devlyn-cli 2.3.0 → 2.3.1

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.
Files changed (219) hide show
  1. package/AGENTS.md +1 -1
  2. package/CLAUDE.md +2 -2
  3. package/README.md +80 -29
  4. package/benchmark/auto-resolve/BENCHMARK-DESIGN.md +61 -44
  5. package/benchmark/auto-resolve/BENCHMARK-RESULTS.md +341 -0
  6. package/benchmark/auto-resolve/README.md +307 -44
  7. package/benchmark/auto-resolve/RUBRIC.md +23 -14
  8. package/benchmark/auto-resolve/fixtures/F1-cli-trivial-flag/NOTES.md +7 -3
  9. package/benchmark/auto-resolve/fixtures/F10-persist-write-collision/NOTES.md +8 -3
  10. package/benchmark/auto-resolve/fixtures/F11-batch-import-all-or-nothing/NOTES.md +8 -3
  11. package/benchmark/auto-resolve/fixtures/F12-webhook-raw-body-signature/NOTES.md +10 -4
  12. package/benchmark/auto-resolve/fixtures/F15-frozen-diff-race-review/NOTES.md +10 -4
  13. package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/NOTES.md +12 -0
  14. package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/spec.md +6 -0
  15. package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/NOTES.md +7 -4
  16. package/benchmark/auto-resolve/fixtures/F21-cli-scheduler-priority/NOTES.md +12 -0
  17. package/benchmark/auto-resolve/fixtures/F21-cli-scheduler-priority/spec.md +6 -0
  18. package/benchmark/auto-resolve/fixtures/F22-cli-ledger-close/NOTES.md +8 -0
  19. package/benchmark/auto-resolve/fixtures/F23-cli-fulfillment-wave/NOTES.md +12 -0
  20. package/benchmark/auto-resolve/fixtures/F23-cli-fulfillment-wave/spec.md +6 -0
  21. package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/NOTES.md +16 -4
  22. package/benchmark/auto-resolve/fixtures/F25-cli-cart-promotion-rules/spec.md +7 -0
  23. package/benchmark/auto-resolve/fixtures/F26-cli-payout-ledger-rules/NOTES.md +11 -5
  24. package/benchmark/auto-resolve/fixtures/F3-backend-contract-risk/NOTES.md +8 -1
  25. package/benchmark/auto-resolve/fixtures/F3-backend-contract-risk/expected.json +4 -2
  26. package/benchmark/auto-resolve/fixtures/F3-backend-contract-risk/spec.md +1 -1
  27. package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/NOTES.md +34 -0
  28. package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/expected.json +57 -0
  29. package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/metadata.json +10 -0
  30. package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/setup.sh +2 -0
  31. package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/spec.md +67 -0
  32. package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/task.txt +7 -0
  33. package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/verifiers/duplicate-event-error.js +35 -0
  34. package/benchmark/auto-resolve/fixtures/F31-cli-seat-rebalance/verifiers/priority-transfer-rollback.js +53 -0
  35. package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/NOTES.md +38 -0
  36. package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/expected.json +57 -0
  37. package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/metadata.json +10 -0
  38. package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/setup.sh +2 -0
  39. package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/spec.md +70 -0
  40. package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/task.txt +3 -0
  41. package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/verifiers/duplicate-renewal-error.js +42 -0
  42. package/benchmark/auto-resolve/fixtures/F32-cli-subscription-renewal/verifiers/priority-credit-rollback.js +70 -0
  43. package/benchmark/auto-resolve/fixtures/F4-web-browser-design/NOTES.md +10 -3
  44. package/benchmark/auto-resolve/fixtures/F5-fix-loop-red-green/NOTES.md +7 -0
  45. package/benchmark/auto-resolve/fixtures/F6-dep-audit-native-module/NOTES.md +5 -0
  46. package/benchmark/auto-resolve/fixtures/F7-out-of-scope-trap/NOTES.md +7 -0
  47. package/benchmark/auto-resolve/fixtures/F8-known-limit-ambiguous/NOTES.md +3 -0
  48. package/benchmark/auto-resolve/fixtures/F8-known-limit-ambiguous/spec.md +1 -1
  49. package/benchmark/auto-resolve/fixtures/F9-e2e-ideate-to-resolve/NOTES.md +15 -3
  50. package/benchmark/auto-resolve/fixtures/F9-e2e-ideate-to-resolve/spec.md +1 -1
  51. package/benchmark/auto-resolve/fixtures/SCHEMA.md +53 -7
  52. package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/NOTES.md +37 -0
  53. package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/RETIRED.md +13 -0
  54. package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/expected.json +56 -0
  55. package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/metadata.json +10 -0
