@openpond/evals 0.5.0 → 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 (118) hide show
  1. package/CONTRACT.md +13 -1
  2. package/LEARNING.md +106 -0
  3. package/README.md +28 -2
  4. package/conformance/telemetry/v1/invalid-batch.json +17 -0
  5. package/conformance/telemetry/v1/valid-batch.json +58 -0
  6. package/dist/graders.js +26 -5
  7. package/dist/index.js +8 -0
  8. package/dist/javascript-verifier-contract.js +7 -0
  9. package/dist/javascript-verifier-node.js +56 -0
  10. package/dist/javascript-verifier-worker-source.js +1 -0
  11. package/dist/javascript-verifier-worker.js +6 -0
  12. package/dist/javascript-verifier.js +64 -0
  13. package/dist/learned-preference.js +334 -0
  14. package/dist/learning/admission.js +209 -0
  15. package/dist/learning/assets.js +37 -0
  16. package/dist/learning/contracts.js +267 -0
  17. package/dist/learning/errors.js +12 -0
  18. package/dist/learning/grade-worker.js +99 -0
  19. package/dist/learning/index.js +9 -0
  20. package/dist/learning/operations.js +33 -0
  21. package/dist/learning/repository.js +48 -0
  22. package/dist/learning/service.js +367 -0
  23. package/dist/learning/transport.js +25 -0
  24. package/dist/preferences.js +77 -11
  25. package/dist/rewards.js +230 -0
  26. package/dist/task-schema.js +142 -0
  27. package/dist/tasksets.js +3 -0
  28. package/dist/telemetry/index.js +4 -0
  29. package/dist/telemetry-analysis.js +183 -0
  30. package/dist/telemetry-bundle.js +60 -0
  31. package/dist/telemetry-catalog.js +50 -0
  32. package/dist/telemetry.js +112 -0
  33. package/dist/types/builtin-benchmarks/harness-refiner.d.ts +7 -0
  34. package/dist/types/builtin-benchmarks/harness-refiner.d.ts.map +1 -1
  35. package/dist/types/conformance.d.ts +14 -0
  36. package/dist/types/conformance.d.ts.map +1 -1
  37. package/dist/types/execution-contracts.d.ts +14 -0
  38. package/dist/types/execution-contracts.d.ts.map +1 -1
  39. package/dist/types/graders.d.ts.map +1 -1
  40. package/dist/types/index.d.ts +8 -0
  41. package/dist/types/index.d.ts.map +1 -1
  42. package/dist/types/javascript-verifier-contract.d.ts +9 -0
  43. package/dist/types/javascript-verifier-contract.d.ts.map +1 -0
  44. package/dist/types/javascript-verifier-node.d.ts +5 -0
  45. package/dist/types/javascript-verifier-node.d.ts.map +1 -0
  46. package/dist/types/javascript-verifier-worker-source.d.ts +2 -0
  47. package/dist/types/javascript-verifier-worker.d.ts +2 -0
  48. package/dist/types/javascript-verifier-worker.d.ts.map +1 -0
  49. package/dist/types/javascript-verifier.d.ts +15 -0
  50. package/dist/types/javascript-verifier.d.ts.map +1 -0
  51. package/dist/types/learned-preference.d.ts +282 -0
  52. package/dist/types/learned-preference.d.ts.map +1 -0
  53. package/dist/types/learning/admission.d.ts +335 -0
  54. package/dist/types/learning/admission.d.ts.map +1 -0
  55. package/dist/types/learning/assets.d.ts +49 -0
  56. package/dist/types/learning/assets.d.ts.map +1 -0
  57. package/dist/types/learning/contracts.d.ts +2149 -0
  58. package/dist/types/learning/contracts.d.ts.map +1 -0
  59. package/dist/types/learning/errors.d.ts +8 -0
  60. package/dist/types/learning/errors.d.ts.map +1 -0
  61. package/dist/types/learning/grade-worker.d.ts +31 -0
  62. package/dist/types/learning/grade-worker.d.ts.map +1 -0
