@uipath/eval-tool 1.204.0-preview.255 → 1.205.0-preview.256
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/dist/{index-e37shzn2.js → index-wm83gmqp.js} +10830 -26616
- package/dist/index.js +2 -2
- package/dist/{tool-xjm2b7dx.js → tool-6dab0khy.js} +40 -44
- package/dist/{tool-wqrb8d7k.js → tool-ja7k1eac.js} +284 -172
- package/dist/tool.js +2 -2
- package/package.json +2 -2
package/dist/index.js
CHANGED
|
@@ -9,7 +9,7 @@ import {
|
|
|
9
9
|
getAuthContext,
|
|
10
10
|
instructionsFor,
|
|
11
11
|
processContext
|
|
12
|
-
} from "./tool-
|
|
12
|
+
} from "./tool-ja7k1eac.js";
|
|
13
13
|
import {
|
|
14
14
|
__require
|
|
15
15
|
} from "./tool-1de529jm.js";
|
|
@@ -18,7 +18,7 @@ var package_default = {
|
|
|
18
18
|
name: "@uipath/eval-tool",
|
|
19
19
|
author: "UiPath",
|
|
20
20
|
license: "SEE LICENSE IN LICENSE.txt",
|
|
21
|
-
version: "1.
|
|
21
|
+
version: "1.205.0-preview.256",
|
|
22
22
|
description: "Manage runtime evaluations, evaluators, eval sets, evaluations, and schedules.",
|
|
23
23
|
private: false,
|
|
24
24
|
repository: {
|
|
@@ -379,7 +379,7 @@ function registerEvalEvaluationsCommand(evalCmd) {
|
|
|
379
379
|
})
|
|
380
380
|
});
|
|
381
381
|
});
|
|
382
|
-
evaluationCmd.command("get").description("Get details of a specific evaluation.").argument("<
|
|
382
|
+
evaluationCmd.command("get").description("Get details of a specific evaluation.").argument("<evaluation-id>", "Evaluation ID (GUID)").requiredOption("--process-key <guid>", "Process key (GUID). Use 'uip or processes list' to find keys.").requiredOption("--eval-set-id <guid>", "Eval set ID (GUID)").option("--tenant <tenant>", "UiPath tenant name").trackedAction(processContext, async (evaluationId, options) => {
|
|
383
383
|
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
384
384
|
if (!auth)
|
|
385
385
|
return;
|
|
@@ -439,7 +439,7 @@ function registerEvalEvaluationsCommand(evalCmd) {
|
|
|
439
439
|
Data: formatEvaluation(evaluation)
|
|
440
440
|
});
|
|
441
441
|
});
|
|
442
|
-
evaluationCmd.command("update").description("Update an existing evaluation. Provide at least one field to change.").argument("<
|
|
442
|
+
evaluationCmd.command("update").description("Update an existing evaluation. Provide at least one field to change.").argument("<evaluation-id>", "Evaluation ID (GUID)").requiredOption("--process-key <guid>", "Process key (GUID). Use 'uip or processes list' to find keys.").requiredOption("--eval-set-id <guid>", "Eval set ID (GUID)").option("--name <name>", "New evaluation name").option("--inputs <json>", "New input values as JSON").option("--expected-output <json>", "New expected output as JSON").option("--expected-behavior <text>", "New expected behavior description").option("--evaluation-criterias <json>", "New per-evaluator criteria overrides as JSON").option("--simulations <json>", 'New simulations as JSON array. Each object needs "componentId" and "componentType". ' + "For LLM strategy, outputSchema is auto-resolved from the deployed agent.").option("--tenant <tenant>", "UiPath tenant name").examples(UPDATE_EXAMPLES).trackedAction(processContext, async (evaluationId, options) => {
|
|
443
443
|
if (options.name === undefined && options.inputs === undefined && options.expectedOutput === undefined && options.expectedBehavior === undefined && options.evaluationCriterias === undefined && options.simulations === undefined) {
|
|
444
444
|
OutputFormatter.error({
|
|
445
445
|
Result: RESULTS.Failure,
|
|
@@ -503,7 +503,7 @@ function registerEvalEvaluationsCommand(evalCmd) {
|
|
|
503
503
|
Data: formatEvaluation(evaluation)
|
|
504
504
|
});
|
|
505
505
|
});
|
|
506
|
-
evaluationCmd.command("delete").description("Delete an evaluation from an eval set.").argument("<
|
|
506
|
+
