@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.
- package/CHANGELOG.md +190 -0
- package/README.md +47 -62
- package/ROADMAP.md +15 -6
- package/SECURITY.md +1 -1
- package/benchmarks/README.md +48 -0
- package/benchmarks/baselines/context-navigation-2026-09-09.json +94 -0
- package/benchmarks/baselines/efficiency-2026-09-08.json +233 -0
- package/benchmarks/baselines/external-final-2026-09-08.json +588 -0
- package/benchmarks/baselines/external-intermediate-2026-09-08.json +116 -0
- package/benchmarks/baselines/external-matched-openai-2026-09-08.json +1922 -0
- package/benchmarks/baselines/external-matched-qwen-2026-09-08.json +1706 -0
- package/benchmarks/baselines/external-pilot-2026-09-08.json +439 -0
- package/benchmarks/baselines/external-qwen-flash-2026-09-08.json +1570 -0
- package/benchmarks/baselines/external-qwen-remediation-2026-09-09.json +1509 -0
- package/benchmarks/baselines/external-qwen-sdk-114-progress-2026-09-09.json +2509 -0
- package/benchmarks/baselines/external-sdk-upgrade-2026-09-08.json +564 -0
- package/benchmarks/baselines/external-verifier-recovery-2026-09-09.json +794 -0
- package/benchmarks/baselines/full-harness-review-2026-09-10.json +134 -0
- package/benchmarks/baselines/harness-audit-2026-09-09.json +136 -0
- package/benchmarks/baselines/harness-remediation-2026-09-09.json +160 -0
- package/benchmarks/baselines/oci-remediation-2026-09-10.json +535 -0
- package/benchmarks/baselines/rc14-holdout-2026-09-10.json +854 -0
- package/benchmarks/baselines/repair-architecture-audit-2026-09-09.json +75 -0
- package/benchmarks/baselines/time-to-safe-fix-live-expanded-2026-08-21.json +186 -0
- package/benchmarks/baselines/time-to-safe-fix-live-smoke-2026-08-21.json +186 -0
- package/contracts/public-api.json +25 -0
- package/contracts/security-controls.json +3 -2
- package/contracts/stable-api-signatures.json +58 -54
- package/dist/bounded-reads.d.ts +4 -0
- package/dist/change-envelope.d.ts +4 -4
- package/dist/cli-options.d.ts +2 -1
- package/dist/cli-profiles.d.ts +39 -0
- package/dist/cli-stream.d.ts +40 -40
- package/dist/cli.d.ts +38 -35
- package/dist/cli.js +6556 -4030
- package/dist/compaction.d.ts +12 -0
- package/dist/config.d.ts +6 -1
- package/dist/console-context.d.ts +26 -0
- package/dist/console-input.d.ts +28 -0
- package/dist/context-engineering.d.ts +5 -5
- package/dist/context-metrics.d.ts +11 -0
- package/dist/edit-contracts.d.ts +2 -2
- package/dist/execution-environment.d.ts +9 -5
- package/dist/harness.d.ts +52 -18
- package/dist/hostile-repository-demo.js +2942 -1088
- package/dist/index.d.ts +3 -3
- package/dist/index.js +4316 -2435
- package/dist/json-contracts.d.ts +292 -236
- package/dist/model-budget.d.ts +61 -0
- package/dist/operations.d.ts +82 -20
- package/dist/orchestration.d.ts +1 -0
- package/dist/providers.d.ts +5 -2
- package/dist/repair-controller.d.ts +72 -0
- package/dist/repair-progress.d.ts +40 -0
- package/dist/repair-verifier.d.ts +6 -0
- package/dist/replacement-edits.d.ts +9 -0
- package/dist/routing.d.ts +1 -1
- package/dist/run-interruption.d.ts +4 -0
- package/dist/runtime-checkpoints.d.ts +7 -0
- package/dist/runtime-diagnostics.d.ts +63 -0
- package/dist/runtime-policy.d.ts +36 -0
- package/dist/sessions.d.ts +1 -1
- package/dist/state-backup.d.ts +2 -2
- package/dist/task-memory.d.ts +36 -0
- package/dist/terminal-markdown.d.ts +12 -0
- package/dist/time-to-safe-fix.d.ts +19 -19
- package/dist/tool-registry.d.ts +4 -0
- package/dist/verify-historical-migrations.js +6987 -5140
- package/dist/workspace-mutation-lock.d.ts +5 -0
- package/dist/workspace.d.ts +39 -4