  56. package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/setup.sh +18 -0
  57. package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/spec.md +69 -0
  58. package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/task.txt +7 -0
  59. package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/verifiers/exact-proration.js +48 -0
  60. package/benchmark/auto-resolve/fixtures/retired/F27-cli-subscription-proration/verifiers/rules-source-and-conflict.js +79 -0
  61. package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/NOTES.md +54 -0
  62. package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/RETIRED.md +7 -0
  63. package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/expected.json +67 -0
  64. package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/metadata.json +10 -0
  65. package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/setup.sh +2 -0
  66. package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/spec.md +67 -0
  67. package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/task.txt +5 -0
  68. package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/verifiers/policy-precedence.js +72 -0
  69. package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/verifiers/validation-and-immutability.js +43 -0
  70. package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/verifiers/validation-boundary.js +116 -0
  71. package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/NOTES.md +35 -0
  72. package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/RETIRED.md +12 -0
  73. package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/expected.json +58 -0
  74. package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/metadata.json +10 -0
  75. package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/setup.sh +2 -0
  76. package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/spec.md +73 -0
  77. package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/task.txt +17 -0
  78. package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/verifiers/mixed-idempotent-settlement.js +53 -0
  79. package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/verifiers/rejection-boundaries.js +74 -0
  80. package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/NOTES.md +60 -0
  81. package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/RETIRED.md +29 -0
  82. package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/expected.json +73 -0
  83. package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/metadata.json +10 -0
  84. package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/setup.sh +28 -0
  85. package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/spec.md +58 -0
  86. package/benchmark/auto-resolve/fixtures/retired/F9-e2e-ideate-to-preflight/task.txt +5 -0
  87. package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/full-pipeline-pair-gate.json +82 -0
  88. package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/full-pipeline-pair-gate.md +18 -0
  89. package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/headroom-gate.json +46 -0
  90. package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/headroom-gate.md +17 -0
  91. package/benchmark/auto-resolve/run-real-benchmark.md +303 -0
  92. package/benchmark/auto-resolve/scripts/audit-headroom-rejections.py +441 -0
  93. package/benchmark/auto-resolve/scripts/audit-pair-evidence.py +1256 -0
  94. package/benchmark/auto-resolve/scripts/build-pair-eligible-manifest.py +147 -15
  95. package/benchmark/auto-resolve/scripts/check-f9-artifacts.py +28 -16
  96. package/benchmark/auto-resolve/scripts/collect-swebench-predictions.py +11 -1
  97. package/benchmark/auto-resolve/scripts/compile-report.py +208 -46
  98. package/benchmark/auto-resolve/scripts/fetch-swebench-instances.py +22 -4
  99. package/benchmark/auto-resolve/scripts/frozen-verify-gate.py +175 -30
  100. package/benchmark/auto-resolve/scripts/full-pipeline-pair-gate.py +408 -46
  101. package/benchmark/auto-resolve/scripts/headroom-gate.py +270 -39
  102. package/benchmark/auto-resolve/scripts/iter-0033c-compare.py +164 -33
  103. package/benchmark/auto-resolve/scripts/iter-0033c-l1-summary.py +97 -0
  104. package/benchmark/auto-resolve/scripts/judge-opus-pass.sh +150 -38
  105. package/benchmark/auto-resolve/scripts/judge.sh +153 -26
  106. package/benchmark/auto-resolve/scripts/oracle-scope-tier-a.py +12 -5
  107. package/benchmark/auto-resolve/scripts/oracle-scope-tier-b.py +25 -2
  108. package/benchmark/auto-resolve/scripts/pair-candidate-frontier.py +469 -0
