@openpond/evals 0.4.2 → 0.6.0
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.
- package/CONTRACT.md +27 -1
- package/README.md +31 -2
- package/conformance/telemetry/v1/invalid-batch.json +17 -0
- package/conformance/telemetry/v1/valid-batch.json +58 -0
- package/dist/artifact-verification.js +172 -0
- package/dist/builtin-benchmarks/harness-refiner.js +469 -24
- package/dist/execution-contracts.js +153 -0
- package/dist/execution-receipts.js +185 -0
- package/dist/graders.js +8 -2
- package/dist/index.js +10 -0
- package/dist/learned-preference.js +334 -0
- package/dist/preferences.js +803 -0
- package/dist/rollouts.js +241 -0
- package/dist/tasksets.js +24 -0
- package/dist/telemetry/index.js +4 -0
- package/dist/telemetry-analysis.js +183 -0
- package/dist/telemetry-bundle.js +60 -0
- package/dist/telemetry-catalog.js +50 -0
- package/dist/telemetry.js +112 -0
- package/dist/types/artifact-verification.d.ts +31 -0
- package/dist/types/artifact-verification.d.ts.map +1 -0
- package/dist/types/builtin-benchmarks/harness-refiner.d.ts +22 -0
- package/dist/types/builtin-benchmarks/harness-refiner.d.ts.map +1 -1
- package/dist/types/conformance.d.ts +44 -0
- package/dist/types/conformance.d.ts.map +1 -1
- package/dist/types/evidence/conformance.d.ts +24 -24
- package/dist/types/evidence/contracts.d.ts +42 -42
- package/dist/types/execution-contracts.d.ts +806 -0
- package/dist/types/execution-contracts.d.ts.map +1 -0
- package/dist/types/execution-receipts.d.ts +55 -0
- package/dist/types/execution-receipts.d.ts.map +1 -0
- package/dist/types/graders.d.ts.map +1 -1
- package/dist/types/index.d.ts +10 -0
- package/dist/types/index.d.ts.map +1 -1
- package/dist/types/learned-preference.d.ts +282 -0
- package/dist/types/learned-preference.d.ts.map +1 -0
- package/dist/types/preferences.d.ts +583 -0
- package/dist/types/preferences.d.ts.map +1 -0
- package/dist/types/review-conformance.d.ts +20 -15
- package/dist/types/review-conformance.d.ts.map +1 -1
- package/dist/types/rollouts.d.ts +221 -0
- package/dist/types/rollouts.d.ts.map +1 -0
- package/dist/types/tasksets.d.ts +89 -0
- package/dist/types/tasksets.d.ts.map +1 -1
- package/dist/types/telemetry/index.d.ts +5 -0
- package/dist/types/telemetry/index.d.ts.map +1 -0
- package/dist/types/telemetry-analysis.d.ts +116 -0
- package/dist/types/telemetry-analysis.d.ts.map +1 -0
- package/dist/types/telemetry-bundle.d.ts +309 -0
- package/dist/types/telemetry-bundle.d.ts.map +1 -0
- package/dist/types/telemetry-catalog.d.ts +269 -0
- package/dist/types/telemetry-catalog.d.ts.map +1 -0
- package/dist/types/telemetry.d.ts +266 -0
- package/dist/types/telemetry.d.ts.map +1 -0
- package/package.json +20 -2
