@tangle-network/agent-runtime 0.101.0 → 0.101.1
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/README.md +1 -1
- package/dist/agent.js +4 -3
- package/dist/agent.js.map +1 -1
- package/dist/chunk-2VZYRB55.js +834 -0
- package/dist/chunk-2VZYRB55.js.map +1 -0
- package/dist/{chunk-Y3SRWZMP.js → chunk-AYU35OTU.js} +2 -2
- package/dist/chunk-DI677IPX.js +200 -0
- package/dist/chunk-DI677IPX.js.map +1 -0
- package/dist/{chunk-HZDEXTSL.js → chunk-IKGCKPDX.js} +2 -833
- package/dist/chunk-IKGCKPDX.js.map +1 -0
- package/dist/{chunk-WYC2XJF2.js → chunk-KSBUSEUA.js} +2 -2
- package/dist/{chunk-UQ6PNNXM.js → chunk-KVJQV342.js} +5 -3
- package/dist/{chunk-UQ6PNNXM.js.map → chunk-KVJQV342.js.map} +1 -1
- package/dist/{chunk-FXF2OL34.js → chunk-MAONWP4R.js} +2 -2
- package/dist/{chunk-SGQ4YIQW.js → chunk-N2CEE5Q3.js} +3 -3
- package/dist/{chunk-VOPHC4LB.js → chunk-RJPQLUDA.js} +5 -187
- package/dist/chunk-RJPQLUDA.js.map +1 -0
- package/dist/{chunk-LV6WCT43.js → chunk-TA4RBJLE.js} +3 -3
- package/dist/index.js +9 -7
- package/dist/index.js.map +1 -1
- package/dist/intelligence.js +8 -5
- package/dist/intelligence.js.map +1 -1
- package/dist/knowledge.js +6 -4
- package/dist/loop-runner-bin.js +5 -4
- package/dist/loops.js +4 -3
- package/dist/mcp/bin.js +4 -3
- package/dist/mcp/bin.js.map +1 -1
- package/dist/mcp/index.js +6 -5
- package/dist/mcp/index.js.map +1 -1
- package/dist/testing.d.ts +6 -0
- package/dist/testing.js +2596 -0
- package/dist/testing.js.map +1 -0
- package/package.json +9 -2
- package/dist/chunk-HZDEXTSL.js.map +0 -1
- package/dist/chunk-VOPHC4LB.js.map +0 -1
- /package/dist/{chunk-Y3SRWZMP.js.map → chunk-AYU35OTU.js.map} +0 -0
- /package/dist/{chunk-WYC2XJF2.js.map → chunk-KSBUSEUA.js.map} +0 -0
- /package/dist/{chunk-FXF2OL34.js.map → chunk-MAONWP4R.js.map} +0 -0
- /package/dist/{chunk-SGQ4YIQW.js.map → chunk-N2CEE5Q3.js.map} +0 -0
- /package/dist/{chunk-LV6WCT43.js.map → chunk-TA4RBJLE.js.map} +0 -0
package/dist/testing.js
ADDED
|
@@ -0,0 +1,2596 @@
|
|
|
1
|
+
import {
|
|
2
|
+
verifyAgentImprovementProposal
|
|
3
|
+
} from "./chunk-RJPQLUDA.js";
|
|
4
|
+
import "./chunk-HGSHPVJ6.js";
|
|
5
|
+
import "./chunk-IKGCKPDX.js";
|
|
6
|
+
import "./chunk-IMSNJSXH.js";
|
|
7
|
+
import "./chunk-3MDZX7YU.js";
|
|
8
|
+
import "./chunk-FD2MBMOH.js";
|
|
9
|
+
import "./chunk-M22PL4GH.js";
|
|
10
|
+
import "./chunk-YEJR7IXO.js";
|
|
11
|
+
|
|
12
|
+
// src/testing/fixtures/agent-improvement-proposal.json
|
|
13
|
+
var agent_improvement_proposal_default = {
|
|
14
|
+
changedSurfaces: ["prompt"],
|
|
15
|
+
digest: "sha256:aa47ef7cce1668303f55c3454a5a762c75a78be6cf907fa3f4f10dea20fd9fc6",
|
|
16
|
+
evaluation: {
|
|
17
|
+
decision: {
|
|
18
|
+
contributingChecks: [
|
|
19
|
+
{
|
|
20
|
+
name: "paired-significance",
|
|
21
|
+
passed: true
|
|
22
|
+
},
|
|
23
|
+
{
|
|
24
|
+
name: "statistical-power",
|
|
25
|
+
passed: true
|
|
26
|
+
},
|
|
27
|
+
{
|
|
28
|
+
name: "all-runs-completed",
|
|
29
|
+
passed: true
|
|
30
|
+
},
|
|
31
|
+
{
|
|
32
|
+
name: "candidate-task-pass",
|
|
33
|
+
passed: true
|
|
34
|
+
},
|
|
35
|
+
{
|
|
36
|
+
name: "critical-dimensions",
|
|
37
|
+
passed: true
|
|
38
|
+
},
|
|
39
|
+
{
|
|
40
|
+
name: "budget",
|
|
41
|
+
passed: true
|
|
42
|
+
}
|
|
43
|
+
],
|
|
44
|
+
outcome: "ship",
|
|
45
|
+
reasons: ["all measured checks passed"]
|
|
46
|
+
},
|
|
47
|
+
diff: '--- baseline/profile (sha256:e53e1c8f9632bcb5db9033e32f33a90b9bd99abecef0bb52ff9069f07509e2f9)\n+++ candidate/profile (sha256:8b1e2f0f7b832958381c29baebe4a961b151af97a0ce9d611a15ad0741aeaa75)\n{\n "baseline": {\n "name": "candidate",\n "prompt": {\n "instructions": [\n "Inspect the repository, implement the fix, and run tests."\n ]\n },\n "model": {\n "default": "provider/model",\n "reasoningEffort": "high"\n },\n "harness": "codex",\n "resources": {\n "failOnError": true\n }\n },\n "candidate": {\n "name": "candidate",\n "prompt": {\n "systemPrompt": "Return the exact measured answer.",\n "instructions": [\n "Inspect the repository, implement the fix, and run tests."\n ]\n },\n "model": {\n "default": "provider/model",\n "reasoningEffort": "high"\n },\n "harness": "codex",\n "resources": {\n "failOnError": true\n }\n }\n}',
|
|
48
|
+
evaluation: {
|
|
49
|
+
durationMs: 300,
|
|
50
|
+
executionCostUsd: 0,
|
|
51
|
+
executionDurationMs: 300,
|
|
52
|
+
generationsExplored: 0,
|
|
53
|
+
searchCostUsd: 0,
|
|
54
|
+
searchDurationMs: 0,
|
|
55
|
+
totalCostUsd: 0
|
|
56
|
+
},
|
|
57
|
+
experiment: {
|
|
58
|
+
baseline: {
|
|
59
|
+
code: {
|
|
60
|
+
kind: "disabled"
|
|
61
|
+
},
|
|
62
|
+
digest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
63
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
64
|
+
execution: {
|
|
65
|
+
cwd: {
|
|
66
|
+
path: ".",
|
|
67
|
+
workspace: "task"
|
|
68
|
+
},
|
|
69
|
+
environment: {
|
|
70
|
+
kind: "evaluator-task-container"
|
|
71
|
+
},
|
|
72
|
+
harness: "codex",
|
|
73
|
+
harnessVersion: "1.2.3",
|
|
74
|
+
instructionDelivery: {
|
|
75
|
+
kind: "stdin-utf8"
|
|
76
|
+
},
|
|
77
|
+
isolation: {
|
|
78
|
+
candidateSecrets: "disabled",
|
|
79
|
+
network: "disabled",
|
|
80
|
+
remoteIntegrations: "disabled"
|
|
81
|
+
},
|
|
82
|
+
launch: {
|
|
83
|
+
executable: "codex",
|
|
84
|
+
kind: "container-command"
|
|
85
|
+
}
|
|
86
|
+
},
|
|
87
|
+
kind: "agent-candidate-bundle",
|
|
88
|
+
memory: {
|
|
89
|
+
mode: "disabled"
|
|
90
|
+
},
|
|
91
|
+
profile: {
|
|
92
|
+
harness: "codex",
|
|
93
|
+
model: {
|
|
94
|
+
default: "provider/model",
|
|
95
|
+
reasoningEffort: "high"
|
|
96
|
+
},
|
|
97
|
+
name: "candidate",
|
|
98
|
+
prompt: {
|
|
99
|
+
instructions: ["Inspect the repository, implement the fix, and run tests."]
|
|
100
|
+
},
|
|
101
|
+
resources: {
|
|
102
|
+
failOnError: true
|
|
103
|
+
}
|
|
104
|
+
}
|
|
105
|
+
},
|
|
106
|
+
benchmark: {
|
|
107
|
+
suite: {
|
|
108
|
+
digest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
109
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
110
|
+
kind: "agent-candidate-benchmark-suite",
|
|
111
|
+
reps: 3,
|
|
112
|
+
seeds: [101, 102, 103],
|
|
113
|
+
taskDigests: ["sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277"]
|
|
114
|
+
},
|
|
115
|
+
tasks: [
|
|
116
|
+
{
|
|
117
|
+
attempt: {
|
|
118
|
+
maxAttempts: 1,
|
|
119
|
+
retryPolicy: "none"
|
|
120
|
+
},
|
|
121
|
+
benchmark: {
|
|
122
|
+
name: "repository-disjoint-smoke",
|
|
123
|
+
splitDigest: "sha256:dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd",
|
|
124
|
+
version: "1"
|
|
125
|
+
},
|
|
126
|
+
digest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
127
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
128
|
+
evaluatorTaskContainer: {
|
|
129
|
+
image: "ghcr.io/example/task",
|
|
130
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
131
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
132
|
+
platform: {
|
|
133
|
+
architecture: "amd64",
|
|
134
|
+
os: "linux"
|
|
135
|
+
},
|
|
136
|
+
source: "evaluator-task-container"
|
|
137
|
+
},
|
|
138
|
+
grader: {
|
|
139
|
+
artifact: {
|
|
140
|
+
byteLength: 25,
|
|
141
|
+
locator: {
|
|
142
|
+
bucket: "candidate-test-artifacts",
|
|
143
|
+
key: "grader/9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad",
|
|
144
|
+
kind: "s3"
|
|
145
|
+
},
|
|
146
|
+
sha256: "sha256:9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad"
|
|
147
|
+
},
|
|
148
|
+
format: "tangle-grader",
|
|
149
|
+
name: "fixture-executable-grader",
|
|
150
|
+
version: "1.0.0"
|
|
151
|
+
},
|
|
152
|
+
instruction: "Fix the failing behavior without changing the public API.",
|
|
153
|
+
kind: "agent-candidate-benchmark-task",
|
|
154
|
+
limits: {
|
|
155
|
+
maxCostUsd: 5,
|
|
156
|
+
maxInputTokens: 1e5,
|
|
157
|
+
maxModelCalls: 50,
|
|
158
|
+
maxOutputTokens: 5e4,
|
|
159
|
+
maxSteps: 100,
|
|
160
|
+
timeoutMs: 6e4
|
|
161
|
+
},
|
|
162
|
+
model: {
|
|
163
|
+
model: "model-snapshot",
|
|
164
|
+
provider: "provider",
|
|
165
|
+
reasoningEffort: "high",
|
|
166
|
+
requested: "provider/model",
|
|
167
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
168
|
+
},
|
|
169
|
+
outcome: {
|
|
170
|
+
kind: "output",
|
|
171
|
+
maxBytes: 1024,
|
|
172
|
+
mediaType: "text/plain"
|
|
173
|
+
},
|
|
174
|
+
scenario: {
|
|
175
|
+
id: "owner-repo-1",
|
|
176
|
+
kind: "coding",
|
|
177
|
+
scenarioDigest: "sha256:8888888888888888888888888888888888888888888888888888888888888888"
|
|
178
|
+
},
|
|
179
|
+
workspace: {
|
|
180
|
+
archive: {
|
|
181
|
+
byteLength: 17,
|
|
182
|
+
content: "ZW1wdHk6b3V0cHV0LXRhc2s=",
|
|
183
|
+
encoding: "base64",
|
|
184
|
+
sha256: "sha256:332dd9c74beab8a177396a4510dab46a50ca2074b203b10694e4eaa3071e2ef0"
|
|
185
|
+
},
|
|
186
|
+
digest: "sha256:3e9fdad46f14ce5b7c78a93e4fee0960483ae9d1cda21f0c390cdbad40bdac02",
|
|
187
|
+
kind: "agent-candidate-workspace-snapshot",
|
|
188
|
+
manifest: {
|
|
189
|
+
byteLength: 56,
|
|
190
|
+
content: "eyJmaWxlcyI6W10sImtpbmQiOiJhZ2VudC1jYW5kaWRhdGUtd29ya3NwYWNlLW1hbmlmZXN0In0=",
|
|
191
|
+
encoding: "base64",
|
|
192
|
+
sha256: "sha256:3e9fdad46f14ce5b7c78a93e4fee0960483ae9d1cda21f0c390cdbad40bdac02"
|
|
193
|
+
},
|
|
194
|
+
material: {
|
|
195
|
+
files: [],
|
|
196
|
+
kind: "agent-candidate-workspace-manifest"
|
|
197
|
+
}
|
|
198
|
+
}
|
|
199
|
+
}
|
|
200
|
+
]
|
|
201
|
+
},
|
|
202
|
+
candidate: {
|
|
203
|
+
code: {
|
|
204
|
+
kind: "disabled"
|
|
205
|
+
},
|
|
206
|
+
digest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
207
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
208
|
+
execution: {
|
|
209
|
+
cwd: {
|
|
210
|
+
path: ".",
|
|
211
|
+
workspace: "task"
|
|
212
|
+
},
|
|
213
|
+
environment: {
|
|
214
|
+
kind: "evaluator-task-container"
|
|
215
|
+
},
|
|
216
|
+
harness: "codex",
|
|
217
|
+
harnessVersion: "1.2.3",
|
|
218
|
+
instructionDelivery: {
|
|
219
|
+
kind: "stdin-utf8"
|
|
220
|
+
},
|
|
221
|
+
isolation: {
|
|
222
|
+
candidateSecrets: "disabled",
|
|
223
|
+
network: "disabled",
|
|
224
|
+
remoteIntegrations: "disabled"
|
|
225
|
+
},
|
|
226
|
+
launch: {
|
|
227
|
+
executable: "codex",
|
|
228
|
+
kind: "container-command"
|
|
229
|
+
}
|
|
230
|
+
},
|
|
231
|
+
kind: "agent-candidate-bundle",
|
|
232
|
+
memory: {
|
|
233
|
+
mode: "disabled"
|
|
234
|
+
},
|
|
235
|
+
profile: {
|
|
236
|
+
harness: "codex",
|
|
237
|
+
model: {
|
|
238
|
+
default: "provider/model",
|
|
239
|
+
reasoningEffort: "high"
|
|
240
|
+
},
|
|
241
|
+
name: "candidate",
|
|
242
|
+
prompt: {
|
|
243
|
+
instructions: ["Inspect the repository, implement the fix, and run tests."],
|
|
244
|
+
systemPrompt: "Return the exact measured answer."
