Python: Fixed sending "text" parameter to OpenAI Responses API

[ymuichiro]

Summary

Fixed an issue where the text parameter was missing in requests to the OpenAI Responses API.

Changes Made

Modified the ResponsesAgentThreadActions._generate_options() method to correctly handle the text parameter:

• Added to the options dictionary only if text is not None.
• Not added if it is an empty dict (the default value).
• This ensures that only explicitly set text parameters are sent to the API.

Fix Location

File: semantic_kernel/agents/open_ai/responses_agent_thread_actions.py

Before:

options = {
    "model": merged.get("model"),
    "top_p": merged.get("top_p"),
    "temperature": merged.get("temperature"),
    "truncation": truncation,
    "metadata": merged.get("metadata"),
    "max_output_tokens": max_output_tokens,
    "parallel_tool_calls": parallel_tool_calls,
}

After:

options = {
    "model": merged.get("model"),
    "top_p": merged.get("top_p"),
    "temperature": merged.get("temperature"),
    "truncation": truncation,
    "metadata": merged.get("metadata"),
    "max_output_tokens": max_output_tokens,
    "parallel_tool_calls": parallel_tool_calls,
}

# Add text option if it exists
if merged.get("text") is not None:
    options["text"] = merged.get("text")

• Closes Python Bug: The text parameter was missing when sending to the OpenAI Responses API. #13281

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the SK Contribution Guidelines and the pre-submission formatting script raises no violations
• All unit tests pass, and I have added new tests where possible
• I didn't break anyone 😄

[Copilot]

Pull Request Overview

This PR fixes a bug where the text parameter was not being included in requests to the OpenAI Responses API. The fix ensures that when a text parameter is explicitly provided, it is correctly added to the options dictionary sent to the API.

• Added conditional logic to include the text parameter in API requests only when it is explicitly set
• Prevents sending None or default empty dict values to the API

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[markwallace-microsoft]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
agents/open_ai
responses_agent_thread_actions.py	440	126	71%	177, 194, 207, 218–219, 227, 234, 247, 407–408, 410, 424, 429, 436, 451–452, 462, 469, 471–472, 481, 488, 490–491, 502, 509, 511–512, 522, 529, 534–535, 539, 551, 585–587, 590, 608–609, 620–622, 626, 630–631, 635–637, 648–650, 672, 674–675, 682–683, 685–686, 688, 690–691, 693–694, 792, 797, 805–806, 808, 814, 819, 824–826, 832–834, 839–840, 842–847, 849, 853–854, 856, 860, 864, 869–870, 875, 878–879, 939–942, 965, 1011–1014, 1055–1056, 1060–1062, 1064, 1089–1090, 1092–1096, 1098, 1108–1109, 1117, 1121, 1128, 1134, 1215
TOTAL	27301	4560	83%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
3759	23 💤	0 ❌	0 🔥	1m 42s ⏱️

[moonbox3]

@ymuichiro are there any unit tests we need to add or update?

[ymuichiro]

@moonbox3

I don’t think any test changes are needed this time 😃

Adding unit tests for this case would be excessive — the logic is simply to pass the text parameter to the subsequent process if it exists, and skip it if it doesn’t.

It’s possible to implement a focused test to check whether text is passed correctly, but that would require using several surrounding functions and essentially become more like an integration test.