Add tests for CLI command generation and model alias resolution

- Implement `test-cli-command-gen.js` to verify the logic of `buildCliCommand` function.
- Create `test-e2e-model-alias.js` for end-to-end testing of model alias resolution in `ccw cli`.
- Add `test-model-alias.js` to test model alias resolution for different models.
- Introduce `test-model-alias.txt` for prompt testing with model alias.
- Develop `test-update-claude-command.js` to test command generation for `update_module_claude`.
- Create a test file in `test-update-claude/src` for future tests.
This commit is contained in:
catlog22
2026-02-05 20:17:10 +08:00
parent 6576886457
commit 01459a34a5
193 changed files with 4796 additions and 9405 deletions

View File

@@ -1,173 +0,0 @@
# Action: Complete
完成工作流并生成最终报告。
## Purpose
序列化最终状态,生成执行摘要,清理临时文件。
## Preconditions
- [ ] `state.status === "running"`
- [ ] 所有 issues 已处理或错误限制达到
## Execution
```javascript
async function execute(state) {
const workDir = state.work_dir;
const issues = state.issues || {};
console.log("\n=== Finalizing Workflow ===");
// 1. 生成统计信息
const totalIssues = Object.keys(issues).length;
const completedCount = Object.values(issues).filter(i => i.status === "completed").length;
const failedCount = Object.values(issues).filter(i => i.status === "failed").length;
const pendingCount = totalIssues - completedCount - failedCount;
const stats = {
total_issues: totalIssues,
completed: completedCount,
failed: failedCount,
pending: pendingCount,
success_rate: totalIssues > 0 ? ((completedCount / totalIssues) * 100).toFixed(1) : 0,
duration_ms: new Date() - new Date(state.created_at)
};
console.log("\n=== Summary ===");
console.log(`Total Issues: ${stats.total_issues}`);
console.log(`✓ Completed: ${stats.completed}`);
console.log(`✗ Failed: ${stats.failed}`);
console.log(`○ Pending: ${stats.pending}`);
console.log(`Success Rate: ${stats.success_rate}%`);
console.log(`Duration: ${(stats.duration_ms / 1000).toFixed(1)}s`);
// 2. 生成详细报告
const reportLines = [
"# Execution Report",
"",
`## Summary`,
`- Total Issues: ${stats.total_issues}`,
`- Completed: ${stats.completed}`,
`- Failed: ${stats.failed}`,
`- Pending: ${stats.pending}`,
`- Success Rate: ${stats.success_rate}%`,
`- Duration: ${(stats.duration_ms / 1000).toFixed(1)}s`,
"",
"## Results by Issue"
];
Object.values(issues).forEach((issue, index) => {
const status = issue.status === "completed" ? "✓" : issue.status === "failed" ? "✗" : "○";
reportLines.push(`### ${status} [${index + 1}] ${issue.id}: ${issue.title}`);
reportLines.push(`- Status: ${issue.status}`);
if (issue.solution_id) {
reportLines.push(`- Solution: ${issue.solution_id}`);
}
if (issue.planned_at) {
reportLines.push(`- Planned: ${issue.planned_at}`);
}
if (issue.executed_at) {
reportLines.push(`- Executed: ${issue.executed_at}`);
}
if (issue.error) {
reportLines.push(`- Error: ${issue.error}`);
}
reportLines.push("");
});
if (state.errors && state.errors.length > 0) {
reportLines.push("## Errors");
state.errors.forEach(error => {
reportLines.push(`- [${error.timestamp}] ${error.action}: ${error.message}`);
});
reportLines.push("");
}
reportLines.push("## Files Generated");
reportLines.push(`- Work Directory: ${workDir}`);
reportLines.push(`- State File: ${workDir}/state.json`);
reportLines.push(`- Execution Results: ${workDir}/execution-results.json`);
reportLines.push(`- Solutions: ${workDir}/solutions/`);
reportLines.push(`- Snapshots: ${workDir}/snapshots/`);
// 3. 保存报告
const reportPath = `${workDir}/final-report.md`;
Write(reportPath, reportLines.join("\n"));
// 4. 保存最终状态
const finalState = {
...state,
status: "completed",
phase: "completed",
completed_at: new Date().toISOString(),
completed_actions: [...state.completed_actions, "action-complete"],
context: {
...state.context,
...stats
}
};
Write(`${workDir}/state.json`, JSON.stringify(finalState, null, 2));
// 5. 保存汇总 JSON
Write(`${workDir}/summary.json`, JSON.stringify({
status: "completed",
stats: stats,
report_file: reportPath,
work_dir: workDir,
completed_at: new Date().toISOString()
}, null, 2));
// 6. 输出完成消息
console.log(`\n✓ Workflow completed`);
console.log(`📄 Report: ${reportPath}`);
console.log(`📁 Working directory: ${workDir}`);
return {
stateUpdates: {
status: "completed",
phase: "completed",
completed_at: new Date().toISOString(),
completed_actions: [...state.completed_actions, "action-complete"],
context: finalState.context
}
};
}
```
## State Updates
```javascript
return {
stateUpdates: {
status: "completed",
phase: "completed",
completed_at: timestamp,
completed_actions: [...state.completed_actions, "action-complete"],
context: {
total_issues: stats.total_issues,
completed_count: stats.completed,
failed_count: stats.failed,
success_rate: stats.success_rate
}
}
};
```
## Error Handling
| Error Type | Recovery |
|------------|----------|
| 报告生成失败 | 输出文本摘要到控制台 |
| 文件写入失败 | 继续完成,允许手动保存 |
| 权限错误 | 使用替代目录 |
## Next Actions (Hints)
- 无(终止状态)
- 用户可选择:
- 查看报告:`cat {report_path}`
- 恢复并重试失败的 issues`codex issue:plan-execute --resume {work_dir}`
- 清理临时文件:`rm -rf {work_dir}`

