@mastra/mcp-docs-server 1.1.26-alpha.18 → 1.1.26-alpha.20

package/.docs/docs/agents/supervisor-agents.md

@@ -300,8 +300,26 @@ Success criteria:
 })
 ```
 
+## Sub-agent versioning
+
+When using the [editor](https://mastra.ai/docs/editor/overview), you can control which stored version of each sub-agent the supervisor uses at runtime. Set version overrides on the Mastra instance or per invocation:
+
+```typescript
+const result = await supervisor.generate('Research and write about AI safety', {
+  versions: {
+    agents: {
+      'research-agent': { status: 'published' },
+      'writing-agent': { versionId: 'draft-456' },
+    },
+  },
+})
+```
+
+Version overrides propagate automatically through delegation. See [Sub-agent versioning](https://mastra.ai/docs/editor/overview) for details on resolution order and server API usage.
+
 ## Related
 
+- [Sub-agent versioning](https://mastra.ai/docs/editor/overview)
 - [Guide: Research coordinator](https://mastra.ai/guides/guide/research-coordinator)
 - [Agent.stream() reference](https://mastra.ai/reference/streaming/agents/stream)
 - [Agent.generate() reference](https://mastra.ai/reference/agents/generate)

package/.docs/docs/editor/overview.md

@@ -214,6 +214,75 @@ curl http://localhost:4111/agents/support-agent?versionId=abc-123
 
 See the [Client SDK agents reference](https://mastra.ai/reference/client-js/agents) for API methods.
 
+### Sub-agent versioning
+
+When a [supervisor agent](https://mastra.ai/docs/agents/supervisor-agents) delegates to sub-agents, version overrides determine which stored version of each sub-agent to use instead of the code-defined default. This lets you iterate on sub-agent prompts and tools through the editor without redeploying the supervisor.
+
+Set version overrides at three levels, with later levels taking priority:
+
+1. **Mastra instance config** — global defaults that apply to every `generate()` and `stream()` call.
+2. **Per-invocation options** — overrides passed directly to `generate()` or `stream()`.
+3. **Server request body** — overrides sent in the `versions` field of an API request.
+
+Resolution order: **per-invocation > request body > Mastra instance defaults > code-defined agent**.
+
+#### Mastra instance config
+
+Set global defaults when creating the `Mastra` instance. Every supervisor call inherits these overrides:
+
+```typescript
+import { Mastra } from '@mastra/core'
+import { MastraEditor } from '@mastra/editor'
+
+export const mastra = new Mastra({
+  agents: { supervisor, researchAgent, writerAgent },
+  editor: new MastraEditor(),
+  versions: {
+    agents: {
+      'research-agent': { status: 'published' },
+      'writer-agent': { versionId: 'abc-123' },
+    },
+  },
+})
+```
+
+#### Per-invocation overrides
+
+Override versions for a single call to `generate()` or `stream()`. These take priority over Mastra instance defaults:
+
+```typescript
+const result = await supervisor.generate('Research and write an article about AI safety', {
+  versions: {
+    agents: {
+      'research-agent': { versionId: 'draft-456' },
+    },
+  },
+})
+```
+
+#### Server request body
+
+When calling agents through the Mastra server, pass version overrides in the request body:
+
+```bash
+curl -X POST http://localhost:4111/agents/supervisor/generate \
+  -H "Content-Type: application/json" \
+  -d '{
+    "messages": [{ "role": "user", "content": "Research AI safety" }],
+    "versions": {
+      "agents": {
+        "research-agent": { "versionId": "draft-456" }
+      }
+    }
+  }'
+```
+
+#### How propagation works
+
+Version overrides propagate automatically through sub-agent delegation via `requestContext`. When a supervisor delegates to a sub-agent, the framework checks if a version override exists for that sub-agent's ID. If one is found, it resolves the stored version from the editor and uses it instead of the code-defined default.
+
+If version resolution fails (for example, when the editor is not configured or the version ID doesn't exist), the framework logs a warning and falls back to the code-defined agent.
+
 ## Next steps
 
 - Set up [prompts](https://mastra.ai/docs/editor/prompts) to build reusable instruction templates.

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 63 models through Mastra's model router.
+Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 62 models through Mastra's model router.
 
 Learn more in the [Netlify documentation](https://docs.netlify.com/build/ai-gateway/overview/).
 
@@ -13,7 +13,7 @@ const agent = new Agent({
   id: "my-agent",
   name: "My Agent",
   instructions: "You are a helpful assistant",
-  model: "netlify/anthropic/claude-3-haiku-20240307"
+  model: "netlify/anthropic/claude-haiku-4-5"
 });
 ```
 
@@ -35,7 +35,6 @@ ANTHROPIC_API_KEY=ant-...
 
 | Model                                       |
 | ------------------------------------------- |
-| `anthropic/claude-3-haiku-20240307`         |
 | `anthropic/claude-haiku-4-5`                |
 | `anthropic/claude-haiku-4-5-20251001`       |
 | `anthropic/claude-opus-4-1-20250805`        |

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 3667 models from 104 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3670 models from 104 providers through a single API.
 
