@zhivex-ai/harness 1.0.0-rc.7 → 1.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (170) hide show
  1. package/CHANGELOG.md +190 -0
  2. package/README.md +47 -62
  3. package/ROADMAP.md +15 -6
  4. package/SECURITY.md +1 -1
  5. package/benchmarks/README.md +48 -0
  6. package/benchmarks/baselines/context-navigation-2026-09-09.json +94 -0
  7. package/benchmarks/baselines/efficiency-2026-09-08.json +233 -0
  8. package/benchmarks/baselines/external-final-2026-09-08.json +588 -0
  9. package/benchmarks/baselines/external-intermediate-2026-09-08.json +116 -0
  10. package/benchmarks/baselines/external-matched-openai-2026-09-08.json +1922 -0
  11. package/benchmarks/baselines/external-matched-qwen-2026-09-08.json +1706 -0
  12. package/benchmarks/baselines/external-pilot-2026-09-08.json +439 -0
  13. package/benchmarks/baselines/external-qwen-flash-2026-09-08.json +1570 -0
  14. package/benchmarks/baselines/external-qwen-remediation-2026-09-09.json +1509 -0
  15. package/benchmarks/baselines/external-qwen-sdk-114-progress-2026-09-09.json +2509 -0
  16. package/benchmarks/baselines/external-sdk-upgrade-2026-09-08.json +564 -0
  17. package/benchmarks/baselines/external-verifier-recovery-2026-09-09.json +794 -0
  18. package/benchmarks/baselines/full-harness-review-2026-09-10.json +134 -0
  19. package/benchmarks/baselines/harness-audit-2026-09-09.json +136 -0
  20. package/benchmarks/baselines/harness-remediation-2026-09-09.json +160 -0
  21. package/benchmarks/baselines/oci-remediation-2026-09-10.json +535 -0
  22. package/benchmarks/baselines/rc14-holdout-2026-09-10.json +854 -0
  23. package/benchmarks/baselines/repair-architecture-audit-2026-09-09.json +75 -0
  24. package/benchmarks/baselines/time-to-safe-fix-live-expanded-2026-08-21.json +186 -0
  25. package/benchmarks/baselines/time-to-safe-fix-live-smoke-2026-08-21.json +186 -0
  26. package/contracts/public-api.json +25 -0
  27. package/contracts/security-controls.json +3 -2
  28. package/contracts/stable-api-signatures.json +58 -54
  29. package/dist/bounded-reads.d.ts +4 -0
  30. package/dist/change-envelope.d.ts +4 -4
  31. package/dist/cli-options.d.ts +2 -1
  32. package/dist/cli-profiles.d.ts +39 -0
  33. package/dist/cli-stream.d.ts +40 -40
  34. package/dist/cli.d.ts +38 -35
  35. package/dist/cli.js +6556 -4030
  36. package/dist/compaction.d.ts +12 -0
  37. package/dist/config.d.ts +6 -1
  38. package/dist/console-context.d.ts +26 -0
  39. package/dist/console-input.d.ts +28 -0
  40. package/dist/context-engineering.d.ts +5 -5
  41. package/dist/context-metrics.d.ts +11 -0
  42. package/dist/edit-contracts.d.ts +2 -2
  43. package/dist/execution-environment.d.ts +9 -5
  44. package/dist/harness.d.ts +52 -18
  45. package/dist/hostile-repository-demo.js +2942 -1088
  46. package/dist/index.d.ts +3 -3
  47. package/dist/index.js +4316 -2435
  48. package/dist/json-contracts.d.ts +292 -236
  49. package/dist/model-budget.d.ts +61 -0
  50. package/dist/operations.d.ts +82 -20
  51. package/dist/orchestration.d.ts +1 -0
  52. package/dist/providers.d.ts +5 -2
  53. package/dist/repair-controller.d.ts +72 -0
  54. package/dist/repair-progress.d.ts +40 -0
  55. package/dist/repair-verifier.d.ts +6 -0
  56. package/dist/replacement-edits.d.ts +9 -0
  57. package/dist/routing.d.ts +1 -1
  58. package/dist/run-interruption.d.ts +4 -0
  59. package/dist/runtime-checkpoints.d.ts +7 -0
  60. package/dist/runtime-diagnostics.d.ts +63 -0
  61. package/dist/runtime-policy.d.ts +36 -0
  62. package/dist/sessions.d.ts +1 -1
  63. package/dist/state-backup.d.ts +2 -2
  64. package/dist/task-memory.d.ts +36 -0
  65. package/dist/terminal-markdown.d.ts +12 -0
  66. package/dist/time-to-safe-fix.d.ts +19 -19
  67. package/dist/tool-registry.d.ts +4 -0
  68. package/dist/verify-historical-migrations.js +6987 -5140
  69. package/dist/workspace-mutation-lock.d.ts +5 -0
  70. package/dist/workspace.d.ts +39 -4
