@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
@@ -1,35 +0,0 @@
1
- {
2
- "kind": "registry-sdk-integration-acceptance",
3
- "versions": {
4
- "core": "1.22.0",
5
- "openai": "0.13.3",
6
- "qwen": "0.14.3"
7
- },
8
- "network": "mock-only for acceptance; dependencies downloaded from registry",
9
- "integration": {
10
- "passed": true,
11
- "runFailed": true,
12
- "toolExecutions": 0,
13
- "inputTokens": 12,
14
- "outputTokens": 8,
15
- "usageComplete": true
16
- },
17
- "validation": {
18
- "focusedTests": 10,
19
- "failed": 0,
20
- "toolingTypes": "passed",
21
- "priorFullSuite": 559,
22
- "installedPackageSmoke": "passed"
23
- },
24
- "limits": [
25
- "Harness integration uses workspace source and registry-installed provider",
26
- "Not live provider evidence or SDK provenance verification"
27
- ],
28
- "hashes": {
29
- "package.json": "5379cb4dcfab000eb5a9b8f4cdf11c26cc09aa12622cfc91a06504c69cf7b875",
30
- "bun.lock": "c213d497a98bfbea1379bd60850d0ec8ede02560df9a63bf3b737d35648c4909",
31
- "scripts/validate-openai-stream-usage.ts": "76f5cd2c3ca055196a73c002fca78924db0c0d631157aab1b50e3daedaa791ea",
32
- "scripts/validate-openai-harness-usage.mjs": "ff05810248ced9944aa98ea148634d8b6cc9d9bd2c335df9342b5544eac01a6e",
33
- "tests/model-budget-error-usage.test.ts": "33ff7b350428212544c670d47ad49b4a71435a1bc35a07eaf2089ec8b16bc753"
34
- }
35
- }
@@ -1,95 +0,0 @@
1
- {
2
- "schemaVersion": 1,
3
- "kind": "python-checkout-import-binding",
4
- "oldImage": "sha256:d53dbd1313ddea4f813b0a8328cd740e978ce6ebb05d4d3c88c4e8f66f79bca1",
5
- "newImage": "sha256:4c8b7a320988313b8881a96f334a189bfd0d6fda47cc0219d648867ffe765b80",
6
- "candidateRunner": {
7
- "exitCode": 1,
8
- "checkoutOriginConfirmed": true,
9
- "reportedTests": 26,
10
- "reportedSkipped": 5,
11
- "outputSha256": "4c65332fe5222b2ef3a0077004298e07fa4f5b798cc3de121fb98fcc0b275780"
12
- },
13
- "controlOriginConfirmed": true,
14
- "newModelCalls": 0,
15
- "classification": "Offline development environment validation; no delivery or GA acceptance claim",
16
- "requirementVerifier": {
17
- "sha256": "91ebcf3d8e6038e8b3ca4e4ca889f756a3bcb278e1417fda3add6b5cb849da05",
18
- "basis": "Public issue description and four argument-order variants; no evaluator tests used",
19
- "runs": [
20
- {
21
- "kind": "original-image-candidate",
22
- "exitCode": 1,
23
- "sourceOriginRejected": true,
24
- "requirementRejected": false,
25
- "assertionsPassed": false
26
- },
27
- {
28
- "kind": "corrected-image-baseline",
29
- "exitCode": 1,
30
- "sourceOriginRejected": false,
31
- "requirementRejected": true,
32
- "assertionsPassed": false
33
- },
34
- {
35
- "kind": "corrected-image-candidate",
36
- "exitCode": 0,
37
- "sourceOriginRejected": false,
38
- "requirementRejected": false,
39
- "assertionsPassed": true
40
- }
41
- ]
42
- },
43
- "nativePreflight": {
44
- "manifestSha256": "8eca749bc33963a90c8c89ab585c2e11f6a062a1f67c2a7c1fe63667d75cca00",
45
- "driverSha256": "67cee044060e78afea9fa663af8a686220aeafdb0db9ec318ef846f31aa9985d",
46
- "results": [
47
- {
48
- "candidateSnapshot": null,
49
- "candidateCaptureFailure": null,
50
- "modelTimings": [],
51
- "modelCatalog": {
52
- "records": [],
53
- "omittedCalls": 0
54
- },
55
- "stageTimings": [],
56
- "approvalTimings": [],
57
- "toolTimings": [],
58
- "schemaVersion": 1,
59
- "candidate": "zhivex",
60
- "instanceId": "django__django-15851",
61
- "status": "preflight-passed",
62
- "failure": null,
63
- "phase": "preflight",
64
- "durationMs": 15219.306999999999,
65
- "approvals": 0,
66
- "turns": [],
67
- "inputTokens": 0,
68
- "outputTokens": 0,
69
- "cachedInputTokens": 0,
70
- "modelCalls": 0,
71
- "usageComplete": true,
72
- "compactions": [],
73
- "terminalDiagnostic": null,
74
- "thrownDiagnostic": null,
75
- "guardrails": [],
76
- "repairProgress": null,
77
- "contextMetrics": [],
78
- "omittedContextMeasurements": 0,
79
- "toolCalls": 0
80
- }
81
- ]
82
- },
83
- "validation": {
84
- "focusedTests": 12,
85
- "failures": 0,
86
- "toolingTypecheck": "passed",
87
- "pythonCompile": "passed"
88
- },
89
- "sources": {
90
- "scripts/swebench/prepare.py": "5785a924596c208679710f1ccaa9493437f0a9317d1ec69f8ec2acede8538908",
91
- "scripts/swebench/python-environment.ts": "b83440b5ea095c6eded67745ba009b82e4d3d2c40f9ee3d53bd5b53766a375f8",
92
- "scripts/swebench/zhivex-driver.ts": "67cee044060e78afea9fa663af8a686220aeafdb0db9ec318ef846f31aa9985d"
93
- },
94
- "interpretation": "Old-image public runner passed against /testbed, not the candidate. Corrected-image public suite detects one historical expectation for old argument ordering; a four-case verifier derived only from the public issue fails on the baseline and passes on the candidate. No existing tests changed."
