resolve-reviews

name	resolve-reviews
description	Resolve all PR review comments (human and bot) on current PR. Fetches unanswered comments, evaluates each one, fixes real issues, dismisses false positives, and replies to every comment with the outcome.
license	MIT
compatibility	Requires git, gh (GitHub CLI), and Node.js installed.
allowed-tools	Bash(npx agent-reviews *) Bash(pnpm dlx agent-reviews *) Bash(yarn dlx agent-reviews *) Bash(bunx agent-reviews *) Bash(git config *) Bash(git add *) Bash(git commit *) Bash(git push *)
metadata	{"author":"pbakaus","version":"1.0.2","homepage":"https://github.com/pbakaus/agent-reviews"}

Automatically resolve all review comments (both human and bot) on the current PR. Uses a two-phase workflow: fix all existing issues, then poll for new ones until quiet.

Prerequisites

All commands below use npx agent-reviews. If the project uses a different package manager, substitute the appropriate runner (e.g., pnpm dlx agent-reviews for pnpm, yarn dlx agent-reviews for Yarn, bunx agent-reviews for Bun). Honor the user's package manager preference throughout.

Cloud environments only (e.g., Codespaces, remote agents): verify git author identity so CI checks can map commits to the user. Run git config --global --get user.email and if empty or a placeholder, set it manually. Skip this check in local environments.

Phase 1: FETCH & FIX (synchronous)

Step 1: Fetch All Comments (Expanded)

Run npx agent-reviews --unanswered --expanded

The CLI auto-detects the current branch, finds the associated PR, and authenticates via gh CLI or environment variables. If anything fails (no token, no PR, CLI not installed), it exits with a clear error message.

This shows all unanswered comments (both human and bot) with full detail: complete comment body (no truncation), diff hunk (code context), and all replies. Each comment shows its ID in brackets (e.g., [12345678]).

If zero comments are returned, print "No unanswered comments found" and skip to Phase 2.

Step 3: Process Each Unanswered Comment

For each comment from the expanded output, apply the appropriate evaluation based on whether the author is a bot or a human.

For Bot Comments

Read the referenced code and determine:

1. TRUE POSITIVE - A real bug that needs fixing
2. FALSE POSITIVE - Not actually a bug (intentional behavior, bot misunderstanding)
3. UNCERTAIN - Not sure; ask the user

Likely TRUE POSITIVE:

• Code obviously violates stated behavior
• Missing null checks on potentially undefined values
• Type mismatches or incorrect function signatures
• Logic errors in conditionals
• Missing error handling for documented failure cases

Likely FALSE POSITIVE:

• Bot doesn't understand the framework/library patterns
• Code is intentionally structured that way (with comments explaining why)
• Bot is flagging style preferences, not bugs
• The "bug" is actually a feature or intentional behavior
• Bot misread the code flow

For Human Comments

Read the referenced code and the reviewer's comment. Human reviewers are generally more accurate and context-aware than bots. Determine:

1. ACTIONABLE - The reviewer identified a real issue or requested a concrete change
2. DISCUSSION - The comment raises a valid point but the right approach is unclear
3. ALREADY ADDRESSED - The concern has already been fixed or is no longer relevant

Likely ACTIONABLE:

• Reviewer points out a bug or logic error
• Reviewer requests a specific code change
• Reviewer identifies missing edge cases or error handling

Likely DISCUSSION -- ask the user:

• Reviewer suggests an architectural change you're unsure about
• Comment involves a tradeoff (performance vs readability, etc.)
• The feedback is subjective without team consensus

When UNCERTAIN -- ask the user

For both bot and human comments:

• The fix would require architectural changes
• You're genuinely unsure if the behavior is intentional
• Multiple valid interpretations exist
• The fix could have unintended side effects

Act on Evaluation

If TRUE POSITIVE / ACTIONABLE: Fix the code. Track the comment ID and a brief description of the fix.

If FALSE POSITIVE: Do NOT change the code. Track the comment ID and the reason it's not a real bug.

If DISCUSSION: Ask the user to consult the PR author. Apply their decision and track it.

If ALREADY ADDRESSED: Track the comment ID and note why.

