kiokuko-dsh 0.2.18 → 0.2.19
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/dist/dsh/core/host.d.ts.map +1 -1
- package/dist/dsh/core/host.js +2 -0
- package/dist/dsh/core/host.js.map +1 -1
- package/dist/dsh/head-worker-configuration.js +1 -1
- package/dist/dsh/head-worker-configuration.js.map +1 -1
- package/dist/dsh/lisp/manager.d.ts.map +1 -1
- package/dist/dsh/lisp/manager.js +18 -2
- package/dist/dsh/lisp/manager.js.map +1 -1
- package/dist/dsh/lisp/recovery.d.ts +13 -0
- package/dist/dsh/lisp/recovery.d.ts.map +1 -0
- package/dist/dsh/lisp/recovery.js +59 -0
- package/dist/dsh/lisp/recovery.js.map +1 -0
- package/dist/dsh/lisp/worker.js +2 -2
- package/dist/dsh/lisp/worker.js.map +1 -1
- package/dist/dsh/model-configuration.d.ts +1 -1
- package/dist/dsh/model-configuration.d.ts.map +1 -1
- package/dist/dsh/model-configuration.js +3 -2
- package/dist/dsh/model-configuration.js.map +1 -1
- package/dist/dsh/models/service.d.ts +1 -0
- package/dist/dsh/models/service.d.ts.map +1 -1
- package/dist/dsh/models/service.js +16 -8
- package/dist/dsh/models/service.js.map +1 -1
- package/dist/dsh/models/surface.d.ts.map +1 -1
- package/dist/dsh/models/surface.js +0 -3
- package/dist/dsh/models/surface.js.map +1 -1
- package/dist/dsh/models/vendor/nous-oauth.d.ts +1 -1
- package/dist/dsh/models/vendor/nous-oauth.d.ts.map +1 -1
- package/dist/dsh/models/vendor/nous-oauth.js +3 -2
- package/dist/dsh/models/vendor/nous-oauth.js.map +1 -1
- package/dist/locale/en.json +1 -1
- package/dist/locale/ja.json +1 -1
- package/dist/locale/ko.json +1 -1
- package/dist/locale/zh-CN.json +1 -1
- package/docs/lisp-recovery-evaluation.json +693 -0
- package/docs/lisp-recovery-verification.md +61 -0
- package/docs/lisp-recovery.md +108 -0
- package/docs/lisp.md +2 -0
- package/docs/provider-auth-boundaries.md +37 -0
- package/lisp/tools.lisp +35 -3
- package/package.json +1 -1
|
@@ -0,0 +1,693 @@
|
|
|
1
|
+
{
|
|
2
|
+
"version": 1,
|
|
3
|
+
"baseCommit": "f59448c2e492e3dd8f9c00b16e76172cfb1d7e09",
|
|
4
|
+
"recordedAt": "2026-10-21T08:41:49.650600+00:00",
|
|
5
|
+
"sourceIdentity": {
|
|
6
|
+
"lisp/tools.lisp": "a16bd242eab2bce839ab1ee518c34654344571951967a0bea5c3d7b0cc39b193",
|
|
7
|
+
"src/dsh/lisp/recovery.ts": "94215c7f768142e4d7f6ef87e9eeaf1142a9ed5c0e44f093b04601d14dfc0388",
|
|
8
|
+
"src/dsh/lisp/manager.ts": "e2e74bb7ccc8875fa277878d68600569bd1c710300501899bef8366993c39af6",
|
|
9
|
+
"src/dsh/lisp/worker.ts": "cabfd5db7bd4df850b0fb851d45b18cb4b824a6b84b68cc70ab068aec9783edb",
|
|
10
|
+
"tests/dsh/unit/lisp/recovery.test.ts": "4ce64b9d3ecb7b1b0ffad8389395d52af6acf6589f532cf0b806676f03839acb",
|
|
11
|
+
"tests/dsh/integration/lisp/recovery-runtime.test.ts": "bc7d3126a2d1e484d0dd5618bab1a8855228ad9eb994fa4f26035bcb465b6dc8",
|
|
12
|
+
"scripts/run-lisp-recovery-evaluation.mjs": "b66985772c52e1576887861be00f26c42dcc9c0f904ef1406cfe04cc6e340901",
|
|
13
|
+
"scripts/run-lisp-typed-recovery-evaluation.mjs": "43806ec9f61839e6e0da3db9fbf5b52b701ec1466a82f0480535f177392ef0d8"
|
|
14
|
+
},
|
|
15
|
+
"checks": {
|
|
16
|
+
"focused": {
|
|
17
|
+
"tests": 10,
|
|
18
|
+
"pass": 10,
|
|
19
|
+
"fail": 0,
|
|
20
|
+
"cancelled": 0,
|
|
21
|
+
"skipped": 0
|
|
22
|
+
},
|
|
23
|
+
"lispSuite": {
|
|
24
|
+
"tests": 333,
|
|
25
|
+
"pass": 308,
|
|
26
|
+
"fail": 3,
|
|
27
|
+
"cancelled": 0,
|
|
28
|
+
"skipped": 22
|
|
29
|
+
},
|
|
30
|
+
"skillDelivery": {
|
|
31
|
+
"tests": 11,
|
|
32
|
+
"pass": 11,
|
|
33
|
+
"fail": 0,
|
|
34
|
+
"cancelled": 0,
|
|
35
|
+
"skipped": 0
|
|
36
|
+
},
|
|
