opencode-swarm-plugin 0.44.0 → 0.44.1

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 (205) hide show
  1. package/bin/swarm.serve.test.ts +6 -4
  2. package/bin/swarm.ts +16 -10
  3. package/dist/compaction-prompt-scoring.js +139 -0
  4. package/dist/eval-capture.js +12811 -0
  5. package/dist/hive.d.ts.map +1 -1
  6. package/dist/index.js +7644 -62599
  7. package/dist/plugin.js +23766 -78721
  8. package/dist/swarm-orchestrate.d.ts.map +1 -1
  9. package/dist/swarm-prompts.d.ts.map +1 -1
  10. package/dist/swarm-review.d.ts.map +1 -1
  11. package/package.json +17 -5
  12. package/.changeset/swarm-insights-data-layer.md +0 -63
  13. package/.hive/analysis/eval-failure-analysis-2025-12-25.md +0 -331
  14. package/.hive/analysis/session-data-quality-audit.md +0 -320
  15. package/.hive/eval-results.json +0 -483
  16. package/.hive/issues.jsonl +0 -138
  17. package/.hive/memories.jsonl +0 -729
  18. package/.opencode/eval-history.jsonl +0 -327
  19. package/.turbo/turbo-build.log +0 -9
  20. package/CHANGELOG.md +0 -2286
  21. package/SCORER-ANALYSIS.md +0 -598
  22. package/docs/analysis/subagent-coordination-patterns.md +0 -902
  23. package/docs/analysis-socratic-planner-pattern.md +0 -504
  24. package/docs/planning/ADR-001-monorepo-structure.md +0 -171
  25. package/docs/planning/ADR-002-package-extraction.md +0 -393
  26. package/docs/planning/ADR-003-performance-improvements.md +0 -451
  27. package/docs/planning/ADR-004-message-queue-features.md +0 -187
  28. package/docs/planning/ADR-005-devtools-observability.md +0 -202
  29. package/docs/planning/ADR-007-swarm-enhancements-worktree-review.md +0 -168
  30. package/docs/planning/ADR-008-worker-handoff-protocol.md +0 -293
  31. package/docs/planning/ADR-009-oh-my-opencode-patterns.md +0 -353
  32. package/docs/planning/ADR-010-cass-inhousing.md +0 -1215
  33. package/docs/planning/ROADMAP.md +0 -368
  34. package/docs/semantic-memory-cli-syntax.md +0 -123
  35. package/docs/swarm-mail-architecture.md +0 -1147
  36. package/docs/testing/context-recovery-test.md +0 -470
  37. package/evals/ARCHITECTURE.md +0 -1189
  38. package/evals/README.md +0 -768
  39. package/evals/compaction-prompt.eval.ts +0 -149
  40. package/evals/compaction-resumption.eval.ts +0 -289
  41. package/evals/coordinator-behavior.eval.ts +0 -307
  42. package/evals/coordinator-session.eval.ts +0 -154
  43. package/evals/evalite.config.ts.bak +0 -15
  44. package/evals/example.eval.ts +0 -31
  45. package/evals/fixtures/cass-baseline.ts +0 -217
  46. package/evals/fixtures/compaction-cases.ts +0 -350
  47. package/evals/fixtures/compaction-prompt-cases.ts +0 -311
  48. package/evals/fixtures/coordinator-sessions.ts +0 -328
  49. package/evals/fixtures/decomposition-cases.ts +0 -105
  50. package/evals/lib/compaction-loader.test.ts +0 -248
  51. package/evals/lib/compaction-loader.ts +0 -320
  52. package/evals/lib/data-loader.evalite-test.ts +0 -289
  53. package/evals/lib/data-loader.test.ts +0 -345
  54. package/evals/lib/data-loader.ts +0 -281
  55. package/evals/lib/llm.ts +0 -115
  56. package/evals/scorers/compaction-prompt-scorers.ts +0 -145
  57. package/evals/scorers/compaction-scorers.ts +0 -305
  58. package/evals/scorers/coordinator-discipline.evalite-test.ts +0 -539
  59. package/evals/scorers/coordinator-discipline.ts +0 -325
  60. package/evals/scorers/index.test.ts +0 -146
  61. package/evals/scorers/index.ts +0 -328
  62. package/evals/scorers/outcome-scorers.evalite-test.ts +0 -27
  63. package/evals/scorers/outcome-scorers.ts +0 -349
  64. package/evals/swarm-decomposition.eval.ts +0 -121
  65. package/examples/commands/swarm.md +0 -745
  66. package/examples/plugin-wrapper-template.ts +0 -2515
  67. package/examples/skills/hive-workflow/SKILL.md +0 -212
  68. package/examples/skills/skill-creator/SKILL.md +0 -223
  69. package/examples/skills/swarm-coordination/SKILL.md +0 -292
  70. package/global-skills/cli-builder/SKILL.md +0 -344
  71. package/global-skills/cli-builder/references/advanced-patterns.md +0 -244
  72. package/global-skills/learning-systems/SKILL.md +0 -644
  73. package/global-skills/skill-creator/LICENSE.txt +0 -202
  74. package/global-skills/skill-creator/SKILL.md +0 -352
  75. package/global-skills/skill-creator/references/output-patterns.md +0 -82
  76. package/global-skills/skill-creator/references/workflows.md +0 -28
  77. package/global-skills/swarm-coordination/SKILL.md +0 -995
  78. package/global-skills/swarm-coordination/references/coordinator-patterns.md +0 -235
  79. package/global-skills/swarm-coordination/references/strategies.md +0 -138
  80. package/global-skills/system-design/SKILL.md +0 -213
  81. package/global-skills/testing-patterns/SKILL.md +0 -430
  82. package/global-skills/testing-patterns/references/dependency-breaking-catalog.md +0 -586
  83. package/opencode-swarm-plugin-0.30.7.tgz +0 -0
  84. package/opencode-swarm-plugin-0.31.0.tgz +0 -0
  85. package/scripts/cleanup-test-memories.ts +0 -346
  86. package/scripts/init-skill.ts +0 -222
  87. package/scripts/migrate-unknown-sessions.ts +0 -349
  88. package/scripts/validate-skill.ts +0 -204
  89. package/src/agent-mail.ts +0 -1724
  90. package/src/anti-patterns.test.ts +0 -1167
  91. package/src/anti-patterns.ts +0 -448
  92. package/src/compaction-capture.integration.test.ts +0 -257
  93. package/src/compaction-hook.test.ts +0 -838
  94. package/src/compaction-hook.ts +0 -1204
