feat!: AI wrappers and MCP send personless as a per-event option

[eli-r-ph]

💡 Motivation and Context

AI wrappers and MCP instrumentation fall back to a trace, run or session ID when the caller gives no distinct ID. A person profile for that ID is always wrong, so these integrations turn person processing off. Until now they did it with the legacy $process_person_profile property. As of the previous PR in this stack, a property loses to any option, so a global or context option could turn person processing back on for these events.

This PR moves the override to a per-event option, process_person_profile: false. A per-event option beats every lower layer: legacy properties, super_options and context options. before_send can still change it.

Sites:

• the OpenAI, Anthropic and Gemini wrappers: sync and async, response and stream, and embeddings
• LangChain callbacks: trace, span and generation
• the Claude Agent SDK processor and client
• the OpenAI Agents processor
• MCP tool-call and $exception events

Behavior changes:

• A caller's $process_person_profile: true in posthog_properties or MCP custom properties no longer opts a fallback-ID event in. For non-streaming OpenAI, Anthropic and Gemini calls the caller used to win; everywhere else the SDK did. Now the SDK wins everywhere.
• MCP's PostHogCaptureEvent gains an options key. The MCP before_send hook sees it and can change it.
• The OpenAI Agents processor now falls back to the trace ID in one place, _capture_event, instead of at each call site. Span handlers take Optional[str] distinct IDs.

Not in this PR: routing every AI wrapper event through capture_ai. That comes later in the stack.

💚 How did you test it?

• Every site: the existing personless tests now assert options == {"process_person_profile": False} instead of the property. Identified events assert that no options is passed.
• Anthropic: the personless test now runs sync and async, response and stream, with a caller $process_person_profile: true. It covers the async and streaming paths, which no earlier test did.
• Layering, through a real client:
  • an AI event with a context option, a super_options value, a caller option and a legacy property all set to true still sends false
  • a before_send can set it back to true
• MCP, through the real sink and client: the same check for an anonymous event, plus the before_send override.
• Break-on-purpose: each site was reverted in turn, and each reversion failed its test. The reversions:
  • the option dropped in the shared helper
  • caller options placed above the SDK option
  • the processor path
  • the sync and async LLM paths
  • the streaming path
  • each embeddings wrapper
  • LangChain, Claude Agent SDK and OpenAI Agents
  • the OpenAI Agents trace ID fallback
  • the MCP builder
  • the MCP sink dropping options, on both MCP SDK majors
• I ran ruff, mypy (baseline), the strict type smoke, the full pytest suite, the MCP suite against MCP SDK v2, the adapter tests, python -W error -c "import posthog", the public API snapshot and uv lock --check.

📝 Checklist

• I reviewed the submitted code.
• I added tests to verify the changes.
• I updated the docs if needed.
• No breaking change or entry added to the changelog.

If releasing new changes

• Ran sampo add to generate a changeset file

Covered by the existing capture-v1-major changeset; the migration guide lands later in this stack.

🤖 Agent context

Autonomy: Human-driven (agent-assisted)

Written with Cursor (Claude Opus) under the direction of the assignee.

Agreed before implementation:

• AI and MCP set personless as a per-event option after user input, so it overrides user layers
• before_send can still change it
• it applies only when there is no real distinct ID

Agent calls worth review:

• _capture_ai_event takes a personless flag and merges the option over any caller options. No wrapper passes caller options today.
• In the OpenAI Agents processor, _capture_event takes the fallback ID from the event's $ai_trace_id. Every handler sets it. If one did not, the existing "unknown" fallback applies.
• MCP events stay on capture(). They are not $ai_* events, so capture_ai does not apply.

[github-actions]

posthog-python Compliance Report

Date: 2026-10-10T23:40:21.591508+00:00
Duration: 246846ms

✅ All Tests Passed!

116/116 tests passed

---

Capture_V1 Tests

✅ 95/95 tests passed

View Details

Test	Status	Duration
Endpoint And Method.Targets V1 Endpoint	✅	514ms
Endpoint And Method.Does Not Use Legacy Endpoints	✅	509ms
Required Headers.Has Authorization Bearer Header	✅	508ms
Required Headers.Has Content Type Json	✅	508ms
Required Headers.Has Posthog Sdk Info Format	✅	509ms
Required Headers.Has Posthog Attempt Header	✅	508ms
Required Headers.Has Posthog Request Id	✅	508ms
Required Headers.Has Posthog Request Timestamp	✅	508ms
Required Headers.Has User Agent	✅	510ms
Body Format.Body Has Created At And Batch	✅	509ms
Body Format.No Api Key In Body	✅	508ms
Body Format.No Sent At In Body	✅	508ms
Event Format.Event Has Required Root Fields	✅	508ms
Event Format.Event Uuid Is Valid	✅	508ms
Event Format.Event Timestamp Is Rfc3339	✅	509ms
Event Format.Non Utc Event Timestamp Is Converted To Utc	✅	513ms
Event Format.Distinct Id Is String	✅	508ms
Event Format.Distinct Id At Root Not Properties	✅	508ms
Event Format.Custom Properties Preserved	✅	509ms
Event Format.Set Properties Preserved	✅	508ms
Event Format.Set Once Properties Preserved	✅	508ms
Event Format.Groups Properties Preserved	✅	509ms
Event Format.Sdk Generates Uuid If Not Provided	✅	508ms
Event Format.Event Has Required Root Fields Batch	✅	511ms
Event Format.Event Uuid Is Valid Batch	✅	511ms
Event Format.Event Timestamp Is Rfc3339 Batch	✅	511ms
Event Format.Distinct Id Is String Batch	✅	511ms
Event Format.Distinct Id At Root Not Properties Batch	✅	511ms
Event Format.Custom Properties Preserved Batch	✅	511ms
Event Format.Set Properties Preserved Batch	✅	511ms
Event Format.Set Once Properties Preserved Batch	✅	511ms
Event Format.Groups Properties Preserved Batch	✅	511ms
Event Format.Sdk Generates Uuid If Not Provided Batch	✅	511ms
Batch Behavior.Multiple Events In Single Batch	✅	513ms
Batch Behavior.Batch Envelope Smoke	✅	513ms
Batch Behavior.Flush With No Events Sends Nothing	✅	505ms
Batch Behavior.Flush At Triggers Batch	✅	1009ms
Batch Behavior.Created At Reflects Batch Creation Time	✅	509ms
Deduplication.Generates Unique Uuids	✅	514ms
Deduplication.Different Events Same Content Different Uuids	✅	510ms
Deduplication.Preserves Uuid On Retry	✅	6517ms
Deduplication.Preserves Timestamp On Retry	✅	6514ms
Deduplication.Preserves Uuid And Timestamp On Batch Retry	✅	6519ms
Deduplication.No Duplicate Events In Batch	✅	514ms
Header Behavior On Retry.Attempt Header Starts At One	✅	509ms
Header Behavior On Retry.Attempt Header Increments On Retry	✅	12516ms
Header Behavior On Retry.Request Id Preserved On Retry	✅	6517ms
Header Behavior On Retry.Different Requests Have Different Request Ids	✅	3018ms
Header Behavior On Retry.Request Timestamp Changes On Retry	✅	6513ms
Response Format Validation.Success Response Has Uuid Keyed Results	✅	509ms
Response Format Validation.Success Response Has Ok For Each Event	✅	512ms
Response Format Validation.Success No Retry After When All Ok	✅	510ms
Response Format Validation.Success Retry After Present When Retry Events	✅	1513ms
Response Format Validation.Success No Retry After When Drop Only	✅	510ms
Response Format Validation.Response Echoes Request Id	✅	509ms
Retry Behavior.Retries On 408	✅	6512ms
Retry Behavior.Retries On 500	✅	6513ms
Retry Behavior.Retries On 503	✅	7515ms
Retry Behavior.Retries On 504	✅	6517ms
Retry Behavior.Retryable Errors Have Retry After	✅	3513ms
Retry Behavior.Respects Retry After On Retryable Error	✅	11521ms
Retry Behavior.Does Not Retry On 400	✅	2511ms
Retry Behavior.Does Not Retry On 401	✅	2511ms
Retry Behavior.Does Not Retry On 402	✅	2512ms
Retry Behavior.Does Not Retry On 413	✅	2511ms
Retry Behavior.Does Not Retry On 415	✅	2512ms
Retry Behavior.Non Retryable Errors Have No Retry After	✅	2511ms
Retry Behavior.Implements Backoff	✅	18527ms
Retry Behavior.Max Retries Respected	✅	18533ms
Partial Batch Handling.Handles 200 Full Success	✅	2511ms
Partial Batch Handling.Handles 200 With All Ok	✅	3515ms
Partial Batch Handling.Does Not Retry Dropped Events	✅	3513ms
Partial Batch Handling.Does Not Retry Limited Events	✅	3513ms
Partial Batch Handling.Prunes Ok Events On Partial Retry	✅	6518ms
Partial Batch Handling.Prunes Dropped Events On Partial Retry	✅	6514ms
Partial Batch Handling.Retries Only Retry Events From Partial	✅	6520ms
Partial Batch Handling.Partial Retry Preserves Uuids	✅	6515ms
Partial Batch Handling.Partial Retry Attempt Header Increments	✅	6516ms
Partial Batch Handling.Partial Retry Request Id Preserved	✅	6519ms
Partial Batch Handling.Respects Retry After On Partial	✅	8517ms
Partial Batch Handling.Unknown Result Treated As Terminal	✅	3513ms
Partial Batch Handling.Mixed Ok Drop Limited No Retry	✅	3516ms
Compression.Sends Gzip Content Encoding	✅	509ms
Compression.No Content Encoding When Disabled	✅	508ms
Compression.Compressed Body Is Decompressible	✅	508ms
Error Handling.Does Not Retry On Unknown 4Xx	✅	2511ms
Event Options.Cookieless Mode Override	✅	508ms
Event Options.Disable Skew Correction Override	✅	509ms
Event Options.Process Person Profile Override	✅	508ms
Event Options.Product Tour Id Override	✅	508ms
Event Options.Unset Options Omitted	✅	509ms
Event Options.Options Override In Batch	✅	511ms
Geoip And Historical Migration.Geoip Disable Injected Into Properties	✅	508ms
Geoip And Historical Migration.Historical Migration Set In Body	✅	508ms
Geoip And Historical Migration.Historical Migration Absent By Default	✅	509ms

