AI inputs and outputs retained or exposed by default

Turn off prompt and completion content capture in GenAI tracing, send store=False to the provider, and set a retention limit on stored conversations by default.

Set the defaults in the configuration that ships to production: OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT false or unset, TRACELOOP_TRACE_CONTENT=false (Traceloop captures content when it is unset), and LANGSMITH_HIDE_INPUTS and LANGSMITH_HIDE_OUTPUTS true, or a masking function, whenever LangSmith tracing is on. Model calls pass store=False unless a documented feature needs provider-side storage (the OpenAI Responses API stores by default). Stored conversations carry a retention period enforced by a TTL or purge job, and any wider capture is an explicit opt-in scoped to a debugging environment or a sampled, masked subset.

Where it goes: 2 data models, 3 config and feature flags, 8 model configuration, 10 logs and telemetry.

What reviewers look for: production env files, Helm values, and Dockerfiles without OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=true or TRACELOOP_TRACE_CONTENT=true, with TRACELOOP_TRACE_CONTENT=false wherever Traceloop is initialized and LANGSMITH_HIDE_INPUTS/OUTPUTS wherever LangSmith tracing is on; no store=True on responses.create or chat.completions.create without a recorded need; a TTL, expires_at column, or scheduled purge on the conversation store.

OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=true
LANGSMITH_TRACING=true

OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=false
TRACELOOP_TRACE_CONTENT=false
LANGSMITH_TRACING=true
LANGSMITH_HIDE_INPUTS=true
LANGSMITH_HIDE_OUTPUTS=true

Engineering guidance, not legal advice. Each provision below may add its own details (a cadence, a deadline, a required notice element): open it for those.