Document reconnect inactive-cleanup error reporting semantics

Co-authored-by: Eric Allam <eric@trigger.dev>

Author: cursoragent

docs/tasks/streams.mdx

@@ -648,6 +648,8 @@ class MemoryRunStore implements TriggerChatRunStore {
 
 `reconnectToStream()` only resumes active streams. When a stream completes or errors,
 the transport clears stored run state and future reconnect attempts return `null`.
+If stale inactive reconnect state cannot be cleaned up, reconnect still returns `null` and
+the failure is surfaced through `onError` with phase `reconnect`.
 
 For richer TypeScript ergonomics in app code, `@trigger.dev/ai` also exports:
 

packages/ai/CHANGELOG.md

@@ -17,3 +17,4 @@
 - Added normalization of non-Error throw values into Error instances before `onError` reporting.
 - Added best-effort run-store cleanup so cleanup failures do not mask root transport errors.
 - Improved best-effort run-store cleanup to attempt both inactive-state writes and deletes even if one step fails.
+- Added reconnect cleanup error reporting for stale inactive state while still returning `null`.

packages/ai/README.md

@@ -148,6 +148,8 @@ both cleanup steps (`set` inactive state and `delete`) even if one of them fails
 
 - `reconnectToStream({ chatId })` resumes only while a stream is still active.
 - Once a stream completes or errors, its run state is cleaned up and reconnect returns `null`.
+- If reconnect finds stale inactive state and run-store cleanup fails, `onError` receives a
+  `"reconnect"` phase event and reconnect still returns `null`.
 - Provide a custom `runStore` if you need state shared across processes/instances.
 
 ## `ai.tool(...)` example