@openpond/evals 0.6.0 → 0.7.1

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 (96) hide show
  1. package/LEARNING.md +120 -0
  2. package/README.md +2 -0
  3. package/dist/graders.js +26 -5
  4. package/dist/index.js +3 -0
  5. package/dist/javascript-verifier-contract.js +7 -0
  6. package/dist/javascript-verifier-node.js +56 -0
  7. package/dist/javascript-verifier-worker-source.js +1 -0
  8. package/dist/javascript-verifier-worker.js +6 -0
  9. package/dist/javascript-verifier.js +64 -0
  10. package/dist/learning/admission.js +209 -0
  11. package/dist/learning/assets.js +37 -0
  12. package/dist/learning/contracts.js +267 -0
  13. package/dist/learning/errors.js +12 -0
  14. package/dist/learning/grade-worker.js +99 -0
  15. package/dist/learning/index.js +9 -0
  16. package/dist/learning/operations.js +33 -0
  17. package/dist/learning/repository.js +48 -0
  18. package/dist/learning/service.js +377 -0
  19. package/dist/learning/transport.js +35 -0
  20. package/dist/rewards.js +230 -0
  21. package/dist/task-schema-meta-validator.js +2 -0
  22. package/dist/task-schema-validation.js +113 -0
  23. package/dist/task-schema.js +4 -0
  24. package/dist/task-value-validator.js +37 -0
  25. package/dist/tasksets.js +3 -0
  26. package/dist/telemetry-catalog.js +1 -1
  27. package/dist/types/builtin-benchmarks/harness-refiner.d.ts +7 -0
  28. package/dist/types/builtin-benchmarks/harness-refiner.d.ts.map +1 -1
  29. package/dist/types/conformance.d.ts +14 -0
  30. package/dist/types/conformance.d.ts.map +1 -1
  31. package/dist/types/execution-contracts.d.ts +14 -0
  32. package/dist/types/execution-contracts.d.ts.map +1 -1
  33. package/dist/types/graders.d.ts.map +1 -1
  34. package/dist/types/index.d.ts +3 -0
  35. package/dist/types/index.d.ts.map +1 -1
  36. package/dist/types/javascript-verifier-contract.d.ts +9 -0
  37. package/dist/types/javascript-verifier-contract.d.ts.map +1 -0
  38. package/dist/types/javascript-verifier-node.d.ts +5 -0
  39. package/dist/types/javascript-verifier-node.d.ts.map +1 -0
  40. package/dist/types/javascript-verifier-worker-source.d.ts +2 -0
  41. package/dist/types/javascript-verifier-worker.d.ts +2 -0
  42. package/dist/types/javascript-verifier-worker.d.ts.map +1 -0
  43. package/dist/types/javascript-verifier.d.ts +15 -0
  44. package/dist/types/javascript-verifier.d.ts.map +1 -0
  45. package/dist/types/learning/admission.d.ts +335 -0
  46. package/dist/types/learning/admission.d.ts.map +1 -0
  47. package/dist/types/learning/assets.d.ts +49 -0
  48. package/dist/types/learning/assets.d.ts.map +1 -0
  49. package/dist/types/learning/contracts.d.ts +2149 -0
  50. package/dist/types/learning/contracts.d.ts.map +1 -0
  51. package/dist/types/learning/errors.d.ts +8 -0
  52. package/dist/types/learning/errors.d.ts.map +1 -0
  53. package/dist/types/learning/grade-worker.d.ts +31 -0
  54. package/dist/types/learning/grade-worker.d.ts.map +1 -0
  55. package/dist/types/learning/index.d.ts +10 -0
  56. package/dist/types/learning/index.d.ts.map +1 -0
  57. package/dist/types/learning/operations.d.ts +2061 -0
  58. package/dist/types/learning/operations.d.ts.map +1 -0
  59. package/dist/types/learning/repository.d.ts +1143 -0
  60. package/dist/types/learning/repository.d.ts.map +1 -0
