@mastra/mcp-docs-server 1.2.24-alpha.9 → 1.2.25-alpha.1

package/.docs/docs/server/middleware.md

@@ -131,7 +131,11 @@ export const mastra = new Mastra({
 
 ### Authorization (User Isolation)
 
-Authentication verifies who the user is. Authorization controls what they can access. Without resource ID scoping, an authenticated user could access other users' threads by guessing IDs or manipulating the `resourceId` parameter.
+Authentication verifies who the user is, while authorization controls what they can access.
+
+Without server-enforced resource scoping or another authorization policy, authenticated callers can list threads across resources and access their messages and working memory. Callers don't need to guess thread IDs: an unscoped listing can expose them. For private per-user or per-tenant memory, configure `mapUserToResourceId` or set a trusted resource ID in middleware.
+
+Cross-resource access can be intentional in shared applications. A resource ID can identify a user, tenant, project, or another grouping. Choose an authorization policy that matches who can access those resources.
 
 The simplest way to scope memory and threads to the authenticated user is the `mapUserToResourceId` callback in the auth config:
 
@@ -152,10 +156,16 @@ export const mastra = new Mastra({
 
 After successful authentication, `mapUserToResourceId` is called with the authenticated user object. The returned value is set as `MASTRA_RESOURCE_ID_KEY` on the request context, which works across all server adapters (Hono, Express, Next.js, etc.).
 
+When configured, the callback must return a non-empty string. If it throws or returns `null`, `undefined`, an empty or whitespace-only string, or a non-string value, authentication middleware rejects the request with a 500 error before the route runs. This applies to all requests that run authentication, including non-memory routes. A client-provided resource ID can't override a failed mapping.
+
+With `CompositeAuth`, this requirement applies to the provider that authenticated the request. A provider without a mapper keeps its existing behavior, even if another provider in the composite has one. The same validation applies to configured Studio auth mappers.
+
+Without a mapper, authentication doesn't enable user isolation: you're responsible for setting a trusted resource ID in middleware or otherwise enforcing authorization.
+
 The resource ID doesn't have to be `user.id`. Common patterns:
 
 ```typescript
-// Org-scoped
+// Per-user within an organization
 mapUserToResourceId: user => `${user.orgId}:${user.id}`
 
 // From a JWT claim
@@ -167,12 +177,12 @@ mapUserToResourceId: user => `${user.workspaceId}:${user.projectId}:${user.id}`
 
 With a resource ID set, the server automatically:
 
-- **Filters thread listing** to only return threads owned by the user
-- **Validates thread access** and returns 403 if accessing another user's thread
-- **Forces thread creation** to use the authenticated user's ID
-- **Validates message operations** including deletion, ensuring messages belong to owned threads
+- **Filters thread listing** to only return threads in the configured resource scope
+- **Validates thread access** and returns 403 if accessing a thread belonging to a different resource
+- **Forces thread creation** to use the configured resource ID
+- **Validates message operations** including deletion, ensuring messages belong to threads in the configured resource scope
 
-Even if a client passes `?resourceId=other-user-id`, the auth-set value takes precedence. Attempts to access threads or messages owned by other users will return a 403 error.
+Even if a client passes `?resourceId=other-resource-id`, the server-set value takes precedence. Attempts to access threads or messages belonging to a different resource return a 403 error. Users mapped to the same resource ID share that resource scope.
 
 #### Advanced: Setting resource ID in middleware
 

package/.docs/docs/server/pubsub.md

@@ -4,7 +4,7 @@
 
 # PubSub
 
-Mastra uses a publish/subscribe (pub/sub) system as its internal event bus. Components publish events to topics, and other components subscribe to those topics to react. The backend you configure decides how far those events travel: within one process or across processes on one host, or alternatively across separate instances.
+Mastra uses a publish/subscribe (pub/sub) system as its internal event bus. Components publish events to topics, and other components subscribe to those topics to react. The backend determines whether events are delivered within a single process, between processes on one host, or across separate instances.
 
 Set the backend once on the `Mastra` instance for use throughout the system. The default is an in-process backend that requires no setup.
 

package/.docs/docs/server/request-context.md

@@ -259,7 +259,7 @@ Visit [createTool()](https://mastra.ai/reference/tools/create-tool) for a full l
 
 ## Reserved keys
 
-Mastra reserves special context keys for security purposes. When set, these keys take precedence over client-provided values. The server automatically validates ownership and returns 403 errors when users attempt to access resources they don't own.
+Mastra reserves special context keys for the server to read. The resource and thread keys take precedence over client-provided values: the server validates ownership and returns 403 errors when users attempt to access resources they don't own.
 
 The easiest way to set `MASTRA_RESOURCE_ID_KEY` is via the `mapUserToResourceId` callback in auth config:
 
@@ -284,10 +284,11 @@ requestContext.set(MASTRA_RESOURCE_ID_KEY, user.id)
 requestContext.set(MASTRA_THREAD_ID_KEY, threadId)
 ```
 
-| Key                      | Purpose                                                                                                                                          |
-| ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `MASTRA_RESOURCE_ID_KEY` | Forces all memory operations to use this resource ID. The server validates that accessed threads belong to this resource and returns 403 if not. |
-| `MASTRA_THREAD_ID_KEY`   | Forces thread operations to use this thread ID, overriding client-provided values                                                                |
+| Key                         | Purpose                                                                                                                                                                                                                                 |
+| --------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `MASTRA_RESOURCE_ID_KEY`    | Forces all memory operations to use this resource ID. The server validates that accessed threads belong to this resource and returns 403 if not.                                                                                        |
+| `MASTRA_THREAD_ID_KEY`      | Forces thread operations to use this thread ID, overriding client-provided values                                                                                                                                                       |
+| `MASTRA_MESSAGE_AUTHOR_KEY` | Names who sent a user message as `{ id, name?, avatarUrl? }`. Agent-controller sessions copy it onto every message the request sends as `providerMetadata.mastra.author`, so a thread shared by several people can show who wrote what. |
 
 These keys are used to implement user isolation in multi-tenant applications. See [Authorization middleware](https://mastra.ai/docs/server/middleware) for usage examples.
 
@@ -503,6 +504,7 @@ requestContextSchema: z.object({
 
 ## Related
 
+- [Agent lifecycle](https://mastra.ai/docs/guides/agent-lifecycle): Understand when context values become visible during an agent run
 - [Agent Request Context](https://mastra.ai/docs/memory/overview)
 - [Workflow Request Context](https://mastra.ai/docs/workflows/overview)
 - [Server Middleware](https://mastra.ai/docs/server/middleware)

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

@@ -67,7 +67,7 @@ Use [Agent Builder](https://agent-builder.mastra.ai) to create and manage fully
 
 Visualize your workflow as a graph and run it step by step with a custom input. During execution, the interface updates in real time to show the active step and the path taken.
 
-When running a workflow, you can also view detailed traces showing tool calls and raw JSON outputs, plus any errors that might have occurred along the way.
+Workflow traces show tool calls and raw JSON outputs, along with any execution errors.
 
 ### Processors
 

package/.docs/docs/workflows/control-flow.md

@@ -332,8 +332,6 @@ export const testWorkflow = createWorkflow({
 
 When using `.then()`, `.parallel()`, or `.branch()`, it's sometimes necessary to transform the output of a previous step to match the input of the next. In these cases you can use `.map()` to access the `inputData` and transform it to create a suitable data shape for the next step.
 
-![Mapping with .map()](/assets/images/workflows-data-mapping-map-87fd84a06b4bbf4b93868a5db99ca179.jpg)
-
 ```typescript
 const step1 = createStep({...});
 const step2 = createStep({...});
@@ -439,8 +437,6 @@ Workflows support different looping methods that let you repeat steps until or w
 
 Use `.dountil()` to run a step repeatedly until a condition becomes true.
 
-![Repeating with .dountil()](/assets/images/workflows-control-flow-dountil-6b7b06e872f3bd878f69c716b0e38ae6.jpg)
-
 ```typescript
 const step1 = createStep({...});
 
@@ -463,8 +459,6 @@ export const testWorkflow = createWorkflow({})
 
 Use `.dowhile()` to run a step repeatedly while a condition remains true.
 
-![Repeating with .dowhile()](/assets/images/workflows-control-flow-dowhile-09bba2d43fb44352f458c144484326ed.jpg)
-
 ```typescript
 const step1 = createStep({...});
 
@@ -487,8 +481,6 @@ export const testWorkflow = createWorkflow({})
 
 Use `.foreach()` to run the same step for each item in an array. The input must be of type `array` so the loop can iterate over its values, applying the step's logic to each one. See [Choosing the right pattern](#choosing-the-right-pattern) for guidance on when to use `.foreach()` vs other methods.
 
-![Repeating with .foreach()](/assets/images/workflows-control-flow-foreach-a5b6f38d8797c4d1b7dca93879d709f7.jpg)
-
 ```typescript
 const step1 = createStep({
   inputSchema: z.string(),

package/.docs/integrations/browsers/browser-viewer.md

@@ -95,7 +95,13 @@ export const mastra = new Mastra({
 })
 ```
 
-When the agent runs a CLI command like `browser-use open https://example.com`, Mastra automatically launches Chrome and injects the CDP connection, plus starts streaming the screencast to Studio.
+When the agent runs a browser CLI command, Mastra automatically launches Chrome, passes the CDP connection to the CLI, and starts streaming the screencast to Studio. For Browser Use, the agent can pass Python through stdin:
+
+```bash
+browser-use <<'PY'
+print("Connected to the managed browser")
+PY
+```
 
 ## How it works
 
@@ -133,7 +139,9 @@ pip install browser-use
 npx skills add browser-use/browser-use --skill browser-use
 ```
 
-CDP flag: `--cdp-url`
+For direct stdin invocations (`browser-use`, `browseruse`, `browser`, or `bu`, optionally followed by `<` redirection or a heredoc), Mastra sets `BU_CDP_WS` to the managed browser's CDP URL and `BU_NAME` to a stable daemon name. The name is unique to the thread and browser endpoint, so repeated calls reuse the same daemon while different threads or endpoints stay isolated. Mastra preserves the stdin script without adding CLI arguments.
+
+Legacy subcommands retain `--cdp-url` and `--session` injection for compatibility. These flags aren't added to stdin invocations.
 
 ### `browse`
 

package/.docs/integrations/deploy/kubernetes-helm.md

@@ -72,10 +72,13 @@ You'll need:
    kubectl create secret generic mastra-app-env -n mastra \
      --from-literal=DATABASE_URL='postgresql://user:pass@host:5432/mastra' \
      --from-literal=MASTRA_EE_LICENSE='<your-license-key>' \
-     --from-literal=OPENAI_API_KEY='<provider-key>'
+     --from-literal=OPENAI_API_KEY='<provider-key>' \
+     --from-literal=CLICKHOUSE_URL='https://your-instance.clickhouse.cloud:8443' \
+     --from-literal=CLICKHOUSE_USERNAME='<clickhouse-username>' \
+     --from-literal=CLICKHOUSE_PASSWORD='<clickhouse-password>'
    ```
 
-   Include any other environment variables your agents need, such as model provider API keys.
+   Include any other environment variables your agents need, such as model provider API keys. Omit the `CLICKHOUSE_*` variables unless you use ClickHouse for observability.
 
 3. Create a values file pointing the chart at your image and secret:
 
@@ -259,6 +262,14 @@ mastra-server:
 
 Put `S3_ACCESS_KEY_ID` and `S3_SECRET_ACCESS_KEY` in your existing Secret rather than in values. On EKS and GKE, prefer IRSA or Workload Identity over static keys.
 
+## ClickHouse observability
+
+To persist traces, logs, metrics, scores, and feedback in ClickHouse, add `CLICKHOUSE_URL`, `CLICKHOUSE_USERNAME`, and `CLICKHOUSE_PASSWORD` to the Secret that `mastra-server.existingSecret` references. The Secret example above includes those variables for ClickHouse Cloud.
+
+The chart makes the variables available to your application. It doesn't configure observability or send telemetry by itself. Configure `ObservabilityStorageClickhouseVNext` for the `observability` storage domain and add `MastraStorageExporter` to your Mastra application. See [ClickHouse](https://mastra.ai/integrations/databases/clickhouse) for the complete application configuration.
+
+When you enable `mastra-workers`, worker pods mount the Server's Secret. If you install the `mastra-workers` chart separately, set `mastra-workers.server.existingSecret` to the same Secret name. The `mastra-projects` chart verifies that the names match.
+
 ## Scale server replicas
 
 The chart starts one Server replica by default. A HorizontalPodAutoscaler can add pods, but it doesn't make Mastra's in-process state available across them.

package/.docs/integrations/frameworks/tanstack-start.md

@@ -53,13 +53,13 @@ You'll pass the Mastra instance exported from `src/mastra/index.ts` to the serve
 
