**, **suggested response**, and **thread title** use the same extraction pipeline as custom values.
+
+The following example extracts a compact user profile from observations:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { Extractor, Memory } from '@mastra/memory'
+import { z } from 'zod'
+
+const memory = new Memory({
+  options: {
+    observationalMemory: {
+      model: 'openai/gpt-5-mini',
+      observation: {
+        extract: [
+          new Extractor({
+            name: 'User profile',
+            instructions: 'Extract stable user profile facts that should be remembered.',
+            schema: z.object({
+              preferredName: z.string().optional(),
+              timezone: z.string().optional(),
+              tools: z.array(z.string()).optional(),
+            }),
+          }),
+        ],
+      },
+    },
+  },
+})
+
+export const agent = new Agent({
+  name: 'assistant',
+  instructions: 'You are a helpful assistant.',
+  model: 'openai/gpt-5-mini',
+  memory,
+})
+```
+
+Adding a `schema` makes the extractor run as a follow-up structured output request. Schema-less extractors are inline string extractors emitted directly in the Observer or Reflector response.
+
+```typescript
+new Extractor({
+  name: 'Mood',
+  instructions: 'Extract the user mood as a short phrase.',
+})
+```
+
+By default, OM shows the last extracted value to the extractor on later runs. Set `includePreviousExtraction: false` when the Observer should not see the previous value.
+
+```typescript
+new Extractor({
+  name: 'Latest blocker',
+  instructions: 'Extract any blockers the agent is running into.',
+  includePreviousExtraction: false,
+})
+```
+
+Use dynamic `instructions` or `schema` functions when an extractor needs runtime context, such as the active memory instance or request context:
+
+```typescript
+new Extractor({
+  name: 'Workspace summary',
+  instructions: ({ memory }) =>
+    memory ? 'Extract workspace facts for this memory instance.' : 'Extract workspace facts.',
+})
+```
+
+### Working memory updates
+
+Use `observationalMemory.observation.manageWorkingMemory` to let the Observer manage working memory automatically. The main agent no longer needs to call the working memory tool while it handles the user request, so working memory updates don't depend on the agent remembering to make them.
+
+This also keeps working memory prompt-cache friendly. Working memory normally lives in the system prompt, so updates can invalidate the prompt cache. OM-managed working memory defaults `workingMemory.useStateSignals` to `true`, which moves working memory into state signals instead.
+
+```typescript
+import { Memory } from '@mastra/memory'
+
+const memory = new Memory({
+  options: {
+    workingMemory: {
+      enabled: true,
+    },
+    observationalMemory: {
+      enabled: true,
+      observation: {
+        manageWorkingMemory: true,
+      },
+    },
+  },
+})
+```
+
+This setting adds `WorkingMemoryExtractor`, defaults `workingMemory.agentManaged` to `false`, and defaults `workingMemory.useStateSignals` to `true`. Set `workingMemory.agentManaged: true` if the main agent should still receive working memory tool and instruction injection.
+
+Use `onExtracted` to normalize or react to custom extracted values before they are persisted:
+
+```typescript
+new Extractor({
+  name: 'Project status',
+  instructions: 'Extract the current project status.',
+  schema: z.string(),
+  async onExtracted({ current, sendSignal }) {
+    await sendSignal?.({
+      type: 'user-message',
+      contents: `Project status extracted: ${current}`,
+    })
+    return current.trim().toLowerCase()
+  },
+})
+```
+
+Extractor failures are reported in OM markers and do not block other successful extractor values. See [the API reference](https://mastra.ai/reference/memory/observational-memory) for the full `Extractor` shape.
+
 If your Observer model is text-only or its API rejects multimodal input, set `observation.observeAttachments` to `false` to drop attachments before they reach the Observer. The readable placeholders (`[Image #1: ...]`, `[File #1: ...]`) are kept in the transcript so the Observer can still reason about what was shared without receiving the binary payload. The same filter applies to tool results that contain image or file parts:
 
 ```typescript

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

@@ -6,6 +6,8 @@ Think of it as the agent's active thoughts or scratchpad – the key information
 
 This is useful for maintaining ongoing state that's always relevant and should always be available to the agent.
 
+If you use [Observational Memory](https://mastra.ai/docs/memory/observational-memory), `observationalMemory.observation.manageWorkingMemory` lets OM update working memory for the agent.
+
 Working memory can persist at two different scopes:
 
 - **Resource-scoped** (default): Memory persists across all conversation threads for the same user

package/.docs/docs/observability/integrations/exporters/otel.md

@@ -1,6 +1,6 @@
 # OpenTelemetry exporter
 
-The OpenTelemetry (OTEL) exporter sends your traces and logs to any OTEL-compatible observability platform using standardized [OpenTelemetry Semantic Conventions for GenAI](https://opentelemetry.io/docs/specs/semconv/gen-ai/). This ensures broad compatibility with platforms like Datadog, New Relic, SigNoz, MLflow, Dash0, Traceloop, Laminar, and more.
+The OpenTelemetry (OTEL) exporter sends your traces and logs to any OTEL-compatible observability platform using standardized [OpenTelemetry Semantic Conventions for GenAI](https://opentelemetry.io/docs/specs/semconv/gen-ai/). This ensures broad compatibility with platforms like Datadog, New Relic, SigNoz, MLflow, Latitude, Dash0, Traceloop, Laminar, and more.
 
 > **Looking for bidirectional OTEL integration?:** If you have existing OpenTelemetry instrumentation and want Mastra traces to inherit context from active OTEL spans, see the [OpenTelemetry Bridge](https://mastra.ai/docs/observability/integrations/bridges/otel) instead.
 
@@ -8,7 +8,7 @@ The OpenTelemetry (OTEL) exporter sends your traces and logs to any OTEL-compati
 
 Each provider requires specific protocol packages. Install the base exporter plus the protocol package for your provider:
 
-### For HTTP/Protobuf Providers (SigNoz, New Relic, Laminar, MLflow)
+### For HTTP/Protobuf Providers (SigNoz, New Relic, Laminar, MLflow, Latitude)
 
 **npm**:
 
@@ -118,6 +118,27 @@ new OtelExporter({
 })
 ```
 
