sillyspec 3.34.0 → 3.34.2

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.
@@ -3,24 +3,15 @@
3
3
  "generated_by": "eval/knowledge/run.mjs",
4
4
  "snapshot": {
5
5
  "sillyspec": {
6
- "head": "e194ad0c29256646e26f08577d45ca548663121d",
7
- "knowledge_hash": "3d6f2756df2fe467987f29a1df7e9ea46ff1a0d8c84862e140f15197c7028a57",
8
- "knowledge_files": 139
9
- },
10
- "platform": {
11
- "head": "954873529837ce253ef611f7aa38df9e512ae12e",
12
- "knowledge_hash": "36cb77cf9b1e1f50f1aea28c9a1d9ad1b887dec8cd7e6b1b10c71527011ae0e3",
13
- "knowledge_files": 160
6
+ "head": "c5b1d9a5a6cd83437910253ba0a6ff9ea5dd7904",
7
+ "knowledge_hash": "ef33189ed3662e37e286fb6827eb06e5ea449853459da0a74a99d0305b973665",
8
+ "knowledge_files": 141
14
9
  }
15
10
  },
16
11
  "cases": {
17
12
  "sillyspec": {
18
13
  "organic": 31,
19
14
  "self": 214
20
- },
21
- "platform": {
22
- "organic": 42,
23
- "self": 330
24
15
  }
25
16
  },
26
17
  "metrics": {
@@ -272,47 +263,47 @@
272
263
  },
273
264
  "scope": {
274
265
  "raw": {
275
- "top1": 0.4167,
276
- "top3": 0.5,
277
- "mrr": 0.4583,
266
+ "top1": 0.6667,
267
+ "top3": 0.75,
268
+ "mrr": 0.7215,
278
269
  "n": 12
279
270
  },
280
271
  "rendered": {
281
- "top1": 0.4167,
282
- "top3": 0.5,
283
- "mrr": 0.4583,
272
+ "top1": 0.6667,
273
+ "top3": 0.75,
274
+ "mrr": 0.7215,
284
275
  "n": 12
285
276
  },
286
277
  "truncated": [],
287
278
  "details": [
288
279
  {
289
280
  "id": "s-man-01",
290
- "raw_rank": null,
291
- "rendered_rank": null,
281
+ "raw_rank": 1,
282
+ "rendered_rank": 1,
292
283
  "truncated": false
293
284
  },
294
285
  {
295
286
  "id": "s-man-02",
296
- "raw_rank": 2,
297
- "rendered_rank": 2,
287
+ "raw_rank": 8,
288
+ "rendered_rank": 8,
298
289
  "truncated": false
299
290
  },
300
291
  {
301
292
  "id": "s-man-03",
302
- "raw_rank": null,
303
- "rendered_rank": null,
293
+ "raw_rank": 1,
294
+ "rendered_rank": 1,
304
295
  "truncated": false
305
296
  },
306
297
  {
307
298
  "id": "s-man-04",
308
- "raw_rank": null,
309
- "rendered_rank": null,
299
+ "raw_rank": 1,
300
+ "rendered_rank": 1,
310
301
  "truncated": false
311
302
  },
312
303
  {
313
304
  "id": "s-man-05",
314
- "raw_rank": null,
315
- "rendered_rank": null,
305
+ "raw_rank": 1,
306
+ "rendered_rank": 1,
316
307
  "truncated": false
317
308
  },
318
309
  {
@@ -329,14 +320,14 @@
329
320
  },
330
321
  {
331
322
  "id": "s-scope-03",
332
- "raw_rank": 1,
333
- "rendered_rank": 1,
323
+ "raw_rank": 3,
324
+ "rendered_rank": 3,
334
325
  "truncated": false
335
326
  },
336
327
  {
337
328
  "id": "s-scope-04",
338
- "raw_rank": null,
339
- "rendered_rank": null,
329
+ "raw_rank": 5,
330
+ "rendered_rank": 5,
340
331
  "truncated": false
341
332
  },
342
333
  {
@@ -360,18 +351,18 @@
360
351
  ],
361
352
  "subsets": {
362
353
  "frozen": {
363
- "top1": 0,
364
- "top3": 0.2,
365
- "mrr": 0.1,
354
+ "top1": 0.8,
355
+ "top3": 0.8,
356
+ "mrr": 0.825,
366
357
  "n": 5,
367
- "reachable": 0.2
358
+ "reachable": 1
368
359
  },
369
360
  "added": {
370
- "top1": 0.6,
361
+ "top1": 0.4,
371
362
  "top3": 0.6,
372
- "mrr": 0.6,
363
+ "mrr": 0.5067,
373
364
  "n": 5,
374
- "reachable": 0.6
365