|
|
245
|
+
},
|
|
246
|
+
resources: {
|
|
247
|
+
failOnError: true
|
|
248
|
+
}
|
|
249
|
+
}
|
|
250
|
+
},
|
|
251
|
+
candidateLineage: {
|
|
252
|
+
source: "human"
|
|
253
|
+
},
|
|
254
|
+
digest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
|
|
255
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
256
|
+
kind: "agent-candidate-experiment",
|
|
257
|
+
policy: {
|
|
258
|
+
bootstrapSeed: 1337,
|
|
259
|
+
budgetUsd: 1,
|
|
260
|
+
confidenceLevel: 0.95,
|
|
261
|
+
criticalDimensions: ["quality"],
|
|
262
|
+
deltaThreshold: 0,
|
|
263
|
+
minProductiveRuns: 3,
|
|
264
|
+
regressionTolerance: 0.05,
|
|
265
|
+
resamples: 500
|
|
266
|
+
}
|
|
267
|
+
},
|
|
268
|
+
kind: "agent-improvement-measured-comparison",
|
|
269
|
+
measurements: [
|
|
270
|
+
{
|
|
271
|
+
baseline: {
|
|
272
|
+
digest: "sha256:4514f8b5f875371d69b88add160843806e84f854898a351bdce03646c3750495",
|
|
273
|
+
kind: "agent-candidate-execution-evidence",
|
|
274
|
+
materializationReceipt: {
|
|
275
|
+
benchmark: {
|
|
276
|
+
suite: {
|
|
277
|
+
digest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
278
|
+
material: {
|
|
279
|
+
byteLength: 198,
|
|
280
|
+
content: "eyJkaWdlc3RBbGdvcml0aG0iOiJyZmM4Nzg1LXNoYTI1NiIsImtpbmQiOiJhZ2VudC1jYW5kaWRhdGUtYmVuY2htYXJrLXN1aXRlIiwicmVwcyI6Mywic2VlZHMiOlsxMDEsMTAyLDEwM10sInRhc2tEaWdlc3RzIjpbInNoYTI1Njo2YWE3MTgzMzFiNmRhMzEwZGNhYjZkZjJlMzM5N2NiNzcwODQwZTU1NWE4MmUwNjg5NTc3MTU3Yjg5YjRlMjc3Il19",
|
|
281
|
+
encoding: "base64",
|
|
282
|
+
sha256: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5"
|
|
283
|
+
}
|
|
284
|
+
},
|
|
285
|
+
task: {
|
|
286
|
+
digest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
287
|
+
material: {
|
|
288
|
+
byteLength: 2096,
|
|
289
|
+
content: "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",
|
|
290
|
+
encoding: "base64",
|
|
291
|
+
sha256: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277"
|
|
292
|
+
}
|
|
293
|
+
}
|
|
294
|
+
},
|
|
295
|
+
bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
296
|
+
codeKind: "disabled",
|
|
297
|
+
container: {
|
|
298
|
+
image: "ghcr.io/example/task",
|
|
299
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
300
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
301
|
+
platform: {
|
|
302
|
+
architecture: "amd64",
|
|
303
|
+
os: "linux"
|
|
304
|
+
},
|
|
305
|
+
source: "evaluator-task-container"
|
|
306
|
+
},
|
|
307
|
+
digest: "sha256:707a959a5ee03b48f523417ec3fca971565986bbe46ec0d44412e1c9873819af",
|
|
308
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
309
|
+
executionPlan: {
|
|
310
|
+
artifact: {
|
|
311
|
+
byteLength: 1967,
|
|
312
|
+
content: "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",
|
|
313
|
+
encoding: "base64",
|
|
314
|
+
sha256: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5"
|
|
315
|
+
},
|
|
316
|
+
digest: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5",
|
|
317
|
+
kind: "agent-candidate-execution-plan",
|
|
318
|
+
material: {
|
|
319
|
+
codeKind: "disabled",
|
|
320
|
+
container: {
|
|
321
|
+
image: "ghcr.io/example/task",
|
|
322
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
323
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
324
|
+
platform: {
|
|
325
|
+
architecture: "amd64",
|
|
326
|
+
os: "linux"
|
|
327
|
+
},
|
|
328
|
+
source: "evaluator-task-container"
|
|
329
|
+
},
|
|
330
|
+
executionId: "experiment-baseline-0-0",
|
|
331
|
+
harness: "codex",
|
|
332
|
+
harnessVersion: "1.2.3",
|
|
333
|
+
instructionDelivery: {
|
|
334
|
+
kind: "stdin-utf8"
|
|
335
|
+
},
|
|
336
|
+
kind: "agent-candidate-execution-plan-material",
|
|
337
|
+
launch: {
|
|
338
|
+
args: [],
|
|
339
|
+
cwd: {
|
|
340
|
+
path: ".",
|
|
341
|
+
workspace: "task"
|
|
342
|
+
},
|
|
343
|
+
env: {},
|
|
344
|
+
executable: "codex"
|
|
345
|
+
},
|
|
346
|
+
limits: {
|
|
347
|
+
maxCostUsd: 5,
|
|
348
|
+
maxInputTokens: 1e5,
|
|
349
|
+
maxModelCalls: 50,
|
|
350
|
+
maxOutputTokens: 5e4,
|
|
351
|
+
maxSteps: 100,
|
|
352
|
+
timeoutMs: 6e4
|
|
353
|
+
},
|
|
354
|
+
memory: {
|
|
355
|
+
mode: "disabled"
|
|
356
|
+
},
|
|
357
|
+
model: {
|
|
358
|
+
access: {
|
|
359
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
360
|
+
kind: "evaluator-mediated",
|
|
361
|
+
network: {
|
|
362
|
+
domains: ["router.tangle.tools"],
|
|
363
|
+
mode: "gateway-only"
|
|
364
|
+
}
|
|
365
|
+
},
|
|
366
|
+
policy: "single",
|
|
367
|
+
resolved: {
|
|
368
|
+
model: "model-snapshot",
|
|
369
|
+
provider: "provider",
|
|
370
|
+
reasoningEffort: "high",
|
|
371
|
+
requested: "provider/model",
|
|
372
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
373
|
+
},
|
|
374
|
+
routes: [
|
|
375
|
+
{
|
|
376
|
+
kind: "primary",
|
|
377
|
+
requested: "provider/model"
|
|
378
|
+
}
|
|
379
|
+
]
|
|
380
|
+
},
|
|
381
|
+
network: {
|
|
382
|
+
mode: "disabled"
|
|
383
|
+
},
|
|
384
|
+
profile: {
|
|
385
|
+
mountPaths: ["AGENTS.md"],
|
|
386
|
+
planDigest: "sha256:af65bd67cf53561cd7bfac4e8c913ef18e36c0c2fe20a0bca1df55e59b21fab5",
|
|
387
|
+
targetWorkspace: "task"
|
|
388
|
+
},
|
|
389
|
+
runCell: {
|
|
390
|
+
arm: "baseline",
|
|
391
|
+
attempt: 1,
|
|
392
|
+
bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
393
|
+
digest: "sha256:c170a7cb938c3e5b7550a264f6b6b08a13ea262fe80a2e24b020a415c1dad595",
|
|
394
|
+
experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
|
|
395
|
+
kind: "agent-candidate-run-cell",
|
|
396
|
+
repetition: 0,
|
|
397
|
+
seed: 101,
|
|
398
|
+
suiteDigest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
399
|
+
taskDigest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
400
|
+
taskIndex: 0
|
|
401
|
+
},
|
|
402
|
+
workspaces: {
|
|
403
|
+
taskRoot: "/workspace/task"
|
|
404
|
+
}
|
|
405
|
+
}
|
|
406
|
+
},
|
|
407
|
+
harness: "codex",
|
|
408
|
+
harnessVersion: "1.2.3",
|
|
409
|
+
kind: "agent-candidate-materialization",
|
|
410
|
+
profileActivation: {
|
|
411
|
+
digest: "sha256:273b700e4080e7e6cc4bd58a755466d18ce323eaaa195bb4202fea456422bb66",
|
|
412
|
+
files: [
|
|
413
|
+
{
|
|
414
|
+
content: "Inspect the repository, implement the fix, and run tests.\n",
|
|
415
|
+
mode: 420,
|
|
416
|
+
path: "AGENTS.md"
|
|
417
|
+
}
|
|
418
|
+
],
|
|
419
|
+
kind: "agent-candidate-profile-activation",
|
|
420
|
+
profilePlan: {
|
|
421
|
+
artifact: {
|
|
422
|
+
byteLength: 287,
|
|
423
|
+
content: "eyJlbnYiOnt9LCJmaWxlcyI6W3siY29udGVudFNoYTI1NiI6InNoYTI1NjozOWFkYmI5YjdmNTcxZjBmZDU4NmU3Nzk1MDIzZDI1OTA5YWRiZTk1ODZiYjIxZWUxMzRkM2Q3MjQ4YmYxNTk5IiwibW9kZSI6NDIwLCJyZWxQYXRoIjoiQUdFTlRTLm1kIn1dLCJmbGFncyI6W10sImhhcm5lc3MiOiJjb2RleCIsInNvdXJjZVByb2ZpbGVEaWdlc3QiOiJzaGEyNTY6ZTUzZTFjOGY5NjMyYmNiNWRiOTAzM2UzMmYzM2E5MGI5YmQ5OWFiZWNlZjBiYjUyZmY5MDY5ZjA3NTA5ZTJmOSIsInVuc3VwcG9ydGVkIjpbXX0=",
|
|
424
|
+
encoding: "base64",
|
|
425
|
+
sha256: "sha256:af65bd67cf53561cd7bfac4e8c913ef18e36c0c2fe20a0bca1df55e59b21fab5"
|
|
426
|
+
},
|
|
427
|
+
digest: "sha256:af65bd67cf53561cd7bfac4e8c913ef18e36c0c2fe20a0bca1df55e59b21fab5",
|
|
428
|
+
kind: "agent-profile-workspace-plan",
|
|
429
|
+
material: {
|
|
430
|
+
env: {},
|
|
431
|
+
files: [
|
|
432
|
+
{
|
|
433
|
+
contentSha256: "sha256:39adbb9b7f571f0fd586e7795023d25909adbe9586bb21ee134d3d7248bf1599",
|
|
434
|
+
mode: 420,
|
|
435
|
+
relPath: "AGENTS.md"
|
|
436
|
+
}
|
|
437
|
+
],
|
|
438
|
+
flags: [],
|
|
439
|
+
harness: "codex",
|
|
440
|
+
sourceProfileDigest: "sha256:e53e1c8f9632bcb5db9033e32f33a90b9bd99abecef0bb52ff9069f07509e2f9",
|
|
441
|
+
unsupported: []
|
|
442
|
+
}
|
|
443
|
+
}
|
|
444
|
+
},
|
|
445
|
+
resolvedModel: {
|
|
446
|
+
model: "model-snapshot",
|
|
447
|
+
provider: "provider",
|
|
448
|
+
reasoningEffort: "high",
|
|
449
|
+
requested: "provider/model",
|
|
450
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
451
|
+
}
|
|
452
|
+
},
|
|
453
|
+
receipt: {
|
|
454
|
+
benchmarkResult: {
|
|
455
|
+
artifact: {
|
|
456
|
+
byteLength: 1122,
|
|
457
|
+
locator: {
|
|
458
|
+
bucket: "candidate-test-artifacts",
|
|
459
|
+
key: "benchmark-result/ec815a7d6556928ba69e6f08cf38fed9ddd64c9cff4ba1ccf471f8e7a0aa63f4",
|
|
460
|
+
kind: "s3"
|
|
461
|
+
},
|
|
462
|
+
sha256: "sha256:ec815a7d6556928ba69e6f08cf38fed9ddd64c9cff4ba1ccf471f8e7a0aa63f4"
|
|
463
|
+
},
|
|
464
|
+
digest: "sha256:ec815a7d6556928ba69e6f08cf38fed9ddd64c9cff4ba1ccf471f8e7a0aa63f4",
|
|
465
|
+
kind: "agent-candidate-benchmark-result",
|
|
466
|
+
material: {
|
|
467
|
+
dimensions: [
|
|
468
|
+
{
|
|
469
|
+
name: "quality",
|
|
470
|
+
score: 0
|
|
471
|
+
}
|
|
472
|
+
],
|
|
473
|
+
evidence: {
|
|
474
|
+
byteLength: 11,
|
|
475
|
+
locator: {
|
|
476
|
+
bucket: "candidate-test-artifacts",
|
|
477
|
+
key: "grader-evidence/628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b",
|
|
478
|
+
kind: "s3"
|
|
479
|
+
},
|
|
480
|
+
sha256: "sha256:628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b"
|
|
481
|
+
},
|
|
482
|
+
executionPlanDigest: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5",
|
|
483
|
+
grader: {
|
|
484
|
+
artifact: {
|
|
485
|
+
byteLength: 25,
|
|
486
|
+
locator: {
|
|
487
|
+
bucket: "candidate-test-artifacts",
|
|
488
|
+
key: "grader/9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad",
|
|
489
|
+
kind: "s3"
|
|
490
|
+
},
|
|
491
|
+
sha256: "sha256:9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad"
|
|
492
|
+
},
|
|
493
|
+
format: "tangle-grader",
|
|
494
|
+
name: "fixture-executable-grader",
|
|
495
|
+
version: "1.0.0"
|
|
496
|
+
},
|
|
497
|
+
grading: {
|
|
498
|
+
timing: {
|
|
499
|
+
durationMs: 0,
|
|
500
|
+
endedAtMs: 17836416e5,
|
|
501
|
+
startedAtMs: 17836416e5
|
|
502
|
+
},
|
|
503
|
+
usage: {
|
|
504
|
+
cachedInputTokens: 0,
|
|
505
|
+
costUsdNanos: 0,
|
|
506
|
+
inputTokens: 0,
|
|
507
|
+
modelCalls: 0,
|
|
508
|
+
outputTokens: 0,
|
|
509
|
+
reasoningTokens: 0
|
|
510
|
+
}
|
|
511
|
+
},
|
|
512
|
+
kind: "agent-candidate-benchmark-result-material",
|
|
513
|
+
passed: false,
|
|
514
|
+
score: 0,
|
|
515
|
+
taskOutcomeDigest: "sha256:3fc660e792f3883048a3e04dfa9b361d5b88f0afd3141fe7858cf9b53952e914"
|
|
516
|
+
}
|
|
517
|
+
},
|
|
518
|
+
bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
519
|
+
digest: "sha256:6b565143b4115b64a682bbc0fe56d6ef44302947df1c1a6d562d45533b346a7e",
|
|
520
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
521
|
+
executionPlanDigest: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5",
|
|
522
|
+
executorCapture: {
|
|
523
|
+
byteLength: 477,
|
|
524
|
+
locator: {
|
|
525
|
+
bucket: "candidate-test-artifacts",
|
|
526
|
+
key: "executor-capture/72d7612e1df0fbb53498c79ba7cf4464f141aa6e031b013ce87f887d8f16a07a",
|
|
527
|
+
kind: "s3"
|
|
528
|
+
},
|
|
529
|
+
sha256: "sha256:72d7612e1df0fbb53498c79ba7cf4464f141aa6e031b013ce87f887d8f16a07a"
|
|
530
|
+
},
|
|
531
|
+
kind: "agent-candidate-run",
|
|
532
|
+
materializationReceiptDigest: "sha256:707a959a5ee03b48f523417ec3fca971565986bbe46ec0d44412e1c9873819af",
|
|
533
|
+
memory: {
|
|
534
|
+
mode: "disabled"
|
|
535
|
+
},
|
|
536
|
+
modelSettlement: {
|
|
537
|
+
artifact: {
|
|
538
|
+
byteLength: 615,
|
|
539
|
+
locator: {
|
|
540
|
+
bucket: "candidate-test-artifacts",
|
|
541
|
+
key: "model-settlement/e923d98a8c5620f72b41a7c4b75024149f1ebe14128c14a576a1de5a5ec688bd",
|
|
542
|
+
kind: "s3"
|
|
543
|
+
},
|
|
544
|
+
sha256: "sha256:e923d98a8c5620f72b41a7c4b75024149f1ebe14128c14a576a1de5a5ec688bd"
|
|
545
|
+
},
|
|
546
|
+
digest: "sha256:e923d98a8c5620f72b41a7c4b75024149f1ebe14128c14a576a1de5a5ec688bd",
|
|
547
|
+
kind: "agent-candidate-model-settlement",
|
|
548
|
+
material: {
|
|
549
|
+
calls: [],
|
|
550
|
+
closed: true,
|
|
551
|
+
executionPlanDigest: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5",
|
|
552
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
553
|
+
kind: "agent-candidate-model-settlement-material",
|
|
554
|
+
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
555
|
+
resolved: {
|
|
556
|
+
model: "model-snapshot",
|
|
557
|
+
provider: "provider",
|
|
558
|
+
reasoningEffort: "high",
|
|
559
|
+
requested: "provider/model",
|
|
560
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
561
|
+
},
|
|
562
|
+
usage: {
|
|
563
|
+
cachedInputTokens: 0,
|
|
564
|
+
costUsdNanos: 0,
|
|
565
|
+
inputTokens: 0,
|
|
566
|
+
modelCalls: 0,
|
|
567
|
+
outputTokens: 0,
|
|
568
|
+
reasoningTokens: 0
|
|
569
|
+
}
|
|
570
|
+
}
|
|
571
|
+
},
|
|
572
|
+
runCellDigest: "sha256:c170a7cb938c3e5b7550a264f6b6b08a13ea262fe80a2e24b020a415c1dad595",
|
|
573
|
+
taskOutcome: {
|
|
574
|
+
artifact: {
|
|
575
|
+
byteLength: 478,
|
|
576
|
+
locator: {
|
|
577
|
+
bucket: "candidate-test-artifacts",
|
|
578
|
+
key: "task-outcome/3fc660e792f3883048a3e04dfa9b361d5b88f0afd3141fe7858cf9b53952e914",
|
|
579
|
+
kind: "s3"
|
|
580
|
+
},
|
|
581
|
+
sha256: "sha256:3fc660e792f3883048a3e04dfa9b361d5b88f0afd3141fe7858cf9b53952e914"
|
|
582
|
+
},
|
|
583
|
+
digest: "sha256:3fc660e792f3883048a3e04dfa9b361d5b88f0afd3141fe7858cf9b53952e914",
|
|
584
|
+
