Commit graph

14 commits

Author SHA1 Message Date
Rohan Mehta
5727a1c73a
Example for streaming guardrails (#505)
An example for the question in the issue attached - how to run
guardrails during streaming.

Towards #495.
2025-04-14 12:40:41 -04:00
Daniele Morotti
e04d87cb1f
Add extra request parameters extra_query and extra_body (#500)
Added the possibility to pass `extra_query` and `extra_body` parameters
when sending a request.
In this implementation I added the attributes to `ModelSettings` as
suggested by @rm-openai in #487 .

I'll be happy to add some tests if you have any suggestions.
2025-04-14 10:37:00 -04:00
Ddper
8ded8a9981
add overwrite mechanism for stream_options (#465)
fix issue https://github.com/openai/openai-agents-python/issues/442

below is an example to overwrite include_usage


```
    result = Runner.run_streamed(
        agent,
        "Write a haiku about recursion in programming.",
        run_config=RunConfig(
            model_provider=CUSTOM_MODEL_PROVIDER,
            model_settings=ModelSettings(include_usage=True)
        ),
    )
```
2025-04-10 16:54:00 -04:00
Rohan Mehta
2bcc864b81
Don't send the "store" param unless its hitting OpenAI (#455)
Summary: See #443. Causes issues with Gemini.

Test Plan: Tests. Also tested with Gemini to ensure it works.
2025-04-07 19:13:08 -04:00
Suveen Ellawela
07a627e8eb
Add reasoning parameter to ModelSettings (#388)
fixes #189 

@rm-openai Would really appreciate if this can get a quick review.

---------

Co-authored-by: Rohan Mehta <rm@openai.com>
2025-04-03 19:35:59 -04:00
Drew Youngwerth
0110f3ad96
Add metadata to ModelSettings (#431) 2025-04-03 17:50:24 -04:00
Rohan Mehta
bf302c574c
Use "{}" instead of empty string for arguments (#422) 2025-04-02 12:27:42 -04:00
Steven Heidel
aad8accc86
Expose the "store" parameter through ModelSettings (#357)
Closes https://github.com/openai/openai-agents-python/issues/173

This will also set stored completions to True by default, encouraging a
best practice.
2025-03-26 19:01:28 -04:00
Raduan77
e9f6d08260 fix typos in src/ 2025-03-20 11:24:08 +01:00
Rohan Mehta
8c9974bc90 Fix breaking changes from openai 1.66.2 2025-03-19 12:30:45 -04:00
Rohan Mehta
2302b478af Fix streaming in chat completions 2025-03-12 17:17:07 -07:00
Rohan Mehta
fde49cfcf7 Add max_tokens and documentation to model settings 2025-03-12 13:35:10 -07:00
Muhammad Junaid
51d79bf141 fix: support assistant role in message conversion
- The _Converter.items_to_messages method was incorrectly rejecting 'assistant'
as a valid role in conversation messages, causing runtime errors when processing
standard chat completion message formats.
- This fix enables proper handling of
complete conversation contexts that include both user and assistant messages.
2025-03-12 21:10:03 +05:00
Rohan Mehta
aaec57a426 Initial commit 2025-03-11 09:42:28 -07:00