@mastra/mcp-docs-server 0.13.8 → 0.13.9-alpha.1

package/.docs/organized/changelogs/%40mastra%2Fserver.md

@@ -1,5 +1,36 @@
 # @mastra/deployer
 
+## 0.13.0-alpha.1
+
+### Patch Changes
+
+- Updated dependencies [ea0c5f2]
+- Updated dependencies [b0e43c1]
+- Updated dependencies [1fb812e]
+- Updated dependencies [35c5798]
+  - @mastra/core@0.13.0-alpha.1
+
+## 0.12.2-alpha.0
+
+### Patch Changes
+
+- e202b82: Add getThreadsByResourceIdPaginated to the Memory Class
+- Updated dependencies [94f4812]
+- Updated dependencies [e202b82]
+- Updated dependencies [e00f6a0]
+  - @mastra/core@0.12.2-alpha.0
+
+## 0.12.1
+
+### Patch Changes
+
+- Updated dependencies [33dcb07]
+- Updated dependencies [d0d9500]
+- Updated dependencies [d30b1a0]
+- Updated dependencies [bff87f7]
+- Updated dependencies [b4a8df0]
+  - @mastra/core@0.12.1
+
 ## 0.12.1-alpha.1
 
 ### Patch Changes
@@ -268,35 +299,4 @@
 - Updated dependencies [6c89d7f]
   - @mastra/core@0.10.15
 
-## 0.10.15-alpha.1
-
-### Patch Changes
-
-- Updated dependencies [0b56518]
-- Updated dependencies [2ba5b76]
-- Updated dependencies [c3a30de]
-- Updated dependencies [cf3a184]
-- Updated dependencies [d6bfd60]
-  - @mastra/core@0.10.15-alpha.1
-
-## 0.10.15-alpha.0
-
-### Patch Changes
-
-- 626b0f4: [Cloud-126] Working Memory Playground - Added working memory to playground to allow users to view/edit working memory
-- Updated dependencies [db5cc15]
-- Updated dependencies [5237998]
-- Updated dependencies [37c1acd]
-- Updated dependencies [1aa60b1]
-- Updated dependencies [89ec9d4]
-- Updated dependencies [626b0f4]
-- Updated dependencies [c22a91f]
-- Updated dependencies [f7403ab]
-- Updated dependencies [6c89d7f]
-  - @mastra/core@0.10.15-alpha.0
-
-## 0.10.14
-
-### Patch Changes
-
-... 2637 more lines hidden. See full changelog in package directory.
+... 2668 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fupstash.md

@@ -1,5 +1,19 @@
 # @mastra/upstash
 
+## 0.14.0-alpha.0
+
+### Minor Changes
+
+- ea0c5f2: Add store support to new score api
+
+### Patch Changes
+
+- Updated dependencies [ea0c5f2]
+- Updated dependencies [b0e43c1]
+- Updated dependencies [1fb812e]
+- Updated dependencies [35c5798]
+  - @mastra/core@0.13.0-alpha.1
+
 ## 0.13.0
 
 ### Minor Changes
@@ -284,19 +298,5 @@
 
 - 704d1ca: Thread Timestamp Auto-Update Enhancement
   Added automatic thread updatedAt timestamp updates when messages are saved across all storage providers
-  Enhanced user experience: Threads now accurately reflect their latest activity with automatic timestamp updates when new messages are added
-  Universal implementation: Consistent behavior across all 7 storage backends (ClickHouse, Cloudflare D1, DynamoDB, MongoDB, PostgreSQL, Upstash, LibSQL)
-  Performance optimized: Updates execute in parallel with message saving operations for minimal performance impact
-  Backwards compatible: No breaking changes - existing code continues to work unchanged
-  Improved conversation ordering: Chat interfaces can now properly sort threads by actual last activity
-  This enhancement resolves the issue where active conversations appeared stale due to outdated thread timestamps, providing better conversation management and user experience in chat applications.
-
-### Patch Changes
-
-- 2fda031: Clarify upstash argument concepts.
-- e8fdbdd: Fix dynamic require of crypto using upstash.
-  caused by a bad import was used in the monorepo
-
-  Fixes #4801
 