- package/schemas/telemetry/v1/evidence-completeness.schema.json +82 -0
- package/schemas/telemetry/v1/evidence-reference.schema.json +41 -0
- package/schemas/telemetry/v1/metric-definition.schema.json +96 -0
- package/schemas/telemetry/v1/metric-observation.schema.json +182 -0
- package/schemas/telemetry/v1/run-metric-summary.schema.json +98 -0
- package/schemas/telemetry/v1/run-telemetry-batch.schema.json +405 -0
- package/schemas/telemetry/v1/run-telemetry-event.schema.json +201 -0
- package/schemas/telemetry/v1/telemetry-cohort.schema.json +100 -0
- package/schemas/telemetry/v1/telemetry-export-bundle.schema.json +655 -0
|
@@ -0,0 +1,266 @@
|
|
|
1
|
+
import { z } from "zod";
|
|
2
|
+
export declare const RUN_TELEMETRY_SCHEMA_VERSION: "openpond.runTelemetryEvent.v1";
|
|
3
|
+
export declare const METRIC_DEFINITION_SCHEMA_VERSION: "openpond.metricDefinition.v1";
|
|
4
|
+
export declare const METRIC_OBSERVATION_SCHEMA_VERSION: "openpond.metricObservation.v1";
|
|
5
|
+
export declare const TelemetryVisibilitySchema: z.ZodEnum<{
|
|
6
|
+
host_private: "host_private";
|
|
7
|
+
policy_visible: "policy_visible";
|
|
8
|
+
team_visible: "team_visible";
|
|
9
|
+
}>;
|
|
10
|
+
export declare const TelemetrySourceSchema: z.ZodEnum<{
|
|
11
|
+
environment: "environment";
|
|
12
|
+
evaluation: "evaluation";
|
|
13
|
+
runtime: "runtime";
|
|
14
|
+
grader: "grader";
|
|
15
|
+
optimizer: "optimizer";
|
|
16
|
+
control_plane: "control_plane";
|
|
17
|
+
}>;
|
|
18
|
+
export declare const TelemetryEventTypeSchema: z.ZodEnum<{
|
|
19
|
+
cleanup_completed: "cleanup_completed";
|
|
20
|
+
run_started: "run_started";
|
|
21
|
+
run_state_changed: "run_state_changed";
|
|
22
|
+
rollout_group_started: "rollout_group_started";
|
|
23
|
+
attempt_completed: "attempt_completed";
|
|
24
|
+
grader_completed: "grader_completed";
|
|
25
|
+
reward_composed: "reward_composed";
|
|
26
|
+
optimizer_step_completed: "optimizer_step_completed";
|
|
27
|
+
checkpoint_committed: "checkpoint_committed";
|
|
28
|
+
evaluation_completed: "evaluation_completed";
|
|
29
|
+
run_completed: "run_completed";
|
|
30
|
+
run_failed: "run_failed";
|
|
31
|
+
}>;
|
|
32
|
+
export declare const RunTelemetryLineageSchema: z.ZodObject<{
|
|
33
|
+
modelProjectId: z.ZodString;
|
|
34
|
+
runId: z.ZodString;
|
|
35
|
+
modelVersionId: z.ZodNullable<z.ZodString>;
|
|
36
|
+
harnessReleaseHash: z.ZodString;
|
|
37
|
+
tasksetReleaseHash: z.ZodString;
|
|
38
|
+
environmentReleaseHash: z.ZodNullable<z.ZodString>;
|
|
39
|
+
checkpointId: z.ZodNullable<z.ZodString>;
|
|
40
|
+
step: z.ZodNullable<z.ZodNumber>;
|
|
41
|
+
rolloutGroupId: z.ZodNullable<z.ZodString>;
|
|
42
|
+
