Repository navigation
feat: add Jev and Clef support ticket triage benchmark - #15
Merged
Merged
Conversation
Triage Bitext support tickets with Jev, Clef and Clef-flash through OpenRouter's Decisions API. Includes a resumable benchmark, a report on accuracy, latency, cost, thresholds, calibration and agreement, and a no-network test suite.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
Adds
Jev-and-clef/: support ticket triage with the System One decision models Jev, Clef and Clef-flash on OpenRouter's Decisions API. A 100-ticket Bitext sample is benchmarked on accuracy, latency, cost, auto-route thresholds, calibration and model agreement. Results are inJev-and-clef/results/report.md.Type of change
Checklist
README.md(from.github/MODULE_README_TEMPLATE.md).README.mdunder the right area, plus rows in the Module map and Prerequisites at a glance tables. Not done yet. Follow-up..envis not committed..env.examplehas names only.Tests:
uv run pytest(49 passed),mypy --strict, ruff and black pass on Python 3.13.