-... 1787 more lines hidden. See full changelog in package directory.
+... 1801 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fvoice-murf.md

@@ -1,5 +1,18 @@
 # @mastra/voice-murf
 
+## 0.10.7
+
+### Patch Changes
+
+- dcbfcb5: dependencies updates:
+  - Updated dependency [`ky@^1.8.2` ↗︎](https://www.npmjs.com/package/ky/v/1.8.2) (from `^1.8.1`, in `dependencies`)
+- Updated dependencies [33dcb07]
+- Updated dependencies [d0d9500]
+- Updated dependencies [d30b1a0]
+- Updated dependencies [bff87f7]
+- Updated dependencies [b4a8df0]
+  - @mastra/core@0.12.1
+
 ## 0.10.7-alpha.0
 
 ### Patch Changes
@@ -286,17 +299,4 @@
 - Updated dependencies [3e9c131]
   - @mastra/core@0.9.4-alpha.4
 
-## 0.1.18-alpha.3
-
-### Patch Changes
-
-- Updated dependencies [396be50]
-- Updated dependencies [c3bd795]
-- Updated dependencies [da082f8]
-- Updated dependencies [a5810ce]
-  - @mastra/core@0.9.4-alpha.3
-
-## 0.1.18-alpha.2
-
-
-... 1043 more lines hidden. See full changelog in package directory.
+... 1056 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/%40mastra%2Fvoice-openai.md

@@ -1,5 +1,18 @@
 # @mastra/voice-openai
 
+## 0.10.7
+
+### Patch Changes
+
+- df0bf51: dependencies updates:
+  - Updated dependency [`openai@^5.10.2` ↗︎](https://www.npmjs.com/package/openai/v/5.10.2) (from `^5.10.1`, in `dependencies`)
+- Updated dependencies [33dcb07]
+- Updated dependencies [d0d9500]
+- Updated dependencies [d30b1a0]
+- Updated dependencies [bff87f7]
+- Updated dependencies [b4a8df0]
+  - @mastra/core@0.12.1
+
 ## 0.10.7-alpha.0
 
 ### Patch Changes
@@ -285,18 +298,5 @@
 
 ### Patch Changes
 
-- Updated dependencies [f53a6ac]
-- Updated dependencies [eabdcd9]
-- Updated dependencies [90be034]
-- Updated dependencies [99f050a]
-- Updated dependencies [d0ee3c6]
-- Updated dependencies [23f258c]
-- Updated dependencies [2672a05]
-  - @mastra/core@0.9.5-alpha.0
-
-## 0.1.19
-
-### Patch Changes
-
 
-... 1069 more lines hidden. See full changelog in package directory.
+... 1082 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/create-mastra.md

@@ -1,5 +1,21 @@
 # create-mastra
 
+## 0.10.19-alpha.1
+
+## 0.10.19-alpha.0
+
+## 0.10.15
+
+### Patch Changes
+
+- ad04455: Missed changeset in last release, needed to include create-mastra
+
+## 0.10.15-alpha.0
+
+### Patch Changes
+
+- ad04455: Missed changeset in last release, needed to include create-mastra
+
 ## 0.10.14
 
 ### Patch Changes
@@ -282,21 +298,5 @@
 ### Patch Changes
 
 - 44ba52d: Add proper error message when installation of mastra fails
-- 3270d9d: Fix runtime context being undefined
-- fc677d7: For final result for a workflow
-
-## 0.10.5-alpha.0
-
-### Patch Changes
-
-- 02560d4: lift evals fetching to the playground package instead
-- 63f6b7d: dependencies updates:
-  - Updated dependency [`execa@^9.6.0` ↗︎](https://www.npmjs.com/package/execa/v/9.6.0) (from `^9.5.2`, in `dependencies`)
-  - Updated dependency [`pino@^9.7.0` ↗︎](https://www.npmjs.com/package/pino/v/9.7.0) (from `^9.6.0`, in `dependencies`)
-  - Updated dependency [`posthog-node@^4.18.0` ↗︎](https://www.npmjs.com/package/posthog-node/v/4.18.0) (from `^4.10.1`, in `dependencies`)
-- 311132e: move useWorkflow to playground instead of playground-ui
-- 53d3c37: Get workflows from an agent if not found from Mastra instance #5083
-
-## 0.10.4
 
