@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.
- package/CHANGELOG.md +97 -1
- package/README.md +52 -306
- package/SECURITY.md +1 -1
- package/SUPPORT.md +7 -3
- package/benchmarks/README.md +3 -3
- package/contracts/client-protocol-v1.schema.json +341 -0
- package/contracts/public-api.json +100 -1
- package/contracts/stable-api-signatures.json +14 -14
- package/dist/approval-diff.d.ts +45 -0
- package/dist/approval-history.d.ts +38 -0
- package/dist/approval-preview.d.ts +26 -0
- package/dist/cli-credentials.d.ts +38 -0
- package/dist/cli-help.d.ts +3 -0
- package/dist/cli-options.d.ts +1 -1
- package/dist/cli-stream.d.ts +3 -3
- package/dist/cli.d.ts +15 -69
- package/dist/cli.js +13796 -10032
- package/dist/client-contract.d.ts +208 -0
- package/dist/console-commands.d.ts +6 -0
- package/dist/console-context.d.ts +5 -1
- package/dist/console-input.d.ts +44 -4
- package/dist/console-model-catalog.d.ts +25 -0
- package/dist/console-navigation.d.ts +27 -0
- package/dist/console-presentation.d.ts +18 -0
- package/dist/console-welcome.d.ts +13 -0
- package/dist/execution-environment.d.ts +4 -0
- package/dist/harness.d.ts +3 -0
- package/dist/hostile-repository-demo.js +1913 -798
- package/dist/index.d.ts +7 -0
- package/dist/index.js +7908 -6330
- package/dist/local-service.d.ts +34 -0
- package/dist/operations.d.ts +23 -1
- package/dist/orchestration.d.ts +3 -0
- package/dist/persistence-secrets.d.ts +2 -0
- package/dist/recorded-workspace.d.ts +4 -0
- package/dist/run-document.d.ts +91 -0
- package/dist/runtime-policy.d.ts +4 -4
- package/dist/service-cli.d.ts +2 -0
- package/dist/service-cli.js +10858 -0
- package/dist/service-client-cli.d.ts +2 -0
- package/dist/service-events.d.ts +50 -0
- package/dist/sessions.d.ts +3 -0
- package/dist/sqlite-access.d.ts +26 -0
- package/dist/sqlite-database.d.ts +2 -0
- package/dist/state-backup.d.ts +8 -0
- package/dist/task-memory.d.ts +2 -2
- package/dist/terminal-continuation.d.ts +3 -0
- package/dist/terminal-markdown.d.ts +1 -0
- package/dist/terminal-ui.d.ts +5 -0
- package/dist/usage-ledger.d.ts +84 -0
- package/dist/verify-historical-migrations.js +5699 -5191
- package/dist/workspace.d.ts +22 -0
- package/dist/zhx.js +13796 -10032
- package/docs/CLI.md +136 -30
- package/docs/CLIENT_PROTOCOL.md +212 -0
- package/docs/CREDENTIALS.md +59 -0
- package/docs/DURABLE_OPERATIONS.md +2 -2
- package/docs/FIRST_USE.md +82 -0
- package/docs/FIRST_USE_EXAMPLE.md +40 -0
- package/docs/HOSTILE_REPOSITORY_DEMO.md +1 -1
- package/docs/LOCAL_SERVICE.md +142 -0
- package/docs/README.md +24 -23
- package/docs/THREAT_MODEL.md +1 -1
- package/docs/TIME_TO_SAFE_FIX.md +2 -2
- package/docs/USAGE.md +181 -0
- package/evaluations/daily-cli-cohort.json +33 -0
- package/evaluations/representative-assembly-matrix.json +19 -1
- package/examples/README.md +26 -0
- package/examples/first-use/greeting.test.ts +3 -0
- package/examples/first-use/greeting.ts +1 -0
- package/examples/first-use/package.json +7 -0
- package/package.json +34 -9
- package/ROADMAP.md +0 -414
- package/benchmarks/baselines/context-navigation-2026-09-09.json +0 -94
- package/benchmarks/baselines/efficiency-2026-09-08.json +0 -233
- package/benchmarks/baselines/external-final-2026-09-08.json +0 -588
- package/benchmarks/baselines/external-intermediate-2026-09-08.json +0 -116
- package/benchmarks/baselines/external-matched-openai-2026-09-08.json +0 -1922
- package/benchmarks/baselines/external-matched-qwen-2026-09-08.json +0 -1706
- package/benchmarks/baselines/external-pilot-2026-09-08.json +0 -439
- package/benchmarks/baselines/external-qwen-flash-2026-09-08.json +0 -1570
- package/benchmarks/baselines/external-qwen-remediation-2026-09-09.json +0 -1509
- package/benchmarks/baselines/external-qwen-sdk-114-progress-2026-09-09.json +0 -2509
- package/benchmarks/baselines/external-sdk-upgrade-2026-09-08.json +0 -564
- package/benchmarks/baselines/external-verifier-recovery-2026-09-09.json +0 -794
- package/benchmarks/baselines/full-harness-review-2026-09-10.json +0 -134
- package/benchmarks/baselines/harness-audit-2026-09-09.json +0 -136
- package/benchmarks/baselines/harness-remediation-2026-09-09.json +0 -160
- package/benchmarks/baselines/oci-remediation-2026-09-10.json +0 -535
- package/benchmarks/baselines/rc14-holdout-2026-09-10.json +0 -854
- package/benchmarks/baselines/repair-architecture-audit-2026-09-09.json +0 -75