 ## Configure Vite and Nitro
 
-Update `vite.config.ts` so Vite and Nitro leave DuckDB's native dependencies out of their processing pipelines:
+Update `vite.config.ts` so Vite and Nitro leave DuckDB's and `@mastra/core`'s Node-only dependencies out of their processing pipelines:
 
 ```diff
 const config = defineConfig({
    resolve: { tsconfigPaths: true },
 +  optimizeDeps: {
-+    exclude: ['@mastra/duckdb'],
++    exclude: ['@mastra/duckdb', 'execa'],
 +  },
    plugins: [
      devtools(),
@@ -71,7 +71,7 @@ const config = defineConfig({
 +    }),
 ```
 
-The `optimizeDeps.exclude` setting prevents Vite's development optimizer from opening DuckDB's native `.node` binary as JavaScript. Adding `/^@duckdb\//` to Nitro's `rollupConfig.external` keeps DuckDB's native Node packages out of the production bundle so Node.js can load them at runtime.
+The `optimizeDeps.exclude` setting prevents Vite's development optimizer from opening DuckDB's native `.node` binary as JavaScript. Excluding `execa` stops the optimizer from pre-bundling the server-only dependency `@mastra/core` uses for local process execution; its transitive `npm-run-path` and `unicorn-magic` packages use Node-only conditional exports that the optimizer cannot resolve in the browser build. Adding `/^@duckdb\//` to Nitro's `rollupConfig.external` keeps DuckDB's native Node packages out of the production bundle so Node.js can load them at runtime.
 
 These changes apply only to `vite.config.ts`; you don't need to change your application or Mastra source files.
 

package/.docs/integrations/observability/langfuse.md

@@ -216,10 +216,13 @@ const tracingOptions = {
 
 This example produces `langfuse.trace.metadata.customerId` and `langfuse.trace.metadata.tier`.
 
+Metadata on the root span is also forwarded. Mastra sets `runId` and `resourceId` on every agent and workflow root span, and you can add your own keys through `tracingOptions.metadata`. The exporter forwards each of these root span keys to `langfuse.trace.metadata.<key>`. Keys that map to a dedicated Langfuse field (`userId`, `sessionId`, `threadId`, `traceName`, and `version`) are not duplicated as trace metadata. Metadata on child spans stays on the observation and never changes the trace.
+
 Notes:
 
 - The reserved `prompt` key is used for [prompt linking](#prompt-linking) and isn't forwarded as trace metadata.
 - The reserved identity keys `agentId`, `agentName`, `workflowId`, and `workflowName` are set from the root span and take precedence over custom values with the same name.
+- Keys under `langfuse` take precedence over root span metadata with the same name.
 - Values are sent as strings, because Langfuse maps trace metadata attributes as strings. Numbers, booleans, and objects are serialized with JSON. Langfuse Cloud restores them to their original types on ingestion.
 
 ## Prompt linking

package/.docs/integrations/tools/parallel.md

@@ -4,7 +4,7 @@
 
 # Parallel
 
-The `@mastra/parallel` package exposes [Parallel Search](https://docs.parallel.ai/search/search-quickstart) and [Extract](https://docs.parallel.ai/search/extract-quickstart) as Mastra-compatible tools. Each factory returns a tool created with [`createTool()`](https://mastra.ai/reference/tools/create-tool) and a typed Zod input and output schema.
+The `@mastra/parallel` package exposes [Parallel Search](https://docs.parallel.ai/search/search-quickstart) and [Extract](https://docs.parallel.ai/extract/extract-quickstart) as Mastra-compatible tools. Each factory returns a tool created with [`createTool()`](https://mastra.ai/reference/tools/create-tool) and a typed Zod input and output schema.
 
 ## Installation
 
@@ -238,5 +238,5 @@ export const researchAgent = new Agent({
 ## Related
 
 - [Parallel Search documentation](https://docs.parallel.ai/search/search-quickstart)
-- [Parallel Extract documentation](https://docs.parallel.ai/search/extract-quickstart)
+- [Parallel Extract documentation](https://docs.parallel.ai/extract/extract-quickstart)
 - [`createTool()` reference](https://mastra.ai/reference/tools/create-tool)

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 180 models through Mastra's model router.
+Merge Gateway aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 181 models through Mastra's model router.
 
 Learn more in the [Merge Gateway documentation](https://docs.merge.dev/merge-gateway).
 
