@tangle-network/agent-runtime 0.101.1 → 0.102.0

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/dist/testing.js CHANGED
@@ -1,7 +1,7 @@
1
1
  import {
2
2
  verifyAgentImprovementProposal
3
- } from "./chunk-RJPQLUDA.js";
4
- import "./chunk-HGSHPVJ6.js";
3
+ } from "./chunk-4AMAFNUD.js";
4
+ import "./chunk-TGDHHHH4.js";
5
5
  import "./chunk-IKGCKPDX.js";
6
6
  import "./chunk-IMSNJSXH.js";
7
7
  import "./chunk-3MDZX7YU.js";
@@ -12,7 +12,7 @@ import "./chunk-YEJR7IXO.js";
12
12
  // src/testing/fixtures/agent-improvement-proposal.json
13
13
  var agent_improvement_proposal_default = {
14
14
  changedSurfaces: ["prompt"],
15
- digest: "sha256:aa47ef7cce1668303f55c3454a5a762c75a78be6cf907fa3f4f10dea20fd9fc6",
15
+ digest: "sha256:b1a7049775c37741f37c3b5279a879748b7d33d114fc4b8f498fa2daa1fce1e3",
16
16
  evaluation: {
17
17
  decision: {
18
18
  contributingChecks: [
@@ -59,13 +59,19 @@ var agent_improvement_proposal_default = {
59
59
  code: {
60
60
  kind: "disabled"
61
61
  },
62
- digest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
62
+ digest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
63
63
  digestAlgorithm: "rfc8785-sha256",
64
64
  execution: {
65
65
  cwd: {
66
66
  path: ".",
67
67
  workspace: "task"
68
68
  },
69
+ env: {
70
+ PATH: {
71
+ kind: "public",
72
+ value: "/usr/local/bin:/usr/bin:/bin"
73
+ }
74
+ },
69
75
  environment: {
70
76
  kind: "evaluator-task-container"
71
77
  },
@@ -203,13 +209,19 @@ var agent_improvement_proposal_default = {
203
209
  code: {
204
210
  kind: "disabled"
205
211
  },
206
- digest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
212
+ digest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
207
213
  digestAlgorithm: "rfc8785-sha256",
208
214
  execution: {
209
215
  cwd: {
210
216
  path: ".",
211
217
  workspace: "task"
212
218
  },
219
+ env: {
220
+ PATH: {
221
+ kind: "public",
222
+ value: "/usr/local/bin:/usr/bin:/bin"
223
+ }
224
+ },
213
225
  environment: {
214
226
  kind: "evaluator-task-container"
215
227
  },
@@ -251,7 +263,7 @@ var agent_improvement_proposal_default = {
251
263
  candidateLineage: {
252
264
  source: "human"
253
265
  },
254
- digest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
266
+ digest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
255
267
  digestAlgorithm: "rfc8785-sha256",
256
268
  kind: "agent-candidate-experiment",
257
269
  policy: {
@@ -269,7 +281,7 @@ var agent_improvement_proposal_default = {
269
281
  measurements: [
270
282
  {
271
283
  baseline: {
272
- digest: "sha256:4514f8b5f875371d69b88add160843806e84f854898a351bdce03646c3750495",
284
+ digest: "sha256:6bf8492d4fb6cb795715f861ad1150ce8194aaf6075ce898e411fdbaf4e6f534",
273
285
  kind: "agent-candidate-execution-evidence",
274
286
  materializationReceipt: {
275
287
  benchmark: {
@@ -292,7 +304,7 @@ var agent_improvement_proposal_default = {
292
304
  }
293
305
  }
294
306
  },
295
- bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
307
+ bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
296
308
  codeKind: "disabled",
297
309
  container: {
298
310
  image: "ghcr.io/example/task",
@@ -304,16 +316,16 @@ var agent_improvement_proposal_default = {
304
316
  },
305
317
  source: "evaluator-task-container"
306
318
  },
307
- digest: "sha256:707a959a5ee03b48f523417ec3fca971565986bbe46ec0d44412e1c9873819af",
319
+ digest: "sha256:50573a8655c2f83044a105990573b1a5ed84d3a8d9241e01cda565eead22b7cc",
308
320
  digestAlgorithm: "rfc8785-sha256",
309
321
  executionPlan: {
310
322
  artifact: {
311
- byteLength: 1967,
312
- content: "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",
323
+ byteLength: 2030,
324
+ content: "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",
313
325
  encoding: "base64",
314
- sha256: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5"
326
+ sha256: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf"
315
327
  },
316
- digest: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5",
328
+ digest: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf",
317
329
  kind: "agent-candidate-execution-plan",
318
330
  material: {
319
331
  codeKind: "disabled",
@@ -340,7 +352,12 @@ var agent_improvement_proposal_default = {
340
352
  path: ".",
341
353
  workspace: "task"
342
354
  },
343
- env: {},
355
+ env: {
356
+ PATH: {
357
+ kind: "public",
358
+ value: "/usr/local/bin:/usr/bin:/bin"
359
+ }
360
+ },
344
361
  executable: "codex"
345
362
  },
346
363
  limits: {
@@ -389,9 +406,9 @@ var agent_improvement_proposal_default = {
389
406
  runCell: {
390
407
  arm: "baseline",
391
408
  attempt: 1,
392
- bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
393
- digest: "sha256:c170a7cb938c3e5b7550a264f6b6b08a13ea262fe80a2e24b020a415c1dad595",
394
- experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
409
+ bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
410
+ digest: "sha256:5246bcb23929d3ef84c78c5185390aab5e2309f1267d38e0d1c0ddc18232b6d4",
411
+ experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
395
412
  kind: "agent-candidate-run-cell",
396
413
  repetition: 0,
397
414
  seed: 101,
@@ -456,12 +473,12 @@ var agent_improvement_proposal_default = {
456
473
  byteLength: 1122,
457
474
  locator: {
458
475
  bucket: "candidate-test-artifacts",
459
- key: "benchmark-result/ec815a7d6556928ba69e6f08cf38fed9ddd64c9cff4ba1ccf471f8e7a0aa63f4",
476
+ key: "benchmark-result/e9a709a18c6a51d8f81080c79f856162eb740e7664eba2906bc5888752eb27a6",
460
477
  kind: "s3"
461
478
  },
462
- sha256: "sha256:ec815a7d6556928ba69e6f08cf38fed9ddd64c9cff4ba1ccf471f8e7a0aa63f4"
479
+ sha256: "sha256:e9a709a18c6a51d8f81080c79f856162eb740e7664eba2906bc5888752eb27a6"
463
480
  },
464
- digest: "sha256:ec815a7d6556928ba69e6f08cf38fed9ddd64c9cff4ba1ccf471f8e7a0aa63f4",
481
+ digest: "sha256:e9a709a18c6a51d8f81080c79f856162eb740e7664eba2906bc5888752eb27a6",
465
482
  kind: "agent-candidate-benchmark-result",
466
483
  material: {
467
484
  dimensions: [
@@ -479,7 +496,7 @@ var agent_improvement_proposal_default = {
479
496
  },
480
497
  sha256: "sha256:628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b"
481
498
  },
482
- executionPlanDigest: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5",
499
+ executionPlanDigest: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf",
483
500
  grader: {
484
501
  artifact: {
485
502
  byteLength: 25,
@@ -512,24 +529,24 @@ var agent_improvement_proposal_default = {
512
529
  kind: "agent-candidate-benchmark-result-material",
513
530
  passed: false,
514
531
  score: 0,
515
- taskOutcomeDigest: "sha256:3fc660e792f3883048a3e04dfa9b361d5b88f0afd3141fe7858cf9b53952e914"
532
+ taskOutcomeDigest: "sha256:96d90a54ff0cdc7ef2dc49e80fad20175c10a761eb6abd3bf127da35340994ed"
516
533
  }
517
534
  },
518
- bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
519
- digest: "sha256:6b565143b4115b64a682bbc0fe56d6ef44302947df1c1a6d562d45533b346a7e",
535
+ bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
536
+ digest: "sha256:792a1fc3d525e029e74f9fe88940277b6d7c162959b4ecc943b25cbaffe3d86f",
520
537
  digestAlgorithm: "rfc8785-sha256",
521
- executionPlanDigest: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5",
538
+ executionPlanDigest: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf",
522
539
  executorCapture: {
523
540