  95. package/src/compaction-observability.integration.test.ts +0 -139
  96. package/src/compaction-observability.test.ts +0 -187
  97. package/src/compaction-observability.ts +0 -324
  98. package/src/compaction-prompt-scorers.test.ts +0 -475
  99. package/src/compaction-prompt-scoring.ts +0 -300
  100. package/src/contributor-tools.test.ts +0 -133
  101. package/src/contributor-tools.ts +0 -201
  102. package/src/dashboard.test.ts +0 -611
  103. package/src/dashboard.ts +0 -462
  104. package/src/error-enrichment.test.ts +0 -403
  105. package/src/error-enrichment.ts +0 -219
  106. package/src/eval-capture.test.ts +0 -1015
  107. package/src/eval-capture.ts +0 -929
  108. package/src/eval-gates.test.ts +0 -306
  109. package/src/eval-gates.ts +0 -218
  110. package/src/eval-history.test.ts +0 -508
  111. package/src/eval-history.ts +0 -214
  112. package/src/eval-learning.test.ts +0 -378
  113. package/src/eval-learning.ts +0 -360
  114. package/src/eval-runner.test.ts +0 -223
  115. package/src/eval-runner.ts +0 -402
  116. package/src/export-tools.test.ts +0 -476
  117. package/src/export-tools.ts +0 -257
  118. package/src/hive.integration.test.ts +0 -2241
  119. package/src/hive.ts +0 -1628
  120. package/src/index.ts +0 -940
  121. package/src/learning.integration.test.ts +0 -1815
  122. package/src/learning.ts +0 -1079
  123. package/src/logger.test.ts +0 -189
  124. package/src/logger.ts +0 -135
  125. package/src/mandate-promotion.test.ts +0 -473
  126. package/src/mandate-promotion.ts +0 -239
  127. package/src/mandate-storage.integration.test.ts +0 -601
  128. package/src/mandate-storage.test.ts +0 -578
  129. package/src/mandate-storage.ts +0 -794
  130. package/src/mandates.ts +0 -540
  131. package/src/memory-tools.test.ts +0 -195
  132. package/src/memory-tools.ts +0 -344
  133. package/src/memory.integration.test.ts +0 -334
  134. package/src/memory.test.ts +0 -158
  135. package/src/memory.ts +0 -527
  136. package/src/model-selection.test.ts +0 -188
  137. package/src/model-selection.ts +0 -68
  138. package/src/observability-tools.test.ts +0 -359
  139. package/src/observability-tools.ts +0 -871
  140. package/src/output-guardrails.test.ts +0 -438
  141. package/src/output-guardrails.ts +0 -381
  142. package/src/pattern-maturity.test.ts +0 -1160
  143. package/src/pattern-maturity.ts +0 -525
  144. package/src/planning-guardrails.test.ts +0 -491
  145. package/src/planning-guardrails.ts +0 -438
  146. package/src/plugin.ts +0 -23
  147. package/src/post-compaction-tracker.test.ts +0 -251
  148. package/src/post-compaction-tracker.ts +0 -237
  149. package/src/query-tools.test.ts +0 -636
  150. package/src/query-tools.ts +0 -324
  151. package/src/rate-limiter.integration.test.ts +0 -466
  152. package/src/rate-limiter.ts +0 -774
  153. package/src/replay-tools.test.ts +0 -496
  154. package/src/replay-tools.ts +0 -240
  155. package/src/repo-crawl.integration.test.ts +0 -441
  156. package/src/repo-crawl.ts +0 -610
  157. package/src/schemas/cell-events.test.ts +0 -347
  158. package/src/schemas/cell-events.ts +0 -807
  159. package/src/schemas/cell.ts +0 -257
  160. package/src/schemas/evaluation.ts +0 -166
  161. package/src/schemas/index.test.ts +0 -199
  162. package/src/schemas/index.ts +0 -286
  163. package/src/schemas/mandate.ts +0 -232
  164. package/src/schemas/swarm-context.ts +0 -115
  165. package/src/schemas/task.ts +0 -161
  166. package/src/schemas/worker-handoff.test.ts +0 -302
  167. package/src/schemas/worker-handoff.ts +0 -131
  168. package/src/sessions/agent-discovery.test.ts +0 -137
  169. package/src/sessions/agent-discovery.ts +0 -112
  170. package/src/sessions/index.ts +0 -15
  171. package/src/skills.integration.test.ts +0 -1192
  172. package/src/skills.test.ts +0 -643
  173. package/src/skills.ts +0 -1549
  174. package/src/storage.integration.test.ts +0 -341
  175. package/src/storage.ts +0 -884
  176. package/src/structured.integration.test.ts +0 -817
  177. package/src/structured.test.ts +0 -1046
  178. package/src/structured.ts +0 -762
  179. package/src/swarm-decompose.test.ts +0 -188
  180. package/src/swarm-decompose.ts +0 -1302
  181. package/src/swarm-deferred.integration.test.ts +0 -157
  182. package/src/swarm-deferred.test.ts +0 -38
  183. package/src/swarm-insights.test.ts +0 -214
  184. package/src/swarm-insights.ts +0 -459
  185. package/src/swarm-mail.integration.test.ts +0 -970
  186. package/src/swarm-mail.ts +0 -739
  187. package/src/swarm-orchestrate.integration.test.ts +0 -282
  188. package/src/swarm-orchestrate.test.ts +0 -548
  189. package/src/swarm-orchestrate.ts +0 -3084
  190. package/src/swarm-prompts.test.ts +0 -1270
  191. package/src/swarm-prompts.ts +0 -2077
  192. package/src/swarm-research.integration.test.ts +0 -701
  193. package/src/swarm-research.test.ts +0 -698
  194. package/src/swarm-research.ts +0 -472
  195. package/src/swarm-review.integration.test.ts +0 -285
  196. package/src/swarm-review.test.ts +0 -879
  197. package/src/swarm-review.ts +0 -709
  198. package/src/swarm-strategies.ts +0 -407
  199. package/src/swarm-worktree.test.ts +0 -501
  200. package/src/swarm-worktree.ts +0 -575
  201. package/src/swarm.integration.test.ts +0 -2377
  202. package/src/swarm.ts +0 -38
  203. package/src/tool-adapter.integration.test.ts +0 -1221
  204. package/src/tool-availability.ts +0 -461
  205. package/tsconfig.json +0 -28
