类class agentscope.formatter

OpenAIResponseFormatter

class OpenAIResponseFormatter(_OpenAIResponseFormatterBase)

源码Source agentscope/formatter/_openai_response_formatter.py:162–403

OpenAIResponse 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 _OpenAIResponseFormatterBase。核心成员包括 format。

Produces input items compatible with client.responses.create( input=...). Compared with the Chat Completions format, the key differences are:

Text content blocks use input_text instead of text.
Image content blocks use input_image instead of image_url.
Assistant tool-call messages become top-level function_call items.
Tool result messages become function_call_output items.
Reasoning items (ThinkingBlock with reasoning_item_id) are echoed back verbatim as required by reasoning models (e.g. o1).

方法摘要Method Summary

方法Method	说明Description
`async def format(msgs: list[Msg]) -> list[dict[str, Any]]`async	设置格式。 Format message objects into OpenAI Response API input items.

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

async

设置格式。

Format message objects into OpenAI Response API input items.

参数Parameters

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

返回Returns list[dict[str, Any]]

返回dict[str,任意]列表。`list[dict[str, Any]]`:

源码Source agentscope/formatter/_openai_response_formatter.py:178–403