@tangle-network/agent-runtime 0.101.1 → 0.102.1
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/agent.d.ts +1 -1
- package/dist/agent.js +5 -3
- package/dist/agent.js.map +1 -1
- package/dist/analyst-loop.d.ts +1 -1
- package/dist/candidate-execution/index.d.ts +13 -2
- package/dist/candidate-execution/index.js +8 -3
- package/dist/chunk-377GOJHJ.js +578 -0
- package/dist/chunk-377GOJHJ.js.map +1 -0
- package/dist/{chunk-DI677IPX.js → chunk-3DW5DEKQ.js} +3 -3
- package/dist/{chunk-KVJQV342.js → chunk-6MR4IJRW.js} +25 -1777
- package/dist/chunk-6MR4IJRW.js.map +1 -0
- package/dist/{chunk-RJPQLUDA.js → chunk-7FJJUC73.js} +336 -43
- package/dist/chunk-7FJJUC73.js.map +1 -0
- package/dist/{chunk-TA4RBJLE.js → chunk-CI7WS6S2.js} +5 -5
- package/dist/{chunk-U4PRAATQ.js → chunk-CK76OZPM.js} +3 -3
- package/dist/{chunk-KSBUSEUA.js → chunk-KJ2Q4T7F.js} +2 -2
- package/dist/{chunk-MAONWP4R.js → chunk-KPHTCHQ4.js} +611 -1419
- package/dist/chunk-KPHTCHQ4.js.map +1 -0
- package/dist/{chunk-BXZ7GPL4.js → chunk-KSM6GFHP.js} +2 -2
- package/dist/chunk-L5DST3QC.js +351 -0
- package/dist/chunk-L5DST3QC.js.map +1 -0
- package/dist/{chunk-HGSHPVJ6.js → chunk-LJLG734E.js} +200 -441
- package/dist/chunk-LJLG734E.js.map +1 -0
- package/dist/chunk-ROILMKDL.js +1338 -0
- package/dist/chunk-ROILMKDL.js.map +1 -0
- package/dist/{chunk-N2CEE5Q3.js → chunk-RTB3TC73.js} +3 -3
- package/dist/chunk-SQ3ZJH3Y.js +3082 -0
- package/dist/chunk-SQ3ZJH3Y.js.map +1 -0
- package/dist/chunk-UPWGXKXB.js +254 -0
- package/dist/chunk-UPWGXKXB.js.map +1 -0
- package/dist/{completion-gate-C80jiRfN.d.ts → completion-gate-C6dhVN-N.d.ts} +2 -2
- package/dist/{coordination-BFE3Den7.d.ts → coordination-D9l_YmwW.d.ts} +6 -6
- package/dist/environment-provider.d.ts +2 -2
- package/dist/{improve-g75IE2Cx.d.ts → improve-B40dRu0X.d.ts} +47 -19
- package/dist/index.d.ts +331 -23
- package/dist/index.js +544 -136
- package/dist/index.js.map +1 -1
- package/dist/intelligence.d.ts +63 -62
- package/dist/intelligence.js +62 -471
- package/dist/intelligence.js.map +1 -1
- package/dist/knowledge.d.ts +8 -8
- package/dist/knowledge.js +9 -7
- package/dist/{local-harness-ZqCx51u7.d.ts → local-harness-CtK9dSny.d.ts} +14 -2
- package/dist/{loop-runner-bin-Cn1N2rRo.d.ts → loop-runner-bin-PnWslIw4.d.ts} +2 -2
- package/dist/loop-runner-bin.d.ts +6 -6
- package/dist/loop-runner-bin.js +6 -4
- package/dist/loops.d.ts +231 -460
- package/dist/loops.js +58 -37
- package/dist/mcp/bin.js +2 -2
- package/dist/mcp/index.d.ts +184 -12
- package/dist/mcp/index.js +31 -9
- package/dist/mcp/index.js.map +1 -1
- package/dist/mcp/memory-bin.d.ts +1 -0
- package/dist/mcp/memory-bin.js +22 -0
- package/dist/mcp/memory-bin.js.map +1 -0
- package/dist/profiles.d.ts +3 -3
- package/dist/structural-rollout-D7xik9XR.d.ts +446 -0
- package/dist/{substrate-DO2GHNg2.d.ts → substrate-Dyiqmd3o.d.ts} +1 -1
- package/dist/{supervise-BLPI50-w.d.ts → supervise-BQdNAXtK.d.ts} +4 -4
- package/dist/testing.js +255 -211
- package/dist/testing.js.map +1 -1
- package/dist/{types-B3vAW0Oq.d.ts → types-CLat4bT9.d.ts} +1 -1
- package/dist/{types-CmnA2iL3.d.ts → types-D870JlH0.d.ts} +2 -2
- package/dist/{worktree-fanout-DCA3G4bO.d.ts → worktree-fanout-DsIR4d6w.d.ts} +234 -234
- package/package.json +6 -5
- package/dist/chunk-HGSHPVJ6.js.map +0 -1
- package/dist/chunk-IKGCKPDX.js +0 -1115
- package/dist/chunk-IKGCKPDX.js.map +0 -1
- package/dist/chunk-KVJQV342.js.map +0 -1
- package/dist/chunk-MAONWP4R.js.map +0 -1
- package/dist/chunk-RJPQLUDA.js.map +0 -1
- package/dist/{chunk-DI677IPX.js.map → chunk-3DW5DEKQ.js.map} +0 -0
- package/dist/{chunk-TA4RBJLE.js.map → chunk-CI7WS6S2.js.map} +0 -0
- package/dist/{chunk-U4PRAATQ.js.map → chunk-CK76OZPM.js.map} +0 -0
- package/dist/{chunk-KSBUSEUA.js.map → chunk-KJ2Q4T7F.js.map} +0 -0
- package/dist/{chunk-BXZ7GPL4.js.map → chunk-KSM6GFHP.js.map} +0 -0
- package/dist/{chunk-N2CEE5Q3.js.map → chunk-RTB3TC73.js.map} +0 -0
- package/dist/{sanitize-BTSsdBXw.d.ts → sanitize-DEbPNtyI.d.ts} +58 -58
package/dist/testing.js
CHANGED
|
@@ -1,8 +1,10 @@
|
|
|
1
1
|
import {
|
|
2
2
|
verifyAgentImprovementProposal
|
|
3
|
-
} from "./chunk-
|
|
4
|
-
import "./chunk-
|
|
5
|
-
import "./chunk-
|
|
3
|
+
} from "./chunk-7FJJUC73.js";
|
|
4
|
+
import "./chunk-LJLG734E.js";
|
|
5
|
+
import "./chunk-ROILMKDL.js";
|
|
6
|
+
import "./chunk-UPWGXKXB.js";
|
|
7
|
+
import "./chunk-SQ3ZJH3Y.js";
|
|
6
8
|
import "./chunk-IMSNJSXH.js";
|
|
7
9
|
import "./chunk-3MDZX7YU.js";
|
|
8
10
|
import "./chunk-FD2MBMOH.js";
|
|
@@ -12,7 +14,7 @@ import "./chunk-YEJR7IXO.js";
|
|
|
12
14
|
// src/testing/fixtures/agent-improvement-proposal.json
|
|
13
15
|
var agent_improvement_proposal_default = {
|
|
14
16
|
changedSurfaces: ["prompt"],
|
|
15
|
-
digest: "sha256:
|
|
17
|
+
digest: "sha256:576dddc41e8a65834faa1f0dc08d7a76da9f387f141780de175853125f7b8755",
|
|
16
18
|
evaluation: {
|
|
17
19
|
decision: {
|
|
18
20
|
contributingChecks: [
|
|
@@ -59,13 +61,19 @@ var agent_improvement_proposal_default = {
|
|
|
59
61
|
code: {
|
|
60
62
|
kind: "disabled"
|
|
61
63
|
},
|
|
62
|
-
digest: "sha256:
|
|
64
|
+
digest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
63
65
|
digestAlgorithm: "rfc8785-sha256",
|
|
64
66
|
execution: {
|
|
65
67
|
cwd: {
|
|
66
68
|
path: ".",
|
|
67
69
|
workspace: "task"
|
|
68
70
|
},
|
|
71
|
+
env: {
|
|
72
|
+
PATH: {
|
|
73
|
+
kind: "public",
|
|
74
|
+
value: "/usr/local/bin:/usr/bin:/bin"
|
|
75
|
+
}
|
|
76
|
+
},
|
|
69
77
|
environment: {
|
|
70
78
|
kind: "evaluator-task-container"
|
|
71
79
|
},
|
|
@@ -203,13 +211,19 @@ var agent_improvement_proposal_default = {
|
|
|
203
211
|
code: {
|
|
204
212
|
kind: "disabled"
|
|
205
213
|
},
|
|
206
|
-
digest: "sha256:
|
|
214
|
+
digest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
207
215
|
digestAlgorithm: "rfc8785-sha256",
|
|
208
216
|
execution: {
|
|
209
217
|
cwd: {
|
|
210
218
|
path: ".",
|
|
211
219
|
workspace: "task"
|
|
212
220
|
},
|
|
221
|
+
env: {
|
|
222
|
+
PATH: {
|
|
223
|
+
kind: "public",
|
|
224
|
+
value: "/usr/local/bin:/usr/bin:/bin"
|
|
225
|
+
}
|
|
226
|
+
},
|
|
213
227
|
environment: {
|
|
214
228
|
kind: "evaluator-task-container"
|
|
215
229
|
},
|
|
@@ -251,7 +265,7 @@ var agent_improvement_proposal_default = {
|
|
|
251
265
|
candidateLineage: {
|
|
252
266
|
source: "human"
|
|
253
267
|
},
|
|
254
|
-
digest: "sha256:
|
|
268
|
+
digest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
|
|
255
269
|
digestAlgorithm: "rfc8785-sha256",
|
|
256
270
|
kind: "agent-candidate-experiment",
|
|
257
271
|
policy: {
|
|
@@ -269,7 +283,7 @@ var agent_improvement_proposal_default = {
|
|
|
269
283
|
measurements: [
|
|
270
284
|
{
|
|
271
285
|
baseline: {
|
|
272
|
-
digest: "sha256:
|
|
286
|
+
digest: "sha256:6bf8492d4fb6cb795715f861ad1150ce8194aaf6075ce898e411fdbaf4e6f534",
|
|
273
287
|
kind: "agent-candidate-execution-evidence",
|
|
274
288
|
materializationReceipt: {
|
|
275
289
|
benchmark: {
|
|
@@ -292,7 +306,7 @@ var agent_improvement_proposal_default = {
|
|
|
292
306
|
}
|
|
293
307
|
}
|
|
294
308
|
},
|
|
295
|
-
bundleDigest: "sha256:
|
|
309
|
+
bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
296
310
