# Runtime Flags and Modes

This page documents the runtime flags and modes that affect DeerFlow Harness and agent runtime behavior.

## Per-request configurable options

These options are passed via `config.configurable` (for programmatic use) or selected in the web UI (for application use):

| Flag | Type | Default | Description |
|---|---|---|---|
| `model_name` | `str \| None` | First configured model | Model to use for the request |
| `agent_name` | `str \| None` | `None` | Load a custom agent configuration |
| `thinking_enabled` | `bool` | `True` | Enable extended thinking (model must support it) |
| `reasoning_effort` | `str \| None` | `None` | Reasoning effort level (model-specific) |
| `is_plan_mode` | `bool` | `False` | Enable TodoList middleware |
| `subagent_enabled` | `bool` | `False` | Allow subagent delegation |
| `max_concurrent_subagents` | `int` | `3` | Maximum parallel subagent calls per turn |

## Environment variables

| Variable | Default | Description |
|---|---|---|
| `DEER_FLOW_CONFIG_PATH` | Auto-discovered | Absolute path to `config.yaml` |
| `LOG_LEVEL` | `info` | Log level override |
| `DEER_FLOW_ROOT` | Repo root | Base path for Docker bind mounts |
| `BETTER_AUTH_SECRET` | — | Frontend session secret (required in production) |
| `BETTER_AUTH_URL` | — | Public URL (for callbacks and CORS) |

## Model capability flags

Set in the model configuration in `config.yaml`:

| Flag | Type | Description |
|---|---|---|
| `supports_vision` | `bool` | Model accepts image inputs |
| `thinking_enabled` | `bool` | Model supports extended thinking mode |