+### Latitude
+
+[Latitude](https://latitude.so) is an open-source LLM observability and evaluation platform that ingests OTLP traces. Use the `custom` provider with HTTP/Protobuf, pointing at Latitude's ingestion endpoint and authenticating with your API key and project slug:
+
+```typescript
+new OtelExporter({
+  provider: {
+    custom: {
+      endpoint: 'https://ingest.latitude.so/v1/traces',
+      protocol: 'http/protobuf',
+      headers: {
+        Authorization: `Bearer ${process.env.LATITUDE_API_KEY}`,
+        'X-Latitude-Project': process.env.LATITUDE_PROJECT,
+      },
+    },
+  },
+})
+```
+
+Sign up at [console.latitude.so](https://console.latitude.so/login), or self-host and point the endpoint at your own ingestion host.
+
 ### Dash0
 
 [Dash0](https://www.dash0.com/) provides real-time observability with automatic insights.

package/.docs/models/gateways/netlify.md

@@ -1,6 +1,6 @@
 # Netlify
 
-Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 64 models through Mastra's model router.
+Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 66 models through Mastra's model router.
 
 Learn more in the [Netlify documentation](https://docs.netlify.com/build/ai-gateway/overview/).
 
@@ -46,6 +46,7 @@ ANTHROPIC_API_KEY=ant-...
 | `anthropic/claude-sonnet-4-5`               |
 | `anthropic/claude-sonnet-4-5-20250929`      |
 | `anthropic/claude-sonnet-4-6`               |
+| `anthropic/claude-sonnet-5`                 |
 | `gemini/gemini-2.5-flash`                   |
 | `gemini/gemini-2.5-flash-image`             |
 | `gemini/gemini-2.5-flash-lite`              |
@@ -54,6 +55,7 @@ ANTHROPIC_API_KEY=ant-...
 | `gemini/gemini-3-pro-image`                 |
 | `gemini/gemini-3.1-flash-image`             |
 | `gemini/gemini-3.1-flash-lite`              |
+| `gemini/gemini-3.1-flash-lite-image`        |
 | `gemini/gemini-3.1-pro-preview`             |
 | `gemini/gemini-3.1-pro-preview-customtools` |
 | `gemini/gemini-3.5-flash`                   |

package/.docs/models/gateways/openrouter.md

@@ -1,6 +1,6 @@
 # ![OpenRouter logo](https://models.dev/logos/openrouter.svg)OpenRouter
 
-OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 337 models through Mastra's model router.
+OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 335 models through Mastra's model router.
 
 Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
 
@@ -61,7 +61,6 @@ ANTHROPIC_API_KEY=ant-...
 | `anthropic/claude-opus-4.1`                                     |
 | `anthropic/claude-opus-4.5`                                     |
 | `anthropic/claude-opus-4.6`                                     |
-| `anthropic/claude-opus-4.6-fast`                                |
 | `anthropic/claude-opus-4.7`                                     |
 | `anthropic/claude-opus-4.7-fast`                                |
 | `anthropic/claude-opus-4.8`                                     |
@@ -271,7 +270,6 @@ ANTHROPIC_API_KEY=ant-...
 | `openrouter/bodybuilder`                                        |
 | `openrouter/free`                                               |
 | `openrouter/fusion`                                             |
-| `openrouter/owl-alpha`                                          |
 | `openrouter/pareto-code`                                        |
 | `perceptron/perceptron-mk1`                                     |
 | `perplexity/sonar`                                              |

package/.docs/models/index.md

@@ -1,6 +1,6 @@
 # Model Providers
 
-Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 4481 models from 135 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 4488 models from 136 providers through a single API.
 
 ## Features
 

package/.docs/models/providers/anthropic.md

@@ -1,6 +1,6 @@
 # ![Anthropic logo](https://models.dev/logos/anthropic.svg)Anthropic
 
-Access 17 Anthropic models through Mastra's model router. Authentication is handled automatically using the `ANTHROPIC_API_KEY` environment variable.
+Access 18 Anthropic models through Mastra's model router. Authentication is handled automatically using the `ANTHROPIC_API_KEY` environment variable.
 
 Learn more in the [Anthropic documentation](https://docs.anthropic.com/en/docs/about-claude/models).
 
@@ -49,6 +49,7 @@ for await (const chunk of stream) {
 | `anthropic/claude-sonnet-4-5`          | 200K    |       |           |       |       |       | $3         | $15         |
 | `anthropic/claude-sonnet-4-5-20250929` | 200K    |       |           |       |       |       | $3         | $15         |
 | `anthropic/claude-sonnet-4-6`          | 1.0M    |       |           |       |       |       | $3         | $15         |
+| `anthropic/claude-sonnet-5`            | 1.0M    |       |           |       |       |       | $2         | $10         |
 
 ## Advanced configuration
 
@@ -77,7 +78,7 @@ const agent = new Agent({
   model: ({ requestContext }) => {
     const useAdvanced = requestContext.task === "complex";
     return useAdvanced
-      ? "anthropic/claude-sonnet-4-6"
+      ? "anthropic/claude-sonnet-5"
       : "anthropic/claude-fable-5";
   }
 });

package/.docs/models/providers/deepinfra.md

@@ -1,6 +1,6 @@
 # ![Deep Infra logo](https://models.dev/logos/deepinfra.svg)Deep Infra
 
-Access 26 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
+Access 27 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
 
 Learn more in the [Deep Infra documentation](https://deepinfra.com/models).
 
@@ -44,6 +44,7 @@ for await (const chunk of stream) {
 | `deepinfra/MiniMaxAI/MiniMax-M2.5`                            | 197K    |       |           |       |       |       | $0.15      | $1          |
 | `deepinfra/moonshotai/Kimi-K2.5`                              | 262K    |       |           |       |       |       | $0.45      | $2          |
 | `deepinfra/moonshotai/Kimi-K2.6`                              | 262K    |       |           |       |       |       | $0.75      | $4          |
+| `deepinfra/moonshotai/Kimi-K2.7-Code`                         | 262K    |       |           |       |       |       | $0.74      | $4          |
 | `deepinfra/openai/gpt-oss-120b`                               | 131K    |       |           |       |       |       | $0.04      | $0.19       |
 | `deepinfra/openai/gpt-oss-20b`                                | 131K    |       |           |       |       |       | $0.03      | $0.14       |
 | `deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo`         | 262K    |       |           |       |       |       | $0.30      | $1          |