-... 1139 more lines hidden. See full changelog in package directory.
+... 1155 more lines hidden. See full changelog in package directory.

package/.docs/organized/changelogs/mastra.md

@@ -1,5 +1,64 @@
 # mastra
 
+## 0.10.19-alpha.1
+
+### Patch Changes
+
+- ea0c5f2: Update to support new scorer api
+- 35c5798: Add support for transpilePackages option
+- Updated dependencies [7b8172f]
+- Updated dependencies [ea0c5f2]
+- Updated dependencies [b0e43c1]
+- Updated dependencies [1fb812e]
+- Updated dependencies [35c5798]
+  - @mastra/deployer@0.13.0-alpha.1
+  - @mastra/core@0.13.0-alpha.1
+
+## 0.10.19-alpha.0
+
+### Patch Changes
+
+- Updated dependencies [94f4812]
+- Updated dependencies [e202b82]
+- Updated dependencies [e00f6a0]
+  - @mastra/core@0.12.2-alpha.0
+  - @mastra/deployer@0.12.2-alpha.0
+
+## 0.10.18
+
+### Patch Changes
+
+- ad04455: Missed changeset in last release, needed to include create-mastra
+
+## 0.10.18-alpha.0
+
+### Patch Changes
+
+- ad04455: Missed changeset in last release, needed to include create-mastra
+
+## 0.10.17
+
+### Patch Changes
+
+- 9862477: Install specific ai v4 deps when scaffolding a project
+- 33dcb07: dependencies updates:
+  - Updated dependency [`@opentelemetry/instrumentation@^0.203.0` ↗︎](https://www.npmjs.com/package/@opentelemetry/instrumentation/v/0.203.0) (from `^0.202.0`, in `dependencies`)
+  - Updated dependency [`@opentelemetry/auto-instrumentations-node@^0.62.0` ↗︎](https://www.npmjs.com/package/@opentelemetry/auto-instrumentations-node/v/0.62.0) (from `^0.60.1`, in `dependencies`)
+  - Updated dependency [`@opentelemetry/exporter-trace-otlp-grpc@^0.203.0` ↗︎](https://www.npmjs.com/package/@opentelemetry/exporter-trace-otlp-grpc/v/0.203.0) (from `^0.202.0`, in `dependencies`)
+  - Updated dependency [`@opentelemetry/exporter-trace-otlp-http@^0.203.0` ↗︎](https://www.npmjs.com/package/@opentelemetry/exporter-trace-otlp-http/v/0.203.0) (from `^0.202.0`, in `dependencies`)
+  - Updated dependency [`@opentelemetry/sdk-node@^0.203.0` ↗︎](https://www.npmjs.com/package/@opentelemetry/sdk-node/v/0.203.0) (from `^0.202.0`, in `dependencies`)
+  - Updated dependency [`@opentelemetry/semantic-conventions@^1.36.0` ↗︎](https://www.npmjs.com/package/@opentelemetry/semantic-conventions/v/1.36.0) (from `^1.34.0`, in `dependencies`)
+- Updated dependencies [33dcb07]
+- Updated dependencies [f90797b]
+- Updated dependencies [d0d9500]
+- Updated dependencies [d30b1a0]
+- Updated dependencies [bff87f7]
+- Updated dependencies [07fe7a2]
+- Updated dependencies [b4a8df0]
+  - @mastra/core@0.12.1
+  - @mastra/mcp@0.10.9
+  - @mastra/deployer@0.12.1
+
 ## 0.10.17-alpha.1
 