@@ -1,327 +0,0 @@
1
- {"timestamp":"2025-12-25T04:28:42.041Z","eval_name":"compaction-prompt","score":0.85,"run_count":1}
2
- {"timestamp":"2025-12-25T04:28:42.041Z","eval_name":"coordinator-behavior","score":0.85,"run_count":1}
3
- {"timestamp":"2025-12-25T04:28:42.042Z","eval_name":"coordinator-session","score":0.85,"run_count":1}
4
- {"timestamp":"2025-12-25T04:28:42.042Z","eval_name":"swarm-decomposition","score":0.85,"run_count":1}
5
- {"timestamp":"2025-12-25T04:28:52.405Z","eval_name":"compaction-prompt","score":0.85,"run_count":2}
6
- {"timestamp":"2025-12-25T04:28:52.405Z","eval_name":"coordinator-behavior","score":0.85,"run_count":2}
7
- {"timestamp":"2025-12-25T04:28:52.405Z","eval_name":"coordinator-session","score":0.85,"run_count":2}
8
- {"timestamp":"2025-12-25T04:28:52.405Z","eval_name":"swarm-decomposition","score":0.85,"run_count":2}
9
- {"timestamp":"2025-12-25T05:11:18.469Z","eval_name":"compaction-prompt","score":0.85,"run_count":3}
10
- {"timestamp":"2025-12-25T05:11:18.469Z","eval_name":"coordinator-behavior","score":0.85,"run_count":3}
11
- {"timestamp":"2025-12-25T05:11:18.469Z","eval_name":"coordinator-session","score":0.85,"run_count":3}
12
- {"timestamp":"2025-12-25T05:11:18.469Z","eval_name":"swarm-decomposition","score":0.85,"run_count":3}
13
- {"timestamp":"2025-12-25T16:30:42.957Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":1}
14
- {"timestamp":"2025-12-25T16:30:42.957Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":1}
15
- {"timestamp":"2025-12-25T16:30:42.957Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":1}
16
- {"timestamp":"2025-12-25T16:30:42.957Z","eval_name":"Swarm Decomposition Quality","score":0.7213888888888889,"run_count":1}
17
- {"timestamp":"2025-12-25T16:30:42.957Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":1}
18
- {"timestamp":"2025-12-25T16:30:42.957Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":1}
19
- {"timestamp":"2025-12-25T16:30:42.957Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":1}
20
- {"timestamp":"2025-12-25T16:30:42.958Z","eval_name":"No False Positives","score":1,"run_count":1}
21
- {"timestamp":"2025-12-25T16:30:42.958Z","eval_name":"Example: Basic scorer test","score":1,"run_count":1}
22
- {"timestamp":"2025-12-25T16:30:42.958Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":1}
23
- {"timestamp":"2025-12-25T16:30:42.958Z","eval_name":"Placeholder Detection","score":0,"run_count":1}
24
- {"timestamp":"2025-12-25T16:30:42.958Z","eval_name":"Generic Instructions Fail","score":0,"run_count":1}
25
- {"timestamp":"2025-12-25T16:30:42.958Z","eval_name":"First Tool Discipline","score":0,"run_count":1}
26
- {"timestamp":"2025-12-25T16:30:42.958Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":1}
27
- {"timestamp":"2025-12-25T16:30:42.958Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":1}
28
- {"timestamp":"2025-12-25T16:30:42.958Z","eval_name":"Coordinator Behavior After Compaction","score":0.8645833333333333,"run_count":1}
29
- {"timestamp":"2025-12-25T16:30:43.088Z","eval_name":"Example: Basic scorer test","score":1,"run_count":2}
30
- {"timestamp":"2025-12-25T16:30:43.202Z","eval_name":"Example: Basic scorer test","score":1,"run_count":3}
31
- {"timestamp":"2025-12-25T16:30:43.316Z","eval_name":"Example: Basic scorer test","score":1,"run_count":4}
32
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":2}
33
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":2}
34
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":2}
35
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Swarm Decomposition Quality","score":0.6748148148148146,"run_count":2}
36
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":2}
37
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":2}
38
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":2}
39
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"No False Positives","score":1,"run_count":2}
40
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Example: Basic scorer test","score":1,"run_count":5}
41
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Coordinator Behavior After Compaction","score":1,"run_count":2}
42
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":2}
43
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":2}
44
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Placeholder Detection","score":0,"run_count":2}
45
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Generic Instructions Fail","score":0,"run_count":2}
46
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"First Tool Discipline","score":0,"run_count":2}
47
- {"timestamp":"2025-12-25T16:31:17.738Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":2}
48
- {"timestamp":"2025-12-25T16:31:17.874Z","eval_name":"Example: Basic scorer test","score":1,"run_count":6}
49
- {"timestamp":"2025-12-25T16:31:17.995Z","eval_name":"Example: Basic scorer test","score":1,"run_count":7}
50
- {"timestamp":"2025-12-25T16:31:18.113Z","eval_name":"Example: Basic scorer test","score":1,"run_count":8}
51
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":3}
52
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":3}
53
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":3}
54
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Swarm Decomposition Quality","score":0.6988888888888889,"run_count":3}
55
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":3}
56
