chore: update PR review skill and docs #8
Conversation
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
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Sorry @sheepdestroyer, you have reached your weekly rate limit of 500000 diff characters.
Please try again later or upgrade to continue using Sourcery
📝 WalkthroughWalkthroughThis pull request updates agent rules, skills, and workflows to establish clearer deployment paths, enforce rate-limiting exit conditions, and introduce mandatory behavioral rules for PR review automation. Changes include restructured compliance documentation, enhanced tool path references, and improved instructional messaging across multiple configuration files. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~22 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 unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Summary of ChangesHello @sheepdestroyer, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request refines the operational guidelines and associated tooling for autonomous agents involved in the PR review process. The primary goal is to enforce more robust and predictable agent behaviors by clarifying rules around review cycles, code freshness, rate limit management, and critical prohibitions. These updates ensure agents operate more autonomously and effectively within the defined review workflow, while also providing clearer instructions through tool outputs. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
ⓘ Your approaching your monthly quota for Qodo. Upgrade your plan PR Compliance Guide 🔍Below is a summary of compliance checks for this PR:
Compliance status legend🟢 - Fully Compliant🟡 - Partial Compliant 🔴 - Not Compliant ⚪ - Requires Further Human Verification 🏷️ - Compliance label |
|||||||||||||||||||||||
![ellipsis-dev[bot]](https://avatars.githubusercontent.com/in/64358?s=60&v=4){kind=small}
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed everything up to 4d4a0f3 in 27 seconds. Click for details.
- Reviewed
224lines of code in5files - Skipped
0files when reviewing. - Skipped posting
0draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
Workflow ID: wflow_Bxun4R9u8LnP9m5k
You can customize 
Owner
Author
|
/gemini review |
Owner
Author
|
@coderabbitai review |
Owner
Author
|
@sourcery-ai review |
Contributor
|
Here's the code health analysis summary for commits Analysis Summary
|
There was a problem hiding this comment.
Skipped PR review on 4df283c because no changed files had a supported extension. If you think this was in error, please contact us and we'll fix it right away.
Owner
Author
|
/review |
Owner
Author
|
@ellipsis review this |
|
Sorry @sheepdestroyer, you have reached your weekly rate limit of 500000 diff characters. Please try again later or upgrade to continue using Sourcery |
✅ Actions performedReview triggered.
|
PR Reviewer Guide 🔍(Review updated until commit 60c69b6)Here are some key observations to aid the review process:
|
ⓘ Your approaching your monthly quota for Qodo. Upgrade your plan PR Code Suggestions ✨Explore these optional code suggestions:
|
||||||||||||||
|
Sorry @sheepdestroyer, you have reached your weekly rate limit of 500000 diff characters. Please try again later or upgrade to continue using Sourcery |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request enhances the PR review skill and its associated documentation to enforce stricter behaviors for autonomous agents. The changes introduce new rules for freshness, rate limits, and clarify prohibitions. The skill's Python code is updated to provide more detailed next_step instructions.
My review focuses on improving the maintainability of the Python code and correcting minor grammatical issues in the documentation. The main suggestion is to refactor the heavily duplicated instruction strings in pr_skill.py into constants to improve readability and ease of maintenance. I've also pointed out several typos and grammatical errors in the markdown files.
| * **No Idling**: Agents must actively monitor PR status. Do NOT exit/notify the user just to wait for a bot or a long process. | ||
| * **Polling Strategy**: Use GitHub MCP tools (`mcp_github_pull_request_read`) for reliable, non-blocking status polling. Wait ~3 minutes after triggering before first check, then poll every 2 minutes. | ||
| * **Autonomous Action**: Agents are AUTHORIZED and REQUIRED to `git commit` and `git push` fixes autonomously if tests pass. Do not ask the user to push for you. | ||
| * **Freshness**: Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may since have pushed formatting fixes to your previous changes. |
There was a problem hiding this comment.
The phrasing "may since have pushed" is slightly awkward. For better clarity, consider rephrasing to "may have since pushed".
Suggested change
| * **Freshness**: Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may since have pushed formatting fixes to your previous changes. | |
| * **Freshness**: Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may have since pushed formatting fixes to your previous changes. |
.agent/rules/pr-standards.md
Outdated
| **ABSOLUTE RULE**: Agents must **NEVER** merge a PR, close a PR, or delete a PR's branch. | ||
| * **Reason**: Merging, closing, and branch deletion are privileged actions reserved for human maintainers or specific CI/CD pipelines. | ||
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. | ||
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review. |
There was a problem hiding this comment.