37
|
+
"typecheck": {
|
|
38
|
+
"status": "passed",
|
|
39
|
+
"command": "npm run typecheck"
|
|
40
|
+
},
|
|
41
|
+
"baselinePython": {
|
|
42
|
+
"tests": 3,
|
|
43
|
+
"pass": 0,
|
|
44
|
+
"fail": 3,
|
|
45
|
+
"cancelled": 0,
|
|
46
|
+
"skipped": 0
|
|
47
|
+
},
|
|
48
|
+
"diffCheck": "passed"
|
|
49
|
+
},
|
|
50
|
+
"mutations": [
|
|
51
|
+
{
|
|
52
|
+
"mutation": "duplicate-guard",
|
|
53
|
+
"exit": 1,
|
|
54
|
+
"detected": true,
|
|
55
|
+
"assertionFailure": true
|
|
56
|
+
},
|
|
57
|
+
{
|
|
58
|
+
"mutation": "stale-guard",
|
|
59
|
+
"exit": 1,
|
|
60
|
+
"detected": true,
|
|
61
|
+
"assertionFailure": true
|
|
62
|
+
},
|
|
63
|
+
{
|
|
64
|
+
"mutation": "publication-authority",
|
|
65
|
+
"exit": 1,
|
|
66
|
+
"detected": true,
|
|
67
|
+
"assertionFailure": true
|
|
68
|
+
},
|
|
69
|
+
{
|
|
70
|
+
"mutation": "unknown-effect-gate",
|
|
71
|
+
"exit": 1,
|
|
72
|
+
"detected": true,
|
|
73
|
+
"assertionFailure": true,
|
|
74
|
+
"specificFailure": true
|
|
75
|
+
}
|
|
76
|
+
],
|
|
77
|
+
"modelComparison": {
|
|
78
|
+
"version": 1,
|
|
79
|
+
"scope": "live-synthetic",
|
|
80
|
+
"binding": {
|
|
81
|
+
"provider": "configured-infron-route",
|
|
82
|
+
"model": "qwen/qwen3.8-27b-abliterated-cyber:free"
|
|
83
|
+
},
|
|
84
|
+
"modelRequests": 20,
|
|
85
|
+
"status": "completed",
|
|
86
|
+
"records": [
|
|
87
|
+
{
|
|
88
|
+
"family": "recovery",
|
|
89
|
+
"attempt": 0,
|
|
90
|
+
"arm": "unwound-error",
|
|
91
|
+
"uncertain": false,
|
|
92
|
+
"executionSuccess": false,
|
|
93
|
+
"recoveredValueCorrect": false,
|
|
94
|
+
"selectionAppropriate": true,
|
|
95
|
+
"stoppedOnUnknown": null,
|
|
96
|
+
"effectCount": 1,
|
|
97
|
+
"duplicateEffects": 0,
|
|
98
|
+
"selection": 0,
|
|
99
|
+
"state": "FAILED",
|
|
100
|
+
"elapsedMs": 841
|
|
101
|
+
},
|
|
102
|
+
{
|
|
103
|
+
"family": "recovery",
|
|
104
|
+
"attempt": 0,
|
|
105
|
+
"arm": "live-restart",
|
|
106
|
+
"uncertain": false,
|
|
107
|
+
"executionSuccess": true,
|
|
108
|
+
"recoveredValueCorrect": true,
|
|
109
|
+
"selectionAppropriate": true,
|
|
110
|
+
"stoppedOnUnknown": null,
|
|
111
|
+
"effectCount": 1,
|
|
112
|
+
"duplicateEffects": 0,
|
|
113
|
+
"selection": 0,
|
|
114
|
+
"state": "SUCCEEDED",
|
|
115
|
+
"elapsedMs": 2003
|
|
116
|
+
},
|
|
117
|
+
{
|
|
118
|
+
"family": "prototype",
|
|
119
|
+
"attempt": 0,
|
|
120
|
+
"arm": "direct",
|
|
121
|
+
"expected": 0,
|
|
122
|
+
"selected": "0",
|
|
123
|
+
"choiceCorrect": true,
|
|
124
|
+
"executionSuccess": true,
|
|
125
|
+
"probeSucceeded": null,
|
|
126
|
+
"inspected": false,
|
|
127
|
+
"workflowSatisfied": null,
|
|
128
|
+
"elapsedMs": 422
|
|
129
|
+
},
|
|
130
|
+
{
|
|
131
|
+
"family": "prototype",
|
|
132
|
+
"attempt": 0,
|
|
133
|
+
"arm": "prototype-inspected",
|
|
134
|
+
"expected": 0,
|
|
135
|
+
"selected": "0",
|
|
136
|
+
"choiceCorrect": true,
|
|
137
|
+
"executionSuccess": true,
|
|
138
|
+
"probeSucceeded": true,
|
|
139
|
+
"inspected": true,
|
|
140
|
+
"workflowSatisfied": true,
|
|
141
|
+
"elapsedMs": 421
|
|
142
|
+
},
|
|
143
|
+
{
|
|
144
|
+
"family": "recovery",
|
|
145
|
+
"attempt": 1,
|
|
146
|
+
"arm": "live-restart",
|
|
147
|
+
"uncertain": true,
|
|
148
|
+
"executionSuccess": false,
|
|
149
|
+
"recoveredValueCorrect": false,
|
|
150
|
+
"selectionAppropriate": true,
|
|
151
|
+
"stoppedOnUnknown": true,
|
|
152
|
+
"effectCount": 1,
|
|
153
|
+
"duplicateEffects": 0,
|
|
154
|
+
"selection": "abstain",
|
|
155
|
+
"state": "FAILED",
|
|
156
|
+
"elapsedMs": 2096
|
|
157
|
+
},
