Repository navigation
WIP: Judge tuning (5/6): Resolve OpenRouter reference prices - #139
Closed
ErlisLushtaku wants to merge 9 commits into
Closed
ErlisLushtaku wants to merge 9 commits into
ErlisLushtaku wants to merge 9 commits into
Conversation
This was referenced Oct 9, 2026
…judge-tuning-reference-prices # Conflicts: # judgearena/pricing.py # judgearena/tuning/runner.py # tests/test_tuning.py
ErlisLushtaku
changed the title
…judge-tuning-reference-prices
…judge-tuning-reference-prices
…judge-tuning-reference-prices # Conflicts: # tests/test_tuning.py
…judge-tuning-reference-prices # Conflicts: # tests/test_tuning.py
Collaborator
Author
|
The reference-price lookup is now included in #136 with its configuration example and documentation. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
WIP. Not ready for review yet.
Adds OpenRouter catalog resolution to the shared pricing module for every judge provider, including local vLLM models. Explicit input/output overrides take precedence. New cost-objective sessions fetch free catalog metadata when needed and use the cached catalog offline. Matching uses the Hugging Face ID first, then the model-name suffix.
Resume and helper workers reuse the session's saved prices. Unlisted models need an override. Agreement-only searches skip price resolution. Cached catalogs use the current format; incompatible historical files produce refresh-or-override guidance.
Part 5 of 6, stacked on #133 and followed by #136. All remain WIP.