kind: "agent-candidate-task-outcome",
|
|
585
|
+
material: {
|
|
586
|
+
executionPlanDigest: "sha256:827ecfb1615809335ef3221364d051c427c8942fe871cd743617dd05ee705ad5",
|
|
587
|
+
kind: "agent-candidate-task-outcome-material",
|
|
588
|
+
outcome: {
|
|
589
|
+
artifact: {
|
|
590
|
+
byteLength: 4,
|
|
591
|
+
locator: {
|
|
592
|
+
bucket: "candidate-test-artifacts",
|
|
593
|
+
key: "task-output/481ba4019c9d2710c3386537382592c093ef02bf5b056c30237b3d92b0e19a1d",
|
|
594
|
+
kind: "s3"
|
|
595
|
+
},
|
|
596
|
+
sha256: "sha256:481ba4019c9d2710c3386537382592c093ef02bf5b056c30237b3d92b0e19a1d"
|
|
597
|
+
},
|
|
598
|
+
kind: "output",
|
|
599
|
+
spec: {
|
|
600
|
+
maxBytes: 1024,
|
|
601
|
+
mediaType: "text/plain"
|
|
602
|
+
}
|
|
603
|
+
}
|
|
604
|
+
}
|
|
605
|
+
},
|
|
606
|
+
termination: {
|
|
607
|
+
exitCode: 0,
|
|
608
|
+
kind: "exit"
|
|
609
|
+
},
|
|
610
|
+
timing: {
|
|
611
|
+
durationMs: 50,
|
|
612
|
+
endedAtMs: 1050,
|
|
613
|
+
startedAtMs: 1e3
|
|
614
|
+
},
|
|
615
|
+
trace: {
|
|
616
|
+
artifact: {
|
|
617
|
+
byteLength: 748,
|
|
618
|
+
locator: {
|
|
619
|
+
bucket: "candidate-test-artifacts",
|
|
620
|
+
key: "trace/3bfe9931c331dda75f96eac7761181cdcbc1302318c1ffdebab4c53fb275fc55",
|
|
621
|
+
kind: "s3"
|
|
622
|
+
},
|
|
623
|
+
sha256: "sha256:3bfe9931c331dda75f96eac7761181cdcbc1302318c1ffdebab4c53fb275fc55"
|
|
624
|
+
},
|
|
625
|
+
eventCount: 1,
|
|
626
|
+
modelCallCount: 0
|
|
627
|
+
}
|
|
628
|
+
}
|
|
629
|
+
},
|
|
630
|
+
candidate: {
|
|
631
|
+
digest: "sha256:2579dfae2c22ac30917c688f0ae31736e8c1cc81979e877c3139c80ca88f0064",
|
|
632
|
+
kind: "agent-candidate-execution-evidence",
|
|
633
|
+
materializationReceipt: {
|
|
634
|
+
benchmark: {
|
|
635
|
+
suite: {
|
|
636
|
+
digest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
637
|
+
material: {
|
|
638
|
+
byteLength: 198,
|
|
639
|
+
content: "eyJkaWdlc3RBbGdvcml0aG0iOiJyZmM4Nzg1LXNoYTI1NiIsImtpbmQiOiJhZ2VudC1jYW5kaWRhdGUtYmVuY2htYXJrLXN1aXRlIiwicmVwcyI6Mywic2VlZHMiOlsxMDEsMTAyLDEwM10sInRhc2tEaWdlc3RzIjpbInNoYTI1Njo2YWE3MTgzMzFiNmRhMzEwZGNhYjZkZjJlMzM5N2NiNzcwODQwZTU1NWE4MmUwNjg5NTc3MTU3Yjg5YjRlMjc3Il19",
|
|
640
|
+
encoding: "base64",
|
|
641
|
+
sha256: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5"
|
|
642
|
+
}
|
|
643
|
+
},
|
|
644
|
+
task: {
|
|
645
|
+
digest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
646
|
+
material: {
|
|
647
|
+
byteLength: 2096,
|
|
648
|
+
content: "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",
|
|
649
|
+
encoding: "base64",
|
|
650
|
+
sha256: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277"
|
|
651
|
+
}
|
|
652
|
+
}
|
|
653
|
+
},
|
|
654
|
+
bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
655
|
+
codeKind: "disabled",
|
|
656
|
+
container: {
|
|
657
|
+
image: "ghcr.io/example/task",
|
|
658
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
659
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
660
|
+
platform: {
|
|
661
|
+
architecture: "amd64",
|
|
662
|
+
os: "linux"
|
|
663
|
+
},
|
|
664
|
+
source: "evaluator-task-container"
|
|
665
|
+
},
|
|
666
|
+
digest: "sha256:aee4c8842fa9a4c926a63ad2ad6f1ae370096b01987947d47568811b873e952f",
|
|
667
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
668
|
+
executionPlan: {
|
|
669
|
+
artifact: {
|
|
670
|
+
byteLength: 1969,
|
|
671
|
+
content: "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",
|
|
672
|
+
encoding: "base64",
|
|
673
|
+
sha256: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715"
|
|
674
|
+
},
|
|
675
|
+
digest: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715",
|
|
676
|
+
kind: "agent-candidate-execution-plan",
|
|
677
|
+
material: {
|
|
678
|
+
codeKind: "disabled",
|
|
679
|
+
container: {
|
|
680
|
+
image: "ghcr.io/example/task",
|
|
681
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
682
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
683
|
+
platform: {
|
|
684
|
+
architecture: "amd64",
|
|
685
|
+
os: "linux"
|
|
686
|
+
},
|
|
687
|
+
source: "evaluator-task-container"
|
|
688
|
+
},
|
|
689
|
+
executionId: "experiment-candidate-0-0",
|
|
690
|
+
harness: "codex",
|
|
691
|
+
harnessVersion: "1.2.3",
|
|
692
|
+
instructionDelivery: {
|
|
693
|
+
kind: "stdin-utf8"
|
|
694
|
+
},
|
|
695
|
+
kind: "agent-candidate-execution-plan-material",
|
|
696
|
+
launch: {
|
|
697
|
+
args: [],
|
|
698
|
+
cwd: {
|
|
699
|
+
path: ".",
|
|
700
|
+
workspace: "task"
|
|
701
|
+
},
|
|
702
|
+
env: {},
|
|
703
|
+
executable: "codex"
|
|
704
|
+
},
|
|
705
|
+
limits: {
|
|
706
|
+
maxCostUsd: 5,
|
|
707
|
+
maxInputTokens: 1e5,
|
|
708
|
+
maxModelCalls: 50,
|
|
709
|
+
maxOutputTokens: 5e4,
|
|
710
|
+
maxSteps: 100,
|
|
711
|
+
timeoutMs: 6e4
|
|
712
|
+
},
|
|
713
|
+
memory: {
|
|
714
|
+
mode: "disabled"
|
|
715
|
+
},
|
|
716
|
+
model: {
|
|
717
|
+
access: {
|
|
718
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
719
|
+
kind: "evaluator-mediated",
|
|
720
|
+
network: {
|
|
721
|
+
domains: ["router.tangle.tools"],
|
|
722
|
+
mode: "gateway-only"
|
|
723
|
+
}
|
|
724
|
+
},
|
|
725
|
+
policy: "single",
|
|
726
|
+
resolved: {
|
|
727
|
+
model: "model-snapshot",
|
|
728
|
+
provider: "provider",
|
|
729
|
+
reasoningEffort: "high",
|
|
730
|
+
requested: "provider/model",
|
|
731
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
732
|
+
},
|
|
733
|
+
routes: [
|
|
734
|
+
{
|
|
735
|
+
kind: "primary",
|
|
736
|
+
requested: "provider/model"
|
|
737
|
+
}
|
|
738
|
+
]
|
|
739
|
+
},
|
|
740
|
+
network: {
|
|
741
|
+
mode: "disabled"
|
|
742
|
+
},
|
|
743
|
+
profile: {
|
|
744
|
+
mountPaths: ["AGENTS.md"],
|
|
745
|
+
planDigest: "sha256:4b4214d1bae911df6dda3a5d8585c65df2f0b2380126eb40c0cbd46a4a2fba5b",
|
|
746
|
+
targetWorkspace: "task"
|
|
747
|
+
},
|
|
748
|
+
runCell: {
|
|
749
|
+
arm: "candidate",
|
|
750
|
+
attempt: 1,
|
|
751
|
+
bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
752
|
+
digest: "sha256:9774b5757485d7b4147d43caba5126f8f7ae7fef1a2d176982b592db034db605",
|
|
753
|
+
experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
|
|
754
|
+
kind: "agent-candidate-run-cell",
|
|
755
|
+
repetition: 0,
|
|
756
|
+
seed: 101,
|
|
757
|
+
suiteDigest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
758
|
+
taskDigest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
759
|
+
taskIndex: 0
|
|
760
|
+
},
|
|
761
|
+
workspaces: {
|
|
762
|
+
taskRoot: "/workspace/task"
|
|
763
|
+
}
|
|
764
|
+
}
|
|
765
|
+
},
|
|
766
|
+
harness: "codex",
|
|
767
|
+
harnessVersion: "1.2.3",
|
|
768
|
+
kind: "agent-candidate-materialization",
|
|
769
|
+
profileActivation: {
|
|
770
|
+
digest: "sha256:3103f8282be70a843eada63410c41d9eb5ac7b824c758eed6c2f8610de169f45",
|
|
771
|
+
files: [
|
|
772
|
+
{
|
|
773
|
+
content: "Inspect the repository, implement the fix, and run tests.\n",
|
|
774
|
+
mode: 420,
|
|
775
|
+
path: "AGENTS.md"
|
|
776
|
+
}
|
|
777
|
+
],
|
|
778
|
+
kind: "agent-candidate-profile-activation",
|
|
779
|
+
profilePlan: {
|
|
780
|
+
artifact: {
|
|
781
|
+
byteLength: 364,
|
|
782
|
+
content: "eyJlbnYiOnt9LCJmaWxlcyI6W3siY29udGVudFNoYTI1NiI6InNoYTI1NjozOWFkYmI5YjdmNTcxZjBmZDU4NmU3Nzk1MDIzZDI1OTA5YWRiZTk1ODZiYjIxZWUxMzRkM2Q3MjQ4YmYxNTk5IiwibW9kZSI6NDIwLCJyZWxQYXRoIjoiQUdFTlRTLm1kIn1dLCJmbGFncyI6W10sImhhcm5lc3MiOiJjb2RleCIsInNvdXJjZVByb2ZpbGVEaWdlc3QiOiJzaGEyNTY6OGIxZTJmMGY3YjgzMjk1ODM4MWMyOWJhZWJlNGE5NjFiMTUxYWY5N2EwY2U5ZDYxMWExNWFkMDc0MWFlYWE3NSIsInN5c3RlbVByb21wdCI6eyJraW5kIjoicHVibGljIiwidmFsdWUiOiJSZXR1cm4gdGhlIGV4YWN0IG1lYXN1cmVkIGFuc3dlci4ifSwidW5zdXBwb3J0ZWQiOltdfQ==",
|
|
783
|
+
encoding: "base64",
|
|
784
|
+
sha256: "sha256:4b4214d1bae911df6dda3a5d8585c65df2f0b2380126eb40c0cbd46a4a2fba5b"
|
|
785
|
+
},
|
|
786
|
+
digest: "sha256:4b4214d1bae911df6dda3a5d8585c65df2f0b2380126eb40c0cbd46a4a2fba5b",
|
|
787
|
+
kind: "agent-profile-workspace-plan",
|
|
788
|
+
material: {
|
|
789
|
+
env: {},
|
|
790
|
+
files: [
|
|
791
|
+
{
|
|
792
|
+
contentSha256: "sha256:39adbb9b7f571f0fd586e7795023d25909adbe9586bb21ee134d3d7248bf1599",
|
|
793
|
+
mode: 420,
|
|
794
|
+
relPath: "AGENTS.md"
|
|
795
|
+
}
|
|
796
|
+
],
|
|
797
|
+
flags: [],
|
|
798
|
+
harness: "codex",
|
|
799
|
+
sourceProfileDigest: "sha256:8b1e2f0f7b832958381c29baebe4a961b151af97a0ce9d611a15ad0741aeaa75",
|
|
800
|
+
systemPrompt: {
|
|
801
|
+
kind: "public",
|
|
802
|
+
value: "Return the exact measured answer."
|
|
803
|
+
},
|
|
804
|
+
unsupported: []
|
|
805
|
+
}
|
|
806
|
+
}
|
|
807
|
+
},
|
|
808
|
+
resolvedModel: {
|
|
809
|
+
model: "model-snapshot",
|
|
810
|
+
provider: "provider",
|
|
811
|
+
reasoningEffort: "high",
|
|
812
|
+
requested: "provider/model",
|
|
813
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
814
|
+
}
|
|
815
|
+
},
|
|
816
|
+
receipt: {
|
|
817
|
+
benchmarkResult: {
|
|
818
|
+
artifact: {
|
|
819
|
+
byteLength: 1121,
|
|
820
|
+
locator: {
|
|
821
|
+
bucket: "candidate-test-artifacts",
|
|
822
|
+
key: "benchmark-result/ca685e9d916e6eef4155c93421d4a11569106ec3115e65df20b9d73324cbeccd",
|
|
823
|
+
kind: "s3"
|
|
824
|
+
},
|
|
825
|
+
sha256: "sha256:ca685e9d916e6eef4155c93421d4a11569106ec3115e65df20b9d73324cbeccd"
|
|
826
|
+
},
|
|
827
|
+
digest: "sha256:ca685e9d916e6eef4155c93421d4a11569106ec3115e65df20b9d73324cbeccd",
|
|
828
|
+
kind: "agent-candidate-benchmark-result",
|
|
829
|
+
material: {
|
|
830
|
+
dimensions: [
|
|
831
|
+
{
|
|
832
|
+
name: "quality",
|
|
833
|
+
score: 1
|
|
834
|
+
}
|
|
835
|
+
],
|
|
836
|
+
evidence: {
|
|
837
|
+
byteLength: 11,
|
|
838
|
+
locator: {
|
|
839
|
+
bucket: "candidate-test-artifacts",
|
|
840
|
+
key: "grader-evidence/9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d",
|
|
841
|
+
kind: "s3"
|
|
842
|
+
},
|
|
843
|
+
sha256: "sha256:9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d"
|
|
844
|
+
},
|
|
845
|
+
executionPlanDigest: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715",
|
|
846
|
+
grader: {
|
|
847
|
+
artifact: {
|
|
848
|
+
byteLength: 25,
|
|
849
|
+
locator: {
|
|
850
|
+
bucket: "candidate-test-artifacts",
|
|
851
|
+
key: "grader/9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad",
|
|
852
|
+
kind: "s3"
|
|
853
|
+
},
|
|
854
|
+
sha256: "sha256:9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad"
|
|
855
|
+
},
|
|
856
|
+
format: "tangle-grader",
|
|
857
|
+
name: "fixture-executable-grader",
|
|
858
|
+
version: "1.0.0"
|
|
859
|
+
},
|
|
860
|
+
grading: {
|
|
861
|
+
timing: {
|
|
862
|
+
durationMs: 0,
|
|
863
|
+
endedAtMs: 17836416e5,
|
|
864
|
+
startedAtMs: 17836416e5
|
|
865
|
+
},
|
|
866
|
+
usage: {
|
|
867
|
+
cachedInputTokens: 0,
|
|
868
|
+
costUsdNanos: 0,
|
|
869
|
+
inputTokens: 0,
|
|
870
|
+
modelCalls: 0,
|
|
871
|
+
outputTokens: 0,
|
|
872
|
+
reasoningTokens: 0
|
|
873
|
+
}
|
|
874
|
+
},
|
|
875
|
+
kind: "agent-candidate-benchmark-result-material",
|
|
876
|
+
passed: true,
|
|
877
|
+
score: 1,
|
|
878
|
+
taskOutcomeDigest: "sha256:de4d75f7614ad314a31d7e3afc730af7f012bcf59b18059f5fa40cb287a12bde"
|
|
879
|
+
}
|
|
880
|
+
},
|
|
881
|
+
bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
882
|
+
digest: "sha256:60c4d05ae65274f073a39b00e3245a4b953fbfeca393b67a327fe4ed9f0114f3",
|
|
883
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
884
|
+
executionPlanDigest: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715",
|
|
885
|
+
executorCapture: {
|
|
886
|
+
byteLength: 477,
|
|
887
|
+
locator: {
|
|
888
|
+
bucket: "candidate-test-artifacts",
|
|
889
|
+
key: "executor-capture/d4b84f1358debca607a88fbf3879c91ee2709935101010d8cf361b86451b6c68",
|
|
890
|
+
kind: "s3"
|
|
891
|
+
},
|
|
892
|
+
sha256: "sha256:d4b84f1358debca607a88fbf3879c91ee2709935101010d8cf361b86451b6c68"
|
|
893
|
+
},
|
|
894
|
+
kind: "agent-candidate-run",
|
|
895
|
+
materializationReceiptDigest: "sha256:aee4c8842fa9a4c926a63ad2ad6f1ae370096b01987947d47568811b873e952f",
|
|
896
|
+
memory: {
|
|
897
|
+
mode: "disabled"
|
|
898
|
+
},
|
|
899
|
+
modelSettlement: {
|
|
900
|
+
artifact: {
|
|
901
|
+
byteLength: 615,
|
|
902
|
+
locator: {
|
|
903
|
+
bucket: "candidate-test-artifacts",
|
|
904
|
+
key: "model-settlement/5e58f7eacab44aac8bd7ea381ef68d300f5dbed0cd25c292cb1a4d4e187b30fe",
|
|
905
|
+
kind: "s3"
|
|
906
|
+
},
|
|
907
|
+
sha256: "sha256:5e58f7eacab44aac8bd7ea381ef68d300f5dbed0cd25c292cb1a4d4e187b30fe"
|
|
908
|
+
},
|
|
909
|
+
digest: "sha256:5e58f7eacab44aac8bd7ea381ef68d300f5dbed0cd25c292cb1a4d4e187b30fe",
|
|
910
|
+
kind: "agent-candidate-model-settlement",
|
|
911
|
+
material: {
|
|
912
|
+
calls: [],
|
|
913
|
+
closed: true,
|
|
914
|
+
executionPlanDigest: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715",
|
|
915
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
916
|
+
kind: "agent-candidate-model-settlement-material",
|
|
917
|
+
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
918
|
+
resolved: {
|
|
919
|
+
model: "model-snapshot",
|
|
920
|
+
provider: "provider",
|
|
921
|
+
reasoningEffort: "high",
|
|
922
|
+
requested: "provider/model",
|
|
923