|
|
158
|
+
{
|
|
159
|
+
"family": "recovery",
|
|
160
|
+
"attempt": 1,
|
|
161
|
+
"arm": "unwound-error",
|
|
162
|
+
"uncertain": true,
|
|
163
|
+
"executionSuccess": false,
|
|
164
|
+
"recoveredValueCorrect": false,
|
|
165
|
+
"selectionAppropriate": true,
|
|
166
|
+
"stoppedOnUnknown": true,
|
|
167
|
+
"effectCount": 1,
|
|
168
|
+
"duplicateEffects": 0,
|
|
169
|
+
"selection": "abstain",
|
|
170
|
+
"state": "FAILED",
|
|
171
|
+
"elapsedMs": 412
|
|
172
|
+
},
|
|
173
|
+
{
|
|
174
|
+
"family": "prototype",
|
|
175
|
+
"attempt": 1,
|
|
176
|
+
"arm": "prototype-inspected",
|
|
177
|
+
"expected": 1,
|
|
178
|
+
"selected": "1",
|
|
179
|
+
"choiceCorrect": true,
|
|
180
|
+
"executionSuccess": true,
|
|
181
|
+
"probeSucceeded": true,
|
|
182
|
+
"inspected": true,
|
|
183
|
+
"workflowSatisfied": true,
|
|
184
|
+
"elapsedMs": 431
|
|
185
|
+
},
|
|
186
|
+
{
|
|
187
|
+
"family": "prototype",
|
|
188
|
+
"attempt": 1,
|
|
189
|
+
"arm": "direct",
|
|
190
|
+
"expected": 1,
|
|
191
|
+
"selected": "1",
|
|
192
|
+
"choiceCorrect": true,
|
|
193
|
+
"executionSuccess": true,
|
|
194
|
+
"probeSucceeded": null,
|
|
195
|
+
"inspected": false,
|
|
196
|
+
"workflowSatisfied": null,
|
|
197
|
+
"elapsedMs": 428
|
|
198
|
+
},
|
|
199
|
+
{
|
|
200
|
+
"family": "recovery",
|
|
201
|
+
"attempt": 2,
|
|
202
|
+
"arm": "unwound-error",
|
|
203
|
+
"uncertain": false,
|
|
204
|
+
"executionSuccess": false,
|
|
205
|
+
"recoveredValueCorrect": false,
|
|
206
|
+
"selectionAppropriate": true,
|
|
207
|
+
"stoppedOnUnknown": null,
|
|
208
|
+
"effectCount": 1,
|
|
209
|
+
"duplicateEffects": 0,
|
|
210
|
+
"selection": 0,
|
|
211
|
+
"state": "FAILED",
|
|
212
|
+
"elapsedMs": 423
|
|
213
|
+
},
|
|
214
|
+
{
|
|
215
|
+
"family": "recovery",
|
|
216
|
+
"attempt": 2,
|
|
217
|
+
"arm": "live-restart",
|
|
218
|
+
"uncertain": false,
|
|
219
|
+
"executionSuccess": true,
|
|
220
|
+
"recoveredValueCorrect": true,
|
|
221
|
+
"selectionAppropriate": true,
|
|
222
|
+
"stoppedOnUnknown": null,
|
|
223
|
+
"effectCount": 1,
|
|
224
|
+
"duplicateEffects": 0,
|
|
225
|
+
"selection": 0,
|
|
226
|
+
"state": "SUCCEEDED",
|
|
227
|
+
"elapsedMs": 2065
|
|
228
|
+
},
|
|
229
|
+
{
|
|
230
|
+
"family": "prototype",
|
|
231
|
+
"attempt": 2,
|
|
232
|
+
"arm": "direct",
|
|
233
|
+
"expected": 0,
|
|
234
|
+
"selected": "0",
|
|
235
|
+
"choiceCorrect": true,
|
|
236
|
+
"executionSuccess": true,
|
|
237
|
+
"probeSucceeded": null,
|
|
238
|
+
"inspected": false,
|
|
239
|
+
"workflowSatisfied": null,
|
|
240
|
+
"elapsedMs": 401
|
|
241
|
+
},
|
|
242
|
+
{
|
|
243
|
+
"family": "prototype",
|
|
244
|
+
"attempt": 2,
|
|
245
|
+
"arm": "prototype-inspected",
|
|
246
|
+
"expected": 0,
|
|
247
|
+
"selected": "0",
|
|
248
|
+
"choiceCorrect": true,
|
|
249
|
+
"executionSuccess": true,
|
|
250
|
+
"probeSucceeded": true,
|
|
251
|
+
"inspected": true,
|
|
252
|
+
"workflowSatisfied": true,
|
|
253
|
+
"elapsedMs": 420
|
|
254
|
+
},
|
|
255
|
+
{
|
|
256
|
+
"family": "recovery",
|
|
257
|
+
"attempt": 3,
|
|
258
|
+
"arm": "live-restart",
|
|
259
|
+
"uncertain": true,
|
|
260
|
+
"executionSuccess": false,
|
|
261
|
+
"recoveredValueCorrect": false,
|
|
262
|
+
"selectionAppropriate": true,
|
|
263
|
+
"stoppedOnUnknown": true,
|
|
264
|
+
"effectCount": 1,
|
|
265
|
+
"duplicateEffects": 0,
|
|
266
|
+
"selection": "abstain",
|
|
267
|
+
"state": "FAILED",
|
|
268
|
+
"elapsedMs": 2112
|
|
269
|
+
},
|
|
270
|
+
{
|
|
271
|
+
"family": "recovery",
|
|
272
|
+
"attempt": 3,
|
|
273
|
+
