CounterDroneBackend/AGENTS.md
tian b957a5e2b4 feat: Planner 使用真实物理计算 + 完善单元测试 + 规则7
- ComputeEffectiveRadius: 基于 AmmunitionSpec 三阶段扩散模型
- CalcRoundsNeeded: 真实有效半径和弹药参数
- GenerateFireEvents: recommendedTiming = arrivalTime - expansionTime
- 候选概率基于真实覆盖计算
- 24 个单元测试覆盖威胁排序/弹药匹配/候选过滤/弹药数/时机/多威胁/空基
- AGENTS.md 规则7: 只跑相关测试,不跑全量
2026-06-13 09:30:04 +08:00

3.2 KiB

CLAUDE.md

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

  • State your assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them - don't pick silently.
  • If a simpler approach exists, say so. Push back when warranted.
  • If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked.
  • No abstractions for single-use code.
  • No "flexibility" or "configurability" that wasn't requested.
  • No error handling for impossible scenarios.
  • If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

  • Don't "improve" adjacent code, comments, or formatting.
  • Don't refactor things that aren't broken.
  • Match existing style, even if you'd do it differently.
  • If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

  • Remove imports/variables/functions that YOUR changes made unused.
  • Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "Add validation" → "Write tests for invalid inputs, then make them pass"
  • "Fix the bug" → "Write a test that reproduces it, then make it pass"
  • "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:

1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.


5. Use PowerShell for Shell Commands

All shell commands, scripts, rg/fd calls run through pwsh, never cmd or bash.

  • Prefix every shell invocation with pwsh -Command "..."
  • Example: pwsh -Command "rg -n 'class' src/"
  • Example: pwsh -Command "./build.bat"

6. Verify Unity Scripts After Changes

After modifying src/CounterDrone.Core/ or src/Unity/Assets/Scripts/, run:

pwsh scripts/check_unity_build.ps1

This automatically rebuilds Core.dll, copies it to Unity Plugins, and compiles Unity scripts. Exits 0 if all pass.

7. Run Targeted Tests, Not Full Suite

Never run all tests unless explicitly asked. Always use --filter to run only the tests relevant to what you changed.

# Run a single test:
pwsh -Command "dotnet test test/unit/CounterDrone.Core.Tests/ --filter 'FullyQualifiedName~TestName'"

# Run a test class:
pwsh -Command "dotnet test test/unit/CounterDrone.Core.Tests/ --filter 'FullyQualifiedName~DefensePlannerTests'"

Running all 125+ tests wastes ~30 seconds every time and buries the failures you actually care about.


These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.