@zhivex-ai/harness 1.0.0-rc.7 → 1.0.0
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/CHANGELOG.md +190 -0
- package/README.md +47 -62
- package/ROADMAP.md +15 -6
- package/SECURITY.md +1 -1
- package/benchmarks/README.md +48 -0
- package/benchmarks/baselines/context-navigation-2026-09-09.json +94 -0
- package/benchmarks/baselines/efficiency-2026-09-08.json +233 -0
- package/benchmarks/baselines/external-final-2026-09-08.json +588 -0
- package/benchmarks/baselines/external-intermediate-2026-09-08.json +116 -0
- package/benchmarks/baselines/external-matched-openai-2026-09-08.json +1922 -0
- package/benchmarks/baselines/external-matched-qwen-2026-09-08.json +1706 -0
- package/benchmarks/baselines/external-pilot-2026-09-08.json +439 -0
- package/benchmarks/baselines/external-qwen-flash-2026-09-08.json +1570 -0
- package/benchmarks/baselines/external-qwen-remediation-2026-09-09.json +1509 -0
- package/benchmarks/baselines/external-qwen-sdk-114-progress-2026-09-09.json +2509 -0
- package/benchmarks/baselines/external-sdk-upgrade-2026-09-08.json +564 -0
- package/benchmarks/baselines/external-verifier-recovery-2026-09-09.json +794 -0
- package/benchmarks/baselines/full-harness-review-2026-09-10.json +134 -0
- package/benchmarks/baselines/harness-audit-2026-09-09.json +136 -0
- package/benchmarks/baselines/harness-remediation-2026-09-09.json +160 -0
- package/benchmarks/baselines/oci-remediation-2026-09-10.json +535 -0
- package/benchmarks/baselines/rc14-holdout-2026-09-10.json +854 -0
- package/benchmarks/baselines/repair-architecture-audit-2026-09-09.json +75 -0
- package/benchmarks/baselines/time-to-safe-fix-live-expanded-2026-08-21.json +186 -0
- package/benchmarks/baselines/time-to-safe-fix-live-smoke-2026-08-21.json +186 -0
- package/contracts/public-api.json +25 -0
- package/contracts/security-controls.json +3 -2
- package/contracts/stable-api-signatures.json +58 -54
- package/dist/bounded-reads.d.ts +4 -0
- package/dist/change-envelope.d.ts +4 -4
- package/dist/cli-options.d.ts +2 -1
- package/dist/cli-profiles.d.ts +39 -0
- package/dist/cli-stream.d.ts +40 -40
- package/dist/cli.d.ts +38 -35
- package/dist/cli.js +6556 -4030
- package/dist/compaction.d.ts +12 -0
- package/dist/config.d.ts +6 -1
- package/dist/console-context.d.ts +26 -0
- package/dist/console-input.d.ts +28 -0
- package/dist/context-engineering.d.ts +5 -5
- package/dist/context-metrics.d.ts +11 -0
- package/dist/edit-contracts.d.ts +2 -2
- package/dist/execution-environment.d.ts +9 -5
- package/dist/harness.d.ts +52 -18
- package/dist/hostile-repository-demo.js +2942 -1088
- package/dist/index.d.ts +3 -3
- package/dist/index.js +4316 -2435
- package/dist/json-contracts.d.ts +292 -236
- package/dist/model-budget.d.ts +61 -0
- package/dist/operations.d.ts +82 -20
- package/dist/orchestration.d.ts +1 -0
- package/dist/providers.d.ts +5 -2
- package/dist/repair-controller.d.ts +72 -0
- package/dist/repair-progress.d.ts +40 -0
- package/dist/repair-verifier.d.ts +6 -0
- package/dist/replacement-edits.d.ts +9 -0
- package/dist/routing.d.ts +1 -1
- package/dist/run-interruption.d.ts +4 -0
- package/dist/runtime-checkpoints.d.ts +7 -0
- package/dist/runtime-diagnostics.d.ts +63 -0
- package/dist/runtime-policy.d.ts +36 -0
- package/dist/sessions.d.ts +1 -1
- package/dist/state-backup.d.ts +2 -2
- package/dist/task-memory.d.ts +36 -0
- package/dist/terminal-markdown.d.ts +12 -0
- package/dist/time-to-safe-fix.d.ts +19 -19
- package/dist/tool-registry.d.ts +4 -0
- package/dist/verify-historical-migrations.js +6987 -5140
- package/dist/workspace-mutation-lock.d.ts +5 -0
- package/dist/workspace.d.ts +39 -4
- package/dist/zhx.js +6556 -4030
- package/docs/CLI.md +89 -3
- package/docs/CONTEXT_ENGINEERING.md +160 -0
- package/docs/EXECUTION_ENVIRONMENTS.md +21 -0
- package/docs/EXTENSIBILITY.md +2 -2
- package/docs/GA_READINESS.md +13 -7
- package/docs/LIVE_CERTIFICATION.md +12 -2
- package/docs/RC13_SECURITY_REVIEW.md +28 -0
- package/docs/RC14_DELEGATED_SECURITY_DECISION.md +80 -0
- package/docs/RC14_SECURITY_REVIEW.md +40 -0
- package/docs/README.md +33 -0
- package/docs/RELEASE.md +4 -2
- package/docs/REPOSITORY_EDITING.md +47 -0
- package/docs/SECURITY_REVIEW_EVIDENCE.md +5 -3
