# Agent Config

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

<!-- interactive demo: agent-config -->

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 [#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](/vue/claude-sdk-python/shared-state) instead.

How agent config flows from the UI into the agent's reasoning loop depends on your runtime architecture. Most agents read the config from the context that the UI publishes with `useAgentContext`. The Built-in Agent reads it from `input.forwardedProps`, which the UI sets with the `properties` prop on `<CopilotKit>`.

## How it works [#how-it-works]

<Steps>
  <Step>
    ### Make runtime configuration explicit

    The Claude Agent SDK demo reads configuration from shared state and folds it
    into the system prompt. This keeps the agent behavior visible to the UI and
    lets users tune model behavior without rebuilding the backend.

~~~~python title="agent_config_agent.py"
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: Any) -> dict[str, str]:
    """Read the three config axes with defensive defaults.

    ``forwarded_props`` may arrive as either the raw top-level dict (when
    the Next.js route forwards provider ``properties`` straight through)
    or nested under ``config.configurable.properties`` (the LangGraph
    convention the shared runtime route adopts for compatibility). We
    accept both shapes — unknown values fall back to the defaults; the
    function never raises.
    """
    if not isinstance(forwarded_props, dict):
        forwarded_props = {}

    # Prefer the nested shape (mirrors the langgraph-python convention
    # the dedicated route repacks into) but fall back to top-level keys
    # so the demo still works if a caller forwards properties directly.
    nested = ((forwarded_props.get("config") or {}).get("configurable") or {}).get(
        "properties"
    ) or {}
    props = nested if isinstance(nested, dict) and nested else forwarded_props

    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 the 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]}"
    )


~~~~

  </Step>
</Steps>

Agent config is a typed object the frontend owns and publishes to the agent as
runtime context. The backend reads that context entry and turns it into a
system prompt.

The framework setup above shows the exact backend bridge for the selected
agent. In every framework, the flow is the same: read the latest valid context
from the current run and use it to build the system prompt for that turn.

```text title="Backend flow"
config = latestValidConfig(currentRun.context)
systemPrompt = buildSystemPrompt(config)
model.invoke(systemPrompt, currentUserRequest)
```

At the start of every turn, the agent reads the latest config. Then it rebuilds the system prompt and runs the turn.

Change the tone in your UI and send a message. The next reply uses the new tone.

<IntegrationGrid path="agent-config" />