evaluationCmd.command("delete").description("Delete an evaluation from an eval set.").argument("<evaluation-id>", "Evaluation ID (GUID)").requiredOption("--process-key <guid>", "Process key (GUID). Use 'uip or processes list' to find keys.").requiredOption("--eval-set-id <guid>", "Eval set ID (GUID)").option("--tenant <tenant>", "UiPath tenant name").trackedAction(processContext, async (evaluationId, options) => {
|
|
507
507
|
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
508
508
|
if (!auth)
|
|
509
509
|
return;
|
|
@@ -606,7 +606,7 @@ function registerEvalEvaluatorsCommand(evalCmd) {
|
|
|
606
606
|
})
|
|
607
607
|
});
|
|
608
608
|
});
|
|
609
|
-
evaluatorCmd.command("get").description("Get details of a specific evaluator.").argument("<
|
|
609
|
+
evaluatorCmd.command("get").description("Get details of a specific evaluator.").argument("<evaluator-id>", "Evaluator ID (GUID)").requiredOption("--process-key <guid>", "Process key (GUID). Use 'uip or processes list' to find keys.").option("--tenant <tenant>", "UiPath tenant name").trackedAction(processContext, async (evaluatorId, options) => {
|
|
610
610
|
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
611
611
|
if (!auth)
|
|
612
612
|
return;
|
|
@@ -645,7 +645,7 @@ function registerEvalEvaluatorsCommand(evalCmd) {
|
|
|
645
645
|
Data: formatEvaluator(evaluator)
|
|
646
646
|
});
|
|
647
647
|
});
|
|
648
|
-
evaluatorCmd.command("update").description("Update an existing evaluator. Provide at least one field to change.").argument("<
|
|
648
|
+
evaluatorCmd.command("update").description("Update an existing evaluator. Provide at least one field to change.").argument("<evaluator-id>", "Evaluator ID (GUID)").requiredOption("--process-key <guid>", "Process key (GUID). Use 'uip or processes list' to find keys.").option("--name <name>", "New evaluator name").option("--description <text>", "New evaluator description").option("--evaluator-type-id <id>", "Evaluator type ID (e.g. uipath-exact-match, uipath-llm-judge-output-semantic-similarity, uipath-llm-judge-trajectory-similarity)").option("--evaluator-config <json>", "Evaluator config as JSON object").option("--version <version>", "Evaluator version").option("--tenant <tenant>", "UiPath tenant name").examples(UPDATE_EXAMPLES2).trackedAction(processContext, async (evaluatorId, options) => {
|
|
649
649
|
if (options.name === undefined && options.description === undefined && options.evaluatorTypeId === undefined && options.evaluatorConfig === undefined && options.version === undefined) {
|
|
650
650
|
OutputFormatter.error({
|
|
651
651
|
Result: RESULTS.Failure,
|
|
@@ -688,7 +688,7 @@ function registerEvalEvaluatorsCommand(evalCmd) {
|
|
|
688
688
|
Data: formatEvaluator(evaluator)
|
|
689
689
|
});
|
|
690
690
|
});
|
|
691
|
-
evaluatorCmd.command("delete").description("Delete an evaluator.").argument("<
|
|
691
|
+
evaluatorCmd.command("delete").description("Delete an evaluator.").argument("<evaluator-id>", "Evaluator ID (GUID)").requiredOption("--process-key <guid>", "Process key (GUID). Use 'uip or processes list' to find keys.").option("--tenant <tenant>", "UiPath tenant name").trackedAction(processContext, async (evaluatorId, options) => {
|
|
692
692
|
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
693
693
|
if (!auth)
|
|
694
694
|
return;
|
|
@@ -810,7 +810,7 @@ function registerEvalProcessRunsCommand(evalCmd) {
|
|
|
810
810
|
})
|
|
811
811
|
});
|
|
812
812
|
});
|
|
813
|
-
runCmd.command("get").description("Get details of a specific eval set run by process key.").argument("<
|
|
813
|
+
runCmd.command("get").description("Get details of a specific eval set run by process key.").argument("<eval-set-run-id>", "Eval set run ID (GUID)").requiredOption("--process-key <guid>", "Process key (deployment GUID).").option("--tenant <tenant>", "UiPath tenant name").examples(GET_RUN_EXAMPLES).trackedAction(processContext, async (evalSetRunId, options) => {