View File

@@ -1,220 +0,0 @@
# Action: Execute Solutions
按队列顺序执行已规划的解决方案。
## Purpose
加载计划的解决方案并使用 subagent 执行所有任务、提交更改。
## Preconditions
- [ ] `state.status === "running"`
- [ ] `issues with solution_id` exist (来自规划阶段)
## Execution
```javascript
async function execute(state) {
const workDir = state.work_dir;
const issues = state.issues || {};
const queue = state.queue || [];
// 1. 构建执行队列(来自已规划的 issues
const plannedIssues = Object.values(issues).filter(i => i.status === "planned");
if (plannedIssues.length === 0) {
console.log("No planned solutions to execute");
return { stateUpdates: { queue } };
}
console.log(`\n=== Executing ${plannedIssues.length} Solutions ===`);
// 2. 序列化执行每个解决方案
const executionResults = [];
for (let i = 0; i < plannedIssues.length; i++) {
const issue = plannedIssues[i];
const solutionId = issue.solution_id;
console.log(`\n[${i + 1}/${plannedIssues.length}] Executing: ${solutionId}`);
try {
// 创建快照(便于恢复)
const beforeSnapshot = {
timestamp: new Date().toISOString(),
phase: "before-execute",
issue_id: issue.id,
solution_id: solutionId,
state: { ...state }
};
Write(`${workDir}/snapshots/snapshot-before-execute-${i}.json`, JSON.stringify(beforeSnapshot, null, 2));
// 执行 subagent
const executionPrompt = `
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: ~/.codex/agents/issue-execute-agent.md (MUST read first)
2. Read: .workflow/project-tech.json
3. Read: .workflow/project-guidelines.json
---
Goal: Execute solution "${solutionId}" for issue "${issue.id}"
Scope:
- CAN DO: Implement tasks, run tests, commit code
- CANNOT DO: Push to remote or create PRs without approval
- Directory: ${process.cwd()}
Solution ID: ${solutionId}
Load solution details:
- Read: ${workDir}/solutions/${issue.id}-plan.json
Execution steps:
1. Parse all tasks from solution
2. Execute each task: implement → test → verify
3. Commit once for all tasks with formatted summary
4. Report completion
Quality bar:
- All acceptance criteria verified
- Tests passing
- Commit message follows conventions
Return: JSON with files_modified[], commit_hash, status
`;
const result = await Task({
subagent_type: "universal-executor",
run_in_background: false,
description: `Execute solution ${solutionId}`,
prompt: executionPrompt
});
// 解析执行结果
let execResult;
try {
execResult = typeof result === "string" ? JSON.parse(result) : result;
} catch {
execResult = { status: "executed", commit_hash: "unknown" };
}
// 保存执行结果
Write(`${workDir}/solutions/${issue.id}-execution.json`, JSON.stringify({
solution_id: solutionId,
issue_id: issue.id,
status: "completed",
executed_at: new Date().toISOString(),
execution_result: execResult
}, null, 2));
// 更新 issue 状态
issues[issue.id].status = "completed";
issues[issue.id].executed_at = new Date().toISOString();
// 更新队列项
const queueIndex = queue.findIndex(q => q.solution_id === solutionId);
if (queueIndex >= 0) {
queue[queueIndex].status = "completed";
}
// 更新 ccw
try {
Bash(`ccw issue update ${issue.id} --status completed`);
} catch (error) {
console.log(`Note: Could not update ccw status (${error.message})`);
}
console.log(`${solutionId} completed`);
executionResults.push({
issue_id: issue.id,
solution_id: solutionId,
status: "completed",
commit: execResult.commit_hash
});
state.context.completed_count++;
} catch (error) {
console.error(`✗ Execution failed for ${solutionId}: ${error.message}`);
// 更新失败状态
issues[issue.id].status = "failed";
issues[issue.id].error = error.message;
state.context.failed_count++;
executionResults.push({
issue_id: issue.id,
solution_id: solutionId,
status: "failed",
error: error.message
});
}
}
// 3. 保存执行结果摘要
Write(`${workDir}/execution-results.json`, JSON.stringify({
total: plannedIssues.length,
completed: state.context.completed_count,
failed: state.context.failed_count,
results: executionResults,
timestamp: new Date().toISOString()
}, null, 2));
return {
stateUpdates: {
issues: issues,
queue: queue,
context: state.context,
completed_actions: [...state.completed_actions, "action-execute"]
}
};
}
```
## State Updates
```javascript
return {
stateUpdates: {
issues: {
[issue.id]: {
...issue,
status: "completed|failed",
executed_at: timestamp,
error: errorMessage
}
},
queue: [
...queue.map(item =>
item.solution_id === solutionId
? { ...item, status: "completed|failed" }
: item
)
],
context: {
...state.context,
completed_count: newCompletedCount,
failed_count: newFailedCount
}
}
};
```
## Error Handling
| Error Type | Recovery |
|------------|----------|
| 任务执行失败 | 标记为失败,继续下一个 |
| 测试失败 | 不提交,标记为失败 |
| 提交失败 | 保存快照便于恢复 |
| Subagent 超时 | 记录超时,继续 |
## Next Actions (Hints)
- 执行完成:转入 action-complete 阶段
- 有失败项:用户选择是否重试
- 全部完成:生成最终报告

