Skip to content

Commit c340db3

Browse files
committed
eval: preserve terminal v7 pair attempt
1 parent c4935e9 commit c340db3

31 files changed

Lines changed: 2079 additions & 0 deletions
Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
{
2+
"READY_FOR_72": false,
3+
"authorization": "approve the frozen range-large/v7-r1 pair",
4+
"binary_sha256": "e5198d15000e093a2a28e57ad4a093dde8f66bcab21462549ddf9114064c25f4",
5+
"full_run_authorized": false,
6+
"image_id": "sha256:589fce58d7ddf09910876afe0198bcee0086a840af6de7c08515bbce3e8367a7",
7+
"infrastructure_commit": "a8d2d8260ceed56baf0d1cf8fcc2f40776e9f7b6",
8+
"manifest_commit": "369f3c7c0d751da72fa658a2ec810557d6669e39",
9+
"manifest_sha256": "67789b85c08802a87f5d14bb72aa2d36068c43a45aa27187ddab5d66dba3eca4",
10+
"order": [
11+
"D1",
12+
"B0"
13+
],
14+
"pair_id": "range-large/v7-r1",
15+
"probe_authorized": false,
16+
"rerun_authorized": false,
17+
"schema_version": "deltawire-v7-pair-approval.v1",
18+
"six_run_canary_authorized": false
19+
}
Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
{
2+
"active_pair_processes": 0,
3+
"approval_sha256": "c6b493851951e72ead0d15e38231f47d036331f94ded94d9d3dceb38db7c3154",
4+
"bytes_scanned": 143725,
5+
"exact_credential_matches": 0,
6+
"files_scanned": 29,
7+
"generic_secret_matches": 0,
8+
"schema_version": "deltawire-v7-security-scan.v1",
9+
"status": "pass",
10+
"temporary_credential_files_remaining": 0
11+
}
Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
{
2+
"artifact_manifest_sha256": "0c8e85115c5bc9a68deb3aa39b84e4f734bdeb8b7742a97b72bc139b1192b386",
3+
"checks": {
4+
"binary_hash_frozen": true,
5+
"config_hash_frozen": true,
6+
"manifest_exists": true,
7+
"manifest_status_ok": true,
8+
"public_contract_hash_frozen": true,
9+
"receipt_canonical_path": true,
10+
"receipt_checks_complete": true,
11+
"receipt_checks_true": true,
12+
"receipt_schema_exact": true,
13+
"receipt_status_pass": true,
14+
"schema_hash_frozen": true,
15+
"single_convention_entry": true
16+
},
17+
"convention_entry": {
18+
"destination": "artifacts/logs/artifacts",
19+
"service": null,
20+
"source": "/logs/artifacts",
21+
"status": "ok",
22+
"type": "directory"
23+
},
24+
"environment_receipt_path": "/home/apple/deltawire-preflight-v7-frozen/labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/artifacts/logs/artifacts/deltawire/environment-receipt.json",
25+
"environment_receipt_sha256": "4a30e8e33d3dee9c4fcb4761da3e10c2a27c5dc4c2aca296e185e1eb758620b1",
26+
"schema_version": "artifact-manifest-receipt.v1",
27+
"status": "pass"
28+
}
Lines changed: 30 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,30 @@
1+
{
2+
"READY_FOR_72": false,
3+
"arm": "D1",
4+
"component_checks": {
5+
"artifact_manifest": true,
6+
"environment": true,
7+
"plan_contract": false,
8+
"semantic": true,
9+
"setup": true,
10+
"treatment": false
11+
},
12+
"identity_checks": {
13+
"agent_match": true,
14+
"harbor_exit_zero": true,
15+
"model_match": true,
16+
"trial_completed": true
17+
},
18+
"schema_version": "deltawire-end-to-end-receipt.v7",
19+
"source_hashes": {
20+
"artifact_manifest": "40cf6ddc54e657621f177afcb92e88a94eec553ef2f29d829174d920b86ab469",
21+
"environment": "4a30e8e33d3dee9c4fcb4761da3e10c2a27c5dc4c2aca296e185e1eb758620b1",
22+
"output": "9d205b57ab166d23c81927899f99b6ccece261c679c96979c58fbde975637776",
23+
