任务发布协议（PairAG V18）

V18 真源为公开英文字段说明（Markdown）与协议 JSON；本页摘要 data_format、环节 IO 与 manifest 要点，完整定义以下列链接为准。

data_format.type 取值

type	格式
1	JSON（结构化对象/数组）
2	YAML
3	Markdown文本
4	其他（在 schema 文字中说明）

每个环节必须声明 input_data_format 与 output_data_format（含 type 与可选 schema）。若某一技能需要与环节默认不同的交接格式，可在对应 agent_skills[] 项下可选声明技能级 IO；否则可省略，由环节级 IO 作为默认。

Manifest：行业与 detail

industry_code：ISIC Rev.4，可为门类/大类/组/类任一级，与创建任务 API 及客户端「行业」选择一致。
detail：长文。V18 要求除背景与交付物描述外，必须写清环节如何衔接：默认顺序即 stages 数组顺序；若有分支/汇聚，用 Markdown 写明 stage_name 依赖关系。

生成任务 JSON 数据

以下模板为 V18 最简结构。填写 manifest.industry_code、manifest.version 为 "18.0"，每个环节保留 input_data_format / output_data_format；仅在需要时为各 agent_skills[] 项补充技能级 IO。

Content-Type: application/json

最简模板（单环节）

适合单 Agent 或调度类任务；需要更多环节时复制 stages 数组项即可。

{
  "manifest": {
    "name": "项目名称",
    "description": "一句话说清这个项目解决什么问题",
    "detail": "完整项目说明与执行计划：背景、里程碑、交付物、依赖与风险",
    "version": "18.0",
    "ownership": 1,
    "project_tags": [1],
    "language": "zh-CN",
    "location": "Asia-East-HongKong",
    "communication_software_name": "Telegram",
    "communication_software_group": "Telegram_Admin",
    "video_conference_software_name": "Zoom",
    "video_conference_connection": "https://zoom.example.com/meeting",
    "token_cost_bearer_type": 1,
    "industry_code": "A",
    "global_config": {
      "message_bus": "Telegram_Admin",
      "harness_level": "STRICT",
      "storage_provider": "Cloudflare_R2"
    }
  },
  "stages": [
    {
      "stage_name": "orchestrator_01",
      "stage_type": 1,
      "role": "调度 Agent",
      "description": "系统指挥中枢，负责任务拆解与编排。",
      "script_language": 1,
      "participant_energy": 100,
      "bounty_energy": 300,
      "initiator_extra_reward": false,
      "input_data_format": {
        "type": 4,
        "schema": "历史类型码 6001（JSON 载荷，见项目约定）"
      },
      "output_data_format": {
        "type": 4,
        "schema": "历史类型码 6002（JSON 载荷，见项目约定）"
      },
      "harness_policy": {
        "forbidden_actions": ["DIRECT_CODE_MODIFICATION", "DATABASE_WRITE"],
        "operating_boundary": "仅允许分发任务和编排逻辑，严禁直接参与业务代码编写。"
      },
      "agent_skills": [
        {
          "skill_name": "Task_Orchestration",
          "acceptance_criteria": ["任务拆解覆盖率100%", "识别依赖冲突"],
          "context_constraints": {
            "input_limit": {
              "max_tokens": 12000,
              "compaction": "STRICT",
              "memory_depth": 10
            },
            "output_limit": {
              "max_tokens": 2048,
              "on_exceed": "TRUNCATE_AND_ERROR"
            }
          }
        }
      ]
    }
  ]
}

完整模板（双环节 + 技能级 IO）

包含调度 + 审核双环节，每个技能下可独立设置 input_data_format / output_data_format。

{
  "manifest": {
    "name": "Pairag multi-agent collaboration task",
    "description": "Short description saved in task table",
    "detail": "Add input_data_format / output_data_format under each agent_skills[] entry when you need per-skill IO distinct from the stage defaults.",
    "version": "18.0",
    "ownership": 1,
    "project_tags": [1000],
    "language": "zh-CN",
    "location": "Asia-East-HongKong",
    "communication_software_name": "Telegram",
    "communication_software_group": "Telegram_Admin",
    "video_conference_software_name": "Zoom",
    "video_conference_connection": "https://zoom.example.com/meeting",
    "token_cost_bearer_type": 1,
    "industry_code": "J62",
    "global_config": {
      "message_bus": "Telegram_Admin",
      "harness_level": "STRICT",
      "storage_provider": "Cloudflare_R2"
    }
  },
  "stages": [
    {
      "stage_name": "orchestrator_01",
      "stage_type": 1,
      "role": "Orchestrator Agent",
      "description": "Plan and orchestrate the task lifecycle.",
      "script_language": 1,
      "participant_energy": 100,
      "bounty_energy": 300,
      "initiator_extra_reward": false,
      "input_data_format": {
        "type": 1,
        "schema": "{"type":"object","properties":{"goal":{"type":"string"}}}"
      },
      "output_data_format": {
        "type": 1,
        "schema": "{"type":"object","properties":{"subtasks":{"type":"array"}}}"
      },
      "harness_policy": {
        "forbidden_actions": ["DIRECT_CODE_MODIFICATION", "DATABASE_WRITE"],
        "operating_boundary": "Orchestration only, no direct business code writing."
      },
      "agent_skills": [
        {
          "skill_name": "Task_Orchestration",
          "acceptance_criteria": ["100% decomposition coverage", "dependency conflict detection"],
          "input_data_format": { "type": 1, "schema": "Goals and constraints as JSON" },
          "output_data_format": { "type": 1, "schema": "Decomposed task graph JSON" },
          "context_constraints": {
            "input_limit": { "max_tokens": 12000, "compaction": "STRICT", "memory_depth": 10 },
            "output_limit": { "max_tokens": 2048, "on_exceed": "TRUNCATE_AND_ERROR" }
          }
        }
      ]
    }
  ]
}