  byteLength: 477,
524
541
  locator: {
525
542
  bucket: "candidate-test-artifacts",
526
- key: "executor-capture/72d7612e1df0fbb53498c79ba7cf4464f141aa6e031b013ce87f887d8f16a07a",
543
+ key: "executor-capture/64bb8b780db79c2a5bf89c46cefb755060f18271084748143c194d5716c5bedd",
527
544
  kind: "s3"
528
545
  },
529
- sha256: "sha256:72d7612e1df0fbb53498c79ba7cf4464f141aa6e031b013ce87f887d8f16a07a"
546
+ sha256: "sha256:64bb8b780db79c2a5bf89c46cefb755060f18271084748143c194d5716c5bedd"
530
547
  },
531
548
  kind: "agent-candidate-run",
532
- materializationReceiptDigest: "sha256:707a959a5ee03b48f523417ec3fca971565986bbe46ec0d44412e1c9873819af",
549
+ materializationReceiptDigest: "sha256:50573a8655c2f83044a105990573b1a5ed84d3a8d9241e01cda565eead22b7cc",
533
550
  memory: {
534
551
  mode: "disabled"
535
552
  },
@@ -538,17 +555,17 @@ var agent_improvement_proposal_default = {
538
555
  byteLength: 615,
539
556
  locator: {
540
557
  bucket: "candidate-test-artifacts",
541
- key: "model-settlement/e923d98a8c5620f72b41a7c4b75024149f1ebe14128c14a576a1de5a5ec688bd",
558
+ key: "model-settlement/625a1690d64a8ccee6b2d616f7ee7a9648edb1ddf9ea58711bef5a4a306cdba0",
542
559
  kind: "s3"
543
560
  },
544
- sha256: "sha256:e923d98a8c5620f72b41a7c4b75024149f1ebe14128c14a576a1de5a5ec688bd"
561
+ sha256: "sha256:625a1690d64a8ccee6b2d616f7ee7a9648edb1ddf9ea58711bef5a4a306cdba0"
545
562
  },
546
- digest: "sha256:e923d98a8c5620f72b41a7c4b75024149f1ebe14128c14a576a1de5a5ec688bd",
563
+ digest: "sha256:625a1690d64a8ccee6b2d616f7ee7a9648edb1ddf9ea58711bef5a4a306cdba0",
547
564
  kind: "agent-candidate-model-settlement",
548
565
  material: {
549
566
  calls: [],
550
567
  closed: true,
551
- executionPlanDigest: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5",
568
+ executionPlanDigest: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf",
552
569
  grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
553
570
  kind: "agent-candidate-model-settlement-material",
554
571
  preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
@@ -569,21 +586,21 @@ var agent_improvement_proposal_default = {
569
586
  }
570
587
  }
571
588
  },
572
- runCellDigest: "sha256:c170a7cb938c3e5b7550a264f6b6b08a13ea262fe80a2e24b020a415c1dad595",
589
+ runCellDigest: "sha256:5246bcb23929d3ef84c78c5185390aab5e2309f1267d38e0d1c0ddc18232b6d4",
573
590
  taskOutcome: {
574
591
  artifact: {
575
592
  byteLength: 478,
576
593
  locator: {
577
594
  bucket: "candidate-test-artifacts",
578
- key: "task-outcome/3fc660e792f3883048a3e04dfa9b361d5b88f0afd3141fe7858cf9b53952e914",
595
+ key: "task-outcome/96d90a54ff0cdc7ef2dc49e80fad20175c10a761eb6abd3bf127da35340994ed",
579
596
  kind: "s3"
580
597
  },
581
- sha256: "sha256:3fc660e792f3883048a3e04dfa9b361d5b88f0afd3141fe7858cf9b53952e914"
598
+ sha256: "sha256:96d90a54ff0cdc7ef2dc49e80fad20175c10a761eb6abd3bf127da35340994ed"
582
599
  },
583
- digest: "sha256:3fc660e792f3883048a3e04dfa9b361d5b88f0afd3141fe7858cf9b53952e914",
600
+ digest: "sha256:96d90a54ff0cdc7ef2dc49e80fad20175c10a761eb6abd3bf127da35340994ed",
584
601
  kind: "agent-candidate-task-outcome",
585
602
  material: {
586
- executionPlanDigest: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5",
603
+ executionPlanDigest: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf",
587
604
  kind: "agent-candidate-task-outcome-material",
588
605
  outcome: {
589
606
  artifact: {
@@ -617,10 +634,10 @@ var agent_improvement_proposal_default = {
617
634
  byteLength: 748,
618
635
  locator: {
619
636
  bucket: "candidate-test-artifacts",
620
- key: "trace/3bfe9931c331dda75f96eac7761181cdcbc1302318c1ffdebab4c53fb275fc55",
637
+ key: "trace/2fce8b3ba11deb5251d3b7b9de66d1b4788c18a2b56aafe77ddd57423db41593",
621
638
  kind: "s3"
622
639
  },
623
- sha256: "sha256:3bfe9931c331dda75f96eac7761181cdcbc1302318c1ffdebab4c53fb275fc55"
640
+ sha256: "sha256:2fce8b3ba11deb5251d3b7b9de66d1b4788c18a2b56aafe77ddd57423db41593"
624
641
  },
625
642
  eventCount: 1,
626
643
  modelCallCount: 0
@@ -628,7 +645,7 @@ var agent_improvement_proposal_default = {
628
645
  }
629
646
  },
630
647
  candidate: {
631
- digest: "sha256:2579dfae2c22ac30917c688f0ae31736e8c1cc81979e877c3139c80ca88f0064",
648
+ digest: "sha256:d99b9e877621de7c5fe20850fcdcf6b88119e46b0505dc4a7bf867201b0afafe",
632
649
  kind: "agent-candidate-execution-evidence",
633
650
  materializationReceipt: {
634
651
  benchmark: {
@@ -651,7 +668,7 @@ var agent_improvement_proposal_default = {
651
668
  }
652
669
  }
653
670
  },
654
- bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
671
+ bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
655
672
  codeKind: "disabled",
656
673
  container: {
657
674
  image: "ghcr.io/example/task",
@@ -663,16 +680,16 @@ var agent_improvement_proposal_default = {
663
680
  },
664
681
  source: "evaluator-task-container"
665
682
  },
666
- digest: "sha256:aee4c8842fa9a4c926a63ad2ad6f1ae370096b01987947d47568811b873e952f",
683
+ digest: "sha256:dc45d1b3f6fb88d4b0b709f6a2ff63164df737dddd582a8749ff7d91368662d9",
667
684
  digestAlgorithm: "rfc8785-sha256",
668
685
  executionPlan: {
669
686
  artifact: {
670
- byteLength: 1969,
671
- content: "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",
687
+ byteLength: 2032,
688
+ content: "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",
672
689
  encoding: "base64",
673
- sha256: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715"
690
+ sha256: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6"
674
691
  },
675
- digest: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715",
692
+ digest: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6",
676
693
  kind: "agent-candidate-execution-plan",
677
694
  material: {
678
695
  codeKind: "disabled",
@@ -699,7 +716,12 @@ var agent_improvement_proposal_default = {
699
716
  path: ".",
700
717
  workspace: "task"
701
718
  },
702
- env: {},
719
+ env: {
720
+ PATH: {
721
+ kind: "public",
722
+ value: "/usr/local/bin:/usr/bin:/bin"
723
+ }
724
+ },
703
725
  executable: "codex"
704
726
  },
705
727
  limits: {
@@ -748,9 +770,9 @@ var agent_improvement_proposal_default = {
748
770
  runCell: {
749
771
  arm: "candidate",
750
772
  attempt: 1,
751
- bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
752
- digest: "sha256:9774b5757485d7b4147d43caba5126f8f7ae7fef1a2d176982b592db034db605",
753
- experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
773
+ bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
774
+ digest: "sha256:e8faaad9b6ae2779d56d4f56d98f3197ed3d375298084ac08410c54632fb8b61",
775
+ experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
754
776
  kind: "agent-candidate-run-cell",
755
777
  repetition: 0,
756
778
  seed: 101,
@@ -819,12 +841,12 @@ var agent_improvement_proposal_default = {
819
841
  byteLength: 1121,
820
842
  locator: {
821
843
  bucket: "candidate-test-artifacts",
822
- key: "benchmark-result/ca685e9d916e6eef4155c93421d4a11569106ec3115e65df20b9d73324cbeccd",
844
+ key: "benchmark-result/78dab25681b91e59579ac46cc8b3d2bfb58d9f57430eb2625e9f2cd534d2b15a",
823
845
  kind: "s3"
824
846
  },
825
- sha256: "sha256:ca685e9d916e6eef4155c93421d4a11569106ec3115e65df20b9d73324cbeccd"
847
+ sha256: "sha256:78dab25681b91e59579ac46cc8b3d2bfb58d9f57430eb2625e9f2cd534d2b15a"
826
848
  },
827
