@mastra/mcp-docs-server 1.1.15-alpha.7 → 1.1.15

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

@@ -89,6 +89,34 @@ The result is a three-tier system:
 2. **Observations**: A log of what the Observer has seen
 3. **Reflections**: Condensed observations when memory becomes too long
 
+### Retrieval mode (experimental)
+
+> **Note:** Retrieval mode is experimental. The API may change in future releases.
+
+Normal OM compresses messages into observations, which is great for staying on task — but the original wording is gone. Retrieval mode fixes this by keeping each observation group linked to the raw messages that produced it. When the agent needs exact wording, tool output, or chronology that the summary compressed away, it can call a `recall` tool to page through the source messages.
+
+```typescript
+const memory = new Memory({
+  options: {
+    observationalMemory: {
+      model: 'google/gemini-2.5-flash',
+      scope: 'thread',
+      retrieval: true,
+    },
+  },
+})
+```
+
+With retrieval mode enabled, OM:
+
+- Stores a `range` (e.g. `startId:endId`) on each observation group pointing to the messages it was derived from
+- Keeps range metadata visible in the agent's context so the agent knows which observations map to which messages
+- Registers a `recall` tool the agent can call to page through the raw messages behind any range
+
+Retrieval mode is only active for thread-scoped OM. Setting `retrieval: true` with `scope: 'resource'` has no effect — OM keeps resource-scoped behavior but skips retrieval-mode context and does not register the `recall` tool.
+
+See the [recall tool reference](https://mastra.ai/reference/memory/observational-memory) for the full API (detail levels, part indexing, pagination, and token limiting).
+
 ## Models
 
 The Observer and Reflector run in the background. Any model that works with Mastra's [model routing](https://mastra.ai/models) (`provider/model`) can be used. When using `observationalMemory: true`, the default model is `google/gemini-2.5-flash`. When passing a config object, a `model` must be explicitly set.

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

@@ -1,6 +1,6 @@
 # ![OpenRouter logo](https://models.dev/logos/openrouter.svg)OpenRouter
 
-OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 199 models through Mastra's model router.
+OpenRouter 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 [OpenRouter documentation](https://openrouter.ai/models).
 
@@ -160,6 +160,8 @@ ANTHROPIC_API_KEY=ant-...
 | `openai/gpt-5.2-pro`                                            |
 | `openai/gpt-5.3-codex`                                          |
 | `openai/gpt-5.4`                                                |
+| `openai/gpt-5.4-mini`                                           |
+| `openai/gpt-5.4-nano`                                           |
 | `openai/gpt-5.4-pro`                                            |
 | `openai/gpt-oss-120b`                                           |
 | `openai/gpt-oss-120b:exacto`                                    |
@@ -224,6 +226,8 @@ ANTHROPIC_API_KEY=ant-...
 | `x-ai/grok-4.20-multi-agent-beta`                               |
 | `x-ai/grok-code-fast-1`                                         |
 | `xiaomi/mimo-v2-flash`                                          |
+| `xiaomi/mimo-v2-omni`                                           |
+| `xiaomi/mimo-v2-pro`                                            |
 | `z-ai/glm-4.5`                                                  |
 | `z-ai/glm-4.5-air`                                              |
 | `z-ai/glm-4.5-air:free`                                         |

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 3386 models from 94 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3396 models from 94 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 40 Cloudflare Workers AI models through Mastra's model router. Authentication is handled automatically using the `CLOUDFLARE_ACCOUNT_ID` environment variable.
+Access 42 Cloudflare Workers AI models through Mastra's model router. Authentication is handled automatically using the `CLOUDFLARE_ACCOUNT_ID` environment variable.
 
 Learn more in the [Cloudflare Workers AI documentation](https://developers.cloudflare.com/workers-ai/models/).
 
