Add review risk assessment and optional repository review rules#2391
Open
xiaodeng666a wants to merge 25 commits into
Open
Add review risk assessment and optional repository review rules#2391xiaodeng666a wants to merge 25 commits into
xiaodeng666a wants to merge 25 commits into
Conversation
Contributor
Review Summary by QodoAdd review risk assessment, merge recommendations, and repository review rules
WalkthroughsDescription• Add risk assessment and merge recommendation fields to PR reviews • Implement optional repository-specific review rules injection • Add review history tracking and retrieval from JSONL file • Enhance markdown rendering for new review fields Diagramflowchart LR
A["PR Review Process"] --> B["Load Review Rules"]
A --> C["Load Review History"]
B --> D["Inject into Prompt"]
C --> D
D --> E["Generate Review"]
E --> F["Extract Risk Level"]
E --> G["Extract Merge Recommendation"]
E --> H["Extract Priority Files"]
F --> I["Store in Memory"]
G --> I
H --> I
I --> J["Render Markdown"]
File Changes1. pr_agent/algo/utils.py
|
Contributor
Code Review by Qodo
1.
|
![qodo-free-for-open-source-projects[bot]](https://avatars.githubusercontent.com/in/1068000?s=60&v=4){kind=small}
Contributor
|
Persistent review updated to latest commit 104a696 |
Contributor
Code Review by QodoSorry, something went wrongWe weren't able to complete the code review on our side. Please try again |
Contributor
|
Persistent review updated to latest commit fc8ee1d |
Contributor
|
Persistent review updated to latest commit d8cbb89 |
Contributor
|
Persistent review updated to latest commit e237f87 |
Contributor
|
Persistent review updated to latest commit 13136c6 |
Contributor
|
Persistent review updated to latest commit 03e0a0d |
Contributor
|
Persistent review updated to latest commit 2d099fa |
Comment on lines
+255
to
+262
| elif "Review priority files" in key_nice.lower(): | ||
| if not value: | ||
| markdown_text += f"### {emoji} Priority files: None\n\n" | ||
| else: | ||
| markdown_text += f"### {emoji} Priority files\n\n" | ||
| for priority_file in value: | ||
| markdown_text += f"- {priority_file}\n" | ||
| markdown_text += "\n" |
Contributor
There was a problem hiding this comment.
1. Priority files condition unreachable 📘 Rule violation ≡ Correctness
The new convert_to_markdown_v2() branch intended to render review_priority_files is effectively dead code because it checks for a capitalized/mixed-case substring against key_nice.lower(), so it can never match. As a result, review_priority_files falls through to the generic renderer instead of being formatted as the intended priority-files list/output.
Agent Prompt
## Issue description
The `review_priority_files` rendering branch in `convert_to_markdown_v2()` is unreachable because it performs a case-sensitive substring search using a mixed/capitalized literal (e.g., `"Review priority files"`) against `key_nice.lower()`, which is always lowercase.
## Issue Context
`key_nice` is transformed and then compared via `key_nice.lower()`. With the current mixed-case substring in the condition, the match can never succeed, so the new priority-files rendering path never runs and `review_priority_files` falls through to the generic renderer instead of being formatted as the intended priority-files list/output.
## Fix Focus Areas
- pr_agent/algo/utils.py[175-180]
- pr_agent/algo/utils.py[255-263]
ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools
Comment on lines
+4
to
7
|
|
||
|
|
||
|
|
||
| from collections import OrderedDict |
Contributor
There was a problem hiding this comment.
2. Extra blank lines in imports 📘 Rule violation ⚙ Maintainability
The PR introduces three consecutive blank lines within the import block, which is likely to fail Ruff/PEP8 blank-line rules and create unnecessary diff noise. This can break linting CI and violates the repository formatting conventions.
Agent Prompt
## Issue description
There are too many consecutive blank lines inside the imports section, which can violate Ruff/PEP8 formatting rules.
## Issue Context
The file currently has three blank lines between `import traceback` and the next import group.
