neograph::llm::Agent Class Reference

Standalone ReAct agent that loops between LLM calls and tool execution. More...

#include <agent.h>

Public Member Functions
	Agent (std::shared_ptr< Provider > provider, std::vector< std::unique_ptr< Tool > > tools, const std::string &instructions="", const std::string &model="")
	Construct an agent with a provider and tools.
ChatCompletion	complete (const std::vector< ChatMessage > &messages)
	Perform a single LLM completion (no tool loop).
std::string	run (std::vector< ChatMessage > &messages, int max_iterations=10)
	Run the agent loop until completion.
std::string	run_stream (std::vector< ChatMessage > &messages, const StreamCallback &on_chunk, int max_iterations=10)
	Run the agent loop with streaming token output.

Detailed Description

Standalone ReAct agent that loops between LLM calls and tool execution.

The agent sends messages to the LLM, checks for tool calls, executes them, feeds results back, and repeats until the LLM produces a final text response or the iteration limit is reached.

auto agent = Agent(provider, std::move(tools), "You are a helpful assistant.");
std::vector<ChatMessage> messages = {{.role = "user", .content = "What's 2+2?"}};
std::string reply = agent.run(messages);

See also

neograph::graph::create_react_graph for the graph-based equivalent.

Definition at line 37 of file agent.h.

Constructor & Destructor Documentation

Agent()

neograph::llm::Agent::Agent	(	std::shared_ptr< Provider >	provider,
		std::vector< std::unique_ptr< Tool > >	tools,
		const std::string &	instructions = "",
		const std::string &	model = ""
	)

Construct an agent with a provider and tools.

Parameters

provider	LLM provider for making completions.
tools	Vector of tools available to the agent (ownership transferred).
instructions	Optional system prompt prepended to the conversation.
model	Optional model name override (empty = use provider default).

Member Function Documentation

complete()

ChatCompletion neograph::llm::Agent::complete

(

const std::vector< ChatMessage > &

messages

)

Perform a single LLM completion (no tool loop).

Parameters

messages

Conversation history (not modified).

Returns

The full completion response.

run()

std::string neograph::llm::Agent::run	(	std::vector< ChatMessage > &	messages,
		int	max_iterations = 10
	)

Run the agent loop until completion.

Iterates between LLM calls and tool execution until the LLM produces a response with no tool calls, or max_iterations is reached.

Parameters

[in,out]	messages	Conversation history (modified in-place with new messages).
	max_iterations	Maximum number of LLM call iterations (default: 10).

Returns

The final text response from the LLM.

run_stream()

std::string neograph::llm::Agent::run_stream	(	std::vector< ChatMessage > &	messages,
		const StreamCallback &	on_chunk,
		int	max_iterations = 10
	)

Run the agent loop with streaming token output.

Same as run(), but streams the final response tokens via the callback.

Parameters

[in,out]	messages	Conversation history (modified in-place).
	on_chunk	Callback invoked per token during the final LLM response.
	max_iterations	Maximum LLM call iterations (default: 10).

Returns

The final text response.

---

The documentation for this class was generated from the following file:

• include/neograph/llm/agent.h