 ## Features
 

package/.docs/models/providers/cloudflare-workers-ai.md

@@ -1,6 +1,6 @@
 # ![Cloudflare Workers AI logo](https://models.dev/logos/cloudflare-workers-ai.svg)Cloudflare Workers AI
 
-Access 7 Cloudflare Workers AI models through Mastra's model router. Authentication is handled automatically using the `CLOUDFLARE_API_KEY` environment variable. Configure `CLOUDFLARE_ACCOUNT_ID` as well.
+Access 8 Cloudflare Workers AI models through Mastra's model router. Authentication is handled automatically using the `CLOUDFLARE_API_KEY` environment variable. Configure `CLOUDFLARE_ACCOUNT_ID` as well.
 
 Learn more in the [Cloudflare Workers AI documentation](https://developers.cloudflare.com/workers-ai/models/).
 
@@ -38,6 +38,7 @@ for await (const chunk of stream) {
 | `cloudflare-workers-ai/@cf/google/gemma-4-26b-a4b-it`           | 256K    |       |           |       |       |       | $0.10      | $0.30       |
 | `cloudflare-workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct` | 128K    |       |           |       |       |       | $0.27      | $0.85       |
 | `cloudflare-workers-ai/@cf/moonshotai/kimi-k2.5`                | 256K    |       |           |       |       |       | $0.60      | $3          |
+| `cloudflare-workers-ai/@cf/moonshotai/kimi-k2.6`                | 256K    |       |           |       |       |       | $0.95      | $4          |
 | `cloudflare-workers-ai/@cf/nvidia/nemotron-3-120b-a12b`         | 256K    |       |           |       |       |       | $0.50      | $2          |
 | `cloudflare-workers-ai/@cf/openai/gpt-oss-120b`                 | 128K    |       |           |       |       |       | $0.35      | $0.75       |
 | `cloudflare-workers-ai/@cf/openai/gpt-oss-20b`                  | 128K    |       |           |       |       |       | $0.20      | $0.30       |

package/.docs/models/providers/huggingface.md

@@ -1,6 +1,6 @@
 # ![Hugging Face logo](https://models.dev/logos/huggingface.svg)Hugging Face
 
-Access 22 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
+Access 23 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
 
 Learn more in the [Hugging Face documentation](https://huggingface.co).
 
@@ -43,6 +43,7 @@ for await (const chunk of stream) {
 | `huggingface/moonshotai/Kimi-K2-Instruct-0905`    | 262K    |       |           |       |       |       | $1         | $3          |
 | `huggingface/moonshotai/Kimi-K2-Thinking`         | 262K    |       |           |       |       |       | $0.60      | $3          |
 | `huggingface/moonshotai/Kimi-K2.5`                | 262K    |       |           |       |       |       | $0.60      | $3          |
+| `huggingface/moonshotai/Kimi-K2.6`                | 262K    |       |           |       |       |       | $0.95      | $4          |
 | `huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507`  | 262K    |       |           |       |       |       | $0.30      | $3          |
 | `huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct` | 262K    |       |           |       |       |       | $2         | $2          |
 | `huggingface/Qwen/Qwen3-Coder-Next`               | 262K    |       |           |       |       |       | $0.20      | $2          |

package/.docs/models/providers/kimi-for-coding.md

@@ -1,6 +1,6 @@
 # ![Kimi For Coding logo](https://models.dev/logos/kimi-for-coding.svg)Kimi For Coding
 
-Access 2 Kimi For Coding models through Mastra's model router. Authentication is handled automatically using the `KIMI_API_KEY` environment variable.
+Access 3 Kimi For Coding models through Mastra's model router. Authentication is handled automatically using the `KIMI_API_KEY` environment variable.
 
 Learn more in the [Kimi For Coding documentation](https://www.kimi.com/coding/docs/en/third-party-agents.html).
 