- digest: "sha256:ca685e9d916e6eef4155c93421d4a11569106ec3115e65df20b9d73324cbeccd",
849
+ digest: "sha256:78dab25681b91e59579ac46cc8b3d2bfb58d9f57430eb2625e9f2cd534d2b15a",
828
850
  kind: "agent-candidate-benchmark-result",
829
851
  material: {
830
852
  dimensions: [
@@ -842,7 +864,7 @@ var agent_improvement_proposal_default = {
842
864
  },
843
865
  sha256: "sha256:9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d"
844
866
  },
845
- executionPlanDigest: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715",
867
+ executionPlanDigest: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6",
846
868
  grader: {
847
869
  artifact: {
848
870
  byteLength: 25,
@@ -875,24 +897,24 @@ var agent_improvement_proposal_default = {
875
897
  kind: "agent-candidate-benchmark-result-material",
876
898
  passed: true,
877
899
  score: 1,
878
- taskOutcomeDigest: "sha256:de4d75f7614ad314a31d7e3afc730af7f012bcf59b18059f5fa40cb287a12bde"
900
+ taskOutcomeDigest: "sha256:1674e3e6fc00ca4e74f44dc8247f3f6fd334c62f25b24eda25e37ca91d5fb016"
879
901
  }
880
902
  },
881
- bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
882
- digest: "sha256:60c4d05ae65274f073a39b00e3245a4b953fbfeca393b67a327fe4ed9f0114f3",
903
+ bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
904
+ digest: "sha256:3e003fb6cf3bde16a59f28901d29c752595794b000b79268b4b7be853adb4551",
883
905
  digestAlgorithm: "rfc8785-sha256",
884
- executionPlanDigest: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715",
906
+ executionPlanDigest: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6",
885
907
  executorCapture: {
886
908
  byteLength: 477,
887
909
  locator: {
888
910
  bucket: "candidate-test-artifacts",
889
- key: "executor-capture/d4b84f1358debca607a88fbf3879c91ee2709935101010d8cf361b86451b6c68",
911
+ key: "executor-capture/7b8a015c52a055cc2befaf553c1fe14e2f4daeafd520f085be2f5e29682baff3",
890
912
  kind: "s3"
891
913
  },
892
- sha256: "sha256:d4b84f1358debca607a88fbf3879c91ee2709935101010d8cf361b86451b6c68"
914
+ sha256: "sha256:7b8a015c52a055cc2befaf553c1fe14e2f4daeafd520f085be2f5e29682baff3"
893
915
  },
894
916
  kind: "agent-candidate-run",
895
- materializationReceiptDigest: "sha256:aee4c8842fa9a4c926a63ad2ad6f1ae370096b01987947d47568811b873e952f",
917
+ materializationReceiptDigest: "sha256:dc45d1b3f6fb88d4b0b709f6a2ff63164df737dddd582a8749ff7d91368662d9",
896
918
  memory: {
897
919
  mode: "disabled"
898
920
  },
@@ -901,17 +923,17 @@ var agent_improvement_proposal_default = {
901
923
  byteLength: 615,
902
924
  locator: {
903
925
  bucket: "candidate-test-artifacts",
904
- key: "model-settlement/5e58f7eacab44aac8bd7ea381ef68d300f5dbed0cd25c292cb1a4d4e187b30fe",
926
+ key: "model-settlement/6436cd10c36b64083ac00b0925efc03ef8d5e873f64cc2be5bdce4533366c8c4",
905
927
  kind: "s3"
906
928
  },
907
- sha256: "sha256:5e58f7eacab44aac8bd7ea381ef68d300f5dbed0cd25c292cb1a4d4e187b30fe"
929
+ sha256: "sha256:6436cd10c36b64083ac00b0925efc03ef8d5e873f64cc2be5bdce4533366c8c4"
908
930
  },
909
- digest: "sha256:5e58f7eacab44aac8bd7ea381ef68d300f5dbed0cd25c292cb1a4d4e187b30fe",
931
+ digest: "sha256:6436cd10c36b64083ac00b0925efc03ef8d5e873f64cc2be5bdce4533366c8c4",
910
932
  kind: "agent-candidate-model-settlement",
911
933
  material: {
912
934
  calls: [],
913
935
  closed: true,
914
- executionPlanDigest: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715",
936
+ executionPlanDigest: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6",
915
937
  grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
916
938
  kind: "agent-candidate-model-settlement-material",
917
939
  preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
@@ -932,21 +954,21 @@ var agent_improvement_proposal_default = {
932
954
  }
933
955
  }
934
956
  },
935
- runCellDigest: "sha256:9774b5757485d7b4147d43caba5126f8f7ae7fef1a2d176982b592db034db605",
957
+ runCellDigest: "sha256:e8faaad9b6ae2779d56d4f56d98f3197ed3d375298084ac08410c54632fb8b61",
936
958
  taskOutcome: {
937
959
  artifact: {
938
960
  byteLength: 478,
939
961
  locator: {
940
962
  bucket: "candidate-test-artifacts",
941
- key: "task-outcome/de4d75f7614ad314a31d7e3afc730af7f012bcf59b18059f5fa40cb287a12bde",
963
+ key: "task-outcome/1674e3e6fc00ca4e74f44dc8247f3f6fd334c62f25b24eda25e37ca91d5fb016",
942
964
  kind: "s3"
943
965
  },
944
- sha256: "sha256:de4d75f7614ad314a31d7e3afc730af7f012bcf59b18059f5fa40cb287a12bde"
966
+ sha256: "sha256:1674e3e6fc00ca4e74f44dc8247f3f6fd334c62f25b24eda25e37ca91d5fb016"
945
967
  },
946
- digest: "sha256:de4d75f7614ad314a31d7e3afc730af7f012bcf59b18059f5fa40cb287a12bde",
968
+ digest: "sha256:1674e3e6fc00ca4e74f44dc8247f3f6fd334c62f25b24eda25e37ca91d5fb016",
947
969
  kind: "agent-candidate-task-outcome",
948
970
  material: {
949
- executionPlanDigest: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715",
971
+ executionPlanDigest: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6",
950
972
  kind: "agent-candidate-task-outcome-material",
951
973
  outcome: {
952
974
  artifact: {
@@ -980,10 +1002,10 @@ var agent_improvement_proposal_default = {
980
1002
  byteLength: 750,
981
1003
  locator: {
982
1004
  bucket: "candidate-test-artifacts",
983
- key: "trace/8b368b3a19e808c43984c75e39301b3b69591d072453286e19960f85f0f988a6",
1005
+ key: "trace/f40b48a52282eaf104755ceb8dd6d713f6cc93fda296767f2656ef66ac4a55ff",
984
1006
  kind: "s3"
985
1007
  },
986
- sha256: "sha256:8b368b3a19e808c43984c75e39301b3b69591d072453286e19960f85f0f988a6"
1008
+ sha256: "sha256:f40b48a52282eaf104755ceb8dd6d713f6cc93fda296767f2656ef66ac4a55ff"
987
1009
  },
988
1010
  eventCount: 1,
989
1011
  modelCallCount: 0
@@ -993,7 +1015,7 @@ var agent_improvement_proposal_default = {
993
1015
  },
994
1016
  {
995
1017
  baseline: {
996
- digest: "sha256:23630e0e9893a8bc51f3632a4ea9b8d20828dad45bb52ad8aa70057b6f4ce388",
1018
+ digest: "sha256:9795afbb773b45c2d794522ad8c1fde600feda44cfd978572d62b93e9afb5724",
997
1019
  kind: "agent-candidate-execution-evidence",
998
1020
  materializationReceipt: {
999
1021
  benchmark: {
@@ -1016,7 +1038,7 @@ var agent_improvement_proposal_default = {
1016
1038
  }
1017
1039
  }
1018
1040
  },
1019
- bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
1041
+ bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
1020
1042
  codeKind: "disabled",
1021
1043
  container: {
1022
1044
  image: "ghcr.io/example/task",
@@ -1028,16 +1050,16 @@ var agent_improvement_proposal_default = {
1028
1050
  },
1029
1051
  source: "evaluator-task-container"
1030
1052
  },
1031
- digest: "sha256:8483cca8159d0fcbcc7ebe4bee689cdcf8e5872194335db4cf41301fc61be396",
1053
+ digest: "sha256:0406c21aababc8747dd9de4bc66e83dbc1bb48ad55048168178dcaa4016dc48f",
1032
1054
  digestAlgorithm: "rfc8785-sha256",
1033
1055
  executionPlan: {
1034
1056
  artifact: {
1035
- byteLength: 1967,
1036
- content: "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",
1057
+ byteLength: 2030,
1058
+ content: "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",
1037
1059
  encoding: "base64",
1038
- sha256: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca"
1060
+ sha256: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287"
1039
1061
  },
1040
- digest: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca",
1062
+ digest: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287",
1041
1063
  kind: "agent-candidate-execution-plan",
