Skip to content

PR analysis: adjust prompt to suppress LLM thinking output #64

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.

Sign up for GitHub

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

Merged
avasilevskii merged 1 commit into from
Dec 4, 2025
Merged

PR analysis: adjust prompt to suppress LLM thinking output #64

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions bugzooka/analysis/prompts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@
- OpenShift Version: {version}

**Required Output Structure:**
Output ONLY the sections below with no additional commentary, thinking process, or explanations.
Output ONLY the sections below with ABSOLUTELY NO additional commentary, thinking process, or meta-commentary.

*Performance Impact Assessment*
- Overall Impact: State EXACTLY one of: ":exclamation: *Regression* :exclamation:" (only if 1 or more significant regression found), ":rocket: *Improvement* :rocket:" (only if 1 or more significant improvement found), ":arrow_right: *Neutral* :arrow_right:" (no significant changes)
Expand Down Expand Up @@ -114,7 +114,7 @@
- The tools provide percentage changes - use them as provided
- CHECK thresholds (5% and 10%) before categorizing
- SORT by absolute percentage change (highest first) - this is mandatory
- DO NOT include any thinking process, explanations, or meta-commentary - output ONLY the required format
- DO NOT include any thinking process, explanations, or meta-commentary - output ONLY the required format with ABSOLUTELY NO additional commentary, thinking process, or meta-commentary.
""",
"assistant": """Understood. I will:
- Use the tools to fetch data (percentage changes are already calculated)
Expand Down