There is a typo in this line. "an branch" should be "a branch".
Suggested change
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review. | |
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. Never merge or delete a branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review. |
|
|
||
| ### Mandatory Behavior Rules (Enforced by Tool Output) | ||
| 1. **Autonomy**: "Be autonomous, don't stop the cycle. you must regularly poll for the main-reviewer's review until it eventually gets posted, then continue" | ||
| 2. **Freshness**: "Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may since have pushed formatting fixes to your previous changes" |
There was a problem hiding this comment.
The phrasing "may since have pushed" is a bit awkward. For better readability, I suggest changing it to "may have since pushed".
Suggested change
| 2. **Freshness**: "Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may since have pushed formatting fixes to your previous changes" | |
| 2. **Freshness**: "Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may have since pushed formatting fixes to your previous changes" |
| ### Mandatory Behavior Rules (Enforced by Tool Output) | ||
| 1. **Autonomy**: "Be autonomous, don't stop the cycle. you must regularly poll for the main-reviewer's review until it eventually gets posted, then continue" | ||
| 2. **Freshness**: "Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may since have pushed formatting fixes to your previous changes" | ||
| 3. **Completeness**: "Be sure to address every comments and code reviews from all reviewers, ensure CI passes" |
There was a problem hiding this comment.
There's a grammatical error here. "every comments" should be either "every comment" or "all comments". I'd suggest "all comments" for consistency.
Suggested change
| 3. **Completeness**: "Be sure to address every comments and code reviews from all reviewers, ensure CI passes" | |
| 3. **Completeness**: "Be sure to address all comments and code reviews from all reviewers, ensure CI passes" |
.agent/skills/pr_review/SKILL.md
Outdated
| 3. **Completeness**: "Be sure to address every comments and code reviews from all reviewers, ensure CI passes" | ||
| 4. **Quality**: "Be sure to run and fix all available tests and Linting before pushing your next changes" | ||
| 5. **Rate Limits**: "If main reviewer says it just became rate-limited, address remaining code reviews then stop there" | ||
| 6. **Prohibitions**: "Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" |
There was a problem hiding this comment.
There is a typo in this line. "an branch" should be "a branch".
Suggested change
| 6. **Prohibitions**: "Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" | |
| 6. **Prohibitions**: "Never merge or delete a branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" |
| poll_interval=None, | ||
| ): | ||
| """ | ||
| Polls until the main reviewer has provided feedback since the given timestamp. |
There was a problem hiding this comment.
This string has a trailing space, which is likely unintentional. It's best to remove it for code cleanliness.
Suggested change
| Polls until the main reviewer has provided feedback since the given timestamp. | |
| "next_step": status_data.get("next_step", "Run 'status' to check for feedback. Be autonomous, don't stop the cycle. you must regularly poll for the main-reviewer's review until it eventually gets posted, then continue") |
There was a problem hiding this comment.
Code Review
This pull request updates the PR review skill and related documentation to enforce stricter autonomous agent behaviors. The changes introduce new rules for freshness, rate limits, and prohibitions in the documentation. The Python skill script is updated to reflect these new rules in its next_step messages and has been auto-formatted for better readability. My review focuses on improving the maintainability of the new instructional strings and correcting some minor typos in the documentation and code. All original comments were kept as they did not contradict any provided rules.
.agent/rules/pr-standards.md
Outdated
| **ABSOLUTE RULE**: Agents must **NEVER** merge a PR, close a PR, or delete a PR's branch. | ||
| * **Reason**: Merging, closing, and branch deletion are privileged actions reserved for human maintainers or specific CI/CD pipelines. | ||
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. | ||
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review. |
There was a problem hiding this comment.
There's a small grammatical error here. 'an branch' should be 'a branch'.
Suggested change
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review. | |
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. Never merge or delete a branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review. |
.agent/skills/pr_review/SKILL.md
Outdated
| 3. **Completeness**: "Be sure to address every comments and code reviews from all reviewers, ensure CI passes" | ||
| 4. **Quality**: "Be sure to run and fix all available tests and Linting before pushing your next changes" | ||
| 5. **Rate Limits**: "If main reviewer says it just became rate-limited, address remaining code reviews then stop there" | ||
| 6. **Prohibitions**: "Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" |
There was a problem hiding this comment.
