@mastra/mcp-docs-server 1.1.26-alpha.1 → 1.1.26-alpha.4

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

@@ -333,13 +333,29 @@ Reflection works similarly — the Reflector runs in the background when observa
 
 ### Settings
 
-| Setting                        | Default | What it controls                                                                                                                                                                      |
-| ------------------------------ | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `observation.bufferTokens`     | `0.2`   | How often to buffer. `0.2` means every 20% of `messageTokens` — with the default 30k threshold, that's roughly every 6k tokens. Can also be an absolute token count (e.g. `5000`).    |
-| `observation.bufferActivation` | `0.8`   | How aggressively to clear the message window on activation. `0.8` means remove enough messages to keep only 20% of `messageTokens` remaining. Lower values keep more message history. |
-| `observation.blockAfter`       | `1.2`   | Safety threshold as a multiplier of `messageTokens`. At `1.2`, synchronous observation is forced at 36k tokens (1.2 × 30k). Only matters if buffering can't keep up.                  |
-| `reflection.bufferActivation`  | `0.5`   | When to start background reflection. `0.5` means reflection begins when observations reach 50% of the `observationTokens` threshold.                                                  |
-| `reflection.blockAfter`        | `1.2`   | Safety threshold for reflection, same logic as observation.                                                                                                                           |
+| Setting                        | Default | What it controls                                                                                                                                                                                                                                                                                                                       |
+| ------------------------------ | ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `observation.bufferTokens`     | `0.2`   | How often to buffer. `0.2` means every 20% of `messageTokens` — with the default 30k threshold, that's roughly every 6k tokens. Can also be an absolute token count (e.g. `5000`).                                                                                                                                                     |
+| `observation.bufferActivation` | `0.8`   | How aggressively to clear the message window on activation. `0.8` means remove enough messages to keep only 20% of `messageTokens` remaining. Lower values keep more message history.                                                                                                                                                  |
+| `observation.blockAfter`       | `1.2`   | Safety threshold as a multiplier of `messageTokens`. At `1.2`, synchronous observation is forced at 36k tokens (1.2 × 30k). Only matters if buffering can't keep up.                                                                                                                                                                   |
+| `activateAfterIdle`            | none    | Forces buffered observations and buffered reflections to activate after a period of inactivity, even if their token thresholds have not been reached yet. Accepts milliseconds or duration strings like `300_000`, `"5m"`, or `"1hr"`. Set this to your prompt cache TTL if you want activation to happen before the next cold prompt. |
+| `reflection.bufferActivation`  | `0.5`   | When to start background reflection. `0.5` means reflection begins when observations reach 50% of the `observationTokens` threshold.                                                                                                                                                                                                   |
+| `reflection.blockAfter`        | `1.2`   | Safety threshold for reflection, same logic as observation.                                                                                                                                                                                                                                                                            |
+
+If you're relying on prompt caching, set `activateAfterIdle` to match your cache TTL. That way, once a thread has been idle long enough for the cache to expire, the next request can activate buffered observations or reflections first and send a smaller compressed context window.
+
+```typescript
+const memory = new Memory({
+  options: {
+    observationalMemory: {
+      model: 'google/gemini-2.5-flash',
+      activateAfterIdle: '5m',
+    },
+  },
+})
+```
+
+With a 5-minute prompt cache TTL, this activates buffered context after 5 minutes of inactivity so the next uncached prompt uses observations and reflections instead of a larger raw message window. If you prefer, `300_000` works the same way.
 
 ### Disabling
 

package/.docs/docs/observability/tracing/exporters/cloud.md

@@ -2,6 +2,12 @@
 
 The `CloudExporter` sends traces, logs, metrics, scores, and feedback to the Mastra platform. Use it to route observability data from any Mastra app to a hosted project in the Mastra platform.
 
+## Version compatibility
+
+- Use `CloudExporter` with `@mastra/observability@1.8.0` or later.
+- If you use `@mastra/observability@1.8.0` through `1.9.1`, set `MASTRA_CLOUD_TRACES_ENDPOINT=https://observability.mastra.ai` in addition to `MASTRA_CLOUD_ACCESS_TOKEN` and `MASTRA_PROJECT_ID`.
+- Starting in `@mastra/observability@1.9.2`, `CloudExporter` defaults to `https://observability.mastra.ai`, so `MASTRA_CLOUD_TRACES_ENDPOINT` is only required when you want to send telemetry to a different collector.
+
 ## Quickstart
 