  71. package/dist/zhx.js +6556 -4030
  72. package/docs/CLI.md +89 -3
  73. package/docs/CONTEXT_ENGINEERING.md +160 -0
  74. package/docs/EXECUTION_ENVIRONMENTS.md +21 -0
  75. package/docs/EXTENSIBILITY.md +2 -2
  76. package/docs/GA_READINESS.md +13 -7
  77. package/docs/LIVE_CERTIFICATION.md +12 -2
  78. package/docs/RC13_SECURITY_REVIEW.md +28 -0
  79. package/docs/RC14_DELEGATED_SECURITY_DECISION.md +80 -0
  80. package/docs/RC14_SECURITY_REVIEW.md +40 -0
  81. package/docs/README.md +33 -0
  82. package/docs/RELEASE.md +4 -2
  83. package/docs/REPOSITORY_EDITING.md +47 -0
  84. package/docs/SECURITY_REVIEW_EVIDENCE.md +5 -3
  85. package/docs/THREAT_MODEL.md +3 -3
  86. package/docs/TIME_TO_SAFE_FIX.md +4 -4
  87. package/docs/ga-readiness.json +147 -16
  88. package/docs/reports/EFFICIENCY_REVIEW.md +156 -0
  89. package/docs/reports/EXTERNAL_COMPARISON.md +434 -0
  90. package/docs/reports/FULL_HARNESS_REVIEW_2026-09-10.md +200 -0
  91. package/docs/reports/GA_BUDGET_REMEDIATION_2026-09-19.md +38 -0
  92. package/docs/reports/GA_REPAIR_RECOVERY_2026-09-19.md +700 -0
  93. package/docs/reports/GA_VALIDATION_2026-09-19.md +111 -0
  94. package/docs/reports/HARNESS_ARCHITECTURE_REVIEW_2026-09-09.md +202 -0
  95. package/docs/reports/HARNESS_AUDIT_2026-09-09.md +306 -0
  96. package/docs/reports/HARNESS_REMEDIATION_2026-09-09.md +74 -0
  97. package/docs/reports/HARNESS_REMEDIATION_2026-09-10.md +90 -0
  98. package/docs/reports/MODEL_COMPARISON_2026-09-09.md +184 -0
  99. package/docs/reports/QWEN_REMEDIATION_COMPARISON_2026-09-09.md +142 -0
  100. package/docs/reports/RC14_VALIDATION_2026-09-10.md +45 -0
  101. package/docs/reports/README.md +26 -0
  102. package/docs/reports/evidence/ga-budget-remediation-2026-09-19.json +133 -0
  103. package/docs/reports/evidence/ga-catalog-ablation-2026-09-19.json +699 -0
  104. package/docs/reports/evidence/ga-catalog-ablation-plan-2026-09-19.json +40 -0
  105. package/docs/reports/evidence/ga-catalog-observed-2026-09-19.json +985 -0
  106. package/docs/reports/evidence/ga-catalog-observed-plan-2026-09-19.json +28 -0
  107. package/docs/reports/evidence/ga-catalog-observed-status-2026-09-19.json +15 -0
  108. package/docs/reports/evidence/ga-complete-local-check-2026-09-19.json +47 -0
  109. package/docs/reports/evidence/ga-completion-reminder-2026-09-19.json +22 -0
  110. package/docs/reports/evidence/ga-fresh-cohort-plan-2026-09-19.json +54 -0
  111. package/docs/reports/evidence/ga-fresh-cohort-preparation-2026-09-19.json +242 -0
  112. package/docs/reports/evidence/ga-fresh-cohort-result-2026-09-19.json +4318 -0
  113. package/docs/reports/evidence/ga-local-validation-followup-2026-09-19.json +66 -0
  114. package/docs/reports/evidence/ga-node-consumers-2026-09-19.json +31 -0
  115. package/docs/reports/evidence/ga-package-content-validation-2026-09-19.json +22 -0
  116. package/docs/reports/evidence/ga-plan-completion-2026-09-19.json +39 -0
  117. package/docs/reports/evidence/ga-plan-reserve-2026-09-19.json +573 -0
  118. package/docs/reports/evidence/ga-plan-reserve-plan-2026-09-19.json +24 -0
  119. package/docs/reports/evidence/ga-plan-transition-2026-09-19.json +19 -0
  120. package/docs/reports/evidence/ga-private-verifier-plan-2026-09-19.json +24 -0
  121. package/docs/reports/evidence/ga-private-verifier-root-cause-2026-09-19.json +41 -0
  122. package/docs/reports/evidence/ga-published-sdk-2026-09-19.json +35 -0
  123. package/docs/reports/evidence/ga-python-checkout-imports-2026-09-19.json +95 -0
  124. package/docs/reports/evidence/ga-python-origin-delivery-2026-09-19.json +211 -0
  125. package/docs/reports/evidence/ga-python-origin-delivery-plan-2026-09-19.json +27 -0
  126. package/docs/reports/evidence/ga-qwen-patched-package-2026-09-19.json +1092 -0
  127. package/docs/reports/evidence/ga-qwen-patched-package-plan-2026-09-19.json +18 -0
  128. package/docs/reports/evidence/ga-qwen-published-2026-09-19.json +571 -0
