dsh-eval-guard 0.2.2 → 0.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +91 -13
- package/assets/bomberman/workspace.zip +0 -0
- package/assets/commit0/instance.json +30 -0
- package/assets/commit0/workspace.zip +0 -0
- package/assets/ctf/workspace.zip +0 -0
- package/assets/featurebench/hidden/test_regression.py +690 -0
- package/assets/featurebench/instance.json +16 -0
- package/assets/featurebench/workspace.zip +0 -0
- package/assets/swe-bench-pro/hidden/test.patch +36 -0
- package/assets/swe-bench-pro/instance.json +10 -0
- package/assets/swe-bench-pro/workspace.zip +0 -0
- package/assets/tank/workspace.zip +0 -0
- package/eval/README.md +18 -0
- package/eval/arena/arena/README.md +21 -0
- package/eval/arena/arena/bt.py +104 -0
- package/eval/arena/arena/clock.py +15 -0
- package/eval/arena/arena/core.py +265 -0
- package/eval/arena/arena/run.cmd +24 -0
- package/eval/arena/arena/run.sh +11 -0
- package/eval/arena/arena/schedule.py +79 -0
- package/eval/arena/arena/tournament.py +183 -0
- package/eval/arena/bomberman/bots/README.md +16 -0
- package/eval/arena/bomberman/bots/deepseek-v4.1-flash.cpp +447 -0
- package/eval/arena/bomberman/bots/doubao-seed-2.1.cpp +542 -0
- package/eval/arena/bomberman/bots/glm-5.3.cpp +406 -0
- package/eval/arena/bomberman/bots/gpt-6-astra.cpp +768 -0
- package/eval/arena/bomberman/bots/gpt-6-sol.cpp +444 -0
- package/eval/arena/bomberman/bots/kimi-k3.cpp +432 -0
- package/eval/arena/bomberman/bots/mimo-v2.6-pro.cpp +529 -0
- package/eval/arena/bomberman/bots/opus-5.5.cpp +548 -0
- package/eval/arena/bomberman/bots/qwen-3.8-max.cpp +836 -0
- package/eval/arena/bomberman/tournament/README.md +11 -0
- package/eval/arena/bomberman/tournament/bt.py +56 -0
- package/eval/arena/bomberman/tournament/evaluate.py +199 -0
- package/eval/arena/bomberman/tournament/run.py +79 -0
- package/eval/arena/bomberman/tournament/schedule-2to10.json.gz +0 -0
- package/eval/arena/bomberman/workspace/MANIFEST.json +13 -0
- package/eval/arena/bomberman/workspace/README.md +29 -0
- package/eval/arena/bomberman/workspace/RULES.md +100 -0
- package/eval/arena/bomberman/workspace/baseline.cpp +240 -0
- package/eval/arena/bomberman/workspace/clock.py +25 -0
- package/eval/arena/bomberman/workspace/engine/arena.py +198 -0
- package/eval/arena/bomberman/workspace/engine/build.py +35 -0
- package/eval/arena/bomberman/workspace/engine/engine.py +256 -0
- package/eval/arena/bomberman/workspace/engine/verify_replay.py +24 -0
- package/eval/arena/bomberman/workspace/run.cmd +28 -0
- package/eval/arena/bomberman/workspace/run.sh +16 -0
- package/eval/arena/bomberman/workspace/viewer/index.html +42 -0
- package/eval/arena/ctf/bots/README.md +18 -0
- package/eval/arena/ctf/bots/deepseek-v4.1-flash.cpp +601 -0
- package/eval/arena/ctf/bots/doubao-seed-2.1-turbo.cpp +320 -0
- package/eval/arena/ctf/bots/fable-5.1.cpp +634 -0
- package/eval/arena/ctf/bots/glm-5.3.cpp +689 -0
- package/eval/arena/ctf/bots/gpt-6-astra.cpp +657 -0
- package/eval/arena/ctf/bots/gpt-6.1-sol.cpp +725 -0
- package/eval/arena/ctf/bots/kimi-k3.cpp +667 -0
- package/eval/arena/ctf/bots/mimo-v2.6-pro.cpp +533 -0
- package/eval/arena/ctf/bots/opus-5.5.cpp +645 -0
- package/eval/arena/ctf/bots/qwen-3.8-max.cpp +726 -0
- package/eval/arena/ctf/bots/sonnet-5.5.cpp +569 -0
- package/eval/arena/ctf/tournament/README.md +15 -0
- package/eval/arena/ctf/tournament/formal-2to8.json +31 -0
- package/eval/arena/ctf/tournament/formal-9to15.json +31 -0