@@ -35,6 +35,7 @@ for await (const chunk of stream) {
 | Model                              | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
 | ---------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
 | `kimi-for-coding/k2p5`             | 262K    |       |           |       |       |       | —          | —           |
+| `kimi-for-coding/k2p6`             | 262K    |       |           |       |       |       | —          | —           |
 | `kimi-for-coding/kimi-k2-thinking` | 262K    |       |           |       |       |       | —          | —           |
 
 ## Advanced configuration

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 10 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).
 
@@ -37,6 +37,7 @@ for await (const chunk of stream) {
 | `opencode-go/glm-5`        | 205K    |       |           |       |       |       | $1         | $3          |
 | `opencode-go/glm-5.1`      | 205K    |       |           |       |       |       | $1         | $4          |
 | `opencode-go/kimi-k2.5`    | 262K    |       |           |       |       |       | $0.60      | $3          |
+| `opencode-go/kimi-k2.6`    | 262K    |       |           |       |       |       | $0.95      | $4          |
 | `opencode-go/mimo-v2-omni` | 262K    |       |           |       |       |       | $0.40      | $2          |
 | `opencode-go/mimo-v2-pro`  | 1.0M    |       |           |       |       |       | $1         | $3          |
 | `opencode-go/minimax-m2.5` | 205K    |       |           |       |       |       | $0.30      | $1          |

package/.docs/reference/agents/generate.md

@@ -298,6 +298,14 @@ const response = await agent.generate('Help me organize my day', {
 
 **options.tracingOptions.tags** (`string[]`): Tags to apply to this trace. String labels for categorizing and filtering traces.
 
+**options.versions** (`VersionOverrides`): Per-invocation version overrides for sub-agent delegation. Merged on top of Mastra instance-level versions and propagated automatically through sub-agent calls via requestContext. Requires the editor package. See \[Sub-agent versioning]\(/docs/editor/overview#sub-agent-versioning).
+
+**options.versions.agents** (`Record<string, VersionSelector>`): A map of agent IDs to their version selectors.
+
+**options.versions.agents.versionId** (`string`): Target a specific version by ID.
+
+**options.versions.agents.status** (`'draft' | 'published'`): Target the latest version with this publication status.
+
 **options.includeRawChunks** (`boolean`): Whether to include raw chunks in the stream output. Not available on all model providers.
 
 ## Response structure

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

@@ -140,6 +140,18 @@ await run.resume({
 })
 ```
 
+When a [`.foreach()`](https://mastra.ai/reference/workflows/workflow-methods/foreach) step suspends across multiple iterations, pass `forEachIndex` (zero-based; `0` targets the first iteration) to resume one iteration at a time. Iterations you don't target remain suspended.
+
+```typescript
+await run.resume({
+  step: 'approve',
+  resumeData: { ok: true },
+  forEachIndex: 1, // resumes the second iteration
+})
+```
+
+`forEachIndex` is also supported by `resumeAsync()` and `resumeStream()`.
+
 ### `cancel()`
 
 Cancel a running workflow:

package/.docs/reference/core/mastra-class.md

@@ -63,4 +63,12 @@ Visit the [Configuration reference](https://mastra.ai/reference/configuration) f
 
 **gateways** (`Record<string, MastraModelGateway>`): Custom model gateways to register for accessing AI models through alternative providers or private deployments. Structured as a key-value pair, with keys being the registry key (used for getGateway()) and values being gateway instances. (Default: `{}`)
 
-**memory** (`Record<string, MastraMemory>`): Memory instances to register. These can be referenced by stored agents and resolved at runtime. Structured as a key-value pair, with keys being the registry key and values being memory instances. (Default: `{}`)
+**memory** (`Record<string, MastraMemory>`): Memory instances to register. These can be referenced by stored agents and resolved at runtime. Structured as a key-value pair, with keys being the registry key and values being memory instances. (Default: `{}`)
+
+**versions** (`VersionOverrides`): Global version overrides for sub-agent delegation. When a supervisor agent delegates to a sub-agent, these overrides determine which stored version of that sub-agent to use instead of the code-defined default. Requires the editor package to be configured. See \[Sub-agent versioning]\(/docs/editor/overview#sub-agent-versioning) for details.
+
+**versions.agents** (`Record<string, VersionSelector>`): A map of agent IDs to their version selectors. Each selector can target a specific version by ID or by publication status.
+
+**versions.agents.versionId** (`string`): The ID of a specific version to use.
+
+**versions.agents.status** (`'draft' | 'published'`): Select the latest version with this publication status.

package/.docs/reference/processors/prefill-error-handler.md

@@ -1,14 +1,14 @@
 # PrefillErrorHandler
 
-The `PrefillErrorHandler` is an **error processor** that handles the Anthropic "assistant message prefill" error. This error occurs when a conversation ends with an assistant message and the model doesn't support prefilling assistant responses.
+The `PrefillErrorHandler` is an **error processor** that handles assistant-response prefill errors. This error occurs when a conversation ends with an assistant message and the model rejects the request because it interprets it as prefilling the assistant response.
 
 When the error is detected, the processor appends a hidden `<system-reminder>continue</system-reminder>` user message to the conversation and signals a retry. The reminder is persisted with `metadata.systemReminder = { type: 'anthropic-prefill-processor-retry' }`, which keeps it available for retry reconstruction and raw history while standard UI-facing message conversions hide it.
 
-Add this processor to `errorProcessors` when you want Mastra to recover from Anthropic assistant message prefill errors.
+Add this processor to `errorProcessors` when you want Mastra to recover from assistant prefill rejections (for example Anthropic's "assistant message prefill" and Qwen/llama.cpp's "assistant response prefill is incompatible with `enable_thinking`" errors).
 
 ## How it works
 
-1. The LLM API call fails with a message containing "assistant message prefill"
+1. The LLM API call fails with a known assistant-prefill rejection message
 2. `PrefillErrorHandler` checks that this is the first retry attempt
 3. It appends a hidden `<system-reminder>continue</system-reminder>` user message to the `messageList`
 4. It returns `{ retry: true }` to signal the LLM call should be retried with the modified messages
@@ -17,7 +17,7 @@ The processor now reacts to the API rejection itself instead of re-checking whet
 
 ## Usage example
 
-Add `PrefillErrorHandler` to `errorProcessors` for any agent that should retry Anthropic prefill failures:
+Add `PrefillErrorHandler` to `errorProcessors` for any agent that should retry assistant-prefill failures:
 
