agent-framework

mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00

Files

T

claude89757 f8c84d4ee6 Python: Fix: Add system_instructions to ChatClient LLM span tracing (#3164 )

* Fix: Add system_instructions to ChatClient LLM span tracing

- Add system_instructions parameter to _capture_messages() calls in
  _trace_get_response() and _trace_get_streaming_response()
- Extract instructions from chat_options in kwargs
- Add unit tests to verify system_instructions are captured correctly

When using ChatClient with ChatOptions.instructions, the OpenTelemetry
LLM span was missing system messages in gen_ai.input.messages and the
gen_ai.system_instructions attribute was not being set.

This fix aligns the ChatClient-level tracing with the Agent-level
tracing which already correctly passes system_instructions.

Fixes #3163

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Add edge case tests for system_instructions

- Add test for empty string instructions (should not set attribute)
- Add test for list-type instructions (verify multiple items captured)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Simplify: use options.get('instructions') directly instead of kwargs.get('chat_options')

Addresses reviewer feedback:
- Removed unnecessary chat_options variable from kwargs
- Directly access instructions from the options parameter
- Updated tests to use dict syntax for options (TypedDict convention)

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

f8c84d4ee6 · 2026-01-20 14:04:31 +00:00

History

azure

Python: Fixed Azure chat client for asynchronous filtering (#3260 )

2026-01-19 12:49:23 +00:00

core

Python: Fix: Add system_instructions to ChatClient LLM span tracing (#3164 )

2026-01-20 14:04:31 +00:00

openai

Create/Get Agent API - fixes and example improvements (#3246 )

2026-01-16 04:36:34 +00:00

workflow