|
|
814
814
|
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
815
815
|
if (!auth)
|
|
816
816
|
return;
|
|
@@ -824,7 +824,7 @@ function registerEvalProcessRunsCommand(evalCmd) {
|
|
|
824
824
|
Data: formatEvalSetRun(run)
|
|
825
825
|
});
|
|
826
826
|
});
|
|
827
|
-
runCmd.command("results").description("View per-item eval run results for an eval set run by process key.").argument("<
|
|
827
|
+
runCmd.command("results").description("View per-item eval run results for an eval set run by process key.").argument("<eval-set-run-id>", "Eval set run ID (GUID)").requiredOption("--process-key <guid>", "Process key (deployment GUID).").option("--tenant <tenant>", "UiPath tenant name").examples(RESULTS_EXAMPLES).trackedAction(processContext, async (evalSetRunId, options) => {
|
|
828
828
|
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
829
829
|
if (!auth)
|
|
830
830
|
return;
|
|
@@ -1068,7 +1068,7 @@ async function resolveInline(options) {
|
|
|
1068
1068
|
folderKey = options.folderKey;
|
|
1069
1069
|
folderLabel = folderKey;
|
|
1070
1070
|
} else {
|
|
1071
|
-
const { createApiClient, PersonalWorkspacesApi } = await import("./index-
|
|
1071
|
+
const { createApiClient, PersonalWorkspacesApi } = await import("./index-wm83gmqp.js");
|
|
1072
1072
|
const [wsApiErr, wsApi] = await catchError(createApiClient(PersonalWorkspacesApi, {
|
|
1073
1073
|
tenant: options.tenant
|
|
1074
1074
|
}));
|
|
@@ -1228,6 +1228,26 @@ function formatSchedule(schedule) {
|
|
|
1228
1228
|
...schedule.updatedAt ? { UpdatedAt: schedule.updatedAt } : {}
|
|
1229
1229
|
};
|
|
1230
1230
|
}
|
|
1231
|
+
var SCHEDULE_STATE_CODES = {
|
|
1232
|
+
pause: "EvalSchedulePaused",
|
|
1233
|
+
resume: "EvalScheduleResumed"
|
|
1234
|
+
};
|
|
1235
|
+
async function setScheduleState(scheduleId, options, action) {
|
|
1236
|
+
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
1237
|
+
if (!auth)
|
|
1238
|
+
return;
|
|
1239
|
+
const schedule = await evalApiRequestOrFail(`${scheduleUrl(auth.agentsApiBase, options.processKey, scheduleId)}/${action}`, auth.authHeaders, "PUT", "Check the schedule ID and process key.");
|
|
1240
|
+
if (!schedule)
|
|
1241
|
+
return;
|
|
1242
|
+
OutputFormatter.success({
|
|
1243
|
+
Result: RESULTS.Success,
|
|
1244
|
+
Code: SCHEDULE_STATE_CODES[action],
|
|
1245
|
+
Data: formatSchedule(schedule)
|
|
1246
|
+
});
|
|
1247
|
+
}
|
|
1248
|
+
function scheduleStateAction(action) {
|
|
1249
|
+
return (scheduleId, options) => setScheduleState(scheduleId, options, action);
|
|
1250
|
+
}
|
|
1231
1251
|
function registerEvalScheduleCommand(evalCmd) {
|
|
1232
1252
|
const scheduleCmd = evalCmd.command("schedule").description("Manage eval schedules for agent processes. " + "Create, list, update, pause, resume, and delete scheduled evaluation runs.");
|
|
1233
1253
|
scheduleCmd.command("create").description("Create a new eval schedule for a process.").requiredOption("--process-key <guid>", "Process key (deployment GUID) — identifies the Orchestrator release.").option("--workload-id <guid>", "Workload ID (GUID). Resolved from the eval set when omitted.").requiredOption("--eval-set-id <guid>", "Eval set ID (GUID) — the evaluation set to run.").requiredOption("--cron <expression>", 'Five-field cron expression in UTC (e.g. "0 9 * * *" for daily at 9 AM).').option("--folder-key <guid>", "Orchestrator folder key (GUID). Resolved from the eval set when omitted.").option("--tenant <tenant>", "UiPath tenant name").examples(CREATE_EXAMPLES3).trackedAction(processContext, async (options) => {
|
|
@@ -1276,7 +1296,7 @@ function registerEvalScheduleCommand(evalCmd) {
|
|
|
1276
1296
|
Data: schedules.map(formatSchedule)
|
|
1277
1297
|
});
|
|
1278
1298
|
});
|
|
