Mask Span Attributes

What it is

Mask Span Attributes lets you control which data gets recorded in your traces. Using environment variables or a TraceConfig object passed to any auto-instrumentor, you can hide inputs, outputs, messages, images, text, and embedding vectors before they leave your application. This is useful for preventing sensitive data from being logged and for reducing payload size when working with large base64-encoded images.

Use cases

• Privacy and compliance — Hide user inputs and LLM outputs to prevent sensitive data from being stored in trace backends.
• Image redaction — Suppress base64-encoded images from input messages or cap their length to reduce payload size.
• Selective masking — Hide only specific parts of a span (e.g. input text but not output messages) while keeping the rest visible.
• Environment-specific config — Use environment variables for deployment-level defaults and TraceConfig in code for per-instrumentor overrides.

How to

from fi_instrumentation import TraceConfig

config = TraceConfig(
    hide_inputs=False,
    hide_outputs=False,
    hide_input_messages=False,
    hide_output_messages=False,
    hide_input_images=False,
    hide_input_text=False,
    hide_output_text=False,
    hide_embedding_vectors=False,
    base64_image_max_length=32000,
)

from traceai_openai import OpenAIInstrumentor
OpenAIInstrumentor().instrument(
    tracer_provider=trace_provider,
    config=config,
)

import { OpenAIInstrumentor, FITraceConfig } from "@traceai/openai";
import { NodeTracerProvider } from "@opentelemetry/sdk-trace-node";

const config: FITraceConfig = {
    hideInputs: false,
    hideOutputs: false,
    hideInputMessages: false,
    hideOutputMessages: false,
    hideInputImages: false,
    hideInputText: false,
    hideOutputText: false,
    hideEmbeddingVectors: false,
    base64ImageMaxLength: 32000,
};

const instrumentor = new OpenAIInstrumentor();
instrumentor.instrument(
    tracerProvider,
    config
);

console.log("OpenAIInstrumentor configured with custom TraceConfig.");

Key concepts

• TraceConfig — An object accepted by all traceAI auto-instrumentors. Use it to specify masking settings directly in code, scoped to a single instrumentor.
• Environment variables — Global defaults applied to all instrumentors. Useful for deployment-level configuration without changing code.
• Precedence order — TraceConfig in code → environment variables → default values. More specific settings always win.
• hide_inputs / hide_outputs — Broad flags that hide all input/output values and messages in one setting.
• base64_image_max_length — Caps the logged length of base64-encoded images. Default is 32,000 characters.

What you can do next