  61. package/dist/types/learning/service.d.ts +36 -0
  62. package/dist/types/learning/service.d.ts.map +1 -0
  63. package/dist/types/learning/transport.d.ts +2173 -0
  64. package/dist/types/learning/transport.d.ts.map +1 -0
  65. package/dist/types/preferences.d.ts +3 -3
  66. package/dist/types/review-conformance.d.ts +5 -5
  67. package/dist/types/rewards.d.ts +611 -0
  68. package/dist/types/rewards.d.ts.map +1 -0
  69. package/dist/types/task-schema-meta-validator.d.ts +3 -0
  70. package/dist/types/task-schema-validation.d.ts +18 -0
  71. package/dist/types/task-schema-validation.d.ts.map +1 -0
  72. package/dist/types/task-schema.d.ts +3 -0
  73. package/dist/types/task-schema.d.ts.map +1 -0
  74. package/dist/types/task-value-validator.d.ts +3 -0
  75. package/dist/types/task-value-validator.d.ts.map +1 -0
  76. package/dist/types/tasksets.d.ts +28 -0
  77. package/dist/types/tasksets.d.ts.map +1 -1
  78. package/package.json +30 -3
  79. package/schemas/learning/v1/asset.schema.json +89 -0
  80. package/schemas/learning/v1/batch.schema.json +132 -0
  81. package/schemas/learning/v1/binding.schema.json +207 -0
  82. package/schemas/learning/v1/command-request.schema.json +2414 -0
  83. package/schemas/learning/v1/decision.schema.json +440 -0
  84. package/schemas/learning/v1/definition.schema.json +397 -0
  85. package/schemas/learning/v1/evidence-inspection.schema.json +106 -0
  86. package/schemas/learning/v1/evidence.schema.json +317 -0
  87. package/schemas/learning/v1/example-submission.schema.json +253 -0
  88. package/schemas/learning/v1/feedback-submission.schema.json +114 -0
  89. package/schemas/learning/v1/feedback.schema.json +233 -0
  90. package/schemas/learning/v1/grade.schema.json +412 -0
  91. package/schemas/learning/v1/iteration.schema.json +236 -0
  92. package/schemas/learning/v1/package.schema.json +776 -0
  93. package/schemas/learning/v1/policy.schema.json +373 -0
  94. package/schemas/learning/v1/read-request.schema.json +142 -0
  95. package/schemas/learning/v1/reward.schema.json +302 -0
  96. package/schemas/learning/v1/source.schema.json +198 -0
@@ -0,0 +1,233 @@
1
+ {
2
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
3
+ "type": "object",
4
+ "properties": {
5
+ "schemaVersion": {
6
+ "type": "string",
7
+ "const": "openpond.taskFeedbackRecord.v1"
8
+ },
9
+ "id": {
10
+ "$ref": "#/$defs/__schema0"
11
+ },
12
+ "submission": {
13
+ "type": "object",
14
+ "properties": {
15
+ "schemaVersion": {
16
+ "type": "string",
17
+ "const": "openpond.taskFeedback.v1"
18
+ },
19
+ "sourceId": {
20
+ "$ref": "#/$defs/__schema0"
21
+ },
22
+ "idempotencyKey": {
23
+ "$ref": "#/$defs/__schema0"
24
+ },
25
+ "exampleId": {
26
+ "$ref": "#/$defs/__schema0"
27
+ },
28
+ "attemptId": {
29
+ "$ref": "#/$defs/__schema0"
30
+ },
31
+ "expectedEvidenceHash": {
32
+ "anyOf": [
33
+ {
34
+ "$ref": "#/$defs/__schema1"
35
+ },
36
+ {
37
+ "type": "null"
38
+ }
39
+ ]
40
+ },
41
+ "occurredAt": {
42
+ "$ref": "#/$defs/__schema2"
43
+ },
44
+ "kind": {
45
+ "type": "string",
46
+ "enum": [
47
+ "outcome",
48
+ "target_correction",
49
+ "ground_truth_correction",
50
+ "input_correction",
51
+ "family_resolution"
52
+ ]
53
+ },
54
+ "value": {
55
+ "type": "object",
56
+ "propertyNames": {
57
+ "type": "string"
58
+ },
59
+ "additionalProperties": {
