@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.
Files changed (170) hide show
  1. package/CHANGELOG.md +190 -0
  2. package/README.md +47 -62
  3. package/ROADMAP.md +15 -6
  4. package/SECURITY.md +1 -1
  5. package/benchmarks/README.md +48 -0
  6. package/benchmarks/baselines/context-navigation-2026-09-09.json +94 -0
  7. package/benchmarks/baselines/efficiency-2026-09-08.json +233 -0
  8. package/benchmarks/baselines/external-final-2026-09-08.json +588 -0
  9. package/benchmarks/baselines/external-intermediate-2026-09-08.json +116 -0
  10. package/benchmarks/baselines/external-matched-openai-2026-09-08.json +1922 -0
  11. package/benchmarks/baselines/external-matched-qwen-2026-09-08.json +1706 -0
  12. package/benchmarks/baselines/external-pilot-2026-09-08.json +439 -0
  13. package/benchmarks/baselines/external-qwen-flash-2026-09-08.json +1570 -0
  14. package/benchmarks/baselines/external-qwen-remediation-2026-09-09.json +1509 -0
  15. package/benchmarks/baselines/external-qwen-sdk-114-progress-2026-09-09.json +2509 -0
  16. package/benchmarks/baselines/external-sdk-upgrade-2026-09-08.json +564 -0
  17. package/benchmarks/baselines/external-verifier-recovery-2026-09-09.json +794 -0
  18. package/benchmarks/baselines/full-harness-review-2026-09-10.json +134 -0
  19. package/benchmarks/baselines/harness-audit-2026-09-09.json +136 -0
  20. package/benchmarks/baselines/harness-remediation-2026-09-09.json +160 -0
  21. package/benchmarks/baselines/oci-remediation-2026-09-10.json +535 -0
  22. package/benchmarks/baselines/rc14-holdout-2026-09-10.json +854 -0
  23. package/benchmarks/baselines/repair-architecture-audit-2026-09-09.json +75 -0
  24. package/benchmarks/baselines/time-to-safe-fix-live-expanded-2026-08-21.json +186 -0
  25. package/benchmarks/baselines/time-to-safe-fix-live-smoke-2026-08-21.json +186 -0
  26. package/contracts/public-api.json +25 -0
  27. package/contracts/security-controls.json +3 -2
  28. package/contracts/stable-api-signatures.json +58 -54
  29. package/dist/bounded-reads.d.ts +4 -0
  30. package/dist/change-envelope.d.ts +4 -4
  31. package/dist/cli-options.d.ts +2 -1
  32. package/dist/cli-profiles.d.ts +39 -0
  33. package/dist/cli-stream.d.ts +40 -40
  34. package/dist/cli.d.ts +38 -35
  35. package/dist/cli.js +6556 -4030
  36. package/dist/compaction.d.ts +12 -0
  37. package/dist/config.d.ts +6 -1
  38. package/dist/console-context.d.ts +26 -0
  39. package/dist/console-input.d.ts +28 -0
  40. package/dist/context-engineering.d.ts +5 -5
  41. package/dist/context-metrics.d.ts +11 -0
  42. package/dist/edit-contracts.d.ts +2 -2
  43. package/dist/execution-environment.d.ts +9 -5
  44. package/dist/harness.d.ts +52 -18
  45. package/dist/hostile-repository-demo.js +2942 -1088
  46. package/dist/index.d.ts +3 -3
  47. package/dist/index.js +4316 -2435
  48. package/dist/json-contracts.d.ts +292 -236
  49. package/dist/model-budget.d.ts +61 -0
  50. package/dist/operations.d.ts +82 -20
  51. package/dist/orchestration.d.ts +1 -0
  52. package/dist/providers.d.ts +5 -2
  53. package/dist/repair-controller.d.ts +72 -0
  54. package/dist/repair-progress.d.ts +40 -0
  55. package/dist/repair-verifier.d.ts +6 -0
  56. package/dist/replacement-edits.d.ts +9 -0
  57. package/dist/routing.d.ts +1 -1
  58. package/dist/run-interruption.d.ts +4 -0
  59. package/dist/runtime-checkpoints.d.ts +7 -0
  60. package/dist/runtime-diagnostics.d.ts +63 -0
  61. package/dist/runtime-policy.d.ts +36 -0
  62. package/dist/sessions.d.ts +1 -1
  63. package/dist/state-backup.d.ts +2 -2
  64. package/dist/task-memory.d.ts +36 -0
  65. package/dist/terminal-markdown.d.ts +12 -0
  66. package/dist/time-to-safe-fix.d.ts +19 -19
  67. package/dist/tool-registry.d.ts +4 -0
  68. package/dist/verify-historical-migrations.js +6987 -5140
  69. package/dist/workspace-mutation-lock.d.ts +5 -0
  70. package/dist/workspace.d.ts +39 -4
  71. package/dist/zhx.js +6556 -4030
  72. package/docs/CLI.md +89 -3
  73. package/docs/CONTEXT_ENGINEERING.md +160 -0
  74. package/docs/EXECUTION_ENVIRONMENTS.md +21 -0
  75. package/docs/EXTENSIBILITY.md +2 -2
  76. package/docs/GA_READINESS.md +13 -7
  77. package/docs/LIVE_CERTIFICATION.md +12 -2
  78. package/docs/RC13_SECURITY_REVIEW.md +28 -0