95
- }
@@ -1,211 +0,0 @@
1
- {
2
- "schemaVersion": 1,
3
- "kind": "python-origin-delivery-diagnostic",
4
- "classification": "Single known development diagnostic; not acceptance",
5
- "result": {
6
- "candidateCaptureFailure": null,
7
- "modelTimings": [
8
- {
9
- "durationMs": 3389.3995830000003,
10
- "firstTokenMs": 3388.229375,
11
- "completed": true
12
- }
13
- ],
14
- "modelCatalog": {
15
- "records": [
16
- {
17
- "call": 1,
18
- "offered": [
19
- "apply_reviewed_edits",
20
- "apply_reviewed_replacement",
21
- "inspect_environment_patch",
22
- "list_files",
23
- "mutation_audit",
24
- "read_files",
25
- "read_task",
26
- "repair_plan",
27
- "run_environment_command",
28
- "run_environment_shell",
29
- "search_files",
30
- "search_many",
31
- "verify_and_apply_environment_patch"
32
- ],
33
- "unknownOffered": 0,
34
- "systemMessages": 1,
35
- "choice": "required",
36
- "returned": [
37
- {
38
- "name": "other-tool",
39
- "offered": false,
40
- "registered": false
41
- },
42
- {
43
- "name": "other-tool",
44
- "offered": false,
45
- "registered": false
46
- }
47
- ],
48
- "omittedReturned": 0,
49
- "completed": true
50
- }
51
- ],
52
- "omittedCalls": 0
53
- },
54
- "stageTimings": [],
55
- "approvalTimings": [],
56
- "toolTimings": [],
57
- "schemaVersion": 1,
58
- "candidate": "zhivex",
59
- "instanceId": "django__django-15851",
60
- "status": "failed",
61
- "failure": "EXECUTION_FAILED",
62
- "phase": "agent",
63
- "durationMs": 8190.240667000001,
64
- "approvals": 0,
65
- "turns": [
66
- {
67
- "index": 1,
68
- "status": "failed",
69
- "finishReason": "tool-calls",
70
- "requestedTools": [
71
- "other-tool",
72
- "other-tool"
73
- ],
74
- "inputTokens": 4652,
75
- "outputTokens": 97,
76
- "cachedInputTokens": 0,
77
- "requestCharacters": 1617,
78
- "tools": [
79
- {
80
- "name": "other-tool",
81
- "isError": true,
82
- "characters": 4,
83
- "diagnostic": {
84
- "code": "EXECUTION_FAILED",
85
- "category": "execution",
86
- "failureType": "execution",
87
- "retryable": false,
88
- "chain": [
89
- {
90
- "validationCode": null,
91
- "verifierExitCode": null,
92
- "providerReason": null,
93
- "validationIssues": [],
94
- "status": null,
95
- "errorClass": "Object",
96
- "providerHints": [],
97
- "fingerprint": "6d0579d910635f92f565c11d29a0704f48dc1b126b5cff8674e01de04ef58a64",
98
- "reason": "not registered"
99
- }
100
- ]
101
- }
102
- },
103
- {
104
- "name": "other-tool",
105
- "isError": true,
106
- "characters": 4,
107
- "diagnostic": {
108
- "code": "EXECUTION_FAILED",
109
- "category": "execution",
110
- "failureType": "execution",
111
- "retryable": false,
112
- "chain": [
113
- {
114
- "validationCode": null,
115
- "verifierExitCode": null,
116
- "providerReason": null,
117
- "validationIssues": [],
118
- "status": null,
119
- "errorClass": "Object",
120
- "providerHints": [],
121
- "fingerprint": "6d0579d910635f92f565c11d29a0704f48dc1b126b5cff8674e01de04ef58a64",
122
- "reason": "not registered"
123
- }
124
- ]
125
- }
126
- }
127
- ]
128
- }
129
- ],
130
- "inputTokens": 4652,
131
- "outputTokens": 97,
132
- "cachedInputTokens": 0,
133
- "modelCalls": 1,
134
- "usageComplete": true,
135
- "compactions": [],
136
- "terminalDiagnostic": {
137
- "code": "EXECUTION_FAILED",
138
- "category": "execution",
139
- "failureType": "execution",
140
- "retryable": false,
141
- "chain": [
142
- {
143
- "validationCode": null,
144