+ "reachable": 0.8
375
366
  },
376
367
  "fusion": {
377
368
  "top1": 1,
@@ -382,11 +373,6 @@
382
373
  }
383
374
  },
384
375
  "scope_unreachable": [
385
- "s-man-01",
386
- "s-man-03",
387
- "s-man-04",
388
- "s-man-05",
389
- "s-scope-04",
390
376
  "s-scope-05"
391
377
  ]
392
378
  },
@@ -394,7 +380,7 @@
394
380
  "raw": {
395
381
  "top1": 0.25,
396
382
  "top3": 0.5,
397
- "mrr": 0.4236,
383
+ "mrr": 0.4167,
398
384
  "n": 4
399
385
  },
400
386
  "rendered": {
@@ -422,7 +408,7 @@
422
408
  },
423
409
  {
424
410
  "id": "s-man-10",
425
- "raw_rank": 9,
411
+ "raw_rank": 12,
426
412
  "rendered_rank": null,
427
413
  "truncated": true
428
414
  },
@@ -437,7 +423,7 @@
437
423
  "approx": {
438
424
  "top1": 0,
439
425
  "top3": 0.3333,
440
- "mrr": 0.2315,
426
+ "mrr": 0.2222,
441
427
  "n": 3,
442
428
  "reachable": 1
443
429
  },
@@ -450,448 +436,15 @@
450
436
  }
451
437
  }
452
438
  }
453
- },
454
- "platform": {
455
- "entries": {
456
- "raw": {
457
- "top1": 0.5556,
458
- "top3": 0.8889,
459
- "mrr": 0.7037,
460
- "n": 9
461
- },
462
- "rendered": {
463
- "top1": 0.5556,
464
- "top3": 0.8889,
465
- "mrr": 0.7037,
466
- "n": 9
467
- },
468
- "truncated": [],
469
- "details": [
470
- {
471
- "id": "p-tel-01",
472
- "raw_rank": 1,
473
- "rendered_rank": 1,
474
- "truncated": false
475
- },
476
- {
477
- "id": "p-tel-02",
478
- "raw_rank": 2,
479
- "rendered_rank": 2,
480
- "truncated": false
481
- },
482
- {
483
- "id": "p-tel-03",
484
- "raw_rank": 3,
485
- "rendered_rank": 3,
486
- "truncated": false
487
- },
488
- {
489
- "id": "p-tel-04",
490
- "raw_rank": 1,
491
- "rendered_rank": 1,
492
- "truncated": false
493
- },
494
- {
495
- "id": "p-tel-05",
496
- "raw_rank": 2,
497
- "rendered_rank": 2,
498
- "truncated": false
499
- },
500
- {
501
- "id": "p-tel-06",
502
- "raw_rank": 1,
503
- "rendered_rank": 1,
504
- "truncated": false
505
- },
506
- {
507
- "id": "p-tel-07",
508
- "raw_rank": null,
509
- "rendered_rank": null,
510
- "truncated": false
511
- },
512
- {
513
- "id": "p-tel-09",
514
- "raw_rank": 1,
515
- "rendered_rank": 1,
516
- "truncated": false
517
- },
518
- {
519
- "id": "p-tel-13",
520
- "raw_rank": 1,
521
- "rendered_rank": 1,
522
- "truncated": false
523
- }
524
- ]
525
- },
526
- "decisions": {
527
- "raw": {
528
- "top1": 0.8571,
529
- "top3": 0.9048,
530
- "mrr": 0.9008,
531
- "n": 21
532
- },
533
- "rendered": {
534
- "top1": 0.8571,
535
- "top3": 0.9048,
536
- "mrr": 0.8929,
537
- "n": 21
538
- },
539
- "truncated": [
540
- "auto-platform-04"
541
- ],
542
- "details": [
543
- {
544
- "id": "p-tel-08",
545
- "raw_rank": 1,
546
- "rendered_rank": 1,
547
- "truncated": false
548
- },
549
- {
550
- "id": "p-dec-01",
551
- "raw_rank": 1,
552
- "rendered_rank": 1,
553
- "truncated": false
554
- },
555
- {
556
- "id": "p-dec-02",
557
- "raw_rank": 1,
558
- "rendered_rank": 1,
559
- "truncated": false
560
- },
561
- {
562
- "id": "p-dec-03",
563
- "raw_rank": 1,
564
- "rendered_rank": 1,
565
- "truncated": false
566
- },
567
- {
568
- "id": "p-dec-04",
569
- "raw_rank": 1,
570
- "rendered_rank": 1,
571
- "truncated": false
572
- },
573
- {
574
- "id": "p-dec-05",
575