 ### Patch Changes
@@ -239,64 +298,5 @@
 - Updated dependencies [45469c5]
 - Updated dependencies [40c2525]
 - Updated dependencies [e473f27]
-- Updated dependencies [032cb66]
-- Updated dependencies [24eb25c]
-- Updated dependencies [703ac71]
-- Updated dependencies [a723d69]
-- Updated dependencies [4c06f06]
-- Updated dependencies [5889a31]
-- Updated dependencies [65e3395]
-- Updated dependencies [9de6f58]
-- Updated dependencies [4933192]
-- Updated dependencies [d1c77a4]
-- Updated dependencies [bea9dd1]
-- Updated dependencies [dcd4802]
-- Updated dependencies [7ba91fa]
-- Updated dependencies [15ce274]
-  - @mastra/core@0.11.0-alpha.2
-  - @mastra/deployer@0.11.0-alpha.2
-
-## 0.10.14-alpha.1
-
-### Patch Changes
-
-- 8f89bcd: fix traces pagination + sharing trace view with cloud
-- 59f0dcd: Add light background color for step statuses
-- cf8d497: factorize tabs component between cloud and core
-- 80692d5: refactor: sharing only the UI and not data fetching for traces
-- Updated dependencies [7983e53]
-  - @mastra/deployer@0.11.0-alpha.1
-  - @mastra/core@0.11.0-alpha.1
-
-## 0.10.14-alpha.0
-
-### Patch Changes
-
-- 0bf0bc8: fix link in shared components + add e2e tests
-- 7827943: Handle streaming large data
-- 808b493: wrap runtime context with tooltip provider for usage in cloud
-- Updated dependencies [0938991]
-- Updated dependencies [6f50efd]
-- Updated dependencies [bf6903e]
-- Updated dependencies [7827943]
-- Updated dependencies [bf1e7e7]
-- Updated dependencies [cbddd18]
-  - @mastra/deployer@0.11.0-alpha.0
-  - @mastra/core@0.11.0-alpha.0
-
-## 0.10.13
-
-### Patch Changes
 
-- 593631d: allow to pass ref to the link abstraction
-- 5237998: Fix foreach output
-- 1aa60b1: Pipe runtimeContext to vNext network agent stream and generate steps, wire up runtimeContext for vNext Networks in cliet SDK & playground
-- d49334d: export tool list for usage in cloud
-- 9cdfcb5: fix infinite rerenders on agents table + share runtime context for cloud
-- 794d9f3: Fix thread creation in playground
-- 5130bcb: dependencies updates:
-  - Updated dependency [`swr@^2.3.4` ↗︎](https://www.npmjs.com/package/swr/v/2.3.4) (from `^2.3.3`, in `dependencies`)
-- 984887a: dependencies updates:
-  - Updated dependency [`prettier@^3.6.2` ↗︎](https://www.npmjs.com/package/prettier/v/3.6.2) (from `^3.5.3`, in `dependencies`)
-
-... 4683 more lines hidden. See full changelog in package directory.
+... 4742 more lines hidden. See full changelog in package directory.

package/.docs/organized/code-examples/memory-per-resource-example.md

@@ -66,33 +66,33 @@ const userChoice = await new Promise<string>(resolve => {
   });
 });
 
-let resourceId: string;
+let resource: string;
 let userName: string;
 
 switch (userChoice) {
   case '1':
-    resourceId = USERS.alice;
+    resource = USERS.alice;
     userName = 'Alice';
     break;
   case '2':
-    resourceId = USERS.bob;
+    resource = USERS.bob;
     userName = 'Bob';
     break;
   case '3':
-    resourceId = USERS.demo;
+    resource = USERS.demo;
     userName = 'Demo User';
     break;
   default:
-    resourceId = `user-${randomUUID()}`;
+    resource = `user-${randomUUID()}`;
     userName = 'Random User';
 }
 
 // Always generate a new thread ID to demonstrate cross-thread persistence
-const threadId = randomUUID();
+const thread = randomUUID();
 
 console.log(chalk.green(`\n✅ Simulating: ${userName}`));
-console.log(chalk.gray(`📧 Resource ID: ${resourceId}`));
-console.log(chalk.gray(`🧵 Thread ID: ${threadId}`));
+console.log(chalk.gray(`📧 Resource ID: ${resource}`));
+console.log(chalk.gray(`🧵 Thread ID: ${thread}`));
 console.log(chalk.bold.yellow('\n💡 TIP: Run this example multiple times with the same user choice'));
 console.log(chalk.bold.yellow('   to see how working memory persists across conversation threads!\n'));
 