 To connect `CloudExporter`, create an access token, find the destination `projectId`, and add the exporter to your observability config.
@@ -57,52 +63,30 @@ MASTRA_PROJECT_ID=<your-project-id>
 
 ### 3. Set your environment variables
 
-Tokens created with `mastra auth tokens create` are organization-scoped, so `MASTRA_PROJECT_ID` is required.
-
-If you use a project-scoped token from the Mastra platform instead, `CloudExporter` can route without `projectId`, but setting it explicitly is still supported.
-
-Add both values to your environment:
+Set both values in your environment so `CloudExporter` can authenticate and route telemetry to the correct project:
 
 ```bash
 MASTRA_CLOUD_ACCESS_TOKEN=<your-cloud-access-token>
 MASTRA_PROJECT_ID=<your-project-id>
 ```
 
-For example:
+If you use `@mastra/observability@1.8.0` through `1.9.1`, also set the Mastra platform collector explicitly:
 
 ```bash
-MASTRA_CLOUD_ACCESS_TOKEN=<your-cloud-access-token>
-MASTRA_PROJECT_ID=<your-project-id>
+MASTRA_CLOUD_TRACES_ENDPOINT=https://observability.mastra.ai
 ```
 
-### 4. Enable `CloudExporter`
-
-The following example demonstrates how to add `CloudExporter` to your observability config:
-
-```ts
-import { Mastra } from '@mastra/core'
-import { Observability, CloudExporter } from '@mastra/observability'
+If you want to send telemetry somewhere other than Mastra platform, set `MASTRA_CLOUD_TRACES_ENDPOINT` as well. Pass either a base origin or a full traces publish URL ending in `/spans/publish`.
 
-export const mastra = new Mastra({
-  observability: new Observability({
-    configs: {
-      production: {
-        serviceName: 'my-service',
-        exporters: [
-          new CloudExporter({
-            accessToken: process.env.MASTRA_CLOUD_ACCESS_TOKEN,
-            projectId: process.env.MASTRA_PROJECT_ID,
-          }),
-        ],
-      },
-    },
-  }),
-})
+```bash
+MASTRA_CLOUD_TRACES_ENDPOINT=https://collector.example.com
 ```
 
-Set `serviceName` in code on the observability config, not on `CloudExporter` itself. In the example above, the value is `configs.production.serviceName`.
+When you pass a base origin, `CloudExporter` derives the matching publish URLs for traces, logs, metrics, scores, and feedback automatically.
 
-For example:
+### 4. Enable `CloudExporter`
+
+The following example demonstrates how to add `CloudExporter` to your observability config:
 
 ```ts
 import { Mastra } from '@mastra/core'
@@ -120,6 +104,8 @@ export const mastra = new Mastra({
 })
 ```
 
+Set `serviceName` on the observability config, not on `CloudExporter` itself.
+
 Use a stable `serviceName` value. In Studio, traces can be filtered by **Deployments → Service Name**, so a consistent name makes traces easier to find.
 
 Visit [Observability configuration reference](https://mastra.ai/reference/observability/tracing/configuration) for the full observability config shape.
@@ -130,7 +116,7 @@ If you prefer, rely entirely on environment variables:
 new CloudExporter()
 ```
 
-With `MASTRA_CLOUD_ACCESS_TOKEN` and `MASTRA_PROJECT_ID` set, `CloudExporter` automatically sends data to the correct Mastra platform project.
+With `MASTRA_CLOUD_ACCESS_TOKEN` and `MASTRA_PROJECT_ID` set, `CloudExporter` sends data to the Mastra platform project you configured. If you also set `MASTRA_CLOUD_TRACES_ENDPOINT`, it sends data to that collector instead.
 
 > **Note:** Visit [CloudExporter reference](https://mastra.ai/reference/observability/tracing/exporters/cloud-exporter) for the full list of configuration options.
 
