@openpond/evals 0.6.0 → 0.7.0

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 (87) hide show
  1. package/LEARNING.md +106 -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 +367 -0
  19. package/dist/learning/transport.js +25 -0
  20. package/dist/rewards.js +230 -0
  21. package/dist/task-schema.js +142 -0
  22. package/dist/tasksets.js +3 -0
  23. package/dist/telemetry-catalog.js +1 -1
  24. package/dist/types/builtin-benchmarks/harness-refiner.d.ts +7 -0
  25. package/dist/types/builtin-benchmarks/harness-refiner.d.ts.map +1 -1
  26. package/dist/types/conformance.d.ts +14 -0
  27. package/dist/types/conformance.d.ts.map +1 -1
  28. package/dist/types/execution-contracts.d.ts +14 -0
  29. package/dist/types/execution-contracts.d.ts.map +1 -1
  30. package/dist/types/graders.d.ts.map +1 -1
  31. package/dist/types/index.d.ts +3 -0
  32. package/dist/types/index.d.ts.map +1 -1
  33. package/dist/types/javascript-verifier-contract.d.ts +9 -0
  34. package/dist/types/javascript-verifier-contract.d.ts.map +1 -0
  35. package/dist/types/javascript-verifier-node.d.ts +5 -0
  36. package/dist/types/javascript-verifier-node.d.ts.map +1 -0
  37. package/dist/types/javascript-verifier-worker-source.d.ts +2 -0
  38. package/dist/types/javascript-verifier-worker.d.ts +2 -0
  39. package/dist/types/javascript-verifier-worker.d.ts.map +1 -0
  40. package/dist/types/javascript-verifier.d.ts +15 -0
  41. package/dist/types/javascript-verifier.d.ts.map +1 -0
  42. package/dist/types/learning/admission.d.ts +335 -0
  43. package/dist/types/learning/admission.d.ts.map +1 -0
  44. package/dist/types/learning/assets.d.ts +49 -0
  45. package/dist/types/learning/assets.d.ts.map +1 -0
  46. package/dist/types/learning/contracts.d.ts +2149 -0
  47. package/dist/types/learning/contracts.d.ts.map +1 -0
  48. package/dist/types/learning/errors.d.ts +8 -0
  49. package/dist/types/learning/errors.d.ts.map +1 -0
  50. package/dist/types/learning/grade-worker.d.ts +31 -0
  51. package/dist/types/learning/grade-worker.d.ts.map +1 -0
  52. package/dist/types/learning/index.d.ts +10 -0
  53. package/dist/types/learning/index.d.ts.map +1 -0
  54. package/dist/types/learning/operations.d.ts +2061 -0
  55. package/dist/types/learning/operations.d.ts.map +1 -0
  56. package/dist/types/learning/repository.d.ts +1143 -0
  57. package/dist/types/learning/repository.d.ts.map +1 -0
  58. package/dist/types/learning/service.d.ts +22 -0
  59. package/dist/types/learning/service.d.ts.map +1 -0
  60. package/dist/types/learning/transport.d.ts +2139 -0
  61. package/dist/types/learning/transport.d.ts.map +1 -0
  62. package/dist/types/preferences.d.ts +3 -3
  63. package/dist/types/review-conformance.d.ts +5 -5
  64. package/dist/types/rewards.d.ts +611 -0
  65. package/dist/types/rewards.d.ts.map +1 -0
  66. package/dist/types/task-schema.d.ts +18 -0
  67. package/dist/types/task-schema.d.ts.map +1 -0
  68. package/dist/types/tasksets.d.ts +28 -0
  69. package/dist/types/tasksets.d.ts.map +1 -1
  70. package/package.json +30 -3
  71. package/schemas/learning/v1/asset.schema.json +89 -0
  72. package/schemas/learning/v1/batch.schema.json +132 -0
  73. package/schemas/learning/v1/binding.schema.json +207 -0
  74. package/schemas/learning/v1/command-request.schema.json +2414 -0
  75. package/schemas/learning/v1/decision.schema.json +440 -0
  76. package/schemas/learning/v1/definition.schema.json +397 -0
  77. package/schemas/learning/v1/evidence.schema.json +317 -0
  78. package/schemas/learning/v1/example-submission.schema.json +253 -0
  79. package/schemas/learning/v1/feedback-submission.schema.json +114 -0
