@zhivex-ai/harness 1.0.0 → 1.1.0-rc.2

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 (181) hide show
  1. package/CHANGELOG.md +97 -1
  2. package/README.md +52 -306
  3. package/SECURITY.md +1 -1
  4. package/SUPPORT.md +7 -3
  5. package/benchmarks/README.md +3 -3
  6. package/contracts/client-protocol-v1.schema.json +341 -0
  7. package/contracts/public-api.json +100 -1
  8. package/contracts/stable-api-signatures.json +14 -14
  9. package/dist/approval-diff.d.ts +45 -0
  10. package/dist/approval-history.d.ts +38 -0
  11. package/dist/approval-preview.d.ts +26 -0
  12. package/dist/cli-credentials.d.ts +38 -0
  13. package/dist/cli-help.d.ts +3 -0
  14. package/dist/cli-options.d.ts +1 -1
  15. package/dist/cli-stream.d.ts +3 -3
  16. package/dist/cli.d.ts +15 -69
  17. package/dist/cli.js +13796 -10032
  18. package/dist/client-contract.d.ts +208 -0
  19. package/dist/console-commands.d.ts +6 -0
  20. package/dist/console-context.d.ts +5 -1
  21. package/dist/console-input.d.ts +44 -4
  22. package/dist/console-model-catalog.d.ts +25 -0
  23. package/dist/console-navigation.d.ts +27 -0
  24. package/dist/console-presentation.d.ts +18 -0
  25. package/dist/console-welcome.d.ts +13 -0
  26. package/dist/execution-environment.d.ts +4 -0
  27. package/dist/harness.d.ts +3 -0
  28. package/dist/hostile-repository-demo.js +1913 -798
  29. package/dist/index.d.ts +7 -0
  30. package/dist/index.js +7908 -6330
  31. package/dist/local-service.d.ts +34 -0
  32. package/dist/operations.d.ts +23 -1
  33. package/dist/orchestration.d.ts +3 -0
  34. package/dist/persistence-secrets.d.ts +2 -0
  35. package/dist/recorded-workspace.d.ts +4 -0
  36. package/dist/run-document.d.ts +91 -0
  37. package/dist/runtime-policy.d.ts +4 -4
  38. package/dist/service-cli.d.ts +2 -0
  39. package/dist/service-cli.js +10858 -0
  40. package/dist/service-client-cli.d.ts +2 -0
  41. package/dist/service-events.d.ts +50 -0
  42. package/dist/sessions.d.ts +3 -0
  43. package/dist/sqlite-access.d.ts +26 -0
  44. package/dist/sqlite-database.d.ts +2 -0
  45. package/dist/state-backup.d.ts +8 -0
  46. package/dist/task-memory.d.ts +2 -2
  47. package/dist/terminal-continuation.d.ts +3 -0
  48. package/dist/terminal-markdown.d.ts +1 -0
  49. package/dist/terminal-ui.d.ts +5 -0
  50. package/dist/usage-ledger.d.ts +84 -0
  51. package/dist/verify-historical-migrations.js +5699 -5191
  52. package/dist/workspace.d.ts +22 -0
  53. package/dist/zhx.js +13796 -10032
  54. package/docs/CLI.md +136 -30
  55. package/docs/CLIENT_PROTOCOL.md +212 -0
  56. package/docs/CREDENTIALS.md +59 -0
  57. package/docs/DURABLE_OPERATIONS.md +2 -2
  58. package/docs/FIRST_USE.md +82 -0
  59. package/docs/FIRST_USE_EXAMPLE.md +40 -0
  60. package/docs/HOSTILE_REPOSITORY_DEMO.md +1 -1
  61. package/docs/LOCAL_SERVICE.md +142 -0
  62. package/docs/README.md +24 -23
  63. package/docs/THREAT_MODEL.md +1 -1
  64. package/docs/TIME_TO_SAFE_FIX.md +2 -2
  65. package/docs/USAGE.md +181 -0
  66. package/evaluations/daily-cli-cohort.json +33 -0
  67. package/evaluations/representative-assembly-matrix.json +19 -1
  68. package/examples/README.md +26 -0
  69. package/examples/first-use/greeting.test.ts +3 -0
  70. package/examples/first-use/greeting.ts +1 -0
  71. package/examples/first-use/package.json +7 -0
  72. package/package.json +34 -9
  73. package/ROADMAP.md +0 -414
  74. package/benchmarks/baselines/context-navigation-2026-09-09.json +0 -94
  75. package/benchmarks/baselines/efficiency-2026-09-08.json +0 -233
  76. package/benchmarks/baselines/external-final-2026-09-08.json +0 -588
  77. package/benchmarks/baselines/external-intermediate-2026-09-08.json +0 -116
  78. package/benchmarks/baselines/external-matched-openai-2026-09-08.json +0 -1922
  79. package/benchmarks/baselines/external-matched-qwen-2026-09-08.json +0 -1706
  80. package/benchmarks/baselines/external-pilot-2026-09-08.json +0 -439
  81. package/benchmarks/baselines/external-qwen-flash-2026-09-08.json +0 -1570
  82. package/benchmarks/baselines/external-qwen-remediation-2026-09-09.json +0 -1509
  83. package/benchmarks/baselines/external-qwen-sdk-114-progress-2026-09-09.json +0 -2509
  84. package/benchmarks/baselines/external-sdk-upgrade-2026-09-08.json +0 -564
  85. package/benchmarks/baselines/external-verifier-recovery-2026-09-09.json +0 -794