"result": "22f50c59c4eac9f5f1a680572304f25a11270c3fb2caa66be584bbd9d7a3525b",
24+
"semantic": "09654564d33620bb4b39ae7cb64af13243078013118e6595adaf3a40af59cba0",
25+
"setup": "adca6d256d43f320bb542745bc37f58fcfa97db736eebcc2aa1ce885d84c5240",
26+
"trajectory": "d6659287d950b37b9ea1364e6256d715ce0220b652c45689355b79e623be7af5",
27+
"treatment": "298daa00fb33afe6f7a93b67028bcc243fe1ef809f58199f89b36d35438148aa"
28+
},
29+
"status": "fail"
30+
}
Lines changed: 55 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,55 @@
1+
{
2+
"binary": {
3+
"actual_sha256": "e5198d15000e093a2a28e57ad4a093dde8f66bcab21462549ddf9114064c25f4",
4+
"executable": true,
5+
"exists": true,
6+
"expected_sha256": "e5198d15000e093a2a28e57ad4a093dde8f66bcab21462549ddf9114064c25f4",
7+
"expected_version": "deltawire version dev",
8+
"is_regular": true,
9+
"is_symlink": false,
10+
"path": "/usr/local/bin/deltawire",
11+
"realpath": "/usr/local/bin/deltawire",
12+
"version_exit_code": 0,
13+
"version_stderr": "",
14+
"version_stdout": "deltawire version dev\nGo runtime version go1.26.5\nsupported config version deltawire.config.v1\nsupported plan version deltawire.plan.v1\nsupported state version deltawire.state.v1"
15+
},
16+
"checks": {
17+
"binary_executable": true,
18+
"binary_exists": true,
19+
"binary_hash": true,
20+
"binary_not_symlink": true,
21+
"binary_path": true,
22+
"binary_realpath": true,
23+
"binary_regular": true,
24+
"config_hash": true,
25+
"public_contract_hash": true,
26+
"schema_hash": true,
27+
"version_exact": true,
28+
"version_exit_0": true
29+
},
30+
"files": {
31+
"config": {
32+
"actual_sha256": "673b9cf053e3ba2263bfbc49034360ed8dba8d959bd167f8ff4b1f7cb4302b6f",
33+
"exists": true,
34+
"expected_sha256": "673b9cf053e3ba2263bfbc49034360ed8dba8d959bd167f8ff4b1f7cb4302b6f",
35+
"hash_match": true,
36+
"path": "/.deltawire/config.json"
37+
},
38+
"public_contract": {
39+
"actual_sha256": "d3e1b7b3e5a4576540b3a2969d59f49818c7c0a12197b26d271e7e277b0054e5",
40+
"exists": true,
41+
"expected_sha256": "d3e1b7b3e5a4576540b3a2969d59f49818c7c0a12197b26d271e7e277b0054e5",
42+
"hash_match": true,
43+
"path": "/task-contract.json"
44+
},
45+
"schema": {
46+
"actual_sha256": "2fe7bdc8de996a09ccc651f42611dc88faee60c7390b36c62443ed3e523800b5",
47+
"exists": true,
48+
"expected_sha256": "2fe7bdc8de996a09ccc651f42611dc88faee60c7390b36c62443ed3e523800b5",
49+
"hash_match": true,
50+
"path": "/.deltawire/schemas/range-large.schema.json"
51+
}
52+
},
53+
"schema_version": "deltawire-environment-receipt.v1",
54+
"status": "pass"
55+
}
Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
{
2+
"checks": {},
3+
"error": "expected one plan; found 0",
4+
"schema_version": "plan-contract-receipt.v1",
5+
"status": "fail"
6+
}
Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
{
2+
"exact_match": 1,
3+
"oracle": {
4+
"exact_match": 1
5+
},
6+
"schema_version": "semantic-result.v7",
7+
"status": "pass"
8+
}
Lines changed: 44 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,44 @@
1+
{
2+
"checks": {
3+
"agent_exact": true,
4+
"checks_exact": true,
5+
"checks_true": true,
6+
"gemini_path_exact": true,
7+
"gemini_version_exact": true,
8+
"image_id_exact": true,
9+
"no_timestamps": true,
10+
"node_path_exact": true,
11+
"node_version_exact": true,
12+
"npm_version_exact": true,
13+
"package_version_exact": true,
14+
"receipt_canonical_path": true,
15+
"receipt_exists": true,
16+
"schema_exact": true,