  109. package/benchmark/auto-resolve/scripts/pair-plan-idgen.py +5 -5
  110. package/benchmark/auto-resolve/scripts/pair-plan-lint.py +9 -2
  111. package/benchmark/auto-resolve/scripts/pair-rejected-fixtures.sh +91 -0
  112. package/benchmark/auto-resolve/scripts/pair_evidence_contract.py +269 -0
  113. package/benchmark/auto-resolve/scripts/prepare-swebench-frozen-case.py +39 -10
  114. package/benchmark/auto-resolve/scripts/prepare-swebench-frozen-corpus.py +34 -4
  115. package/benchmark/auto-resolve/scripts/prepare-swebench-solver-worktree.py +23 -5
  116. package/benchmark/auto-resolve/scripts/recent-benchmark-summary.py +232 -0
  117. package/benchmark/auto-resolve/scripts/run-fixture.sh +118 -51
  118. package/benchmark/auto-resolve/scripts/run-frozen-verify-pair.sh +211 -39
  119. package/benchmark/auto-resolve/scripts/run-full-pipeline-pair-candidate.sh +335 -39
  120. package/benchmark/auto-resolve/scripts/run-headroom-candidate.sh +249 -6
  121. package/benchmark/auto-resolve/scripts/run-iter-0033c.sh +22 -48
  122. package/benchmark/auto-resolve/scripts/run-suite.sh +44 -7
  123. package/benchmark/auto-resolve/scripts/run-swebench-frozen-corpus.sh +120 -19
  124. package/benchmark/auto-resolve/scripts/run-swebench-solver-batch.sh +32 -14
  125. package/benchmark/auto-resolve/scripts/ship-gate.py +219 -50
  126. package/benchmark/auto-resolve/scripts/solo-ceiling-avoidance.py +53 -0
  127. package/benchmark/auto-resolve/scripts/solo-headroom-hypothesis.py +77 -0
  128. package/benchmark/auto-resolve/scripts/swebench-frozen-matrix.py +239 -26
  129. package/benchmark/auto-resolve/scripts/test-audit-headroom-rejections.sh +288 -0
  130. package/benchmark/auto-resolve/scripts/test-audit-pair-evidence.sh +1672 -0
  131. package/benchmark/auto-resolve/scripts/test-benchmark-arg-parsing.sh +933 -0
  132. package/benchmark/auto-resolve/scripts/test-build-pair-eligible-manifest.sh +491 -0
  133. package/benchmark/auto-resolve/scripts/test-check-f9-artifacts.sh +91 -0
  134. package/benchmark/auto-resolve/scripts/test-frozen-verify-gate.sh +328 -3
  135. package/benchmark/auto-resolve/scripts/test-full-pipeline-pair-gate.sh +497 -18
  136. package/benchmark/auto-resolve/scripts/test-headroom-gate.sh +331 -14
  137. package/benchmark/auto-resolve/scripts/test-iter-0033c-compare.sh +525 -0
  138. package/benchmark/auto-resolve/scripts/test-iter-0033c-l1-summary.sh +254 -0
  139. package/benchmark/auto-resolve/scripts/test-lint-fixtures.sh +580 -0
  140. package/benchmark/auto-resolve/scripts/test-pair-candidate-frontier.sh +591 -0
  141. package/benchmark/auto-resolve/scripts/test-run-full-pipeline-pair-candidate.sh +497 -0
  142. package/benchmark/auto-resolve/scripts/test-run-headroom-candidate.sh +401 -0
  143. package/benchmark/auto-resolve/scripts/test-run-swebench-solver-batch.sh +111 -0
  144. package/benchmark/auto-resolve/scripts/test-ship-gate.sh +1189 -0
  145. package/benchmark/auto-resolve/scripts/test-swebench-frozen-case.sh +924 -5
  146. package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/NOTES.md +28 -0
  147. package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/expected.json +63 -0
  148. package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/metadata.json +10 -0
  149. package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/setup.sh +3 -0
  150. package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/spec.md +47 -0
  151. package/benchmark/auto-resolve/shadow-fixtures/S1-cli-lang-flag/task.txt +1 -0
  152. package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/NOTES.md +34 -0
  153. package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/expected.json +53 -0
  154. package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/metadata.json +10 -0
  155. package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/setup.sh +3 -0
  156. package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/spec.md +50 -0
  157. package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/task.txt +1 -0
  158. package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/verifiers/duplicate-order-error.js +27 -0
  159. package/benchmark/auto-resolve/shadow-fixtures/S2-cli-inventory-reservation/verifiers/priority-stock-reservation.js +44 -0
  160. package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/NOTES.md +34 -0
  161. package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/expected.json +55 -0
  162. package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/metadata.json +10 -0
  163. package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/setup.sh +3 -0