- package/benchmarks/baselines/time-to-safe-fix-live-expanded-2026-08-21.json +0 -186
- package/benchmarks/baselines/time-to-safe-fix-live-smoke-2026-08-21.json +0 -186
- package/docs/GA_READINESS.md +0 -29
- package/docs/GEMINI_1_0_DECISION.md +0 -9
- package/docs/LIVE_CERTIFICATION.md +0 -107
- package/docs/RC13_SECURITY_REVIEW.md +0 -28
- package/docs/RC14_DELEGATED_SECURITY_DECISION.md +0 -80
- package/docs/RC14_SECURITY_REVIEW.md +0 -40
- package/docs/RELEASE.md +0 -96
- package/docs/ROLLBACK.md +0 -9
- package/docs/SECURITY_REVIEW_EVIDENCE.md +0 -17
- package/docs/ga-readiness.json +0 -366
- package/docs/reports/EFFICIENCY_REVIEW.md +0 -156
- package/docs/reports/EXTERNAL_COMPARISON.md +0 -434
- package/docs/reports/FULL_HARNESS_REVIEW_2026-09-10.md +0 -200
- package/docs/reports/GA_BUDGET_REMEDIATION_2026-09-19.md +0 -38
- package/docs/reports/GA_REPAIR_RECOVERY_2026-09-19.md +0 -700
- package/docs/reports/GA_VALIDATION_2026-09-19.md +0 -111
- package/docs/reports/HARNESS_ARCHITECTURE_REVIEW_2026-09-09.md +0 -202
- package/docs/reports/HARNESS_AUDIT_2026-09-09.md +0 -306
- package/docs/reports/HARNESS_REMEDIATION_2026-09-09.md +0 -74
- package/docs/reports/HARNESS_REMEDIATION_2026-09-10.md +0 -90
- package/docs/reports/MODEL_COMPARISON_2026-09-09.md +0 -184
- package/docs/reports/QWEN_REMEDIATION_COMPARISON_2026-09-09.md +0 -142
- package/docs/reports/RC14_VALIDATION_2026-09-10.md +0 -45
- package/docs/reports/README.md +0 -26
- package/docs/reports/evidence/ga-budget-remediation-2026-09-19.json +0 -133
- package/docs/reports/evidence/ga-catalog-ablation-2026-09-19.json +0 -699
- package/docs/reports/evidence/ga-catalog-ablation-plan-2026-09-19.json +0 -40
- package/docs/reports/evidence/ga-catalog-observed-2026-09-19.json +0 -985
- package/docs/reports/evidence/ga-catalog-observed-plan-2026-09-19.json +0 -28
- package/docs/reports/evidence/ga-catalog-observed-status-2026-09-19.json +0 -15
- package/docs/reports/evidence/ga-complete-local-check-2026-09-19.json +0 -47
- package/docs/reports/evidence/ga-completion-reminder-2026-09-19.json +0 -22
- package/docs/reports/evidence/ga-fresh-cohort-plan-2026-09-19.json +0 -54
- package/docs/reports/evidence/ga-fresh-cohort-preparation-2026-09-19.json +0 -242
- package/docs/reports/evidence/ga-fresh-cohort-result-2026-09-19.json +0 -4318
- package/docs/reports/evidence/ga-local-validation-followup-2026-09-19.json +0 -66
- package/docs/reports/evidence/ga-node-consumers-2026-09-19.json +0 -31
- package/docs/reports/evidence/ga-package-content-validation-2026-09-19.json +0 -22
- package/docs/reports/evidence/ga-plan-completion-2026-09-19.json +0 -39
- package/docs/reports/evidence/ga-plan-reserve-2026-09-19.json +0 -573
- package/docs/reports/evidence/ga-plan-reserve-plan-2026-09-19.json +0 -24
- package/docs/reports/evidence/ga-plan-transition-2026-09-19.json +0 -19
- package/docs/reports/evidence/ga-private-verifier-plan-2026-09-19.json +0 -24
- package/docs/reports/evidence/ga-private-verifier-root-cause-2026-09-19.json +0 -41
- package/docs/reports/evidence/ga-published-sdk-2026-09-19.json +0 -35
- package/docs/reports/evidence/ga-python-checkout-imports-2026-09-19.json +0 -95
- package/docs/reports/evidence/ga-python-origin-delivery-2026-09-19.json +0 -211
- package/docs/reports/evidence/ga-python-origin-delivery-plan-2026-09-19.json +0 -27
- package/docs/reports/evidence/ga-qwen-patched-package-2026-09-19.json +0 -1092
- package/docs/reports/evidence/ga-qwen-patched-package-plan-2026-09-19.json +0 -18
- package/docs/reports/evidence/ga-qwen-published-2026-09-19.json +0 -571
- package/docs/reports/evidence/ga-qwen-published-plan-2026-09-19.json +0 -18
- package/docs/reports/evidence/ga-qwen-tool-choice-2026-09-19.json +0 -85
- package/docs/reports/evidence/ga-qwen-tool-choice-patched-2026-09-19.json +0 -85
- package/docs/reports/evidence/ga-recovery-development-2026-09-19.json +0 -1066
- package/docs/reports/evidence/ga-recovery-graded-development-2026-09-19.json +0 -1313
- package/docs/reports/evidence/ga-recovery-graded-v2-2026-09-19.json +0 -1151
- package/docs/reports/evidence/ga-recovery-v3-2026-09-19.json +0 -3943
- package/docs/reports/evidence/ga-recovery-v4-2026-09-19.json +0 -1055
- package/docs/reports/evidence/ga-recovery-v5-2026-09-19.json +0 -1245
- package/docs/reports/evidence/ga-recovery-v6-2026-09-19.json +0 -699
