@mastra/mcp-docs-server 1.3.7-alpha.7 → 1.3.7-alpha.9

package/.docs/docs/harness/durable-agents.md

@@ -364,6 +364,18 @@ Enforcement of the claim depends on the workflows store. When the store supports
 - `InMemoryStore` from `@mastra/core/storage`
 - `@mastra/pg`
 - `@mastra/libsql` and `@mastra/turso`
+- `@mastra/mysql`
+- `@mastra/mssql`
+- `@mastra/oracledb`
+- `@mastra/spanner`
+- `@mastra/dsql`
+- `@mastra/cloudflare-d1`
+- `@mastra/cloudflare`, with `CloudflareDOStorage`
+- `@mastra/convex`
+- `@mastra/mongodb`, on a replica set or sharded cluster
+- `@mastra/dynamodb`
+
+On Convex, run fencing runs in the Mastra server functions you deploy. Redeploy your Convex functions after upgrading `@mastra/convex`. Until you do, durable agent runs fail with an error asking you to redeploy, while other writes keep working.
 
 Stores that support run fencing keep one claim record per run, plus one memory fence record per run with memory. Stores with retention support prune them with the `workflows.runOwnership` and `memory.runFences` [retention keys](https://mastra.ai/reference/storage/retention). A run's first generation comes from the store's clock, so a run that reuses a `runId` after its records were pruned still outranks the fences and stream events of its earlier executions.
 

package/.docs/docs/observability/metrics/overview.md

@@ -10,7 +10,7 @@ Mastra emits:
 
 - **Duration metrics** for agent runs, workflows, tools, model calls, and processors
 - **Token usage metrics** for model input and output, including detailed token categories when the provider reports them
-- **Cost estimates** calculated from token usage, provider, model, and model prices from [models.dev](https://models.dev)
+- **Cost estimates** calculated from token usage, provider, model, and model prices from [models.dev](https://models.dev) or from a [custom gateway](https://mastra.ai/models/gateways/custom-gateways)
 
 Metrics retain trace correlation context, so you can investigate a change in a chart by finding the related span. See the [Automatic metrics reference](https://mastra.ai/reference/observability/metrics/automatic-metrics) for metric names, labels, and cost fields.
 

package/.docs/docs/studio/overview.md

@@ -117,7 +117,7 @@ See [datasets overview](https://mastra.ai/docs/evals/datasets) for the full API
 
 ### Experiments
 
-Run all items in a dataset against an agent, workflow, or scorer and collect the results in one place. Select a target, optionally attach scorers, and trigger the experiment. The results view shows each item's input, output, status, and individual score breakdowns. Compare two experiments side by side to measure the impact of prompt, model, or code changes.
+Run all items in a dataset against an agent, workflow, or scorer and collect the results in one place. Select a target, optionally attach scorers, and trigger the experiment. The results view shows each item's input, output, status, and individual score breakdowns. Compare two to ten experiments side by side against a baseline to measure the impact of prompt, model, or code changes.
 
 See [datasets overview](https://mastra.ai/docs/evals/datasets) for setup details.
 

package/.docs/integrations/observability/opentelemetry.md

@@ -766,7 +766,7 @@ No Mastra exporters are required when using the bridge. Traces are sent via your
 
 #### Forwarding logs (optional)
 
-The bridge also forwards Mastra log events to the globally registered OTEL `LoggerProvider`. To wire up logs alongside traces, register a `logRecordProcessor` on `NodeSDK`:
+The bridge also forwards Mastra log events to the globally registered OTEL `LoggerProvider`. To wire up logs alongside traces, register a log record processor on `NodeSDK`:
 
 ```typescript
 import { NodeSDK } from '@opentelemetry/sdk-node'
@@ -775,11 +775,13 @@ import { BatchLogRecordProcessor } from '@opentelemetry/sdk-logs'
 
 const sdk = new NodeSDK({
   // ...trace config as usual
-  logRecordProcessor: new BatchLogRecordProcessor(
-    new OTLPLogExporter({
-      url: process.env.OTEL_EXPORTER_OTLP_LOGS_ENDPOINT || 'http://localhost:4318/v1/logs',
+  logRecordProcessors: [
+    new BatchLogRecordProcessor({
+      exporter: new OTLPLogExporter({
+        url: process.env.OTEL_EXPORTER_OTLP_LOGS_ENDPOINT || 'http://localhost:4318/v1/logs',
+      }),
     }),
-  ),
+  ],
 })
 ```
 
