@ora-ai/cli 0.3.0 → 0.4.0

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 (8) hide show
  1. package/dist/generated/operations.d.ts +1 -1
  2. package/dist/generated/operations.d.ts.map +1 -1
  3. package/dist/generated/operations.js +155 -3
  4. package/dist/generated/operations.js.map +1 -1
  5. package/dist/generated/types.d.ts +401 -2
  6. package/dist/generated/types.d.ts.map +1 -1
  7. package/dist/generated/types.js +1 -1
  8. package/package.json +1 -1
package/dist/generated/types.d.ts CHANGED
@@ -61,9 +61,12 @@ export type BenchmarksListResponse = {
61
61
  "provider"?: string;
62
62
  }>;
63
63
  "taskCount": number;
64
+ "variantsPerTask": number;
65
+ "repeats": number;
64
66
  "status": string;
65
67
  "error": string | null;
66
68
  "visibility": "private" | "public";
69
+ "lowSampleOverride": boolean;
67
70
  "publishedAt": string | null;
68
71
  "verdict": unknown;
69
72
  "createdAt": string;
@@ -94,12 +97,15 @@ export type BenchmarksCreateRequest = {
94
97
  "baselineLabel"?: string;
95
98
  "treatmentLabel"?: string;
96
99
  "taskCount"?: number;
100
+ "variantsPerTask"?: number;
101
+ "repeats"?: number;
97
102
  "tasks"?: Array<{
98
103
  "prompt": string;
99
104
  "rationale"?: string;
100
105
  "category"?: string;
101
106
  "requiresWeb"?: boolean;
102
107
  "rubric": Array<string>;
108
+ "variants"?: Array<string>;
103
109
  }>;
104
110
  "matrix": Array<{
105
111
  "harness": string;
@@ -153,9 +159,12 @@ export type BenchmarksCreateResponse = {
153
159
  "provider"?: string;
154
160
  }>;
155
161
  "taskCount": number;
162
+ "variantsPerTask": number;
163
+ "repeats": number;
156
164
  "status": string;
157
165
  "error": string | null;
158
166
  "visibility": "private" | "public";
167
+ "lowSampleOverride": boolean;
159
168
  "publishedAt": string | null;
160
169
  "verdict": unknown;
161
170
  "createdAt": string;
@@ -208,9 +217,12 @@ export type BenchmarksGetResponse = {
208
217
  "provider"?: string;
209
218
  }>;
210
219
  "taskCount": number;
220
+ "variantsPerTask": number;
221
+ "repeats": number;
211
222
  "status": string;
212
223
  "error": string | null;
213
224
  "visibility": "private" | "public";
225
+ "lowSampleOverride": boolean;
214
226
  "publishedAt": string | null;
215
227
  "verdict": unknown;
216
228
  "createdAt": string;
@@ -225,6 +237,7 @@ export type BenchmarksGetResponse = {
225
237
  "category": string | null;
226
238
  "requiresWeb": boolean;
227
239
  "rubric": Array<string>;
240
+ "variants"?: Array<string> | null;
228
241
  }>;
229
242
  "runs": Array<{
230
243
  "runId": string;
@@ -233,6 +246,8 @@ export type BenchmarksGetResponse = {
233
246
  "harness": string;
234
247
  "model": string;
235
248
  "provider": string | null;
249
+ "variantIndex"?: number;
250
+ "repeatIndex"?: number;
236
251
  "status": string;
237
252
  "outcome": string | null;
238
253
  "outcomeReason": string | null;
@@ -255,11 +270,21 @@ export type BenchmarksGetResponse = {
255
270
  "votes"?: {
256
271
  "passed": number;
257
272
  "judges": number;
273
+ "byJudge"?: Array<{
274
+ "judge": string;
275
+ "passed": boolean;
276
+ "note"?: string;
277
+ }>;
258
278
  };
259
279
  }> | null;
260
280
  "gradedAt": string | null;
261
281
  "judgeModel": string | null;
262
282
  "pairVerdict": "skill" | "baseline" | "tie" | "unmeasurable" | null;
283
+ "pairVotes": Array<{
284
+ "judge": string;
285
+ "ordering": "base-first" | "skill-first";
286
+ "answer": "A" | "B" | "tie";
287
+ }> | null;
263
288
  "pairGradedAt": string | null;
264
289
  "runCreatedAt": string | null;
265
290
  "startedAt": string | null;