  79. package/docs/RC14_DELEGATED_SECURITY_DECISION.md +80 -0
  80. package/docs/RC14_SECURITY_REVIEW.md +40 -0
  81. package/docs/README.md +33 -0
  82. package/docs/RELEASE.md +4 -2
  83. package/docs/REPOSITORY_EDITING.md +47 -0
  84. package/docs/SECURITY_REVIEW_EVIDENCE.md +5 -3
  85. package/docs/THREAT_MODEL.md +3 -3
  86. package/docs/TIME_TO_SAFE_FIX.md +4 -4
  87. package/docs/ga-readiness.json +147 -16
  88. package/docs/reports/EFFICIENCY_REVIEW.md +156 -0
  89. package/docs/reports/EXTERNAL_COMPARISON.md +434 -0
  90. package/docs/reports/FULL_HARNESS_REVIEW_2026-09-10.md +200 -0
  91. package/docs/reports/GA_BUDGET_REMEDIATION_2026-09-19.md +38 -0
  92. package/docs/reports/GA_REPAIR_RECOVERY_2026-09-19.md +700 -0
  93. package/docs/reports/GA_VALIDATION_2026-09-19.md +111 -0
  94. package/docs/reports/HARNESS_ARCHITECTURE_REVIEW_2026-09-09.md +202 -0
  95. package/docs/reports/HARNESS_AUDIT_2026-09-09.md +306 -0
  96. package/docs/reports/HARNESS_REMEDIATION_2026-09-09.md +74 -0
  97. package/docs/reports/HARNESS_REMEDIATION_2026-09-10.md +90 -0
  98. package/docs/reports/MODEL_COMPARISON_2026-09-09.md +184 -0
  99. package/docs/reports/QWEN_REMEDIATION_COMPARISON_2026-09-09.md +142 -0
  100. package/docs/reports/RC14_VALIDATION_2026-09-10.md +45 -0
  101. package/docs/reports/README.md +26 -0
  102. package/docs/reports/evidence/ga-budget-remediation-2026-09-19.json +133 -0
  103. package/docs/reports/evidence/ga-catalog-ablation-2026-09-19.json +699 -0
  104. package/docs/reports/evidence/ga-catalog-ablation-plan-2026-09-19.json +40 -0
  105. package/docs/reports/evidence/ga-catalog-observed-2026-09-19.json +985 -0
  106. package/docs/reports/evidence/ga-catalog-observed-plan-2026-09-19.json +28 -0
  107. package/docs/reports/evidence/ga-catalog-observed-status-2026-09-19.json +15 -0
  108. package/docs/reports/evidence/ga-complete-local-check-2026-09-19.json +47 -0
  109. package/docs/reports/evidence/ga-completion-reminder-2026-09-19.json +22 -0
  110. package/docs/reports/evidence/ga-fresh-cohort-plan-2026-09-19.json +54 -0
  111. package/docs/reports/evidence/ga-fresh-cohort-preparation-2026-09-19.json +242 -0
  112. package/docs/reports/evidence/ga-fresh-cohort-result-2026-09-19.json +4318 -0
  113. package/docs/reports/evidence/ga-local-validation-followup-2026-09-19.json +66 -0
  114. package/docs/reports/evidence/ga-node-consumers-2026-09-19.json +31 -0
  115. package/docs/reports/evidence/ga-package-content-validation-2026-09-19.json +22 -0
  116. package/docs/reports/evidence/ga-plan-completion-2026-09-19.json +39 -0
  117. package/docs/reports/evidence/ga-plan-reserve-2026-09-19.json +573 -0
  118. package/docs/reports/evidence/ga-plan-reserve-plan-2026-09-19.json +24 -0
  119. package/docs/reports/evidence/ga-plan-transition-2026-09-19.json +19 -0
  120. package/docs/reports/evidence/ga-private-verifier-plan-2026-09-19.json +24 -0
  121. package/docs/reports/evidence/ga-private-verifier-root-cause-2026-09-19.json +41 -0
  122. package/docs/reports/evidence/ga-published-sdk-2026-09-19.json +35 -0
  123. package/docs/reports/evidence/ga-python-checkout-imports-2026-09-19.json +95 -0
  124. package/docs/reports/evidence/ga-python-origin-delivery-2026-09-19.json +211 -0
  125. package/docs/reports/evidence/ga-python-origin-delivery-plan-2026-09-19.json +27 -0
  126. package/docs/reports/evidence/ga-qwen-patched-package-2026-09-19.json +1092 -0
  127. package/docs/reports/evidence/ga-qwen-patched-package-plan-2026-09-19.json +18 -0
  128. package/docs/reports/evidence/ga-qwen-published-2026-09-19.json +571 -0
  129. package/docs/reports/evidence/ga-qwen-published-plan-2026-09-19.json +18 -0
  130. package/docs/reports/evidence/ga-qwen-tool-choice-2026-09-19.json +85 -0
  131. package/docs/reports/evidence/ga-qwen-tool-choice-patched-2026-09-19.json +85 -0
  132. package/docs/reports/evidence/ga-recovery-development-2026-09-19.json +1066 -0
  133. package/docs/reports/evidence/ga-recovery-graded-development-2026-09-19.json +1313 -0
  134. package/docs/reports/evidence/ga-recovery-graded-v2-2026-09-19.json +1151 -0
  135. package/docs/reports/evidence/ga-recovery-v3-2026-09-19.json +3943 -0
  136. package/docs/reports/evidence/ga-recovery-v4-2026-09-19.json +1055 -0
