> ## Documentation Index
> Fetch the complete documentation index at: https://docs.forii.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Context & Metadata

> Graceful context truncation for long prompts, and request metadata for cost attribution across teams.

## Context truncation

Instead of returning an error for prompts that exceed the context window, truncate gracefully:

```python theme={null}
response = client.chat.completions.create(
    model="forii/deepseek-v3",
    messages=long_messages,
    context_length_exceeded_behavior="truncate",  # or "error"
    max_tokens=2048,
)
```

| Value        | Behavior                                                                   |
| ------------ | -------------------------------------------------------------------------- |
| `"truncate"` | Truncate the prompt to fit the context window. Process continues normally. |
| `"error"`    | Return an error if the prompt exceeds the context limit.                   |

<Info>
  `truncate` is the default. It removes the oldest messages first (system message preserved), giving you a better UX than a hard error. Use `"error"` when you need to know exactly when context limits are hit.
</Info>

## Request metadata

Attach key-value metadata for cost attribution across teams and projects:

```python theme={null}
response = client.chat.completions.create(
    model="forii/deepseek-v3",
    messages=[{"role": "user", "content": "Hello"}],
    extra_body={"metadata": {
        "user_id": "u_12345",
        "session_id": "s_abc",
        "team": "search",
        "project": "ranker",
    }},
)
```

Metadata appears in usage logs and the usage API, letting you attribute costs to specific teams, projects, or users.

<Info>
  Metadata is a Forii extension adopted from Fireworks' parameters. Values must be strings. Useful for cost attribution, A/B test labeling, and debugging.
</Info>

## Additional Forii extensions

| Parameter                          | Type    | Description                                                                                                    |
| ---------------------------------- | ------- | -------------------------------------------------------------------------------------------------------------- |
| `reasoning_effort`                 | string  | `none` \| `low` \| `medium` \| `high` — see [Reasoning Models](/docs/api-reference/chat-completions/reasoning) |
| `context_length_exceeded_behavior` | string  | `"truncate"` (default) or `"error"`                                                                            |
| `repetition_penalty`               | float   | 0–2, applies to both prompt and output                                                                         |
| `top_k`                            | integer | Top-K sampling                                                                                                 |
| `metadata`                         | object  | Key-value string metadata for tracing and cost attribution                                                     |