17+
"status_pass": true
18+
},
19+
"receipt": {
20+
"agent": "preinstalled-gemini-cli-v1",
21+
"checks": {
22+
"agent_identity": true,
23+
"gemini_executable": true,
24+
"gemini_version": true,
25+
"image_id": true,
26+
"node_executable": true,
27+
"node_version": true,
28+
"npm_version": true,
29+
"package_identity": true
30+
},
31+
"gemini_path": "/usr/local/bin/gemini",
32+
"gemini_version": "0.51.0",
33+
"image_id": "sha256:589fce58d7ddf09910876afe0198bcee0086a840af6de7c08515bbce3e8367a7",
34+
"node_path": "/usr/local/bin/node",
35+
"node_version": "v22.23.1",
36+
"npm_version": "10.9.8",
37+
"package_version": "0.51.0",
38+
"schema_version": "preinstalled-gemini-setup-receipt.v1",
39+
"status": "pass"
40+
},
41+
"receipt_sha256": "a88d221e573265997797dcad31136aec0ed74a5bd37e50887595e5ea85cfa0d1",
42+
"schema_version": "preinstalled-gemini-setup-validation.v1",
43+
"status": "pass"
44+
}
Lines changed: 131 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,131 @@
1+
{
2+
"arm": "D1",
3+
"artifact_hashes": {
4+
"config": "673b9cf053e3ba2263bfbc49034360ed8dba8d959bd167f8ff4b1f7cb4302b6f",
5+
"output": "9d205b57ab166d23c81927899f99b6ccece261c679c96979c58fbde975637776",
6+
"schema": "2fe7bdc8de996a09ccc651f42611dc88faee60c7390b36c62443ed3e523800b5",
7+
"state": "5e1cf20f1d0945a30accb87152086fc61c848cdf18ac46ad2f0fa65fbd5b8c76"
8+
},
9+
"assignment": {
10+
"checks": {
11+
"config_exactly_one_skill": true,
12+
"config_skill_name": true,
13+
"local_tree_hash": true,
14+
"lock_exactly_one_skill": true,
15+
"lock_skill_digest": true,
16+
"lock_skill_name": true
17+
},
18+
"status": "pass"
19+
},
20+
"checks": {
21+
"assignment_pass": true,
22+
"check_invoked": true,
23+
"check_not_proven_failed": true,
24+
"in_container_contract_pass": false,
25+
"independent_contract_pass": false,
26+
"public_contract_access": false,
27+
"render_invoked": true,
28+
"render_not_proven_failed": true,
29+
"retained_config": true,
30+
"retained_in_container_contract": false,
31+
"retained_output": true,
32+
"retained_plan": false,
33+
"retained_schema": true,
34+
"retained_state": true,
35+
"schema_integrity": true,
36+
"semantic_exact_pass": true,
37+
"structured_activation": true,
38+
"validate_invoked": true,
39+
"validate_not_proven_failed": true
40+
},
41+
"classification": "attempted_failed",
42+
"contamination": false,
43+
"diagnostics": {
44+
"binary_introspection": false,
45+
"direct_skill_read": true,
46+
"direct_validate_count": 1,
47+
"failed_direct_validate_count": 0,
48+
"gemini_skills_list_observed": false,
49+
"matching_example_read": true,
50+
"reference_read": true,
51+
"subprocess_bruteforce_loops": 0
52+
},
53+
"lifecycle_invocations": [
54+
{
55+
"command": "validate",
56+
"invocation": "deltawire validate --repo . plan.json",
57+
"shell_exit_code": null
58+
},
59+
{
60+
"command": "render",
61+
"invocation": "deltawire render --repo . plan.json",
62+
"shell_exit_code": null
63+
},
64+
{
65+
"command": "check",
66+
"invocation": "deltawire check --repo . plan.json",
67+
"shell_exit_code": null
68+
}
69+
],
70+
"schema_version": "deltawire-treatment-receipt.v7",
71+
"shell_observations": [
72+
{
73+
"command": "deltawire validate --repo . plan.json",
74+
"observable": true,
75+
"shell_exit_code": null,
76+
"shell_exit_provenance": null,
77+
"tool_status": "success"
78+
},
79+
{
80+
"command": "find / -maxdepth 3 -name \"*contract*check*\" -o -name \"*check*contract*\" 2>/dev/null",