@@ -162,13 +148,17 @@ export const mastra = new Mastra({
 
 ## Complete configuration
 
-The following example demonstrates how to configure custom endpoints and batching behavior:
+`CloudExporter` defaults to Mastra platform. If you want to send telemetry to a different collector, set `MASTRA_CLOUD_TRACES_ENDPOINT` in your environment or pass `endpoint` in code.
+
+```bash
+MASTRA_CLOUD_TRACES_ENDPOINT=https://collector.example.com
+```
+
+The following example demonstrates how to override the collector endpoint and batching behavior in code:
 
 ```ts
 new CloudExporter({
-  accessToken: process.env.MASTRA_CLOUD_ACCESS_TOKEN,
-  projectId: process.env.MASTRA_PROJECT_ID,
-  endpoint: 'https://cloud.your-domain.com',
+  endpoint: 'https://collector.example.com',
   maxBatchSize: 1000,
   maxBatchWaitMs: 5000,
   logLevel: 'info',
@@ -179,13 +169,10 @@ new CloudExporter({
 
 After you enable `CloudExporter`, open your project in [Mastra Studio](https://projects.mastra.ai) to inspect the exported data.
 
-- Open your project and select **Open Studio**.
+- Open the project you set `MASTRA_PROJECT_ID` to and select **Open Studio**.
 - In Studio, go to **Traces** to inspect agent and workflow traces.
 - Open the filter menu and use **Deployments → Service Name** to isolate traces from a specific app or deployment.
 - Use the **Logs** page in the project dashboard to inspect exported logs.
-- Use the project named by `MASTRA_PROJECT_ID` when you work with organization-scoped tokens.
-
-> **Note:** If you use a project-scoped token, open the project that issued the token. If you use an organization-scoped token, open the project named by `MASTRA_PROJECT_ID`.
 
 When you deploy with Mastra Studio, set **Deployment → Service Name** to a stable value and keep it aligned with the `serviceName` in your observability config. This makes traces easier to filter in Studio through **Deployments → Service Name** when multiple services or deployments send data to the same project.
 

package/.docs/guides/build-your-ui/ai-sdk-ui.md

@@ -242,7 +242,7 @@ Use [`prepareSendMessagesRequest`](https://ai-sdk.dev/docs/reference/ai-sdk-ui/u
 
 When your agent has [memory](https://mastra.ai/docs/memory/overview) configured, Mastra loads conversation history from storage on the server. Send only the new message from the client instead of the full conversation history.
 
-Sending the full history is redundant and can cause message ordering bugs because client-side timestamps can conflict with the timestamps stored in your database.
+Sending the full history is redundant and can cause message-ordering bugs because client-side timestamps can conflict with the timestamps stored in your database.
 
 ```typescript
 import { useChat } from '@ai-sdk/react'
@@ -392,7 +392,8 @@ Mastra streams data to the frontend as "parts" within messages. Each part has a
 | Data Part Type       | Source                  | Description                                                                        |
 | -------------------- | ----------------------- | ---------------------------------------------------------------------------------- |
 | `tool-{toolKey}`     | AI SDK built-in         | Tool invocation with states: `input-available`, `output-available`, `output-error` |
-| `data-workflow`      | `workflowRoute()`       | Workflow execution with step inputs, outputs, and status                           |
+| `data-workflow`      | `workflowRoute()`       | Workflow execution state snapshots with step status and final outputs              |
+| `data-workflow-step` | `workflowRoute()`       | Workflow step delta with the full payload for the step that just changed           |
 | `data-network`       | `networkRoute()`        | Agent network execution with ordered steps and outputs                             |
 | `data-tool-agent`    | Nested agent in tool    | Agent output streamed from within a tool's `execute()`                             |
 | `data-tool-workflow` | Nested workflow in tool | Workflow output streamed from within a tool's `execute()`                          |
@@ -505,11 +506,11 @@ export function Chat() {
 
 ### Rendering workflow data
 
-When using `workflowRoute()` or `handleWorkflowStream()`, Mastra emits `data-workflow` parts that contain the workflow's execution state, including step statuses and outputs.
+When using `workflowRoute()` or `handleWorkflowStream()`, Mastra emits `data-workflow` parts for workflow state snapshots and `data-workflow-step` parts for the full payload of the step that just changed. This keeps long-running workflows from repeating every completed step output in every intermediate snapshot.
 
 **Backend**:
 
-Define a workflow with multiple steps that will emit `data-workflow` parts as it executes.
+Define a workflow with multiple steps that will emit `data-workflow` and `data-workflow-step` parts as it executes.
 
 ```typescript
 import { createStep, createWorkflow } from '@mastra/core/workflows'
@@ -584,14 +585,15 @@ export const mastra = new Mastra({
 
 **Frontend**:
 
-Check for `data-workflow` parts and render each step's status and output using the `WorkflowDataPart` type for type safety.
+Check for `data-workflow` parts to render workflow status snapshots. If you need the full payload for the step that just changed, also read `data-workflow-step` parts.
 
