init datamate

backend/openapi/specs/data-annotation.yaml

@@ -0,0 +1,298 @@
+openapi: 3.0.3
+info:
+  title: Data Annotation Service API
+  description: 数据标注服务API - 智能预标注、人工平台、主动学习
+  version: 1.0.0
+  contact:
+    name: Data Mate Platform Team
+
+servers:
+  - url: http://localhost:8080
+    description: Development server
+
+tags:
+  - name: annotation-tasks
+    description: 标注任务管理
+  - name: annotation-data
+    description: 标注数据管理
+  - name: pre-annotation
+    description: 智能预标注
+  - name: active-learning
+    description: 主动学习
+
+paths:
+  /api/v1/annotation/tasks:
+    get:
+      tags:
+        - annotation-tasks
+      summary: 获取标注任务列表
+      description: 分页获取标注任务列表
+      parameters:
+        - name: page
+          in: query
+          description: 页码
+          schema:
+            type: integer
+            default: 0
+        - name: size
+          in: query
+          description: 每页大小
+          schema:
+            type: integer
+            default: 20
+        - name: status
+          in: query
+          description: 任务状态
+          schema:
+            type: string
+            enum: [PENDING, IN_PROGRESS, COMPLETED, PAUSED]
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/AnnotationTaskPageResponse'
+        '400':
+          description: 请求参数错误
+        '500':
+          description: 服务器内部错误
+
+    post:
+      tags:
+        - annotation-tasks
+      summary: 创建标注任务
+      description: 创建新的标注任务
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreateAnnotationTaskRequest'
+      responses:
+        '201':
+          description: 创建成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/AnnotationTaskResponse'
+        '400':
+          description: 请求参数错误
+        '500':
+          description: 服务器内部错误
+
+  /api/v1/annotation/tasks/{taskId}:
+    get:
+      tags:
+        - annotation-tasks
+      summary: 获取标注任务详情
+      parameters:
+        - name: taskId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/AnnotationTaskResponse'
+        '404':
+          description: 任务不存在
+
+    put:
+      tags:
+        - annotation-tasks
+      summary: 更新标注任务
+      parameters:
+        - name: taskId
+          in: path
+          required: true
+          schema:
+            type: string
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/UpdateAnnotationTaskRequest'
+      responses:
+        '200':
+          description: 更新成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/AnnotationTaskResponse'
+
+  /api/v1/annotation/pre-annotate:
+    post:
+      tags:
+        - pre-annotation
+      summary: 智能预标注
+      description: 使用AI模型进行智能预标注
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/PreAnnotationRequest'
+      responses:
+        '200':
+          description: 预标注成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/PreAnnotationResponse'
+
+components:
+  schemas:
+    AnnotationTaskResponse:
+      type: object
+      properties:
+        id:
+          type: string
+          description: 任务ID
+        name:
+          type: string
+          description: 任务名称
+        description:
+          type: string
+          description: 任务描述
+        type:
+          type: string
+          enum: [TEXT_CLASSIFICATION, NAMED_ENTITY_RECOGNITION, OBJECT_DETECTION, SEMANTIC_SEGMENTATION]
+          description: 标注类型
+        status:
+          type: string
+          enum: [PENDING, IN_PROGRESS, COMPLETED, PAUSED]
+          description: 任务状态
+        datasetId:
+          type: string
+          description: 数据集ID
+        progress:
+          type: number
+          format: double
+          description: 进度百分比
+        createdAt:
+          type: string
+          format: date-time
+          description: 创建时间
+        updatedAt:
+          type: string
+          format: date-time
+          description: 更新时间
+
+    CreateAnnotationTaskRequest:
+      type: object
+      required:
+        - name
+        - type
+        - datasetId
+      properties:
+        name:
+          type: string
+          description: 任务名称
+        description:
+          type: string
+          description: 任务描述
+        type:
+          type: string
+          enum: [TEXT_CLASSIFICATION, NAMED_ENTITY_RECOGNITION, OBJECT_DETECTION, SEMANTIC_SEGMENTATION]
+          description: 标注类型
+        datasetId:
+          type: string
+          description: 数据集ID
+        configuration:
+          type: object
+          description: 标注配置
+
+    UpdateAnnotationTaskRequest:
+      type: object
+      properties:
+        name:
+          type: string
+          description: 任务名称
+        description:
+          type: string
+          description: 任务描述
+        status:
+          type: string
+          enum: [PENDING, IN_PROGRESS, COMPLETED, PAUSED]
+          description: 任务状态
+
+    AnnotationTaskPageResponse:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/AnnotationTaskResponse'
+        totalElements:
+          type: integer
+          format: int64
+        totalPages:
+          type: integer
+        size:
+          type: integer
+        number:
+          type: integer
+
+    PreAnnotationRequest:
+      type: object
+      required:
+        - taskId
+        - dataIds
+      properties:
+        taskId:
+          type: string
+          description: 标注任务ID
+        dataIds:
+          type: array
+          items:
+            type: string
+          description: 待预标注的数据ID列表
+        modelId:
+          type: string
+          description: 预标注模型ID
+        confidence:
+          type: number
+          format: double
+          description: 置信度阈值
+
+    PreAnnotationResponse:
+      type: object
+      properties:
+        taskId:
+          type: string
+          description: 任务ID
+        processedCount:
+          type: integer
+          description: 已处理数据数量
+        successCount:
+          type: integer
+          description: 成功预标注数量
+        results:
+          type: array
+          items:
+            type: object
+            properties:
+              dataId:
+                type: string
+              annotations:
+                type: array
+                items:
+                  type: object
+              confidence:
+                type: number
+                format: double
+
+  securitySchemes:
+    BearerAuth:
+      type: http
+      scheme: bearer
+      bearerFormat: JWT
+
+security:
+  - BearerAuth: []

backend/openapi/specs/data-cleaning.yaml

@@ -0,0 +1,491 @@
+openapi: 3.0.3
+info:
+  title: Data Cleaning Service API
+  description: 数据清洗服务API - 策略/规则、流程编排对接
+  version: 1.0.0
+  contact:
+    name: Data Mate Platform Team
+
+servers:
+  - url: http://localhost:8084
+    description: Development server
+
+tags:
+  - name: CleaningTask
+    description: 数据清洗任务管理
+  - name: CleaningTemplate
+    description: 数据清洗模板管理
+
+paths:
+  /ray/log:
+    get:
+      summary: 获取ray日志文件
+      deprecated: false
+      description: ''
+      tags: [ ]
+      parameters: [ ]
+      responses:
+        '200':
+          description: ''
+          content:
+            application/json:
+              schema:
+                type: object
+                properties: { }
+          headers: { }
+      security: [ ]
+  /cleaning/tasks:
+    get:
+      summary: 查询数据清洗任务列表
+      deprecated: false
+      description: 获取所有数据清洗任务或根据查询参数筛选任务。
+      tags:
+        - CleaningTask
+      parameters:
+        - name: status
+          in: query
+          description: 根据任务状态筛选 (e.g., pending, running, completed, failed)
+          required: false
+          schema:
+            type: string
+        - name: keywords
+          in: query
+          description: 关键字
+          required: false
+          schema:
+            type: string
+        - name: page
+          in: query
+          description: 分页数
+          required: true
+          schema:
+            type: integer
+        - name: size
+          in: query
+          description: 分页单页数
+          required: true
+          schema:
+            type: integer
+      responses:
+        '200':
+          description: 成功获取任务列表
+          content:
+            application/json:
+              schema:
+                type: array
+                items: &ref_1
+                  $ref: '#/components/schemas/CleaningTask'
+          headers: { }
+      security: [ ]
+    post:
+      summary: 创建新的数据清洗任务
+      deprecated: false
+      description: 可以直接创建任务或基于现有模板创建任务。
+      tags:
+        - CleaningTask
+      parameters: [ ]
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreateCleaningTaskRequest'
+            examples: { }
+      responses:
+        '201':
+          description: 任务创建成功
+          content:
+            application/json:
+              schema: *ref_1
+          headers: { }
+      security: [ ]
+  /cleaning/tasks/{taskId}:
+    get:
+      summary: 获取单个数据清洗任务详情
+      deprecated: false
+      description: 根据任务ID获取任务的详细信息。
+      tags:
+        - CleaningTask
+      parameters:
+        - name: taskId
+          in: path
+          description: 任务的唯一标识符
+          required: true
+          example: ''
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 成功获取任务详情
+          content:
+            application/json:
+              schema: *ref_1
+          headers: { }
+      security: [ ]
+    delete:
+      summary: 删除数据清洗任务
+      deprecated: false
+      description: 根据任务ID删除指定的任务。
+      tags:
+        - CleaningTask
+      parameters:
+        - name: taskId
+          in: path
+          description: 任务的唯一标识符
+          required: true
+          example: ''
+          schema:
+            type: string
+      responses:
+        '204':
+          description: 任务删除成功
+          headers: { }
+      security: [ ]
+  /cleaning/templates:
+    get:
+      summary: 查询数据清洗模板列表
+      deprecated: false
+      description: 获取所有可用的数据清洗模板。
+      tags:
+        - CleaningTemplate
+      parameters: [ ]
+      responses:
+        '200':
+          description: 成功获取模板列表
+          content:
+            application/json:
+              schema:
+                type: array
+                items: &ref_2
+                  $ref: '#/components/schemas/CleaningTemplate'
+          headers: { }
+      security: [ ]
+    post:
+      summary: 创建新的数据清洗模板
+      deprecated: false
+      description: 定义一个新的数据清洗模板。
+      tags:
+        - CleaningTemplate
+      parameters: [ ]
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreateCleaningTemplateRequest'
+      responses:
+        '201':
+          description: 模板创建成功
+          content:
+            application/json:
+              schema: *ref_2
+          headers: { }
+      security: [ ]
+  /cleaning/templates/{templateId}:
+    get:
+      summary: 获取单个数据清洗模板详情
+      deprecated: false
+      description: 根据模板ID获取模板的详细信息。
+      tags:
+        - CleaningTemplate
+      parameters:
+        - name: templateId
+          in: path
+          description: 模板的唯一标识符
+          required: true
+          example: ''
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 成功获取模板详情
+          content:
+            application/json:
+              schema: *ref_2
+          headers: { }
+      security: [ ]
+    put:
+      summary: 更新数据清洗模板
+      deprecated: false
+      description: 根据模板ID更新模板的全部信息。
+      tags:
+        - CleaningTemplate
+      parameters:
+        - name: templateId
+          in: path
+          description: 模板的唯一标识符
+          required: true
+          example: ''
+          schema:
+            type: string
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/UpdateCleaningTemplateRequest'
+      responses:
+        '200':
+          description: 模板更新成功
+          content:
+            application/json:
+              schema: *ref_2
+          headers: { }
+      security: [ ]
+    delete:
+      summary: 删除数据清洗模板
+      deprecated: false
+      description: 根据模板ID删除指定的模板。
+      tags:
+        - CleaningTemplate
+      parameters:
+        - name: templateId
+          in: path
+          description: 模板的唯一标识符
+          required: true
+          example: ''
+          schema:
+            type: string
+      responses:
+        '204':
+          description: 模板删除成功
+          headers: { }
+      security: [ ]
+
+components:
+  schemas:
+    OperatorInstance:
+      type: object
+      properties:
+        id:
+          type: string
+        overrides:
+          type: object
+          properties: { }
+          additionalProperties:
+            type: object
+            properties: { }
+      required:
+        - id
+        - overrides
+    CleaningProcess:
+      type: object
+      properties:
+        process:
+          type: number
+          format: float
+          description: 进度百分比
+        totalFileNum:
+          type: integer
+          description: 总文件数量
+        finishedFileNum:
+          type: integer
+          description: 已完成文件数量
+      required:
+        - process
+        - totalFileNum
+        - finishedFileNum
+    OperatorResponse:
+      type: object
+      properties:
+        id:
+          type: string
+          description: 算子ID
+        name:
+          type: string
+          description: 算子名称
+        description:
+          type: string
+          description: 算子描述
+        version:
+          type: string
+          description: 算子版本
+        inputs:
+          type: string
+          description: 输入类型
+        outputs:
+          type: string
+          description: 输入类型
+        runtime:
+          type: string
+          description: 运行时设置
+        settings:
+          type: string
+          description: 算子参数
+        isStar:
+          type: boolean
+          description: 是否收藏
+        createdAt:
+          type: string
+          format: date-time
+          description: 创建时间
+        updatedAt:
+          type: string
+          format: date-time
+          description: 更新时间
+      required:
+        - inputs
+        - outputs
+        - runtime
+        - settings
+        - isStar
+    UpdateCleaningTemplateRequest:
+      type: object
+      required:
+        - name
+        - instance
+        - id
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+          description: 模板名称
+        description:
+          type: string
+          description: 模板描述
+        instance:
+          type: array
+          items: &ref_3
+            $ref: '#/components/schemas/OperatorInstance'
+          description: 模板定义的清洗规则和配置
+    CreateCleaningTemplateRequest:
+      type: object
+      required:
+        - name
+        - instance
+      properties:
+        name:
+          type: string
+          description: 模板名称
+        description:
+          type: string
+          description: 模板描述
+        instance:
+          type: array
+          items: *ref_3
+          description: 任务的具体配置（如果非模板创建，则直接定义）'
+    CleaningTemplate:
+      type: object
+      required:
+        - id
+        - name
+        - instance
+        - createdAt
+      properties:
+        id:
+          type: string
+          description: 模板唯一标识符
+        name:
+          type: string
+          description: 模板名称
+        description:
+          type: string
+          description: 模板描述
+        instance:
+          type: array
+          items: &ref_4
+            $ref: '#/components/schemas/OperatorResponse'
+          description: 模板定义的清洗规则和配置
+        createdAt:
+          type: string
+          format: date-time
+          description: 模板创建时间
+        updatedAt:
+          type: string
+          format: date-time
+          description: 模板最后更新时间
+    CreateCleaningTaskRequest:
+      type: object
+      required:
+        - name
+        - instance
+        - srcDatasetId
+        - srcDatasetName
+        - destDatasetName
+        - destDatasetType
+      properties:
+        name:
+          type: string
+          description: 任务名称
+        description:
+          type: string
+          description: 任务描述
+        srcDatasetId:
+          type: string
+        srcDatasetName:
+          type: string
+        destDatasetName:
+          type: string
+        destDatasetType:
+          type: string
+        instance:
+          type: array
+          items: *ref_3
+          description: 任务的具体配置（如果非模板创建，则直接定义）
+    ErrorResponse:
+      type: object
+      properties:
+        error:
+          type: string
+          description: 错误类型
+        message:
+          type: string
+          description: 错误详细信息
+    CleaningTask:
+      type: object
+      required:
+        - id
+        - name
+        - status
+        - createdAt
+        - startedAt
+      properties:
+        id:
+          type: string
+          description: 任务唯一标识符
+        name:
+          type: string
+          description: 任务名称
+        description:
+          type: string
+          description: 任务描述
+        srcDatasetId:
+          type: string
+          description: 源数据集id
+        srcDatasetName:
+          type: string
+          description: 源数据集名称
+        destDatasetId:
+          type: string
+          description: 目标数据集id
+        destDatasetName:
+          type: string
+          description: 目标数据集名称
+        status:
+          type: string
+          description: 任务当前状态
+          enum:
+            - pending
+            - running
+            - completed
+            - failed
+        templateId:
+          type: string
+          description: 关联的模板ID（如果基于模板创建）
+        instance:
+          type: array
+          items: *ref_4
+          description: 任务的具体配置（如果非模板创建，则直接定义）
+        progress:
+          $ref: '#/components/schemas/CleaningProcess'
+        createdAt:
+          type: string
+          description: 任务创建时间
+          format: date-time
+        startedAt:
+          type: string
+          format: date-time
+          description: 任务开始时间
+        finishedAt:
+          type: string
+          format: date-time
+          description: 任务最后更新时间
+    securitySchemes: { }