  164. package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/spec.md +52 -0
  165. package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/task.txt +1 -0
  166. package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/verifiers/duplicate-ticket-error.js +29 -0
  167. package/benchmark/auto-resolve/shadow-fixtures/S3-cli-ticket-assignment/verifiers/priority-agent-assignment.js +48 -0
  168. package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/NOTES.md +34 -0
  169. package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/expected.json +55 -0
  170. package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/metadata.json +10 -0
  171. package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/setup.sh +3 -0
  172. package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/spec.md +55 -0
  173. package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/task.txt +1 -0
  174. package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/verifiers/duplicate-return-error.js +43 -0
  175. package/benchmark/auto-resolve/shadow-fixtures/S4-cli-return-routing/verifiers/priority-return-routing.js +70 -0
  176. package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/NOTES.md +37 -0
  177. package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/expected.json +54 -0
  178. package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/metadata.json +10 -0
  179. package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/setup.sh +3 -0
  180. package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/spec.md +59 -0
  181. package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/task.txt +1 -0
  182. package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/verifiers/credit-ledger-priority.js +98 -0
  183. package/benchmark/auto-resolve/shadow-fixtures/S5-cli-credit-grant-ledger/verifiers/duplicate-charge-error.js +38 -0
  184. package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/NOTES.md +36 -0
  185. package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/expected.json +56 -0
  186. package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/metadata.json +10 -0
  187. package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/setup.sh +3 -0
  188. package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/spec.md +59 -0
  189. package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/task.txt +1 -0
  190. package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/verifiers/duplicate-refund-error.js +41 -0
  191. package/benchmark/auto-resolve/shadow-fixtures/S6-cli-refund-window-ledger/verifiers/priority-refund-ledger.js +65 -0
  192. package/bin/devlyn.js +210 -17
  193. package/config/skills/_shared/adapters/README.md +3 -0
  194. package/config/skills/_shared/adapters/gpt-5-5.md +5 -1
  195. package/config/skills/_shared/adapters/opus-4-7.md +9 -1
  196. package/config/skills/_shared/archive_run.py +78 -6
  197. package/config/skills/_shared/codex-config.md +3 -2
  198. package/config/skills/_shared/codex-monitored.sh +46 -1
  199. package/config/skills/_shared/collect-codex-findings.py +20 -5
  200. package/config/skills/_shared/engine-preflight.md +1 -1
  201. package/config/skills/_shared/runtime-principles.md +5 -8
  202. package/config/skills/_shared/spec-verify-check.py +2664 -107
  203. package/config/skills/_shared/verify-merge-findings.py +1369 -19
  204. package/config/skills/devlyn:ideate/SKILL.md +7 -4
  205. package/config/skills/devlyn:ideate/references/elicitation.md +50 -4
  206. package/config/skills/devlyn:ideate/references/from-spec-mode.md +26 -4
  207. package/config/skills/devlyn:ideate/references/project-mode.md +20 -1
  208. package/config/skills/devlyn:ideate/references/spec-template.md +10 -1
  209. package/config/skills/devlyn:resolve/SKILL.md +49 -18
  210. package/config/skills/devlyn:resolve/references/free-form-mode.md +15 -0
  211. package/config/skills/devlyn:resolve/references/phases/build-gate.md +2 -2
  212. package/config/skills/devlyn:resolve/references/phases/probe-derive.md +74 -2
  213. package/config/skills/devlyn:resolve/references/phases/verify.md +62 -28
  214. package/config/skills/devlyn:resolve/references/state-schema.md +7 -4
  215. package/package.json +47 -2
  216. package/scripts/lint-fixtures.sh +349 -0
  217. package/scripts/lint-shadow-fixtures.sh +58 -0
  218. package/scripts/lint-skills.sh +3642 -92
  219. /package/{optional-skills → config/skills}/devlyn:design-ui/SKILL.md +0 -0
@@ -0,0 +1,254 @@
1
+ #!/usr/bin/env bash
2
+ # Regression tests for iter-0033c-l1-summary.py score-source handling.
3
+
4
+ set -euo pipefail
5
+
6
+ SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
7
+ SUMMARY="$SCRIPT_DIR/iter-0033c-l1-summary.py"
8
+ TMP_DIR="$(mktemp -d /tmp/iter-0033c-l1-summary-test.XXXXXX)"
9
+ trap 'rm -rf "$TMP_DIR"' EXIT
10
+
11
+ RUN_DIR="$TMP_DIR/results"
12
+ FIXTURE_DIR="$RUN_DIR/F1-synthetic"
13
+ mkdir -p "$FIXTURE_DIR"/{solo_claude,l2_gated,l2_forced,bare}
14
+ for arm in solo_claude l2_gated l2_forced bare; do
15
+ cat > "$FIXTURE_DIR/$arm/result.json" <<'JSON'
16
+ {"elapsed_seconds": 12, "verify_score": 1, "files_changed": 2, "timed_out": false, "disqualifier": false}
17
+ JSON
18
+ done
19
+ cat > "$FIXTURE_DIR/judge.json" <<'JSON'
20
+ {
21
+ "_blind_mapping": {"A": "solo_claude", "B": "l2_gated", "C": "l2_forced", "seed": 1},
22
+ "scores_by_arm": {"solo_claude": 60, "l2_gated": 70},
23
+ "c_score": 80
24
+ }
25
+ JSON
26
+
27
+ python3 "$SUMMARY" \
28
+ --results-dir "$RUN_DIR" \
29
+ --out "$TMP_DIR/summary.json" \
30
+ --run-id synthetic \
31
+ --git-sha abc123 >/dev/null
32
+ python3 - "$TMP_DIR/summary.json" <<'PY'
33
+ import json
34
+ import sys
35
+
36
+ summary = json.load(open(sys.argv[1], encoding="utf8"))
37
+ arms = summary["rows"][0]["arms"]
38
+ if arms["solo_claude"]["score"] != 60:
39
+ raise SystemExit("solo_claude score must come from scores_by_arm")
40
+ if arms["l2_gated"]["score"] != 70:
41
+ raise SystemExit("l2_gated score must come from scores_by_arm")
42
+ if arms["l2_forced"]["score"] != 80:
43
+ raise SystemExit("l2_forced score must fall back to lowercase c_score")
44
+ if "bare" in arms:
45
+ raise SystemExit("unmapped bare arm must not appear in iter-0033c L1 summary")
46
+ PY
47
+
48
+ MALFORMED_DIR="$TMP_DIR/malformed"
49
+ MALFORMED_FIXTURE="$MALFORMED_DIR/F2-synthetic"
50
+ mkdir -p "$MALFORMED_FIXTURE"/{solo_claude,l2_gated}
51
+ for arm in solo_claude l2_gated; do
52
+ cat > "$MALFORMED_FIXTURE/$arm/result.json" <<'JSON'
53
+ {"elapsed_seconds": 12, "verify_score": 1, "files_changed": 2, "timed_out": false, "disqualifier": false}
54
+ JSON
55
+ done
56
+ cat > "$MALFORMED_FIXTURE/judge.json" <<'JSON'
57
+ {
58
+ "_blind_mapping": "not-a-dict",
59
+ "scores_by_arm": {"solo_claude": 60, "l2_gated": 70}
60
+ }
61
+ JSON
62
+ python3 "$SUMMARY" \
63
+ --results-dir "$MALFORMED_DIR" \
64
+ --out "$TMP_DIR/malformed-summary.json" \
65
+ --run-id malformed \
66
+ --git-sha abc123 >/dev/null
67
+ python3 - "$TMP_DIR/malformed-summary.json" <<'PY'
68
+ import json
69
+ import sys
70
+
71
+ summary = json.load(open(sys.argv[1], encoding="utf8"))
72
+ arms = summary["rows"][0]["arms"]