attemptId: z.ZodNullable<z.ZodString>;
|
|
43
|
+
scenarioId: z.ZodNullable<z.ZodString>;
|
|
44
|
+
}, z.core.$strict>;
|
|
45
|
+
export declare const RunTelemetryEventSchema: z.ZodObject<{
|
|
46
|
+
schemaVersion: z.ZodLiteral<"openpond.runTelemetryEvent.v1">;
|
|
47
|
+
eventId: z.ZodString;
|
|
48
|
+
sequence: z.ZodNumber;
|
|
49
|
+
occurredAt: z.ZodString;
|
|
50
|
+
source: z.ZodEnum<{
|
|
51
|
+
environment: "environment";
|
|
52
|
+
evaluation: "evaluation";
|
|
53
|
+
runtime: "runtime";
|
|
54
|
+
grader: "grader";
|
|
55
|
+
optimizer: "optimizer";
|
|
56
|
+
control_plane: "control_plane";
|
|
57
|
+
}>;
|
|
58
|
+
type: z.ZodEnum<{
|
|
59
|
+
cleanup_completed: "cleanup_completed";
|
|
60
|
+
run_started: "run_started";
|
|
61
|
+
run_state_changed: "run_state_changed";
|
|
62
|
+
rollout_group_started: "rollout_group_started";
|
|
63
|
+
attempt_completed: "attempt_completed";
|
|
64
|
+
grader_completed: "grader_completed";
|
|
65
|
+
reward_composed: "reward_composed";
|
|
66
|
+
optimizer_step_completed: "optimizer_step_completed";
|
|
67
|
+
checkpoint_committed: "checkpoint_committed";
|
|
68
|
+
evaluation_completed: "evaluation_completed";
|
|
69
|
+
run_completed: "run_completed";
|
|
70
|
+
run_failed: "run_failed";
|
|
71
|
+
}>;
|
|
72
|
+
visibility: z.ZodEnum<{
|
|
73
|
+
host_private: "host_private";
|
|
74
|
+
policy_visible: "policy_visible";
|
|
75
|
+
team_visible: "team_visible";
|
|
76
|
+
}>;
|
|
77
|
+
lineage: z.ZodObject<{
|
|
78
|
+
modelProjectId: z.ZodString;
|
|
79
|
+
runId: z.ZodString;
|
|
80
|
+
modelVersionId: z.ZodNullable<z.ZodString>;
|
|
81
|
+
harnessReleaseHash: z.ZodString;
|
|
82
|
+
tasksetReleaseHash: z.ZodString;
|
|
83
|
+
environmentReleaseHash: z.ZodNullable<z.ZodString>;
|
|
84
|
+
checkpointId: z.ZodNullable<z.ZodString>;
|
|
85
|
+
step: z.ZodNullable<z.ZodNumber>;
|
|
86
|
+
rolloutGroupId: z.ZodNullable<z.ZodString>;
|
|
87
|
+
attemptId: z.ZodNullable<z.ZodString>;
|
|
88
|
+
scenarioId: z.ZodNullable<z.ZodString>;
|
|
89
|
+
}, z.core.$strict>;
|
|
90
|
+
attributes: z.ZodDefault<z.ZodRecord<z.ZodString, z.ZodUnknown>>;
|
|
91
|
+
}, z.core.$strict>;
|
|
92
|
+
export declare const MetricValueTypeSchema: z.ZodEnum<{
|
|
93
|
+
gauge: "gauge";
|
|
94
|
+
counter: "counter";
|
|
95
|
+
distribution: "distribution";
|
|
96
|
+
}>;
|
|
97
|
+
export declare const MetricUnitSchema: z.ZodEnum<{
|
|
98
|
+
ratio: "ratio";
|
|
99
|
+
count: "count";
|
|
100
|
+
seconds: "seconds";
|
|
101
|
+
milliseconds: "milliseconds";
|
|
102
|
+
tokens: "tokens";
|
|
103
|
+
bytes: "bytes";
|
|
104
|
+
usd: "usd";
|
|
105
|
+
scalar: "scalar";
|
|
106
|
+
}>;
|
|
107
|
+