@@ -795,6 +797,10 @@ Use the `--import` flag to ensure instrumentation loads before your application:
 tsx --import ./instrumentation.ts ./src/index.ts
 ```
 
+#### Flushing before exit
+
+Mastra's `flush()` and `shutdown()` ask the registered OTEL providers to flush, but a `BatchSpanProcessor` can still hold a batch it has already started exporting. In serverless or short-lived processes, also `await sdk.shutdown()` after Mastra's flush, so no spans are left in your OTEL SDK when the process exits. The provider's own `forceFlush()` is not enough: it does not wait for a batch the exporter is already sending.
+
 ### Semantic conventions
 
 The `OtelBridge` exports Mastra spans using [OpenTelemetry Semantic Conventions for GenAI v1.38.0](https://github.com/open-telemetry/semantic-conventions/tree/v1.38.0/docs/gen-ai). This includes standardized span names (`chat {model}`, `execute_tool {tool_name}`, etc.) and attributes (`gen_ai.usage.input_tokens`, `gen_ai.request.model`, etc.).

package/.docs/integrations/sandboxes/e2b.md

@@ -402,23 +402,18 @@ Setup commands that need their own credentials — a registry token, a private i
 
 ### Per-session sandboxes
 
-Hosts that construct one sandbox per session, such as Mastra Factory's `sandbox` config, combine the pieces above in a small callback: sandbox identity is the session id (id-keyed getOrCreate — the sandbox pauses on E2B's idle timeout and resumes by id), and the repo template comes from `createRepoTemplate`. The host's session context carries everything the template needs, so it can be passed straight through:
+Hosts that construct one sandbox per session, such as Mastra Factory's `sandbox` config, use `E2BFactorySandbox`: sandbox identity is the session id (id-keyed getOrCreate, so the sandbox pauses on E2B's idle timeout and resumes by id), the repo template comes from `createRepoTemplate` over the session's repositories, and the project's `cpuCount` and `memoryMb` settings flow into the template. See the [FactorySandbox reference](https://mastra.ai/reference/workspace/factory-sandbox).
 
 ```typescript
 import { MastraFactory } from '@mastra/factory'
-import { E2BSandbox, createRepoTemplate } from '@mastra/e2b'
+import { E2BFactorySandbox } from '@mastra/e2b'
 
 new MastraFactory({
-  sandbox: ctx =>
-    new E2BSandbox({
-      id: ctx.sessionId,
-      // Undefined for a session with no repository.
-      template: createRepoTemplate(ctx),
-    }),
+  sandbox: new E2BFactorySandbox({ apiKey: process.env.E2B_API_KEY }),
 })
 ```
 
-Factory attaches its own session setup to the sandbox it gets back, so the callback doesn't wire up a start hook.
+The bare callback form, `sandbox: ctx => new E2BSandbox({ id: ctx.sessionId, template: createRepoTemplate(ctx) })`, is also supported: factory sees it as a custom provider with no settings to tune. Either way, factory attaches its own session setup to the sandbox it gets back.
 
 ## Using with Code Mode
 

package/.docs/models/environment-variables.md

@@ -15,6 +15,7 @@ List of required environment variables for each model provider and gateway suppo
 | [AgentRouter](https://mastra.ai/models/providers/agentrouter)                                | `agentrouter/*`            | `AGENTROUTER_API_KEY`                                                                                 |
 | [Agnes AI](https://mastra.ai/models/providers/agnes)                                         | `agnes/*`                  | `AGNES_API_KEY`                                                                                       |
 | [AI-ROUTER](https://mastra.ai/models/providers/ai-router)                                    | `ai-router/*`              | `AI_ROUTER_API_KEY`                                                                                   |
+| [AI/ML API](https://mastra.ai/models/providers/aimlapi)                                      | `aimlapi/*`                | `AIMLAPI_API_KEY`                                                                                     |
 | [ai&](https://mastra.ai/models/providers/aiand)                                              | `aiand/*`                  | `AIAND_API_KEY`                                                                                       |
 | [AI21 Labs](https://mastra.ai/models/providers/ai21)                                         | `ai21/*`                   | `AI21_API_KEY`                                                                                        |
 | [ainetcafe](https://mastra.ai/models/providers/ainetcafe)                                    | `ainetcafe/*`              | `AINETCAFE_API_KEY`                                                                                   |

package/.docs/models/gateways/custom-gateways.md

@@ -371,6 +371,28 @@ interface ProviderConfig {
   url?: string;                    // Optional API base URL
   apiKeyHeader?: string;           // Optional custom auth header
   docUrl?: string;                 // Optional documentation URL
+  pricing?: Record<string, ModelPricing>; // Optional prices per model ID
+}
+```
+
+### Model pricing
+
+models.dev does not list private deployments, so their calls have no cost in [metrics](https://mastra.ai/docs/observability/metrics/overview). Add a `pricing` entry per model to give them one. Prices are in USD per 1 million tokens and use the same keys as a model's `cost` on [models.dev](https://models.dev): `input`, `output`, `cache_read`, `cache_write`, `reasoning`, `input_audio`, and `output_audio`. `@mastra/observability` reads these prices on the first call to a model it can't price, which also picks up gateways added later with `addGateway()`. Under `mastra dev`, or with `MASTRA_AUTO_REFRESH_PRICING=true`, it also reads them when Mastra starts, so the first call is priced too. models.dev prices take precedence. A gateway price is used only when models.dev has none for that provider and model ID, and then it applies to every call with those IDs, including direct calls. Give a reseller its own provider ID when its rates must stay separate from direct calls. A gateway whose `fetchProviders()` fails is logged and retried about once an hour. Set `MASTRA_OFFLINE=true` to skip loading them. The same shape as models.dev also means you can add `tiers` for long-context pricing.
+
+```typescript
+async fetchProviders(): Promise<Record<string, ProviderConfig>> {
+  return {
+    'my-provider': {
+      name: 'My Provider',
+      models: ['model-1'],
+      apiKeyEnvVar: 'MY_API_KEY',
+      gateway: 'private',
+      url: 'https://api.myprovider.com/v1',
+      pricing: {
+        'model-1': { input: 0.5, output: 1.5, cache_read: 0.05 },
+      },
+    },
+  };
 }
 ```
 

package/.docs/models/gateways/merge-gateway.md

@@ -4,7 +4,7 @@
 
 # ![Merge Gateway logo](https://models.dev/logos/merge-gateway.svg)Merge Gateway
 
-Merge Gateway aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 199 models through Mastra's model router.
+Merge Gateway aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 203 models through Mastra's model router.
 
 Learn more in the [Merge Gateway documentation](https://docs.merge.dev/merge-gateway).
 
@@ -96,6 +96,7 @@ ANTHROPIC_API_KEY=ant-...
 | `google/gemini-3.6-flash`                        |
 | `google/gemini-3.7-flash`                        |
 | `google/gemini-3.8-flash`                        |
+| `google/gemini-4-argon`                          |
 | `google/gemini-embedding-001`                    |
 | `google/gemini-embedding-2`                      |
 | `google/gemini-flash-latest`                     |
@@ -189,11 +190,13 @@ ANTHROPIC_API_KEY=ant-...
 | `qwen/qwen3-coder-next`                          |
 | `qwen/qwen3-coder-plus`                          |
 | `qwen/qwen3-max`                                 |
+| `qwen/qwen3-max-preview`                         |
 | `qwen/qwen3-next-80b-a3b-instruct`               |
 | `qwen/qwen3-next-80b-a3b-thinking`               |
 | `qwen/qwen3-vl-235b-a22b-instruct`               |
 | `qwen/qwen3-vl-235b-a22b-thinking`               |
 | `qwen/qwen3-vl-30b-a3b-instruct`                 |
+| `qwen/qwen3-vl-flash`                            |
 | `qwen/qwen3-vl-plus`                             |
 | `qwen/qwen3.5-122b-a10b`                         |
 | `qwen/qwen3.5-27b`                               |
@@ -212,6 +215,7 @@ ANTHROPIC_API_KEY=ant-...
 | `qwen/qwen3.8-2.4t-a95b`                         |
 | `qwen/qwen3.8-flash`                             |
 | `qwen/qwen3.8-max`                               |
+| `sakana/fugu-max`                                |
 | `sakana/fugu-ultra`                              |
 | `sakana/sakana-namazu`                           |
 | `thinkingmachines/inkling`                       |

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

@@ -4,7 +4,7 @@
 
 # Netlify
 
-Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 274 models through Mastra's model router.
+Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 275 models through Mastra's model router.
 
 Learn more in the [Netlify documentation](https://docs.netlify.com/build/ai-gateway/overview/).
 