1042
1064
  material: {
1043
1065
  codeKind: "disabled",
@@ -1064,7 +1086,12 @@ var agent_improvement_proposal_default = {
1064
1086
  path: ".",
1065
1087
  workspace: "task"
1066
1088
  },
1067
- env: {},
1089
+ env: {
1090
+ PATH: {
1091
+ kind: "public",
1092
+ value: "/usr/local/bin:/usr/bin:/bin"
1093
+ }
1094
+ },
1068
1095
  executable: "codex"
1069
1096
  },
1070
1097
  limits: {
@@ -1113,9 +1140,9 @@ var agent_improvement_proposal_default = {
1113
1140
  runCell: {
1114
1141
  arm: "baseline",
1115
1142
  attempt: 1,
1116
- bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
1117
- digest: "sha256:ce44b5854c9133ba5f2c78069462c2977fed54a09eb18a0bca250902cf2718eb",
1118
- experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
1143
+ bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
1144
+ digest: "sha256:1c64f3d18b9d8c5a34231c5c7c2d3496e225051c9f2930ca97d01176492e8e76",
1145
+ experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
1119
1146
  kind: "agent-candidate-run-cell",
1120
1147
  repetition: 1,
1121
1148
  seed: 102,
@@ -1180,12 +1207,12 @@ var agent_improvement_proposal_default = {
1180
1207
  byteLength: 1122,
1181
1208
  locator: {
1182
1209
  bucket: "candidate-test-artifacts",
1183
- key: "benchmark-result/73c5061dc61b9840165883f6b4950405917399949b459e1cba5933153883f94d",
1210
+ key: "benchmark-result/c9891b43d8cc45bb7b1d76eccce93421af4c329983e4d2cbfd4411df4cd228da",
1184
1211
  kind: "s3"
1185
1212
  },
1186
- sha256: "sha256:73c5061dc61b9840165883f6b4950405917399949b459e1cba5933153883f94d"
1213
+ sha256: "sha256:c9891b43d8cc45bb7b1d76eccce93421af4c329983e4d2cbfd4411df4cd228da"
1187
1214
  },
1188
- digest: "sha256:73c5061dc61b9840165883f6b4950405917399949b459e1cba5933153883f94d",
1215
+ digest: "sha256:c9891b43d8cc45bb7b1d76eccce93421af4c329983e4d2cbfd4411df4cd228da",
1189
1216
  kind: "agent-candidate-benchmark-result",
1190
1217
  material: {
1191
1218
  dimensions: [
@@ -1203,7 +1230,7 @@ var agent_improvement_proposal_default = {
1203
1230
  },
1204
1231
  sha256: "sha256:628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b"
1205
1232
  },
1206
- executionPlanDigest: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca",
1233
+ executionPlanDigest: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287",
1207
1234
  grader: {
1208
1235
  artifact: {
1209
1236
  byteLength: 25,
@@ -1236,24 +1263,24 @@ var agent_improvement_proposal_default = {
1236
1263
  kind: "agent-candidate-benchmark-result-material",
1237
1264
  passed: false,
1238
1265
  score: 0,
1239
- taskOutcomeDigest: "sha256:6531580f45e8618a7e381fe78de4e49b0d68d589702ad23f81fa27ccea872e06"
1266
+ taskOutcomeDigest: "sha256:24cd5d7f59ab6334118cd341ad8f8fd4d20156a561ddb2b55fe86c61c2895aa2"
1240
1267
  }
1241
1268
  },
1242
- bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
1243
- digest: "sha256:1758e0ee11654db77d6c11b02ec1e777b2b7a1610ae4e363effd1dfb51a8d643",
1269
+ bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
1270
+ digest: "sha256:362e0b403b592b762ec92734f1286ecaf0c08e40970525de14b3052b335b8618",
1244
1271
  digestAlgorithm: "rfc8785-sha256",
1245
- executionPlanDigest: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca",
1272
+ executionPlanDigest: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287",
1246
1273
  executorCapture: {
1247
1274
  byteLength: 477,
1248
1275
  locator: {
1249
1276
  bucket: "candidate-test-artifacts",
1250
- key: "executor-capture/c7e618da9214d4e3b4ce81fc70d3c6edec1fa80e6ab06369b0a3684548cfbf1f",
1277
+ key: "executor-capture/da5fc6561b02133890cdfb4cdc0b3495d17059040b27c1be20b8a123d2a6524a",
1251
1278
  kind: "s3"
1252
1279
  },
1253
- sha256: "sha256:c7e618da9214d4e3b4ce81fc70d3c6edec1fa80e6ab06369b0a3684548cfbf1f"
1280
+ sha256: "sha256:da5fc6561b02133890cdfb4cdc0b3495d17059040b27c1be20b8a123d2a6524a"
1254
1281
  },
1255
1282
  kind: "agent-candidate-run",
1256
- materializationReceiptDigest: "sha256:8483cca8159d0fcbcc7ebe4bee689cdcf8e5872194335db4cf41301fc61be396",
1283
+ materializationReceiptDigest: "sha256:0406c21aababc8747dd9de4bc66e83dbc1bb48ad55048168178dcaa4016dc48f",
1257
1284
  memory: {
1258
1285
  mode: "disabled"
1259
1286
  },
@@ -1262,17 +1289,17 @@ var agent_improvement_proposal_default = {
1262
1289
  byteLength: 615,
1263
1290
  locator: {
1264
1291
  bucket: "candidate-test-artifacts",
1265
- key: "model-settlement/ef07959f28b6123ce5d2776d81d7cae1408b48038aeee70c76b308a30e26de65",
1292
+ key: "model-settlement/446db011d1af4c39f2d0fd21a7e64774b9aaa685efe56e928d8e67d8ea1b3fa3",
1266
1293
  kind: "s3"
1267
1294
  },
1268
- sha256: "sha256:ef07959f28b6123ce5d2776d81d7cae1408b48038aeee70c76b308a30e26de65"
1295
+ sha256: "sha256:446db011d1af4c39f2d0fd21a7e64774b9aaa685efe56e928d8e67d8ea1b3fa3"
1269
1296
  },
1270
- digest: "sha256:ef07959f28b6123ce5d2776d81d7cae1408b48038aeee70c76b308a30e26de65",
1297
+ digest: "sha256:446db011d1af4c39f2d0fd21a7e64774b9aaa685efe56e928d8e67d8ea1b3fa3",
1271
1298
  kind: "agent-candidate-model-settlement",
1272
1299
  material: {
1273
1300
  calls: [],
1274
1301
  closed: true,
1275
- executionPlanDigest: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca",
1302
+ executionPlanDigest: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287",
1276
1303
  grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
1277
1304
  kind: "agent-candidate-model-settlement-material",
1278
1305
  preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
@@ -1293,21 +1320,21 @@ var agent_improvement_proposal_default = {
1293
1320
  }
1294
1321
  }
1295
1322
  },
1296
- runCellDigest: "sha256:ce44b5854c9133ba5f2c78069462c2977fed54a09eb18a0bca250902cf2718eb",
1323
+ runCellDigest: "sha256:1c64f3d18b9d8c5a34231c5c7c2d3496e225051c9f2930ca97d01176492e8e76",
1297
1324
  taskOutcome: {
1298
1325
  artifact: {
1299
1326
  byteLength: 478,
1300
1327
  locator: {
1301
1328
  bucket: "candidate-test-artifacts",
1302
- key: "task-outcome/6531580f45e8618a7e381fe78de4e49b0d68d589702ad23f81fa27ccea872e06",
1329
+ key: "task-outcome/24cd5d7f59ab6334118cd341ad8f8fd4d20156a561ddb2b55fe86c61c2895aa2",
1303
1330
  kind: "s3"
1304
1331
  },
1305
- sha256: "sha256:6531580f45e8618a7e381fe78de4e49b0d68d589702ad23f81fa27ccea872e06"
1332
+ sha256: "sha256:24cd5d7f59ab6334118cd341ad8f8fd4d20156a561ddb2b55fe86c61c2895aa2"
1306
1333
  },
1307
- digest: "sha256:6531580f45e8618a7e381fe78de4e49b0d68d589702ad23f81fa27ccea872e06",
1334
+ digest: "sha256:24cd5d7f59ab6334118cd341ad8f8fd4d20156a561ddb2b55fe86c61c2895aa2",
1308
1335
  kind: "agent-candidate-task-outcome",
1309
1336
  material: {
1310
- executionPlanDigest: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca",
1337
+ executionPlanDigest: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287",
1311
1338
  kind: "agent-candidate-task-outcome-material",
1312
1339
  outcome: {
1313
1340
  artifact: {
@@ -1341,10 +1368,10 @@ var agent_improvement_proposal_default = {
1341
1368
  byteLength: 748,
1342
1369
  locator: {
1343
1370
  bucket: "candidate-test-artifacts",
1344
- key: "trace/6f94838ea9d7d02576c9b692a388eba163ccab95bc9b39fd99d30f97e34db45e",
1371
+ key: "trace/c03c3bd51fb421ffc65985a27619e57b16623ba3f2bc8d22b2f963cdae6e41f6",
1345
1372
  kind: "s3"
1346
1373
  },
1347
- sha256: "sha256:6f94838ea9d7d02576c9b692a388eba163ccab95bc9b39fd99d30f97e34db45e"
