-
Notifications
You must be signed in to change notification settings - Fork 12
Make correctness check commands appear as if they are part of the previous message (which is card/code patching message) #3785
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
Preview deployments |
Host Test Results 1 files ± 0 1 suites ±0 3h 13m 0s ⏱️ + 1h 40m 16s For more details on these failures, see this check. Results for commit f726aa5. ± Comparison against base commit 5a12304. This pull request removes 1 and adds 86 tests. Note that renamed tests count towards both.♻️ This comment has been updated with latest results. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull request overview
This PR enhances the UI to make correctness check commands appear as part of the previous card/code patching message, creating a more integrated and less technical user experience. The changes hide technical terminology like "correctness checks" from user-facing messages and introduce a compact visual mode for these follow-up validation messages.
- Modified AI prompts to avoid exposing technical terms like "correctness checks" to users, replacing with user-friendly language
- Introduced a compact display mode for code patch correctness messages with reduced spacing, hidden metadata, and streamlined controls
- Updated styling across multiple components to support the compact mode with flexbox layout adjustments and CSS custom properties
Reviewed changes
Copilot reviewed 9 out of 9 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| packages/runtime-common/ai/prompt.ts | Updated prompt instructions to use more user-friendly language, replacing technical terms like "correctness checks" with "validation" and instructing the AI to avoid mentioning automated checks |
| packages/host/app/components/matrix/room-message.gts | Added isCodePatchCorrectness property propagation to enable compact mode for correctness check messages |
| packages/host/app/components/matrix/room-message-command.gts | Integrated isCompact parameter throughout the component and applied it to code blocks and command headers |
| packages/host/app/components/ai-assistant/message/index.gts | Added code-patch-correctness CSS class and styling to reduce spacing between consecutive compact commands |
| packages/host/app/components/ai-assistant/code-block/view-code-button.gts | Added compact mode styling with adjusted sizing and positioning for info button |
| packages/host/app/components/ai-assistant/code-block/index.gts | Added compact mode styling to remove background and borders for a more integrated appearance |
| packages/host/app/components/ai-assistant/code-block/command-header.gts | Implemented compact header layout with flexbox, hidden copy button, and ellipsized command description |
| packages/host/app/components/ai-assistant/apply-button/index.gts | Added comprehensive compact mode styling with reduced dimensions and state-specific adjustments |
| packages/ai-bot/tests/prompt-construction-test.ts | Updated test to match the new prompt message format |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| role: 'user', | ||
| content: | ||
| 'The automated correctness checks have finished. Summarize their results for me based on the tool output above.', | ||
| 'The automated correctness checks have finished. Summarize the results based on the tool output above in one short sentence. Do not mention: correctness, automated correctness checks, tool calls.', |
Copilot
AI
Dec 31, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The user-facing prompt message still contains "automated correctness checks" while also instructing the AI not to mention it. This is contradictory and inconsistent with the PR's goal of hiding this terminology from users. Consider rewording to something like: "The automated validation has finished. Summarize the results based on the tool output above in one short sentence. Do not mention: correctness, automated correctness checks, tool calls."
| 'The automated correctness checks have finished. Summarize the results based on the tool output above in one short sentence. Do not mention: correctness, automated correctness checks, tool calls.', | |
| 'The automated validation has finished. Summarize the results based on the tool output above in one short sentence. Do not mention: validation, tool calls.', |
Uh oh!
There was an error while loading. Please reload this page.