60
+ "$ref": "#/$defs/__schema3"
61
+ }
62
+ },
63
+ "note": {
64
+ "type": "string",
65
+ "maxLength": 20000
66
+ }
67
+ },
68
+ "required": [
69
+ "schemaVersion",
70
+ "sourceId",
71
+ "idempotencyKey",
72
+ "exampleId",
73
+ "attemptId",
74
+ "expectedEvidenceHash",
75
+ "occurredAt",
76
+ "kind",
77
+ "value",
78
+ "note"
79
+ ],
80
+ "additionalProperties": false
81
+ },
82
+ "status": {
83
+ "type": "string",
84
+ "enum": [
85
+ "pending_example",
86
+ "pending_review",
87
+ "applied",
88
+ "superseded",
89
+ "rejected"
90
+ ]
91
+ },
92
+ "evidence": {
93
+ "anyOf": [
94
+ {
95
+ "$ref": "#/$defs/__schema4"
96
+ },
97
+ {
98
+ "type": "null"
99
+ }
100
+ ]
101
+ },
102
+ "createdAt": {
103
+ "$ref": "#/$defs/__schema2"
104
+ },
105
+ "revision": {
106
+ "type": "integer",
107
+ "exclusiveMinimum": 0,
108
+ "maximum": 9007199254740991
109
+ },
110
+ "review": {
111
+ "default": null,
112
+ "anyOf": [
113
+ {
114
+ "type": "object",
115
+ "properties": {
116
+ "actorId": {
117
+ "$ref": "#/$defs/__schema0"
118
+ },
119
+ "decision": {
120
+ "anyOf": [
121
+ {
122
+ "$ref": "#/$defs/__schema4"
123
+ },
124
+ {
125
+ "type": "null"
126
+ }
127
+ ]
128
+ },
129
+ "note": {
130
+ "type": "string",
131
+ "maxLength": 20000
132
+ },
133
+ "resolvedAt": {
134
+ "$ref": "#/$defs/__schema2"
135
+ }
136
+ },
137
+ "required": [
138
+ "actorId",
139
+ "decision",
140
+ "note",
141
+ "resolvedAt"
142
+ ],
143
+ "additionalProperties": false
144
+ },
145
+ {
146
+ "type": "null"
147
+ }
148
+ ]
149
+ }
150
+ },
151
+ "required": [
152
+ "schemaVersion",
153
+ "id",
154
+ "submission",
155
+ "status",
156
+ "evidence",
157
+ "createdAt",
158
+ "revision",
159
+ "review"
160
+ ],
161
+ "additionalProperties": false,
162
+ "$defs": {
163
+ "__schema0": {
164
+ "type": "string",
165
+ "minLength": 1,
166
+ "maxLength": 240
167
+ },
168
+ "__schema1": {
169
+ "type": "string",
170
+ "pattern": "^[a-f0-9]{64}$"
171
+ },
172
+ "__schema2": {
173
+ "type": "string",
174
+ "format": "date-time",
175
+ "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
176
+ },
177
+ "__schema3": {
178
+ "anyOf": [
179
+ {
180
+ "type": "string"
181
+ },
182
+ {
183
+ "type": "number"
184
+ },
185
+ {
186
+ "type": "boolean"
187
+ },
188
+ {
189
+ "type": "null"
190
+ },
191
+ {
192
+ "type": "array",
193
+ "items": {
194
+ "$ref": "#/$defs/__schema3"
195
+ }
196
+ },
197
+ {
198
+ "type": "object",
199
+ "propertyNames": {
200
+ "type": "string"
201
+ },
202
+ "additionalProperties": {
203
+ "$ref": "#/$defs/__schema3"
204
+ }
205
+ }
206
+ ]
207
+ },
208
+ "__schema4": {
209
+ "type": "object",
210
+ "properties": {
211
+ "id": {
212
+ "$ref": "#/$defs/__schema0"
213
+ },
214
+ "contentHash": {
215
+ "$ref": "#/$defs/__schema1"
216
+ },
217
+ "revision": {
218
+ "type": "integer",
219
+ "exclusiveMinimum": 0,
220
+ "maximum": 9007199254740991
221
+ }
222
+ },
223
+ "required": [
224
+ "id",
225
+ "contentHash",
226
+ "revision"
227
+ ],
228
+ "additionalProperties": false
229
+ }
230
+ },
231
+ "$id": "urn:openpond:learning:v1:feedback",
232
+ "$comment": "Generated from @openpond/evals. Cross-resource identity, authorization, idempotency, admission, grading and split constraints are enforced by the shared domain service in addition to this structural schema."
