@agent-delivery-harness/conformance 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (101) hide show
  1. package/LICENSE +202 -0
  2. package/NOTICE +5 -0
  3. package/README.md +159 -0
  4. package/fixtures/repo-config-adapter.ts +250 -0
  5. package/package.json +24 -0
  6. package/src/generate.ts +1013 -0
  7. package/src/index.ts +36 -0
  8. package/src/json-schema.ts +222 -0
  9. package/src/runner.ts +687 -0
  10. package/vectors/context/environment.json +21 -0
  11. package/vectors/context/repo-config.json +22 -0
  12. package/vectors/kit.json +1250 -0
  13. package/vectors/vectors/accept/a-completed-order-differs.json +112 -0
  14. package/vectors/vectors/accept/a-cost-fractional.json +116 -0
  15. package/vectors/vectors/accept/a-cost-tokens.json +120 -0
  16. package/vectors/vectors/accept/a-deferred-expansion.json +124 -0
  17. package/vectors/vectors/accept/a-idempotent-resubmission.json +115 -0
  18. package/vectors/vectors/accept/a-minimal-green.json +97 -0
  19. package/vectors/vectors/accept/a-resolved-and-advisory.json +129 -0
  20. package/vectors/vectors/accept/a-three-reviewers.json +113 -0
  21. package/vectors/vectors/reject/env-1-unregistered-provider.json +114 -0
  22. package/vectors/vectors/reject/env-10-artifact-duplicate.json +103 -0
  23. package/vectors/vectors/reject/env-10-artifact-missing-file.json +104 -0
  24. package/vectors/vectors/reject/env-10-artifact-traversal.json +99 -0
  25. package/vectors/vectors/reject/env-11-artifact-digest-mismatch.json +98 -0
  26. package/vectors/vectors/reject/env-12-unknown-attestation-level.json +114 -0
  27. package/vectors/vectors/reject/env-13-nonempty-signatures.json +118 -0
  28. package/vectors/vectors/reject/env-14-duplicate-claim.json +149 -0
  29. package/vectors/vectors/reject/env-14-no-claims.json +78 -0
  30. package/vectors/vectors/reject/env-14-unconfigured-obligation.json +114 -0
  31. package/vectors/vectors/reject/env-14-unsupported-payload-spec.json +114 -0
  32. package/vectors/vectors/reject/env-2-run-id-1.json +114 -0
  33. package/vectors/vectors/reject/env-2-run-id-2.json +114 -0
  34. package/vectors/vectors/reject/env-2-run-id-3.json +114 -0
  35. package/vectors/vectors/reject/env-2-run-id-4.json +114 -0
  36. package/vectors/vectors/reject/env-2-run-id-5.json +114 -0
  37. package/vectors/vectors/reject/env-4-unsupported-vcs.json +114 -0
  38. package/vectors/vectors/reject/env-5-malformed-object-id.json +114 -0
  39. package/vectors/vectors/reject/env-6-missing-identity.json +111 -0
  40. package/vectors/vectors/reject/env-6-unknown-identity-version.json +114 -0
  41. package/vectors/vectors/reject/env-8-repository-required.json +116 -0
  42. package/vectors/vectors/reject/env-9-empty-run-history.json +107 -0
  43. package/vectors/vectors/reject/env-9-final-pass-mismatch.json +110 -0
  44. package/vectors/vectors/reject/env-9-final-tree-mismatch.json +110 -0
  45. package/vectors/vectors/reject/gen-1-legacy-count-field.json +115 -0