  63. package/dist/types/learning/index.d.ts +10 -0
  64. package/dist/types/learning/index.d.ts.map +1 -0
  65. package/dist/types/learning/operations.d.ts +2061 -0
  66. package/dist/types/learning/operations.d.ts.map +1 -0
  67. package/dist/types/learning/repository.d.ts +1143 -0
  68. package/dist/types/learning/repository.d.ts.map +1 -0
  69. package/dist/types/learning/service.d.ts +22 -0
  70. package/dist/types/learning/service.d.ts.map +1 -0
  71. package/dist/types/learning/transport.d.ts +2139 -0
  72. package/dist/types/learning/transport.d.ts.map +1 -0
  73. package/dist/types/preferences.d.ts +55 -7
  74. package/dist/types/preferences.d.ts.map +1 -1
  75. package/dist/types/review-conformance.d.ts +5 -5
  76. package/dist/types/rewards.d.ts +611 -0
  77. package/dist/types/rewards.d.ts.map +1 -0
  78. package/dist/types/task-schema.d.ts +18 -0
  79. package/dist/types/task-schema.d.ts.map +1 -0
  80. package/dist/types/tasksets.d.ts +28 -0
  81. package/dist/types/tasksets.d.ts.map +1 -1
  82. package/dist/types/telemetry/index.d.ts +5 -0
  83. package/dist/types/telemetry/index.d.ts.map +1 -0
  84. package/dist/types/telemetry-analysis.d.ts +116 -0
  85. package/dist/types/telemetry-analysis.d.ts.map +1 -0
  86. package/dist/types/telemetry-bundle.d.ts +309 -0
  87. package/dist/types/telemetry-bundle.d.ts.map +1 -0
  88. package/dist/types/telemetry-catalog.d.ts +269 -0
  89. package/dist/types/telemetry-catalog.d.ts.map +1 -0
  90. package/dist/types/telemetry.d.ts +266 -0
  91. package/dist/types/telemetry.d.ts.map +1 -0
  92. package/package.json +40 -3
  93. package/schemas/learning/v1/asset.schema.json +89 -0
  94. package/schemas/learning/v1/batch.schema.json +132 -0
  95. package/schemas/learning/v1/binding.schema.json +207 -0
  96. package/schemas/learning/v1/command-request.schema.json +2414 -0
  97. package/schemas/learning/v1/decision.schema.json +440 -0
  98. package/schemas/learning/v1/definition.schema.json +397 -0
  99. package/schemas/learning/v1/evidence.schema.json +317 -0
  100. package/schemas/learning/v1/example-submission.schema.json +253 -0
  101. package/schemas/learning/v1/feedback-submission.schema.json +114 -0
  102. package/schemas/learning/v1/feedback.schema.json +233 -0
  103. package/schemas/learning/v1/grade.schema.json +412 -0
  104. package/schemas/learning/v1/iteration.schema.json +236 -0
  105. package/schemas/learning/v1/package.schema.json +776 -0
  106. package/schemas/learning/v1/policy.schema.json +373 -0
  107. package/schemas/learning/v1/read-request.schema.json +101 -0
  108. package/schemas/learning/v1/reward.schema.json +302 -0
  109. package/schemas/learning/v1/source.schema.json +198 -0
  110. package/schemas/telemetry/v1/evidence-completeness.schema.json +82 -0
  111. package/schemas/telemetry/v1/evidence-reference.schema.json +41 -0
  112. package/schemas/telemetry/v1/metric-definition.schema.json +96 -0
  113. package/schemas/telemetry/v1/metric-observation.schema.json +182 -0
  114. package/schemas/telemetry/v1/run-metric-summary.schema.json +98 -0
  115. package/schemas/telemetry/v1/run-telemetry-batch.schema.json +405 -0
  116. package/schemas/telemetry/v1/run-telemetry-event.schema.json +201 -0
  117. package/schemas/telemetry/v1/telemetry-cohort.schema.json +100 -0
  118. package/schemas/telemetry/v1/telemetry-export-bundle.schema.json +655 -0
