fix(#196): fix race condition in job status updates

Implemented optimistic locking with version field and SELECT FOR UPDATE
transactions to prevent data corruption from concurrent job status updates.

Changes:
- Added version field to RunnerJob schema for optimistic locking
- Created migration 20260202_add_runner_job_version_for_concurrency
- Implemented ConcurrentUpdateException for conflict detection
- Updated RunnerJobsService methods with optimistic locking:
  * updateStatus() - with version checking and retry logic
  * updateProgress() - with version checking and retry logic
  * cancel() - with version checking and retry logic
- Updated CoordinatorIntegrationService with SELECT FOR UPDATE:
  * updateJobStatus() - transaction with row locking
  * completeJob() - transaction with row locking
  * failJob() - transaction with row locking
  * updateJobProgress() - optimistic locking
- Added retry mechanism (3 attempts) with exponential backoff
- Added comprehensive concurrency tests (10 tests, all passing)
- Updated existing test mocks to support updateMany

Test Results:
- All 10 concurrency tests passing ✓
- Tests cover concurrent status updates, progress updates, completions,
  cancellations, retry logic, and exponential backoff

This fix prevents race conditions that could cause:
- Lost job results (double completion)
- Lost progress updates
- Invalid status transitions
- Data corruption under concurrent access

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
Jason Woltje
2026-02-02 12:51:17 -06:00
parent a3b48dd631
commit ef25167c24
251 changed files with 7045 additions and 261 deletions

View File

@@ -1,10 +1,19 @@
import { Injectable, NotFoundException } from "@nestjs/common";
import { Prisma } from "@prisma/client";
import { Prisma, Task } from "@prisma/client";
import { PrismaService } from "../prisma/prisma.service";
import { ActivityService } from "../activity/activity.service";
import { TaskStatus, TaskPriority } from "@prisma/client";
import type { CreateTaskDto, UpdateTaskDto, QueryTasksDto } from "./dto";
type TaskWithRelations = Task & {
assignee: { id: string; name: string; email: string } | null;
creator: { id: string; name: string; email: string };
project: { id: string; name: string; color: string | null } | null;
subtasks?: (Task & {
assignee: { id: string; name: string; email: string } | null;
})[];
};
/**
* Service for managing tasks
*/
@@ -18,7 +27,11 @@ export class TasksService {
/**
* Create a new task
*/
async create(workspaceId: string, userId: string, createTaskDto: CreateTaskDto) {
async create(
workspaceId: string,
userId: string,
createTaskDto: CreateTaskDto
): Promise<Omit<TaskWithRelations, "subtasks">> {
const assigneeConnection = createTaskDto.assigneeId
? { connect: { id: createTaskDto.assigneeId } }
: undefined;
@@ -79,7 +92,15 @@ export class TasksService {
/**
* Get paginated tasks with filters
*/
async findAll(query: QueryTasksDto) {
async findAll(query: QueryTasksDto): Promise<{
data: Omit<TaskWithRelations, "subtasks">[];
meta: {
total: number;
page: number;
limit: number;
totalPages: number;
};
}> {
const page = query.page ?? 1;
const limit = query.limit ?? 50;
const skip = (page - 1) * limit;
@@ -159,7 +180,7 @@ export class TasksService {
/**
* Get a single task by ID
*/
async findOne(id: string, workspaceId: string) {
async findOne(id: string, workspaceId: string): Promise<TaskWithRelations> {
const task = await this.prisma.task.findUnique({
where: {
id,
@@ -195,7 +216,12 @@ export class TasksService {
/**
* Update a task
*/
async update(id: string, workspaceId: string, userId: string, updateTaskDto: UpdateTaskDto) {
async update(
id: string,
workspaceId: string,
userId: string,
updateTaskDto: UpdateTaskDto
): Promise<Omit<TaskWithRelations, "subtasks">> {
// Verify task exists
const existingTask = await this.prisma.task.findUnique({
where: { id, workspaceId },
@@ -305,7 +331,7 @@ export class TasksService {
/**
* Delete a task
*/
async remove(id: string, workspaceId: string, userId: string) {
async remove(id: string, workspaceId: string, userId: string): Promise<void> {
// Verify task exists
const task = await this.prisma.task.findUnique({
where: { id, workspaceId },