73
+ if arms:
74
+ raise SystemExit("malformed blind mapping must not trust scores_by_arm")
75
+ PY
76
+
77
+ MALFORMED_SCORES_DIR="$TMP_DIR/malformed-scores"
78
+ MALFORMED_SCORES_FIXTURE="$MALFORMED_SCORES_DIR/F3-synthetic"
79
+ mkdir -p "$MALFORMED_SCORES_FIXTURE"/{solo_claude,l2_gated}
80
+ for arm in solo_claude l2_gated; do
81
+ cat > "$MALFORMED_SCORES_FIXTURE/$arm/result.json" <<'JSON'
82
+ {"elapsed_seconds": 12, "verify_score": 1, "files_changed": 2, "timed_out": false, "disqualifier": false}
83
+ JSON
84
+ done
85
+ cat > "$MALFORMED_SCORES_FIXTURE/judge.json" <<'JSON'
86
+ {
87
+ "_blind_mapping": {"A": "solo_claude", "B": "l2_gated", "seed": 1},
88
+ "scores_by_arm": ["not", "a", "dict"]
89
+ }
90
+ JSON
91
+ python3 "$SUMMARY" \
92
+ --results-dir "$MALFORMED_SCORES_DIR" \
93
+ --out "$TMP_DIR/malformed-scores-summary.json" \
94
+ --run-id malformed-scores \
95
+ --git-sha abc123 >/dev/null
96
+ python3 - "$TMP_DIR/malformed-scores-summary.json" <<'PY'
97
+ import json
98
+ import sys
99
+
100
+ summary = json.load(open(sys.argv[1], encoding="utf8"))
101
+ arms = summary["rows"][0]["arms"]
102
+ if arms["solo_claude"]["score"] is not None or arms["l2_gated"]["score"] is not None:
103
+ raise SystemExit("malformed scores_by_arm must not provide arm scores")
104
+ PY
105
+
106
+ OVERRANGE_SCORES_DIR="$TMP_DIR/overrange-scores"
107
+ OVERRANGE_SCORES_FIXTURE="$OVERRANGE_SCORES_DIR/F5-synthetic"
108
+ mkdir -p "$OVERRANGE_SCORES_FIXTURE"/{solo_claude,l2_gated}
109
+ for arm in solo_claude l2_gated; do
110
+ cat > "$OVERRANGE_SCORES_FIXTURE/$arm/result.json" <<'JSON'
111
+ {"elapsed_seconds": 12, "verify_score": 1, "files_changed": 2, "timed_out": false, "disqualifier": false}
112
+ JSON
113
+ done
114
+ cat > "$OVERRANGE_SCORES_FIXTURE/judge.json" <<'JSON'
115
+ {
116
+ "_blind_mapping": {"A": "solo_claude", "B": "l2_gated", "seed": 1},
117
+ "scores_by_arm": {"solo_claude": 101, "l2_gated": 70},
118
+ "a_score": 101
119
+ }
120
+ JSON
121
+ python3 "$SUMMARY" \
122
+ --results-dir "$OVERRANGE_SCORES_DIR" \
123
+ --out "$TMP_DIR/overrange-scores-summary.json" \
124
+ --run-id overrange-scores \
125
+ --git-sha abc123 >/dev/null
126
+ python3 - "$TMP_DIR/overrange-scores-summary.json" <<'PY'
127
+ import json
128
+ import sys
129
+
130
+ summary = json.load(open(sys.argv[1], encoding="utf8"))
131
+ arms = summary["rows"][0]["arms"]
132
+ if arms["solo_claude"]["score"] is not None:
133
+ raise SystemExit("out-of-range scores must not appear in L1 summary")
134
+ PY
135
+
136
+ BOOLEAN_SCORES_DIR="$TMP_DIR/boolean-scores"
