Optimize daily code review agent with focused detection playbook#128
Merged
Optimize daily code review agent with focused detection playbook#128
Conversation
Replace ~750 lines of generic, multi-language reference material with a ~145-line focused Detection Playbook appendix tailored to this TypeScript SDK. Changes: - Remove Python/C#/Java/Go detection patterns (irrelevant to this repo) - Remove React/Next.js section (not in this codebase) - Remove ES2024+/ES2025 features (repo targets ES2022) - Remove bash grep commands (agent uses search/read tools) - Deduplicate patterns that appeared in 2-3 places - Add repo-specific bug patterns from copilot-instructions.md - Add 'Do NOT Flag' guardrails for CommonJS, React, ES2024+ - Integrate appendix into Step 2 workflow with cross-reference - Organize into 5 scannable sections (A-E) mapped to Categories
There was a problem hiding this comment.
Pull request overview
This PR streamlines the daily code review agent definition by replacing a large, generic multi-language appendix with a shorter, repo-specific “Detection Playbook” tailored to this DurableTask TypeScript/Node.js SDK.
Changes:
- Updates Step 2 to explicitly reference the new appendix for concrete detection heuristics.
- Adds a focused “Detection Playbook” appendix with complexity thresholds, bug patterns (including Durable Task replay-specific pitfalls), dead-code patterns, modernization guidance, and refactoring strategies.
- Removes irrelevant and duplicated reference material to reduce token usage and noise.
Member
Author
|
@copilot open a new pull request to apply changes based on the comments in this thread |
Contributor
YunchuWang
approved these changes
Mar 4, 2026
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.
This pull request updates the daily code review agent guide to improve the code analysis process and provide reviewers with a more concrete, actionable workflow. The most significant change is the addition of a comprehensive "Detection Playbook" appendix, which standardizes the patterns and thresholds for code scanning. This helps reviewers consistently identify bugs, dead code, and modernization opportunities in the TypeScript/Node.js codebase.
Enhancements to code analysis workflow:
Addition of Detection Playbook (Appendix):