market-assistant/docs/openapi/pipeline-jobs.openapi.yaml

openapi: 3.0.3
info:
  title: Market-Assistant — Pipeline & JD 数据集 API（子集）
  description: |
    与 `docs/pipeline-job-output-spec.md` 一致的核心路径；完整行为以 `pipeline/views.py` 为准。
  version: "1.0.0"

servers:
  - url: http://127.0.0.1:8000
    description: 本地 Django 默认端口

tags:
  - name: jobs
    description: 京东流水线任务
  - name: dataset
    description: 任务入库后的分页与导出
  - name: jd
    description: 全局 SKU 主档与快照

paths:
  /api/jobs/:
    get:
      tags: [jobs]
      summary: 任务列表（最近 200 条）
      responses:
        "200":
          description: OK
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: "#/components/schemas/PipelineJob"
    post:
      tags: [jobs]
      summary: 创建任务并异步执行
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/CreatePipelineJob"
      responses:
        "201":
          description: Created
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/PipelineJob"
        "503":
          description: LOW_GI_PROJECT_ROOT 未配置
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/ErrorDetail"

  /api/jobs/{id}/:
    get:
      tags: [jobs]
      summary: 任务详情
      parameters:
        - $ref: "#/components/parameters/JobId"
      responses:
        "200":
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/PipelineJob"
        "404":
          description: Not found
    patch:
      tags: [jobs]
      summary: 仅更新 report_config（报告关注词/场景/外部市场表等）
      parameters:
        - $ref: "#/components/parameters/JobId"
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/PatchReportConfig"
      responses:
        "200":
          description: OK
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/PipelineJob"
        "400":
          description: 校验失败（未知键或体积过大等）
        "404":
          description: Not found

  /api/jobs/{id}/cancel/:
    post:
      tags: [jobs]
      summary: 请求终止待执行/执行中的采集任务（协作式，在可停点结束）
      parameters:
        - $ref: "#/components/parameters/JobId"
      responses:
        "200":
          description: OK（cancellation_requested=true，随后状态变为 cancelled）
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/PipelineJob"
        "400":
          description: 任务已结束，不可再终止
        "404":
          description: Not found

  /api/report-config-defaults/:
    get:
      tags: [jobs]
      summary: 报告调参默认模板（与 jd_competitor_report 脚本常量一致）
      responses:
        "200":
          description: OK
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/ReportConfig"
        "503":
          description: 爬虫副本路径不可用等

  /api/jobs/{id}/download/:
    get:
      tags: [jobs]
      summary: 下载 run_dir 内产物
      parameters:
        - $ref: "#/components/parameters/JobId"
        - name: name
          in: query
          required: true
          schema:
            type: string
            enum: [merged, pc_search, comments, detail_ware, report]
      responses:
        "200":
          description: 文件流
        "404":
          description: 任务未成功或文件不存在

  /api/jobs/{id}/dataset/summary/:
    get:
      tags: [dataset]
      summary: 库内行数与列说明
      parameters:
        - $ref: "#/components/parameters/JobId"
      responses:
        "200":
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/DatasetSummary"

  /api/jobs/{id}/dataset/merged/:
    get:
      tags: [dataset]
      summary: 合并宽表分页
      parameters:
        - $ref: "#/components/parameters/JobId"
        - $ref: "#/components/parameters/Page"
        - $ref: "#/components/parameters/PageSize"
      responses:
        "200":
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/PaginatedMergedRows"

  /api/jobs/{id}/export/:
    get:
      tags: [dataset]
      summary: 导出 JSON / CSV / xlsx
      parameters:
        - $ref: "#/components/parameters/JobId"
        - name: kind
          in: query
          schema:
            type: string
            enum: [search, detail, comments, merged, all]
        - name: export_fmt
          in: query
          schema:
            type: string
            enum: [json, csv, xlsx]
      responses:
        "200":
          description: 文件下载