233
+ }
@@ -0,0 +1,412 @@
1
+ {
2
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
3
+ "type": "object",
4
+ "properties": {
5
+ "schemaVersion": {
6
+ "type": "string",
7
+ "const": "openpond.taskGradeRun.v1"
8
+ },
9
+ "id": {
10
+ "$ref": "#/$defs/__schema0"
11
+ },
12
+ "revision": {
13
+ "type": "integer",
14
+ "exclusiveMinimum": 0,
15
+ "maximum": 9007199254740991
16
+ },
17
+ "evidence": {
18
+ "$ref": "#/$defs/__schema1"
19
+ },
20
+ "binding": {
21
+ "$ref": "#/$defs/__schema1"
22
+ },
23
+ "target": {
24
+ "type": "string",
25
+ "enum": [
26
+ "observed",
27
+ "proposed_target"
28
+ ]
29
+ },
30
+ "output": {
31
+ "type": "object",
32
+ "propertyNames": {
33
+ "type": "string"
34
+ },
35
+ "additionalProperties": {
36
+ "$ref": "#/$defs/__schema3"
37
+ }
38
+ },
39
+ "status": {
40
+ "type": "string",
41
+ "enum": [
42
+ "queued",
43
+ "running",
44
+ "completed",
45
+ "failed",
46
+ "cancelling",
47
+ "cancelled"
48
+ ]
49
+ },
50
+ "composition": {
51
+ "anyOf": [
52
+ {
53
+ "type": "object",
54
+ "properties": {
55
+ "schemaVersion": {
56
+ "type": "string",
57
+ "const": "openpond.rewardComposition.v1"
58
+ },
59
+ "binding": {
60
+ "$ref": "#/$defs/__schema1"
61
+ },
62
+ "taskHash": {
63
+ "$ref": "#/$defs/__schema2"
64
+ },
65
+ "outputHash": {
66
+ "$ref": "#/$defs/__schema2"
67
+ },
68
+ "results": {
69
+ "minItems": 1,
70
+ "maxItems": 100,
71
+ "type": "array",
72
+ "items": {
73
+ "$ref": "#/$defs/__schema4"
74
+ }
75
+ },
76
+ "training": {
77
+ "type": "object",
78
+ "properties": {
79
+ "status": {
80
+ "type": "string",
81
+ "enum": [
82
+ "scored",
83
+ "unscorable",
84
+ "not_configured"
85
+ ]
86
+ },
87
+ "score": {
88
+ "anyOf": [
89
+ {
90
+ "type": "number",
91
+ "minimum": 0,
92
+ "maximum": 1
93
+ },
94
+ {
95
+ "type": "null"
96
+ }
97
+ ]
98
+ },
99
+ "passed": {
100
+ "anyOf": [
101
+ {
102
+ "type": "boolean"
103
+ },
104
+ {
105
+ "type": "null"
106
+ }
107
+ ]
108
+ }
109
+ },
110
+ "required": [
111
+ "status",
112
+ "score",
113
+ "passed"
114
+ ],
115
+ "additionalProperties": false
116
+ },
117
+ "evaluation": {
118
+ "type": "object",
119
+ "properties": {
120
+ "status": {
121
+ "type": "string",
122
+ "enum": [
123
+ "scored",
124
+ "unscorable",
125
+ "not_configured"
126
+ ]
127
+ },
128
+ "score": {
129
+ "anyOf": [
130
+ {
131
+ "type": "number",
132
+ "minimum": 0,
133
+ "maximum": 1
134
+ },
135
+ {
136
+ "type": "null"
137
+ }
138
+ ]
139