  46. package/vectors/vectors/reject/gen-1-unknown-envelope-member.json +117 -0
  47. package/vectors/vectors/reject/gen-2-unsupported-spec.json +114 -0
  48. package/vectors/vectors/reject/rg-1-edited-after-final-pass.json +114 -0
  49. package/vectors/vectors/reject/rg-1-not-finalized.json +114 -0
  50. package/vectors/vectors/reject/rg-1-verdict-not-green.json +114 -0
  51. package/vectors/vectors/reject/rg-10-cost-by-reviewer-exceeds-total.json +115 -0
  52. package/vectors/vectors/reject/rg-10-cost-empty-reported-by.json +111 -0
  53. package/vectors/vectors/reject/rg-10-cost-empty-unit.json +111 -0
  54. package/vectors/vectors/reject/rg-10-cost-missing-unit.json +110 -0
  55. package/vectors/vectors/reject/rg-10-cost-negative-by-reviewer.json +114 -0
  56. package/vectors/vectors/reject/rg-10-cost-negative-total.json +111 -0
  57. package/vectors/vectors/reject/rg-10-cost-null-total.json +111 -0
  58. package/vectors/vectors/reject/rg-10-cost-unknown-reviewer-in-breakdown.json +114 -0
  59. package/vectors/vectors/reject/rg-2-duplicate-selected.json +99 -0
  60. package/vectors/vectors/reject/rg-3-completed-missing.json +96 -0
  61. package/vectors/vectors/reject/rg-3-completed-unrelated.json +99 -0
  62. package/vectors/vectors/reject/rg-3-failed-reviewer.json +100 -0
  63. package/vectors/vectors/reject/rg-3-timed-out-reviewer.json +100 -0
  64. package/vectors/vectors/reject/rg-4-approval-extra.json +104 -0
  65. package/vectors/vectors/reject/rg-4-approval-malformed.json +98 -0
  66. package/vectors/vectors/reject/rg-4-approval-missing.json +100 -0
  67. package/vectors/vectors/reject/rg-4-approval-not-approved.json +98 -0
  68. package/vectors/vectors/reject/rg-4-approval-wrong-candidate.json +98 -0
  69. package/vectors/vectors/reject/rg-4-approval-wrong-pass.json +98 -0
  70. package/vectors/vectors/reject/rg-4-approval-wrong-provider.json +98 -0
  71. package/vectors/vectors/reject/rg-4-approval-wrong-reviewer.json +98 -0
  72. package/vectors/vectors/reject/rg-4-approval-wrong-run.json +98 -0
  73. package/vectors/vectors/reject/rg-4-approval-wrong-workspace.json +98 -0
  74. package/vectors/vectors/reject/rg-5-duplicate-finding-id.json +131 -0
  75. package/vectors/vectors/reject/rg-5-unknown-disposition.json +123 -0
  76. package/vectors/vectors/reject/rg-5-unknown-scope.json +123 -0
  77. package/vectors/vectors/reject/rg-5-unknown-severity.json +123 -0
  78. package/vectors/vectors/reject/rg-6-actionable-ignored.json +123 -0
  79. package/vectors/vectors/reject/rg-6-actionable-unresolved.json +123 -0
  80. package/vectors/vectors/reject/rg-6-blocking-finding.json +123 -0
  81. package/vectors/vectors/reject/rg-7-defer-adjacent.json +126 -0
  82. package/vectors/vectors/reject/rg-7-defer-blocking.json +126 -0
  83. package/vectors/vectors/reject/rg-7-defer-in-contract.json +126 -0
  84. package/vectors/vectors/reject/rg-7-defer-lowercase-issue-id.json +126 -0
  85. package/vectors/vectors/reject/rg-7-defer-missing-issue-id.json +125 -0