@@ -72,6 +72,7 @@ ANTHROPIC_API_KEY=ant-...
 | `gemini/gemini-3.6-flash`                                             |
 | `gemini/gemini-3.7-flash`                                             |
 | `gemini/gemini-3.8-flash`                                             |
+| `gemini/gemini-4-argon`                                               |
 | `gemini/gemini-flash-latest`                                          |
 | `gemini/gemini-flash-lite-latest`                                     |
 | `gemini/gemini-nano-banana-2.1`                                       |
@@ -136,7 +137,6 @@ ANTHROPIC_API_KEY=ant-...
 | `openrouter/~z-ai/glm-flash-latest`                                   |
 | `openrouter/~z-ai/glm-latest`                                         |
 | `openrouter/anthracite-org/magnum-v4-72b`                             |
-| `openrouter/apodex/apodex-1.1-mini:free`                              |
 | `openrouter/bytedance-seed/seed-1.6`                                  |
 | `openrouter/bytedance-seed/seed-1.6-flash`                            |
 | `openrouter/bytedance-seed/seed-2-1-turbo`                            |
@@ -169,12 +169,11 @@ ANTHROPIC_API_KEY=ant-...
 | `openrouter/inception/mercury-2`                                      |
 | `openrouter/inception/mercury-2.5`                                    |
 | `openrouter/inclusionai/ling-3.0-flash`                               |
-| `openrouter/inclusionai/ling-3.0-flash-fin`                           |
-| `openrouter/inclusionai/ling-3.0-flash-sante`                         |
 | `openrouter/inclusionai/ling-3.0-flash-vl`                            |
 | `openrouter/inclusionai/ling-3.1-flash`                               |
 | `openrouter/inference-net/schematron-v2-small`                        |
 | `openrouter/inference-net/schematron-v2-turbo`                        |
+| `openrouter/liquid/lfm-2.5-24b-a2b`                                   |
 | `openrouter/mancer/weaver`                                            |
 | `openrouter/meta-llama/llama-3.1-70b-instruct`                        |
 | `openrouter/meta-llama/llama-3.1-8b-instruct`                         |
@@ -272,6 +271,8 @@ ANTHROPIC_API_KEY=ant-...
 | `openrouter/sao10k/l3-lunaris-8b`                                     |
 | `openrouter/sao10k/l3.1-euryale-70b`                                  |
 | `openrouter/sao10k/l3.3-euryale-70b`                                  |
+| `openrouter/scaledown/extract`                                        |
+| `openrouter/scaledown/summarize`                                      |
 | `openrouter/stepfun/step-3.7-flash`                                   |
 | `openrouter/tencent/hy-mt2-1.8b`                                      |
 | `openrouter/tencent/hy-mt2-30b-a3b`                                   |

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

@@ -4,7 +4,7 @@
 
 # ![OpenRouter logo](https://models.dev/logos/openrouter.svg)OpenRouter
 
-OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 380 models through Mastra's model router.
+OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 382 models through Mastra's model router.
 
 Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
 
@@ -84,7 +84,6 @@ ANTHROPIC_API_KEY=ant-...
 | `anthropic/claude-sonnet-4.6`                              |
 | `anthropic/claude-sonnet-5`                                |
 | `anthropic/claude-sonnet-5.5`                              |
-| `apodex/apodex-1.1-mini:free`                              |
 | `arcee-ai/trinity-large-thinking`                          |
 | `bytedance-seed/seed-1.6`                                  |
 | `bytedance-seed/seed-1.6-flash`                            |
@@ -136,6 +135,7 @@ ANTHROPIC_API_KEY=ant-...
 | `google/gemini-3.6-flash`                                  |
 | `google/gemini-3.7-flash`                                  |
 | `google/gemini-3.8-flash`                                  |
+| `google/gemini-4-argon`                                    |
 | `google/gemini-nano-banana-2.1`                            |
 | `google/gemma-2-27b-it`                                    |
 | `google/gemma-3-12b-it`                                    |
@@ -153,13 +153,12 @@ ANTHROPIC_API_KEY=ant-...
 | `inception/mercury-2`                                      |
 | `inception/mercury-2.5`                                    |
 | `inclusionai/ling-3.0-flash`                               |
-| `inclusionai/ling-3.0-flash-fin`                           |
-| `inclusionai/ling-3.0-flash-sante`                         |
 | `inclusionai/ling-3.0-flash-vl`                            |
 | `inclusionai/ling-3.1-flash`                               |
 | `inference-net/schematron-v2-small`                        |
 | `inference-net/schematron-v2-turbo`                        |
 | `liquid/lfm-2.5-2.6b:free`                                 |
+| `liquid/lfm-2.5-24b-a2b`                                   |
 | `mancer/weaver`                                            |
 | `meituan/longcat-2.0`                                      |
 | `meta-llama/llama-3.1-70b-instruct`                        |
@@ -366,6 +365,8 @@ ANTHROPIC_API_KEY=ant-...
 | `sao10k/l3-lunaris-8b`                                     |
 | `sao10k/l3.1-euryale-70b`                                  |
 | `sao10k/l3.3-euryale-70b`                                  |
+| `scaledown/extract`                                        |
+| `scaledown/summarize`                                      |
 | `stepfun/step-3.5-flash`                                   |
 | `stepfun/step-3.7-flash`                                   |
 | `stepfun/step-5-preview`                                   |
@@ -385,6 +386,7 @@ ANTHROPIC_API_KEY=ant-...
 | `thinkingmachines/inkling:free`                            |
 | `unbiased/pareto`                                          |
 | `unbiased/pareto-26.10-preview`                            |
+| `unbiased/pareto-26.9`                                     |
 | `undi95/remm-slerp-l2-13b`                                 |
 | `upstage/solar-mini4`                                      |
 | `upstage/solar-pro-3`                                      |

