@wix/evalforge-types 0.66.0 → 0.68.0
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/build/index.mjs
CHANGED
|
@@ -1159,7 +1159,17 @@ var EvalRunSchema = TenantEntitySchema.extend({
|
|
|
1159
1159
|
/** Rule IDs to enable for this run (optional) */
|
|
1160
1160
|
ruleIds: z28.array(z28.string()).optional(),
|
|
1161
1161
|
/** Tags used to select scenarios for this run (for traceability) */
|
|
1162
|
-
tags: z28.array(z28.string()).optional()
|
|
1162
|
+
tags: z28.array(z28.string()).optional(),
|
|
1163
|
+
/** How many times each scenario is executed within this eval run. Default: 1. Max: 20. */
|
|
1164
|
+
runsPerScenario: z28.number().int().min(1).max(20).optional(),
|
|
1165
|
+
/** Snapshot of agent configuration captured at run creation time */
|
|
1166
|
+
agentSnapshot: z28.object({
|
|
1167
|
+
name: z28.string().optional(),
|
|
1168
|
+
agentType: AgentTypeSchema.optional(),
|
|
1169
|
+
runCommand: AgentRunCommandSchema.optional(),
|
|
1170
|
+
systemPrompt: z28.string().nullable().optional(),
|
|
1171
|
+
modelConfig: ModelConfigSchema.optional()
|
|
1172
|
+
}).optional()
|
|
1163
1173
|
});
|
|
1164
1174
|
var CreateEvalRunInputSchema = EvalRunSchema.omit({
|
|
1165
1175
|
id: true,
|
|
@@ -1171,7 +1181,8 @@ var CreateEvalRunInputSchema = EvalRunSchema.omit({
|
|
|
1171
1181
|
aggregateMetrics: true,
|
|
1172
1182
|
startedAt: true,
|
|
1173
1183
|
completedAt: true,
|
|
1174
|
-
scenarioIds: true
|
|
1184
|
+
scenarioIds: true,
|
|
1185
|
+
agentSnapshot: true
|
|
1175
1186
|
}).extend({
|
|
1176
1187
|
/** Optional on input — backend resolves from tags when not provided */
|
|
1177
1188
|
scenarioIds: z28.array(z28.string()).optional()
|
|
@@ -1283,6 +1294,8 @@ var EvalRunResultSchema = z30.object({
|
|
|
1283
1294
|
skillVersion: z30.string().optional(),
|
|
1284
1295
|
scenarioId: z30.string(),
|
|
1285
1296
|
scenarioName: z30.string(),
|
|
1297
|
+
/** Snapshot of the trigger prompt used during the run (prevents stale display after edits) */
|
|
1298
|
+
triggerPrompt: z30.string().optional(),
|
|
1286
1299
|
modelConfig: ModelConfigSchema.optional(),
|
|
1287
1300
|
assertionResults: z30.array(AssertionResultSchema),
|
|
1288
1301
|
metrics: EvalMetricsSchema.optional(),
|
|
@@ -1299,7 +1312,9 @@ var EvalRunResultSchema = z30.object({
|
|
|
1299
1312
|
completedAt: z30.string().optional(),
|
|
1300
1313
|
llmTrace: LLMTraceSchema.optional(),
|
|
1301
1314
|
/** Full conversation messages (only present in transit; stripped before DB storage) */
|
|
1302
|
-
conversation: z30.array(ConversationMessageSchema).optional()
|
|
1315
|
+
conversation: z30.array(ConversationMessageSchema).optional(),
|
|
1316
|
+
/** 0-based iteration index when a scenario is run multiple times within a single eval run */
|
|
1317
|
+
iterationIndex: z30.number().int().min(0).optional()
|
|
1303
1318
|
});
|
|
1304
1319
|
var PromptResultSchema = z30.object({
|
|
1305
1320
|
text: z30.string(),
|