- package/docs/THREAT_MODEL.md +3 -3
- package/docs/TIME_TO_SAFE_FIX.md +4 -4
- package/docs/ga-readiness.json +147 -16
- package/docs/reports/EFFICIENCY_REVIEW.md +156 -0
- package/docs/reports/EXTERNAL_COMPARISON.md +434 -0
- package/docs/reports/FULL_HARNESS_REVIEW_2026-09-10.md +200 -0
- package/docs/reports/GA_BUDGET_REMEDIATION_2026-09-19.md +38 -0
- package/docs/reports/GA_REPAIR_RECOVERY_2026-09-19.md +700 -0
- package/docs/reports/GA_VALIDATION_2026-09-19.md +111 -0
- package/docs/reports/HARNESS_ARCHITECTURE_REVIEW_2026-09-09.md +202 -0
- package/docs/reports/HARNESS_AUDIT_2026-09-09.md +306 -0
- package/docs/reports/HARNESS_REMEDIATION_2026-09-09.md +74 -0
- package/docs/reports/HARNESS_REMEDIATION_2026-09-10.md +90 -0
- package/docs/reports/MODEL_COMPARISON_2026-09-09.md +184 -0
- package/docs/reports/QWEN_REMEDIATION_COMPARISON_2026-09-09.md +142 -0
- package/docs/reports/RC14_VALIDATION_2026-09-10.md +45 -0
- package/docs/reports/README.md +26 -0
- package/docs/reports/evidence/ga-budget-remediation-2026-09-19.json +133 -0
- package/docs/reports/evidence/ga-catalog-ablation-2026-09-19.json +699 -0
- package/docs/reports/evidence/ga-catalog-ablation-plan-2026-09-19.json +40 -0
- package/docs/reports/evidence/ga-catalog-observed-2026-09-19.json +985 -0
- package/docs/reports/evidence/ga-catalog-observed-plan-2026-09-19.json +28 -0
- package/docs/reports/evidence/ga-catalog-observed-status-2026-09-19.json +15 -0
- package/docs/reports/evidence/ga-complete-local-check-2026-09-19.json +47 -0
- package/docs/reports/evidence/ga-completion-reminder-2026-09-19.json +22 -0
- package/docs/reports/evidence/ga-fresh-cohort-plan-2026-09-19.json +54 -0
- package/docs/reports/evidence/ga-fresh-cohort-preparation-2026-09-19.json +242 -0
- package/docs/reports/evidence/ga-fresh-cohort-result-2026-09-19.json +4318 -0
- package/docs/reports/evidence/ga-local-validation-followup-2026-09-19.json +66 -0
- package/docs/reports/evidence/ga-node-consumers-2026-09-19.json +31 -0
- package/docs/reports/evidence/ga-package-content-validation-2026-09-19.json +22 -0
- package/docs/reports/evidence/ga-plan-completion-2026-09-19.json +39 -0
- package/docs/reports/evidence/ga-plan-reserve-2026-09-19.json +573 -0
- package/docs/reports/evidence/ga-plan-reserve-plan-2026-09-19.json +24 -0
- package/docs/reports/evidence/ga-plan-transition-2026-09-19.json +19 -0
- package/docs/reports/evidence/ga-private-verifier-plan-2026-09-19.json +24 -0
- package/docs/reports/evidence/ga-private-verifier-root-cause-2026-09-19.json +41 -0
- package/docs/reports/evidence/ga-published-sdk-2026-09-19.json +35 -0
- package/docs/reports/evidence/ga-python-checkout-imports-2026-09-19.json +95 -0
- package/docs/reports/evidence/ga-python-origin-delivery-2026-09-19.json +211 -0
- package/docs/reports/evidence/ga-python-origin-delivery-plan-2026-09-19.json +27 -0
- package/docs/reports/evidence/ga-qwen-patched-package-2026-09-19.json +1092 -0
- package/docs/reports/evidence/ga-qwen-patched-package-plan-2026-09-19.json +18 -0
- package/docs/reports/evidence/ga-qwen-published-2026-09-19.json +571 -0
- package/docs/reports/evidence/ga-qwen-published-plan-2026-09-19.json +18 -0
- package/docs/reports/evidence/ga-qwen-tool-choice-2026-09-19.json +85 -0
- package/docs/reports/evidence/ga-qwen-tool-choice-patched-2026-09-19.json +85 -0
- package/docs/reports/evidence/ga-recovery-development-2026-09-19.json +1066 -0
- package/docs/reports/evidence/ga-recovery-graded-development-2026-09-19.json +1313 -0
- package/docs/reports/evidence/ga-recovery-graded-v2-2026-09-19.json +1151 -0
- package/docs/reports/evidence/ga-recovery-v3-2026-09-19.json +3943 -0
- package/docs/reports/evidence/ga-recovery-v4-2026-09-19.json +1055 -0
- package/docs/reports/evidence/ga-recovery-v5-2026-09-19.json +1245 -0
- package/docs/reports/evidence/ga-recovery-v6-2026-09-19.json +699 -0
- package/docs/reports/evidence/ga-recovery-v7-2026-09-19.json +854 -0
- package/docs/reports/evidence/ga-recovery-v8-2026-09-19.json +596 -0
- package/docs/reports/evidence/ga-required-delivery-2026-09-19.json +25 -0
- package/docs/reports/evidence/ga-required-delivery-live-2026-09-19.json +1337 -0
