fix(nova): keep user message when stopping generation early#1055
fix(nova): keep user message when stopping generation early#1055MaheshtheDev wants to merge 1 commit into
Conversation
Clicking stop before the first assistant token streamed in deleted the triggering user message: handleStop unconditionally sliced off a trailing user message, which during the submitted/thinking window is the user's own message. Drop the slice so the message is preserved on stop. ENG-732
Deploying with
|
| Status | Name | Latest Commit | Preview URL | Updated (UTC) |
|---|---|---|---|---|
| ✅ Deployment successful! View logs |
supermemory-app | c591e82 | Commit Preview URL Branch Preview URL |
Jun 05 2026, 08:59 PM |
Deploying with
|
| Status | Name | Latest Commit | Updated (UTC) |
|---|---|---|---|
| ✅ Deployment successful! View logs |
supermemory-mcp | c591e82 | Jun 05 2026, 08:59 PM |
How to use the Graphite Merge QueueAdd the label Main to this PR to add it to the merge queue. You must have a Graphite account in order to use the merge queue. Sign up using this link. An organization admin has enabled the Graphite Merge Queue in this repository. Please do not merge from GitHub as this will restart CI on PRs being processed by the merge queue. This stack of pull requests is managed by Graphite. Learn more about stacking. |
|
Claude finished @MaheshtheDev's task in 1m 28s —— View job Review Complete
Summary: This is a clean, correct fix. The original code incorrectly removed the user's message when stopping generation before any assistant response arrived. The fix simply calls Score: 10/10 — Good to ship. |
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
There was a problem hiding this comment.
Overview: Removes incorrect message cleanup logic in handleStop that was deleting the user's message when stopping generation before an assistant response arrived.
Issues found: None — this looks good to ship.
The fix is correct. The original code assumed the last user message was a "dangling" artifact that needed cleanup, but in the submitted/thinking window (before any assistant token streams), that last user message is the user's own input. Removing it lost the user's message.
The Vercel AI SDK's useChat hook manages the messages array internally — when sendMessage is called, it adds a user message immediately. Calling stop() aborts the request but correctly preserves that message. The old comment's concern about duplication "on the next send" was unfounded: each sendMessage call creates a new message with a unique ID, so no deduplication logic is needed.
Score: 10/10
1 participant
Clicking stop before the first assistant token streamed in deleted the triggering user message: handleStop unconditionally sliced off a trailing user message, which during the submitted/thinking window is the user's own
message. Drop the slice so the message is preserved on stop.
ENG-732