Derive LiteLLM reasoning capabilities from local metadata - #2240
Open
Selene29 wants to merge 1 commit into
Open
Conversation
Catalog construction called reasoning helpers for every model and offered a fixed low/medium/high set. Read the loaded model_cost metadata when building model options, derive effort choices from explicit levels and capability flags, and filter known non-text model categories. Honor explicit negative capability metadata and thinking-always-on constraints. Prefer local metadata for runtime validation, retaining the existing capability lookup fallback when metadata is absent. Validation: - 6 LiteLLM provider tests passed with SDK calls mocked. - Ruff lint/format checks and git diff --check passed.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Problem
LiteLLM discovery offered a fixed
low,medium, andhighset for reasoning models, while execution used a separate capability lookup. The two paths could disagree about which effort values a model accepts.Catalog construction also consulted per-model helpers and included non-text model categories. This change keeps enumeration local, filters those categories, and treats explicit negative or always-on metadata as authoritative.
Testing