- package/docs/reports/evidence/ga-required-delivery-live-plan-2026-09-19.json +25 -0
- package/docs/reports/evidence/ga-retained-candidate-grading-2026-09-19.json +30 -0
- package/docs/reports/evidence/ga-tool-selection-live-2026-09-19.json +559 -0
- package/docs/reports/evidence/ga-tool-selection-live-plan-2026-09-19.json +28 -0
- package/docs/reports/evidence/ga-tool-selection-recovery-2026-09-19.json +27 -0
- package/docs/reports/evidence/ga-validation-2026-09-19.json +236 -0
- package/docs/reports/evidence/ga-verifier-discovery-live-2026-09-19.json +1369 -0
- package/docs/reports/evidence/ga-verifier-discovery-plan-2026-09-19.json +29 -0
- package/docs/reports/evidence/ga-verifier-failure-identification-2026-09-19.json +30 -0
- package/docs/reports/evidence/ga-verifier-feedback-2026-09-19.json +65 -0
- package/docs/reports/evidence/ga-verifier-hints-live-2026-09-19.json +1297 -0
- package/docs/reports/evidence/ga-verifier-hints-plan-2026-09-19.json +27 -0
- package/docs/reports/evidence/ga-work-boundary-context-analysis-2026-09-19.json +113 -0
- package/docs/reports/evidence/ga-work-boundary-live-2026-09-19.json +301 -0
- package/docs/reports/evidence/ga-work-boundary-live-plan-2026-09-19.json +84 -0
- package/docs/reports/evidence/ga-work-budget-planning-2026-09-19.json +32 -0
- package/docs/reports/evidence/ga-working-context-2026-09-19.json +22 -0
- package/docs/reports/evidence/rc14-delegated-security-review-2026-09-20.json +81 -0
- package/docs/reports/evidence/rc14-ga-gate-2026-09-20.json +18 -0
- package/docs/reports/evidence/rc14-representative-2026-09-20.json +509 -0
- package/docs/reports/evidence/rc14-security-regressions-2026-09-20.json +64 -0
- package/docs/reports/evidence/security-current-2026-09-19.json +91 -0
- package/docs/reports/evidence/security-remediation-2026-09-19.json +97 -0
- package/evaluations/repair-controller-experiment.json +24 -0
- package/evaluations/representative-assembly-matrix.json +63 -0
- package/evaluations/representative-matrix.json +2219 -2
- package/fixtures/contracts/v1/init.json +19 -0
- package/package.json +25 -16
|
@@ -0,0 +1,439 @@
|
|
|
1
|
+
{
|
|
2
|
+
"schemaVersion": 1,
|
|
3
|
+
"date": "2026-09-08",
|
|
4
|
+
"kind": "exploratory-external-pilot",
|
|
5
|
+
"dataset": "princeton-nlp/SWE-bench_Verified",
|
|
6
|
+
"revision": "c104f840cc67f8b6eec6f759ebc8b2693d585d4a",
|
|
7
|
+
"model": "gpt-5.6-luna",
|
|
8
|
+
"seed": 20260908,
|
|
9
|
+
"repetitions": 1,
|
|
10
|
+
"limits": {
|
|
11
|
+
"steps": 24,
|
|
12
|
+
"outputPerTurn": 2048,
|
|
13
|
+
"inputTokens": 100000,
|
|
14
|
+
"outputTokens": 16000,
|
|
15
|
+
"timeoutSeconds": 300,
|
|
16
|
+
"memoryMb": 2048,
|
|
17
|
+
"cpus": 2
|
|
18
|
+
},
|
|
19
|
+
"versions": {
|
|
20
|
+
"mini-swe-agent": "2.4.6",
|
|
21
|
+
"swebench": "4.1.0"
|
|
22
|
+
},
|
|
23
|
+
"implementation": {
|
|
24
|
+
"gitCommit": "0a7b69dddaa70a54b6b5b4097691c8112d4d76eb",
|
|
25
|
+
"sources": {
|
|
26
|
+
"bun.lock": "1293016c4d75c3dba51281c95485ea23c80097541ced9575803fe5dcf3e9f8d9",
|
|
27
|
+
"evaluations/external/requirements.lock": "42e90a08f10f821ebb958af79256f707a9fb5cf365277c4f9e2715d612028179",
|
|
28
|
+
"package.json": "c9cb835bf12a8630846d79909950636d10896a1b6b60ed1fd5468697b94aee08",
|
|
29
|
+
"scripts/swebench/common.py": "c19cfc30b85dc3ad8dbf1ba6a4165e72ce96f624eb1721b613cfa3207636f7be",
|
|
30
|
+
"scripts/swebench/mini_driver.py": "46badf61f041208b3a4428beb4e574f896a459d43ab4b7a03dc616ff04b1baf3",
|
|
31
|
+
"scripts/swebench/preflight.py": "f3a9fc241896eb5d63138127fea4396e59d95c277c009a29a2265ee35f4aa6eb",
|
|
32
|
+
"scripts/swebench/prepare.py": "94e535c7b8c0f7581eebb06f4ed6d60ad7d566d42d7e8c603bf2964f45d42156",
|
|
33
|
+
"scripts/swebench/report.py": "70afcdf0d1f081014bb75d878f3ddf9195959e96b523ddf1e0ad5d3ec8273549",
|
|
34
|
+
"scripts/swebench/run.py": "a3f99566856a97489177722702082c88b861f3b9af5d4bea8d833962b2db491f",
|
|
35
|
+
"scripts/swebench/test_contracts.py": "a8c1348f1dff2e563c139e6d3e83eb141b4f2a71f91a58e2c5c051ed2a431024",
|
|
36
|
+
"scripts/swebench/zhivex-driver.ts": "0883f23e050d4fb3ac56a8e751d811bbc8e964085d2bd575c68a86ed10180486",
|
|
37
|
+