 ```typescript
 import { useChat } from '@ai-sdk/react'
 import { DefaultChatTransport } from 'ai'
-import type { WorkflowDataPart } from '@mastra/ai-sdk'
+import type { WorkflowDataPart, WorkflowStepDataPart } from '@mastra/ai-sdk'
 
 type WorkflowData = WorkflowDataPart['data']
+type WorkflowStepData = WorkflowStepDataPart['data']
 type StepStatus = 'running' | 'success' | 'failed' | 'suspended' | 'waiting'
 
 function StepIndicator({
@@ -652,6 +654,17 @@ export function WorkflowChat() {
                 </div>
               )
             }
+            if (part.type === 'data-workflow-step') {
+              const stepData = part.data as WorkflowStepData
+              return (
+                <StepIndicator
+                  key={index}
+                  name={stepData.step.name}
+                  status={stepData.step.status}
+                  output={stepData.step.output}
+                />
+              )
+            }
             return null
           })}
         </div>

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 3596 models from 99 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3592 models from 99 providers through a single API.
 
 ## Features
 

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

@@ -1,6 +1,6 @@
 # ![OpenCode Go logo](https://models.dev/logos/opencode-go.svg)OpenCode Go
 
-Access 9 OpenCode Go models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
+Access 7 OpenCode Go models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
 
 Learn more in the [OpenCode Go documentation](https://opencode.ai/docs/zen).
 
@@ -41,8 +41,6 @@ for await (const chunk of stream) {
 | `opencode-go/mimo-v2-pro`  | 1.0M    |       |           |       |       |       | $1         | $3          |
 | `opencode-go/minimax-m2.5` | 205K    |       |           |       |       |       | $0.30      | $1          |
 | `opencode-go/minimax-m2.7` | 205K    |       |           |       |       |       | $0.30      | $1          |
-| `opencode-go/qwen3.5-plus` | 262K    |       |           |       |       |       | $0.20      | $1          |
-| `opencode-go/qwen3.6-plus` | 262K    |       |           |       |       |       | $0.50      | $3          |
 
 ## Advanced configuration
 
@@ -72,7 +70,7 @@ const agent = new Agent({
   model: ({ requestContext }) => {
     const useAdvanced = requestContext.task === "complex";
     return useAdvanced
-      ? "opencode-go/qwen3.6-plus"
+      ? "opencode-go/minimax-m2.7"
       : "opencode-go/glm-5";
   }
 });

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

@@ -1,6 +1,6 @@
 # ![OpenCode Zen logo](https://models.dev/logos/opencode.svg)OpenCode Zen
 
-Access 34 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
+Access 32 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
 
 Learn more in the [OpenCode Zen documentation](https://opencode.ai/docs/zen).
 
@@ -66,8 +66,6 @@ for await (const chunk of stream) {
 | `opencode/minimax-m2.5`          | 205K    |       |           |       |       |       | $0.30      | $1          |
 | `opencode/minimax-m2.5-free`     | 205K    |       |           |       |       |       | —          | —           |
 | `opencode/nemotron-3-super-free` | 205K    |       |           |       |       |       | —          | —           |
-| `opencode/qwen3.5-plus`          | 262K    |       |           |       |       |       | $0.20      | $1          |
-| `opencode/qwen3.6-plus`          | 262K    |       |           |       |       |       | $0.50      | $3          |
 
 ## Advanced configuration
 
@@ -97,7 +95,7 @@ const agent = new Agent({
   model: ({ requestContext }) => {
     const useAdvanced = requestContext.task === "complex";
     return useAdvanced
-      ? "opencode/qwen3.6-plus"
+      ? "opencode/nemotron-3-super-free"
       : "opencode/big-pickle";
   }
 });

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

@@ -36,6 +36,8 @@ OM performs thresholding with fast local token estimation. Text uses `tokenx`, a
 
 **scope** (`'resource' | 'thread'`): Memory scope for observations. \`'thread'\` keeps observations per-thread. \`'resource'\` (experimental) shares observations across all threads for a resource, enabling cross-conversation memory. (Default: `'thread'`)
 
+**activateAfterIdle** (`number | string`): Time before buffered observations or buffered reflections are forced to activate after inactivity, even if their token thresholds have not been reached yet. Accepts milliseconds or duration strings like \`300\_000\`, \`"5m"\`, or \`"1hr"\`. When the gap between the current time and the last assistant message part timestamp exceeds this value, buffered observational memory activates before the next prompt. Useful for aligning with prompt cache TTLs.
+
 **shareTokenBudget** (`boolean`): Share the token budget between messages and observations. When enabled, the total budget is \`observation.messageTokens + reflection.observationTokens\`. Messages can use more space when observations are small, and vice versa. This maximizes context usage through flexible allocation. \`shareTokenBudget\` is not yet compatible with async buffering. You must set \`observation: { bufferTokens: false }\` when using this option (this is a temporary limitation). (Default: `false`)
 
