docs(chat): cover the second review round in the changesets

A prepared steer keeps its form on later turns, a failed action is still
not a turn, and an action's rollback after a failed turn keeps the right
cursor.

Author: ericallam

.changeset/action-stream-into-conversation.md

@@ -4,4 +4,4 @@
 
 A response streamed back from `onAction` is now part of the conversation. Returning a `StreamTextResult` from an action sent it to the browser and nowhere else, so a regenerate showed the user a new answer that the model had no memory of, and the next turn carried on from the answer it had replaced.
 
-A stream that fails part-way through is also no longer committed as though it finished. Whatever streamed is still kept, but the failure is reported instead of the truncated text being stored, and built on, as a complete answer. An action that used to end quietly on a mid-stream failure now surfaces an error to the frontend, so handle it the way you handle a failed turn.
+A stream that fails part-way through is also no longer committed as though it finished. Whatever streamed is still kept, but the failure is reported instead of the truncated text being stored, and built on, as a complete answer. An action that used to end quietly on a mid-stream failure now surfaces an error to the frontend. It is still an action, not a turn: `onTurnComplete` does not fire for it, the turn count is unchanged, and an instruction injected for the next turn still reaches that turn.

.changeset/persist-action-history-mutations.md

@@ -2,4 +2,4 @@
 "@trigger.dev/sdk": patch
 ---
 
-Undo, edit and regenerate now survive a run ending. History rolled back from `onAction` was only kept in the running worker's memory, so the rollback held while that worker stayed warm and then reverted on the next continuation. The undone messages came back, minutes later, with no error.
+Undo, edit and regenerate now survive a run ending. History rolled back from `onAction` was only kept in the running worker's memory, so the rollback held while that worker stayed warm and then reverted on the next continuation. The undone messages came back, minutes later, with no error. This also holds when the turn before the action failed: the rollback used to be written against the cursor from before that turn, so a continuation could replay output the failed turn had already superseded.

.changeset/steering-messages-accumulator.md

@@ -2,6 +2,6 @@
 "@trigger.dev/sdk": patch
 ---
 
-Steering messages injected mid-answer are now part of the conversation, both for your hooks and for the model on later turns. Previously they reached the model for the answer they steered and reached the browser, but nothing else: `onTurnComplete` never saw them, so an app storing its own transcript lost the instruction the answer was shaped by, and it vanished from the conversation on reload. The model also forgot the instruction from the next turn onwards, answering as though the message had never been sent, while the chat UI still showed it.
+Steering messages injected mid-answer are now part of the conversation, both for your hooks and for the model on later turns. Previously they reached the model for the answer they steered and reached the browser, but nothing else: `onTurnComplete` never saw them, so an app storing its own transcript lost the instruction the answer was shaped by, and it vanished from the conversation on reload. The model also forgot the instruction from the next turn onwards, answering as though the message had never been sent, while the chat UI still showed it. This holds when the steered turn fails part-way, and when `pendingMessages.prepare` reshapes the message: later turns now see the same form the steered turn did, not the original message.
 
 If you worked around this by saving steering messages as they arrive, in `pendingMessages.onReceived` for example, that write now duplicates the one you get from `newUIMessages`. Drop it, or skip messages you have already stored.