  86. package/benchmarks/baselines/full-harness-review-2026-09-10.json +0 -134
  87. package/benchmarks/baselines/harness-audit-2026-09-09.json +0 -136
  88. package/benchmarks/baselines/harness-remediation-2026-09-09.json +0 -160
  89. package/benchmarks/baselines/oci-remediation-2026-09-10.json +0 -535
  90. package/benchmarks/baselines/rc14-holdout-2026-09-10.json +0 -854
  91. package/benchmarks/baselines/repair-architecture-audit-2026-09-09.json +0 -75
  92. package/benchmarks/baselines/time-to-safe-fix-live-expanded-2026-08-21.json +0 -186
  93. package/benchmarks/baselines/time-to-safe-fix-live-smoke-2026-08-21.json +0 -186
  94. package/docs/GA_READINESS.md +0 -29
  95. package/docs/GEMINI_1_0_DECISION.md +0 -9
  96. package/docs/LIVE_CERTIFICATION.md +0 -107
  97. package/docs/RC13_SECURITY_REVIEW.md +0 -28
  98. package/docs/RC14_DELEGATED_SECURITY_DECISION.md +0 -80
  99. package/docs/RC14_SECURITY_REVIEW.md +0 -40
  100. package/docs/RELEASE.md +0 -96
  101. package/docs/ROLLBACK.md +0 -9
  102. package/docs/SECURITY_REVIEW_EVIDENCE.md +0 -17
  103. package/docs/ga-readiness.json +0 -366
  104. package/docs/reports/EFFICIENCY_REVIEW.md +0 -156
  105. package/docs/reports/EXTERNAL_COMPARISON.md +0 -434
  106. package/docs/reports/FULL_HARNESS_REVIEW_2026-09-10.md +0 -200
  107. package/docs/reports/GA_BUDGET_REMEDIATION_2026-09-19.md +0 -38
  108. package/docs/reports/GA_REPAIR_RECOVERY_2026-09-19.md +0 -700
  109. package/docs/reports/GA_VALIDATION_2026-09-19.md +0 -111
  110. package/docs/reports/HARNESS_ARCHITECTURE_REVIEW_2026-09-09.md +0 -202
  111. package/docs/reports/HARNESS_AUDIT_2026-09-09.md +0 -306
  112. package/docs/reports/HARNESS_REMEDIATION_2026-09-09.md +0 -74
  113. package/docs/reports/HARNESS_REMEDIATION_2026-09-10.md +0 -90
  114. package/docs/reports/MODEL_COMPARISON_2026-09-09.md +0 -184
  115. package/docs/reports/QWEN_REMEDIATION_COMPARISON_2026-09-09.md +0 -142
  116. package/docs/reports/RC14_VALIDATION_2026-09-10.md +0 -45
  117. package/docs/reports/README.md +0 -26
  118. package/docs/reports/evidence/ga-budget-remediation-2026-09-19.json +0 -133
  119. package/docs/reports/evidence/ga-catalog-ablation-2026-09-19.json +0 -699
  120. package/docs/reports/evidence/ga-catalog-ablation-plan-2026-09-19.json +0 -40
  121. package/docs/reports/evidence/ga-catalog-observed-2026-09-19.json +0 -985
  122. package/docs/reports/evidence/ga-catalog-observed-plan-2026-09-19.json +0 -28
  123. package/docs/reports/evidence/ga-catalog-observed-status-2026-09-19.json +0 -15
  124. package/docs/reports/evidence/ga-complete-local-check-2026-09-19.json +0 -47
  125. package/docs/reports/evidence/ga-completion-reminder-2026-09-19.json +0 -22
  126. package/docs/reports/evidence/ga-fresh-cohort-plan-2026-09-19.json +0 -54
  127. package/docs/reports/evidence/ga-fresh-cohort-preparation-2026-09-19.json +0 -242
  128. package/docs/reports/evidence/ga-fresh-cohort-result-2026-09-19.json +0 -4318
  129. package/docs/reports/evidence/ga-local-validation-followup-2026-09-19.json +0 -66
  130. package/docs/reports/evidence/ga-node-consumers-2026-09-19.json +0 -31
  131. package/docs/reports/evidence/ga-package-content-validation-2026-09-19.json +0 -22
  132. package/docs/reports/evidence/ga-plan-completion-2026-09-19.json +0 -39
  133. package/docs/reports/evidence/ga-plan-reserve-2026-09-19.json +0 -573
  134. package/docs/reports/evidence/ga-plan-reserve-plan-2026-09-19.json +0 -24
  135. package/docs/reports/evidence/ga-plan-transition-2026-09-19.json +0 -19
  136. package/docs/reports/evidence/ga-private-verifier-plan-2026-09-19.json +0 -24
  137. package/docs/reports/evidence/ga-private-verifier-root-cause-2026-09-19.json +0 -41
  138. package/docs/reports/evidence/ga-published-sdk-2026-09-19.json +0 -35
  139. package/docs/reports/evidence/ga-python-checkout-imports-2026-09-19.json +0 -95
  140. package/docs/reports/evidence/ga-python-origin-delivery-2026-09-19.json +0 -211
  141. package/docs/reports/evidence/ga-python-origin-delivery-plan-2026-09-19.json +0 -27
  142. package/docs/reports/evidence/ga-qwen-patched-package-2026-09-19.json +0 -1092
  143. package/docs/reports/evidence/ga-qwen-patched-package-plan-2026-09-19.json +0 -18
  144. package/docs/reports/evidence/ga-qwen-published-2026-09-19.json +0 -571
