feat: add audio-input-prefer routing strategy - #131
Merged
Conversation
Prefer audio-capable models when metadata requires_audio / audio_input / audio is truthy, using audio_models allowlist, known-map audio capability (gpt-5* / gemini*), or name heuristics for GPT-5.5 / Claude Sonnet 4.6 / Gemini 3.x / Kimi K2. Co-authored-by: shunqil <shunqil@usc.edu>
cursor Bot
pushed a commit
that referenced
this pull request
Aug 28, 2026
Rebased onto main after #131 audio-input-prefer; keeps audio on main and re-inserts only web-search-prefer into shared router files. Co-authored-by: shunqil <shunqil@usc.edu>
cursor Bot
pushed a commit
that referenced
this pull request
Aug 28, 2026
Rebased onto main after #131 audio-input-prefer; keeps audio on main and re-inserts only computer-use-prefer into shared router files. Co-authored-by: shunqil <shunqil@usc.edu>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds
audio-input-prefercapability routing (OpenRouter/LiteLLM-style) for speech/audio requests — gap vs existing multimodal/tool/streaming/long-context prefer strategies.Stack
Routes across GPT-5.5 / Claude Sonnet 4.6 / Gemini 3.x / Kimi K2 catalogs
Suggested repo description / topics
llm-router,openai,anthropic,gemini,kimiTest plan