|
codeKind: "disabled",
|
|
297
311
|
container: {
|
|
298
312
|
image: "ghcr.io/example/task",
|
|
@@ -304,16 +318,16 @@ var agent_improvement_proposal_default = {
|
|
|
304
318
|
},
|
|
305
319
|
source: "evaluator-task-container"
|
|
306
320
|
},
|
|
307
|
-
digest: "sha256:
|
|
321
|
+
digest: "sha256:50573a8655c2f83044a105990573b1a5ed84d3a8d9241e01cda565eead22b7cc",
|
|
308
322
|
digestAlgorithm: "rfc8785-sha256",
|
|
309
323
|
executionPlan: {
|
|
310
324
|
artifact: {
|
|
311
|
-
byteLength:
|
|
312
|
-
content: "
|
|
325
|
+
byteLength: 2030,
|
|
326
|
+
content: "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",
|
|
313
327
|
encoding: "base64",
|
|
314
|
-
sha256: "sha256:
|
|
328
|
+
sha256: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf"
|
|
315
329
|
},
|
|
316
|
-
digest: "sha256:
|
|
330
|
+
digest: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf",
|
|
317
331
|
kind: "agent-candidate-execution-plan",
|
|
318
332
|
material: {
|
|
319
333
|
codeKind: "disabled",
|
|
@@ -340,7 +354,12 @@ var agent_improvement_proposal_default = {
|
|
|
340
354
|
path: ".",
|
|
341
355
|
workspace: "task"
|
|
342
356
|
},
|
|
343
|
-
env: {
|
|
357
|
+
env: {
|
|
358
|
+
PATH: {
|
|
359
|
+
kind: "public",
|
|
360
|
+
value: "/usr/local/bin:/usr/bin:/bin"
|
|
361
|
+
}
|
|
362
|
+
},
|
|
344
363
|
executable: "codex"
|
|
345
364
|
},
|
|
346
365
|
limits: {
|
|
@@ -389,9 +408,9 @@ var agent_improvement_proposal_default = {
|
|
|
389
408
|
runCell: {
|
|
390
409
|
arm: "baseline",
|
|
391
410
|
attempt: 1,
|
|
392
|
-
bundleDigest: "sha256:
|
|
393
|
-
digest: "sha256:
|
|
394
|
-
experimentDigest: "sha256:
|
|
411
|
+
bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
412
|
+
digest: "sha256:5246bcb23929d3ef84c78c5185390aab5e2309f1267d38e0d1c0ddc18232b6d4",
|
|
413
|
+
experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
|
|
395
414
|
kind: "agent-candidate-run-cell",
|
|
396
415
|
repetition: 0,
|
|
397
416
|
seed: 101,
|
|
@@ -456,12 +475,12 @@ var agent_improvement_proposal_default = {
|
|
|
456
475
|
byteLength: 1122,
|
|
457
476
|
locator: {
|
|
458
477
|
bucket: "candidate-test-artifacts",
|
|
459
|
-
key: "benchmark-result/
|
|
478
|
+
key: "benchmark-result/e9a709a18c6a51d8f81080c79f856162eb740e7664eba2906bc5888752eb27a6",
|
|
460
479
|
kind: "s3"
|
|
461
480
|
},
|
|
462
|
-
sha256: "sha256:
|
|
481
|
+
sha256: "sha256:e9a709a18c6a51d8f81080c79f856162eb740e7664eba2906bc5888752eb27a6"
|
|
463
482
|
},
|
|
464
|
-
digest: "sha256:
|
|
483
|
+
digest: "sha256:e9a709a18c6a51d8f81080c79f856162eb740e7664eba2906bc5888752eb27a6",
|
|
465
484
|
kind: "agent-candidate-benchmark-result",
|
|
466
485
|
material: {
|
|
467
486
|
dimensions: [
|
|
@@ -479,7 +498,7 @@ var agent_improvement_proposal_default = {
|
|
|
479
498
|
},
|
|
480
499
|
sha256: "sha256:628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b"
|
|
481
500
|
},
|
|
482
|
-
executionPlanDigest: "sha256:
|
|
501
|
+
executionPlanDigest: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf",
|
|
483
502
|
grader: {
|
|
484
503
|
artifact: {
|
|
485
504
|
byteLength: 25,
|
|
@@ -512,24 +531,24 @@ var agent_improvement_proposal_default = {
|
|
|
512
531
|
kind: "agent-candidate-benchmark-result-material",
|
|
513
532
|
passed: false,
|
|
514
533
|
score: 0,
|
|
515
|
-
taskOutcomeDigest: "sha256:
|
|
534
|
+
taskOutcomeDigest: "sha256:96d90a54ff0cdc7ef2dc49e80fad20175c10a761eb6abd3bf127da35340994ed"
|
|
516
535
|
}
|
|
517
536
|
},
|
|
518
|
-
bundleDigest: "sha256:
|
|
519
|
-
digest: "sha256:
|
|
537
|
+
bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
538
|
+
digest: "sha256:792a1fc3d525e029e74f9fe88940277b6d7c162959b4ecc943b25cbaffe3d86f",
|
|
520
539
|
digestAlgorithm: "rfc8785-sha256",
|
|
521
|
-
executionPlanDigest: "sha256:
|
|
540
|
+
executionPlanDigest: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf",
|
|
522
541
|
executorCapture: {
|
|
523
542
|
byteLength: 477,
|
|
524
543
|
locator: {
|
|
525
544
|
bucket: "candidate-test-artifacts",
|
|
526
|
-
key: "executor-capture/
|
|
545
|
+
key: "executor-capture/64bb8b780db79c2a5bf89c46cefb755060f18271084748143c194d5716c5bedd",
|
|
527
546
|
kind: "s3"
|
|
528
547
|
},
|
|
529
|
-
sha256: "sha256:
|
|
548
|
+
sha256: "sha256:64bb8b780db79c2a5bf89c46cefb755060f18271084748143c194d5716c5bedd"
|
|
530
549
|
},
|
|
531
550
|
kind: "agent-candidate-run",
|
|
532
|
-
materializationReceiptDigest: "sha256:
|
|
551
|
+
materializationReceiptDigest: "sha256:50573a8655c2f83044a105990573b1a5ed84d3a8d9241e01cda565eead22b7cc",
|
|
533
552
|
memory: {
|
|
534
553
|
mode: "disabled"
|
|
535
554
|
},
|
|
@@ -538,17 +557,17 @@ var agent_improvement_proposal_default = {
|
|
|
538
557
|
byteLength: 615,
|
|
539
558
|
locator: {
|
|
540
559
|
bucket: "candidate-test-artifacts",
|
|
541
|
-
key: "model-settlement/
|
|
560
|
+
key: "model-settlement/625a1690d64a8ccee6b2d616f7ee7a9648edb1ddf9ea58711bef5a4a306cdba0",
|
|
542
561
|
kind: "s3"
|
|
543
562
|
},
|
|
544
|
-
sha256: "sha256:
|
|
563
|
+
sha256: "sha256:625a1690d64a8ccee6b2d616f7ee7a9648edb1ddf9ea58711bef5a4a306cdba0"
|
|
545
564
|
},
|
|
546
|
-
digest: "sha256:
|
|
565
|
+
digest: "sha256:625a1690d64a8ccee6b2d616f7ee7a9648edb1ddf9ea58711bef5a4a306cdba0",
|
|
547
566
|
kind: "agent-candidate-model-settlement",
|
|
548
567
|
material: {
|
|
549
568
|
calls: [],
|
|
550
569
|
closed: true,
|
|
551
|
-
executionPlanDigest: "sha256:
|
|
570
|
+
executionPlanDigest: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf",
|
|
552
571
|
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
553
572
|
kind: "agent-candidate-model-settlement-material",
|
|
554
573
|
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
@@ -569,21 +588,21 @@ var agent_improvement_proposal_default = {
|
|
|
569
588
|
}
|
|
570
589
|
}
|
|
571
590
|
},
|
|
572
|
-
runCellDigest: "sha256:
|
|
591
|
+
runCellDigest: "sha256:5246bcb23929d3ef84c78c5185390aab5e2309f1267d38e0d1c0ddc18232b6d4",
|
|
573
592
|
taskOutcome: {
|
|
574
593
|
artifact: {
|
|
575
594
|
byteLength: 478,
|
|
576
595
|
locator: {
|
|
577
596
|
bucket: "candidate-test-artifacts",
|
|
578
|
-
key: "task-outcome/
|
|
597
|
+
key: "task-outcome/96d90a54ff0cdc7ef2dc49e80fad20175c10a761eb6abd3bf127da35340994ed",
|
|
579
598
|
kind: "s3"
|
|
580
599
|
},
|
|
581
|
-
sha256: "sha256:
|
|
600
|
+
sha256: "sha256:96d90a54ff0cdc7ef2dc49e80fad20175c10a761eb6abd3bf127da35340994ed"
|
|
582
601
|
},
|
|
583
|
-
digest: "sha256:
|
|
602
|
+
digest: "sha256:96d90a54ff0cdc7ef2dc49e80fad20175c10a761eb6abd3bf127da35340994ed",
|
|
584
603
|
kind: "agent-candidate-task-outcome",
|
|
585
604
|
material: {
|
|
586
|
-
executionPlanDigest: "sha256:
|
|
605
|
+
executionPlanDigest: "sha256:205204302122b2c90373cf000406d8841c6bf8cd99f621637fe7c6824e243acf",
|
|
587
606
|
kind: "agent-candidate-task-outcome-material",
|
|
588
607
|
outcome: {
|
|
589
608
|
artifact: {
|
|
@@ -617,10 +636,10 @@ var agent_improvement_proposal_default = {
|
|
|
617
636
|
byteLength: 748,
|
|
618
637
|
locator: {
|
|
619
638
|
bucket: "candidate-test-artifacts",
|
|
620
|
-
key: "trace/
|
|
639
|
+
key: "trace/2fce8b3ba11deb5251d3b7b9de66d1b4788c18a2b56aafe77ddd57423db41593",
|
|