 ```typescript
 import { Agent } from '@mastra/core/agent'
@@ -62,7 +62,7 @@ The `PrefillErrorHandler` takes no constructor parameters.
 
 **name** (`'Prefill Error Handler'`): Processor display name.
 
-**processAPIError** (`(args: ProcessAPIErrorArgs) => ProcessAPIErrorResult | void`): Handles the Anthropic prefill error by appending a hidden system reminder continue message and signaling retry. Only triggers on the first retry attempt.
+**processAPIError** (`(args: ProcessAPIErrorArgs) => ProcessAPIErrorResult | void`): Handles known assistant-prefill errors by appending a hidden system reminder continue message and signaling retry. Only triggers on the first retry attempt.
 
 ## Related
 

package/.docs/reference/streaming/agents/stream.md

@@ -206,6 +206,14 @@ const stream = await agent.stream('message for agent')
 
 **options.tracingOptions.tags** (`string[]`): Tags to apply to this trace. String labels for categorizing and filtering traces.
 
+**options.versions** (`VersionOverrides`): Per-invocation version overrides for sub-agent delegation. Merged on top of Mastra instance-level versions and propagated automatically through sub-agent calls via requestContext. Requires the editor package. See \[Sub-agent versioning]\(/docs/editor/overview#sub-agent-versioning).
+
+**options.versions.agents** (`Record<string, VersionSelector>`): A map of agent IDs to their version selectors.
+
+**options.versions.agents.versionId** (`string`): Target a specific version by ID.
+
+**options.versions.agents.status** (`'draft' | 'published'`): Target the latest version with this publication status.
+
 ## Returns
 
 **stream** (`MastraModelOutput<Output>`): Returns a MastraModelOutput instance that provides access to the streaming output.

package/.docs/reference/streaming/workflows/resumeStream.md

@@ -32,6 +32,8 @@ if (result!.status === 'suspended') {
 
 **step** (`Step<string, any, any, any, any, TEngineType>`): The step to resume execution from
 
+**forEachIndex** (`number`): Target a specific iteration of a suspended \`.foreach()\` step. Pass the zero-based index of the iteration to resume; other iterations remain suspended. Omit to resume all suspended iterations of the step with the same \`resumeData\`.
+
 **tracingOptions** (`TracingOptions`): Options for Tracing configuration.
 
 **tracingOptions.metadata** (`Record<string, any>`): Metadata to add to the root trace span. Useful for adding custom attributes like user IDs, session IDs, or feature flags.

package/.docs/reference/workflows/run-methods/resume.md

@@ -26,6 +26,8 @@ if (result.status === 'suspended') {
 
 **retryCount** (`number`): Optional retry count for nested workflow execution
 
+**forEachIndex** (`number`): Target a specific iteration of a suspended \`.foreach()\` step. Pass the zero-based index of the iteration you want to resume; other iterations remain suspended. Omit this field to resume all suspended iterations of the step with the same \`resumeData\`.
+
 **tracingContext** (`TracingContext`): Tracing context for creating child spans and adding metadata. Automatically injected when using Mastra's tracing system.
 