- package/docs/reports/evidence/ga-recovery-v7-2026-09-19.json +0 -854
- package/docs/reports/evidence/ga-recovery-v8-2026-09-19.json +0 -596
- package/docs/reports/evidence/ga-required-delivery-2026-09-19.json +0 -25
- package/docs/reports/evidence/ga-required-delivery-live-2026-09-19.json +0 -1337
- package/docs/reports/evidence/ga-required-delivery-live-plan-2026-09-19.json +0 -25
- package/docs/reports/evidence/ga-retained-candidate-grading-2026-09-19.json +0 -30
- package/docs/reports/evidence/ga-tool-selection-live-2026-09-19.json +0 -559
- package/docs/reports/evidence/ga-tool-selection-live-plan-2026-09-19.json +0 -28
- package/docs/reports/evidence/ga-tool-selection-recovery-2026-09-19.json +0 -27
- package/docs/reports/evidence/ga-validation-2026-09-19.json +0 -236
- package/docs/reports/evidence/ga-verifier-discovery-live-2026-09-19.json +0 -1369
- package/docs/reports/evidence/ga-verifier-discovery-plan-2026-09-19.json +0 -29
- package/docs/reports/evidence/ga-verifier-failure-identification-2026-09-19.json +0 -30
- package/docs/reports/evidence/ga-verifier-feedback-2026-09-19.json +0 -65
- package/docs/reports/evidence/ga-verifier-hints-live-2026-09-19.json +0 -1297
- package/docs/reports/evidence/ga-verifier-hints-plan-2026-09-19.json +0 -27
- package/docs/reports/evidence/ga-work-boundary-context-analysis-2026-09-19.json +0 -113
- package/docs/reports/evidence/ga-work-boundary-live-2026-09-19.json +0 -301
- package/docs/reports/evidence/ga-work-boundary-live-plan-2026-09-19.json +0 -84
- package/docs/reports/evidence/ga-work-budget-planning-2026-09-19.json +0 -32
- package/docs/reports/evidence/ga-working-context-2026-09-19.json +0 -22
- package/docs/reports/evidence/rc14-delegated-security-review-2026-09-20.json +0 -81
- package/docs/reports/evidence/rc14-ga-gate-2026-09-20.json +0 -18
- package/docs/reports/evidence/rc14-representative-2026-09-20.json +0 -509
- package/docs/reports/evidence/rc14-security-regressions-2026-09-20.json +0 -64
- package/docs/reports/evidence/security-current-2026-09-19.json +0 -91
- package/docs/reports/evidence/security-remediation-2026-09-19.json +0 -97
|
@@ -1,134 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"networkCalls": 0,
|
|
3
|
-
"runtimeFilesChanged": false,
|
|
4
|
-
"collisions": [
|
|
5
|
-
{
|
|
6
|
-
"name": "read_task",
|
|
7
|
-
"accepted": true,
|
|
8
|
-
"metadata": {
|
|
9
|
-
"source": "mcp",
|
|
10
|
-
"originalName": "task",
|
|
11
|
-
"title": null,
|
|
12
|
-
"inputSchema": {
|
|
13
|
-
"type": "object",
|
|
14
|
-
"properties": {}
|
|
15
|
-
},
|
|
16
|
-
"outputSchema": null,
|
|
17
|
-
"annotations": {
|
|
18
|
-
"readOnlyHint": true
|
|
19
|
-
},
|
|
20
|
-
"advancedRegistry": {
|
|
21
|
-
"permissions": [
|
|
22
|
-
"read"
|
|
23
|
-
],
|
|
24
|
-
"audit": {
|
|
25
|
-
"riskLevel": "low"
|
|
26
|
-
}
|
|
27
|
-
},
|
|
28
|
-
"server": "fixture",
|
|
29
|
-
"untrustedContent": true
|
|
30
|
-
},
|
|
31
|
-
"result": {
|
|
32
|
-
"content": [
|
|
33
|
-
{
|
|
34
|
-
"type": "text",
|
|
35
|
-
"text": "injected fixture result"
|
|
36
|
-
}
|
|
37
|
-
]
|
|
38
|
-
}
|
|
39
|
-
},
|
|
40
|
-
{
|
|
41
|
-
"name": "repair_plan",
|
|
42
|
-
"accepted": true,
|
|
43
|
-
"metadata": {
|
|
44
|
-
"source": "mcp",
|
|
45
|
-
"originalName": "plan",
|
|
46
|
-
"title": null,
|
|
47
|
-
"inputSchema": {
|
|
48
|
-
"type": "object",
|
|
49
|
-
"properties": {}
|
|
50
|
-
},
|
|
51
|
-
"outputSchema": null,
|
|
52
|
-
"annotations": {
|
|
53
|
-
"readOnlyHint": true
|
|
54
|
-
},
|
|
55
|
-
"advancedRegistry": {
|
|
56
|
-
"permissions": [
|
|
57
|
-
"read"
|
|
58
|
-
],
|
|
59
|
-
"audit": {
|
|
60
|
-
"riskLevel": "low"
|
|
61
|
-
}
|
|
62
|
-
},
|
|
63
|
-
"server": "fixture",
|
|
64
|
-
"untrustedContent": true
|
|
65
|
-
},
|
|
66
|
-
"result": {
|
|
67
|
-
"content": [
|
|
68
|
-
{
|
|
69
|
-
"type": "text",
|
|
70
|
-
"text": "injected fixture result"
|
|
71
|
-
}
|
|
72
|
-
]
|
|
73
|
-
}
|
|
74
|
-
},
|
|
75
|
-
{
|
|
76
|
-
"name": "read_file",
|
|
77
|
-
"accepted": false,
|
|
78
|
-
"error": "MCP tool read_file conflicts with a built-in workspace tool."
|
|
79
|
-
}
|
|
80
|
-
],
|
|
81
|
-
"manualCompaction": {
|
|
82
|
-
"inputCharacters": 190271,
|
|
83
|
-
"outputCharacters": 192826,
|
|
84
|
-
"retainedFullRequests": 20
|
|
85
|
-
},
|
|
86
|
-
"sse": {
|
|
87
|
-
"accepted": false,
|
|
88
|
-
"error": "MCP server fixture returned a mismatched JSON-RPC id."