1374
+ sha256: "sha256:c03c3bd51fb421ffc65985a27619e57b16623ba3f2bc8d22b2f963cdae6e41f6"
1348
1375
  },
1349
1376
  eventCount: 1,
1350
1377
  modelCallCount: 0
@@ -1352,7 +1379,7 @@ var agent_improvement_proposal_default = {
1352
1379
  }
1353
1380
  },
1354
1381
  candidate: {
1355
- digest: "sha256:7ca0ac188c3520be751d9154b5911ccb72ac9025a8abb7516027ee5c4e0aee78",
1382
+ digest: "sha256:90aa644ce8a4a7bd8968146189ec279b74c550ae6ff02b08adfa984008b68ce5",
1356
1383
  kind: "agent-candidate-execution-evidence",
1357
1384
  materializationReceipt: {
1358
1385
  benchmark: {
@@ -1375,7 +1402,7 @@ var agent_improvement_proposal_default = {
1375
1402
  }
1376
1403
  }
1377
1404
  },
1378
- bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
1405
+ bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
1379
1406
  codeKind: "disabled",
1380
1407
  container: {
1381
1408
  image: "ghcr.io/example/task",
@@ -1387,16 +1414,16 @@ var agent_improvement_proposal_default = {
1387
1414
  },
1388
1415
  source: "evaluator-task-container"
1389
1416
  },
1390
- digest: "sha256:7d002279e2baef8149e264789cffb919024e4290c4a1e3793823a8930c7a94a1",
1417
+ digest: "sha256:d6e837e515c14c86a79f6fb099384a0ac97d74cbfebc2e1a095a8b7660ef1fed",
1391
1418
  digestAlgorithm: "rfc8785-sha256",
1392
1419
  executionPlan: {
1393
1420
  artifact: {
1394
- byteLength: 1969,
1395
- content: "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",
1421
+ byteLength: 2032,
1422
+ content: "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",
1396
1423
  encoding: "base64",
1397
- sha256: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e"
1424
+ sha256: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6"
1398
1425
  },
1399
- digest: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e",
1426
+ digest: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6",
1400
1427
  kind: "agent-candidate-execution-plan",
1401
1428
  material: {
1402
1429
  codeKind: "disabled",
@@ -1423,7 +1450,12 @@ var agent_improvement_proposal_default = {
1423
1450
  path: ".",
1424
1451
  workspace: "task"
1425
1452
  },
1426
- env: {},
1453
+ env: {
1454
+ PATH: {
1455
+ kind: "public",
1456
+ value: "/usr/local/bin:/usr/bin:/bin"
1457
+ }
1458
+ },
1427
1459
  executable: "codex"
1428
1460
  },
1429
1461
  limits: {
@@ -1472,9 +1504,9 @@ var agent_improvement_proposal_default = {
1472
1504
  runCell: {
1473
1505
  arm: "candidate",
1474
1506
  attempt: 1,
1475
- bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
1476
- digest: "sha256:1033e245dd0fbb12ef169f86149fcf93e90f2a5a76b05c0f05c26a165fcaa15c",
1477
- experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
1507
+ bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
1508
+ digest: "sha256:3056f0119ac4643dc3defb95fb324552e10f94e40621231d1f60d148f59d1d39",
1509
+ experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
1478
1510
  kind: "agent-candidate-run-cell",
1479
1511
  repetition: 1,
1480
1512
  seed: 102,
@@ -1543,12 +1575,12 @@ var agent_improvement_proposal_default = {
1543
1575
  byteLength: 1121,
1544
1576
  locator: {
1545
1577
  bucket: "candidate-test-artifacts",
1546
- key: "benchmark-result/de40c4387aab2c749b768a55f4569348ae55ee882485356a65b5509bf6f00620",
1578
+ key: "benchmark-result/8b1ecbcec1ebdb0ec02a3785ff61796b8de31c83830d446c560029dc127a45ca",
1547
1579
  kind: "s3"
1548
1580
  },
1549
- sha256: "sha256:de40c4387aab2c749b768a55f4569348ae55ee882485356a65b5509bf6f00620"
1581
+ sha256: "sha256:8b1ecbcec1ebdb0ec02a3785ff61796b8de31c83830d446c560029dc127a45ca"
1550
1582
  },
1551
- digest: "sha256:de40c4387aab2c749b768a55f4569348ae55ee882485356a65b5509bf6f00620",
1583
+ digest: "sha256:8b1ecbcec1ebdb0ec02a3785ff61796b8de31c83830d446c560029dc127a45ca",
1552
1584
  kind: "agent-candidate-benchmark-result",
1553
1585
  material: {
1554
1586
  dimensions: [
@@ -1566,7 +1598,7 @@ var agent_improvement_proposal_default = {
1566
1598
  },
1567
1599
  sha256: "sha256:9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d"
1568
1600
  },
1569
- executionPlanDigest: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e",
1601
+ executionPlanDigest: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6",
1570
1602
  grader: {
1571
1603
  artifact: {
1572
1604
  byteLength: 25,
@@ -1599,24 +1631,24 @@ var agent_improvement_proposal_default = {
1599
1631
  kind: "agent-candidate-benchmark-result-material",
1600
1632
  passed: true,
1601
1633
  score: 1,
1602
- taskOutcomeDigest: "sha256:71e7ac55968898115c4b3e0a8e71f02eaf6c5d4b46a67806f1bde01efc96b777"
1634
+ taskOutcomeDigest: "sha256:f24062b48a7ba4bfe3e2566ef7e0d4e97d3c38d7a54e86bf86446adf7fa1cef4"
1603
1635
  }
1604
1636
  },
1605
- bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
1606
- digest: "sha256:1ab7c0b04a606512d0cbadc08858d7e127122d3ccc8a4c22cf450e37600663a0",
1637
+ bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
1638
+ digest: "sha256:bbfcb8dfe7d34f06ce47c8a6562ab15fcaa1dc083524eb692890055e2e2ccc27",
1607
1639
  digestAlgorithm: "rfc8785-sha256",
1608
- executionPlanDigest: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e",
1640
+ executionPlanDigest: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6",
1609
1641
  executorCapture: {
1610
1642
  byteLength: 477,
1611
1643
  locator: {
1612
1644
  bucket: "candidate-test-artifacts",
1613
- key: "executor-capture/7750feebcefe19391bdb10cc84100db9941cf738a4e26921a387ac3a2b5094a3",
1645
+ key: "executor-capture/5d5db54b6c1e1d5e8d3c1248b3617dcdc8cefb80aa69cf750a1abacbadf9efdb",
1614
1646
  kind: "s3"
1615
1647
  },
1616
- sha256: "sha256:7750feebcefe19391bdb10cc84100db9941cf738a4e26921a387ac3a2b5094a3"
1648
+ sha256: "sha256:5d5db54b6c1e1d5e8d3c1248b3617dcdc8cefb80aa69cf750a1abacbadf9efdb"
1617
1649
  },
1618
1650
  kind: "agent-candidate-run",
1619
- materializationReceiptDigest: "sha256:7d002279e2baef8149e264789cffb919024e4290c4a1e3793823a8930c7a94a1",
1651
+ materializationReceiptDigest: "sha256:d6e837e515c14c86a79f6fb099384a0ac97d74cbfebc2e1a095a8b7660ef1fed",
1620
1652
  memory: {
1621
1653
  mode: "disabled"
1622
1654
  },
@@ -1625,17 +1657,17 @@ var agent_improvement_proposal_default = {
1625
1657
  byteLength: 615,
1626
1658
  locator: {
1627
1659
  bucket: "candidate-test-artifacts",
1628
- key: "model-settlement/ba3d7012d96e93d5b4f5877d53b9509562f761e5c387c94410f69b39c238cef3",
1660
+ key: "model-settlement/87ad72eeccca5a0d4593d75b73d7cd4d0d3ffba748b30becc3b496e74ad5d83b",
1629
1661
  kind: "s3"
1630
1662
  },
1631
- sha256: "sha256:ba3d7012d96e93d5b4f5877d53b9509562f761e5c387c94410f69b39c238cef3"
1663
+ sha256: "sha256:87ad72eeccca5a0d4593d75b73d7cd4d0d3ffba748b30becc3b496e74ad5d83b"
1632
1664
  },
1633
- digest: "sha256:ba3d7012d96e93d5b4f5877d53b9509562f761e5c387c94410f69b39c238cef3",
1665
+ digest: "sha256:87ad72eeccca5a0d4593d75b73d7cd4d0d3ffba748b30becc3b496e74ad5d83b",
1634
1666
  kind: "agent-candidate-model-settlement",
1635
1667
  material: {
1636
1668
  calls: [],
1637
1669
  closed: true,
1638
- executionPlanDigest: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e",
1670
+ executionPlanDigest: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6",
1639
1671
  grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
1640
1672
  kind: "agent-candidate-model-settlement-material",
1641
1673
  preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
