CopilotKit

Agent Config

Forward typed configuration from your UI into the agent's reasoning loop.

"""Agno agent backing the Agent Config Object demo.Reads three forwarded properties — ``tone``, ``expertise``,``responseLength`` — that the CopilotKit provider forwards on every run,and composes the system prompt dynamically per turn.Agno does not have a LangGraph-style ``configurable`` channel; instead thecustom AGUI handler in ``agent_server.py`` (mounted at``/agent-config/agui``) reads ``RunAgentInput.forwarded_props``, builds afresh system prompt, and constructs a per-request Agno ``Agent`` with thatprompt before invoking it. The factory in this module produces thoseper-request agents."""from typing import Literalfrom agno.agent.agent import Agentfrom agno.models.openai import OpenAIChatfrom dotenv import load_dotenvload_dotenv()Tone = Literal["professional", "casual", "enthusiastic"]Expertise = Literal["beginner", "intermediate", "expert"]ResponseLength = Literal["concise", "detailed"]DEFAULT_TONE: Tone = "professional"DEFAULT_EXPERTISE: Expertise = "intermediate"DEFAULT_RESPONSE_LENGTH: ResponseLength = "concise"VALID_TONES: set[str] = {"professional", "casual", "enthusiastic"}VALID_EXPERTISE: set[str] = {"beginner", "intermediate", "expert"}VALID_RESPONSE_LENGTHS: set[str] = {"concise", "detailed"}def read_properties(forwarded_props: dict | None) -> dict[str, str]:    """Read the forwarded ``properties`` dict with defensive defaults.    The CopilotKit provider forwards its ``properties`` prop as top-level    keys on ``forwarded_props`` (see the runtime's run handler). This    function never raises — every unrecognized value falls back to the    matching ``DEFAULT_*`` constant.    """    props = forwarded_props or {}    tone = props.get("tone", DEFAULT_TONE)    expertise = props.get("expertise", DEFAULT_EXPERTISE)    response_length = props.get("responseLength", DEFAULT_RESPONSE_LENGTH)    if tone not in VALID_TONES:        tone = DEFAULT_TONE    if expertise not in VALID_EXPERTISE:        expertise = DEFAULT_EXPERTISE    if response_length not in VALID_RESPONSE_LENGTHS:        response_length = DEFAULT_RESPONSE_LENGTH    return {        "tone": tone,        "expertise": expertise,        "response_length": response_length,    }def build_system_prompt(tone: str, expertise: str, response_length: str) -> str:    """Compose a system prompt from the three axes."""    tone_rules = {        "professional": ("Use neutral, precise language. No emoji. Short sentences."),        "casual": (            "Use friendly, conversational language. Contractions OK. "            "Light humor welcome."        ),        "enthusiastic": (            "Use upbeat, energetic language. Exclamation points OK. Emoji OK."        ),    }    expertise_rules = {        "beginner": "Assume no prior knowledge. Define jargon. Use analogies.",        "intermediate": (            "Assume common terms are understood; explain specialized terms."        ),        "expert": ("Assume technical fluency. Use precise terminology. Skip basics."),    }    length_rules = {        "concise": "Respond in 1-3 sentences.",        "detailed": ("Respond in multiple paragraphs with examples where relevant."),    }    return (        "You are a helpful assistant.\n\n"        f"Tone: {tone_rules[tone]}\n"        f"Expertise level: {expertise_rules[expertise]}\n"        f"Response length: {length_rules[response_length]}"    )def build_agent(forwarded_props: dict | None) -> Agent:    """Build a per-request Agno agent whose system prompt reflects the    forwarded provider properties.    Constructed fresh on each run so the system prompt is current; the    Agno session DB still tracks history via ``session_id`` (the AGUI    handler passes ``thread_id`` through).    """    props = read_properties(forwarded_props)    system_prompt = build_system_prompt(        props["tone"], props["expertise"], props["response_length"]    )    return Agent(        model=OpenAIChat(id="gpt-4o-mini", temperature=0.4, timeout=120),        tools=[],        description=system_prompt,    )# A neutral default so AgentOS' agent-registry init doesn't fail before the# first run materialises a per-request agent.agent = build_agent(None)

You have a working agent and want the user to be able to tune how it behaves: tone, expertise level, response length, language, persona. By the end of this guide, your UI will own a typed config object that the agent reads on every run and rebuilds its system prompt from.

When to use this#

Reach for agent config whenever the agent's behaviour depends on user-controllable settings that don't fit naturally as chat input:

  • Tone, voice, persona: "playful", "formal", "casual"
  • Expertise level: "beginner", "intermediate", "expert"
  • Response shape: short / medium / long, structured / prose, language
  • Domain switches: which knowledge base to consult, which tool subset to enable

If the values are a channel the user occasionally tunes (a settings panel, a toolbar of selects), agent config is the right shape. If the values are content the agent should write back to (notes, a document, a plan), use Shared State instead.

How agent config flows from the UI into the agent's reasoning loop depends on your runtime architecture. Agents living behind a runtime read it from agent state on every run, while in-process agents receive the same object as forwarded properties on the provider — same UX, slightly different wiring on each side.

How it works#

Agent config is a typed object the frontend owns and keeps in sync with the agent. There are two pieces: the UI side, which owns the React state and pushes every change into agent state, and the backend node, which reads those fields out of state and turns them into a system prompt.

The UI side stays simple. Hold the typed config in React state, then mirror every change into the agent through agent.setState({...}):

frontend/src/app/page.tsx — UI owns the typed config
function ConfigStateSync({ config }: { config: AgentConfig }) {
  const { agent } = useAgent({ agentId: "agent-config" });
  useEffect(() => {
    agent.setState({ ...config });
  }, [agent, config]);
  return null;
}

The backend half is also a single node. Read the config out of state at the top of every run and use it to build the system prompt for that turn:

backend/agent.py — agent reads config and rebuilds the system prompt
async def my_agent_node(state: AgentState, config: RunnableConfig):
    cfg = state.get("config", {})
    tone = cfg.get("tone", "casual")
    expertise = cfg.get("expertise", "intermediate")
    response_length = cfg.get("response_length", "medium")
    system_prompt = build_system_prompt(tone, expertise, response_length)
    # ...

The agent reads the latest typed config at the start of every turn, rebuilds the system prompt, runs the turn. This is the same shape as the shared-state write-side pattern; agent config is just a specific use of that pattern with a UI-owned typed object on top.

On this page

When to use thisHow it works