  80. package/schemas/learning/v1/feedback.schema.json +233 -0
  81. package/schemas/learning/v1/grade.schema.json +412 -0
  82. package/schemas/learning/v1/iteration.schema.json +236 -0
  83. package/schemas/learning/v1/package.schema.json +776 -0
  84. package/schemas/learning/v1/policy.schema.json +373 -0
  85. package/schemas/learning/v1/read-request.schema.json +101 -0
  86. package/schemas/learning/v1/reward.schema.json +302 -0
  87. package/schemas/learning/v1/source.schema.json +198 -0
@@ -0,0 +1,253 @@
1
+ {
2
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
3
+ "type": "object",
4
+ "properties": {
5
+ "schemaVersion": {
6
+ "type": "string",
7
+ "const": "openpond.taskExample.v1"
8
+ },
9
+ "sourceId": {
10
+ "$ref": "#/$defs/__schema0"
11
+ },
12
+ "idempotencyKey": {
13
+ "$ref": "#/$defs/__schema0"
14
+ },
15
+ "taskDefinition": {
16
+ "type": "object",
17
+ "properties": {
18
+ "id": {
19
+ "$ref": "#/$defs/__schema0"
20
+ },
21
+ "contentHash": {
22
+ "$ref": "#/$defs/__schema1"
23
+ },
24
+ "revision": {
25
+ "type": "integer",
26
+ "exclusiveMinimum": 0,
27
+ "maximum": 9007199254740991
28
+ }
29
+ },
30
+ "required": [
31
+ "id",
32
+ "contentHash",
33
+ "revision"
34
+ ],
35
+ "additionalProperties": false
36
+ },
37
+ "exampleId": {
38
+ "$ref": "#/$defs/__schema0"
39
+ },
40
+ "attemptId": {
41
+ "$ref": "#/$defs/__schema0"
42
+ },
43
+ "occurredAt": {
44
+ "type": "string",
45
+ "format": "date-time",
46
+ "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
47
+ },
48
+ "familyKey": {
49
+ "anyOf": [
50
+ {
51
+ "$ref": "#/$defs/__schema0"
52
+ },
53
+ {
54
+ "type": "null"
55
+ }
56
+ ]
57
+ },
58
+ "split": {
59
+ "type": "string",
60
+ "enum": [
61
+ "train",
62
+ "validation",
63
+ "test",
64
+ "frozen_eval"
65
+ ]
66
+ },
67
+ "input": {
68
+ "$ref": "#/$defs/__schema2"
69
+ },
70
+ "observedOutput": {
71
+ "anyOf": [
72
+ {
73
+ "$ref": "#/$defs/__schema2"
74
+ },
75
+ {
76
+ "type": "null"
77
+ }
78
+ ]
79
+ },
80
+ "expected": {
81
+ "anyOf": [
82
+ {
83
+ "$ref": "#/$defs/__schema2"
84
+ },
85
+ {
86
+ "type": "null"
87
+ }
88
+ ]
89
+ },
90
+ "evaluatorContext": {
91
+ "anyOf": [
92
+ {
93
+ "$ref": "#/$defs/__schema2"
94
+ },
95
+ {
96
+ "type": "null"
97
+ }
98
+ ]
99
+ },
100
+ "assets": {
101
+ "maxItems": 1000,
102
+ "type": "array",
103
+ "items": {
104
+ "$ref": "#/$defs/__schema4"
105
+ }
106
+ },
107
+ "provenance": {
108
+ "type": "object",
109
+ "properties": {
110
+ "sourceRecordRef": {
111
+ "anyOf": [
112
+ {
113
+ "type": "string",
114
+ "maxLength": 2000
115
+ },
116
+ {
117
+ "type": "null"
118
+ }
119
+ ]
120
+ },
121
+ "mappingHash": {
122
+ "anyOf": [
123
+ {
124
+ "$ref": "#/$defs/__schema1"
125
+ },
126
+ {
127
+ "type": "null"
128
+ }
129
+ ]
130
+ }
131
+ },
132
+ "required": [
133
+ "sourceRecordRef",
134
+ "mappingHash"
135
+ ],
136
+ "additionalProperties": false
137
+ }
138
+ },
139
+ "required": [
140
+ "schemaVersion",
141
+ "sourceId",
142
+ "idempotencyKey",
143
+ "taskDefinition",
144
+ "exampleId",
145
+ "attemptId",
146
+ "occurredAt",
147
+ "familyKey",
148
+ "split",
149
+ "input",
150
+ "observedOutput",
151
+ "expected",
152
+ "evaluatorContext",
153
+ "assets",
154
+ "provenance"
155
+ ],
156
+ "additionalProperties": false,
157
+ "$defs": {
158
+ "__schema0": {
159
+ "type": "string",
160
+ "minLength": 1,
161
+ "maxLength": 240
162
+ },
163
+ "__schema1": {
164
+ "type": "string",
165
+ "pattern": "^[a-f0-9]{64}$"
166
+ },
167
+ "__schema2": {
168
+ "type": "object",
169
+ "propertyNames": {
170
+ "type": "string"
171
+ },
172
+ "additionalProperties": {
173
+ "$ref": "#/$defs/__schema3"
174
+ }
175
+ },
176
+ "__schema3": {