@@ -64,7 +64,9 @@ for await (const chunk of stream) {
 | `cloudflare-workers-ai/@cf/meta/m2m100-1.2b`                         | 128K    |       |           |       |       |       | $0.34      | $0.34       |
 | `cloudflare-workers-ai/@cf/mistral/mistral-7b-instruct-v0.1`         | 128K    |       |           |       |       |       | $0.11      | $0.19       |
 | `cloudflare-workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct` | 128K    |       |           |       |       |       | $0.35      | $0.56       |
+| `cloudflare-workers-ai/@cf/moonshotai/kimi-k2.5`                     | 256K    |       |           |       |       |       | $0.60      | $3          |
 | `cloudflare-workers-ai/@cf/myshell-ai/melotts`                       | 128K    |       |           |       |       |       | —          | —           |
+| `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       |
 | `cloudflare-workers-ai/@cf/pfnet/plamo-embedding-1b`                 | 128K    |       |           |       |       |       | $0.02      | —           |

package/.docs/models/providers/ollama-cloud.md

@@ -1,6 +1,6 @@
 # ![Ollama Cloud logo](https://models.dev/logos/ollama-cloud.svg)Ollama Cloud
 
-Access 33 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
+Access 34 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
 
 Learn more in the [Ollama Cloud documentation](https://docs.ollama.com/cloud).
 
@@ -54,6 +54,7 @@ for await (const chunk of stream) {
 | `ollama-cloud/minimax-m2`             | 205K    |       |           |       |       |       | —          | —           |
 | `ollama-cloud/minimax-m2.1`           | 205K    |       |           |       |       |       | —          | —           |
 | `ollama-cloud/minimax-m2.5`           | 205K    |       |           |       |       |       | —          | —           |
+| `ollama-cloud/minimax-m2.7`           | 205K    |       |           |       |       |       | —          | —           |
 | `ollama-cloud/ministral-3:14b`        | 262K    |       |           |       |       |       | —          | —           |
 | `ollama-cloud/ministral-3:3b`         | 262K    |       |           |       |       |       | —          | —           |
 | `ollama-cloud/ministral-3:8b`         | 262K    |       |           |       |       |       | —          | —           |

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

@@ -1,6 +1,6 @@
 # ![Xiaomi logo](https://models.dev/logos/xiaomi.svg)Xiaomi
 
-Access 1 Xiaomi model through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
+Access 3 Xiaomi models through Mastra's model router. Authentication is handled automatically using the `XIAOMI_API_KEY` environment variable.
 
 Learn more in the [Xiaomi documentation](https://platform.xiaomimimo.com/#/docs).
 
@@ -35,6 +35,8 @@ for await (const chunk of stream) {
 | Model                  | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
 | ---------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
 | `xiaomi/mimo-v2-flash` | 256K    |       |           |       |       |       | $0.10      | $0.30       |
+| `xiaomi/mimo-v2-omni`  | 256K    |       |           |       |       |       | $0.40      | $2          |
+| `xiaomi/mimo-v2-pro`   | 1.0M    |       |           |       |       |       | $1         | $3          |
 
 ## Advanced configuration
 
@@ -64,7 +66,7 @@ const agent = new Agent({
   model: ({ requestContext }) => {
     const useAdvanced = requestContext.task === "complex";
     return useAdvanced
-      ? "xiaomi/mimo-v2-flash"
+      ? "xiaomi/mimo-v2-pro"
       : "xiaomi/mimo-v2-flash";
   }
 });

package/.docs/models/providers/zhipuai-coding-plan.md

@@ -1,6 +1,6 @@
 # ![Zhipu AI Coding Plan logo](https://models.dev/logos/zhipuai-coding-plan.svg)Zhipu AI Coding Plan
 
-Access 9 Zhipu AI Coding Plan models through Mastra's model router. Authentication is handled automatically using the `ZHIPU_API_KEY` environment variable.
+Access 10 Zhipu AI Coding Plan models through Mastra's model router. Authentication is handled automatically using the `ZHIPU_API_KEY` environment variable.
 
 Learn more in the [Zhipu AI Coding Plan documentation](https://docs.bigmodel.cn/cn/coding-plan/overview).
 
