@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
@@ -1,596 +0,0 @@
1
- {
2
- "schemaVersion": 1,
3
- "kind": "development-comparison",
4
- "classification": "known development task, one Qwen repetition and control; not holdout",
5
- "providers": {
6
- "qwen": {
7
- "model": "qwen3.8-flash",
8
- "limits": {
9
- "steps": 24,
10
- "outputPerTurn": 2048,
11
- "inputTokens": 100000,
12
- "outputTokens": 16000,
13
- "timeoutSeconds": 300,
14
- "memoryMb": 2048,
15
- "cpus": 2
16
- },
17
- "implementation": {
18
- "gitCommit": "50f255d7d48ac8ed99627d80ad5c0339fa0936a3",
19
- "sources": {
20
- "bun.lock": "e370459197ce52c3961770f3c5ccaab7ff35ddbe641ef72e8bd61f87a8b8e3fe",
21
- "evaluations/external/requirements.lock": "42e90a08f10f821ebb958af79256f707a9fb5cf365277c4f9e2715d612028179",
22
- "package.json": "a4a2507e3ad876d72cad49a16e149192d33521fb4175bb40a3eb077ccfdf43a1",
23
- "scripts/benchmark-swebench.ts": "ed17063e1847017ba2e72f14732b6ff8f5b1af7cd5253b91302af75f2a9e8476",
24
- "scripts/swebench/candidate.py": "f5e3410b91b950acfbe50fc7511891816a8fb1c223082397e2c6300cf1e866cf",
25
- "scripts/swebench/candidate.ts": "bf102becfcce0c9a3f0df0a8f1ce0e5aaea7db2d252f6d9454a8370c24e53982",
26
- "scripts/swebench/common.py": "ad790227dac3bec1f592c458c993efff4f9d3de8f0df39b33e3238b58b3f0b3b",
27
- "scripts/swebench/context-metrics.ts": "7b84da6789413aa634d997c5963ee6796584e06c3eafe5f68f424fb7e27815e9",
28
- "scripts/swebench/mini_driver.py": "bd0a77221878370ec44760122a51f07fb56d969612afa9a7f171248b2958baa6",
29
- "scripts/swebench/model-budget.ts": "e46dd406ee5d58a051a15c7d7133513666292303d8c6534f861a6db0e711f47c",
30
- "scripts/swebench/preflight.py": "aed092a75dd52f504fba6d14814b69bd627ff17d0e311a1f1279f8b613b69675",
31
- "scripts/swebench/prepare.py": "bb7edd3fba5dbbe26597c97d744c60b94dbb7bcdfd7740a4a058c8583bd27e4c",
32
- "scripts/swebench/report.py": "d0b8d45f32c48e0ba2cb977f50838065a497a0ecaf3b4243ed94139393ce4d6b",
33
- "scripts/swebench/run.py": "94dccd55dfe6f70d8f8f2da70331700ec85eddd958547e0c3afe3dc416c9802c",
34
- "scripts/swebench/telemetry.ts": "743c9baf273e9240d704d098b6bd5eea9e76ef3e49ae636aaafa9bfd7a85b45b",
35
- "scripts/swebench/test_candidate.py": "e77d16379b748baa2daf184a45ea62587d938b6a7d48dcf9f6061f8af21fafd9",
36
- "scripts/swebench/test_contracts.py": "902e966d0fbf8501dbb15e011849f160331c033cd2a5480f9920d0f365a08d03",
37
- "scripts/swebench/zhivex-driver.ts": "b17e937484a28cf7fc7728595b51900efa5015dfa37cf6c1d4f9322051fe1ece",
38
- "scripts/time-to-safe-fix-efficiency.ts": "dd20fd8839280332ae4ca80d6846e98e07ff15d79e200b206fa2ba6be2724d2f",
39
- "src/bounded-reads.ts": "9807bb460894be3279c5425af19863d1c6e419a1582ba6910ec7e7fc35703ed6",
40
- "src/capabilities.ts": "56fdb60a2f6e1d33b2dc26d38b6d2709807e491ba1268d47b97876c2c0591d65",
41