621
640
|
kind: "s3"
|
|
622
641
|
},
|
|
623
|
-
sha256: "sha256:
|
|
642
|
+
sha256: "sha256:2fce8b3ba11deb5251d3b7b9de66d1b4788c18a2b56aafe77ddd57423db41593"
|
|
624
643
|
},
|
|
625
644
|
eventCount: 1,
|
|
626
645
|
modelCallCount: 0
|
|
@@ -628,7 +647,7 @@ var agent_improvement_proposal_default = {
|
|
|
628
647
|
}
|
|
629
648
|
},
|
|
630
649
|
candidate: {
|
|
631
|
-
digest: "sha256:
|
|
650
|
+
digest: "sha256:d99b9e877621de7c5fe20850fcdcf6b88119e46b0505dc4a7bf867201b0afafe",
|
|
632
651
|
kind: "agent-candidate-execution-evidence",
|
|
633
652
|
materializationReceipt: {
|
|
634
653
|
benchmark: {
|
|
@@ -651,7 +670,7 @@ var agent_improvement_proposal_default = {
|
|
|
651
670
|
}
|
|
652
671
|
}
|
|
653
672
|
},
|
|
654
|
-
bundleDigest: "sha256:
|
|
673
|
+
bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
655
674
|
codeKind: "disabled",
|
|
656
675
|
container: {
|
|
657
676
|
image: "ghcr.io/example/task",
|
|
@@ -663,16 +682,16 @@ var agent_improvement_proposal_default = {
|
|
|
663
682
|
},
|
|
664
683
|
source: "evaluator-task-container"
|
|
665
684
|
},
|
|
666
|
-
digest: "sha256:
|
|
685
|
+
digest: "sha256:dc45d1b3f6fb88d4b0b709f6a2ff63164df737dddd582a8749ff7d91368662d9",
|
|
667
686
|
digestAlgorithm: "rfc8785-sha256",
|
|
668
687
|
executionPlan: {
|
|
669
688
|
artifact: {
|
|
670
|
-
byteLength:
|
|
671
|
-
content: "
|
|
689
|
+
byteLength: 2032,
|
|
690
|
+
content: "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",
|
|
672
691
|
encoding: "base64",
|
|
673
|
-
sha256: "sha256:
|
|
692
|
+
sha256: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6"
|
|
674
693
|
},
|
|
675
|
-
digest: "sha256:
|
|
694
|
+
digest: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6",
|
|
676
695
|
kind: "agent-candidate-execution-plan",
|
|
677
696
|
material: {
|
|
678
697
|
codeKind: "disabled",
|
|
@@ -699,7 +718,12 @@ var agent_improvement_proposal_default = {
|
|
|
699
718
|
path: ".",
|
|
700
719
|
workspace: "task"
|
|
701
720
|
},
|
|
702
|
-
env: {
|
|
721
|
+
env: {
|
|
722
|
+
PATH: {
|
|
723
|
+
kind: "public",
|
|
724
|
+
value: "/usr/local/bin:/usr/bin:/bin"
|
|
725
|
+
}
|
|
726
|
+
},
|
|
703
727
|
executable: "codex"
|
|
704
728
|
},
|
|
705
729
|
limits: {
|
|
@@ -748,9 +772,9 @@ var agent_improvement_proposal_default = {
|
|
|
748
772
|
runCell: {
|
|
749
773
|
arm: "candidate",
|
|
750
774
|
attempt: 1,
|
|
751
|
-
bundleDigest: "sha256:
|
|
752
|
-
digest: "sha256:
|
|
753
|
-
experimentDigest: "sha256:
|
|
775
|
+
bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
776
|
+
digest: "sha256:e8faaad9b6ae2779d56d4f56d98f3197ed3d375298084ac08410c54632fb8b61",
|
|
777
|
+
experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
|
|
754
778
|
kind: "agent-candidate-run-cell",
|
|
755
779
|
repetition: 0,
|
|
756
780
|
seed: 101,
|
|
@@ -819,12 +843,12 @@ var agent_improvement_proposal_default = {
|
|
|
819
843
|
byteLength: 1121,
|
|
820
844
|
locator: {
|
|
821
845
|
bucket: "candidate-test-artifacts",
|
|
822
|
-
key: "benchmark-result/
|
|
846
|
+
key: "benchmark-result/78dab25681b91e59579ac46cc8b3d2bfb58d9f57430eb2625e9f2cd534d2b15a",
|
|
823
847
|
kind: "s3"
|
|
824
848
|
},
|
|
825
|
-
sha256: "sha256:
|
|
849
|
+
sha256: "sha256:78dab25681b91e59579ac46cc8b3d2bfb58d9f57430eb2625e9f2cd534d2b15a"
|
|
826
850
|
},
|
|
827
|
-
digest: "sha256:
|
|
851
|
+
digest: "sha256:78dab25681b91e59579ac46cc8b3d2bfb58d9f57430eb2625e9f2cd534d2b15a",
|
|
828
852
|
kind: "agent-candidate-benchmark-result",
|
|
829
853
|
material: {
|
|
830
854
|
dimensions: [
|
|
@@ -842,7 +866,7 @@ var agent_improvement_proposal_default = {
|
|
|
842
866
|
},
|
|
843
867
|
sha256: "sha256:9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d"
|
|
844
868
|
},
|
|
845
|
-
executionPlanDigest: "sha256:
|
|
869
|
+
executionPlanDigest: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6",
|
|
846
870
|
grader: {
|
|
847
871
|
artifact: {
|
|
848
872
|
byteLength: 25,
|
|
@@ -875,24 +899,24 @@ var agent_improvement_proposal_default = {
|
|
|
875
899
|
kind: "agent-candidate-benchmark-result-material",
|
|
876
900
|
passed: true,
|
|
877
901
|
score: 1,
|
|
878
|
-
taskOutcomeDigest: "sha256:
|
|
902
|
+
taskOutcomeDigest: "sha256:1674e3e6fc00ca4e74f44dc8247f3f6fd334c62f25b24eda25e37ca91d5fb016"
|
|
879
903
|
}
|
|
880
904
|
},
|
|
881
|
-
bundleDigest: "sha256:
|
|
882
|
-
digest: "sha256:
|
|
905
|
+
bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
906
|
+
digest: "sha256:3e003fb6cf3bde16a59f28901d29c752595794b000b79268b4b7be853adb4551",
|
|
883
907
|
digestAlgorithm: "rfc8785-sha256",
|
|
884
|
-
executionPlanDigest: "sha256:
|
|
908
|
+
executionPlanDigest: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6",
|
|
885
909
|
executorCapture: {
|
|
886
910
|
byteLength: 477,
|
|
887
911
|
locator: {
|
|
888
912
|
bucket: "candidate-test-artifacts",
|
|
889
|
-
key: "executor-capture/
|
|
913
|
+
key: "executor-capture/7b8a015c52a055cc2befaf553c1fe14e2f4daeafd520f085be2f5e29682baff3",
|
|
890
914
|
kind: "s3"
|
|
891
915
|
},
|
|
892
|
-
sha256: "sha256:
|
|
916
|
+
sha256: "sha256:7b8a015c52a055cc2befaf553c1fe14e2f4daeafd520f085be2f5e29682baff3"
|
|
893
917
|
},
|
|
894
918
|
kind: "agent-candidate-run",
|
|
895
|
-
materializationReceiptDigest: "sha256:
|
|
919
|
+
materializationReceiptDigest: "sha256:dc45d1b3f6fb88d4b0b709f6a2ff63164df737dddd582a8749ff7d91368662d9",
|
|
896
920
|
memory: {
|
|
897
921
|
mode: "disabled"
|
|
898
922
|
},
|
|
@@ -901,17 +925,17 @@ var agent_improvement_proposal_default = {
|
|
|
901
925
|
byteLength: 615,
|
|
902
926
|
locator: {
|
|
903
927
|
bucket: "candidate-test-artifacts",
|
|
904
|
-
key: "model-settlement/
|
|
928
|
+
key: "model-settlement/6436cd10c36b64083ac00b0925efc03ef8d5e873f64cc2be5bdce4533366c8c4",
|
|
905
929
|
kind: "s3"
|
|
906
930
|
},
|
|
907
|
-
sha256: "sha256:
|
|
931
|
+
sha256: "sha256:6436cd10c36b64083ac00b0925efc03ef8d5e873f64cc2be5bdce4533366c8c4"
|
|
908
932
|
},
|
|
909
|
-
digest: "sha256:
|
|
933
|
+
digest: "sha256:6436cd10c36b64083ac00b0925efc03ef8d5e873f64cc2be5bdce4533366c8c4",
|
|
910
934
|
kind: "agent-candidate-model-settlement",
|
|
911
935
|
material: {
|
|
912
936
|
calls: [],
|
|
913
937
|
closed: true,
|
|
914
|
-
executionPlanDigest: "sha256:
|
|
938
|
+
executionPlanDigest: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6",
|
|
915
939
|
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
916
940
|
kind: "agent-candidate-model-settlement-material",
|
|
917
941
|
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
@@ -932,21 +956,21 @@ var agent_improvement_proposal_default = {
|
|
|
932
956
|
}
|
|
933
957
|
}
|
|
934
958
|
},
|
|
935
|
-
runCellDigest: "sha256:
|
|
959
|
+
runCellDigest: "sha256:e8faaad9b6ae2779d56d4f56d98f3197ed3d375298084ac08410c54632fb8b61",
|
|
936
960
|
taskOutcome: {
|
|
937
961
|
artifact: {
|
|
938
962
|
byteLength: 478,
|
|
939
963
|
locator: {
|
|
940
964
|
bucket: "candidate-test-artifacts",
|
|
941
|
-
key: "task-outcome/
|
|
965
|
+
key: "task-outcome/1674e3e6fc00ca4e74f44dc8247f3f6fd334c62f25b24eda25e37ca91d5fb016",
|
|
942
966
|
kind: "s3"
|
|
943
967
|
},
|
|
944
|
-
sha256: "sha256:
|
|
968
|
+
sha256: "sha256:1674e3e6fc00ca4e74f44dc8247f3f6fd334c62f25b24eda25e37ca91d5fb016"
|
|
945
969
|
},
|
|
946
|
-
digest: "sha256:
|
|
970
|
+
digest: "sha256:1674e3e6fc00ca4e74f44dc8247f3f6fd334c62f25b24eda25e37ca91d5fb016",
|
|
947
971
|
kind: "agent-candidate-task-outcome",
|
|
948
972
|
material: {
|
|
949
|
-
executionPlanDigest: "sha256:
|
|
973
|
+
executionPlanDigest: "sha256:9ee298c2aa3a2b814f4ce41bf8698e20aab372d28922dca97a5c829516ea44f6",
|
|
950
974
|
kind: "agent-candidate-task-outcome-material",
|
|
951
975
|
outcome: {
|
|
952
976
|
artifact: {
|
|
@@ -980,10 +1004,10 @@ var agent_improvement_proposal_default = {
|
|
|
980
1004
|
byteLength: 750,
|
|
981
1005
|
locator: {
|
|
982
1006
|
bucket: "candidate-test-artifacts",
|
|
983
|
-
key: "trace/
|
|
1007
|
+
key: "trace/f40b48a52282eaf104755ceb8dd6d713f6cc93fda296767f2656ef66ac4a55ff",
|
|
984
1008
|
kind: "s3"
|
|
985
1009
|
},
|
|
986
|
-
sha256: "sha256:
|
|
1010
|
+
sha256: "sha256:f40b48a52282eaf104755ceb8dd6d713f6cc93fda296767f2656ef66ac4a55ff"
|
|
987
1011
|
},
|
|
988
1012
|
eventCount: 1,
|
|
989
1013
|
modelCallCount: 0
|
|
@@ -993,7 +1017,7 @@ var agent_improvement_proposal_default = {
|
|
|
993
1017
|
},
|
|
994
1018
|
{
|
|
995
1019
|
baseline: {
|
|
996
|
-
digest: "sha256:
|
|
1020
|
+
digest: "sha256:9795afbb773b45c2d794522ad8c1fde600feda44cfd978572d62b93e9afb5724",
|
|
997
1021
|
kind: "agent-candidate-execution-evidence",
|
|
998
1022
|
materializationReceipt: {
|
|
999
1023
|
benchmark: {
|
|
@@ -1016,7 +1040,7 @@ var agent_improvement_proposal_default = {
|
|
|
1016
1040
|
}
|
|
1017
1041
|
}
|
|
1018
1042
|
},
|
|
1019
|
-
bundleDigest: "sha256:
|
|
1043
|
+
bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
1020
1044
|
codeKind: "disabled",
|
|
1021
1045
|
container: {
|
|
1022
1046
|
image: "ghcr.io/example/task",
|
|
@@ -1028,16 +1052,16 @@ var agent_improvement_proposal_default = {
|
|
|
1028
1052
|
},
|
|
1029
1053
|
source: "evaluator-task-container"
|
|
1030
1054
|
},
|
|
1031
|
-
digest: "sha256:
|
|
1055
|
+
digest: "sha256:0406c21aababc8747dd9de4bc66e83dbc1bb48ad55048168178dcaa4016dc48f",
|
|
1032
1056
|
digestAlgorithm: "rfc8785-sha256",
|
|
1033
1057
|
executionPlan: {
|
|
1034
1058
|
artifact: {
|
|
1035
|
-
byteLength:
|
|
1036
|
-
content: "
|
|
1059
|
+
byteLength: 2030,
|
|
1060
|
+
content: "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",
|
|
1037
1061
|
encoding: "base64",
|
|
1038
|
-
sha256: "sha256:
|
|
1062
|
+
sha256: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287"
|
|
1039
1063
|
},
|
|
1040
|
-
digest: "sha256:
|
|
1064
|
+
digest: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287",
|
|
1041
1065
|
kind: "agent-candidate-execution-plan",
|
|
1042
1066
|
material: {
|
|
1043
1067
|
codeKind: "disabled",
|
|
@@ -1064,7 +1088,12 @@ var agent_improvement_proposal_default = {
|
|
|
1064
1088
|
path: ".",
|
|
1065
1089
|
workspace: "task"
|
|
1066
1090
|
},
|
|
1067
|
-
env: {
|
|
1091
|
+
env: {
|
|
1092
|
+
PATH: {
|
|
1093
|
+
kind: "public",
|
|
1094
|
+
value: "/usr/local/bin:/usr/bin:/bin"
|
|
1095
|
+
}
|
|
1096
|
+
},
|
|
1068
1097
|
executable: "codex"
|
|
1069
1098
|
},
|
|
1070
1099
|
limits: {
|
|
@@ -1113,9 +1142,9 @@ var agent_improvement_proposal_default = {
|
|
|
1113
1142
|
runCell: {
|
|
1114
1143
|
arm: "baseline",
|
|
1115
1144
|
attempt: 1,
|
|
1116
|
-
bundleDigest: "sha256:
|
|
1117
|
-
digest: "sha256:
|
|
1118
|
-
experimentDigest: "sha256:
|
|
1145
|
+
bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
1146
|
+
digest: "sha256:1c64f3d18b9d8c5a34231c5c7c2d3496e225051c9f2930ca97d01176492e8e76",
|
|
1147
|
+
experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
|
|
1119
1148
|
kind: "agent-candidate-run-cell",
|
|
1120
1149
|
repetition: 1,
|
|
1121
1150
|
seed: 102,
|
|
@@ -1180,12 +1209,12 @@ var agent_improvement_proposal_default = {
|
|
|
1180
1209
|
byteLength: 1122,
|
|
1181
1210
|
locator: {
|
|
1182
1211
|
bucket: "candidate-test-artifacts",
|
|
1183
|
-
key: "benchmark-result/
|
|
1212
|
+
key: "benchmark-result/c9891b43d8cc45bb7b1d76eccce93421af4c329983e4d2cbfd4411df4cd228da",
|
|
1184
1213
|
kind: "s3"
|
|
1185
1214
|
},
|
|
1186
|
-
sha256: "sha256:
|
|
1215
|
+
sha256: "sha256:c9891b43d8cc45bb7b1d76eccce93421af4c329983e4d2cbfd4411df4cd228da"
|
|
1187
1216
|
},
|
|
1188
|
-
digest: "sha256:
|
|
1217
|
+
digest: "sha256:c9891b43d8cc45bb7b1d76eccce93421af4c329983e4d2cbfd4411df4cd228da",
|
|
1189
1218
|
kind: "agent-candidate-benchmark-result",
|
|
1190
1219
|
material: {
|
|
1191
1220
|
dimensions: [
|
|
@@ -1203,7 +1232,7 @@ var agent_improvement_proposal_default = {
|
|
|
1203
1232
|
},
|
|
1204
1233
|
sha256: "sha256:628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b"
|
|
1205
1234
|
},
|
|
1206
|
-
executionPlanDigest: "sha256:
|
|
1235
|
+
executionPlanDigest: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287",
|
|
1207
1236
|
grader: {
|
|
1208
1237
|
artifact: {
|
|
1209
1238
|
byteLength: 25,
|
|
@@ -1236,24 +1265,24 @@ var agent_improvement_proposal_default = {
|
|
|
1236
1265
|
kind: "agent-candidate-benchmark-result-material",
|
|
1237
1266
|
passed: false,
|
|
1238
1267
|
score: 0,
|
|
1239
|
-
taskOutcomeDigest: "sha256:
|
|
1268
|
+
taskOutcomeDigest: "sha256:24cd5d7f59ab6334118cd341ad8f8fd4d20156a561ddb2b55fe86c61c2895aa2"
|
|
1240
1269
|
}
|
|
1241
1270
|
},
|
|
1242
|
-
bundleDigest: "sha256:
|
|
1243
|
-
digest: "sha256:
|
|
1271
|
+
bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
1272
|
+
digest: "sha256:362e0b403b592b762ec92734f1286ecaf0c08e40970525de14b3052b335b8618",
|
|
1244
1273
|
digestAlgorithm: "rfc8785-sha256",
|
|
1245
|
-
executionPlanDigest: "sha256:
|
|
1274
|
+
executionPlanDigest: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287",
|
|
1246
1275
|
executorCapture: {
|
|
1247
1276
|
byteLength: 477,
|
|
1248
1277
|
locator: {
|
|
1249
1278
|
bucket: "candidate-test-artifacts",
|
|
1250
|
-
key: "executor-capture/
|
|
1279
|
+
key: "executor-capture/da5fc6561b02133890cdfb4cdc0b3495d17059040b27c1be20b8a123d2a6524a",
|
|
1251
1280
|
kind: "s3"
|
|
1252
1281
|
},
|
|
1253
|
-
sha256: "sha256:
|
|
1282
|
+
sha256: "sha256:da5fc6561b02133890cdfb4cdc0b3495d17059040b27c1be20b8a123d2a6524a"
|
|
1254
1283
|
},
|
|
1255
1284
|
kind: "agent-candidate-run",
|
|
1256
|
-
materializationReceiptDigest: "sha256:
|
|
1285
|
+
materializationReceiptDigest: "sha256:0406c21aababc8747dd9de4bc66e83dbc1bb48ad55048168178dcaa4016dc48f",
|
|
1257
1286
|
memory: {
|
|
1258
1287
|
mode: "disabled"
|
|
1259
1288
|
},
|
|
@@ -1262,17 +1291,17 @@ var agent_improvement_proposal_default = {
|
|
|
1262
1291
|
byteLength: 615,
|
|
1263
1292
|
locator: {
|
|
1264
1293
|
bucket: "candidate-test-artifacts",
|
|
1265
|
-
key: "model-settlement/
|
|
1294
|
+
key: "model-settlement/446db011d1af4c39f2d0fd21a7e64774b9aaa685efe56e928d8e67d8ea1b3fa3",
|
|
1266
1295
|
kind: "s3"
|
|
1267
1296
|
},
|
|
1268
|
-
sha256: "sha256:
|
|
1297
|
+
sha256: "sha256:446db011d1af4c39f2d0fd21a7e64774b9aaa685efe56e928d8e67d8ea1b3fa3"
|
|
1269
1298
|
},
|
|
1270
|
-
digest: "sha256:
|
|
1299
|
+
digest: "sha256:446db011d1af4c39f2d0fd21a7e64774b9aaa685efe56e928d8e67d8ea1b3fa3",
|
|
1271
1300
|
kind: "agent-candidate-model-settlement",
|
|
1272
1301
|
material: {
|
|
1273
1302
|
calls: [],
|
|
1274
1303
|
closed: true,
|
|
1275
|
-
executionPlanDigest: "sha256:
|
|
1304
|
+
executionPlanDigest: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287",
|
|
1276
1305
|
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
1277
1306
|
kind: "agent-candidate-model-settlement-material",
|
|
1278
1307
|
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
@@ -1293,21 +1322,21 @@ var agent_improvement_proposal_default = {
|
|
|
1293
1322
|
}
|
|
1294
1323
|
}
|
|
1295
1324
|
},
|
|
1296
|
-
runCellDigest: "sha256:
|
|
1325
|
+
runCellDigest: "sha256:1c64f3d18b9d8c5a34231c5c7c2d3496e225051c9f2930ca97d01176492e8e76",
|
|
1297
1326
|
taskOutcome: {
|
|
1298
1327
|
artifact: {
|
|
1299
1328
|
byteLength: 478,
|
|
1300
1329
|
locator: {
|
|
1301
1330
|
bucket: "candidate-test-artifacts",
|
|
1302
|
-
key: "task-outcome/
|
|
1331
|
+
key: "task-outcome/24cd5d7f59ab6334118cd341ad8f8fd4d20156a561ddb2b55fe86c61c2895aa2",
|
|
1303
1332
|
kind: "s3"
|
|
1304
1333
|
},
|
|
1305
|
-
sha256: "sha256:
|
|
1334
|
+
sha256: "sha256:24cd5d7f59ab6334118cd341ad8f8fd4d20156a561ddb2b55fe86c61c2895aa2"
|
|
1306
1335
|
},
|
|
1307
|
-
digest: "sha256:
|
|
1336
|
+
digest: "sha256:24cd5d7f59ab6334118cd341ad8f8fd4d20156a561ddb2b55fe86c61c2895aa2",
|
|
1308
1337
|
kind: "agent-candidate-task-outcome",
|
|
1309
1338
|
material: {
|
|
1310
|
-
executionPlanDigest: "sha256:
|
|
1339
|
+
executionPlanDigest: "sha256:e719f546b4f6585879b1210ff9c2263859efc625b5d78cfbab46f5a180e29287",
|
|
1311
1340
|
kind: "agent-candidate-task-outcome-material",
|
|
1312
1341
|
outcome: {
|
|
1313
1342
|
artifact: {
|
|
@@ -1341,10 +1370,10 @@ var agent_improvement_proposal_default = {
|
|
|
1341
1370
|
byteLength: 748,
|
|
1342
1371
|
locator: {
|
|
1343
1372
|
bucket: "candidate-test-artifacts",
|
|
1344
|
-
key: "trace/
|
|
1373
|
+
key: "trace/c03c3bd51fb421ffc65985a27619e57b16623ba3f2bc8d22b2f963cdae6e41f6",
|
|
1345
1374
|
kind: "s3"
|
|
1346
1375
|
},
|
|
1347
|
-
sha256: "sha256:
|
|
1376
|
+
sha256: "sha256:c03c3bd51fb421ffc65985a27619e57b16623ba3f2bc8d22b2f963cdae6e41f6"
|
|
1348
1377
|
},
|
|
1349
1378
|
eventCount: 1,
|
|
1350
1379
|
modelCallCount: 0
|
|
@@ -1352,7 +1381,7 @@ var agent_improvement_proposal_default = {
|
|
|
1352
1381
|
}
|
|
1353
1382
|
},
|
|
1354
1383
|
candidate: {
|
|
1355
|
-
digest: "sha256:
|
|
1384
|
+
digest: "sha256:90aa644ce8a4a7bd8968146189ec279b74c550ae6ff02b08adfa984008b68ce5",
|
|
1356
1385
|
kind: "agent-candidate-execution-evidence",
|
|
1357
1386
|
materializationReceipt: {
|
|
1358
1387
|
benchmark: {
|
|
@@ -1375,7 +1404,7 @@ var agent_improvement_proposal_default = {
|
|
|
1375
1404
|
}
|
|
1376
1405
|
}
|
|
1377
1406
|
},
|
|
1378
|
-
bundleDigest: "sha256:
|
|
1407
|
+
bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
1379
1408
|
codeKind: "disabled",
|
|
1380
1409
|
container: {
|
|
1381
1410
|
image: "ghcr.io/example/task",
|
|
@@ -1387,16 +1416,16 @@ var agent_improvement_proposal_default = {
|
|
|
1387
1416
|
},
|
|
1388
1417
|
source: "evaluator-task-container"
|
|
1389
1418
|
},
|
|
1390
|
-
digest: "sha256:
|
|
1419
|
+
digest: "sha256:d6e837e515c14c86a79f6fb099384a0ac97d74cbfebc2e1a095a8b7660ef1fed",
|
|
1391
1420
|
digestAlgorithm: "rfc8785-sha256",
|
|
1392
1421
|
executionPlan: {
|
|
1393
1422
|
artifact: {
|
|
1394
|
-
byteLength:
|
|
1395
|
-
content: "
|
|
1423
|
+
byteLength: 2032,
|
|
1424
|
+
content: "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",
|
|
1396
1425
|
encoding: "base64",
|
|
1397
|
-
sha256: "sha256:
|
|
1426
|
+
sha256: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6"
|
|
1398
1427
|
},
|
|
1399
|
-
digest: "sha256:
|
|
1428
|
+
digest: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6",
|
|
1400
1429
|
kind: "agent-candidate-execution-plan",
|
|
1401
1430
|
material: {
|
|
1402
1431
|
codeKind: "disabled",
|
|
@@ -1423,7 +1452,12 @@ var agent_improvement_proposal_default = {
|
|
|
1423
1452
|
path: ".",
|
|
1424
1453
|
workspace: "task"
|
|
1425
1454
|
},
|
|
1426
|
-
env: {
|
|
1455
|
+
env: {
|
|
1456
|
+
PATH: {
|
|
1457
|
+
kind: "public",
|
|
1458
|
+
value: "/usr/local/bin:/usr/bin:/bin"
|
|
1459
|
+
}
|
|
1460
|
+
},
|
|
1427
1461
|
executable: "codex"
|
|
1428
1462
|
},
|
|
1429
1463
|
limits: {
|
|
@@ -1472,9 +1506,9 @@ var agent_improvement_proposal_default = {
|
|
|
1472
1506
|
runCell: {
|
|
1473
1507
|
arm: "candidate",
|
|
1474
1508
|
attempt: 1,
|
|
1475
|
-
bundleDigest: "sha256:
|
|
1476
|
-
digest: "sha256:
|
|
1477
|
-
experimentDigest: "sha256:
|
|
1509
|
+
bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
1510
|
+
digest: "sha256:3056f0119ac4643dc3defb95fb324552e10f94e40621231d1f60d148f59d1d39",
|
|
1511
|
+
experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
|
|
1478
1512
|
kind: "agent-candidate-run-cell",
|
|
1479
1513
|
repetition: 1,
|
|
1480
1514
|
seed: 102,
|
|
@@ -1543,12 +1577,12 @@ var agent_improvement_proposal_default = {
|
|
|
1543
1577
|
byteLength: 1121,
|
|
1544
1578
|
locator: {
|
|
1545
1579
|
bucket: "candidate-test-artifacts",
|
|
1546
|
-
key: "benchmark-result/
|
|
1580
|
+
key: "benchmark-result/8b1ecbcec1ebdb0ec02a3785ff61796b8de31c83830d446c560029dc127a45ca",
|
|
1547
1581
|
kind: "s3"
|
|
1548
1582
|
},
|
|
1549
|
-
sha256: "sha256:
|
|
1583
|
+
sha256: "sha256:8b1ecbcec1ebdb0ec02a3785ff61796b8de31c83830d446c560029dc127a45ca"
|
|
1550
1584
|
},
|
|
1551
|
-
digest: "sha256:
|
|
1585
|
+
digest: "sha256:8b1ecbcec1ebdb0ec02a3785ff61796b8de31c83830d446c560029dc127a45ca",
|
|
1552
1586
|
kind: "agent-candidate-benchmark-result",
|
|
1553
1587
|
material: {
|
|
1554
1588
|
dimensions: [
|
|
@@ -1566,7 +1600,7 @@ var agent_improvement_proposal_default = {
|
|
|
1566
1600
|
},
|
|
1567
1601
|
sha256: "sha256:9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d"
|
|
1568
1602
|
},
|
|
1569
|
-
executionPlanDigest: "sha256:
|
|
1603
|
+
executionPlanDigest: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6",
|
|
1570
1604
|
grader: {
|
|
1571
1605
|
artifact: {
|
|
1572
1606
|
byteLength: 25,
|
|
@@ -1599,24 +1633,24 @@ var agent_improvement_proposal_default = {
|
|
|
1599
1633
|
kind: "agent-candidate-benchmark-result-material",
|
|
1600
1634
|
passed: true,
|
|
1601
1635
|
score: 1,
|
|
1602
|
-
taskOutcomeDigest: "sha256:
|
|
1636
|
+
taskOutcomeDigest: "sha256:f24062b48a7ba4bfe3e2566ef7e0d4e97d3c38d7a54e86bf86446adf7fa1cef4"
|
|
1603
1637
|
}
|
|
1604
1638
|
},
|
|
1605
|
-
bundleDigest: "sha256:
|
|
1606
|
-
digest: "sha256:
|
|
1639
|
+
bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
1640
|
+
digest: "sha256:bbfcb8dfe7d34f06ce47c8a6562ab15fcaa1dc083524eb692890055e2e2ccc27",
|
|
1607
1641
|
digestAlgorithm: "rfc8785-sha256",
|
|
1608
|
-
executionPlanDigest: "sha256:
|
|
1642
|
+
executionPlanDigest: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6",
|
|
1609
1643
|
executorCapture: {
|
|
1610
1644
|
byteLength: 477,
|
|
1611
1645
|
locator: {
|
|
1612
1646
|
bucket: "candidate-test-artifacts",
|
|
1613
|
-
key: "executor-capture/
|
|
1647
|
+
key: "executor-capture/5d5db54b6c1e1d5e8d3c1248b3617dcdc8cefb80aa69cf750a1abacbadf9efdb",
|
|
1614
1648
|
