Skip to main content

​
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 union via the actual_instance pattern. 
from adaline_api.models.log_span_guardrail_content import LogSpanGuardrailContent

​
Fields

​
type
str
required
Must be "Guardrail".
​
input
str
required
The input payload as a JSON string. Must be valid, parseable JSON (the result of json.dumps()).
​
output
str
required
The output payload as a JSON string. Must be valid, parseable JSON (the result of json.dumps()).

​
Construction Pattern

All span content is wrapped in LogSpanContent using the actual_instance parameter: 
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

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),
        )
    ),
})