401 lines
11 KiB
Markdown
401 lines
11 KiB
Markdown
---
|
||
created: "2026-04-06"
|
||
type: resource
|
||
tags: [resource, claude-code, AI-tools, autonomous-loops, agent-orchestration, ECC]
|
||
source: "~/.claude/skills/autonomous-loops/SKILL.md"
|
||
---
|
||
|
||
# Autonomous Loops 自主循环模式
|
||
|
||
ECC 提供的让 Claude Code 在无人干预下持续循环工作的模式集合。v1.10.0 中 `autonomous-loops` 已标记为兼容保留，新的 canonical 名称是 `continuous-agent-loop`。
|
||
|
||
相关笔记：[[dmux 多Agent并行编排]]、[[Everything Claude Code 完整指南]]、[[Ralphinho RFC-DAG 编排模式]]、[[Autonomous Agent Harness 自主代理框架]]、[[ECC 编排替代方案 (orchestrate 迁移)]]
|
||
|
||
## 模式选择流程
|
||
|
||
```
|
||
单个聚焦的改动？
|
||
├─ 是 -> Sequential Pipeline
|
||
└─ 否 -> 有写好的 spec/RFC？
|
||
├─ 是 -> 需要并行实现？
|
||
│ ├─ 是 -> Ralphinho (DAG)
|
||
│ └─ 否 -> Continuous PR Loop
|
||
└─ 否 -> 需要同一事物的多个变体？
|
||
├─ 是 -> Infinite Agentic Loop
|
||
└─ 否 -> Sequential + De-Sloppify
|
||
```
|
||
|
||
## 模式总览
|
||
|
||
| 模式 | 复杂度 | 适用场景 | 上下文管理 |
|
||
|------|--------|---------|-----------|
|
||
| Sequential Pipeline | 低 | 单功能开发、日常 bugfix | 每步全新上下文，靠文件系统传递 |
|
||
| NanoClaw REPL | 低 | 交互式探索、持久会话 | Markdown 文件累积历史 |
|
||
| Infinite Agentic Loop | 中 | 批量内容生成、多变体 | Orchestrator 分配方向 |
|
||
| Continuous PR Loop | 中 | 多天迭代、提升覆盖率 | SHARED_TASK_NOTES.md 桥接 |
|
||
| De-Sloppify | 附加 | 任何实现步骤后的清理 | 独立清理 agent |
|
||
| Ralphinho RFC-DAG | 高 | 大型功能、多 unit 并行 | DAG 依赖 + 合并队列 |
|
||
|
||
---
|
||
|
||
## 模式 1: Sequential Pipeline
|
||
|
||
最简单最实用。把开发拆成多个 `claude -p` 非交互调用，串行执行。
|
||
|
||
### 核心原理
|
||
|
||
- 每次 `claude -p` 是全新上下文，无前一步记忆
|
||
- 靠文件系统状态在步骤间传递信息
|
||
- `set -e` 任何步骤失败就停止
|
||
|
||
### 基本模板
|
||
|
||
```bash
|
||
#!/bin/bash
|
||
set -e
|
||
|
||
# 实现
|
||
claude -p "Read the spec in docs/spec.md. Implement the feature. Write tests first (TDD)."
|
||
|
||
# 清理 (De-Sloppify)
|
||
claude -p "Review all changes. Remove unnecessary tests and defensive checks. Run tests."
|
||
|
||
# 验证
|
||
claude -p "Run full build, lint, test suite. Fix any failures. Do not add new features."
|
||
|
||
# 提交
|
||
claude -p "Create a conventional commit for all staged changes."
|
||
```
|
||
|
||
### 进阶技巧
|
||
|
||
**按复杂度选模型：**
|
||
```bash
|
||
claude -p --model haiku "Fix import ordering in src/utils.ts" # 简单
|
||
claude -p --model sonnet "Implement caching layer" # 中等
|
||
claude -p --model opus "Refactor auth module to strategy pattern" # 复杂
|
||
```
|
||
|
||
**限制工具权限：**
|
||
```bash
|
||
claude -p --allowedTools "Read,Grep,Glob" "Audit for security..." # 只读分析
|
||
claude -p --allowedTools "Read,Write,Edit,Bash" "Implement fixes..." # 可写实现
|
||
```
|
||
|
||
**通过文件传递上下文：**
|
||
```bash
|
||
echo "Focus: auth module, API rate limiting" > .claude-context.md
|
||
claude -p "Read .claude-context.md for priorities. Work through them."