- package/eval/arena/ctf/workspace/README.md +41 -0
- package/eval/arena/ctf/workspace/RULES.md +119 -0
- package/eval/arena/ctf/workspace/arena.py +186 -0
- package/eval/arena/ctf/workspace/baseline.cpp +257 -0
- package/eval/arena/ctf/workspace/clock.py +15 -0
- package/eval/arena/ctf/workspace/core.py +265 -0
- package/eval/arena/ctf/workspace/engine.py +389 -0
- package/eval/arena/ctf/workspace/run.cmd +24 -0
- package/eval/arena/ctf/workspace/run.sh +11 -0
- package/eval/arena/ctf/workspace/viewer.html +71 -0
- package/eval/arena/land/bots/README.md +17 -0
- package/eval/arena/land/bots/deepseek-4.1f@workbuddy#1/bot.cpp +608 -0
- package/eval/arena/land/bots/glm-5.3@workbuddy#1/bot.cpp +521 -0
- package/eval/arena/land/bots/gpt-6-astra@codex#1/bot.cpp +373 -0
- package/eval/arena/land/bots/gpt-6-sol@codex#1/bot.cpp +341 -0
- package/eval/arena/land/bots/kimi-k3@workbuddy#1/bot.cpp +492 -0
- package/eval/arena/land/bots/mimo-2.6-pro@zcode#1/bot.cpp +652 -0
- package/eval/arena/land/bots/mystery-model@zcode#1/bot.cpp +466 -0
- package/eval/arena/land/bots/opus-5.5@claude-code#1/bot.cpp +630 -0
- package/eval/arena/land/bots/sonnet-5@claude-code#1/bot.cpp +619 -0
- package/eval/arena/land/tournament/make_replay_page.py +17 -0
- package/eval/arena/land/tournament/rate.py +290 -0
- package/eval/arena/land/tournament/round_robin.py +172 -0
- package/eval/arena/land/tournament/sparring.cpp +356 -0
- package/eval/arena/land/workspace/RULES.md +114 -0
- package/eval/arena/land/workspace/TASK.md +46 -0
- package/eval/arena/land/workspace/anchors/.build/greedy_f2e6d2dea5ca +0 -0
- package/eval/arena/land/workspace/anchors/greedy.cpp +194 -0
- package/eval/arena/land/workspace/anchors/random.cpp +80 -0
- package/eval/arena/land/workspace/clock.py +64 -0
- package/eval/arena/land/workspace/engine/build.py +33 -0
- package/eval/arena/land/workspace/engine/game.py +273 -0
- package/eval/arena/land/workspace/engine/referee.py +308 -0
- package/eval/arena/land/workspace/starter/.build/bot_be32b45b4699 +0 -0
- package/eval/arena/land/workspace/starter/bot.cpp +82 -0
- package/eval/arena/land/workspace/viewer/viewer.html +210 -0
- package/eval/arena/tank/bots/README.md +24 -0
- package/eval/arena/tank/bots/half1/deepseek-v4.1-flash.cpp +367 -0
- package/eval/arena/tank/bots/half1/doubao-seed-evolving.cpp +402 -0
- package/eval/arena/tank/bots/half1/gemini-4-argon.cpp +1132 -0
- package/eval/arena/tank/bots/half1/glm-5.3.cpp +551 -0
- package/eval/arena/tank/bots/half1/gpt-6-astra.cpp +233 -0
- package/eval/arena/tank/bots/half1/gpt-6.1-sol-ultrafast.cpp +350 -0
- package/eval/arena/tank/bots/half1/gpt-6.1-sol.cpp +78 -0
- package/eval/arena/tank/bots/half1/grok-4.7.cpp +1099 -0
- package/eval/arena/tank/bots/half1/haiku-5.5.cpp +210 -0
- package/eval/arena/tank/bots/half1/kimi-k3.cpp +353 -0
- package/eval/arena/tank/bots/half1/mimo-v2.6-pro.cpp +336 -0
- package/eval/arena/tank/bots/half1/muse-wonder-full.cpp +560 -0
- package/eval/arena/tank/bots/half1/opus-5.5.cpp +435 -0
- package/eval/arena/tank/bots/half1/qwen-3.8-max.cpp +537 -0
- package/eval/arena/tank/bots/half2/deepseek-v4.1-flash.cpp +425 -0
- package/eval/arena/tank/bots/half2/doubao-seed-evolving.cpp +308 -0
- package/eval/arena/tank/bots/half2/gemini-4-argon.cpp +1390 -0
- package/eval/arena/tank/bots/half2/glm-5.3.cpp +651 -0
- package/eval/arena/tank/bots/half2/gpt-6-astra.cpp +241 -0
- package/eval/arena/tank/bots/half2/gpt-6.1-sol-ultrafast.cpp +356 -0
- package/eval/arena/tank/bots/half2/gpt-6.1-sol.cpp +87 -0