package/.docs/models/gateways/vercel.md

@@ -4,7 +4,7 @@
 
 # ![Vercel logo](https://models.dev/logos/vercel.svg)Vercel
 
-Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 402 models through Mastra's model router.
+Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 407 models through Mastra's model router.
 
 Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
 
@@ -146,6 +146,7 @@ ANTHROPIC_API_KEY=ant-...
 | `deepseek/deepseek-v4.1-flash`             |
 | `deepseek/deepseek-v4.1-flash-fast`        |
 | `fireworks/ember-1`                        |
+| `fish-audio/drama-3`                       |
 | `fish-audio/s1`                            |
 | `fish-audio/s2-pro`                        |
 | `fish-audio/s2.1-pro`                      |
@@ -172,6 +173,7 @@ ANTHROPIC_API_KEY=ant-...
 | `google/gemini-3.8-flash-tts`              |
 | `google/gemini-3.8-live`                   |
 | `google/gemini-3.8-live-extended-thinking` |
+| `google/gemini-4-argon`                    |
 | `google/gemini-embedding-001`              |
 | `google/gemini-embedding-2`                |
 | `google/gemini-nano-banana-2.1`            |
@@ -194,7 +196,6 @@ ANTHROPIC_API_KEY=ant-...
 | `inclusionai/ling-3.0-flash-sante`         |
 | `inclusionai/ling-3.0-flash-vl`            |
 | `inclusionai/ling-3.1-flash`               |
-| `inclusionai/ling-3.1-flash-free`          |
 | `inference-net/schematron-v2-small`        |
 | `inference-net/schematron-v2-turbo`        |
 | `interfaze/interfaze-beta`                 |
@@ -206,6 +207,7 @@ ANTHROPIC_API_KEY=ant-...
 | `klingai/kling-v3.0-i2v`                   |
 | `klingai/kling-v3.0-motion-control`        |
 | `klingai/kling-v3.0-t2v`                   |
+| `liquid/lfm2.5-24b-a2b`                    |
 | `meituan/longcat-2.5-preview`              |
 | `meta/llama-3.1-70b`                       |
 | `meta/llama-3.1-8b`                        |
@@ -220,6 +222,8 @@ ANTHROPIC_API_KEY=ant-...
 | `meta/muse-spark-1.3`                      |
 | `meta/muse-spark-1.3-contributor`          |
 | `meta/muse-wonder-1.0`                     |
+| `microsoft/mai-image-2.6`                  |
+| `microsoft/mai-image-2.6-flash`            |
 | `microsoft/mai-transcribe-2`               |
 | `microsoft/mai-transcribe-2-streaming`     |
 | `microsoft/mai-voice-2`                    |
@@ -261,6 +265,7 @@ ANTHROPIC_API_KEY=ant-...
 | `nvidia/nemotron-3-super-120b-a12b`        |
 | `nvidia/nemotron-3-ultra-550b-a55b`        |
 | `nvidia/nemotron-3.5-lightning`            |
+| `nvidia/nemotron-3.5-lightning-free`       |
 | `nvidia/nemotron-nano-12b-v2-vl`           |
 | `nvidia/nemotron-nano-9b-v2`               |
 | `openai/gpt-3.5-turbo`                     |

package/.docs/models/index.md

@@ -4,7 +4,7 @@
 
 # Model Providers
 
-Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 7910 models from 215 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 8147 models from 216 providers through a single API.
 
 ## Features
 
@@ -383,6 +383,7 @@ Every provider below works with the model router as `provider/model`. Read the p
 - [AgentRouter](https://mastra.ai/models/providers/agentrouter)
 - [Agnes AI](https://mastra.ai/models/providers/agnes)
 - [AI-ROUTER](https://mastra.ai/models/providers/ai-router)
+- [AI/ML API](https://mastra.ai/models/providers/aimlapi)
 - [ai&](https://mastra.ai/models/providers/aiand)
 - [AI21 Labs](https://mastra.ai/models/providers/ai21)
 - [ainetcafe](https://mastra.ai/models/providers/ainetcafe)