  129. package/docs/reports/evidence/ga-qwen-published-plan-2026-09-19.json +18 -0
  130. package/docs/reports/evidence/ga-qwen-tool-choice-2026-09-19.json +85 -0
  131. package/docs/reports/evidence/ga-qwen-tool-choice-patched-2026-09-19.json +85 -0
  132. package/docs/reports/evidence/ga-recovery-development-2026-09-19.json +1066 -0
  133. package/docs/reports/evidence/ga-recovery-graded-development-2026-09-19.json +1313 -0
  134. package/docs/reports/evidence/ga-recovery-graded-v2-2026-09-19.json +1151 -0
  135. package/docs/reports/evidence/ga-recovery-v3-2026-09-19.json +3943 -0
  136. package/docs/reports/evidence/ga-recovery-v4-2026-09-19.json +1055 -0
  137. package/docs/reports/evidence/ga-recovery-v5-2026-09-19.json +1245 -0
  138. package/docs/reports/evidence/ga-recovery-v6-2026-09-19.json +699 -0
  139. package/docs/reports/evidence/ga-recovery-v7-2026-09-19.json +854 -0
  140. package/docs/reports/evidence/ga-recovery-v8-2026-09-19.json +596 -0
  141. package/docs/reports/evidence/ga-required-delivery-2026-09-19.json +25 -0
  142. package/docs/reports/evidence/ga-required-delivery-live-2026-09-19.json +1337 -0
  143. package/docs/reports/evidence/ga-required-delivery-live-plan-2026-09-19.json +25 -0
  144. package/docs/reports/evidence/ga-retained-candidate-grading-2026-09-19.json +30 -0
  145. package/docs/reports/evidence/ga-tool-selection-live-2026-09-19.json +559 -0
  146. package/docs/reports/evidence/ga-tool-selection-live-plan-2026-09-19.json +28 -0
  147. package/docs/reports/evidence/ga-tool-selection-recovery-2026-09-19.json +27 -0
  148. package/docs/reports/evidence/ga-validation-2026-09-19.json +236 -0
  149. package/docs/reports/evidence/ga-verifier-discovery-live-2026-09-19.json +1369 -0
  150. package/docs/reports/evidence/ga-verifier-discovery-plan-2026-09-19.json +29 -0
  151. package/docs/reports/evidence/ga-verifier-failure-identification-2026-09-19.json +30 -0
  152. package/docs/reports/evidence/ga-verifier-feedback-2026-09-19.json +65 -0
  153. package/docs/reports/evidence/ga-verifier-hints-live-2026-09-19.json +1297 -0
  154. package/docs/reports/evidence/ga-verifier-hints-plan-2026-09-19.json +27 -0
  155. package/docs/reports/evidence/ga-work-boundary-context-analysis-2026-09-19.json +113 -0
  156. package/docs/reports/evidence/ga-work-boundary-live-2026-09-19.json +301 -0
  157. package/docs/reports/evidence/ga-work-boundary-live-plan-2026-09-19.json +84 -0
  158. package/docs/reports/evidence/ga-work-budget-planning-2026-09-19.json +32 -0
  159. package/docs/reports/evidence/ga-working-context-2026-09-19.json +22 -0
  160. package/docs/reports/evidence/rc14-delegated-security-review-2026-09-20.json +81 -0
  161. package/docs/reports/evidence/rc14-ga-gate-2026-09-20.json +18 -0
  162. package/docs/reports/evidence/rc14-representative-2026-09-20.json +509 -0
  163. package/docs/reports/evidence/rc14-security-regressions-2026-09-20.json +64 -0
  164. package/docs/reports/evidence/security-current-2026-09-19.json +91 -0
  165. package/docs/reports/evidence/security-remediation-2026-09-19.json +97 -0
  166. package/evaluations/repair-controller-experiment.json +24 -0
  167. package/evaluations/representative-assembly-matrix.json +63 -0
  168. package/evaluations/representative-matrix.json +2219 -2
  169. package/fixtures/contracts/v1/init.json +19 -0
  170. package/package.json +25 -16
@@ -0,0 +1,18 @@
1
+ {
2
+ "kind": "local-package-repair-validation",
3
+ "classification": "known development case; not registry or GA acceptance",
4
+ "sdkCommit": "35e2bb49340acb68af125fc03df4389cab785c28",
5
+ "qwenTarballSha256": "b1568426c2a10322fcb61388da87f5d889c6dc721e79eb25a0078730fb673359",
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
+ "repetitions": 1,
16
+ "control": "unchanged mini-SWE-agent",
17
+ "baseline": "ga-plan-reserve-qwen"
18
+ }
