devlyn-cli 2.10.1 → 3.0.0

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 (75) hide show
  1. package/AGENTS.md +4 -9
  2. package/CLAUDE.md +11 -15
  3. package/README.md +31 -7
  4. package/benchmark/auto-resolve/results/20260507-f10-f11-tier1-full-pipeline/headroom-gate.json +25 -0
  5. package/benchmark/auto-resolve/results/20260507-f10-f11-tier1-full-pipeline/headroom-gate.md +10 -0
  6. package/benchmark/auto-resolve/results/20260508-f22-exact-error-headroom/headroom-gate.json +18 -0
  7. package/benchmark/auto-resolve/results/20260508-f22-exact-error-headroom/headroom-gate.md +9 -0
  8. package/benchmark/auto-resolve/results/20260508-f26-headroom/headroom-gate.json +18 -0
  9. package/benchmark/auto-resolve/results/20260508-f26-headroom/headroom-gate.md +9 -0
  10. package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/F16-cli-quote-tax-rules/l2_risk_probes/result.json +28 -0
  11. package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/F23-cli-fulfillment-wave/l2_risk_probes/result.json +28 -0
  12. package/benchmark/auto-resolve/results/20260510-f16-f23-f25-combined-proof/F25-cli-cart-promotion-rules/l2_risk_probes/result.json +30 -0
  13. package/benchmark/auto-resolve/results/20260511-f12-webhook-headroom/headroom-gate.json +28 -0
  14. package/benchmark/auto-resolve/results/20260511-f12-webhook-headroom/headroom-gate.md +15 -0
  15. package/benchmark/auto-resolve/results/20260511-f15-concurrency-headroom/headroom-gate.json +28 -0
  16. package/benchmark/auto-resolve/results/20260511-f15-concurrency-headroom/headroom-gate.md +15 -0
  17. package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/F21-cli-scheduler-priority/l2_risk_probes/result.json +32 -0
  18. package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/full-pipeline-pair-gate.json +44 -0
  19. package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/full-pipeline-pair-gate.md +16 -0
  20. package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/headroom-gate.json +18 -0
  21. package/benchmark/auto-resolve/results/20260511-f21-current-riskprobes-v1/headroom-gate.md +9 -0
  22. package/benchmark/auto-resolve/results/20260511-f3-http-error-headroom/headroom-gate.json +28 -0
  23. package/benchmark/auto-resolve/results/20260511-f3-http-error-headroom/headroom-gate.md +15 -0
  24. package/benchmark/auto-resolve/results/20260512-f2-medium-headroom/headroom-gate.json +28 -0
  25. package/benchmark/auto-resolve/results/20260512-f2-medium-headroom/headroom-gate.md +15 -0
  26. package/benchmark/auto-resolve/results/20260512-f31-seat-rebalance-headroom/headroom-gate.json +28 -0
  27. package/benchmark/auto-resolve/results/20260512-f31-seat-rebalance-headroom/headroom-gate.md +15 -0
  28. package/benchmark/auto-resolve/results/20260512-f32-subscription-renewal-headroom/headroom-gate.json +28 -0
  29. package/benchmark/auto-resolve/results/20260512-f32-subscription-renewal-headroom/headroom-gate.md +15 -0
  30. package/benchmark/auto-resolve/results/20260512-f4-web-headroom/headroom-gate.json +28 -0
  31. package/benchmark/auto-resolve/results/20260512-f4-web-headroom/headroom-gate.md +15 -0
  32. package/benchmark/auto-resolve/results/20260512-f5-fixloop-headroom/headroom-gate.json +28 -0
  33. package/benchmark/auto-resolve/results/20260512-f5-fixloop-headroom/headroom-gate.md +15 -0
  34. package/benchmark/auto-resolve/results/20260512-f6-checksum-headroom/headroom-gate.json +28 -0
  35. package/benchmark/auto-resolve/results/20260512-f6-checksum-headroom/headroom-gate.md +15 -0
  36. package/benchmark/auto-resolve/results/20260512-f7-scope-headroom/headroom-gate.json +28 -0
  37. package/benchmark/auto-resolve/results/20260512-f7-scope-headroom/headroom-gate.md +15 -0
  38. package/benchmark/auto-resolve/results/20260512-f9-e2e-headroom/headroom-gate.json +28 -0
  39. package/benchmark/auto-resolve/results/20260512-f9-e2e-headroom/headroom-gate.md +15 -0
  40. package/bin/devlyn.js +6 -1
  41. package/config/skills/_shared/.ruff.toml +2 -0
  42. package/config/skills/_shared/adapters/claude.md +9 -1
  43. package/config/skills/_shared/adapters/codex.md +5 -0
  44. package/config/skills/_shared/adapters/grok.md +4 -2
  45. package/config/skills/_shared/archive_run.py +738 -56
  46. package/config/skills/_shared/codex-config.md +19 -4
  47. package/config/skills/_shared/codex-monitored.sh +81 -12
  48. package/config/skills/_shared/collect-codex-findings.py +311 -128
  49. package/config/skills/_shared/engine-preflight.md +8 -7
  50. package/config/skills/_shared/expected.schema.json +61 -0
  51. package/config/skills/_shared/finish-gate.py +12 -11
  52. package/config/skills/_shared/grok-anchor-guard.py +18 -1
  53. package/config/skills/_shared/invocation-receipt.py +1041 -0
  54. package/config/skills/_shared/judge-output-parser.py +200 -0
  55. package/config/skills/_shared/judge-role-evidence.py +273 -0
  56. package/config/skills/_shared/process-evidence.py +909 -0
  57. package/config/skills/_shared/resolve-bootstrap.py +776 -84
  58. package/config/skills/_shared/resolve-stop-hook.py +33 -1
  59. package/config/skills/_shared/role-config.py +552 -0
  60. package/config/skills/_shared/run-bounded.py +1 -1
  61. package/config/skills/_shared/spec-verify-check.py +749 -181
  62. package/config/skills/_shared/state-phase-write.py +1838 -58
  63. package/config/skills/_shared/terminal-claim-check.py +15 -0
  64. package/config/skills/_shared/verify-merge-findings.py +958 -51
  65. package/config/skills/devlyn:engines/SKILL.md +8 -16
  66. package/config/skills/devlyn:ideate/references/spec-template.md +1 -0
  67. package/config/skills/devlyn:queue/SKILL.md +7 -4
  68. package/config/skills/devlyn:resolve/SKILL.md +91 -33
  69. package/config/skills/devlyn:resolve/references/outer-loop.md +15 -0
  70. package/config/skills/devlyn:resolve/references/phases/build-gate.md +31 -2
  71. package/config/skills/devlyn:resolve/references/phases/implement.md +3 -2
  72. package/config/skills/devlyn:resolve/references/phases/verify.md +120 -84
  73. package/config/skills/devlyn:resolve/references/state-schema.md +22 -8
  74. package/package.json +5 -1
  75. package/scripts/lint-skills.sh +314 -285
@@ -60,6 +60,15 @@ def reject_json_constant(token: str) -> None:
60
60
  raise ValueError(f"invalid JSON numeric constant: {token}")
61
61
 