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":3}
57
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":3}
58
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"No False Positives","score":1,"run_count":3}
59
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Example: Basic scorer test","score":1,"run_count":9}
60
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":3}
61
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":3}
62
- {"timestamp":"2025-12-25T16:32:49.807Z","eval_name":"Placeholder Detection","score":0,"run_count":3}
63
- {"timestamp":"2025-12-25T16:32:49.808Z","eval_name":"Generic Instructions Fail","score":0,"run_count":3}
64
- {"timestamp":"2025-12-25T16:32:49.808Z","eval_name":"First Tool Discipline","score":0,"run_count":3}
65
- {"timestamp":"2025-12-25T16:32:49.808Z","eval_name":"Coordinator Behavior After Compaction","score":1,"run_count":3}
66
- {"timestamp":"2025-12-25T16:32:49.808Z","eval_name":"Coordinator Resists Direct Implementation","score":0.9375,"run_count":3}
67
- {"timestamp":"2025-12-25T16:32:49.943Z","eval_name":"Example: Basic scorer test","score":1,"run_count":10}
68
- {"timestamp":"2025-12-25T16:32:50.073Z","eval_name":"Example: Basic scorer test","score":1,"run_count":11}
69
- {"timestamp":"2025-12-25T16:32:50.199Z","eval_name":"Example: Basic scorer test","score":1,"run_count":12}
70
- {"timestamp":"2025-12-25T16:35:31.083Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":4}
71
- {"timestamp":"2025-12-25T16:35:31.083Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":4}
72
- {"timestamp":"2025-12-25T16:35:31.083Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":4}
73
- {"timestamp":"2025-12-25T16:35:31.083Z","eval_name":"Swarm Decomposition Quality","score":0.6798611111111109,"run_count":4}
74
- {"timestamp":"2025-12-25T16:35:31.083Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":4}
75
- {"timestamp":"2025-12-25T16:35:31.083Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":4}
76
- {"timestamp":"2025-12-25T16:35:31.083Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":4}
77
- {"timestamp":"2025-12-25T16:35:31.083Z","eval_name":"No False Positives","score":1,"run_count":4}
78
- {"timestamp":"2025-12-25T16:35:31.083Z","eval_name":"Example: Basic scorer test","score":1,"run_count":13}
79
- {"timestamp":"2025-12-25T16:35:31.084Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":4}
80
- {"timestamp":"2025-12-25T16:35:31.084Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":4}
81
- {"timestamp":"2025-12-25T16:35:31.084Z","eval_name":"Placeholder Detection","score":0,"run_count":4}
82
- {"timestamp":"2025-12-25T16:35:31.084Z","eval_name":"Generic Instructions Fail","score":0,"run_count":4}
83
- {"timestamp":"2025-12-25T16:35:31.084Z","eval_name":"First Tool Discipline","score":0,"run_count":4}
84
- {"timestamp":"2025-12-25T16:35:31.084Z","eval_name":"Coordinator Resists Direct Implementation","score":0.9375,"run_count":4}
85
- {"timestamp":"2025-12-25T16:35:31.084Z","eval_name":"Coordinator Behavior After Compaction","score":0.8645833333333333,"run_count":4}
86
- {"timestamp":"2025-12-25T16:35:31.221Z","eval_name":"Example: Basic scorer test","score":1,"run_count":14}
87
- {"timestamp":"2025-12-25T16:35:31.329Z","eval_name":"Example: Basic scorer test","score":1,"run_count":15}
88
- {"timestamp":"2025-12-25T16:35:31.444Z","eval_name":"Example: Basic scorer test","score":1,"run_count":16}
89
- {"timestamp":"2025-12-25T16:35:31.685Z","eval_name":"Example: Basic scorer test","score":1,"run_count":17}
90
- {"timestamp":"2025-12-25T16:35:31.843Z","eval_name":"Example: Basic scorer test","score":1,"run_count":18}
91
- {"timestamp":"2025-12-25T16:35:31.962Z","eval_name":"Example: Basic scorer test","score":1,"run_count":19}
92
- {"timestamp":"2025-12-25T16:35:32.076Z","eval_name":"Example: Basic scorer test","score":1,"run_count":20}
93
- {"timestamp":"2025-12-25T16:36:03.596Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":5}
94
- {"timestamp":"2025-12-25T16:36:03.596Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":5}
95
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":5}
96
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Swarm Decomposition Quality","score":0.6845833333333333,"run_count":5}
97
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":5}
98
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":5}
99
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":5}
100
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"No False Positives","score":1,"run_count":5}
101
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Example: Basic scorer test","score":1,"run_count":21}
102
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":5}
103
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":5}
104
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Placeholder Detection","score":0,"run_count":5}
105
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Generic Instructions Fail","score":0,"run_count":5}
106
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"First Tool Discipline","score":0,"run_count":5}
107
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Coordinator Behavior After Compaction","score":1,"run_count":5}
108
- {"timestamp":"2025-12-25T16:36:03.597Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":5}
109
- {"timestamp":"2025-12-25T16:36:03.727Z","eval_name":"Example: Basic scorer test","score":1,"run_count":22}