  86. package/vectors/vectors/reject/rg-7-defer-non-actionable.json +126 -0
  87. package/vectors/vectors/reject/rg-7-defer-p0.json +126 -0
  88. package/vectors/vectors/reject/rg-7-defer-p1.json +126 -0
  89. package/vectors/vectors/reject/rg-7-defer-placeholder-issue-id.json +126 -0
  90. package/vectors/vectors/reject/rg-7-issue-id-on-resolved.json +124 -0
  91. package/vectors/vectors/reject/rg-8-counts-contradict-findings.json +126 -0
  92. package/vectors/vectors/reject/rg-8-deferral-count-disagrees.json +124 -0
  93. package/vectors/vectors/reject/rg-8-deferral-ids-disagree.json +126 -0
  94. package/vectors/vectors/reject/rg-9-iteration-count-mismatch.json +114 -0
  95. package/vectors/vectors/reject/sub-1-base-tip-moved.json +131 -0
  96. package/vectors/vectors/reject/sub-1-deliverable-changed.json +131 -0
  97. package/vectors/vectors/reject/sub-1-merge-base-moved.json +131 -0
  98. package/vectors/vectors/reject/sub-1-raw-tree-changed.json +131 -0
  99. package/vectors/vectors/reject/sub-2-unprepared.json +117 -0
  100. package/vectors/vectors/reject/sub-3-manifest-outside-run-root.json +117 -0
  101. package/vectors/vectors/reject/sub-4-record-conflict.json +220 -0
@@ -0,0 +1,112 @@
1
+ {
2
+ "vectorVersion": 1,
3
+ "id": "a-completed-order-differs",
4
+ "title": "completed lists the same reviewers in a different order",
5
+ "rules": [
6
+ "RG-3"
7
+ ],
8
+ "provenance": "delivery-evidence/1 (new in spec; no Athena antecedent)",
9
+ "expect": {
10
+ "result": "accepted",
11
+ "notes": "Set equality, not sequence equality."
12
+ },
13
+ "artifacts": {
14
+ "reviewers/correctness.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"correctness\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n",
15
+ "reviewers/security.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"security\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n",
16
+ "reviewers/tests.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"tests\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n"
17
+ },
18
+ "manifest": {
19
+ "spec": "delivery-evidence/1",
20
+ "provider": {
21
+ "id": "claude-code.ce-code-review",
22
+ "version": "1.0.0",
23
+ "runId": "r-conformance-01",
24
+ "finalPassId": "pass-2"
25
+ },
26
+ "candidate": {
27
+ "vcs": "git",
28
+ "treeSha": "3dd16b56e3035a4c9f3d591f55edde08a4107990",
29
+ "headSha": "31740476c0227fc5c77b00c37aff24d03d692e47",
30
+ "deliverable": {
31
+ "digest": "c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9",
32
+ "identity": "deliverable-tree/v1"
33
+ },
34
+ "base": {
35
+ "ref": "origin/main",
36
+ "tipSha": "8248f1bc1cf32509843ef77387841c8ea06245cb",
37
+ "mergeBaseSha": "892135fcf4acee18bebcefd8398192fd0faf1293"
38
+ },
39
+ "workspaceId": "w-0dcf2d98505da17d"
40
+ },
41
+ "repository": null,
42
+ "runHistory": [
43
+ {
44
+ "preparedTreeSha": "132c7f8efa52032271d4f06fc0cb9e264a05e0e1",
45
+ "evaluatedInPassId": "pass-1"
46
+ },
47
+ {
48
+ "preparedTreeSha": "3dd16b56e3035a4c9f3d591f55edde08a4107990",