  137. package/docs/reports/evidence/ga-recovery-v5-2026-09-19.json +1245 -0
  138. package/docs/reports/evidence/ga-recovery-v6-2026-09-19.json +699 -0
  139. package/docs/reports/evidence/ga-recovery-v7-2026-09-19.json +854 -0
  140. package/docs/reports/evidence/ga-recovery-v8-2026-09-19.json +596 -0
  141. package/docs/reports/evidence/ga-required-delivery-2026-09-19.json +25 -0
  142. package/docs/reports/evidence/ga-required-delivery-live-2026-09-19.json +1337 -0
  143. package/docs/reports/evidence/ga-required-delivery-live-plan-2026-09-19.json +25 -0
  144. package/docs/reports/evidence/ga-retained-candidate-grading-2026-09-19.json +30 -0
  145. package/docs/reports/evidence/ga-tool-selection-live-2026-09-19.json +559 -0
  146. package/docs/reports/evidence/ga-tool-selection-live-plan-2026-09-19.json +28 -0
  147. package/docs/reports/evidence/ga-tool-selection-recovery-2026-09-19.json +27 -0
  148. package/docs/reports/evidence/ga-validation-2026-09-19.json +236 -0
  149. package/docs/reports/evidence/ga-verifier-discovery-live-2026-09-19.json +1369 -0
  150. package/docs/reports/evidence/ga-verifier-discovery-plan-2026-09-19.json +29 -0
  151. package/docs/reports/evidence/ga-verifier-failure-identification-2026-09-19.json +30 -0
  152. package/docs/reports/evidence/ga-verifier-feedback-2026-09-19.json +65 -0
  153. package/docs/reports/evidence/ga-verifier-hints-live-2026-09-19.json +1297 -0
  154. package/docs/reports/evidence/ga-verifier-hints-plan-2026-09-19.json +27 -0
  155. package/docs/reports/evidence/ga-work-boundary-context-analysis-2026-09-19.json +113 -0
  156. package/docs/reports/evidence/ga-work-boundary-live-2026-09-19.json +301 -0
  157. package/docs/reports/evidence/ga-work-boundary-live-plan-2026-09-19.json +84 -0
  158. package/docs/reports/evidence/ga-work-budget-planning-2026-09-19.json +32 -0
  159. package/docs/reports/evidence/ga-working-context-2026-09-19.json +22 -0
  160. package/docs/reports/evidence/rc14-delegated-security-review-2026-09-20.json +81 -0
  161. package/docs/reports/evidence/rc14-ga-gate-2026-09-20.json +18 -0
  162. package/docs/reports/evidence/rc14-representative-2026-09-20.json +509 -0
  163. package/docs/reports/evidence/rc14-security-regressions-2026-09-20.json +64 -0
  164. package/docs/reports/evidence/security-current-2026-09-19.json +91 -0
  165. package/docs/reports/evidence/security-remediation-2026-09-19.json +97 -0
  166. package/evaluations/repair-controller-experiment.json +24 -0
  167. package/evaluations/representative-assembly-matrix.json +63 -0
  168. package/evaluations/representative-matrix.json +2219 -2
  169. package/fixtures/contracts/v1/init.json +19 -0
  170. package/package.json +25 -16
@@ -0,0 +1,588 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "date": "2026-09-08",
4
+ "kind": "final-external-cohort",
5
+ "dataset": "princeton-nlp/SWE-bench_Verified",
6
+ "revision": "c104f840cc67f8b6eec6f759ebc8b2693d585d4a",
7
+ "model": "gpt-5.6-luna",
8
+ "seed": 20260910,
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/benchmark-swebench.ts": "ed17063e1847017ba2e72f14732b6ff8f5b1af7cd5253b91302af75f2a9e8476",
30
+ "scripts/swebench/common.py": "c19cfc30b85dc3ad8dbf1ba6a4165e72ce96f624eb1721b613cfa3207636f7be",
31
+ "scripts/swebench/mini_driver.py": "46badf61f041208b3a4428beb4e574f896a459d43ab4b7a03dc616ff04b1baf3",
32
+ "scripts/swebench/model-budget.ts": "8d2f5e33340bc9d3b44e40ad9fde7fcea32d0df20c4733d7f2e58a255bfd55cd",
33
+ "scripts/swebench/preflight.py": "f3a9fc241896eb5d63138127fea4396e59d95c277c009a29a2265ee35f4aa6eb",
34
+ "scripts/swebench/prepare.py": "8dc3695a24b49e4fbc81333f602d484431485800dcb3381130249bfe13391c20",
35
+ "scripts/swebench/report.py": "70afcdf0d1f081014bb75d878f3ddf9195959e96b523ddf1e0ad5d3ec8273549",
36
+ "scripts/swebench/run.py": "f39254bdb12ffcc2a3d39c131d02c91ff839535af6e234a0923d09b5443f459e",
37
+ "scripts/swebench/telemetry.ts": "66bb6393641de2b789e6daa2f1dcc4cb9e0c77cfcf15f351d03f606d4da262b1",
38
+ "scripts/swebench/test_contracts.py": "a8c1348f1dff2e563c139e6d3e83eb141b4f2a71f91a58e2c5c051ed2a431024",
39
+ "scripts/swebench/zhivex-driver.ts": "02153ad5812219b71d19c6fea8d01a51bc3793686090b343a53da1aaccb0ecaf",
40