"src/bounded-reads.ts": "9807bb460894be3279c5425af19863d1c6e419a1582ba6910ec7e7fc35703ed6",
|
|
38
|
+
"src/capabilities.ts": "56fdb60a2f6e1d33b2dc26d38b6d2709807e491ba1268d47b97876c2c0591d65",
|
|
39
|
+
"src/change-envelope.ts": "9047ec978c9e5117965b8093ec961d855f97bbc2c3accdc79b74cfe6a0e4f01e",
|
|
40
|
+
"src/cli-options.ts": "97781386289e3877c1318e4c94698ca7aaf2f256b89534dfcb21e966eb7d939f",
|
|
41
|
+
"src/cli-profiles.ts": "4fe451f1645e95f4957597a8724fa989b3c661ae1693252bfd6e74a51d20fc74",
|
|
42
|
+
"src/cli-stream.ts": "5ab8a4b1b8cf0a3dfa7b5b1f9e4e0facf8f6e7f6c341bdf700a41dc8927c825e",
|
|
43
|
+
"src/cli.ts": "cce6f58dfbc543acdc029b188d4394cd059d940bdd361351fd877ae2d6e94880",
|
|
44
|
+
"src/compaction.ts": "9cc6ef39ebd2a024fac729177e2015db5121cc7168c25096d439061258599d1b",
|
|
45
|
+
"src/config.ts": "c160faaf2d9fb637c5a08a7aff65d761a12c707ed23ebb87ab0e8519e9536bf3",
|
|
46
|
+
"src/console-context.ts": "0ad7e4559504b9ed09ab500d615dea09af1075d357f02ec3b77f003d55d951db",
|
|
47
|
+
"src/console-input.ts": "dc8ea0cdbba1364db288d5156c5ff9819362c46b37ef35a98b0475b6c445b1f8",
|
|
48
|
+
"src/context-engineering.ts": "1995e564f6b91974e75bf66dd421ddcbea29b1f8eee59b76eb4e34c9d6d8f47e",
|
|
49
|
+
"src/edit-contracts.ts": "47cc3132e27f8749d54a32bbcc33bb174cf4448f0d0171b2578cdb559cf2176b",
|
|
50
|
+
"src/errors.ts": "e02f4eb80562a83762f908bda56c950ec6a2b78725c0c8a49f41fee0057ab903",
|
|
51
|
+
"src/execution-environment.ts": "341c977be61b9c2d50ed0239a52e9ef7ea5d553f3ea2b322b6567c5b645c1ff8",
|
|
52
|
+
"src/file-security.ts": "4590b46c8e4b9d3891a75cd0d0ada14e0ae7b58e8e4bdf82f68df688a1fbb750",
|
|
53
|
+
"src/harness.ts": "e2186d84e7c969de8ed2141853aabbd9b28ba48422afcd87af2b0084d1aac5fc",
|
|
54
|
+
"src/index.ts": "f791311f14dc27105191d97bb5454748d10beab827da9aba3ea949ffc32fce7c",
|
|
55
|
+
"src/json-contracts.ts": "0702e5b0ff16ff6304c74b4101bd31a3fa8eabdebe267d312b56d3871a7e302c",
|
|
56
|
+
"src/mcp.ts": "5f3f7a35b89063264ae18ab9273b84e2e59ac8c8e611a6b64be377ba61cc1ac5",
|
|
57
|
+
"src/operations.ts": "0775da79208c6f5d18476cc76404e84ddda610979d9d0e5dc15035aa6999613c",
|
|
58
|
+
"src/orchestration.ts": "7383da1047363819e6560f51892fd4082e5337856a3d889cdc076f021273774e",
|
|
59
|
+
"src/package-manager.ts": "cec4666bbab2f42e0a269709631f79f9f87c2c4dbb3cafeffacfaff761069e2c",
|
|
60
|
+
"src/process-runtime.ts": "b7286731a0b5c96dcad0b8e3a4bf1155d0539d73303cd7ebe77ffabf858f1729",
|
|
61
|
+
"src/providers.ts": "70ccfc7f315cd7238e83d69b719ce4908f3b620c564cbb4f00f93e102e025602",
|
|
62
|
+
"src/routing.ts": "8e7c9f5968b4bd638cbbc86b19847ca183f3418b9a298783b96a88cffa568e22",
|
|
63
|
+
"src/run-interruption.ts": "df99129cf2dd6b938eca629cb897c4350a7d57fe6bf0ce437f5f3f30271617df",
|
|
64
|
+
"src/sessions.ts": "5167c8cf36bd4b8845ee278883394700321b65397f49c1dda0cf0d0de09dd06e",
|
|
65
|
+
"src/sqlite-database.ts": "18765d1ca0c2f2ad87bfd82d311312dfe8a42006556f27bc21da5892ed3b044e",
|
|
66
|
+
"src/state-backup.ts": "b6f8f1aedeb5dce31b65c23c7ffc50030870655b58a5aaaef9989bafb9da5c68",
|
|
67
|
+
"src/state-directory.ts": "3711550991951e6b738a08deaa0e06da84d01864c03a9602600f592963fa3211",
|
|
68
|
+
"src/terminal-markdown.ts": "8cffb6ebaf25108cb2bee04956d9b2973635b010f5d7ce6be21b3ceffe3e8bfd",
|
|
69
|
+
"src/terminal-ui.ts": "e50025a8649d1f60efdf3af895b8639730ec2e86553fb80a61a776b11076c705",
|
|
70
|
+
"src/time-to-safe-fix.ts": "4add1d49c0ea209cc496c66fa2b2012dc7bcab87e678a58c8591b3c2cdc8df8a",
|
|
71
|
+
"src/version.ts": "b2c2f80a40adc08e8258b81e82434273f0bdfa787528b2221f14efe7f06aa747",
|
|
72
|
+
"src/workspace.ts": "e5cff88e2b1e1ef4b0226d197c5a563b44133dd9f7de6e0c9a9dcf1d575fac3b"
|
|
73
|
+
}
|
|
74
|
+
},
|
|
75
|
+
"environmentDifferences": [
|
|
76
|
+
"Zhivex native OCI: read-only root and writable /workspace snapshot, operator auto-approval; mini: writable /testbed. Both deny container network and use the same derived image and CPU/memory limits.",
|
|
77
|
+
"Zhivex tool-call limit is steps times eight; mini counts model steps and executes each response's actions. Tool counts are reported, not claimed equivalent.",
|
|
78
|
+
"Input/output token ceilings are checked between model requests and can overshoot by one response; outputPerTurn is sent to both APIs."