@@ -0,0 +1,571 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "kind": "published-qwen-development-validation",
4
+ "classification": "known development case; not holdout or GA acceptance",
5
+ "qwenVersion": "0.14.4",
6
+ "implementation": {
7
+ "gitCommit": "c2b2bb917d0471e61afc5f731a61c00b44fa3731",
8
+ "sources": {
9
+ "bun.lock": "dbabdf161b3dba306f475c81f37e5ab1620fb98052127bb3ed2a0a0cb611ede4",
10
+ "evaluations/external/requirements.lock": "42e90a08f10f821ebb958af79256f707a9fb5cf365277c4f9e2715d612028179",
11
+ "package.json": "78989c243298fa78066ce1670439277c689a5a538d973b91f7ea7061281dd82a",
12
+ "scripts/benchmark-swebench.ts": "ed17063e1847017ba2e72f14732b6ff8f5b1af7cd5253b91302af75f2a9e8476",
13
+ "scripts/swebench/candidate.py": "f5e3410b91b950acfbe50fc7511891816a8fb1c223082397e2c6300cf1e866cf",
14
+ "scripts/swebench/candidate.ts": "bf102becfcce0c9a3f0df0a8f1ce0e5aaea7db2d252f6d9454a8370c24e53982",
15
+ "scripts/swebench/common.py": "ad790227dac3bec1f592c458c993efff4f9d3de8f0df39b33e3238b58b3f0b3b",
16
+ "scripts/swebench/context-metrics.ts": "7b84da6789413aa634d997c5963ee6796584e06c3eafe5f68f424fb7e27815e9",
17
+ "scripts/swebench/mini_driver.py": "bd0a77221878370ec44760122a51f07fb56d969612afa9a7f171248b2958baa6",
18
+ "scripts/swebench/model-budget.ts": "e46dd406ee5d58a051a15c7d7133513666292303d8c6534f861a6db0e711f47c",
19
+ "scripts/swebench/model-catalog.ts": "eb79e7333f4f5804f96da87d1952382f620e7165a95b60489fcc2588debe64d8",
20
+ "scripts/swebench/preflight.py": "aed092a75dd52f504fba6d14814b69bd627ff17d0e311a1f1279f8b613b69675",
21
+ "scripts/swebench/prepare.py": "bb7edd3fba5dbbe26597c97d744c60b94dbb7bcdfd7740a4a058c8583bd27e4c",
22
+ "scripts/swebench/report.py": "d0b8d45f32c48e0ba2cb977f50838065a497a0ecaf3b4243ed94139393ce4d6b",
23
+ "scripts/swebench/run.py": "94dccd55dfe6f70d8f8f2da70331700ec85eddd958547e0c3afe3dc416c9802c",
24
+ "scripts/swebench/telemetry.ts": "743c9baf273e9240d704d098b6bd5eea9e76ef3e49ae636aaafa9bfd7a85b45b",
25
+ "scripts/swebench/test_candidate.py": "e77d16379b748baa2daf184a45ea62587d938b6a7d48dcf9f6061f8af21fafd9",
26
+ "scripts/swebench/test_contracts.py": "902e966d0fbf8501dbb15e011849f160331c033cd2a5480f9920d0f365a08d03",
27
+ "scripts/swebench/zhivex-driver.ts": "24830996fb91c8ad34928a4b7d5da62ea1ab8f8792a77ac675cc9638d750ff2b",
28
+ "scripts/time-to-safe-fix-efficiency.ts": "dd20fd8839280332ae4ca80d6846e98e07ff15d79e200b206fa2ba6be2724d2f",
29
+ "src/bounded-reads.ts": "9807bb460894be3279c5425af19863d1c6e419a1582ba6910ec7e7fc35703ed6",
30
+ "src/capabilities.ts": "56fdb60a2f6e1d33b2dc26d38b6d2709807e491ba1268d47b97876c2c0591d65",
31
+ "src/change-envelope.ts": "9047ec978c9e5117965b8093ec961d855f97bbc2c3accdc79b74cfe6a0e4f01e",
32
+ "src/cli-options.ts": "f48d9be132fed38f2ddbcfecbd8222c664a0df2f20edc28ce8d1b9b1a1900863",
33
+ "src/cli-profiles.ts": "4fe451f1645e95f4957597a8724fa989b3c661ae1693252bfd6e74a51d20fc74",
34
+ "src/cli-stream.ts": "5ab8a4b1b8cf0a3dfa7b5b1f9e4e0facf8f6e7f6c341bdf700a41dc8927c825e",
35
+ "src/cli.ts": "5a4acb4695a968a58fbeac05c4bb89848a9653d6189590f0ff90e430ffa98d14",
36
+ "src/compaction.ts": "9e06a0abeeef155377f40c160b21c56256bca95ec18c5ee897681a5fc73db169",
37
+ "src/config.ts": "b1d3991e84add58603fb85b2a604b9b3eb56ae879d0fa30b0cb40545fa44edc1",
38
+ "src/console-context.ts": "0ad7e4559504b9ed09ab500d615dea09af1075d357f02ec3b77f003d55d951db",
39
+ "src/console-input.ts": "dc8ea0cdbba1364db288d5156c5ff9819362c46b37ef35a98b0475b6c445b1f8",
40
+ "src/context-engineering.ts": "1995e564f6b91974e75bf66dd421ddcbea29b1f8eee59b76eb4e34c9d6d8f47e",
41
+ "src/context-metrics.ts": "3eb30f9db808f918ed8d73d4f8ac19a13acb09ed5c1ee70fdae05201714b9198",
42
+ "src/edit-contracts.ts": "47cc3132e27f8749d54a32bbcc33bb174cf4448f0d0171b2578cdb559cf2176b",
43
+ "src/errors.ts": "e02f4eb80562a83762f908bda56c950ec6a2b78725c0c8a49f41fee0057ab903",
44
+ "src/execution-environment.ts": "9ce6c49afab26527d5296f0c11f106063590f7333300d58dd49d5a1ec1b4b6e9",
45
