We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent e3b0733 commit 02ffbe5Copy full SHA for 02ffbe5
1 file changed
QA.md
@@ -213,6 +213,11 @@ this QA pass (touching benchmark code = regression risk on v1 results):
213
- `benchmarks/aggregate_sweep.py:100` (23→15)
214
- `benchmarks/adapters/multi_swebench.py:100` (17→15)
215
- `benchmarks/diffctx_eval_fn.py:70` (18→15)
216
+- `benchmarks/diffctx_eval_fn.py:241` (19→15)
217
+- `benchmarks/adapters/calibrate.py:73` (25→15) — `evaluate_grid` retry/pool loop
218
+- `benchmarks/adapters/calibrate.py:160` (40→15) — `evaluate_grid_cached`, already
219
+ `# noqa: C901` for ruff (orchestration with timeout/exception/checkpoint dispatch
220
+ does not factor cleanly without behavior change)
221
- `benchmarks/adapters/evaluator.py:49` (32→15)
222
- `scripts/bake_bench_cache.py:72` (16→15)
223
0 commit comments