backend/openapi/specs/data-collection.yaml

@@ -0,0 +1,517 @@
+openapi: 3.0.3
+info:
+  title: Data Collection Service API
+  description: |
+    数据归集服务API，基于数据归集实现数据采集和归集功能。
+
+    主要功能：
+    - 数据归集任务创建和管理
+    - 数据同步任务执行
+    - 任务监控和状态查询
+    - 执行日志查看
+
+  version: 1.0.0
+
+servers:
+  - url: http://localhost:8090/api/v1/collection
+    description: Development server
+
+tags:
+  - name: CollectionTask
+    description: 数据归集任务管理（包括模板查询）
+  - name: TaskExecution
+    description: 任务执行管理
+
+paths:
+  /data-collection/tasks:
+    get:
+      operationId: getTasks
+      tags: [CollectionTask]
+      summary: 获取归集任务列表
+      parameters:
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+        - name: size
+          in: query
+          schema:
+            type: integer
+            default: 20
+        - name: status
+          in: query
+          schema:
+            $ref: '#/components/schemas/TaskStatus'
+        - name: name
+          in: query
+          description: 任务名称关键字搜索
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 归集任务列表
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/PagedCollectionTaskSummary'
+
+    post:
+      operationId: createTask
+      tags: [CollectionTask]
+      summary: 创建归集任务
+      description: 创建新的数据归集任务
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreateCollectionTaskRequest'
+      responses:
+        '201':
+          description: 归集任务创建成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/CollectionTaskResponse'
+
+  /data-collection/tasks/{id}:
+    get:
+      operationId: getTaskDetail
+      tags: [CollectionTask]
+      summary: 获取归集任务详情
+      parameters:
+        - name: id
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 归集任务详情
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/CollectionTaskResponse'
+        '404':
+          description: 归集任务不存在
+
+    put:
+      operationId: updateTask
+      tags: [CollectionTask]
+      summary: 更新归集任务
+      parameters:
+        - name: id
+          in: path
+          required: true
+          schema:
+            type: string
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/UpdateCollectionTaskRequest'
+      responses:
+        '200':
+          description: 归集任务更新成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/CollectionTaskResponse'
+
+    delete:
+      operationId: deleteTask
+      tags: [CollectionTask]
+      summary: 删除归集任务
+      parameters:
+        - name: id
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '204':
+          description: 归集任务删除成功
+
+  /tasks/{id}/execute:
+    post:
+      tags: [TaskExecution]
+      summary: 执行归集任务
+      description: 立即执行指定的归集任务
+      parameters:
+        - name: id
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '201':
+          description: 任务执行已启动
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/TaskExecutionResponse'
+
+  /tasks/{id}/executions:
+    get:
+      tags: [TaskExecution]
+      summary: 获取任务执行记录
+      parameters:
+        - name: id
+          in: path
+          required: true
+          schema:
+            type: string
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+        - name: size
+          in: query
+          schema:
+            type: integer
+            default: 20
+      responses:
+        '200':
+          description: 任务执行记录列表
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/PagedTaskExecutions'
+
+  /executions/{id}:
+    get:
+      tags: [TaskExecution]
+      summary: 获取执行详情
+      parameters:
+        - name: id
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 执行详情
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/TaskExecutionDetail'
+
+    delete:
+      tags: [TaskExecution]
+      summary: 停止任务执行
+      parameters:
+        - name: id
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '204':
+          description: 任务执行已停止
+
+  /templates:
+    get:
+      tags: [CollectionTask]
+      summary: 获取DataX模板列表
+      description: 获取可用的DataX任务模板列表，用于创建任务时选择
+      parameters:
+        - name: sourceType
+          in: query
+          description: 源数据源类型过滤
+          schema:
+            type: string
+        - name: targetType
+          in: query
+          description: 目标数据源类型过滤
+          schema:
+            type: string
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+        - name: size
+          in: query
+          schema:
+            type: integer
+            default: 20
+      responses:
+        '200':
+          description: 归集模板列表
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/PagedDataxTemplates'
+
+components:
+  schemas:
+    TaskStatus:
+      type: string
+      enum:
+        - DRAFT
+        - READY
+        - RUNNING
+        - SUCCESS
+        - FAILED
+        - STOPPED
+      description: |
+        任务和执行状态枚举:
+        - DRAFT: 草稿状态
+        - READY: 就绪状态
+        - RUNNING: 运行中
+        - SUCCESS: 执行成功 (对应原来的COMPLETED/SUCCESS)
+        - FAILED: 执行失败
+        - STOPPED: 已停止
+
+    SyncMode:
+      type: string
+      enum: [ONCE, SCHEDULED]
+      description: 同步方式：一次性(ONCE) 或 定时(SCHEDULED)
+
+    CollectionTaskSummary:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        description:
+          type: string
+        status:
+          $ref: '#/components/schemas/TaskStatus'
+        syncMode:
+          $ref: '#/components/schemas/SyncMode'
+        lastExecutionId:
+          type: string
+          description: 最后执行ID
+        createdAt:
+          type: string
+          format: date-time
+        updatedAt:
+          type: string
+          format: date-time
+      description: 任务列表摘要信息（不包含详细配置与调度表达式）
+
+    CollectionTaskResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        description:
+          type: string
+        config:
+          type: object
+          additionalProperties: true
+          description: 归集配置，包含源端和目标端配置信息
+        status:
+          $ref: '#/components/schemas/TaskStatus'
+        syncMode:
+          $ref: '#/components/schemas/SyncMode'
+        scheduleExpression:
+          type: string
+          description: Cron调度表达式 (仅当 syncMode = SCHEDULED 时有效)
+        lastExecutionId:
+          type: string
+          description: 最后执行ID
+        createdAt:
+          type: string
+          format: date-time
+        updatedAt:
+          type: string
+          format: date-time
+
+    CreateCollectionTaskRequest:
+      type: object
+      required:
+        - name
+        - config
+        - syncMode
+      properties:
+        name:
+          type: string
+          description: 任务名称
+          minLength: 1
+          maxLength: 100
+        description:
+          type: string
+          description: 任务描述
+          maxLength: 500
+        config:
+          type: object
+          description: 归集配置，包含源端和目标端配置信息
+          additionalProperties: true
+        syncMode:
+          $ref: '#/components/schemas/SyncMode'
+        scheduleExpression:
+          type: string
+          description: Cron调度表达式 (syncMode=SCHEDULED 时必填)
+
+    UpdateCollectionTaskRequest:
+      type: object
+      properties:
+        name:
+          type: string
+          description: 任务名称
+          minLength: 1
+          maxLength: 100
+        description:
+          type: string
+          description: 任务描述
+          maxLength: 500
+        config:
+          type: object
+          description: 归集配置，包含源端和目标端配置信息
+          additionalProperties: true
+        syncMode:
+          $ref: '#/components/schemas/SyncMode'
+        scheduleExpression:
+          type: string
+          description: Cron调度表达式 (syncMode=SCHEDULED 时必填)
+
+    PagedCollectionTaskSummary:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/CollectionTaskSummary'
+        totalElements:
+          type: integer
+        totalPages:
+          type: integer
+        number:
+          type: integer
+        size:
+          type: integer
+
+    PagedCollectionTasks:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/CollectionTaskResponse'
+        totalElements:
+          type: integer
+        totalPages:
+          type: integer
+        number:
+          type: integer
+        size:
+          type: integer
+
+    TaskExecutionResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        taskId:
+          type: string
+        taskName:
+          type: string
+        status:
+          $ref: '#/components/schemas/TaskStatus'
+        startedAt:
+          type: string
+          format: date-time
+
+    TaskExecutionDetail:
+      type: object
+      properties:
+        id:
+          type: string
+        taskId:
+          type: string
+        taskName:
+          type: string
+        status:
+          $ref: '#/components/schemas/TaskStatus'
+        progress:
+          type: number
+          format: double
+          minimum: 0
+          maximum: 100
+        recordsTotal:
+          type: integer
+        recordsProcessed:
+          type: integer
+        recordsSuccess:
+          type: integer
+        recordsFailed:
+          type: integer
+        throughput:
+          type: number
+          format: double
+        dataSizeBytes:
+          type: integer
+        startedAt:
+          type: string
+          format: date-time
+        completedAt:
+          type: string
+          format: date-time
+        durationSeconds:
+          type: integer
+        errorMessage:
+          type: string
+
+    PagedTaskExecutions:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/TaskExecutionDetail'
+        totalElements:
+          type: integer
+        totalPages:
+          type: integer
+        number:
+          type: integer
+        size:
+          type: integer
+
+    DataxTemplateSummary:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        sourceType:
+          type: string
+          description: 源数据源类型
+        targetType:
+          type: string
+          description: 目标数据源类型
+        description:
+          type: string
+        version:
+          type: string
+        isSystem:
+          type: boolean
+          description: 是否为系统模板
+        createdAt:
+          type: string
+          format: date-time
+
+    PagedDataxTemplates:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/DataxTemplateSummary'
+        totalElements:
+          type: integer
+        totalPages:
+          type: integer
+        number:
+          type: integer
+        size:
+          type: integer