export declare const MetricDirectionSchema: z.ZodEnum<{
|
|
108
|
+
higher: "higher";
|
|
109
|
+
lower: "lower";
|
|
110
|
+
neutral: "neutral";
|
|
111
|
+
}>;
|
|
112
|
+
export declare const MetricAggregationSchema: z.ZodEnum<{
|
|
113
|
+
last: "last";
|
|
114
|
+
sum: "sum";
|
|
115
|
+
mean: "mean";
|
|
116
|
+
min: "min";
|
|
117
|
+
max: "max";
|
|
118
|
+
p50: "p50";
|
|
119
|
+
p95: "p95";
|
|
120
|
+
}>;
|
|
121
|
+
export declare const MetricDefinitionSchema: z.ZodObject<{
|
|
122
|
+
schemaVersion: z.ZodLiteral<"openpond.metricDefinition.v1">;
|
|
123
|
+
id: z.ZodString;
|
|
124
|
+
displayName: z.ZodString;
|
|
125
|
+
description: z.ZodString;
|
|
126
|
+
valueType: z.ZodEnum<{
|
|
127
|
+
gauge: "gauge";
|
|
128
|
+
counter: "counter";
|
|
129
|
+
distribution: "distribution";
|
|
130
|
+
}>;
|
|
131
|
+
unit: z.ZodEnum<{
|
|
132
|
+
ratio: "ratio";
|
|
133
|
+
count: "count";
|
|
134
|
+
seconds: "seconds";
|
|
135
|
+
milliseconds: "milliseconds";
|
|
136
|
+
tokens: "tokens";
|
|
137
|
+
bytes: "bytes";
|
|
138
|
+
usd: "usd";
|
|
139
|
+
scalar: "scalar";
|
|
140
|
+
}>;
|
|
141
|
+
direction: z.ZodEnum<{
|
|
142
|
+
higher: "higher";
|
|
143
|
+
lower: "lower";
|
|
144
|
+
neutral: "neutral";
|
|
145
|
+
}>;
|
|
146
|
+
aggregation: z.ZodEnum<{
|
|
147
|
+
last: "last";
|
|
148
|
+
sum: "sum";
|
|
149
|
+
mean: "mean";
|
|
150
|
+
min: "min";
|
|
151
|
+
max: "max";
|
|
152
|
+
p50: "p50";
|
|
153
|
+
p95: "p95";
|
|
154
|
+
}>;
|
|
155
|
+
visibility: z.ZodEnum<{
|
|
156
|
+
host_private: "host_private";
|
|
157
|
+
policy_visible: "policy_visible";
|
|
158
|
+
team_visible: "team_visible";
|
|
159
|
+
}>;
|
|
160
|
+
boundedDimensions: z.ZodArray<z.ZodString>;
|
|
161
|
+
}, z.core.$strict>;
|
|
162
|
+
export declare const MetricObservationSchema: z.ZodObject<{
|
|
163
|
+
schemaVersion: z.ZodLiteral<"openpond.metricObservation.v1">;
|
|
164
|
+
observationId: z.ZodString;
|
|
165
|
+
metricId: z.ZodString;
|
|
166
|
+
eventId: z.ZodString;
|
|
167
|
+
sequence: z.ZodNumber;
|
|
168
|
+
observedAt: z.ZodString;
|
|
169
|
+
value: z.ZodNumber;
|
|
170
|
+
lineage: z.ZodObject<{
|
|
171
|
+
modelProjectId: z.ZodString;
|
|
172
|
+
runId: z.ZodString;
|
|
173
|
+
modelVersionId: z.ZodNullable<z.ZodString>;
|
|
174
|
+
harnessReleaseHash: z.ZodString;
|
|
175
|
+
tasksetReleaseHash: z.ZodString;
|
|
176
|
+
environmentReleaseHash: z.ZodNullable<z.ZodString>;
|
|
177
|
+
checkpointId: z.ZodNullable<z.ZodString>;
|
|
178
|
+
step: z.ZodNullable<z.ZodNumber>;
|
|
179
|
+
rolloutGroupId: z.ZodNullable<z.ZodString>;
|
|
180
|
+
attemptId: z.ZodNullable<z.ZodString>;
|
|
181
|
+
scenarioId: z.ZodNullable<z.ZodString>;
|
|
182
|
+
}, z.core.$strict>;
|
|