  145. package/docs/reports/evidence/ga-qwen-published-plan-2026-09-19.json +0 -18
  146. package/docs/reports/evidence/ga-qwen-tool-choice-2026-09-19.json +0 -85
  147. package/docs/reports/evidence/ga-qwen-tool-choice-patched-2026-09-19.json +0 -85
  148. package/docs/reports/evidence/ga-recovery-development-2026-09-19.json +0 -1066
  149. package/docs/reports/evidence/ga-recovery-graded-development-2026-09-19.json +0 -1313
  150. package/docs/reports/evidence/ga-recovery-graded-v2-2026-09-19.json +0 -1151
  151. package/docs/reports/evidence/ga-recovery-v3-2026-09-19.json +0 -3943
  152. package/docs/reports/evidence/ga-recovery-v4-2026-09-19.json +0 -1055
  153. package/docs/reports/evidence/ga-recovery-v5-2026-09-19.json +0 -1245
  154. package/docs/reports/evidence/ga-recovery-v6-2026-09-19.json +0 -699
  155. package/docs/reports/evidence/ga-recovery-v7-2026-09-19.json +0 -854
  156. package/docs/reports/evidence/ga-recovery-v8-2026-09-19.json +0 -596
  157. package/docs/reports/evidence/ga-required-delivery-2026-09-19.json +0 -25
  158. package/docs/reports/evidence/ga-required-delivery-live-2026-09-19.json +0 -1337
  159. package/docs/reports/evidence/ga-required-delivery-live-plan-2026-09-19.json +0 -25
  160. package/docs/reports/evidence/ga-retained-candidate-grading-2026-09-19.json +0 -30
  161. package/docs/reports/evidence/ga-tool-selection-live-2026-09-19.json +0 -559
  162. package/docs/reports/evidence/ga-tool-selection-live-plan-2026-09-19.json +0 -28
  163. package/docs/reports/evidence/ga-tool-selection-recovery-2026-09-19.json +0 -27
  164. package/docs/reports/evidence/ga-validation-2026-09-19.json +0 -236
  165. package/docs/reports/evidence/ga-verifier-discovery-live-2026-09-19.json +0 -1369
  166. package/docs/reports/evidence/ga-verifier-discovery-plan-2026-09-19.json +0 -29
  167. package/docs/reports/evidence/ga-verifier-failure-identification-2026-09-19.json +0 -30
  168. package/docs/reports/evidence/ga-verifier-feedback-2026-09-19.json +0 -65
  169. package/docs/reports/evidence/ga-verifier-hints-live-2026-09-19.json +0 -1297
  170. package/docs/reports/evidence/ga-verifier-hints-plan-2026-09-19.json +0 -27
  171. package/docs/reports/evidence/ga-work-boundary-context-analysis-2026-09-19.json +0 -113
  172. package/docs/reports/evidence/ga-work-boundary-live-2026-09-19.json +0 -301
  173. package/docs/reports/evidence/ga-work-boundary-live-plan-2026-09-19.json +0 -84
  174. package/docs/reports/evidence/ga-work-budget-planning-2026-09-19.json +0 -32
  175. package/docs/reports/evidence/ga-working-context-2026-09-19.json +0 -22
  176. package/docs/reports/evidence/rc14-delegated-security-review-2026-09-20.json +0 -81
  177. package/docs/reports/evidence/rc14-ga-gate-2026-09-20.json +0 -18
  178. package/docs/reports/evidence/rc14-representative-2026-09-20.json +0 -509
  179. package/docs/reports/evidence/rc14-security-regressions-2026-09-20.json +0 -64
  180. package/docs/reports/evidence/security-current-2026-09-19.json +0 -91
  181. package/docs/reports/evidence/security-remediation-2026-09-19.json +0 -97
@@ -1,699 +0,0 @@
1
- {
2
- "schemaVersion": 1,
3
- "kind": "diagnostic-tool-catalog-ablation",
4
- "classification": "Known development task; experimental driver, not product or GA acceptance",
5
- "plan": "ga-catalog-ablation-plan-2026-09-19.json",
6
- "implementation": {
7
- "gitCommit": "c2b2bb917d0471e61afc5f731a61c00b44fa3731",
8
- "sources": {
9
- "bun.lock": "e370459197ce52c3961770f3c5ccaab7ff35ddbe641ef72e8bd61f87a8b8e3fe",
10
- "evaluations/external/requirements.lock": "42e90a08f10f821ebb958af79256f707a9fb5cf365277c4f9e2715d612028179",
11
- "package.json": "a4a2507e3ad876d72cad49a16e149192d33521fb4175bb40a3eb077ccfdf43a1",
12
- "scripts/benchmark-swebench.ts": "ed17063e1847017ba2e72f14732b6ff8f5b1af7cd5253b91302af75f2a9e8476",
13
- "scripts/swebench/candidate.py": "f5e3410b91b950acfbe50fc7511891816a8fb1c223082397e2c6300cf1e866cf",
14
- "scripts/swebench/candidate.ts": "bf102becfcce0c9a3f0df0a8f1ce0e5aaea7db2d252f6d9454a8370c24e53982",
15
- "scripts/swebench/common.py": "ad790227dac3bec1f592c458c993efff4f9d3de8f0df39b33e3238b58b3f0b3b",
16
- "scripts/swebench/context-metrics.ts": "7b84da6789413aa634d997c5963ee6796584e06c3eafe5f68f424fb7e27815e9",
17