49
+ "evaluatedInPassId": "pass-2"
50
+ }
51
+ ],
52
+ "artifacts": [
53
+ {
54
+ "path": "reviewers/correctness.json",
55
+ "sha256": "128b2a9756c778c36ce29b4390e944c2f05438904d1953a0bed4027f55e1ede8",
56
+ "role": "reviewer-approval"
57
+ },
58
+ {
59
+ "path": "reviewers/security.json",
60
+ "sha256": "4933efc56d9e3fe6173f31b703ba7c41cb7490cbd2f5538b5b5ef2a7cc8fa03e",
61
+ "role": "reviewer-approval"
62
+ },
63
+ {
64
+ "path": "reviewers/tests.json",
65
+ "sha256": "3ec8364e062dcfc9f631262d9d36afc750f49080483755767345fcc22c1b1e42",
66
+ "role": "reviewer-approval"
67
+ }
68
+ ],
69
+ "attestation": {
70
+ "level": "self",
71
+ "signatures": []
72
+ },
73
+ "recordedAt": "2026-08-25T00:00:00Z",
74
+ "claims": [
75
+ {
76
+ "obligation": "review.green",
77
+ "payloadSpec": "review.green/1",
78
+ "payload": {
79
+ "verdict": "green",
80
+ "finalized": true,
81
+ "editedAfterFinalPass": false,
82
+ "reviewers": {
83
+ "selected": [
84
+ "correctness",
85
+ "security",
86
+ "tests"
87
+ ],
88
+ "completed": [
89
+ "tests",
90
+ "correctness",
91
+ "security"
92
+ ],
93
+ "failed": [],
94
+ "timedOut": []
95
+ },
96
+ "findings": [],
97
+ "telemetry": {
98
+ "iterationCount": 2,
99
+ "findingCounts": {
100
+ "P0": 0,
101
+ "P1": 0,
102
+ "P2": 0,
103
+ "P3": 0
104
+ },
105
+ "deferredExpansionCount": 0,
106
+ "deferredIssueIds": []
107
+ }
108
+ }
109
+ }
110
+ ]
111
+ }
112
+ }
@@ -0,0 +1,116 @@
1
+ {
2
+ "vectorVersion": 1,
3
+ "id": "a-cost-fractional",
4
+ "title": "Fractional cost units from a platform's own metering",
5
+ "rules": [
6
+ "RG-10"
7
+ ],
8
+ "provenance": "athena:scripts/harness-review-evidence.test.ts \"platform metering fractional units\"",
9
+ "expect": {
10
+ "result": "accepted"
11
+ },
12
+ "artifacts": {
13
+ "reviewers/correctness.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"correctness\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n",
14
+ "reviewers/security.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"security\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n",
15
+ "reviewers/tests.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"tests\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n"
16
+ },
17
+ "manifest": {
18
+ "spec": "delivery-evidence/1",
19
+ "provider": {
20
+ "id": "claude-code.ce-code-review",
21
+ "version": "1.0.0",
22
+ "runId": "r-conformance-01",
23
+ "finalPassId": "pass-2"
24
+ },
25
+ "candidate": {
26
+ "vcs": "git",
27
+ "treeSha": "3dd16b56e3035a4c9f3d591f55edde08a4107990",
28
+ "headSha": "31740476c0227fc5c77b00c37aff24d03d692e47",
29
+ "deliverable": {
30
+ "digest": "c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9",
31
+ "identity": "deliverable-tree/v1"
32
+ },
33
+ "base": {
34
+ "ref": "origin/main",
35
+ "tipSha": "8248f1bc1cf32509843ef77387841c8ea06245cb",
36
+ "mergeBaseSha": "892135fcf4acee18bebcefd8398192fd0faf1293"
37
+ },
38
+ "workspaceId": "w-0dcf2d98505da17d"
39
+ },
40
+ "repository": null,
41
+ "runHistory": [
42
+ {
43
