@mastra/memory 1.21.1-alpha.0 → 1.21.1

package/CHANGELOG.md

@@ -1,5 +1,29 @@
 # @mastra/memory
 
+## 1.21.1
+
+### Patch Changes
+
+- Fixed direct memory recall so semantic recall score thresholds filter recalled messages. ([#18211](https://github.com/mastra-ai/mastra/pull/18211))
+
+- Fixed semantic recall failing on long unbroken content. When a memory-enabled agent received a message containing a single very long whitespace-free string — a base64 data URI, a minified JS/JSON blob, a long URL, or spaceless CJK text — embedding could throw a provider "maximum context length" error and break that turn's persistence or recall. ([#18236](https://github.com/mastra-ai/mastra/pull/18236))
+
+  `chunkText` now hard-splits any single word that is longer than the chunk budget so every chunk stays under the embedder's token limit, and it no longer emits an empty leading chunk when the first word is oversized.
+
+- Updated dependencies [[`5bd72d2`](https://github.com/mastra-ai/mastra/commit/5bd72d255f45b5ea8ab342643bd463814a980a24), [`1cc9ee1`](https://github.com/mastra-ai/mastra/commit/1cc9ee1ba51db53020a735626d33017a60b4b5b3), [`417baae`](https://github.com/mastra-ai/mastra/commit/417baae40b995db5819c845036947f0c27dc1c00), [`65f255a`](https://github.com/mastra-ai/mastra/commit/65f255a38667beb6ceeadabfa9eb5059bfec8298), [`74955f9`](https://github.com/mastra-ai/mastra/commit/74955f9120cde8b1d8ce4399232b4033236be858), [`30ebaf0`](https://github.com/mastra-ai/mastra/commit/30ebaf07bed5f4d30f2f257836c15d1bf7e40aae), [`5704634`](https://github.com/mastra-ai/mastra/commit/5704634b22133167dea337a942a34f57aaa3fa14), [`5c4e9a4`](https://github.com/mastra-ai/mastra/commit/5c4e9a4cfb2216bb3ea7f8988ad3727f3b92bb3a), [`4a88c6e`](https://github.com/mastra-ai/mastra/commit/4a88c6e2bdce316f8d7551b4ec3449b0b06fc71c), [`417baae`](https://github.com/mastra-ai/mastra/commit/417baae40b995db5819c845036947f0c27dc1c00), [`74955f9`](https://github.com/mastra-ai/mastra/commit/74955f9120cde8b1d8ce4399232b4033236be858), [`74955f9`](https://github.com/mastra-ai/mastra/commit/74955f9120cde8b1d8ce4399232b4033236be858), [`25961e3`](https://github.com/mastra-ai/mastra/commit/25961e3260ff3b1464637af8fcdb36210551c39f), [`6a1428a`](https://github.com/mastra-ai/mastra/commit/6a1428a23133fc070fc6c1caa08d28f3ba4fe5ff), [`87a17ef`](https://github.com/mastra-ai/mastra/commit/87a17efbd725aca6639febdc5e69e2abb3048689), [`e11ff30`](https://github.com/mastra-ai/mastra/commit/e11ff301408bf1731dca2fb7fbfcd8c819500a35), [`7794d71`](https://github.com/mastra-ai/mastra/commit/7794d71872c68733a30e028dfb7b1705daf6c5d2), [`9d2c946`](https://github.com/mastra-ai/mastra/commit/9d2c946d0859e90ae4bcec5beeb1da7398d2ad1e), [`c0eda2b`](https://github.com/mastra-ai/mastra/commit/c0eda2bcd91a228427314b12c91d8b147f3a739f), [`7b29f33`](https://github.com/mastra-ai/mastra/commit/7b29f332a357a83e555f29e718e5f2fab9979943), [`c0eda2b`](https://github.com/mastra-ai/mastra/commit/c0eda2bcd91a228427314b12c91d8b147f3a739f), [`b13925b`](https://github.com/mastra-ai/mastra/commit/b13925bfa91aa8700f56fa54a9ce707ee7e4ba62), [`f1ec385`](https://github.com/mastra-ai/mastra/commit/f1ec385386f62b1a0847ec5353ae2bb169d1c3d9), [`e14986f`](https://github.com/mastra-ai/mastra/commit/e14986f6e5478d6384d04ff9a7f9a79a46a8b529), [`24912b1`](https://github.com/mastra-ai/mastra/commit/24912b1f855d29ec36af4ef4bde1f7417e20cdf5), [`bf94ec6`](https://github.com/mastra-ai/mastra/commit/bf94ec68192d9f16e46ef7e5ac36370aeeddf35d), [`a29f371`](https://github.com/mastra-ai/mastra/commit/a29f371aef629ac8562661524a497127e93b5131), [`7686216`](https://github.com/mastra-ai/mastra/commit/7686216f37e74568feddec17cef3c3d24e10e60a), [`74955f9`](https://github.com/mastra-ai/mastra/commit/74955f9120cde8b1d8ce4399232b4033236be858), [`073f910`](https://github.com/mastra-ai/mastra/commit/073f910481e7d94b95ba3830f96531774ae95d33), [`0be490f`](https://github.com/mastra-ai/mastra/commit/0be490fabb538