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
924
|
+
},
|
|
925
|
+
usage: {
|
|
926
|
+
cachedInputTokens: 0,
|
|
927
|
+
costUsdNanos: 0,
|
|
928
|
+
inputTokens: 0,
|
|
929
|
+
modelCalls: 0,
|
|
930
|
+
outputTokens: 0,
|
|
931
|
+
reasoningTokens: 0
|
|
932
|
+
}
|
|
933
|
+
}
|
|
934
|
+
},
|
|
935
|
+
runCellDigest: "sha256:9774b5757485d7b4147d43caba5126f8f7ae7fef1a2d176982b592db034db605",
|
|
936
|
+
taskOutcome: {
|
|
937
|
+
artifact: {
|
|
938
|
+
byteLength: 478,
|
|
939
|
+
locator: {
|
|
940
|
+
bucket: "candidate-test-artifacts",
|
|
941
|
+
key: "task-outcome/de4d75f7614ad314a31d7e3afc730af7f012bcf59b18059f5fa40cb287a12bde",
|
|
942
|
+
kind: "s3"
|
|
943
|
+
},
|
|
944
|
+
sha256: "sha256:de4d75f7614ad314a31d7e3afc730af7f012bcf59b18059f5fa40cb287a12bde"
|
|
945
|
+
},
|
|
946
|
+
digest: "sha256:de4d75f7614ad314a31d7e3afc730af7f012bcf59b18059f5fa40cb287a12bde",
|
|
947
|
+
kind: "agent-candidate-task-outcome",
|
|
948
|
+
material: {
|
|
949
|
+
executionPlanDigest: "sha256:ce44a1f51191d8d14b0eaaffce4797f43f7100d7590d334daaf896acb9a6c715",
|
|
950
|
+
kind: "agent-candidate-task-outcome-material",
|
|
951
|
+
outcome: {
|
|
952
|
+
artifact: {
|
|
953
|
+
byteLength: 6,
|
|
954
|
+
locator: {
|
|
955
|
+
bucket: "candidate-test-artifacts",
|
|
956
|
+
key: "task-output/eda15ce4834ac303532bc6973df5ff8a5deb75d7dfceb9fc2cdf1bb450a01cf5",
|
|
957
|
+
kind: "s3"
|
|
958
|
+
},
|
|
959
|
+
sha256: "sha256:eda15ce4834ac303532bc6973df5ff8a5deb75d7dfceb9fc2cdf1bb450a01cf5"
|
|
960
|
+
},
|
|
961
|
+
kind: "output",
|
|
962
|
+
spec: {
|
|
963
|
+
maxBytes: 1024,
|
|
964
|
+
mediaType: "text/plain"
|
|
965
|
+
}
|
|
966
|
+
}
|
|
967
|
+
}
|
|
968
|
+
},
|
|
969
|
+
termination: {
|
|
970
|
+
exitCode: 0,
|
|
971
|
+
kind: "exit"
|
|
972
|
+
},
|
|
973
|
+
timing: {
|
|
974
|
+
durationMs: 50,
|
|
975
|
+
endedAtMs: 1050,
|
|
976
|
+
startedAtMs: 1e3
|
|
977
|
+
},
|
|
978
|
+
trace: {
|
|
979
|
+
artifact: {
|
|
980
|
+
byteLength: 750,
|
|
981
|
+
locator: {
|
|
982
|
+
bucket: "candidate-test-artifacts",
|
|
983
|
+
key: "trace/8b368b3a19e808c43984c75e39301b3b69591d072453286e19960f85f0f988a6",
|
|
984
|
+
kind: "s3"
|
|
985
|
+
},
|
|
986
|
+
sha256: "sha256:8b368b3a19e808c43984c75e39301b3b69591d072453286e19960f85f0f988a6"
|
|
987
|
+
},
|
|
988
|
+
eventCount: 1,
|
|
989
|
+
modelCallCount: 0
|
|
990
|
+
}
|
|
991
|
+
}
|
|
992
|
+
}
|
|
993
|
+
},
|
|
994
|
+
{
|
|
995
|
+
baseline: {
|
|
996
|
+
digest: "sha256:23630e0e9893a8bc51f3632a4ea9b8d20828dad45bb52ad8aa70057b6f4ce388",
|
|
997
|
+
kind: "agent-candidate-execution-evidence",
|
|
998
|
+
materializationReceipt: {
|
|
999
|
+
benchmark: {
|
|
1000
|
+
suite: {
|
|
1001
|
+
digest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
1002
|
+
material: {
|
|
1003
|
+
byteLength: 198,
|
|
1004
|
+
content: "eyJkaWdlc3RBbGdvcml0aG0iOiJyZmM4Nzg1LXNoYTI1NiIsImtpbmQiOiJhZ2VudC1jYW5kaWRhdGUtYmVuY2htYXJrLXN1aXRlIiwicmVwcyI6Mywic2VlZHMiOlsxMDEsMTAyLDEwM10sInRhc2tEaWdlc3RzIjpbInNoYTI1Njo2YWE3MTgzMzFiNmRhMzEwZGNhYjZkZjJlMzM5N2NiNzcwODQwZTU1NWE4MmUwNjg5NTc3MTU3Yjg5YjRlMjc3Il19",
|
|
1005
|
+
encoding: "base64",
|
|
1006
|
+
sha256: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5"
|
|
1007
|
+
}
|
|
1008
|
+
},
|
|
1009
|
+
task: {
|
|
1010
|
+
digest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
1011
|
+
material: {
|
|
1012
|
+
byteLength: 2096,
|
|
1013
|
+
content: "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",
|
|
1014
|
+
encoding: "base64",
|
|
1015
|
+
sha256: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277"
|
|
1016
|
+
}
|
|
1017
|
+
}
|
|
1018
|
+
},
|
|
1019
|
+
bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
1020
|
+
codeKind: "disabled",
|
|
1021
|
+
container: {
|
|
1022
|
+
image: "ghcr.io/example/task",
|
|
1023
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
1024
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
1025
|
+
platform: {
|
|
1026
|
+
architecture: "amd64",
|
|
1027
|
+
os: "linux"
|
|
1028
|
+
},
|
|
1029
|
+
source: "evaluator-task-container"
|
|
1030
|
+
},
|
|
1031
|
+
digest: "sha256:8483cca8159d0fcbcc7ebe4bee689cdcf8e5872194335db4cf41301fc61be396",
|
|
1032
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
1033
|
+
executionPlan: {
|
|
1034
|
+
artifact: {
|
|
1035
|
+
byteLength: 1967,
|
|
1036
|
+
content: "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",
|
|
1037
|
+
encoding: "base64",
|
|
1038
|
+
sha256: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca"
|
|
1039
|
+
},
|
|
1040
|
+
digest: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca",
|
|
1041
|
+
kind: "agent-candidate-execution-plan",
|
|
1042
|
+
material: {
|
|
1043
|
+
codeKind: "disabled",
|
|
1044
|
+
container: {
|
|
1045
|
+
image: "ghcr.io/example/task",
|
|
1046
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
1047
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
1048
|
+
platform: {
|
|
1049
|
+
architecture: "amd64",
|
|
1050
|
+
os: "linux"
|
|
1051
|
+
},
|
|
1052
|
+
source: "evaluator-task-container"
|
|
1053
|
+
},
|
|
1054
|
+
executionId: "experiment-baseline-0-1",
|
|
1055
|
+
harness: "codex",
|
|
1056
|
+
harnessVersion: "1.2.3",
|
|
1057
|
+
instructionDelivery: {
|
|
1058
|
+
kind: "stdin-utf8"
|
|
1059
|
+
},
|
|
1060
|
+
kind: "agent-candidate-execution-plan-material",
|
|
1061
|
+
launch: {
|
|
1062
|
+
args: [],
|
|
1063
|
+
cwd: {
|
|
1064
|
+
path: ".",
|
|
1065
|
+
workspace: "task"
|
|
1066
|
+
},
|
|
1067
|
+
env: {},
|
|
1068
|
+
executable: "codex"
|
|
1069
|
+
},
|
|
1070
|
+
limits: {
|
|
1071
|
+
maxCostUsd: 5,
|
|
1072
|
+
maxInputTokens: 1e5,
|
|
1073
|
+
maxModelCalls: 50,
|
|
1074
|
+
maxOutputTokens: 5e4,
|
|
1075
|
+
maxSteps: 100,
|
|
1076
|
+
timeoutMs: 6e4
|
|
1077
|
+
},
|
|
1078
|
+
memory: {
|
|
1079
|
+
mode: "disabled"
|
|
1080
|
+
},
|
|
1081
|
+
model: {
|
|
1082
|
+
access: {
|
|
1083
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
1084
|
+
kind: "evaluator-mediated",
|
|
1085
|
+
network: {
|
|
1086
|
+
domains: ["router.tangle.tools"],
|
|
1087
|
+
mode: "gateway-only"
|
|
1088
|
+
}
|
|
1089
|
+
},
|
|
1090
|
+
policy: "single",
|
|
1091
|
+
resolved: {
|
|
1092
|
+
model: "model-snapshot",
|
|
1093
|
+
provider: "provider",
|
|
1094
|
+
reasoningEffort: "high",
|
|
1095
|
+
requested: "provider/model",
|
|
1096
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
1097
|
+
},
|
|
1098
|
+
routes: [
|
|
1099
|
+
{
|
|
1100
|
+
kind: "primary",
|
|
1101
|
+
requested: "provider/model"
|
|
1102
|
+
}
|
|
1103
|
+
]
|
|
1104
|
+
},
|
|
1105
|
+
network: {
|
|
1106
|
+
mode: "disabled"
|
|
1107
|
+
},
|
|
1108
|
+
profile: {
|
|
1109
|
+
mountPaths: ["AGENTS.md"],
|
|
1110
|
+
planDigest: "sha256:af65bd67cf53561cd7bfac4e8c913ef18e36c0c2fe20a0bca1df55e59b21fab5",
|
|
1111
|
+
targetWorkspace: "task"
|
|
1112
|
+
},
|
|
1113
|
+
runCell: {
|
|
1114
|
+
arm: "baseline",
|
|
1115
|
+
attempt: 1,
|
|
1116
|
+
bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
1117
|
+
digest: "sha256:ce44b5854c9133ba5f2c78069462c2977fed54a09eb18a0bca250902cf2718eb",
|
|
1118
|
+
experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
|
|
1119
|
+
kind: "agent-candidate-run-cell",
|
|
1120
|
+
repetition: 1,
|
|
1121
|
+
seed: 102,
|
|
1122
|
+
suiteDigest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
1123
|
+
taskDigest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
1124
|
+
taskIndex: 0
|
|
1125
|
+
},
|
|
1126
|
+
workspaces: {
|
|
1127
|
+
taskRoot: "/workspace/task"
|
|
1128
|
+
}
|
|
1129
|
+
}
|
|
1130
|
+
},
|
|
1131
|
+
harness: "codex",
|
|
1132
|
+
harnessVersion: "1.2.3",
|
|
1133
|
+
kind: "agent-candidate-materialization",
|
|
1134
|
+
profileActivation: {
|
|
1135
|
+
digest: "sha256:273b700e4080e7e6cc4bd58a755466d18ce323eaaa195bb4202fea456422bb66",
|
|
1136
|
+
files: [
|
|
1137
|
+
{
|
|
1138
|
+
content: "Inspect the repository, implement the fix, and run tests.\n",
|
|
1139
|
+
mode: 420,
|
|
1140
|
+
path: "AGENTS.md"
|
|
1141
|
+
}
|
|
1142
|
+
],
|
|
1143
|
+
kind: "agent-candidate-profile-activation",
|
|
1144
|
+
profilePlan: {
|
|
1145
|
+
artifact: {
|
|
1146
|
+
byteLength: 287,
|
|
1147
|
+
content: "eyJlbnYiOnt9LCJmaWxlcyI6W3siY29udGVudFNoYTI1NiI6InNoYTI1NjozOWFkYmI5YjdmNTcxZjBmZDU4NmU3Nzk1MDIzZDI1OTA5YWRiZTk1ODZiYjIxZWUxMzRkM2Q3MjQ4YmYxNTk5IiwibW9kZSI6NDIwLCJyZWxQYXRoIjoiQUdFTlRTLm1kIn1dLCJmbGFncyI6W10sImhhcm5lc3MiOiJjb2RleCIsInNvdXJjZVByb2ZpbGVEaWdlc3QiOiJzaGEyNTY6ZTUzZTFjOGY5NjMyYmNiNWRiOTAzM2UzMmYzM2E5MGI5YmQ5OWFiZWNlZjBiYjUyZmY5MDY5ZjA3NTA5ZTJmOSIsInVuc3VwcG9ydGVkIjpbXX0=",
|
|
1148
|
+
encoding: "base64",
|
|
1149
|
+
sha256: "sha256:af65bd67cf53561cd7bfac4e8c913ef18e36c0c2fe20a0bca1df55e59b21fab5"
|
|
1150
|
+
},
|
|
1151
|
+
digest: "sha256:af65bd67cf53561cd7bfac4e8c913ef18e36c0c2fe20a0bca1df55e59b21fab5",
|
|
1152
|
+
kind: "agent-profile-workspace-plan",
|
|
1153
|
+
material: {
|
|
1154
|
+
env: {},
|
|
1155
|
+
files: [
|
|
1156
|
+
{
|
|
1157
|
+
contentSha256: "sha256:39adbb9b7f571f0fd586e7795023d25909adbe9586bb21ee134d3d7248bf1599",
|
|
1158
|
+
mode: 420,
|
|
1159
|
+
relPath: "AGENTS.md"
|
|
1160
|
+
}
|
|
1161
|
+
],
|
|
1162
|
+
flags: [],
|
|
1163
|
+
harness: "codex",
|
|
1164
|
+
sourceProfileDigest: "sha256:e53e1c8f9632bcb5db9033e32f33a90b9bd99abecef0bb52ff9069f07509e2f9",
|
|
1165
|
+
unsupported: []
|
|
1166
|
+
}
|
|
1167
|
+
}
|
|
1168
|
+
},
|
|
1169
|
+
resolvedModel: {
|
|
1170
|
+
model: "model-snapshot",
|
|
1171
|
+
provider: "provider",
|
|
1172
|
+
reasoningEffort: "high",
|
|
1173
|
+
requested: "provider/model",
|
|
1174
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
1175
|
+
}
|
|
1176
|
+
},
|
|
1177
|
+
receipt: {
|
|
1178
|
+
benchmarkResult: {
|
|
1179
|
+
artifact: {
|
|
1180
|
+
byteLength: 1122,
|
|
1181
|
+
locator: {
|
|
1182
|
+
bucket: "candidate-test-artifacts",
|
|
1183
|
+
key: "benchmark-result/73c5061dc61b9840165883f6b4950405917399949b459e1cba5933153883f94d",
|
|
1184
|
+
kind: "s3"
|
|
1185
|
+
},
|
|
1186
|
+
sha256: "sha256:73c5061dc61b9840165883f6b4950405917399949b459e1cba5933153883f94d"
|
|
1187
|
+
},
|
|
1188
|
+
digest: "sha256:73c5061dc61b9840165883f6b4950405917399949b459e1cba5933153883f94d",
|
|
1189
|
+
kind: "agent-candidate-benchmark-result",
|
|
1190
|
+
material: {
|
|
1191
|
+
dimensions: [
|
|
1192
|
+
{
|
|
1193
|
+
name: "quality",
|
|
1194
|
+
score: 0
|
|
1195
|
+
}
|
|
1196
|
+
],
|
|
1197
|
+
evidence: {
|
|
1198
|
+
byteLength: 11,
|
|
1199
|
+
locator: {
|
|
1200
|
+
bucket: "candidate-test-artifacts",
|
|
1201
|
+
key: "grader-evidence/628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b",
|
|
1202
|
+
kind: "s3"
|
|
1203
|
+
},
|
|
1204
|
+
sha256: "sha256:628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b"
|
|
1205
|
+
},
|
|
1206
|
+
executionPlanDigest: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca",
|
|
1207
|
+
grader: {
|
|
1208
|
+
artifact: {
|
|
1209
|
+
byteLength: 25,
|
|
1210
|
+
locator: {
|
|
1211
|
+
bucket: "candidate-test-artifacts",
|
|
1212
|
+
key: "grader/9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad",
|
|
1213
|
+
kind: "s3"
|
|
1214
|
+
},
|
|
1215
|
+
sha256: "sha256:9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad"
|
|
1216
|
+
},
|
|
1217
|
+
format: "tangle-grader",
|
|
1218
|
+
name: "fixture-executable-grader",
|
|
1219
|
+
version: "1.0.0"
|
|
1220
|
+
},
|
|
1221
|
+
grading: {
|
|
1222
|
+
timing: {
|
|
1223
|
+
durationMs: 0,
|
|
1224
|
+
endedAtMs: 17836416e5,
|
|
1225
|
+
startedAtMs: 17836416e5
|
|
1226
|
+
},
|
|
1227
|
+
usage: {
|
|
1228
|
+
cachedInputTokens: 0,
|
|
1229
|
+
costUsdNanos: 0,
|
|
1230
|
+
inputTokens: 0,
|
|
1231
|
+
modelCalls: 0,
|
|
1232
|
+
outputTokens: 0,
|
|
1233
|
+
reasoningTokens: 0
|
|
1234
|
+
}
|
|
1235
|
+
},
|
|
1236
|
+
kind: "agent-candidate-benchmark-result-material",
|
|
1237
|
+
passed: false,
|
|
1238
|
+
score: 0,
|
|
1239
|
+
taskOutcomeDigest: "sha256:6531580f45e8618a7e381fe78de4e49b0d68d589702ad23f81fa27ccea872e06"
|
|
1240
|
+
}
|
|
1241
|
+
},
|
|
1242
|
+
bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
1243
|
+
digest: "sha256:1758e0ee11654db77d6c11b02ec1e777b2b7a1610ae4e363effd1dfb51a8d643",
|
|
1244
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
1245
|
+
executionPlanDigest: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca",
|
|
1246
|
+
executorCapture: {
|
|
1247
|
+
byteLength: 477,
|
|
1248
|
+
locator: {
|
|
1249
|
+
bucket: "candidate-test-artifacts",
|
|
1250
|
+
key: "executor-capture/c7e618da9214d4e3b4ce81fc70d3c6edec1fa80e6ab06369b0a3684548cfbf1f",
|
|
1251
|
+
kind: "s3"
|
|
1252
|
+
},
|
|
1253
|
+
sha256: "sha256:c7e618da9214d4e3b4ce81fc70d3c6edec1fa80e6ab06369b0a3684548cfbf1f"
|
|
1254
|
+
},
|
|
1255
|
+
kind: "agent-candidate-run",
|
|
1256
|
+
materializationReceiptDigest: "sha256:8483cca8159d0fcbcc7ebe4bee689cdcf8e5872194335db4cf41301fc61be396",
|
|
1257
|
+
memory: {
|
|
1258
|
+
mode: "disabled"
|
|
1259
|
+
},
|
|
1260
|
+
modelSettlement: {
|
|
1261
|
+
artifact: {
|
|
1262
|
+
byteLength: 615,
|
|
1263
|
+
locator: {
|
|
1264
|
+