+ "preparedTreeSha": "132c7f8efa52032271d4f06fc0cb9e264a05e0e1",
44
+ "evaluatedInPassId": "pass-1"
45
+ },
46
+ {
47
+ "preparedTreeSha": "3dd16b56e3035a4c9f3d591f55edde08a4107990",
48
+ "evaluatedInPassId": "pass-2"
49
+ }
50
+ ],
51
+ "artifacts": [
52
+ {
53
+ "path": "reviewers/correctness.json",
54
+ "sha256": "128b2a9756c778c36ce29b4390e944c2f05438904d1953a0bed4027f55e1ede8",
55
+ "role": "reviewer-approval"
56
+ },
57
+ {
58
+ "path": "reviewers/security.json",
59
+ "sha256": "4933efc56d9e3fe6173f31b703ba7c41cb7490cbd2f5538b5b5ef2a7cc8fa03e",
60
+ "role": "reviewer-approval"
61
+ },
62
+ {
63
+ "path": "reviewers/tests.json",
64
+ "sha256": "3ec8364e062dcfc9f631262d9d36afc750f49080483755767345fcc22c1b1e42",
65
+ "role": "reviewer-approval"
66
+ }
67
+ ],
68
+ "attestation": {
69
+ "level": "self",
70
+ "signatures": []
71
+ },
72
+ "recordedAt": "2026-08-25T00:00:00Z",
73
+ "claims": [
74
+ {
75
+ "obligation": "review.green",
76
+ "payloadSpec": "review.green/1",
77
+ "payload": {
78
+ "verdict": "green",
79
+ "finalized": true,
80
+ "editedAfterFinalPass": false,
81
+ "reviewers": {
82
+ "selected": [
83
+ "correctness",
84
+ "security",
85
+ "tests"
86
+ ],
87
+ "completed": [
88
+ "correctness",
89
+ "security",
90
+ "tests"
91
+ ],
92
+ "failed": [],
93
+ "timedOut": []
94
+ },
95
+ "findings": [],
96
+ "telemetry": {
97
+ "iterationCount": 2,
98
+ "findingCounts": {
99
+ "P0": 0,
100
+ "P1": 0,
101
+ "P2": 0,
102
+ "P3": 0
103
+ },
104
+ "deferredExpansionCount": 0,
105
+ "deferredIssueIds": [],
106
+ "cost": {
107
+ "unit": "credits",
108
+ "total": 12.5,
109
+ "reportedBy": "some-other-runtime"
110
+ }
111
+ }
112
+ }
113
+ }
114
+ ]
115
+ }
116
+ }
@@ -0,0 +1,120 @@
1
+ {
2
+ "vectorVersion": 1,
3
+ "id": "a-cost-tokens",
4
+ "title": "Self-reported token cost with per-reviewer breakdown summing below total",
5
+ "rules": [
6
+ "RG-10"
7
+ ],
8
+ "provenance": "athena:scripts/harness-review-evidence.test.ts \"records a self-reported review cost\"",
9
+ "expect": {
10
+ "result": "accepted"
11
+ },
12
+ "artifacts": {
13
+ "reviewers/correctness.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"correctness\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n",
14
+ "reviewers/security.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"security\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n",
15
+ "reviewers/tests.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"tests\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n"
16
+ },
17
+ "manifest": {
18
+ "spec": "delivery-evidence/1",
19
+ "provider": {
20
+ "id": "claude-code.ce-code-review",
21
+ "version": "1.0.0",
22
+ "runId": "r-conformance-01",
23
+ "finalPassId": "pass-2"
24
+ },
25
+ "candidate": {
26
+ "vcs": "git",
27
+ "treeSha": "3dd16b56e3035a4c9f3d591f55edde08a4107990",
28
+ "headSha": "31740476c0227fc5c77b00c37aff24d03d692e47",
29
+ "deliverable": {
30
+ "digest": "c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9",
31
+ "identity": "deliverable-tree/v1"