@@ -43,6 +43,7 @@ for await (const chunk of stream) {
 | `zhipuai-coding-plan/glm-4.6v-flash` | 128K    |       |           |       |       |       | —          | —           |
 | `zhipuai-coding-plan/glm-4.7`        | 205K    |       |           |       |       |       | —          | —           |
 | `zhipuai-coding-plan/glm-5`          | 205K    |       |           |       |       |       | —          | —           |
+| `zhipuai-coding-plan/glm-5-turbo`    | 200K    |       |           |       |       |       | —          | —           |
 
 ## Advanced configuration
 
@@ -72,7 +73,7 @@ const agent = new Agent({
   model: ({ requestContext }) => {
     const useAdvanced = requestContext.task === "complex";
     return useAdvanced
-      ? "zhipuai-coding-plan/glm-5"
+      ? "zhipuai-coding-plan/glm-5-turbo"
       : "zhipuai-coding-plan/glm-4.5";
   }
 });

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

@@ -38,6 +38,8 @@ OM performs thresholding with fast local token estimation. Text uses `tokenx`, a
 
 **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`): \*\*Experimental.\*\* Enable retrieval-mode observation groups as durable pointers to raw message history. Retrieval mode is only active when \`scope\` is \`'thread'\`. If you set \`retrieval: true\` with \`scope: 'resource'\`, OM keeps resource-scoped memory behavior but skips retrieval-mode context and does not register the \`recall\` tool. (Default: `false`)
+
 **observation** (`ObservationalMemoryObservationConfig`): Configuration for the observation step. Controls when the Observer agent runs and how it behaves.
 
 **observation.model** (`string | LanguageModel | DynamicModel | ModelWithRetries[]`): Model for the Observer agent. Cannot be set if a top-level \`model\` is also provided. If neither this nor the top-level \`model\` is set, falls back to \`reflection.model\`.
@@ -574,6 +576,42 @@ The standalone `ObservationalMemory` class accepts all the same options as the `
 
 **obscureThreadIds** (`boolean`): When enabled, thread IDs are hashed before being included in observation context. This prevents the LLM from recognizing patterns in thread identifiers. Automatically enabled when using resource scope through the Memory class. (Default: `false`)
 
+## Recall tool
+
+When `retrieval: true` is set with `scope: 'thread'`, OM registers a `recall` tool that the agent can call to page through the raw messages behind an observation group's `_range`. The tool is automatically added to the agent's tool list — no manual registration is needed.
+
+### Parameters
+
+**cursor** (`string`): A message ID to anchor the recall query. Extract the start or end ID from an observation group range (e.g. from \`\_range: \\\`startId:endId\\\`\_\`, use either \`startId\` or \`endId\`). If a range string is passed directly, the tool returns a hint explaining how to extract the correct ID.
+
+**page** (`number`): Pagination offset from the cursor. Positive values page forward (messages after the cursor), negative values page backward (messages before the cursor). \`0\` is treated as \`1\`. (Default: `1`)
+
+**limit** (`number`): Maximum number of messages per page. (Default: `20`)
+
+**detail** (`'low' | 'high'`): Controls how much content is shown per message part. \`'low'\` shows truncated text and tool names with positional indices (\`\[p0]\`, \`\[p1]\`). \`'high'\` shows full content including tool arguments and results, clamped to one part per call with continuation hints. (Default: `'low'`)
+
+**partIndex** (`number`): Fetch a single message part at full detail by its positional index. Use this when a low-detail recall shows an interesting part at \`\[p1]\` — call again with \`partIndex: 1\` to see the full content without loading every part.
+
+### Returns
+
+**messages** (`string`): Formatted message content. Format depends on the \`detail\` level.
+
+**count** (`number`): Number of messages in this page.
+
+**cursor** (`string`): The cursor message ID used for this query.
+
+**page** (`number`): The page number returned.
+
+**limit** (`number`): The limit used for this query.
+
+**hasNextPage** (`boolean`): Whether more messages exist after this page.
+
+**hasPrevPage** (`boolean`): Whether more messages exist before this page.
+
+**truncated** (`boolean`): Present and \`true\` when the output was capped by the token budget. The agent can paginate or use \`partIndex\` to access remaining content.
+
+**tokenOffset** (`number`): Approximate number of tokens that were trimmed when \`truncated\` is true.
+
 ### Related
 
