Skip to content

Build a Chat Agent with a Graph

Create an agent whose graph is a simple RegexGuardrail → Generate chain, send a message, and get a streamed reply.

Prerequisites

Steps

  1. In the Project window: right-click → Create → Tryll → Workflow Asset. Name it ChatWorkflow.
  2. In the Inspector, expand Graph and add two nodes:
    • guard — Params type RegexGuardrail. Leave Triggered Exit empty (END) to drop jailbreaks silently, and set Not Triggered Exit = answer.
    • answer — Params type Generate. Default Exit stays empty (END).

Set Start Node = guard and Default Model Name = your model. 3. Attach a TryllAgentComponent to a GameObject and assign ChatWorkflow to its Workflow Asset field. 4. Wire events and send:

var agentComp = GetComponent<TryllAgentComponent>();

agentComp.OnAnswerText.AddListener(
    (text, isDelta, isFinal) => chatText.text += text);
agentComp.OnTurnComplete.AddListener(
    (status, _, _) => typingIndicator.SetActive(false));

// When the agent is created, send the first message.
agentComp.OnAgentCreated.AddListener(() => agentComp.SendMessage("Hello!"));
  1. In the Content Browser, right-click → Tryll → Workflow Asset. Name it ChatWorkflow and open it. On the guard node, set Triggered Exit to "" (END) and Not Triggered Exit to "answer". The answer node's Default Exit can be left empty (END).
  2. Add a UTryllAgentComponent to your actor and assign ChatWorkflow to its Workflow Asset slot.
  3. In Blueprint:
    • Bind On Agent Ready to a handler that calls Send Message.
    • Bind On Answer Text to append each chunk to a UI text block.
    • Bind On Turn Complete to flip the "typing" indicator off.
#include <tryll/TryllClient.h>

namespace TC = Tryll::Client;

TC::RegexGuardrailParams guardParams;
// guardParams.triggered_exit defaults to "" (END) — drop jailbreaks silently.
guardParams.not_triggered_exit = "answer";

TC::GraphDescription graph;
graph.AddNode("guard",  guardParams)
     .AddNode("answer", TC::GenerateParams{})
     .SetStartNode("guard")
     .SetDefaultModelName("My Local Model");

auto agent = client.CreateAgent(graph);

// Register persistent callbacks, then send — fire-and-forget.
agent.SetOnAnswerText([](std::string_view text, bool, bool)
    { std::cout << text << std::flush; });
agent.SetOnTurnComplete([](TC::TurnStatus, std::string_view, std::int32_t)
    { std::cout << "\n"; });
agent.SendText("Hello!");

from tryll_client.graph import GraphDescription, RegexGuardrailParams, GenerateParams

# 1. Build the graph.
guard_params = RegexGuardrailParams(
    # triggered_exit defaults to "" (END) — drop jailbreaks silently.
    not_triggered_exit = "answer",
)

graph = (
    GraphDescription()
    .add_node("guard",  guard_params)
    .add_node("answer", GenerateParams())
    .set_start_node("guard")
    .set_default_model_name("My Local Model")
)

# 2. Create the agent.
agent = client.create_agent(graph)

# 3. Send a message. send_message blocks and returns the full reply.
reply = agent.send_message("Hello!")
print(reply)

Verify it worked

Server-side, at info log level, one turn produces:

[info] Agent 7: turn starting
[info] Node guard: not_triggered
[info] Node answer: default
[info] Agent 7: turn complete (Success, tokens=128)

Client-side, Python returns the full reply string from send_message, while C++ and Unreal see each streamed chunk arrive in the SendText callback / OnAnswerText delegate, terminated by a TurnComplete with status Success.

Common pitfalls

  • "Model not found" (error 4002) — either the name is wrong, or the model is not in models.json. Double-check with client.list_models().
  • "Graph validation failed" (error 3003) — check for a bad start node name or duplicate node names in the graph. If the message says InvalidExitTarget (3008), an exit field on one of the nodes names a node that doesn't exist — fix the string or leave it empty for END.
  • Silent nothing after SendMessage. Check that the start node is not an always-END branch (e.g., guardrail that matches everything). The server log will show which route was taken.