32
+ },
33
+ "base": {
34
+ "ref": "origin/main",
35
+ "tipSha": "8248f1bc1cf32509843ef77387841c8ea06245cb",
36
+ "mergeBaseSha": "892135fcf4acee18bebcefd8398192fd0faf1293"
37
+ },
38
+ "workspaceId": "w-0dcf2d98505da17d"
39
+ },
40
+ "repository": null,
41
+ "runHistory": [
42
+ {
43
+ "preparedTreeSha": "132c7f8efa52032271d4f06fc0cb9e264a05e0e1",
44
+ "evaluatedInPassId": "pass-1"
45
+ },
46
+ {
47
+ "preparedTreeSha": "3dd16b56e3035a4c9f3d591f55edde08a4107990",
48
+ "evaluatedInPassId": "pass-2"
49
+ }
50
+ ],
51
+ "artifacts": [
52
+ {
53
+ "path": "reviewers/correctness.json",
54
+ "sha256": "128b2a9756c778c36ce29b4390e944c2f05438904d1953a0bed4027f55e1ede8",
55
+ "role": "reviewer-approval"
56
+ },
57
+ {
58
+ "path": "reviewers/security.json",
59
+ "sha256": "4933efc56d9e3fe6173f31b703ba7c41cb7490cbd2f5538b5b5ef2a7cc8fa03e",
60
+ "role": "reviewer-approval"
61
+ },
62
+ {
63
+ "path": "reviewers/tests.json",
64
+ "sha256": "3ec8364e062dcfc9f631262d9d36afc750f49080483755767345fcc22c1b1e42",
65
+ "role": "reviewer-approval"
66
+ }
67
+ ],
68
+ "attestation": {
69
+ "level": "self",
70
+ "signatures": []
71
+ },
72
+ "recordedAt": "2026-08-25T00:00:00Z",
73
+ "claims": [
74
+ {
75
+ "obligation": "review.green",
76
+ "payloadSpec": "review.green/1",
77
+ "payload": {
78
+ "verdict": "green",
79
+ "finalized": true,
80
+ "editedAfterFinalPass": false,
81
+ "reviewers": {
82
+ "selected": [
83
+ "correctness",
84
+ "security",
85
+ "tests"
86
+ ],
87
+ "completed": [
88
+ "correctness",
89
+ "security",
90
+ "tests"
91
+ ],
92
+ "failed": [],
93
+ "timedOut": []
94
+ },
95
+ "findings": [],
96
+ "telemetry": {
97
+ "iterationCount": 2,
98
+ "findingCounts": {
99
+ "P0": 0,
100
+ "P1": 0,
101
+ "P2": 0,
102
+ "P3": 0
103
+ },
104
+ "deferredExpansionCount": 0,
105
+ "deferredIssueIds": [],
106
+ "cost": {
107
+ "unit": "tokens",
108
+ "total": 512345,
109
+ "reportedBy": "claude-code",
110
+ "byReviewer": {
111
+ "correctness": 190000,
112
+ "security": 150000
113
+ }
114
+ }
115
+ }
116
+ }
117
+ }
118
+ ]
119
+ }
120
+ }
@@ -0,0 +1,124 @@
1
+ {
2
+ "vectorVersion": 1,
3
+ "id": "a-deferred-expansion",
4
+ "title": "Deferred P2 expansion finding with a tracker id and matching telemetry",
5
+ "rules": [
6
+ "RG-7",
7
+ "RG-8"
8
+ ],
9
+ "provenance": "athena:scripts/harness-review-evidence.test.ts \"records a deferred expansion finding\"",
10
+ "expect": {
11
+ "result": "accepted"
12
+ },
13
+ "artifacts": {
14
+ "reviewers/correctness.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"correctness\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n",
15
+ "reviewers/security.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"security\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n",
16
+ "reviewers/tests.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"tests\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n"
17
+ },
18
+ "manifest": {
19
+ "spec": "delivery-evidence/1",
20
+ "provider": {
21