There's a small grammatical error here. 'an branch' should be 'a branch'.
Suggested change
| 6. **Prohibitions**: "Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" | |
| 6. **Prohibitions**: "Never merge or delete a branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" |
.agent/skills/pr_review/pr_skill.py
Outdated
| "next_step": status_data.get("next_step", "Run 'status' to check for feedback.") | ||
| "next_step": status_data.get( | ||
| "next_step", | ||
| "Run 'status' to check for feedback. Be autonomous, don't stop the cycle. you must regularly poll for the main-reviewer's review until it eventually gets posted, then continue ", |
There was a problem hiding this comment.
The default next_step message appears to have a typo. It ends with a space and a comma ( ,) inside the string, which is likely unintentional. This should probably be a period or removed entirely for clarity.
Suggested change
| "Run 'status' to check for feedback. Be autonomous, don't stop the cycle. you must regularly poll for the main-reviewer's review until it eventually gets posted, then continue ", | |
| "Run 'status' to check for feedback. Be autonomous, don't stop the cycle. you must regularly poll for the main-reviewer's review until it eventually gets posted, then continue.", |
.agent/skills/pr_review/pr_skill.py
Outdated
Comment on lines
732
to
754
| if has_changes_requested: | ||
| next_step = "CRITICAL: Changes requested by reviewer. ANALYZE feedback -> FIX code -> SAFE_PUSH. DO NOT STOP." | ||
| next_step = "CRITICAL: Changes requested by reviewer. ANALYZE feedback -> FIX code -> SAFE_PUSH. DO NOT STOP. Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may since have pushed formatting fixes to your previous changes. Be sure to address every comments and code reviews from all reviewers, ensure CI passes. Be sure to run and fix all available tests and Linting before pushing your next changes. If main reviewer says it just became rate-limited, address remaining code reviews then stop there." | ||
| elif has_new_main_reviewer_comments: | ||
| next_step = f"New comments from {validation_reviewer} after approval. ANALYZE feedback -> FIX code -> SAFE_PUSH." | ||
| next_step = f"New comments from {validation_reviewer} after approval. ANALYZE feedback -> FIX code -> SAFE_PUSH. Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may since have pushed formatting fixes to your previous changes. Be sure to address every comments and code reviews from all reviewers, ensure CI passes. Be sure to run and fix all available tests and Linting before pushing your next changes. If main reviewer says it just became rate-limited, address remaining code reviews then stop there." | ||
| elif main_reviewer_state == "APPROVED": | ||
| # Check if there's any OTHER feedback besides the main reviewer's approval | ||
| other_feedback = [ | ||
| item for item in new_feedback | ||
| if not (item.get("user") == validation_reviewer | ||
| and item.get("type") == "review_summary" | ||
| and item.get("state") == "APPROVED") | ||
| ] | ||
| if other_feedback: | ||
| next_step = "New feedback received. ANALYZE items -> FIX issues -> SAFE_PUSH. DO NOT STOP." | ||
| else: | ||
| next_step = "Validation Complete (STOP LOOP - DO NOT MERGE AUTONOMOUSLY). Notify User." | ||
| # Check if there's any OTHER feedback besides the main reviewer's approval | ||
| other_feedback = [ | ||
| item | ||
| for item in new_feedback | ||
| if not ( | ||
| item.get("user") == validation_reviewer | ||
| and item.get("type") == "review_summary" | ||
| and item.get("state") == "APPROVED" | ||
| ) | ||
| ] | ||
| if other_feedback: | ||
| next_step = "New feedback received. ANALYZE items -> FIX issues -> SAFE_PUSH. DO NOT STOP. Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may since have pushed formatting fixes to your previous changes. Be sure to address every comments and code reviews from all reviewers, ensure CI passes. Be sure to run and fix all available tests and Linting before pushing your next changes." | ||
| else: | ||
| next_step = "Validation Complete (STOP LOOP - DO NOT MERGE AUTONOMOUSLY). Notify User. Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" | ||
| elif new_feedback: | ||
| next_step = "New feedback received. ANALYZE items -> FIX issues -> SAFE_PUSH. DO NOT STOP." | ||
| next_step = "New feedback received. ANALYZE items -> FIX issues -> SAFE_PUSH. DO NOT STOP. Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may since have pushed formatting fixes to your previous changes. Be sure to address every comments and code reviews from all reviewers, ensure CI passes. Be sure to run and fix all available tests and Linting before pushing your next changes." | ||
| else: | ||
| next_step = f"Waiting for approval from {validation_reviewer} (Current: {main_reviewer_state}). Poll again." | ||
| next_step = f"Waiting for approval from {validation_reviewer} (Current: {main_reviewer_state}). Poll again. Be autonomous, don't stop the cycle. you must regularly poll for the main-reviewer's review until it eventually gets posted, then continue" |
There was a problem hiding this comment.