kind: "s3"
|
|
1615
1649
|
},
|
|
1616
|
-
sha256: "sha256:
|
|
1650
|
+
sha256: "sha256:5d5db54b6c1e1d5e8d3c1248b3617dcdc8cefb80aa69cf750a1abacbadf9efdb"
|
|
1617
1651
|
},
|
|
1618
1652
|
kind: "agent-candidate-run",
|
|
1619
|
-
materializationReceiptDigest: "sha256:
|
|
1653
|
+
materializationReceiptDigest: "sha256:d6e837e515c14c86a79f6fb099384a0ac97d74cbfebc2e1a095a8b7660ef1fed",
|
|
1620
1654
|
memory: {
|
|
1621
1655
|
mode: "disabled"
|
|
1622
1656
|
},
|
|
@@ -1625,17 +1659,17 @@ var agent_improvement_proposal_default = {
|
|
|
1625
1659
|
byteLength: 615,
|
|
1626
1660
|
locator: {
|
|
1627
1661
|
bucket: "candidate-test-artifacts",
|
|
1628
|
-
key: "model-settlement/
|
|
1662
|
+
key: "model-settlement/87ad72eeccca5a0d4593d75b73d7cd4d0d3ffba748b30becc3b496e74ad5d83b",
|
|
1629
1663
|
kind: "s3"
|
|
1630
1664
|
},
|
|
1631
|
-
sha256: "sha256:
|
|
1665
|
+
sha256: "sha256:87ad72eeccca5a0d4593d75b73d7cd4d0d3ffba748b30becc3b496e74ad5d83b"
|
|
1632
1666
|
},
|
|
1633
|
-
digest: "sha256:
|
|
1667
|
+
digest: "sha256:87ad72eeccca5a0d4593d75b73d7cd4d0d3ffba748b30becc3b496e74ad5d83b",
|
|
1634
1668
|
kind: "agent-candidate-model-settlement",
|
|
1635
1669
|
material: {
|
|
1636
1670
|
calls: [],
|
|
1637
1671
|
closed: true,
|
|
1638
|
-
executionPlanDigest: "sha256:
|
|
1672
|
+
executionPlanDigest: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6",
|
|
1639
1673
|
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
1640
1674
|
kind: "agent-candidate-model-settlement-material",
|
|
1641
1675
|
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
@@ -1656,21 +1690,21 @@ var agent_improvement_proposal_default = {
|
|
|
1656
1690
|
}
|
|
1657
1691
|
}
|
|
1658
1692
|
},
|
|
1659
|
-
runCellDigest: "sha256:
|
|
1693
|
+
runCellDigest: "sha256:3056f0119ac4643dc3defb95fb324552e10f94e40621231d1f60d148f59d1d39",
|
|
1660
1694
|
taskOutcome: {
|
|
1661
1695
|
artifact: {
|
|
1662
1696
|
byteLength: 478,
|
|
1663
1697
|
locator: {
|
|
1664
1698
|
bucket: "candidate-test-artifacts",
|
|
1665
|
-
key: "task-outcome/
|
|
1699
|
+
key: "task-outcome/f24062b48a7ba4bfe3e2566ef7e0d4e97d3c38d7a54e86bf86446adf7fa1cef4",
|
|
1666
1700
|
kind: "s3"
|
|
1667
1701
|
},
|
|
1668
|
-
sha256: "sha256:
|
|
1702
|
+
sha256: "sha256:f24062b48a7ba4bfe3e2566ef7e0d4e97d3c38d7a54e86bf86446adf7fa1cef4"
|
|
1669
1703
|
},
|
|
1670
|
-
digest: "sha256:
|
|
1704
|
+
digest: "sha256:f24062b48a7ba4bfe3e2566ef7e0d4e97d3c38d7a54e86bf86446adf7fa1cef4",
|
|
1671
1705
|
kind: "agent-candidate-task-outcome",
|
|
1672
1706
|
material: {
|
|
1673
|
-
executionPlanDigest: "sha256:
|
|
1707
|
+
executionPlanDigest: "sha256:8d12d5d6466c0dd8f2592be9f6d66b5b6a2139bfe8cdc5b793bde9e28ebec4c6",
|
|
1674
1708
|
kind: "agent-candidate-task-outcome-material",
|
|
1675
1709
|
outcome: {
|
|
1676
1710
|
artifact: {
|
|
@@ -1704,10 +1738,10 @@ var agent_improvement_proposal_default = {
|
|
|
1704
1738
|
byteLength: 750,
|
|
1705
1739
|
locator: {
|
|
1706
1740
|
bucket: "candidate-test-artifacts",
|
|
1707
|
-
key: "trace/
|
|
1741
|
+
key: "trace/e2cdd682a809a037e0049d1b3d3280d7b4099a3e0507b3591fc05b2872641166",
|
|
1708
1742
|
kind: "s3"
|
|
1709
1743
|
},
|
|
1710
|
-
sha256: "sha256:
|
|
1744
|
+
sha256: "sha256:e2cdd682a809a037e0049d1b3d3280d7b4099a3e0507b3591fc05b2872641166"
|
|
1711
1745
|
},
|
|
1712
1746
|
eventCount: 1,
|
|
1713
1747
|
modelCallCount: 0
|
|
@@ -1717,7 +1751,7 @@ var agent_improvement_proposal_default = {
|
|
|
1717
1751
|
},
|
|
1718
1752
|
{
|
|
1719
1753
|
baseline: {
|
|
1720
|
-
digest: "sha256:
|
|
1754
|
+
digest: "sha256:7ebfc740cb6c0156ce54d450015af9e418a57473299022f926555f2a5b706454",
|
|
1721
1755
|
kind: "agent-candidate-execution-evidence",
|
|
1722
1756
|
materializationReceipt: {
|
|
1723
1757
|
benchmark: {
|
|
@@ -1740,7 +1774,7 @@ var agent_improvement_proposal_default = {
|
|
|
1740
1774
|
}
|
|
1741
1775
|
}
|
|
1742
1776
|
},
|
|
1743
|
-
bundleDigest: "sha256:
|
|
1777
|
+
bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
1744
1778
|
codeKind: "disabled",
|
|
1745
1779
|
container: {
|
|
1746
1780
|
image: "ghcr.io/example/task",
|
|
@@ -1752,16 +1786,16 @@ var agent_improvement_proposal_default = {
|
|
|
1752
1786
|
},
|
|
1753
1787
|
source: "evaluator-task-container"
|
|
1754
1788
|
},
|
|
1755
|
-
digest: "sha256:
|
|
1789
|
+
digest: "sha256:0e3da90681970b46a99808f5d5a623329bae9529bf0f46ccebe7cac7a202ec8a",
|
|
1756
1790
|
digestAlgorithm: "rfc8785-sha256",
|
|
1757
1791
|
executionPlan: {
|
|
1758
1792
|
artifact: {
|
|
1759
|
-
byteLength:
|
|
1760
|
-
content: "
|
|
1793
|
+
byteLength: 2030,
|
|
1794
|
+
content: "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",
|
|
1761
1795
|
encoding: "base64",
|
|
1762
|
-
sha256: "sha256:
|
|
1796
|
+
sha256: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e"
|
|
1763
1797
|
},
|
|
1764
|
-
digest: "sha256:
|
|
1798
|
+
digest: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e",
|
|
1765
1799
|
kind: "agent-candidate-execution-plan",
|
|
1766
1800
|
material: {
|
|
1767
1801
|
codeKind: "disabled",
|
|
@@ -1788,7 +1822,12 @@ var agent_improvement_proposal_default = {
|
|
|
1788
1822
|
path: ".",
|
|
1789
1823
|
workspace: "task"
|
|
1790
1824
|
},
|
|
1791
|
-
env: {
|
|
1825
|
+
env: {
|
|
1826
|
+
PATH: {
|
|
1827
|
+
kind: "public",
|
|
1828
|
+
value: "/usr/local/bin:/usr/bin:/bin"
|
|
1829
|
+
}
|
|
1830
|
+
},
|
|
1792
1831
|
executable: "codex"
|
|
1793
1832
|
},
|
|
1794
1833
|
limits: {
|
|
@@ -1837,9 +1876,9 @@ var agent_improvement_proposal_default = {
|
|
|
1837
1876
|
runCell: {
|
|
1838
1877
|
arm: "baseline",
|
|
1839
1878
|
attempt: 1,
|
|
1840
|
-
bundleDigest: "sha256:
|
|
1841
|
-
digest: "sha256:
|
|
1842
|
-
experimentDigest: "sha256:
|
|
1879
|
+
bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
1880
|
+
digest: "sha256:9c427cc67507cda8dcdac327f390adfa7e045d069e677d62921678b46a96d66c",
|
|
1881
|
+
experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
|
|
1843
1882
|
kind: "agent-candidate-run-cell",
|
|
1844
1883
|
repetition: 2,
|
|
1845
1884
|
seed: 103,
|
|
@@ -1904,12 +1943,12 @@ var agent_improvement_proposal_default = {
|
|
|
1904
1943
|
byteLength: 1122,
|
|
1905
1944
|
locator: {
|
|
1906
1945
|
bucket: "candidate-test-artifacts",
|
|
1907
|
-
key: "benchmark-result/
|
|
1946
|
+
key: "benchmark-result/df1a5884a7ed4e54dae3d023b47c21596d27264b5ca59693b51eb221dd533284",
|
|
1908
1947
|
kind: "s3"
|
|
1909
1948
|
},
|
|
1910
|
-
sha256: "sha256:
|
|
1949
|
+
sha256: "sha256:df1a5884a7ed4e54dae3d023b47c21596d27264b5ca59693b51eb221dd533284"
|
|
1911
1950
|
},
|
|
1912
|
-
digest: "sha256:
|
|
1951
|
+
digest: "sha256:df1a5884a7ed4e54dae3d023b47c21596d27264b5ca59693b51eb221dd533284",
|
|
1913
1952
|
kind: "agent-candidate-benchmark-result",
|
|
1914
1953
|
material: {
|
|
1915
1954
|
dimensions: [
|
|
@@ -1927,7 +1966,7 @@ var agent_improvement_proposal_default = {
|
|
|
1927
1966
|
},
|
|
1928
1967
|
sha256: "sha256:628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b"
|
|
1929
1968
|
},
|
|
1930
|
-
executionPlanDigest: "sha256:
|
|
1969
|
+
executionPlanDigest: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e",
|
|
1931
1970
|
grader: {
|
|
1932