@@ -95,6 +95,7 @@ ANTHROPIC_API_KEY=ant-...
 | `google/gemini-flash-lite-latest`                |
 | `google/gemma-4-26b-a4b-it`                      |
 | `google/gemma-4-31b-it`                          |
+| `meta/llama-3.1-70b-instruct`                    |
 | `meta/llama-3.1-8b-instruct`                     |
 | `meta/llama-3.3-70b-instruct`                    |
 | `meta/muse-spark-1.1`                            |

package/.docs/models/gateways/neon.md

@@ -4,7 +4,7 @@
 
 # ![Neon logo](https://models.dev/logos/neon.svg)Neon
 
-Neon aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 42 models through Mastra's model router.
+Neon aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 46 models through Mastra's model router.
 
 Learn more in the [Neon documentation](https://neon.com/docs).
 
@@ -36,6 +36,7 @@ NEON_AI_GATEWAY_TOKEN=your-gateway-key
 | Model                         |
 | ----------------------------- |
 | `claude-fable-5`              |
+| `claude-fable-5-1`            |
 | `claude-haiku-4-5`            |
 | `claude-opus-4-1`             |
 | `claude-opus-4-5`             |
@@ -54,6 +55,7 @@ NEON_AI_GATEWAY_TOKEN=your-gateway-key
 | `gemini-3-flash`              |
 | `gemma-3-12b`                 |
 | `glm-5-2`                     |
+| `glm-5-3-flash`               |
 | `gpt-5`                       |
 | `gpt-5-1`                     |
 | `gpt-5-2`                     |
@@ -68,8 +70,10 @@ NEON_AI_GATEWAY_TOKEN=your-gateway-key
 | `gpt-5-6-terra`               |
 | `gpt-5-mini`                  |
 | `gpt-5-nano`                  |
+| `gpt-6-astra`                 |
 | `gpt-oss-120b`                |
 | `gpt-oss-20b`                 |
+| `grok-4-6`                    |
 | `inkling`                     |
 | `kimi-k3`                     |
 | `llama-4-maverick`            |

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 243 models through Mastra's model router.
+Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 242 models through Mastra's model router.
 
 Learn more in the [Netlify documentation](https://docs.netlify.com/build/ai-gateway/overview/).
 
@@ -147,7 +147,7 @@ ANTHROPIC_API_KEY=ant-...
 | `openrouter/gryphe/mythomax-l2-13b`                                   |
 | `openrouter/ibm-granite/granite-4.2-8b`                               |
 | `openrouter/inception/mercury-2`                                      |
-| `openrouter/inception/mercury-2.5-preview`                            |
+| `openrouter/inception/mercury-2.5`                                    |
 | `openrouter/inclusionai/ling-3.0-flash`                               |
 | `openrouter/inclusionai/ling-3.0-flash-fin`                           |
 | `openrouter/inclusionai/ling-3.0-flash-fin:free`                      |
@@ -279,6 +279,5 @@ ANTHROPIC_API_KEY=ant-...
 | `openrouter/z-ai/glm-5`                                               |
 | `openrouter/z-ai/glm-5.1`                                             |
 | `openrouter/z-ai/glm-5.2`                                             |
-| `openrouter/z-ai/glm-5.2:free`                                        |
 | `openrouter/z-ai/glm-5.3`                                             |
 | `openrouter/z-ai/glm-5.3-flash`                                       |

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 361 models through Mastra's model router.
+OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 358 models through Mastra's model router.
 
 Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
 
@@ -141,7 +141,7 @@ ANTHROPIC_API_KEY=ant-...
 | `ibm-granite/granite-4.0-h-micro`                          |
 | `ibm-granite/granite-4.2-8b`                               |
 | `inception/mercury-2`                                      |
-| `inception/mercury-2.5-preview`                            |
+| `inception/mercury-2.5`                                    |
 | `inclusionai/ling-3.0-flash`                               |
 | `inclusionai/ling-3.0-flash-fin`                           |
 | `inclusionai/ling-3.0-flash-fin:free`                      |
@@ -174,9 +174,7 @@ ANTHROPIC_API_KEY=ant-...
 | `minimax/minimax-m2.1`                                     |
 | `minimax/minimax-m2.5`                                     |
 | `minimax/minimax-m2.7`                                     |
-| `minimax/minimax-m2.7:free`                                |
 | `minimax/minimax-m3`                                       |
-| `minimax/minimax-m3:free`                                  |
 | `mistralai/codestral-2508`                                 |
 | `mistralai/devstral-2512`                                  |
 | `mistralai/ministral-14b-2512`                             |
@@ -205,8 +203,8 @@ ANTHROPIC_API_KEY=ant-...
 | `moonshotai/kimi-k3`                                       |
 | `morph/morph-v3-fast`                                      |
 | `morph/morph-v3-large`                                     |
-| `nex-agi/nex-n2-mini`                                      |
-| `nex-agi/nex-n2-pro`                                       |
+| `nex-agi/nex-n2.5-mini:free`                               |
+| `nex-agi/nex-n2.5-pro:free`                                |
 | `nousresearch/hermes-3-llama-3.1-405b`                     |
 | `nousresearch/hermes-3-llama-3.1-70b`                      |
 | `nousresearch/hermes-4-405b`                               |
@@ -346,7 +344,7 @@ ANTHROPIC_API_KEY=ant-...
 | `qwen/qwen3.8-2.4t-a95b`                                   |
 | `qwen/qwen3.8-27b`                                         |
 | `qwen/qwen3.8-flash`                                       |
-| `qwen/qwen3.8-max`                                         |
+| `qwen/qwen3.8-max-0902`                                    |
 | `rekaai/reka-edge`                                         |
 | `rekaai/reka-flash-3`                                      |
 | `relace/relace-apply-3`                                    |
@@ -395,7 +393,6 @@ ANTHROPIC_API_KEY=ant-...
 | `z-ai/glm-5-turbo`                                         |
 | `z-ai/glm-5.1`                                             |
 | `z-ai/glm-5.2`                                             |
-| `z-ai/glm-5.2:free`                                        |
 | `z-ai/glm-5.3`                                             |
 | `z-ai/glm-5.3-flash`                                       |
 | `z-ai/glm-5v-turbo`                                        |

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

@@ -143,6 +143,7 @@ ANTHROPIC_API_KEY=ant-...
 | `deepseek/deepseek-v4-flash-vision-exp`   |
 | `deepseek/deepseek-v4-pro`                |
 | `deepseek/deepseek-v4-pro-0813`           |
+| `deepseek/deepseek-v4.1-flash-beta`       |
 | `fish-audio/s1`                           |
 | `fish-audio/s1-free`                      |
 | `fish-audio/s2-pro`                       |
@@ -182,6 +183,7 @@ ANTHROPIC_API_KEY=ant-...
 | `google/veo-3.1-generate-001`             |
 | `google/veo-3.1-lite-generate-001`        |
 | `inception/mercury-2`                     |
+| `inception/mercury-2.5`                   |
 | `inception/mercury-coder-small`           |
 | `inclusionai/ling-3.0-flash`              |
 | `inclusionai/ling-3.0-flash-fin`          |
@@ -221,10 +223,8 @@ ANTHROPIC_API_KEY=ant-...
 | `minimax/minimax-m2.5`                    |
 | `minimax/minimax-m2.5-highspeed`          |
 | `minimax/minimax-m2.7`                    |
-| `minimax/minimax-m2.7-free`               |
 | `minimax/minimax-m2.7-highspeed`          |
 | `minimax/minimax-m3`                      |
-| `minimax/minimax-m3-free`                 |
 | `mistral/codestral`                       |
 | `mistral/codestral-embed`                 |
 | `mistral/devstral-2`                      |
@@ -308,6 +308,8 @@ ANTHROPIC_API_KEY=ant-...
 | `openai/gpt-image-1-mini`                 |
 | `openai/gpt-image-1.5`                    |
 | `openai/gpt-image-2`                      |
+| `openai/gpt-image-2.5-flare`              |
+| `openai/gpt-image-2.5-sunburst`           |
 | `openai/gpt-oss-120b`                     |
 | `openai/gpt-oss-20b`                      |
 | `openai/gpt-oss-safeguard-120b`           |
@@ -393,7 +395,6 @@ ANTHROPIC_API_KEY=ant-...
 | `voyage/voyage-law-2`                     |
 | `xiaomi/mimo-v2.5`                        |
 | `xiaomi/mimo-v2.5-pro`                    |
-| `xiaomi/mimo-v2.5-pro-ultraspeed`         |
 | `zai/glm-4.5`                             |
 | `zai/glm-4.5-air`                         |
 | `zai/glm-4.5v`                            |
@@ -409,5 +410,4 @@ ANTHROPIC_API_KEY=ant-...
 | `zai/glm-5.3`                             |
 | `zai/glm-5.3-fast`                        |
 | `zai/glm-5.3-flash`                       |
-| `zai/glm-5.3-promo-50`                    |
 | `zai/glm-5v-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 7096 models from 200 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 7122 models from 200 providers through a single API.
 
 ## Features