110
- {"timestamp":"2025-12-25T16:36:03.842Z","eval_name":"Example: Basic scorer test","score":1,"run_count":23}
111
- {"timestamp":"2025-12-25T16:36:03.951Z","eval_name":"Example: Basic scorer test","score":1,"run_count":24}
112
- {"timestamp":"2025-12-25T16:36:04.183Z","eval_name":"Example: Basic scorer test","score":1,"run_count":25}
113
- {"timestamp":"2025-12-25T16:36:04.330Z","eval_name":"Example: Basic scorer test","score":1,"run_count":26}
114
- {"timestamp":"2025-12-25T16:36:04.445Z","eval_name":"Example: Basic scorer test","score":1,"run_count":27}
115
- {"timestamp":"2025-12-25T16:36:04.555Z","eval_name":"Example: Basic scorer test","score":1,"run_count":28}
116
- {"timestamp":"2025-12-25T16:36:32.176Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":6}
117
- {"timestamp":"2025-12-25T16:36:32.176Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":6}
118
- {"timestamp":"2025-12-25T16:36:32.176Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":6}
119
- {"timestamp":"2025-12-25T16:36:32.176Z","eval_name":"Swarm Decomposition Quality","score":0.6852777777777778,"run_count":6}
120
- {"timestamp":"2025-12-25T16:36:32.176Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":6}
121
- {"timestamp":"2025-12-25T16:36:32.176Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":6}
122
- {"timestamp":"2025-12-25T16:36:32.176Z","eval_name":"No False Positives","score":1,"run_count":6}
123
- {"timestamp":"2025-12-25T16:36:32.177Z","eval_name":"Example: Basic scorer test","score":1,"run_count":29}
124
- {"timestamp":"2025-12-25T16:36:32.177Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":6}
125
- {"timestamp":"2025-12-25T16:36:32.177Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":6}
126
- {"timestamp":"2025-12-25T16:36:32.177Z","eval_name":"Placeholder Detection","score":0,"run_count":6}
127
- {"timestamp":"2025-12-25T16:36:32.177Z","eval_name":"Generic Instructions Fail","score":0,"run_count":6}
128
- {"timestamp":"2025-12-25T16:36:32.177Z","eval_name":"First Tool Discipline","score":0,"run_count":6}
129
- {"timestamp":"2025-12-25T16:36:32.177Z","eval_name":"Coordinator Behavior After Compaction","score":0.978125,"run_count":6}
130
- {"timestamp":"2025-12-25T16:36:32.177Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":6}
131
- {"timestamp":"2025-12-25T16:36:32.177Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":6}
132
- {"timestamp":"2025-12-25T16:36:32.305Z","eval_name":"Example: Basic scorer test","score":1,"run_count":30}
133
- {"timestamp":"2025-12-25T16:36:32.416Z","eval_name":"Example: Basic scorer test","score":1,"run_count":31}
134
- {"timestamp":"2025-12-25T16:36:32.527Z","eval_name":"Example: Basic scorer test","score":1,"run_count":32}
135
- {"timestamp":"2025-12-25T16:36:32.755Z","eval_name":"Example: Basic scorer test","score":1,"run_count":33}
136
- {"timestamp":"2025-12-25T16:36:32.957Z","eval_name":"Example: Basic scorer test","score":1,"run_count":34}
137
- {"timestamp":"2025-12-25T16:36:33.071Z","eval_name":"Example: Basic scorer test","score":1,"run_count":35}
138
- {"timestamp":"2025-12-25T16:36:33.180Z","eval_name":"Example: Basic scorer test","score":1,"run_count":36}
139
- {"timestamp":"2025-12-25T16:38:02.146Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":7}
140
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":7}
141
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":7}
142
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Swarm Decomposition Quality","score":0.6726388888888888,"run_count":7}
143
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":7}
144
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":7}
145
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":7}
146
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"No False Positives","score":1,"run_count":7}
147
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Example: Basic scorer test","score":1,"run_count":37}
148
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":7}
149
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":7}
150
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Placeholder Detection","score":0,"run_count":7}
151
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"Generic Instructions Fail","score":0,"run_count":7}
152
- {"timestamp":"2025-12-25T16:38:02.147Z","eval_name":"First Tool Discipline","score":0,"run_count":7}
153
- {"timestamp":"2025-12-25T16:38:02.148Z","eval_name":"Coordinator Behavior After Compaction","score":0.8645833333333333,"run_count":7}
154
- {"timestamp":"2025-12-25T16:38:02.148Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":7}
155
- {"timestamp":"2025-12-25T16:38:02.276Z","eval_name":"Example: Basic scorer test","score":1,"run_count":38}
156
- {"timestamp":"2025-12-25T16:38:02.428Z","eval_name":"Example: Basic scorer test","score":1,"run_count":39}
157
- {"timestamp":"2025-12-25T16:38:02.547Z","eval_name":"Example: Basic scorer test","score":1,"run_count":40}
158
- {"timestamp":"2025-12-25T16:38:02.782Z","eval_name":"Example: Basic scorer test","score":1,"run_count":41}
159
- {"timestamp":"2025-12-25T16:38:02.933Z","eval_name":"Example: Basic scorer test","score":1,"run_count":42}
160
- {"timestamp":"2025-12-25T16:38:03.050Z","eval_name":"Example: Basic scorer test","score":1,"run_count":43}
161
- {"timestamp":"2025-12-25T16:38:03.165Z","eval_name":"Example: Basic scorer test","score":1,"run_count":44}