@@ -130,7 +130,7 @@ async function main() {
         If this is a returning user, greet them warmly and reference what you remember!`,
         },
       ],
-      { threadId, resourceId },
+      { memory: { thread, resource } },
     ),
   );
 
@@ -147,7 +147,7 @@ async function main() {
       break;
     }
 
-    await logResponse(await agent.stream(userInput, { threadId, resourceId }));
+    await logResponse(await agent.stream(userInput, { memory: { thread, resource } }));
   }
 
   rl.close();

package/.docs/organized/code-examples/memory-with-libsql.md

@@ -21,12 +21,12 @@ import { mastra } from './mastra';
 
 const agent = mastra.getAgent('memoryAgent');
 
-let threadId = randomUUID();
+let thread = randomUUID();
 // use this to play with a long running conversation. comment it out to get a new thread id every time
-threadId = `f45a59b3-d9da-4a2a-8348-9386e4e621a3`;
-console.log(threadId);
+thread = `f45a59b3-d9da-4a2a-8348-9386e4e621a3`;
+console.log(thread);
 
-const resourceId = 'SOME_USER_ID';
+const resource = 'SOME_USER_ID';
 
 async function logRes(res: Awaited<ReturnType<typeof agent.stream>>) {
   console.log(`\n🤖 Agent:`);
@@ -45,7 +45,7 @@ async function main() {
           content: `Chat with user started now ${new Date().toISOString()}. Don't mention this message. This means some time may have passed between this message and the one before. The user left and came back again. Say something to start the conversation up again. If there are no other messages besides this one then this is a new conversation.`,
         },
       ],
-      { resourceId, threadId },
+      { memory: { resource, thread } },
     ),
   );
 
@@ -63,8 +63,7 @@ async function main() {
 
     await logRes(
       await agent.stream(prompt, {
-        threadId,
-        resourceId,
+        memory: { thread, resource },
       }),
     );
   }

package/.docs/organized/code-examples/memory-with-pg.md

@@ -26,13 +26,13 @@ import { mastra } from './mastra';
 
 const agent = mastra.getAgent('memoryAgent');
 
-let threadId = randomUUID();
+let thread = randomUUID();
 // use this to play with a long running conversation. comment it out to get a new thread id every time
-threadId = `39873fbf-84d6-425e-8c1b-8afd798d72a4`;
-// threadId = `12569b14-3e16-4e31-8130-8d9676f1932c`;
-console.log(threadId);
+thread = `39873fbf-84d6-425e-8c1b-8afd798d72a4`;
+// thread = `12569b14-3e16-4e31-8130-8d9676f1932c`;
+console.log(thread);
 
-const resourceId = 'SOME_USER_ID';
+const resource = 'SOME_USER_ID';
 
 async function logRes(res: Awaited<ReturnType<typeof agent.stream>>) {
   console.log(`\n🤖 Agent:`);
@@ -51,7 +51,7 @@ async function main() {
           content: `Chat with user started now ${new Date().toISOString()}. Don't mention this message. This means some time may have passed between this message and the one before. The user left and came back again. Say something to start the conversation up again.`,
         },
       ],
-      { resourceId, threadId },
+      { memory: { resource, thread } },
     ),
   );
 
@@ -69,8 +69,7 @@ async function main() {
 
     await logRes(
       await agent.stream(prompt, {
-        threadId,
-        resourceId,
+        memory: { thread, resource },
       }),
     );
   }

package/.docs/raw/agents/agent-memory.mdx

@@ -165,22 +165,26 @@ const response = await agent.generate("Remember my favorite color is blue.", {
 
 ## Using Memory in Agent Calls
 
-To utilize memory during interactions, you **must** provide `resourceId` and `threadId` when calling the agent's `stream()` or `generate()` methods.
+To utilize memory during interactions, you **must** provide a `memory` object with `resource` and `thread` properties when calling the agent's `stream()` or `generate()` methods.
 