1971
|
artifact: {
|
|
1933
1972
|
byteLength: 25,
|
|
@@ -1960,24 +1999,24 @@ var agent_improvement_proposal_default = {
|
|
|
1960
1999
|
kind: "agent-candidate-benchmark-result-material",
|
|
1961
2000
|
passed: false,
|
|
1962
2001
|
score: 0,
|
|
1963
|
-
taskOutcomeDigest: "sha256:
|
|
2002
|
+
taskOutcomeDigest: "sha256:664358fd0e890ca17d0c31aa0157e434c3bc7f6ecaa77c581d5ef600b6a836ce"
|
|
1964
2003
|
}
|
|
1965
2004
|
},
|
|
1966
|
-
bundleDigest: "sha256:
|
|
1967
|
-
digest: "sha256:
|
|
2005
|
+
bundleDigest: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
2006
|
+
digest: "sha256:7dfea3ef8bf6e5c0432180fefe63cad9f62833ecb8bea1ce0de7d41ca3ef3bc5",
|
|
1968
2007
|
digestAlgorithm: "rfc8785-sha256",
|
|
1969
|
-
executionPlanDigest: "sha256:
|
|
2008
|
+
executionPlanDigest: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e",
|
|
1970
2009
|
executorCapture: {
|
|
1971
2010
|
byteLength: 477,
|
|
1972
2011
|
locator: {
|
|
1973
2012
|
bucket: "candidate-test-artifacts",
|
|
1974
|
-
key: "executor-capture/
|
|
2013
|
+
key: "executor-capture/3fdb1d6105bd10c22daa6c0267015a8f6a88b13d1703e8bf2c901c0887a4b242",
|
|
1975
2014
|
kind: "s3"
|
|
1976
2015
|
},
|
|
1977
|
-
sha256: "sha256:
|
|
2016
|
+
sha256: "sha256:3fdb1d6105bd10c22daa6c0267015a8f6a88b13d1703e8bf2c901c0887a4b242"
|
|
1978
2017
|
},
|
|
1979
2018
|
kind: "agent-candidate-run",
|
|
1980
|
-
materializationReceiptDigest: "sha256:
|
|
2019
|
+
materializationReceiptDigest: "sha256:0e3da90681970b46a99808f5d5a623329bae9529bf0f46ccebe7cac7a202ec8a",
|
|
1981
2020
|
memory: {
|
|
1982
2021
|
mode: "disabled"
|
|
1983
2022
|
},
|
|
@@ -1986,17 +2025,17 @@ var agent_improvement_proposal_default = {
|
|
|
1986
2025
|
byteLength: 615,
|
|
1987
2026
|
locator: {
|
|
1988
2027
|
bucket: "candidate-test-artifacts",
|
|
1989
|
-
key: "model-settlement/
|
|
2028
|
+
key: "model-settlement/39c54b821165bbff4a33cf310c51e20f6d1ff0ee10ff7630618010e91d5a1615",
|
|
1990
2029
|
kind: "s3"
|
|
1991
2030
|
},
|
|
1992
|
-
sha256: "sha256:
|
|
2031
|
+
sha256: "sha256:39c54b821165bbff4a33cf310c51e20f6d1ff0ee10ff7630618010e91d5a1615"
|
|
1993
2032
|
},
|
|
1994
|
-
digest: "sha256:
|
|
2033
|
+
digest: "sha256:39c54b821165bbff4a33cf310c51e20f6d1ff0ee10ff7630618010e91d5a1615",
|
|
1995
2034
|
kind: "agent-candidate-model-settlement",
|
|
1996
2035
|
material: {
|
|
1997
2036
|
calls: [],
|
|
1998
2037
|
closed: true,
|
|
1999
|
-
executionPlanDigest: "sha256:
|
|
2038
|
+
executionPlanDigest: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e",
|
|
2000
2039
|
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
2001
2040
|
kind: "agent-candidate-model-settlement-material",
|
|
2002
2041
|
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
@@ -2017,21 +2056,21 @@ var agent_improvement_proposal_default = {
|
|
|
2017
2056
|
}
|
|
2018
2057
|
}
|
|
2019
2058
|
},
|
|
2020
|
-
runCellDigest: "sha256:
|
|
2059
|
+
runCellDigest: "sha256:9c427cc67507cda8dcdac327f390adfa7e045d069e677d62921678b46a96d66c",
|
|
2021
2060
|
taskOutcome: {
|
|
2022
2061
|
artifact: {
|
|
2023
2062
|
byteLength: 478,
|
|
2024
2063
|
locator: {
|
|
2025
2064
|
bucket: "candidate-test-artifacts",
|
|
2026
|
-
key: "task-outcome/
|
|
2065
|
+
key: "task-outcome/664358fd0e890ca17d0c31aa0157e434c3bc7f6ecaa77c581d5ef600b6a836ce",
|
|
2027
2066
|
kind: "s3"
|
|
2028
2067
|
},
|
|
2029
|
-
sha256: "sha256:
|
|
2068
|
+
sha256: "sha256:664358fd0e890ca17d0c31aa0157e434c3bc7f6ecaa77c581d5ef600b6a836ce"
|
|
2030
2069
|
},
|
|
2031
|
-
digest: "sha256:
|
|
2070
|
+
digest: "sha256:664358fd0e890ca17d0c31aa0157e434c3bc7f6ecaa77c581d5ef600b6a836ce",
|
|
2032
2071
|
kind: "agent-candidate-task-outcome",
|
|
2033
2072
|
material: {
|
|
2034
|
-
executionPlanDigest: "sha256:
|
|
2073
|
+
executionPlanDigest: "sha256:a8fe2f7c6d5bc4d0832a2aa3a0ec6b0c311a1f1bafe9a0fc406991802a87685e",
|
|
2035
2074
|
kind: "agent-candidate-task-outcome-material",
|
|
2036
2075
|
outcome: {
|
|
2037
2076
|
artifact: {
|
|
@@ -2065,10 +2104,10 @@ var agent_improvement_proposal_default = {
|
|
|
2065
2104
|
byteLength: 748,
|
|
2066
2105
|
locator: {
|
|
2067
2106
|
bucket: "candidate-test-artifacts",
|
|
2068
|
-
key: "trace/
|
|
2107
|
+
key: "trace/f1867bc538dae9c3a35e73fd7c21c06150bbcba815a56835f70b26d615a6e66d",
|
|
2069
2108
|
kind: "s3"
|
|
2070
2109
|
},
|
|
2071
|
-
sha256: "sha256:
|
|
2110
|
+
sha256: "sha256:f1867bc538dae9c3a35e73fd7c21c06150bbcba815a56835f70b26d615a6e66d"
|
|
2072
2111
|
},
|
|
2073
2112
|
eventCount: 1,
|
|
2074
2113
|
modelCallCount: 0
|
|
@@ -2076,7 +2115,7 @@ var agent_improvement_proposal_default = {
|
|
|
2076
2115
|
}
|
|
2077
2116
|
},
|
|
2078
2117
|
candidate: {
|
|
2079
|
-
digest: "sha256:
|
|
2118
|
+
digest: "sha256:325bbde1ccafdb3786a26b48ad407fea1912f0d7b340c4a654a1ebdc622d960c",
|
|
2080
2119
|
kind: "agent-candidate-execution-evidence",
|
|
2081
2120
|
materializationReceipt: {
|
|
2082
2121
|
benchmark: {
|
|
@@ -2099,7 +2138,7 @@ var agent_improvement_proposal_default = {
|
|
|
2099
2138
|
}
|
|
2100
2139
|
}
|
|
2101
2140
|
},
|
|
2102
|
-
bundleDigest: "sha256:
|
|
2141
|
+
bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
2103
2142
|
codeKind: "disabled",
|
|
2104
2143
|
container: {
|
|
2105
2144
|
image: "ghcr.io/example/task",
|
|
@@ -2111,16 +2150,16 @@ var agent_improvement_proposal_default = {
|
|
|
2111
2150
|
},
|
|
2112
2151
|
source: "evaluator-task-container"
|
|
2113
2152
|
},
|
|
2114
|
-
digest: "sha256:
|
|
2153
|
+
digest: "sha256:b3718d6b33e7316d37af34e81e93a6521b0e9914bdec820d56e14fd7008f3e05",
|
|
2115
2154
|
digestAlgorithm: "rfc8785-sha256",
|
|
2116
2155
|
executionPlan: {
|
|
2117
2156
|
artifact: {
|
|
2118
|
-
byteLength:
|
|
2119
|
-
content: "
|
|
2157
|
+
byteLength: 2032,
|
|
2158
|
+
content: "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",
|
|
2120
2159
|
encoding: "base64",
|
|
2121
|
-
sha256: "sha256:
|
|
2160
|
+
sha256: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f"
|
|
2122
2161
|
},
|
|
2123
|
-
digest: "sha256:
|
|
2162
|
+
digest: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f",
|
|
2124
2163
|
kind: "agent-candidate-execution-plan",
|
|
2125
2164
|
material: {
|
|
2126
2165
|
codeKind: "disabled",
|
|
@@ -2147,7 +2186,12 @@ var agent_improvement_proposal_default = {
|
|
|
2147
2186
|
path: ".",
|
|
2148
2187
|
workspace: "task"
|
|
2149
2188
|
},
|
|
2150
|
-
env: {
|
|
2189
|
+
env: {
|
|
2190
|
+
PATH: {
|
|
2191
|
+
kind: "public",
|
|
2192
|
+
value: "/usr/local/bin:/usr/bin:/bin"
|
|
2193
|
+
}
|
|
2194
|
+
},
|
|
2151
2195
|
executable: "codex"
|
|
2152
2196
|
},
|
|
2153
2197
|
limits: {
|
|
@@ -2196,9 +2240,9 @@ var agent_improvement_proposal_default = {
|
|
|
2196
2240
|
runCell: {
|
|
2197
2241
|
arm: "candidate",
|
|
2198
2242
|
attempt: 1,
|
|
2199
|
-
bundleDigest: "sha256:
|
|
2200
|
-
digest: "sha256:
|
|
2201
|
-
experimentDigest: "sha256:
|
|
2243
|
+
bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
2244
|
+
digest: "sha256:ea5cab9dff49326dfe856aab19514d2bc5bc0fab2b4b685c4fea356801dbd1c3",
|
|
2245
|
+
experimentDigest: "sha256:c47a0dad80e6cc4856cdb8a02a279da621ab7d9409e3127650b67f1fc1c14b2d",
|
|
2202
2246
|
kind: "agent-candidate-run-cell",
