Python: Refactoring and fix bug. AuthorRole instead of string literals.

[stefan521]

Motivation and Context

There's an enum called AuthorRole. I replaced string literals with the enum values. PyCharm highlights this in some cases: Expected type 'AuthorRole', got 'str' instead

I also fixed a bug in function_invocation_filters_stream.py where the argument name was wrong. author="assistant" instead of role="assistant"

Description

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]

LGTM

[moonbox3]

Hi @stefan521, could you resolve the one file conflict, please? Thanks!

[markwallace-microsoft]

Python 3.10 Test Coverage Report •

File	Stmts	Miss	Cover	Missing
semantic_kernel/connectors/ai/ollama/services
ollama_chat_completion.py	67	6	91%	56, 94, 116, 133, 167, 188
semantic_kernel/connectors/ai/open_ai/services
open_ai_chat_completion_base.py	219	96	56%	97, 101, 121, 146–150, 174, 178, 182, 198–203, 220–248, 251–262, 277–284, 295–303, 319–326, 347, 355, 361–364, 376–379, 410, 449, 454, 459–464, 468–475, 479–491, 513, 523–534
semantic_kernel/contents
function_result_content.py	57	12	79%	50, 55, 66, 81, 93, 107, 112, 119–123
TOTAL	6125	716	88%

Python 3.10 Unit Test Overview

Tests	Skipped	Failures	Errors	Time
1433	1 💤	0 ❌	0 🔥	23.846s ⏱️

[stefan521]

Hi @moonbox3 , thanks for reviewing! I've solved the conflicts.

[eavanvalkenburg]

@stefan521 sorry, I think I wasn't clear enough, I like that most tests run with AuthorRole... but there need to be some with a str (one per type) so that we know both ways of creating them work!

[stefan521]

@eavanvalkenburg got it! I’ll update the PR tonight. Thanks for reviewing!