|
|
89
|
-
},
|
|
90
|
-
"kind": "full-harness-review",
|
|
91
|
-
"schemaVersion": 1,
|
|
92
|
-
"baseCommit": "0a7b69dddaa70a54b6b5b4097691c8112d4d76eb",
|
|
93
|
-
"scope": "Local working tree plus historical reports; not live certification",
|
|
94
|
-
"validation": {
|
|
95
|
-
"testsPassed": 485,
|
|
96
|
-
"testsFailed": 0,
|
|
97
|
-
"testFiles": 58,
|
|
98
|
-
"assertions": 2923,
|
|
99
|
-
"sourceTypecheck": "passed",
|
|
100
|
-
"probeTypecheck": "passed",
|
|
101
|
-
"docs": "passed",
|
|
102
|
-
"contracts": "passed-one-GA-blocker",
|
|
103
|
-
"migrations": "passed",
|
|
104
|
-
"deterministicEvaluations": "7/7",
|
|
105
|
-
"build": "passed",
|
|
106
|
-
"artifactCheck": "passed"
|
|
107
|
-
},
|
|
108
|
-
"extendedTypecheck": {
|
|
109
|
-
"diagnostics": 200,
|
|
110
|
-
"files": 37,
|
|
111
|
-
"byArea": {
|
|
112
|
-
"scripts": 114,
|
|
113
|
-
"tests": 86
|
|
114
|
-
}
|
|
115
|
-
},
|
|
116
|
-
"packaging": {
|
|
117
|
-
"auditProbeIncluded": true,
|
|
118
|
-
"probeSourceImportsIncluded": false,
|
|
119
|
-
"comparisonLinkedBaselineIncluded": false
|
|
120
|
-
},
|
|
121
|
-
"sourceSha256": {
|
|
122
|
-
"src/harness.ts": "e2be99d72763fe2be66072a70748eaa58ba783184bfb6bcadac9d769e361541a",
|
|
123
|
-
"src/model-budget.ts": "82cd70eed3927e951f8683a02b2936b9e02e15b7a999bca9a81097feacfc84e9",
|
|
124
|
-
"src/repair-progress.ts": "0fba72b12e6a59e950b3b1f52f89bb55cf2574be490633fc46620f5cfd98c363",
|
|
125
|
-
"src/mcp.ts": "5f3f7a35b89063264ae18ab9273b84e2e59ac8c8e611a6b64be377ba61cc1ac5",
|
|
126
|
-
"src/compaction.ts": "1214b92173f3fb44eb80839baae357ebc52c97e24f6b5647fb5c0e33dc1febed",
|
|
127
|
-
"src/orchestration.ts": "7383da1047363819e6560f51892fd4082e5337856a3d889cdc076f021273774e",
|
|
128
|
-
"src/task-memory.ts": "bf171cee4508fcca4793b5717e5e9ba48c77320182baa6faab867fe36b8da6df",
|
|
129
|
-
"src/workspace.ts": "0f472998a55672a326bfb32404a10073a90c9a34c24758471fede0345f582961",
|
|
130
|
-
"tsconfig.json": "e8aaf4cf79c1f522a5f0c266a05930abd582b94626db0bd487c50aac88121b06",
|
|
131
|
-
"package.json": "05c32a3c97231dbca903ab336ca9698c467c803a1890157ddec8df6a16c3cf87",
|
|
132
|
-
"evaluations/audits/full-review-2026-09-10.ts": "582a371ce21c8da947b389d66544088a3d918ad501ccfb7dd1eacc4a169e5b48"
|
|
133
|
-
}
|
|
134
|
-
}
|
|
@@ -1,136 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"schemaVersion": 1,
|
|
3
|
-
"audit": "harness-review-2026-09-09",
|
|
4
|
-
"evidence": {
|
|
5
|
-
"compaction": {
|
|
6
|
-
"originalCharacters": 1589,
|
|
7
|
-
"objectiveCharacters": 768,
|
|
8
|
-
"acceptanceSurvives": false
|
|
9
|
-
},
|
|
10
|
-
"ancestorSwap": {
|
|
11
|
-
"outsideContentReturned": true,
|
|
12
|
-
"reportedPath": "parent/fixture.txt"
|
|
13
|
-
},
|
|
14
|
-
"exactFileSearch": "search_files requires a directory.",
|
|
15
|
-
"exactFileSearchMany": 1,
|
|
16
|
-
"searchPayloadCharacters": 310975,
|
|
17
|
-
"readOnlyInspectionResetsDuplicateTracking": {
|
|
18
|
-
"identicalReads": 4,
|
|
19
|
-
"repeatedResults": 0,
|
|
20
|
-
"suppressedResults": 0,
|
|
21
|
-
"blockedBroadCalls": 0,
|
|
22
|
-
"enteredClosure": false
|
|
23
|
-
},
|
|
24
|
-
"skippedSearch": {
|
|
25
|
-
"results": [
|
|
26
|
-
{
|
|
27
|
-
"query": "unique-large-file-marker",
|
|
28
|
-
"caseSensitive": false,
|
|
29
|
-
"matches": [],
|
|
30
|
-
"truncated": false
|
|
31
|
-
}
|
|
32
|
-
]
|
|
33
|
-
},
|
|
34
|
-
"maxStepsContinuation": {
|
|
35
|
-
"requestedMaxSteps": 1,
|
|
36
|
-
"modelRequests": 1,
|
|
37
|
-
"status": "failed"
|
|
38
|
-
},
|
|
39
|
-
"ociMutationAudit": {
|
|
40
|
-
"beforeReacquire": 1,
|
|
41
|
-
"afterReacquire": 0,
|
|
42
|
-
"patchEntries": 1
|
|
43
|
-
},
|
|
44
|
-
"terminalCancellation": {
|
|
45
|
-
"status": "completed",
|
|
46
|
-
"aborted": true,
|
|
47
|
-
"executions": 1,
|
|
48
|
-
"signalPresent": false,
|
|
49
|
-
"hostImported": true
|
|
50
|
-
},
|
|
51
|
-
"absentButInstructedTools": [
|
|
52
|
-
"mutation_audit",
|
|
53
|
-
"git_diff",
|
|
54
|
-
"load_skill",
|
|
55
|
-
"apply_patch",
|
|
56
|
-
"run_check"