81+
"observable": true,
82+
"shell_exit_code": null,
83+
"shell_exit_provenance": null,
84+
"tool_status": "success"
85+
},
86+
{
87+
"command": "ls -l /usr/local/bin | grep check",
88+
"observable": true,
89+
"shell_exit_code": 1,
90+
"shell_exit_provenance": "explicit_output",
91+
"tool_status": "success"
92+
},
93+
{
94+
"command": "ls -l /usr/local/bin",
95+
"observable": true,
96+
"shell_exit_code": null,
97+
"shell_exit_provenance": null,
98+
"tool_status": "success"
99+
},
100+
{
101+
"command": "verify_plan_contract.py plan.json",
102+
"observable": true,
103+
"shell_exit_code": 2,
104+
"shell_exit_provenance": "explicit_output",
105+
"tool_status": "success"
106+
},
107+
{
108+
"command": "verify_plan_contract.py --contract task-contract.json --plan plan.json",
109+
"observable": true,
110+
"shell_exit_code": null,
111+
"shell_exit_provenance": null,
112+
"tool_status": "success"
113+
},
114+
{
115+
"command": "deltawire render --repo . plan.json",
116+
"observable": true,
117+
"shell_exit_code": null,
118+
"shell_exit_provenance": null,
119+
"tool_status": "success"
120+
},
121+
{
122+
"command": "deltawire check --repo . plan.json",
123+
"observable": true,
124+
"shell_exit_code": null,
125+
"shell_exit_provenance": null,
126+
"tool_status": "success"
127+
}
128+
],
129+
"status": "fail",
130+
"trajectory_sha256": "d6659287d950b37b9ea1364e6256d715ce0220b652c45689355b79e623be7af5"
131+
}
Lines changed: 44 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,44 @@
1+
{
2+
"READY_FOR_72": false,
3+
"file_count": 33,
4+
"files": {
5+
"labs/20-deltawire/eval/results/preflight-v7/pair-approval.json": "c6b493851951e72ead0d15e38231f47d036331f94ded94d9d3dceb38db7c3154",
6+
"labs/20-deltawire/eval/results/preflight-v7/pair-security-scan.json": "4ab32a7795109d3973bd8665dbe60df485c6ac0af25b0b2e752e15a448650411",
7+
"labs/20-deltawire/eval/results/preflight-v7/skill-conformance.json": "4d0e142a1bc801642b5de8c77b9cbebc9680a42f6f64da95b3d48b8624fe7c46",
8+
"labs/20-deltawire/eval/results/range-large-v7-r1/D1-artifact-manifest.json": "40cf6ddc54e657621f177afcb92e88a94eec553ef2f29d829174d920b86ab469",
9+
"labs/20-deltawire/eval/results/range-large-v7-r1/D1-end-to-end.json": "207e6e300158c9d87b92589c412a7ae15aa732549dbb7bdaa8654a366efc62e1",
10+
"labs/20-deltawire/eval/results/range-large-v7-r1/D1-environment.json": "4a30e8e33d3dee9c4fcb4761da3e10c2a27c5dc4c2aca296e185e1eb758620b1",
11+
"labs/20-deltawire/eval/results/range-large-v7-r1/D1-plan-contract-receipt.json": "d3c6d569d9353120583551f280753e457683c2b886594cda291b93b4e30515a3",
12+
"labs/20-deltawire/eval/results/range-large-v7-r1/D1-semantic-result.json": "09654564d33620bb4b39ae7cb64af13243078013118e6595adaf3a40af59cba0",
13+
"labs/20-deltawire/eval/results/range-large-v7-r1/D1-setup.json": "adca6d256d43f320bb542745bc37f58fcfa97db736eebcc2aa1ce885d84c5240",
14+
"labs/20-deltawire/eval/results/range-large-v7-r1/D1-treatment.json": "298daa00fb33afe6f7a93b67028bcc243fe1ef809f58199f89b36d35438148aa",
15+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/config.json": "27de86441290364f9bc0c6c66854b4bc0194f591b909dbaf275b628f40471728",
16+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/job.log": "ad20c3e97e7c89bf6f07934e3cc709c4880709c400461527d363ea53ba121dfe",
