resolve-agent-reviews

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Automatically resolve findings from PR review bots (Copilot, Cursor Bugbot, CodeRabbit, etc.) on the current PR. Uses a two-phase workflow: fix all existing issues, then poll for new ones until bots go quiet.

自动处理当前PR上来自PR审查机器人（Copilot、Cursor Bugbot、CodeRabbit等）发现的问题。采用两阶段工作流：先修复所有现有问题，再轮询新问题直到机器人不再输出新内容。

Prerequisites

前置要求

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.

以下所有命令均使用

npx agent-reviews

。如果项目使用其他包管理器，请替换为对应的运行命令（例如pnpm使用

pnpm dlx agent-reviews

，Yarn使用

yarn dlx agent-reviews

，Bun使用

bunx agent-reviews

）。全程遵循用户的包管理器偏好。

仅云环境（例如Codespaces、远程Agent）：需要验证git提交者身份，以便CI检查可以将提交映射到对应使用者。运行

git config --global --get user.email

，如果返回为空或者是占位符，请手动设置。本地环境可跳过此检查。

Phase 1: FETCH & FIX (synchronous)

阶段1：拉取与修复（同步执行）

Step 1: Fetch All Bot Comments (Expanded)

步骤1：拉取所有机器人评论（扩展模式）

Run

npx agent-reviews --bots-only --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 only unanswered bot comments 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 bot comments found" and skip to Phase 2.

运行

npx agent-reviews --bots-only --unanswered --expanded

该CLI会自动检测当前分支，查找关联的PR，并通过

gh

CLI或环境变量完成鉴权。如果任何环节出错（无token、无对应PR、CLI未安装），会返回清晰的错误信息并退出。

该命令仅返回未回复的机器人评论的完整详情：完整评论内容（无截断）、差异片段（代码上下文）以及所有回复。每条评论会在括号中显示其ID（例如

[12345678]

）。

如果返回零条评论，打印“未找到未回复的机器人评论”并直接跳转到阶段2。

Step 3: Process Each Unanswered Comment

步骤3：处理每条未回复评论

For each comment from the expanded output:

针对扩展输出中的每条评论：

A. Evaluate the Finding

A. 评估发现的问题

Read the referenced code and determine:

TRUE POSITIVE - A real bug that needs fixing
FALSE POSITIVE - Not actually a bug (intentional behavior, bot misunderstanding)
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

When UNCERTAIN -- ask the user:

The fix would require architectural changes
You're genuinely unsure if the behavior is intentional
The "bug" relates to business logic you don't fully understand
Multiple valid interpretations exist
The fix could have unintended side effects

阅读引用的代码并判定问题类型：

真阳性（TRUE POSITIVE） - 确实需要修复的真实bug
假阳性（FALSE POSITIVE） - 实际不是bug（预期行为、机器人理解错误）
不确定（UNCERTAIN） - 无法判定，询问用户

大概率为真阳性的情况：

代码明显违反了既定行为
潜在未定义值缺少空值检查
类型不匹配或函数签名错误
条件判断存在逻辑错误
已文档化的失败场景缺少错误处理

大概率为假阳性的情况：

机器人不理解所使用的框架/库的模式
代码是有意这样设计的（有注释说明原因）
机器人标记的是风格偏好，而非bug
所谓的“bug”实际上是功能或预期行为
机器人误读了代码流程

不确定时需询问用户的情况：

修复需要进行架构调整
你真的不确定该行为是否是预期设计
所谓的“bug”涉及你不完全理解的业务逻辑
存在多种合理的解读
修复可能会产生意外的副作用

B. Act on Evaluation

B. 根据评估结果执行操作

If TRUE POSITIVE: 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 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).

如果是真阳性： 修复代码。记录评论ID和修复内容的简短描述。

如果是假阳性： 不要修改代码。记录评论ID以及该问题不是真实bug的原因。

如果是不确定： 询问用户。如果用户要求跳过，则标记为已跳过。

暂时不要回复评论，回复操作会在提交后执行（步骤5）。

Step 4: Commit and Push

步骤4：提交并推送

After evaluating and fixing ALL unanswered comments:

Run your project's lint and type-check

Stage, commit, and push:

bash

git add -A
git commit -m "fix: address PR review bot findings

{List of bugs fixed, grouped by bot}"
git push

Capture the commit hash from the output.