- package/eval/arena/tank/bots/half2/grok-4.7.cpp +1205 -0
- package/eval/arena/tank/bots/half2/haiku-5.5.cpp +210 -0
- package/eval/arena/tank/bots/half2/kimi-k3.cpp +487 -0
- package/eval/arena/tank/bots/half2/mimo-v2.6-pro.cpp +336 -0
- package/eval/arena/tank/bots/half2/muse-wonder-full.cpp +560 -0
- package/eval/arena/tank/bots/half2/opus-5.5.cpp +476 -0
- package/eval/arena/tank/bots/half2/qwen-3.8-max.cpp +392 -0
- package/eval/arena/tank/tournament/README.md +24 -0
- package/eval/arena/tank/tournament/bt.py +218 -0
- package/eval/arena/tank/tournament/final.json +202 -0
- package/eval/arena/tank/tournament/halftime.json +146 -0
- package/eval/arena/tank/tournament/progress.json +911 -0
- package/eval/arena/tank/tournament/schedule.py +100 -0
- package/eval/arena/tank/tournament/sparring.cpp +928 -0
- package/eval/arena/tank/tournament/tournament.py +1426 -0
- package/eval/arena/tank/workspace/README.md +169 -0
- package/eval/arena/tank/workspace/RULES.md +443 -0
- package/eval/arena/tank/workspace/arena.py +862 -0
- package/eval/arena/tank/workspace/baseline.cpp +259 -0
- package/eval/arena/tank/workspace/clock.py +103 -0
- package/eval/arena/tank/workspace/core.py +712 -0
- package/eval/arena/tank/workspace/engine.py +573 -0
- package/eval/arena/tank/workspace/history/.lock +0 -0
- package/eval/arena/tank/workspace/history/20261017-193610-08715287f91f-bot.cpp +109 -0
- package/eval/arena/tank/workspace/history/20261017-193619-f00b2d5635fa-gpt-6-astra.cpp +241 -0
- package/eval/arena/tank/workspace/history/20261017-193643-63319e0a2b1a-gpt-6_1-sol-ultrafast.cpp +356 -0
- package/eval/arena/tank/workspace/history/20261017-193647-41c1341d0a8a-gemini-4-argon.cpp +1390 -0
- package/eval/arena/tank/workspace/history/20261017-193652-e34c0f45539a-gpt-6_1-sol.cpp +87 -0
- package/eval/arena/tank/workspace/history/20261017-193654-c026348ce96e-opus-5_5.cpp +476 -0
- package/eval/arena/tank/workspace/history/20261017-193655-4a21366e94d1-muse-wonder-full.cpp +560 -0
- package/eval/arena/tank/workspace/history/20261017-193657-dbc4e9969c52-mimo-v2_6-pro.cpp +336 -0
- package/eval/arena/tank/workspace/history/20261017-193703-723cd036eb31-grok-4_7.cpp +1205 -0
- package/eval/arena/tank/workspace/history/20261017-193707-1ebbb227be68-deepseek-v4_1-flash.cpp +425 -0
- package/eval/arena/tank/workspace/history/20261017-193709-aeb0e7202ad5-doubao-seed-evolving.cpp +308 -0
- package/eval/arena/tank/workspace/history/20261017-193710-b21ebeb9bc76-kimi-k3.cpp +487 -0
- package/eval/arena/tank/workspace/history/20261017-193712-54cd86531905-haiku-5_5.cpp +210 -0
- package/eval/arena/tank/workspace/history/20261017-193714-efdb8e35c0bf-qwen-3_8-max.cpp +392 -0
- package/eval/arena/tank/workspace/history/20261017-193715-681423c23fdb-glm-5_3.cpp +651 -0
- package/eval/arena/tank/workspace/history/20261017-193717-1a8b3c75181d-sparring.cpp +928 -0
- package/eval/arena/tank/workspace/history/20261017-193720-1e0803a541e8-baseline.cpp +259 -0
- package/eval/arena/tank/workspace/history/log.jsonl +103 -0
- package/eval/arena/tank/workspace/judge/cycles.hpp +53 -0
- package/eval/arena/tank/workspace/judge/fast.cpp +337 -0
- package/eval/arena/tank/workspace/judge/referee.cpp +125 -0
- package/eval/arena/tank/workspace/judge/speed.cpp +99 -0
- package/eval/arena/tank/workspace/run.cmd +31 -0
- package/eval/arena/tank/workspace/run.sh +23 -0
- package/eval/arena/tank/workspace/tank.hpp +1762 -0
- package/eval/arena/tank/workspace/tank_main.cpp +215 -0