|
|
2203
2247
|
repetition: 2,
|
|
2204
2248
|
seed: 103,
|
|
@@ -2267,12 +2311,12 @@ var agent_improvement_proposal_default = {
|
|
|
2267
2311
|
byteLength: 1121,
|
|
2268
2312
|
locator: {
|
|
2269
2313
|
bucket: "candidate-test-artifacts",
|
|
2270
|
-
key: "benchmark-result/
|
|
2314
|
+
key: "benchmark-result/95541270205f83cd4d1fe61062e133c4f2afdb1978d1af56de0aef0410999aa4",
|
|
2271
2315
|
kind: "s3"
|
|
2272
2316
|
},
|
|
2273
|
-
sha256: "sha256:
|
|
2317
|
+
sha256: "sha256:95541270205f83cd4d1fe61062e133c4f2afdb1978d1af56de0aef0410999aa4"
|
|
2274
2318
|
},
|
|
2275
|
-
digest: "sha256:
|
|
2319
|
+
digest: "sha256:95541270205f83cd4d1fe61062e133c4f2afdb1978d1af56de0aef0410999aa4",
|
|
2276
2320
|
kind: "agent-candidate-benchmark-result",
|
|
2277
2321
|
material: {
|
|
2278
2322
|
dimensions: [
|
|
@@ -2290,7 +2334,7 @@ var agent_improvement_proposal_default = {
|
|
|
2290
2334
|
},
|
|
2291
2335
|
sha256: "sha256:9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d"
|
|
2292
2336
|
},
|
|
2293
|
-
executionPlanDigest: "sha256:
|
|
2337
|
+
executionPlanDigest: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f",
|
|
2294
2338
|
grader: {
|
|
2295
2339
|
artifact: {
|
|
2296
2340
|
byteLength: 25,
|
|
@@ -2323,24 +2367,24 @@ var agent_improvement_proposal_default = {
|
|
|
2323
2367
|
kind: "agent-candidate-benchmark-result-material",
|
|
2324
2368
|
passed: true,
|
|
2325
2369
|
score: 1,
|
|
2326
|
-
taskOutcomeDigest: "sha256:
|
|
2370
|
+
taskOutcomeDigest: "sha256:61d53d0789c46c98b43acdc7177b1b6102f48aa2d6b3b2ff0ec5ee4b287c8d92"
|
|
2327
2371
|
}
|
|
2328
2372
|
},
|
|
2329
|
-
bundleDigest: "sha256:
|
|
2330
|
-
digest: "sha256:
|
|
2373
|
+
bundleDigest: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
2374
|
+
digest: "sha256:62fb136a6376e729f10efa210b6dba6607923b2502597e555bd055d72ee307dd",
|
|
2331
2375
|
digestAlgorithm: "rfc8785-sha256",
|
|
2332
|
-
executionPlanDigest: "sha256:
|
|
2376
|
+
executionPlanDigest: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f",
|
|
2333
2377
|
executorCapture: {
|
|
2334
2378
|
byteLength: 477,
|
|
2335
2379
|
locator: {
|
|
2336
2380
|
bucket: "candidate-test-artifacts",
|
|
2337
|
-
key: "executor-capture/
|
|
2381
|
+
key: "executor-capture/c8e3a1667966134d3f7b24b4df19a5f5286814522f7884f0a76f7cfd3d4832a2",
|
|
2338
2382
|
kind: "s3"
|
|
2339
2383
|
},
|
|
2340
|
-
sha256: "sha256:
|
|
2384
|
+
sha256: "sha256:c8e3a1667966134d3f7b24b4df19a5f5286814522f7884f0a76f7cfd3d4832a2"
|
|
2341
2385
|
},
|
|
2342
2386
|
kind: "agent-candidate-run",
|
|
2343
|
-
materializationReceiptDigest: "sha256:
|
|
2387
|
+
materializationReceiptDigest: "sha256:b3718d6b33e7316d37af34e81e93a6521b0e9914bdec820d56e14fd7008f3e05",
|
|
2344
2388
|
memory: {
|
|
2345
2389
|
mode: "disabled"
|
|
2346
2390
|
},
|
|
@@ -2349,17 +2393,17 @@ var agent_improvement_proposal_default = {
|
|
|
2349
2393
|
byteLength: 615,
|
|
2350
2394
|
locator: {
|
|
2351
2395
|
bucket: "candidate-test-artifacts",
|
|
2352
|
-
key: "model-settlement/
|
|
2396
|
+
key: "model-settlement/397df4f1827292bad160efdfeb9f92748df604396b285b20f527299b073a8988",
|
|
2353
2397
|
kind: "s3"
|
|
2354
2398
|
},
|
|
2355
|
-
sha256: "sha256:
|
|
2399
|
+
sha256: "sha256:397df4f1827292bad160efdfeb9f92748df604396b285b20f527299b073a8988"
|
|
2356
2400
|
},
|
|
2357
|
-
digest: "sha256:
|
|
2401
|
+
digest: "sha256:397df4f1827292bad160efdfeb9f92748df604396b285b20f527299b073a8988",
|
|
2358
2402
|
kind: "agent-candidate-model-settlement",
|
|
2359
2403
|
material: {
|
|
2360
2404
|
calls: [],
|
|
2361
2405
|
closed: true,
|
|
2362
|
-
executionPlanDigest: "sha256:
|
|
2406
|
+
executionPlanDigest: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f",
|
|
2363
2407
|
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
2364
2408
|
kind: "agent-candidate-model-settlement-material",
|
|
2365
2409
|
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
@@ -2380,21 +2424,21 @@ var agent_improvement_proposal_default = {
|
|
|
2380
2424
|
}
|
|
2381
2425
|
}
|
|
2382
2426
|
},
|
|
2383
|
-
runCellDigest: "sha256:
|
|
2427
|
+
runCellDigest: "sha256:ea5cab9dff49326dfe856aab19514d2bc5bc0fab2b4b685c4fea356801dbd1c3",
|
|
2384
2428
|
taskOutcome: {
|
|
2385
2429
|
artifact: {
|
|
2386
2430
|
byteLength: 478,
|
|
2387
2431
|
locator: {
|
|
2388
2432
|
bucket: "candidate-test-artifacts",
|
|
2389
|
-
key: "task-outcome/
|
|
2433
|
+
key: "task-outcome/61d53d0789c46c98b43acdc7177b1b6102f48aa2d6b3b2ff0ec5ee4b287c8d92",
|
|
2390
2434
|
kind: "s3"
|
|
2391
2435
|
},
|
|
2392
|
-
sha256: "sha256:
|
|
2436
|
+
sha256: "sha256:61d53d0789c46c98b43acdc7177b1b6102f48aa2d6b3b2ff0ec5ee4b287c8d92"
|
|
2393
2437
|
},
|
|
2394
|
-
digest: "sha256:
|
|
2438
|
+
digest: "sha256:61d53d0789c46c98b43acdc7177b1b6102f48aa2d6b3b2ff0ec5ee4b287c8d92",
|
|
2395
2439
|
kind: "agent-candidate-task-outcome",
|
|
2396
2440
|
material: {
|
|
2397
|
-
executionPlanDigest: "sha256:
|
|
2441
|
+
executionPlanDigest: "sha256:c642749f2907277b811c99017d96103dd1ab6d2564fe1c8caba27bbe8d6c151f",
|
|
2398
2442
|
kind: "agent-candidate-task-outcome-material",
|
|
2399
2443
|
outcome: {
|
|
2400
2444
|
artifact: {
|
|
@@ -2428,10 +2472,10 @@ var agent_improvement_proposal_default = {
|
|
|
2428
2472
|
byteLength: 750,
|
|
2429
2473
|
locator: {
|
|
2430
2474
|
bucket: "candidate-test-artifacts",
|
|
2431
|
-
key: "trace/
|
|
2475
|
+
key: "trace/59f819d9564d5e61e59e52545f9b269083f0a0b57a92a5e8f93e566da560ef17",
|
|
2432
2476
|
kind: "s3"
|
|
2433
2477
|
},
|
|
2434
|
-
sha256: "sha256:
|
|
2478
|
+
sha256: "sha256:59f819d9564d5e61e59e52545f9b269083f0a0b57a92a5e8f93e566da560ef17"
|
|
2435
2479
|
},
|
|
2436
2480
|
eventCount: 1,
|
|
2437
2481
|
modelCallCount: 0
|
|
@@ -2442,7 +2486,7 @@ var agent_improvement_proposal_default = {
|
|
|
2442
2486
|
],
|
|
2443
2487
|
metadata: {
|
|
2444
2488
|
fixture: "agent-improvement-proposal",
|
|
2445
|
-
runtimeVersion: "0.
|
|
2489
|
+
runtimeVersion: "0.102.1"
|
|
2446
2490
|
},
|
|
2447
2491
|
objectives: [
|
|
2448
2492
|
{
|
|
@@ -2550,11 +2594,11 @@ var agent_improvement_proposal_default = {
|
|
|
2550
2594
|
sufficient: true
|
|
2551
2595
|
},
|
|
2552
2596
|
provenance: {
|
|
2553
|
-
baselineContentHash: "sha256:
|
|
2554
|
-
candidateContentHash: "sha256:
|
|
2597
|
+
baselineContentHash: "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
|
|
2598
|
+
candidateContentHash: "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
|
|
2555
2599
|
kind: "agent-eval-loop",
|
|
2556
|
-
recordDigest: "sha256:
|
|
2557
|
-
runId: "agent-runtime-0.
|
|
2600
|
+
recordDigest: "sha256:1717efccc6e84dfdf441e6b7751493aa044efc4b45188c5c26f715c18f874cfc",
|
|
2601
|
+
runId: "agent-runtime-0.102.1-proposal-fixture",
|
|
2558
2602
|
schema: "agent-candidate-experiment"
|
|
2559
2603
|
}
|
|
2560
2604
|
},
|
|
@@ -2580,7 +2624,7 @@ var agent_improvement_proposal_default = {
|
|
|
2580
2624
|
],
|
|
2581
2625
|
kind: "agent-improvement-proposal",
|
|
2582
2626
|
proposedAt: "2026-07-10T01:00:00.000Z",
|
|
2583
|
-
runId: "agent-runtime-0.
|
|
2627
|
+
runId: "agent-runtime-0.102.1-proposal-fixture"
|
|
2584
2628
|
};
|
|
2585
2629
|
|
|
2586
2630
|
// src/testing/index.ts
|