AS AgentScopeAPI 手册 / API Reference
类class agentscope.formatter

AnthropicChatFormatter

class AnthropicChatFormatter(_AnthropicFormatterBase)
源码Source agentscope/formatter/_anthropic_formatter.py:363–397

Anthropic 聊天格式化器,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 _AnthropicFormatterBase。核心成员包括 format。

The Anthropic formatter class for chatbot scenario, where only a user and an agent are involved. Declared in agentscope.formatter. Extends _AnthropicFormatterBase.

属性摘要Attribute Summary

属性Attribute类型Type说明Description值Value
input_typeslist[str]
输入类型字段。
Field(default_factory=lambda: ['text/plain', 'image/*', 'application/pdf'], description='The supported input types. Defaults to ``["text/plain", "image/*", "application/pdf"]``.')

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 Anthropic API format.

属性详情Attribute Detail

input_types

list[str] = Field(default_factory=lambda: ['text/plain', 'image/*', 'application/pdf'], description='The supported input types. Defaults to ``["text/plain", "image/*", "application/pdf"]``.')

输入类型字段。声明为 list[str]。

The supported input types.

源码Source agentscope/formatter/_anthropic_formatter.py:369

方法详情Method Detail

format

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

设置格式。

Format message objects into Anthropic API format.

说明Notes

  • 注意:该行为受运行时配置或底层实现影响,建议结合对应源码与版本说明确认。Note: Anthropic suggests always passing all previous thinking blocks back to the API in subsequent calls to maintain reasoning continuity. For more details, please refer to `Anthropic's documentation `_.
参数Parameters
名称Name类型Type说明Description
msgslist[Msg]消息列表(类型 `list[Msg]`)。The list of message 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/_anthropic_formatter.py:377–397
基于官方固定版本源码静态生成Generated from pinned official sources · Python 2.0.11 · Java 2.0.4
签名与文档为静态抽取;如有疑问请以源码为准。Signatures and docs are extracted statically; verify against the source when in doubt.