- "scripts/swebench/mini_driver.py": "bd0a77221878370ec44760122a51f07fb56d969612afa9a7f171248b2958baa6",
18
- "scripts/swebench/model-budget.ts": "e46dd406ee5d58a051a15c7d7133513666292303d8c6534f861a6db0e711f47c",
19
- "scripts/swebench/preflight.py": "aed092a75dd52f504fba6d14814b69bd627ff17d0e311a1f1279f8b613b69675",
20
- "scripts/swebench/prepare.py": "bb7edd3fba5dbbe26597c97d744c60b94dbb7bcdfd7740a4a058c8583bd27e4c",
21
- "scripts/swebench/report.py": "d0b8d45f32c48e0ba2cb977f50838065a497a0ecaf3b4243ed94139393ce4d6b",
22
- "scripts/swebench/run.py": "94dccd55dfe6f70d8f8f2da70331700ec85eddd958547e0c3afe3dc416c9802c",
23
- "scripts/swebench/telemetry.ts": "743c9baf273e9240d704d098b6bd5eea9e76ef3e49ae636aaafa9bfd7a85b45b",
24
- "scripts/swebench/test_candidate.py": "e77d16379b748baa2daf184a45ea62587d938b6a7d48dcf9f6061f8af21fafd9",
25
- "scripts/swebench/test_contracts.py": "902e966d0fbf8501dbb15e011849f160331c033cd2a5480f9920d0f365a08d03",
26
- "scripts/swebench/zhivex-driver.ts": "8d68286b42979a603dcded8860133e134d351f25aedb5dd98ed2ef6f810cbd74",
27
- "scripts/time-to-safe-fix-efficiency.ts": "dd20fd8839280332ae4ca80d6846e98e07ff15d79e200b206fa2ba6be2724d2f",
28
- "src/bounded-reads.ts": "9807bb460894be3279c5425af19863d1c6e419a1582ba6910ec7e7fc35703ed6",
29
- "src/capabilities.ts": "56fdb60a2f6e1d33b2dc26d38b6d2709807e491ba1268d47b97876c2c0591d65",
30
- "src/change-envelope.ts": "9047ec978c9e5117965b8093ec961d855f97bbc2c3accdc79b74cfe6a0e4f01e",
31
- "src/cli-options.ts": "f48d9be132fed38f2ddbcfecbd8222c664a0df2f20edc28ce8d1b9b1a1900863",
32
- "src/cli-profiles.ts": "4fe451f1645e95f4957597a8724fa989b3c661ae1693252bfd6e74a51d20fc74",
33
- "src/cli-stream.ts": "5ab8a4b1b8cf0a3dfa7b5b1f9e4e0facf8f6e7f6c341bdf700a41dc8927c825e",
34
- "src/cli.ts": "5a4acb4695a968a58fbeac05c4bb89848a9653d6189590f0ff90e430ffa98d14",
35
- "src/compaction.ts": "9e06a0abeeef155377f40c160b21c56256bca95ec18c5ee897681a5fc73db169",
36
- "src/config.ts": "b1d3991e84add58603fb85b2a604b9b3eb56ae879d0fa30b0cb40545fa44edc1",
37
- "src/console-context.ts": "0ad7e4559504b9ed09ab500d615dea09af1075d357f02ec3b77f003d55d951db",
38
- "src/console-input.ts": "dc8ea0cdbba1364db288d5156c5ff9819362c46b37ef35a98b0475b6c445b1f8",
39
- "src/context-engineering.ts": "1995e564f6b91974e75bf66dd421ddcbea29b1f8eee59b76eb4e34c9d6d8f47e",
40
- "src/context-metrics.ts": "3eb30f9db808f918ed8d73d4f8ac19a13acb09ed5c1ee70fdae05201714b9198",
41
- "src/edit-contracts.ts": "47cc3132e27f8749d54a32bbcc33bb174cf4448f0d0171b2578cdb559cf2176b",
42
- "src/errors.ts": "e02f4eb80562a83762f908bda56c950ec6a2b78725c0c8a49f41fee0057ab903",
43
- "src/execution-environment.ts": "9ce6c49afab26527d5296f0c11f106063590f7333300d58dd49d5a1ec1b4b6e9",
44
- "src/file-security.ts": "b8c9f4988c4339c73a60ab4fa8d394b3eecc19117a0c61a8d19ab6483ca253df",
45
- "src/harness.ts": "195983cfbacb6097a5c8c2a106e59c3fae2437f053299da1c0170dd914879c8d",
46
- "src/index.ts": "4bbfcd11376d48c4f1c1ec17d6b5c9f51baa9331fa999432be178bae94530a5e",
47
- "src/json-contracts.ts": "0780145636b47829a1aa6087c574d5654eb31b7534ea7d9c38c188d648c90272",
48
- "src/mcp.ts": "7722de031921c620ec03b9e42a6596ef8415aa8e4bb5f93ea84d2427c466e554",
49
- "src/model-budget.ts": "97c00019d7e737fc7acdd04cdac0811dca8d85c3e858de519ebba91888cf1ee7",
50
- "src/operations.ts": "bcccaf4d1d0ec117c2ed35df92185564d33399e5fdc5c12225ac61f14fd0b4b1",
51
- "src/orchestration.ts": "b56c8c7d526a99b745cc17769e0a1b7b500b25920e77f34aa0dd01c9758de319",
52
- "src/package-manager.ts": "cec4666bbab2f42e0a269709631f79f9f87c2c4dbb3cafeffacfaff761069e2c",
53
- "src/process-runtime.ts": "b7286731a0b5c96dcad0b8e3a4bf1155d0539d73303cd7ebe77ffabf858f1729",
54
- "src/providers.ts": "70ccfc7f315cd7238e83d69b719ce4908f3b620c564cbb4f00f93e102e025602",
55
- "src/repair-controller.ts": "2c05370e93978a5bf106b2cee293478a77b47920cec7470f536b31757198f41c",
56
- "src/repair-progress.ts": "cf30117ab69564f2b36ff8f0e86dcb876e6c031647340a7b1bef648d1e0366b9",
57
- "src/repair-verifier.ts": "b70fb11feee8cdc7933947ccac0b78f8bb5c0eaccc3b29ad527197d77f40ffc9",
58
- "src/replacement-edits.ts": "8a0efdd3a7a9fc3e5a5475916cbd17ef882265881bb61076db58673e80b72957",
59
- "src/routing.ts": "8e7c9f5968b4bd638cbbc86b19847ca183f3418b9a298783b96a88cffa568e22",
60
- "src/run-interruption.ts": "df99129cf2dd6b938eca629cb897c4350a7d57fe6bf0ce437f5f3f30271617df",
61
