Add reasoning parameter handling to completion extras transformation #13695
+224
−2
Conversation
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
- Add _handle_reasoning_parameters() method to LiteLLMResponsesTransformationHandler: * Promotes reasoning_effort from extra_body to top-level parameter * Sets default reasoning_effort="medium" for reasoning-capable models * Uses supports_reasoning() to detect reasoning-capable models - Enhance transform_request() to call reasoning parameter handler - Add auto-routing logic in main.py for reasoning-capable models - Add comprehensive test suite for reasoning routing and transformation - Enable reasoning summaries by default for reasoning models
- Rename test_gpt5_reasoning_routing.py -> test_reasoning_routing.py - Move from tests/ to tests/llm_translation/ for better organization - Update class names to be more descriptive: * TestGPT5ReasoningRouting -> TestReasoningRouting * TestTransformationLayerReasoningHandling -> TestReasoningParameterTransformation - Keep all test functionality intact, just better organized
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
hi @oabdellatif can you help me understand - what is the issue you are trying to solve here? |
|
Hi @krrishdholakia, the main goal is to enable reasoning summaries by default for OpenAI models through tools like Aider. There’s no way to configure this currently:
The rationale is that reasoning-capable models should show reasoning summaries by default, and the auto-routing is one way to accomplish that. I can create an issue for further discussion. |
|
Created #13780 for clarification |
There was a problem hiding this comment.
move mock tests inside test_litellm/ to ensure they run on this PR
There was a problem hiding this comment.
bump on this? @oabdellatif
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.
Title
Add reasoning parameter handling to completion extras transformation
Relevant issues
N/A
Pre-Submission checklist
Please complete all items before asking a LiteLLM maintainer to review your PR
tests/litellm/directory, Adding at least 1 test is a hard requirement - see detailsmake test-unitType
🆕 New Feature
Changes
Enhanced
/chat/completions→litellm.responses()transformation:_handle_reasoning_parameters()method toLiteLLMResponsesTransformationHandlerextra_body.reasoning_effortto top-levelreasoning_effort="medium"for reasoning-capable models when not providedmain.pyKey benefits:
reasoning_effortrequired)