@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
@@ -1,573 +0,0 @@
1
- {
2
- "schemaVersion": 1,
3
- "kind": "development-plan-reserve-validation",
4
- "classification": "known development task; not holdout or GA acceptance",
5
- "implementation": {
6
- "gitCommit": "c2b2bb917d0471e61afc5f731a61c00b44fa3731",
7
- "sources": {
8
- "bun.lock": "c213d497a98bfbea1379bd60850d0ec8ede02560df9a63bf3b737d35648c4909",
9
- "evaluations/external/requirements.lock": "42e90a08f10f821ebb958af79256f707a9fb5cf365277c4f9e2715d612028179",
10
- "package.json": "5379cb4dcfab000eb5a9b8f4cdf11c26cc09aa12622cfc91a06504c69cf7b875",
11
- "scripts/benchmark-swebench.ts": "ed17063e1847017ba2e72f14732b6ff8f5b1af7cd5253b91302af75f2a9e8476",
12
- "scripts/swebench/candidate.py": "f5e3410b91b950acfbe50fc7511891816a8fb1c223082397e2c6300cf1e866cf",
13
- "scripts/swebench/candidate.ts": "bf102becfcce0c9a3f0df0a8f1ce0e5aaea7db2d252f6d9454a8370c24e53982",
14
- "scripts/swebench/common.py": "ad790227dac3bec1f592c458c993efff4f9d3de8f0df39b33e3238b58b3f0b3b",
15
- "scripts/swebench/context-metrics.ts": "7b84da6789413aa634d997c5963ee6796584e06c3eafe5f68f424fb7e27815e9",
16
- "scripts/swebench/mini_driver.py": "bd0a77221878370ec44760122a51f07fb56d969612afa9a7f171248b2958baa6",
17
- "scripts/swebench/model-budget.ts": "e46dd406ee5d58a051a15c7d7133513666292303d8c6534f861a6db0e711f47c",
18
- "scripts/swebench/model-catalog.ts": "eb79e7333f4f5804f96da87d1952382f620e7165a95b60489fcc2588debe64d8",
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": "24830996fb91c8ad34928a4b7d5da62ea1ab8f8792a77ac675cc9638d750ff2b",
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": "e9b85f5d83634ac7ec79d8052addb35e765d04fc46883d1e38612269bcf12609",
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": "df19e273be815b2e37ace12e03a02793fe13c13853fcb70b8d2c9d217a68bc87",
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
- "changedSourcesFromBaseline": [
89
- "src/harness.ts",
90
- "src/repair-controller.ts"
91
- ],
92
- "samples": [
93
- {
94
- "candidate": "zhivex",
95
- "instanceId": "django__django-15851",
96
- "repetition": 0,
97
- "resolved": false,
98
- "gradingStatus": "completed",
99
- "usageComplete": true,
100
- "costUsd": null,
101
- "candidateCaptureFailure": null,
102
- "modelTimings": [
103
- {
104
- "durationMs": 3388.923459,
105
- "firstTokenMs": 3387.653417,
106
- "completed": true
107
- },
108
- {
109
- "durationMs": 1408.218417,
110
- "firstTokenMs": 1407.9608749999998,
111
- "completed": true
112
- },
113
- {
114
- "durationMs": 2716.434375,
115
- "firstTokenMs": 2716.1829580000003,
116
- "completed": true
117
- },
118
- {
119
- "durationMs": 4837.4990419999995,
120
- "firstTokenMs": null,
121
- "completed": true
122
- },
123
- {
124
- "durationMs": 4781.182208,
125
- "firstTokenMs": null,
126
- "completed": true
127
- }
128
- ],
129
- "modelCatalog": {
130
- "records": [
131
- {
132
- "call": 1,
133
- "offered": [
134
- "apply_reviewed_edits",
135
- "apply_reviewed_replacement",
136
- "inspect_environment_patch",
137
- "list_files",
138
- "mutation_audit",
139
- "read_files",
140
- "read_task",
141
- "repair_plan",
142
- "run_environment_command",
143
- "run_environment_shell",
144
- "search_files",
145
- "search_many",
146
- "verify_and_apply_environment_patch"
147
- ],
148
- "unknownOffered": 0,
149
- "systemMessages": 1,
150
- "choice": "default",
151
- "returned": [
152
- {
153
- "name": "search_files",
154
- "offered": true,
155
- "registered": true
156
- }
157
- ],
158
- "omittedReturned": 0,
159
- "completed": true
160
- },
161
- {
162
- "call": 2,
163
- "offered": [
164
- "apply_reviewed_edits",
165
- "apply_reviewed_replacement",
166
- "inspect_environment_patch",
167
- "list_files",
168
- "mutation_audit",
169
- "read_files",
170
- "read_task",
171
- "repair_plan",
172
- "run_environment_command",
173
- "run_environment_shell",
174
- "search_files",
175
- "search_many",
176
- "verify_and_apply_environment_patch"
177
- ],
178
- "unknownOffered": 0,
179
- "systemMessages": 1,
180
- "choice": "default",
181
- "returned": [
182
- {
183
- "name": "read_files",
184
- "offered": true,
185
- "registered": true
186
- }
187
- ],
188
- "omittedReturned": 0,
189
- "completed": true
190
- },
191
- {
192
- "call": 3,
193
- "offered": [
194
- "apply_reviewed_edits",
195
- "apply_reviewed_replacement",
196
- "inspect_environment_patch",
197
- "list_files",
198
- "mutation_audit",
199
- "read_files",
200
- "read_task",
201
- "repair_plan",
202
- "run_environment_command",
203
- "run_environment_shell",
204
- "search_files",
205
- "search_many",
206
- "verify_and_apply_environment_patch"
207
- ],
208
- "unknownOffered": 0,
209
- "systemMessages": 1,
210
- "choice": "default",
211
- "returned": [
212
- {
213
- "name": "apply_reviewed_replacement",
214
- "offered": true,
215
- "registered": true
216
- }
217
- ],
218
- "omittedReturned": 0,
219
- "completed": true
220
- },
221
- {
222
- "call": 4,
223
- "offered": [
224
- "read_task",
225
- "repair_plan"
226
- ],
227
- "unknownOffered": 0,
228
- "systemMessages": 1,
229
- "choice": "named",
230
- "returned": [],
231
- "omittedReturned": 0,
232
- "completed": true
233
- },
234
- {
235
- "call": 5,
236
- "offered": [
237
- "read_task",
238
- "repair_plan"
239
- ],
240
- "unknownOffered": 0,
241
- "systemMessages": 1,
242
- "choice": "named",
243
- "returned": [],
244
- "omittedReturned": 0,
245
- "completed": true
246
- }
247
- ],
248
- "omittedCalls": 0
249
- },
250
- "stageTimings": [
251
- {
252
- "event": "edit-requested",
253
- "elapsedMs": 10804.035083
254
- }
255
- ],
256
- "approvalTimings": [
257
- {
258
- "durationMs": 0.12304200000107812,
259
- "resolved": true
260
- }
261
- ],
262
- "toolTimings": [
263
- {
264
- "name": "search_files",
265
- "calls": 1,
266
- "errors": 0,
267
- "totalMs": 428.341958,
268
- "maxMs": 428.341958
269
- },
270
- {
271
- "name": "read_files",
272
- "calls": 1,
273
- "errors": 0,
274
- "totalMs": 1.6014580000000933,
275
- "maxMs": 1.6014580000000933
276
- },
277
- {
278
- "name": "read_task",
279
- "calls": 1,
280
- "errors": 0,
281
- "totalMs": 0.16408299999966403,
282
- "maxMs": 0.16408299999966403
283
- }
284
- ],
285
- "schemaVersion": 1,
286
- "status": "failed",
287
- "failure": "AGENT_FAILED",
288
- "phase": "agent",
289
- "durationMs": 25111.734458,
290
- "approvals": 1,
291
- "turns": [
292
- {
293
- "index": 1,
294
- "status": "completed",
295
- "finishReason": "tool-calls",
296
- "requestedTools": [
297
- "search_files"
298
- ],
299
- "inputTokens": 4610,
300
- "outputTokens": 68,
301
- "cachedInputTokens": 4096,
302
- "requestCharacters": 7403,
303
- "tools": [
304
- {
305
- "name": "search_files",
306
- "isError": false,
307
- "characters": 346
308
- }
309
- ]
310
- },
311
- {
312
- "index": 2,
313
- "status": "completed",
314
- "finishReason": "tool-calls",
315
- "requestedTools": [
316
- "read_files"
317
- ],
318
- "inputTokens": 4841,
319
- "outputTokens": 39,
320
- "cachedInputTokens": 4096,
321
- "requestCharacters": 8139,
322
- "tools": [
323
- {
324
- "name": "read_files",
325
- "isError": false,
326
- "characters": 2673
327
- }
328
- ]
329
- },
330
- {
331
- "index": 3,
332
- "status": "waiting_approval",
333
- "finishReason": "tool-calls",
334
- "requestedTools": [
335
- "apply_reviewed_replacement"
336
- ],
337
- "inputTokens": 5762,
338
- "outputTokens": 167,
339
- "cachedInputTokens": 4096,
340
- "requestCharacters": 11164,
341
- "tools": []
342
- },
343
- {
344
- "index": 4,
345
- "status": "completed",
346
- "finishReason": "tool-calls",
347
- "requestedTools": [
348
- "read_task"
349
- ],
350
- "inputTokens": 3640,
351
- "outputTokens": 354,
352
- "cachedInputTokens": 0,
353
- "requestCharacters": 12027,
354
- "tools": [
355
- {
356
- "name": "apply_reviewed_replacement",
357
- "isError": true,
358
- "characters": 4,
359
- "diagnostic": {
360
- "code": "EXECUTION_FAILED",
361
- "category": "execution",
362
- "failureType": "execution",
363
- "retryable": false,
364
- "chain": [
365
- {
366
- "validationCode": null,
367
- "providerReason": null,
368
- "validationIssues": [],
369
- "status": null,
370
- "errorClass": "Object",
371
- "providerHints": [],
372
- "fingerprint": "191319844fbd1d61162a1c24b2ba46a21807b79e1c51028566f84e8c0aa8a329",
373
- "reason": null
374
- }
375
- ]
376
- }
377
- }
378
- ]
379
- },
380
- {
381
- "index": 5,
382
- "status": "completed",
383
- "finishReason": "stop",
384
- "requestedTools": [],
385
- "inputTokens": 4063,
386
- "outputTokens": 321,
387
- "cachedInputTokens": 3072,
388
- "requestCharacters": 13640,
389
- "tools": []
390
- }
391
- ],
392
- "inputTokens": 22916,
393
- "outputTokens": 949,
394
- "cachedInputTokens": 15360,
395
- "modelCalls": 5,
396
- "compactions": [],
397
- "terminalDiagnostic": {
398
- "code": "EXECUTION_FAILED",
399
- "category": "execution",
400
- "failureType": "execution",
401
- "retryable": false,
402
- "chain": [
403
- {
404
- "validationCode": null,
405
- "providerReason": null,
406
- "validationIssues": [],
407
- "status": null,
408
- "errorClass": "Object",
409
- "providerHints": [],
410
- "fingerprint": "df4ad18f75f381d4abf1c3a9a9cb1ce99246204330b132a8d70938de039a0be4",
411
- "reason": null
412
- }
413
- ]
414
- },
415
- "thrownDiagnostic": null,
416
- "guardrails": [],
417
- "repairProgress": {
418
- "repeatedResults": 0,
419
- "suppressedResults": 0,
420
- "blockedBroadCalls": 0,
421
- "enteredClosure": false,
422
- "phase": "explore",
423
- "blockedPhaseCalls": 0,
424
- "planRecorded": false
425
- },
426
- "contextMetrics": [
427
- {
428
- "systemCharacters": 4851,
429
- "userCharacters": 2548,
430
- "assistantCharacters": 0,
431
- "toolResultCharacters": 0,
432
- "otherMessageCharacters": 0,
433
- "toolDefinitionCharacters": 9375,
434
- "unmeasuredToolDefinitions": 0
435
- },
436
- {
437
- "systemCharacters": 4851,
438
- "userCharacters": 2548,
439
- "assistantCharacters": 228,
440
- "toolResultCharacters": 506,
441
- "otherMessageCharacters": 0,
442
- "toolDefinitionCharacters": 9375,
443
- "unmeasuredToolDefinitions": 0
444
- },
445
- {
446
- "systemCharacters": 4851,
447
- "userCharacters": 2548,
448
- "assistantCharacters": 420,
449
- "toolResultCharacters": 3337,
450
- "otherMessageCharacters": 0,
451
- "toolDefinitionCharacters": 9375,
452
- "unmeasuredToolDefinitions": 0
453
- },
454
- {
455
- "systemCharacters": 4851,
456
- "userCharacters": 2547,
457
- "assistantCharacters": 895,
458
- "toolResultCharacters": 3724,
459
- "otherMessageCharacters": 0,
460
- "toolDefinitionCharacters": 1635,
461
- "unmeasuredToolDefinitions": 0
462
- },
463
- {
464
- "systemCharacters": 4851,
465
- "userCharacters": 2687,
466
- "assistantCharacters": 1044,
467
- "toolResultCharacters": 5046,
468
- "otherMessageCharacters": 0,
469
- "toolDefinitionCharacters": 1635,
470
- "unmeasuredToolDefinitions": 0
471
- }
472
- ],
473
- "omittedContextMeasurements": 0,
474
- "toolCalls": 3,
475
- "patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
476
- "protectedFilesChanged": [],
477
- "gradingMethod": "empty-patch-no-solution",
478
- "officialResolved": false,
479
- "candidateCaptured": true,
480
- "candidatePatchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
481
- "candidateGradingStatus": "completed",
482
- "candidateResolved": false,
483
- "repairStages": {
484
- "candidatePresent": false,
485
- "importedPatchPresent": false,
486
- "verificationAttempted": false
487
- },
488
- "gradingDurationMs": 0.1598750241100788,
489
- "totalDurationMs": 35821.911707986146
490
- },
491
- {
492
- "candidate": "mini-swe-agent",
493
- "instanceId": "django__django-15851",
494
- "repetition": 0,
495
- "resolved": true,
496
- "gradingStatus": "completed",
497
- "usageComplete": true,
498
- "costUsd": null,
499
- "schemaVersion": 1,
500
- "status": "Submitted",
501
- "failure": null,
502
- "phase": "agent",
503
- "durationMs": 21215.51474998705,
504
- "approvals": 0,
505
- "toolCalls": 9,
506
- "inputTokens": 21973,
507
- "outputTokens": 589,
508
- "cachedInputTokens": 15360,
509
- "modelCalls": 9,
510
- "patchSha256": "873ee0e2d09108303f5ebe1fa4d0aec08ee9e4ce52b93941c70b4c8c91c21db4",
511
- "protectedFilesChanged": [],
512
- "officialResolved": true,
513
- "candidateCaptured": true,
514
- "candidatePatchSha256": "873ee0e2d09108303f5ebe1fa4d0aec08ee9e4ce52b93941c70b4c8c91c21db4",
515
- "candidateGradingStatus": "completed",
516
- "candidateResolved": true,
517
- "repairStages": {
518
- "candidatePresent": true,
519
- "importedPatchPresent": null,
520
- "verificationAttempted": null
521
- },
522
- "gradingDurationMs": 24117.599625024013,
523
- "totalDurationMs": 47536.88254201552
524
- }
525
- ],
526
- "report": {
527
- "schemaVersion": 1,
528
- "kind": "swebench-comparison",
529
- "manifestSha256": "6893be2c42449a5ee7eda852bb13dd55863190612d793fb11c34ecc112ab9b4a",
530
- "complete": true,
531
- "candidates": {
532
- "zhivex": {
533
- "planned": 1,
534
- "recorded": 1,
535
- "resolved": 0,
536
- "candidateCaptured": 1,
537
- "candidateResolved": 0,
538
- "candidateGraded": 1,
539
- "resolutionRate": 0.0,
540
- "missing": 0,
541
- "gradingFailures": 0,
542
- "usageComplete": true,
543
- "totalCostUsd": null,
544
- "costPerResolvedUsd": null,
545
- "resolvedP50Ms": null
546
- },
547
- "mini-swe-agent": {
548
- "planned": 1,
549
- "recorded": 1,
550
- "resolved": 1,
551
- "candidateCaptured": 1,
552
- "candidateResolved": 1,
553
- "candidateGraded": 1,
554
- "resolutionRate": 1.0,
555
- "missing": 0,
556
- "gradingFailures": 0,
557
- "usageComplete": true,
558
- "totalCostUsd": null,
559
- "costPerResolvedUsd": null,
560
- "resolvedP50Ms": 47536.88254201552
561
- }
562
- },
563
- "pairedTaskResolutionDifference": -1.0,
564
- "pairedTaskBootstrap95": null,
565
- "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."
566
- },
567
- "limitations": [
568
- "Single repetition; cannot infer causal efficacy",
569
- "Missing-plan rejection occurred before reserve threshold",
570
- "Two named-tool selection turns returned no tool calls; local wire serialization verified separately",
571
- "Do not infer provider-side request contents from adapter observation alone"
572
- ]
573
- }
@@ -1,24 +0,0 @@
1
- {
2
- "kind": "development-plan-reserve-validation",
3
- "classification": "known development task, not holdout or GA acceptance",
4
- "baseline": "ga-catalog-observed-qwen",
5
- "change": "bounded missing-plan recovery may consume existing closure reserve; policy fingerprint updated",
6
- "repetitions": 1,
7
- "control": "unchanged mini-SWE-agent",
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
- "model": "qwen3.8-flash",
18
- "sources": {
19
- "src/harness.ts": "e9b85f5d83634ac7ec79d8052addb35e765d04fc46883d1e38612269bcf12609",
20
- "src/repair-controller.ts": "df19e273be815b2e37ace12e03a02793fe13c13853fcb70b8d2c9d217a68bc87",
21
- "package.json": "5379cb4dcfab000eb5a9b8f4cdf11c26cc09aa12622cfc91a06504c69cf7b875",
22
- "bun.lock": "c213d497a98bfbea1379bd60850d0ec8ede02560df9a63bf3b737d35648c4909"
23
- }
24
- }
@@ -1,19 +0,0 @@
1
- {
2
- "schemaVersion": 1,
3
- "kind": "local-plan-transition-validation",
4
- "baseCommit": "50f255d7d48ac8ed99627d80ad5c0339fa0936a3",
5
- "candidate": "working tree, not a release attestation",
6
- "fileSha256": {
7
- "src/repair-controller.ts": "063ee52351d70bd99e53a28d2009694ff4ead2236a2b227844ae8980b4bc03ea",
8
- "tests/repair-plan-transition.test.ts": "052a65328e5866f0dcdb86d7fbd8b554e904176e72c120f81f386227d34bafb8",
9
- "tests/full-remediation.test.ts": "d109108c5b4ad2eb5cf7f11c97a521e45d9f84eba3cee182a0931bc9d59aeeec"
10
- },
11
- "suite": {
12
- "passed": 554,
13
- "failed": 0
14
- },
15
- "types": "passed",
16
- "preparationContract": "passed",
17
- "installedPackage": "passed",
18
- "live": "v7 failed before exercising missing-plan transition"
19
- }
@@ -1,24 +0,0 @@
1
- {
2
- "kind": "private-verifier-diagnosis",
3
- "repetitions": 1,
4
- "control": null,
5
- "classification": "Debugging only; not comparative acceptance or holdout",
6
- "limits": {
7
- "steps": 24,
8
- "outputPerTurn": 2048,
9
- "inputTokens": 100000,
10
- "outputTokens": 16000,
11
- "timeoutSeconds": 300,
12
- "memoryMb": 2048,
13
- "cpus": 2
14
- },
15
- "sources": {
16
- "scripts/swebench/verifier-observer.ts": "a90544437473218a83477a1cffb59ee9f645c12abdf8960b787f3e21606035bf",
17
- "scripts/swebench/zhivex-driver.ts": "53fbd6c51659f40d169c71b7450416724693641be2c237425f1924277b0fd496",
18
- "src/harness.ts": "1d305078e3c56c24bb659c34aac37c96bf11a4e60af6607bb4b9d65964e84791",
19
- "src/repair-controller.ts": "41f1f09032131306f3284edbf105930577504af0bf764ba98a105c4eee70a1e7",
20
- "bun.lock": "dbabdf161b3dba306f475c81f37e5ab1620fb98052127bb3ed2a0a0cb611ede4"
21
- },
22
- "retention": "Local mode-0700 temporary directory, bounded verifier details only; no raw diagnostic in public reports",
23
- "stopRule": "One execution; no automatic retry"
24
- }
@@ -1,41 +0,0 @@
1
- {
2
- "schemaVersion": 1,
3
- "kind": "private-verifier-root-cause",
4
- "classification": "One development diagnostic; no holdout or acceptance claim",
5
- "result": {
6
- "status": "failed",
7
- "failure": "INPUT_TOKEN_BUDGET",
8
- "inputTokens": 92923,
9
- "outputTokens": 1028,
10
- "usageComplete": true
11
- },
12
- "verifier": {
13
- "command": "python",
14
- "runner": "pytest",
15
- "exitCode": 1,
16
- "timedOut": false,
17
- "cause": "pytest is not installed in the execution image",
18
- "rawRecordSha256": "e6abe285468b47bade51ea28ed0665160ed042bad33a494b239a050d400a419e"
19
- },
20
- "captureDefect": {
21
- "observedScopes": [
22
- "[\"local\",null,\"workspace-c55b2d1c50bf51cc\"]",
23
- "[null,null,null]"
24
- ],
25
- "cause": "Capture used config.scope while actual run state was unscoped; these identify distinct snapshots.",
26
- "impact": "Historical candidatePresent=false does not prove the run had no candidate; imported host patch and official resolved results are unchanged."
27
- },
28
- "corrections": [
29
- "Remove unverified pytest recommendation from benchmark instructions; discover existing runner or self-contained assertion.",
30
- "Capture candidates using state.runId and state.scope, including undefined scope."
31
- ],
32
- "validation": {
33
- "focusedSuite": "13 passed",
34
- "toolingTypecheck": "passed"
35
- },
36
- "limitations": [
37
- "Does not retroactively identify every prior verifier failure.",
38
- "No claim that instruction correction resolves the task live.",
39
- "Private state retained locally for offline candidate diagnosis; raw output not embedded in this report."
40
- ]
41
- }