  /api/jobs/{id}/regenerate-report/:
    post:
      tags: [jobs]
      summary: 根据已有 CSV 重写 competitor_analysis.md（不重新爬取）；可选大模型生成（AI_crawler 同网关）
      parameters:
        - $ref: "#/components/parameters/JobId"
      requestBody:
        required: false
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/RegenerateReportRequest"
      responses:
        "200":
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/PipelineJob"
        "400":
          description: 任务状态或路径无效
        "502":
          description: 大模型网关 HTTP 错误
        "503":
          description: 未配置 OPENAI_* / LLM_* 等（generator=llm 时）

  /api/jobs/{id}/competitor-brief/:
    get:
      tags: [jobs]
      summary: 结构化竞品摘要 JSON（与 Markdown 报告统计口径一致）
      parameters:
        - $ref: "#/components/parameters/JobId"
      responses:
        "200":
          description: schema_version=1 的规则摘要
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
        "400":
          description: 任务未成功或缺少 run_dir / 合并表

  /api/jobs/{id}/competitor-brief-pack/:
    get:
      tags: [jobs]
      summary: 一键简报包（ZIP：报告 md + 摘要 json + 要点摘录 md + 说明）
      parameters:
        - $ref: "#/components/parameters/JobId"
      responses:
        "200":
          description: application/zip 附件
          content:
            application/zip:
              schema:
                type: string
                format: binary
        "400":
          description: 缺少 competitor_analysis.md 等
        "503":
          description: LOW_GI_PROJECT_ROOT 未配置

  /api/jobs/{id}/strategy-draft/:
    post:
      tags: [jobs]
      summary: 市场策略 Markdown 草稿（规则或可选大模型润色，网关同 AI_crawler）
      parameters:
        - $ref: "#/components/parameters/JobId"
      requestBody:
        required: false
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/StrategyDraftRequest"
      responses:
        "200":
          description: OK
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StrategyDraftResponse"
        "400":
          description: 任务未成功、缺少 run_dir，或 brief 构建失败
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/ErrorDetail"
        "404":
          description: Not found
        "502":
          description: 大模型网关 HTTP 错误
        "503":
          description: LOW_GI_PROJECT_ROOT 未配置，或大模型凭证未配置（generator=llm）
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/ErrorDetail"

  /api/jobs/{id}/ingest-merged/:
    post:
      tags: [dataset]
      summary: 从 run_dir 将 CSV 全量写入库（幂等：先清空该任务四类行）
      parameters:
        - $ref: "#/components/parameters/JobId"
      responses:
        "200":
          description: 统计信息（dataset + merged 块）

  /api/jd/products/:
    get:
      tags: [jd]
      summary: SKU 主档列表
      responses:
        "200":
          description: OK

components:
  parameters:
    JobId:
      name: id
      in: path
      required: true
      schema:
        type: integer
    Page:
      name: page
      in: query
      schema:
        type: integer
        default: 1
    PageSize:
      name: page_size
      in: query
      schema:
        type: integer
        default: 20

  schemas:
    ErrorDetail:
      type: object
      properties:
        detail:
          type: string

    CreatePipelineJob:
      type: object
      required: [platform, keyword]
      properties:
        platform:
          type: string
          example: jd
        keyword:
          type: string
        max_skus:
          type: integer
        page_start:
          type: integer
        page_to:
          type: integer
        pipeline_run_dir:
          type: string
        cookie_file_path:
          type: string
        cookie_text:
          type: string
        pvid:
          type: string
        request_delay:
          type: string
        list_pages:
          type: string
        scenario_filter_enabled:
          type: boolean
        report_config:
          $ref: "#/components/schemas/ReportConfig"