+ "src/file-security.ts": "b8c9f4988c4339c73a60ab4fa8d394b3eecc19117a0c61a8d19ab6483ca253df",
46
+ "src/harness.ts": "e9b85f5d83634ac7ec79d8052addb35e765d04fc46883d1e38612269bcf12609",
47
+ "src/index.ts": "4bbfcd11376d48c4f1c1ec17d6b5c9f51baa9331fa999432be178bae94530a5e",
48
+ "src/json-contracts.ts": "0780145636b47829a1aa6087c574d5654eb31b7534ea7d9c38c188d648c90272",
49
+ "src/mcp.ts": "7722de031921c620ec03b9e42a6596ef8415aa8e4bb5f93ea84d2427c466e554",
50
+ "src/model-budget.ts": "97c00019d7e737fc7acdd04cdac0811dca8d85c3e858de519ebba91888cf1ee7",
51
+ "src/operations.ts": "bcccaf4d1d0ec117c2ed35df92185564d33399e5fdc5c12225ac61f14fd0b4b1",
52
+ "src/orchestration.ts": "b56c8c7d526a99b745cc17769e0a1b7b500b25920e77f34aa0dd01c9758de319",
53
+ "src/package-manager.ts": "cec4666bbab2f42e0a269709631f79f9f87c2c4dbb3cafeffacfaff761069e2c",
54
+ "src/process-runtime.ts": "b7286731a0b5c96dcad0b8e3a4bf1155d0539d73303cd7ebe77ffabf858f1729",
55
+ "src/providers.ts": "70ccfc7f315cd7238e83d69b719ce4908f3b620c564cbb4f00f93e102e025602",
56
+ "src/repair-controller.ts": "df19e273be815b2e37ace12e03a02793fe13c13853fcb70b8d2c9d217a68bc87",
57
+ "src/repair-progress.ts": "cf30117ab69564f2b36ff8f0e86dcb876e6c031647340a7b1bef648d1e0366b9",
58
+ "src/repair-verifier.ts": "b70fb11feee8cdc7933947ccac0b78f8bb5c0eaccc3b29ad527197d77f40ffc9",
59
+ "src/replacement-edits.ts": "8a0efdd3a7a9fc3e5a5475916cbd17ef882265881bb61076db58673e80b72957",
60
+ "src/routing.ts": "8e7c9f5968b4bd638cbbc86b19847ca183f3418b9a298783b96a88cffa568e22",
61
+ "src/run-interruption.ts": "df99129cf2dd6b938eca629cb897c4350a7d57fe6bf0ce437f5f3f30271617df",
62
+ "src/runtime-checkpoints.ts": "e3b75a0b86fb5d21992b1a126b35446110ba5fcaf4317ed5005b1a44555118dc",
63
+ "src/runtime-diagnostics.ts": "e1e5a3a558fa2aaeb477335dc336551f022c1234fe5e742eefc6599c8803e364",
64
+ "src/runtime-policy.ts": "8356acf0102f0e73839b81ed628a5c0d9a89d9c21b0ca416efedde8f1b3414e2",
65
+ "src/sessions.ts": "5167c8cf36bd4b8845ee278883394700321b65397f49c1dda0cf0d0de09dd06e",
66
+ "src/sqlite-database.ts": "18765d1ca0c2f2ad87bfd82d311312dfe8a42006556f27bc21da5892ed3b044e",
67
+ "src/state-backup.ts": "b6f8f1aedeb5dce31b65c23c7ffc50030870655b58a5aaaef9989bafb9da5c68",
68
+ "src/state-directory.ts": "3711550991951e6b738a08deaa0e06da84d01864c03a9602600f592963fa3211",
69
+ "src/task-memory.ts": "5b62c863be5a23c33608633cd7aac0464f5536d01cba930aca58b11870170731",
70
+ "src/terminal-markdown.ts": "8cffb6ebaf25108cb2bee04956d9b2973635b010f5d7ce6be21b3ceffe3e8bfd",
71
+ "src/terminal-ui.ts": "4da1878a76ba608a2517bf5d5c992a9a88702aba3fd800a9980129ba93e157bc",
72
+ "src/time-to-safe-fix.ts": "4add1d49c0ea209cc496c66fa2b2012dc7bcab87e678a58c8591b3c2cdc8df8a",
73
+ "src/tool-registry.ts": "7e90fff11940e525883c9ec0d2adbea2e6616f8bd9bc4ec77e1b7277e4217f2c",
74
+ "src/version.ts": "b2c2f80a40adc08e8258b81e82434273f0bdfa787528b2221f14efe7f06aa747",
75
+ "src/workspace-mutation-lock.ts": "ca201242db16173bd3a4d86c5d8bb0c2b6f3c43bfed3e4fa4ff5f06a75b19e80",
76
+ "src/workspace.ts": "809f8bbfcf72fed10d860c48585089ca65bb3ef7c672ee6df3c918907a968302"
77
+ }
78
+ },
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
+ "model": "qwen3.8-flash",
89
+ "samples": [
90
+ {
91
+ "candidate": "zhivex",
92
+ "instanceId": "django__django-15851",
93
+ "repetition": 0,
94
+ "resolved": false,
95
+ "gradingStatus": "completed",
96
+ "usageComplete": true,
97
+ "costUsd": null,
98
+ "candidateCaptureFailure": null,
99
+ "modelTimings": [
100
+ {
101
+ "durationMs": 3791.4333749999996,
102
+ "firstTokenMs": 2602.9065419999997,
103
+ "completed": true
104
+ },
105
+ {
106
+ "durationMs": 1591.2223749999994,
107
+ "firstTokenMs": 1591.012917,
108
+ "completed": true
109
+ },
110
+ {
111
+ "durationMs": 2689.4465,
112
+ "firstTokenMs": 2689.1815829999996,
113
+ "completed": true
114
+ },
115
+ {
116
+ "durationMs": 1378.9131249999991,
117
+ "firstTokenMs": 1378.6666669999995,
118