@@ -0,0 +1,96 @@
1
+ {
2
+ "$schema": "http://json-schema.org/draft-07/schema#",
3
+ "type": "object",
4
+ "properties": {
5
+ "schemaVersion": {
6
+ "type": "string",
7
+ "const": "openpond.metricDefinition.v1"
8
+ },
9
+ "id": {
10
+ "type": "string",
11
+ "minLength": 1,
12
+ "maxLength": 240
13
+ },
14
+ "displayName": {
15
+ "type": "string",
16
+ "minLength": 1,
17
+ "maxLength": 200
18
+ },
19
+ "description": {
20
+ "type": "string",
21
+ "minLength": 1,
22
+ "maxLength": 2000
23
+ },
24
+ "valueType": {
25
+ "type": "string",
26
+ "enum": [
27
+ "gauge",
28
+ "counter",
29
+ "distribution"
30
+ ]
31
+ },
32
+ "unit": {
33
+ "type": "string",
34
+ "enum": [
35
+ "ratio",
36
+ "count",
37
+ "seconds",
38
+ "milliseconds",
39
+ "tokens",
40
+ "bytes",
41
+ "usd",
42
+ "scalar"
43
+ ]
44
+ },
45
+ "direction": {
46
+ "type": "string",
47
+ "enum": [
48
+ "higher",
49
+ "lower",
50
+ "neutral"
51
+ ]
52
+ },
53
+ "aggregation": {
54
+ "type": "string",
55
+ "enum": [
56
+ "last",
57
+ "sum",
58
+ "mean",
59
+ "min",
60
+ "max",
61
+ "p50",
62
+ "p95"
63
+ ]
64
+ },
65
+ "visibility": {
66
+ "type": "string",
67
+ "enum": [
68
+ "policy_visible",
69
+ "team_visible",
70
+ "host_private"
71
+ ]
72
+ },
73
+ "boundedDimensions": {
74
+ "maxItems": 32,
75
+ "type": "array",
76
+ "items": {
77
+ "type": "string",
78
+ "minLength": 1,
79
+ "maxLength": 100
80
+ }
81
+ }
82
+ },
83
+ "required": [
84
+ "schemaVersion",
85
+ "id",
86
+ "displayName",
87
+ "description",
88
+ "valueType",
89
+ "unit",
90
+ "direction",
91
+ "aggregation",
92
+ "visibility",
93
+ "boundedDimensions"
94
+ ],
95
+ "additionalProperties": false
96
+ }
@@ -0,0 +1,182 @@
1
+ {
2
+ "$schema": "http://json-schema.org/draft-07/schema#",
3
+ "type": "object",
4
+ "properties": {
5
+ "schemaVersion": {
6
+ "type": "string",
7
+ "const": "openpond.metricObservation.v1"
8
+ },
9
+ "observationId": {
10
+ "type": "string",
11
+ "minLength": 1,
12
+ "maxLength": 240
13
+ },
14
+ "metricId": {
15
+ "type": "string",
16
+ "minLength": 1,
17
+ "maxLength": 240
18
+ },
19
+ "eventId": {
20
+ "type": "string",
21
+ "minLength": 1,
22
+ "maxLength": 240
23
+ },
24
+ "sequence": {
25
+ "type": "integer",
26
+ "minimum": 0,
27
+ "maximum": 9007199254740991
28
+ },
29
+ "observedAt": {
30
+ "type": "string",
31
+ "format": "date-time",
32
+ "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)))$"
33
+ },
34
+ "value": {
35
+ "type": "number"
36
+ },
37
+ "lineage": {
38
+ "type": "object",
39
+ "properties": {
40
+ "modelProjectId": {
41
+ "type": "string",
42
+ "minLength": 1,
43
+ "maxLength": 240
44
+ },
45
+ "runId": {
46
+ "type": "string",
47
+ "minLength": 1,
48
+ "maxLength": 240
49
+ },
50
+ "modelVersionId": {
51
+ "anyOf": [
52
+ {
53
+ "type": "string",
54
+ "minLength": 1,
55
+ "maxLength": 240
56
+ },
57
+ {
58
+ "type": "null"
59
+ }
60
+ ]
61
+ },
62
+ "harnessReleaseHash": {
63
+ "type": "string",
64
+ "pattern": "^[a-f0-9]{64}$"
65
+ },
66
+ "tasksetReleaseHash": {
67
+ "type": "string",
68
+ "pattern": "^[a-f0-9]{64}$"
69
+ },
70
+ "environmentReleaseHash": {
71
+ "anyOf": [
72
+ {
73
+ "type": "string",
74
+ "pattern": "^[a-f0-9]{64}$"
75
+ },
76
+ {
77
+ "type": "null"
78
+ }
79
+ ]
80
+ },
81
+ "checkpointId": {
82
+ "anyOf": [
83
+ {
84
+ "type": "string",
85
+ "minLength": 1,
86
