Skip to content

Support xhigh/max/other reasoning efforts + fastmcp 3.x - #27

Merged
Tuhin Kundu (TuhinKundu) merged 1 commit into
mainfrom
tuhinkundu/support_xhigh
Sep 2, 2026
Merged

Support xhigh/max/other reasoning efforts + fastmcp 3.x#27
Tuhin Kundu (TuhinKundu) merged 1 commit into
mainfrom
tuhinkundu/support_xhigh

Conversation

@TuhinKundu

@TuhinKundu Tuhin Kundu (TuhinKundu) commented Sep 1, 2026

Copy link
Copy Markdown
Contributor

Summary

Adds xhigh | max and others as supported reasoning-effort values for AOAI chat and response configurations. This came up while reviewing the ThinkingBox integration in huggingface/OpenEnv#1092. Native support lets that adapter remove its temporary xhigh -> high -> xhigh validation workaround.

It also constrains FastMCP to the supported 3.x series. Fresh CI environments with fastmcp 4.x failing github unit tests.

Testing

  • Fresh Python 3.12 environment: 389 tests passed with FastMCP 3.4.7
  • uv run pre-commit run --all-files
  • Five-task x3 OpenEnv-TB AML smoke with GPT-5.4 xhigh: 15 terminal rows, zero system errors

Copilot AI lite review requested due to automatic review settings September 1, 2026 07:10

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds xhigh as an accepted reasoning_effort value across Azure OpenAI Chat Completions (aoai) and Responses (aoai_responses) configs, and verifies it’s forwarded into request payloads.

Changes:

  • Introduces a shared ReasoningEffort type (low|medium|high|xhigh|None) and applies it to both AOAI config models.
  • Updates AOAI Responses session typing to reuse the shared reasoning-effort type.
  • Adds unit tests ensuring xhigh is accepted by config validation and appears in request payloads for both APIs; updates docs to list supported values.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated no comments.

Show a summary per file
File Description
thinkingbox/common/config_types.py Adds shared ReasoningEffort alias and uses it for both AOAI config models’ reasoning_effort.
thinkingbox/common/aoai_responses_session.py Reuses ReasoningEffort for the internal responses request helper typing.
tests/test_aoai_session.py Adds config-validation and chat-completions payload assertions for reasoning_effort="xhigh".
tests/test_aoai_responses_session.py Adds config-validation and responses payload assertions for reasoning_effort="xhigh".
docs/llm_endpoint_config.md Documents xhigh alongside existing supported reasoning-effort values.

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

Accept and forward provider-defined reasoning-effort strings for AOAI Chat Completions and Responses configurations, including xhigh. Keep fresh installations on the supported FastMCP 3.x API series.

Validated with schema and outgoing-payload tests.
@TuhinKundu Tuhin Kundu (TuhinKundu) changed the title Support xhigh reasoning effort Support xhigh/other reasoning effort Sep 1, 2026
@TuhinKundu Tuhin Kundu (TuhinKundu) changed the title Support xhigh/other reasoning effort Support xhigh/other reasoning efforts Sep 1, 2026
@TuhinKundu Tuhin Kundu (TuhinKundu) changed the title Support xhigh/other reasoning efforts Support xhigh/max/other reasoning efforts Sep 1, 2026
@TuhinKundu Tuhin Kundu (TuhinKundu) changed the title Support xhigh/max/other reasoning efforts Support xhigh/max/other reasoning efforts + fastmcp 3.x Sep 2, 2026
@TuhinKundu
Tuhin Kundu (TuhinKundu) merged commit 40c1212 into main Sep 2, 2026
6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants