Add suppress_invoke_agent_input option to OpenAI trace processor

[Copilot]

SDK parity with Node.js PR microsoft/Agent365-nodejs#121. Adds option to suppress LLM prompt data in InvokeAgent scopes while preserving other telemetry.

Changes

• OpenAIAgentsTraceProcessor: Added suppress_invoke_agent_input parameter (defaults to False)

  • Detects InvokeAgent scope by checking parent span's GEN_AI_OPERATION_NAME_KEY attribute
  • Conditionally filters GEN_AI_INPUT_MESSAGES_KEY for Generation/Response spans when inside InvokeAgent scope
  • Helper method _should_suppress_input(span) encapsulates the detection and suppression logic

• OpenAIAgentsTraceInstrumentor: Accepts and forwards suppress_invoke_agent_input kwarg to processor

• Tests: Added unit tests for configuration validation and suppression behavior

Implementation Details

The implementation checks if a span's parent has an operation name matching INVOKE_AGENT_OPERATION_NAME by looking up the parent span in the existing _otel_spans dictionary and inspecting its attributes. This approach avoids the need for separate state tracking.

Usage

instrumentor = OpenAIAgentsTraceInstrumentor()
instrumentor.instrument(suppress_invoke_agent_input=True)

When enabled, input messages are suppressed only for spans within InvokeAgent scopes. Spans outside these scopes continue recording input messages normally. Output messages and all other attributes remain unaffected.

---

Parity source: microsoft/Agent365-nodejs#121 by @fpfp100

Original prompt

---

This section details on the original issue you should resolve

<issue_title>[SDK Parity] Python for PR microsoft/Agent365-nodejs#121</issue_title>
<issue_description>## SDK Parity Update Required

This issue was automatically created by the AI-First Polling workflow to maintain SDK parity.

Source PR Information

Original PR: microsoft/Agent365-nodejs#121 - Add option to auto instrumentation to prevent sending the LLM [FILTERED] …
PR URL: microsoft/Agent365-nodejs#121
PR Author: @fpfp100

PR Description

[Node.js SDK] Add option to auto instrumentation to prevent sending the LLM [FILTERED] on InvokeAgent scopes.

---

Parity Task

Changes detected in: Node.js/TypeScript SDK
Target SDK: Python

Action Required

Please apply the changes described in the original PR (microsoft/Agent365-nodejs#121) to the Python SDK to maintain feature parity across all SDKs.

Before implementing:

• First, check if this feature already exists in the Python SDK
• If the feature is already implemented, close this issue with the wontfix label and add a comment explaining that parity already exists

For bug fixes (IMPORTANT):

• Bug fixes require extra caution - only act if the same bug exists in the Python SDK
• Carefully analyze whether the bug described in the original PR replicates in the target platform
• If the bug does NOT exist in the Python SDK, close this issue with the wontfix label and explain that the bug is not present
• Stay strictly in context - only fix the specific bug described, do not make additional changes or "improvements"
• Do not port bug fixes that are specific to the source SDK's language or platform constraints

When creating the PR for this implementation:

• Assign the PR to @fpfp100 (the author of the original PR)
• Reference this issue in the PR description
• Ensure the PR description explains what parity changes were made

Implementation Guidelines for Python

When implementing this feature in the Python SDK:

• Review existing code in python/libraries/ to understand the codebase structure and patterns
• Follow the coding style, naming conventions, and architectural patterns used in the Python SDK
• Check for configuration files (e.g., pyproject.toml, .flake8, mypy.ini) that define coding standards
• Ensure your implementation is consistent with existing SDK components
• Include appropriate tests following the testing patterns in the Python SDK

Related Information

• Workflow Run: https://github.com/microsoft/AI-First-Development/actions/runs/20860864857
• Trigger: Polling workflow
• Detected: 2026-01-09 18:01:11 UTC

---

This is an automated issue. Please close with wontfix label if parity is not needed.</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes [SDK Parity] Python for PR microsoft/Agent365-nodejs#121 #110

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

[sergioescalera]

🤖 Auto-Assignment

This PR was automatically assigned to @fpfp100 for review.

Reason: This is a parity implementation for issue #110, which was triggered by @fpfp100's original PR (microsoft/Agent365-nodejs#121).

Next Steps:

• @fpfp100: Please review this implementation to ensure it matches your intent
• Validate the parity changes are correct and complete
• Approve and merge when satisfied

---

Automated by AI-First Polling Workflow

[juliomenendez]

Can we use a different way of detecting an invoke agent span?

[sergioescalera]

@copilot can we use a different tactic to detect invoke agent spans? one that does not require keeping track all active agent spans in a dictionary?

For example:

core/trace_processor/span_processor.py

operation_name = ... // get operation name from attributes
is_invoke_agent = False
if operation_name == INVOKE_AGENT_OPERATION_NAME:
is_invoke_agent = True

[Copilot]

Refactored the implementation to check the parent span's operation name instead of maintaining a tracking dictionary. The new approach:

1. Checks if span.parent_id exists
2. Retrieves the parent span from self._otel_spans
3. Checks if the parent's GEN_AI_OPERATION_NAME_KEY attribute equals INVOKE_AGENT_OPERATION_NAME

This eliminates the need for the _active_agent_spans dictionary and associated tracking logic in on_span_start and on_span_end.

Changes in commit cff467f.