162
- {"timestamp":"2025-12-25T16:38:52.756Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":8}
163
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":8}
164
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":8}
165
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Swarm Decomposition Quality","score":0.695,"run_count":8}
166
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":8}
167
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":8}
168
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":8}
169
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"No False Positives","score":1,"run_count":8}
170
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Example: Basic scorer test","score":1,"run_count":45}
171
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":8}
172
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Placeholder Detection","score":0,"run_count":8}
173
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Generic Instructions Fail","score":0,"run_count":8}
174
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"First Tool Discipline","score":0,"run_count":8}
175
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":8}
176
- {"timestamp":"2025-12-25T16:38:52.757Z","eval_name":"Coordinator Behavior After Compaction","score":0.9526041666666667,"run_count":8}
177
- {"timestamp":"2025-12-25T16:38:52.758Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":8}
178
- {"timestamp":"2025-12-25T16:38:52.903Z","eval_name":"Example: Basic scorer test","score":1,"run_count":46}
179
- {"timestamp":"2025-12-25T16:38:53.020Z","eval_name":"Example: Basic scorer test","score":1,"run_count":47}
180
- {"timestamp":"2025-12-25T16:38:53.136Z","eval_name":"Example: Basic scorer test","score":1,"run_count":48}
181
- {"timestamp":"2025-12-25T16:38:53.367Z","eval_name":"Example: Basic scorer test","score":1,"run_count":49}
182
- {"timestamp":"2025-12-25T16:38:53.511Z","eval_name":"Example: Basic scorer test","score":1,"run_count":50}
183
- {"timestamp":"2025-12-25T16:38:53.624Z","eval_name":"Example: Basic scorer test","score":1,"run_count":51}
184
- {"timestamp":"2025-12-25T16:38:53.737Z","eval_name":"Example: Basic scorer test","score":1,"run_count":52}
185
- {"timestamp":"2025-12-25T16:40:39.219Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":9}
186
- {"timestamp":"2025-12-25T16:40:39.219Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":9}
187
- {"timestamp":"2025-12-25T16:40:39.219Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":9}
188
- {"timestamp":"2025-12-25T16:40:39.219Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":9}
189
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"Swarm Decomposition Quality","score":0.7020833333333334,"run_count":9}
190
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":9}
191
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"No False Positives","score":1,"run_count":9}
192
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":9}
193
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"Example: Basic scorer test","score":1,"run_count":53}
194
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"Coordinator Behavior After Compaction","score":0.7291666666666666,"run_count":9}
195
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":9}
196
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":9}
197
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":9}
198
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"Placeholder Detection","score":0,"run_count":9}
199
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"Generic Instructions Fail","score":0,"run_count":9}
200
- {"timestamp":"2025-12-25T16:40:39.220Z","eval_name":"First Tool Discipline","score":0,"run_count":9}
201
- {"timestamp":"2025-12-25T16:40:39.352Z","eval_name":"Example: Basic scorer test","score":1,"run_count":54}
202
- {"timestamp":"2025-12-25T16:40:39.460Z","eval_name":"Example: Basic scorer test","score":1,"run_count":55}
203
- {"timestamp":"2025-12-25T16:40:39.572Z","eval_name":"Example: Basic scorer test","score":1,"run_count":56}
204
- {"timestamp":"2025-12-25T16:40:39.816Z","eval_name":"Example: Basic scorer test","score":1,"run_count":57}
205
- {"timestamp":"2025-12-25T16:40:39.947Z","eval_name":"Example: Basic scorer test","score":1,"run_count":58}
206
- {"timestamp":"2025-12-25T16:40:40.084Z","eval_name":"Example: Basic scorer test","score":1,"run_count":59}
207
- {"timestamp":"2025-12-25T16:40:40.202Z","eval_name":"Example: Basic scorer test","score":1,"run_count":60}
208
- {"timestamp":"2025-12-25T16:43:12.851Z","eval_name":"Example: Basic scorer test","score":1,"run_count":61}
209
- {"timestamp":"2025-12-25T16:43:43.041Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":10}
210
- {"timestamp":"2025-12-25T16:43:43.041Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":10}
211
- {"timestamp":"2025-12-25T16:43:43.041Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":10}
212
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"Swarm Decomposition Quality","score":0.6909722222222222,"run_count":10}
213
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":10}
214
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":10}
215
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":10}
216
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"No False Positives","score":1,"run_count":10}
217