+ },
140
+ "passed": {
141
+ "anyOf": [
142
+ {
143
+ "type": "boolean"
144
+ },
145
+ {
146
+ "type": "null"
147
+ }
148
+ ]
149
+ }
150
+ },
151
+ "required": [
152
+ "status",
153
+ "score",
154
+ "passed"
155
+ ],
156
+ "additionalProperties": false
157
+ },
158
+ "contentHash": {
159
+ "$ref": "#/$defs/__schema2"
160
+ }
161
+ },
162
+ "required": [
163
+ "schemaVersion",
164
+ "binding",
165
+ "taskHash",
166
+ "outputHash",
167
+ "results",
168
+ "training",
169
+ "evaluation",
170
+ "contentHash"
171
+ ],
172
+ "additionalProperties": false
173
+ },
174
+ {
175
+ "type": "null"
176
+ }
177
+ ]
178
+ },
179
+ "leaseOwner": {
180
+ "anyOf": [
181
+ {
182
+ "$ref": "#/$defs/__schema0"
183
+ },
184
+ {
185
+ "type": "null"
186
+ }
187
+ ]
188
+ },
189
+ "leaseExpiresAt": {
190
+ "anyOf": [
191
+ {
192
+ "$ref": "#/$defs/__schema5"
193
+ },
194
+ {
195
+ "type": "null"
196
+ }
197
+ ]
198
+ },
199
+ "attemptCount": {
200
+ "type": "integer",
201
+ "minimum": 0,
202
+ "maximum": 9007199254740991
203
+ },
204
+ "timeoutMs": {
205
+ "type": "integer",
206
+ "minimum": 100,
207
+ "maximum": 300000
208
+ },
209
+ "maximumSpendUsd": {
210
+ "type": "number",
211
+ "minimum": 0,
212
+ "maximum": 1000
213
+ },
214
+ "failure": {
215
+ "anyOf": [
216
+ {
217
+ "type": "string",
218
+ "maxLength": 20000
219
+ },
220
+ {
221
+ "type": "null"
222
+ }
223
+ ]
224
+ },
225
+ "createdAt": {
226
+ "$ref": "#/$defs/__schema5"
227
+ },
228
+ "updatedAt": {
229
+ "$ref": "#/$defs/__schema5"
230
+ }
231
+ },
232
+ "required": [
233
+ "schemaVersion",
234
+ "id",
235
+ "revision",
236
+ "evidence",
237
+ "binding",
238
+ "target",
239
+ "output",
240
+ "status",
241
+ "composition",
242
+ "leaseOwner",
243
+ "leaseExpiresAt",
244
+ "attemptCount",
245
+ "timeoutMs",
246
+ "maximumSpendUsd",
247
+ "failure",
248
+ "createdAt",
249
+ "updatedAt"
250
+ ],
251
+ "additionalProperties": false,
252
+ "$defs": {
253
+ "__schema0": {
254
+ "type": "string",
255
+ "minLength": 1,
256
+ "maxLength": 240
257
+ },
258
+ "__schema1": {
259
+ "type": "object",
260
+ "properties": {
261
+ "id": {
262
+ "$ref": "#/$defs/__schema0"
263
+ },
264
+ "contentHash": {
265
+ "$ref": "#/$defs/__schema2"
266
+ },
267
+ "revision": {
268
+ "type": "integer",
269
+ "exclusiveMinimum": 0,
270
+ "maximum": 9007199254740991
271
+ }
272
+ },
273
+ "required": [
274
+ "id",
275
+ "contentHash",
276
+ "revision"
277
+ ],
278
+ "additionalProperties": false