+ "completed": true
119
+ },
120
+ {
121
+ "durationMs": 1292.3041250000006,
122
+ "firstTokenMs": 1068.277709,
123
+ "completed": true
124
+ }
125
+ ],
126
+ "modelCatalog": {
127
+ "records": [
128
+ {
129
+ "call": 1,
130
+ "offered": [
131
+ "apply_reviewed_edits",
132
+ "apply_reviewed_replacement",
133
+ "inspect_environment_patch",
134
+ "list_files",
135
+ "mutation_audit",
136
+ "read_files",
137
+ "read_task",
138
+ "repair_plan",
139
+ "run_environment_command",
140
+ "run_environment_shell",
141
+ "search_files",
142
+ "search_many",
143
+ "verify_and_apply_environment_patch"
144
+ ],
145
+ "unknownOffered": 0,
146
+ "systemMessages": 1,
147
+ "choice": "default",
148
+ "returned": [
149
+ {
150
+ "name": "search_files",
151
+ "offered": true,
152
+ "registered": true
153
+ },
154
+ {
155
+ "name": "list_files",
156
+ "offered": true,
157
+ "registered": true
158
+ }
159
+ ],
160
+ "omittedReturned": 0,
161
+ "completed": true
162
+ },
163
+ {
164
+ "call": 2,
165
+ "offered": [
166
+ "apply_reviewed_edits",
167
+ "apply_reviewed_replacement",
168
+ "inspect_environment_patch",
169
+ "list_files",
170
+ "mutation_audit",
171
+ "read_files",
172
+ "read_task",
173
+ "repair_plan",
174
+ "run_environment_command",
175
+ "run_environment_shell",
176
+ "search_files",
177
+ "search_many",
178
+ "verify_and_apply_environment_patch"
179
+ ],
180
+ "unknownOffered": 0,
181
+ "systemMessages": 1,
182
+ "choice": "default",
183
+ "returned": [
184
+ {
185
+ "name": "read_files",
186
+ "offered": true,
187
+ "registered": true
188
+ }
189
+ ],
190
+ "omittedReturned": 0,
191
+ "completed": true
192
+ },
193
+ {
194
+ "call": 3,
195
+ "offered": [
196
+ "apply_reviewed_edits",
197
+ "apply_reviewed_replacement",
198
+ "inspect_environment_patch",
199
+ "list_files",
200
+ "mutation_audit",
201
+ "read_files",
202
+ "read_task",
203
+ "repair_plan",
204
+ "run_environment_command",
205
+ "run_environment_shell",
206
+ "search_files",
207
+ "search_many",
208
+ "verify_and_apply_environment_patch"
209
+ ],
210
+ "unknownOffered": 0,
211
+ "systemMessages": 1,
212
+ "choice": "default",
213
+ "returned": [
214
+ {
215
+ "name": "search_files",
216
+ "offered": true,
217
+ "registered": true
218
+ }
219
+ ],
220
+ "omittedReturned": 0,
221
+ "completed": true
222
+ },
223
+ {
224
+ "call": 4,
225
+ "offered": [
226
+ "apply_reviewed_edits",
227
+ "apply_reviewed_replacement",
228
+ "inspect_environment_patch",
229
+ "list_files",
230
+ "mutation_audit",
231
+ "read_files",
232
+ "read_task",
233
+ "repair_plan",
234
+ "run_environment_command",
235
+ "run_environment_shell",
236
+ "search_files",
237
+ "search_many",
238
+ "verify_and_apply_environment_patch"
239
+ ],
240
+ "unknownOffered": 0,
241
+ "systemMessages": 1,
242
+ "choice": "default",
243
+ "returned": [
244
+ {
245
+ "name": "read_task",
246
+ "offered": true,
247
+ "registered": true
248
+ }
249
+ ],
250
+ "omittedReturned": 0,
251
+ "completed": true
252
+ },
253
+ {
254
+ "call": 5,
255
+ "offered": [
256
+ "apply_reviewed_edits",
257
+ "apply_reviewed_replacement",
258
+ "inspect_environment_patch",
259
+ "list_files",
260
+ "mutation_audit",
261
+ "read_files",
262
+ "read_task",
263
+ "repair_plan",
264
+ "run_environment_command",
265
+ "run_environment_shell",
266
+ "search_files",
267
+ "search_many",
268
+ "verify_and_apply_environment_patch"
269
+ ],
270
+ "unknownOffered": 0,
271
+ "systemMessages": 1,
272
+ "choice": "default",
273
+ "returned": [],
274
+ "omittedReturned": 0,
275
+ "completed": true
276
+ }
277
+ ],
278
+ "omittedCalls": 0
279
+ },
280
+ "stageTimings": [],
281
+ "approvalTimings": [],
282
+ "toolTimings": [
283
+ {
284
+ "name": "search_files",
285
+ "calls": 2,
286
+ "errors": 0,
287
+ "totalMs": 389.34508300000016,
288
+ "maxMs": 371.1230830000004
289
+ },
290
+ {
291
+ "name": "list_files",
292
+ "calls": 1,
293
+ "errors": 0,
294
+ "totalMs": 7.581958000000668,
295