|
||
rm .claude-context.md
|
||
```
|
||
|
||
### 实际例子：smart-support 加反馈评分功能
|
||
|
||
```bash
|
||
#!/bin/bash
|
||
set -e
|
||
|
||
# Step 1: 规划
|
||
claude -p "Read docs/DEVELOPMENT-PLAN.md and docs/ARCHITECTURE.md.
|
||
Plan a user feedback rating feature:
|
||
- Backend: POST /api/feedback, store in PostgreSQL
|
||
- Frontend: thumbs up/down on AI reply
|
||
- Analytics: feedback stats query
|
||
Write plan to docs/phases/feedback-plan.md"
|
||
|
||
# Step 2: 后端 TDD
|
||
claude -p "Read docs/phases/feedback-plan.md.
|
||
Create backend/app/feedback/models.py and router.py.
|
||
Write tests FIRST in backend/tests/unit/test_feedback.py.
|
||
Follow patterns from backend/app/analytics/.
|
||
Run pytest --cov=app."
|
||
|
||
# Step 3: 前端
|
||
claude -p "Read docs/phases/feedback-plan.md.
|
||
Create FeedbackButton component. Wire into chat message.
|
||
Call POST /api/feedback on click."
|
||
|
||
# Step 4: 清理
|
||
claude -p "Review git diff. Remove test slop, console.log, commented code.
|
||
Run pytest --cov=app."
|
||
|
||
# Step 5: 验证 + 提交
|
||
claude -p "Run pytest --cov=app --cov-report=term-missing. Fix failures."
|
||
claude -p "Stage feedback-related files. Commit: feat: add user feedback rating"
|
||
```
|
||
|
||
---
|
||
|
||
## 模式 2: NanoClaw REPL
|
||
|
||
ECC 内置的持久会话 REPL，对话历史存储为 Markdown。
|
||
|
||
### 启动
|
||
|
||
```bash
|
||
node ~/.claude/scripts/claw.js
|
||
|
||
# 带名称和技能
|
||
CLAW_SESSION=my-project CLAW_SKILLS=tdd-workflow,security-review node ~/.claude/scripts/claw.js
|
||
```
|
||
|
||
### 内置命令
|
||
|
||
| 命令 | 功能 |
|
||
|------|------|
|
||
| `/model` | 切换模型 |
|
||
| `/load` | 动态加载 skill |
|
||
| `/branch` | 会话分支 |
|
||
| `/search` | 跨会话搜索 |
|
||
| `/compact` | 压缩历史 |
|
||
| `/export` | 导出为 md/json/txt |
|
||
| `/metrics` | 会话指标 |
|
||
|
||
### vs Sequential Pipeline
|
||
|
||
| | NanoClaw | Sequential Pipeline |
|
||
|---|---|---|
|
||
| 交互式 | 是 | 否 |
|
||
| 上下文累积 | 每轮增长 | 每步全新 |
|
||
| 会话持久化 | 内置 | 手动 |
|
||
| CI/CD 集成 | 差 | 好 |
|
||
| 适合 | 探索性工作 | 脚本自动化 |
|
||
|
||
---
|
||
|
||
## 模式 3: Infinite Agentic Loop
|
||
|
||
按 spec 批量并行生成多个变体。Orchestrator 读 spec，分配不同创意方向给 N 个子 agent。
|
||
|
||
### 原理
|
||
|
||
1. Orchestrator 读取 specification 文件
|
||
2. 扫描 output 目录找到最高迭代号
|
||
3. 并行启动 N 个子 agent，每个分配不同的创意方向和迭代号
|
||
4. infinite 模式下以 3-5 个为一波持续生成
|
||
|
||
### 设置
|
||
|
||
创建 `.claude/commands/infinite.md`：
|
||
|
||
```markdown
|
||
Parse the following arguments from $ARGUMENTS:
|
||
1. spec_file -- path to the specification markdown
|
||
2. output_dir -- where iterations are saved
|
||
3. count -- integer 1-N or "infinite"
|
||
|
||
PHASE 1: Read and deeply understand the specification.
|
||
PHASE 2: List output_dir, find highest iteration number. Start at N+1.
|
||
PHASE 3: Plan creative directions -- each agent gets a DIFFERENT theme.