"arm": "unwound-error",
|
|
274
|
+
"uncertain": true,
|
|
275
|
+
"executionSuccess": false,
|
|
276
|
+
"recoveredValueCorrect": false,
|
|
277
|
+
"selectionAppropriate": true,
|
|
278
|
+
"stoppedOnUnknown": true,
|
|
279
|
+
"effectCount": 1,
|
|
280
|
+
"duplicateEffects": 0,
|
|
281
|
+
"selection": "abstain",
|
|
282
|
+
"state": "FAILED",
|
|
283
|
+
"elapsedMs": 397
|
|
284
|
+
},
|
|
285
|
+
{
|
|
286
|
+
"family": "prototype",
|
|
287
|
+
"attempt": 3,
|
|
288
|
+
"arm": "prototype-inspected",
|
|
289
|
+
"expected": 1,
|
|
290
|
+
"selected": "1",
|
|
291
|
+
"choiceCorrect": true,
|
|
292
|
+
"executionSuccess": true,
|
|
293
|
+
"probeSucceeded": true,
|
|
294
|
+
"inspected": true,
|
|
295
|
+
"workflowSatisfied": true,
|
|
296
|
+
"elapsedMs": 420
|
|
297
|
+
},
|
|
298
|
+
{
|
|
299
|
+
"family": "prototype",
|
|
300
|
+
"attempt": 3,
|
|
301
|
+
"arm": "direct",
|
|
302
|
+
"expected": 1,
|
|
303
|
+
"selected": "1",
|
|
304
|
+
"choiceCorrect": true,
|
|
305
|
+
"executionSuccess": true,
|
|
306
|
+
"probeSucceeded": null,
|
|
307
|
+
"inspected": false,
|
|
308
|
+
"workflowSatisfied": null,
|
|
309
|
+
"elapsedMs": 401
|
|
310
|
+
},
|
|
311
|
+
{
|
|
312
|
+
"family": "recovery",
|
|
313
|
+
"attempt": 4,
|
|
314
|
+
"arm": "unwound-error",
|
|
315
|
+
"uncertain": false,
|
|
316
|
+
"executionSuccess": false,
|
|
317
|
+
"recoveredValueCorrect": false,
|
|
318
|
+
"selectionAppropriate": true,
|
|
319
|
+
"stoppedOnUnknown": null,
|
|
320
|
+
"effectCount": 1,
|
|
321
|
+
"duplicateEffects": 0,
|
|
322
|
+
"selection": 0,
|
|
323
|
+
"state": "FAILED",
|
|
324
|
+
"elapsedMs": 543
|
|
325
|
+
},
|
|
326
|
+
{
|
|
327
|
+
"family": "recovery",
|
|
328
|
+
"attempt": 4,
|
|
329
|
+
"arm": "live-restart",
|
|
330
|
+
"uncertain": false,
|
|
331
|
+
"executionSuccess": true,
|
|
332
|
+
"recoveredValueCorrect": true,
|
|
333
|
+
"selectionAppropriate": true,
|
|
334
|
+
"stoppedOnUnknown": null,
|
|
335
|
+
"effectCount": 1,
|
|
336
|
+
"duplicateEffects": 0,
|
|
337
|
+
"selection": 0,
|
|
338
|
+
"state": "SUCCEEDED",
|
|
339
|
+
"elapsedMs": 2021
|
|
340
|
+
},
|
|
341
|
+
{
|
|
342
|
+
"family": "prototype",
|
|
343
|
+
"attempt": 4,
|
|
344
|
+
"arm": "direct",
|
|
345
|
+
"expected": 0,
|
|
346
|
+
"selected": "0",
|
|
347
|
+
"choiceCorrect": true,
|
|
348
|
+
"executionSuccess": true,
|
|
349
|
+
"probeSucceeded": null,
|
|
350
|
+
"inspected": false,
|
|
351
|
+
"workflowSatisfied": null,
|
|
352
|
+
"elapsedMs": 426
|
|
353
|
+
},
|
|
354
|
+
{
|
|
355
|
+
"family": "prototype",
|
|
356
|
+
"attempt": 4,
|
|
357
|
+
"arm": "prototype-inspected",
|
|
358
|
+
"expected": 0,
|
|
359
|
+
"selected": "0",
|
|
360
|
+
"choiceCorrect": true,
|
|
361
|
+
"executionSuccess": true,
|
|
362
|
+
"probeSucceeded": true,
|
|
363
|
+
"inspected": true,
|
|
364
|
+
"workflowSatisfied": true,
|
|
365
|
+
"elapsedMs": 418
|
|
366
|
+
}
|
|
367
|
+
],
|
|
368
|
+
"limitations": [
|
|
369
|
+
"Five interleaved runs per arm; selected synthetic finite choices only. No general quality or superiority claim.",
|
|
370
|
+
"Recovery uses a harness decisionCall backed by the saved ordinary model adapter, not the deployed typed-decision service or native UI.",
|
|
371
|
+
"Prototype workflow is scripted: successful prototype:true evaluation and full saved-result inspection before model choice. Autonomous tool-use is unmeasured.",
|
|
372
|
+
"Source worker only; installed/running user processes are not changed. Latency includes model/worker path and excludes first worker compilation."