The long instructional strings are duplicated across several next_step assignments (e.g., lines 733, 735, 748, 752). This duplication makes the code harder to read and maintain. If these instructions need to be updated, the change has to be made in multiple places, which is error-prone.
Consider extracting the common instructional text into a constant and building the final next_step strings dynamically. For example:
ACTION_INSTRUCTIONS = (" Pull and merge latest changes..."
" ensure CI passes..."
" run and fix all tests...")
# ...
if has_changes_requested:
next_step = f"CRITICAL: Changes requested...{ACTION_INSTRUCTIONS}"
elif new_feedback:
next_step = f"New feedback received...{ACTION_INSTRUCTIONS}"
# ...
.agent/skills/pr_review/pr_skill.py
Outdated
| if other_feedback: | ||
| next_step = "New feedback received. ANALYZE items -> FIX issues -> SAFE_PUSH. DO NOT STOP. Pull and merge latest changes from the remote branch before starting addressing code reviews, as bots may since have pushed formatting fixes to your previous changes. Be sure to address every comments and code reviews from all reviewers, ensure CI passes. Be sure to run and fix all available tests and Linting before pushing your next changes." | ||
| else: | ||
| next_step = "Validation Complete (STOP LOOP - DO NOT MERGE AUTONOMOUSLY). Notify User. Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" |
There was a problem hiding this comment.
There's a small grammatical error in this instructional string. 'an branch' should be 'a branch'.
Suggested change
| next_step = "Validation Complete (STOP LOOP - DO NOT MERGE AUTONOMOUSLY). Notify User. Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" | |
| next_step = "Validation Complete (STOP LOOP - DO NOT MERGE AUTONOMOUSLY). Notify User. Never merge or delete a branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" |
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed bb67257 in 24 seconds. Click for details.
- Reviewed
67lines of code in3files - Skipped
0files when reviewing. - Skipped posting
0draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
Workflow ID: wflow_0FDxWrfi4TF8FKGH
You can customize
Owner
Author
|
/gemini review |
Owner
Author
|
@coderabbitai review |
ⓘ Your approaching your monthly quota for Qodo. Upgrade your plan Persistent review updated to latest commit c9dcad1 |
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed c9dcad1 in 26 seconds. Click for details.
- Reviewed
73lines of code in2files - Skipped
0files when reviewing. - Skipped posting
0draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
Workflow ID: wflow_rb4fotV9MmrER5NQ
You can customize
|
Sorry @sheepdestroyer, you have reached your weekly rate limit of 500000 diff characters. Please try again later or upgrade to continue using Sourcery |
There was a problem hiding this comment.
Code Review
This pull request effectively enhances the PR review skill and its documentation to enforce stricter autonomous agent behaviors. The changes are well-organized and consistently applied across both the Python script and the markdown files. The refactoring in pr_skill.py improves readability, and the new next_step messages clearly define the expected agent actions regarding freshness, rate limits, and operational prohibitions. The documentation updates accurately reflect these new standards. I have identified a couple of minor issues in the documentation files and have provided suggestions for correction. Overall, this is a strong improvement for the agent's review cycle management.
.agent/rules/pr-standards.md
Outdated
| **ABSOLUTE RULE**: Agents must **NEVER** merge a PR, close a PR, or delete a PR's branch. | ||
| * **Reason**: Merging, closing, and branch deletion are privileged actions reserved for human maintainers or specific CI/CD pipelines. | ||
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. | ||
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review. |
There was a problem hiding this comment.
There is a minor typo in the action description. "an branch" should be corrected to "a branch" for grammatical accuracy.