bucket: "candidate-test-artifacts",
|
|
1265
|
+
key: "model-settlement/ef07959f28b6123ce5d2776d81d7cae1408b48038aeee70c76b308a30e26de65",
|
|
1266
|
+
kind: "s3"
|
|
1267
|
+
},
|
|
1268
|
+
sha256: "sha256:ef07959f28b6123ce5d2776d81d7cae1408b48038aeee70c76b308a30e26de65"
|
|
1269
|
+
},
|
|
1270
|
+
digest: "sha256:ef07959f28b6123ce5d2776d81d7cae1408b48038aeee70c76b308a30e26de65",
|
|
1271
|
+
kind: "agent-candidate-model-settlement",
|
|
1272
|
+
material: {
|
|
1273
|
+
calls: [],
|
|
1274
|
+
closed: true,
|
|
1275
|
+
executionPlanDigest: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca",
|
|
1276
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
1277
|
+
kind: "agent-candidate-model-settlement-material",
|
|
1278
|
+
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
1279
|
+
resolved: {
|
|
1280
|
+
model: "model-snapshot",
|
|
1281
|
+
provider: "provider",
|
|
1282
|
+
reasoningEffort: "high",
|
|
1283
|
+
requested: "provider/model",
|
|
1284
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
1285
|
+
},
|
|
1286
|
+
usage: {
|
|
1287
|
+
cachedInputTokens: 0,
|
|
1288
|
+
costUsdNanos: 0,
|
|
1289
|
+
inputTokens: 0,
|
|
1290
|
+
modelCalls: 0,
|
|
1291
|
+
outputTokens: 0,
|
|
1292
|
+
reasoningTokens: 0
|
|
1293
|
+
}
|
|
1294
|
+
}
|
|
1295
|
+
},
|
|
1296
|
+
runCellDigest: "sha256:ce44b5854c9133ba5f2c78069462c2977fed54a09eb18a0bca250902cf2718eb",
|
|
1297
|
+
taskOutcome: {
|
|
1298
|
+
artifact: {
|
|
1299
|
+
byteLength: 478,
|
|
1300
|
+
locator: {
|
|
1301
|
+
bucket: "candidate-test-artifacts",
|
|
1302
|
+
key: "task-outcome/6531580f45e8618a7e381fe78de4e49b0d68d589702ad23f81fa27ccea872e06",
|
|
1303
|
+
kind: "s3"
|
|
1304
|
+
},
|
|
1305
|
+
sha256: "sha256:6531580f45e8618a7e381fe78de4e49b0d68d589702ad23f81fa27ccea872e06"
|
|
1306
|
+
},
|
|
1307
|
+
digest: "sha256:6531580f45e8618a7e381fe78de4e49b0d68d589702ad23f81fa27ccea872e06",
|
|
1308
|
+
kind: "agent-candidate-task-outcome",
|
|
1309
|
+
material: {
|
|
1310
|
+
executionPlanDigest: "sha256:fa90746592bb3ec6f664872f3898144ece40775bef865981877039b955f6d8ca",
|
|
1311
|
+
kind: "agent-candidate-task-outcome-material",
|
|
1312
|
+
outcome: {
|
|
1313
|
+
artifact: {
|
|
1314
|
+
byteLength: 4,
|
|
1315
|
+
locator: {
|
|
1316
|
+
bucket: "candidate-test-artifacts",
|
|
1317
|
+
key: "task-output/481ba4019c9d2710c3386537382592c093ef02bf5b056c30237b3d92b0e19a1d",
|
|
1318
|
+
kind: "s3"
|
|
1319
|
+
},
|
|
1320
|
+
sha256: "sha256:481ba4019c9d2710c3386537382592c093ef02bf5b056c30237b3d92b0e19a1d"
|
|
1321
|
+
},
|
|
1322
|
+
kind: "output",
|
|
1323
|
+
spec: {
|
|
1324
|
+
maxBytes: 1024,
|
|
1325
|
+
mediaType: "text/plain"
|
|
1326
|
+
}
|
|
1327
|
+
}
|
|
1328
|
+
}
|
|
1329
|
+
},
|
|
1330
|
+
termination: {
|
|
1331
|
+
exitCode: 0,
|
|
1332
|
+
kind: "exit"
|
|
1333
|
+
},
|
|
1334
|
+
timing: {
|
|
1335
|
+
durationMs: 50,
|
|
1336
|
+
endedAtMs: 1150,
|
|
1337
|
+
startedAtMs: 1100
|
|
1338
|
+
},
|
|
1339
|
+
trace: {
|
|
1340
|
+
artifact: {
|
|
1341
|
+
byteLength: 748,
|
|
1342
|
+
locator: {
|
|
1343
|
+
bucket: "candidate-test-artifacts",
|
|
1344
|
+
key: "trace/6f94838ea9d7d02576c9b692a388eba163ccab95bc9b39fd99d30f97e34db45e",
|
|
1345
|
+
kind: "s3"
|
|
1346
|
+
},
|
|
1347
|
+
sha256: "sha256:6f94838ea9d7d02576c9b692a388eba163ccab95bc9b39fd99d30f97e34db45e"
|
|
1348
|
+
},
|
|
1349
|
+
eventCount: 1,
|
|
1350
|
+
modelCallCount: 0
|
|
1351
|
+
}
|
|
1352
|
+
}
|
|
1353
|
+
},
|
|
1354
|
+
candidate: {
|
|
1355
|
+
digest: "sha256:7ca0ac188c3520be751d9154b5911ccb72ac9025a8abb7516027ee5c4e0aee78",
|
|
1356
|
+
kind: "agent-candidate-execution-evidence",
|
|
1357
|
+
materializationReceipt: {
|
|
1358
|
+
benchmark: {
|
|
1359
|
+
suite: {
|
|
1360
|
+
digest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
1361
|
+
material: {
|
|
1362
|
+
byteLength: 198,
|
|
1363
|
+
content: "eyJkaWdlc3RBbGdvcml0aG0iOiJyZmM4Nzg1LXNoYTI1NiIsImtpbmQiOiJhZ2VudC1jYW5kaWRhdGUtYmVuY2htYXJrLXN1aXRlIiwicmVwcyI6Mywic2VlZHMiOlsxMDEsMTAyLDEwM10sInRhc2tEaWdlc3RzIjpbInNoYTI1Njo2YWE3MTgzMzFiNmRhMzEwZGNhYjZkZjJlMzM5N2NiNzcwODQwZTU1NWE4MmUwNjg5NTc3MTU3Yjg5YjRlMjc3Il19",
|
|
1364
|
+
encoding: "base64",
|
|
1365
|
+
sha256: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5"
|
|
1366
|
+
}
|
|
1367
|
+
},
|
|
1368
|
+
task: {
|
|
1369
|
+
digest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
1370
|
+
material: {
|
|
1371
|
+
byteLength: 2096,
|
|
1372
|
+
content: "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",
|
|
1373
|
+
encoding: "base64",
|
|
1374
|
+
sha256: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277"
|
|
1375
|
+
}
|
|
1376
|
+
}
|
|
1377
|
+
},
|
|
1378
|
+
bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
1379
|
+
codeKind: "disabled",
|
|
1380
|
+
container: {
|
|
1381
|
+
image: "ghcr.io/example/task",
|
|
1382
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
1383
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
1384
|
+
platform: {
|
|
1385
|
+
architecture: "amd64",
|
|
1386
|
+
os: "linux"
|
|
1387
|
+
},
|
|
1388
|
+
source: "evaluator-task-container"
|
|
1389
|
+
},
|
|
1390
|
+
digest: "sha256:7d002279e2baef8149e264789cffb919024e4290c4a1e3793823a8930c7a94a1",
|
|
1391
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
1392
|
+
executionPlan: {
|
|
1393
|
+
artifact: {
|
|
1394
|
+
byteLength: 1969,
|
|
1395
|
+
content: "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",
|
|
1396
|
+
encoding: "base64",
|
|
1397
|
+
sha256: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e"
|
|
1398
|
+
},
|
|
1399
|
+
digest: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e",
|
|
1400
|
+
kind: "agent-candidate-execution-plan",
|
|
1401
|
+
material: {
|
|
1402
|
+
codeKind: "disabled",
|
|
1403
|
+
container: {
|
|
1404
|
+
image: "ghcr.io/example/task",
|
|
1405
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
1406
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
1407
|
+
platform: {
|
|
1408
|
+
architecture: "amd64",
|
|
1409
|
+
os: "linux"
|
|
1410
|
+
},
|
|
1411
|
+
source: "evaluator-task-container"
|
|
1412
|
+
},
|
|
1413
|
+
executionId: "experiment-candidate-0-1",
|
|
1414
|
+
harness: "codex",
|
|
1415
|
+
harnessVersion: "1.2.3",
|
|
1416
|
+
instructionDelivery: {
|
|
1417
|
+
kind: "stdin-utf8"
|
|
1418
|
+
},
|
|
1419
|
+
kind: "agent-candidate-execution-plan-material",
|
|
1420
|
+
launch: {
|
|
1421
|
+
args: [],
|
|
1422
|
+
cwd: {
|
|
1423
|
+
path: ".",
|
|
1424
|
+
workspace: "task"
|
|
1425
|
+
},
|
|
1426
|
+
env: {},
|
|
1427
|
+
executable: "codex"
|
|
1428
|
+
},
|
|
1429
|
+
limits: {
|
|
1430
|
+
maxCostUsd: 5,
|
|
1431
|
+
maxInputTokens: 1e5,
|
|
1432
|
+
maxModelCalls: 50,
|
|
1433
|
+
maxOutputTokens: 5e4,
|
|
1434
|
+
maxSteps: 100,
|
|
1435
|
+
timeoutMs: 6e4
|
|
1436
|
+
},
|
|
1437
|
+
memory: {
|
|
1438
|
+
mode: "disabled"
|
|
1439
|
+
},
|
|
1440
|
+
model: {
|
|
1441
|
+
access: {
|
|
1442
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
1443
|
+
kind: "evaluator-mediated",
|
|
1444
|
+
network: {
|
|
1445
|
+
domains: ["router.tangle.tools"],
|
|
1446
|
+
mode: "gateway-only"
|
|
1447
|
+
}
|
|
1448
|
+
},
|
|
1449
|
+
policy: "single",
|
|
1450
|
+
resolved: {
|
|
1451
|
+
model: "model-snapshot",
|
|
1452
|
+
provider: "provider",
|
|
1453
|
+
reasoningEffort: "high",
|
|
1454
|
+
requested: "provider/model",
|
|
1455
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
1456
|
+
},
|
|
1457
|
+
routes: [
|
|
1458
|
+
{
|
|
1459
|
+
kind: "primary",
|
|
1460
|
+
requested: "provider/model"
|
|
1461
|
+
}
|
|
1462
|
+
]
|
|
1463
|
+
},
|
|
1464
|
+
network: {
|
|
1465
|
+
mode: "disabled"
|
|
1466
|
+
},
|
|
1467
|
+
profile: {
|
|
1468
|
+
mountPaths: ["AGENTS.md"],
|
|
1469
|
+
planDigest: "sha256:4b4214d1bae911df6dda3a5d8585c65df2f0b2380126eb40c0cbd46a4a2fba5b",
|
|
1470
|
+
targetWorkspace: "task"
|
|
1471
|
+
},
|
|
1472
|
+
runCell: {
|
|
1473
|
+
arm: "candidate",
|
|
1474
|
+
attempt: 1,
|
|
1475
|
+
bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
1476
|
+
digest: "sha256:1033e245dd0fbb12ef169f86149fcf93e90f2a5a76b05c0f05c26a165fcaa15c",
|
|
1477
|
+
experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
|
|
1478
|
+
kind: "agent-candidate-run-cell",
|
|
1479
|
+
repetition: 1,
|
|
1480
|
+
seed: 102,
|
|
1481
|
+
suiteDigest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
1482
|
+
taskDigest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
1483
|
+
taskIndex: 0
|
|
1484
|
+
},
|
|
1485
|
+
workspaces: {
|
|
1486
|
+
taskRoot: "/workspace/task"
|
|
1487
|
+
}
|
|
1488
|
+
}
|
|
1489
|
+
},
|
|
1490
|
+
harness: "codex",
|
|
1491
|
+
harnessVersion: "1.2.3",
|
|
1492
|
+
kind: "agent-candidate-materialization",
|
|
1493
|
+
profileActivation: {
|
|
1494
|
+
digest: "sha256:3103f8282be70a843eada63410c41d9eb5ac7b824c758eed6c2f8610de169f45",
|
|
1495
|
+
files: [
|
|
1496
|
+
{
|
|
1497
|
+
content: "Inspect the repository, implement the fix, and run tests.\n",
|
|
1498
|
+
mode: 420,
|
|
1499
|
+
path: "AGENTS.md"
|
|
1500
|
+
}
|
|
1501
|
+
],
|
|
1502
|
+
kind: "agent-candidate-profile-activation",
|
|
1503
|
+
profilePlan: {
|
|
1504
|
+
artifact: {
|
|
1505
|
+
byteLength: 364,
|
|
1506
|
+
content: "eyJlbnYiOnt9LCJmaWxlcyI6W3siY29udGVudFNoYTI1NiI6InNoYTI1NjozOWFkYmI5YjdmNTcxZjBmZDU4NmU3Nzk1MDIzZDI1OTA5YWRiZTk1ODZiYjIxZWUxMzRkM2Q3MjQ4YmYxNTk5IiwibW9kZSI6NDIwLCJyZWxQYXRoIjoiQUdFTlRTLm1kIn1dLCJmbGFncyI6W10sImhhcm5lc3MiOiJjb2RleCIsInNvdXJjZVByb2ZpbGVEaWdlc3QiOiJzaGEyNTY6OGIxZTJmMGY3YjgzMjk1ODM4MWMyOWJhZWJlNGE5NjFiMTUxYWY5N2EwY2U5ZDYxMWExNWFkMDc0MWFlYWE3NSIsInN5c3RlbVByb21wdCI6eyJraW5kIjoicHVibGljIiwidmFsdWUiOiJSZXR1cm4gdGhlIGV4YWN0IG1lYXN1cmVkIGFuc3dlci4ifSwidW5zdXBwb3J0ZWQiOltdfQ==",
|
|
1507
|
+
encoding: "base64",
|
|
1508
|
+
sha256: "sha256:4b4214d1bae911df6dda3a5d8585c65df2f0b2380126eb40c0cbd46a4a2fba5b"
|
|
1509
|
+
},
|
|
1510
|
+
digest: "sha256:4b4214d1bae911df6dda3a5d8585c65df2f0b2380126eb40c0cbd46a4a2fba5b",
|
|
1511
|
+
kind: "agent-profile-workspace-plan",
|
|
1512
|
+
material: {
|
|
1513
|
+
env: {},
|
|
1514
|
+
files: [
|
|
1515
|
+
{
|
|
1516
|
+
contentSha256: "sha256:39adbb9b7f571f0fd586e7795023d25909adbe9586bb21ee134d3d7248bf1599",
|
|
1517
|
+
mode: 420,
|
|
1518
|
+
relPath: "AGENTS.md"
|
|
1519
|
+
}
|
|
1520
|
+
],
|
|
1521
|
+
flags: [],
|
|
1522
|
+
harness: "codex",
|
|
1523
|
+
sourceProfileDigest: "sha256:8b1e2f0f7b832958381c29baebe4a961b151af97a0ce9d611a15ad0741aeaa75",
|
|
1524
|
+
systemPrompt: {
|
|
1525
|
+
kind: "public",
|
|
1526
|
+
value: "Return the exact measured answer."
|
|
1527
|
+
},
|
|
1528
|
+
unsupported: []
|
|
1529
|
+
}
|
|
1530
|
+
}
|
|
1531
|
+
},
|
|
1532
|
+
resolvedModel: {
|
|
1533
|
+
model: "model-snapshot",
|
|
1534
|
+
provider: "provider",
|
|
1535
|
+
reasoningEffort: "high",
|
|
1536
|
+
requested: "provider/model",
|
|
1537
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
1538
|
+
}
|
|
1539
|
+
},
|
|
1540
|
+
receipt: {
|
|
1541
|
+
benchmarkResult: {
|
|
1542
|
+
artifact: {
|
|
1543
|
+
byteLength: 1121,
|
|
1544
|
+
locator: {
|
|
1545
|
+
bucket: "candidate-test-artifacts",
|
|
1546
|
+
key: "benchmark-result/de40c4387aab2c749b768a55f4569348ae55ee882485356a65b5509bf6f00620",
|
|
1547
|
+
kind: "s3"
|
|
1548
|
+
},
|
|
1549
|
+
sha256: "sha256:de40c4387aab2c749b768a55f4569348ae55ee882485356a65b5509bf6f00620"
|
|
1550
|
+
},
|
|
1551
|
+
digest: "sha256:de40c4387aab2c749b768a55f4569348ae55ee882485356a65b5509bf6f00620",
|
|
1552
|
+
kind: "agent-candidate-benchmark-result",
|
|
1553
|
+
material: {
|
|
1554
|
+
dimensions: [
|
|
1555
|
+
{
|
|
1556
|
+
name: "quality",
|
|
1557
|
+
score: 1
|
|
1558
|
+
}
|
|
1559
|
+
],
|
|
1560
|
+
evidence: {
|
|
1561
|
+
byteLength: 11,
|
|
1562
|
+
locator: {
|
|
1563
|
+
bucket: "candidate-test-artifacts",
|
|
1564
|
+
key: "grader-evidence/9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d",
|
|
1565
|
+
kind: "s3"
|
|
1566
|
+
},
|
|
1567
|
+
sha256: "sha256:9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d"
|
|
1568
|
+
},
|
|
1569
|
+
executionPlanDigest: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e",
|
|
1570
|
+
grader: {
|
|
1571
|
+
artifact: {
|
|
1572
|
+
byteLength: 25,
|
|
1573
|
+
locator: {
|
|
1574
|
+
bucket: "candidate-test-artifacts",
|
|
1575
|
+
key: "grader/9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad",
|
|
1576
|
+
kind: "s3"
|
|
1577
|
+
},
|
|
1578
|
+
sha256: "sha256:9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad"
|
|
1579
|
+
},
|
|
1580
|
+
format: "tangle-grader",
|
|
1581
|
+
name: "fixture-executable-grader",
|
|
1582
|
+
version: "1.0.0"
|
|
1583
|
+
},
|
|
1584
|
+
grading: {
|
|
1585
|
+
timing: {
|
|
1586
|
+
durationMs: 0,
|
|
1587
|
+
endedAtMs: 17836416e5,
|
|
1588
|
+
startedAtMs: 17836416e5
|
|
1589
|
+
},
|
|
1590
|
+
usage: {
|
|
1591
|
+
cachedInputTokens: 0,
|
|
1592
|
+
costUsdNanos: 0,
|
|
1593
|
+
inputTokens: 0,
|
|
1594
|
+
modelCalls: 0,
|
|
1595
|
+
outputTokens: 0,
|
|
1596
|
+
reasoningTokens: 0
|
|
1597
|
+
}
|
|
1598
|
+
},
|
|
1599
|
+
