@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 +1,116 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "date": "2026-09-08",
4
+ "kind": "diagnostic-intermediate-cohort",
5
+ "report": {
6
+ "schemaVersion": 1,
7
+ "kind": "swebench-comparison",
8
+ "manifestSha256": "b9f13778ed4c396be2246d71fec57b85c197071b9abdcbf1e0a3dc601e006b1b",
9
+ "complete": true,
10
+ "candidates": {
11
+ "zhivex": {
12
+ "planned": 5,
13
+ "recorded": 5,
14
+ "resolved": 2,
15
+ "resolutionRate": 0.4,
16
+ "missing": 0,
17
+ "gradingFailures": 0,
18
+ "usageComplete": true,
19
+ "totalCostUsd": null,
20
+ "costPerResolvedUsd": null,
21
+ "resolvedP50Ms": 48043.563583050855
22
+ },
23
+ "mini-swe-agent": {
24
+ "planned": 5,
25
+ "recorded": 5,
26
+ "resolved": 4,
27
+ "resolutionRate": 0.8,
28
+ "missing": 0,
29
+ "gradingFailures": 0,
30
+ "usageComplete": true,
31
+ "totalCostUsd": null,
32
+ "costPerResolvedUsd": null,
33
+ "resolvedP50Ms": 53005.8885840117
34
+ }
35
+ },
36
+ "pairedTaskResolutionDifference": -0.4,
37
+ "pairedTaskBootstrap95": [
38
+ -0.8,
39
+ 0.0
40
+ ],
41
+ "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."
42
+ },
43
+ "model": "gpt-5.6-luna",
44
+ "seed": 20260909,
45
+ "taskIds": [
46
+ "astropy__astropy-14995",
47
+ "sympy__sympy-20438",
48
+ "sympy__sympy-15809",
49
+ "pydata__xarray-6721",
50
+ "django__django-13410"
51
+ ],
52
+ "implementation": {
53
+ "gitCommit": "0a7b69dddaa70a54b6b5b4097691c8112d4d76eb",
54
+ "sources": {
55
+ "bun.lock": "1293016c4d75c3dba51281c95485ea23c80097541ced9575803fe5dcf3e9f8d9",
56
+ "evaluations/external/requirements.lock": "42e90a08f10f821ebb958af79256f707a9fb5cf365277c4f9e2715d612028179",
57
+ "package.json": "c9cb835bf12a8630846d79909950636d10896a1b6b60ed1fd5468697b94aee08",
58
+ "scripts/benchmark-swebench.ts": "ed17063e1847017ba2e72f14732b6ff8f5b1af7cd5253b91302af75f2a9e8476",
59
+ "scripts/swebench/common.py": "c19cfc30b85dc3ad8dbf1ba6a4165e72ce96f624eb1721b613cfa3207636f7be",
60
+ "scripts/swebench/mini_driver.py": "46badf61f041208b3a4428beb4e574f896a459d43ab4b7a03dc616ff04b1baf3",
61
+ "scripts/swebench/preflight.py": "f3a9fc241896eb5d63138127fea4396e59d95c277c009a29a2265ee35f4aa6eb",
62
+ "scripts/swebench/prepare.py": "8dc3695a24b49e4fbc81333f602d484431485800dcb3381130249bfe13391c20",
63
+ "scripts/swebench/report.py": "70afcdf0d1f081014bb75d878f3ddf9195959e96b523ddf1e0ad5d3ec8273549",
64
+ "scripts/swebench/run.py": "f39254bdb12ffcc2a3d39c131d02c91ff839535af6e234a0923d09b5443f459e",
65
+ "scripts/swebench/telemetry.ts": "66bb6393641de2b789e6daa2f1dcc4cb9e0c77cfcf15f351d03f606d4da262b1",
66
+ "scripts/swebench/test_contracts.py": "a8c1348f1dff2e563c139e6d3e83eb141b4f2a71f91a58e2c5c051ed2a431024",
67
+ "scripts/swebench/zhivex-driver.ts": "1302a939628434ef173ecb46ea1b6cac04932f10860532acd429f48143847511",
68
+ "scripts/time-to-safe-fix-efficiency.ts": "dd20fd8839280332ae4ca80d6846e98e07ff15d79e200b206fa2ba6be2724d2f",
69
+ "src/bounded-reads.ts": "9807bb460894be3279c5425af19863d1c6e419a1582ba6910ec7e7fc35703ed6",
70
+ "src/capabilities.ts": "56fdb60a2f6e1d33b2dc26d38b6d2709807e491ba1268d47b97876c2c0591d65",
71
+ "src/change-envelope.ts": "9047ec978c9e5117965b8093ec961d855f97bbc2c3accdc79b74cfe6a0e4f01e",
72
+ "src/cli-options.ts": "97781386289e3877c1318e4c94698ca7aaf2f256b89534dfcb21e966eb7d939f",
73
+ "src/cli-profiles.ts": "4fe451f1645e95f4957597a8724fa989b3c661ae1693252bfd6e74a51d20fc74",
74
+ "src/cli-stream.ts": "5ab8a4b1b8cf0a3dfa7b5b1f9e4e0facf8f6e7f6c341bdf700a41dc8927c825e",
75
+ "src/cli.ts": "cce6f58dfbc543acdc029b188d4394cd059d940bdd361351fd877ae2d6e94880",
76