@@ -268,7 +293,27 @@ export type BenchmarksGetResponse = {
268
293
  "aggregate": {
269
294
  "summary": {
270
295
  "verdict": "delivered" | "partial" | "not_delivered" | "inconclusive" | "measured";
271
- "headline": Array<unknown>;
296
+ "headline": Array<{
297
+ "metric": "total_tokens" | "output_tokens" | "cost_usd" | "duration_ms" | "num_turns" | "success_rate" | "completion_rate" | "goal_rate";
298
+ "label": string;
299
+ "direction": "down" | "up";
300
+ "baselineAvg": number | null;
301
+ "skillAvg": number | null;
302
+ "deltaPct": number | null;
303
+ "delta"?: {
304
+ "unit": "pp";
305
+ "absolute": number | null;
306
+ "relativePct": number | null;
307
+ } | {
308
+ "unit": "pts";
309
+ "absolute": number | null;
310
+ "relativePct"?: number | null;
311
+ } | {
312
+ "unit": "%";
313
+ "relativePct": number | null;
314
+ };
315
+ "improved": boolean;
316
+ }>;
272
317
  "completionRate": {
273
318
  "baseline": number | null;
274
319
  "skill": number | null;
@@ -284,7 +329,102 @@ export type BenchmarksGetResponse = {
284
329
  "ties": number;
285
330
  "winRate": number | null;
286
331
  };
332
+ "decision"?: {
333
+ "winner": "treatment" | "baseline" | "tie" | "unmeasurable";
334
+ "basis": "infra" | "goal" | "quality" | "efficiency" | "judge" | "insufficient";
335
+ "reason": string;
336
+ "efficiencyDiscounted": boolean;
337
+ };
287
338
  "leaderboard"?: Array<unknown>;
339
+ "concentration": {
340
+ "perCell": Array<{
341
+ "cell": string;
342
+ "goalDeltaPp": number | null;
343
+ "contributionPct": number | null;
344
+ }>;
345
+ "heterogeneity": {
346
+ "dominantCell": string;
347
+ "contributionPct": number;
348
+ } | null;
349
+ };
350
+ "matrixShape": {
351
+ "cells": number;
352
+ "harnesses": number;
353
+ "models": number;
354
+ "crossed": boolean;
355
+ };
356
+ "flakiness"?: {
357
+ "measured": boolean;
358
+ "conditions": number;
359
+ "unstable": number;
360
+ "worst": {
361
+ "cell": string;
362
+ "taskId": string;
363
+ "arm": "baseline" | "skill";
364
+ "variant"?: number;
365
+ "passRate": number;
366
+ } | null;
367
+ };
368
+ "arms"?: {
369
+ "baseline": {
370
+ "runs": number;
371
+ "completed": number;
372
+ "infraFailures": number;
373
+ "completionRate": number | null;
374
+ "goalRate": number | null;
375
+ "goalTally": {
376
+ "achieved": number;
377
+ "partial": number;
378
+ "missed": number;
379
+ };
380
+ "avgTotalTokens": number | null;
381
+ "avgOutputTokens": number | null;
382
+ "avgCostUsd": number | null;
383
+ "avgDurationMs": number | null;
384
+ "avgTurns": number | null;
385
+ "costCoverage": number | null;
386
+ "avgQualityScore": number | null;
387
+ "gradedCoverage": number | null;
388
+ "medianCostUsd": number | null;
389
+ "medianTotalTokens": number | null;
390
+ "medianDurationMs": number | null;
391
+ "p95CostUsd": number | null;
392
+ "p95TotalTokens": number | null;
393
+ "p95DurationMs": number | null;
394
+ "maxCostUsd": number | null;
395
+ "maxTotalTokens": number | null;
396
+ "maxDurationMs": number | null;
397
+ };
398
+ "skill": {
399
+ "runs": number;
400
+ "completed": number;
401
+ "infraFailures": number;
402
+ "completionRate": number | null;
403
+ "goalRate": number | null;
404
+ "goalTally": {
405
+ "achieved": number;
406
+ "partial": number;
407
+ "missed": number;
408
+ };
409
+ "avgTotalTokens": number | null;
410
+ "avgOutputTokens": number | null;
411
+ "avgCostUsd": number | null;
412
+ "avgDurationMs": number | null;
413
+ "avgTurns": number | null;
414
+ "costCoverage": number | null;
415
+ "avgQualityScore": number | null;
416
+ "gradedCoverage": number | null;