Feature_Flags Tests

✅ 17/17 tests passed

View Details

Test	Status	Duration
Request Payload.Request With Person Properties Device Id	✅	9ms
Request Payload.Flags Request Uses V2 Query Param	✅	7ms
Request Payload.Flags Request Hits Flags Path Not Decide	✅	7ms
Request Payload.Flags Request Omits Authorization Header	✅	7ms
Request Payload.Token In Flags Body Matches Init	✅	7ms
Request Payload.Groups Round Trip	✅	7ms
Request Payload.Groups Default To Empty Object	✅	7ms
Request Payload.Disable Geoip False Propagates As Geoip Disable False	✅	7ms
Request Payload.Disable Geoip Omitted Defaults To False	✅	7ms
Request Payload.Flag Keys To Evaluate Contains Only Requested Key	✅	7ms
Request Lifecycle.No Flags Request On Init Alone	✅	3ms
Request Lifecycle.No Flags Request On Normal Capture	✅	507ms
Request Lifecycle.Two Flag Calls Produce Two Remote Requests	✅	11ms
Request Lifecycle.Mock Response Value Is Returned To Caller	✅	7ms
Retry Behavior.Retries Flags On 502	✅	311ms
Retry Behavior.Retries Flags On 504	✅	311ms
Side Effect Events.Get Feature Flag Captures Feature Flag Called Event	✅	509ms

Feature_Flags_Local_Evaluation Tests

✅ 4/4 tests passed

View Details

Test	Status	Duration
Versioned Boolean Matching.Matching Version Missing	✅	53ms
Versioned Boolean Matching.Matching Version 1	✅	52ms
Versioned Boolean Matching.Matching Version 2	✅	52ms
Versioned Boolean Matching.Version Only Reload 1 2 1 2 Missing	✅	27ms

[eli-r-ph]

@greptileai review