@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
@@ -1,233 +0,0 @@
1
- {
2
- "schemaVersion": 1,
3
- "kind": "local-efficiency-observation",
4
- "date": "2026-09-08",
5
- "baseCommit": "0a7b69dddaa70a54b6b5b4097691c8112d4d76eb",
6
- "evidenceBoundary": "Uncommitted development measurements; three repetitions, non-flushed host cache, Bun runtime. Sequential before/after observations, not randomized paired trials or public agent capability results. No paid model calls.",
7
- "comparisons": [
8
- {
9
- "name": "workspace",
10
- "boundary": "Unmodified checkout versus bounded reads and freshness checks.",
11
- "before": {
12
- "reportSha256": "171c5583f40caa60cc2f8c82bc548625538c816b9903c6695725a0ed8ebac77e",
13
- "fixture": {
14
- "files": 10000,
15
- "pageSize": 100
16
- },
17
- "methodology": {
18
- "repetitions": 3,
19
- "warmups": 0,
20
- "workspaceIndexState": "cold-first-page-then-reused-within-repetition",
21
- "hostFilesystemCache": "not-flushed",
22
- "resultValidation": true
23
- },
24
- "statistics": {
25
- "digestBoundAllPages": {
26
- "samples": 3,
27
- "successes": 3,
28
- "failures": 0,
29
- "minMs": 932.76,
30
- "p50Ms": 970.63,
31
- "maxMs": 1184.52
32
- },
33
- "threeIndependentSearches": {
34
- "samples": 3,
35
- "successes": 3,
36
- "failures": 0,
37
- "minMs": 1058.3,
38
- "p50Ms": 1136.79,
39
- "maxMs": 1195.78
40
- },
41
- "searchMany": {
42
- "samples": 3,
43
- "successes": 3,
44
- "failures": 0,
45
- "minMs": 910.8,
46
- "p50Ms": 941.46,
47
- "maxMs": 979.75
48
- }
49
- }
50
- },
51
- "after": {
52
- "reportSha256": "c70bae665e81ed6870d4369d122a955fb140fac1dd760f612f8604d27eeef9b9",
53
- "fixture": {
54
- "files": 10000,
55
- "pageSize": 100,
56
- "directories": 1,
57
- "minimumFileBytes": 0
58
- },
59
- "methodology": {
60
- "repetitions": 3,
61
- "warmups": 0,
62
- "workspaceIndexState": "cold-first-page-then-reused-within-repetition",
63
- "hostFilesystemCache": "not-flushed",
64
- "resultValidation": true
65
- },
66
- "statistics": {
67
- "digestBoundAllPages": {
68
- "samples": 3,
69
- "successes": 3,
70
- "failures": 0,
71
- "minMs": 242.82,
72
- "p50Ms": 245.74,
73
- "maxMs": 396.97
74
- },
75
- "threeIndependentSearches": {
76
- "samples": 3,
77
- "successes": 3,
78
- "failures": 0,
79
- "minMs": 474.12,
80
- "p50Ms": 492.41,
81
- "maxMs": 526.95
82
- },
83
- "searchMany": {
84
- "samples": 3,
85
- "successes": 3,
86
- "failures": 0,
87
- "minMs": 218.22,
88
- "p50Ms": 232.24,
89
- "maxMs": 237.24
90
- }
91
- }
92
- }
93
- },
94
- {
95
- "name": "nested-freshness",
96
- "boundary": "Both sides use bounded content reads; after also batches index freshness checks.",
97
- "before": {
98
- "reportSha256": "4a7132678700753bdf6005770c6420c7d3e0fd483b5c70f10e5080687c55ed68",
99
- "fixture": {
100
- "files": 1000,
101
- "pageSize": 100,
102
- "directories": 100,
103
- "minimumFileBytes": 4096
104
- },
105
- "methodology": {
106
- "repetitions": 3,
107
- "warmups": 0,
108
- "workspaceIndexState": "cold-first-page-then-reused-within-repetition",
109
- "hostFilesystemCache": "not-flushed",
110