- "src/runtime-checkpoints.ts": "e3b75a0b86fb5d21992b1a126b35446110ba5fcaf4317ed5005b1a44555118dc",
62
- "src/runtime-diagnostics.ts": "e1e5a3a558fa2aaeb477335dc336551f022c1234fe5e742eefc6599c8803e364",
63
- "src/runtime-policy.ts": "8356acf0102f0e73839b81ed628a5c0d9a89d9c21b0ca416efedde8f1b3414e2",
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/task-memory.ts": "5b62c863be5a23c33608633cd7aac0464f5536d01cba930aca58b11870170731",
69
- "src/terminal-markdown.ts": "8cffb6ebaf25108cb2bee04956d9b2973635b010f5d7ce6be21b3ceffe3e8bfd",
70
- "src/terminal-ui.ts": "4da1878a76ba608a2517bf5d5c992a9a88702aba3fd800a9980129ba93e157bc",
71
- "src/time-to-safe-fix.ts": "4add1d49c0ea209cc496c66fa2b2012dc7bcab87e678a58c8591b3c2cdc8df8a",
72
- "src/tool-registry.ts": "7e90fff11940e525883c9ec0d2adbea2e6616f8bd9bc4ec77e1b7277e4217f2c",
73
- "src/version.ts": "b2c2f80a40adc08e8258b81e82434273f0bdfa787528b2221f14efe7f06aa747",
74
- "src/workspace-mutation-lock.ts": "ca201242db16173bd3a4d86c5d8bb0c2b6f3c43bfed3e4fa4ff5f06a75b19e80",
75
- "src/workspace.ts": "809f8bbfcf72fed10d860c48585089ca65bb3ef7c672ee6df3c918907a968302"
76
- }
77
- },
78
- "model": "qwen3.8-flash",
79
- "limits": {
80
- "steps": 24,
81
- "outputPerTurn": 2048,
82
- "inputTokens": 100000,
83
- "outputTokens": 16000,
84
- "timeoutSeconds": 300,
85
- "memoryMb": 2048,
86
- "cpus": 2
87
- },
88
- "samples": [
89
- {
90
- "candidate": "zhivex",
91
- "instanceId": "django__django-15851",
92
- "repetition": 0,
93
- "resolved": false,
94
- "gradingStatus": "completed",
95
- "usageComplete": true,
96
- "costUsd": null,
97
- "candidateCaptureFailure": null,
98
- "modelTimings": [
99
- {
100
- "durationMs": 2857.5545,
101
- "firstTokenMs": 2856.44675,
102
- "completed": true
103
- },
104
- {
105
- "durationMs": 1765.3069590000014,
106
- "firstTokenMs": 1764.9363750000011,
107
- "completed": true
108
- },
109
- {
110
- "durationMs": 1971.8102500000023,
111
- "firstTokenMs": 1971.582500000004,
112
- "completed": true
113
- },
114
- {
115
- "durationMs": 1423.2325410000049,
116
- "firstTokenMs": 1423.1229160000003,
117
- "completed": true
118
- },
119
- {
120
- "durationMs": 1604.3790000000008,
121
- "firstTokenMs": 1604.1530829999974,
122
- "completed": true
123
- },
124
- {
125
- "durationMs": 1363.2940420000086,
126
- "firstTokenMs": 1362.9413330000098,
127
- "completed": true
128
- },
129
- {
130
- "durationMs": 3342.460540999993,
131
- "firstTokenMs": 3341.9722499999916,
132
- "completed": true
133
- },
134
- {
135
- "durationMs": 1671.2688750000088,
136
- "firstTokenMs": 1671.0233750000043,
137
- "completed": true
138
- },
139
- {
140
- "durationMs": 13546.226541000011,
141
- "firstTokenMs": 13545.892208000005,
142
- "completed": true
143
- }
144
- ],
145
- "stageTimings": [
146
- {
147
- "event": "command-requested",
148
- "elapsedMs": 6210.767709
149
- }
150
- ],
151
- "approvalTimings": [
152
- {
153
- "durationMs": 0.08533399999942048,
154
- "resolved": true
155
- },
156
- {
157
- "durationMs": 0.06737500000235741,
158
- "resolved": true
159
- },
160
- {
161
- "durationMs": 0.01600000000325963,
162
- "resolved": true
163
- },
164
- {
165
- "durationMs": 0.022415999999793712,
166
- "resolved": true
167
- },
168
- {
169
- "durationMs": 0.02399999999033753,
170
- "resolved": true
171
- },
172
- {
173
- "durationMs": 0.02983299999323208,
174
- "resolved": true
175
- },
176
- {
177
- "durationMs": 0.03674999999930151,
178
- "resolved": true
179
- }
180
- ],
181
- "toolTimings": [
182
- {
183
- "name": "run_environment_shell",
184
- "calls": 7,
185
- "errors": 0,
186
- "totalMs": 89482.442086,
187
- "maxMs": 13939.199584000002
188
- },
189
- {
190
- "name": "repair_plan",
191
- "calls": 1,
192
- "errors": 0,
193
- "totalMs": 0.08249999998952262,
194
- "maxMs": 0.08249999998952262
195
- }
196
- ],
197
- "schemaVersion": 1,
198
- "status": "failed",
199
- "failure": "EXECUTION_FAILED",
200
- "phase": "agent",
201
- "durationMs": 141427.978167,
202
- "approvals": 7,
203
- "turns": [
204
- {
205
- "index": 1,
206
- "status": "waiting_approval",
207
- "finishReason": "tool-calls",
208
- "requestedTools": [
209
- "run_environment_shell"
210
- ],
211
- "inputTokens": 2628,
212
- "outputTokens": 59,
213
- "cachedInputTokens": 0,
214
- "requestCharacters": 6814,
215
- "tools": []
216
- },
217
- {
218
- "index": 2,
219