c5a7de796ea0aff7d04a0bea1f3), [`0be490f`](https://github.com/mastra-ai/mastra/commit/0be490fabb538c5a7de796ea0aff7d04a0bea1f3), [`ebbe1d3`](https://github.com/mastra-ai/mastra/commit/ebbe1d31a965a3adb0e728758f326b8122b4b55f), [`974f614`](https://github.com/mastra-ai/mastra/commit/974f614e083bd68278536f94453f7b320b86a3c7), [`3818814`](https://github.com/mastra-ai/mastra/commit/38188149ce454c4403fe9fcbdf73b735c68d36be), [`975c59a`](https://github.com/mastra-ai/mastra/commit/975c59ae363ee275fc55062392e1ffd2cbccbd53), [`1f97ce5`](https://github.com/mastra-ai/mastra/commit/1f97ce5695463bebb4eaacf501da6fb403e20885), [`74955f9`](https://github.com/mastra-ai/mastra/commit/74955f9120cde8b1d8ce4399232b4033236be858), [`7f51548`](https://github.com/mastra-ai/mastra/commit/7f515481213780be7047cef00640b9d35f3d545c), [`64f58c0`](https://github.com/mastra-ai/mastra/commit/64f58c04e78b40137497d47f781e897e416f22a5), [`74955f9`](https://github.com/mastra-ai/mastra/commit/74955f9120cde8b1d8ce4399232b4033236be858), [`ebbe1d3`](https://github.com/mastra-ai/mastra/commit/ebbe1d31a965a3adb0e728758f326b8122b4b55f), [`d95f394`](https://github.com/mastra-ai/mastra/commit/d95f394fd24c8411886930d727679c4d5252aa26), [`417baae`](https://github.com/mastra-ai/mastra/commit/417baae40b995db5819c845036947f0c27dc1c00), [`8e25a78`](https://github.com/mastra-ai/mastra/commit/8e25a78e0597575f0b0729bae8c5e190c84869b5), [`417baae`](https://github.com/mastra-ai/mastra/commit/417baae40b995db5819c845036947f0c27dc1c00), [`f3f0c9d`](https://github.com/mastra-ai/mastra/commit/f3f0c9d7c878db5a13177871ce3523a14f14b311), [`a5b22d3`](https://github.com/mastra-ai/mastra/commit/a5b22d314d62a68d801886a8d3d0eb6c089473db), [`31be1cf`](https://github.com/mastra-ai/mastra/commit/31be1cf5f2a7b5eef12f6123a40653b4d8115c16), [`417baae`](https://github.com/mastra-ai/mastra/commit/417baae40b995db5819c845036947f0c27dc1c00), [`74955f9`](https://github.com/mastra-ai/mastra/commit/74955f9120cde8b1d8ce4399232b4033236be858), [`74955f9`](https://github.com/mastra-ai/mastra/commit/74955f9120cde8b1d8ce4399232b4033236be858)]:
+  - @mastra/core@1.46.0
+
+## 1.21.1-alpha.1
+
+### Patch Changes
+
+- Fixed semantic recall failing on long unbroken content. When a memory-enabled agent received a message containing a single very long whitespace-free string — a base64 data URI, a minified JS/JSON blob, a long URL, or spaceless CJK text — embedding could throw a provider "maximum context length" error and break that turn's persistence or recall. ([#18236](https://github.com/mastra-ai/mastra/pull/18236))
+
+  `chunkText` now hard-splits any single word that is longer than the chunk budget so every chunk stays under the embedder's token limit, and it no longer emits an empty leading chunk when the first word is oversized.
+
+- Updated dependencies [[`65f255a`](https://github.com/mastra-ai/mastra/commit/65f255a38667beb6ceeadabfa9eb5059bfec8298), [`4a88c6e`](https://github.com/mastra-ai/mastra/commit/4a88c6e2bdce316f8d7551b4ec3449b0b06fc71c), [`87a17ef`](https://github.com/mastra-ai/mastra/commit/87a17efbd725aca6639febdc5e69e2abb3048689), [`e11ff30`](https://github.com/mastra-ai/mastra/commit/e11ff301408bf1731dca2fb7fbfcd8c819500a35), [`9d2c946`](https://github.com/mastra-ai/mastra/commit/9d2c946d0859e90ae4bcec5beeb1da7398d2ad1e), [`f1ec385`](https://github.com/mastra-ai/mastra/commit/f1ec385386f62b1a0847ec5353ae2bb169d1c3d9), [`e14986f`](https://github.com/mastra-ai/mastra/commit/e14986f6e5478d6384d04ff9a7f9a79a46a8b529), [`0be490f`](https://github.com/mastra-ai/mastra/commit/0be490fabb538c5a7de796ea0aff7d04a0bea1f3), [`0be490f`](https://github.com/mastra-ai/mastra/commit/0be490fabb538c5a7de796ea0aff7d04a0bea1f3), [`974f614`](https://github.com/mastra-ai/mastra/commit/974f614e083bd68278536f94453f7b320b86a3c7), [`31be1cf`](https://github.com/mastra-ai/mastra/commit/31be1cf5f2a7b5eef12f6123a40653b4d8115c16)]:
+  - @mastra/core@1.46.0-alpha.3
+
 ## 1.21.1-alpha.0
 