backend/openapi/specs/data-evaluation.yaml

@@ -0,0 +1,630 @@
+openapi: 3.0.3
+info:
+  title: Data Evaluation Service API
+  description: 数据评估服务API - 质量、适配性、价值评估
+  version: 1.0.0
+  contact:
+    name: Data Mate Platform Team
+
+servers:
+  - url: http://localhost:8086
+    description: Development server
+
+tags:
+  - name: quality-evaluation
+    description: 数据质量评估
+  - name: compatibility-evaluation
+    description: 适配性评估
+  - name: value-evaluation
+    description: 价值评估
+  - name: evaluation-reports
+    description: 评估报告
+
+paths:
+  /api/v1/evaluation/quality:
+    post:
+      tags:
+        - quality-evaluation
+      summary: 数据质量评估
+      description: 对数据集进行质量评估，包括完整性、准确性、一致性等
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/QualityEvaluationRequest'
+      responses:
+        '200':
+          description: 评估成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/QualityEvaluationResponse'
+
+  /api/v1/evaluation/quality/{evaluationId}:
+    get:
+      tags:
+        - quality-evaluation
+      summary: 获取质量评估结果
+      parameters:
+        - name: evaluationId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/QualityEvaluationDetailResponse'
+
+  /api/v1/evaluation/compatibility:
+    post:
+      tags:
+        - compatibility-evaluation
+      summary: 适配性评估
+      description: 评估数据集与目标模型或任务的适配性
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CompatibilityEvaluationRequest'
+      responses:
+        '200':
+          description: 评估成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/CompatibilityEvaluationResponse'
+
+  /api/v1/evaluation/value:
+    post:
+      tags:
+        - value-evaluation
+      summary: 价值评估
+      description: 评估数据集的商业价值和使用价值
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/ValueEvaluationRequest'
+      responses:
+        '200':
+          description: 评估成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ValueEvaluationResponse'
+
+  /api/v1/evaluation/reports:
+    get:
+      tags:
+        - evaluation-reports
+      summary: 获取评估报告列表
+      parameters:
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+        - name: size
+          in: query
+          schema:
+            type: integer
+            default: 20
+        - name: type
+          in: query
+          schema:
+            $ref: '#/components/schemas/EvaluationType'
+        - name: datasetId
+          in: query
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/EvaluationReportPageResponse'
+
+  /api/v1/evaluation/reports/{reportId}:
+    get:
+      tags:
+        - evaluation-reports
+      summary: 获取评估报告详情
+      parameters:
+        - name: reportId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/EvaluationReportDetailResponse'
+
+  /api/v1/evaluation/reports/{reportId}/export:
+    get:
+      tags:
+        - evaluation-reports
+      summary: 导出评估报告
+      parameters:
+        - name: reportId
+          in: path
+          required: true
+          schema:
+            type: string
+        - name: format
+          in: query
+          schema:
+            type: string
+            enum: [PDF, EXCEL, JSON]
+            default: PDF
+      responses:
+        '200':
+          description: 导出成功
+          content:
+            application/octet-stream:
+              schema:
+                type: string
+                format: binary
+
+  /api/v1/evaluation/batch:
+    post:
+      tags:
+        - evaluation-reports
+      summary: 批量评估
+      description: 对多个数据集进行批量评估
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/BatchEvaluationRequest'
+      responses:
+        '202':
+          description: 批量评估任务已提交
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/BatchEvaluationResponse'
+
+components:
+  schemas:
+    QualityEvaluationRequest:
+      type: object
+      required:
+        - datasetId
+        - metrics
+      properties:
+        datasetId:
+          type: string
+          description: 数据集ID
+        metrics:
+          type: array
+          items:
+            $ref: '#/components/schemas/QualityMetric'
+          description: 评估指标
+        sampleSize:
+          type: integer
+          description: 采样大小
+        parameters:
+          type: object
+          description: 评估参数
+
+    QualityEvaluationResponse:
+      type: object
+      properties:
+        evaluationId:
+          type: string
+        status:
+          $ref: '#/components/schemas/EvaluationStatus'
+        overallScore:
+          type: number
+          format: double
+          description: 总体质量分数
+        metrics:
+          type: array
+          items:
+            $ref: '#/components/schemas/QualityMetricResult'
+        recommendations:
+          type: array
+          items:
+            type: string
+        createdAt:
+          type: string
+          format: date-time
+
+    QualityEvaluationDetailResponse:
+      allOf:
+        - $ref: '#/components/schemas/QualityEvaluationResponse'
+        - type: object
+          properties:
+            detailedResults:
+              $ref: '#/components/schemas/DetailedQualityResults'
+            visualizations:
+              type: array
+              items:
+                $ref: '#/components/schemas/VisualizationData'
+
+    CompatibilityEvaluationRequest:
+      type: object
+      required:
+        - datasetId
+        - targetType
+      properties:
+        datasetId:
+          type: string
+        targetType:
+          $ref: '#/components/schemas/TargetType'
+        targetConfig:
+          type: object
+          description: 目标配置（模型、任务等）
+        evaluationCriteria:
+          type: array
+          items:
+            $ref: '#/components/schemas/CompatibilityCriterion'
+
+    CompatibilityEvaluationResponse:
+      type: object
+      properties:
+        evaluationId:
+          type: string
+        compatibilityScore:
+          type: number
+          format: double
+        results:
+          type: array
+          items:
+            $ref: '#/components/schemas/CompatibilityResult'
+        suggestions:
+          type: array
+          items:
+            type: string
+        createdAt:
+          type: string
+          format: date-time
+
+    ValueEvaluationRequest:
+      type: object
+      required:
+        - datasetId
+        - valueCriteria
+      properties:
+        datasetId:
+          type: string
+        valueCriteria:
+          type: array
+          items:
+            $ref: '#/components/schemas/ValueCriterion'
+        marketContext:
+          type: object
+          description: 市场环境信息
+        businessContext:
+          type: object
+          description: 业务环境信息
+
+    ValueEvaluationResponse:
+      type: object
+      properties:
+        evaluationId:
+          type: string
+        valueScore:
+          type: number
+          format: double
+        monetaryValue:
+          type: number
+          format: double
+          description: 货币价值估算
+        strategicValue:
+          type: number
+          format: double
+          description: 战略价值评分
+        results:
+          type: array
+          items:
+            $ref: '#/components/schemas/ValueResult'
+        insights:
+          type: array
+          items:
+            type: string
+
+    EvaluationReportResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        datasetId:
+          type: string
+        type:
+          $ref: '#/components/schemas/EvaluationType'
+        status:
+          $ref: '#/components/schemas/EvaluationStatus'
+        overallScore:
+          type: number
+          format: double
+        summary:
+          type: string
+        createdAt:
+          type: string
+          format: date-time
+        completedAt:
+          type: string
+          format: date-time
+
+    EvaluationReportPageResponse:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/EvaluationReportResponse'
+        totalElements:
+          type: integer
+          format: int64
+        totalPages:
+          type: integer
+        size:
+          type: integer
+        number:
+          type: integer
+
+    EvaluationReportDetailResponse:
+      allOf:
+        - $ref: '#/components/schemas/EvaluationReportResponse'
+        - type: object
+          properties:
+            qualityResults:
+              $ref: '#/components/schemas/QualityEvaluationResponse'
+            compatibilityResults:
+              $ref: '#/components/schemas/CompatibilityEvaluationResponse'
+            valueResults:
+              $ref: '#/components/schemas/ValueEvaluationResponse'
+            attachments:
+              type: array
+              items:
+                $ref: '#/components/schemas/ReportAttachment'
+
+    BatchEvaluationRequest:
+      type: object
+      required:
+        - datasetIds
+        - evaluationTypes
+      properties:
+        datasetIds:
+          type: array
+          items:
+            type: string
+        evaluationTypes:
+          type: array
+          items:
+            $ref: '#/components/schemas/EvaluationType'
+        parameters:
+          type: object
+
+    BatchEvaluationResponse:
+      type: object
+      properties:
+        batchId:
+          type: string
+        status:
+          type: string
+        totalTasks:
+          type: integer
+        submittedAt:
+          type: string
+          format: date-time
+
+    QualityMetric:
+      type: string
+      enum:
+        - COMPLETENESS
+        - ACCURACY
+        - CONSISTENCY
+        - VALIDITY
+        - UNIQUENESS
+        - TIMELINESS
+
+    QualityMetricResult:
+      type: object
+      properties:
+        metric:
+          $ref: '#/components/schemas/QualityMetric'
+        score:
+          type: number
+          format: double
+        details:
+          type: object
+        issues:
+          type: array
+          items:
+            $ref: '#/components/schemas/QualityIssue'
+
+    DetailedQualityResults:
+      type: object
+      properties:
+        fieldAnalysis:
+          type: array
+          items:
+            $ref: '#/components/schemas/FieldAnalysis'
+        distributionAnalysis:
+          $ref: '#/components/schemas/DistributionAnalysis'
+        correlationAnalysis:
+          $ref: '#/components/schemas/CorrelationAnalysis'
+
+    TargetType:
+      type: string
+      enum:
+        - LANGUAGE_MODEL
+        - CLASSIFICATION_MODEL
+        - RECOMMENDATION_SYSTEM
+        - CUSTOM_TASK
+
+    CompatibilityCriterion:
+      type: string
+      enum:
+        - FORMAT_COMPATIBILITY
+        - SCHEMA_COMPATIBILITY
+        - SIZE_ADEQUACY
+        - DISTRIBUTION_MATCH
+        - FEATURE_COVERAGE
+
+    CompatibilityResult:
+      type: object
+      properties:
+        criterion:
+          $ref: '#/components/schemas/CompatibilityCriterion'
+        score:
+          type: number
+          format: double
+        status:
+          type: string
+          enum: [PASS, WARN, FAIL]
+        details:
+          type: string
+
+    ValueCriterion:
+      type: string
+      enum:
+        - RARITY
+        - DEMAND
+        - QUALITY
+        - COMPLETENESS
+        - TIMELINESS
+        - STRATEGIC_IMPORTANCE
+
+    ValueResult:
+      type: object
+      properties:
+        criterion:
+          $ref: '#/components/schemas/ValueCriterion'
+        score:
+          type: number
+          format: double
+        impact:
+          type: string
+          enum: [LOW, MEDIUM, HIGH]
+        explanation:
+          type: string
+
+    EvaluationType:
+      type: string
+      enum:
+        - QUALITY
+        - COMPATIBILITY
+        - VALUE
+        - COMPREHENSIVE
+
+    EvaluationStatus:
+      type: string
+      enum:
+        - PENDING
+        - RUNNING
+        - COMPLETED
+        - FAILED
+
+    QualityIssue:
+      type: object
+      properties:
+        type:
+          type: string
+        severity:
+          type: string
+          enum: [LOW, MEDIUM, HIGH, CRITICAL]
+        description:
+          type: string
+        affectedRecords:
+          type: integer
+        suggestions:
+          type: array
+          items:
+            type: string
+
+    FieldAnalysis:
+      type: object
+      properties:
+        fieldName:
+          type: string
+        dataType:
+          type: string
+        nullCount:
+          type: integer
+        uniqueCount:
+          type: integer
+        statistics:
+          type: object
+
+    DistributionAnalysis:
+      type: object
+      properties:
+        distributions:
+          type: array
+          items:
+            type: object
+        outliers:
+          type: array
+          items:
+            type: object
+        patterns:
+          type: array
+          items:
+            type: string
+
+    CorrelationAnalysis:
+      type: object
+      properties:
+        correlationMatrix:
+          type: array
+          items:
+            type: array
+            items:
+              type: number
+        significantCorrelations:
+          type: array
+          items:
+            type: object
+
+    VisualizationData:
+      type: object
+      properties:
+        type:
+          type: string
+          enum: [CHART, GRAPH, HISTOGRAM, HEATMAP]
+        title:
+          type: string
+        data:
+          type: object
+        config:
+          type: object
+
+    ReportAttachment:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        type:
+          type: string
+        size:
+          type: integer
+          format: int64
+        downloadUrl:
+          type: string
+
+  securitySchemes:
+    BearerAuth:
+      type: http
+      scheme: bearer
+      bearerFormat: JWT
+
+security:
+  - BearerAuth: []