+ "id": "claude-code.ce-code-review",
22
+ "version": "1.0.0",
23
+ "runId": "r-conformance-01",
24
+ "finalPassId": "pass-2"
25
+ },
26
+ "candidate": {
27
+ "vcs": "git",
28
+ "treeSha": "3dd16b56e3035a4c9f3d591f55edde08a4107990",
29
+ "headSha": "31740476c0227fc5c77b00c37aff24d03d692e47",
30
+ "deliverable": {
31
+ "digest": "c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9",
32
+ "identity": "deliverable-tree/v1"
33
+ },
34
+ "base": {
35
+ "ref": "origin/main",
36
+ "tipSha": "8248f1bc1cf32509843ef77387841c8ea06245cb",
37
+ "mergeBaseSha": "892135fcf4acee18bebcefd8398192fd0faf1293"
38
+ },
39
+ "workspaceId": "w-0dcf2d98505da17d"
40
+ },
41
+ "repository": null,
42
+ "runHistory": [
43
+ {
44
+ "preparedTreeSha": "132c7f8efa52032271d4f06fc0cb9e264a05e0e1",
45
+ "evaluatedInPassId": "pass-1"
46
+ },
47
+ {
48
+ "preparedTreeSha": "3dd16b56e3035a4c9f3d591f55edde08a4107990",
49
+ "evaluatedInPassId": "pass-2"
50
+ }
51
+ ],
52
+ "artifacts": [
53
+ {
54
+ "path": "reviewers/correctness.json",
55
+ "sha256": "128b2a9756c778c36ce29b4390e944c2f05438904d1953a0bed4027f55e1ede8",
56
+ "role": "reviewer-approval"
57
+ },
58
+ {
59
+ "path": "reviewers/security.json",
60
+ "sha256": "4933efc56d9e3fe6173f31b703ba7c41cb7490cbd2f5538b5b5ef2a7cc8fa03e",
61
+ "role": "reviewer-approval"
62
+ },
63
+ {
64
+ "path": "reviewers/tests.json",
65
+ "sha256": "3ec8364e062dcfc9f631262d9d36afc750f49080483755767345fcc22c1b1e42",
66
+ "role": "reviewer-approval"
67
+ }
68
+ ],
69
+ "attestation": {
70
+ "level": "self",
71
+ "signatures": []
72
+ },
73
+ "recordedAt": "2026-08-25T00:00:00Z",
74
+ "claims": [
75
+ {
76
+ "obligation": "review.green",
77
+ "payloadSpec": "review.green/1",
78
+ "payload": {
79
+ "verdict": "green",
80
+ "finalized": true,
81
+ "editedAfterFinalPass": false,
82
+ "reviewers": {
83
+ "selected": [
84
+ "correctness",
85
+ "security",
86
+ "tests"
87
+ ],
88
+ "completed": [
89
+ "correctness",
90
+ "security",
91
+ "tests"
92
+ ],
93
+ "failed": [],
94
+ "timedOut": []
95
+ },
96
+ "findings": [
97
+ {
98
+ "id": "f-def-1",
99
+ "severity": "P2",
100
+ "scope": "expansion",
101
+ "actionable": true,
102
+ "blocking": false,
103
+ "disposition": "deferred",
104
+ "deferredIssueId": "EX-1300"
105
+ }
106
+ ],
107
+ "telemetry": {
108
+ "iterationCount": 2,
109
+ "findingCounts": {
110
+ "P0": 0,
111
+ "P1": 0,
112
+ "P2": 1,
113
+ "P3": 0
114
+ },
115
+ "deferredExpansionCount": 1,
116
+ "deferredIssueIds": [
117
+ "EX-1300"
118
+ ]
119
+ }
120
+ }
121
+ }
122
+ ]
123
+ }
124
+ }
@@ -0,0 +1,115 @@
1
+ {
2
+ "vectorVersion": 1,
3
+ "id": "a-idempotent-resubmission",
4
+ "title": "Identical resubmission is an idempotent success with the same record ids",
5
+ "rules": [
6
+ "SUB-4"
7
+ ],
8
+ "provenance": "athena:scripts/harness-review-evidence.test.ts \"is idempotent for the same provider run, pass, and candidate\"",
9
+ "expect": {
10
+ "result": "accepted",
11
+ "notes": "Submit twice; both succeed and record ids are identical across submissions."