在评估并修复所有未回复评论后：

运行项目的lint和类型检查

暂存、提交并推送：

bash

git add -A
git commit -m "fix: address PR review bot findings

{List of bugs fixed, grouped by bot}"
git push

捕获输出中的提交哈希值。

Step 5: Reply to All Comments

步骤5：回复所有评论

Now that the commit hash exists, reply to every processed comment. The

--resolve

flag marks the review thread as resolved on GitHub.

For each TRUE POSITIVE:

Run

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

For each FALSE POSITIVE:

Run

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

For each SKIPPED:

Run

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

DO NOT start Phase 2 until all replies are posted.

现在提交哈希已生成，回复所有处理过的评论。

--resolve

参数会将GitHub上的审查线程标记为已解决。

针对每个真阳性问题：

运行

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

针对每个假阳性问题：

运行

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

针对每个已跳过的问题：

运行

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

所有回复发布前不要开始阶段2。

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

阶段2：轮询新评论（循环直到无新输出）

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.

当发现新评论时，监控程序会立即退出（有5秒的宽限期以捕获批量提交的内容）。这意味着你需要循环运行它：启动监控程序，处理它返回的所有评论，重启监控程序，重复直到监控程序超时且无新评论返回。

Step 6: Start Watcher Loop

步骤6：启动监控循环

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

6a. Launch the watcher in the background:

Run

npx agent-reviews --watch --bots-only

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.

重复以下操作直到监控程序退出且无新评论：

6a. 后台启动监控程序：

后台运行

npx agent-reviews --watch --bots-only

。

6b. 等待后台命令执行完成（默认10分钟；可通过

--timeout

参数覆盖）。

6c. 检查输出：

如果发现新评论（输出包含
```
EXITING WITH NEW COMMENTS
```
）：
1. 使用
```
--detail <id>
```
  读取每条新评论的完整详情
2. 完全按照阶段1的步骤3-5处理（评估、修复、提交、推送、回复）
3. 回到步骤6a重启监控程序
如果无新评论（输出包含
```
WATCH COMPLETE
```
）：停止循环，进入总结报告环节。

Summary Report

总结报告

After both phases complete, provide a summary:

text

undefined

两个阶段都完成后，提供如下总结：

text

undefined

PR Review Bot Resolution Summary

Results

Fixed: X bugs
Already fixed: X bugs
Won't fix (false positives): X
Skipped per user: X

Fixed: X bugs
Already fixed: X bugs
Won't fix (false positives): X
Skipped per user: X

By Bot

cursor[bot]

BUG-001: {description} - Fixed in {commit}
BUG-002: {description} - Won't fix: {reason}

BUG-001: {description} - Fixed in {commit}
BUG-002: {description} - Won't fix: {reason}

Copilot

{description} - Fixed in {commit}

{description} - Fixed in {commit}

Status

All findings addressed. Watch completed.

undefined

All findings addressed. Watch completed.

undefined

Important Notes

重要注意事项

Response Policy

回复规则

Every finding gets a response - No silent ignores
Responses help train bots and document decisions
"Won't fix" responses prevent the same false positive from being re-raised

每条发现的问题都要有回复 - 不要静默忽略
回复有助于训练机器人并记录决策
“不予修复”的回复可以避免相同的假阳性问题被再次提出

User Interaction

用户交互

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

对问题不确定时要询问用户
不要猜测架构或业务逻辑相关的问题
询问好过做出错误的修复或错误的驳回

Best Practices

最佳实践

Verify findings before fixing - bots have false positives
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

修复前先验证问题 - 机器人也会有误报
保持修复最小化且聚焦 - 不要重构不相关的代码
提交前确保类型检查和lint通过
将相关的修复合并到单次提交中
Copilot
```
suggestion
```
块通常包含可直接使用的修复方案