backend/openapi/specs/data-management.yaml

@@ -0,0 +1,719 @@
+openapi: 3.0.3
+info:
+  title: Data Management Service API
+  description: |
+    数据管理服务API，提供数据集的创建、管理和文件操作功能。
+
+    主要功能：
+    - 数据集的创建和管理
+    - 多种数据集类型支持（图像、文本、音频、视频、多模态等）
+    - 数据集文件管理
+    - 数据集标签和元数据管理
+    - 数据集统计信息
+  version: 1.0.0
+
+servers:
+  - url: http://localhost:8092/api/v1/data-management
+    description: Development server
+
+tags:
+  - name: Dataset
+    description: 数据集管理
+  - name: DatasetFile
+    description: 数据集文件管理
+  - name: DatasetType
+    description: 数据集类型管理
+  - name: Tag
+    description: 标签管理
+
+paths:
+  /data-management/datasets:
+    get:
+      tags: [Dataset]
+      operationId: getDatasets
+      summary: 获取数据集列表
+      description: 分页查询数据集列表，支持按类型、标签等条件筛选
+      parameters:
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+          description: 页码，从0开始
+        - name: size
+          in: query
+          schema:
+            type: integer
+            default: 20
+          description: 每页大小
+        - name: type
+          in: query
+          schema:
+            type: string
+          description: 数据集类型过滤
+        - name: tags
+          in: query
+          schema:
+            type: string
+          description: 标签过滤，多个标签用逗号分隔
+        - name: keyword
+          in: query
+          schema:
+            type: string
+          description: 关键词搜索（名称、描述）
+        - name: status
+          in: query
+          schema:
+            type: string
+            enum: [ACTIVE, INACTIVE, PROCESSING]
+          description: 数据集状态过滤
+      responses:
+        '200':
+          description: 成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/PagedDatasetResponse'
+        '400':
+          description: 请求参数错误
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ErrorResponse'
+
+    post:
+      tags: [Dataset]
+      operationId: createDataset
+      summary: 创建数据集
+      description: 创建新的数据集
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreateDatasetRequest'
+      responses:
+        '201':
+          description: 创建成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/DatasetResponse'
+        '400':
+          description: 请求参数错误
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ErrorResponse'
+
+  /data-management/datasets/{datasetId}:
+    get:
+      tags: [Dataset]
+      operationId: getDatasetById
+      summary: 获取数据集详情
+      description: 根据ID获取数据集详细信息
+      parameters:
+        - name: datasetId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 数据集ID
+      responses:
+        '200':
+          description: 成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/DatasetResponse'
+        '404':
+          description: 数据集不存在
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ErrorResponse'
+
+    put:
+      tags: [Dataset]
+      summary: 更新数据集
+      operationId: updateDataset
+      description: 更新数据集信息
+      parameters:
+        - name: datasetId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 数据集ID
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/UpdateDatasetRequest'
+      responses:
+        '200':
+          description: 更新成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/DatasetResponse'
+        '404':
+          description: 数据集不存在
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ErrorResponse'
+
+    delete:
+      tags: [Dataset]
+      operationId: deleteDataset
+      summary: 删除数据集
+      description: 删除指定的数据集
+      parameters:
+        - name: datasetId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 数据集ID
+      responses:
+        '204':
+          description: 删除成功
+        '404':
+          description: 数据集不存在
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ErrorResponse'
+
+  /data-management/datasets/{datasetId}/files:
+    get:
+      tags: [DatasetFile]
+      summary: 获取数据集文件列表
+      operationId: getDatasetFiles
+      description: 分页获取数据集中的文件列表
+      parameters:
+        - name: datasetId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 数据集ID
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+          description: 页码，从0开始
+        - name: size
+          in: query
+          schema:
+            type: integer
+            default: 20
+          description: 每页大小
+        - name: fileType
+          in: query
+          schema:
+            type: string
+          description: 文件类型过滤
+        - name: status
+          in: query
+          schema:
+            type: string
+            enum: [UPLOADED, PROCESSING, COMPLETED, ERROR]
+          description: 文件状态过滤
+      responses:
+        '200':
+          description: 成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/PagedDatasetFileResponse'
+
+    post:
+      tags: [DatasetFile]
+      summary: 上传文件到数据集
+      operationId: uploadDatasetFile
+      description: 向指定数据集上传文件
+      parameters:
+        - name: datasetId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 数据集ID
+      requestBody:
+        required: true
+        content:
+          multipart/form-data:
+            schema:
+              type: object
+              properties:
+                file:
+                  type: string
+                  format: binary
+                  description: 要上传的文件
+                description:
+                  type: string
+                  description: 文件描述
+      responses:
+        '201':
+          description: 上传成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/DatasetFileResponse'
+
+  /data-management/datasets/{datasetId}/files/{fileId}:
+    get:
+      tags: [DatasetFile]
+      summary: 获取文件详情
+      description: 获取数据集中指定文件的详细信息
+      operationId: getDatasetFileById
+      parameters:
+        - name: datasetId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 数据集ID
+        - name: fileId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 文件ID
+      responses:
+        '200':
+          description: 成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/DatasetFileResponse'
+
+    delete:
+      tags: [DatasetFile]
+      summary: 删除文件
+      operationId: deleteDatasetFile
+      description: 从数据集中删除指定文件
+      parameters:
+        - name: datasetId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 数据集ID
+        - name: fileId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 文件ID
+      responses:
+        '204':
+          description: 删除成功
+
+  /data-management/datasets/{datasetId}/files/{fileId}/download:
+    get:
+      tags: [DatasetFile]
+      operationId: downloadDatasetFile
+      summary: 下载文件
+      description: 下载数据集中的指定文件
+      parameters:
+        - name: datasetId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 数据集ID
+        - name: fileId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 文件ID
+      responses:
+        '200':
+          description: 文件内容
+          content:
+            application/octet-stream:
+              schema:
+                type: string
+                format: binary
+
+  /data-management/dataset-types:
+    get:
+      operationId: getDatasetTypes
+      tags: [DatasetType]
+      summary: 获取数据集类型列表
+      description: 获取所有支持的数据集类型
+      responses:
+        '200':
+          description: 成功
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  $ref: '#/components/schemas/DatasetTypeResponse'
+
+  /data-management/tags:
+    get:
+      tags: [Tag]
+      operationId: getTags
+      summary: 获取标签列表
+      description: 获取所有可用的标签
+      parameters:
+        - name: keyword
+          in: query
+          schema:
+            type: string
+          description: 标签名称关键词搜索
+      responses:
+        '200':
+          description: 成功
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  $ref: '#/components/schemas/TagResponse'
+
+    post:
+      tags: [Tag]
+      operationId: createTag
+      summary: 创建标签
+      description: 创建新的标签
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreateTagRequest'
+      responses:
+        '201':
+          description: 创建成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/TagResponse'
+
+  /data-management/datasets/{datasetId}/statistics:
+    get:
+      tags: [Dataset]
+      operationId: getDatasetStatistics
+      summary: 获取数据集统计信息
+      description: 获取数据集的统计信息（文件数量、大小、完成度等）
+      parameters:
+        - name: datasetId
+          in: path
+          required: true
+          schema:
+            type: string
+          description: 数据集ID
+      responses:
+        '200':
+          description: 成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/DatasetStatisticsResponse'
+
+components:
+  schemas:
+    PagedDatasetResponse:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/DatasetResponse'
+        page:
+          type: integer
+          description: 当前页码
+        size:
+          type: integer
+          description: 每页大小
+        totalElements:
+          type: integer
+          description: 总元素数
+        totalPages:
+          type: integer
+          description: 总页数
+        first:
+          type: boolean
+          description: 是否为第一页
+        last:
+          type: boolean
+          description: 是否为最后一页
+
+    DatasetResponse:
+      type: object
+      properties:
+        id:
+          type: string
+          description: 数据集ID
+        name:
+          type: string
+          description: 数据集名称
+        description:
+          type: string
+          description: 数据集描述
+        type:
+          $ref: '#/components/schemas/DatasetTypeResponse'
+        status:
+          type: string
+          enum: [ACTIVE, INACTIVE, PROCESSING]
+          description: 数据集状态
+        tags:
+          type: array
+          items:
+            $ref: '#/components/schemas/TagResponse'
+          description: 标签列表
+        dataSource:
+          type: string
+          description: 数据源
+        targetLocation:
+          type: string
+          description: 目标位置
+        fileCount:
+          type: integer
+          description: 文件数量
+        totalSize:
+          type: integer
+          format: int64
+          description: 总大小（字节）
+        completionRate:
+          type: number
+          format: float
+          description: 完成率（0-100）
+        createdAt:
+          type: string
+          format: date-time
+          description: 创建时间
+        updatedAt:
+          type: string
+          format: date-time
+          description: 更新时间
+        createdBy:
+          type: string
+          description: 创建者
+
+    CreateDatasetRequest:
+      type: object
+      required:
+        - name
+        - type
+      properties:
+        name:
+          type: string
+          description: 数据集名称
+          minLength: 1
+          maxLength: 100
+        description:
+          type: string
+          description: 数据集描述
+          maxLength: 500
+        type:
+          type: string
+          description: 数据集类型
+        tags:
+          type: array
+          items:
+            type: string
+          description: 标签列表
+        dataSource:
+          type: string
+          description: 数据源
+        targetLocation:
+          type: string
+          description: 目标位置
+
+    UpdateDatasetRequest:
+      type: object
+      properties:
+        name:
+          type: string
+          description: 数据集名称
+          maxLength: 100
+        description:
+          type: string
+          description: 数据集描述
+          maxLength: 500
+        tags:
+          type: array
+          items:
+            type: string
+          description: 标签列表
+        status:
+          type: string
+          enum: [ACTIVE, INACTIVE]
+          description: 数据集状态
+
+    DatasetTypeResponse:
+      type: object
+      properties:
+        code:
+          type: string
+          description: 类型编码
+        name:
+          type: string
+          description: 类型名称
+        description:
+          type: string
+          description: 类型描述
+        supportedFormats:
+          type: array
+          items:
+            type: string
+          description: 支持的文件格式
+        icon:
+          type: string
+          description: 图标
+
+    PagedDatasetFileResponse:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/DatasetFileResponse'
+        page:
+          type: integer
+          description: 当前页码
+        size:
+          type: integer
+          description: 每页大小
+        totalElements:
+          type: integer
+          description: 总元素数
+        totalPages:
+          type: integer
+          description: 总页数
+        first:
+          type: boolean
+          description: 是否为第一页
+        last:
+          type: boolean
+          description: 是否为最后一页
+
+    DatasetFileResponse:
+      type: object
+      properties:
+        id:
+          type: string
+          description: 文件ID
+        fileName:
+          type: string
+          description: 文件名
+        originalName:
+          type: string
+          description: 原始文件名
+        fileType:
+          type: string
+          description: 文件类型
+        fileSize:
+          type: integer
+          format: int64
+          description: 文件大小（字节）
+        status:
+          type: string
+          enum: [UPLOADED, PROCESSING, COMPLETED, ERROR]
+          description: 文件状态
+        description:
+          type: string
+          description: 文件描述
+        filePath:
+          type: string
+          description: 文件路径
+        uploadTime:
+          type: string
+          format: date-time
+          description: 上传时间
+        uploadedBy:
+          type: string
+          description: 上传者
+
+    TagResponse:
+      type: object
+      properties:
+        id:
+          type: string
+          description: 标签ID
+        name:
+          type: string
+          description: 标签名称
+        color:
+          type: string
+          description: 标签颜色
+        description:
+          type: string
+          description: 标签描述
+        usageCount:
+          type: integer
+          description: 使用次数
+
+    CreateTagRequest:
+      type: object
+      required:
+        - name
+      properties:
+        name:
+          type: string
+          description: 标签名称
+          minLength: 1
+          maxLength: 50
+        color:
+          type: string
+          description: 标签颜色
+          pattern: '^#[0-9A-Fa-f]{6}$'
+        description:
+          type: string
+          description: 标签描述
+          maxLength: 200
+
+    DatasetStatisticsResponse:
+      type: object
+      properties:
+        totalFiles:
+          type: integer
+          description: 总文件数
+        completedFiles:
+          type: integer
+          description: 已完成文件数
+        totalSize:
+          type: integer
+          format: int64
+          description: 总大小（字节）
+        completionRate:
+          type: number
+          format: float
+          description: 完成率（0-100）
+        fileTypeDistribution:
+          type: object
+          additionalProperties:
+            type: integer
+          description: 文件类型分布
+        statusDistribution:
+          type: object
+          additionalProperties:
+            type: integer
+          description: 状态分布
+
+    ErrorResponse:
+      type: object
+      properties:
+        error:
+          type: string
+          description: 错误代码
+        message:
+          type: string
+          description: 错误消息
+        timestamp:
+          type: string
+          format: date-time
+          description: 错误时间
+        path:
+          type: string
+          description: 请求路径