12
+ },
13
+ "extra": {
14
+ "submitTwice": true
15
+ },
16
+ "artifacts": {
17
+ "reviewers/correctness.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"correctness\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n",
18
+ "reviewers/security.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"security\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n",
19
+ "reviewers/tests.json": "{\n \"schemaVersion\": 1,\n \"reviewerId\": \"tests\",\n \"result\": \"approved\",\n \"provider\": {\n \"id\": \"claude-code.ce-code-review\",\n \"runId\": \"r-conformance-01\",\n \"finalPassId\": \"pass-2\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\",\n \"candidate\": {\n \"vcs\": \"git\",\n \"treeSha\": \"3dd16b56e3035a4c9f3d591f55edde08a4107990\",\n \"headSha\": \"31740476c0227fc5c77b00c37aff24d03d692e47\",\n \"deliverable\": {\n \"digest\": \"c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9\",\n \"identity\": \"deliverable-tree/v1\"\n },\n \"base\": {\n \"ref\": \"origin/main\",\n \"tipSha\": \"8248f1bc1cf32509843ef77387841c8ea06245cb\",\n \"mergeBaseSha\": \"892135fcf4acee18bebcefd8398192fd0faf1293\"\n },\n \"workspaceId\": \"w-0dcf2d98505da17d\"\n }\n}\n"
20
+ },
21
+ "manifest": {
22
+ "spec": "delivery-evidence/1",
23
+ "provider": {
24
+ "id": "claude-code.ce-code-review",
25
+ "version": "1.0.0",
26
+ "runId": "r-conformance-01",
27
+ "finalPassId": "pass-2"
28
+ },
29
+ "candidate": {
30
+ "vcs": "git",
31
+ "treeSha": "3dd16b56e3035a4c9f3d591f55edde08a4107990",
32
+ "headSha": "31740476c0227fc5c77b00c37aff24d03d692e47",
33
+ "deliverable": {
34
+ "digest": "c63b4981ab1c11a6e19a0225d596ecd59a399e2fdf06cffbb8da69bace6b9db9",
35
+ "identity": "deliverable-tree/v1"
36
+ },
37
+ "base": {
38
+ "ref": "origin/main",
39
+ "tipSha": "8248f1bc1cf32509843ef77387841c8ea06245cb",
40
+ "mergeBaseSha": "892135fcf4acee18bebcefd8398192fd0faf1293"
41
+ },
42
+ "workspaceId": "w-0dcf2d98505da17d"
43
+ },
44
+ "repository": null,
45
+ "runHistory": [
46
+ {
47
+ "preparedTreeSha": "132c7f8efa52032271d4f06fc0cb9e264a05e0e1",
48
+ "evaluatedInPassId": "pass-1"
49
+ },
50
+ {
51
+ "preparedTreeSha": "3dd16b56e3035a4c9f3d591f55edde08a4107990",
52
+ "evaluatedInPassId": "pass-2"
53
+ }
54
+ ],
55
+ "artifacts": [
56
+ {
57
+ "path": "reviewers/correctness.json",
58
+ "sha256": "128b2a9756c778c36ce29b4390e944c2f05438904d1953a0bed4027f55e1ede8",
59
+ "role": "reviewer-approval"
60
+ },
61
+ {
62
+ "path": "reviewers/security.json",
63
+ "sha256": "4933efc56d9e3fe6173f31b703ba7c41cb7490cbd2f5538b5b5ef2a7cc8fa03e",
64
+ "role": "reviewer-approval"
65
+ },
66
+ {
67
+ "path": "reviewers/tests.json",
68
+ "sha256": "3ec8364e062dcfc9f631262d9d36afc750f49080483755767345fcc22c1b1e42",
69
+ "role": "reviewer-approval"
70
+ }
71
+ ],
72
+ "attestation": {
73
+ "level": "self",
74
+ "signatures": []
75
+ },
76
+ "recordedAt": "2026-08-25T00:00:00Z",
77
+ "claims": [
78
+ {
79
+ "obligation": "review.green",
80
+ "payloadSpec": "review.green/1",
81
+ "payload": {
82
+ "verdict": "green",
83
+ "finalized": true,
84
+ "editedAfterFinalPass": false,
85
+ "reviewers": {
86
+ "selected": [
87
+ "correctness",
88
+ "security",
89
+ "tests"
90
+ ],
91
+ "completed": [
92
+ "correctness",
93
+ "security",
94
+ "tests"
95
+ ],
96
+ "failed": [],
97
+ "timedOut": []
98
+ },
99
+ "findings": [],
100
+ "telemetry": {
101
+ "iterationCount": 2,
102
+ "findingCounts": {
103
+ "P0": 0,
104
+ "P1": 0,
105
+ "P2": 0,
106
+ "P3": 0
107
+ },
108
+ "deferredExpansionCount": 0,
109
+ "deferredIssueIds": []
110
+ }
111
+ }
112
+ }
113
+ ]
114
+ }
115
+ }