- "src/change-envelope.ts": "9047ec978c9e5117965b8093ec961d855f97bbc2c3accdc79b74cfe6a0e4f01e",
42
- "src/cli-options.ts": "f48d9be132fed38f2ddbcfecbd8222c664a0df2f20edc28ce8d1b9b1a1900863",
43
- "src/cli-profiles.ts": "4fe451f1645e95f4957597a8724fa989b3c661ae1693252bfd6e74a51d20fc74",
44
- "src/cli-stream.ts": "5ab8a4b1b8cf0a3dfa7b5b1f9e4e0facf8f6e7f6c341bdf700a41dc8927c825e",
45
- "src/cli.ts": "5a4acb4695a968a58fbeac05c4bb89848a9653d6189590f0ff90e430ffa98d14",
46
- "src/compaction.ts": "9e06a0abeeef155377f40c160b21c56256bca95ec18c5ee897681a5fc73db169",
47
- "src/config.ts": "b1d3991e84add58603fb85b2a604b9b3eb56ae879d0fa30b0cb40545fa44edc1",
48
- "src/console-context.ts": "0ad7e4559504b9ed09ab500d615dea09af1075d357f02ec3b77f003d55d951db",
49
- "src/console-input.ts": "dc8ea0cdbba1364db288d5156c5ff9819362c46b37ef35a98b0475b6c445b1f8",
50
- "src/context-engineering.ts": "1995e564f6b91974e75bf66dd421ddcbea29b1f8eee59b76eb4e34c9d6d8f47e",
51
- "src/context-metrics.ts": "3eb30f9db808f918ed8d73d4f8ac19a13acb09ed5c1ee70fdae05201714b9198",
52
- "src/edit-contracts.ts": "47cc3132e27f8749d54a32bbcc33bb174cf4448f0d0171b2578cdb559cf2176b",
53
- "src/errors.ts": "e02f4eb80562a83762f908bda56c950ec6a2b78725c0c8a49f41fee0057ab903",
54
- "src/execution-environment.ts": "9ce6c49afab26527d5296f0c11f106063590f7333300d58dd49d5a1ec1b4b6e9",
55
- "src/file-security.ts": "b8c9f4988c4339c73a60ab4fa8d394b3eecc19117a0c61a8d19ab6483ca253df",
56
- "src/harness.ts": "195983cfbacb6097a5c8c2a106e59c3fae2437f053299da1c0170dd914879c8d",
57
- "src/index.ts": "4bbfcd11376d48c4f1c1ec17d6b5c9f51baa9331fa999432be178bae94530a5e",
58
- "src/json-contracts.ts": "0780145636b47829a1aa6087c574d5654eb31b7534ea7d9c38c188d648c90272",
59
- "src/mcp.ts": "7722de031921c620ec03b9e42a6596ef8415aa8e4bb5f93ea84d2427c466e554",
60
- "src/model-budget.ts": "97c00019d7e737fc7acdd04cdac0811dca8d85c3e858de519ebba91888cf1ee7",
61
- "src/operations.ts": "bcccaf4d1d0ec117c2ed35df92185564d33399e5fdc5c12225ac61f14fd0b4b1",
62
- "src/orchestration.ts": "b56c8c7d526a99b745cc17769e0a1b7b500b25920e77f34aa0dd01c9758de319",
63
- "src/package-manager.ts": "cec4666bbab2f42e0a269709631f79f9f87c2c4dbb3cafeffacfaff761069e2c",
64
- "src/process-runtime.ts": "b7286731a0b5c96dcad0b8e3a4bf1155d0539d73303cd7ebe77ffabf858f1729",
65
- "src/providers.ts": "70ccfc7f315cd7238e83d69b719ce4908f3b620c564cbb4f00f93e102e025602",
66
- "src/repair-controller.ts": "2c05370e93978a5bf106b2cee293478a77b47920cec7470f536b31757198f41c",
67
- "src/repair-progress.ts": "cf30117ab69564f2b36ff8f0e86dcb876e6c031647340a7b1bef648d1e0366b9",
68
- "src/repair-verifier.ts": "b70fb11feee8cdc7933947ccac0b78f8bb5c0eaccc3b29ad527197d77f40ffc9",
69
- "src/replacement-edits.ts": "8a0efdd3a7a9fc3e5a5475916cbd17ef882265881bb61076db58673e80b72957",
70