- "status": "waiting_approval",
220
- "finishReason": "tool-calls",
221
- "requestedTools": [
222
- "run_environment_shell"
223
- ],
224
- "inputTokens": 3004,
225
- "outputTokens": 61,
226
- "cachedInputTokens": 2048,
227
- "requestCharacters": 8045,
228
- "tools": [
229
- {
230
- "name": "run_environment_shell",
231
- "isError": false,
232
- "characters": 527,
233
- "phaseLatencies": {
234
- "commandAndAttestationMs": 2852.733541,
235
- "workspaceExportMs": 6749.016,
236
- "totalMs": 13525.643375,
237
- "sessionCreationMs": 3923.315709
238
- },
239
- "exitCode": 0,
240
- "timedOut": false
241
- }
242
- ]
243
- },
244
- {
245
- "index": 3,
246
- "status": "waiting_approval",
247
- "finishReason": "tool-calls",
248
- "requestedTools": [
249
- "run_environment_shell"
250
- ],
251
- "inputTokens": 4115,
252
- "outputTokens": 80,
253
- "cachedInputTokens": 2048,
254
- "requestCharacters": 12232,
255
- "tools": [
256
- {
257
- "name": "run_environment_shell",
258
- "isError": false,
259
- "characters": 3462,
260
- "phaseLatencies": {
261
- "commandAndAttestationMs": 2308.533958,
262
- "workspaceExportMs": 7081.781625,
263
- "totalMs": 11503.703292,
264
- "sessionCreationMs": 2113.314875
265
- },
266
- "exitCode": 0,
267
- "timedOut": false
268
- }
269
- ]
270
- },
271
- {
272
- "index": 4,
273
- "status": "waiting_approval",
274
- "finishReason": "tool-calls",
275
- "requestedTools": [
276
- "run_environment_shell"
277
- ],
278
- "inputTokens": 4415,
279
- "outputTokens": 57,
280
- "cachedInputTokens": 3328,
281
- "requestCharacters": 13344,
282
- "tools": [
283
- {
284
- "name": "run_environment_shell",
285
- "isError": false,
286
- "characters": 628,
287
- "phaseLatencies": {
288
- "commandAndAttestationMs": 2551.948125,
289
- "workspaceExportMs": 8370.394875,
290
- "totalMs": 13939.041666,
291
- "sessionCreationMs": 3016.637958
292
- },
293
- "exitCode": 0,
294
- "timedOut": false
295
- }
296
- ]
297
- },
298
- {
299
- "index": 5,
300
- "status": "waiting_approval",
301
- "finishReason": "tool-calls",
302
- "requestedTools": [
303
- "run_environment_shell"
304
- ],
305
- "inputTokens": 4802,
306
- "outputTokens": 63,
307
- "cachedInputTokens": 3328,
308
- "requestCharacters": 14769,
309
- "tools": [
310
- {
311
- "name": "run_environment_shell",
312
- "isError": false,
313
- "characters": 989,
314
- "phaseLatencies": {
315
- "commandAndAttestationMs": 3493.600166,
316
- "workspaceExportMs": 8051.391792,
317
- "totalMs": 13708.315958,
318
- "sessionCreationMs": 2163.173
319
- },
320
- "exitCode": 0,
321
- "timedOut": false
322
- }
323
- ]
324
- },
325
- {
326
- "index": 6,
327
- "status": "waiting_approval",
328
- "finishReason": "tool-calls",
329
- "requestedTools": [
330
- "run_environment_shell"
331
- ],
332
- "inputTokens": 5089,
333
- "outputTokens": 34,
334
- "cachedInputTokens": 4096,
335
- "requestCharacters": 15822,
336
- "tools": [
337
- {
338
- "name": "run_environment_shell",
339
- "isError": false,
340
- "characters": 601,
341
- "phaseLatencies": {
342
- "commandAndAttestationMs": 2686.813583,
343
- "workspaceExportMs": 7644.495041,
344
- "totalMs": 12726.732584,
345
- "sessionCreationMs": 2395.366833
346
- },
347
- "exitCode": 0,
348
- "timedOut": false
349
- }
350
- ]
351
- },
352
- {
353
- "index": 7,
354
- "status": "completed",
355
- "finishReason": "tool-calls",
356
- "requestedTools": [
357
- "repair_plan"
358
- ],
359
- "inputTokens": 6848,
360
- "outputTokens": 224,
361
- "cachedInputTokens": 4096,
362
- "requestCharacters": 23276,
363
- "tools": [
364
- {
365
- "name": "run_environment_shell",
366
- "isError": false,
367
- "characters": 7093,
368
- "phaseLatencies": {
369
- "commandAndAttestationMs": 2419.42325,
370
- "workspaceExportMs": 7370.358916,
371
- "totalMs": 12047.248042,
372
- "sessionCreationMs": 2257.312958
373
- },
374
- "exitCode": 0,
375
- "timedOut": false
376
- }
377
- ]
378
- },
379
- {
380
- "index": 8,
381
- "status": "waiting_approval",
382
- "finishReason": "tool-calls",
383
- "requestedTools": [
384
- "run_environment_shell"
385
- ],
386
- "inputTokens": 7332,
387
- "outputTokens": 48,
388
- "cachedInputTokens": 6144,
389
- "requestCharacters": 25450,
390
- "tools": [
391
- {
392
- "name": "repair_plan",
393
- "isError": false,
394
- "characters": 801
395
- },
396
- {
397
- "name": "run_environment_shell",