kind: "agent-candidate-benchmark-result-material",
|
|
1600
|
+
passed: true,
|
|
1601
|
+
score: 1,
|
|
1602
|
+
taskOutcomeDigest: "sha256:71e7ac55968898115c4b3e0a8e71f02eaf6c5d4b46a67806f1bde01efc96b777"
|
|
1603
|
+
}
|
|
1604
|
+
},
|
|
1605
|
+
bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
1606
|
+
digest: "sha256:1ab7c0b04a606512d0cbadc08858d7e127122d3ccc8a4c22cf450e37600663a0",
|
|
1607
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
1608
|
+
executionPlanDigest: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e",
|
|
1609
|
+
executorCapture: {
|
|
1610
|
+
byteLength: 477,
|
|
1611
|
+
locator: {
|
|
1612
|
+
bucket: "candidate-test-artifacts",
|
|
1613
|
+
key: "executor-capture/7750feebcefe19391bdb10cc84100db9941cf738a4e26921a387ac3a2b5094a3",
|
|
1614
|
+
kind: "s3"
|
|
1615
|
+
},
|
|
1616
|
+
sha256: "sha256:7750feebcefe19391bdb10cc84100db9941cf738a4e26921a387ac3a2b5094a3"
|
|
1617
|
+
},
|
|
1618
|
+
kind: "agent-candidate-run",
|
|
1619
|
+
materializationReceiptDigest: "sha256:7d002279e2baef8149e264789cffb919024e4290c4a1e3793823a8930c7a94a1",
|
|
1620
|
+
memory: {
|
|
1621
|
+
mode: "disabled"
|
|
1622
|
+
},
|
|
1623
|
+
modelSettlement: {
|
|
1624
|
+
artifact: {
|
|
1625
|
+
byteLength: 615,
|
|
1626
|
+
locator: {
|
|
1627
|
+
bucket: "candidate-test-artifacts",
|
|
1628
|
+
key: "model-settlement/ba3d7012d96e93d5b4f5877d53b9509562f761e5c387c94410f69b39c238cef3",
|
|
1629
|
+
kind: "s3"
|
|
1630
|
+
},
|
|
1631
|
+
sha256: "sha256:ba3d7012d96e93d5b4f5877d53b9509562f761e5c387c94410f69b39c238cef3"
|
|
1632
|
+
},
|
|
1633
|
+
digest: "sha256:ba3d7012d96e93d5b4f5877d53b9509562f761e5c387c94410f69b39c238cef3",
|
|
1634
|
+
kind: "agent-candidate-model-settlement",
|
|
1635
|
+
material: {
|
|
1636
|
+
calls: [],
|
|
1637
|
+
closed: true,
|
|
1638
|
+
executionPlanDigest: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e",
|
|
1639
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
1640
|
+
kind: "agent-candidate-model-settlement-material",
|
|
1641
|
+
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
1642
|
+
resolved: {
|
|
1643
|
+
model: "model-snapshot",
|
|
1644
|
+
provider: "provider",
|
|
1645
|
+
reasoningEffort: "high",
|
|
1646
|
+
requested: "provider/model",
|
|
1647
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
1648
|
+
},
|
|
1649
|
+
usage: {
|
|
1650
|
+
cachedInputTokens: 0,
|
|
1651
|
+
costUsdNanos: 0,
|
|
1652
|
+
inputTokens: 0,
|
|
1653
|
+
modelCalls: 0,
|
|
1654
|
+
outputTokens: 0,
|
|
1655
|
+
reasoningTokens: 0
|
|
1656
|
+
}
|
|
1657
|
+
}
|
|
1658
|
+
},
|
|
1659
|
+
runCellDigest: "sha256:1033e245dd0fbb12ef169f86149fcf93e90f2a5a76b05c0f05c26a165fcaa15c",
|
|
1660
|
+
taskOutcome: {
|
|
1661
|
+
artifact: {
|
|
1662
|
+
byteLength: 478,
|
|
1663
|
+
locator: {
|
|
1664
|
+
bucket: "candidate-test-artifacts",
|
|
1665
|
+
key: "task-outcome/71e7ac55968898115c4b3e0a8e71f02eaf6c5d4b46a67806f1bde01efc96b777",
|
|
1666
|
+
kind: "s3"
|
|
1667
|
+
},
|
|
1668
|
+
sha256: "sha256:71e7ac55968898115c4b3e0a8e71f02eaf6c5d4b46a67806f1bde01efc96b777"
|
|
1669
|
+
},
|
|
1670
|
+
digest: "sha256:71e7ac55968898115c4b3e0a8e71f02eaf6c5d4b46a67806f1bde01efc96b777",
|
|
1671
|
+
kind: "agent-candidate-task-outcome",
|
|
1672
|
+
material: {
|
|
1673
|
+
executionPlanDigest: "sha256:98bc3b015093b6e1476ee3e56713ea10206f893ef2197370e3fa4427356a4f0e",
|
|
1674
|
+
kind: "agent-candidate-task-outcome-material",
|
|
1675
|
+
outcome: {
|
|
1676
|
+
artifact: {
|
|
1677
|
+
byteLength: 6,
|
|
1678
|
+
locator: {
|
|
1679
|
+
bucket: "candidate-test-artifacts",
|
|
1680
|
+
key: "task-output/eda15ce4834ac303532bc6973df5ff8a5deb75d7dfceb9fc2cdf1bb450a01cf5",
|
|
1681
|
+
kind: "s3"
|
|
1682
|
+
},
|
|
1683
|
+
sha256: "sha256:eda15ce4834ac303532bc6973df5ff8a5deb75d7dfceb9fc2cdf1bb450a01cf5"
|
|
1684
|
+
},
|
|
1685
|
+
kind: "output",
|
|
1686
|
+
spec: {
|
|
1687
|
+
maxBytes: 1024,
|
|
1688
|
+
mediaType: "text/plain"
|
|
1689
|
+
}
|
|
1690
|
+
}
|
|
1691
|
+
}
|
|
1692
|
+
},
|
|
1693
|
+
termination: {
|
|
1694
|
+
exitCode: 0,
|
|
1695
|
+
kind: "exit"
|
|
1696
|
+
},
|
|
1697
|
+
timing: {
|
|
1698
|
+
durationMs: 50,
|
|
1699
|
+
endedAtMs: 1150,
|
|
1700
|
+
startedAtMs: 1100
|
|
1701
|
+
},
|
|
1702
|
+
trace: {
|
|
1703
|
+
artifact: {
|
|
1704
|
+
byteLength: 750,
|
|
1705
|
+
locator: {
|
|
1706
|
+
bucket: "candidate-test-artifacts",
|
|
1707
|
+
key: "trace/7a1d1b35b1a21cf30833a83945af1aa5a74d957c91b7bdb742fb832e25c99f0e",
|
|
1708
|
+
kind: "s3"
|
|
1709
|
+
},
|
|
1710
|
+
sha256: "sha256:7a1d1b35b1a21cf30833a83945af1aa5a74d957c91b7bdb742fb832e25c99f0e"
|
|
1711
|
+
},
|
|
1712
|
+
eventCount: 1,
|
|
1713
|
+
modelCallCount: 0
|
|
1714
|
+
}
|
|
1715
|
+
}
|
|
1716
|
+
}
|
|
1717
|
+
},
|
|
1718
|
+
{
|
|
1719
|
+
baseline: {
|
|
1720
|
+
digest: "sha256:19810401295dd6a49219ea005d0b75155f688c9dd972ec6fb6dd43220014426e",
|
|
1721
|
+
kind: "agent-candidate-execution-evidence",
|
|
1722
|
+
materializationReceipt: {
|
|
1723
|
+
benchmark: {
|
|
1724
|
+
suite: {
|
|
1725
|
+
digest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
1726
|
+
material: {
|
|
1727
|
+
byteLength: 198,
|
|
1728
|
+
content: "eyJkaWdlc3RBbGdvcml0aG0iOiJyZmM4Nzg1LXNoYTI1NiIsImtpbmQiOiJhZ2VudC1jYW5kaWRhdGUtYmVuY2htYXJrLXN1aXRlIiwicmVwcyI6Mywic2VlZHMiOlsxMDEsMTAyLDEwM10sInRhc2tEaWdlc3RzIjpbInNoYTI1Njo2YWE3MTgzMzFiNmRhMzEwZGNhYjZkZjJlMzM5N2NiNzcwODQwZTU1NWE4MmUwNjg5NTc3MTU3Yjg5YjRlMjc3Il19",
|
|
1729
|
+
encoding: "base64",
|
|
1730
|
+
sha256: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5"
|
|
1731
|
+
}
|
|
1732
|
+
},
|
|
1733
|
+
task: {
|
|
1734
|
+
digest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
1735
|
+
material: {
|
|
1736
|
+
byteLength: 2096,
|
|
1737
|
+
content: "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",
|
|
1738
|
+
encoding: "base64",
|
|
1739
|
+
sha256: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277"
|
|
1740
|
+
}
|
|
1741
|
+
}
|
|
1742
|
+
},
|
|
1743
|
+
bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
1744
|
+
codeKind: "disabled",
|
|
1745
|
+
container: {
|
|
1746
|
+
image: "ghcr.io/example/task",
|
|
1747
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
1748
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
1749
|
+
platform: {
|
|
1750
|
+
architecture: "amd64",
|
|
1751
|
+
os: "linux"
|
|
1752
|
+
},
|
|
1753
|
+
source: "evaluator-task-container"
|
|
1754
|
+
},
|
|
1755
|
+
digest: "sha256:03fea1af601d95a26c9b22df9ffd8e7cc6f8341ad9eb12e18c008587cf70752e",
|
|
1756
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
1757
|
+
executionPlan: {
|
|
1758
|
+
artifact: {
|
|
1759
|
+
byteLength: 1967,
|
|
1760
|
+
content: "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",
|
|
1761
|
+
encoding: "base64",
|
|
1762
|
+
sha256: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236"
|
|
1763
|
+
},
|
|
1764
|
+
digest: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236",
|
|
1765
|
+
kind: "agent-candidate-execution-plan",
|
|
1766
|
+
material: {
|
|
1767
|
+
codeKind: "disabled",
|
|
1768
|
+
container: {
|
|
1769
|
+
image: "ghcr.io/example/task",
|
|
1770
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
1771
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
1772
|
+
platform: {
|
|
1773
|
+
architecture: "amd64",
|
|
1774
|
+
os: "linux"
|
|
1775
|
+
},
|
|
1776
|
+
source: "evaluator-task-container"
|
|
1777
|
+
},
|
|
1778
|
+
executionId: "experiment-baseline-0-2",
|
|
1779
|
+
harness: "codex",
|
|
1780
|
+
harnessVersion: "1.2.3",
|
|
1781
|
+
instructionDelivery: {
|
|
1782
|
+
kind: "stdin-utf8"
|
|
1783
|
+
},
|
|
1784
|
+
kind: "agent-candidate-execution-plan-material",
|
|
1785
|
+
launch: {
|
|
1786
|
+
args: [],
|
|
1787
|
+
cwd: {
|
|
1788
|
+
path: ".",
|
|
1789
|
+
workspace: "task"
|
|
1790
|
+
},
|
|
1791
|
+
env: {},
|
|
1792
|
+
executable: "codex"
|
|
1793
|
+
},
|
|
1794
|
+
limits: {
|
|
1795
|
+
maxCostUsd: 5,
|
|
1796
|
+
maxInputTokens: 1e5,
|
|
1797
|
+
maxModelCalls: 50,
|
|
1798
|
+
maxOutputTokens: 5e4,
|
|
1799
|
+
maxSteps: 100,
|
|
1800
|
+
timeoutMs: 6e4
|
|
1801
|
+
},
|
|
1802
|
+
memory: {
|
|
1803
|
+
mode: "disabled"
|
|
1804
|
+
},
|
|
1805
|
+
model: {
|
|
1806
|
+
access: {
|
|
1807
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
1808
|
+
kind: "evaluator-mediated",
|
|
1809
|
+
network: {
|
|
1810
|
+
domains: ["router.tangle.tools"],
|
|
1811
|
+
mode: "gateway-only"
|
|
1812
|
+
}
|
|
1813
|
+
},
|
|
1814
|
+
policy: "single",
|
|
1815
|
+
resolved: {
|
|
1816
|
+
model: "model-snapshot",
|
|
1817
|
+
provider: "provider",
|
|
1818
|
+
reasoningEffort: "high",
|
|
1819
|
+
requested: "provider/model",
|
|
1820
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
1821
|
+
},
|
|
1822
|
+
routes: [
|
|
1823
|
+
{
|
|
1824
|
+
kind: "primary",
|
|
1825
|
+
requested: "provider/model"
|
|
1826
|
+
}
|
|
1827
|
+
]
|
|
1828
|
+
},
|
|
1829
|
+
network: {
|
|
1830
|
+
mode: "disabled"
|
|
1831
|
+
},
|
|
1832
|
+
profile: {
|
|
1833
|
+
mountPaths: ["AGENTS.md"],
|
|
1834
|
+
planDigest: "sha256:af65bd67cf53561cd7bfac4e8c913ef18e36c0c2fe20a0bca1df55e59b21fab5",
|
|
1835
|
+
targetWorkspace: "task"
|
|
1836
|
+
},
|
|
1837
|
+
runCell: {
|
|
1838
|
+
arm: "baseline",
|
|
1839
|
+
attempt: 1,
|
|
1840
|
+
bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
1841
|
+
digest: "sha256:7ab33028de32ca70ca169a41bc032b12a3a76bb26baebe8b5802637b996941e4",
|
|
1842
|
+
experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
|
|
1843
|
+
kind: "agent-candidate-run-cell",
|
|
1844
|
+
repetition: 2,
|
|
1845
|
+
seed: 103,
|
|
1846
|
+
suiteDigest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
1847
|
+
taskDigest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
1848
|
+
taskIndex: 0
|
|
1849
|
+
},
|
|
1850
|
+
workspaces: {
|
|
1851
|
+
taskRoot: "/workspace/task"
|
|
1852
|
+
}
|
|
1853
|
+
}
|
|
1854
|
+
},
|
|
1855
|
+
harness: "codex",
|
|
1856
|
+
harnessVersion: "1.2.3",
|
|
1857
|
+
kind: "agent-candidate-materialization",
|
|
1858
|
+
profileActivation: {
|
|
1859
|
+
digest: "sha256:273b700e4080e7e6cc4bd58a755466d18ce323eaaa195bb4202fea456422bb66",
|
|
1860
|
+
files: [
|
|
1861
|
+
{
|
|
1862
|
+
content: "Inspect the repository, implement the fix, and run tests.\n",
|
|
1863
|
+
mode: 420,
|
|
1864
|
+
path: "AGENTS.md"
|
|
1865
|
+
}
|
|
1866
|
+
],
|
|
1867
|
+
kind: "agent-candidate-profile-activation",
|
|
1868
|
+
profilePlan: {
|
|
1869
|
+
artifact: {
|
|
1870
|
+
byteLength: 287,
|
|
1871
|
+
content: "eyJlbnYiOnt9LCJmaWxlcyI6W3siY29udGVudFNoYTI1NiI6InNoYTI1NjozOWFkYmI5YjdmNTcxZjBmZDU4NmU3Nzk1MDIzZDI1OTA5YWRiZTk1ODZiYjIxZWUxMzRkM2Q3MjQ4YmYxNTk5IiwibW9kZSI6NDIwLCJyZWxQYXRoIjoiQUdFTlRTLm1kIn1dLCJmbGFncyI6W10sImhhcm5lc3MiOiJjb2RleCIsInNvdXJjZVByb2ZpbGVEaWdlc3QiOiJzaGEyNTY6ZTUzZTFjOGY5NjMyYmNiNWRiOTAzM2UzMmYzM2E5MGI5YmQ5OWFiZWNlZjBiYjUyZmY5MDY5ZjA3NTA5ZTJmOSIsInVuc3VwcG9ydGVkIjpbXX0=",
|
|
1872
|
+
encoding: "base64",
|
|
1873
|
+
sha256: "sha256:af65bd67cf53561cd7bfac4e8c913ef18e36c0c2fe20a0bca1df55e59b21fab5"
|
|
1874
|
+
},
|
|
1875
|
+
digest: "sha256:af65bd67cf53561cd7bfac4e8c913ef18e36c0c2fe20a0bca1df55e59b21fab5",
|
|
1876
|
+
kind: "agent-profile-workspace-plan",
|
|
1877
|
+
material: {
|
|
1878
|
+
env: {},
|
|
1879
|
+
files: [
|
|
1880
|
+
{
|
|
1881
|
+
contentSha256: "sha256:39adbb9b7f571f0fd586e7795023d25909adbe9586bb21ee134d3d7248bf1599",
|
|
1882
|
+
mode: 420,
|
|
1883
|
+
relPath: "AGENTS.md"
|
|
1884
|
+
}
|
|
1885
|
+
],
|
|
1886
|
+
flags: [],
|
|
1887
|
+
harness: "codex",
|
|
1888
|
+
sourceProfileDigest: "sha256:e53e1c8f9632bcb5db9033e32f33a90b9bd99abecef0bb52ff9069f07509e2f9",
|
|
1889
|
+
unsupported: []
|
|
1890
|
+
}
|
|
1891
|
+
}
|
|
1892
|
+
},
|
|
1893
|
+
resolvedModel: {
|
|
1894
|
+
model: "model-snapshot",
|
|
1895
|
+
provider: "provider",
|
|
1896
|
+
reasoningEffort: "high",
|
|
1897
|
+
requested: "provider/model",
|
|
1898
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
1899
|
+
}
|
|
1900
|
+
},
|
|
1901
|
+
receipt: {
|
|
1902
|
+
benchmarkResult: {
|
|
1903
|
+
artifact: {
|
|
1904
|
+
byteLength: 1122,
|
|
1905
|
+
locator: {
|
|
1906
|
+
bucket: "candidate-test-artifacts",
|
|
1907
|
+
key: "benchmark-result/9deed92c5c6f606541d59db8a52f33334c76e9766ddb19108399942dd28dd66b",
|
|
1908
|
+
kind: "s3"
|
|
1909
|
+
},
|
|
1910
|
+
sha256: "sha256:9deed92c5c6f606541d59db8a52f33334c76e9766ddb19108399942dd28dd66b"
|
|
1911
|
+
},
|
|
1912
|
+
digest: "sha256:9deed92c5c6f606541d59db8a52f33334c76e9766ddb19108399942dd28dd66b",
|
|
1913
|
+
kind: "agent-candidate-benchmark-result",
|
|
1914
|
+
material: {
|
|
1915
|
+
dimensions: [
|
|
1916
|
+
{
|
|
1917
|
+
name: "quality",
|
|
1918
|
+
score: 0
|
|
1919
|
+
}
|
|
1920
|
+
],
|
|
1921
|
+
evidence: {
|
|
1922
|
+
byteLength: 11,
|
|
1923
|
+
locator: {
|
|
1924
|
+
bucket: "candidate-test-artifacts",
|
|
1925
|
+
key: "grader-evidence/628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b",
|
|
1926
|
+
kind: "s3"
|
|
1927
|
+
},
|
|
1928
|
+
sha256: "sha256:628cb4ead38e34e34a34f78fa4481f2a0ccf8e9139acfae69d79dc997e90e36b"