@@ -1656,21 +1688,21 @@ var agent_improvement_proposal_default = {
1656
1688
  }
1657
1689
  }
1658
1690
  },
1659
- runCellDigest: "sha256:1033e245dd0fbb12ef169f86149fcf93e90f2a5a76b05c0f05c26a165fcaa15c",
1691
+ runCellDigest: "sha256:3056f0119ac4643dc3defb95fb324552e10f94e40621231d1f60d148f59d1d39",
1660
1692
  taskOutcome: {
1661
1693
  artifact: {
1662
1694
  byteLength: 478,
1663
1695
  locator: {
1664
1696
  bucket: "candidate-test-artifacts",
1665
- key: "task-outcome/71e7ac55968898115c4b3e0a8e71f02eaf6c5d4b46a67806f1bde01efc96b777",
1697
+ key: "task-outcome/f24062b48a7ba4bfe3e2566ef7e0d4e97d3c38d7a54e86bf86446adf7fa1cef4",
1666
1698
  kind: "s3"
1667
1699
  },
1668
- sha256: "sha256:71e7ac55968898115c4b3e0a8e71f02eaf6c5d4b46a67806f1bde01efc96b777"
1700
+ sha256: "sha256:f24062b48a7ba4bfe3e2566ef7e0d4e97d3c38d7a54e86bf86446adf7fa1cef4"
1669
1701
  },
1670
- digest: "sha256:71e7ac55968898115c4b3e0a8e71f02eaf6c5d4b46a67806f1bde01efc96b777",
1702
+ digest: "sha256:f24062b48a7ba4bfe3e2566ef7e0d4e97d3c38d7a54e86bf86446adf7fa1cef4",
1671
1703
  kind: "agent-candidate-task-outcome",
1672
1704
  material: {
1673
- executionPlanDigest: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e",
1705
+ executionPlanDigest: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6",
1674
1706
  kind: "agent-candidate-task-outcome-material",
1675
1707
  outcome: {
1676
1708
  artifact: {
@@ -1704,10 +1736,10 @@ var agent_improvement_proposal_default = {
1704
1736
  byteLength: 750,
1705
1737
  locator: {
1706
1738
  bucket: "candidate-test-artifacts",
1707
- key: "trace/7a1d1b35b1a21cf30833a83945af1aa5a74d957c91b7bdb742fb832e25c99f0e",
1739
+ key: "trace/e2cdd682a809a037e0049d1b3d3280d7b4099a3e0507b3591fc05b2872641166",
1708
1740
  kind: "s3"
1709
1741
  },
1710
- sha256: "sha256:7a1d1b35b1a21cf30833a83945af1aa5a74d957c91b7bdb742fb832e25c99f0e"
1742
+ sha256: "sha256:e2cdd682a809a037e0049d1b3d3280d7b4099a3e0507b3591fc05b2872641166"
1711
1743
  },
1712
1744
  eventCount: 1,
1713
1745
  modelCallCount: 0
@@ -1717,7 +1749,7 @@ var agent_improvement_proposal_default = {
1717
1749
  },
1718
1750
  {
1719
1751
  baseline: {
1720
- digest: "sha256:19810401295dd6a49219ea005d0b75155f688c9dd972ec6fb6dd43220014426e",
1752
+ digest: "sha256:7ebfc740cb6c0156ce54d450015af9e418a57473299022f926555f2a5b706454",
1721
1753
  kind: "agent-candidate-execution-evidence",
1722
1754
  materializationReceipt: {
1723
1755
  benchmark: {
@@ -1740,7 +1772,7 @@ var agent_improvement_proposal_default = {
1740
1772
  }
1741
1773
  }
1742
1774
  },
1743
- bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
1775
+ bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
1744
1776
  codeKind: "disabled",
1745
1777
  container: {
1746
1778
  image: "ghcr.io/example/task",
@@ -1752,16 +1784,16 @@ var agent_improvement_proposal_default = {
1752
1784
  },
1753
1785
  source: "evaluator-task-container"
1754
1786
  },
1755
- digest: "sha256:03fea1af601d95a26c9b22df9ffd8e7cc6f8341ad9eb12e18c008587cf70752e",
1787
+ digest: "sha256:0e3da90681970b46a99808f5d5a623329bae9529bf0f46ccebe7cac7a202ec8a",
1756
1788
  digestAlgorithm: "rfc8785-sha256",
1757
1789
  executionPlan: {
1758
1790
  artifact: {
1759
- byteLength: 1967,
1760
- content: "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",
1791
+ byteLength: 2030,
1792
+ content: "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",
1761
1793
  encoding: "base64",
1762
- sha256: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236"
1794
+ sha256: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e"
1763
1795
  },
1764
- digest: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236",
1796
+ digest: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e",
1765
1797
  kind: "agent-candidate-execution-plan",
1766
1798
  material: {
1767
1799
  codeKind: "disabled",
@@ -1788,7 +1820,12 @@ var agent_improvement_proposal_default = {
1788
1820
  path: ".",
1789
1821
  workspace: "task"
1790
1822
  },
1791
- env: {},
1823
+ env: {
1824
+ PATH: {
1825
+ kind: "public",
1826
+ value: "/usr/local/bin:/usr/bin:/bin"
1827
+ }
1828
+ },
1792
1829
  executable: "codex"
1793
1830
  },
1794
1831
  limits: {
@@ -1837,9 +1874,9 @@ var agent_improvement_proposal_default = {
1837
1874
  runCell: {
1838
1875
  arm: "baseline",
1839
1876
  attempt: 1,
1840
- bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
1841
- digest: "sha256:7ab33028de32ca70ca169a41bc032b12a3a76bb26baebe8b5802637b996941e4",
1842
- experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
1877
+ bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
1878
+ digest: "sha256:9c427cc67507cda8dcdac327f390adfa7e045d069e677d62921678b46a96d66c",
1879
+ experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
1843
1880
  kind: "agent-candidate-run-cell",
1844
1881
  repetition: 2,
1845
1882
  seed: 103,
@@ -1904,12 +1941,12 @@ var agent_improvement_proposal_default = {
1904
1941
  byteLength: 1122,
1905
1942
  locator: {
1906
1943
  bucket: "candidate-test-artifacts",
1907
- key: "benchmark-result/9deed92c5c6f606541d59db8a52f33334c76e9766ddb19108399942dd28dd66b",
1944
+ key: "benchmark-result/df1a5884a7ed4e54dae3d023b47c21596d27264b5ca59693b51eb221dd533284",
1908
1945
  kind: "s3"
1909
1946
  },
1910
- sha256: "sha256:9deed92c5c6f606541d59db8a52f33334c76e9766ddb19108399942dd28dd66b"
1947
+ sha256: "sha256:df1a5884a7ed4e54dae3d023b47c21596d27264b5ca59693b51eb221dd533284"
1911
1948
  },
1912
- digest: "sha256:9deed92c5c6f606541d59db8a52f33334c76e9766ddb19108399942dd28dd66b",
1949
+ digest: "sha256:df1a5884a7ed4e54dae3d023b47c21596d27264b5ca59693b51eb221dd533284",
1913
1950
  kind: "agent-candidate-benchmark-result",
1914
1951
  material: {
1915
1952
  dimensions: [
@@ -1927,7 +1964,7 @@ var agent_improvement_proposal_default = {
1927
1964
  },
1928
1965
  sha256: "sha256:628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b"
1929
1966
  },
1930
- executionPlanDigest: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236",
1967
+ executionPlanDigest: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e",
1931
1968
  grader: {
1932
1969
  artifact: {
1933
1970
  byteLength: 25,
@@ -1960,24 +1997,24 @@ var agent_improvement_proposal_default = {
1960
1997
  kind: "agent-candidate-benchmark-result-material",
1961
1998
  passed: false,
1962
1999
  score: 0,
1963
- taskOutcomeDigest: "sha256:b7839b059ff6bc2b5606d53992c1e3b1001b5917ca21798e07a696c2b555faef"
2000
+ taskOutcomeDigest: "sha256:664358fd0e890ca17d0c31aa0157e434c3bc7f6ecaa77c581d5ef600b6a836ce"
1964
2001
  }
1965
2002
  },
1966
- bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
1967
- digest: "sha256:b94caa496f9425e76559b3d11482a9156af47aec0c4736a3f2acde6e0d7147f6",
2003
+ bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
2004
+ digest: "sha256:7dfea3ef8bf6e5c0432180fefe63cad9f62833ecb8bea1ce0de7d41ca3ef3bc5",
1968
2005
  digestAlgorithm: "rfc8785-sha256",
1969
- executionPlanDigest: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236",
2006
+ executionPlanDigest: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e",
1970
2007
  executorCapture: {
1971
2008
  byteLength: 477,
1972
2009
  locator: {
1973
2010
  bucket: "candidate-test-artifacts",
1974
- key: "executor-capture/41c380f90694c94d3638d3f6a1bc2984edabc4b841135563ec693988318a789a",
2011