- "src/routing.ts": "8e7c9f5968b4bd638cbbc86b19847ca183f3418b9a298783b96a88cffa568e22",
71
- "src/run-interruption.ts": "df99129cf2dd6b938eca629cb897c4350a7d57fe6bf0ce437f5f3f30271617df",
72
- "src/runtime-checkpoints.ts": "e3b75a0b86fb5d21992b1a126b35446110ba5fcaf4317ed5005b1a44555118dc",
73
- "src/runtime-diagnostics.ts": "e1e5a3a558fa2aaeb477335dc336551f022c1234fe5e742eefc6599c8803e364",
74
- "src/runtime-policy.ts": "8356acf0102f0e73839b81ed628a5c0d9a89d9c21b0ca416efedde8f1b3414e2",
75
- "src/sessions.ts": "5167c8cf36bd4b8845ee278883394700321b65397f49c1dda0cf0d0de09dd06e",
76
- "src/sqlite-database.ts": "18765d1ca0c2f2ad87bfd82d311312dfe8a42006556f27bc21da5892ed3b044e",
77
- "src/state-backup.ts": "b6f8f1aedeb5dce31b65c23c7ffc50030870655b58a5aaaef9989bafb9da5c68",
78
- "src/state-directory.ts": "3711550991951e6b738a08deaa0e06da84d01864c03a9602600f592963fa3211",
79
- "src/task-memory.ts": "5b62c863be5a23c33608633cd7aac0464f5536d01cba930aca58b11870170731",
80
- "src/terminal-markdown.ts": "8cffb6ebaf25108cb2bee04956d9b2973635b010f5d7ce6be21b3ceffe3e8bfd",
81
- "src/terminal-ui.ts": "4da1878a76ba608a2517bf5d5c992a9a88702aba3fd800a9980129ba93e157bc",
82
- "src/time-to-safe-fix.ts": "4add1d49c0ea209cc496c66fa2b2012dc7bcab87e678a58c8591b3c2cdc8df8a",
83
- "src/tool-registry.ts": "7e90fff11940e525883c9ec0d2adbea2e6616f8bd9bc4ec77e1b7277e4217f2c",
84
- "src/version.ts": "b2c2f80a40adc08e8258b81e82434273f0bdfa787528b2221f14efe7f06aa747",
85
- "src/workspace-mutation-lock.ts": "ca201242db16173bd3a4d86c5d8bb0c2b6f3c43bfed3e4fa4ff5f06a75b19e80",
86
- "src/workspace.ts": "809f8bbfcf72fed10d860c48585089ca65bb3ef7c672ee6df3c918907a968302"
87
- }
88
- },
89
- "report": {
90
- "schemaVersion": 1,
91
- "kind": "swebench-comparison",
92
- "manifestSha256": "45523d2da2b72463ee1a018009f4fd33b6af3c70f74669669f63d6e8dc3c5313",
93
- "complete": true,
94
- "candidates": {
95
- "zhivex": {
96
- "planned": 1,
97
- "recorded": 1,
98
- "resolved": 0,
99
- "candidateCaptured": 1,
100
- "candidateResolved": 0,
101
- "candidateGraded": 1,
102
- "resolutionRate": 0.0,
103
- "missing": 0,
104
- "gradingFailures": 0,
105
- "usageComplete": true,
106
- "totalCostUsd": null,
107
- "costPerResolvedUsd": null,
108
- "resolvedP50Ms": null
109
- },
110
- "mini-swe-agent": {
111
- "planned": 1,
112
- "recorded": 1,
113
- "resolved": 1,
114
- "candidateCaptured": 1,
115
- "candidateResolved": 1,
116
- "candidateGraded": 1,
117
- "resolutionRate": 1.0,
118
- "missing": 0,
119
- "gradingFailures": 0,
120
- "usageComplete": true,
121
- "totalCostUsd": null,
122
- "costPerResolvedUsd": null,
123
- "resolvedP50Ms": 51138.973958964925
124
- }
125
- },
126
- "pairedTaskResolutionDifference": -1.0,
127
- "pairedTaskBootstrap95": null,
128
- "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."