package/.docs/models/providers/llmgateway.md

@@ -119,8 +119,8 @@ for await (const chunk of stream) {
 | `llmgateway/grok-4-1-fast-reasoning`               | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
 | `llmgateway/grok-4-20-beta-0309-non-reasoning`     | 2.0M    |       |           |       |       |       | $2         | $6          |
 | `llmgateway/grok-4-20-beta-0309-reasoning`         | 2.0M    |       |           |       |       |       | $2         | $6          |
-| `llmgateway/grok-4-20-non-reasoning`               | 2.0M    |       |           |       |       |       | $2         | $6          |
-| `llmgateway/grok-4-20-reasoning`                   | 2.0M    |       |           |       |       |       | $2         | $6          |
+| `llmgateway/grok-4-20-non-reasoning`               | 2.0M    |       |           |       |       |       | $1         | $3          |
+| `llmgateway/grok-4-20-reasoning`                   | 2.0M    |       |           |       |       |       | $1         | $3          |
 | `llmgateway/grok-4-3`                              | 1.0M    |       |           |       |       |       | $1         | $3          |
 | `llmgateway/grok-build-0-1`                        | 256K    |       |           |       |       |       | $1         | $2          |
 | `llmgateway/kimi-k2`                               | 256K    |       |           |       |       |       | $0.57      | $2          |
@@ -188,7 +188,7 @@ for await (const chunk of stream) {
 | `llmgateway/qwen3-coder-plus`                      | 1.0M    |       |           |       |       |       | $6         | $60         |
 | `llmgateway/qwen3-max`                             | 262K    |       |           |       |       |       | $0.84      | $3          |
 | `llmgateway/qwen3-max-2026-01-23`                  | 262K    |       |           |       |       |       | $1         | $6          |
-| `llmgateway/qwen3-next-80b-a3b-instruct`           | 131K    |       |           |       |       |       | $0.15      | $2          |
+| `llmgateway/qwen3-next-80b-a3b-instruct`           | 131K    |       |           |       |       |       | $0.15      | $1          |
 | `llmgateway/qwen3-next-80b-a3b-thinking`           | 131K    |       |           |       |       |       | $0.15      | $1          |
 | `llmgateway/qwen3-vl-235b-a22b-instruct`           | 131K    |       |           |       |       |       | $0.30      | $2          |
 | `llmgateway/qwen3-vl-235b-a22b-thinking`           | 131K    |       |           |       |       |       | $0.50      | $2          |

package/.docs/models/providers/novita-ai.md

@@ -63,7 +63,7 @@ for await (const chunk of stream) {
 | `novita-ai/google/gemma-4-26b-a4b-it`                         | 262K    |       |           |       |       |       | $0.13      | $0.40       |
 | `novita-ai/google/gemma-4-31b-it`                             | 262K    |       |           |       |       |       | $0.14      | $0.40       |
 | `novita-ai/gryphe/mythomax-l2-13b`                            | 4K      |       |           |       |       |       | $0.09      | $0.09       |
-| `novita-ai/inclusionai/ling-2.6-1t`                           | 262K    |       |           |       |       |       | —          | —           |
+| `novita-ai/inclusionai/ling-2.6-1t`                           | 262K    |       |           |       |       |       | $0.30      | $3          |
 | `novita-ai/inclusionai/ling-2.6-flash`                        | 262K    |       |           |       |       |       | $0.10      | $0.30       |
 | `novita-ai/inclusionai/ring-2.6-1t`                           | 262K    |       |           |       |       |       | $0.30      | $3          |
 | `novita-ai/kwaipilot/kat-coder-pro`                           | 256K    |       |           |       |       |       | $0.30      | $1          |