backend/openapi/specs/data-synthesis.yaml

@@ -0,0 +1,620 @@
+openapi: 3.0.3
+info:
+  title: Data Synthesis Service API
+  description: 数据合成服务API - 指令、COT蒸馏、多模态合成
+  version: 1.0.0
+  contact:
+    name: Data Mate Platform Team
+
+servers:
+  - url: http://localhost:8085
+    description: Development server
+
+tags:
+  - name: synthesis-templates
+    description: 合成模板管理
+  - name: synthesis-jobs
+    description: 合成任务管理
+  - name: instruction-tuning
+    description: 指令调优
+  - name: cot-distillation
+    description: COT蒸馏
+
+paths:
+  /api/v1/synthesis/templates:
+    get:
+      tags:
+        - synthesis-templates
+      summary: 获取合成模板列表
+      parameters:
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+        - name: size
+          in: query
+          schema:
+            type: integer
+            default: 20
+        - name: type
+          in: query
+          schema:
+            $ref: '#/components/schemas/SynthesisType'
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/SynthesisTemplatePageResponse'
+
+    post:
+      tags:
+        - synthesis-templates
+      summary: 创建合成模板
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreateSynthesisTemplateRequest'
+      responses:
+        '201':
+          description: 创建成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/SynthesisTemplateResponse'
+
+  /api/v1/synthesis/templates/{templateId}:
+    get:
+      tags:
+        - synthesis-templates
+      summary: 获取合成模板详情
+      parameters:
+        - name: templateId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/SynthesisTemplateDetailResponse'
+
+    put:
+      tags:
+        - synthesis-templates
+      summary: 更新合成模板
+      parameters:
+        - name: templateId
+          in: path
+          required: true
+          schema:
+            type: string
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/UpdateSynthesisTemplateRequest'
+      responses:
+        '200':
+          description: 更新成功
+
+  /api/v1/synthesis/jobs:
+    get:
+      tags:
+        - synthesis-jobs
+      summary: 获取合成任务列表
+      parameters:
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+        - name: size
+          in: query
+          schema:
+            type: integer
+            default: 20
+        - name: status
+          in: query
+          schema:
+            $ref: '#/components/schemas/JobStatus'
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/SynthesisJobPageResponse'
+
+    post:
+      tags:
+        - synthesis-jobs
+      summary: 创建合成任务
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreateSynthesisJobRequest'
+      responses:
+        '201':
+          description: 任务创建成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/SynthesisJobResponse'
+
+  /api/v1/synthesis/jobs/{jobId}:
+    get:
+      tags:
+        - synthesis-jobs
+      summary: 获取合成任务详情
+      parameters:
+        - name: jobId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/SynthesisJobDetailResponse'
+
+  /api/v1/synthesis/jobs/{jobId}/execute:
+    post:
+      tags:
+        - synthesis-jobs
+      summary: 执行合成任务
+      parameters:
+        - name: jobId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 任务开始执行
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/JobExecutionResponse'
+
+  /api/v1/synthesis/instruction-tuning:
+    post:
+      tags:
+        - instruction-tuning
+      summary: 指令调优数据合成
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/InstructionTuningRequest'
+      responses:
+        '200':
+          description: 合成成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/InstructionTuningResponse'
+
+  /api/v1/synthesis/cot-distillation:
+    post:
+      tags:
+        - cot-distillation
+      summary: COT蒸馏数据合成
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/COTDistillationRequest'
+      responses:
+        '200':
+          description: 蒸馏成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/COTDistillationResponse'
+
+components:
+  schemas:
+    SynthesisTemplateResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        description:
+          type: string
+        type:
+          $ref: '#/components/schemas/SynthesisType'
+        category:
+          type: string
+        modelConfig:
+          $ref: '#/components/schemas/ModelConfig'
+        enabled:
+          type: boolean
+        createdAt:
+          type: string
+          format: date-time
+
+    SynthesisTemplateDetailResponse:
+      allOf:
+        - $ref: '#/components/schemas/SynthesisTemplateResponse'
+        - type: object
+          properties:
+            promptTemplate:
+              type: string
+            parameters:
+              type: object
+            examples:
+              type: array
+              items:
+                $ref: '#/components/schemas/SynthesisExample'
+
+    SynthesisTemplatePageResponse:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/SynthesisTemplateResponse'
+        totalElements:
+          type: integer
+          format: int64
+        totalPages:
+          type: integer
+        size:
+          type: integer
+        number:
+          type: integer
+
+    CreateSynthesisTemplateRequest:
+      type: object
+      required:
+        - name
+        - type
+        - promptTemplate
+      properties:
+        name:
+          type: string
+        description:
+          type: string
+        type:
+          $ref: '#/components/schemas/SynthesisType'
+        category:
+          type: string
+        promptTemplate:
+          type: string
+        modelConfig:
+          $ref: '#/components/schemas/ModelConfig'
+        parameters:
+          type: object
+
+    UpdateSynthesisTemplateRequest:
+      type: object
+      properties:
+        name:
+          type: string
+        description:
+          type: string
+        promptTemplate:
+          type: string
+        enabled:
+          type: boolean
+        parameters:
+          type: object
+
+    SynthesisJobResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        description:
+          type: string
+        templateId:
+          type: string
+        status:
+          $ref: '#/components/schemas/JobStatus'
+        progress:
+          type: number
+          format: double
+        targetCount:
+          type: integer
+        generatedCount:
+          type: integer
+        startTime:
+          type: string
+          format: date-time
+        endTime:
+          type: string
+          format: date-time
+        createdAt:
+          type: string
+          format: date-time
+
+    SynthesisJobDetailResponse:
+      allOf:
+        - $ref: '#/components/schemas/SynthesisJobResponse'
+        - type: object
+          properties:
+            template:
+              $ref: '#/components/schemas/SynthesisTemplateResponse'
+            statistics:
+              $ref: '#/components/schemas/SynthesisStatistics'
+            samples:
+              type: array
+              items:
+                $ref: '#/components/schemas/GeneratedSample'
+
+    SynthesisJobPageResponse:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/SynthesisJobResponse'
+        totalElements:
+          type: integer
+          format: int64
+        totalPages:
+          type: integer
+        size:
+          type: integer
+        number:
+          type: integer
+
+    CreateSynthesisJobRequest:
+      type: object
+      required:
+        - name
+        - templateId
+        - targetCount
+      properties:
+        name:
+          type: string
+        description:
+          type: string
+        templateId:
+          type: string
+        targetCount:
+          type: integer
+        parameters:
+          type: object
+        seedData:
+          type: array
+          items:
+            type: object
+
+    JobExecutionResponse:
+      type: object
+      properties:
+        executionId:
+          type: string
+        status:
+          type: string
+        message:
+          type: string
+
+    InstructionTuningRequest:
+      type: object
+      required:
+        - baseInstructions
+        - targetDomain
+        - count
+      properties:
+        baseInstructions:
+          type: array
+          items:
+            type: string
+        targetDomain:
+          type: string
+        count:
+          type: integer
+        modelConfig:
+          $ref: '#/components/schemas/ModelConfig'
+        parameters:
+          type: object
+
+    InstructionTuningResponse:
+      type: object
+      properties:
+        jobId:
+          type: string
+        generatedInstructions:
+          type: array
+          items:
+            $ref: '#/components/schemas/GeneratedInstruction'
+        statistics:
+          $ref: '#/components/schemas/GenerationStatistics'
+
+    COTDistillationRequest:
+      type: object
+      required:
+        - sourceModel
+        - targetFormat
+        - examples
+      properties:
+        sourceModel:
+          type: string
+        targetFormat:
+          type: string
+          enum: [QA, INSTRUCTION, REASONING]
+        examples:
+          type: array
+          items:
+            $ref: '#/components/schemas/COTExample'
+        parameters:
+          type: object
+
+    COTDistillationResponse:
+      type: object
+      properties:
+        jobId:
+          type: string
+        distilledData:
+          type: array
+          items:
+            $ref: '#/components/schemas/DistilledCOTData'
+        statistics:
+          $ref: '#/components/schemas/DistillationStatistics'
+
+    SynthesisType:
+      type: string
+      enum:
+        - INSTRUCTION_TUNING
+        - COT_DISTILLATION
+        - DIALOGUE_GENERATION
+        - TEXT_AUGMENTATION
+        - MULTIMODAL_SYNTHESIS
+        - CUSTOM
+
+    JobStatus:
+      type: string
+      enum:
+        - PENDING
+        - RUNNING
+        - COMPLETED
+        - FAILED
+        - CANCELLED
+
+    ModelConfig:
+      type: object
+      properties:
+        modelName:
+          type: string
+        temperature:
+          type: number
+          format: double
+        maxTokens:
+          type: integer
+        topP:
+          type: number
+          format: double
+        frequencyPenalty:
+          type: number
+          format: double
+
+    SynthesisExample:
+      type: object
+      properties:
+        input:
+          type: string
+        output:
+          type: string
+        explanation:
+          type: string
+
+    SynthesisStatistics:
+      type: object
+      properties:
+        totalGenerated:
+          type: integer
+        successfulGenerated:
+          type: integer
+        failedGenerated:
+          type: integer
+        averageLength:
+          type: number
+          format: double
+        uniqueCount:
+          type: integer
+
+    GeneratedSample:
+      type: object
+      properties:
+        id:
+          type: string
+        content:
+          type: string
+        score:
+          type: number
+          format: double
+        metadata:
+          type: object
+        createdAt:
+          type: string
+          format: date-time
+
+    GeneratedInstruction:
+      type: object
+      properties:
+        instruction:
+          type: string
+        input:
+          type: string
+        output:
+          type: string
+        quality:
+          type: number
+          format: double
+
+    GenerationStatistics:
+      type: object
+      properties:
+        totalGenerated:
+          type: integer
+        averageQuality:
+          type: number
+          format: double
+        diversityScore:
+          type: number
+          format: double
+
+    COTExample:
+      type: object
+      properties:
+        question:
+          type: string
+        reasoning:
+          type: string
+        answer:
+          type: string
+
+    DistilledCOTData:
+      type: object
+      properties:
+        question:
+          type: string
+        reasoning:
+          type: string
+        answer:
+          type: string
+        confidence:
+          type: number
+          format: double
+
+    DistillationStatistics:
+      type: object
+      properties:
+        totalProcessed:
+          type: integer
+        successfulDistilled:
+          type: integer
+        averageConfidence:
+          type: number
+          format: double
+
+  securitySchemes:
+    BearerAuth:
+      type: http
+      scheme: bearer
+      bearerFormat: JWT
+
+security:
+  - BearerAuth: []