129
- },
130
- "samples": [
131
- {
132
- "candidate": "zhivex",
133
- "instanceId": "django__django-15851",
134
- "repetition": 0,
135
- "resolved": false,
136
- "gradingStatus": "completed",
137
- "usageComplete": true,
138
- "costUsd": null,
139
- "candidateCaptureFailure": null,
140
- "modelTimings": [
141
- {
142
- "durationMs": 3825.269125,
143
- "firstTokenMs": 3824.7088750000003,
144
- "completed": true
145
- },
146
- {
147
- "durationMs": 2067.216957999999,
148
- "firstTokenMs": 2066.932208,
149
- "completed": true
150
- },
151
- {
152
- "durationMs": 2315.4390000000003,
153
- "firstTokenMs": 2314.9894589999985,
154
- "completed": true
155
- },
156
- {
157
- "durationMs": 2319.2926669999997,
158
- "firstTokenMs": 2319.0190839999996,
159
- "completed": true
160
- },
161
- {
162
- "durationMs": 1720.6861250000002,
163
- "firstTokenMs": 1720.5663750000003,
164
- "completed": true
165
- },
166
- {
167
- "durationMs": 2112.905749999998,
168
- "firstTokenMs": 2112.7887499999997,
169
- "completed": true
170
- },
171
- {
172
- "durationMs": 1642.2713750000003,
173
- "firstTokenMs": 1642.114207999999,
174
- "completed": true
175
- },
176
- {
177
- "durationMs": 1830.7312500000007,
178
- "firstTokenMs": 1830.4789170000004,
179
- "completed": true
180
- }
181
- ],
182
- "stageTimings": [],
183
- "approvalTimings": [],
184
- "toolTimings": [
185
- {
186
- "name": "search_files",
187
- "calls": 3,
188
- "errors": 0,
189
- "totalMs": 432.8311649999996,
190
- "maxMs": 363.1053329999995
191
- },
192
- {
193
- "name": "list_files",
194
- "calls": 1,
195
- "errors": 0,
196
- "totalMs": 8.690541999999368,
197
- "maxMs": 8.690541999999368
198
- },
199
- {
200
- "name": "read_files",
201
- "calls": 4,
202
- "errors": 0,
203
- "totalMs": 4.190209000000323,
204
- "maxMs": 1.680833000000348
205
- }
206
- ],
207
- "schemaVersion": 1,
208
- "status": "failed",
209
- "failure": "WORK_TOKEN_BUDGET",
210
- "phase": "agent",
211
- "durationMs": 25486.036625,
212
- "approvals": 0,
213
- "turns": [
214
- {
215
- "index": 1,
216
- "status": "completed",
217
- "finishReason": "tool-calls",
218
- "requestedTools": [
219
- "search_files",
220
- "list_files"
221
- ],
222
- "inputTokens": 4610,
223
- "outputTokens": 123,
224
- "cachedInputTokens": 0,
225
- "requestCharacters": 1584,
226
- "tools": [
227
- {
228
- "name": "search_files",
229
- "isError": false,
230
- "characters": 714
231
- },
232
- {
233
- "name": "list_files",
234
- "isError": false,
235
- "characters": 452
236
- }
237
- ]
238
- },
239
- {
240
- "index": 2,
241
- "status": "completed",
242
- "finishReason": "tool-calls",
243
- "requestedTools": [
244
- "read_files"
245
- ],
246
- "inputTokens": 5179,
247
- "outputTokens": 51,
248
- "cachedInputTokens": 4096,
249
- "requestCharacters": 9281,
250
- "tools": [
251
- {
252
- "name": "read_files",
253
- "isError": false,
254
- "characters": 3979
255
- }
256
- ]
257
- },
258
- {
259
- "index": 3,
260
- "status": "completed",
261
- "finishReason": "tool-calls",
262
- "requestedTools": [
263
- "search_files"
264
- ],
265
- "inputTokens": 6523,
266
- "outputTokens": 66,
267
- "cachedInputTokens": 4096,
268
- "requestCharacters": 13657,
269
- "tools": [
270
- {
271
- "name": "search_files",
272
- "isError": false,
273
- "characters": 158
274
- }
275
- ]
276
- },
277
- {
278
- "index": 4,
279
- "status": "completed",
280
- "finishReason": "tool-calls",
281
- "requestedTools": [
282
- "search_files"
283
- ],
284
- "inputTokens": 6655,
285
- "outputTokens": 65,
286
- "cachedInputTokens": 5120,
287
- "requestCharacters": 14196,
288
- "tools": [
289
- {
290
- "name": "search_files",
291
- "isError": false,
292
- "characters": 6524
293
- }
294
- ]
295
- },
296
- {
297
- "index": 5,
298
- "status": "completed",
299
- "finishReason": "tool-calls",
300
- "requestedTools": [
301
- "read_files"
302
- ],
303
- "inputTokens": 9834,
304
- "outputTokens": 38,
305
- "cachedInputTokens": 6144,
306
- "requestCharacters": 21097,
307
- "tools": [
308
- {
309
- "name": "read_files",
310
- "isError": false,
311
- "characters": 4790
312
- }
313
- ]
314
- },
315
- {
316
- "index": 6,
317
- "status": "completed",
318
- "finishReason": "tool-calls",
319
- "requestedTools": [
320
- "read_files"
321
- ],
322
- "inputTokens": 11321,
323
- "outputTokens": 60,
324
- "cachedInputTokens": 9216,
325
- "requestCharacters": 26232,
326
- "tools": [
327
- {
328
- "name": "read_files",
329
- "isError": true,
330
- "characters": 4,
331
- "diagnostic": {
332
- "code": "EXECUTION_FAILED",
333
- "category": "execution",
334
- "failureType": "schema",
335
- "retryable": false,
336
- "chain": [
337
- {
338
- "validationCode": "TOOL_INPUT_VALIDATION_ERROR",
339
- "providerReason": null,
340
- "validationIssues": [
341
- {
342
- "code": "invalid_type",
343
- "path": [
344
- "files",
345
- 0,
346
- "startLine"
347
- ]
348
- }
349
- ],
350
- "status": null,
351
- "errorClass": "Object",
352
- "providerHints": [],
353
- "fingerprint": "1ab0a587cdf893a886ab62e85890fe1c3290c9e607060e60c6ef210f83c9b520",
354
- "reason": null
355
- }
356
- ]
357
- }
358
- }
359
- ]
360
- },
361
- {
362
- "index": 7,
363
- "status": "completed",
364
- "finishReason": "tool-calls",
365
- "requestedTools": [
366
- "read_files"
367
- ],
368
- "inputTokens": 11437,
369
- "outputTokens": 56,
370
- "cachedInputTokens": 10240,
371
- "requestCharacters": 26773,
372
- "tools": [
373
- {
374
- "name": "read_files",
375
- "isError": false,
376
- "characters": 3399
377
- }
378
- ]
379
- },
380
- {
381
- "index": 8,
382
- "status": "completed",
383
- "finishReason": "tool-calls",
384
- "requestedTools": [
385
- "read_files"
386
- ],
387
- "inputTokens": 6646,
388
- "outputTokens": 72,
389
- "cachedInputTokens": 3328,
390
- "requestCharacters": 1584,
391
- "tools": [
392
- {
393
- "name": "read_files",
394
- "isError": false,
395
- "characters": 5074
396
- }
397
- ]
398
- }
399
- ],
400
- "inputTokens": 62205,
401
- "outputTokens": 531,
402
- "cachedInputTokens": 42240,
403
- "modelCalls": 8,
404
- "compactions": [
405
- {
406
- "beforeStep": 8,
407
- "estimatedTokensBefore": 7241,
408
- "estimatedTokensAfter": 2997
409
- }
410
- ],
411
- "terminalDiagnostic": {
412
- "code": "EXECUTION_FAILED",
413
- "category": "execution",
414
- "failureType": "budget",
415
- "retryable": false,
416
- "chain": [
417
- {
418
- "validationCode": null,
419
- "providerReason": null,
