Python: Add max reasoning effort option

[Brian Caswell (demoray)]

Motivation & Context

Current OpenAI reasoning models support max as a distinct reasoning-effort value, but ReasoningOptions rejects it during static type checking. This prevents callers from using the provider-supported value without weakening or duplicating the options type.

Description & Review Guide

• What are the major changes? Added max to the ReasoningOptions.effort literal.
• What is the impact of these changes? Callers can type-check OpenAI Responses requests that use reasoning.effort="max". Request forwarding is unchanged and already preserves the value.
• What do you want reviewers to focus on? Confirm that the provider-specific type accepts the documented value without adding model-specific runtime validation.

Related Issue

Fixes #8856

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR is linked to an issue and there is no other open PR for this issue (see Related Issue above).
• This is not a breaking change. If it is a breaking change, add the breaking change label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.

[Copilot]

Copilot review overview

🟡 Changes recommended

The linked issue also requires publicly exporting ReasoningOptions, which remains unavailable from the package API.

Review effort: Balanced
Findings: 1

Open (1)

• Expose ReasoningOptions through the public package API · New

What changed in this PR

Adds OpenAI’s max reasoning-effort value to Python type checking.

Changes:

• Extends ReasoningOptions.effort with "max".

File	Description
python/​packages/​openai/​agent_framework_openai/​_chat_client.py	Adds the max effort literal.

---

💡 Add a code-review agent skill for context-aware, tailored reviews. Learn more in the docs.

[Brian Caswell (demoray)]

As the issue creator, I decided that I would not implement that change as this is a larger change to the AI than what is specifically needed.