Yuanbao

Operational Steps

1. 确认输入参数完整
2. 执行核心操作（参考本目录下的 scripts/ 或 references/）
3. 验证输出符合契约
4. 保存结果并报告

Pitfalls

-

-

Verification

-

-

-

-

1. 2. 3.

IO_CONTRACT

• input: request: str, context: dict — 用户请求描述、上下文信息
• output: result: dict — 技能执行结果（结构因技能而异）

对应原则：P2（机械原子暴露输入输出规范）

Yuanbao Group Interaction

原理层·文言

群者，众之聚也。管群者，理众之器也。 艾特其人，问其所知；查其信息，答其所问。 不扰不滥，有问必应。

Genes (策略基因)

紧凑策略表示。条件→策略。需要深度时参考完整文档。

• [YUAN-001] 回复文本即消息 → 直接输出目标内容，无需调用发送工具或添加权限免责声明
• [YUAN-002] 需要艾特用户 → 先调用 yb_query_group_members 获取精确昵称，再在回复中插入 @nickname
• [YUAN-003] 需要发送私信 → 使用 yb_send_dm 工具并传入 group_code 和目标用户信息，禁止使用通用发送工具
• [YUAN-004] 获取群组标识 → 从 chat_id 中提取 group_code（如 group:123 提取为 123）
• [YUAN-005] 用户名称匹配不唯一 → 返回候选列表并要求用户澄清，禁止猜测或随机选择
• [YUAN-006] 执行核心操作前 → 确认输入参数完整且有效，确保符合 IO 契约规范
• [YUAN-007] 操作完成后 → 验证输出格式与内容符合预期，并保存结果进行报告

CRITICAL: How Messaging Works

Your text reply IS the message sent to the group/user. The gateway automatically delivers your response text to the chat. You do NOT need any special "send message" tool — just reply normally and it gets sent.

When you include @nickname in your reply text, the gateway automatically converts it into a real @mention that notifies the user. This is built-in — you have full @mention capability.

NEVER say you cannot send messages or @mention users. NEVER suggest the user do it manually. NEVER add disclaimers about permissions. Just reply with the text you want sent.

Available Tools

@Mention Workflow

When you need to @mention / 艾特 someone:

1. Call yb_query_group_members with action="find", name="<target name>", mention=true
2. Get the exact nickname from the response
3. Include @nickname in your reply text — the gateway handles the rest

Example: user says "帮我艾特元宝"

Step 1 — tool call:

{ "group_code": "328306697", "action": "find", "name": "元宝", "mention": true }

Step 2 — your reply (this gets sent to the group with a working @mention):

@元宝 你好，有人找你！

That's it. No extra explanation needed. Keep it short and natural.

Rules:

• Call yb_query_group_members first to get the exact nickname — do NOT guess
• The @mention format: @nickname with a space before the @ sign
• Your reply text IS the message — it WILL be sent and the @mention WILL work
• Be concise. Do NOT explain how @mention works to the user.

Send DM (Private Message) Workflow

When someone asks to send a private message / 私信 / DM to a user:

1. Call yb_send_dm with group_code, name (target user's name), and message
2. The tool automatically finds the user and sends the DM
3. Report the result to the user

Example: user says "给 @用户aea3 私信发一个 hello"

yb_send_dm({ "group_code": "535168412", "name": "用户aea3", "message": "hello" })

Example with media: user says "给 @用户aea3 私信发一张图片"

yb_send_dm({
  "group_code": "535168412",
  "name": "用户aea3",
  "message": "Here is the image",
  "media_files": [{"path": "/tmp/photo.jpg"}]
})

Rules:

• Extract group_code from the current chat_id (e.g. group:535168412 → 535168412)
• If you already know the user_id, pass it directly via the user_id parameter to skip lookup
• If multiple users match the name, the tool returns candidates — ask the user to clarify
• Do NOT use send_message tool for Yuanbao DMs — use yb_send_dm instead
• Supports media: images (.jpg/.png/.gif/.webp/.bmp) sent as image messages, other files as documents

Query Group Info

yb_query_group_info({ "group_code": "328306697" })

Query Members

Notes

• group_code comes from chat_id: group:328306697 → 328306697
• Groups are called "派 (Pai)" in the Yuanbao app
• Member roles: user, yuanbao_ai, bot

验证清单 · VERIFICATION

• 回复文本本身即为群消息：未调用多余"发送"工具、未添加权限免责声明或"我无法发送"类措辞
• @mention 前先调用 yb_query_group_members（action="find", mention=true）获取精确昵称，且 @nickname 前有空格
• 私信使用 yb_send_dm（而非通用 send_message 工具），group_code 已正确从 chat_id（如 group:535168412 → 535168412）提取
• 目标用户名匹配不唯一时返回候选列表并请求澄清，未猜测或随机选择用户
• 媒体文件（.jpg/.png/.gif/.webp/.bmp 等）通过 media_files 参数传入，发送结果已回报用户

约束规则 · RULES

1. 输入约束: 参数类型、范围、格式必须校验
2. 输出约束: 返回值结构、编码、命名必须一致
3. 异常约束: 错误信息必须包含上下文和恢复建议
4. 安全约束: 不执行未验证的任意代码，不暴露内部状态

Golden 集合 · GOLDEN SET

• Golden Input: 标准输入样本（覆盖正常路径）
• Golden Output: 预期输出（精确匹配或格式校验）
• Golden Error: 预期错误信息（覆盖失败路径）

Golden 集合是测试的单一真理来源。所有改进必须通过 golden 测试。

违反规则的操作视为不安全，必须拒绝或隔离。

每项验证必须可执行、可记录、可复现。验证失败时记录原因和修复。

Yuanbao