+ "scripts/time-to-safe-fix-efficiency.ts": "dd20fd8839280332ae4ca80d6846e98e07ff15d79e200b206fa2ba6be2724d2f",
41
+ "src/bounded-reads.ts": "9807bb460894be3279c5425af19863d1c6e419a1582ba6910ec7e7fc35703ed6",
42
+ "src/capabilities.ts": "56fdb60a2f6e1d33b2dc26d38b6d2709807e491ba1268d47b97876c2c0591d65",
43
+ "src/change-envelope.ts": "9047ec978c9e5117965b8093ec961d855f97bbc2c3accdc79b74cfe6a0e4f01e",
44
+ "src/cli-options.ts": "97781386289e3877c1318e4c94698ca7aaf2f256b89534dfcb21e966eb7d939f",
45
+ "src/cli-profiles.ts": "4fe451f1645e95f4957597a8724fa989b3c661ae1693252bfd6e74a51d20fc74",
46
+ "src/cli-stream.ts": "5ab8a4b1b8cf0a3dfa7b5b1f9e4e0facf8f6e7f6c341bdf700a41dc8927c825e",
47
+ "src/cli.ts": "cce6f58dfbc543acdc029b188d4394cd059d940bdd361351fd877ae2d6e94880",
48
+ "src/compacted-tool-history.ts": "3bd433b9cf3e6fd3ad82e680e5cdc8512ddff380093cec2dc3d918d6f42b7fe7",
49
+ "src/compaction.ts": "3ce3933355d021c7ec8d7a9c791d9f1cd94379c44107547d0adb08145662bc2b",
50
+ "src/config.ts": "c160faaf2d9fb637c5a08a7aff65d761a12c707ed23ebb87ab0e8519e9536bf3",
51
+ "src/console-context.ts": "0ad7e4559504b9ed09ab500d615dea09af1075d357f02ec3b77f003d55d951db",
52
+ "src/console-input.ts": "dc8ea0cdbba1364db288d5156c5ff9819362c46b37ef35a98b0475b6c445b1f8",
53
+ "src/context-engineering.ts": "1995e564f6b91974e75bf66dd421ddcbea29b1f8eee59b76eb4e34c9d6d8f47e",
54
+ "src/edit-contracts.ts": "47cc3132e27f8749d54a32bbcc33bb174cf4448f0d0171b2578cdb559cf2176b",
55
+ "src/errors.ts": "e02f4eb80562a83762f908bda56c950ec6a2b78725c0c8a49f41fee0057ab903",
56
+ "src/execution-environment.ts": "8519e532dfafe4ae51bfbc81e0732267bc6aa9eec871ffde8c917aa001e358e5",
57
+ "src/file-security.ts": "4590b46c8e4b9d3891a75cd0d0ada14e0ae7b58e8e4bdf82f68df688a1fbb750",
58
+ "src/harness.ts": "82b75651065b40e27cbc71a49ce2d27eb307c6f7570f4a35201942ac487e92d6",
59
+ "src/index.ts": "f791311f14dc27105191d97bb5454748d10beab827da9aba3ea949ffc32fce7c",
60
+ "src/json-contracts.ts": "0702e5b0ff16ff6304c74b4101bd31a3fa8eabdebe267d312b56d3871a7e302c",
61
+ "src/mcp.ts": "5f3f7a35b89063264ae18ab9273b84e2e59ac8c8e611a6b64be377ba61cc1ac5",
62
+ "src/operations.ts": "0775da79208c6f5d18476cc76404e84ddda610979d9d0e5dc15035aa6999613c",
63
+ "src/orchestration.ts": "7383da1047363819e6560f51892fd4082e5337856a3d889cdc076f021273774e",
64
+ "src/package-manager.ts": "cec4666bbab2f42e0a269709631f79f9f87c2c4dbb3cafeffacfaff761069e2c",
65
+ "src/process-runtime.ts": "b7286731a0b5c96dcad0b8e3a4bf1155d0539d73303cd7ebe77ffabf858f1729",
66
+ "src/providers.ts": "70ccfc7f315cd7238e83d69b719ce4908f3b620c564cbb4f00f93e102e025602",
67
+ "src/replacement-edits.ts": "8a0efdd3a7a9fc3e5a5475916cbd17ef882265881bb61076db58673e80b72957",
68
+ "src/routing.ts": "8e7c9f5968b4bd638cbbc86b19847ca183f3418b9a298783b96a88cffa568e22",
69
+ "src/run-interruption.ts": "df99129cf2dd6b938eca629cb897c4350a7d57fe6bf0ce437f5f3f30271617df",
70
+ "src/sessions.ts": "5167c8cf36bd4b8845ee278883394700321b65397f49c1dda0cf0d0de09dd06e",
71
+ "src/sqlite-database.ts": "18765d1ca0c2f2ad87bfd82d311312dfe8a42006556f27bc21da5892ed3b044e",
72
+ "src/state-backup.ts": "b6f8f1aedeb5dce31b65c23c7ffc50030870655b58a5aaaef9989bafb9da5c68",
73
+ "src/state-directory.ts": "3711550991951e6b738a08deaa0e06da84d01864c03a9602600f592963fa3211",
74
+ "src/terminal-markdown.ts": "8cffb6ebaf25108cb2bee04956d9b2973635b010f5d7ce6be21b3ceffe3e8bfd",
75
+ "src/terminal-ui.ts": "e50025a8649d1f60efdf3af895b8639730ec2e86553fb80a61a776b11076c705",
76
+ "src/time-to-safe-fix.ts": "4add1d49c0ea209cc496c66fa2b2012dc7bcab87e678a58c8591b3c2cdc8df8a",
77
+ "src/usage-accounting.ts": "b57bf7e48037646b8c40e6c39b5983e28840487a16bb27de632a54b57ff4594b",
78
+ "src/version.ts": "b2c2f80a40adc08e8258b81e82434273f0bdfa787528b2221f14efe7f06aa747",
79
+ "src/workspace.ts": "259d0fef0621a8655c232b23dabc3df508343bb73cdb76713acd9601ca4b3cd7"
80
+ }
81
+ },
82
+ "host": {
83
+ "system": "Darwin",
84
+ "architecture": "arm64",
85
+ "python": "3.12.13",
86
+ "docker": "29.7.2"
87
+ },
88
+ "environmentDifferences": [
89
+ "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.",
90
+ "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.",
91
+ "Input/output token ceilings are checked between model requests and can overshoot by one response; outputPerTurn is sent to both APIs."