417
+ "medianCostUsd": number | null;
418
+ "medianTotalTokens": number | null;
419
+ "medianDurationMs": number | null;
420
+ "p95CostUsd": number | null;
421
+ "p95TotalTokens": number | null;
422
+ "p95DurationMs": number | null;
423
+ "maxCostUsd": number | null;
424
+ "maxTotalTokens": number | null;
425
+ "maxDurationMs": number | null;
426
+ };
427
+ };
288
428
  "totals": {
289
429
  "cells": number;
290
430
  "runs": number;
@@ -316,6 +456,9 @@ export type BenchmarksGetResponse = {
316
456
  };
317
457
  };
318
458
  export type BenchmarksDeleteResponse = unknown;
459
+ export type BenchmarksRegenerateSummaryResponse = {
460
+ "status": "queued";
461
+ };
319
462
  export type BenchmarksGenerateResponse = {
320
463
  "benchmark": {
321
464
  "id": string;
@@ -361,9 +504,12 @@ export type BenchmarksGenerateResponse = {
361
504
  "provider"?: string;
362
505
  }>;
363
506
  "taskCount": number;
507
+ "variantsPerTask": number;
508
+ "repeats": number;
364
509
  "status": string;
365
510
  "error": string | null;
366
511
  "visibility": "private" | "public";
512
+ "lowSampleOverride": boolean;
367
513
  "publishedAt": string | null;
368
514
  "verdict": unknown;
369
515
  "createdAt": string;
@@ -416,9 +562,12 @@ export type BenchmarksLaunchResponse = {
416
562
  "provider"?: string;
417
563
  }>;
418
564
  "taskCount": number;
565
+ "variantsPerTask": number;
566
+ "repeats": number;
419
567
  "status": string;
420
568
  "error": string | null;
421
569
  "visibility": "private" | "public";
570
+ "lowSampleOverride": boolean;
422
571
  "publishedAt": string | null;
423
572
  "verdict": unknown;
424
573
  "createdAt": string;
@@ -466,6 +615,8 @@ export type BenchmarksPreviewResponse = {
466
615
  "provider"?: string;
467
616
  }>;
468
617
  "taskCount": number;
618
+ "variantsPerTask": number;
619
+ "repeats": number;
469
620
  "status": string;
470
621
  "publishedAt": string | null;
471
622
  "createdAt": string;
@@ -478,6 +629,7 @@ export type BenchmarksPreviewResponse = {
478
629
  "category": string | null;
479
630
  "requiresWeb": boolean;
480
631
  "rubric": Array<string>;
632
+ "variants"?: Array<string> | null;
481
633
  }>;
482
634
  "runs": Array<{
483
635
  "runId": string;
@@ -486,6 +638,8 @@ export type BenchmarksPreviewResponse = {
486
638
  "harness": string;
487
639
  "model": string;
488
640
  "provider": string | null;
641
+ "variantIndex"?: number;
642
+ "repeatIndex"?: number;
489
643
  "status": string;
490
644
  "outcome": string | null;
491
645
  "outcomeReason": string | null;
@@ -508,11 +662,21 @@ export type BenchmarksPreviewResponse = {
508
662
  "votes"?: {
509
663
  "passed": number;
510
664
  "judges": number;
665
+ "byJudge"?: Array<{
666
+ "judge": string;
667
+ "passed": boolean;
668
+ "note"?: string;
669
+ }>;
511
670
  };
512
671
  }> | null;
513
672
  "gradedAt": string | null;
514
673
  "judgeModel": string | null;
515
674
  "pairVerdict": "skill" | "baseline" | "tie" | "unmeasurable" | null;
675
+ "pairVotes": Array<{
676
+ "judge": string;
677
+ "ordering": "base-first" | "skill-first";
678
+ "answer": "A" | "B" | "tie";
679
+ }> | null;
516
680
  "pairGradedAt": string | null;
517
681
  "runCreatedAt": string | null;
518
682
  "startedAt": string | null;
@@ -521,7 +685,27 @@ export type BenchmarksPreviewResponse = {
521
685
  "aggregate": {
522
686
  "summary": {
523
687
  "verdict": "delivered" | "partial" | "not_delivered" | "inconclusive" | "measured";
524
- "headline": Array<unknown>;
688
+ "headline": Array<{
689
+ "metric": "total_tokens" | "output_tokens" | "cost_usd" | "duration_ms" | "num_turns" | "success_rate" | "completion_rate" | "goal_rate";