Suggested change
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. Never merge or delete an branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review. | |
| * **Action**: If you believe a PR is ready to be merged or should be closed, you must notify the user and await instructions. **Do NOT** execute commands to merge, close, or delete the branch. Never merge or delete a branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review. |
.agent/skills/pr_review/SKILL.md
Outdated
| 3. **Completeness**: "Be sure to address every comments and code reviews from all reviewers, ensure CI passes" | ||
| 4. **Quality**: "Be sure to run and fix all available tests and Linting before pushing your next changes" | ||
| 5. **Rate Limits**: "If main reviewer says it just became rate-limited, address remaining code reviews then stop there" | ||
| 6. **Prohibitions**: \"Never merge or delete a branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review\" |
There was a problem hiding this comment.
The backslashes (\) used to escape the double quotes are unnecessary in this Markdown context and can be removed to improve readability.
Suggested change
| 6. **Prohibitions**: \"Never merge or delete a branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review\" | |
| 6. **Prohibitions**: "Never merge or delete a branch on your own, if you believe the main reviewer said that the PR is ready, just stop and ask for Human review" |
Owner
Author
|
/gemini review |
Owner
Author
|
@coderabbitai review |
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Owner
Author
|
@sourcery-ai review |
Owner
Author
|
/review |
Owner
Author
|
@ellipsis review this |
|
Sorry @sheepdestroyer, you have reached your weekly rate limit of 500000 diff characters. Please try again later or upgrade to continue using Sourcery |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 6
🤖 Fix all issues with AI agents
In @.agent/rules/pr-standards.md:
- Line 37: Update pr-standards.md to clarify that the referenced path
"skills/pr_review/pr_skill.py" is the local-repo path for development, and add a
brief note that system-wide installations use
"~/.gemini/antigravity/skills/pr_review/pr_skill.py" and agent-local copies use
".agent/skills/pr_review/pr_skill.py"; follow the dual-path wording pattern used
in knowledge-base.md (or reference it) so readers know when to use each variant
and where to find the alternate path.
In @.agent/rules/rules.md:
- Around line 3-8: The Compliance section contains an incomplete sentence
starting with "enforces the **Standards & Rules**..."—update that sentence to
include a clear subject (e.g., "This document enforces the **Standards & Rules**
defined in `~/.gemini/rules/pr-standards.md`.") so the sentence is grammatical
and explicit; adjust the paragraph under the "## 1. Compliance" heading (the
line that currently begins "enforces the **Standards & Rules**...") and keep the
rest of the bullets (`pr_skill.py` references and prohibitions) unchanged.
In @.agent/skills/pr_review/pr_skill.py:
- Line 765: The string assigned to next_step in the PR review skill contains a
grammar mistake: the second sentence starts with a lowercase "you"; update the
literal in the assignment (the next_step variable in
.agent/skills/pr_review/pr_skill.py) to capitalize "You" so the sentence reads
"...Poll again. Be autonomous, don't stop the cycle. You must regularly poll..."
ensuring only the capitalization change to the existing message.
- Around line 54-63: Fix grammar in the instruction constants: update
ACTION_INSTRUCTIONS to say "address every comment" (not "comments") and change
"as bots may since have pushed" to "as bots may have since pushed", and tidy
other awkward phrasing such as removing the duplicated "Be sure to" or rewording
"before starting addressing code reviews" to "before starting to address code
reviews"; also adjust RATE_LIMIT_INSTRUCTION spacing/phrasing if needed to read
naturally. Target the ACTION_INSTRUCTIONS and RATE_LIMIT_INSTRUCTION constants
in .agent/skills/pr_review/pr_skill.py when making these edits.
- Around line 340-341: Remove the duplicated comment "# Separately check
upstream" that appears twice in a row in .agent/skills/pr_review/pr_skill.py
(locate the consecutive duplicate comments near the existing check for upstream
logic inside the surrounding function or method where that comment is used) so
only a single instance of the comment remains; ensure no other nearby comments
or logic are altered.
In @.agent/skills/pr_review/SKILL.md:
- Around line 31-38: The "Prohibitions" line in SKILL.md contains escaped double
quotes (`\"Never merge or delete a branch on your own, if you believe the main
reviewer said that the PR is ready, just stop and ask for Human review\"`) which
are unnecessary in Markdown; edit the "Prohibitions" rule to remove the
backslashes so the text reads with normal quotes (or no quotes) around the
sentence, ensuring the symbol "Prohibitions" and its quoted rule content are
updated accordingly and the Markdown renders correctly.