backend/openapi/specs/execution-engine.yaml

@@ -0,0 +1,712 @@
+openapi: 3.0.3
+info:
+  title: Execution Engine Service API
+  description: 执行引擎服务API - 与Ray/DataX/Python执行器对接
+  version: 1.0.0
+  contact:
+    name: Data Mate Platform Team
+
+servers:
+  - url: http://localhost:8088
+    description: Development server
+
+tags:
+  - name: jobs
+    description: 作业管理
+  - name: executors
+    description: 执行器管理
+  - name: resources
+    description: 资源管理
+  - name: monitoring
+    description: 监控管理
+
+paths:
+  /api/v1/jobs:
+    get:
+      tags:
+        - jobs
+      summary: 获取作业列表
+      parameters:
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+        - name: size
+          in: query
+          schema:
+            type: integer
+            default: 20
+        - name: status
+          in: query
+          schema:
+            $ref: '#/components/schemas/JobStatus'
+        - name: executor
+          in: query
+          schema:
+            $ref: '#/components/schemas/ExecutorType'
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/JobPageResponse'
+
+    post:
+      tags:
+        - jobs
+      summary: 提交作业
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/SubmitJobRequest'
+      responses:
+        '201':
+          description: 作业提交成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/JobResponse'
+
+  /api/v1/jobs/{jobId}:
+    get:
+      tags:
+        - jobs
+      summary: 获取作业详情
+      parameters:
+        - name: jobId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/JobDetailResponse'
+
+    delete:
+      tags:
+        - jobs
+      summary: 取消作业
+      parameters:
+        - name: jobId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 取消成功
+
+  /api/v1/jobs/{jobId}/logs:
+    get:
+      tags:
+        - jobs
+      summary: 获取作业日志
+      parameters:
+        - name: jobId
+          in: path
+          required: true
+          schema:
+            type: string
+        - name: follow
+          in: query
+          description: 是否实时跟踪日志
+          schema:
+            type: boolean
+            default: false
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  $ref: '#/components/schemas/JobLog'
+
+  /api/v1/jobs/{jobId}/retry:
+    post:
+      tags:
+        - jobs
+      summary: 重试作业
+      parameters:
+        - name: jobId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 重试成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/JobResponse'
+
+  /api/v1/executors:
+    get:
+      tags:
+        - executors
+      summary: 获取执行器列表
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  $ref: '#/components/schemas/ExecutorResponse'
+
+    post:
+      tags:
+        - executors
+      summary: 注册执行器
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/RegisterExecutorRequest'
+      responses:
+        '201':
+          description: 注册成功
+
+  /api/v1/executors/{executorId}:
+    get:
+      tags:
+        - executors
+      summary: 获取执行器详情
+      parameters:
+        - name: executorId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ExecutorDetailResponse'
+
+    put:
+      tags:
+        - executors
+      summary: 更新执行器
+      parameters:
+        - name: executorId
+          in: path
+          required: true
+          schema:
+            type: string
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/UpdateExecutorRequest'
+      responses:
+        '200':
+          description: 更新成功
+
+  /api/v1/resources/clusters:
+    get:
+      tags:
+        - resources
+      summary: 获取集群信息
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  $ref: '#/components/schemas/ClusterInfo'
+
+  /api/v1/resources/nodes:
+    get:
+      tags:
+        - resources
+      summary: 获取节点信息
+      parameters:
+        - name: clusterId
+          in: query
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  $ref: '#/components/schemas/NodeInfo'
+
+  /api/v1/monitoring/metrics:
+    get:
+      tags:
+        - monitoring
+      summary: 获取监控指标
+      parameters:
+        - name: metric
+          in: query
+          schema:
+            type: string
+        - name: start
+          in: query
+          schema:
+            type: string
+            format: date-time
+        - name: end
+          in: query
+          schema:
+            type: string
+            format: date-time
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/MetricsResponse'
+
+components:
+  schemas:
+    JobResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        status:
+          $ref: '#/components/schemas/JobStatus'
+        executorType:
+          $ref: '#/components/schemas/ExecutorType'
+        priority:
+          type: integer
+        progress:
+          type: number
+          format: double
+        submittedAt:
+          type: string
+          format: date-time
+        startedAt:
+          type: string
+          format: date-time
+        completedAt:
+          type: string
+          format: date-time
+        submittedBy:
+          type: string
+
+    JobDetailResponse:
+      allOf:
+        - $ref: '#/components/schemas/JobResponse'
+        - type: object
+          properties:
+            configuration:
+              $ref: '#/components/schemas/JobConfiguration'
+            resources:
+              $ref: '#/components/schemas/ResourceRequirement'
+            metrics:
+              $ref: '#/components/schemas/JobMetrics'
+            artifacts:
+              type: array
+              items:
+                $ref: '#/components/schemas/JobArtifact'
+            dependencies:
+              type: array
+              items:
+                type: string
+
+    JobPageResponse:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/JobResponse'
+        totalElements:
+          type: integer
+          format: int64
+        totalPages:
+          type: integer
+        size:
+          type: integer
+        number:
+          type: integer
+
+    SubmitJobRequest:
+      type: object
+      required:
+        - name
+        - executorType
+        - configuration
+      properties:
+        name:
+          type: string
+        description:
+          type: string
+        executorType:
+          $ref: '#/components/schemas/ExecutorType'
+        priority:
+          type: integer
+          minimum: 1
+          maximum: 10
+          default: 5
+        configuration:
+          $ref: '#/components/schemas/JobConfiguration'
+        resources:
+          $ref: '#/components/schemas/ResourceRequirement'
+        dependencies:
+          type: array
+          items:
+            type: string
+        timeoutSeconds:
+          type: integer
+
+    JobConfiguration:
+      type: object
+      properties:
+        script:
+          type: string
+          description: 执行脚本或代码
+        arguments:
+          type: array
+          items:
+            type: string
+          description: 执行参数
+        environment:
+          type: object
+          description: 环境变量
+        files:
+          type: array
+          items:
+            $ref: '#/components/schemas/FileReference'
+        packages:
+          type: array
+          items:
+            type: string
+          description: 依赖包列表
+
+    ResourceRequirement:
+      type: object
+      properties:
+        cpuCores:
+          type: number
+          format: double
+        memoryGB:
+          type: number
+          format: double
+        gpuCount:
+          type: integer
+        diskGB:
+          type: number
+          format: double
+        nodeSelector:
+          type: object
+          description: 节点选择器
+
+    ExecutorResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        type:
+          $ref: '#/components/schemas/ExecutorType'
+        status:
+          $ref: '#/components/schemas/ExecutorStatus'
+        version:
+          type: string
+        capabilities:
+          type: array
+          items:
+            type: string
+        registeredAt:
+          type: string
+          format: date-time
+        lastHeartbeat:
+          type: string
+          format: date-time
+
+    ExecutorDetailResponse:
+      allOf:
+        - $ref: '#/components/schemas/ExecutorResponse'
+        - type: object
+          properties:
+            configuration:
+              type: object
+            resources:
+              $ref: '#/components/schemas/ExecutorResources'
+            currentJobs:
+              type: array
+              items:
+                $ref: '#/components/schemas/JobResponse'
+            statistics:
+              $ref: '#/components/schemas/ExecutorStatistics'
+
+    RegisterExecutorRequest:
+      type: object
+      required:
+        - name
+        - type
+        - endpoint
+      properties:
+        name:
+          type: string
+        type:
+          $ref: '#/components/schemas/ExecutorType'
+        endpoint:
+          type: string
+        capabilities:
+          type: array
+          items:
+            type: string
+        configuration:
+          type: object
+
+    UpdateExecutorRequest:
+      type: object
+      properties:
+        status:
+          $ref: '#/components/schemas/ExecutorStatus'
+        configuration:
+          type: object
+
+    ClusterInfo:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        type:
+          type: string
+          enum: [RAY, KUBERNETES, YARN, STANDALONE]
+        status:
+          type: string
+          enum: [ACTIVE, INACTIVE, ERROR]
+        nodeCount:
+          type: integer
+        totalCpuCores:
+          type: integer
+        totalMemoryGB:
+          type: number
+          format: double
+        totalGpuCount:
+          type: integer
+        availableResources:
+          $ref: '#/components/schemas/ResourceInfo'
+
+    NodeInfo:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        clusterId:
+          type: string
+        status:
+          type: string
+          enum: [ACTIVE, INACTIVE, BUSY, ERROR]
+        resources:
+          $ref: '#/components/schemas/ResourceInfo'
+        usage:
+          $ref: '#/components/schemas/ResourceUsage'
+        lastUpdate:
+          type: string
+          format: date-time
+
+    MetricsResponse:
+      type: object
+      properties:
+        metric:
+          type: string
+        dataPoints:
+          type: array
+          items:
+            $ref: '#/components/schemas/MetricDataPoint'
+        aggregation:
+          type: object
+
+    JobLog:
+      type: object
+      properties:
+        timestamp:
+          type: string
+          format: date-time
+        level:
+          type: string
+          enum: [DEBUG, INFO, WARN, ERROR]
+        source:
+          type: string
+        message:
+          type: string
+
+    JobMetrics:
+      type: object
+      properties:
+        cpuUsage:
+          type: number
+          format: double
+        memoryUsage:
+          type: number
+          format: double
+        diskUsage:
+          type: number
+          format: double
+        networkIO:
+          type: object
+        duration:
+          type: integer
+          format: int64
+
+    JobArtifact:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        type:
+          type: string
+          enum: [LOG, OUTPUT, CHECKPOINT, MODEL]
+        size:
+          type: integer
+          format: int64
+        path:
+          type: string
+        createdAt:
+          type: string
+          format: date-time
+
+    FileReference:
+      type: object
+      properties:
+        name:
+          type: string
+        path:
+          type: string
+        type:
+          type: string
+          enum: [LOCAL, HDFS, S3, HTTP]
+
+    ExecutorResources:
+      type: object
+      properties:
+        total:
+          $ref: '#/components/schemas/ResourceInfo'
+        available:
+          $ref: '#/components/schemas/ResourceInfo'
+        allocated:
+          $ref: '#/components/schemas/ResourceInfo'
+
+    ExecutorStatistics:
+      type: object
+      properties:
+        totalJobs:
+          type: integer
+        successfulJobs:
+          type: integer
+        failedJobs:
+          type: integer
+        averageExecutionTime:
+          type: number
+          format: double
+        uptime:
+          type: integer
+          format: int64
+
+    ResourceInfo:
+      type: object
+      properties:
+        cpuCores:
+          type: number
+          format: double
+        memoryGB:
+          type: number
+          format: double
+        gpuCount:
+          type: integer
+        diskGB:
+          type: number
+          format: double
+
+    ResourceUsage:
+      type: object
+      properties:
+        cpuUsagePercent:
+          type: number
+          format: double
+        memoryUsagePercent:
+          type: number
+          format: double
+        diskUsagePercent:
+          type: number
+          format: double
+
+    MetricDataPoint:
+      type: object
+      properties:
+        timestamp:
+          type: string
+          format: date-time
+        value:
+          type: number
+          format: double
+        tags:
+          type: object
+
+    JobStatus:
+      type: string
+      enum:
+        - SUBMITTED
+        - PENDING
+        - RUNNING
+        - COMPLETED
+        - FAILED
+        - CANCELLED
+        - TIMEOUT
+
+    ExecutorType:
+      type: string
+      enum:
+        - RAY
+        - DATAX
+        - PYTHON
+        - SPARK
+        - FLINK
+        - CUSTOM
+
+    ExecutorStatus:
+      type: string
+      enum:
+        - ACTIVE
+        - INACTIVE
+        - BUSY
+        - ERROR
+        - MAINTENANCE
+
+  securitySchemes:
+    BearerAuth:
+      type: http
+      scheme: bearer
+      bearerFormat: JWT
+
+security:
+  - BearerAuth: []