92
+ ],
93
+ "approvalPolicy": "Automated operator approves supported isolated Zhivex tools; successful approved patch import is a terminal receipt. Human wait is zero. Not a human-UX comparison.",
94
+ "excludedTaskIds": [
95
+ "astropy__astropy-14995",
96
+ "django__django-12262",
97
+ "django__django-13410",
98
+ "django__django-14915",
99
+ "django__django-15569",
100
+ "pydata__xarray-4695",
101
+ "pydata__xarray-6721",
102
+ "pytest-dev__pytest-8399",
103
+ "sympy__sympy-15809",
104
+ "sympy__sympy-20438"
105
+ ],
106
+ "excludedManifestSha256": [
107
+ "4902585186402c9fdd3e10db9c537109b5a108ba46b4e0806e259f6a8c4c15ab",
108
+ "76739783c68673b6f659d20f757a191a52213add63e46706737535484aec6f41"
109
+ ],
110
+ "tasks": [
111
+ {
112
+ "instance_id": "sympy__sympy-21930",
113
+ "repo": "sympy/sympy",
114
+ "base_commit": "de446c6d85f633271dfec1452f6f28ea783e293f",
115
+ "evalImage": "swebench/sweb.eval.x86_64.sympy_1776_sympy-21930:zhx-ac9b1c65d632e5a3",
116
+ "evalImageId": "sha256:ac9b1c65d632e5a3d1af240db144ff27ed9a70b5507705d50480ede6899125d1",
117
+ "evalTag": "zhx-ac9b1c65d632e5a3",
118
+ "image": "sha256:81c7bb0b9b74ae262830b7d4b94d042ab60c10cdbe51620c3b387262c10794fc",
119
+ "checkoutHead": "b7d17e72736ba245d24b87f8f5e8c80565066de4",
120
+ "baseTree": "a8e44f94a63624d1f4af136f7382125a0794eecf",
121
+ "upstreamTree": "a8e44f94a63624d1f4af136f7382125a0794eecf",
122
+ "imageModeDifferences": 0
123
+ },
124
+ {
125
+ "instance_id": "scikit-learn__scikit-learn-10908",
126
+ "repo": "scikit-learn/scikit-learn",
127
+ "base_commit": "67d06b18c68ee4452768f8a1e868565dd4354abf",
128
+ "evalImage": "swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-10908:zhx-8727c0f7bfb76c29",
129
+ "evalImageId": "sha256:8727c0f7bfb76c294cfef16c9fe3d0dc9ddf313e7c0fb3e8e9cbc74c4955404c",
130
+ "evalTag": "zhx-8727c0f7bfb76c29",
131
+ "image": "sha256:4da1cd215c9209495a9aa8638026733275c766ab970311d31b1b6a8f834687d8",
132
+ "checkoutHead": "de60d3cc1d489509f0d7fe1ad141171628d3d4b7",
133
+ "baseTree": "d7e9da7c13c10167281372f397c7313c52c46077",
134
+ "upstreamTree": "d7e9da7c13c10167281372f397c7313c52c46077",
135
+ "imageModeDifferences": 0
136
+ },
137
+ {
138
+ "instance_id": "django__django-15554",
139
+ "repo": "django/django",
140
+ "base_commit": "59ab3fd0e9e606d7f0f7ca26609c06ee679ece97",
141
+ "evalImage": "swebench/sweb.eval.x86_64.django_1776_django-15554:zhx-9e1bc1db0e1ec55a",
142
+ "evalImageId": "sha256:9e1bc1db0e1ec55a32f346c36671df7384a51a9ed84eed9b7e839e1405f04292",
143
+ "evalTag": "zhx-9e1bc1db0e1ec55a",
144
+ "image": "sha256:05b0c262568607baf8716c78d6bef059bf4a57a219141c6877034ee1e90a223d",
145
+ "checkoutHead": "292b4e462f63a7dfa0f9cd742e14cfa0b43727d6",
146
+ "baseTree": "9014f24e170c210492e65fe54bcbf236e7342c4a",
147
+ "upstreamTree": "9014f24e170c210492e65fe54bcbf236e7342c4a",
148
+ "imageModeDifferences": 0
149
+ },
150
+ {
151
+ "instance_id": "scikit-learn__scikit-learn-14141",
152
+ "repo": "scikit-learn/scikit-learn",
153
+ "base_commit": "3d997697fdd166eff428ea9fd35734b6a8ba113e",
154
+ "evalImage": "swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14141:zhx-c0f6a733154dad51",
155
+ "evalImageId": "sha256:c0f6a733154dad51cb8f617ca2ea09d095a6f56a1576740c2d43f9020294f2e0",
156
+ "evalTag": "zhx-c0f6a733154dad51",
157
+ "image": "sha256:a24afa6604e714bb6cf031b045f171e8b883e876534f941bb10ee36854612d6d",
158
+ "checkoutHead": "f863dd9c48aee1eb395e5ca64e675a765cea44a9",
159
+ "baseTree": "74477c0718711537b2cb5f9805ffbf9ffd072312",
160
+ "upstreamTree": "74477c0718711537b2cb5f9805ffbf9ffd072312",
161
+ "imageModeDifferences": 0
162
+ },
163
+ {
164
+ "instance_id": "django__django-11265",
165
+ "repo": "django/django",
166
+ "base_commit": "21aa2a5e785eef1f47beb1c3760fdd7d8915ae09",
167
+ "evalImage": "swebench/sweb.eval.x86_64.django_1776_django-11265:zhx-70a39003fb3ce8f0",
168
+ "evalImageId": "sha256:70a39003fb3ce8f01ee82dfeb16b09bc3714ab669d3743fb3e1e5689f18ea1ef",
169
+ "evalTag": "zhx-70a39003fb3ce8f0",
170
+ "image": "sha256:32bc939face8eeae33506b342f5a260ab00cc49d02b616c58d7ef92b20389532",
171
+ "checkoutHead": "ad2b3670a78c6db994d93f1b71bccd5d5ee4b9c4",
172
+ "baseTree": "cbaf76226fd9f842b01da4d2cd52d99d2d256be2",
173
+ "upstreamTree": "cbaf76226fd9f842b01da4d2cd52d99d2d256be2",