|
|
373
|
+
],
|
|
374
|
+
"budget": {
|
|
375
|
+
"maxRequests": 20,
|
|
376
|
+
"maxOutputTokens": 256,
|
|
377
|
+
"maxDurationMs": 600000
|
|
378
|
+
},
|
|
379
|
+
"configurationAndCredentialsUnchanged": true,
|
|
380
|
+
"sourceHashes": {
|
|
381
|
+
"lisp/tools.lisp": "a16bd242eab2bce839ab1ee518c34654344571951967a0bea5c3d7b0cc39b193",
|
|
382
|
+
"src/dsh/lisp/recovery.ts": "94215c7f768142e4d7f6ef87e9eeaf1142a9ed5c0e44f093b04601d14dfc0388",
|
|
383
|
+
"src/dsh/lisp/manager.ts": "e2e74bb7ccc8875fa277878d68600569bd1c710300501899bef8366993c39af6",
|
|
384
|
+
"src/dsh/lisp/worker.ts": "cabfd5db7bd4df850b0fb851d45b18cb4b824a6b84b68cc70ab068aec9783edb",
|
|
385
|
+
"scripts/run-lisp-recovery-evaluation.mjs": "b66985772c52e1576887861be00f26c42dcc9c0f904ef1406cfe04cc6e340901"
|
|
386
|
+
},
|
|
387
|
+
"runtime": {
|
|
388
|
+
"node": "v26.5.0",
|
|
389
|
+
"platform": "darwin",
|
|
390
|
+
"architecture": "arm64"
|
|
391
|
+
},
|
|
392
|
+
"compilation": {
|
|
393
|
+
"state": "ready",
|
|
394
|
+
"key": "b83d85fb817a579ba6cb1e1ee9e3569ac7eb198d50e771f20c0be17b1f5007d7",
|
|
395
|
+
"reused": false,
|
|
396
|
+
"prepareMs": 6947
|
|
397
|
+
}
|
|
398
|
+
},
|
|
399
|
+
"typedDecisions": {
|
|
400
|
+
"version": 1,
|
|
401
|
+
"scope": "public-typed-decisions-live-synthetic",
|
|
402
|
+
"status": "completed",
|
|
403
|
+
"requestedModel": "jev-latest",
|
|
404
|
+
"configurationSource": "profile typedDecisions or shipped default; no user-DB selection read",
|
|
405
|
+
"records": [
|
|
406
|
+
{
|
|
407
|
+
"attempt": 0,
|
|
408
|
+
"uncertain": false,
|
|
409
|
+
"executionSuccess": true,
|
|
410
|
+
"valueCorrect": true,
|
|
411
|
+
"selectionAppropriate": true,
|
|
412
|
+
"stoppedOnUnknown": null,
|
|
413
|
+
"effectCount": 1,
|
|
414
|
+
"duplicateEffects": 0,
|
|
415
|
+
"outcome": "completed",
|
|
416
|
+
"fallbackReason": null,
|
|
417
|
+
"answerStatus": "selected",
|
|
418
|
+
"returnedModel": "jev-1.13.0",
|
|
419
|
+
"usage": {
|
|
420
|
+
"input_tokens": 644,
|
|
421
|
+
"output_tokens": 401
|
|
422
|
+
},
|
|
423
|
+
"elapsedMs": 243
|
|
424
|
+
},
|
|
425
|
+
{
|
|
426
|
+
"attempt": 1,
|
|
427
|
+
"uncertain": true,
|
|
428
|
+
"executionSuccess": false,
|
|
429
|
+
"valueCorrect": false,
|
|
430
|
+
"selectionAppropriate": true,
|
|
431
|
+
"stoppedOnUnknown": true,
|
|
432
|
+
"effectCount": 1,
|
|
433
|
+
"duplicateEffects": 0,
|
|
434
|
+
"outcome": "completed",
|
|
435
|
+
"fallbackReason": null,
|
|
436
|
+
"answerStatus": "abstained",
|
|
437
|
+
"returnedModel": "jev-1.13.0",
|
|
438
|
+
"usage": {
|
|
439
|
+
"input_tokens": 631,
|
|
440
|
+
"output_tokens": 386
|
|
441
|
+
},
|
|
442
|
+
"elapsedMs": 158
|
|
443
|
+
},
|
|
444
|
+
{
|
|
445
|
+
"attempt": 2,
|
|
446
|
+
"uncertain": false,
|
|
447
|
+
"executionSuccess": true,
|
|
448
|
+
"valueCorrect": true,
|
|
449
|
+
"selectionAppropriate": true,
|
|
450
|
+
"stoppedOnUnknown": null,
|
|
451
|
+
"effectCount": 1,
|
|
452
|
+
"duplicateEffects": 0,
|
|
453
|
+
"outcome": "completed",
|
|
454
|
+
"fallbackReason": null,
|
|
455
|
+
"answerStatus": "selected",
|
|
456
|
+
"returnedModel": "jev-1.13.0",
|
|
457
|
+
"usage": {
|
|
458
|
+
"input_tokens": 632,
|
|
459
|
+
"output_tokens": 381
|
|
460
|
+
},
|
|
461
|
+
"elapsedMs": 185