|
|
79
|
+
],
|
|
80
|
+
"hostObservation": {
|
|
81
|
+
"system": "Darwin",
|
|
82
|
+
"architecture": "arm64",
|
|
83
|
+
"candidateArchitecture": "linux/amd64",
|
|
84
|
+
"recordedAfterRun": true
|
|
85
|
+
},
|
|
86
|
+
"rawSamplesSha256": "3b531a885851dacd5ff3dfe6897661d4ac68b09b6da301acff4962f6dcab0c50",
|
|
87
|
+
"report": {
|
|
88
|
+
"schemaVersion": 1,
|
|
89
|
+
"kind": "swebench-comparison",
|
|
90
|
+
"manifestSha256": "bcaa8b72db20b0fe312fc18f876408b47df60ce57b4e9ecbcd9497a5186f3b71",
|
|
91
|
+
"complete": true,
|
|
92
|
+
"candidates": {
|
|
93
|
+
"zhivex": {
|
|
94
|
+
"planned": 5,
|
|
95
|
+
"recorded": 5,
|
|
96
|
+
"resolved": 0,
|
|
97
|
+
"resolutionRate": 0.0,
|
|
98
|
+
"missing": 0,
|
|
99
|
+
"gradingFailures": 0,
|
|
100
|
+
"usageComplete": false,
|
|
101
|
+
"totalCostUsd": null,
|
|
102
|
+
"costPerResolvedUsd": null,
|
|
103
|
+
"resolvedP50Ms": null
|
|
104
|
+
},
|
|
105
|
+
"mini-swe-agent": {
|
|
106
|
+
"planned": 5,
|
|
107
|
+
"recorded": 5,
|
|
108
|
+
"resolved": 5,
|
|
109
|
+
"resolutionRate": 1.0,
|
|
110
|
+
"missing": 0,
|
|
111
|
+
"gradingFailures": 0,
|
|
112
|
+
"usageComplete": true,
|
|
113
|
+
"totalCostUsd": null,
|
|
114
|
+
"costPerResolvedUsd": null,
|
|
115
|
+
"resolvedP50Ms": 56212.63020799961
|
|
116
|
+
}
|
|
117
|
+
},
|
|
118
|
+
"pairedTaskResolutionDifference": -1.0,
|
|
119
|
+
"pairedTaskBootstrap95": [
|
|
120
|
+
-1.0,
|
|
121
|
+
-1.0
|
|
122
|
+
],
|
|
123
|
+
"evidenceBoundary": "Local matched-model comparison. Missing and failed runs remain in the denominator. Small-sample intervals are exploratory. No safety superiority is inferred from SWE-bench correctness."
|
|
124
|
+
},
|
|
125
|
+
"samples": [
|
|
126
|
+
{
|
|
127
|
+
"candidate": "zhivex",
|
|
128
|
+
"instanceId": "django__django-12262",
|
|
129
|
+
"repetition": 0,
|
|
130
|
+
"status": "failed",
|
|
131
|
+
"failure": "EXECUTION_FAILED",
|
|
132
|
+
"resolved": false,
|
|
133
|
+
"officialResolved": false,
|
|
134
|
+
"gradingStatus": "completed",
|
|
135
|
+
"gradingMethod": "empty-patch-no-solution",
|
|
136
|
+
"inputTokens": null,
|
|
137
|
+
"outputTokens": null,
|
|
138
|
+
"cachedInputTokens": null,
|
|
139
|
+
"modelCalls": null,
|
|
140
|
+
"toolCalls": 7,
|
|
141
|
+
"usageComplete": false,
|
|
142
|
+
"durationMs": 13677.864375,
|
|
143
|
+
"gradingDurationMs": 0.008000002708286047,
|
|
144
|
+
"totalDurationMs": 19484.622207994107,
|
|
145
|
+
"protectedFilesChanged": [],
|
|
146
|
+
"patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
|
147
|
+
"costUsd": null
|
|
148
|
+
},
|
|
149
|
+
{
|
|
150
|
+
"candidate": "mini-swe-agent",
|
|
151
|
+
"instanceId": "django__django-12262",
|
|
152
|
+
"repetition": 0,
|
|
153
|
+
"status": "Submitted",
|
|
154
|
+
"failure": null,
|
|
155
|
+
"resolved": true,
|
|
156
|
+
"officialResolved": true,
|
|
157
|
+
"gradingStatus": "completed",
|
|
158
|
+
"inputTokens": 35265,
|
|
159
|
+
"outputTokens": 1371,
|
|
160
|
+
"cachedInputTokens": 30245,
|
|
161
|
+
"modelCalls": 8,
|
|
162
|
+
"toolCalls": 8,
|
|
163
|
+
"usageComplete": true,
|
|
164
|
+
"durationMs": 30544.840458023828,
|
|
165
|
+
"gradingDurationMs": 28582.4573750142,
|
|
166
|
+
"totalDurationMs": 61055.9477499919,
|
|
167
|
+
"protectedFilesChanged": [],
|
|
168
|
+
"patchSha256": "4fc36a12a7a8626848e6ebcb116505f092b65468b9e7b901db86f11f3ec3fa0a",
|
|
169
|
+
"costUsd": null
|
|
170
|
+
},
|
|
171
|
+
{
|
|
172
|
+
"candidate": "mini-swe-agent",
|
|
173
|
+
"instanceId": "pydata__xarray-4695",
|
|
174
|
+
"repetition": 0,
|
|
175
|
+
"status": "Submitted",
|
|
176
|
+
"failure": null,
|
|
177
|
+
"resolved": true,
|
|
178
|
+
"officialResolved": true,
|
|
179
|
+
"gradingStatus": "completed",
|
|
180
|
+
"inputTokens": 56514,
|
|
181
|
+
"outputTokens": 1687,
|
|
182
|
+