177
+ "anyOf": [
178
+ {
179
+ "type": "string"
180
+ },
181
+ {
182
+ "type": "number"
183
+ },
184
+ {
185
+ "type": "boolean"
186
+ },
187
+ {
188
+ "type": "null"
189
+ },
190
+ {
191
+ "type": "array",
192
+ "items": {
193
+ "$ref": "#/$defs/__schema3"
194
+ }
195
+ },
196
+ {
197
+ "type": "object",
198
+ "propertyNames": {
199
+ "type": "string"
200
+ },
201
+ "additionalProperties": {
202
+ "$ref": "#/$defs/__schema3"
203
+ }
204
+ }
205
+ ]
206
+ },
207
+ "__schema4": {
208
+ "type": "object",
209
+ "properties": {
210
+ "id": {
211
+ "$ref": "#/$defs/__schema0"
212
+ },
213
+ "path": {
214
+ "type": "string",
215
+ "minLength": 1,
216
+ "maxLength": 2000
217
+ },
218
+ "contentHash": {
219
+ "$ref": "#/$defs/__schema1"
220
+ },
221
+ "sizeBytes": {
222
+ "type": "integer",
223
+ "minimum": 0,
224
+ "maximum": 250000000
225
+ },
226
+ "mediaType": {
227
+ "type": "string",
228
+ "minLength": 1,
229
+ "maxLength": 200
230
+ },
231
+ "visibility": {
232
+ "type": "string",
233
+ "enum": [
234
+ "policy",
235
+ "verifier",
236
+ "host_private"
237
+ ]
238
+ }
239
+ },
240
+ "required": [
241
+ "id",
242
+ "path",
243
+ "contentHash",
244
+ "sizeBytes",
245
+ "mediaType",
246
+ "visibility"
247
+ ],
248
+ "additionalProperties": false
249
+ }
250
+ },
251
+ "$id": "urn:openpond:learning:v1:example-submission",
252
+ "$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."
253
+ }
@@ -0,0 +1,114 @@
1
+ {
2
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
3
+ "type": "object",
4
+ "properties": {
5
+ "schemaVersion": {
6
+ "type": "string",
7
+ "const": "openpond.taskFeedback.v1"
8
+ },
9
+ "sourceId": {
10
+ "$ref": "#/$defs/__schema0"
11
+ },
12
+ "idempotencyKey": {
13
+ "$ref": "#/$defs/__schema0"
14
+ },
15
+ "exampleId": {
16
+ "$ref": "#/$defs/__schema0"
17
+ },
18
+ "attemptId": {
19
+ "$ref": "#/$defs/__schema0"
20
+ },
21
+ "expectedEvidenceHash": {
22
+ "anyOf": [
23
+ {
24
+ "type": "string",
25
+ "pattern": "^[a-f0-9]{64}$"
26
+ },
27
+ {
28
+ "type": "null"
29
+ }
30
+ ]
31
+ },
32
+ "occurredAt": {
33
+ "type": "string",
34
+ "format": "date-time",
35
+ "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)))$"
36
+ },
37
+ "kind": {
38
+ "type": "string",
39
+ "enum": [
40
+ "outcome",
41
+ "target_correction",
42
+ "ground_truth_correction",
43
+ "input_correction",
44
+ "family_resolution"
45
+ ]
46
+ },
47
+ "value": {
48
+ "type": "object",
49
+ "propertyNames": {
50
+ "type": "string"
51
+ },
52
+ "additionalProperties": {
53
+ "$ref": "#/$defs/__schema1"
54
+ }
55
+ },
56
+ "note": {
57
+ "type": "string",
58
+ "maxLength": 20000
59
+ }
60
+ },
61
+ "required": [
62
+ "schemaVersion",
63
+ "sourceId",
64
+ "idempotencyKey",
65
+ "exampleId",
66
+ "attemptId",
67
+ "expectedEvidenceHash",
68
+ "occurredAt",
69
+ "kind",
70
+ "value",
71
+ "note"
72
+ ],
73
+ "additionalProperties": false,
74
+ "$defs": {
75
+ "__schema0": {
76
+ "type": "string",
77
+ "minLength": 1,
78
+ "maxLength": 240
79
+ },
80
+ "__schema1": {
81
+ "anyOf": [
82
+ {
83
+ "type": "string"
84
+ },
85
+ {
86
+ "type": "number"
87
+ },
88
+ {
89
+ "type": "boolean"
90
+ },
91
+ {
92
+ "type": "null"
93
+ },
94
+ {
95
+ "type": "array",
96
+ "items": {
97
+ "$ref": "#/$defs/__schema1"
98
+ }
99
+ },
100
+ {
101
+ "type": "object",
102
+ "propertyNames": {
103
+ "type": "string"
104
+ },
105
+ "additionalProperties": {
106
+ "$ref": "#/$defs/__schema1"
107
+ }
108
+ }
109
+ ]
110
+ }
111
+ },
112
+ "$id": "urn:openpond:learning:v1:feedback-submission",
113
+ "$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."
114
+ }
@@ -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
+ }