183
|
+
dimensions: z.ZodRecord<z.ZodString, z.ZodString>;
|
|
184
|
+
}, z.core.$strict>;
|
|
185
|
+
export declare const RunTelemetryBatchSchema: z.ZodObject<{
|
|
186
|
+
schemaVersion: z.ZodLiteral<"openpond.runTelemetryBatch.v1">;
|
|
187
|
+
events: z.ZodArray<z.ZodObject<{
|
|
188
|
+
schemaVersion: z.ZodLiteral<"openpond.runTelemetryEvent.v1">;
|
|
189
|
+
eventId: z.ZodString;
|
|
190
|
+
sequence: z.ZodNumber;
|
|
191
|
+
occurredAt: z.ZodString;
|
|
192
|
+
source: z.ZodEnum<{
|
|
193
|
+
environment: "environment";
|
|
194
|
+
evaluation: "evaluation";
|
|
195
|
+
runtime: "runtime";
|
|
196
|
+
grader: "grader";
|
|
197
|
+
optimizer: "optimizer";
|
|
198
|
+
control_plane: "control_plane";
|
|
199
|
+
}>;
|
|
200
|
+
type: z.ZodEnum<{
|
|
201
|
+
cleanup_completed: "cleanup_completed";
|
|
202
|
+
run_started: "run_started";
|
|
203
|
+
run_state_changed: "run_state_changed";
|
|
204
|
+
rollout_group_started: "rollout_group_started";
|
|
205
|
+
attempt_completed: "attempt_completed";
|
|
206
|
+
grader_completed: "grader_completed";
|
|
207
|
+
reward_composed: "reward_composed";
|
|
208
|
+
optimizer_step_completed: "optimizer_step_completed";
|
|
209
|
+
checkpoint_committed: "checkpoint_committed";
|
|
210
|
+
evaluation_completed: "evaluation_completed";
|
|
211
|
+
run_completed: "run_completed";
|
|
212
|
+
run_failed: "run_failed";
|
|
213
|
+
}>;
|
|
214
|
+
visibility: z.ZodEnum<{
|
|
215
|
+
host_private: "host_private";
|
|
216
|
+
policy_visible: "policy_visible";
|
|
217
|
+
team_visible: "team_visible";
|
|
218
|
+
}>;
|
|
219
|
+
lineage: z.ZodObject<{
|
|
220
|
+
modelProjectId: z.ZodString;
|
|
221
|
+
runId: z.ZodString;
|
|
222
|
+
modelVersionId: z.ZodNullable<z.ZodString>;
|
|
223
|
+
harnessReleaseHash: z.ZodString;
|
|
224
|
+
tasksetReleaseHash: z.ZodString;
|
|
225
|
+
environmentReleaseHash: z.ZodNullable<z.ZodString>;
|
|
226
|
+
checkpointId: z.ZodNullable<z.ZodString>;
|
|
227
|
+
step: z.ZodNullable<z.ZodNumber>;
|
|
228
|
+
rolloutGroupId: z.ZodNullable<z.ZodString>;
|
|
229
|
+
attemptId: z.ZodNullable<z.ZodString>;
|
|
230
|
+
scenarioId: z.ZodNullable<z.ZodString>;
|
|
231
|
+
}, z.core.$strict>;
|
|
232
|
+
attributes: z.ZodDefault<z.ZodRecord<z.ZodString, z.ZodUnknown>>;
|
|
233
|
+
}, z.core.$strict>>;
|
|
234
|
+
observations: z.ZodArray<z.ZodObject<{
|
|
235
|
+
schemaVersion: z.ZodLiteral<"openpond.metricObservation.v1">;
|
|
236
|
+
observationId: z.ZodString;
|
|
237
|
+
metricId: z.ZodString;
|
|
238
|
+
eventId: z.ZodString;
|
|
239
|
+
sequence: z.ZodNumber;
|
|
240
|
+
observedAt: z.ZodString;
|
|
241
|
+
value: z.ZodNumber;
|
|
242
|
+
lineage: z.ZodObject<{
|
|
243
|
+
modelProjectId: z.ZodString;