- package/dist/zhx.js +6556 -4030
- package/docs/CLI.md +89 -3
- package/docs/CONTEXT_ENGINEERING.md +160 -0
- package/docs/EXECUTION_ENVIRONMENTS.md +21 -0
- package/docs/EXTENSIBILITY.md +2 -2
- package/docs/GA_READINESS.md +13 -7
- package/docs/LIVE_CERTIFICATION.md +12 -2
- package/docs/RC13_SECURITY_REVIEW.md +28 -0
- package/docs/RC14_DELEGATED_SECURITY_DECISION.md +80 -0
- package/docs/RC14_SECURITY_REVIEW.md +40 -0
- package/docs/README.md +33 -0
- package/docs/RELEASE.md +4 -2
- package/docs/REPOSITORY_EDITING.md +47 -0
- package/docs/SECURITY_REVIEW_EVIDENCE.md +5 -3
- package/docs/THREAT_MODEL.md +3 -3
- package/docs/TIME_TO_SAFE_FIX.md +4 -4
- package/docs/ga-readiness.json +147 -16
- package/docs/reports/EFFICIENCY_REVIEW.md +156 -0
- package/docs/reports/EXTERNAL_COMPARISON.md +434 -0
- package/docs/reports/FULL_HARNESS_REVIEW_2026-09-10.md +200 -0
- package/docs/reports/GA_BUDGET_REMEDIATION_2026-09-19.md +38 -0
- package/docs/reports/GA_REPAIR_RECOVERY_2026-09-19.md +700 -0
- package/docs/reports/GA_VALIDATION_2026-09-19.md +111 -0
- package/docs/reports/HARNESS_ARCHITECTURE_REVIEW_2026-09-09.md +202 -0
- package/docs/reports/HARNESS_AUDIT_2026-09-09.md +306 -0
- package/docs/reports/HARNESS_REMEDIATION_2026-09-09.md +74 -0
- package/docs/reports/HARNESS_REMEDIATION_2026-09-10.md +90 -0
- package/docs/reports/MODEL_COMPARISON_2026-09-09.md +184 -0
- package/docs/reports/QWEN_REMEDIATION_COMPARISON_2026-09-09.md +142 -0
- package/docs/reports/RC14_VALIDATION_2026-09-10.md +45 -0
- package/docs/reports/README.md +26 -0
- package/docs/reports/evidence/ga-budget-remediation-2026-09-19.json +133 -0
- package/docs/reports/evidence/ga-catalog-ablation-2026-09-19.json +699 -0
- package/docs/reports/evidence/ga-catalog-ablation-plan-2026-09-19.json +40 -0
- package/docs/reports/evidence/ga-catalog-observed-2026-09-19.json +985 -0
- package/docs/reports/evidence/ga-catalog-observed-plan-2026-09-19.json +28 -0
- package/docs/reports/evidence/ga-catalog-observed-status-2026-09-19.json +15 -0
- package/docs/reports/evidence/ga-complete-local-check-2026-09-19.json +47 -0
- package/docs/reports/evidence/ga-completion-reminder-2026-09-19.json +22 -0
- package/docs/reports/evidence/ga-fresh-cohort-plan-2026-09-19.json +54 -0
- package/docs/reports/evidence/ga-fresh-cohort-preparation-2026-09-19.json +242 -0
- package/docs/reports/evidence/ga-fresh-cohort-result-2026-09-19.json +4318 -0
- package/docs/reports/evidence/ga-local-validation-followup-2026-09-19.json +66 -0
- package/docs/reports/evidence/ga-node-consumers-2026-09-19.json +31 -0
- package/docs/reports/evidence/ga-package-content-validation-2026-09-19.json +22 -0
- package/docs/reports/evidence/ga-plan-completion-2026-09-19.json +39 -0
- package/docs/reports/evidence/ga-plan-reserve-2026-09-19.json +573 -0
- package/docs/reports/evidence/ga-plan-reserve-plan-2026-09-19.json +24 -0
- package/docs/reports/evidence/ga-plan-transition-2026-09-19.json +19 -0
- package/docs/reports/evidence/ga-private-verifier-plan-2026-09-19.json +24 -0
- package/docs/reports/evidence/ga-private-verifier-root-cause-2026-09-19.json +41 -0
- package/docs/reports/evidence/ga-published-sdk-2026-09-19.json +35 -0
- package/docs/reports/evidence/ga-python-checkout-imports-2026-09-19.json +95 -0
- package/docs/reports/evidence/ga-python-origin-delivery-2026-09-19.json +211 -0
- package/docs/reports/evidence/ga-python-origin-delivery-plan-2026-09-19.json +27 -0
- package/docs/reports/evidence/ga-qwen-patched-package-2026-09-19.json +1092 -0
- package/docs/reports/evidence/ga-qwen-patched-package-plan-2026-09-19.json +18 -0