1279
|
-
scheduleCmd.command("get").description("Get details of a specific eval schedule.").argument("<
|
|
1299
|
+
scheduleCmd.command("get").description("Get details of a specific eval schedule.").argument("<schedule-id>", "Eval schedule ID (GUID)").requiredOption("--process-key <guid>", "Process key (deployment GUID).").option("--tenant <tenant>", "UiPath tenant name").trackedAction(processContext, async (scheduleId, options) => {
|
|
1280
1300
|
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
1281
1301
|
if (!auth)
|
|
1282
1302
|
return;
|
|
@@ -1289,7 +1309,7 @@ function registerEvalScheduleCommand(evalCmd) {
|
|
|
1289
1309
|
Data: formatSchedule(schedule)
|
|
1290
1310
|
});
|
|
1291
1311
|
});
|
|
1292
|
-
scheduleCmd.command("update").description("Update an existing eval schedule. Provide at least one field to change.").argument("<
|
|
1312
|
+
scheduleCmd.command("update").description("Update an existing eval schedule. Provide at least one field to change.").argument("<schedule-id>", "Eval schedule ID (GUID)").requiredOption("--process-key <guid>", "Process key (deployment GUID).").option("--eval-set-id <guid>", "New eval set ID").option("--cron <expression>", "New five-field cron expression in UTC").option("--tenant <tenant>", "UiPath tenant name").examples(UPDATE_EXAMPLES3).trackedAction(processContext, async (scheduleId, options) => {
|
|
1293
1313
|
if (options.evalSetId === undefined && options.cron === undefined) {
|
|
1294
1314
|
OutputFormatter.error({
|
|
1295
1315
|
Result: RESULTS.Failure,
|
|
@@ -1318,33 +1338,9 @@ function registerEvalScheduleCommand(evalCmd) {
|
|
|
1318
1338
|
Data: formatSchedule(schedule)
|
|
1319
1339
|
});
|
|
1320
1340
|
});
|
|
1321
|
-
scheduleCmd.command("pause").description("Pause an active eval schedule.").argument("<
|
|
1322
|
-
|
|
1323
|
-
|
|
1324
|
-
return;
|
|
1325
|
-
const schedule = await evalApiRequestOrFail(`${scheduleUrl(auth.agentsApiBase, options.processKey, scheduleId)}/pause`, auth.authHeaders, "PUT", "Check the schedule ID and process key.");
|
|
1326
|
-
if (!schedule)
|
|
1327
|
-
return;
|
|
1328
|
-
OutputFormatter.success({
|
|
1329
|
-
Result: RESULTS.Success,
|
|
1330
|
-
Code: "EvalSchedulePaused",
|
|
1331
|
-
Data: formatSchedule(schedule)
|
|
1332
|
-
});
|
|
1333
|
-
});
|
|
1334
|
-
scheduleCmd.command("resume").description("Resume a paused eval schedule.").argument("<scheduleId>", "Eval schedule ID (GUID)").requiredOption("--process-key <guid>", "Process key (deployment GUID).").option("--tenant <tenant>", "UiPath tenant name").trackedAction(processContext, async (scheduleId, options) => {
|
|
1335
|
-
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
1336
|
-
if (!auth)
|
|
1337
|
-
return;
|
|
1338
|
-
const schedule = await evalApiRequestOrFail(`${scheduleUrl(auth.agentsApiBase, options.processKey, scheduleId)}/resume`, auth.authHeaders, "PUT", "Check the schedule ID and process key.");
|
|
1339
|
-
if (!schedule)
|
|
1340
|
-
return;
|
|
1341
|
-
OutputFormatter.success({
|
|
1342
|
-
Result: RESULTS.Success,
|
|
1343
|
-
Code: "EvalScheduleResumed",
|
|
1344
|
-
Data: formatSchedule(schedule)
|
|
1345
|
-
});
|
|
1346
|
-
});
|
|
1347
|
-
scheduleCmd.command("delete").description("Delete an eval schedule.").argument("<scheduleId>", "Eval schedule ID (GUID)").requiredOption("--process-key <guid>", "Process key (deployment GUID).").option("--tenant <tenant>", "UiPath tenant name").examples(DELETE_EXAMPLES).trackedAction(processContext, async (scheduleId, options) => {
|
|
1341
|
+
scheduleCmd.command("pause").description("Pause an active eval schedule.").argument("<schedule-id>", "Eval schedule ID (GUID)").requiredOption("--process-key <guid>", "Process key (deployment GUID).").option("--tenant <tenant>", "UiPath tenant name").trackedAction(processContext, scheduleStateAction("pause"));