- "verifierExitCode": null,
145
- "providerReason": null,
146
- "validationIssues": [],
147
- "status": null,
148
- "errorClass": "Object",
149
- "providerHints": [],
150
- "fingerprint": "9dd570a51f860b7027516142d035799294d0eb7efe13ef7da34365d3dda367df",
151
- "reason": "not registered"
152
- }
153
- ]
154
- },
155
- "thrownDiagnostic": {
156
- "code": "EXECUTION_FAILED",
157
- "category": "execution",
158
- "failureType": "execution",
159
- "retryable": false,
160
- "chain": [
161
- {
162
- "validationCode": null,
163
- "verifierExitCode": null,
164
- "providerReason": null,
165
- "validationIssues": [],
166
- "status": null,
167
- "errorClass": "HarnessExecutionError",
168
- "providerHints": [],
169
- "fingerprint": "9dd570a51f860b7027516142d035799294d0eb7efe13ef7da34365d3dda367df",
170
- "reason": "not registered"
171
- },
172
- {
173
- "validationCode": null,
174
- "verifierExitCode": null,
175
- "providerReason": null,
176
- "validationIssues": [],
177
- "status": null,
178
- "errorClass": null,
179
- "providerHints": [],
180
- "fingerprint": "9dd570a51f860b7027516142d035799294d0eb7efe13ef7da34365d3dda367df",
181
- "reason": "not registered"
182
- }
183
- ]
184
- },
185
- "guardrails": [],
186
- "repairProgress": {
187
- "repeatedResults": 0,
188
- "suppressedResults": 0,
189
- "blockedBroadCalls": 0,
190
- "enteredClosure": false,
191
- "phase": "explore",
192
- "blockedPhaseCalls": 0,
193
- "planRecorded": false
194
- },
195
- "contextMetrics": [
196
- {
197
- "systemCharacters": 5073,
198
- "userCharacters": 2581,
199
- "assistantCharacters": 0,
200
- "toolResultCharacters": 0,
201
- "otherMessageCharacters": 0,
202
- "toolDefinitionCharacters": 9375,
203
- "unmeasuredToolDefinitions": 0
204
- }
205
- ],
206
- "omittedContextMeasurements": 0,
207
- "toolCalls": 0
208
- },
209
- "conclusion": "Failed on the first model turn: two unregistered tools, no tool execution or approval, no verifier. Does not test corrected-image delivery.",
210
- "nextCorrection": "Enable existing Core unknownToolMode tool-result in repair profile only, retaining stopOnError override and tool-error budgets."
211
- }
@@ -1,27 +0,0 @@
1
- {
2
- "schemaVersion": 1,
3
- "kind": "python-origin-delivery-diagnostic",
4
- "classification": "Known development task; not comparison, fresh holdout or GA acceptance",
5
- "repetitions": 1,
6
- "model": "qwen3.8-flash",
7
- "image": "sha256:4c8b7a320988313b8881a96f334a189bfd0d6fda47cc0219d648867ffe765b80",
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
- "change": "Only pinned image import policy changed from previous private diagnostic; current verifier discovery instruction retained",
18
- "sourceHashes": {
19
- "scripts/swebench/zhivex-driver.ts": "67cee044060e78afea9fa663af8a686220aeafdb0db9ec318ef846f31aa9985d",
20
- "scripts/swebench/python-environment.ts": "b83440b5ea095c6eded67745ba009b82e4d3d2c40f9ee3d53bd5b53766a375f8",
21
- "scripts/swebench/verifier-observer.ts": "a90544437473218a83477a1cffb59ee9f645c12abdf8960b787f3e21606035bf",
22
- "src/harness.ts": "1d305078e3c56c24bb659c34aac37c96bf11a4e60af6607bb4b9d65964e84791",
23
- "src/repair-controller.ts": "41f1f09032131306f3284edbf105930577504af0bf764ba98a105c4eee70a1e7",
24
- "bun.lock": "dbabdf161b3dba306f475c81f37e5ab1620fb98052127bb3ed2a0a0cb611ede4"
25
- },
26
- "stopRule": "One model run; retain bounded private verifier failures; no retry"
27
- }