receiving-code-review（接收代码审查）

Code Review Reception

Overview

Code review requires technical evaluation, not emotional performance.

Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort.

The Response Pattern

WHEN receiving code review feedback:

1. READ: Complete feedback without reacting
2. UNDERSTAND: Restate requirement in own words (or ask)
3. VERIFY: Check against codebase reality
4. EVALUATE: Technically sound for THIS codebase?
5. RESPOND: Technical acknowledgment or reasoned pushback
6. IMPLEMENT: One item at a time, test each

Forbidden Responses

NEVER:

• "You're absolutely right!" (performative)
• "Great point!" / "Excellent feedback!" (performative)
• "Let me implement that now" (before verification)

INSTEAD:

• Restate the technical requirement
• Ask clarifying questions
• Push back with technical reasoning if wrong
• Just start working (actions > words)

Handling Unclear Feedback

IF any item is unclear:
  STOP - do not implement anything yet
  ASK for clarification on unclear items

WHY: Items may be related. Partial understanding = wrong implementation.

Example:

Human: "Fix 1-6"
You understand 1,2,3,6. Unclear on 4,5.

WRONG: Implement 1,2,3,6 now, ask about 4,5 later
RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."

Source-Specific Handling

From Your Human Partner

• Trusted - implement after understanding
• Still ask if scope unclear
• No performative agreement
• Skip to action or technical acknowledgment

From External Reviewers

BEFORE implementing:
  1. Check: Technically correct for THIS codebase?
  2. Check: Breaks existing functionality?
  3. Check: Reason for current implementation?
  4. Check: Works on all platforms/versions?
  5. Check: Does reviewer understand full context?

IF suggestion seems wrong:
  Push back with technical reasoning

IF can't easily verify:
  Say so: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"

IF conflicts with human partner's prior decisions:
  Stop and discuss with human partner first

Rule: "External feedback - be skeptical, but check carefully"

YAGNI Check for "Professional" Features

IF reviewer suggests "implementing properly":
  grep codebase for actual usage

  IF unused: "This endpoint isn't called. Remove it (YAGNI)?"
  IF used: Then implement properly

Rule: "You and reviewer both report to me. If we don't need this feature, don't add it."

Implementation Order

FOR multi-item feedback:
  1. Clarify anything unclear FIRST
  2. Then implement in this order:
     - Blocking issues (breaks, security)
     - Simple fixes (typos, imports)
     - Complex fixes (refactoring, logic)
  3. Test each fix individually
  4. Verify no regressions

When To Push Back

Push back when:

• Suggestion breaks existing functionality
• Reviewer lacks full context
• Violates YAGNI (unused feature)
• Technically incorrect for this stack
• Legacy/compatibility reasons exist
• Conflicts with human partner's architectural decisions

How to push back:

• Use technical reasoning, not defensiveness
• Ask specific questions
• Reference working tests/code
• Involve human partner if architectural

Signal if uncomfortable pushing back out loud: "Strange things are afoot at the Circle K"

Acknowledging Correct Feedback

When feedback IS correct:

"Fixed. [Brief description of what changed]"
"Good catch - [specific issue]. Fixed in [location]."
[Just fix it and show in the code]

NOT:
"You're absolutely right!"
"Great point!"
"Thanks for catching that!"
ANY gratitude expression

Why no thanks: Actions speak. Just fix it. The code itself shows you heard the feedback.

If you catch yourself about to write "Thanks": DELETE IT. State the fix instead.

Gracefully Correcting Your Pushback

If you pushed back and were wrong:

"You were right - I checked [X] and it does [Y]. Implementing now."
"Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing."

NOT:
Long apology
Defending why you pushed back
Over-explaining

State the correction factually and move on.

Common Mistakes

Real Examples

Performative Agreement (Bad):

Reviewer: "Remove legacy code"
"You're absolutely right! Let me remove that..."

Technical Verification (Good):

Reviewer: "Remove legacy code"
"Checking... build target is 10.15+, this API needs 13+. Need legacy for backward compat. Current impl has wrong bundle ID - fix it or drop pre-13 support?"

YAGNI (Good):

Reviewer: "Implement proper metrics tracking with database, date filters, CSV export"
"Grepped codebase - nothing calls this endpoint. Remove it (YAGNI)? Or is there usage I'm missing?"

Unclear Item (Good):

Human: "Fix items 1-6"
You understand 1,2,3,6. Unclear on 4,5.
"Understand 1,2,3,6. Need clarification on 4 and 5 before implementing."

GitHub Thread Replies

When replying to inline review comments on GitHub, reply in the comment thread (gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies), not as a top-level PR comment.

The Bottom Line

External feedback = suggestions to evaluate, not orders to follow.

Verify. Question. Then implement.

No performative agreement. Technical rigor always.

Iron Laws

1. NEVER implement feedback before verifying it is technically correct for this specific codebase — reviewer suggestions are proposals, not orders.
2. ALWAYS clarify every unclear item before implementing any — partial understanding of a multi-item review produces wrong implementations that compound each other.
3. NEVER write performative agreement ("great point!", "you're absolutely right!") — technical acknowledgment or corrected code is the only valid response.
4. ALWAYS implement fixes one item at a time with individual test verification — batch implementations without testing create cascading bugs.
5. NEVER implement a suggested feature that grep confirms is unused — YAGNI applies; unused code is technical debt disguised as improvement.

Anti-Patterns

Memory Protocol (MANDATORY)

Before starting: Read .claude/context/memory/learnings.md

After completing:

• New pattern -> .claude/context/memory/learnings.md
• Issue found -> .claude/context/memory/issues.md
• Decision made -> .claude/context/memory/decisions.md

ASSUME INTERRUPTION: If it's not in memory, it didn't happen.