+ "maxLength": 240
87
+ },
88
+ {
89
+ "type": "null"
90
+ }
91
+ ]
92
+ },
93
+ "step": {
94
+ "anyOf": [
95
+ {
96
+ "type": "integer",
97
+ "minimum": 0,
98
+ "maximum": 9007199254740991
99
+ },
100
+ {
101
+ "type": "null"
102
+ }
103
+ ]
104
+ },
105
+ "rolloutGroupId": {
106
+ "anyOf": [
107
+ {
108
+ "type": "string",
109
+ "minLength": 1,
110
+ "maxLength": 240
111
+ },
112
+ {
113
+ "type": "null"
114
+ }
115
+ ]
116
+ },
117
+ "attemptId": {
118
+ "anyOf": [
119
+ {
120
+ "type": "string",
121
+ "minLength": 1,
122
+ "maxLength": 240
123
+ },
124
+ {
125
+ "type": "null"
126
+ }
127
+ ]
128
+ },
129
+ "scenarioId": {
130
+ "anyOf": [
131
+ {
132
+ "type": "string",
133
+ "minLength": 1,
134
+ "maxLength": 240
135
+ },
136
+ {
137
+ "type": "null"
138
+ }
139
+ ]
140
+ }
141
+ },
142
+ "required": [
143
+ "modelProjectId",
144
+ "runId",
145
+ "modelVersionId",
146
+ "harnessReleaseHash",
147
+ "tasksetReleaseHash",
148
+ "environmentReleaseHash",
149
+ "checkpointId",
150
+ "step",
151
+ "rolloutGroupId",
152
+ "attemptId",
153
+ "scenarioId"
154
+ ],
155
+ "additionalProperties": false
156
+ },
157
+ "dimensions": {
158
+ "type": "object",
159
+ "propertyNames": {
160
+ "type": "string",
161
+ "minLength": 1,
162
+ "maxLength": 100
163
+ },
164
+ "additionalProperties": {
165
+ "type": "string",
166
+ "maxLength": 500
167
+ }
168
+ }
169
+ },
170
+ "required": [
171
+ "schemaVersion",
172
+ "observationId",
173
+ "metricId",
174
+ "eventId",
175
+ "sequence",
176
+ "observedAt",
177
+ "value",
178
+ "lineage",
179
+ "dimensions"
180
+ ],
181
+ "additionalProperties": false
182
+ }
@@ -0,0 +1,98 @@
1
+ {
2
+ "$schema": "http://json-schema.org/draft-07/schema#",
3
+ "type": "object",
4
+ "properties": {
5
+ "schemaVersion": {
6
+ "type": "string",
7
+ "const": "openpond.runMetricSummary.v1"
8
+ },
9
+ "runId": {
10
+ "type": "string",
11
+ "minLength": 1,
12
+ "maxLength": 240
13
+ },
14
+ "metricId": {
15
+ "type": "string",
16
+ "minLength": 1,
17
+ "maxLength": 240
18
+ },
19
+ "aggregation": {
20
+ "type": "string",
21
+ "enum": [
22
+ "last",
23
+ "sum",
24
+ "mean",
25
+ "min",
26
+ "max",
27
+ "p50",
28
+ "p95"
29
+ ]
30
+ },
31
+ "value": {
32
+ "anyOf": [
33
+ {
34
+ "type": "number"
35
+ },
36
+ {
37
+ "type": "null"
38
+ }
39
+ ]
40
+ },
41
+ "sampleCount": {
42
+ "type": "integer",
43
+ "minimum": 0,
44
+ "maximum": 9007199254740991
45
+ },
46
+ "series": {
47
+ "maxItems": 100000,
48
+ "type": "array",
49
+ "items": {
50
+ "type": "object",
51
+ "properties": {
52
+ "step": {
53
+ "anyOf": [
54
+ {
55
+ "type": "integer",
56
+ "minimum": 0,
57
+ "maximum": 9007199254740991
58
+ },
59
+ {
60
+ "type": "null"
61
+ }
62
+ ]
63
+ },
64
+ "observedAt": {
65
+ "type": "string",
66
+ "format": "date-time",
67
+ "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
68
+ },
69
+ "value": {
70
+ "type": "number"
71
+ },
72
+ "sampleCount": {
73
+ "type": "integer",
74
+ "exclusiveMinimum": 0,
75
+ "maximum": 9007199254740991
76
+ }
77
+ },
78
+ "required": [
79
+ "step",
80
+ "observedAt",
81
+ "value",
82
+ "sampleCount"
83
+ ],
84
+ "additionalProperties": false
85
+ }
86
+ }
87
+ },
88
+ "required": [
89
+ "schemaVersion",
90
+ "runId",
91
+ "metricId",
92
+ "aggregation",
93
+ "value",
94
+ "sampleCount",
95
+ "series"
96
+ ],
97
+ "additionalProperties": false
98
+ }