package/.docs/models/providers/opencode-go.md

@@ -43,7 +43,7 @@ for await (const chunk of stream) {
 | `opencode-go/mimo-v2.5`         | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
 | `opencode-go/mimo-v2.5-pro`     | 1.0M    |       |           |       |       |       | $2         | $3          |
 | `opencode-go/minimax-m2.7`      | 205K    |       |           |       |       |       | $0.30      | $1          |
-| `opencode-go/minimax-m3`        | 1.0M    |       |           |       |       |       | $0.10      | $0.40       |
+| `opencode-go/minimax-m3`        | 1.0M    |       |           |       |       |       | $0.30      | $1          |
 | `opencode-go/qwen3.6-plus`      | 1.0M    |       |           |       |       |       | $0.50      | $3          |
 | `opencode-go/qwen3.7-max`       | 1.0M    |       |           |       |       |       | $3         | $8          |
 | `opencode-go/qwen3.7-plus`      | 1.0M    |       |           |       |       |       | $0.40      | $2          |

package/.docs/models/providers/sakana.md

@@ -0,0 +1,73 @@
+# ![Sakana AI logo](https://models.dev/logos/sakana.svg)Sakana AI
+
+Access 3 Sakana AI models through Mastra's model router. Authentication is handled automatically using the `SAKANA_API_KEY` environment variable.
+
+Learn more in the [Sakana AI documentation](https://console.sakana.ai/models).
+
+```bash
+SAKANA_API_KEY=your-api-key
+```
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "sakana/fugu"
+});
+
+// Generate a response
+const response = await agent.generate("Hello!");
+
+// Stream a response
+const stream = await agent.stream("Tell me a story");
+for await (const chunk of stream) {
+  console.log(chunk);
+}
+```
+
+> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Sakana AI documentation](https://console.sakana.ai/models) for details.
+
+## Models
+
+| Model                        | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| ---------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `sakana/fugu`                | 1.0M    |       |           |       |       |       | —          | —           |
+| `sakana/fugu-ultra`          | 1.0M    |       |           |       |       |       | $5         | $30         |
+| `sakana/fugu-ultra-20260615` | 1.0M    |       |           |       |       |       | $5         | $30         |
+
+## Advanced configuration
+
+### Custom headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://api.sakana.ai/v1",
+    id: "sakana/fugu",
+    apiKey: process.env.SAKANA_API_KEY,
+    headers: {
+      "X-Custom-Header": "value"
+    }
+  }
+});
+```
+
+### Dynamic model selection
+
+```typescript
+const agent = new Agent({
+  id: "dynamic-agent",
+  name: "Dynamic Agent",
+  model: ({ requestContext }) => {
+    const useAdvanced = requestContext.task === "complex";
+    return useAdvanced
+      ? "sakana/fugu-ultra-20260615"
+      : "sakana/fugu";
+  }
+});
+```

package/.docs/models/providers/stepfun.md

@@ -38,7 +38,7 @@ for await (const chunk of stream) {
 | `stepfun/step-2-16k`          | 16K     |       |           |       |       |       | $5         | $16         |
 | `stepfun/step-3.5-flash`      | 256K    |       |           |       |       |       | $0.10      | $0.30       |
 | `stepfun/step-3.5-flash-2603` | 256K    |       |           |       |       |       | $0.10      | $0.30       |
-| `stepfun/step-3.7-flash`      | 256K    |       |           |       |       |       | $0.19      | $1          |
+| `stepfun/step-3.7-flash`      | 256K    |       |           |       |       |       | $0.20      | $1          |
 
 ## Advanced configuration
 

package/.docs/models/providers/synthetic.md

@@ -1,6 +1,6 @@
 # ![Synthetic logo](https://models.dev/logos/synthetic.svg)Synthetic
 
-Access 8 Synthetic models through Mastra's model router. Authentication is handled automatically using the `SYNTHETIC_API_KEY` environment variable.
+Access 10 Synthetic models through Mastra's model router. Authentication is handled automatically using the `SYNTHETIC_API_KEY` environment variable.
 
 Learn more in the [Synthetic documentation](https://synthetic.new/pricing).
 