137
+ BOOLEAN_SCORES_FIXTURE="$BOOLEAN_SCORES_DIR/F6-synthetic"
138
+ mkdir -p "$BOOLEAN_SCORES_FIXTURE"/{solo_claude,l2_gated}
139
+ for arm in solo_claude l2_gated; do
140
+ cat > "$BOOLEAN_SCORES_FIXTURE/$arm/result.json" <<'JSON'
141
+ {"elapsed_seconds": 12, "verify_score": 1, "files_changed": 2, "timed_out": false, "disqualifier": false}
142
+ JSON
143
+ done
144
+ cat > "$BOOLEAN_SCORES_FIXTURE/judge.json" <<'JSON'
145
+ {
146
+ "_blind_mapping": {"A": "solo_claude", "B": "l2_gated", "seed": 1},
147
+ "scores_by_arm": {"solo_claude": true, "l2_gated": 70},
148
+ "a_score": true
149
+ }
150
+ JSON
151
+ python3 "$SUMMARY" \
152
+ --results-dir "$BOOLEAN_SCORES_DIR" \
153
+ --out "$TMP_DIR/boolean-scores-summary.json" \
154
+ --run-id boolean-scores \
155
+ --git-sha abc123 >/dev/null
156
+ python3 - "$TMP_DIR/boolean-scores-summary.json" <<'PY'
157
+ import json
158
+ import sys
159
+
160
+ summary = json.load(open(sys.argv[1], encoding="utf8"))
161
+ arms = summary["rows"][0]["arms"]
162
+ if arms["solo_claude"]["score"] is not None:
163
+ raise SystemExit("boolean scores must not appear in L1 summary")
164
+ PY
165
+
166
+ BOOLEAN_WALL_DIR="$TMP_DIR/boolean-wall"
167
+ BOOLEAN_WALL_FIXTURE="$BOOLEAN_WALL_DIR/F7-synthetic"
168
+ mkdir -p "$BOOLEAN_WALL_FIXTURE"/{solo_claude,l2_gated}
169
+ cat > "$BOOLEAN_WALL_FIXTURE/solo_claude/result.json" <<'JSON'
170
+ {"elapsed_seconds": true, "verify_score": true, "files_changed": 2, "timed_out": false, "disqualifier": false}
171
+ JSON
172
+ cat > "$BOOLEAN_WALL_FIXTURE/l2_gated/result.json" <<'JSON'
173
+ {"elapsed_seconds": 12, "verify_score": 1, "files_changed": 2, "timed_out": false, "disqualifier": false}
174
+ JSON
175
+ cat > "$BOOLEAN_WALL_FIXTURE/judge.json" <<'JSON'
176
+ {
177
+ "_blind_mapping": {"A": "solo_claude", "B": "l2_gated", "seed": 1},
178
+ "scores_by_arm": {"solo_claude": 60, "l2_gated": 70}
179
+ }
180
+ JSON
181
+ python3 "$SUMMARY" \
182
+ --results-dir "$BOOLEAN_WALL_DIR" \
183
+ --out "$TMP_DIR/boolean-wall-summary.json" \
184
+ --run-id boolean-wall \
185
+ --git-sha abc123 >/dev/null
186
+ python3 - "$TMP_DIR/boolean-wall-summary.json" <<'PY'
187
+ import json
188
+ import sys
189
+
190
+ summary = json.load(open(sys.argv[1], encoding="utf8"))
191
+ solo = summary["rows"][0]["arms"]["solo_claude"]
192
+ if solo["wall_s"] is not None or solo["verify_score"] is not None:
193
+ raise SystemExit("boolean result numeric fields must not appear in L1 summary")
194
+ PY
195
+
196
+ NAN_RESULT_DIR="$TMP_DIR/nan-result"
197