174
+ "imageModeDifferences": 0
175
+ }
176
+ ],
177
+ "report": {
178
+ "schemaVersion": 1,
179
+ "kind": "swebench-comparison",
180
+ "manifestSha256": "41bef4c53a58a99ccbc291b9f45f0e5e0641076913a2291e02407709abeda5e7",
181
+ "complete": true,
182
+ "candidates": {
183
+ "zhivex": {
184
+ "planned": 5,
185
+ "recorded": 5,
186
+ "resolved": 1,
187
+ "resolutionRate": 0.2,
188
+ "missing": 0,
189
+ "gradingFailures": 0,
190
+ "usageComplete": true,
191
+ "totalCostUsd": null,
192
+ "costPerResolvedUsd": null,
193
+ "resolvedP50Ms": 35303.871916024946
194
+ },
195
+ "mini-swe-agent": {
196
+ "planned": 5,
197
+ "recorded": 5,
198
+ "resolved": 2,
199
+ "resolutionRate": 0.4,
200
+ "missing": 0,
201
+ "gradingFailures": 0,
202
+ "usageComplete": true,
203
+ "totalCostUsd": null,
204
+ "costPerResolvedUsd": null,
205
+ "resolvedP50Ms": 51026.759750035126
206
+ }
207
+ },
208
+ "pairedTaskResolutionDifference": -0.2,
209
+ "pairedTaskBootstrap95": [
210
+ -0.6,
211
+ 0.0
212
+ ],
213
+ "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."
214
+ },
215
+ "samples": [
216
+ {
217
+ "candidate": "zhivex",
218
+ "instanceId": "sympy__sympy-21930",
219
+ "repetition": 0,
220
+ "status": "failed",
221
+ "failure": "EXECUTION_FAILED",
222
+ "resolved": false,
223
+ "officialResolved": false,
224
+ "gradingStatus": "completed",
225
+ "gradingMethod": "empty-patch-no-solution",
226
+ "inputTokens": 109770,
227
+ "outputTokens": 1405,
228
+ "cachedInputTokens": 89375,
229
+ "modelCalls": 14,
230
+ "toolCalls": 15,
231
+ "usageComplete": true,
232
+ "durationMs": 36313.512582999996,
233
+ "gradingDurationMs": 0.0038750004023313522,
234
+ "totalDurationMs": 38426.89483403228,
235
+ "protectedFilesChanged": [],
236
+ "patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
237
+ "costUsd": null,
238
+ "compactions": [
239
+ {
240
+ "beforeStep": 9,
241
+ "estimatedTokensBefore": 16191,
242
+ "estimatedTokensAfter": 2451
243
+ },
244
+ {
245
+ "beforeStep": 15,
246
+ "estimatedTokensBefore": 13984,
247
+ "estimatedTokensAfter": 2323
248
+ }
249
+ ],
250
+ "guardrails": [],
251
+ "thrownDiagnostic": {
252
+ "code": "EXECUTION_FAILED",
253
+ "category": "execution",
254
+ "retryable": false,
255
+ "chain": [
256
+ {
257
+ "providerReason": null,
258
+ "validationIssues": [],
259
+ "status": null,
260
+ "errorClass": "HarnessExecutionError",
261
+ "providerHints": [],
262
+ "fingerprint": "44307c15efe2937d3c485a25c58f92f1c49edc8682c93acc9d63fc7f55902d46",
263
+ "reason": "budget"
264
+ },
265
+ {
266
+ "providerReason": null,
267
+ "validationIssues": [],
268
+ "status": null,
269
+ "errorClass": "GuardrailTriggeredError",
270
+ "providerHints": [],
271
+ "fingerprint": "44307c15efe2937d3c485a25c58f92f1c49edc8682c93acc9d63fc7f55902d46",
272
+ "reason": "budget"
273
+ }
274
+ ]
275
+ }
276
+ },
277
+ {
278
+ "candidate": "mini-swe-agent",
279
+ "instanceId": "sympy__sympy-21930",
280
+ "repetition": 0,
281
+ "status": "Submitted",
282
+ "failure": null,
283
+ "resolved": false,
284
+ "officialResolved": false,
285
+ "gradingStatus": "completed",
286
+ "inputTokens": 63382,
287
+ "outputTokens": 1760,
288
+ "cachedInputTokens": 54988,
289
+ "modelCalls": 10,
290
+ "toolCalls": 12,
291
+ "usageComplete": true,
292
+ "durationMs": 43753.464707988314,
293
+ "gradingDurationMs": 30527.015165949706,
294
+ "totalDurationMs": 76162.07329201279,
295
+ "protectedFilesChanged": [],
296
+ "patchSha256": "ca1e662809a4a64f31e79e420c92d3917640414e13da8f99b3d8dbfe1e255654",
297
+ "costUsd": null
298
+ },
299
+ {
300
+ "candidate": "mini-swe-agent",
301
+ "instanceId": "scikit-learn__scikit-learn-10908",
302
+ "repetition": 0,
303
+ "status": "Submitted",
304
+ "failure": null,
305
+ "resolved": true,
306
+ "officialResolved": true,
307
+ "gradingStatus": "completed",
308
+ "inputTokens": 37875,
309
+ "outputTokens": 1739,
310
+ "cachedInputTokens": 31958,
311
+ "modelCalls": 9,
312
+ "toolCalls": 9,
313
+ "usageComplete": true,
314
+ "durationMs": 39658.867082966026,
315
+ "gradingDurationMs": 20469.47483404074,
316
+ "totalDurationMs": 61865.53675000323,
317
+ "protectedFilesChanged": [],
318
+ "patchSha256": "e5f2d5a54427ce867ca72aa5fbbd62212057a967c3aea36883c58ff3bd1cd1f5",
319
+ "costUsd": null