@@ -37,11 +37,13 @@ for await (const chunk of stream) {
 | `synthetic/hf:MiniMaxAI/MiniMax-M3`                           | 524K    |       |           |       |       |       | $0.60      | $1          |
 | `synthetic/hf:moonshotai/Kimi-K2.6`                           | 262K    |       |           |       |       |       | $0.95      | $4          |
 | `synthetic/hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4` | 262K    |       |           |       |       |       | $0.30      | $1          |
-| `synthetic/hf:openai/gpt-oss-120b`                            | 128K    |       |           |       |       |       | $0.10      | $0.10       |
-| `synthetic/hf:Qwen/Qwen3.5-397B-A17B`                         | 262K    |       |           |       |       |       | $0.60      | $3          |
-| `synthetic/hf:zai-org/GLM-4.7`                                | 200K    |       |           |       |       |       | $0.55      | $2          |
-| `synthetic/hf:zai-org/GLM-4.7-Flash`                          | 197K    |       |           |       |       |       | $0.06      | $0.40       |
+| `synthetic/hf:openai/gpt-oss-120b`                            | 131K    |       |           |       |       |       | $0.10      | $0.10       |
+| `synthetic/hf:Qwen/Qwen3.5-397B-A17B`                         | 262K    |       |           |       |       |       | $0.60      | $4          |
+| `synthetic/hf:Qwen/Qwen3.6-27B`                               | 262K    |       |           |       |       |       | $0.45      | $4          |
+| `synthetic/hf:zai-org/GLM-4.7`                                | 203K    |       |           |       |       |       | $0.45      | $2          |
+| `synthetic/hf:zai-org/GLM-4.7-Flash`                          | 197K    |       |           |       |       |       | $0.10      | $0.50       |
 | `synthetic/hf:zai-org/GLM-5.1`                                | 197K    |       |           |       |       |       | $1         | $3          |
+| `synthetic/hf:zai-org/GLM-5.2`                                | 524K    |       |           |       |       |       | $1         | $4          |
 
 ## Advanced configuration
 
@@ -71,7 +73,7 @@ const agent = new Agent({
   model: ({ requestContext }) => {
     const useAdvanced = requestContext.task === "complex";
     return useAdvanced
-      ? "synthetic/hf:zai-org/GLM-5.1"
+      ? "synthetic/hf:zai-org/GLM-5.2"
       : "synthetic/hf:MiniMaxAI/MiniMax-M3";
   }
 });

package/.docs/models/providers/xiaomi.md

@@ -34,8 +34,8 @@ for await (const chunk of stream) {
 
 | Model                             | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
 | --------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
-| `xiaomi/mimo-v2.5`                | 1.0M    |       |           |       |       |       | $0.40      | $2          |
-| `xiaomi/mimo-v2.5-pro`            | 1.0M    |       |           |       |       |       | $1         | $3          |
+| `xiaomi/mimo-v2.5`                | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
+| `xiaomi/mimo-v2.5-pro`            | 1.0M    |       |           |       |       |       | $0.43      | $0.87       |
 | `xiaomi/mimo-v2.5-pro-ultraspeed` | 1.0M    |       |           |       |       |       | $1         | $3          |
 
 ## Advanced configuration

package/.docs/models/providers/zeldoc.md

@@ -34,7 +34,7 @@ for await (const chunk of stream) {
 
 | Model           | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
 | --------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
-| `zeldoc/z-code` | 262K    |       |           |       |       |       | —          | —           |
+| `zeldoc/z-code` | 1.0M    |       |           |       |       |       | —          | —           |
 
 ## Advanced configuration
 

package/.docs/models/providers.md

@@ -98,6 +98,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
 - [Regolo AI](https://mastra.ai/models/providers/regolo-ai)
 - [Requesty](https://mastra.ai/models/providers/requesty)
 - [routing.run](https://mastra.ai/models/providers/routing-run)
+- [Sakana AI](https://mastra.ai/models/providers/sakana)
 - [Sarvam AI](https://mastra.ai/models/providers/sarvam)
 - [Scaleway](https://mastra.ai/models/providers/scaleway)
 - [SiliconFlow](https://mastra.ai/models/providers/siliconflow)

package/.docs/reference/agent-controller/agent-controller-class.md

@@ -128,7 +128,7 @@ await agentController.sendMessage({ content: 'Hello!' })
 
 **disableBuiltinTools** (`BuiltinToolId[]`): Built-in tool IDs to remove from the \`controllerBuiltIn\` toolset. Valid values are \`ask\_user\`, \`submit\_plan\`, \`task\_write\`, \`task\_update\`, \`task\_complete\`, \`task\_check\`, and \`subagent\`.
 