|
|
57
|
-
]
|
|
58
|
-
},
|
|
59
|
-
"gitCommit": "0a7b69dddaa70a54b6b5b4097691c8112d4d76eb",
|
|
60
|
-
"checkout": "Includes pre-existing uncommitted changes; no production source modified by this audit.",
|
|
61
|
-
"sdkVersions": {
|
|
62
|
-
"core": "1.14.0",
|
|
63
|
-
"agents": "1.4.0",
|
|
64
|
-
"qwen": "0.11.4"
|
|
65
|
-
},
|
|
66
|
-
"sourceSha256": {
|
|
67
|
-
"bun.lock": "b0440362d043879ece281bcee4c7adfa775a3724d2a9477079e187babd3b2d26",
|
|
68
|
-
"evaluations/audits/harness-review-2026-09-09.ts": "78dfb85e8a45b734e25854426d8837c8ea6a8455378a22abcc578419dbfbf767",
|
|
69
|
-
"package.json": "05c32a3c97231dbca903ab336ca9698c467c803a1890157ddec8df6a16c3cf87",
|
|
70
|
-
"scripts/swebench/common.py": "c19cfc30b85dc3ad8dbf1ba6a4165e72ce96f624eb1721b613cfa3207636f7be",
|
|
71
|
-
"scripts/swebench/context-metrics.ts": "3eb30f9db808f918ed8d73d4f8ac19a13acb09ed5c1ee70fdae05201714b9198",
|
|
72
|
-
"scripts/swebench/mini_driver.py": "bd0a77221878370ec44760122a51f07fb56d969612afa9a7f171248b2958baa6",
|
|
73
|
-
"scripts/swebench/model-budget.ts": "73bc6dc5f6d2f533e7af96333e2dda18b0da1d90e221def2bd07d4b3d7ddeac0",
|
|
74
|
-
"scripts/swebench/preflight.py": "aed092a75dd52f504fba6d14814b69bd627ff17d0e311a1f1279f8b613b69675",
|
|
75
|
-
"scripts/swebench/prepare.py": "bb7edd3fba5dbbe26597c97d744c60b94dbb7bcdfd7740a4a058c8583bd27e4c",
|
|
76
|
-
"scripts/swebench/report.py": "70afcdf0d1f081014bb75d878f3ddf9195959e96b523ddf1e0ad5d3ec8273549",
|
|
77
|
-
"scripts/swebench/run.py": "b184258e7c32313c9c801b50d28d1a9419d0bd2b077a422012d8fc6bc449c916",
|
|
78
|
-
"scripts/swebench/telemetry.ts": "69fafaf901b3925bec9423bc3a439d47252a11e9f49785f1fdb032e042d39915",
|
|
79
|
-
"scripts/swebench/test_contracts.py": "a8c1348f1dff2e563c139e6d3e83eb141b4f2a71f91a58e2c5c051ed2a431024",
|
|
80
|
-
"scripts/swebench/zhivex-driver.ts": "e8a289d54a541522e72e9351640963a085f2d0ebdce3e7294d756eadb6b9768e",
|
|
81
|
-
"src/bounded-reads.ts": "9807bb460894be3279c5425af19863d1c6e419a1582ba6910ec7e7fc35703ed6",
|
|
82
|
-
"src/capabilities.ts": "56fdb60a2f6e1d33b2dc26d38b6d2709807e491ba1268d47b97876c2c0591d65",
|
|
83
|
-
"src/change-envelope.ts": "9047ec978c9e5117965b8093ec961d855f97bbc2c3accdc79b74cfe6a0e4f01e",
|
|
84
|
-
"src/cli-options.ts": "97781386289e3877c1318e4c94698ca7aaf2f256b89534dfcb21e966eb7d939f",
|
|
85
|
-
"src/cli-profiles.ts": "4fe451f1645e95f4957597a8724fa989b3c661ae1693252bfd6e74a51d20fc74",
|
|
86
|
-
"src/cli-stream.ts": "5ab8a4b1b8cf0a3dfa7b5b1f9e4e0facf8f6e7f6c341bdf700a41dc8927c825e",
|
|
87
|
-
"src/cli.ts": "cce6f58dfbc543acdc029b188d4394cd059d940bdd361351fd877ae2d6e94880",
|
|
88
|
-
"src/compaction.ts": "02321d91d8f00690636e00e3d7b08a9e1e16ae00b2b465e37af686b746d1b55e",
|
|
89
|
-
"src/config.ts": "c160faaf2d9fb637c5a08a7aff65d761a12c707ed23ebb87ab0e8519e9536bf3",
|
|
90
|
-
"src/console-context.ts": "0ad7e4559504b9ed09ab500d615dea09af1075d357f02ec3b77f003d55d951db",
|
|
91
|
-
"src/console-input.ts": "dc8ea0cdbba1364db288d5156c5ff9819362c46b37ef35a98b0475b6c445b1f8",
|
|
92
|
-
"src/context-engineering.ts": "1995e564f6b91974e75bf66dd421ddcbea29b1f8eee59b76eb4e34c9d6d8f47e",
|
|
93
|
-
"src/edit-contracts.ts": "47cc3132e27f8749d54a32bbcc33bb174cf4448f0d0171b2578cdb559cf2176b",
|
|
94
|
-
"src/errors.ts": "e02f4eb80562a83762f908bda56c950ec6a2b78725c0c8a49f41fee0057ab903",
|
|
95
|
-
"src/execution-environment.ts": "8519e532dfafe4ae51bfbc81e0732267bc6aa9eec871ffde8c917aa001e358e5",
|
|
96
|
-
"src/file-security.ts": "4590b46c8e4b9d3891a75cd0d0ada14e0ae7b58e8e4bdf82f68df688a1fbb750",
|
|
97
|
-
"src/harness.ts": "7fd001e847530e0cb1ec5f371078649bd0352d6343948e3cdb4240cdc58c98c7",
|
|
98
|
-
"src/index.ts": "f791311f14dc27105191d97bb5454748d10beab827da9aba3ea949ffc32fce7c",
|
|
99
|
-
"src/json-contracts.ts": "0702e5b0ff16ff6304c74b4101bd31a3fa8eabdebe267d312b56d3871a7e302c",
|
|
100
|
-
"src/mcp.ts": "5f3f7a35b89063264ae18ab9273b84e2e59ac8c8e611a6b64be377ba61cc1ac5",
|
|
101
|
-
"src/operations.ts": "0775da79208c6f5d18476cc76404e84ddda610979d9d0e5dc15035aa6999613c",
