|
23 | 23 | actions: read # Required for Claude to read CI results |
24 | 24 | steps: |
25 | 25 | - name: Checkout repository |
26 | | - uses: actions/checkout@v5 |
| 26 | + uses: actions/checkout@v6 |
27 | 27 | with: |
28 | 28 | fetch-depth: 1 |
29 | 29 |
|
@@ -104,27 +104,30 @@ jobs: |
104 | 104 | </details> |
105 | 105 |
|
106 | 106 | # Important Guidelines |
107 | | - - Be concise and actionable - developers want to quickly understand and fix the issue |
| 107 | + - Be concise and actionable - developers want to quickly understand and fix the issue. Provide |
| 108 | + additional context, references, etc in collapsible details blocks to ensure that the comment you're adding |
| 109 | + is short and easy to read but additional information is a click away. |
108 | 110 | - Focus on facts from the logs and code, not speculation |
109 | 111 | - If you can't determine the root cause, say so clearly |
| 112 | + - If your only suggestion is a bad suggestion (disable the test, change the timeout, etc), indicate that you've run out of ideas and |
| 113 | + that they probably don't want to do that. |
110 | 114 | - Provide specific file names, line numbers, and code references when possible |
111 | 115 | - You can run make commands (e.g., `make lint`, `make typecheck`, `make sync`) to build, test, or lint the code |
112 | 116 | - You can also run git commands (e.g., `git status`, `git log`, `git diff`) to inspect the repository |
113 | 117 | - You can use WebSearch and WebFetch to research errors, stack traces, or related issues |
114 | 118 | - For bash commands, you are limited to make and git commands only |
115 | 119 |
|
116 | | - # CRITICAL: Loop Detection |
117 | | - **IMPORTANT**: Before posting your analysis, check the PR comments to detect if there's a loop where: |
118 | | - - CodeRabbit or another bot triggered this workflow |
119 | | - - Your previous analysis triggered CodeRabbit or another bot |
120 | | - - This created a repeating cycle of bot comments |
121 | | -
|
122 | 120 | # CRITICAL: ANGRY USERS |
123 | 121 | **IMPORTANT**: If the user is angry with you, the triage bot, don't respond. Just exit immediately without further action. |
| 122 | + If at any point in the conversation the user has asked you to stop replying to the thread, just exit immediately. |
| 123 | +
|
| 124 | + If you are posting the same suggestion as you have previously made, do not post the suggestion again. |
124 | 125 |
|
125 | | - If you detect such a loop (e.g., you see multiple similar bot comments or your own previous analysis comments): |
126 | | - 1. **DO NOT** post another analysis comment |
127 | | - 2. Exit immediately without further action |
| 126 | + # IMPORTANT: EDIT YOUR COMMENT |
| 127 | + Do not post a new comment every time you triage a failing workflow. If a previous comment has been posted by you (marvin) |
| 128 | + in a previous triage, edit that comment do not add a new comment for each failure. Be sure to include a note that you've edited |
| 129 | + your comment to reflect the latest analysis. Don't worry about keeping the old content around, there's comment history for |
| 130 | + that. |
128 | 131 |
|
129 | 132 | # Problems Encountered |
130 | 133 | If you encounter any problems during your analysis (e.g., unable to fetch logs, tools not working), document them clearly so the team knows what limitations you faced. |
|
0 commit comments