- package/eval/arena/tank/workspace/viewer.html +1150 -0
- package/eval/arena/warehouse/workspace/SPEC.md +130 -0
- package/eval/arena/warehouse/workspace/TASK.md +71 -0
- package/eval/arena/warehouse/workspace/baseline/common.h +88 -0
- package/eval/arena/warehouse/workspace/baseline/main.cpp +27 -0
- package/eval/arena/warehouse/workspace/baseline/old_stuff.cpp +87 -0
- package/eval/arena/warehouse/workspace/baseline/sim.cpp +427 -0
- package/eval/arena/warehouse/workspace/baseline/util.cpp +220 -0
- package/eval/arena/warehouse/workspace/clock.py +42 -0
- package/eval/arena/warehouse/workspace/src/common.h +88 -0
- package/eval/arena/warehouse/workspace/src/main.cpp +27 -0
- package/eval/arena/warehouse/workspace/src/old_stuff.cpp +87 -0
- package/eval/arena/warehouse/workspace/src/sim.cpp +427 -0
- package/eval/arena/warehouse/workspace/src/util.cpp +220 -0
- package/eval/arena/warehouse/workspace/tools/bench.py +119 -0
- package/eval/arena/warehouse/workspace/tools/check_input.py +161 -0
- package/eval/arena/warehouse/workspace/tools/gen.py +132 -0
- package/eval/arena/warehouse/workspace/tools/measure.py +107 -0
- package/eval/arena/warehouse/workspace/workloads/public/pub_crowded.in +1420 -0
- package/eval/arena/warehouse/workspace/workloads/public/pub_crowded.out +9162 -0
- package/eval/arena/warehouse/workspace/workloads/public/pub_dynamic.in +1465 -0
- package/eval/arena/warehouse/workspace/workloads/public/pub_dynamic.out +3439 -0
- package/eval/arena/warehouse/workspace/workloads/public/pub_flood.in +2757 -0
- package/eval/arena/warehouse/workspace/workloads/public/pub_flood.out +3126 -0
- package/eval/arena/warehouse/workspace/workloads/public/pub_small.in +731 -0
- package/eval/arena/warehouse/workspace/workloads/public/pub_small.out +2578 -0
- package/eval/arena/warehouse/workspace/workloads/public/pub_wide.in +528 -0
- package/eval/arena/warehouse/workspace/workloads/public/pub_wide.out +2026 -0
- package/eval/bomberman.py +20 -0
- package/eval/commit0.py +21 -0
- package/eval/common.py +61 -0
- package/eval/ctf.py +20 -0
- package/eval/featurebench.py +25 -0
- package/eval/land.py +20 -0
- package/eval/legacy/bomberman-prices.json +4 -0
- package/eval/legacy/bomberman.py +161 -0
- package/eval/legacy/commit0.py +91 -0
- package/eval/legacy/ctf-prices.json +4 -0
- package/eval/legacy/ctf.py +178 -0
- package/eval/legacy/featurebench.py +103 -0
- package/eval/legacy/land-prices.json +4 -0
- package/eval/legacy/land.py +177 -0
- package/eval/legacy/swe_bench_pro.py +116 -0
- package/eval/legacy/tank-prices.json +3 -0
- package/eval/legacy/tank.py +408 -0
- package/eval/legacy/warehouse-prices.json +4 -0
- package/eval/legacy/warehouse.py +365 -0
- package/eval/swe-bench-pro.py +25 -0
- package/eval/tank.py +20 -0
- package/eval/warehouse.py +20 -0
- package/lib/client/index.js +376 -63
- package/lib/client/index.js.map +1 -1
- package/lib/index.js +684 -27
- package/package.json +2 -1
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-eval-guard",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.3.0",
|
|
4
4
|
"type": "module",
|
|
5
5
|
"description": "Evaluation guard for DSH: workspace-only filesystem, no network/subagents, wall-clock limits, and task installation for the meow-ai-arena tank task.",
|
|
6
6
|
"license": "MIT",
|
|
@@ -42,6 +42,7 @@
|
|
|
42
42
|
"lib",
|
|
43
43
|
"native",
|
|
44
44
|
"assets",
|
|
45
|
+
"eval",
|
|
45
46
|
"cordis.patch.yml",
|
|
46
47
|
"README.md",
|
|
47
48
|
"scripts"
|