320
+ },
321
+ {
322
+ "candidate": "zhivex",
323
+ "instanceId": "scikit-learn__scikit-learn-10908",
324
+ "repetition": 0,
325
+ "status": "failed",
326
+ "failure": "EXECUTION_FAILED",
327
+ "resolved": false,
328
+ "officialResolved": false,
329
+ "gradingStatus": "completed",
330
+ "gradingMethod": "empty-patch-no-solution",
331
+ "inputTokens": 61923,
332
+ "outputTokens": 1022,
333
+ "cachedInputTokens": 51405,
334
+ "modelCalls": 11,
335
+ "toolCalls": 11,
336
+ "usageComplete": true,
337
+ "durationMs": 22486.702500000003,
338
+ "gradingDurationMs": 0.007875030860304832,
339
+ "totalDurationMs": 24393.029000028037,
340
+ "protectedFilesChanged": [],
341
+ "patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
342
+ "costUsd": null,
343
+ "compactions": [
344
+ {
345
+ "beforeStep": 8,
346
+ "estimatedTokensBefore": 14068,
347
+ "estimatedTokensAfter": 2460
348
+ }
349
+ ],
350
+ "guardrails": [],
351
+ "thrownDiagnostic": {
352
+ "code": "EXECUTION_FAILED",
353
+ "category": "execution",
354
+ "retryable": false,
355
+ "chain": [
356
+ {
357
+ "providerReason": null,
358
+ "validationIssues": [],
359
+ "status": null,
360
+ "errorClass": "HarnessExecutionError",
361
+ "providerHints": [],
362
+ "fingerprint": "571ffa7ac28d66e19b6bd16f27679452d0593632d00d8215db49cf64d2bc1d34",
363
+ "reason": "not allowlisted"
364
+ },
365
+ {
366
+ "providerReason": null,
367
+ "validationIssues": [],
368
+ "status": null,
369
+ "errorClass": "GuardrailTriggeredError",
370
+ "providerHints": [],
371
+ "fingerprint": "571ffa7ac28d66e19b6bd16f27679452d0593632d00d8215db49cf64d2bc1d34",
372
+ "reason": "not allowlisted"
373
+ }
374
+ ]
375
+ }
376
+ },
377
+ {
378
+ "candidate": "zhivex",
379
+ "instanceId": "django__django-15554",
380
+ "repetition": 0,
381
+ "status": "failed",
382
+ "failure": "EXECUTION_FAILED",
383
+ "resolved": false,
384
+ "officialResolved": false,
385
+ "gradingStatus": "completed",
386
+ "gradingMethod": "empty-patch-no-solution",
387
+ "inputTokens": 108608,
388
+ "outputTokens": 1050,
389
+ "cachedInputTokens": 85519,
390
+ "modelCalls": 13,
391
+ "toolCalls": 13,
392
+ "usageComplete": true,
393
+ "durationMs": 30223.128666999997,
394
+ "gradingDurationMs": 0.004749977961182594,
395
+ "totalDurationMs": 36155.90329194674,
396
+ "protectedFilesChanged": [],
397
+ "patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
398
+ "costUsd": null,
399
+ "compactions": [
400
+ {
401
+ "beforeStep": 7,
402
+ "estimatedTokensBefore": 17027,
403
+ "estimatedTokensAfter": 2392
404
+ },
405
+ {
406
+ "beforeStep": 14,
407
+ "estimatedTokensBefore": 15818,
408
+ "estimatedTokensAfter": 2262
409
+ }
410
+ ],
411
+ "guardrails": [],
412
+ "thrownDiagnostic": {
413
+ "code": "EXECUTION_FAILED",
414
+ "category": "execution",
415
+ "retryable": false,
416
+ "chain": [
417
+ {
418
+ "providerReason": null,
419
+ "validationIssues": [],
420
+ "status": null,
421
+ "errorClass": "HarnessExecutionError",
422
+ "providerHints": [],
423
+ "fingerprint": "257a5212bb68ab6203f762391a207d9c3c64d5dc57ab39da72b6941615630aff",
424
+ "reason": "budget"
425
+ },
426
+ {
427
+ "providerReason": null,
428
+ "validationIssues": [],
429
+ "status": null,
430
+ "errorClass": "GuardrailTriggeredError",
431
+ "providerHints": [],
432
+ "fingerprint": "257a5212bb68ab6203f762391a207d9c3c64d5dc57ab39da72b6941615630aff",
433
+ "reason": "budget"
434
+ }
435
+ ]
436
+ }
437
+ },
438
+ {
439
+ "candidate": "mini-swe-agent",
440
+ "instanceId": "django__django-15554",
441
+ "repetition": 0,
442
+ "status": "LimitsExceeded",
443
+ "failure": null,
444
+ "resolved": false,
445
+ "officialResolved": false,
446
+ "gradingStatus": "completed",
447
+ "inputTokens": 113398,
448
+ "outputTokens": 2488,
449
+ "cachedInputTokens": 98935,
450
+ "modelCalls": 12,
451
+ "toolCalls": 14,
452
+ "usageComplete": true,
453
+ "durationMs": 59101.23329202179,
454
+ "gradingDurationMs": 21510.963333013933,
455
+ "totalDurationMs": 82337.00520801358,
456
+ "protectedFilesChanged": [],
457
+ "patchSha256": "d899d303cd872b5a7fa9265b44ad58e897e6ca571b56de5b1edd1c3ad8c96469",
458
+ "costUsd": null
459
+ },
460
+ {
461
+ "candidate": "mini-swe-agent",
462
+ "instanceId": "scikit-learn__scikit-learn-14141",
463
+ "repetition": 0,
464