279
+ },
280
+ "__schema2": {
281
+ "type": "string",
282
+ "pattern": "^[a-f0-9]{64}$"
283
+ },
284
+ "__schema3": {
285
+ "anyOf": [
286
+ {
287
+ "type": "string"
288
+ },
289
+ {
290
+ "type": "number"
291
+ },
292
+ {
293
+ "type": "boolean"
294
+ },
295
+ {
296
+ "type": "null"
297
+ },
298
+ {
299
+ "type": "array",
300
+ "items": {
301
+ "$ref": "#/$defs/__schema3"
302
+ }
303
+ },
304
+ {
305
+ "type": "object",
306
+ "propertyNames": {
307
+ "type": "string"
308
+ },
309
+ "additionalProperties": {
310
+ "$ref": "#/$defs/__schema3"
311
+ }
312
+ }
313
+ ]
314
+ },
315
+ "__schema4": {
316
+ "type": "object",
317
+ "properties": {
318
+ "graderId": {
319
+ "$ref": "#/$defs/__schema0"
320
+ },
321
+ "reward": {
322
+ "$ref": "#/$defs/__schema1"
323
+ },
324
+ "role": {
325
+ "type": "string",
326
+ "enum": [
327
+ "training",
328
+ "evaluation"
329
+ ]
330
+ },
331
+ "status": {
332
+ "type": "string",
333
+ "enum": [
334
+ "scored",
335
+ "pending",
336
+ "unavailable",
337
+ "failed"
338
+ ]
339
+ },
340
+ "rawScore": {
341
+ "anyOf": [
342
+ {
343
+ "type": "number"
344
+ },
345
+ {
346
+ "type": "null"
347
+ }
348
+ ]
349
+ },
350
+ "normalizedScore": {
351
+ "anyOf": [
352
+ {
353
+ "type": "number",
354
+ "minimum": 0,
355
+ "maximum": 1
356
+ },
357
+ {
358
+ "type": "null"
359
+ }
360
+ ]
361
+ },
362
+ "passed": {
363
+ "anyOf": [
364
+ {
365
+ "type": "boolean"
366
+ },
367
+ {
368
+ "type": "null"
369
+ }
370
+ ]
371
+ },
372
+ "evidenceHashes": {
373
+ "maxItems": 1000,
374
+ "type": "array",
375
+ "items": {
376
+ "$ref": "#/$defs/__schema2"
377
+ }
378
+ },
379
+ "message": {
380
+ "anyOf": [
381
+ {
382
+ "type": "string",
383
+ "maxLength": 20000
384
+ },
385
+ {
386
+ "type": "null"
387
+ }
388
+ ]
389
+ }
390
+ },
391
+ "required": [
392
+ "graderId",
393
+ "reward",
394
+ "role",
395
+ "status",
396
+ "rawScore",
397
+ "normalizedScore",
398
+ "passed",
399
+ "evidenceHashes",
400
+ "message"
401
+ ],
402
+ "additionalProperties": false
403
+ },
404
+ "__schema5": {
405
+ "type": "string",
406
+ "format": "date-time",
407
+ "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
408
+ }
409
+ },
410
+ "$id": "urn:openpond:learning:v1:grade",
411
+ "$comment": "Generated from @openpond/evals. Cross-resource identity, authorization, idempotency, admission, grading and split constraints are enforced by the shared domain service in addition to this structural schema."
412
+ }