Python: Don't return code output via on_intermediate_msg callback

[moonbox3]

Motivation and Context

Current, while using an OpenAIAssistantAgent, we are returning code output via the on_intermediate_message callback. This shouldn't be happening right now, as all other agents return code via TextContent with a metadata {"code": True} key-value pair in the dictionary.

Description

• Closes Python: Bug: Assistant Agent puts code interpreter streaming chunks to on_intermediate_message #12956

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 😄

[moonbox3]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
agents/open_ai
assistant_thread_actions.py	338	57	83%	107, 110, 116, 195, 197, 236–242, 416, 474, 487, 500, 599–600, 602–603, 609–610, 612–613, 615–618, 620–621, 623–624, 626–627, 641–645, 648–650, 697, 699–700, 704–708, 710–711, 725–726, 797, 802, 834
TOTAL	27111	4728	82%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
3715	22 💤	0 ❌	0 🔥	1m 39s ⏱️