+ "maxMs": 7.581958000000668
296
+ },
297
+ {
298
+ "name": "read_files",
299
+ "calls": 1,
300
+ "errors": 0,
301
+ "totalMs": 1.8022080000009737,
302
+ "maxMs": 1.8022080000009737
303
+ },
304
+ {
305
+ "name": "read_task",
306
+ "calls": 1,
307
+ "errors": 0,
308
+ "totalMs": 0.21687500000007276,
309
+ "maxMs": 0.21687500000007276
310
+ }
311
+ ],
312
+ "schemaVersion": 1,
313
+ "status": "completed",
314
+ "failure": null,
315
+ "phase": "agent",
316
+ "durationMs": 18415.943792000002,
317
+ "approvals": 0,
318
+ "turns": [
319
+ {
320
+ "index": 1,
321
+ "status": "completed",
322
+ "finishReason": "tool-calls",
323
+ "requestedTools": [
324
+ "search_files",
325
+ "list_files"
326
+ ],
327
+ "inputTokens": 4610,
328
+ "outputTokens": 135,
329
+ "cachedInputTokens": 0,
330
+ "requestCharacters": 7403,
331
+ "tools": [
332
+ {
333
+ "name": "search_files",
334
+ "isError": false,
335
+ "characters": 714
336
+ },
337
+ {
338
+ "name": "list_files",
339
+ "isError": false,
340
+ "characters": 452
341
+ }
342
+ ]
343
+ },
344
+ {
345
+ "index": 2,
346
+ "status": "completed",
347
+ "finishReason": "tool-calls",
348
+ "requestedTools": [
349
+ "read_files"
350
+ ],
351
+ "inputTokens": 5191,
352
+ "outputTokens": 51,
353
+ "cachedInputTokens": 4096,
354
+ "requestCharacters": 9372,
355
+ "tools": [
356
+ {
357
+ "name": "read_files",
358
+ "isError": false,
359
+ "characters": 6327
360
+ }
361
+ ]
362
+ },
363
+ {
364
+ "index": 3,
365
+ "status": "completed",
366
+ "finishReason": "tool-calls",
367
+ "requestedTools": [
368
+ "search_files"
369
+ ],
370
+ "inputTokens": 7201,
371
+ "outputTokens": 69,
372
+ "cachedInputTokens": 4096,
373
+ "requestCharacters": 16097,
374
+ "tools": [
375
+ {
376
+ "name": "search_files",
377
+ "isError": false,
378
+ "characters": 158
379
+ }
380
+ ]
381
+ },
382
+ {
383
+ "index": 4,
384
+ "status": "completed",
385
+ "finishReason": "tool-calls",
386
+ "requestedTools": [
387
+ "read_task"
388
+ ],
389
+ "inputTokens": 7336,
390
+ "outputTokens": 13,
391
+ "cachedInputTokens": 6144,
392
+ "requestCharacters": 16653,
393
+ "tools": [
394
+ {
395
+ "name": "read_task",
396
+ "isError": false,
397
+ "characters": 1147
398
+ }
399
+ ]
400
+ },
401
+ {
402
+ "index": 5,
403
+ "status": "completed",
404
+ "finishReason": "stop",
405
+ "requestedTools": [],
406
+ "inputTokens": 7735,
407
+ "outputTokens": 13,
408
+ "cachedInputTokens": 6656,
409
+ "requestCharacters": 18090,
410
+ "tools": []
411
+ }
412
+ ],
413
+ "inputTokens": 32073,
414
+ "outputTokens": 281,
415
+ "cachedInputTokens": 20992,
416
+ "modelCalls": 5,
417
+ "compactions": [],
418
+ "terminalDiagnostic": null,
419
+ "thrownDiagnostic": null,
420
+ "guardrails": [],
421
+ "repairProgress": {
422
+ "repeatedResults": 0,
423
+ "suppressedResults": 0,
424
+ "blockedBroadCalls": 0,
425
+ "enteredClosure": false,
426
+ "phase": "explore",
427
+ "blockedPhaseCalls": 0,
428
+ "planRecorded": false
429
+ },
430
+ "contextMetrics": [
431
+ {
432
+ "systemCharacters": 4851,
433
+ "userCharacters": 2548,
434
+ "assistantCharacters": 0,
435
+ "toolResultCharacters": 0,
436
+ "otherMessageCharacters": 0,
437
+ "toolDefinitionCharacters": 9375,
438
+ "unmeasuredToolDefinitions": 0
439
+ },
440
+ {
441
+ "systemCharacters": 4851,
442
+ "userCharacters": 2548,
443
+ "assistantCharacters": 482,
444
+ "toolResultCharacters": 1484,
445
+ "otherMessageCharacters": 0,
446
+ "toolDefinitionCharacters": 9375,
447
+ "unmeasuredToolDefinitions": 0
448
+ },
449
+ {
450
+ "systemCharacters": 4851,
451
+ "userCharacters": 2548,
452
+ "assistantCharacters": 720,
453
+ "toolResultCharacters": 7969,
454
+ "otherMessageCharacters": 0,
455
+ "toolDefinitionCharacters": 9375,
456
+ "unmeasuredToolDefinitions": 0
457
+ },
458
+ {
459
+ "systemCharacters": 4851,
460
+ "userCharacters": 2548,
461
+ "assistantCharacters": 956,
462
+ "toolResultCharacters": 8287,
463
+ "otherMessageCharacters": 0,
464
