@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
|
@@ -1,40 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"kind": "diagnostic-tool-catalog-ablation",
|
|
3
|
-
"baseCommit": "c2b2bb917d0471e61afc5f731a61c00b44fa3731",
|
|
4
|
-
"baseline": "ga-recovery-graded-v8-qwen",
|
|
5
|
-
"classification": "known development task; not GA acceptance",
|
|
6
|
-
"model": "qwen3.8-flash",
|
|
7
|
-
"limits": {
|
|
8
|
-
"steps": 24,
|
|
9
|
-
"outputPerTurn": 2048,
|
|
10
|
-
"inputTokens": 100000,
|
|
11
|
-
"outputTokens": 16000,
|
|
12
|
-
"timeoutSeconds": 300,
|
|
13
|
-
"memoryMb": 2048,
|
|
14
|
-
"cpus": 2
|
|
15
|
-
},
|
|
16
|
-
"repetitions": 1,
|
|
17
|
-
"control": "unchanged mini-SWE-agent",
|
|
18
|
-
"tools": [
|
|
19
|
-
"read_task",
|
|
20
|
-
"repair_plan",
|
|
21
|
-
"run_environment_shell",
|
|
22
|
-
"inspect_environment_patch",
|
|
23
|
-
"verify_and_apply_environment_patch"
|
|
24
|
-
],
|
|
25
|
-
"changed": [
|
|
26
|
-
"driver catalog",
|
|
27
|
-
"instructions rendered from catalog"
|
|
28
|
-
],
|
|
29
|
-
"unchanged": [
|
|
30
|
-
"runtime source",
|
|
31
|
-
"OCI policy",
|
|
32
|
-
"approval policy",
|
|
33
|
-
"verification/import gate",
|
|
34
|
-
"model",
|
|
35
|
-
"budgets",
|
|
36
|
-
"official grader"
|
|
37
|
-
],
|
|
38
|
-
"driverSha256": "8d68286b42979a603dcded8860133e134d351f25aedb5dd98ed2ef6f810cbd74",
|
|
39
|
-
"acceptance": "retain every sample and grading result; do not replace product profile or count this variant as GA"
|
|
40
|
-
}
|