类class agentscope.formatter

DashScopeMultiAgentFormatter

class DashScopeMultiAgentFormatter(_DashScopeFormatterBase)

源码Source agentscope/formatter/_dashscope_formatter.py:418–577

DashScope Multi 智能体格式化器，在智能体、模型与前端之间传递结构化消息和事件。位于 agentscope.formatter 包，继承自 _DashScopeFormatterBase。核心成员包括 format。

.. tip:: Telling the assistant's name in the system prompt is very important in multi-agent conversations. So that LLM can know who it is playing as.

属性摘要Attribute Summary

属性Attribute	类型Type	说明Description	值Value
`conversation_history_prompt`	str	会话历史提示词。	`Field(description='The conversation history prompt.', default='# Conversation History\nThe content between <history></history> tags contains your conversation history\n')`

方法摘要Method Summary

方法Method	说明Description
`async def format(msgs: list[Msg]) -> list[dict]`async	设置格式。 Format input messages into the structure required by the DashScope OpenAI-compatible API.

属性详情Attribute Detail

conversation_history_prompt

str = Field(description='The conversation history prompt.', default='# Conversation History\nThe content between <history></history> tags contains your conversation history\n')

会话历史提示词。

The conversation history prompt.

源码Source agentscope/formatter/_dashscope_formatter.py:435

方法详情Method Detail

format

async def format(msgs: list[Msg]) -> list[dict]

async

设置格式。

To support multi-agent conversations, this formatter processes messages as follows: - Prepends an instruction before the first conversation history section.

参数Parameters

名称Name	类型Type	说明Description
`msgs`	list[Msg]	消息列表（类型 `list[Msg]`）。The msgs.

返回Returns list[dict]

返回dict列表。`list[dict[str, Any]]`:

源码Source agentscope/formatter/_dashscope_formatter.py:444–489