View File

@@ -1,86 +0,0 @@
# Action: Initialize
初始化 Skill 执行状态和工作目录。
## Purpose
设置初始状态,创建工作目录,准备执行环境。
## Preconditions
- [ ] `state.status === "pending"`
## Execution
```javascript
async function execute(state) {
// 创建工作目录
const timestamp = new Date().toISOString().slice(0,19).replace(/[-:T]/g, '');
const workDir = `.workflow/.scratchpad/codex-issue-${timestamp}`;
Bash(`mkdir -p "${workDir}/solutions" "${workDir}/snapshots"`);
// 初始化状态
const initialState = {
status: "running",
phase: "initialized",
work_dir: workDir,
issues: {},
queue: [],
completed_actions: ["action-init"],
context: {
total_issues: 0,
completed_count: 0,
failed_count: 0
},
errors: [],
created_at: new Date().toISOString(),
updated_at: new Date().toISOString()
};
// 保存初始状态
Write(`${workDir}/state.json`, JSON.stringify(initialState, null, 2));
Write(`${workDir}/state-history.json`, JSON.stringify([{
timestamp: initialState.created_at,
phase: "init",
completed_actions: 1,
issues_count: 0
}], null, 2));
console.log(`✓ Initialized: ${workDir}`);
return {
stateUpdates: {
status: "running",
phase: "initialized",
work_dir: workDir,
completed_actions: ["action-init"]
}
};
}
```
## State Updates
```javascript
return {
stateUpdates: {
status: "running",
phase: "initialized",
work_dir: workDir,
completed_actions: ["action-init"]
}
};
```
## Error Handling
| Error Type | Recovery |
|------------|----------|
| 目录创建失败 | 检查权限,使用临时目录 |
| 文件写入失败 | 重试或切换存储位置 |
## Next Actions (Hints)
- 成功:进入 listing phase执行 action-list
- 失败:中止工作流