+ key: "executor-capture/3fdb1d6105bd10c22daa6c0267015a8f6a88b13d1703e8bf2c901c0887a4b242",
1975
2012
  kind: "s3"
1976
2013
  },
1977
- sha256: "sha256:41c380f90694c94d3638d3f6a1bc2984edabc4b841135563ec693988318a789a"
2014
+ sha256: "sha256:3fdb1d6105bd10c22daa6c0267015a8f6a88b13d1703e8bf2c901c0887a4b242"
1978
2015
  },
1979
2016
  kind: "agent-candidate-run",
1980
- materializationReceiptDigest: "sha256:03fea1af601d95a26c9b22df9ffd8e7cc6f8341ad9eb12e18c008587cf70752e",
2017
+ materializationReceiptDigest: "sha256:0e3da90681970b46a99808f5d5a623329bae9529bf0f46ccebe7cac7a202ec8a",
1981
2018
  memory: {
1982
2019
  mode: "disabled"
1983
2020
  },
@@ -1986,17 +2023,17 @@ var agent_improvement_proposal_default = {
1986
2023
  byteLength: 615,
1987
2024
  locator: {
1988
2025
  bucket: "candidate-test-artifacts",
1989
- key: "model-settlement/43f369d800ff013c35fc63eab901109849030ade35def608ad3229a97c9b5c52",
2026
+ key: "model-settlement/39c54b821165bbff4a33cf310c51e20f6d1ff0ee10ff7630618010e91d5a1615",
1990
2027
  kind: "s3"
1991
2028
  },
1992
- sha256: "sha256:43f369d800ff013c35fc63eab901109849030ade35def608ad3229a97c9b5c52"
2029
+ sha256: "sha256:39c54b821165bbff4a33cf310c51e20f6d1ff0ee10ff7630618010e91d5a1615"
1993
2030
  },
1994
- digest: "sha256:43f369d800ff013c35fc63eab901109849030ade35def608ad3229a97c9b5c52",
2031
+ digest: "sha256:39c54b821165bbff4a33cf310c51e20f6d1ff0ee10ff7630618010e91d5a1615",
1995
2032
  kind: "agent-candidate-model-settlement",
1996
2033
  material: {
1997
2034
  calls: [],
1998
2035
  closed: true,
1999
- executionPlanDigest: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236",
2036
+ executionPlanDigest: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e",
2000
2037
  grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
2001
2038
  kind: "agent-candidate-model-settlement-material",
2002
2039
  preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
@@ -2017,21 +2054,21 @@ var agent_improvement_proposal_default = {
2017
2054
  }
2018
2055
  }
2019
2056
  },
2020
- runCellDigest: "sha256:7ab33028de32ca70ca169a41bc032b12a3a76bb26baebe8b5802637b996941e4",
2057
+ runCellDigest: "sha256:9c427cc67507cda8dcdac327f390adfa7e045d069e677d62921678b46a96d66c",
2021
2058
  taskOutcome: {
2022
2059
  artifact: {
2023
2060
  byteLength: 478,
2024
2061
  locator: {
2025
2062
  bucket: "candidate-test-artifacts",
2026
- key: "task-outcome/b7839b059ff6bc2b5606d53992c1e3b1001b5917ca21798e07a696c2b555faef",
2063
+ key: "task-outcome/664358fd0e890ca17d0c31aa0157e434c3bc7f6ecaa77c581d5ef600b6a836ce",
2027
2064
  kind: "s3"
2028
2065
  },
2029
- sha256: "sha256:b7839b059ff6bc2b5606d53992c1e3b1001b5917ca21798e07a696c2b555faef"
2066
+ sha256: "sha256:664358fd0e890ca17d0c31aa0157e434c3bc7f6ecaa77c581d5ef600b6a836ce"
2030
2067
  },
2031
- digest: "sha256:b7839b059ff6bc2b5606d53992c1e3b1001b5917ca21798e07a696c2b555faef",
2068
+ digest: "sha256:664358fd0e890ca17d0c31aa0157e434c3bc7f6ecaa77c581d5ef600b6a836ce",
2032
2069
  kind: "agent-candidate-task-outcome",
2033
2070
  material: {
2034
- executionPlanDigest: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236",
2071
+ executionPlanDigest: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e",
2035
2072
  kind: "agent-candidate-task-outcome-material",
2036
2073
  outcome: {
2037
2074
  artifact: {
@@ -2065,10 +2102,10 @@ var agent_improvement_proposal_default = {
2065
2102
  byteLength: 748,
2066
2103
  locator: {
2067
2104
  bucket: "candidate-test-artifacts",
2068
- key: "trace/11de40695ad7fd6a370835f9945fa8e43348443d95a22d559992c294b2fb58b8",
2105
+ key: "trace/f1867bc538dae9c3a35e73fd7c21c06150bbcba815a56835f70b26d615a6e66d",
2069
2106
  kind: "s3"
2070
2107
  },
2071
- sha256: "sha256:11de40695ad7fd6a370835f9945fa8e43348443d95a22d559992c294b2fb58b8"
2108
+ sha256: "sha256:f1867bc538dae9c3a35e73fd7c21c06150bbcba815a56835f70b26d615a6e66d"
2072
2109
  },
2073
2110
  eventCount: 1,
2074
2111
  modelCallCount: 0
@@ -2076,7 +2113,7 @@ var agent_improvement_proposal_default = {
2076
2113
  }
2077
2114
  },
2078
2115
  candidate: {
2079
- digest: "sha256:7f299ebc9ac6801ecadc3325e7e1e474d292db2f3ad626e74daa721ea24998df",
2116
+ digest: "sha256:325bbde1ccafdb3786a26b48ad407fea1912f0d7b340c4a654a1ebdc622d960c",
2080
2117
  kind: "agent-candidate-execution-evidence",
2081
2118
  materializationReceipt: {
2082
2119
  benchmark: {
@@ -2099,7 +2136,7 @@ var agent_improvement_proposal_default = {
2099
2136
  }
2100
2137
  }
2101
2138
  },
2102
- bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
2139
+ bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
2103
2140
  codeKind: "disabled",
2104
2141
  container: {
2105
2142
  image: "ghcr.io/example/task",
@@ -2111,16 +2148,16 @@ var agent_improvement_proposal_default = {
2111
2148
  },
2112
2149
  source: "evaluator-task-container"
2113
2150
  },
2114
- digest: "sha256:58b85d501d6559779de74275f638c76ef2a0c7decff907081b8e20d5df37d1c6",
2151
+ digest: "sha256:b3718d6b33e7316d37af34e81e93a6521b0e9914bdec820d56e14fd7008f3e05",
2115
2152
  digestAlgorithm: "rfc8785-sha256",
2116
2153
  executionPlan: {
2117
2154
  artifact: {
2118
- byteLength: 1969,
2119
- content: "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",
2155
+ byteLength: 2032,
2156
+ content: "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",
2120
2157
  encoding: "base64",
2121
- sha256: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669"
2158
+ sha256: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f"
2122
2159
  },
2123
- digest: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669",
2160
+ digest: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f",
2124
2161
  kind: "agent-candidate-execution-plan",
2125
2162
  material: {
2126
2163
  codeKind: "disabled",
@@ -2147,7 +2184,12 @@ var agent_improvement_proposal_default = {
2147
2184
  path: ".",
2148
2185
  workspace: "task"
2149
2186
  },
2150
- env: {},
2187
+ env: {
2188
+ PATH: {
2189
+ kind: "public",
2190
+ value: "/usr/local/bin:/usr/bin:/bin"
2191
+ }
2192
+ },
2151
2193
  executable: "codex"
2152
2194
  },
2153
2195
  limits: {
@@ -2196,9 +2238,9 @@ var agent_improvement_proposal_default = {
2196
2238
  runCell: {
2197
2239
  arm: "candidate",
2198
2240
  attempt: 1,
2199
- bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
2200
- digest: "sha256:b725cf36cf0b5b2ecf09cd8f09e4a463c98ba909b4622220ce74754c12a51a3a",
2201
- experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
2241
+ bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
2242
+ digest: "sha256:ea5cab9dff49326dfe856aab19514d2bc5bc0fab2b4b685c4fea356801dbd1c3",
2243
+ experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
2202
2244
  kind: "agent-candidate-run-cell",
2203
2245
  repetition: 2,
2204
2246
  seed: 103,
@@ -2267,12 +2309,12 @@ var agent_improvement_proposal_default = {
2267
2309
  byteLength: 1121,
2268
2310
  locator: {
2269
2311
  bucket: "candidate-test-artifacts",
2270
- key: "benchmark-result/065077bb8c8d7ce16e785ddfa6fc633ea492aafcc94162b7ac171fafb3c579ad",
2312
+ key: "benchmark-result/95541270205f83cd4d1fe61062e133c4f2afdb1978d1af56de0aef0410999aa4",
2271
2313
  kind: "s3"
2272
2314
  },
2273
- sha256: "sha256:065077bb8c8d7ce16e785ddfa6fc633ea492aafcc94162b7ac171fafb3c579ad"
2315
+ sha256: "sha256:95541270205f83cd4d1fe61062e133c4f2afdb1978d1af56de0aef0410999aa4"
2274
2316
  },
2275
- digest: "sha256:065077bb8c8d7ce16e785ddfa6fc633ea492aafcc94162b7ac171fafb3c579ad",
2317
+ digest: "sha256:95541270205f83cd4d1fe61062e133c4f2afdb1978d1af56de0aef0410999aa4",
2276
2318
  kind: "agent-candidate-benchmark-result",
2277
2319
  material: {
2278
2320
  dimensions: [
@@ -2290,7 +2332,7 @@ var agent_improvement_proposal_default = {
2290
2332
  },
2291
2333
  sha256: "sha256:9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d"
2292
2334
  },
2293
- executionPlanDigest: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669",
2335
+ executionPlanDigest: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f",
2294
2336
  grader: {
2295
2337
  artifact: {
2296
2338
  byteLength: 25,
@@ -2323,24 +2365,24 @@ var agent_improvement_proposal_default = {
2323
2365
  kind: "agent-candidate-benchmark-result-material",
2324
2366
  passed: true,
2325
2367
  score: 1,
2326
- taskOutcomeDigest: "sha256:4dcf33ca1333772d635d34932d4348fb55d7dd4146f734f97bd1b296ad059f0f"
2368
+ taskOutcomeDigest: "sha256:61d53d0789c46c98b43acdc7177b1b6102f48aa2d6b3b2ff0ec5ee4b287c8d92"
2327
2369
  }
2328
2370
  },
2329
- bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
2330
- digest: "sha256:88fd469bd1018d2b4dd7c1cce8cb6f13dee64599a9054237f39f245d97e446d4",
2371
+ bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
2372
+ digest: "sha256:62fb136a6376e729f10efa210b6dba6607923b2502597e555bd055d72ee307dd",
2331
2373
  digestAlgorithm: "rfc8785-sha256",
2332
- executionPlanDigest: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669",
2374
+ executionPlanDigest: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f",
2333
2375
  executorCapture: {
2334
2376
  byteLength: 477,
2335
2377
  locator: {
2336
2378
  bucket: "candidate-test-artifacts",
2337
- key: "executor-capture/9923cd0fda5e697e70ab83a99dac67d991b9b0ac9c1702bb99990f0d9a5cd1d7",
2379
+ key: "executor-capture/c8e3a1667966134d3f7b24b4df19a5f5286814522f7884f0a76f7cfd3d4832a2",
2338
2380
  kind: "s3"
2339
2381
  },
2340
- sha256: "sha256:9923cd0fda5e697e70ab83a99dac67d991b9b0ac9c1702bb99990f0d9a5cd1d7"
2382
+ sha256: "sha256:c8e3a1667966134d3f7b24b4df19a5f5286814522f7884f0a76f7cfd3d4832a2"
2341
2383
  },
2342
2384
  kind: "agent-candidate-run",
2343
- materializationReceiptDigest: "sha256:58b85d501d6559779de74275f638c76ef2a0c7decff907081b8e20d5df37d1c6",
2385
+ materializationReceiptDigest: "sha256:b3718d6b33e7316d37af34e81e93a6521b0e9914bdec820d56e14fd7008f3e05",
2344
2386
  memory: {
2345
2387
  mode: "disabled"
2346
2388
  },
@@ -2349,17 +2391,17 @@ var agent_improvement_proposal_default = {
2349
2391
  byteLength: 615,
2350
2392
  locator: {
2351
2393
  bucket: "candidate-test-artifacts",
2352
- key: "model-settlement/592d4b35fa6b118a9a20eea887eed44e997bede7b155ca83607c0b11d83bad77",
2394
+ key: "model-settlement/397df4f1827292bad160efdfeb9f92748df604396b285b20f527299b073a8988",
2353
2395
  kind: "s3"
2354
2396
  },
2355
- sha256: "sha256:592d4b35fa6b118a9a20eea887eed44e997bede7b155ca83607c0b11d83bad77"
2397
+ sha256: "sha256:397df4f1827292bad160efdfeb9f92748df604396b285b20f527299b073a8988"
2356
2398
  },
2357
- digest: "sha256:592d4b35fa6b118a9a20eea887eed44e997bede7b155ca83607c0b11d83bad77",
2399
+ digest: "sha256:397df4f1827292bad160efdfeb9f92748df604396b285b20f527299b073a8988",
2358
2400
  kind: "agent-candidate-model-settlement",
2359
2401
  material: {
2360
2402
  calls: [],
2361
2403
  closed: true,
2362
- executionPlanDigest: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669",
2404
+ executionPlanDigest: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f",
2363
2405
  grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
2364
2406
  kind: "agent-candidate-model-settlement-material",
2365
2407
  preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
@@ -2380,21 +2422,21 @@ var agent_improvement_proposal_default = {
2380
2422
  }
2381
2423
  }
2382
2424
  },
2383
- runCellDigest: "sha256:b725cf36cf0b5b2ecf09cd8f09e4a463c98ba909b4622220ce74754c12a51a3a",
2425
+ runCellDigest: "sha256:ea5cab9dff49326dfe856aab19514d2bc5bc0fab2b4b685c4fea356801dbd1c3",
2384
2426
  taskOutcome: {
2385
2427
  artifact: {
2386
2428
  byteLength: 478,
2387
2429
  locator: {
2388
2430
  bucket: "candidate-test-artifacts",
2389
- key: "task-outcome/4dcf33ca1333772d635d34932d4348fb55d7dd4146f734f97bd1b296ad059f0f",
2431
+ key: "task-outcome/61d53d0789c46c98b43acdc7177b1b6102f48aa2d6b3b2ff0ec5ee4b287c8d92",
2390
2432
  kind: "s3"
2391
2433
  },
2392
- sha256: "sha256:4dcf33ca1333772d635d34932d4348fb55d7dd4146f734f97bd1b296ad059f0f"
2434
+ sha256: "sha256:61d53d0789c46c98b43acdc7177b1b6102f48aa2d6b3b2ff0ec5ee4b287c8d92"
2393
2435
  },
2394
- digest: "sha256:4dcf33ca1333772d635d34932d4348fb55d7dd4146f734f97bd1b296ad059f0f",
2436
+ digest: "sha256:61d53d0789c46c98b43acdc7177b1b6102f48aa2d6b3b2ff0ec5ee4b287c8d92",
2395
2437
  kind: "agent-candidate-task-outcome",
2396
2438
  material: {
2397
- executionPlanDigest: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669",
2439
+ executionPlanDigest: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f",
2398
2440
  kind: "agent-candidate-task-outcome-material",
2399
2441
  outcome: {
2400
2442
  artifact: {
@@ -2428,10 +2470,10 @@ var agent_improvement_proposal_default = {
2428
2470
  byteLength: 750,
2429
2471
  locator: {
2430
2472
  bucket: "candidate-test-artifacts",
2431
- key: "trace/3d68a2563c8e0fad81d134e751fe8a6d8a715ba73228c94c7cd0a2fb729186d4",
2473
+ key: "trace/59f819d9564d5e61e59e52545f9b269083f0a0b57a92a5e8f93e566da560ef17",
2432
2474
  kind: "s3"
2433
2475
  },
2434
- sha256: "sha256:3d68a2563c8e0fad81d134e751fe8a6d8a715ba73228c94c7cd0a2fb729186d4"
2476
+ sha256: "sha256:59f819d9564d5e61e59e52545f9b269083f0a0b57a92a5e8f93e566da560ef17"
2435
2477
  },
2436
2478
  eventCount: 1,
2437
2479
  modelCallCount: 0
@@ -2442,7 +2484,7 @@ var agent_improvement_proposal_default = {
2442
2484
  ],
2443
2485
  metadata: {
2444
2486
  fixture: "agent-improvement-proposal",
2445
- runtimeVersion: "0.101.1"
2487
+ runtimeVersion: "0.102.0"
2446
2488
  },
2447
2489
  objectives: [
2448
2490
  {
@@ -2550,11 +2592,11 @@ var agent_improvement_proposal_default = {
2550
2592
  sufficient: true
2551
2593
  },
2552
2594
  provenance: {
2553
- baselineContentHash: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
2554
- candidateContentHash: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
2595
+ baselineContentHash: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
2596
+ candidateContentHash: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
2555
2597
  kind: "agent-eval-loop",
2556
- recordDigest: "sha256:6ee245f7c24f0a28c8f169bc2fef2d85db9dec9e66eff078798993be20885bb3",
2557
- runId: "agent-runtime-0.101.1-proposal-fixture",
2598
+ recordDigest: "sha256:6ca133e58b214ee1b6712edbb59abba570d24c675279e327f35831f8445eafbc",
2599
+ runId: "agent-runtime-0.102.0-proposal-fixture",
2558
2600
  schema: "agent-candidate-experiment"
2559
2601
  }
2560
2602
  },
@@ -2580,7 +2622,7 @@ var agent_improvement_proposal_default = {
2580
2622
  ],
2581
2623
  kind: "agent-improvement-proposal",
2582
2624
  proposedAt: "2026-07-10T01:00:00.000Z",
2583
- runId: "agent-runtime-0.101.1-proposal-fixture"
2625
+ runId: "agent-runtime-0.102.0-proposal-fixture"
2584
2626
  };
2585
2627
 
2586
2628
  // src/testing/index.ts