 ### Patch Changes

package/dist/docs/SKILL.md

@@ -3,7 +3,7 @@ name: mastra-memory
 description: Documentation for @mastra/memory. Use when working with @mastra/memory APIs, configuration, or implementation.
 metadata:
   package: "@mastra/memory"
-  version: "1.21.1-alpha.0"
+  version: "1.21.1"
 ---
 
 ## When to use

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.21.1-alpha.0",
+  "version": "1.21.1",
   "package": "@mastra/memory",
   "exports": {
     "ModelByInputTokens": {

package/dist/docs/references/docs-agents-background-tasks.md

@@ -2,7 +2,7 @@
 
 **Added in:** `@mastra/core@1.29.0`
 
-Background tasks let an agent dispatch a long-running tool call without blocking the agentic loop. The tool returns an immediate acknowledgement, the LLM continues responding, and the task runs to completion in the background. When it finishes, its result is written to memory and if you use [`streamUntilIdle()`](https://mastra.ai/reference/streaming/agents/streamUntilIdle) the agent is re-invoked automatically so the result is processed in the same call.
+Background tasks let an agent dispatch a long-running tool call without blocking the agentic loop. The tool returns an immediate acknowledgement, the LLM continues responding, and the task runs to completion in the background. When it finishes, its result is written to memory and if you use `stream()` with the [`untilIdle`](https://mastra.ai/reference/agents/agent) option the agent is re-invoked automatically so the result is processed in the same call.
 
 ## When to use background tasks
 
@@ -119,7 +119,7 @@ If the agent has `backgroundTasks.disabled: true`, every tool call runs synchron
 
 ## Background tasks related stream chunks
 
-When a tool call dispatches as a background task, two streams may surface lifecycle events for it: the agent's own stream and the [`backgroundTaskManager.stream()`](https://mastra.ai/docs/streaming/background-task-streaming) SSE stream. Each stream covers a different set of chunk types:
+When a tool call dispatches as a background task, two streams may surface lifecycle events for it: the agent's own stream and the [`backgroundTaskManager.stream()`](https://mastra.ai/docs/agents/background-tasks) SSE stream. Each stream covers a different set of chunk types:
 
 | Chunk type                  | When it fires                                                                          | Emitted by     |
 | --------------------------- | -------------------------------------------------------------------------------------- | -------------- |
@@ -133,20 +133,20 @@ When a tool call dispatches as a background task, two streams may surface lifecy
 | `background-task-suspended` | The tool called `suspend()` from inside its execute.                                   | Manager stream |
 | `background-task-resumed`   | A suspended task was resumed via `manager.resume(taskId, resumeData)`.                 | Manager stream |
 
-`agent.stream().fullStream` only emits the agent-loop chunks (`background-task-started`, `background-task-progress`) on its own. `agent.streamUntilIdle()` emits the same two chunks and additionally subscribes to the manager pubsub for the run's memory scope and pipes the seven manager chunks (`background-task-running`, `background-task-output`, `background-task-completed`, `background-task-failed`, `background-task-cancelled`, `background-task-suspended`, `background-task-resumed`) into the same `fullStream`.
+`agent.stream().fullStream` only emits the agent-loop chunks (`background-task-started`, `background-task-progress`) on its own. `agent.stream()` with `untilIdle: true` emits the same two chunks and additionally subscribes to the manager pubsub for the run's memory scope and pipes the seven manager chunks (`background-task-running`, `background-task-output`, `background-task-completed`, `background-task-failed`, `background-task-cancelled`, `background-task-suspended`, `background-task-resumed`) into the same `fullStream`.
 
