Rewrite release summary prompt for scannable output#384
Merged
Conversation
The AI-generated summaries were bloated prose that got truncated mid-sentence on every release. Switch from "2-4 paragraphs" to "intro sentence + bullet list of highlights" matching the style of the hand-written v0.7.0 notes. Add few-shot examples, cut max tokens from 1500 to 600, and drop temperature to 0.
There was a problem hiding this comment.
Pull request overview
This PR updates the GitHub prompt used to generate AI release summaries for the basecamp CLI, shifting output toward a concise, scannable intro + highlights format and reducing verbosity/truncation risk.
Changes:
- Rewrite the system prompt to require a one-line intro followed by highlight bullets (with guidance on bullet counts by release size).
- Add few-shot examples modeled after v0.7.0-style release notes.
- Reduce
maxCompletionTokens(1500 → 600) and settemperatureto0to encourage concise, deterministic output.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
2 issues found across 1 file
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name=".github/prompts/summarize-changelog.prompt.yml">
<violation number="1" location=".github/prompts/summarize-changelog.prompt.yml:9">
P3: The top-of-output ordering rules are contradictory for breaking changes; clarify the exception so the model has one unambiguous sequence.</violation>
<violation number="2" location=".github/prompts/summarize-changelog.prompt.yml:30">
P2: This example bullet violates the prompt’s own `backticks-first` bullet format, which weakens the few-shot guidance.</violation>
</file>
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
Clarify that⚠️ breaking-change line comes before the intro sentence, not after. Relax bullet format to "lead with backticks when there is a command; otherwise just describe." Drop the standalone "Highlights:" label from the large-release example.
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
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
maxCompletionTokensfrom 1500 → 600 andtemperaturefrom 0.2 → 0 to force conciseness and eliminate truncationProblem
Every AI-generated release summary was truncated mid-sentence (v0.7.1 ends with "Multi", v0.4.0 ends with "visual improvements", v0.3.0 ends with "OSC 8 clickable") and read like corporate filler before it cut off. The hand-written v0.7.0 notes showed the right format: punchy, scannable, useful.
Test plan
python3 -c "import yaml; yaml.safe_load(open(...))"