🧹 Nitpick comments (2)
.agent/skills/pr_review/SKILL.md (1)
48-49: Consider using a placeholder for path consistency.The hardcoded path
~/.gemini/antigravity/skills/pr_review/pr_skill.pydiffers from the{PATH_TO_SKILLS}placeholder approach used inpr-review-cycle.md. Consider aligning the documentation to use a consistent path resolution strategy across all files..agent/skills/pr_review/pr_skill.py (1)
761-761: Consider consistent grammar in next_step messages.This message has the same grammar pattern as the constants. For consistency, consider using the
ACTION_INSTRUCTIONSconstant or applying similar grammar fixes.Also note: The message ending lacks proper punctuation after "Human review".
.agent/rules/pr-standards.md
Outdated
|
|
||
| ## 5. Tool Usage | ||
| * **Primary Tool**: Use `.agent/skills/pr_review/pr_skill.py` for triggering, status checks, and safe pushing. | ||
| * **Primary Tool**: Use `skills/pr_review/pr_skill.py` for triggering, status checks, and safe pushing. |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Check for different path references to pr_skill.py across documentation
rg -n "pr_skill.py" --type=mdRepository: sheepdestroyer/agent-tools
Length of output: 2666
Clarify path references across documentation to distinguish local vs. system-wide deployments.
The path in pr-standards.md (skills/pr_review/pr_skill.py) differs from SKILL.md (~/.gemini/antigravity/skills/pr_review/pr_skill.py), and agent-tools.md uses yet another format (.agent/skills/pr_review/pr_skill.py). These represent different deployment contexts (local repository vs. system-wide installation), but this distinction isn't clearly documented. Add a note in pr-standards.md clarifying whether this path is for local development or reference the dual-path pattern from knowledge-base.md.
🤖 Prompt for AI Agents
In @.agent/rules/pr-standards.md at line 37, Update pr-standards.md to clarify
that the referenced path "skills/pr_review/pr_skill.py" is the local-repo path
for development, and add a brief note that system-wide installations use
"~/.gemini/antigravity/skills/pr_review/pr_skill.py" and agent-local copies use
".agent/skills/pr_review/pr_skill.py"; follow the dual-path wording pattern used
in knowledge-base.md (or reference it) so readers know when to use each variant
and where to find the alternate path.
.agent/skills/pr_review/pr_skill.py
Outdated
| else: | ||
| next_step = f"Waiting for approval from {validation_reviewer} (Current: {main_reviewer_state}). Poll again." | ||
| next_step = f"Waiting for approval from {validation_reviewer} (Current: {main_reviewer_state}). Poll again. Be autonomous, don't stop the cycle. you must regularly poll for the main-reviewer's review until it eventually gets posted, then continue" |
There was a problem hiding this comment.
Grammar: "you" should be capitalized at sentence start.
The message "Be autonomous, don't stop the cycle. you must regularly poll..." should capitalize "You" at the start of the second sentence.
📝 Proposed fix
- next_step = f"Waiting for approval from {validation_reviewer} (Current: {main_reviewer_state}). Poll again. Be autonomous, don't stop the cycle. you must regularly poll for the main-reviewer's review until it eventually gets posted, then continue"
+ next_step = f"Waiting for approval from {validation_reviewer} (Current: {main_reviewer_state}). Poll again. Be autonomous, don't stop the cycle. You must regularly poll for the main-reviewer's review until it eventually gets posted, then continue."📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| next_step = f"Waiting for approval from {validation_reviewer} (Current: {main_reviewer_state}). Poll again. Be autonomous, don't stop the cycle. you must regularly poll for the main-reviewer's review until it eventually gets posted, then continue" | |
| next_step = f"Waiting for approval from {validation_reviewer} (Current: {main_reviewer_state}). Poll again. Be autonomous, don't stop the cycle. You must regularly poll for the main-reviewer's review until it eventually gets posted, then continue." |
🤖 Prompt for AI Agents
In @.agent/skills/pr_review/pr_skill.py at line 765, The string assigned to
next_step in the PR review skill contains a grammar mistake: the second sentence
starts with a lowercase "you"; update the literal in the assignment (the
next_step variable in .agent/skills/pr_review/pr_skill.py) to capitalize "You"
so the sentence reads "...Poll again. Be autonomous, don't stop the cycle. You
must regularly poll..." ensuring only the capitalization change to the existing
message.