+ NAN_RESULT_FIXTURE="$NAN_RESULT_DIR/F8-synthetic"
198
+ mkdir -p "$NAN_RESULT_FIXTURE"/{solo_claude,l2_gated}
199
+ cat > "$NAN_RESULT_FIXTURE/solo_claude/result.json" <<'JSON'
200
+ {"elapsed_seconds": NaN, "verify_score": NaN, "files_changed": 2, "timed_out": false, "disqualifier": false}
201
+ JSON
202
+ cat > "$NAN_RESULT_FIXTURE/l2_gated/result.json" <<'JSON'
203
+ {"elapsed_seconds": 12, "verify_score": 1, "files_changed": 2, "timed_out": false, "disqualifier": false}
204
+ JSON
205
+ cat > "$NAN_RESULT_FIXTURE/judge.json" <<'JSON'
206
+ {
207
+ "_blind_mapping": {"A": "solo_claude", "B": "l2_gated", "seed": 1},
208
+ "scores_by_arm": {"solo_claude": 60, "l2_gated": 70}
209
+ }
210
+ JSON
211
+ python3 "$SUMMARY" \
212
+ --results-dir "$NAN_RESULT_DIR" \
213
+ --out "$TMP_DIR/nan-result-summary.json" \
214
+ --run-id nan-result \
215
+ --git-sha abc123 >/dev/null
216
+ python3 - "$TMP_DIR/nan-result-summary.json" <<'PY'
217
+ import json
218
+ import sys
219
+
220
+ summary = json.load(open(sys.argv[1], encoding="utf8"))
221
+ solo = summary["rows"][0]["arms"]["solo_claude"]
222
+ if solo["wall_s"] is not None or solo["verify_score"] is not None:
223
+ raise SystemExit("NaN result numeric fields must not appear in L1 summary")
224
+ PY
225
+
226
+ MALFORMED_RESULT_DIR="$TMP_DIR/malformed-result"
227
+ MALFORMED_RESULT_FIXTURE="$MALFORMED_RESULT_DIR/F4-synthetic"
228
+ mkdir -p "$MALFORMED_RESULT_FIXTURE"/{solo_claude,l2_gated}
229
+ printf '["not", "a", "dict"]\n' > "$MALFORMED_RESULT_FIXTURE/solo_claude/result.json"
230
+ cat > "$MALFORMED_RESULT_FIXTURE/l2_gated/result.json" <<'JSON'
231
+ {"elapsed_seconds": 12, "verify_score": 1, "files_changed": 2, "timed_out": false, "disqualifier": false}
232
+ JSON
233
+ cat > "$MALFORMED_RESULT_FIXTURE/judge.json" <<'JSON'
234
+ {
235
+ "_blind_mapping": {"A": "solo_claude", "B": "l2_gated", "seed": 1},
236
+ "scores_by_arm": {"solo_claude": 60, "l2_gated": 70}
237
+ }
238
+ JSON
239
+ python3 "$SUMMARY" \
240
+ --results-dir "$MALFORMED_RESULT_DIR" \
241
+ --out "$TMP_DIR/malformed-result-summary.json" \
242
+ --run-id malformed-result \
243
+ --git-sha abc123 >/dev/null
244
+ python3 - "$TMP_DIR/malformed-result-summary.json" <<'PY'
245
+ import json
246
+ import sys
247
+
248
+ summary = json.load(open(sys.argv[1], encoding="utf8"))
249
+ solo = summary["rows"][0]["arms"]["solo_claude"]
250
+ if solo["wall_s"] is not None or solo["verify_score"] is not None:
251
+ raise SystemExit("non-dict result.json must not expose result fields")
252
+ PY
253
+
254
+ echo "PASS test-iter-0033c-l1-summary"