690
+ "label": string;
691
+ "direction": "down" | "up";
692
+ "baselineAvg": number | null;
693
+ "skillAvg": number | null;
694
+ "deltaPct": number | null;
695
+ "delta"?: {
696
+ "unit": "pp";
697
+ "absolute": number | null;
698
+ "relativePct": number | null;
699
+ } | {
700
+ "unit": "pts";
701
+ "absolute": number | null;
702
+ "relativePct"?: number | null;
703
+ } | {
704
+ "unit": "%";
705
+ "relativePct": number | null;
706
+ };
707
+ "improved": boolean;
708
+ }>;
525
709
  "completionRate": {
526
710
  "baseline": number | null;
527
711
  "skill": number | null;
@@ -537,7 +721,102 @@ export type BenchmarksPreviewResponse = {
537
721
  "ties": number;
538
722
  "winRate": number | null;
539
723
  };
724
+ "decision"?: {
725
+ "winner": "treatment" | "baseline" | "tie" | "unmeasurable";
726
+ "basis": "infra" | "goal" | "quality" | "efficiency" | "judge" | "insufficient";
727
+ "reason": string;
728
+ "efficiencyDiscounted": boolean;
729
+ };
540
730
  "leaderboard"?: Array<unknown>;
731
+ "concentration": {
732
+ "perCell": Array<{
733
+ "cell": string;
734
+ "goalDeltaPp": number | null;
735
+ "contributionPct": number | null;
736
+ }>;
737
+ "heterogeneity": {
738
+ "dominantCell": string;
739
+ "contributionPct": number;
740
+ } | null;
741
+ };
742
+ "matrixShape": {
743
+ "cells": number;
744
+ "harnesses": number;
745
+ "models": number;
746
+ "crossed": boolean;
747
+ };
748
+ "flakiness"?: {
749
+ "measured": boolean;
750
+ "conditions": number;
751
+ "unstable": number;
752
+ "worst": {
753
+ "cell": string;
754
+ "taskId": string;
755
+ "arm": "baseline" | "skill";
756
+ "variant"?: number;
757
+ "passRate": number;
758
+ } | null;
759
+ };
760
+ "arms"?: {
761
+ "baseline": {
762
+ "runs": number;
763
+ "completed": number;
764
+ "infraFailures": number;
765
+ "completionRate": number | null;
766
+ "goalRate": number | null;
767
+ "goalTally": {
768
+ "achieved": number;
769
+ "partial": number;
770
+ "missed": number;
771
+ };
772
+ "avgTotalTokens": number | null;
773
+ "avgOutputTokens": number | null;
774
+ "avgCostUsd": number | null;
775
+ "avgDurationMs": number | null;
776
+ "avgTurns": number | null;
777
+ "costCoverage": number | null;
778
+ "avgQualityScore": number | null;
779
+ "gradedCoverage": number | null;
780
+ "medianCostUsd": number | null;
781
+ "medianTotalTokens": number | null;
782
+ "medianDurationMs": number | null;
783
+ "p95CostUsd": number | null;
784
+ "p95TotalTokens": number | null;
785
+ "p95DurationMs": number | null;
786
+ "maxCostUsd": number | null;
787
+ "maxTotalTokens": number | null;
788
+ "maxDurationMs": number | null;
789
+ };
790
+ "skill": {
791
+ "runs": number;
792
+ "completed": number;
793
+ "infraFailures": number;
794
+ "completionRate": number | null;
795
+ "goalRate": number | null;
796
+ "goalTally": {
797
+ "achieved": number;
798
+ "partial": number;
799
+ "missed": number;
800
+ };
801
+ "avgTotalTokens": number | null;
802
+ "avgOutputTokens": number | null;
803
+ "avgCostUsd": number | null;
804
+ "avgDurationMs": number | null;
805
+ "avgTurns": number | null;
806
+ "costCoverage": number | null;
807
+ "avgQualityScore": number | null;
808
+ "gradedCoverage": number | null;
809
+ "medianCostUsd": number | null;
810
+ "medianTotalTokens": number | null;
811
+ "medianDurationMs": number | null;
812
+ "p95CostUsd": number | null;
813
+ "p95TotalTokens": number | null;
814
+ "p95DurationMs": number | null;
815
+ "maxCostUsd": number | null;
816
+ "maxTotalTokens": number | null;
817
+ "maxDurationMs": number | null;