backend/openapi/specs/operator-market.yaml

@@ -0,0 +1,547 @@
+openapi: 3.0.1
+info:
+  title: Operator Market Service API
+  description: |
+    算子市场服务API，提供算子的发布、管理和订阅功能。
+
+    主要功能：
+    - 算子发布和管理
+    - 算子版本控制
+    - 算子评分和评论
+    - 算子分类和标签
+    - 算子下载和安装
+  version: 1.0.0
+tags:
+  - name: Operator
+  - name: Category
+  - name: Label
+paths:
+  /operators/list:
+    post:
+      summary: 获取算子列表
+      deprecated: false
+      description: 分页查询算子列表，支持按分类、标签等条件筛选
+      tags:
+        - Operator
+      parameters: []
+      requestBody:
+        content:
+          application/json:
+            schema:
+              type: object
+              properties:
+                page:
+                  type: integer
+                  description: 页数
+                size:
+                  type: integer
+                  description: 单页数量
+                categories:
+                  type: array
+                  items:
+                    type: integer
+                  description: 分类id列表
+                operatorName:
+                  type: string
+                  description: 算子名称
+                labelName:
+                  type: string
+                  description: 标签名称
+                isStar:
+                  type: boolean
+                  description: 是否收藏
+              required:
+                - page
+                - size
+                - categories
+            examples: {}
+      responses:
+        '200':
+          description: 成功返回算子列表
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  $ref: '#/components/schemas/OperatorResponse'
+          headers: {}
+      security: []
+  /operators/create:
+    post:
+      summary: 创建新算子
+      deprecated: false
+      description: 创建并发布一个新的算子
+      tags:
+        - Operator
+      parameters: []
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreateOperatorRequest'
+            example: null
+      responses:
+        '201':
+          description: 算子创建成功
+          content:
+            application/json:
+              schema: &ref_0
+                $ref: '#/components/schemas/OperatorResponse'
+          headers: {}
+      security: []
+  /operators/upload:
+    post:
+      summary: 上传新算子
+      deprecated: false
+      description: 创建并发布一个新的算子
+      tags:
+        - Operator
+      parameters: []
+      requestBody:
+        content:
+          multipart/form-data:
+            schema:
+              type: object
+              properties:
+                file:
+                  type: string
+                  format: binary
+                  example: ''
+                description:
+                  type: string
+                  example: ''
+            examples: {}
+      responses:
+        '201':
+          description: 算子创建成功
+          content:
+            application/json:
+              schema: *ref_0
+          headers: {}
+      security: []
+  /operators/{id}:
+    get:
+      summary: 获取算子详情
+      deprecated: false
+      description: 根据ID获取算子的详细信息
+      tags:
+        - Operator
+      parameters:
+        - name: id
+          in: path
+          description: 算子ID
+          required: true
+          example: ''
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 成功返回算子详情
+          content:
+            application/json:
+              schema: *ref_0
+          headers: {}
+        '404':
+          description: 算子不存在
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ErrorResponse'
+          headers: {}
+      security: []
+    put:
+      summary: 更新算子信息
+      deprecated: false
+      description: 根据ID更新算子信息
+      tags:
+        - Operator
+      parameters:
+        - name: id
+          in: path
+          description: 算子ID
+          required: true
+          example: ''
+          schema:
+            type: string
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/UpdateOperatorRequest'
+            example: null
+      responses:
+        '200':
+          description: 算子更新成功
+          content:
+            application/json:
+              schema: *ref_0
+          headers: {}
+      security: []
+  /category:
+    post:
+      summary: 创建算子分类
+      deprecated: false
+      description: ''
+      tags:
+        - Category
+      parameters: []
+      requestBody:
+        content:
+          application/json:
+            schema:
+              type: object
+              properties:
+                name:
+                  type: string
+                  description: 名称
+                parentId:
+                  type: integer
+                  description: 父分类id
+              required:
+                - name
+                - parentId
+      responses:
+        '201':
+          description: ''
+          headers: {}
+      security: []
+    delete:
+      summary: 删除算子分类
+      deprecated: false
+      description: ''
+      tags:
+        - Category
+      parameters: []
+      requestBody:
+        content:
+          application/json:
+            schema:
+              type: object
+              properties:
+                id:
+                  type: integer
+                  description: ID 编号
+              required:
+                - id
+      responses:
+        '204':
+          description: ''
+          headers: {}
+      security: []
+  /categories/tree:
+    get:
+      summary: 获取算子分类列表
+      deprecated: false
+      description: 获取所有可用的算子分类
+      tags:
+        - Category
+      parameters: []
+      responses:
+        '200':
+          description: 成功返回分类列表
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  type: object
+                  properties:
+                    id:
+                      type: integer
+                    name:
+                      type: string
+                    count:
+                      type: integer
+                    categories:
+                      $ref: '#/components/schemas/CategoryResponse'
+                  required:
+                    - id
+                    - name
+                    - count
+                    - categories
+          headers: {}
+      security: []
+  /labels:
+    get:
+      summary: 获取算子标签列表
+      deprecated: false
+      description: 获取所有算子的标签
+      tags:
+        - Label
+      parameters:
+        - name: page
+          in: query
+          description: 页码，从0开始
+          required: false
+          schema:
+            type: integer
+            default: 0
+        - name: size
+          in: query
+          description: 每页大小
+          required: false
+          schema:
+            type: integer
+            default: 20
+        - name: keyword
+          in: query
+          description: 关键词搜索
+          required: false
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 成功返回标签列表
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  $ref: '#/components/schemas/LabelResponse'
+          headers: {}
+      security: []
+    post:
+      summary: 创建标签
+      deprecated: false
+      description: 批量创建标签
+      tags:
+        - Label
+      parameters: []
+      requestBody:
+        content:
+          application/json:
+            schema:
+              type: object
+              properties:
+                name:
+                  type: string
+                  description: 名称
+              required:
+                - name
+            example: veniam
+      responses:
+        '201':
+          description: 创建成功
+          headers: {}
+      security: []
+    delete:
+      summary: 删除标签
+      deprecated: false
+      description: 批量删除标签
+      tags:
+        - Label
+      parameters: []
+      requestBody:
+        content:
+          application/json:
+            schema:
+              type: array
+              items:
+                type: integer
+                format: int64
+              description: 标签id列表
+            example: null
+      responses:
+        '204':
+          description: 删除成功
+          headers: {}
+      security: []
+  /labels/{id}:
+    put:
+      summary: 更新标签
+      deprecated: false
+      description: 更新标签
+      tags:
+        - Label
+      parameters:
+        - name: id
+          in: path
+          description: 标签ID
+          required: true
+          example: ''
+          schema:
+            type: string
+      requestBody:
+        content:
+          application/json:
+            schema:
+              type: array
+              items:
+                $ref: '#/components/schemas/UpdateLabelRequest'
+            example: null
+      responses:
+        '200':
+          description: 更新成功
+          headers: {}
+      security: []
+components:
+  schemas:
+    UpdateLabelRequest:
+      type: object
+      required:
+        - id
+        - name
+      properties:
+        id:
+          type: integer
+          description: 标签id
+        name:
+          type: string
+          description: 标签名称
+    Response:
+      type: object
+      properties:
+        code:
+          type: string
+        message:
+          type: string
+        data:
+          type: object
+          properties: {}
+      required:
+        - code
+        - message
+        - data
+    LabelResponse:
+      type: object
+      properties:
+        id:
+          type: string
+          description: 标签ID
+        name:
+          type: string
+          description: 标签名称
+    SubCategory:
+      type: object
+      properties:
+        id:
+          type: integer
+          description: 分类id
+        name:
+          type: string
+          description: 分类名称
+        count:
+          type: integer
+        type:
+          type: string
+          description: 分类类型（0：预置，1：自定义）
+        parentId:
+          type: integer
+          description: 父分类id
+      required:
+        - id
+        - name
+        - type
+        - parentId
+        - count
+    CategoryResponse:
+      type: array
+      items:
+        $ref: '#/components/schemas/SubCategory'
+    UpdateOperatorRequest:
+      type: object
+      properties:
+        name:
+          type: string
+          description: 算子名称
+        description:
+          type: string
+          description: 算子描述
+        version:
+          type: string
+          description: 算子版本
+        category:
+          type: string
+          description: 算子分类
+        documentation:
+          type: string
+          description: 文档内容
+    ErrorResponse:
+      type: object
+      properties:
+        error:
+          type: string
+          description: 错误代码
+        message:
+          type: string
+          description: 错误信息
+        timestamp:
+          type: string
+          format: date-time
+          description: 错误时间
+    OperatorResponse:
+      type: object
+      properties:
+        id:
+          type: string
+          description: 算子ID
+        name:
+          type: string
+          description: 算子名称
+        description:
+          type: string
+          description: 算子描述
+        version:
+          type: string
+          description: 算子版本
+        inputs:
+          type: string
+          description: 输入类型
+        outputs:
+          type: string
+          description: 输入类型
+        categories:
+          type: array
+          description: 算子分类列表
+          items:
+            type: integer
+        runtime:
+          type: string
+          description: 运行时设置
+        settings:
+          type: string
+          description: 算子参数
+        isStar:
+          type: boolean
+          description: 是否收藏
+        createdAt:
+          type: string
+          format: date-time
+          description: 创建时间
+        updatedAt:
+          type: string
+          format: date-time
+          description: 更新时间
+      required:
+        - language
+        - modal
+        - inputs
+        - outputs
+        - runtime
+        - settings
+        - isStar
+    CreateOperatorRequest:
+      type: object
+      required:
+        - name
+        - description
+        - version
+        - category
+      properties:
+        name:
+          type: string
+          description: 算子名称
+        description:
+          type: string
+          description: 算子描述
+        version:
+          type: string
+          description: 算子版本
+        category:
+          type: string
+          description: 算子分类
+        documentation:
+          type: string
+          description: 文档内容
+  securitySchemes: {}
+servers: []