-- `resourceId`: Typically identifies the user or entity (e.g., `user_123`).
-- `threadId`: Identifies a specific conversation thread (e.g., `support_chat_456`).
+- `resource`: Typically identifies the user or entity (e.g., `user_123`).
+- `thread`: Identifies a specific conversation thread (e.g., `support_chat_456`).
 
 ```typescript
 // Example agent call using memory
 await agent.stream("Remember my favorite color is blue.", {
-  resourceId: "user_alice",
-  threadId: "preferences_thread",
+  memory: {
+    resource: "user_alice",
+    thread: "preferences_thread",
+  },
 });
 
 // Later in the same thread...
 const response = await agent.stream("What's my favorite color?", {
-  resourceId: "user_alice",
-  threadId: "preferences_thread",
+  memory: {
+    resource: "user_alice",
+    thread: "preferences_thread",
+  },
 });
 // Agent will use memory to recall the favorite color.
 ```

package/.docs/raw/memory/semantic-recall.mdx

@@ -2,6 +2,8 @@
 
 If you ask your friend what they did last weekend, they will search in their memory for events associated with "last weekend" and then tell you what they did. That's sort of like how semantic recall works in Mastra.
 
+> **📹 Watch**: What semantic recall is, how it works, and how to configure it in Mastra → [YouTube (5 minutes)](https://youtu.be/UVZtK8cK8xQ)
+
 ## How Semantic Recall Works
 
 Semantic recall is RAG-based search that helps agents maintain context across longer interactions when messages are no longer within [recent conversation history](./overview.mdx#conversation-history).

package/.docs/raw/memory/working-memory.mdx

@@ -43,7 +43,7 @@ const agent = new Agent({
 
 Working memory is a block of Markdown text that the agent is able to update over time to store continuously relevant information:
 
-<YouTube id="ik-ld_XA96s" />
+<YouTube id="UMy_JHLf1n8" />
 
 ## Memory Persistence Scopes
 

package/.docs/raw/rag/chunking-and-embedding.mdx

@@ -25,21 +25,37 @@ Use `chunk` to split documents into manageable pieces. Mastra supports multiple
 - `html`: HTML structure-aware splitting
 - `json`: JSON structure-aware splitting
 - `latex`: LaTeX structure-aware splitting
+- `sentence`: Sentence-aware splitting
+
+**Note:** Each strategy accepts different parameters optimized for its chunking approach.
 
 Here's an example of how to use the `recursive` strategy:
 
 ```ts showLineNumbers copy
 const chunks = await doc.chunk({
   strategy: "recursive",
-  size: 512,
+  maxSize: 512,
   overlap: 50,
-  separator: "\n",
+  separators: ["\n"],
   extract: {
     metadata: true, // Optionally extract metadata
   },
 });
 ```
 
+For text where preserving sentence structure is important, here's an example of how to use the `sentence` strategy:
+
+```ts showLineNumbers copy
+const chunks = await doc.chunk({
+  strategy: "sentence",
+  maxSize: 450,
+  minSize: 50,
+  overlap: 0,
+  sentenceEnders: ["."],
+  keepSeparator: true,
+});
+```
+
 **Note:** Metadata extraction may use LLM calls, so ensure your API key is set.
 
 We go deeper into chunking strategies in our [chunk documentation](/reference/rag/chunk.mdx).
@@ -130,7 +146,7 @@ const doc = MDocument.fromText(`
 // Create chunks
 const chunks = await doc.chunk({
   strategy: "recursive",
-  size: 256,
+  maxSize: 256,
   overlap: 50,
 });
 

package/.docs/raw/reference/memory/getThreadsByResourceId.mdx

@@ -75,6 +75,7 @@ interface ThreadSortOptions {
 ### Related
 
 - [Memory Class Reference](/reference/memory/Memory.mdx)
+- [getThreadsByResourceIdPaginated](/reference/memory/getThreadsByResourceIdPaginated.mdx) - Paginated version
 - [Getting Started with Memory](/docs/memory/overview.mdx) (Covers threads/resources concept)
 - [createThread](/reference/memory/createThread.mdx)
 - [getThreadById](/reference/memory/getThreadById.mdx)