|
|
102
|
-
"src/orchestration.ts": "7383da1047363819e6560f51892fd4082e5337856a3d889cdc076f021273774e",
|
|
103
|
-
"src/package-manager.ts": "cec4666bbab2f42e0a269709631f79f9f87c2c4dbb3cafeffacfaff761069e2c",
|
|
104
|
-
"src/process-runtime.ts": "b7286731a0b5c96dcad0b8e3a4bf1155d0539d73303cd7ebe77ffabf858f1729",
|
|
105
|
-
"src/providers.ts": "70ccfc7f315cd7238e83d69b719ce4908f3b620c564cbb4f00f93e102e025602",
|
|
106
|
-
"src/repair-progress.ts": "114a7b42f596ea3bd3fe7efac4363195921385d4e86ad5b17ced0e12c8520e23",
|
|
107
|
-
"src/replacement-edits.ts": "8a0efdd3a7a9fc3e5a5475916cbd17ef882265881bb61076db58673e80b72957",
|
|
108
|
-
"src/routing.ts": "8e7c9f5968b4bd638cbbc86b19847ca183f3418b9a298783b96a88cffa568e22",
|
|
109
|
-
"src/run-interruption.ts": "df99129cf2dd6b938eca629cb897c4350a7d57fe6bf0ce437f5f3f30271617df",
|
|
110
|
-
"src/sessions.ts": "5167c8cf36bd4b8845ee278883394700321b65397f49c1dda0cf0d0de09dd06e",
|
|
111
|
-
"src/sqlite-database.ts": "18765d1ca0c2f2ad87bfd82d311312dfe8a42006556f27bc21da5892ed3b044e",
|
|
112
|
-
"src/state-backup.ts": "b6f8f1aedeb5dce31b65c23c7ffc50030870655b58a5aaaef9989bafb9da5c68",
|
|
113
|
-
"src/state-directory.ts": "3711550991951e6b738a08deaa0e06da84d01864c03a9602600f592963fa3211",
|
|
114
|
-
"src/terminal-markdown.ts": "8cffb6ebaf25108cb2bee04956d9b2973635b010f5d7ce6be21b3ceffe3e8bfd",
|
|
115
|
-
"src/terminal-ui.ts": "e50025a8649d1f60efdf3af895b8639730ec2e86553fb80a61a776b11076c705",
|
|
116
|
-
"src/time-to-safe-fix.ts": "4add1d49c0ea209cc496c66fa2b2012dc7bcab87e678a58c8591b3c2cdc8df8a",
|
|
117
|
-
"src/version.ts": "b2c2f80a40adc08e8258b81e82434273f0bdfa787528b2221f14efe7f06aa747",
|
|
118
|
-
"src/workspace.ts": "e9c2ed5c950d751d0f93a5512584d0698449b551d3270b3e115ccca380565222"
|
|
119
|
-
},
|
|
120
|
-
"validation": {
|
|
121
|
-
"existingTests": 466,
|
|
122
|
-
"failedTests": 0,
|
|
123
|
-
"deterministicEvaluations": 7,
|
|
124
|
-
"sourceTypecheck": "passed",
|
|
125
|
-
"auditTypecheck": "passed",
|
|
126
|
-
"contractCheck": "passed; one GA security-review blocker remains open",
|
|
127
|
-
"historicalMigrationFixtures": "passed",
|
|
128
|
-
"newLiveModelCalls": 0,
|
|
129
|
-
"newRealOciSmoke": false
|
|
130
|
-
},
|
|
131
|
-
"limits": [
|
|
132
|
-
"Ancestor race uses a deterministic filesystem interleaving with synthetic files; it does not measure real-world race probability.",
|
|
133
|
-
"Cancellation uses the real approval/snapshot/import path with a simulated OCI process.",
|
|
134
|
-
"Findings are local source evidence, not a remote release certification."
|
|
135
|
-
]
|
|
136
|
-
}
|
|
@@ -1,160 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"schemaVersion": 1,
|
|
3
|
-
"audit": "harness-review-2026-09-09",
|
|
4
|
-
"evidence": {
|
|
5
|
-
"compaction": {
|
|
6
|
-
"originalCharacters": 1589,
|
|
7
|
-
"objectiveCharacters": 768,
|
|
8
|
-
"acceptanceSurvives": true
|
|
9
|
-
},
|
|
10
|
-
"ancestorSwap": {
|
|
11
|
-
"blocked": true,
|
|
12
|
-
"error": "The file must be a regular file and must not be a symbolic link."
|
|
13
|
-
},
|
|
14
|
-
"exactFileSearch": "supported",
|
|
15
|
-
"exactFileSearchMany": 1,
|
|
16
|
-
"searchPayloadCharacters": 28618,
|
|
17
|
-
"readOnlyInspectionResetsDuplicateTracking": {
|
|
18
|
-
"identicalReads": 4,
|
|
19
|
-
"repeatedResults": 3,
|
|
20
|
-
"suppressedResults": 2,
|
|
21
|
-
"blockedBroadCalls": 0,
|
|
22
|
-
"enteredClosure": false,
|
|
23
|
-
"phase": "explore",
|
|
24
|
-
"blockedPhaseCalls": 0,
|
|
25
|
-
"planRecorded": false
|
|
26
|
-
},
|
|
27
|
-
"skippedSearch": {
|
|
28
|
-
"coverage": {
|
|
29
|
-
"inspectedFiles": 2,
|
|
30
|
-
"skippedFiles": 1,
|
|
31
|
-
"incomplete": true,
|
|
32
|
-
"skippedReasons": {
|
|
33
|
-
"tooLarge": 1,
|
|
34
|
-
"unsafe": 0,
|
|
35
|
-
"unreadable": 0
|
|
36
|
-
}
|
|
37
|
-
},
|
|
38
|
-
"outputTruncated": false,
|
|
39
|
-
"continuation": "For a truncated query, use search_files with that query and its nextCursor, or narrow to the returned file/line locations.",
|
|