"cachedInputTokens": 49365,
|
|
183
|
+
"modelCalls": 8,
|
|
184
|
+
"toolCalls": 10,
|
|
185
|
+
"usageComplete": true,
|
|
186
|
+
"durationMs": 42424.86758297309,
|
|
187
|
+
"gradingDurationMs": 32091.419000003953,
|
|
188
|
+
"totalDurationMs": 76435.33033295535,
|
|
189
|
+
"protectedFilesChanged": [],
|
|
190
|
+
"patchSha256": "e80a2529f817bff7b55bad625289999722349994e461c8bdbc41089986d67929",
|
|
191
|
+
"costUsd": null
|
|
192
|
+
},
|
|
193
|
+
{
|
|
194
|
+
"candidate": "zhivex",
|
|
195
|
+
"instanceId": "pydata__xarray-4695",
|
|
196
|
+
"repetition": 0,
|
|
197
|
+
"status": "failed",
|
|
198
|
+
"failure": null,
|
|
199
|
+
"resolved": false,
|
|
200
|
+
"officialResolved": false,
|
|
201
|
+
"gradingStatus": "completed",
|
|
202
|
+
"gradingMethod": "empty-patch-no-solution",
|
|
203
|
+
"inputTokens": 152643,
|
|
204
|
+
"outputTokens": 983,
|
|
205
|
+
"cachedInputTokens": 126124,
|
|
206
|
+
"modelCalls": 8,
|
|
207
|
+
"toolCalls": 8,
|
|
208
|
+
"usageComplete": true,
|
|
209
|
+
"durationMs": 18746.6455,
|
|
210
|
+
"gradingDurationMs": 0.00833295052871108,
|
|
211
|
+
"totalDurationMs": 19573.17333301762,
|
|
212
|
+
"protectedFilesChanged": [],
|
|
213
|
+
"patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
|
214
|
+
"costUsd": null
|
|
215
|
+
},
|
|
216
|
+
{
|
|
217
|
+
"candidate": "zhivex",
|
|
218
|
+
"instanceId": "pytest-dev__pytest-8399",
|
|
219
|
+
"repetition": 0,
|
|
220
|
+
"status": "failed",
|
|
221
|
+
"failure": null,
|
|
222
|
+
"resolved": false,
|
|
223
|
+
"officialResolved": false,
|
|
224
|
+
"gradingStatus": "completed",
|
|
225
|
+
"gradingMethod": "empty-patch-no-solution",
|
|
226
|
+
"inputTokens": 119718,
|
|
227
|
+
"outputTokens": 2621,
|
|
228
|
+
"cachedInputTokens": 91384,
|
|
229
|
+
"modelCalls": 10,
|
|
230
|
+
"toolCalls": 10,
|
|
231
|
+
"usageComplete": true,
|
|
232
|
+
"durationMs": 38416.944709,
|
|
233
|
+
"gradingDurationMs": 0.00504200579598546,
|
|
234
|
+
"totalDurationMs": 39259.015540999826,
|
|
235
|
+
"protectedFilesChanged": [],
|
|
236
|
+
"patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
|
237
|
+
"costUsd": null
|
|
238
|
+
},
|
|
239
|
+
{
|
|
240
|
+
"candidate": "mini-swe-agent",
|
|
241
|
+
"instanceId": "pytest-dev__pytest-8399",
|
|
242
|
+
"repetition": 0,
|
|
243
|
+
"status": "Submitted",
|
|
244
|
+
"failure": null,
|
|
245
|
+
"resolved": true,
|
|
246
|
+
"officialResolved": true,
|
|
247
|
+
"gradingStatus": "completed",
|
|
248
|
+
"inputTokens": 31289,
|
|
249
|
+
"outputTokens": 1390,
|
|
250
|
+
"cachedInputTokens": 24682,
|
|
251
|
+
"modelCalls": 7,
|
|
252
|
+
"toolCalls": 7,
|
|
253
|
+
"usageComplete": true,
|
|
254
|
+
"durationMs": 28087.192916020285,
|
|
255
|
+
"gradingDurationMs": 22515.386040962767,
|
|
256
|
+
"totalDurationMs": 52476.374458987266,
|
|
257
|
+
"protectedFilesChanged": [],
|
|
258
|
+
"patchSha256": "6c49c4e740cea7386407d88688ee488142668d3a908aaeea1ca630296dd52ff7",
|
|
259
|
+
"costUsd": null
|
|
260
|
+
},
|
|
261
|
+
{
|
|
262
|
+
"candidate": "mini-swe-agent",
|
|
263
|
+
"instanceId": "django__django-15569",
|
|
264
|
+
"repetition": 0,
|
|
265
|
+
"status": "Submitted",
|
|
266
|
+
"failure": null,
|
|
267
|
+
"resolved": true,
|
|
268
|
+
"officialResolved": true,
|
|
269
|
+
"gradingStatus": "completed",
|
|
270
|
+
"inputTokens": 24366,
|
|
271
|
+
"outputTokens": 1240,
|
|
272
|
+
"cachedInputTokens": 19770,
|
|
273
|
+
"modelCalls": 8,
|
|
274
|
+
"toolCalls": 8,
|
|
275
|
+
"usageComplete": true,
|
|
276
|
+
"durationMs": 27954.237999976613,
|
|
277
|
+
"gradingDurationMs": 23797.319792036433,
|
|
278
|
+
"totalDurationMs": 53833.63074995577,
|
|
279
|
+
"protectedFilesChanged": [],
|
|
280
|
+
"patchSha256": "613e2497df50016f646c4772f08c0caef5e393f7281f89cc7902829eabfcf727",
|
|
281
|
+