818
+ };
819
+ };
541
820
  "totals": {
542
821
  "cells": number;
543
822
  "runs": number;
@@ -616,9 +895,12 @@ export type BenchmarksPublishResponse = {
616
895
  "provider"?: string;
617
896
  }>;
618
897
  "taskCount": number;
898
+ "variantsPerTask": number;
899
+ "repeats": number;
619
900
  "status": string;
620
901
  "error": string | null;
621
902
  "visibility": "private" | "public";
903
+ "lowSampleOverride": boolean;
622
904
  "publishedAt": string | null;
623
905
  "verdict": unknown;
624
906
  "createdAt": string;
@@ -670,9 +952,12 @@ export type BenchmarksRegradeResponse = {
670
952
  "provider"?: string;
671
953
  }>;
672
954
  "taskCount": number;
955
+ "variantsPerTask": number;
956
+ "repeats": number;
673
957
  "status": string;
674
958
  "error": string | null;
675
959
  "visibility": "private" | "public";
960
+ "lowSampleOverride": boolean;
676
961
  "publishedAt": string | null;
677
962
  "verdict": unknown;
678
963
  "createdAt": string;
@@ -694,6 +979,7 @@ export type BenchmarksUpdateTaskResponse = {
694
979
  "category": string | null;
695
980
  "requiresWeb": boolean;
696
981
  "rubric": Array<string>;
982
+ "variants"?: Array<string> | null;
697
983
  };
698
984
  };
699
985
  export type BenchmarksUnpublishResponse = {
@@ -741,9 +1027,12 @@ export type BenchmarksUnpublishResponse = {
741
1027
  "provider"?: string;
742
1028
  }>;
743
1029
  "taskCount": number;
1030
+ "variantsPerTask": number;
1031
+ "repeats": number;
744
1032
  "status": string;
745
1033
  "error": string | null;
746
1034
  "visibility": "private" | "public";
1035
+ "lowSampleOverride": boolean;
747
1036
  "publishedAt": string | null;
748
1037
  "verdict": unknown;
749
1038
  "createdAt": string;
@@ -775,6 +1064,9 @@ export type ExperimentRunsListResponse = {
775
1064
  "harness": string;
776
1065
  "model"?: string;
777
1066
  "provider"?: string;
1067
+ "tools"?: "default" | "none" | {
1068
+ "tools": Array<string>;
1069
+ } | null;
778
1070
  "intent_text"?: string;
779
1071
  "target_domain"?: string;
780
1072
  "status": string;
@@ -809,6 +1101,11 @@ export type ExperimentRunsCreateRequest = {
809
1101
  "tools"?: "default" | "none" | {
810
1102
  "tools": Array<string>;
811
1103
  };
1104
+ "mcp_servers"?: Array<{
1105
+ "name": string;
1106
+ "url": string;
1107
+ "secretId"?: string;
1108
+ }>;
812
1109
  "wait"?: boolean;
813
1110
  };
814
1111
  export type ExperimentRunsCreateResponse = {
@@ -1042,6 +1339,74 @@ export type SkillsUpdateResponse = {
1042
1339
  };
1043
1340
  };
1044
1341
  export type SkillsDeleteResponse = unknown;
1342
+ export type WebmcpArenaCreateRequest = {
1343
+ "targetUrl": string;
1344
+ "intent": string;
1345
+ "harness": string;
1346
+ "model": string;
1347
+ "provider"?: string;
1348
+ "baseline"?: "webdriver" | "none" | "devtools" | "browserbase" | "oxylabs";
1349
+ "treatment"?: "webmcp-native" | "webdriver" | "webdriver-webmcp" | "devtools" | "devtools-webmcp" | "webmcp-shim";
1350
+ "name"?: string;
1351
+ };
1352
+ export type WebmcpArenaCreateResponse = {
1353
+ "benchmark": {
1354
+ "id": string;
1355
+ "executiveSummary"?: string | null;
1356
+ "plannedRunCount": number;
1357
+ "organizationId": string;
1358
+ "createdBy": string | null;
1359
+ "name": string;
1360
+ "slug": string;
1361
+ "description": string | null;
1362
+ "skillRef": string | null;
1363
+ "skillSlug": string | null;
1364
+ "skillName": string | null;
1365
+ "skillPromise": string;
1366
+ "subjectKind": "skill" | "tools" | "addon" | "custom";
1367
+ "subjectName": string | null;
1368
+ "subjectLabel": string;
1369