- "resultValidation": true
111
- },
112
- "statistics": {
113
- "topologyAllPages": {
114
- "samples": 3,
115
- "successes": 3,
116
- "failures": 0,
117
- "minMs": 27.57,
118
- "p50Ms": 27.61,
119
- "maxMs": 33.75
120
- }
121
- }
122
- },
123
- "after": {
124
- "reportSha256": "20bff97fb983a56e0729ec183b32764af093489911a84a4b99979b8c40e21036",
125
- "fixture": {
126
- "files": 1000,
127
- "pageSize": 100,
128
- "directories": 100,
129
- "minimumFileBytes": 4096
130
- },
131
- "methodology": {
132
- "repetitions": 3,
133
- "warmups": 0,
134
- "workspaceIndexState": "cold-first-page-then-reused-within-repetition",
135
- "hostFilesystemCache": "not-flushed",
136
- "resultValidation": true
137
- },
138
- "statistics": {
139
- "topologyAllPages": {
140
- "samples": 3,
141
- "successes": 3,
142
- "failures": 0,
143
- "minMs": 10.13,
144
- "p50Ms": 10.32,
145
- "maxMs": 11.51
146
- }
147
- }
148
- }
149
- },
150
- {
151
- "name": "oci-snapshot",
152
- "boundary": "Before already uses bounded content reads; after additionally batches snapshot construction and index freshness.",
153
- "before": {
154
- "reportSha256": "6db33e8a52442485111cca2ec96c6b304b61d639559c96873a53c38411398a8a",
155
- "fixture": {
156
- "files": 1001,
157
- "commands": 1,
158
- "commandsPerRepetition": 1,
159
- "reusedNoOpCommandsPerRepetition": 0,
160
- "batchCommandsPerRepetition": 1
161
- },
162
- "methodology": {
163
- "repetitions": 3,
164
- "warmups": 0,
165
- "hostFilesystemCache": "not-flushed",
166
- "resultValidation": true
167
- },
168
- "statistics": {
169
- "sessionAcquire": {
170
- "samples": 3,
171
- "successes": 3,
172
- "failures": 0,
173
- "minMs": 383.97,
174
- "p50Ms": 417.04,
175
- "maxMs": 567.24
176
- },
177
- "completeScenario": {
178
- "samples": 3,
179
- "successes": 3,
180
- "failures": 0,
181
- "minMs": 2196.8,
182
- "p50Ms": 2555.25,
183
- "maxMs": 4134.44
184
- }
185
- },
186
- "runtime": {
187
- "name": "docker",
188
- "version": "29.7.2",
189
- "imageDigest": "sha256:3638d9a6fe4030bd716be989438248074489337ba3275657f93595428be4fc03"
190
- }
191
- },
192
- "after": {
193
- "reportSha256": "7267ae148ec503c2bb3029833e6e77119443709474344eb3126cd511faa4288d",
194
- "fixture": {
195
- "files": 1001,
196
- "commands": 1,
197
- "commandsPerRepetition": 1,
198
- "reusedNoOpCommandsPerRepetition": 0,
199
- "batchCommandsPerRepetition": 1
200
- },
201
- "methodology": {
202
- "repetitions": 3,
203
- "warmups": 0,
204
- "hostFilesystemCache": "not-flushed",
205
- "resultValidation": true
206
- },
207
- "statistics": {
208
- "sessionAcquire": {
209
- "samples": 3,
210
- "successes": 3,
211
- "failures": 0,
212
- "minMs": 183.55,
213
- "p50Ms": 193.16,
214
- "maxMs": 195.77
215
- },
216
- "completeScenario": {
217
- "samples": 3,
218
- "successes": 3,
219
- "failures": 0,
220
- "minMs": 1770.2,
221
- "p50Ms": 1844.69,
222
- "maxMs": 2144.49
223
- }
224
- },
225
- "runtime": {
226
- "name": "docker",
227
- "version": "29.7.2",
228
- "imageDigest": "sha256:3638d9a6fe4030bd716be989438248074489337ba3275657f93595428be4fc03"
229
- }
230
- }
231
- }
232
- ]
233
- }