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"Example: Basic scorer test","score":1,"run_count":62}
218
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":10}
219
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"Placeholder Detection","score":0,"run_count":10}
220
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"Generic Instructions Fail","score":0,"run_count":10}
221
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"First Tool Discipline","score":0,"run_count":10}
222
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":10}
223
- {"timestamp":"2025-12-25T16:43:43.042Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":10}
224
- {"timestamp":"2025-12-25T16:43:43.043Z","eval_name":"Coordinator Behavior After Compaction","score":1,"run_count":10}
225
- {"timestamp":"2025-12-25T16:44:12.471Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":11}
226
- {"timestamp":"2025-12-25T16:44:12.471Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":11}
227
- {"timestamp":"2025-12-25T16:44:12.471Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":11}
228
- {"timestamp":"2025-12-25T16:44:12.471Z","eval_name":"Swarm Decomposition Quality","score":0.6720833333333333,"run_count":11}
229
- {"timestamp":"2025-12-25T16:44:12.471Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":11}
230
- {"timestamp":"2025-12-25T16:44:12.471Z","eval_name":"Example: Basic scorer test","score":1,"run_count":63}
231
- {"timestamp":"2025-12-25T16:44:12.471Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":11}
232
- {"timestamp":"2025-12-25T16:44:12.472Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":11}
233
- {"timestamp":"2025-12-25T16:44:12.472Z","eval_name":"No False Positives","score":1,"run_count":11}
234
- {"timestamp":"2025-12-25T16:44:12.472Z","eval_name":"Coordinator Behavior After Compaction","score":0.9796875,"run_count":11}
235
- {"timestamp":"2025-12-25T16:44:12.472Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":11}
236
- {"timestamp":"2025-12-25T16:44:12.472Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":11}
237
- {"timestamp":"2025-12-25T16:44:12.472Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":11}
238
- {"timestamp":"2025-12-25T16:44:12.472Z","eval_name":"Placeholder Detection","score":0,"run_count":11}
239
- {"timestamp":"2025-12-25T16:44:12.472Z","eval_name":"Generic Instructions Fail","score":0,"run_count":11}
240
- {"timestamp":"2025-12-25T16:44:12.472Z","eval_name":"First Tool Discipline","score":0,"run_count":11}
241
- {"timestamp":"2025-12-25T16:49:55.548Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":12}
242
- {"timestamp":"2025-12-25T16:49:55.549Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":12}
243
- {"timestamp":"2025-12-25T16:49:55.555Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":12}
244
- {"timestamp":"2025-12-25T16:49:55.555Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":12}
245
- {"timestamp":"2025-12-25T16:49:55.555Z","eval_name":"Swarm Decomposition Quality","score":0.7001388888888888,"run_count":12}
246
- {"timestamp":"2025-12-25T16:49:55.555Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":12}
247
- {"timestamp":"2025-12-25T16:49:55.556Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":12}
248
- {"timestamp":"2025-12-25T16:49:55.557Z","eval_name":"No False Positives","score":1,"run_count":12}
249
- {"timestamp":"2025-12-25T16:49:55.557Z","eval_name":"Example: Basic scorer test","score":1,"run_count":64}
250
- {"timestamp":"2025-12-25T16:49:55.557Z","eval_name":"Generic Instructions Fail","score":0,"run_count":12}
251
- {"timestamp":"2025-12-25T16:49:55.557Z","eval_name":"First Tool Discipline","score":0,"run_count":12}
252
- {"timestamp":"2025-12-25T16:49:55.561Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":12}
253
- {"timestamp":"2025-12-25T16:49:55.561Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":12}
254
- {"timestamp":"2025-12-25T16:49:55.561Z","eval_name":"Placeholder Detection","score":0,"run_count":12}
255
- {"timestamp":"2025-12-25T16:49:55.561Z","eval_name":"Coordinator Behavior After Compaction","score":1,"run_count":12}
256
- {"timestamp":"2025-12-25T16:49:55.565Z","eval_name":"Coordinator Resists Direct Implementation","score":0.9375,"run_count":12}
257
- {"timestamp":"2025-12-25T16:49:55.697Z","eval_name":"Example: Basic scorer test","score":1,"run_count":65}
258
- {"timestamp":"2025-12-25T16:49:55.813Z","eval_name":"Example: Basic scorer test","score":1,"run_count":66}
259
- {"timestamp":"2025-12-25T16:49:55.934Z","eval_name":"Example: Basic scorer test","score":1,"run_count":67}
260
- {"timestamp":"2025-12-25T16:49:56.178Z","eval_name":"Example: Basic scorer test","score":1,"run_count":68}
261
- {"timestamp":"2025-12-25T16:49:56.327Z","eval_name":"Example: Basic scorer test","score":1,"run_count":69}
262
- {"timestamp":"2025-12-25T16:49:56.446Z","eval_name":"Example: Basic scorer test","score":1,"run_count":70}
263
- {"timestamp":"2025-12-25T16:49:56.556Z","eval_name":"Example: Basic scorer test","score":1,"run_count":71}
264
- {"timestamp":"2025-12-25T17:06:10.610Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":13}
265
- {"timestamp":"2025-12-25T17:06:10.610Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":13}
266
- {"timestamp":"2025-12-25T17:06:10.610Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":13}
267
- {"timestamp":"2025-12-25T17:06:10.610Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":13}