|
|
1342
|
+
scheduleCmd.command("resume").description("Resume a paused eval schedule.").argument("<schedule-id>", "Eval schedule ID (GUID)").requiredOption("--process-key <guid>", "Process key (deployment GUID).").option("--tenant <tenant>", "UiPath tenant name").trackedAction(processContext, scheduleStateAction("resume"));
|
|
1343
|
+
scheduleCmd.command("delete").description("Delete an eval schedule.").argument("<schedule-id>", "Eval schedule ID (GUID)").requiredOption("--process-key <guid>", "Process key (deployment GUID).").option("--tenant <tenant>", "UiPath tenant name").examples(DELETE_EXAMPLES).trackedAction(processContext, async (scheduleId, options) => {
|
|
1348
1344
|
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
1349
1345
|
if (!auth)
|
|
1350
1346
|
return;
|
|
@@ -1445,7 +1441,7 @@ function registerEvalSetsCommand(evalCmd) {
|
|
|
1445
1441
|
})
|
|
1446
1442
|
});
|
|
1447
1443
|
});
|
|
1448
|
-
evalSetCmd.command("get").description("Get details of a specific eval set.").argument("<
|
|
1444
|
+
evalSetCmd.command("get").description("Get details of a specific eval set.").argument("<eval-set-id>", "Eval set ID (GUID)").requiredOption("--process-key <guid>", "Process key (GUID). Use 'uip or processes list' to find keys.").option("--tenant <tenant>", "UiPath tenant name").trackedAction(processContext, async (evalSetId, options) => {
|
|
1449
1445
|
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
1450
1446
|
if (!auth)
|
|
1451
1447
|
return;
|
|
@@ -1492,7 +1488,7 @@ function registerEvalSetsCommand(evalCmd) {
|
|
|
1492
1488
|
Data: formatEvalSet(evalSet)
|
|
1493
1489
|
});
|
|
1494
1490
|
});
|
|
1495
|
-
evalSetCmd.command("update").description("Update an existing eval set. Provide at least one field to change.").argument("<
|
|
1491
|
+
evalSetCmd.command("update").description("Update an existing eval set. Provide at least one field to change.").argument("<eval-set-id>", "Eval set ID (GUID)").requiredOption("--process-key <guid>", "Process key (GUID). Use 'uip or processes list' to find keys.").option("--name <name>", "New eval set name").option("--description <text>", "New description").option("--batch-size <n>", "Max concurrent evaluations").option("--timeout-minutes <n>", "Timeout in minutes per evaluation").option("--evaluator-refs <refs...>", "Evaluator ExternalIds to link to this eval set (from 'uip eval evaluator list')").option("--tenant <tenant>", "UiPath tenant name").examples(UPDATE_EXAMPLES4).trackedAction(processContext, async (evalSetId, options) => {
|
|
1496
1492
|
if (options.name === undefined && options.description === undefined && options.batchSize === undefined && options.timeoutMinutes === undefined && options.evaluatorRefs === undefined) {
|
|
1497
1493
|
OutputFormatter.error({
|
|
1498
1494
|
Result: RESULTS.Failure,
|
|
@@ -1543,7 +1539,7 @@ function registerEvalSetsCommand(evalCmd) {
|
|
|
1543
1539
|
Data: formatEvalSet(evalSet)
|
|
1544
1540
|
});
|
|
1545
1541
|
});
|
|
1546
|
-
evalSetCmd.command("delete").description("Delete an eval set.").argument("<
|
|
1542
|
+
evalSetCmd.command("delete").description("Delete an eval set.").argument("<eval-set-id>", "Eval set ID (GUID)").requiredOption("--process-key <guid>", "Process key (GUID). Use 'uip or processes list' to find keys.").option("--tenant <tenant>", "UiPath tenant name").trackedAction(processContext, async (evalSetId, options) => {
|
|
1547
1543
|
const auth = await resolveEvalAuthOrFail(options.tenant);
|
|
1548
1544
|
if (!auth)
|
|
1549
1545
|
return;
|
|
@@ -1635,4 +1631,4 @@ var registerCommands = async (program) => {
|
|
|
1635
1631
|
|
|
1636
1632
|
export { metadata, registerCommands };
|
|
1637
1633
|
|
|
1638
|
-
//# debugId=
|
|
1634
|
+
//# debugId=A7DFA0ABF600CE1B64756E2164756E21
|