## Fix Focus Areas
- pr_agent/tools/pr_reviewer.py[4-7]
ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools
Comment on lines
+241
to
+253
| elif "risk level" in key_nice.lower(): | ||
| risk_value = str(value).strip().lower().replace("_", " ") | ||
| risk_display = risk_value.capitalize() if risk_value else "Unknown" | ||
| markdown_text += f"### {emoji} Risk level: {risk_display}\n\n" | ||
|
|
||
| elif "merge recommendation" in key_nice.lower(): | ||
| recommendation = str(value).strip().replace("_", " ") | ||
| recommendation_display = ( | ||
| recommendation.capitalize() if recommendation else "Unknown" | ||
| ) | ||
| markdown_text += ( | ||
| f"### {emoji} Merge recommendation: {recommendation_display}\n\n" | ||
| ) |
Contributor
There was a problem hiding this comment.
3. Headings break gfm table 🐞 Bug ≡ Correctness
When gfm_supported is true, convert_to_markdown_v2() opens an HTML <table> but the new risk_level and merge_recommendation branches emit Markdown headings (### ...) rather than <tr><td>...</td></tr>. This produces malformed mixed HTML/Markdown output and can render the review comment unpredictably.
Agent Prompt
## Issue description
`convert_to_markdown_v2()` writes markdown headings for `risk_level` / `merge_recommendation` even while a `<table>` is open in GFM mode, breaking the table structure.
## Issue Context
The function opens `<table>` when `gfm_supported` is true, and most branches emit `<tr><td>...</td></tr>`. The new branches should follow the same pattern (or close the table before emitting headings).
## Fix Focus Areas
- pr_agent/algo/utils.py[171-173]
- pr_agent/algo/utils.py[241-253]
- pr_agent/algo/utils.py[347-349]
ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools
Contributor
|
Persistent review updated to latest commit 71011b3 |
Contributor
|
Persistent review updated to latest commit 9298146 |
Contributor
|
Persistent review updated to latest commit 20673da |
Author
|
I’ve addressed the automated review feedback, added targeted tests, and narrowed the scope to structured review assessment plus optional repository review rules. At this point the persistent review is updating to the latest commit, so I’ll pause here unless you’d like any further changes. |
Contributor
|
Persistent review updated to latest commit d2f6982 |
Contributor
Code Review by QodoNew Review StartedThis review has been superseded by a new analysis |
Contributor
|
Persistent review updated to latest commit 6020941 |
Contributor
|
Persistent review updated to latest commit ca9ab5e |
Contributor
|
Persistent review updated to latest commit c133868 |
Contributor
|
Persistent review updated to latest commit b2b3f6a |
Contributor
|
Persistent review updated to latest commit fecf295 |
|
Error running review: Traceback (most recent call last): |
1 similar comment
|
Error running review: Traceback (most recent call last): |
📋 Ensemble PR ReviewPR: Add review risk assessment and optional repository review rules 🟠 Gemini 3.1 FlashSummaryThis PR enhances the PR-Agent review process by introducing two main features: a structured risk assessment (risk level, merge recommendation, and priority files) and the ability to inject repository-specific review rules from markdown files (e.g., Issues Found1. Logic / Robustness: Missing
|
|
Error running review: Traceback (most recent call last): |
📋 Ensemble PR ReviewPR: Add review risk assessment and optional repository review rules 🟠 Gemini 3.1 FlashPR Review SummarySummary Issues Found1. Logic Error: Missing
|
📋 Ensemble PR ReviewPR: Add review risk assessment and optional repository review rules 🔵 DeepSeek V4 Flash❌ Error: 402 Client Error: Payment Required for url: https://api.poe.com/v1/chat/completions 🟠 Gemini 3.1 FlashSummaryThis PR enhances the Issues Found1. Potential Logic Error:
|
📋 Ensemble PR ReviewPR: Add review risk assessment and optional repository review rules 🔵 DeepSeek V4 Flash❌ Error: 402 Client Error: Payment Required for url: https://api.poe.com/v1/chat/completions 🟠 Gemini 3.1 FlashSummaryThis PR enhances the Issues Found1. Logic Error: Missing
|
|
Error running review: Traceback (most recent call last): |
|
Test comment from webhook via API |
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
2 participants
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
This PR introduces two related review enhancements for PR-Agent:
risk_levelmerge_recommendationreview_priority_filesMotivation
These changes make review output more actionable and more adaptable to repository-specific expectations, while keeping the default behavior backward-compatible.
Notes