+ "src/compacted-tool-history.ts": "3bd433b9cf3e6fd3ad82e680e5cdc8512ddff380093cec2dc3d918d6f42b7fe7",
77
+ "src/compaction.ts": "3ce3933355d021c7ec8d7a9c791d9f1cd94379c44107547d0adb08145662bc2b",
78
+ "src/config.ts": "c160faaf2d9fb637c5a08a7aff65d761a12c707ed23ebb87ab0e8519e9536bf3",
79
+ "src/console-context.ts": "0ad7e4559504b9ed09ab500d615dea09af1075d357f02ec3b77f003d55d951db",
80
+ "src/console-input.ts": "dc8ea0cdbba1364db288d5156c5ff9819362c46b37ef35a98b0475b6c445b1f8",
81
+ "src/context-engineering.ts": "1995e564f6b91974e75bf66dd421ddcbea29b1f8eee59b76eb4e34c9d6d8f47e",
82
+ "src/edit-contracts.ts": "47cc3132e27f8749d54a32bbcc33bb174cf4448f0d0171b2578cdb559cf2176b",
83
+ "src/errors.ts": "e02f4eb80562a83762f908bda56c950ec6a2b78725c0c8a49f41fee0057ab903",
84
+ "src/execution-environment.ts": "321d626649bdb00f8cb8313b5191e9fd3f932b17850a91dd9c18678e699e2a1b",
85
+ "src/file-security.ts": "4590b46c8e4b9d3891a75cd0d0ada14e0ae7b58e8e4bdf82f68df688a1fbb750",
86
+ "src/harness.ts": "6d36f99bd141f1ccf0ee7fd39db9f11427063313c9cc258def4fdce2ea1a5017",
87
+ "src/index.ts": "f791311f14dc27105191d97bb5454748d10beab827da9aba3ea949ffc32fce7c",
88
+ "src/json-contracts.ts": "0702e5b0ff16ff6304c74b4101bd31a3fa8eabdebe267d312b56d3871a7e302c",
89
+ "src/mcp.ts": "5f3f7a35b89063264ae18ab9273b84e2e59ac8c8e611a6b64be377ba61cc1ac5",
90
+ "src/operations.ts": "0775da79208c6f5d18476cc76404e84ddda610979d9d0e5dc15035aa6999613c",
91
+ "src/orchestration.ts": "7383da1047363819e6560f51892fd4082e5337856a3d889cdc076f021273774e",
92
+ "src/package-manager.ts": "cec4666bbab2f42e0a269709631f79f9f87c2c4dbb3cafeffacfaff761069e2c",
93
+ "src/process-runtime.ts": "b7286731a0b5c96dcad0b8e3a4bf1155d0539d73303cd7ebe77ffabf858f1729",
94
+ "src/providers.ts": "70ccfc7f315cd7238e83d69b719ce4908f3b620c564cbb4f00f93e102e025602",
95
+ "src/replacement-edits.ts": "8a0efdd3a7a9fc3e5a5475916cbd17ef882265881bb61076db58673e80b72957",
96
+ "src/routing.ts": "8e7c9f5968b4bd638cbbc86b19847ca183f3418b9a298783b96a88cffa568e22",
97
+ "src/run-interruption.ts": "df99129cf2dd6b938eca629cb897c4350a7d57fe6bf0ce437f5f3f30271617df",
98
+ "src/sessions.ts": "5167c8cf36bd4b8845ee278883394700321b65397f49c1dda0cf0d0de09dd06e",
99
+ "src/sqlite-database.ts": "18765d1ca0c2f2ad87bfd82d311312dfe8a42006556f27bc21da5892ed3b044e",
100
+ "src/state-backup.ts": "b6f8f1aedeb5dce31b65c23c7ffc50030870655b58a5aaaef9989bafb9da5c68",
101
+ "src/state-directory.ts": "3711550991951e6b738a08deaa0e06da84d01864c03a9602600f592963fa3211",
102
+ "src/terminal-markdown.ts": "8cffb6ebaf25108cb2bee04956d9b2973635b010f5d7ce6be21b3ceffe3e8bfd",
103
+ "src/terminal-ui.ts": "e50025a8649d1f60efdf3af895b8639730ec2e86553fb80a61a776b11076c705",
104
+ "src/time-to-safe-fix.ts": "4add1d49c0ea209cc496c66fa2b2012dc7bcab87e678a58c8591b3c2cdc8df8a",
105
+ "src/version.ts": "b2c2f80a40adc08e8258b81e82434273f0bdfa787528b2221f14efe7f06aa747",
106
+ "src/workspace.ts": "259d0fef0621a8655c232b23dabc3df508343bb73cdb76713acd9601ca4b3cd7"
107
+ }
108
+ },
109
+ "rawSamplesSha256": "0d5ac0b062e8779aa890b07d5c20d8a383c72d17321f983464c6a595318e08e1",
110
+ "limitations": [
111
+ "SDK 1.11.0 duplicated streamed usage after compaction; this attempt does not establish equal effective token budgets.",
112
+ "An offline control measured three responses of 100 input tokens but SDK usage reported 500; the later correction and final cohort are separate.",
113
+ "Five tasks and one repetition do not establish general superiority.",
114
+ "Docker image preparation overlapped part of this diagnostic run; do not use it for latency comparisons."
115
+ ]
116
+ }