 - [Observational Memory](https://mastra.ai/docs/memory/observational-memory)

package/CHANGELOG.md

@@ -1,5 +1,21 @@
 # @mastra/mcp-docs-server
 
+## 1.1.15
+
+### Patch Changes
+
+- Updated dependencies [[`cb611a1`](https://github.com/mastra-ai/mastra/commit/cb611a1e89a4f4cf74c97b57e0c27bb56f2eceb5), [`da93115`](https://github.com/mastra-ai/mastra/commit/da931155c1a9bc63d455d3d86b4ec984db5991fe), [`44df54a`](https://github.com/mastra-ai/mastra/commit/44df54a28e6315d9699cf437e4f3e8c7c7d10217), [`62d1d3c`](https://github.com/mastra-ai/mastra/commit/62d1d3cc08fe8182e7080237fd975de862ec8c91), [`9e1a3ed`](https://github.com/mastra-ai/mastra/commit/9e1a3ed07cfafb5e8e19a796ce0bee817002d7c0), [`56c9ad9`](https://github.com/mastra-ai/mastra/commit/56c9ad9c871d258af9da4d6e50065b01d339bf34), [`0773d08`](https://github.com/mastra-ai/mastra/commit/0773d089859210217702d3175ad4b2f3d63d267e), [`8681ecb`](https://github.com/mastra-ai/mastra/commit/8681ecb86184d5907267000e4576cc442a9a83fc), [`28d0249`](https://github.com/mastra-ai/mastra/commit/28d0249295782277040ad1e0d243e695b7ab1ce4), [`681ee1c`](https://github.com/mastra-ai/mastra/commit/681ee1c811359efd1b8bebc4bce35b9bb7b14bec), [`bb0f09d`](https://github.com/mastra-ai/mastra/commit/bb0f09dbac58401b36069f483acf5673202db5b5), [`6a8f1e6`](https://github.com/mastra-ai/mastra/commit/6a8f1e66272d2928351db334da091ee27e304c23), [`a579f7a`](https://github.com/mastra-ai/mastra/commit/a579f7a31e582674862b5679bc79af7ccf7429b8), [`5f7e9d0`](https://github.com/mastra-ai/mastra/commit/5f7e9d0db664020e1f3d97d7d18c6b0b9d4843d0), [`d7f14c3`](https://github.com/mastra-ai/mastra/commit/d7f14c3285cd253ecdd5f58139b7b6cbdf3678b5), [`0efe12a`](https://github.com/mastra-ai/mastra/commit/0efe12a5f008a939a1aac71699486ba40138054e)]:
+  - @mastra/core@1.15.0
+  - @mastra/mcp@1.3.1
+
+## 1.1.15-alpha.8
+
+### Patch Changes
+
+- Updated dependencies [[`da93115`](https://github.com/mastra-ai/mastra/commit/da931155c1a9bc63d455d3d86b4ec984db5991fe), [`44df54a`](https://github.com/mastra-ai/mastra/commit/44df54a28e6315d9699cf437e4f3e8c7c7d10217), [`0efe12a`](https://github.com/mastra-ai/mastra/commit/0efe12a5f008a939a1aac71699486ba40138054e)]:
+  - @mastra/core@1.15.0-alpha.4
+  - @mastra/mcp@1.3.1-alpha.1
+
 ## 1.1.15-alpha.7
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/mcp-docs-server",
-  "version": "1.1.15-alpha.7",
+  "version": "1.1.15",
   "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/core": "1.15.0-alpha.3",
-    "@mastra/mcp": "^1.3.1-alpha.0"
+    "@mastra/mcp": "^1.3.1",
+    "@mastra/core": "1.15.0"
   },
   "devDependencies": {
     "@hono/node-server": "^1.19.11",
@@ -46,9 +46,9 @@
     "tsx": "^4.21.0",
     "typescript": "^5.9.3",
     "vitest": "4.0.18",
-    "@internal/lint": "0.0.72",
-    "@internal/types-builder": "0.0.47",
-    "@mastra/core": "1.15.0-alpha.3"
+    "@internal/lint": "0.0.73",
+    "@mastra/core": "1.15.0",
+    "@internal/types-builder": "0.0.48"
   },
   "homepage": "https://mastra.ai",
   "repository": {