 `backgroundTaskManager.stream()` only emits the seven manager chunks.
 
 The full payload shapes are documented in the [background task chunks reference](https://mastra.ai/reference/streaming/ChunkType).
 
-## Keep the agent stream open with `streamUntilIdle()`
+## Keep the agent stream open with `untilIdle`
 
-`agent.stream()` returns once the LLM emits a final response even if a background task is still running. Use `agent.streamUntilIdle()` when you want the stream to stay open until every dispatched background task has completed and the LLM has had a chance to respond to the result:
+`agent.stream()` returns once the LLM emits a final response even if a background task is still running. Pass `untilIdle: true` when you want the stream to stay open until every dispatched background task has completed and the LLM has had a chance to respond to the result:
 
 ```typescript
-const stream = await agent.streamUntilIdle('Research solana for me', {
+const stream = await agent.stream('Research solana for me', {
   memory: { thread: 't1', resource: 'u1' },
-  maxIdleMs: 5 * 60_000,
+  untilIdle: true,
 })
 
 for await (const chunk of stream.fullStream) {
@@ -155,15 +155,22 @@ for await (const chunk of stream.fullStream) {
 }
 ```
 
-When a background task completes, the result is injected into the agent memory, `streamUntilIdle()` re-enters the agentic loop so the LLM can react to it. The stream closes when no tasks are running and no completions are queued.
+When a background task completes, the result is injected into the agent memory, `stream()` re-enters the agentic loop so the LLM can react to it. The stream closes when no tasks are running and no completions are queued.
 
-`maxIdleMs` caps how long the stream waits between turns. The timer only runs while the wrapper is between turns, so a slow first token won't close the stream. The default is 5 minutes.
+Customize the idle timeout by passing an object instead of `true`. The timer only runs while the wrapper is between turns, so a slow first token won't close the stream. The default is 5 minutes:
 
-> **Note:** Visit [`Agent.streamUntilIdle()`](https://mastra.ai/reference/streaming/agents/streamUntilIdle) for the full API.
+```typescript
+const stream = await agent.stream('Research solana for me', {
+  memory: { thread: 't1', resource: 'u1' },
+  untilIdle: { maxIdleMs: 30_000 },
+})
+```
+
+> **Note:** Visit [`Agent.stream()`](https://mastra.ai/reference/agents/agent) for the full API.
 
 ### Aggregate properties
 
-`streamUntilIdle()` returns a `MastraModelOutput` that looks like the one from `stream()`, but only `fullStream` spans the initial turn **and** any auto-continuations. Aggregate properties (`text`, `toolCalls`, `toolResults`, `finishReason`, `messageList`, `getFullOutput()`) still resolve against the **first turn's** internal buffer. If you need an aggregate view across continuations, consume `fullStream` yourself and accumulate.
+`stream()` with `untilIdle` returns a `MastraModelOutput` that looks like the one from a regular `stream()` call, but only `fullStream` spans the initial turn **and** any auto-continuations. Aggregate properties (`text`, `toolCalls`, `toolResults`, `finishReason`, `messageList`, `getFullOutput()`) still resolve against the **first turn's** internal buffer. If you need an aggregate view across continuations, consume `fullStream` yourself and accumulate.
 
 ## Subagents in the background
 
@@ -185,8 +192,9 @@ const supervisor = new Agent({
   },
 })
 
