Answer: Telemetry is structural by default and content your agent reads and writes is not recorded by default; content is only added by opt-in variables such as OTEL_LOG_USER_PROMPTS=1, OTEL_LOG_TOOL_DETAILS=1, OTEL_LOG_TOOL_CONTENT=1, and OTEL_LOG_RAW_API_BODIES, which should be left unset unless your observability pipeline is approved to store the data your agent handles. Status: Confirmed Entry: tool/claude-code/privacy-and-data/control-sensitive-data-exports Revision: 1 Digest: sha256:405b6a767163a9b8 (changes whenever the content changes) Timeline: Created: 2026-11-13T12:06:48Z Last changed: 2026-11-13T12:06:48Z Last verified: 2026-11-20T12:16:54Z Next check: 2026-11-21T12:16:54Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Default behavior | The content your agent reads and writes is not recorded by default. | [1] | 2026-11-20 Prompt logging variable | OTEL_LOG_USER_PROMPTS=1 | [1] | 2026-11-20 Tool details variable | OTEL_LOG_TOOL_DETAILS=1 | [1] | 2026-11-20 Tool content variable | OTEL_LOG_TOOL_CONTENT=1 | [1] | 2026-11-20 Raw API bodies variable | OTEL_LOG_RAW_API_BODIES | [1] | 2026-11-20 Recommendation | Leave these unset unless your observability pipeline is approved to store the data your agent handles. | [1] | 2026-11-20 Sources: [1] Anthropic. "Observability with OpenTelemetry". https://code.claude.com/docs/en/agent-sdk/observability.md Role: primary. Accessed: 2026-11-20T12:16:54Z Quote: "The content your agent reads and writes is not recorded by default." (Supports: Default behavior) Quote: "`OTEL_LOG_USER_PROMPTS=1`" (Supports: Prompt logging variable) Quote: "`OTEL_LOG_TOOL_DETAILS=1`" (Supports: Tool details variable) Quote: "`OTEL_LOG_TOOL_CONTENT=1`" (Supports: Tool content variable) Quote: "`OTEL_LOG_RAW_API_BODIES`" (Supports: Raw API bodies variable) Quote: "Leave these unset unless your observability pipeline is approved to store the data your agent handles." (Supports: Recommendation) Published: 2026-11-20T10:36:10Z Snapshot SHA-256: 01e682cd9021a18dc9d162abc2354c4eda3478f2879c1666cd438ff23100515d (captured 2026-11-13T03:02:50Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T12:06:48Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:16:54Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:16:54Z Last attempt: 2026-11-20T12:16:54Z Notes and limitations: Extracted automatically from a single official source (section "Control sensitive data in exports"). Related: https://latestn.com/tool/claude-code/privacy-and-data/data-training-commercial-terms Does Anthropic train generative models on code or prompts sent to Claude Code under commercial terms like Team, Enterprise, or API? https://latestn.com/tool/claude-code/privacy-and-data/data-training-consumer-plans Does Anthropic train models on my Claude Code data if I'm on a Free, Pro, Max, or Ultra plan? https://latestn.com/tool/claude-code/privacy-and-data/features-disabled-under-zdr Which Claude Code features are disabled under Zero Data Retention? https://latestn.com/tool/claude-code/privacy-and-data/checkpoint-snapshot-retention How long does Claude Code keep checkpoint file snapshots before they are deleted? https://latestn.com/tool/claude-code/privacy-and-data/clear-local-data How do I clear local Claude Code application data? https://latestn.com/tool/claude-code/privacy-and-data/code-review-data-access What can a Claude Code Code Review access during a review? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T12:06:48Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-code/privacy-and-data/control-sensitive-data-exports/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/claude-code/privacy-and-data/control-sensitive-data-exports POST: https://latestn.com/dispute/tool/claude-code/privacy-and-data/control-sensitive-data-exports with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-code/privacy-and-data/control-sensitive-data-exports?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I control sensitive data in Claude Agent SDK OpenTelemetry exports? Revision 1, last verified 2026-11-20T12:16:54Z. https://latestn.com/tool/claude-code/privacy-and-data/control-sensitive-data-exports (accessed 2026-11-21T10:01:09Z). @misc{LatestN_tool_claude_code_privacy_and_data_control_sensitive_data_exports_r1, title = {How do I control sensitive data in Claude Agent SDK OpenTelemetry exports?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-code/privacy-and-data/control-sensitive-data-exports}}, note = {Revision 1; digest sha256:405b6a767163a9b8; last verified 2026-11-20T12:16:54Z; accessed 2026-11-21T10:01:09Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/claude-code/privacy-and-data/control-sensitive-data-exports