Compare commits

..

4 Commits

Author SHA1 Message Date
cexll
9ba6950d21 style(codex-skill): replace emoji with text labels
替换  emoji 为 # Bad: 文字标记,保持文档简洁专业。

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-01 16:22:32 +08:00
cexll
7f790fbe15 remove codex-wrapper bin 2025-12-01 16:21:57 +08:00
cexll
06f14aa695 fix(codex-wrapper): improve --parallel parameter validation and docs
修复问题:
- codex-wrapper --parallel 模式缺少参数验证,用户误传额外参数导致 shell 解析错误
- 文档中缺少正确 vs 错误用法对比,容易误导用户

主要改进:

1. codex-wrapper/main.go:
   - 添加 --parallel 参数验证 (366-373行)
   - 当检测到额外参数时,输出清晰的错误提示和正确用法示例
   - 更新 --help 文档,添加 --parallel 使用说明

2. skills/codex/SKILL.md:
   - 添加重要提示框,明确 --parallel 只从 stdin 读取配置
   - 新增"正确 vs 错误用法"对比部分,包含3种常见错误示例
   - 修复所有示例中多余的 `-` 参数
   - 在 Delimiter Format 部分强调 workdir 的正确用法

测试验证:
-  所有单元测试通过
-  参数验证功能正常
-  并行执行功能正常
-  中文内容解析正常

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-01 16:18:36 +08:00
cexll
9fa872a1f0 update codex skill dependencies 2025-12-01 00:11:31 +08:00
2 changed files with 92 additions and 7 deletions

View File

@@ -363,6 +363,14 @@ func run() int {
printHelp()
return 0
case "--parallel":
if len(os.Args) > 2 {
fmt.Fprintln(os.Stderr, "ERROR: --parallel reads its task configuration from stdin and does not accept additional arguments.")
fmt.Fprintln(os.Stderr, "Usage examples:")
fmt.Fprintln(os.Stderr, " codex-wrapper --parallel < tasks.txt")
fmt.Fprintln(os.Stderr, " echo '...' | codex-wrapper --parallel")
fmt.Fprintln(os.Stderr, " codex-wrapper --parallel <<'EOF'")
return 1
}
// Parallel mode: read task config from stdin
data, err := io.ReadAll(stdinReader)
if err != nil {
@@ -888,9 +896,15 @@ Usage:
codex-wrapper - [workdir] Read task from stdin
codex-wrapper resume <session_id> "task" [workdir]
codex-wrapper resume <session_id> - [workdir]
codex-wrapper --parallel Run tasks in parallel (config from stdin)
codex-wrapper --version
codex-wrapper --help
Parallel mode examples:
codex-wrapper --parallel < tasks.txt
echo '...' | codex-wrapper --parallel
codex-wrapper --parallel <<'EOF'
Environment Variables:
CODEX_TIMEOUT Timeout in milliseconds (default: 7200000)

View File

@@ -180,26 +180,89 @@ EOF
### Parallel Execution
> Important:
> - `--parallel` only reads task definitions from stdin.
> - It does not accept extra command-line arguments (no inline `workdir`, `task`, or other params).
> - Put all task metadata and content in stdin; nothing belongs after `--parallel` on the command line.
**Correct vs Incorrect Usage**
**Correct:**
```bash
# Option 1: file redirection
codex-wrapper --parallel < tasks.txt
# Option 2: heredoc (recommended for multiple tasks)
codex-wrapper --parallel <<'EOF'
---TASK---
id: task1
workdir: /path/to/dir
---CONTENT---
task content
EOF
# Option 3: pipe
echo "---TASK---..." | codex-wrapper --parallel
```
**Incorrect (will trigger shell parsing errors):**
```bash
# Bad: no extra args allowed after --parallel
codex-wrapper --parallel - /path/to/dir <<'EOF'
...
EOF
# Bad: --parallel does not take a task argument
codex-wrapper --parallel "task description"
# Bad: workdir must live inside the task config
codex-wrapper --parallel /path/to/dir < tasks.txt
```
For multiple independent or dependent tasks, use `--parallel` mode with delimiter format:
**Typical Workflow (analyze → implement → test, chained in a single parallel call)**:
```bash
codex-wrapper --parallel - <<'EOF'
codex-wrapper --parallel <<'EOF'
---TASK---
id: analyze_1732876800
workdir: /home/user/project
---CONTENT---
analyze requirements @spec.md
analyze @spec.md and summarize API and UI requirements
---TASK---
id: implement_1732876801
workdir: /home/user/project
dependencies: analyze_1732876800
---CONTENT---
implement feature based on analyze_1732876800 analysis
implement features from analyze_1732876800 summary in backend @services and frontend @ui
---TASK---
id: docs_1732876802
workdir: /home/user/project/docs
id: test_1732876802
workdir: /home/user/project
dependencies: implement_1732876801
---CONTENT---
independent task runs in parallel with analyze_1732876800
add and run regression tests covering the new endpoints and UI flows
EOF
```
A single `codex-wrapper --parallel` call schedules all three stages concurrently, using `dependencies` to enforce sequential ordering without multiple invocations.
```bash
codex-wrapper --parallel <<'EOF'
---TASK---
id: backend_1732876800
workdir: /home/user/project/backend
---CONTENT---
implement /api/orders endpoints with validation and pagination
---TASK---
id: frontend_1732876801
workdir: /home/user/project/frontend
---CONTENT---
build Orders page consuming /api/orders with loading/error states
---TASK---
id: tests_1732876802
workdir: /home/user/project/tests
dependencies: backend_1732876800, frontend_1732876801
---CONTENT---
run API contract tests and UI smoke tests (waits for backend+frontend)
EOF
```
@@ -211,15 +274,23 @@ EOF
- `workdir: <path>`: Optional, working directory (default: `.`)
- Best practice: use absolute paths (e.g., `/home/user/project/backend`)
- Avoids ambiguity and ensures consistent behavior across environments
- Must be specified inside each task block; do not pass `workdir` as a CLI argument to `--parallel`
- Each task can set its own `workdir` when different directories are needed
- `dependencies: <id1>, <id2>`: Optional, comma-separated task IDs
- `session_id: <uuid>`: Optional, resume a previous session
- `---CONTENT---`: Separates metadata from task content
- Task content: Any text, code, special characters (no escaping needed)
**Dependencies Best Practices**
- Avoid multiple invocations: Place "analyze then implement" in a single `codex-wrapper --parallel` call, chaining them via `dependencies`, rather than running analysis first and then launching implementation separately.
- Naming convention: Use `<action>_<timestamp>` format (e.g., `analyze_1732876800`, `implement_1732876801`), where action names map to features/stages and timestamps ensure uniqueness and sortability.
- Dependency chain design: Keep chains short; only add dependencies for tasks that truly require ordering, let others run in parallel, avoiding over-serialization that reduces throughput.
**Resume Failed Tasks**:
```bash
# Use session_id from previous output to resume
codex-wrapper --parallel - <<'EOF'
codex-wrapper --parallel <<'EOF'
---TASK---
id: T2
session_id: 019xxx-previous-session-id