+ "status": "Submitted",
465
+ "failure": null,
466
+ "resolved": true,
467
+ "officialResolved": true,
468
+ "gradingStatus": "completed",
469
+ "inputTokens": 48594,
470
+ "outputTokens": 992,
471
+ "cachedInputTokens": 40803,
472
+ "modelCalls": 8,
473
+ "toolCalls": 8,
474
+ "usageComplete": true,
475
+ "durationMs": 28712.256375001743,
476
+ "gradingDurationMs": 20437.585500010755,
477
+ "totalDurationMs": 51026.759750035126,
478
+ "protectedFilesChanged": [],
479
+ "patchSha256": "1650dcf9f4fe3e202d584bc014b3a0b054812ba3138f5c710b35c8d10f883172",
480
+ "costUsd": null
481
+ },
482
+ {
483
+ "candidate": "zhivex",
484
+ "instanceId": "scikit-learn__scikit-learn-14141",
485
+ "repetition": 0,
486
+ "status": "completed",
487
+ "failure": null,
488
+ "resolved": true,
489
+ "officialResolved": true,
490
+ "gradingStatus": "completed",
491
+ "inputTokens": 38637,
492
+ "outputTokens": 637,
493
+ "cachedInputTokens": 31743,
494
+ "modelCalls": 6,
495
+ "toolCalls": 7,
496
+ "usageComplete": true,
497
+ "durationMs": 12561.703917,
498
+ "gradingDurationMs": 20575.091709033586,
499
+ "totalDurationMs": 35303.871916024946,
500
+ "protectedFilesChanged": [],
501
+ "patchSha256": "c8e5d23fa74e9c51166898ccadad0fb3550252a530cbb9cb1afd74da1ad160d8",
502
+ "costUsd": null,
503
+ "compactions": [],
504
+ "guardrails": [],
505
+ "thrownDiagnostic": null
506
+ },
507
+ {
508
+ "candidate": "zhivex",
509
+ "instanceId": "django__django-11265",
510
+ "repetition": 0,
511
+ "status": "failed",
512
+ "failure": null,
513
+ "resolved": false,
514
+ "officialResolved": false,
515
+ "gradingStatus": "completed",
516
+ "gradingMethod": "empty-patch-no-solution",
517
+ "inputTokens": 103654,
518
+ "outputTokens": 1349,
519
+ "cachedInputTokens": 82882,
520
+ "modelCalls": 13,
521
+ "toolCalls": 14,
522
+ "usageComplete": true,
523
+ "durationMs": 30578.890375,
524
+ "gradingDurationMs": 0.0037499703466892242,
525
+ "totalDurationMs": 36611.47362500196,
526
+ "protectedFilesChanged": [],
527
+ "patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
528
+ "costUsd": null,
529
+ "compactions": [
530
+ {
531
+ "beforeStep": 7,
532
+ "estimatedTokensBefore": 18334,
533
+ "estimatedTokensAfter": 3871
534
+ }
535
+ ],
536
+ "guardrails": [
537
+ {
538
+ "stage": "output",
539
+ "budgetLimit": "maxInputTokens"
540
+ }
541
+ ],
542
+ "thrownDiagnostic": null
543
+ },
544
+ {
545
+ "candidate": "mini-swe-agent",
546
+ "instanceId": "django__django-11265",
547
+ "repetition": 0,
548
+ "status": "Submitted",
549
+ "failure": null,
550
+ "resolved": false,
551
+ "officialResolved": false,
552
+ "gradingStatus": "completed",
553
+ "inputTokens": 68305,
554
+ "outputTokens": 1767,
555
+ "cachedInputTokens": 57620,
556
+ "modelCalls": 9,
557
+ "toolCalls": 13,
558
+ "usageComplete": true,
559
+ "durationMs": 38476.34570900118,
560
+ "gradingDurationMs": 26749.848500010557,
561
+ "totalDurationMs": 67099.94679200463,
562
+ "protectedFilesChanged": [],
563
+ "patchSha256": "eae54f8d808244d0b0e7c17c38d022f6e3d3d461dbe119bdc2cbb93a5069c6d9",
564
+ "costUsd": null
565
+ }
566
+ ],
567
+ "rawSamplesSha256": "3127eab6724c58d70b6d50b1681c3c3e711565dec77bcf285d75726d8e18878f",
568
+ "validation": {
569
+ "checkPassed": true,
570
+ "testsPassed": 427,
571
+ "preflightPassed": 5,
572
+ "sourceHashesVerifiedAfterRun": true,
573
+ "offlineAccountingControl": {
574
+ "modelResponses": 3,
575
+ "inputTokensPerResponse": 100,
576
+ "beforeReportedInputTokens": 500,
577
+ "afterReportedInputTokens": 300
578
+ }
579
+ },
580
+ "limitations": [
581
+ "Five tasks and one repetition; exploratory local evidence, no general superiority claim.",
582
+ "This cohort differs from earlier pilot/intermediate selections, so changes in success rate do not measure causal improvement.",
583
+ "No pricing rates supplied; monetary costs unknown. Earlier interrupted/failed development attempts can have incomplete billed usage.",
584
+ "Native approvals, tools, filesystem policies and terminal import differ from upstream mini submission.",
585
+ "Local macOS ARM host emulates Linux AMD64; no general latency claim.",
586
+ "The intermediate cohort exposed duplicate SDK usage accounting and remains separate; all its tasks were excluded here."
587
+ ]
588
+ }