-**heartbeatHandlers** (`HeartbeatHandler[]`): Periodic background tasks started during \`init()\`. Use for gateway sync, cache refresh, and similar tasks.
+**intervalHandlers** (`IntervalHandler[]`): Periodic background tasks started during \`init()\`. Use for gateway sync, cache refresh, and similar tasks.
 
 **idGenerator** (`() => string`): Custom ID generator for AgentController-managed IDs such as threads and mode-run identifiers. (Default: `timestamp + random string`)
 
@@ -162,7 +162,7 @@ await agentController.sendMessage({ content: 'Hello!' })
 
 #### `init()`
 
-Initialize the agentController. Loads storage, initializes a static workspace (dynamic factory workspaces are resolved per-session during `createSession`), propagates memory and workspace to mode agents, and starts heartbeat handlers. Call this before using the agentController.
+Initialize the agentController. Loads storage, initializes a static workspace (dynamic factory workspaces are resolved per-session during `createSession`), propagates memory and workspace to mode agents, and starts interval handlers. Call this before using the agentController.
 
 ```typescript
 await agentController.init()
@@ -220,26 +220,26 @@ const thread = await agentController.selectOrCreateThread()
 
 #### `destroy()`
 
-Stop all heartbeat handlers and clean up resources.
+Stop all interval handlers and clean up resources.
 
 ```typescript
 await agentController.destroy()
 ```
 
-#### `removeHeartbeat({ id })`
+#### `removeInterval({ id })`
 
-Remove a specific heartbeat handler by ID. Calls the handler's `shutdown()` callback if defined.
+Remove a specific interval handler by ID. Calls the handler's `shutdown()` callback if defined.
 
 ```typescript
-await agentController.removeHeartbeat({ id: 'gateway-sync' })
+await agentController.removeInterval({ id: 'gateway-sync' })
 ```
 
-#### `stopHeartbeats()`
+#### `stopIntervals()`
 
-Stop and remove all heartbeat handlers.
+Stop and remove all interval handlers.
 