|
||
PHASE 4: Deploy sub-agents in parallel (Task tool).
|
||
PHASE 5 (infinite mode): Loop in waves of 3-5 until context is low.
|
||
```
|
||
|
||
### 调用
|
||
|
||
```bash
|
||
/project:infinite specs/component-spec.md src/ 5 # 生成5个
|
||
/project:infinite specs/component-spec.md src/ infinite # 持续生成
|
||
```
|
||
|
||
### 批次策略
|
||
|
||
| 数量 | 策略 |
|
||
|------|------|
|
||
| 1-5 | 全部同时 |
|
||
| 6-20 | 每批5个 |
|
||
| infinite | 每波3-5个，逐步提升复杂度 |
|
||
|
||
### 关键：通过分配确保唯一性
|
||
|
||
不要依赖 agent 自行区分。Orchestrator 显式分配每个 agent 的创意方向和迭代号，避免重复。
|
||
|
||
---
|
||
|
||
## 模式 4: Continuous PR Loop
|
||
|
||
生产级自动 PR 循环：建分支 -> 实现 -> 建 PR -> 等 CI -> 合并 -> 循环。
|
||
|
||
### 循环流程
|
||
|
||
```
|
||
1. Create branch (continuous-claude/iteration-N)
|
||
2. Run claude -p with enhanced prompt
|
||
3. (Optional) Reviewer pass
|
||
4. Commit changes
|
||
5. Push + create PR (gh pr create)
|
||
6. Wait for CI checks (poll gh pr checks)
|
||
7. CI failure? -> Auto-fix pass
|
||
8. Merge PR
|
||
9. Return to main -> repeat
|
||
```
|
||
|
||
### 使用
|
||
|
||
```bash
|
||
# 基本：10轮迭代
|
||
continuous-claude --prompt "Add unit tests for untested functions" --max-runs 10
|
||
|
||
# 限制花费
|
||
continuous-claude --prompt "Fix all linter errors" --max-cost 5.00
|
||
|
||
# 限制时间
|
||
continuous-claude --prompt "Improve test coverage" --max-duration 8h
|
||
|
||
# 带 review pass
|
||
continuous-claude \
|
||
--prompt "Add authentication feature" \
|
||
--max-runs 10 \
|
||
--review-prompt "Run npm test && npm run lint, fix any failures"
|
||
|
||
# 并行 (worktree 隔离)
|
||
continuous-claude --prompt "Add tests" --worktree tests-worker &
|
||
continuous-claude --prompt "Refactor" --worktree refactor-worker &
|
||
wait
|
||
```
|
||
|
||
### 跨迭代上下文：SHARED_TASK_NOTES.md
|
||
|
||
每轮开始读、结束写，桥接 `claude -p` 的无记忆问题：
|
||
|
||
```markdown
|
||
## Progress
|
||
- [x] app/feedback/ - 65% -> 92% (iteration 1)
|
||
- [x] app/graph.py - 70% -> 88% (iteration 2)
|
||
- [ ] app/openapi/ - 68% (next target)
|
||
|
||
## Overall: 82% -> 91%
|
||
```
|
||
|
||
### CI 失败自动恢复
|
||
|
||
自动 `gh run view` 查日志 -> 修代码 -> 推送 -> 重新等 CI（最多 `--ci-retry-max` 次）。
|
||
|
||
### 完成信号
|
||
|
||
```bash
|
||
continuous-claude \
|
||
--prompt "Fix all bugs" \
|
||
--completion-signal "CONTINUOUS_CLAUDE_PROJECT_COMPLETE" \
|
||
--completion-threshold 3 # 连续3轮"完成"才停
|
||
```
|
||
|
||
### 关键配置
|
||
|
||
| Flag | 功能 |
|
||
|------|------|
|
||
| `--max-runs N` | 最多 N 轮 |
|
||
| `--max-cost $X` | 花费上限 |
|
||
| `--max-duration 2h` | 时间上限 |
|
||
| `--merge-strategy squash` | squash/merge/rebase |
|
||
| `--worktree <name>` | 并行用 worktree |
|
||
| `--disable-commits` | 干跑模式 |
|
||
| `--review-prompt "..."` | 每轮加 review |
|
||
| `--ci-retry-max N` | CI 失败自动修复次数 |
|
||
|
||
### 实际例子：提升 smart-support 测试覆盖率
|
||
|
||
```bash
|
||
continuous-claude \
|
||
--prompt "Read backend/tests/ and find modules with lowest coverage.