- package/docs/reports/evidence/ga-qwen-published-2026-09-19.json +571 -0
- package/docs/reports/evidence/ga-qwen-published-plan-2026-09-19.json +18 -0
- package/docs/reports/evidence/ga-qwen-tool-choice-2026-09-19.json +85 -0
- package/docs/reports/evidence/ga-qwen-tool-choice-patched-2026-09-19.json +85 -0
- package/docs/reports/evidence/ga-recovery-development-2026-09-19.json +1066 -0
- package/docs/reports/evidence/ga-recovery-graded-development-2026-09-19.json +1313 -0
- package/docs/reports/evidence/ga-recovery-graded-v2-2026-09-19.json +1151 -0
- package/docs/reports/evidence/ga-recovery-v3-2026-09-19.json +3943 -0
- package/docs/reports/evidence/ga-recovery-v4-2026-09-19.json +1055 -0
- package/docs/reports/evidence/ga-recovery-v5-2026-09-19.json +1245 -0
- package/docs/reports/evidence/ga-recovery-v6-2026-09-19.json +699 -0
- package/docs/reports/evidence/ga-recovery-v7-2026-09-19.json +854 -0
- package/docs/reports/evidence/ga-recovery-v8-2026-09-19.json +596 -0
- package/docs/reports/evidence/ga-required-delivery-2026-09-19.json +25 -0
- package/docs/reports/evidence/ga-required-delivery-live-2026-09-19.json +1337 -0
- package/docs/reports/evidence/ga-required-delivery-live-plan-2026-09-19.json +25 -0
- package/docs/reports/evidence/ga-retained-candidate-grading-2026-09-19.json +30 -0
- package/docs/reports/evidence/ga-tool-selection-live-2026-09-19.json +559 -0
- package/docs/reports/evidence/ga-tool-selection-live-plan-2026-09-19.json +28 -0
- package/docs/reports/evidence/ga-tool-selection-recovery-2026-09-19.json +27 -0
- package/docs/reports/evidence/ga-validation-2026-09-19.json +236 -0
- package/docs/reports/evidence/ga-verifier-discovery-live-2026-09-19.json +1369 -0
- package/docs/reports/evidence/ga-verifier-discovery-plan-2026-09-19.json +29 -0
- package/docs/reports/evidence/ga-verifier-failure-identification-2026-09-19.json +30 -0
- package/docs/reports/evidence/ga-verifier-feedback-2026-09-19.json +65 -0
- package/docs/reports/evidence/ga-verifier-hints-live-2026-09-19.json +1297 -0
- package/docs/reports/evidence/ga-verifier-hints-plan-2026-09-19.json +27 -0
- package/docs/reports/evidence/ga-work-boundary-context-analysis-2026-09-19.json +113 -0
- package/docs/reports/evidence/ga-work-boundary-live-2026-09-19.json +301 -0
- package/docs/reports/evidence/ga-work-boundary-live-plan-2026-09-19.json +84 -0
- package/docs/reports/evidence/ga-work-budget-planning-2026-09-19.json +32 -0
- package/docs/reports/evidence/ga-working-context-2026-09-19.json +22 -0
- package/docs/reports/evidence/rc14-delegated-security-review-2026-09-20.json +81 -0
- package/docs/reports/evidence/rc14-ga-gate-2026-09-20.json +18 -0
- package/docs/reports/evidence/rc14-representative-2026-09-20.json +509 -0
- package/docs/reports/evidence/rc14-security-regressions-2026-09-20.json +64 -0
- package/docs/reports/evidence/security-current-2026-09-19.json +91 -0
- package/docs/reports/evidence/security-remediation-2026-09-19.json +97 -0
- package/evaluations/repair-controller-experiment.json +24 -0
- package/evaluations/representative-assembly-matrix.json +63 -0
- package/evaluations/representative-matrix.json +2219 -2
- package/fixtures/contracts/v1/init.json +19 -0
- package/package.json +25 -16
|
@@ -0,0 +1,35 @@
|
|
|
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
|
+
}
|
|
@@ -0,0 +1,95 @@
|
|
|
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
|
+
}
|
|
@@ -0,0 +1,211 @@
|
|
|
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
|
+
}
|
|
@@ -0,0 +1,27 @@
|
|
|
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
|
+
}
|