If UNCERTAIN: Ask the user. If they say skip, track it as skipped.

Do NOT reply to comments yet. Replies happen after the commit (Step 5).

Step 4: Commit and Push

After evaluating and fixing ALL unanswered comments:

1. Run your project's lint and type-check
2. Stage, commit, and push:

   git add -A
   git commit -m "fix: address PR review findings
   
   {List of changes made, grouped by reviewer/bot}"
   git push
   

3. Capture the commit hash from the output.

Step 5: Reply to All Comments

Now that the commit hash exists, reply to every processed comment. The --resolve flag marks the review thread as resolved on GitHub. Use it only when closing the conversation (false positives, discussions concluded, already-addressed, user-skipped), not for fresh fixes that reviewers should still verify.

For each TRUE POSITIVE / ACTIONABLE (we fixed it; leave the thread open so reviewers can verify):

Run npx agent-reviews --reply <comment_id> "Fixed in {hash}. {Brief description of the fix}"

For each FALSE POSITIVE (closing the conversation):

Run npx agent-reviews --reply <comment_id> "Won't fix: {reason}. {Explanation of why this is intentional or not applicable}" --resolve

For each DISCUSSION (after user decision) (the decision concludes the thread):

Run npx agent-reviews --reply <comment_id> "{Outcome}. {Explanation of the decision and any changes made}" --resolve

For each ALREADY ADDRESSED (nothing more to do):

Run npx agent-reviews --reply <comment_id> "Already addressed. {Explanation of when/how this was fixed}" --resolve

For each SKIPPED (user chose not to address it):

Run npx agent-reviews --reply <comment_id> "Skipped per user request" --resolve

Non-threadable comments: If a comment was posted as a PR-level issue comment or review-summary submission (not an inline review comment on a specific line), the CLI cannot post a threaded reply and will print ⊘ Skipped reply: comment is not part of a review thread. That's expected. Record the outcome in the summary and move on; do not retry.

DO NOT start Phase 2 until all replies are posted.

---

Phase 2: POLL FOR NEW COMMENTS (loop until quiet)

The watcher exits immediately when new comments are found (after a 5s grace period to catch batch posts). This means you run it in a loop: start watcher, process any comments it returns, restart watcher, repeat until the watcher times out with no new comments.

Step 6: Start Watcher Loop

Repeat the following until the watcher exits with no new comments:

6a. Launch the watcher in the background:

Run npx agent-reviews --watch as a background task.

6b. Wait for the background command to complete (default 10 minutes; override with --timeout).

6c. Check the output:

• If new comments were found (output contains EXITING WITH NEW COMMENTS):

  1. Use --detail <id> to read each new comment's full detail
  2. Process them exactly as in Phase 1, Steps 3-5 (evaluate, fix, commit, push, reply)
  3. Go back to Step 6a to restart the watcher

• If no new comments (output contains WATCH COMPLETE): Stop looping and move to the Summary Report.

---

Summary Report

After both phases complete, provide a summary:

## PR Review Resolution Summary

### Results
- Fixed: X issues
- Already addressed: X
- Won't fix (false positives): X
- Discussion resolved: X
- Skipped per user: X

### By Reviewer/Bot
#### cursor[bot]
- {description} - Fixed in {commit}
- {description} - Won't fix: {reason}

#### @reviewer-name
- {description} - Fixed in {commit}

### Status
All findings addressed. Watch completed.

Important Notes

Response Policy

• Every comment gets a response - No silent ignores
• For bots: responses help train them and prevent re-raised false positives
• For humans: replies keep reviewers informed and unblock approvals

User Interaction

• Ask the user when uncertain about a finding
• Don't guess on architectural or business logic questions
• It's better to ask than to make a wrong fix or wrong dismissal
• Human reviewers often have context you don't - defer to the author when unsure

Best Practices

• Verify findings before fixing - bots have false positives, humans rarely do
• Keep fixes minimal and focused - don't refactor unrelated code
• Ensure type-check and lint pass before committing
• Group related fixes into a single commit
• Copilot suggestion blocks often contain ready-to-use fixes
• If a human reviewer suggests a specific code change, prefer their version unless it introduces issues