✅ Actions performedReview triggered.
|
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed be41ea7 in 28 seconds. Click for details.
- Reviewed
23lines of code in2files - Skipped
0files when reviewing. - Skipped posting
0draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
Workflow ID: wflow_i1yPgy4K4QWfyk6l
You can customize
ⓘ Your approaching your monthly quota for Qodo. Upgrade your plan Persistent review updated to latest commit be41ea7 |
|
Sorry @sheepdestroyer, you have reached your weekly rate limit of 500000 diff characters. Please try again later or upgrade to continue using Sourcery |
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed 60c69b6 in 10 seconds. Click for details.
- Reviewed
41lines of code in2files - Skipped
0files when reviewing. - Skipped posting
0draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
Workflow ID: wflow_rx4pw0Spa2OnloNv
You can customize
Owner
Author
|
/gemini review |
Owner
Author
|
@coderabbitai review |
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Owner
Author
|
@sourcery-ai review |
Owner
Author
|
/review |
Owner
Author
|
@ellipsis review this |
|
Sorry @sheepdestroyer, you have reached your weekly rate limit of 500000 diff characters. Please try again later or upgrade to continue using Sourcery |
✅ Actions performedReview triggered.
|
ⓘ Your approaching your monthly quota for Qodo. Upgrade your plan Persistent review updated to latest commit 60c69b6 |
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed 52fa107 in 10 seconds. Click for details.
- Reviewed
26lines of code in2files - Skipped
0files when reviewing. - Skipped posting
0draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
Workflow ID: wflow_fqXXn6nKf7hlVEuu
You can customize
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.
User description
Updating PR Review Skill and documentation to enforced strict autonomous agent behaviors (The Loop, Freshness, Prohibitions).
PR Type
Enhancement, Documentation
Description
Enhanced PR review skill with stricter autonomous agent behavior enforcement
Added mandatory behavior rules for autonomy, freshness, completeness, and quality
Expanded next_step messages with detailed instructions for code review handling
Updated documentation paths and added new sections on freshness and rate limits
Clarified prohibitions against autonomous merging and branch deletion
Diagram Walkthrough
File Walkthrough
pr_skill.py
Enhanced next_step messages with stricter behavior enforcement.agent/skills/pr_review/pr_skill.py
trigger_reviewnext_step message to enforce autonomouspolling behavior
instructions for code review handling
running tests, and handling rate limits
ask for human review
pr-standards.md
Added freshness and rate limit rules with path corrections.agent/rules/pr-standards.md
.agent/skills/pr_review/pr_skill.pyto
skills/pr_review/pr_skill.pyresolution requirements
strategies
explicit instruction against autonomous branch operations
rules.md
Added compliance section enforcing PR standards.agent/rules/rules.md
standards and prohibitions
SKILL.md
Updated paths and added mandatory behavior rules documentation.agent/skills/pr_review/SKILL.md
.agent/rules/pr-standards.mdto
~/.gemini/rules/pr-standards.mdbehaviors
~/.gemini/antigravity/skills/pr_review/pr_skill.pyinstructions
pr-review-cycle.md
Updated workflow paths and added freshness requirements.agent/workflows/pr-review-cycle.md
~/.gemini/antigravity/skills/pr_review/pr_skill.pyformatImplement)
~/.gemini/rules/pr-standards.mdImportant
Enhances PR review skill with stricter autonomous agent behaviors and updates documentation for clarity and consistency.
pr_skill.pyto enforce stricter autonomous agent behaviors, including mandatory rules for autonomy, freshness, completeness, and quality.next_stepmessages with detailed instructions for code review handling.pr-standards.mdwith new sections on freshness and rate limits, and clarified prohibitions.rules.mdto include a compliance section enforcing PR standards.SKILL.mdandpr-review-cycle.mdwith new path references and mandatory behavior rules.This description was created by
for 52fa107. You can customize this summary. It will automatically update as commits are pushed.
Summary by CodeRabbit
Documentation
Chores
✏️ Tip: You can customize this high-level summary in your review settings.