@mastra/client-js 1.53.0-alpha.5 → 1.53.0-alpha.6

package/dist/docs/SKILL.md

@@ -3,7 +3,7 @@ name: mastra-client-js
 description: Documentation for @mastra/client-js. Use when working with @mastra/client-js APIs, configuration, or implementation.
 metadata:
   package: "@mastra/client-js"
-  version: "1.53.0-alpha.5"
+  version: "1.53.0-alpha.6"
 ---
 
 ## When to use

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.53.0-alpha.5",
+  "version": "1.53.0-alpha.6",
   "package": "@mastra/client-js",
   "exports": {},
   "modules": {}

package/dist/docs/references/docs-harness-signals.md

@@ -48,6 +48,18 @@ for await (const chunk of subscription.stream) {
 
 When the thread has a running agent stream, `sendMessage()` becomes new input inside that agent loop. When the thread is idle, Mastra starts a stream with the message as the first input.
 
+### Input during reasoning
+
+In the default agent loop, accepted pending messages and signals interrupt a model request that has produced only reasoning or metadata. This includes the wait for its first token. Mastra cancels that request, discards its response from model history and memory, and includes queued input in the next request within the same run. Earlier completed responses stay in history.
+
+Once text, tool calls, or other response content starts, signals wait for the next loop boundary. Running tools aren't cancelled or repeated. If the run reaches `maxSteps`, queued input may be saved without a response. `queueMessage()` still waits for the active run to finish. Signals that processors write directly to the message history don't interrupt their own request.
+
+Interrupted requests don't count toward `maxSteps` or advance `stepNumber`. The next request uses the same logical step, so `maxSteps: 1` still allows a replacement response. Mastra doesn't set a separate interruption limit. Repeated signals can keep restarting reasoning until a request completes, the run is cancelled, or its total timeout expires.
+
+Already-streamed reasoning may remain visible until the client reloads history. When input arrives while per-step input processors (`processInputStep`) run, the processors finish and Mastra cancels the model request they prepared. Custom output processors also keep running after a cancellation, and the next request waits for their in-flight work to settle. Mastra discards framework-owned response buffers, but doesn't undo processor state, data that processors write while the cancelled request settles, or external side effects. Usage totals exclude interrupted requests, including any usage the provider reports for them. Providers may still bill for those requests.
+
+This reasoning interruption applies to the default loop, not the experimental durable or evented agents or the Inngest engine.
+
 ## Message input
 
 ### Send a message now

package/dist/index.cjs

@@ -6087,6 +6087,7 @@ const KNOWN_AGENT_CONTROLLER_EVENT_TYPES = new Set(Object.keys({
 	workspace_ready: true,
 	workspace_error: true,
 	workspace_status_changed: true,
+	task_complete_evaluation: true,
 	info: true,
 	error: true
 }));