 **retrieval** (`boolean | { vector?: boolean; scope?: 'thread' | 'resource' }`): \*\*Experimental.\*\* Enable retrieval-mode observation groups as durable pointers to raw message history. \`true\` enables cross-thread browsing by default. \`{ vector: true }\` also enables semantic search using Memory's vector store and embedder. \`{ scope: 'thread' }\` restricts the recall tool to the current thread only. Default scope is \`'resource'\`. (Default: `false`)

package/.docs/reference/observability/tracing/exporters/cloud-exporter.md

@@ -1,5 +1,7 @@
 # CloudExporter
 
+**Added in:** `@mastra/observability@1.8.0`
+
 Sends tracing spans, logs, metrics, scores, and feedback to the Mastra platform for online visualization and monitoring.
 
 ## Constructor
@@ -56,9 +58,9 @@ Extends `BaseExporterConfig`, which includes:
 
 The exporter reads these environment variables if not provided in config:
 
-- `MASTRA_CLOUD_ACCESS_TOKEN` - Authentication token. Project-scoped tokens work with the default `/ai/{signal}/publish` routes. Organization API keys require `projectId` or `MASTRA_PROJECT_ID`.
+- `MASTRA_CLOUD_ACCESS_TOKEN` - Authentication token for `CloudExporter` requests
 - `MASTRA_PROJECT_ID` - Project ID to use when deriving project-scoped collector routes such as `/projects/:projectId/ai/spans/publish`
-- `MASTRA_CLOUD_TRACES_ENDPOINT` - Traces endpoint override. Pass either a base origin or a full traces publish URL. Defaults to `https://api.mastra.ai`
+- `MASTRA_CLOUD_TRACES_ENDPOINT` - Traces endpoint override. Pass either a base origin or a full traces publish URL. Defaults to `https://observability.mastra.ai` in `@mastra/observability@1.9.2` and later
 
 ## Properties
 

package/CHANGELOG.md

@@ -1,5 +1,21 @@
 # @mastra/mcp-docs-server
 
+## 1.1.26-alpha.3
+
+### Patch Changes
+
+- Updated dependencies [[`3d83d06`](https://github.com/mastra-ai/mastra/commit/3d83d06f776f00fb5f4163dddd32a030c5c20844), [`7e0e63e`](https://github.com/mastra-ai/mastra/commit/7e0e63e2e485e84442351f4c7a79a424c83539dc), [`9467ea8`](https://github.com/mastra-ai/mastra/commit/9467ea87695749a53dfc041576410ebf9ee7bb67), [`7338d94`](https://github.com/mastra-ai/mastra/commit/7338d949380cf68b095342e8e42610dc51d557c1), [`c65aec3`](https://github.com/mastra-ai/mastra/commit/c65aec356cc037ee7c4b30ccea946807d4c4f443)]:
+  - @mastra/core@1.26.0-alpha.2
+  - @mastra/mcp@1.5.1-alpha.1
+
+## 1.1.26-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [[`7020c06`](https://github.com/mastra-ai/mastra/commit/7020c0690b199d9da337f0e805f16948e557922e), [`7020c06`](https://github.com/mastra-ai/mastra/commit/7020c0690b199d9da337f0e805f16948e557922e)]:
+  - @mastra/mcp@1.5.1-alpha.0
+  - @mastra/core@1.25.1-alpha.1
+
 ## 1.1.26-alpha.0
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/mcp-docs-server",
-  "version": "1.1.26-alpha.1",
+  "version": "1.1.26-alpha.4",
   "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
   "type": "module",
   "main": "dist/index.js",
@@ -29,8 +29,8 @@
     "jsdom": "^26.1.0",
     "local-pkg": "^1.1.2",
     "zod": "^4.3.6",
-    "@mastra/mcp": "^1.5.0",
-    "@mastra/core": "1.25.1-alpha.0"
+    "@mastra/core": "1.26.0-alpha.2",
+    "@mastra/mcp": "^1.5.1-alpha.1"
   },
   "devDependencies": {
     "@hono/node-server": "^1.19.11",
@@ -48,7 +48,7 @@
     "vitest": "4.0.18",
     "@internal/lint": "0.0.83",
     "@internal/types-builder": "0.0.58",
-    "@mastra/core": "1.25.1-alpha.0"
+    "@mastra/core": "1.26.0-alpha.2"
   },
   "homepage": "https://mastra.ai",
   "repository": {