"costUsd": null
|
|
282
|
+
},
|
|
283
|
+
{
|
|
284
|
+
"candidate": "zhivex",
|
|
285
|
+
"instanceId": "django__django-15569",
|
|
286
|
+
"repetition": 0,
|
|
287
|
+
"status": "failed",
|
|
288
|
+
"failure": null,
|
|
289
|
+
"resolved": false,
|
|
290
|
+
"officialResolved": false,
|
|
291
|
+
"gradingStatus": "completed",
|
|
292
|
+
"gradingMethod": "empty-patch-no-solution",
|
|
293
|
+
"inputTokens": 110074,
|
|
294
|
+
"outputTokens": 2469,
|
|
295
|
+
"cachedInputTokens": 96292,
|
|
296
|
+
"modelCalls": 10,
|
|
297
|
+
"toolCalls": 11,
|
|
298
|
+
"usageComplete": true,
|
|
299
|
+
"durationMs": 58955.677459,
|
|
300
|
+
"gradingDurationMs": 0.012500036973506212,
|
|
301
|
+
"totalDurationMs": 66539.94154103566,
|
|
302
|
+
"protectedFilesChanged": [],
|
|
303
|
+
"patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
|
304
|
+
"costUsd": null
|
|
305
|
+
},
|
|
306
|
+
{
|
|
307
|
+
"candidate": "zhivex",
|
|
308
|
+
"instanceId": "django__django-14915",
|
|
309
|
+
"repetition": 0,
|
|
310
|
+
"status": "completed",
|
|
311
|
+
"failure": null,
|
|
312
|
+
"resolved": false,
|
|
313
|
+
"officialResolved": false,
|
|
314
|
+
"gradingStatus": "completed",
|
|
315
|
+
"gradingMethod": "empty-patch-no-solution",
|
|
316
|
+
"inputTokens": 1607,
|
|
317
|
+
"outputTokens": 494,
|
|
318
|
+
"cachedInputTokens": 1348,
|
|
319
|
+
"modelCalls": 1,
|
|
320
|
+
"toolCalls": 0,
|
|
321
|
+
"usageComplete": true,
|
|
322
|
+
"durationMs": 8851.873416,
|
|
323
|
+
"gradingDurationMs": 0.01737498678267002,
|
|
324
|
+
"totalDurationMs": 15627.18308402691,
|
|
325
|
+
"protectedFilesChanged": [],
|
|
326
|
+
"patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
|
327
|
+
"costUsd": null
|
|
328
|
+
},
|
|
329
|
+
{
|
|
330
|
+
"candidate": "mini-swe-agent",
|
|
331
|
+
"instanceId": "django__django-14915",
|
|
332
|
+
"repetition": 0,
|
|
333
|
+
"status": "Submitted",
|
|
334
|
+
"failure": null,
|
|
335
|
+
"resolved": true,
|
|
336
|
+
"officialResolved": true,
|
|
337
|
+
"gradingStatus": "completed",
|
|
338
|
+
"inputTokens": 27973,
|
|
339
|
+
"outputTokens": 1390,
|
|
340
|
+
"cachedInputTokens": 23001,
|
|
341
|
+
"modelCalls": 8,
|
|
342
|
+
"toolCalls": 11,
|
|
343
|
+
"usageComplete": true,
|
|
344
|
+
"durationMs": 31511.68758404674,
|
|
345
|
+
"gradingDurationMs": 22792.866834031884,
|
|
346
|
+
"totalDurationMs": 56212.63020799961,
|
|
347
|
+
"protectedFilesChanged": [],
|
|
348
|
+
"patchSha256": "de226204ce78325860a067864ba2e168c4a57884a0af11655a2af3ff6416255c",
|
|
349
|
+
"costUsd": null
|
|
350
|
+
}
|
|
351
|
+
],
|
|
352
|
+
"graderControls": {
|
|
353
|
+
"negative": {
|
|
354
|
+
"gradingStatus": "completed",
|
|
355
|
+
"resolved": false
|
|
356
|
+
},
|
|
357
|
+
"gold": {
|
|
358
|
+
"gradingStatus": "completed",
|
|
359
|
+
"resolved": true
|
|
360
|
+
}
|
|
361
|
+
},
|
|
362
|
+
"limitations": [
|
|
363
|
+
"Five tasks, one repetition: development pilot, not a population estimate or leaderboard claim.",
|
|
364
|
+
"Failed native run lost model telemetry; unknown values normalized to null here.",
|
|
365
|
+
"Three native failed runs exceeded cumulative input ceiling; exact terminal reasons were not retained.",
|
|
366
|
+
"Prices were not supplied; costs unknown. Earlier interrupted integration attempt may include unknown billed usage.",
|
|
367
|
+
"Native and upstream tools, prompts, filesystem policies and patch-import flows differ.",
|
|
368
|
+
"Host ARM emulates Linux AMD64; timing is local only.",
|
|
369
|
+
"Source snapshot preserves executed version; subsequent runner identity checks were added after the pilot.",
|
|
370
|
+
"Pilot source hash list omitted the shared telemetry helper and CLI launcher; future runner includes both. Raw source snapshot covers the recorded hashes only."