|
|
1929
|
+
},
|
|
1930
|
+
executionPlanDigest: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236",
|
|
1931
|
+
grader: {
|
|
1932
|
+
artifact: {
|
|
1933
|
+
byteLength: 25,
|
|
1934
|
+
locator: {
|
|
1935
|
+
bucket: "candidate-test-artifacts",
|
|
1936
|
+
key: "grader/9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad",
|
|
1937
|
+
kind: "s3"
|
|
1938
|
+
},
|
|
1939
|
+
sha256: "sha256:9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad"
|
|
1940
|
+
},
|
|
1941
|
+
format: "tangle-grader",
|
|
1942
|
+
name: "fixture-executable-grader",
|
|
1943
|
+
version: "1.0.0"
|
|
1944
|
+
},
|
|
1945
|
+
grading: {
|
|
1946
|
+
timing: {
|
|
1947
|
+
durationMs: 0,
|
|
1948
|
+
endedAtMs: 17836416e5,
|
|
1949
|
+
startedAtMs: 17836416e5
|
|
1950
|
+
},
|
|
1951
|
+
usage: {
|
|
1952
|
+
cachedInputTokens: 0,
|
|
1953
|
+
costUsdNanos: 0,
|
|
1954
|
+
inputTokens: 0,
|
|
1955
|
+
modelCalls: 0,
|
|
1956
|
+
outputTokens: 0,
|
|
1957
|
+
reasoningTokens: 0
|
|
1958
|
+
}
|
|
1959
|
+
},
|
|
1960
|
+
kind: "agent-candidate-benchmark-result-material",
|
|
1961
|
+
passed: false,
|
|
1962
|
+
score: 0,
|
|
1963
|
+
taskOutcomeDigest: "sha256:b7839b059ff6bc2b5606d53992c1e3b1001b5917ca21798e07a696c2b555faef"
|
|
1964
|
+
}
|
|
1965
|
+
},
|
|
1966
|
+
bundleDigest: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
1967
|
+
digest: "sha256:b94caa496f9425e76559b3d11482a9156af47aec0c4736a3f2acde6e0d7147f6",
|
|
1968
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
1969
|
+
executionPlanDigest: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236",
|
|
1970
|
+
executorCapture: {
|
|
1971
|
+
byteLength: 477,
|
|
1972
|
+
locator: {
|
|
1973
|
+
bucket: "candidate-test-artifacts",
|
|
1974
|
+
key: "executor-capture/41c380f90694c94d3638d3f6a1bc2984edabc4b841135563ec693988318a789a",
|
|
1975
|
+
kind: "s3"
|
|
1976
|
+
},
|
|
1977
|
+
sha256: "sha256:41c380f90694c94d3638d3f6a1bc2984edabc4b841135563ec693988318a789a"
|
|
1978
|
+
},
|
|
1979
|
+
kind: "agent-candidate-run",
|
|
1980
|
+
materializationReceiptDigest: "sha256:03fea1af601d95a26c9b22df9ffd8e7cc6f8341ad9eb12e18c008587cf70752e",
|
|
1981
|
+
memory: {
|
|
1982
|
+
mode: "disabled"
|
|
1983
|
+
},
|
|
1984
|
+
modelSettlement: {
|
|
1985
|
+
artifact: {
|
|
1986
|
+
byteLength: 615,
|
|
1987
|
+
locator: {
|
|
1988
|
+
bucket: "candidate-test-artifacts",
|
|
1989
|
+
key: "model-settlement/43f369d800ff013c35fc63eab901109849030ade35def608ad3229a97c9b5c52",
|
|
1990
|
+
kind: "s3"
|
|
1991
|
+
},
|
|
1992
|
+
sha256: "sha256:43f369d800ff013c35fc63eab901109849030ade35def608ad3229a97c9b5c52"
|
|
1993
|
+
},
|
|
1994
|
+
digest: "sha256:43f369d800ff013c35fc63eab901109849030ade35def608ad3229a97c9b5c52",
|
|
1995
|
+
kind: "agent-candidate-model-settlement",
|
|
1996
|
+
material: {
|
|
1997
|
+
calls: [],
|
|
1998
|
+
closed: true,
|
|
1999
|
+
executionPlanDigest: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236",
|
|
2000
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
2001
|
+
kind: "agent-candidate-model-settlement-material",
|
|
2002
|
+
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
2003
|
+
resolved: {
|
|
2004
|
+
model: "model-snapshot",
|
|
2005
|
+
provider: "provider",
|
|
2006
|
+
reasoningEffort: "high",
|
|
2007
|
+
requested: "provider/model",
|
|
2008
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
2009
|
+
},
|
|
2010
|
+
usage: {
|
|
2011
|
+
cachedInputTokens: 0,
|
|
2012
|
+
costUsdNanos: 0,
|
|
2013
|
+
inputTokens: 0,
|
|
2014
|
+
modelCalls: 0,
|
|
2015
|
+
outputTokens: 0,
|
|
2016
|
+
reasoningTokens: 0
|
|
2017
|
+
}
|
|
2018
|
+
}
|
|
2019
|
+
},
|
|
2020
|
+
runCellDigest: "sha256:7ab33028de32ca70ca169a41bc032b12a3a76bb26baebe8b5802637b996941e4",
|
|
2021
|
+
taskOutcome: {
|
|
2022
|
+
artifact: {
|
|
2023
|
+
byteLength: 478,
|
|
2024
|
+
locator: {
|
|
2025
|
+
bucket: "candidate-test-artifacts",
|
|
2026
|
+
key: "task-outcome/b7839b059ff6bc2b5606d53992c1e3b1001b5917ca21798e07a696c2b555faef",
|
|
2027
|
+
kind: "s3"
|
|
2028
|
+
},
|
|
2029
|
+
sha256: "sha256:b7839b059ff6bc2b5606d53992c1e3b1001b5917ca21798e07a696c2b555faef"
|
|
2030
|
+
},
|
|
2031
|
+
digest: "sha256:b7839b059ff6bc2b5606d53992c1e3b1001b5917ca21798e07a696c2b555faef",
|
|
2032
|
+
kind: "agent-candidate-task-outcome",
|
|
2033
|
+
material: {
|
|
2034
|
+
executionPlanDigest: "sha256:f5dcd0596f8c63a2d42cd817d0a9a2b0eab0afec46d1ae6f50e7b1e8449d1236",
|
|
2035
|
+
kind: "agent-candidate-task-outcome-material",
|
|
2036
|
+
outcome: {
|
|
2037
|
+
artifact: {
|
|
2038
|
+
byteLength: 4,
|
|
2039
|
+
locator: {
|
|
2040
|
+
bucket: "candidate-test-artifacts",
|
|
2041
|
+
key: "task-output/481ba4019c9d2710c3386537382592c093ef02bf5b056c30237b3d92b0e19a1d",
|
|
2042
|
+
kind: "s3"
|
|
2043
|
+
},
|
|
2044
|
+
sha256: "sha256:481ba4019c9d2710c3386537382592c093ef02bf5b056c30237b3d92b0e19a1d"
|
|
2045
|
+
},
|
|
2046
|
+
kind: "output",
|
|
2047
|
+
spec: {
|
|
2048
|
+
maxBytes: 1024,
|
|
2049
|
+
mediaType: "text/plain"
|
|
2050
|
+
}
|
|
2051
|
+
}
|
|
2052
|
+
}
|
|
2053
|
+
},
|
|
2054
|
+
termination: {
|
|
2055
|
+
exitCode: 0,
|
|
2056
|
+
kind: "exit"
|
|
2057
|
+
},
|
|
2058
|
+
timing: {
|
|
2059
|
+
durationMs: 50,
|
|
2060
|
+
endedAtMs: 1250,
|
|
2061
|
+
startedAtMs: 1200
|
|
2062
|
+
},
|
|
2063
|
+
trace: {
|
|
2064
|
+
artifact: {
|
|
2065
|
+
byteLength: 748,
|
|
2066
|
+
locator: {
|
|
2067
|
+
bucket: "candidate-test-artifacts",
|
|
2068
|
+
key: "trace/11de40695ad7fd6a370835f9945fa8e43348443d95a22d559992c294b2fb58b8",
|
|
2069
|
+
kind: "s3"
|
|
2070
|
+
},
|
|
2071
|
+
sha256: "sha256:11de40695ad7fd6a370835f9945fa8e43348443d95a22d559992c294b2fb58b8"
|
|
2072
|
+
},
|
|
2073
|
+
eventCount: 1,
|
|
2074
|
+
modelCallCount: 0
|
|
2075
|
+
}
|
|
2076
|
+
}
|
|
2077
|
+
},
|
|
2078
|
+
candidate: {
|
|
2079
|
+
digest: "sha256:7f299ebc9ac6801ecadc3325e7e1e474d292db2f3ad626e74daa721ea24998df",
|
|
2080
|
+
kind: "agent-candidate-execution-evidence",
|
|
2081
|
+
materializationReceipt: {
|
|
2082
|
+
benchmark: {
|
|
2083
|
+
suite: {
|
|
2084
|
+
digest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
2085
|
+
material: {
|
|
2086
|
+
byteLength: 198,
|
|
2087
|
+
content: "eyJkaWdlc3RBbGdvcml0aG0iOiJyZmM4Nzg1LXNoYTI1NiIsImtpbmQiOiJhZ2VudC1jYW5kaWRhdGUtYmVuY2htYXJrLXN1aXRlIiwicmVwcyI6Mywic2VlZHMiOlsxMDEsMTAyLDEwM10sInRhc2tEaWdlc3RzIjpbInNoYTI1Njo2YWE3MTgzMzFiNmRhMzEwZGNhYjZkZjJlMzM5N2NiNzcwODQwZTU1NWE4MmUwNjg5NTc3MTU3Yjg5YjRlMjc3Il19",
|
|
2088
|
+
encoding: "base64",
|
|
2089
|
+
sha256: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5"
|
|
2090
|
+
}
|
|
2091
|
+
},
|
|
2092
|
+
task: {
|
|
2093
|
+
digest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
2094
|
+
material: {
|
|
2095
|
+
byteLength: 2096,
|
|
2096
|
+
content: "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",
|
|
2097
|
+
encoding: "base64",
|
|
2098
|
+
sha256: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277"
|
|
2099
|
+
}
|
|
2100
|
+
}
|
|
2101
|
+
},
|
|
2102
|
+
bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
2103
|
+
codeKind: "disabled",
|
|
2104
|
+
container: {
|
|
2105
|
+
image: "ghcr.io/example/task",
|
|
2106
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
2107
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
2108
|
+
platform: {
|
|
2109
|
+
architecture: "amd64",
|
|
2110
|
+
os: "linux"
|
|
2111
|
+
},
|
|
2112
|
+
source: "evaluator-task-container"
|
|
2113
|
+
},
|
|
2114
|
+
digest: "sha256:58b85d501d6559779de74275f638c76ef2a0c7decff907081b8e20d5df37d1c6",
|
|
2115
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
2116
|
+
executionPlan: {
|
|
2117
|
+
artifact: {
|
|
2118
|
+
byteLength: 1969,
|
|
2119
|
+
content: "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",
|
|
2120
|
+
encoding: "base64",
|
|
2121
|
+
sha256: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669"
|
|
2122
|
+
},
|
|
2123
|
+
digest: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669",
|
|
2124
|
+
kind: "agent-candidate-execution-plan",
|
|
2125
|
+
material: {
|
|
2126
|
+
codeKind: "disabled",
|
|
2127
|
+
container: {
|
|
2128
|
+
image: "ghcr.io/example/task",
|
|
2129
|
+
indexDigest: "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
2130
|
+
manifestDigest: "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
2131
|
+
platform: {
|
|
2132
|
+
architecture: "amd64",
|
|
2133
|
+
os: "linux"
|
|
2134
|
+
},
|
|
2135
|
+
source: "evaluator-task-container"
|
|
2136
|
+
},
|
|
2137
|
+
executionId: "experiment-candidate-0-2",
|
|
2138
|
+
harness: "codex",
|
|
2139
|
+
harnessVersion: "1.2.3",
|
|
2140
|
+
instructionDelivery: {
|
|
2141
|
+
kind: "stdin-utf8"
|
|
2142
|
+
},
|
|
2143
|
+
kind: "agent-candidate-execution-plan-material",
|
|
2144
|
+
launch: {
|
|
2145
|
+
args: [],
|
|
2146
|
+
cwd: {
|
|
2147
|
+
path: ".",
|
|
2148
|
+
workspace: "task"
|
|
2149
|
+
},
|
|
2150
|
+
env: {},
|
|
2151
|
+
executable: "codex"
|
|
2152
|
+
},
|
|
2153
|
+
limits: {
|
|
2154
|
+
maxCostUsd: 5,
|
|
2155
|
+
maxInputTokens: 1e5,
|
|
2156
|
+
maxModelCalls: 50,
|
|
2157
|
+
maxOutputTokens: 5e4,
|
|
2158
|
+
maxSteps: 100,
|
|
2159
|
+
timeoutMs: 6e4
|
|
2160
|
+
},
|
|
2161
|
+
memory: {
|
|
2162
|
+
mode: "disabled"
|
|
2163
|
+
},
|
|
2164
|
+
model: {
|
|
2165
|
+
access: {
|
|
2166
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
2167
|
+
kind: "evaluator-mediated",
|
|
2168
|
+
network: {
|
|
2169
|
+
domains: ["router.tangle.tools"],
|
|
2170
|
+
mode: "gateway-only"
|
|
2171
|
+
}
|
|
2172
|
+
},
|
|
2173
|
+
policy: "single",
|
|
2174
|
+
resolved: {
|
|
2175
|
+
model: "model-snapshot",
|
|
2176
|
+
provider: "provider",
|
|
2177
|
+
reasoningEffort: "high",
|
|
2178
|
+
requested: "provider/model",
|
|
2179
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
2180
|
+
},
|
|
2181
|
+
routes: [
|
|
2182
|
+
{
|
|
2183
|
+
kind: "primary",
|
|
2184
|
+
requested: "provider/model"
|
|
2185
|
+
}
|
|
2186
|
+
]
|
|
2187
|
+
},
|
|
2188
|
+
network: {
|
|
2189
|
+
mode: "disabled"
|
|
2190
|
+
},
|
|
2191
|
+
profile: {
|
|
2192
|
+
mountPaths: ["AGENTS.md"],
|
|
2193
|
+
planDigest: "sha256:4b4214d1bae911df6dda3a5d8585c65df2f0b2380126eb40c0cbd46a4a2fba5b",
|
|
2194
|
+
targetWorkspace: "task"
|
|
2195
|
+
},
|
|
2196
|
+
runCell: {
|
|
2197
|
+
arm: "candidate",
|
|
2198
|
+
attempt: 1,
|
|
2199
|
+
bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
2200
|
+
digest: "sha256:b725cf36cf0b5b2ecf09cd8f09e4a463c98ba909b4622220ce74754c12a51a3a",
|
|
2201
|
+
experimentDigest: "sha256:4e7760541729a4f61232f8084b42496e2d7e40f8604c1c8ca413fb12799ce31c",
|
|
2202
|
+
kind: "agent-candidate-run-cell",
|
|
2203
|
+
repetition: 2,
|
|
2204
|
+
seed: 103,
|
|
2205
|
+
suiteDigest: "sha256:963d6ad7abe359c963f31c21036ac6176fe7d5f097b2200ab4430c0d1bf1bcd5",
|
|
2206
|
+
taskDigest: "sha256:6aa718331b6da310dcab6df2e3397cb770840e555a82e0689577157b89b4e277",
|
|
2207
|
+
taskIndex: 0
|
|
2208
|
+
},
|
|
2209
|
+
workspaces: {
|
|
2210
|
+
taskRoot: "/workspace/task"
|
|
2211
|
+
}
|
|
2212
|
+
}
|
|
2213
|
+
},
|
|
2214
|
+
harness: "codex",
|
|
2215
|
+
harnessVersion: "1.2.3",
|
|
2216
|
+
kind: "agent-candidate-materialization",
|
|
2217
|
+
profileActivation: {
|
|
2218
|
+
digest: "sha256:3103f8282be70a843eada63410c41d9eb5ac7b824c758eed6c2f8610de169f45",
|
|
2219
|
+
files: [
|
|
2220
|
+
{
|
|
2221
|
+
content: "Inspect the repository, implement the fix, and run tests.\n",
|
|
2222
|
+
mode: 420,
|
|
2223
|
+
path: "AGENTS.md"
|
|
2224
|
+
}
|
|
2225
|
+
],
|
|
2226
|
+
kind: "agent-candidate-profile-activation",
|
|
2227
|
+
profilePlan: {
|
|
2228
|
+
artifact: {
|
|
2229
|
+
byteLength: 364,
|
|
2230
|
+
content: "eyJlbnYiOnt9LCJmaWxlcyI6W3siY29udGVudFNoYTI1NiI6InNoYTI1NjozOWFkYmI5YjdmNTcxZjBmZDU4NmU3Nzk1MDIzZDI1OTA5YWRiZTk1ODZiYjIxZWUxMzRkM2Q3MjQ4YmYxNTk5IiwibW9kZSI6NDIwLCJyZWxQYXRoIjoiQUdFTlRTLm1kIn1dLCJmbGFncyI6W10sImhhcm5lc3MiOiJjb2RleCIsInNvdXJjZVByb2ZpbGVEaWdlc3QiOiJzaGEyNTY6OGIxZTJmMGY3YjgzMjk1ODM4MWMyOWJhZWJlNGE5NjFiMTUxYWY5N2EwY2U5ZDYxMWExNWFkMDc0MWFlYWE3NSIsInN5c3RlbVByb21wdCI6eyJraW5kIjoicHVibGljIiwidmFsdWUiOiJSZXR1cm4gdGhlIGV4YWN0IG1lYXN1cmVkIGFuc3dlci4ifSwidW5zdXBwb3J0ZWQiOltdfQ==",
|
|
2231
|
+
encoding: "base64",
|
|
2232
|
+
sha256: "sha256:4b4214d1bae911df6dda3a5d8585c65df2f0b2380126eb40c0cbd46a4a2fba5b"
|
|
2233
|
+
},
|
|
2234
|
+
digest: "sha256:4b4214d1bae911df6dda3a5d8585c65df2f0b2380126eb40c0cbd46a4a2fba5b",
|
|
2235
|
+
kind: "agent-profile-workspace-plan",
|
|
2236
|
+
material: {
|
|
2237
|
+
env: {},
|
|
2238
|
+
files: [
|
|
2239
|
+
{
|
|
2240
|
+
contentSha256: "sha256:39adbb9b7f571f0fd586e7795023d25909adbe9586bb21ee134d3d7248bf1599",
|
|
2241
|
+
mode: 420,
|
|
2242
|
+
relPath: "AGENTS.md"
|
|
2243
|
+
}
|
|
2244
|
+
],
|
|
2245
|
+
flags: [],
|
|
2246
|
+
harness: "codex",
|
|
2247
|
+
sourceProfileDigest: "sha256:8b1e2f0f7b832958381c29baebe4a961b151af97a0ce9d611a15ad0741aeaa75",
|
|
2248
|
+
systemPrompt: {
|
|
2249
|
+
kind: "public",
|
|
2250
|
+
value: "Return the exact measured answer."