- "raw_rank": 1,
576
- "rendered_rank": 1,
577
- "truncated": false
578
- },
579
- {
580
- "id": "p-dec-06",
581
- "raw_rank": 1,
582
- "rendered_rank": 1,
583
- "truncated": false
584
- },
585
- {
586
- "id": "p-dec-07",
587
- "raw_rank": 1,
588
- "rendered_rank": 1,
589
- "truncated": false
590
- },
591
- {
592
- "id": "p-dec-08",
593
- "raw_rank": 1,
594
- "rendered_rank": 1,
595
- "truncated": false
596
- },
597
- {
598
- "id": "auto-platform-01",
599
- "raw_rank": 1,
600
- "rendered_rank": 1,
601
- "truncated": false
602
- },
603
- {
604
- "id": "auto-platform-02",
605
- "raw_rank": 1,
606
- "rendered_rank": 1,
607
- "truncated": false
608
- },
609
- {
610
- "id": "auto-platform-03",
611
- "raw_rank": 2,
612
- "rendered_rank": 2,
613
- "truncated": false
614
- },
615
- {
616
- "id": "auto-platform-04",
617
- "raw_rank": 6,
618
- "rendered_rank": null,
619
- "truncated": true
620
- },
621
- {
622
- "id": "auto-platform-05",
623
- "raw_rank": 1,
624
- "rendered_rank": 1,
625
- "truncated": false
626
- },
627
- {
628
- "id": "auto-platform-06",
629
- "raw_rank": 1,
630
- "rendered_rank": 1,
631
- "truncated": false
632
- },
633
- {
634
- "id": "auto-platform-07",
635
- "raw_rank": 1,
636
- "rendered_rank": 1,
637
- "truncated": false
638
- },
639
- {
640
- "id": "auto-platform-08",
641
- "raw_rank": 1,
642
- "rendered_rank": 1,
643
- "truncated": false
644
- },
645
- {
646
- "id": "auto-platform-09",
647
- "raw_rank": 1,
648
- "rendered_rank": 1,
649
- "truncated": false
650
- },
651
- {
652
- "id": "auto-platform-10",
653
- "raw_rank": 1,
654
- "rendered_rank": 1,
655
- "truncated": false
656
- },
657
- {
658
- "id": "auto-platform-11",
659
- "raw_rank": 4,
660
- "rendered_rank": 4,
661
- "truncated": false
662
- },
663
- {
664
- "id": "auto-platform-12",
665
- "raw_rank": 1,
666
- "rendered_rank": 1,
667
- "truncated": false
668
- }
669
- ]
670
- },
671
- "search": {
672
- "raw": {
673
- "top1": 0.5556,
674
- "top3": 0.8889,
675
- "mrr": 0.7037,
676
- "n": 9
677
- },
678
- "rendered": {
679
- "top1": 0.5556,
680
- "top3": 0.8889,
681
- "mrr": 0.7037,
682
- "n": 9
683
- },
684
- "truncated": [],
685
- "details": [
686
- {
687
- "id": "p-tel-01",
688
- "raw_rank": 1,
689
- "rendered_rank": 1,
690
- "truncated": false
691
- },
692
- {
693
- "id": "p-tel-02",
694
- "raw_rank": 2,
695
- "rendered_rank": 2,
696
- "truncated": false
697
- },
698
- {
699
- "id": "p-tel-03",
700
- "raw_rank": 3,
701
- "rendered_rank": 3,
702
- "truncated": false
703
- },
704
- {
705
- "id": "p-tel-04",
706
- "raw_rank": 1,
707
- "rendered_rank": 1,
708
- "truncated": false
709
- },
710
- {
711
- "id": "p-tel-05",
712
- "raw_rank": 2,
713
- "rendered_rank": 2,
714
- "truncated": false
715
- },
716
- {
717
- "id": "p-tel-06",
718
- "raw_rank": 1,
719
- "rendered_rank": 1,
720
- "truncated": false
721
- },
722
- {
723
- "id": "p-tel-07",
724
- "raw_rank": null,
725
- "rendered_rank": null,
726
- "truncated": false
727
- },
728
- {
729
- "id": "p-tel-09",
730
- "raw_rank": 1,
731
- "rendered_rank": 1,
732
- "truncated": false
733
- },
734
- {
735
- "id": "p-tel-13",
736
- "raw_rank": 1,
737
- "rendered_rank": 1,
738
- "truncated": false
739
