feat: enable message queuing in ask mode#366
Merged
Conversation
Remove agent-only restrictions so users can queue messages and use stop-and-send while a response is streaming in ask mode too. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
✅ Files skipped from review due to trivial changes (1)
📝 WalkthroughWalkthroughDecouples agent-only gating from queue and streaming submission logic so submissions and queued-message processing/display occur across all chat modes, and minor wording/logging tweaks were made. Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant ChatInput
participant ChatController
participant QueueManager
participant StreamProcessor
User->>ChatInput: submit message
ChatInput->>ChatController: handleSubmit(status, chatMode)
ChatController->>QueueManager: enqueue or route (queue / stop-and-send)
alt status == "streaming"
ChatController->>StreamProcessor: allow submit during streaming
StreamProcessor->>QueueManager: process queued items
else status == "ready"
QueueManager->>StreamProcessor: normal send flow
end
QueueManager->>ChatInput: update messageQueue
ChatInput->>User: render QueuedMessagesPanel (when queue length > 0)
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
app/hooks/useChatHandlers.ts (2)
200-228:⚠️ Potential issue | 🟠 MajorValidate first, then await
stopActiveStream()for stop-and-send.This branch now runs in ask mode too, but it stops the active response before the validation block below. An invalid replacement prompt can cancel the in-flight answer and then be rejected. It also bypasses
stopActiveStream(), so cancel/save are fire-and-forget and local Codex chats fall into the temp-stream cancel path instead of the local-provider no-op path.Suggested change
+ let shouldStopAndSend = false; + if (status === "streaming") { const validFiles = uploadedFiles.filter( (file) => file.uploaded && file.url && file.fileId, ); if (queueBehavior === "queue") { // Queue the message - will auto-send after current response completes queueMessage( input, validFiles.map((f) => ({ file: f.file, fileId: f.fileId! as Id<"files">, url: f.url!, })), ); clearInput(); clearUploadedFiles(); return; } else if (queueBehavior === "stop-and-send") { - // Immediately stop current stream and send right away - stop(); - - // Cancel the stream in database and save current message state - if ( - !temporaryChatsEnabledRef.current && - !isCodexLocal(selectedModel) - ) { - cancelStreamMutation({ chatId }).catch((error) => { - console.error("Failed to cancel stream:", error); - }); - - const lastMessage = messages[messages.length - 1]; - if (lastMessage && lastMessage.role === "assistant") { - saveAssistantMessage({ - id: lastMessage.id, - chatId, - role: lastMessage.role, - parts: lastMessage.parts, - }).catch((error) => { - console.error("Failed to save message on stop:", error); - }); - } - } else { - // Temporary chats: signal cancel via temp stream coordination - cancelTempStreamMutation({ chatId }).catch(() => {}); - } - // Continue to send the new message immediately below (don't return) + shouldStopAndSend = true; } } // Check token limit before sending based on user plan const tokenCount = countInputTokens(input, uploadedFiles); const maxTokens = getMaxTokensForSubscription(subscription, { mode: chatMode, }); + + if (shouldStopAndSend) { + await stopActiveStream(); + }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@app/hooks/useChatHandlers.ts` around lines 200 - 228, The "stop-and-send" branch currently calls stop() and performs fire-and-forget cancel/save before validating the new prompt; change it to validate first, then await stopActiveStream() to gracefully stop the in-flight response; replace the direct stop() call with await stopActiveStream() and ensure cancelStreamMutation/saveAssistantMessage/cancelTempStreamMutation are awaited (or handled inside stopActiveStream) so local Codex chats use the local-provider no-op path via isCodexLocal(selectedModel) and temporaryChatsEnabledRef.current is respected rather than falling into the temp-stream cancel path.
182-200:⚠️ Potential issue | 🟠 MajorQueued ask-mode messages now skip token enforcement.
With Line 182 no longer gated to agent mode, the
queueBehavior === "queue"path returns before the ask-mode file limit andmaxTokenschecks on Lines 237-260. Those queued items are later submitted byhandleSendNowwithout revalidation, and the auto-dequeue flow inapp/components/chat.tsxalso runs regardless of mode, so oversized ask-mode requests can be enqueued and then sent anyway.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@app/hooks/useChatHandlers.ts` around lines 182 - 200, The current early return in the status === "streaming" block lets the queueBehavior === "queue" path enqueue messages without running ask-mode validations (file count and maxTokens) before queueMessage is called; update the logic in useChatHandlers so that either (A) the queueBehavior === "queue" branch only executes for agent mode, or (B) run the ask-mode validation checks (the same file limit and maxTokens logic used later) before calling queueMessage and returning; adjust the queueMessage call site and/or handleSendNow to ensure queued ask-mode items are validated (use the existing symbols queueMessage, handleSendNow, queueBehavior, and uploadedFiles) so oversized ask-mode requests cannot be enqueued.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Outside diff comments:
In `@app/hooks/useChatHandlers.ts`:
- Around line 200-228: The "stop-and-send" branch currently calls stop() and
performs fire-and-forget cancel/save before validating the new prompt; change it
to validate first, then await stopActiveStream() to gracefully stop the
in-flight response; replace the direct stop() call with await stopActiveStream()
and ensure cancelStreamMutation/saveAssistantMessage/cancelTempStreamMutation
are awaited (or handled inside stopActiveStream) so local Codex chats use the
local-provider no-op path via isCodexLocal(selectedModel) and
temporaryChatsEnabledRef.current is respected rather than falling into the
temp-stream cancel path.
- Around line 182-200: The current early return in the status === "streaming"
block lets the queueBehavior === "queue" path enqueue messages without running
ask-mode validations (file count and maxTokens) before queueMessage is called;
update the logic in useChatHandlers so that either (A) the queueBehavior ===
"queue" branch only executes for agent mode, or (B) run the ask-mode validation
checks (the same file limit and maxTokens logic used later) before calling
queueMessage and returning; adjust the queueMessage call site and/or
handleSendNow to ensure queued ask-mode items are validated (use the existing
symbols queueMessage, handleSendNow, queueBehavior, and uploadedFiles) so
oversized ask-mode requests cannot be enqueued.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: bae2346f-cd6e-40a0-b5d2-7d18d878fc8d
📒 Files selected for processing (3)
app/components/ChatInput/ChatInput.tsxapp/components/chat.tsxapp/hooks/useChatHandlers.ts
💤 Files with no reviewable changes (1)
- app/components/chat.tsx
…f reset time Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This is an unrecoverable condition (stale WebSocket on long local streams) that doesn't affect the user — logging as error is noise. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
QueuedMessagesPanelto render in all chat modesTest plan
🤖 Generated with Claude Code
Summary by CodeRabbit
New Features
Bug Fixes
Style
Chores