398
- "isError": false,
399
- "characters": 463,
400
- "phaseLatencies": {
401
- "commandAndAttestationMs": 2746.627709,
402
- "workspaceExportMs": 7016.995125,
403
- "totalMs": 12029.79325,
404
- "sessionCreationMs": 2266.033208
405
- },
406
- "exitCode": 0,
407
- "timedOut": false
408
- }
409
- ]
410
- },
411
- {
412
- "index": 9,
413
- "status": "failed",
414
- "finishReason": "tool-calls",
415
- "requestedTools": [
416
- "other-tool"
417
- ],
418
- "inputTokens": 3387,
419
- "outputTokens": 54,
420
- "cachedInputTokens": 1024,
421
- "requestCharacters": 2472,
422
- "tools": [
423
- {
424
- "name": "other-tool",
425
- "isError": true,
426
- "characters": 4,
427
- "diagnostic": {
428
- "code": "EXECUTION_FAILED",
429
- "category": "execution",
430
- "failureType": "execution",
431
- "retryable": false,
432
- "chain": [
433
- {
434
- "validationCode": null,
435
- "providerReason": null,
436
- "validationIssues": [],
437
- "status": null,
438
- "errorClass": "Object",
439
- "providerHints": [],
440
- "fingerprint": "6d0579d910635f92f565c11d29a0704f48dc1b126b5cff8674e01de04ef58a64",
441
- "reason": "not registered"
442
- }
443
- ]
444
- }
445
- }
446
- ]
447
- }
448
- ],
449
- "inputTokens": 41620,
450
- "outputTokens": 680,
451
- "cachedInputTokens": 26112,
452
- "modelCalls": 9,
453
- "compactions": [
454
- {
455
- "beforeStep": 9,
456
- "estimatedTokensBefore": 5972,
457
- "estimatedTokensAfter": 1850
458
- }
459
- ],
460
- "terminalDiagnostic": {
461
- "code": "EXECUTION_FAILED",
462
- "category": "execution",
463
- "failureType": "execution",
464
- "retryable": false,
465
- "chain": [
466
- {
467
- "validationCode": null,
468
- "providerReason": null,
469
- "validationIssues": [],
470
- "status": null,
471
- "errorClass": "Object",
472
- "providerHints": [],
473
- "fingerprint": "4781c6db9c61c01642ad93cb9a3b069cb6ef16d947024b4852fa71e010ef7fed",
474
- "reason": "not registered"
475
- }
476
- ]
477
- },
478
- "thrownDiagnostic": {
479
- "code": "EXECUTION_FAILED",
480
- "category": "execution",
481
- "failureType": "execution",
482
- "retryable": false,
483
- "chain": [
484
- {
485
- "validationCode": null,
486
- "providerReason": null,
487
- "validationIssues": [],
488
- "status": null,
489
- "errorClass": "HarnessExecutionError",
490
- "providerHints": [],
491
- "fingerprint": "4781c6db9c61c01642ad93cb9a3b069cb6ef16d947024b4852fa71e010ef7fed",
492
- "reason": "not registered"
493
- },
494
- {
495
- "validationCode": null,
496
- "providerReason": null,
497
- "validationIssues": [],
498
- "status": null,
499
- "errorClass": null,
500
- "providerHints": [],
501
- "fingerprint": "4781c6db9c61c01642ad93cb9a3b069cb6ef16d947024b4852fa71e010ef7fed",
502
- "reason": "not registered"
503
- }
504
- ]
505
- },
506
- "guardrails": [],
507
- "repairProgress": {
508
- "repeatedResults": 0,
509
- "suppressedResults": 0,
510
- "blockedBroadCalls": 0,
511
- "enteredClosure": false,
512
- "phase": "explore",
513
- "blockedPhaseCalls": 0,
514
- "planRecorded": true
515
- },
516
- "contextMetrics": [
517
- {
518
- "systemCharacters": 4262,
519
- "userCharacters": 2548,
520
- "assistantCharacters": 0,
521
- "toolResultCharacters": 0,
522
- "otherMessageCharacters": 0,
523
- "toolDefinitionCharacters": 3357,
524
- "unmeasuredToolDefinitions": 0
525
- },
526
- {
527
- "systemCharacters": 4262,
528
- "userCharacters": 2815,
529
- "assistantCharacters": 266,
530
- "toolResultCharacters": 696,
531
- "otherMessageCharacters": 0,
532
- "toolDefinitionCharacters": 3357,
533
- "unmeasuredToolDefinitions": 0
534
- },
535
- {
536
- "systemCharacters": 4262,
537
- "userCharacters": 3081,
538
- "assistantCharacters": 554,
539
- "toolResultCharacters": 4327,
540
- "otherMessageCharacters": 0,
541
- "toolDefinitionCharacters": 3357,
542
- "unmeasuredToolDefinitions": 0
543
- },
544
- {
545
- "systemCharacters": 4262,
546
- "userCharacters": 3081,
547
- "assistantCharacters": 867,
548
- "toolResultCharacters": 5124,
549
- "otherMessageCharacters": 0,
550
- "toolDefinitionCharacters": 3357,
551
- "unmeasuredToolDefinitions": 0
552
- },
553
- {
554
- "systemCharacters": 4262,
555
- "userCharacters": 3081,
556
- "assistantCharacters": 1132,
557
- "toolResultCharacters": 6282,
558
- "otherMessageCharacters": 0,
559
- "toolDefinitionCharacters": 3357,
560
- "unmeasuredToolDefinitions": 0