backend/openapi/specs/pipeline-orchestration.yaml

@@ -0,0 +1,639 @@
+openapi: 3.0.3
+info:
+  title: Pipeline Orchestration Service API
+  description: 流程编排服务API - 可视化、模板、执行计划
+  version: 1.0.0
+  contact:
+    name: Data Mate Platform Team
+
+servers:
+  - url: http://localhost:8087
+    description: Development server
+
+tags:
+  - name: pipelines
+    description: 流水线管理
+  - name: pipeline-templates
+    description: 流水线模板
+  - name: executions
+    description: 执行管理
+  - name: workflows
+    description: 工作流编排
+
+paths:
+  /api/v1/pipelines:
+    get:
+      tags:
+        - pipelines
+      summary: 获取流水线列表
+      parameters:
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+        - name: size
+          in: query
+          schema:
+            type: integer
+            default: 20
+        - name: status
+          in: query
+          schema:
+            $ref: '#/components/schemas/PipelineStatus'
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/PipelinePageResponse'
+
+    post:
+      tags:
+        - pipelines
+      summary: 创建流水线
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreatePipelineRequest'
+      responses:
+        '201':
+          description: 创建成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/PipelineResponse'
+
+  /api/v1/pipelines/{pipelineId}:
+    get:
+      tags:
+        - pipelines
+      summary: 获取流水线详情
+      parameters:
+        - name: pipelineId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/PipelineDetailResponse'
+
+    put:
+      tags:
+        - pipelines
+      summary: 更新流水线
+      parameters:
+        - name: pipelineId
+          in: path
+          required: true
+          schema:
+            type: string
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/UpdatePipelineRequest'
+      responses:
+        '200':
+          description: 更新成功
+
+  /api/v1/pipelines/{pipelineId}/execute:
+    post:
+      tags:
+        - executions
+      summary: 执行流水线
+      parameters:
+        - name: pipelineId
+          in: path
+          required: true
+          schema:
+            type: string
+      requestBody:
+        required: false
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/ExecutePipelineRequest'
+      responses:
+        '200':
+          description: 执行开始
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/PipelineExecutionResponse'
+
+  /api/v1/executions:
+    get:
+      tags:
+        - executions
+      summary: 获取执行历史
+      parameters:
+        - name: pipelineId
+          in: query
+          schema:
+            type: string
+        - name: status
+          in: query
+          schema:
+            $ref: '#/components/schemas/ExecutionStatus'
+        - name: page
+          in: query
+          schema:
+            type: integer
+            default: 0
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ExecutionPageResponse'
+
+  /api/v1/executions/{executionId}:
+    get:
+      tags:
+        - executions
+      summary: 获取执行详情
+      parameters:
+        - name: executionId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ExecutionDetailResponse'
+
+  /api/v1/executions/{executionId}/stop:
+    post:
+      tags:
+        - executions
+      summary: 停止执行
+      parameters:
+        - name: executionId
+          in: path
+          required: true
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 停止成功
+
+  /api/v1/templates:
+    get:
+      tags:
+        - pipeline-templates
+      summary: 获取模板列表
+      parameters:
+        - name: category
+          in: query
+          schema:
+            type: string
+      responses:
+        '200':
+          description: 获取成功
+          content:
+            application/json:
+              schema:
+                type: array
+                items:
+                  $ref: '#/components/schemas/PipelineTemplateResponse'
+
+    post:
+      tags:
+        - pipeline-templates
+      summary: 创建模板
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/CreatePipelineTemplateRequest'
+      responses:
+        '201':
+          description: 创建成功
+
+components:
+  schemas:
+    PipelineResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        description:
+          type: string
+        status:
+          $ref: '#/components/schemas/PipelineStatus'
+        version:
+          type: string
+        category:
+          type: string
+        tags:
+          type: array
+          items:
+            type: string
+        createdBy:
+          type: string
+        createdAt:
+          type: string
+          format: date-time
+        lastModified:
+          type: string
+          format: date-time
+
+    PipelineDetailResponse:
+      allOf:
+        - $ref: '#/components/schemas/PipelineResponse'
+        - type: object
+          properties:
+            definition:
+              $ref: '#/components/schemas/PipelineDefinition'
+            parameters:
+              type: array
+              items:
+                $ref: '#/components/schemas/PipelineParameter'
+            dependencies:
+              type: array
+              items:
+                type: string
+            statistics:
+              $ref: '#/components/schemas/PipelineStatistics'
+
+    PipelinePageResponse:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/PipelineResponse'
+        totalElements:
+          type: integer
+          format: int64
+        totalPages:
+          type: integer
+        size:
+          type: integer
+        number:
+          type: integer
+
+    CreatePipelineRequest:
+      type: object
+      required:
+        - name
+        - definition
+      properties:
+        name:
+          type: string
+        description:
+          type: string
+        category:
+          type: string
+        definition:
+          $ref: '#/components/schemas/PipelineDefinition'
+        parameters:
+          type: array
+          items:
+            $ref: '#/components/schemas/PipelineParameter'
+        tags:
+          type: array
+          items:
+            type: string
+
+    UpdatePipelineRequest:
+      type: object
+      properties:
+        name:
+          type: string
+        description:
+          type: string
+        definition:
+          $ref: '#/components/schemas/PipelineDefinition'
+        status:
+          $ref: '#/components/schemas/PipelineStatus'
+
+    ExecutePipelineRequest:
+      type: object
+      properties:
+        parameters:
+          type: object
+          description: 执行参数
+        environment:
+          type: string
+          description: 执行环境
+        priority:
+          type: integer
+          description: 优先级
+
+    PipelineExecutionResponse:
+      type: object
+      properties:
+        executionId:
+          type: string
+        pipelineId:
+          type: string
+        status:
+          $ref: '#/components/schemas/ExecutionStatus'
+        startTime:
+          type: string
+          format: date-time
+        message:
+          type: string
+
+    ExecutionResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        pipelineId:
+          type: string
+        pipelineName:
+          type: string
+        status:
+          $ref: '#/components/schemas/ExecutionStatus'
+        progress:
+          type: number
+          format: double
+        startTime:
+          type: string
+          format: date-time
+        endTime:
+          type: string
+          format: date-time
+        duration:
+          type: integer
+          format: int64
+          description: 执行时长（毫秒）
+
+    ExecutionDetailResponse:
+      allOf:
+        - $ref: '#/components/schemas/ExecutionResponse'
+        - type: object
+          properties:
+            steps:
+              type: array
+              items:
+                $ref: '#/components/schemas/ExecutionStep'
+            logs:
+              type: array
+              items:
+                $ref: '#/components/schemas/ExecutionLog'
+            metrics:
+              $ref: '#/components/schemas/ExecutionMetrics'
+            artifacts:
+              type: array
+              items:
+                $ref: '#/components/schemas/ExecutionArtifact'
+
+    ExecutionPageResponse:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/ExecutionResponse'
+        totalElements:
+          type: integer
+          format: int64
+        totalPages:
+          type: integer
+        size:
+          type: integer
+        number:
+          type: integer
+
+    PipelineTemplateResponse:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        description:
+          type: string
+        category:
+          type: string
+        version:
+          type: string
+        definition:
+          $ref: '#/components/schemas/PipelineDefinition'
+        usageCount:
+          type: integer
+        createdAt:
+          type: string
+          format: date-time
+
+    CreatePipelineTemplateRequest:
+      type: object
+      required:
+        - name
+        - definition
+      properties:
+        name:
+          type: string
+        description:
+          type: string
+        category:
+          type: string
+        definition:
+          $ref: '#/components/schemas/PipelineDefinition'
+
+    PipelineDefinition:
+      type: object
+      properties:
+        nodes:
+          type: array
+          items:
+            $ref: '#/components/schemas/PipelineNode'
+        edges:
+          type: array
+          items:
+            $ref: '#/components/schemas/PipelineEdge'
+        settings:
+          type: object
+          description: 流水线设置
+
+    PipelineNode:
+      type: object
+      properties:
+        id:
+          type: string
+        type:
+          type: string
+          enum: [OPERATOR, CONDITION, LOOP, PARALLEL]
+        name:
+          type: string
+        operatorId:
+          type: string
+        configuration:
+          type: object
+        position:
+          $ref: '#/components/schemas/NodePosition'
+
+    PipelineEdge:
+      type: object
+      properties:
+        id:
+          type: string
+        source:
+          type: string
+        target:
+          type: string
+        condition:
+          type: string
+        type:
+          type: string
+          enum: [SUCCESS, FAILURE, ALWAYS]
+
+    NodePosition:
+      type: object
+      properties:
+        x:
+          type: number
+        y:
+          type: number
+
+    PipelineParameter:
+      type: object
+      properties:
+        name:
+          type: string
+        type:
+          type: string
+        required:
+          type: boolean
+        defaultValue:
+          type: string
+        description:
+          type: string
+
+    PipelineStatistics:
+      type: object
+      properties:
+        totalExecutions:
+          type: integer
+        successfulExecutions:
+          type: integer
+        failedExecutions:
+          type: integer
+        averageDuration:
+          type: number
+          format: double
+        lastExecutionTime:
+          type: string
+          format: date-time
+
+    ExecutionStep:
+      type: object
+      properties:
+        id:
+          type: string
+        nodeId:
+          type: string
+        name:
+          type: string
+        status:
+          $ref: '#/components/schemas/ExecutionStatus'
+        startTime:
+          type: string
+          format: date-time
+        endTime:
+          type: string
+          format: date-time
+        duration:
+          type: integer
+          format: int64
+        message:
+          type: string
+
+    ExecutionLog:
+      type: object
+      properties:
+        timestamp:
+          type: string
+          format: date-time
+        level:
+          type: string
+          enum: [DEBUG, INFO, WARN, ERROR]
+        nodeId:
+          type: string
+        message:
+          type: string
+
+    ExecutionMetrics:
+      type: object
+      properties:
+        totalNodes:
+          type: integer
+        completedNodes:
+          type: integer
+        failedNodes:
+          type: integer
+        cpuUsage:
+          type: number
+          format: double
+        memoryUsage:
+          type: number
+          format: double
+        throughput:
+          type: number
+          format: double
+
+    ExecutionArtifact:
+      type: object
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        type:
+          type: string
+        size:
+          type: integer
+          format: int64
+        path:
+          type: string
+        createdAt:
+          type: string
+          format: date-time
+
+    PipelineStatus:
+      type: string
+      enum:
+        - DRAFT
+        - ACTIVE
+        - INACTIVE
+        - DEPRECATED
+
+    ExecutionStatus:
+      type: string
+      enum:
+        - PENDING
+        - RUNNING
+        - SUCCESS
+        - FAILED
+        - CANCELLED
+        - SKIPPED
+
+  securitySchemes:
+    BearerAuth:
+      type: http
+      scheme: bearer
+      bearerFormat: JWT
+
+security:
+  - BearerAuth: []