Support xhigh/max/other reasoning efforts + fastmcp 3.x - #27
Merged
Conversation
Copilot started reviewing on behalf of
Tuhin Kundu (TuhinKundu)
September 1, 2026 07:10
View session
There was a problem hiding this comment.
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
ReasoningEfforttype (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
xhighis 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.
12 tasks
Tuhin Kundu (TuhinKundu)
force-pushed
the
tuhinkundu/support_xhigh
branch
from
September 1, 2026 07:24
faa959a to
5287421
Compare
Tuhin Kundu (TuhinKundu)
marked this pull request as ready for review
September 1, 2026 08:23
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.
Tuhin Kundu (TuhinKundu)
force-pushed
the
tuhinkundu/support_xhigh
branch
from
September 1, 2026 21:26
5287421 to
36695ae
Compare
Nico (s91323)
approved these changes
Sep 2, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds
xhigh | maxand 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 temporaryxhigh -> high -> xhighvalidation workaround.It also constrains FastMCP to the supported 3.x series. Fresh CI environments with fastmcp 4.x failing github unit tests.
Testing
uv run pre-commit run --all-files