|
|
244
|
+
runId: z.ZodString;
|
|
245
|
+
modelVersionId: z.ZodNullable<z.ZodString>;
|
|
246
|
+
harnessReleaseHash: z.ZodString;
|
|
247
|
+
tasksetReleaseHash: z.ZodString;
|
|
248
|
+
environmentReleaseHash: z.ZodNullable<z.ZodString>;
|
|
249
|
+
checkpointId: z.ZodNullable<z.ZodString>;
|
|
250
|
+
step: z.ZodNullable<z.ZodNumber>;
|
|
251
|
+
rolloutGroupId: z.ZodNullable<z.ZodString>;
|
|
252
|
+
attemptId: z.ZodNullable<z.ZodString>;
|
|
253
|
+
scenarioId: z.ZodNullable<z.ZodString>;
|
|
254
|
+
}, z.core.$strict>;
|
|
255
|
+
dimensions: z.ZodRecord<z.ZodString, z.ZodString>;
|
|
256
|
+
}, z.core.$strict>>;
|
|
257
|
+
}, z.core.$strict>;
|
|
258
|
+
export type TelemetryVisibility = z.infer<typeof TelemetryVisibilitySchema>;
|
|
259
|
+
export type TelemetrySource = z.infer<typeof TelemetrySourceSchema>;
|
|
260
|
+
export type TelemetryEventType = z.infer<typeof TelemetryEventTypeSchema>;
|
|
261
|
+
export type RunTelemetryLineage = z.infer<typeof RunTelemetryLineageSchema>;
|
|
262
|
+
export type RunTelemetryEvent = z.infer<typeof RunTelemetryEventSchema>;
|
|
263
|
+
export type MetricDefinition = z.infer<typeof MetricDefinitionSchema>;
|
|
264
|
+
export type MetricObservation = z.infer<typeof MetricObservationSchema>;
|
|
265
|
+
export type RunTelemetryBatch = z.infer<typeof RunTelemetryBatchSchema>;
|
|
266
|
+
//# sourceMappingURL=telemetry.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"telemetry.d.ts","sourceRoot":"","sources":["../../../../src/telemetry.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AASxB,eAAO,MAAM,4BAA4B,EAAG,+BAAwC,CAAC;AACrF,eAAO,MAAM,gCAAgC,EAAG,8BAAuC,CAAC;AACxF,eAAO,MAAM,iCAAiC,EAAG,+BAAwC,CAAC;AAE1F,eAAO,MAAM,yBAAyB;;;;EAIpC,CAAC;AAEH,eAAO,MAAM,qBAAqB;;;;;;;EAOhC,CAAC;AAEH,eAAO,MAAM,wBAAwB;;;;;;;;;;;;;EAanC,CAAC;AAEH,eAAO,MAAM,yBAAyB;;;;;;;;;;;;kBAY3B,CAAC;AAEZ,eAAO,MAAM,uBAAuB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;kBAUzB,CAAC;AAEZ,eAAO,MAAM,qBAAqB;;;;EAA+C,CAAC;AAClF,eAAO,MAAM,gBAAgB;;;;;;;;;EAS3B,CAAC;AACH,eAAO,MAAM,qBAAqB;;;;EAAyC,CAAC;AAC5E,eAAO,MAAM,uBAAuB;;;;;;;;EAA8D,CAAC;AAEnG,eAAO,MAAM,sBAAsB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;kBAWxB,CAAC;AAEZ,eAAO,MAAM,uBAAuB;;;;;;;;;;;;;;;;;;;;;;kBAUzB,CAAC;AAEZ,eAAO,MAAM,uBAAuB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;kBAmBlC,CAAC;AAEH,MAAM,MAAM,mBAAmB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,yBAAyB,CAAC,CAAC;AAC5E,MAAM,MAAM,eAAe,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,qBAAqB,CAAC,CAAC;AACpE,MAAM,MAAM,kBAAkB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,wBAAwB,CAAC,CAAC;AAC1E,MAAM,MAAM,mBAAmB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,yBAAyB,CAAC,CAAC;AAC5E,MAAM,MAAM,iBAAiB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,uBAAuB,CAAC,CAAC;AACxE,MAAM,MAAM,gBAAgB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,sBAAsB,CAAC,CAAC;AACtE,MAAM,MAAM,iBAAiB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,uBAAuB,CAAC,CAAC;AACxE,MAAM,MAAM,iBAAiB,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,uBAAuB,CAAC,CAAC"}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@openpond/evals",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.6.0",
|
|
4
4
|
"description": "Portable Tasksets, graders, evaluation runs, receipts, conformance fixtures, and Work evidence for OpenPond Harnesses",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"type": "module",
|
|
@@ -8,6 +8,8 @@
|
|
|
8
8
|
"types": "./dist/types/index.d.ts",
|
|
9
9
|
"files": [
|
|
10
10
|
"dist",
|
|
11
|
+
"conformance",
|
|
12
|
+
"schemas",
|
|
11
13
|
"README.md",
|
|
12
14
|
"CONTRACT.md",
|
|
13
15
|
"RELEASING.md",
|
|
@@ -38,6 +40,22 @@
|
|
|
38
40
|
"types": "./dist/types/runs.d.ts",
|
|
39
41
|
"import": "./dist/runs.js"
|
|
40
42
|
},
|
|
43
|
+
"./rollouts": {
|
|
44
|
+
"types": "./dist/types/rollouts.d.ts",
|
|
45
|
+
"import": "./dist/rollouts.js"
|
|
46
|
+
},
|
|
47
|
+
"./telemetry": {
|
|
48
|
+
"types": "./dist/types/telemetry/index.d.ts",
|
|
49
|
+
"import": "./dist/telemetry/index.js"
|
|
50
|
+
},
|
|
51
|
+
"./preferences": {
|
|
52
|
+
"types": "./dist/types/preferences.d.ts",
|
|
53
|
+
"import": "./dist/preferences.js"
|
|
54
|
+
},
|
|
55
|
+
"./learned-preference": {
|
|
56
|
+
"types": "./dist/types/learned-preference.d.ts",
|
|
57
|
+
"import": "./dist/learned-preference.js"
|
|
58
|
+
},
|
|
41
59
|
"./review": {
|
|
42
60
|
"types": "./dist/types/review-conformance.d.ts",
|
|
43
61
|
"import": "./dist/review-conformance.js"
|
|
@@ -73,7 +91,7 @@
|
|
|
73
91
|
"node": ">=22.14.0 <25"
|
|
74
92
|
},
|
|
75
93
|
"scripts": {
|
|
76
|
-
"build": "tsx scripts/build.ts",
|
|
94
|
+
"build": "tsx scripts/generate-telemetry-schemas.ts && tsx scripts/build.ts",
|
|
77
95
|
"typecheck": "tsc --noEmit --project tsconfig.json",
|
|
78
96
|
"test": "vitest run --root ../.. --config vitest.config.ts --project evals",
|
|
79
97
|
"check:api": "tsx scripts/check-public-package.ts",
|
|
@@ -0,0 +1,82 @@
|
|
|
1
|
+
{
|
|
2
|
+
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
3
|
+
"type": "object",
|
|
4
|
+
"properties": {
|
|
5
|
+
"schemaVersion": {
|
|
6
|
+
"type": "string",
|
|
7
|
+
"const": "openpond.telemetryEvidenceCompleteness.v1"
|
|
8
|
+
},
|
|
9
|
+
"runId": {
|
|
10
|
+
"type": "string",
|
|
11
|
+
"minLength": 1,
|
|
12
|
+
"maxLength": 240
|
|
13
|
+
},
|
|
14
|
+
"status": {
