agent: Chat with tool use (agentic mode)

In llm.api: Minimal LLM Chat Interface

Chat with tool use (agentic mode)

Description

Send a prompt to an LLM with tools. Automatically handles tool calls in a loop until the model responds with text only.

Usage

agent(prompt, tools = list(), tool_handler = NULL, system = NULL, model = NULL,
      provider = c("anthropic", "openai", "moonshot", "ollama"),
      max_turns = 20L, verbose = TRUE, history = NULL, ...)

Arguments

prompt	Character. The user message.
tools	List. Tool definitions (from mcp_tools_for_claude or manual).
tool_handler	Function. Called with (name, args), returns result string.
system	Character. System prompt.
model	Character. Model name.
provider	Character. Provider: "anthropic", "openai", "moonshot", or "ollama".
max_turns	Integer. Maximum tool-use turns (default: 20).
verbose	Logical. Print tool calls and results.
history	List or NULL. Previous conversation history to continue from.
...	Additional parameters passed to the API.

Value

List with final response and conversation history.

Examples

## Not run: 
# With MCP server
conn <- mcp_connect("r", "mcp_server.R")
tools <- mcp_tools_for_claude(conn)

result <- agent(
  "What files are in the current directory?",
  tools = tools,
  tool_handler = function(name, args) {
    mcp_call(conn, name, args)$text
  }
)

## End(Not run)

llm.api documentation built on April 16, 2026, 5:08 p.m.