- }
740
- ]
741
- },
742
- "scope": {
743
- "raw": {
744
- "top1": 0.8333,
745
- "top3": 1,
746
- "mrr": 0.9167,
747
- "n": 6
748
- },
749
- "rendered": {
750
- "top1": 0.8333,
751
- "top3": 1,
752
- "mrr": 0.9167,
753
- "n": 6
754
- },
755
- "truncated": [],
756
- "details": [
757
- {
758
- "id": "p-scope-01",
759
- "raw_rank": 1,
760
- "rendered_rank": 1,
761
- "truncated": false
762
- },
763
- {
764
- "id": "p-scope-02",
765
- "raw_rank": 2,
766
- "rendered_rank": 2,
767
- "truncated": false
768
- },
769
- {
770
- "id": "p-scope-03",
771
- "raw_rank": 1,
772
- "rendered_rank": 1,
773
- "truncated": false
774
- },
775
- {
776
- "id": "p-scope-04",
777
- "raw_rank": 1,
778
- "rendered_rank": 1,
779
- "truncated": false
780
- },
781
- {
782
- "id": "p-scope-05",
783
- "raw_rank": 1,
784
- "rendered_rank": 1,
785
- "truncated": false
786
- },
787
- {
788
- "id": "p-scope-06",
789
- "raw_rank": 1,
790
- "rendered_rank": 1,
791
- "truncated": false
792
- }
793
- ],
794
- "subsets": {
795
- "added": {
796
- "top1": 0.8333,
797
- "top3": 1,
798
- "mrr": 0.9167,
799
- "n": 6,
800
- "reachable": 1
801
- }
802
- },
803
- "scope_unreachable": []
804
- },
805
- "fr": {
806
- "raw": {
807
- "top1": 0.1667,
808
- "top3": 0.3333,
809
- "mrr": 0.2732,
810
- "n": 6
811
- },
812
- "rendered": {
813
- "top1": 0.1667,
814
- "top3": 0.3333,
815
- "mrr": 0.25,
816
- "n": 6
817
- },
818
- "truncated": [
819
- "p-tel-10",
820
- "p-tel-11",
821
- "p-tel-12",
822
- "p-tel-14"
823
- ],
824
- "details": [
825
- {
826
- "id": "p-tel-10",
827
- "raw_rank": 34,
828
- "rendered_rank": null,
829
- "truncated": true
830
- },
831
- {
832
- "id": "p-tel-11",
833
- "raw_rank": 32,
834
- "rendered_rank": null,
835
- "truncated": true
836
- },
837
- {
838
- "id": "p-tel-12",
839
- "raw_rank": 35,
840
- "rendered_rank": null,
841
- "truncated": true
842
- },
843
- {
844
- "id": "p-tel-14",
845
- "raw_rank": 20,
846
- "rendered_rank": null,
847
- "truncated": true
848
- },
849
- {
850
- "id": "p-tel-15",
851
- "raw_rank": 2,
852
- "rendered_rank": 2,
853
- "truncated": false
854
- },
855
- {
856
- "id": "p-fr-prod-01",
857
- "raw_rank": 1,
858
- "rendered_rank": 1,
859
- "truncated": false
860
- }
861
- ],
862
- "subsets": {
863
- "approx": {
864
- "top1": 0,
865
- "top3": 0.2,
866
- "mrr": 0.1278,
867
- "n": 5,
868
- "reachable": 1
869
- },
870
- "prod": {
871
- "top1": 1,
872
- "top3": 1,
873
- "mrr": 1,
874
- "n": 1,
875
- "reachable": 1
876
- }
877
- }
878
- }
879
439
  }
880
440
  },
881
441
  "self_smoke": {
882
442
  "sillyspec": {
883
443
  "cases": 214,
884
- "skipped": 603,
444
+ "skipped": 618,
885
445
  "own_hit_top3": 0.0187,
886
446
  "name_only_top3": 0.028,
887
447
  "leak_gap": -0.0093
888
- },
889
- "platform": {
890
- "cases": 330,
891
- "skipped": 488,
892
- "own_hit_top3": 0.0121,
893
- "name_only_top3": 0.003,
894
- "leak_gap": 0.0091
895
448
  }
896
449
  },
897
450
  "probes": {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "sillyspec",
3
- "version": "3.34.0",
3
+ "version": "3.34.2",
4
4
  "description": "SillySpec CLI — 流程状态机,让 AI 严格按步骤来",
5
5
  "icon": "logo.jpg",
6
6
  "homepage": "https://sillyspec.ppdmq.top/",