    ReportConfig:
      type: object
      description: |
        允许键仅限下列三项；可全部省略或 `{}` 表示使用脚本内置默认。
      properties:
        comment_focus_words:
          type: array
          items:
            type: string
        comment_scenario_groups:
          type: array
          items:
            type: object
            properties:
              label:
                type: string
              triggers:
                type: array
                items:
                  type: string
        external_market_table_rows:
          type: array
          items:
            type: object
            properties:
              indicator:
                type: string
              value_and_scope:
                type: string
              source:
                type: string
              year:
                type: string

    PatchReportConfig:
      type: object
      required: [report_config]
      properties:
        report_config:
          $ref: "#/components/schemas/ReportConfig"

    PipelineJob:
      type: object
      properties:
        id:
          type: integer
        platform:
          type: string
        keyword:
          type: string
        status:
          type: string
          enum: [pending, running, success, failed, cancelled]
        cancellation_requested:
          type: boolean
        run_dir:
          type: string
        error_message:
          type: string
        analysis_artifacts:
          type: object
          additionalProperties:
            type: boolean
          nullable: true
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
        report_config:
          $ref: "#/components/schemas/ReportConfig"

    ColumnMeta:
      type: object
      properties:
        key:
          type: string
        label:
          type: string

    DatasetSummary:
      type: object
      properties:
        job_id:
          type: integer
        keyword:
          type: string
        status:
          type: string
        search_rows:
          type: integer
        detail_rows:
          type: integer
        comment_rows:
          type: integer
        merged_rows:
          type: integer
        search_columns:
          type: array
          items:
            $ref: "#/components/schemas/ColumnMeta"
        detail_columns:
          type: array
          items:
            $ref: "#/components/schemas/ColumnMeta"
        comment_columns:
          type: array
          items:
            $ref: "#/components/schemas/ColumnMeta"
        merged_columns:
          type: array
          items:
            $ref: "#/components/schemas/ColumnMeta"

    PaginatedMergedRows:
      type: object
      properties:
        total:
          type: integer
        page:
          type: integer
        page_size:
          type: integer
        results:
          type: array
          items:
            type: object
            additionalProperties: true

    RegenerateReportRequest:
      type: object
      properties:
        generator:
          type: string
          enum: [rules, llm]
          default: rules
          description: rules=jd_competitor_report 规则引擎；llm=结构化摘要 JSON + AI_crawler 文本接口

    StrategyDraftRequest:
      type: object
      properties:
        generator:
          type: string
          enum: [rules, llm]
          default: rules
          description: llm 时在规则底稿与同任务摘要基础上由大模型润色全文
        business_notes:
          type: string
          maxLength: 20000
          description: 可选业务约束/假设，写入 §八
        product_role:
          type: string
          maxLength: 500
        time_horizon:
          type: string
          maxLength: 200
        success_criteria:
          type: string
          maxLength: 2000
        non_goals:
          type: string
          maxLength: 1000
        battlefield_one_line:
          type: string
          maxLength: 1000
        positioning_choice:
          type: string
          enum: ['', 'top', 'mid', 'entry', 'different']
          description: 价格带主定位；空字符串表示文稿中四项均为未勾选
        competitive_stance:
          type: string
          enum: ['', 'flank', 'head_on', 'both', 'undecided']
        pillar_product:
          type: string
          maxLength: 800
        pillar_price:
          type: string
          maxLength: 800
        pillar_channel:
          type: string
          maxLength: 800
        pillar_comm:
          type: string
          maxLength: 800
        ack_risk_keywords:
          type: boolean
          default: false
        ack_risk_price:
          type: boolean
          default: false
        ack_risk_concentration:
          type: boolean
          default: false

    StrategyDraftResponse:
      type: object
      required:
        - schema_version
        - job_id
        - keyword
        - generated_at
        - source
        - markdown
      properties:
        schema_version:
          type: integer
          example: 1
        job_id:
          type: integer
        keyword:
          type: string
        generated_at:
          type: string
          format: date-time
        source:
          type: string
          description: structured_summary_rules_v1 或 llm_text_ai_crawler_v1
          example: structured_summary_rules_v1
        markdown:
          type: string