|
|
462
|
+
},
|
|
463
|
+
{
|
|
464
|
+
"attempt": 3,
|
|
465
|
+
"uncertain": true,
|
|
466
|
+
"executionSuccess": false,
|
|
467
|
+
"valueCorrect": false,
|
|
468
|
+
"selectionAppropriate": true,
|
|
469
|
+
"stoppedOnUnknown": true,
|
|
470
|
+
"effectCount": 1,
|
|
471
|
+
"duplicateEffects": 0,
|
|
472
|
+
"outcome": "completed",
|
|
473
|
+
"fallbackReason": null,
|
|
474
|
+
"answerStatus": "abstained",
|
|
475
|
+
"returnedModel": "jev-1.13.0",
|
|
476
|
+
"usage": {
|
|
477
|
+
"input_tokens": 640,
|
|
478
|
+
"output_tokens": 401
|
|
479
|
+
},
|
|
480
|
+
"elapsedMs": 160
|
|
481
|
+
},
|
|
482
|
+
{
|
|
483
|
+
"attempt": 4,
|
|
484
|
+
"uncertain": false,
|
|
485
|
+
"executionSuccess": false,
|
|
486
|
+
"valueCorrect": false,
|
|
487
|
+
"selectionAppropriate": false,
|
|
488
|
+
"stoppedOnUnknown": null,
|
|
489
|
+
"effectCount": 1,
|
|
490
|
+
"duplicateEffects": 0,
|
|
491
|
+
"outcome": "completed",
|
|
492
|
+
"fallbackReason": null,
|
|
493
|
+
"answerStatus": "abstained",
|
|
494
|
+
"returnedModel": "jev-1.13.0",
|
|
495
|
+
"usage": {
|
|
496
|
+
"input_tokens": 641,
|
|
497
|
+
"output_tokens": 396
|
|
498
|
+
},
|
|
499
|
+
"elapsedMs": 151
|
|
500
|
+
}
|
|
501
|
+
],
|
|
502
|
+
"budget": {
|
|
503
|
+
"maxRequests": 5,
|
|
504
|
+
"maxDurationMs": 60000
|
|
505
|
+
},
|
|
506
|
+
"limitations": [
|
|
507
|
+
"Five synthetic cases, not a general quality benchmark.",
|
|
508
|
+
"Real LispManager/worker to DecisionService/TypeSafe serializer, HTTP and result validation. Native UI and installed user process unmeasured."
|
|
509
|
+
],
|
|
510
|
+
"configurationAndCredentialsUnchanged": true,
|
|
511
|
+
"credential": {
|
|
512
|
+
"configured": true,
|
|
513
|
+
"writable": true,
|
|
514
|
+
"source": "file"
|
|
515
|
+
},
|
|
516
|
+
"sourceHashes": {
|
|
517
|
+
"lisp/tools.lisp": "a16bd242eab2bce839ab1ee518c34654344571951967a0bea5c3d7b0cc39b193",
|
|
518
|
+
"src/dsh/lisp/recovery.ts": "94215c7f768142e4d7f6ef87e9eeaf1142a9ed5c0e44f093b04601d14dfc0388",
|
|
519
|
+
"src/dsh/lisp/manager.ts": "e2e74bb7ccc8875fa277878d68600569bd1c710300501899bef8366993c39af6",
|
|
520
|
+
"src/dsh/lisp/worker.ts": "cabfd5db7bd4df850b0fb851d45b18cb4b824a6b84b68cc70ab068aec9783edb",
|
|
521
|
+
"src/dsh/decisions/service.ts": "f7423d0a82b8fab07189f419507f539d53641ac941e99845b902ebc8c89b4f44",
|
|
522
|
+
"src/dsh/decisions/providers.ts": "ac81c87a2a1553bfcd14a173c7060b204ed2133d93889d845f5e45575c61802f",
|
|
523
|
+
"src/dsh/decisions/contracts.ts": "829121e8788ee4cea9f34335985ca368bca638924d04c170a444e41fd9f971b3",
|
|
524
|
+
"scripts/run-lisp-typed-recovery-evaluation.mjs": "43806ec9f61839e6e0da3db9fbf5b52b701ec1466a82f0480535f177392ef0d8"
|
|
525
|
+
},
|
|
526
|
+
"runtime": {
|
|
527
|
+
"node": "v26.5.0",
|
|
528
|
+
"platform": "darwin",
|
|
529
|
+
"architecture": "arm64"
|
|
530
|
+
},
|
|
531
|
+
"compilation": {
|
|
532
|
+
"state": "ready",
|
|
533
|
+
"key": "b83d85fb817a579ba6cb1e1ee9e3569ac7eb198d50e771f20c0be17b1f5007d7",
|
|
534
|
+
"reused": false,
|
|
535
|
+
"prepareMs": 7146
|
|
536
|
+
},
|
|
537
|
+
"modelRequests": 5
|
|
538
|
+
},
|
|
539
|
+
"summary": [
|
|
540
|
+
{
|
|
541
|
+
"family": "recovery",
|
|
542
|
+
"arm": "unwound-error",
|
|
543
|
+
"n": 5,
|
|
544
|
+