+ "toolDefinitionCharacters": 9375,
465
+ "unmeasuredToolDefinitions": 0
466
+ },
467
+ {
468
+ "systemCharacters": 4851,
469
+ "userCharacters": 2548,
470
+ "assistantCharacters": 1087,
471
+ "toolResultCharacters": 9591,
472
+ "otherMessageCharacters": 0,
473
+ "toolDefinitionCharacters": 9375,
474
+ "unmeasuredToolDefinitions": 0
475
+ }
476
+ ],
477
+ "omittedContextMeasurements": 0,
478
+ "toolCalls": 5,
479
+ "patchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
480
+ "protectedFilesChanged": [],
481
+ "gradingMethod": "empty-patch-no-solution",
482
+ "officialResolved": false,
483
+ "candidateCaptured": true,
484
+ "candidatePatchSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
485
+ "candidateGradingStatus": "completed",
486
+ "candidateResolved": false,
487
+ "repairStages": {
488
+ "candidatePresent": false,
489
+ "importedPatchPresent": false,
490
+ "verificationAttempted": false
491
+ },
492
+ "gradingDurationMs": 0.15750003512948751,
493
+ "totalDurationMs": 28261.96345902281
494
+ },
495
+ {
496
+ "candidate": "mini-swe-agent",
497
+ "instanceId": "django__django-15851",
498
+ "repetition": 0,
499
+ "resolved": true,
500
+ "gradingStatus": "completed",
501
+ "usageComplete": true,
502
+ "costUsd": null,
503
+ "schemaVersion": 1,
504
+ "status": "Submitted",
505
+ "failure": null,
506
+ "phase": "agent",
507
+ "durationMs": 28995.18733395962,
508
+ "approvals": 0,
509
+ "toolCalls": 10,
510
+ "inputTokens": 26718,
511
+ "outputTokens": 820,
512
+ "cachedInputTokens": 19200,
513
+ "modelCalls": 9,
514
+ "patchSha256": "873ee0e2d09108303f5ebe1fa4d0aec08ee9e4ce52b93941c70b4c8c91c21db4",
515
+ "protectedFilesChanged": [],
516
+ "officialResolved": true,
517
+ "candidateCaptured": true,
518
+ "candidatePatchSha256": "873ee0e2d09108303f5ebe1fa4d0aec08ee9e4ce52b93941c70b4c8c91c21db4",
519
+ "candidateGradingStatus": "completed",
520
+ "candidateResolved": true,
521
+ "repairStages": {
522
+ "candidatePresent": true,
523
+ "importedPatchPresent": null,
524
+ "verificationAttempted": null
525
+ },
526
+ "gradingDurationMs": 23900.430458015762,
527
+ "totalDurationMs": 54979.53154199058
528
+ }
529
+ ],
530
+ "report": {
531
+ "schemaVersion": 1,
532
+ "kind": "swebench-comparison",
533
+ "manifestSha256": "8ce32615aaaa6fa69268106411b6322f124d3a941db59368b1b647dbde456f67",
534
+ "complete": true,
535
+ "candidates": {
536
+ "zhivex": {
537
+ "planned": 1,
538
+ "recorded": 1,
539
+ "resolved": 0,
540
+ "candidateCaptured": 1,
541
+ "candidateResolved": 0,
542
+ "candidateGraded": 1,
543
+ "resolutionRate": 0.0,
544
+ "missing": 0,
545
+ "gradingFailures": 0,
546
+ "usageComplete": true,
547
+ "totalCostUsd": null,
548
+ "costPerResolvedUsd": null,
549
+ "resolvedP50Ms": null
550
+ },
551
+ "mini-swe-agent": {
552
+ "planned": 1,
553
+ "recorded": 1,
554
+ "resolved": 1,
555
+ "candidateCaptured": 1,
556
+ "candidateResolved": 1,
557
+ "candidateGraded": 1,
558
+ "resolutionRate": 1.0,
559
+ "missing": 0,
560
+ "gradingFailures": 0,
561
+ "usageComplete": true,
562
+ "totalCostUsd": null,
563
+ "costPerResolvedUsd": null,
564
+ "resolvedP50Ms": 54979.53154199058
565
+ }
566
+ },
567
+ "pairedTaskResolutionDifference": -1.0,
568
+ "pairedTaskBootstrap95": null,
569
+ "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."
570
+ }
571
+ }
@@ -0,0 +1,18 @@
1
+ {
2
+ "kind": "published-qwen-development-validation",
3
+ "classification": "known development task; not holdout or GA acceptance",
4
+ "qwenVersion": "0.14.4",
5
+ "repetitions": 1,
6
+ "control": "unchanged mini-SWE-agent",
7
+ "limits": {
8
+ "steps": 24,
9
+ "outputPerTurn": 2048,
10
+ "inputTokens": 100000,
11
+ "outputTokens": 16000,
12
+ "timeoutSeconds": 300,
13
+ "memoryMb": 2048,
14
+ "cpus": 2
15
+ },
16
+ "lockSha256": "dbabdf161b3dba306f475c81f37e5ab1620fb98052127bb3ed2a0a0cb611ede4",
17
+ "releaseRun": "https://github.com/Zhivex/zhivex-ai-sdk/actions/runs/35477096556"
18
+ }