40
|
-
"results": [
|
|
41
|
-
{
|
|
42
|
-
"query": "unique-large-file-marker",
|
|
43
|
-
"caseSensitive": false,
|
|
44
|
-
"matches": [],
|
|
45
|
-
"truncated": false
|
|
46
|
-
}
|
|
47
|
-
]
|
|
48
|
-
},
|
|
49
|
-
"maxStepsContinuation": {
|
|
50
|
-
"requestedMaxSteps": 1,
|
|
51
|
-
"modelRequests": 1,
|
|
52
|
-
"status": "failed"
|
|
53
|
-
},
|
|
54
|
-
"ociMutationAudit": {
|
|
55
|
-
"beforeReacquire": 1,
|
|
56
|
-
"afterReacquire": 1,
|
|
57
|
-
"patchEntries": 1
|
|
58
|
-
},
|
|
59
|
-
"terminalCancellation": {
|
|
60
|
-
"status": "threw",
|
|
61
|
-
"aborted": true,
|
|
62
|
-
"executions": 0,
|
|
63
|
-
"signalPresent": false,
|
|
64
|
-
"hostImported": false
|
|
65
|
-
},
|
|
66
|
-
"absentButInstructedTools": []
|
|
67
|
-
},
|
|
68
|
-
"implementationSources": {
|
|
69
|
-
"scripts/swebench/candidate.py": "f5e3410b91b950acfbe50fc7511891816a8fb1c223082397e2c6300cf1e866cf",
|
|
70
|
-
"scripts/swebench/candidate.ts": "bf102becfcce0c9a3f0df0a8f1ce0e5aaea7db2d252f6d9454a8370c24e53982",
|
|
71
|
-
"scripts/swebench/common.py": "12f7851e8106b22f2124751ce56e3742348ebb3c40ef0bc89ee9d2fefa0aff77",
|
|
72
|
-
"scripts/swebench/context-metrics.ts": "7b84da6789413aa634d997c5963ee6796584e06c3eafe5f68f424fb7e27815e9",
|
|
73
|
-
"scripts/swebench/mini_driver.py": "bd0a77221878370ec44760122a51f07fb56d969612afa9a7f171248b2958baa6",
|
|
74
|
-
"scripts/swebench/model-budget.ts": "e46dd406ee5d58a051a15c7d7133513666292303d8c6534f861a6db0e711f47c",
|
|
75
|
-
"scripts/swebench/preflight.py": "aed092a75dd52f504fba6d14814b69bd627ff17d0e311a1f1279f8b613b69675",
|
|
76
|
-
"scripts/swebench/prepare.py": "bb7edd3fba5dbbe26597c97d744c60b94dbb7bcdfd7740a4a058c8583bd27e4c",
|
|
77
|
-
"scripts/swebench/report.py": "d0b8d45f32c48e0ba2cb977f50838065a497a0ecaf3b4243ed94139393ce4d6b",
|
|
78
|
-
"scripts/swebench/run.py": "24ffa302e673bbf240d6396474631bb4ce80447797584c3ed27f2d1e55e452cb",
|
|
79
|
-
"scripts/swebench/telemetry.ts": "743c9baf273e9240d704d098b6bd5eea9e76ef3e49ae636aaafa9bfd7a85b45b",
|
|
80
|
-
"scripts/swebench/test_candidate.py": "e77d16379b748baa2daf184a45ea62587d938b6a7d48dcf9f6061f8af21fafd9",
|
|
81
|
-
"scripts/swebench/test_contracts.py": "a8c1348f1dff2e563c139e6d3e83eb141b4f2a71f91a58e2c5c051ed2a431024",
|
|
82
|
-
"scripts/swebench/zhivex-driver.ts": "e33ed929256133fb29be67e3feb282f0d0fd52086576a668021852c151ff35d1",
|
|
83
|
-
"src/bounded-reads.ts": "9807bb460894be3279c5425af19863d1c6e419a1582ba6910ec7e7fc35703ed6",
|
|
84
|
-
"src/capabilities.ts": "56fdb60a2f6e1d33b2dc26d38b6d2709807e491ba1268d47b97876c2c0591d65",
|
|
85
|
-
"src/change-envelope.ts": "9047ec978c9e5117965b8093ec961d855f97bbc2c3accdc79b74cfe6a0e4f01e",
|
|
86
|
-
"src/cli-options.ts": "f48d9be132fed38f2ddbcfecbd8222c664a0df2f20edc28ce8d1b9b1a1900863",
|
|
87
|
-
"src/cli-profiles.ts": "4fe451f1645e95f4957597a8724fa989b3c661ae1693252bfd6e74a51d20fc74",
|
|
88
|
-
"src/cli-stream.ts": "5ab8a4b1b8cf0a3dfa7b5b1f9e4e0facf8f6e7f6c341bdf700a41dc8927c825e",
|
|
89
|
-
"src/cli.ts": "2210d89050a4d6821288bd0845577b56f42af94eac92599785f2d1d68105f199",
|
|
90
|
-
"src/compaction.ts": "1214b92173f3fb44eb80839baae357ebc52c97e24f6b5647fb5c0e33dc1febed",
|
|
91
|
-
"src/config.ts": "a31e9f91c0eb59b4d77496431639aa4b47b149e1968c6e0a002a508de4919c35",
|
|
92
|
-
"src/console-context.ts": "0ad7e4559504b9ed09ab500d615dea09af1075d357f02ec3b77f003d55d951db",
|
|
93
|
-
"src/console-input.ts": "dc8ea0cdbba1364db288d5156c5ff9819362c46b37ef35a98b0475b6c445b1f8",
|
|
94
|
-
"src/context-engineering.ts": "1995e564f6b91974e75bf66dd421ddcbea29b1f8eee59b76eb4e34c9d6d8f47e",
|
|
95
|
-
"src/context-metrics.ts": "3eb30f9db808f918ed8d73d4f8ac19a13acb09ed5c1ee70fdae05201714b9198",
|
|
96
|
-
"src/edit-contracts.ts": "47cc3132e27f8749d54a32bbcc33bb174cf4448f0d0171b2578cdb559cf2176b",
|
|
97
|
-
"src/errors.ts": "e02f4eb80562a83762f908bda56c950ec6a2b78725c0c8a49f41fee0057ab903",
|
|
98
|
-
"src/execution-environment.ts": "ff683e9c48fe15aee6decad54ce3aa489c9a70edf72c421bf583922ca42eae3f",
|
|
99
|
-