-const stream = await supervisor.streamUntilIdle('Research AI in education and write an article', {
+const stream = await supervisor.stream('Research AI in education and write an article', {
   memory: { thread: 't1', resource: 'u1' },
+  untilIdle: true,
 })
 ```
 
@@ -263,7 +271,7 @@ await mastra.backgroundTaskManager?.resume(taskId, {
 
 ### What happens to the agent loop
 
-When a task suspends mid-`streamUntilIdle()`, the wrapper treats it as terminal for the current iteration and closes. To continue the agent immediately when the resume payload is in hand, call `agent.resumeStreamUntilIdle(resumeData, { runId, toolCallId, memory })`: the resumed bg task runs to completion, its result lands in the message list, and the agent runs a follow-up turn — all on the same SSE connection. If you'd rather drive the resume out-of-band, call `mastra.backgroundTaskManager.resume(taskId, resumeData)` directly and the result still writes into the thread for the next user turn to pick up.
+When a task suspends mid-`stream()` with `untilIdle`, the wrapper treats it as terminal for the current iteration and closes. To continue the agent immediately when the resume payload is in hand, call `agent.resumeStream(resumeData, { runId, toolCallId, memory, untilIdle: true })`: the resumed bg task runs to completion, its result lands in the message list, and the agent runs a follow-up turn — all on the same SSE connection. If you'd rather drive the resume out-of-band, call `mastra.backgroundTaskManager.resume(taskId, resumeData)` directly and the result still writes into the thread for the next user turn to pick up.
 
 ### Re-registering the executor on resume
 
@@ -296,10 +304,77 @@ export const mastra = new Mastra({
 })
 ```
 
+## Streaming
+
+### Subscribe to all task events
+
+Calling `stream()` with no filter returns a stream of every task event in the system. On connection, the stream emits a snapshot of all currently running tasks, then forwards live events as they happen.
+
+```typescript
+const bgManager = mastra.backgroundTaskManager
+if (!bgManager) throw new Error('Background tasks are not enabled')
+
+const controller = new AbortController()
+const stream = bgManager.stream({ abortSignal: controller.signal })
+
+for await (const chunk of stream) {
+  switch (chunk.type) {
+    case 'background-task-running':
+      console.log('started', chunk.payload.taskId, chunk.payload.toolName)
+      break
+    case 'background-task-completed':
+      console.log('done', chunk.payload.taskId, chunk.payload.result)
+      break
+    case 'background-task-failed':
+      console.error('failed', chunk.payload.taskId, chunk.payload.error)
+      break
+  }
+}
+```
+
+The stream stays open until the caller's `AbortSignal` fires. Always pass an `abortSignal` so you can disconnect cleanly.
+
+### Filter the stream
+
+Pass any combination of filter options to narrow the events you receive. Filters apply to both the initial snapshot and the live event subscription.
+
+```typescript
+const stream = bgManager.stream({
+  agentId: 'researcher',
+  threadId: 't1',
+  resourceId: 'u1',
+  abortSignal: controller.signal,
+})
+```
+
+| Filter        | Description                                         |
+| ------------- | --------------------------------------------------- |
+| `agentId`     | Only events from tasks dispatched by this agent     |
+| `runId`       | Only events from this specific agent run            |
+| `threadId`    | Only events from tasks scoped to this memory thread |
+| `resourceId`  | Only events from tasks scoped to this resource      |
+| `taskId`      | Only events for a single task                       |
+| `abortSignal` | Closes the stream when the signal aborts            |
+
+### Look up task state directly
+
+For one-off lookups instead of a live stream, use `getTask` and `listTasks`:
+
+```typescript
+const task = await mastra.backgroundTaskManager?.getTask(taskId)
+const { tasks, total } = await mastra.backgroundTaskManager?.listTasks({
+  status: 'running',
+  agentId: 'researcher',
+})
+```
+
+These read from storage rather than the pubsub stream, so they're suitable for paginated lists and detail views.
+
 ## Related
 
-- [`Agent.streamUntilIdle()` reference](https://mastra.ai/reference/streaming/agents/streamUntilIdle)
+- [`Agent.stream()` reference](https://mastra.ai/reference/agents/agent)
 - [backgroundTasks configuration reference](https://mastra.ai/reference/configuration)
+- [Durable agents](https://mastra.ai/docs/agents/durable-agents)
 - [Supervisor agents](https://mastra.ai/docs/agents/supervisor-agents)
 - [Stream chunk types](https://mastra.ai/reference/streaming/ChunkType)
 - [Storage](https://mastra.ai/docs/memory/storage)

package/dist/index.cjs

@@ -47670,9 +47670,21 @@ ${workingMemory}`;
     let currentChunk = "";
     const words = text4.split(/\s+/);
     for (const word of words) {
+      if (word.length > charSize) {
+        if (currentChunk) {
+          chunks.push(currentChunk);
+          currentChunk = "";
+        }
+        for (let i = 0; i < word.length; i += charSize) {
+          chunks.push(word.slice(i, i + charSize));
+        }
+        continue;
+      }
       const wordWithSpace = currentChunk ? " " + word : word;
       if (currentChunk.length + wordWithSpace.length > charSize) {
-        chunks.push(currentChunk);
+        if (currentChunk) {
+          chunks.push(currentChunk);
+        }
         currentChunk = word;
       } else {
         currentChunk += wordWithSpace;