Data Masking
Prompts, completions, retrieved documents, and media frequently contain personal or sensitive information. The trace configuration settings let an application keep that content out of its traces. This page describes what each setting hides.
Redacted Content
When content is hidden by a setting, its value is replaced with the placeholder "__REDACTED__", or the attribute is
omitted. The constant placeholder lets consumers tell that content was intentionally hidden rather than missing or
empty.
Inputs and Outputs
OPENINFERENCE_HIDE_INPUTShidesinput.value,input.images,input.documents, all input messages, and the tool definitions advertised to the LLM (llm.tools.*).OPENINFERENCE_HIDE_OUTPUTShidesoutput.value,output.images,output.documents, and all output messages.
Messages
- Input messages are hidden if either
OPENINFERENCE_HIDE_INPUTSorOPENINFERENCE_HIDE_INPUT_MESSAGESis true. - Output messages are hidden if either
OPENINFERENCE_HIDE_OUTPUTSorOPENINFERENCE_HIDE_OUTPUT_MESSAGESis true.
When messages are not already hidden, finer settings hide parts of them:
OPENINFERENCE_HIDE_INPUT_TEXTreplaces text content in input messages with"__REDACTED__", including message documentdocument.content.OPENINFERENCE_HIDE_OUTPUT_TEXTdoes the same for output messages.OPENINFERENCE_HIDE_INPUT_IMAGESreplaces image URLs in input messages with"__REDACTED__".
LLM Request Details
OPENINFERENCE_HIDE_LLM_INVOCATION_PARAMETERShidesllm.invocation_parameters, independent of input and output hiding.OPENINFERENCE_HIDE_LLM_TOOLShides the tool definitions advertised to the LLM (llm.tools.*). They are also hidden whenOPENINFERENCE_HIDE_INPUTSis true.OPENINFERENCE_HIDE_PROMPTShides the prompts of a completions API call (llm.prompts.*).OPENINFERENCE_HIDE_CHOICEShides the choices of a completions API call (llm.choices.*).
Embeddings
OPENINFERENCE_HIDE_EMBEDDINGS_VECTORSreplaces eachembedding.embeddings.N.embedding.vectorvalue with"__REDACTED__", so vector data is not included in traces.OPENINFERENCE_HIDE_EMBEDDING_VECTORSis a deprecated name for the same setting.OPENINFERENCE_HIDE_EMBEDDINGS_TEXTreplaces eachembedding.embeddings.N.embedding.textvalue with"__REDACTED__", so the input text is not included in traces.
Retrieval Documents
OPENINFERENCE_HIDE_RETRIEVAL_DOCUMENTS replaces retrieval.documents.*.document.content and
retrieval.documents.*.document.metadata values with "__REDACTED__". OPENINFERENCE_HIDE_OUTPUTS implies it.
Only the Python SDK supports this setting today.
Images and Documents
The image settings apply to the span-kind-independent input.images and output.images attributes the same way they
apply to message-content images:
OPENINFERENCE_HIDE_INPUT_IMAGESremoves allinput.images.*attributes.OPENINFERENCE_HIDE_INPUTSremovesinput.images.*andOPENINFERENCE_HIDE_OUTPUTSremovesoutput.images.*, just as they hideinput.valueandoutput.value.
Base64 Size Limit
OPENINFERENCE_BASE64_IMAGE_MAX_LENGTH (default 32000) limits the length of a base64 data URI recorded in an image
image.url or a document document.url, in messages and in <input|output>.images and <input|output>.documents.
The setting keeps its image-specific name but sets the limit for both.
- A data URI longer than the limit is replaced with
"__REDACTED__". - If a blob uploader is configured, an over-limit image or document is uploaded instead, and the attribute records the destination URI.
- Hide settings take precedence: hidden content is never uploaded.
- Audio and video data URIs are not size-gated, and the shared masking does not yet hide audio or video.
SDK Support
Support for the image and document settings differs by SDK: Python enforces the size limit and can externalize to a
blob uploader; JavaScript enforces the size limit and redacts oversized images to "__REDACTED__"; Java and Go apply
the hide flags only.
Feedback
Annotation and evaluation explanations and metadata can contain sensitive data and MUST follow the same masking and access policies as other span content.