"src/file-security.ts": "b8c9f4988c4339c73a60ab4fa8d394b3eecc19117a0c61a8d19ab6483ca253df",
|
|
100
|
-
"src/harness.ts": "e2be99d72763fe2be66072a70748eaa58ba783184bfb6bcadac9d769e361541a",
|
|
101
|
-
"src/index.ts": "4bbfcd11376d48c4f1c1ec17d6b5c9f51baa9331fa999432be178bae94530a5e",
|
|
102
|
-
"src/json-contracts.ts": "0780145636b47829a1aa6087c574d5654eb31b7534ea7d9c38c188d648c90272",
|
|
103
|
-
"src/mcp.ts": "5f3f7a35b89063264ae18ab9273b84e2e59ac8c8e611a6b64be377ba61cc1ac5",
|
|
104
|
-
"src/model-budget.ts": "82cd70eed3927e951f8683a02b2936b9e02e15b7a999bca9a81097feacfc84e9",
|
|
105
|
-
"src/operations.ts": "0775da79208c6f5d18476cc76404e84ddda610979d9d0e5dc15035aa6999613c",
|
|
106
|
-
"src/orchestration.ts": "7383da1047363819e6560f51892fd4082e5337856a3d889cdc076f021273774e",
|
|
107
|
-
"src/package-manager.ts": "cec4666bbab2f42e0a269709631f79f9f87c2c4dbb3cafeffacfaff761069e2c",
|
|
108
|
-
"src/process-runtime.ts": "b7286731a0b5c96dcad0b8e3a4bf1155d0539d73303cd7ebe77ffabf858f1729",
|
|
109
|
-
"src/providers.ts": "70ccfc7f315cd7238e83d69b719ce4908f3b620c564cbb4f00f93e102e025602",
|
|
110
|
-
"src/repair-progress.ts": "0fba72b12e6a59e950b3b1f52f89bb55cf2574be490633fc46620f5cfd98c363",
|
|
111
|
-
"src/replacement-edits.ts": "8a0efdd3a7a9fc3e5a5475916cbd17ef882265881bb61076db58673e80b72957",
|
|
112
|
-
"src/routing.ts": "8e7c9f5968b4bd638cbbc86b19847ca183f3418b9a298783b96a88cffa568e22",
|
|
113
|
-
"src/run-interruption.ts": "df99129cf2dd6b938eca629cb897c4350a7d57fe6bf0ce437f5f3f30271617df",
|
|
114
|
-
"src/sessions.ts": "5167c8cf36bd4b8845ee278883394700321b65397f49c1dda0cf0d0de09dd06e",
|
|
115
|
-
"src/sqlite-database.ts": "18765d1ca0c2f2ad87bfd82d311312dfe8a42006556f27bc21da5892ed3b044e",
|
|
116
|
-
"src/state-backup.ts": "b6f8f1aedeb5dce31b65c23c7ffc50030870655b58a5aaaef9989bafb9da5c68",
|
|
117
|
-
"src/state-directory.ts": "3711550991951e6b738a08deaa0e06da84d01864c03a9602600f592963fa3211",
|
|
118
|
-
"src/task-memory.ts": "bf171cee4508fcca4793b5717e5e9ba48c77320182baa6faab867fe36b8da6df",
|
|
119
|
-
"src/terminal-markdown.ts": "8cffb6ebaf25108cb2bee04956d9b2973635b010f5d7ce6be21b3ceffe3e8bfd",
|
|
120
|
-
"src/terminal-ui.ts": "e50025a8649d1f60efdf3af895b8639730ec2e86553fb80a61a776b11076c705",
|
|
121
|
-
"src/time-to-safe-fix.ts": "4add1d49c0ea209cc496c66fa2b2012dc7bcab87e678a58c8591b3c2cdc8df8a",
|
|
122
|
-
"src/version.ts": "b2c2f80a40adc08e8258b81e82434273f0bdfa787528b2221f14efe7f06aa747",
|
|
123
|
-
"src/workspace.ts": "0f472998a55672a326bfb32404a10073a90c9a34c24758471fede0345f582961",
|
|
124
|
-
"tests/audit-remediation.test.ts": "8fe0513fadef543279f3ce919b3f091f5a0c61eb13b2c1798f660ef894ecfb4a",
|
|
125
|
-
"tests/swebench.test.ts": "1b87b2b1c48132cdb383455bfc538d21f3a817d92cf201a44bf78156d14040eb",
|
|
126
|
-
"tests/terminal-verification-recovery.test.ts": "fba52c7d20425721647d2a30e1fe271623cd27621b6b7d477211378de6d23b97"
|
|
127
|
-
},
|
|
128
|
-
"validation": {
|
|
129
|
-
"unitTests": {
|
|
130
|
-
"passed": 485,
|
|
131
|
-
"failed": 0,
|
|
132
|
-
"files": 58
|
|
133
|
-
},
|
|
134
|
-
"finalTargetedTests": {
|
|
135
|
-
"passed": 23,
|
|
136
|
-
"failed": 0
|
|
137
|
-
},
|
|
138
|
-
"deterministicEvaluations": {
|
|
139
|
-
"passed": 7,
|
|
140
|
-
"failed": 0
|
|
141
|
-
},
|
|
142
|
-
"typecheck": "passed",
|
|
143
|
-
"scriptAndRegressionTypecheck": "passed",
|
|
144
|
-
"docsAndContracts": "passed",
|
|
145
|
-
"historicalMigrations": "passed",
|
|
146
|
-
"workspaceAndSafeFixCi": "passed",
|
|
147
|
-
"ociDocker": "passed",
|
|
148
|
-
"mcpControlled": "passed",
|
|
149
|
-
"mcpOfficialSdk": "passed",
|
|
150
|
-
"installedPackage": "passed",
|
|
151
|
-
"descriptorPlatforms": [
|
|
152
|
-
"darwin-node",
|
|
153
|
-
"darwin-bun",
|
|
154
|
-
"linux-node24"
|
|
155
|
-
],
|
|
156
|
-
"paidModelCalls": 0,
|
|
157
|
-
"aggregateCheck": "sandbox-port-restriction; remaining checks passed separately"
|
|
158
|
-
},
|
|
159
|
-
"previousAuditSha256": "f4f1bf002faca2aed506af0ede6f9fabba3a0e629f1549bba39568cc71349219"
|
|
160
|
-
}
|