Kritin Vongthongsri 4598fe8eb7 Merge pull request #3417 from ykocaogullar/main ...

feat(dataset): send the pulled dataset version with test runs

2026-10-09 17:15:09 -07:00

..

test_benchmarks

fix(benchmarks): correct silent answer mis-scoring in MathQA, DROP, and BBH

2026-07-18 15:28:21 +05:00

test_confident

fix(confident): respect CONFIDENT_REGION setting in backend routing (#3041)

2026-08-21 16:38:16 +08:00

test_core

Merge pull request #3417 from ykocaogullar/main

2026-10-09 17:15:09 -07:00

test_docs

.

2026-04-25 18:20:32 +08:00

test_integrations

Update json

2026-09-06 22:29:44 +08:00

test_metrics

rename to provider_transcript

2026-10-05 10:37:18 +05:30

test_models

Fix judges

2026-09-30 01:25:11 +08:00

test_templates

New trajectory evals

2026-09-30 02:34:09 +08:00

__init__.py

skip confident tests if no key on CI

2026-06-01 23:43:03 +05:30

test_agent_loop_detection.py

fix: harden cycle detection with input_hash, add SequenceMatcher stagnation signal, document limitations

2026-05-12 18:39:20 +05:30