View File

@@ -1,165 +0,0 @@
# Action: List Issues
列出 issues 并支持用户交互选择。
## Purpose
展示当前所有 issues 的状态,收集用户的规划/执行意图。
## Preconditions
- [ ] `state.status === "running"`
## Execution
```javascript
async function execute(state) {
// 1. 加载或初始化 issues
let issues = state.issues || {};
// 2. 从 ccw issue list 或提供的参数加载 issues
// 这取决于用户是否在命令行提供了 issue IDs
// 示例ccw codex issue:plan-execute ISS-001,ISS-002
// 对于本次演示,我们假设从 issues.jsonl 加载
try {
const issuesListOutput = Bash("ccw issue list --status registered,planned --json").output;
const issuesList = JSON.parse(issuesListOutput);
issuesList.forEach(issue => {
if (!issues[issue.id]) {
issues[issue.id] = {
id: issue.id,
title: issue.title,
status: "registered",
solution_id: null,
planned_at: null,
executed_at: null,
error: null
};
}
});
} catch (error) {
console.log("Note: Could not load issues from ccw issue list");
// 使用来自参数的 issues或者空列表
}
// 3. 显示当前状态
const totalIssues = Object.keys(issues).length;
const registeredCount = Object.values(issues).filter(i => i.status === "registered").length;
const plannedCount = Object.values(issues).filter(i => i.status === "planned").length;
const completedCount = Object.values(issues).filter(i => i.status === "completed").length;
console.log("\n=== Issue Status ===");
console.log(`Total: ${totalIssues} | Registered: ${registeredCount} | Planned: ${plannedCount} | Completed: ${completedCount}`);
if (totalIssues === 0) {
console.log("\nNo issues found. Please create issues first using 'ccw issue init'");
return {
stateUpdates: {
context: {
...state.context,
total_issues: 0
}
}
};
}
// 4. 显示详细列表
console.log("\n=== Issue Details ===");
Object.values(issues).forEach((issue, index) => {
const status = issue.status === "completed" ? "✓" : issue.status === "planned" ? "→" : "○";
console.log(`${status} [${index + 1}] ${issue.id}: ${issue.title} (${issue.status})`);
});
// 5. 询问用户下一步
const issueIds = Object.keys(issues);
const pendingIds = issueIds.filter(id => issues[id].status === "registered");
if (pendingIds.length === 0) {
console.log("\nNo unplanned issues. Ready to execute planned solutions.");
return {
stateUpdates: {
context: {
...state.context,
total_issues: totalIssues
}
}
};
}
// 6. 显示选项
console.log("\nNext action:");
console.log("- Enter 'p' to PLAN selected issues");
console.log("- Enter 'x' to EXECUTE planned solutions");
console.log("- Enter 'a' to plan ALL pending issues");
console.log("- Enter 'q' to QUIT");
const response = await AskUserQuestion({
questions: [{
question: "Select issues to plan (comma-separated numbers, or 'all'):",
header: "Selection",
multiSelect: false,
options: pendingIds.slice(0, 4).map(id => ({
label: `${issues[id].id}: ${issues[id].title}`,
description: `Current status: ${issues[id].status}`
}))
}]
});
// 7. 更新 issues 状态为 "planning"
const selectedIds = [];
if (response.Selection === "all") {
selectedIds.push(...pendingIds);
} else {
// 解析用户选择
selectedIds.push(response.Selection);
}
selectedIds.forEach(issueId => {
if (issues[issueId]) {
issues[issueId].status = "planning";
}
});
return {
stateUpdates: {
issues: issues,
context: {
...state.context,
total_issues: totalIssues
}
}
};
}
```
## State Updates
```javascript
return {
stateUpdates: {
issues: issues,
context: {
total_issues: Object.keys(issues).length,
registered_count: registeredCount,
planned_count: plannedCount,
completed_count: completedCount
}
}
};
```
## Error Handling
| Error Type | Recovery |
|------------|----------|
| Issues 加载失败 | 使用空列表继续 |
| 用户输入无效 | 要求重新选择 |
| 列表显示异常 | 使用 JSON 格式输出 |
## Next Actions (Hints)
- 有 "planning" issues执行 action-plan
- 无 pending issues执行 action-execute
- 用户取消:中止