"executionSuccess": 0,
|
|
545
|
+
"correct": 0,
|
|
546
|
+
"appropriateSelection": 5,
|
|
547
|
+
"unknownStopped": 2,
|
|
548
|
+
"duplicateCounterEffects": 0,
|
|
549
|
+
"completeInspection": 0,
|
|
550
|
+
"latencyMs": {
|
|
551
|
+
"min": 397,
|
|
552
|
+
"median": 423,
|
|
553
|
+
"max": 841
|
|
554
|
+
}
|
|
555
|
+
},
|
|
556
|
+
{
|
|
557
|
+
"family": "recovery",
|
|
558
|
+
"arm": "live-restart",
|
|
559
|
+
"n": 5,
|
|
560
|
+
"executionSuccess": 3,
|
|
561
|
+
"correct": 3,
|
|
562
|
+
"appropriateSelection": 5,
|
|
563
|
+
"unknownStopped": 2,
|
|
564
|
+
"duplicateCounterEffects": 0,
|
|
565
|
+
"completeInspection": 0,
|
|
566
|
+
"latencyMs": {
|
|
567
|
+
"min": 2003,
|
|
568
|
+
"median": 2065,
|
|
569
|
+
"max": 2112
|
|
570
|
+
}
|
|
571
|
+
},
|
|
572
|
+
{
|
|
573
|
+
"family": "prototype",
|
|
574
|
+
"arm": "direct",
|
|
575
|
+
"n": 5,
|
|
576
|
+
"executionSuccess": 5,
|
|
577
|
+
"correct": 5,
|
|
578
|
+
"appropriateSelection": 0,
|
|
579
|
+
"unknownStopped": 0,
|
|
580
|
+
"duplicateCounterEffects": 0,
|
|
581
|
+
"completeInspection": 0,
|
|
582
|
+
"latencyMs": {
|
|
583
|
+
"min": 401,
|
|
584
|
+
"median": 422,
|
|
585
|
+
"max": 428
|
|
586
|
+
}
|
|
587
|
+
},
|
|
588
|
+
{
|
|
589
|
+
"family": "prototype",
|
|
590
|
+
"arm": "prototype-inspected",
|
|
591
|
+
"n": 5,
|
|
592
|
+
"executionSuccess": 5,
|
|
593
|
+
"correct": 5,
|
|
594
|
+
"appropriateSelection": 0,
|
|
595
|
+
"unknownStopped": 0,
|
|
596
|
+
"duplicateCounterEffects": 0,
|
|
597
|
+
"completeInspection": 5,
|
|
598
|
+
"latencyMs": {
|
|
599
|
+
"min": 418,
|
|
600
|
+
"median": 420,
|
|
601
|
+
"max": 431
|
|
602
|
+
}
|
|
603
|
+
}
|
|
604
|
+
],
|
|
605
|
+
"generatedProtectedArtifact": {
|
|
606
|
+
"manifest": {
|
|
607
|
+
"format": 1,
|
|
608
|
+
"key": "e50c3508b41c6e6969cef7bdd0281f8da376c5cb6f164e29befa45e3fbc9a075",
|
|
609
|
+
"hash": "5c1ff482dbaf6f0fb802f4b5b27d9199926bb54a583d1b0c35058640d8d6a25c",
|
|
610
|
+
"bytes": 6794503
|
|
611
|
+
},
|
|
612
|
+
"executedValue": 42,
|
|
613
|
+
"generation": "dc9ea2d7-11d9-46bf-b6e2-b49fe50b2694",
|
|
614
|
+
"protected": true,
|
|
615
|
+
"artifactInstalled": false
|
|
616
|
+
},
|
|
617
|
+
"exploratoryMeasurements": [
|
|
618
|
+
{
|
|
619
|
+
"modelRequests": 20,
|
|
620
|
+
"harnessValid": false,
|
|
621
|
+
"reason": "Prototype inspection used an invalid page limit; not evidence of prototype workflow.",
|
|
622
|
+
"sourceHashes": null
|
|
623
|
+
},
|
|
624
|
+
{
|
|
625
|
+
"modelRequests": 20,
|
|
626
|
+
"harnessValid": true,
|
|
627
|
+
"reason": "Earlier implementation revision; superseded by final source-bound measurement.",
|
|
628
|
+
"sourceHashes": {
|
|
629
|
+
"lisp/tools.lisp": "6e7d30fa01ca1ad0ec95305c6043bd5d9e31965680b7ae3665ad7663e34e9952",
|
|
630
|
+
"src/dsh/lisp/recovery.ts": "751f55d9ed824f7ec4c74689990fd7623896b50b6bf2585153e0aaaaf9bfe301",
|
|
631
|
+
"src/dsh/lisp/manager.ts": "571f173135bf3b006e49e28e0d07a606b10ce1186d9eacf1b175ae00d2d56572",
|
|
632
|
+
"src/dsh/lisp/worker.ts": "cabfd5db7bd4df850b0fb851d45b18cb4b824a6b84b68cc70ab068aec9783edb",
|
|
633
|
+
"scripts/run-lisp-recovery-evaluation.mjs": "b66985772c52e1576887861be00f26c42dcc9c0f904ef1406cfe04cc6e340901"
|
|
634
|
+
}
|
|
635
|
+
},
|
|
636
|
+
{
|
|
637
|
