resolve-reviews

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

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.

自动处理当前PR上的所有评审评论（包括人工和机器人发出的）。采用两阶段工作流：先修复所有现有问题，再轮询新评论直到无新内容产生。

Prerequisites

前置条件

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，请替换为对应的执行命令（例如pnpm用

pnpm dlx agent-reviews

，Yarn用

yarn dlx agent-reviews

，Bun用

bunx agent-reviews

）。全程遵循用户的包管理器偏好。

仅云环境适用（如Codespaces、远程Agent）：请验证git作者身份，以便CI检查可以将提交映射到对应用户。执行

git config --global --get user.email

，如果返回为空或占位符，请手动设置。本地环境可跳过此检查。

Phase 1: FETCH & FIX (synchronous)

第一阶段：拉取与修复（同步执行）

Step 1: Fetch All Comments (Expanded)

步骤1：拉取所有评论（扩展模式）

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.

执行

npx agent-reviews --unanswered --expanded

该CLI会自动检测当前分支，找到关联的PR，并通过

gh

CLI或环境变量进行身份验证。如果任何步骤失败（无token、无对应PR、CLI未安装），会输出清晰的错误信息并退出。

命令会返回所有未回复评论（含人工和机器人发出的）的完整详情：完整评论内容（无截断）、diff片段（代码上下文）以及所有回复。每条评论会在括号中标注其ID（例如

[12345678]

）。

如果返回零条评论，打印"未找到未回复评论"并直接跳转至第二阶段。

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, apply the appropriate evaluation based on whether the author is a bot or a human.

针对扩展输出中的每条评论，根据评论发布者是机器人还是人工采用对应的评估逻辑。

For Bot Comments

机器人评论

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

读取关联代码并判断属于以下哪类：

真阳性（TRUE POSITIVE）：确实存在需要修复的Bug
假阳性（FALSE POSITIVE）：实际不存在Bug（是预期行为、机器人理解错误）
不确定（UNCERTAIN）：无法判断，询问用户

大概率为真阳性的情况：

代码明显不符合约定的行为
潜在的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：

机器人不理解所用框架/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问题，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

For Human Comments

人工评论

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

ACTIONABLE - The reviewer identified a real issue or requested a concrete change
DISCUSSION - The comment raises a valid point but the right approach is unclear
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

读取关联代码和评审者的评论。人工评审者通常比机器人更准确，上下文感知能力更强。判断属于以下哪类：

可执行（ACTIONABLE）：评审者发现了真实问题，或要求进行具体的修改
待讨论（DISCUSSION）：评论提出了有效观点，但最佳实现方案不明确
已处理（ALREADY ADDRESSED）：相关问题已修复，或不再相关

大概率为可执行的情况：

评审者指出了Bug或逻辑错误
评审者要求进行具体的代码修改
评审者发现了缺失的边界场景或错误处理

大概率为待讨论（需询问用户）的情况：

评审者提出的架构改动你不确定是否合理
评论涉及权衡取舍（比如性能 vs 可读性等）
反馈是主观的，没有团队共识作为依据

When UNCERTAIN -- ask the user

不确定时的处理：询问用户

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

针对机器人和人工评论，出现以下情况时均需询问用户：

修复需要改动架构
你真的不确定当前行为是否是预期内的
存在多种合理解读
修复可能产生意料之外的副作用

Act on Evaluation

基于评估结果执行操作

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).

如果是真阳性/可执行： 修复代码。记录评论ID和修复内容的简要说明。

如果是假阳性： 不要修改代码。记录评论ID和不属于真实Bug的原因。

如果是待讨论： 请用户咨询PR作者。按照用户的决定执行并记录结果。

如果是已处理： 记录评论ID和相关说明。

如果是不确定： 询问用户。如果用户要求跳过，记录为已跳过。

暂时不要回复评论，所有回复会在提交之后（步骤5）统一处理。

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 findings

{List of changes made, grouped by reviewer/bot}"
git push

Capture the commit hash from the output.

评估并修复完所有未回复评论后：

执行项目的lint和类型检查

暂存、提交并推送：

bash

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

{按评审者/机器人分组的修改列表}"
git push

从输出中获取提交哈希值。

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 / ACTIONABLE:

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 DISCUSSION (after user decision):

Run

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

For each ALREADY ADDRESSED:

Run

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

现在已经有了提交哈希值，给每条处理过的评论回复。

--resolve

参数会在GitHub上将评审线程标记为已解决。

针对每条真阳性/可执行评论：

执行

npx agent-reviews --reply <comment_id> "Fixed in {hash}. {修复内容的简要说明}" --resolve

针对每条假阳性评论：

执行

npx agent-reviews --reply <comment_id> "Won't fix: {原因}. {说明为什么是预期行为或不适用}" --resolve

针对每条待讨论评论（用户作出决定后）：

执行

npx agent-reviews --reply <comment_id> "{处理结果}. {说明决策原因和所作改动}" --resolve

针对每条已处理评论：

执行

npx agent-reviews --reply <comment_id> "Already addressed. {说明修复的时间/方式}" --resolve

针对每条已跳过评论：

执行

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

所有回复发布完成前，不要开始第二阶段。

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

第二阶段：轮询新评论（循环直到无新内容）

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.

当检测到新评论时，监听程序会立即退出（会有5秒的宽限期来接收批量发布的评论）。这意味着你需要循环运行它：启动监听程序，处理返回的所有评论，重启监听程序，重复直到监听程序超时且没有新评论产生。

Step 6: Start Watcher Loop

步骤6：启动监听循环

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

6a. Launch the watcher in the background:

Run

npx agent-reviews --watch

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听程序退出且无新评论：

6a. 在后台启动监听程序：

将

npx agent-reviews --watch

作为后台任务运行。

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. 完全按照第一阶段的步骤3-5处理（评估、修复、提交、推送、回复）
3. 返回步骤6a重启监听程序
如果没有新评论（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 Resolution Summary

Results

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

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}

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

@reviewer-name

{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 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

每条评论都必须回复 - 不要默默忽略
对机器人的回复有助于训练它们，避免后续重复提出假阳性问题
对人工的回复可以让评审者及时了解进度，消除审批阻塞

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
Human reviewers often have context you don't - defer to the author when unsure

对评审结果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
询问用户好过做出错误的修复或驳回
人工评审者通常拥有你不了解的上下文 - 不确定时请遵从PR作者的意见

Best Practices

最佳实践

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

修复前验证问题的真实性 - 机器人会有误报，人工很少出现
修复内容要最小化且聚焦 - 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的
```
suggestion
```
块通常包含可直接使用的修复方案
如果人工评审者提出了具体的代码修改建议，优先采用他们的方案，除非该方案会引入问题