|
|
15
|
+
"type": "string",
|
|
16
|
+
"enum": [
|
|
17
|
+
"complete",
|
|
18
|
+
"partial",
|
|
19
|
+
"missing"
|
|
20
|
+
]
|
|
21
|
+
},
|
|
22
|
+
"expectedEventTypes": {
|
|
23
|
+
"maxItems": 100,
|
|
24
|
+
"type": "array",
|
|
25
|
+
"items": {
|
|
26
|
+
"type": "string",
|
|
27
|
+
"minLength": 1,
|
|
28
|
+
"maxLength": 100
|
|
29
|
+
}
|
|
30
|
+
},
|
|
31
|
+
"observedEventTypes": {
|
|
32
|
+
"maxItems": 100,
|
|
33
|
+
"type": "array",
|
|
34
|
+
"items": {
|
|
35
|
+
"type": "string",
|
|
36
|
+
"minLength": 1,
|
|
37
|
+
"maxLength": 100
|
|
38
|
+
}
|
|
39
|
+
},
|
|
40
|
+
"missingEventTypes": {
|
|
41
|
+
"maxItems": 100,
|
|
42
|
+
"type": "array",
|
|
43
|
+
"items": {
|
|
44
|
+
"type": "string",
|
|
45
|
+
"minLength": 1,
|
|
46
|
+
"maxLength": 100
|
|
47
|
+
}
|
|
48
|
+
},
|
|
49
|
+
"lastSequence": {
|
|
50
|
+
"anyOf": [
|
|
51
|
+
{
|
|
52
|
+
"type": "integer",
|
|
53
|
+
"minimum": 0,
|
|
54
|
+
"maximum": 9007199254740991
|
|
55
|
+
},
|
|
56
|
+
{
|
|
57
|
+
"type": "null"
|
|
58
|
+
}
|
|
59
|
+
]
|
|
60
|
+
},
|
|
61
|
+
"sequenceGaps": {
|
|
62
|
+
"maxItems": 10000,
|
|
63
|
+
"type": "array",
|
|
64
|
+
"items": {
|
|
65
|
+
"type": "integer",
|
|
66
|
+
"minimum": 0,
|
|
67
|
+
"maximum": 9007199254740991
|
|
68
|
+
}
|
|
69
|
+
}
|
|
70
|
+
},
|
|
71
|
+
"required": [
|
|
72
|
+
"schemaVersion",
|
|
73
|
+
"runId",
|
|
74
|
+
"status",
|
|
75
|
+
"expectedEventTypes",
|
|
76
|
+
"observedEventTypes",
|
|
77
|
+
"missingEventTypes",
|
|
78
|
+
"lastSequence",
|
|
79
|
+
"sequenceGaps"
|
|
80
|
+
],
|
|
81
|
+
"additionalProperties": false
|
|
82
|
+
}
|
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
{
|
|
2
|
+
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
3
|
+
"type": "object",
|
|
4
|
+
"properties": {
|
|
5
|
+
"id": {
|
|
6
|
+
"type": "string",
|
|
7
|
+
"minLength": 1,
|
|
8
|
+
"maxLength": 240
|
|
9
|
+
},
|
|
10
|
+
"contentHash": {
|
|
11
|
+
"type": "string",
|
|
12
|
+
"pattern": "^[a-f0-9]{64}$"
|
|
13
|
+
},
|
|
14
|
+
"kind": {
|
|
15
|
+
"type": "string",
|
|
16
|
+
"enum": [
|
|
17
|
+
"rollout",
|
|
18
|
+
"attempt",
|
|
19
|
+
"trace",
|
|
20
|
+
"grader",
|
|
21
|
+
"checkpoint",
|
|
22
|
+
"artifact"
|
|
23
|
+
]
|
|
24
|
+
},
|
|
25
|
+
"visibility": {
|
|
26
|
+
"type": "string",
|
|
27
|
+
"enum": [
|
|
28
|
+
"policy_visible",
|
|
29
|
+
"team_visible",
|
|
30
|
+
"host_private"
|
|
31
|
+
]
|
|
32
|
+
}
|
|
33
|
+
},
|
|
34
|
+
"required": [
|
|
35
|
+
"id",
|
|
36
|
+
"contentHash",
|
|
37
|
+
"kind",
|
|
38
|
+
"visibility"
|
|
39
|
+
],
|
|
40
|
+
"additionalProperties": false
|
|
41
|
+
}
|
|
@@ -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
|
+
}
|