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

# LogSpanGuardrailContent

# LogSpanGuardrailContent

Content type for safety and compliance check spans.

## Overview

`LogSpanGuardrailContent` captures guardrail evaluations such as content moderation, policy checks, or input validation. It is wrapped in a [LogSpanContent](/docs/reference/sdk/v2/python/types/LogSpanContent) union via the `actual_instance` pattern.

```python theme={null}
from adaline_api.models.log_span_guardrail_content import LogSpanGuardrailContent
```

***

## Fields

<ParamField body="type" type="str" required>
  Must be `"Guardrail"`.
</ParamField>

<ParamField body="input" type="str" required>
  The input payload as a JSON string. Must be valid, parseable JSON (the result of `json.dumps()`).
</ParamField>

<ParamField body="output" type="str" required>
  The output payload as a JSON string. Must be valid, parseable JSON (the result of `json.dumps()`).
</ParamField>

***

## Construction Pattern

All span content is wrapped in [LogSpanContent](/docs/reference/sdk/v2/python/types/LogSpanContent) using the `actual_instance` parameter:

```python theme={null}
from adaline_api.models.log_span_content import LogSpanContent
from adaline_api.models.log_span_guardrail_content import LogSpanGuardrailContent

content = LogSpanContent(
    actual_instance=LogSpanGuardrailContent(
        type="Guardrail",
        input=json.dumps({"text": "user message"}),
        output=json.dumps({"safe": True}),
    )
)
```

***

## Example

```python theme={null}
import json
from adaline_api.models.log_span_content import LogSpanContent
from adaline_api.models.log_span_guardrail_content import LogSpanGuardrailContent

guard_input = {"text": "How do I reset my password?"}
guard_output = {"safe": True, "categories": [], "flagged": False}

span.update({
    "status": "success",
    "content": LogSpanContent(
        actual_instance=LogSpanGuardrailContent(
            type="Guardrail",
            input=json.dumps(guard_input),
            output=json.dumps(guard_output),
        )
    ),
})
```