561
- },
562
- {
563
- "systemCharacters": 4262,
564
- "userCharacters": 3081,
565
- "assistantCharacters": 1413,
566
- "toolResultCharacters": 7052,
567
- "otherMessageCharacters": 0,
568
- "toolDefinitionCharacters": 3357,
569
- "unmeasuredToolDefinitions": 0
570
- },
571
- {
572
- "systemCharacters": 4262,
573
- "userCharacters": 3081,
574
- "assistantCharacters": 1603,
575
- "toolResultCharacters": 14314,
576
- "otherMessageCharacters": 0,
577
- "toolDefinitionCharacters": 3357,
578
- "unmeasuredToolDefinitions": 0
579
- },
580
- {
581
- "systemCharacters": 4262,
582
- "userCharacters": 3399,
583
- "assistantCharacters": 2497,
584
- "toolResultCharacters": 15274,
585
- "otherMessageCharacters": 0,
586
- "toolDefinitionCharacters": 3357,
587
- "unmeasuredToolDefinitions": 0
588
- },
589
- {
590
- "systemCharacters": 4262,
591
- "userCharacters": 2470,
592
- "assistantCharacters": 2501,
593
- "toolResultCharacters": 632,
594
- "otherMessageCharacters": 0,
595
- "toolDefinitionCharacters": 3357,
596
- "unmeasuredToolDefinitions": 0
597
- }
598
- ],
599
- "omittedContextMeasurements": 0,
600
- "toolCalls": 8,
601
- "patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
602
- "protectedFilesChanged": [],
603
- "gradingMethod": "empty-patch-no-solution",
604
- "officialResolved": false,
605
- "candidateCaptured": true,
606
- "candidatePatchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
607
- "candidateGradingStatus": "completed",
608
- "candidateResolved": false,
609
- "repairStages": {
610
- "candidatePresent": false,
611
- "importedPatchPresent": false,
612
- "verificationAttempted": false
613
- },
614
- "gradingDurationMs": 0.16387499636039138,
615
- "totalDurationMs": 153439.36329201097
616
- },
617
- {
618
- "candidate": "mini-swe-agent",
619
- "instanceId": "django__django-15851",
620
- "repetition": 0,
621
- "resolved": true,
622
- "gradingStatus": "completed",
623
- "usageComplete": true,
624
- "costUsd": null,
625
- "schemaVersion": 1,
626
- "status": "Submitted",
627
- "failure": null,
628
- "phase": "agent",
629
- "durationMs": 22133.75095796073,
630
- "approvals": 0,
631
- "toolCalls": 8,
632
- "inputTokens": 22969,
633
- "outputTokens": 636,
634
- "cachedInputTokens": 15872,
635
- "modelCalls": 8,
636
- "patchSha256": "873ee0e2d09108303f5ebe1fa4d0aec08ee9e4ce52b93941c70b4c8c91c21db4",
637
- "protectedFilesChanged": [],
638
- "officialResolved": true,
639
- "candidateCaptured": true,
640
- "candidatePatchSha256": "873ee0e2d09108303f5ebe1fa4d0aec08ee9e4ce52b93941c70b4c8c91c21db4",
641
- "candidateGradingStatus": "completed",
642
- "candidateResolved": true,
643
- "repairStages": {
644
- "candidatePresent": true,
645
- "importedPatchPresent": null,
646
- "verificationAttempted": null
647
- },
648
- "gradingDurationMs": 24649.95683298912,
649
- "totalDurationMs": 49208.5399160278
650
- }
651
- ],
652
- "report": {
653
- "schemaVersion": 1,
654
- "kind": "swebench-comparison",
655
- "manifestSha256": "69eec29ad77147b4e43408679277faacc89bb04680b711b15217cfa9fe5f34ed",
656
- "complete": true,
657
- "candidates": {
658
- "zhivex": {
659
- "planned": 1,
660
- "recorded": 1,
661
- "resolved": 0,
662
- "candidateCaptured": 1,
663
- "candidateResolved": 0,
664
- "candidateGraded": 1,
665
- "resolutionRate": 0.0,
666
- "missing": 0,
667
- "gradingFailures": 0,
668
- "usageComplete": true,
669
- "totalCostUsd": null,
670
- "costPerResolvedUsd": null,
671
- "resolvedP50Ms": null
672
- },
673
- "mini-swe-agent": {
674
- "planned": 1,
675
- "recorded": 1,
676
- "resolved": 1,
677
- "candidateCaptured": 1,
678
- "candidateResolved": 1,
679
- "candidateGraded": 1,
680
- "resolutionRate": 1.0,
681
- "missing": 0,
682
- "gradingFailures": 0,
683
- "usageComplete": true,
684
- "totalCostUsd": null,
685
- "costPerResolvedUsd": null,
686
- "resolvedP50Ms": 49208.5399160278
687
- }
688
- },
689
- "pairedTaskResolutionDifference": -1.0,
690
- "pairedTaskBootstrap95": null,
691
- "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."
692
- },
693
- "limitations": [
694
- "One repetition; no causal or general reliability claim",
695
- "Catalog and rendered instructions changed together",
696
- "Existing shell route uses different existing quotas from native reads",
697
- "No runtime policy or product profile changed"
698
- ]
699
- }