Implementation:Cohere ai Cohere python AssistantMessage Model

Knowledge Sources	Cohere Python SDK
Domains	SDK, Chat
Last Updated	2026-02-15 14:00 GMT

Overview

The AssistantMessage class is a Pydantic model representing a message from the assistant role that can contain text content, tool calls, and citations.

Description

The AssistantMessage model represents a message produced by the assistant in the Cohere chat API. It can contain structured content via the content field (of type AssistantMessageV2Content), a list of tool calls (of type ToolCallV2) when the model invokes tools, a tool_plan string containing chain-of-thought reasoning when working with tools, and a list of Citation objects linking generated text to source documents. This model extends UncheckedBaseModel and is auto-generated from the Cohere API definition by Fern.

Usage

Use this model when constructing chat history for the V2 chat API. It is used to represent prior assistant turns in a multi-turn conversation, including any tool invocations and citations that were part of the assistant's response.

Code Reference

Source Location

Repository: Cohere Python SDK
File: src/cohere/types/assistant_message.py

Signature

class AssistantMessage(UncheckedBaseModel):
    tool_calls: typing.Optional[typing.List[ToolCallV2]] = None
    tool_plan: typing.Optional[str] = pydantic.Field(default=None)
    content: typing.Optional[AssistantMessageV2Content] = None
    citations: typing.Optional[typing.List[Citation]] = None

Import

from cohere.types import AssistantMessage

I/O Contract

Field	Type	Required	Default	Description
`tool_calls`	`Optional[List[ToolCallV2]]`	No	`None`	List of tool calls made by the assistant during this turn.
`tool_plan`	`Optional[str]`	No	`None`	A chain-of-thought style reflection and plan that the model generates when working with Tools.
`content`	`Optional[AssistantMessageV2Content]`	No	`None`	Structured content of the assistant message (text or thinking items).
`citations`	`Optional[List[Citation]]`	No	`None`	List of citations linking generated text to source documents.

Usage Examples

from cohere.types import AssistantMessage

# Construct an assistant message for chat history
assistant_msg = AssistantMessage(
    content=[{"type": "text", "text": "The capital of France is Paris."}],
    citations=None,
    tool_calls=None,
    tool_plan=None,
)

# Use in a multi-turn conversation with the V2 chat API
import cohere

client = cohere.ClientV2(api_key="YOUR_API_KEY")

response = client.chat(
    model="command-r-plus",
    messages=[
        {"role": "user", "content": "What is the capital of France?"},
        {"role": "assistant", "content": "The capital of France is Paris."},
        {"role": "user", "content": "What is its population?"},
    ],
)

# Access the assistant message from the response
assistant = response.message
if assistant.tool_calls:
    for tc in assistant.tool_calls:
        print(f"Tool call: {tc}")
if assistant.tool_plan:
    print(f"Tool plan: {assistant.tool_plan}")

Related Pages

Environment:Cohere_ai_Cohere_python_Python_SDK_Runtime

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment