@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
@@ -1,854 +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": "866115b64d90c0b2ffa3e07da6a015210afae0babe46052912d0cc288e23bc4b",
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": "063ee52351d70bd99e53a28d2009694ff4ead2236a2b227844ae8980b4bc03ea",
67
- "src/repair-progress.ts": "3550509a2a6c1e4a2e091c1012d5fb63ad8512a06f09b41e6b3a915a9a2b31a3",
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": "7649e883075276b68fe5e1a4913e820a8e8830fd012c55b33a02976803713127",
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": 50162.21049998421
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": 16717.623375,
143
- "firstTokenMs": 15144.019292,
144
- "completed": true
145
- },
146
- {
147
- "durationMs": 1748.0521659999977,
148
- "firstTokenMs": 1747.899290999998,
149
- "completed": true
150
- },
151
- {
152
- "durationMs": 2382.638833000001,
153
- "firstTokenMs": 2382.2706660000003,
154
- "completed": true
155
- },
156
- {
157
- "durationMs": 2600.980166000001,
158
- "firstTokenMs": 2600.8398750000015,
159
- "completed": true
160
- },
161
- {
162
- "durationMs": 1741.1551250000011,
163
- "firstTokenMs": 1741.010957999999,
164
- "completed": true
165
- },
166
- {
167
- "durationMs": 2603.8613750000004,
168
- "firstTokenMs": 2603.7424170000013,
169
- "completed": true
170
- },
171
- {
172
- "durationMs": 2907.7530420000003,
173
- "firstTokenMs": 1548.345541999999,
174
- "completed": true
175
- },
176
- {
177
- "durationMs": 2236.802834000002,
178
- "firstTokenMs": 2236.631125,
179
- "completed": true
180
- },
181
- {
182
- "durationMs": 5179.1805410000015,
183
- "firstTokenMs": 5178.969665999997,
184
- "completed": true
185
- },
186
- {
187
- "durationMs": 1755.3518750000003,
188
- "firstTokenMs": 1755.1841249999998,
189
- "completed": true
190
- },
191
- {
192
- "durationMs": 1865.7711659999986,
193
- "firstTokenMs": 1865.6578329999975,
194
- "completed": true
195
- },
196
- {
197
- "durationMs": 1328.6271669999987,
198
- "firstTokenMs": 1328.5239589999983,
199
- "completed": true
200
- },
201
- {
202
- "durationMs": 2011.0182920000007,
203
- "firstTokenMs": 2010.8164169999945,
204
- "completed": true
205
- }
206
- ],
207
- "stageTimings": [],
208
- "approvalTimings": [],
209
- "toolTimings": [
210
- {
211
- "name": "search_files",
212
- "calls": 7,
213
- "errors": 0,
214
- "totalMs": 724.1692509999957,
215
- "maxMs": 384.63158399999884
216
- },
217
- {
218
- "name": "list_files",
219
- "calls": 2,
220
- "errors": 0,
221
- "totalMs": 25.290167000006477,
222
- "maxMs": 15.807959000005212
223
- },
224
- {
225
- "name": "read_files",
226
- "calls": 4,
227
- "errors": 1,
228
- "totalMs": 5.024126000000251,
229
- "maxMs": 1.6802089999982854
230
- },
231
- {
232
- "name": "repair_plan",
233
- "calls": 1,
234
- "errors": 0,
235
- "totalMs": 0.10225000000355067,
236
- "maxMs": 0.10225000000355067
237
- }
238
- ],
239
- "schemaVersion": 1,
240
- "status": "failed",
241
- "failure": "INPUT_TOKEN_BUDGET",
242
- "phase": "agent",
243
- "durationMs": 54244.162707999996,
244
- "approvals": 0,
245
- "turns": [
246
- {
247
- "index": 1,
248
- "status": "completed",
249
- "finishReason": "tool-calls",
250
- "requestedTools": [
251
- "search_files",
252
- "list_files"
253
- ],
254
- "inputTokens": 4590,
255
- "outputTokens": 142,
256
- "cachedInputTokens": 0,
257
- "requestCharacters": 1490,
258
- "tools": [
259
- {
260
- "name": "search_files",
261
- "isError": false,
262
- "characters": 158
263
- },
264
- {
265
- "name": "list_files",
266
- "isError": false,
267
- "characters": 452
268
- }
269
- ]
270
- },
271
- {
272
- "index": 2,
273
- "status": "completed",
274
- "finishReason": "tool-calls",
275
- "requestedTools": [
276
- "read_files"
277
- ],
278
- "inputTokens": 4910,
279
- "outputTokens": 69,
280
- "cachedInputTokens": 4096,
281
- "requestCharacters": 8768,
282
- "tools": [
283
- {
284
- "name": "read_files",
285
- "isError": true,
286
- "characters": 4,
287
- "diagnostic": {
288
- "code": "EXECUTION_FAILED",
289
- "category": "execution",
290
- "failureType": "execution",
291
- "retryable": false,
292
- "chain": [
293
- {
294
- "validationCode": null,
295
- "providerReason": null,
296
- "validationIssues": [],
297
- "status": null,
298
- "errorClass": "Object",
299
- "providerHints": [],
300
- "fingerprint": "6796122e7aebe1e2c1763d5e3aa2831c06255d3d24af070953886a182927f12f",
301
- "reason": "enoent"
302
- }
303
- ]
304
- }
305
- }
306
- ]
307
- },
308
- {
309
- "index": 3,
310
- "status": "completed",
311
- "finishReason": "tool-calls",
312
- "requestedTools": [
313
- "read_files",
314
- "search_files"
315
- ],
316
- "inputTokens": 5093,
317
- "outputTokens": 115,
318
- "cachedInputTokens": 4096,
319
- "requestCharacters": 9445,
320
- "tools": [
321
- {
322
- "name": "read_files",
323
- "isError": false,
324
- "characters": 2673
325
- },
326
- {
327
- "name": "search_files",
328
- "isError": false,
329
- "characters": 834
330
- }
331
- ]
332
- },
333
- {
334
- "index": 4,
335
- "status": "completed",
336
- "finishReason": "tool-calls",
337
- "requestedTools": [
338
- "search_files",
339
- "search_files"
340
- ],
341
- "inputTokens": 6435,
342
- "outputTokens": 127,
343
- "cachedInputTokens": 4096,
344
- "requestCharacters": 13688,
345
- "tools": [
346
- {
347
- "name": "search_files",
348
- "isError": false,
349
- "characters": 164
350
- },
351
- {
352
- "name": "search_files",
353
- "isError": false,
354
- "characters": 2270
355
- }
356
- ]
357
- },
358
- {
359
- "index": 5,
360
- "status": "completed",
361
- "finishReason": "tool-calls",
362
- "requestedTools": [
363
- "search_files"
364
- ],
365
- "inputTokens": 7702,
366
- "outputTokens": 67,
367
- "cachedInputTokens": 5120,
368
- "requestCharacters": 16834,
369
- "tools": [
370
- {
371
- "name": "search_files",
372
- "isError": false,
373
- "characters": 986
374
- }
375
- ]
376
- },
377
- {
378
- "index": 6,
379
- "status": "completed",
380
- "finishReason": "tool-calls",
381
- "requestedTools": [
382
- "search_files"
383
- ],
384
- "inputTokens": 8217,
385
- "outputTokens": 67,
386
- "cachedInputTokens": 7168,
387
- "requestCharacters": 18206,
388
- "tools": [
389
- {
390
- "name": "search_files",
391
- "isError": false,
392
- "characters": 158
393
- }
394
- ]
395
- },
396
- {
397
- "index": 7,
398
- "status": "completed",
399
- "finishReason": "tool-calls",
400
- "requestedTools": [
401
- "list_files",
402
- "search_files"
403
- ],
404
- "inputTokens": 5613,
405
- "outputTokens": 136,
406
- "cachedInputTokens": 3072,
407
- "requestCharacters": 1490,
408
- "tools": [
409
- {
410
- "name": "list_files",
411
- "isError": false,
412
- "characters": 4693
413
- },
414
- {
415
- "name": "search_files",
416
- "isError": false,
417
- "characters": 159
418
- }
419
- ]
420
- },
421
- {
422
- "index": 8,
423
- "status": "completed",
424
- "finishReason": "tool-calls",
425
- "requestedTools": [
426
- "read_files"
427
- ],
428
- "inputTokens": 7089,
429
- "outputTokens": 65,
430
- "cachedInputTokens": 5120,
431
- "requestCharacters": 16013,
432
- "tools": [
433
- {
434
- "name": "read_files",
435
- "isError": false,
436
- "characters": 6204
437
- }
438
- ]
439
- },
440
- {
441
- "index": 9,
442
- "status": "completed",
443
- "finishReason": "tool-calls",
444
- "requestedTools": [
445
- "repair_plan"
446
- ],
447
- "inputTokens": 9080,
448
- "outputTokens": 289,
449
- "cachedInputTokens": 6144,
450
- "requestCharacters": 22668,
451
- "tools": [
452
- {
453
- "name": "repair_plan",
454
- "isError": false,
455
- "characters": 1016
456
- }
457
- ]
458
- },
459
- {
460
- "index": 10,
461
- "status": "completed",
462
- "finishReason": "tool-calls",
463
- "requestedTools": [
464
- "search_files"
465
- ],
466
- "inputTokens": 9699,
467
- "outputTokens": 69,
468
- "cachedInputTokens": 8320,
469
- "requestCharacters": 25305,
470
- "tools": [
471
- {
472
- "name": "search_files",
473
- "isError": true,
474
- "characters": 4,
475
- "diagnostic": {
476
- "code": "EXECUTION_FAILED",
477
- "category": "execution",
478
- "failureType": "execution",
479
- "retryable": false,
480
- "chain": [
481
- {
482
- "validationCode": null,
483
- "providerReason": null,
484
- "validationIssues": [],
485
- "status": null,
486
- "errorClass": "Object",
487
- "providerHints": [],
488
- "fingerprint": "8d9717b4ef3febc41dc92b0bf34c50fec70e14065a7b61d22cade5b39f794b1b",
489
- "reason": null
490
- }
491
- ]
492
- }
493
- }
494
- ]
495
- },
496
- {
497
- "index": 11,
498
- "status": "completed",
499
- "finishReason": "tool-calls",
500
- "requestedTools": [
501
- "search_files"
502
- ],
503
- "inputTokens": 9812,
504
- "outputTokens": 69,
505
- "cachedInputTokens": 9216,
506
- "requestCharacters": 25825,
507
- "tools": [
508
- {
509
- "name": "search_files",
510
- "isError": true,
511
- "characters": 4,
512
- "diagnostic": {
513
- "code": "EXECUTION_FAILED",
514
- "category": "execution",
515
- "failureType": "execution",
516
- "retryable": false,
517
- "chain": [
518
- {
519
- "validationCode": null,
520
- "providerReason": null,
521
- "validationIssues": [],
522
- "status": null,
523
- "errorClass": "Object",
524
- "providerHints": [],
525
- "fingerprint": "8d9717b4ef3febc41dc92b0bf34c50fec70e14065a7b61d22cade5b39f794b1b",
526
- "reason": null
527
- }
528
- ]
529
- }
530
- }
531
- ]
532
- },
533
- {
534
- "index": 12,
535
- "status": "completed",
536
- "finishReason": "tool-calls",
537
- "requestedTools": [
538
- "read_files"
539
- ],
540
- "inputTokens": 9925,
541
- "outputTokens": 36,
542
- "cachedInputTokens": 9216,
543
- "requestCharacters": 26345,
544
- "tools": [
545
- {
546
- "name": "read_files",
547
- "isError": true,
548
- "characters": 4,
549
- "diagnostic": {
550
- "code": "EXECUTION_FAILED",
551
- "category": "execution",
552
- "failureType": "execution",
553
- "retryable": false,
554
- "chain": [
555
- {
556
- "validationCode": null,
557
- "providerReason": null,
558
- "validationIssues": [],
559
- "status": null,
560
- "errorClass": "Object",
561
- "providerHints": [],
562
- "fingerprint": "8d9717b4ef3febc41dc92b0bf34c50fec70e14065a7b61d22cade5b39f794b1b",
563
- "reason": null
564
- }
565
- ]
566
- }
567
- }
568
- ]
569
- },
570
- {
571
- "index": 13,
572
- "status": "completed",
573
- "finishReason": "tool-calls",
574
- "requestedTools": [
575
- "read_files"
576
- ],
577
- "inputTokens": 5843,
578
- "outputTokens": 36,
579
- "cachedInputTokens": 4096,
580
- "requestCharacters": 1841,
581
- "tools": [
582
- {
583
- "name": "read_files",
584
- "isError": true,
585
- "characters": 4,
586
- "diagnostic": {
587
- "code": "EXECUTION_FAILED",
588
- "category": "execution",
589
- "failureType": "execution",
590
- "retryable": false,
591
- "chain": [
592
- {
593
- "validationCode": null,
594
- "providerReason": null,
595
- "validationIssues": [],
596
- "status": null,
597
- "errorClass": "Object",
598
- "providerHints": [],
599
- "fingerprint": "a3693b65e8a63323d4d6d9d7125761d116a89efbf8ac80713295d4398769f9c2",
600
- "reason": null
601
- }
602
- ]
603
- }
604
- }
605
- ]
606
- }
607
- ],
608
- "inputTokens": 94008,
609
- "outputTokens": 1287,
610
- "cachedInputTokens": 69760,
611
- "modelCalls": 13,
612
- "compactions": [
613
- {
614
- "beforeStep": 7,
615
- "estimatedTokensBefore": 4317,
616
- "estimatedTokensAfter": 2216
617
- },
618
- {
619
- "beforeStep": 13,
620
- "estimatedTokensBefore": 6242,
621
- "estimatedTokensAfter": 2407
622
- }
623
- ],
624
- "terminalDiagnostic": {
625
- "code": "EXECUTION_FAILED",
626
- "category": "execution",
627
- "failureType": "budget",
628
- "retryable": false,
629
- "chain": [
630
- {
631
- "validationCode": null,
632
- "providerReason": null,
633
- "validationIssues": [],
634
- "status": null,
635
- "errorClass": "Object",
636
- "providerHints": [],
637
- "fingerprint": "064591d1d6249f6eadfb2800eddbdfe8576a334f23f5e1215117dc19107f21f4",
638
- "reason": "budget"
639
- }
640
- ]
641
- },
642
- "thrownDiagnostic": {
643
- "code": "EXECUTION_FAILED",
644
- "category": "execution",
645
- "failureType": "budget",
646
- "retryable": false,
647
- "chain": [
648
- {
649
- "validationCode": null,
650
- "providerReason": null,
651
- "validationIssues": [],
652
- "status": null,
653
- "errorClass": "HarnessExecutionError",
654
- "providerHints": [],
655
- "fingerprint": "064591d1d6249f6eadfb2800eddbdfe8576a334f23f5e1215117dc19107f21f4",
656
- "reason": "budget"
657
- },
658
- {
659
- "validationCode": null,
660
- "providerReason": null,
661
- "validationIssues": [],
662
- "status": null,
663
- "errorClass": "Error",
664
- "providerHints": [],
665
- "fingerprint": "064591d1d6249f6eadfb2800eddbdfe8576a334f23f5e1215117dc19107f21f4",
666
- "reason": "budget"
667
- }
668
- ]
669
- },
670
- "guardrails": [],
671
- "repairProgress": {
672
- "repeatedResults": 1,
673
- "suppressedResults": 1,
674
- "blockedBroadCalls": 0,
675
- "enteredClosure": true,
676
- "phase": "explore",
677
- "blockedPhaseCalls": 3,
678
- "planRecorded": true
679
- },
680
- "contextMetrics": [
681
- {
682
- "systemCharacters": 4851,
683
- "userCharacters": 2454,
684
- "assistantCharacters": 0,
685
- "toolResultCharacters": 0,
686
- "otherMessageCharacters": 0,
687
- "toolDefinitionCharacters": 9375,
688
- "unmeasuredToolDefinitions": 0
689
- },
690
- {
691
- "systemCharacters": 4851,
692
- "userCharacters": 2454,
693
- "assistantCharacters": 528,
694
- "toolResultCharacters": 928,
695
- "otherMessageCharacters": 0,
696
- "toolDefinitionCharacters": 9375,
697
- "unmeasuredToolDefinitions": 0
698
- },
699
- {
700
- "systemCharacters": 4851,
701
- "userCharacters": 2454,
702
- "assistantCharacters": 814,
703
- "toolResultCharacters": 1317,
704
- "otherMessageCharacters": 0,
705
- "toolDefinitionCharacters": 9375,
706
- "unmeasuredToolDefinitions": 0
707
- },
708
- {
709
- "systemCharacters": 4851,
710
- "userCharacters": 2454,
711
- "assistantCharacters": 1229,
712
- "toolResultCharacters": 5142,
713
- "otherMessageCharacters": 0,
714
- "toolDefinitionCharacters": 9375,
715
- "unmeasuredToolDefinitions": 0
716
- },
717
- {
718
- "systemCharacters": 4851,
719
- "userCharacters": 2454,
720
- "assistantCharacters": 1618,
721
- "toolResultCharacters": 7896,
722
- "otherMessageCharacters": 0,
723
- "toolDefinitionCharacters": 9375,
724
- "unmeasuredToolDefinitions": 0
725
- },
726
- {
727
- "systemCharacters": 4851,
728
- "userCharacters": 2454,
729
- "assistantCharacters": 1842,
730
- "toolResultCharacters": 9042,
731
- "otherMessageCharacters": 0,
732
- "toolDefinitionCharacters": 9375,
733
- "unmeasuredToolDefinitions": 0
734
- },
735
- {
736
- "systemCharacters": 4851,
737
- "userCharacters": 1488,
738
- "assistantCharacters": 3687,
739
- "toolResultCharacters": 318,
740
- "otherMessageCharacters": 0,
741
- "toolDefinitionCharacters": 9375,
742
- "unmeasuredToolDefinitions": 0
743
- },
744
- {
745
- "systemCharacters": 4851,
746
- "userCharacters": 1488,
747
- "assistantCharacters": 4177,
748
- "toolResultCharacters": 5488,
749
- "otherMessageCharacters": 0,
750
- "toolDefinitionCharacters": 9375,
751
- "unmeasuredToolDefinitions": 0
752
- },
753
- {
754
- "systemCharacters": 4851,
755
- "userCharacters": 1488,
756
- "assistantCharacters": 4468,
757
- "toolResultCharacters": 11850,
758
- "otherMessageCharacters": 0,
759
- "toolDefinitionCharacters": 9375,
760
- "unmeasuredToolDefinitions": 0
761
- },
762
- {
763
- "systemCharacters": 4851,
764
- "userCharacters": 1839,
765
- "assistantCharacters": 5577,
766
- "toolResultCharacters": 13025,
767
- "otherMessageCharacters": 0,
768
- "toolDefinitionCharacters": 9375,
769
- "unmeasuredToolDefinitions": 0
770
- },
771
- {
772
- "systemCharacters": 4851,
773
- "userCharacters": 1839,
774
- "assistantCharacters": 5827,
775
- "toolResultCharacters": 13293,
776
- "otherMessageCharacters": 0,
777
- "toolDefinitionCharacters": 9375,
778
- "unmeasuredToolDefinitions": 0
779
- },
780
- {
781
- "systemCharacters": 4851,
782
- "userCharacters": 1839,
783
- "assistantCharacters": 6077,
784
- "toolResultCharacters": 13561,
785
- "otherMessageCharacters": 0,
786
- "toolDefinitionCharacters": 9375,
787
- "unmeasuredToolDefinitions": 0
788
- },
789
- {
790
- "systemCharacters": 4851,
791
- "userCharacters": 1839,
792
- "assistantCharacters": 4505,
793
- "toolResultCharacters": 266,
794
- "otherMessageCharacters": 0,
795
- "toolDefinitionCharacters": 9375,
796
- "unmeasuredToolDefinitions": 0
797
- }
798
- ],
799
- "omittedContextMeasurements": 0,
800
- "toolCalls": 14,
801
- "patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
802
- "protectedFilesChanged": [],
803
- "gradingMethod": "empty-patch-no-solution",
804
- "officialResolved": false,
805
- "candidateCaptured": true,
806
- "candidatePatchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
807
- "candidateGradingStatus": "completed",
808
- "candidateResolved": false,
809
- "repairStages": {
810
- "candidatePresent": false,
811
- "importedPatchPresent": false,
812
- "verificationAttempted": false
813
- },
814
- "gradingDurationMs": 0.22466701921075583,
815
- "totalDurationMs": 64975.14075000072
816
- },
817
- {
818
- "candidate": "mini-swe-agent",
819
- "instanceId": "django__django-15851",
820
- "repetition": 0,
821
- "resolved": true,
822
- "gradingStatus": "completed",
823
- "usageComplete": true,
824
- "costUsd": null,
825
- "schemaVersion": 1,
826
- "status": "Submitted",
827
- "failure": null,
828
- "phase": "agent",
829
- "durationMs": 23770.26995801134,
830
- "approvals": 0,
831
- "toolCalls": 9,
832
- "inputTokens": 27391,
833
- "outputTokens": 628,
834
- "cachedInputTokens": 18688,
835
- "modelCalls": 9,
836
- "patchSha256": "873ee0e2d09108303f5ebe1fa4d0aec08ee9e4ce52b93941c70b4c8c91c21db4",
837
- "protectedFilesChanged": [],
838
- "officialResolved": true,
839
- "candidateCaptured": true,
840
- "candidatePatchSha256": "873ee0e2d09108303f5ebe1fa4d0aec08ee9e4ce52b93941c70b4c8c91c21db4",
841
- "candidateGradingStatus": "completed",
842
- "candidateResolved": true,
843
- "repairStages": {
844
- "candidatePresent": true,
845
- "importedPatchPresent": null,
846
- "verificationAttempted": null
847
- },
848
- "gradingDurationMs": 24181.44116702024,
849
- "totalDurationMs": 50162.21049998421
850
- }
851
- ]
852
- }
853
- }
854
- }