 ```typescript
-await agentController.stopHeartbeats()
+await agentController.stopIntervals()
 ```
 
 #### `getCurrentAgent()`

package/.docs/reference/agents/listSuspendedRuns.md

@@ -0,0 +1,91 @@
+# Agent.listSuspendedRuns()
+
+**Added in:** `@mastra/core@1.43.0`
+
+The `.listSuspendedRuns()` method lists suspended agent runs from workflow snapshot storage: runs waiting on a tool call requiring [approval](https://mastra.ai/docs/agents/agent-approval), or on a tool that called `suspend()`. Because discovery is backed by storage rather than in-memory state, it works after a server restart and across multiple server instances.
+
+Pass the returned `runId` to [`resumeStream()`](https://mastra.ai/docs/agents/agent-approval), `approveToolCall()`, or `declineToolCall()` to continue the run.
+
+The filter contract mirrors the workflow run listing APIs (`listWorkflowRuns`), plus the agent-level `threadId` filter.
+
+## Usage example
+
+Discover the pending run for a conversation and continue it. Check `requiresApproval` to pick the right continuation — `approveToolCall()` / `declineToolCall()` for approval suspensions, `resumeStream()` with resume data for `suspend()`-based suspensions:
+
+```typescript
+const { runs } = await agent.listSuspendedRuns({
+  threadId: 'thread-123',
+  resourceId: 'user-456',
+})
+
+const run = runs[0]
+const toolCall = run?.toolCalls[0]
+
+if (run && toolCall) {
+  const stream = toolCall.requiresApproval
+    ? await agent.approveToolCall({ runId: run.runId, toolCallId: toolCall.toolCallId })
+    : await agent.resumeStream({ name: 'San Francisco' }, { runId: run.runId })
+}
+```
+
+## Parameters
+
+**options** (`AgentListSuspendedRunsOptions`): Filters and pagination for scoping the results. (Default: `{}`)
+
+**options.threadId** (`string`): Only return runs that belong to this memory thread.
+
+**options.resourceId** (`string`): Only return runs that belong to this memory resource.
+
+**options.fromDate** (`Date`): Only return runs created at or after this date.
+
+**options.toDate** (`Date`): Only return runs created at or before this date.
+
+**options.perPage** (`number`): Number of items per page. Pagination is applied when both perPage and page are provided; otherwise all matching runs are returned.
+
+**options.page** (`number`): Zero-indexed page number.
+
+## Returns
+
+**result** (`Promise<AgentListSuspendedRunsResult>`): A promise that resolves to the matching runs and the total count before pagination.
+
+```typescript
+interface AgentListSuspendedRunsResult {
+  runs: AgentRun[]
+  /** Total number of matching runs, before pagination */
+  total: number
+}
+
+interface AgentRun {
+  /** Run ID accepted by resumeStream(), approveToolCall(), and declineToolCall() */
+  runId: string
+  status: 'suspended'
+  threadId?: string
+  resourceId?: string
+  /** When the run suspended */
+  suspendedAt: Date
+  /** Suspended tool calls awaiting approval or resume data */
+  toolCalls: AgentRunToolCall[]
+}
+
+interface AgentRunToolCall {
+  toolCallId?: string
+  toolName?: string
+  /** Arguments the model supplied (approval suspensions only) */
+  args?: unknown
+  /** True when the run is waiting on a tool-call approval */
+  requiresApproval: boolean
+  /** The tool-defined suspend payload when the tool called suspend() */
+  suspendPayload?: unknown
+}
+```
+
+## Discovery scope
+
+Results are scoped to runs started by the agent you call `listSuspendedRuns()` on: snapshots persist the owning agent's id, so runs started by other agents on the same Mastra instance are not returned. In [supervisor setups](https://mastra.ai/docs/agents/agent-approval) the supervisor sees its outer run — the one to resume — while a subagent's inner run is only visible from the subagent itself. Filter by `threadId` and `resourceId` to scope results to one conversation.
+
+Run snapshots are only persisted while a run is waiting on input and are deleted when it finishes, so suspended runs are the only runs discoverable from storage. Suspended runs only survive restarts when the Mastra instance has a persistent [storage provider](https://mastra.ai/docs/memory/storage) configured. With the default in-memory store, snapshots are lost on restart.
+
+## Related
+
+- [Agent approval](https://mastra.ai/docs/agents/agent-approval)
+- [Storage](https://mastra.ai/docs/memory/storage)

package/.docs/reference/client-js/agents.md

@@ -362,6 +362,27 @@ response.processDataStream({
 })
 ```
 
+### `listSuspendedRuns()`
+
+List suspended runs for the agent from storage — runs waiting on a tool-call approval or on a tool that suspended. Discovery is backed by storage, so it works after a server restart and across server instances. Pass the returned `runId` to `approveToolCall()`, `declineToolCall()`, or `resumeStream()`.
+
+```typescript
+const { runs, total } = await agent.listSuspendedRuns({
+  threadId: 'thread-456',
+  resourceId: 'user-123',
+})
+
+if (runs[0]) {
+  console.log(runs[0].toolCalls) // [{ toolCallId, toolName, args, requiresApproval }]
+  await agent.approveToolCall({
+    runId: runs[0].runId,
+    toolCallId: runs[0].toolCalls[0].toolCallId,
+  })
+}
+```
+
+Accepts optional filters (`threadId`, `resourceId`, `fromDate`, `toDate`) and pagination (`perPage`, `page`). Returns `{ runs, total }`, where `total` is the number of matching runs before pagination. See [`Agent.listSuspendedRuns()`](https://mastra.ai/reference/agents/listSuspendedRuns) for details on the returned run shape.
+
 ### `approveToolCall()`
 
 Approve a pending tool call and return a continuation stream. Use this when you are rendering the resumed chunks from the approval response.