feat: 重试与超时策略细化(可配 + 退避)tsk_N5wO3Armums2

## 变更摘要

### 1. 项目级可配重试上限与超时
- `Project` 新增 `maxRetries`(默认 2)和 `timeoutMs`(默认 30min = 1800000ms)字段
- SQLite schema:`projects` 表补 `max_retries` / `timeout_ms` 列(带 DEFAULT 的轻量迁移)
- `createProject` / `patchProject` 支持设置 / 校验新字段(maxRetries>=0, timeoutMs>=1000)
- API `POST /api/projects` 与 `PATCH /api/projects/:id` 透传新字段
- `runner.ts` 将 `project.timeoutMs` 传给 `runClaude`,不再固定 30min

### 2. 失败重试指数退避
- 编排器内存维护 `backoffUntil` Map(taskId → nextRetryAt),daemon 重启后清空
- 退避公式:`min(30s * 2^(attempt-1), 10min)`,第 1 次 30s / 第 2 次 60s / ...
- `claimable()` 过滤退避冷却中的任务
- `nowMs` 注入点(默认 `Date.now`)使测试可快进时钟验证退避行为

### 3. needs_attention 一键重投
- `Task` 新增 `retryBaseline` 字段(默认 0):记录上次重投时的失败 run 基线
- `Store.requeueTask(taskId)`:设置基线 = 当前失败 run 数 → 转 `queued`(仅限 needs_attention)
- 编排器用净失败数(`allFailed - retryBaseline`)判断是否已耗尽重试次数
- API `POST /api/tasks/:id/requeue` + MCP `requeue_task` 工具

### 4. 测试
- 重命名 `MAX_RETRIES` → `DEFAULT_MAX_RETRIES`,新增导出 `computeBackoffMs`
- 新增测试(共 +18):maxRetries=1/0、退避时序(精确 ms 边界)、重投后基线重置
- 迁移测试扩展:验证旧库补列后 maxRetries/timeoutMs/retryBaseline 使用默认值

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
wangjia
2026-06-13 04:04:41 +08:00
parent bb6186902a
commit c89d6d129c
12 changed files with 347 additions and 31 deletions
+8 -4
View File
@@ -7,14 +7,16 @@ import type { RunKind, RunStatus, EventType } from '../model/types.js';
export interface ProjectRow {
id: string; name: string; repo_path: string; default_branch: string;
verify_cmd: string | null; autonomy: string; model: string | null;
concurrency: number; status: string; created_at: string;
concurrency: number; max_retries: number; timeout_ms: number;
status: string; created_at: string;
last_sync_at: string | null; logo: string | null; sort_order: number;
}
export interface TaskRow {
id: string; project_id: string; parent_id: string | null; depth: number;
title: string; complexity: string; status: string; priority: number;
deps: string; plan: string | null; spec: string | null; operations: string | null;
result: string | null; assignee: string | null; created_at: string; updated_at: string;
result: string | null; assignee: string | null; retry_baseline: number;
created_at: string; updated_at: string;
source_ref: string | null;
}
export interface ApprovalRow {
@@ -34,7 +36,8 @@ export function rowToProject(r: ProjectRow): Project {
return {
id: r.id, name: r.name, repoPath: r.repo_path, defaultBranch: r.default_branch,
verifyCmd: r.verify_cmd, autonomy: r.autonomy as Autonomy, model: r.model,
concurrency: r.concurrency, status: r.status as Project['status'], createdAt: r.created_at,
concurrency: r.concurrency, maxRetries: r.max_retries ?? 2, timeoutMs: r.timeout_ms ?? 1_800_000,
status: r.status as Project['status'], createdAt: r.created_at,
lastSyncAt: r.last_sync_at, logo: r.logo, sortOrder: r.sort_order,
};
}
@@ -63,7 +66,8 @@ export function rowToTask(r: TaskRow, approvals: ApprovalRecord[] = []): Task {
priority: r.priority, deps: JSON.parse(r.deps) as string[],
plan: r.plan, spec: r.spec, operations: r.operations,
approvals, result: r.result ? parseResult(r.result) : null,
assignee: r.assignee as Task['assignee'], createdAt: r.created_at, updatedAt: r.updated_at,
assignee: r.assignee as Task['assignee'], retryBaseline: r.retry_baseline ?? 0,
createdAt: r.created_at, updatedAt: r.updated_at,
};
}