|
||
Write unit tests for the least-covered module.
|
||
Use pytest patterns from conftest.py.
|
||
Run pytest --cov=app --cov-report=term-missing.
|
||
Update SHARED_TASK_NOTES.md with progress." \
|
||
--max-runs 8 \
|
||
--max-cost 10.00 \
|
||
--review-prompt "Run pytest --cov=app. If coverage < 95%, note gaps." \
|
||
--completion-signal "COVERAGE_TARGET_MET" \
|
||
--completion-threshold 2
|
||
```
|
||
|
||
---
|
||
|
||
## 模式 5: De-Sloppify (附加清理 Pass)
|
||
|
||
不是独立模式，而是加在任何实现步骤后的清理。
|
||
|
||
### 问题
|
||
|
||
LLM 做 TDD 时过度测试：测类型系统能不能工作、加不必要的防御性检查。
|
||
|
||
### 错误做法
|
||
|
||
在提示里说"不要测类型系统" -> 模型变畏首畏尾，跳过正常测试。
|
||
|
||
### 正确做法
|
||
|
||
让实现步骤自由发挥，然后加独立清理 agent：
|
||
|
||
```bash
|
||
for feature in "${features[@]}"; do
|
||
claude -p "Implement $feature with TDD."
|
||
claude -p "Cleanup: remove test/code slop, run tests."
|
||
claude -p "Run build + lint + tests. Fix failures."
|
||
claude -p "Commit: feat: add $feature"
|
||
done
|
||
```
|
||
|
||
> 核心洞察：两个专注的 agent 优于一个受约束的 agent。
|
||
|
||
---
|
||
|
||
## ECC 内置命令
|
||
|
||
### 启动循环
|
||
|
||
```bash
|
||
/ecc:loop-start sequential # Sequential 模式
|
||
/ecc:loop-start continuous-pr # PR 循环模式
|
||
/ecc:loop-start rfc-dag # Ralphinho 模式
|
||
/ecc:loop-start infinite # 无限生成模式
|
||
|
||
/ecc:loop-start sequential --mode safe # safe = 严格质量门
|
||
/ecc:loop-start sequential --mode fast # fast = 减少检查
|
||
```
|
||
|
||
### 监控
|
||
|
||
```bash
|
||
/ecc:loop-status # 查看当前循环状态
|
||
/ecc:loop-status --watch # 持续监控
|
||
```
|
||
|
||
### 故障恢复
|
||
|
||
```
|
||
1. 冻结循环
|
||
2. 运行 /harness-audit
|
||
3. 缩小范围到失败的 unit
|
||
4. 用明确的验收标准重试
|
||
```
|
||
|
||
---
|
||
|
||
## 反模式
|
||
|
||
| 反模式 | 问题 | 正确做法 |
|
||
|--------|------|---------|
|
||
| 无退出条件的无限循环 | 烧钱 | 始终设 max-runs/max-cost/max-duration |
|
||
| 迭代间无上下文桥梁 | 重复劳动 | 用 SHARED_TASK_NOTES.md |
|
||
| 对同一失败盲目重试 | 浪费 | 捕获错误上下文给下次 |
|
||
| 用否定指令代替清理 pass | 质量下降 | De-Sloppify 独立 pass |
|
||
| 所有 agent 在同一上下文 | 自我审查偏差 | 每阶段独立进程 |
|
||
| 并行任务编辑同一文件 | 冲突 | git worktree 隔离 |
|
||
|
||
---
|
||
|
||
## 组合使用
|
||
|
||
1. **Sequential + De-Sloppify** -- 最常见，每个实现步骤后加清理
|
||
2. **Continuous PR + De-Sloppify** -- `--review-prompt` 里加清理指令
|
||
3. **任何循环 + Verification** -- 提交前用 `/ecc:verify` 做质量门
|
||
4. **简单循环里用分级模型** -- 简单任务 Haiku，复杂任务 Opus
|
||
|
||
## Related
|
||
|
||
- [[dmux 多Agent并行编排]]
|
||
- [[Ralphinho RFC-DAG 编排模式]]
|
||
- [[Everything Claude Code 完整指南]]
|
||
- [[Everything Claude Code 用法速查]]
|