 **tracingContext.currentSpan** (`Span`): Current span for creating child spans and adding metadata. Use this to create custom child spans or update span attributes during execution.
@@ -67,6 +69,28 @@ if (result.status === 'suspended') {
 
 > **Note:** When exactly one step is suspended, you can omit the `step` parameter and the workflow will automatically resume that step. For workflows with multiple suspended steps, you must explicitly specify which step to resume.
 
+### Resuming a single [`.foreach()`](https://mastra.ai/reference/workflows/workflow-methods/foreach) iteration
+
+When a [`.foreach()`](https://mastra.ai/reference/workflows/workflow-methods/foreach) step suspends across multiple iterations, use `forEachIndex` (zero-based) to resume one iteration at a time with different `resumeData`. Iterations not targeted by `forEachIndex` remain suspended until resumed.
+
+```typescript
+// Resume only the second iteration (index 1) with its own data
+await run.resume({
+  step: 'approve',
+  resumeData: { ok: true },
+  forEachIndex: 1,
+})
+
+// Later, resume the first iteration with different data
+await run.resume({
+  step: 'approve',
+  resumeData: { ok: false },
+  forEachIndex: 0,
+})
+```
+
+If `forEachIndex` is omitted, every suspended iteration of the step is resumed with the same `resumeData`.
+
 ## Related
 
 - [Workflows overview](https://mastra.ai/docs/workflows/overview)

package/.docs/reference/workflows/workflow-methods/foreach.md

@@ -113,6 +113,19 @@ Each progress event payload contains:
 
 **iterationOutput** (`Record<string, any>`): Output of the iteration (present when iterationStatus is 'success')
 
+### Resuming a single iteration
+
+When a step inside `.foreach()` suspends, each iteration suspends independently. Pass `forEachIndex` to [`run.resume()`](https://mastra.ai/reference/workflows/run-methods/resume) to resume one iteration at a time with its own `resumeData`. Omitting `forEachIndex` resumes every suspended iteration with the same data.
+
+```typescript
+await run.resume({
+  step: 'approve',
+  resumeData: { ok: true },
+  forEachIndex: 1,
+})
+```
+
 ## Related
 
-- [Looping with foreach](https://mastra.ai/docs/workflows/control-flow)
+- [Looping with foreach](https://mastra.ai/docs/workflows/control-flow)
+- [run.resume()](https://mastra.ai/reference/workflows/run-methods/resume)

package/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @mastra/mcp-docs-server
 
+## 1.1.26-alpha.19
+
+### Patch Changes
+
+- Updated dependencies [[`aba393e`](https://github.com/mastra-ai/mastra/commit/aba393e2da7390c69b80e516a4f153cda6f09376), [`0a5fa1d`](https://github.com/mastra-ai/mastra/commit/0a5fa1d3cb0583889d06687155f26fd7d2edc76c), [`ea43e64`](https://github.com/mastra-ai/mastra/commit/ea43e646dd95d507694b6112b0bf1df22ad552b2), [`00d1b16`](https://github.com/mastra-ai/mastra/commit/00d1b16b401199cb294fa23f43336547db4dca9b), [`af8a57e`](https://github.com/mastra-ai/mastra/commit/af8a57ed9ba9685ad8601d5b71ae3706da6222f9)]:
+  - @mastra/core@1.26.0-alpha.10
+
 ## 1.1.26-alpha.17
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/mcp-docs-server",
-  "version": "1.1.26-alpha.18",
+  "version": "1.1.26-alpha.20",
   "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
   "type": "module",
   "main": "dist/index.js",
@@ -29,7 +29,7 @@
     "jsdom": "^26.1.0",
     "local-pkg": "^1.1.2",
     "zod": "^4.3.6",
-    "@mastra/core": "1.26.0-alpha.9",
+    "@mastra/core": "1.26.0-alpha.10",
     "@mastra/mcp": "^1.5.1-alpha.1"
   },
   "devDependencies": {
@@ -48,7 +48,7 @@
     "vitest": "4.0.18",
     "@internal/lint": "0.0.83",
     "@internal/types-builder": "0.0.58",
-    "@mastra/core": "1.26.0-alpha.9"
+    "@mastra/core": "1.26.0-alpha.10"
   },
   "homepage": "https://mastra.ai",
   "repository": {