17+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/lock.json": "0a58888ac484406279a52b2109f9aa8215cc7890204b7ff2f17022bd5d703286",
18+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/agent/gemini-cli.trajectory.jsonl": "d6659287d950b37b9ea1364e6256d715ce0220b652c45689355b79e623be7af5",
19+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/agent/gemini-cli.txt": "54e1b5e6d019e43be0e7141827f3dccb32b4a613792551ca6b80e08452e9ee6c",
20+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/agent/trajectory.json": "d6c4bae360f51d98c467028fa0354f351e8b98d6b157b19baae328ea5f514db5",
21+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/artifacts/.deltawire/config.json": "673b9cf053e3ba2263bfbc49034360ed8dba8d959bd167f8ff4b1f7cb4302b6f",
22+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/artifacts/.deltawire/schemas/range-large.schema.json": "2fe7bdc8de996a09ccc651f42611dc88faee60c7390b36c62443ed3e523800b5",
23+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/artifacts/.deltawire/state.json": "5e1cf20f1d0945a30accb87152086fc61c848cdf18ac46ad2f0fa65fbd5b8c76",
24+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/artifacts/logs/artifacts/deltawire/environment-receipt.json": "4a30e8e33d3dee9c4fcb4761da3e10c2a27c5dc4c2aca296e185e1eb758620b1",
25+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/artifacts/logs/artifacts/preinstalled-gemini/setup-receipt.json": "a88d221e573265997797dcad31136aec0ed74a5bd37e50887595e5ea85cfa0d1",
26+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/artifacts/manifest.json": "0c8e85115c5bc9a68deb3aa39b84e4f734bdeb8b7742a97b72bc139b1192b386",
27+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/artifacts/testdata/generated/output.ndjson": "9d205b57ab166d23c81927899f99b6ccece261c679c96979c58fbde975637776",
28+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/config.json": "0768e4213b3a05725c0ef62c851d2c0bd902b102dfa134de749cfe2e992f5bad",
29+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/lock.json": "5a931c5b1058e58b3792de2f7a9303139778180b3efedc2d3b91081ef14679a3",
30+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/result.json": "22f50c59c4eac9f5f1a680572304f25a11270c3fb2caa66be584bbd9d7a3525b",
31+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/trial.log": "ad20c3e97e7c89bf6f07934e3cc709c4880709c400461527d363ea53ba121dfe",
32+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/verifier/reward.json": "36a492513204040f04d7bdf4146d84ede71353d8cc7df112fc3ebff66327683a",
33+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/range-large-v7-r1__3wEHYmv/verifier/test-stdout.txt": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
34+
"labs/20-deltawire/eval/results/range-large-v7-r1/raw/D1/2026-07-22__19-57-08/result.json": "5596535bf83df1d66ae5fa4f6388734fd456a6825505e7f6ad11295552c48cb3",
35+
"labs/20-deltawire/eval/results/range-large-v7-r1/readiness.json": "93124d41c2c3c66043bf5fa46673893faf31737bdfcada75656320a98ea543e9",
36+
"labs/20-deltawire/eval/results/range-large-v7-r1/run-ledger.json": "8b4438d59fffcc5b193c68cae268d400f30200bc28b2156249d978f544b5f541",
37+
"labs/20-deltawire/eval/results/range-large-v7-r1/terminal-report.json": "86dcc3abf7f998089ebdfed173322a7db96e28a36eac7eb9a5087630b89a85aa"
38+
},
39+
"pair_id": "range-large/v7-r1",
40+
"pair_valid": false,
41+
"rerun_authorized": false,
42+
"schema_version": "deltawire-v7-evidence-closure.v1",
43+
"status": "closed"
44+
}

0 commit comments

Comments
 (0)