|
|
2251
|
+
},
|
|
2252
|
+
unsupported: []
|
|
2253
|
+
}
|
|
2254
|
+
}
|
|
2255
|
+
},
|
|
2256
|
+
resolvedModel: {
|
|
2257
|
+
model: "model-snapshot",
|
|
2258
|
+
provider: "provider",
|
|
2259
|
+
reasoningEffort: "high",
|
|
2260
|
+
requested: "provider/model",
|
|
2261
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
2262
|
+
}
|
|
2263
|
+
},
|
|
2264
|
+
receipt: {
|
|
2265
|
+
benchmarkResult: {
|
|
2266
|
+
artifact: {
|
|
2267
|
+
byteLength: 1121,
|
|
2268
|
+
locator: {
|
|
2269
|
+
bucket: "candidate-test-artifacts",
|
|
2270
|
+
key: "benchmark-result/065077bb8c8d7ce16e785ddfa6fc633ea492aafcc94162b7ac171fafb3c579ad",
|
|
2271
|
+
kind: "s3"
|
|
2272
|
+
},
|
|
2273
|
+
sha256: "sha256:065077bb8c8d7ce16e785ddfa6fc633ea492aafcc94162b7ac171fafb3c579ad"
|
|
2274
|
+
},
|
|
2275
|
+
digest: "sha256:065077bb8c8d7ce16e785ddfa6fc633ea492aafcc94162b7ac171fafb3c579ad",
|
|
2276
|
+
kind: "agent-candidate-benchmark-result",
|
|
2277
|
+
material: {
|
|
2278
|
+
dimensions: [
|
|
2279
|
+
{
|
|
2280
|
+
name: "quality",
|
|
2281
|
+
score: 1
|
|
2282
|
+
}
|
|
2283
|
+
],
|
|
2284
|
+
evidence: {
|
|
2285
|
+
byteLength: 11,
|
|
2286
|
+
locator: {
|
|
2287
|
+
bucket: "candidate-test-artifacts",
|
|
2288
|
+
key: "grader-evidence/9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d",
|
|
2289
|
+
kind: "s3"
|
|
2290
|
+
},
|
|
2291
|
+
sha256: "sha256:9b9b3a1471309177261cfe65ea9c298e0dd372e4b5d087f8d35d7b732485373d"
|
|
2292
|
+
},
|
|
2293
|
+
executionPlanDigest: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669",
|
|
2294
|
+
grader: {
|
|
2295
|
+
artifact: {
|
|
2296
|
+
byteLength: 25,
|
|
2297
|
+
locator: {
|
|
2298
|
+
bucket: "candidate-test-artifacts",
|
|
2299
|
+
key: "grader/9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad",
|
|
2300
|
+
kind: "s3"
|
|
2301
|
+
},
|
|
2302
|
+
sha256: "sha256:9a354495185587b25e8c98104060068871a44c719e4f57d345a905fc2d72a6ad"
|
|
2303
|
+
},
|
|
2304
|
+
format: "tangle-grader",
|
|
2305
|
+
name: "fixture-executable-grader",
|
|
2306
|
+
version: "1.0.0"
|
|
2307
|
+
},
|
|
2308
|
+
grading: {
|
|
2309
|
+
timing: {
|
|
2310
|
+
durationMs: 0,
|
|
2311
|
+
endedAtMs: 17836416e5,
|
|
2312
|
+
startedAtMs: 17836416e5
|
|
2313
|
+
},
|
|
2314
|
+
usage: {
|
|
2315
|
+
cachedInputTokens: 0,
|
|
2316
|
+
costUsdNanos: 0,
|
|
2317
|
+
inputTokens: 0,
|
|
2318
|
+
modelCalls: 0,
|
|
2319
|
+
outputTokens: 0,
|
|
2320
|
+
reasoningTokens: 0
|
|
2321
|
+
}
|
|
2322
|
+
},
|
|
2323
|
+
kind: "agent-candidate-benchmark-result-material",
|
|
2324
|
+
passed: true,
|
|
2325
|
+
score: 1,
|
|
2326
|
+
taskOutcomeDigest: "sha256:4dcf33ca1333772d635d34932d4348fb55d7dd4146f734f97bd1b296ad059f0f"
|
|
2327
|
+
}
|
|
2328
|
+
},
|
|
2329
|
+
bundleDigest: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
2330
|
+
digest: "sha256:88fd469bd1018d2b4dd7c1cce8cb6f13dee64599a9054237f39f245d97e446d4",
|
|
2331
|
+
digestAlgorithm: "rfc8785-sha256",
|
|
2332
|
+
executionPlanDigest: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669",
|
|
2333
|
+
executorCapture: {
|
|
2334
|
+
byteLength: 477,
|
|
2335
|
+
locator: {
|
|
2336
|
+
bucket: "candidate-test-artifacts",
|
|
2337
|
+
key: "executor-capture/9923cd0fda5e697e70ab83a99dac67d991b9b0ac9c1702bb99990f0d9a5cd1d7",
|
|
2338
|
+
kind: "s3"
|
|
2339
|
+
},
|
|
2340
|
+
sha256: "sha256:9923cd0fda5e697e70ab83a99dac67d991b9b0ac9c1702bb99990f0d9a5cd1d7"
|
|
2341
|
+
},
|
|
2342
|
+
kind: "agent-candidate-run",
|
|
2343
|
+
materializationReceiptDigest: "sha256:58b85d501d6559779de74275f638c76ef2a0c7decff907081b8e20d5df37d1c6",
|
|
2344
|
+
memory: {
|
|
2345
|
+
mode: "disabled"
|
|
2346
|
+
},
|
|
2347
|
+
modelSettlement: {
|
|
2348
|
+
artifact: {
|
|
2349
|
+
byteLength: 615,
|
|
2350
|
+
locator: {
|
|
2351
|
+
bucket: "candidate-test-artifacts",
|
|
2352
|
+
key: "model-settlement/592d4b35fa6b118a9a20eea887eed44e997bede7b155ca83607c0b11d83bad77",
|
|
2353
|
+
kind: "s3"
|
|
2354
|
+
},
|
|
2355
|
+
sha256: "sha256:592d4b35fa6b118a9a20eea887eed44e997bede7b155ca83607c0b11d83bad77"
|
|
2356
|
+
},
|
|
2357
|
+
digest: "sha256:592d4b35fa6b118a9a20eea887eed44e997bede7b155ca83607c0b11d83bad77",
|
|
2358
|
+
kind: "agent-candidate-model-settlement",
|
|
2359
|
+
material: {
|
|
2360
|
+
calls: [],
|
|
2361
|
+
closed: true,
|
|
2362
|
+
executionPlanDigest: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669",
|
|
2363
|
+
grantDigest: "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
2364
|
+
kind: "agent-candidate-model-settlement-material",
|
|
2365
|
+
preparationId: "candidate-preparation.nBqsDbKYlsiY4Tto5XaxkR3RCTop9PA9_kX-kOSzR8U",
|
|
2366
|
+
resolved: {
|
|
2367
|
+
model: "model-snapshot",
|
|
2368
|
+
provider: "provider",
|
|
2369
|
+
reasoningEffort: "high",
|
|
2370
|
+
requested: "provider/model",
|
|
2371
|
+
snapshot: "model-snapshot-2026-07-01"
|
|
2372
|
+
},
|
|
2373
|
+
usage: {
|
|
2374
|
+
cachedInputTokens: 0,
|
|
2375
|
+
costUsdNanos: 0,
|
|
2376
|
+
inputTokens: 0,
|
|
2377
|
+
modelCalls: 0,
|
|
2378
|
+
outputTokens: 0,
|
|
2379
|
+
reasoningTokens: 0
|
|
2380
|
+
}
|
|
2381
|
+
}
|
|
2382
|
+
},
|
|
2383
|
+
runCellDigest: "sha256:b725cf36cf0b5b2ecf09cd8f09e4a463c98ba909b4622220ce74754c12a51a3a",
|
|
2384
|
+
taskOutcome: {
|
|
2385
|
+
artifact: {
|
|
2386
|
+
byteLength: 478,
|
|
2387
|
+
locator: {
|
|
2388
|
+
bucket: "candidate-test-artifacts",
|
|
2389
|
+
key: "task-outcome/4dcf33ca1333772d635d34932d4348fb55d7dd4146f734f97bd1b296ad059f0f",
|
|
2390
|
+
kind: "s3"
|
|
2391
|
+
},
|
|
2392
|
+
sha256: "sha256:4dcf33ca1333772d635d34932d4348fb55d7dd4146f734f97bd1b296ad059f0f"
|
|
2393
|
+
},
|
|
2394
|
+
digest: "sha256:4dcf33ca1333772d635d34932d4348fb55d7dd4146f734f97bd1b296ad059f0f",
|
|
2395
|
+
kind: "agent-candidate-task-outcome",
|
|
2396
|
+
material: {
|
|
2397
|
+
executionPlanDigest: "sha256:e28d078113fb86520834d5b51c506b7472398bff1dc3072bd2a44096e6b1c669",
|
|
2398
|
+
kind: "agent-candidate-task-outcome-material",
|
|
2399
|
+
outcome: {
|
|
2400
|
+
artifact: {
|
|
2401
|
+
byteLength: 6,
|
|
2402
|
+
locator: {
|
|
2403
|
+
bucket: "candidate-test-artifacts",
|
|
2404
|
+
key: "task-output/eda15ce4834ac303532bc6973df5ff8a5deb75d7dfceb9fc2cdf1bb450a01cf5",
|
|
2405
|
+
kind: "s3"
|
|
2406
|
+
},
|
|
2407
|
+
sha256: "sha256:eda15ce4834ac303532bc6973df5ff8a5deb75d7dfceb9fc2cdf1bb450a01cf5"
|
|
2408
|
+
},
|
|
2409
|
+
kind: "output",
|
|
2410
|
+
spec: {
|
|
2411
|
+
maxBytes: 1024,
|
|
2412
|
+
mediaType: "text/plain"
|
|
2413
|
+
}
|
|
2414
|
+
}
|
|
2415
|
+
}
|
|
2416
|
+
},
|
|
2417
|
+
termination: {
|
|
2418
|
+
exitCode: 0,
|
|
2419
|
+
kind: "exit"
|
|
2420
|
+
},
|
|
2421
|
+
timing: {
|
|
2422
|
+
durationMs: 50,
|
|
2423
|
+
endedAtMs: 1250,
|
|
2424
|
+
startedAtMs: 1200
|
|
2425
|
+
},
|
|
2426
|
+
trace: {
|
|
2427
|
+
artifact: {
|
|
2428
|
+
byteLength: 750,
|
|
2429
|
+
locator: {
|
|
2430
|
+
bucket: "candidate-test-artifacts",
|
|
2431
|
+
key: "trace/3d68a2563c8e0fad81d134e751fe8a6d8a715ba73228c94c7cd0a2fb729186d4",
|
|
2432
|
+
kind: "s3"
|
|
2433
|
+
},
|
|
2434
|
+
sha256: "sha256:3d68a2563c8e0fad81d134e751fe8a6d8a715ba73228c94c7cd0a2fb729186d4"
|
|
2435
|
+
},
|
|
2436
|
+
eventCount: 1,
|
|
2437
|
+
modelCallCount: 0
|
|
2438
|
+
}
|
|
2439
|
+
}
|
|
2440
|
+
}
|
|
2441
|
+
}
|
|
2442
|
+
],
|
|
2443
|
+
metadata: {
|
|
2444
|
+
fixture: "agent-improvement-proposal",
|
|
2445
|
+
runtimeVersion: "0.101.1"
|
|
2446
|
+
},
|
|
2447
|
+
objectives: [
|
|
2448
|
+
{
|
|
2449
|
+
availability: "measured",
|
|
2450
|
+
baseline: 0,
|
|
2451
|
+
candidate: 1,
|
|
2452
|
+
confidenceInterval: {
|
|
2453
|
+
level: 0.95,
|
|
2454
|
+
lower: 1,
|
|
2455
|
+
method: "paired-bootstrap",
|
|
2456
|
+
resamples: 500,
|
|
2457
|
+
statistic: "mean",
|
|
2458
|
+
upper: 1
|
|
2459
|
+
},
|
|
2460
|
+
delta: 1,
|
|
2461
|
+
direction: "higher-is-better",
|
|
2462
|
+
kind: "objective",
|
|
2463
|
+
n: 3,
|
|
2464
|
+
name: "benchmark-score",
|
|
2465
|
+
unit: "score"
|
|
2466
|
+
},
|
|
2467
|
+
{
|
|
2468
|
+
availability: "measured",
|
|
2469
|
+
baseline: 0,
|
|
2470
|
+
candidate: 1,
|
|
2471
|
+
confidenceInterval: {
|
|
2472
|
+
level: 0.95,
|
|
2473
|
+
lower: 1,
|
|
2474
|
+
method: "paired-bootstrap",
|
|
2475
|
+
resamples: 500,
|
|
2476
|
+
statistic: "mean",
|
|
2477
|
+
upper: 1
|
|
2478
|
+
},
|
|
2479
|
+
delta: 1,
|
|
2480
|
+
direction: "higher-is-better",
|
|
2481
|
+
kind: "dimension",
|
|
2482
|
+
n: 3,
|
|
2483
|
+
name: "quality",
|
|
2484
|
+
objective: "benchmark-score",
|
|
2485
|
+
unit: "score"
|
|
2486
|
+
},
|
|
2487
|
+
{
|
|
2488
|
+
availability: "measured",
|
|
2489
|
+
baseline: 0,
|
|
2490
|
+
candidate: 0,
|
|
2491
|
+
confidenceInterval: {
|
|
2492
|
+
level: 0.95,
|
|
2493
|
+
lower: 0,
|
|
2494
|
+
method: "paired-bootstrap",
|
|
2495
|
+
resamples: 500,
|
|
2496
|
+
statistic: "mean",
|
|
2497
|
+
upper: 0
|
|
2498
|
+
},
|
|
2499
|
+
delta: 0,
|
|
2500
|
+
direction: "lower-is-better",
|
|
2501
|
+
kind: "cost",
|
|
2502
|
+
n: 3,
|
|
2503
|
+
name: "cost",
|
|
2504
|
+
unit: "usd"
|
|
2505
|
+
},
|
|
2506
|
+
{
|
|
2507
|
+
availability: "measured",
|
|
2508
|
+
baseline: 50,
|
|
2509
|
+
candidate: 50,
|
|
2510
|
+
confidenceInterval: {
|
|
2511
|
+
level: 0.95,
|
|
2512
|
+
lower: 0,
|
|
2513
|
+
method: "paired-bootstrap",
|
|
2514
|
+
resamples: 500,
|
|
2515
|
+
statistic: "mean",
|
|
2516
|
+
upper: 0
|
|
2517
|
+
},
|
|
2518
|
+
delta: 0,
|
|
2519
|
+
direction: "lower-is-better",
|
|
2520
|
+
kind: "latency",
|
|
2521
|
+
n: 3,
|
|
2522
|
+
name: "latency",
|
|
2523
|
+
unit: "milliseconds"
|
|
2524
|
+
}
|
|
2525
|
+
],
|
|
2526
|
+
overall: {
|
|
2527
|
+
baseline: 0,
|
|
2528
|
+
candidate: 1,
|
|
2529
|
+
confidenceInterval: {
|
|
2530
|
+
level: 0.95,
|
|
2531
|
+
lower: 1,
|
|
2532
|
+
method: "paired-bootstrap",
|
|
2533
|
+
resamples: 500,
|
|
2534
|
+
statistic: "mean",
|
|
2535
|
+
upper: 1
|
|
2536
|
+
},
|
|
2537
|
+
delta: 1,
|
|
2538
|
+
direction: "higher-is-better",
|
|
2539
|
+
n: 3,
|
|
2540
|
+
name: "composite",
|
|
2541
|
+
unit: "score"
|
|
2542
|
+
},
|
|
2543
|
+
power: {
|
|
2544
|
+
confidenceLevel: 0.95,
|
|
2545
|
+
minimumDetectableDelta: 0,
|
|
2546
|
+
n: 3,
|
|
2547
|
+
reason: "Minimum detectable lift at n=3: 0.000 (baseline sd 0.000). Effects smaller than this cannot clear the gate; budget the search for effects you believe exceed it. Holdout and gate share one scoring channel: raising n/reps reduces only idiosyncratic noise \u2014 systematic judge bias remains and this MDE is a lower bound. Full debiasing needs an independent second scoring channel (different judge/benchmark family).",
|
|
2548
|
+
scaleAssumed: true,
|
|
2549
|
+
sharedScorerChannel: true,
|
|
2550
|
+
sufficient: true
|
|
2551
|
+
},
|
|
2552
|
+
provenance: {
|
|
2553
|
+
baselineContentHash: "sha256:90b1cc05f0d389d95d856ad6fb3da6e0f0e382a10cfd1fdf4f778a56c56a0079",
|
|
2554
|
+
candidateContentHash: "sha256:406857e8226d46490a1ff07453439dcdb71bfaed26f87ed0ed4e42b3b5c83b79",
|
|
2555
|
+
kind: "agent-eval-loop",
|
|
2556
|
+
recordDigest: "sha256:6ee245f7c24f0a28c8f169bc2fef2d85db9dec9e66eff078798993be20885bb3",
|
|
2557
|
+
runId: "agent-runtime-0.101.1-proposal-fixture",
|
|
2558
|
+
schema: "agent-candidate-experiment"
|
|
2559
|
+
}
|
|
2560
|
+
},
|
|
2561
|
+
findings: [
|
|
2562
|
+
{
|
|
2563
|
+
analyst_id: "runtime-testing-fixture",
|
|
2564
|
+
area: "prompt",
|
|
2565
|
+
claim: "The baseline omits the exact measured answer.",
|
|
2566
|
+
confidence: 0.9,
|
|
2567
|
+
evidence_refs: [
|
|
2568
|
+
{
|
|
2569
|
+
id: "runtime-testing-fixture-span",
|
|
2570
|
+
kind: "span"
|
|
2571
|
+
}
|
|
2572
|
+
],
|
|
2573
|
+
finding_id: "runtime-testing-fixture-finding",
|
|
2574
|
+
produced_at: "2026-07-10T00:30:00.000Z",
|
|
2575
|
+
recommended_action: "Return the exact measured answer.",
|
|
2576
|
+
schema_version: "1.0.0",
|
|
2577
|
+
severity: "high",
|
|
2578
|
+
subject: "agent-profile:prompt.systemPrompt"
|
|
2579
|
+
}
|
|
2580
|
+
],
|
|
2581
|
+
kind: "agent-improvement-proposal",
|
|
2582
|
+
proposedAt: "2026-07-10T01:00:00.000Z",
|
|
2583
|
+
runId: "agent-runtime-0.101.1-proposal-fixture"
|
|
2584
|
+
};
|
|
2585
|
+
|
|
2586
|
+
// src/testing/index.ts
|
|
2587
|
+
var serializedAgentImprovementProposalFixture = JSON.stringify(
|
|
2588
|
+
agent_improvement_proposal_default
|
|
2589
|
+
);
|
|
2590
|
+
function loadAgentImprovementProposalFixture() {
|
|
2591
|
+
return verifyAgentImprovementProposal(JSON.parse(serializedAgentImprovementProposalFixture));
|
|
2592
|
+
}
|
|
2593
|
+
export {
|
|
2594
|
+
loadAgentImprovementProposalFixture
|
|
2595
|
+
};
|
|
2596
|
+
//# sourceMappingURL=testing.js.map
|