62
62
 
63
+ def reject_duplicate_keys(pairs: list[tuple[str, object]]) -> dict:
64
+ result = {}
65
+ for key, value in pairs:
66
+ if key in result:
67
+ raise ValueError(f"duplicate JSON key: {key}")
68
+ result[key] = value
69
+ return result
70
+
71
+
63
72
  def malformed(reason: str, run_id: str | None = None) -> Classification:
64
73
  return Classification("MALFORMED", None, reason, run_id, True)
65
74
 
@@ -132,6 +141,7 @@ def classify_state_bytes(
132
141
  state = json.loads(
133
142
  state_bytes.decode("utf-8"),
134
143
  parse_constant=reject_json_constant,
144
+ object_pairs_hook=reject_duplicate_keys,
135
145
  )
136
146
  except (UnicodeError, ValueError):
137
147
  return malformed(f"run state unreadable or invalid: {state_path}"), None
@@ -349,6 +359,11 @@ def write_archived_state(root: pathlib.Path, state: dict[str, object]) -> None:
349
359
 
350
360
  def self_test() -> int:
351
361
  tests = 0
362
+ classification, _state = classify_state_bytes(
363
+ pathlib.Path("."), pathlib.Path("pipeline.state.json"),
364
+ b'{"run_id":"a","run_id":"b","phases":{}}', archived=False,
365
+ )
366
+ assert classification.status == "MALFORMED"
352
367
  with tempfile.TemporaryDirectory() as tmp:
353
368
  base = pathlib.Path(tmp)
354
369