|
|
371
|
+
],
|
|
372
|
+
"tasks": [
|
|
373
|
+
{
|
|
374
|
+
"instance_id": "django__django-12262",
|
|
375
|
+
"repo": "django/django",
|
|
376
|
+
"base_commit": "69331bb851c34f05bc77e9fc24020fe6908b9cd5",
|
|
377
|
+
"evalImage": "swebench/sweb.eval.x86_64.django_1776_django-12262:zhx-23c0777e08a37bd0",
|
|
378
|
+
"evalImageId": "sha256:23c0777e08a37bd0643f7638eaca9c57d1ee16fca79b6312b8d6de7fd1b5e7da",
|
|
379
|
+
"evalTag": "zhx-23c0777e08a37bd0",
|
|
380
|
+
"image": "sha256:9d73ee28310b4c46b552ac5af1df9a1a29ca892e7c1197474a53ed8ab33e73b5",
|
|
381
|
+
"checkoutHead": "6b2b46b41688bca917e590c7420e045d635365e5",
|
|
382
|
+
"baseTree": "88307fafa4610ef0c958cab7d18d723d63d5f495",
|
|
383
|
+
"upstreamTree": "88307fafa4610ef0c958cab7d18d723d63d5f495",
|
|
384
|
+
"imageModeDifferences": 0
|
|
385
|
+
},
|
|
386
|
+
{
|
|
387
|
+
"instance_id": "pydata__xarray-4695",
|
|
388
|
+
"repo": "pydata/xarray",
|
|
389
|
+
"base_commit": "51ef2a66c4e0896eab7d2b03e3dfb3963e338e3c",
|
|
390
|
+
"evalImage": "swebench/sweb.eval.x86_64.pydata_1776_xarray-4695:zhx-fe6074de116357f2",
|
|
391
|
+
"evalImageId": "sha256:fe6074de116357f2b6f1b3b964726cd02b866f68509f3e74d3a58c48a778ac6d",
|
|
392
|
+
"evalTag": "zhx-fe6074de116357f2",
|
|
393
|
+
"image": "sha256:b754ea0042638b1b5a021b1b6acefaae4ec97d689587e6c2c0a3cdaf053383c5",
|
|
394
|
+
"checkoutHead": "a4cf03327c39366aca0ca7dfa7ab72b4521c658a",
|
|
395
|
+
"baseTree": "2452479f6f4c2de000d4f024a9b815c75c273d2a",
|
|
396
|
+
"upstreamTree": "2452479f6f4c2de000d4f024a9b815c75c273d2a",
|
|
397
|
+
"imageModeDifferences": 0
|
|
398
|
+
},
|
|
399
|
+
{
|
|
400
|
+
"instance_id": "pytest-dev__pytest-8399",
|
|
401
|
+
"repo": "pytest-dev/pytest",
|
|
402
|
+
"base_commit": "6e7dc8bac831cd8cf7a53b08efa366bd84f0c0fe",
|
|
403
|
+
"evalImage": "swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-8399:zhx-1403b263348f1da0",
|
|
404
|
+
"evalImageId": "sha256:1403b263348f1da02330634d688ebf8dd61fa69f2c301203c89551889946cb0d",
|
|
405
|
+
"evalTag": "zhx-1403b263348f1da0",
|
|
406
|
+
"image": "sha256:3269ccbd3f71a0b1ac4a3f5987b5288ce842c5880e81acd4410913ee514756c7",
|
|
407
|
+
"checkoutHead": "ac43e94eaf25c8c109af2500d327ef938dcf24d7",
|
|
408
|
+
"baseTree": "8501ad3839bb098676d9d3354979cef6e218d95c",
|
|
409
|
+
"upstreamTree": "8501ad3839bb098676d9d3354979cef6e218d95c",
|
|
410
|
+
"imageModeDifferences": 0
|
|
411
|
+
},
|
|
412
|
+
{
|
|
413
|
+
"instance_id": "django__django-15569",
|
|
414
|
+
"repo": "django/django",
|
|
415
|
+
"base_commit": "884b4c27f506b3c29d58509fc83a35c30ea10d94",
|
|
416
|
+
"evalImage": "swebench/sweb.eval.x86_64.django_1776_django-15569:zhx-13d3ee8c6e4aa4d5",
|
|
417
|
+
"evalImageId": "sha256:13d3ee8c6e4aa4d5c34024f32ada971a11153bfe0023339ddc4bdfb0ca48925d",
|
|
418
|
+
"evalTag": "zhx-13d3ee8c6e4aa4d5",
|
|
419
|
+
"image": "sha256:75df77fc887642fcd8876219377a295e5d9aece12fe530bbed442a2bbeb3664f",
|
|
420
|
+
"checkoutHead": "d838c27da4388d13219dd8b7a858cb43c5e83623",
|
|
421
|
+
"baseTree": "5a345ced69aa5bba7a0f9d893d984359555160af",
|
|
422
|
+
"upstreamTree": "5a345ced69aa5bba7a0f9d893d984359555160af",
|
|
423
|
+
"imageModeDifferences": 0
|
|
424
|
+
},
|
|
425
|
+
{
|
|
426
|
+
"instance_id": "django__django-14915",
|
|
427
|
+
"repo": "django/django",
|
|
428
|
+
"base_commit": "903aaa35e5ceaa33bfc9b19b7f6da65ce5a91dd4",
|
|
429
|
+
"evalImage": "swebench/sweb.eval.x86_64.django_1776_django-14915:zhx-a677be35326049cb",
|
|
430
|
+
"evalImageId": "sha256:a677be35326049cb42933368d879f3ecfe408c4da1fb8842b70b556e22245b6b",
|
|
431
|
+
"evalTag": "zhx-a677be35326049cb",
|
|
432
|
+
"image": "sha256:14eed0dac453442afc6e6970a22d0bfdcca453b1c0d5cdb8fd5b88a8a83b5834",
|
|
433
|
+
"checkoutHead": "76ca4f33ea42f4e92e485096ca5a06f91aa51c15",
|
|
434
|
+
"baseTree": "e11d86a000acf1f8b4d18e945abd62be478041e0",
|
|
435
|
+
"upstreamTree": "e11e4698c812238fda4177459904145cbbb1176a",
|
|
436
|
+
"imageModeDifferences": 6514
|
|
437
|
+
}
|
|
438
|
+
]
|
|
439
|
+
}
|