420
- "validationIssues": [],
421
- "status": null,
422
- "errorClass": "Object",
423
- "providerHints": [],
424
- "fingerprint": "e28d443c2f098dca74c2ebb674bfac969cc7e5a8c1621de8718feec56bdb994a",
425
- "reason": "budget"
426
- }
427
- ]
428
- },
429
- "thrownDiagnostic": {
430
- "code": "EXECUTION_FAILED",
431
- "category": "execution",
432
- "failureType": "budget",
433
- "retryable": false,
434
- "chain": [
435
- {
436
- "validationCode": null,
437
- "providerReason": null,
438
- "validationIssues": [],
439
- "status": null,
440
- "errorClass": "HarnessExecutionError",
441
- "providerHints": [],
442
- "fingerprint": "e28d443c2f098dca74c2ebb674bfac969cc7e5a8c1621de8718feec56bdb994a",
443
- "reason": "budget"
444
- },
445
- {
446
- "validationCode": null,
447
- "providerReason": null,
448
- "validationIssues": [],
449
- "status": null,
450
- "errorClass": "Error",
451
- "providerHints": [],
452
- "fingerprint": "e28d443c2f098dca74c2ebb674bfac969cc7e5a8c1621de8718feec56bdb994a",
453
- "reason": "budget"
454
- }
455
- ]
456
- },
457
- "guardrails": [],
458
- "repairProgress": {
459
- "repeatedResults": 0,
460
- "suppressedResults": 0,
461
- "blockedBroadCalls": 0,
462
- "enteredClosure": false,
463
- "phase": "explore",
464
- "blockedPhaseCalls": 0,
465
- "planRecorded": false
466
- },
467
- "contextMetrics": [
468
- {
469
- "systemCharacters": 4851,
470
- "userCharacters": 2548,
471
- "assistantCharacters": 0,
472
- "toolResultCharacters": 0,
473
- "otherMessageCharacters": 0,
474
- "toolDefinitionCharacters": 9375,
475
- "unmeasuredToolDefinitions": 0
476
- },
477
- {
478
- "systemCharacters": 4851,
479
- "userCharacters": 2548,
480
- "assistantCharacters": 391,
481
- "toolResultCharacters": 1484,
482
- "otherMessageCharacters": 0,
483
- "toolDefinitionCharacters": 9375,
484
- "unmeasuredToolDefinitions": 0
485
- },
486
- {
487
- "systemCharacters": 4851,
488
- "userCharacters": 2548,
489
- "assistantCharacters": 628,
490
- "toolResultCharacters": 5621,
491
- "otherMessageCharacters": 0,
492
- "toolDefinitionCharacters": 9375,
493
- "unmeasuredToolDefinitions": 0
494
- },
495
- {
496
- "systemCharacters": 4851,
497
- "userCharacters": 2548,
498
- "assistantCharacters": 847,
499
- "toolResultCharacters": 5939,
500
- "otherMessageCharacters": 0,
501
- "toolDefinitionCharacters": 9375,
502
- "unmeasuredToolDefinitions": 0
503
- },
504
- {
505
- "systemCharacters": 4851,
506
- "userCharacters": 2548,
507
- "assistantCharacters": 1062,
508
- "toolResultCharacters": 12623,
509
- "otherMessageCharacters": 0,
510
- "toolDefinitionCharacters": 9375,
511
- "unmeasuredToolDefinitions": 0
512
- },
513
- {
514
- "systemCharacters": 4851,
515
- "userCharacters": 2548,
516
- "assistantCharacters": 1247,
517
- "toolResultCharacters": 17571,
518
- "otherMessageCharacters": 0,
519
- "toolDefinitionCharacters": 9375,
520
- "unmeasuredToolDefinitions": 0
521
- },
522
- {
523
- "systemCharacters": 4851,
524
- "userCharacters": 2548,
525
- "assistantCharacters": 1468,
526
- "toolResultCharacters": 17889,
527
- "otherMessageCharacters": 0,
528
- "toolDefinitionCharacters": 9375,
529
- "unmeasuredToolDefinitions": 0
530
- },
531
- {
532
- "systemCharacters": 4851,