+
"modelRequests": 20,
|
|
638
|
+
"harnessValid": true,
|
|
639
|
+
"reason": "Earlier implementation revision; superseded by final source-bound measurement.",
|
|
640
|
+
"sourceHashes": {
|
|
641
|
+
"lisp/tools.lisp": "a16bd242eab2bce839ab1ee518c34654344571951967a0bea5c3d7b0cc39b193",
|
|
642
|
+
"src/dsh/lisp/recovery.ts": "94215c7f768142e4d7f6ef87e9eeaf1142a9ed5c0e44f093b04601d14dfc0388",
|
|
643
|
+
"src/dsh/lisp/manager.ts": "56fdb44984d951bed6b4b5f86bf65a13027da721c6d4c0ed2bb171bbf383cb52",
|
|
644
|
+
"src/dsh/lisp/worker.ts": "cabfd5db7bd4df850b0fb851d45b18cb4b824a6b84b68cc70ab068aec9783edb",
|
|
645
|
+
"scripts/run-lisp-recovery-evaluation.mjs": "b66985772c52e1576887861be00f26c42dcc9c0f904ef1406cfe04cc6e340901"
|
|
646
|
+
}
|
|
647
|
+
},
|
|
648
|
+
{
|
|
649
|
+
"modelRequests": 5,
|
|
650
|
+
"harnessValid": true,
|
|
651
|
+
"reason": "Earlier implementation revision; superseded by final source-bound measurement.",
|
|
652
|
+
"sourceHashes": {
|
|
653
|
+
"lisp/tools.lisp": "a16bd242eab2bce839ab1ee518c34654344571951967a0bea5c3d7b0cc39b193",
|
|
654
|
+
"src/dsh/lisp/recovery.ts": "94215c7f768142e4d7f6ef87e9eeaf1142a9ed5c0e44f093b04601d14dfc0388",
|
|
655
|
+
"src/dsh/lisp/manager.ts": "56fdb44984d951bed6b4b5f86bf65a13027da721c6d4c0ed2bb171bbf383cb52",
|
|
656
|
+
"src/dsh/lisp/worker.ts": "cabfd5db7bd4df850b0fb851d45b18cb4b824a6b84b68cc70ab068aec9783edb",
|
|
657
|
+
"src/dsh/decisions/service.ts": "f7423d0a82b8fab07189f419507f539d53641ac941e99845b902ebc8c89b4f44",
|
|
658
|
+
"src/dsh/decisions/providers.ts": "ac81c87a2a1553bfcd14a173c7060b204ed2133d93889d845f5e45575c61802f",
|
|
659
|
+
"src/dsh/decisions/contracts.ts": "829121e8788ee4cea9f34335985ca368bca638924d04c170a444e41fd9f971b3",
|
|
660
|
+
"scripts/run-lisp-typed-recovery-evaluation.mjs": "43806ec9f61839e6e0da3db9fbf5b52b701ec1466a82f0480535f177392ef0d8"
|
|
661
|
+
}
|
|
662
|
+
}
|
|
663
|
+
],
|
|
664
|
+
"evaluationRequestAccounting": {
|
|
665
|
+
"final": 25,
|
|
666
|
+
"earlier": 65,
|
|
667
|
+
"total": 90,
|
|
668
|
+
"readiness": "Two separate startup probes; one unusable response under restricted execution, one confirmed synthetic 42. Excluded from quality results."
|
|
669
|
+
},
|
|
670
|
+
"runtimeScope": {
|
|
671
|
+
"sourceTested": true,
|
|
672
|
+
"temporaryGeneratedWorkerTested": true,
|
|
673
|
+
"installedOrUserProcessUpdated": false,
|
|
674
|
+
"fullNativeUISessionTested": false
|
|
675
|
+
},
|
|
676
|
+
"baselineEnvironmentFailure": {
|
|
677
|
+
"tests": [
|
|
678
|
+
"project-workflow.test.ts",
|
|
679
|
+
"protected-python-capability.test.ts",
|
|
680
|
+
"runtime.test.ts"
|
|
681
|
+
],
|
|
682
|
+
"cause": "/usr/bin/python3 invokes xcrun, whose libxcrun under /Applications/Xcode.app is outside the existing protected read roots. Baseline HEAD and candidate both fail these same three tests.",
|
|
683
|
+
"sandboxSourceMatchesBase": true,
|
|
684
|
+
"baselineBuild": "git archive HEAD in /tmp, shared read-only installed dependencies, tsc -p tsconfig.build.json passed",
|
|
685
|
+
"settingsChanged": false
|
|
686
|
+
},
|
|
687
|
+
"environment": {
|
|
688
|
+
"node": "v26.5.0",
|
|
689
|
+
"sbcl": "2.6.8",
|
|
690
|
+
"platform": "darwin",
|
|
691
|
+
"architecture": "arm64"
|
|
692
|
+
}
|
|
693
|
+
}
|