View File

@@ -1,170 +0,0 @@
# Action: Plan Solutions
为选中的 issues 生成执行方案。
## Purpose
使用 subagent 分析 issues 并生成解决方案,支持多解决方案选择和自动绑定。
## Preconditions
- [ ] `state.status === "running"`
- [ ] `issues with status === "planning"` exist
## Execution
```javascript
async function execute(state) {
const workDir = state.work_dir;
const issues = state.issues || {};
// 1. 识别需要规划的 issues
const planningIssues = Object.values(issues).filter(i => i.status === "planning");
if (planningIssues.length === 0) {
console.log("No issues to plan");
return { stateUpdates: { issues } };
}
console.log(`\n=== Planning ${planningIssues.length} Issues ===`);
// 2. 为每个 issue 生成规划 subagent
const planningAgents = planningIssues.map(issue => ({
issue_id: issue.id,
issue_title: issue.title,
prompt: `
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: ~/.codex/agents/issue-plan-agent.md (MUST read first)
2. Read: .workflow/project-tech.json
3. Read: .workflow/project-guidelines.json
4. Read schema: ~/.claude/workflows/cli-templates/schemas/solution-schema.json
---
Goal: Plan solution for issue "${issue.id}: ${issue.title}"
Scope:
- CAN DO: Explore codebase, design solutions, create tasks
- CANNOT DO: Execute solutions, modify production code
- Directory: ${process.cwd()}
Task Description:
${issue.title}
Deliverables:
- Create ONE primary solution
- Write to: ${workDir}/solutions/${issue.id}-plan.json
- Format: JSON following solution-schema.json
Quality bar:
- Tasks have quantified acceptance.criteria
- Each task includes test.commands
- Solution follows schema exactly
Return: JSON with solution_id, task_count, status
`
}));
// 3. 执行规划(串行执行避免竞争)
for (const agent of planningAgents) {
console.log(`\n→ Planning: ${agent.issue_id}`);
try {
// 对于 Codex这里应该使用 spawn_agent
// 对于 Claude Code Task使用 Task()
// 模拟 Task 调用 (实际应该是 spawn_agent 对于 Codex)
const result = await Task({
subagent_type: "universal-executor",
run_in_background: false,
description: `Plan solution for ${agent.issue_id}`,
prompt: agent.prompt
});
// 解析结果
let planResult;
try {
planResult = typeof result === "string" ? JSON.parse(result) : result;
} catch {
planResult = { status: "executed", solution_id: `SOL-${agent.issue_id}-1` };
}
// 更新 issue 状态
issues[agent.issue_id].status = "planned";
issues[agent.issue_id].solution_id = planResult.solution_id || `SOL-${agent.issue_id}-1`;
issues[agent.issue_id].planned_at = new Date().toISOString();
console.log(`${agent.issue_id}${issues[agent.issue_id].solution_id}`);
// 绑定解决方案
try {
Bash(`ccw issue bind ${agent.issue_id} ${issues[agent.issue_id].solution_id}`);
} catch (error) {
console.log(`Note: Could not bind solution (${error.message})`);
}
} catch (error) {
console.error(`✗ Planning failed for ${agent.issue_id}: ${error.message}`);
issues[agent.issue_id].status = "registered"; // 回退
issues[agent.issue_id].error = error.message;
}
}
// 4. 更新 issue 状态到 ccw
try {
Bash(`ccw issue update --from-planning`);
} catch {
console.log("Note: Could not update issue status");
}
return {
stateUpdates: {
issues: issues,
completed_actions: [...state.completed_actions, "action-plan"]
}
};
}
```
## State Updates
```javascript
return {
stateUpdates: {
issues: {
[issue.id]: {
...issue,
status: "planned",
solution_id: solutionId,
planned_at: timestamp
}
},
queue: [
...state.queue,
{
item_id: `S-${index}`,
issue_id: issue.id,
solution_id: solutionId,
status: "pending"
}
]
}
};
```
## Error Handling
| Error Type | Recovery |
|------------|----------|
| Subagent 超时 | 标记为失败,继续下一个 |
| 无效解决方案 | 回退到 registered 状态 |
| 绑定失败 | 记录警告,但继续 |
| 文件写入失败 | 重试 3 次 |
## Next Actions (Hints)
- 所有 issues 规划完成:执行 action-execute
- 部分失败:用户选择是否继续或重试
- 全部失败:返回 action-list 重新选择