533
- "userCharacters": 1582,
534
- "assistantCharacters": 3573,
535
- "toolResultCharacters": 3557,
536
- "otherMessageCharacters": 0,
537
- "toolDefinitionCharacters": 9375,
538
- "unmeasuredToolDefinitions": 0
539
- }
540
- ],
541
- "omittedContextMeasurements": 0,
542
- "toolCalls": 8,
543
- "patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
544
- "protectedFilesChanged": [],
545
- "gradingMethod": "empty-patch-no-solution",
546
- "officialResolved": false,
547
- "candidateCaptured": true,
548
- "candidatePatchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
549
- "candidateGradingStatus": "completed",
550
- "candidateResolved": false,
551
- "repairStages": {
552
- "candidatePresent": false,
553
- "importedPatchPresent": false,
554
- "verificationAttempted": false
555
- },
556
- "gradingDurationMs": 0.2003329573199153,
557
- "totalDurationMs": 35933.55404102476
558
- },
559
- {
560
- "candidate": "mini-swe-agent",
561
- "instanceId": "django__django-15851",
562
- "repetition": 0,
563
- "resolved": true,
564
- "gradingStatus": "completed",
565
- "usageComplete": true,
566
- "costUsd": null,
567
- "schemaVersion": 1,
568
- "status": "Submitted",
569
- "failure": null,
570
- "phase": "agent",
571
- "durationMs": 24763.874333002605,
572
- "approvals": 0,
573
- "toolCalls": 9,
574
- "inputTokens": 24332,
575
- "outputTokens": 727,
576
- "cachedInputTokens": 16384,
577
- "modelCalls": 9,
578
- "patchSha256": "873ee0e2d09108303f5ebe1fa4d0aec08ee9e4ce52b93941c70b4c8c91c21db4",
579
- "protectedFilesChanged": [],
580
- "officialResolved": true,
581
- "candidateCaptured": true,
582
- "candidatePatchSha256": "873ee0e2d09108303f5ebe1fa4d0aec08ee9e4ce52b93941c70b4c8c91c21db4",
583
- "candidateGradingStatus": "completed",
584
- "candidateResolved": true,
585
- "repairStages": {
586
- "candidatePresent": true,
587
- "importedPatchPresent": null,
588
- "verificationAttempted": null
589
- },
590
- "gradingDurationMs": 24148.144167033024,
591
- "totalDurationMs": 51138.973958964925
592
- }
593
- ]
594
- }
595
- }
596
- }
@@ -1,25 +0,0 @@
1
- {
2
- "kind": "explicit-verified-delivery-contract",
3
- "option": "requireVerifiedDelivery",
4
- "default": false,
5
- "allowedProfile": "repair",
6
- "benchmarkEnabled": true,
7
- "validation": {
8
- "fullSuitePassed": 566,
9
- "additionalBindingTest": "passed",
10
- "focusedTestsPassed": 4,
11
- "types": "passed",
12
- "docs": "passed",
13
- "contract": "passed; GA blocker open",
14
- "installedPackage": "passed"
15
- },
16
- "liveEvidence": false,
17
- "hashes": {
18
- "src/config.ts": "67ed44b55505ff8dd94f60ba89c33c217759cd7c79de45ccda369f248309cdff",
19
- "src/harness.ts": "1d305078e3c56c24bb659c34aac37c96bf11a4e60af6607bb4b9d65964e84791",
20
- "src/repair-controller.ts": "41f1f09032131306f3284edbf105930577504af0bf764ba98a105c4eee70a1e7",
21
- "scripts/swebench/zhivex-driver.ts": "3d1c143b4c2a1438a1249db8cc10c70a80cbd1c9e3ed44317230795b7a9be2b4",
22
- "tests/required-repair-delivery.test.ts": "917b9196bfd1c5515af7e4da7d0c97ea94fae3f0501a913ec34f07b8a7c8c198",
23
- "contracts/stable-api-signatures.json": "80df6ea03251111072985e12d8f7736d3333a79e53b787c78ef5d4cbbb6aaa42"
24
- }
25
- }