+ "armConfig": {
1370
+ "baseline"?: {
1371
+ "tools"?: "default" | "none" | {
1372
+ "tools": Array<string>;
1373
+ };
1374
+ "addons"?: Record<string, unknown>;
1375
+ };
1376
+ "treatment"?: {
1377
+ "tools"?: "default" | "none" | {
1378
+ "tools": Array<string>;
1379
+ };
1380
+ "addons"?: Record<string, unknown>;
1381
+ };
1382
+ };
1383
+ "comparisonMode": "ab_vs_none" | "ab_custom" | "single";
1384
+ "baselineLabel": string | null;
1385
+ "treatmentLabel": string | null;
1386
+ "promiseMetrics": Array<{
1387
+ "metric": "total_tokens" | "output_tokens" | "cost_usd" | "duration_ms" | "num_turns" | "success_rate" | "completion_rate" | "goal_rate";
1388
+ "direction": "down" | "up";
1389
+ "label": string;
1390
+ }>;
1391
+ "matrix": Array<{
1392
+ "harness": string;
1393
+ "model": string;
1394
+ "provider"?: string;
1395
+ }>;
1396
+ "taskCount": number;
1397
+ "variantsPerTask": number;
1398
+ "repeats": number;
1399
+ "status": string;
1400
+ "error": string | null;
1401
+ "visibility": "private" | "public";
1402
+ "lowSampleOverride": boolean;
1403
+ "publishedAt": string | null;
1404
+ "verdict": unknown;
1405
+ "createdAt": string;
1406
+ "updatedAt": string;
1407
+ };
1408
+ "streamUrl": string;
1409
+ };
1045
1410
  export type ActivityListResponse = {
1046
1411
  "success": true;
1047
1412
  "data": Array<{
@@ -1273,6 +1638,7 @@ export type IntentsGetResponse = {
1273
1638
  "share": number;
1274
1639
  "tracked": boolean;
1275
1640
  "domain"?: string | null;
1641
+ "curated"?: boolean;
1276
1642
  }>;
1277
1643
  "sources": Array<{
1278
1644
  "host": string;
@@ -1536,6 +1902,7 @@ export type JourneysCreateRequest = {
1536
1902
  "model"?: string;
1537
1903
  }>;
1538
1904
  "intentId"?: string;
1905
+ "promptId"?: string;
1539
1906
  "targetDomain"?: string;
1540
1907
  "domains"?: Array<string>;
1541
1908
  "competitors"?: Array<string>;
@@ -1590,6 +1957,30 @@ export type JourneysGetResponse = {
1590
1957
  "numTurns": number | null;
1591
1958
  "costUsd": number | null;
1592
1959
  };
1960
+ "targetCheck": {
1961
+ "chip": "NO TARGET" | "HIT" | "MISS";
1962
+ "state": "no_target" | "hit" | "miss_not_reached" | "miss_page_broken" | "miss_content_short" | "miss_bypassed";
1963
+ "reason": string;
1964
+ "targets": Array<{
1965
+ "targetId": string;
1966
+ "displayPath": string;
1967
+ "reached": boolean;
1968
+ "stepsTo": number | null;
1969
+ "httpStatus": number | null;
1970
+ "fetchOk": boolean | null;
1971
+ "nearMissPath": string | null;
1972
+ "contribution": number | null;
1973
+ "reachStepId": number | null;
1974
+ "sufficiency": string | null;
1975
+ "reason": string | null;
1976
+ "contentFacts": {
1977
+ "found": Array<string>;
1978
+ "missing": Array<string>;
1979
+ } | null;
1980
+ "pageState": string;
1981
+ "pageStateAt": string | null;
1982
+ }>;
1983
+ } | null;
1593
1984
  }>;
1594
1985
  };
1595
1986
  };
@@ -1632,6 +2023,9 @@ export type StudioRunsListResponse = {
1632
2023
  "harness": string;
1633
2024
  "model"?: string;
1634
2025
  "provider"?: string;
2026
+ "tools"?: "default" | "none" | {
2027
+ "tools": Array<string>;
2028
+ } | null;
1635
2029
  "intent_text"?: string;
1636
2030
  "target_domain"?: string;
1637
2031
  "status": string;
@@ -1666,6 +2060,11 @@ export type StudioRunsCreateRequest = {
1666
2060
  "tools"?: "default" | "none" | {
1667
2061
  "tools": Array<string>;
1668
2062
  };
2063
+ "mcp_servers"?: Array<{
2064
+ "name": string;
2065
+ "url": string;
2066
+ "secretId"?: string;
2067
+ }>;
1669
2068
  "wait"?: boolean;
1670
2069
  };
1671
2070
  export type StudioRunsCreateResponse = {