sora 44303d8953 Allow resume when only sample limit changes, and keep CSV rows across runs. ...

Identity fingerprints ignore limit so later larger runs reuse cached predictions. Summary tables upsert by benchmark and take agent TTFT/latency from the report's per-request stats.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-09-03 03:54:26 +00:00

..

case

fix: terminal_bench_v2_1 result collection, apt mirror, and restore run.py env var

2026-08-05 03:56:44 +00:00

fingerprint

stop tracking fingerprint markdown docs (keep files on disk)

2026-09-03 02:38:35 +00:00

images_load

Preload Pier uv and mini-swe-agent wheels so DeepSWE sandbox builds skip GitHub.

2026-09-02 09:44:17 +00:00

tests

Allow resume when only sample limit changes, and keep CSV rows across runs.

2026-09-03 03:54:26 +00:00

cleanup_docker_images.sh

feat: add docker image cleanup script for benchmark images

2026-08-05 05:38:20 +00:00

collect_results.py

Allow resume when only sample limit changes, and keep CSV rows across runs.

2026-09-03 03:54:26 +00:00

diagnose_swe_images.py

Optimize SWE-bench build_images: skip make_test_spec when images are pre-loaded

2026-07-27 08:46:15 +00:00

load_swe_images.sh

update benchmark suites and evaluation docs

2026-08-18 03:19:01 +00:00

perf_backup.py

chore: update evalscope runner, thinking config and webui

2026-07-31 02:36:51 +00:00

pull_swe_bench_images.py

feat(pull_swe_bench_images): support comma-separated --dataset

2026-07-23 02:34:49 +00:00

run.py

Allow resume when only sample limit changes, and keep CSV rows across runs.

2026-09-03 03:54:26 +00:00

save_swe_images.sh

Add SWE image save/load scripts and update Docker config docs

2026-07-24 06:27:49 +00:00

set.sh

docs: add resource prep section and sync docker/bash helpers

2026-07-23 02:18:15 +00:00