268
- {"timestamp":"2025-12-25T17:06:10.610Z","eval_name":"Swarm Decomposition Quality","score":0.6847222222222221,"run_count":13}
269
- {"timestamp":"2025-12-25T17:06:10.610Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":13}
270
- {"timestamp":"2025-12-25T17:06:10.610Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":13}
271
- {"timestamp":"2025-12-25T17:06:10.610Z","eval_name":"No False Positives","score":1,"run_count":13}
272
- {"timestamp":"2025-12-25T17:06:10.611Z","eval_name":"Example: Basic scorer test","score":1,"run_count":72}
273
- {"timestamp":"2025-12-25T17:06:10.611Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":13}
274
- {"timestamp":"2025-12-25T17:06:10.611Z","eval_name":"Placeholder Detection","score":0,"run_count":13}
275
- {"timestamp":"2025-12-25T17:06:10.611Z","eval_name":"Generic Instructions Fail","score":0,"run_count":13}
276
- {"timestamp":"2025-12-25T17:06:10.611Z","eval_name":"First Tool Discipline","score":0,"run_count":13}
277
- {"timestamp":"2025-12-25T17:06:10.611Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":13}
278
- {"timestamp":"2025-12-25T17:06:10.611Z","eval_name":"Coordinator Behavior After Compaction","score":0.8645833333333333,"run_count":13}
279
- {"timestamp":"2025-12-25T17:06:10.611Z","eval_name":"Coordinator Resists Direct Implementation","score":0.9375,"run_count":13}
280
- {"timestamp":"2025-12-25T18:58:44.923Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":14}
281
- {"timestamp":"2025-12-25T18:58:44.923Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":14}
282
- {"timestamp":"2025-12-25T18:58:44.923Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":14}
283
- {"timestamp":"2025-12-25T18:58:44.924Z","eval_name":"Swarm Decomposition Quality","score":0.7095833333333333,"run_count":14}
284
- {"timestamp":"2025-12-25T18:58:44.924Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":14}
285
- {"timestamp":"2025-12-25T18:58:44.924Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":14}
286
- {"timestamp":"2025-12-25T18:58:44.924Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":14}
287
- {"timestamp":"2025-12-25T18:58:44.924Z","eval_name":"No False Positives","score":1,"run_count":14}
288
- {"timestamp":"2025-12-25T18:58:44.924Z","eval_name":"Example: Basic scorer test","score":1,"run_count":73}
289
- {"timestamp":"2025-12-25T18:58:44.924Z","eval_name":"Generic Instructions Fail","score":0,"run_count":14}
290
- {"timestamp":"2025-12-25T18:58:44.924Z","eval_name":"First Tool Discipline","score":0,"run_count":14}
291
- {"timestamp":"2025-12-25T18:58:44.924Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":14}
292
- {"timestamp":"2025-12-25T18:58:44.925Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":14}
293
- {"timestamp":"2025-12-25T18:58:44.925Z","eval_name":"Placeholder Detection","score":0,"run_count":14}
294
- {"timestamp":"2025-12-25T18:58:44.925Z","eval_name":"Coordinator Behavior After Compaction","score":0.9375,"run_count":14}
295
- {"timestamp":"2025-12-25T18:58:44.925Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":14}
296
- {"timestamp":"2025-12-25T18:59:58.928Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":15}
297
- {"timestamp":"2025-12-25T18:59:58.929Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":15}
298
- {"timestamp":"2025-12-25T18:59:58.929Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":15}
299
- {"timestamp":"2025-12-25T18:59:58.929Z","eval_name":"Swarm Decomposition Quality","score":0.6944444444444443,"run_count":15}
300
- {"timestamp":"2025-12-25T18:59:58.929Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":15}
301
- {"timestamp":"2025-12-25T18:59:58.929Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":15}
302
- {"timestamp":"2025-12-25T18:59:58.929Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":15}
303
- {"timestamp":"2025-12-25T18:59:58.929Z","eval_name":"No False Positives","score":1,"run_count":15}
304
- {"timestamp":"2025-12-25T18:59:58.929Z","eval_name":"Example: Basic scorer test","score":1,"run_count":74}
305
- {"timestamp":"2025-12-25T18:59:58.929Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":15}
306
- {"timestamp":"2025-12-25T18:59:58.929Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":15}
307
- {"timestamp":"2025-12-25T18:59:58.930Z","eval_name":"Placeholder Detection","score":0,"run_count":15}
308
- {"timestamp":"2025-12-25T18:59:58.930Z","eval_name":"Generic Instructions Fail","score":0,"run_count":15}
309
- {"timestamp":"2025-12-25T18:59:58.930Z","eval_name":"First Tool Discipline","score":0,"run_count":15}
310
- {"timestamp":"2025-12-25T18:59:58.930Z","eval_name":"Coordinator Behavior After Compaction","score":0.9171875,"run_count":15}
311
- {"timestamp":"2025-12-25T18:59:58.930Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":15}
312
- {"timestamp":"2025-12-25T19:00:48.709Z","eval_name":"Coordinator Discipline - Synthetic Fixtures","score":0.6354444444444443,"run_count":16}
313
- {"timestamp":"2025-12-25T19:00:48.709Z","eval_name":"Coordinator Discipline - Real Sessions","score":0,"run_count":16}
314
- {"timestamp":"2025-12-25T19:00:48.710Z","eval_name":"Coordinator Discipline - Perfect vs Bad","score":0.5416666666666666,"run_count":16}
315
- {"timestamp":"2025-12-25T19:00:48.710Z","eval_name":"Swarm Decomposition Quality","score":0.5464583333333334,"run_count":16}
316
- {"timestamp":"2025-12-25T19:00:48.710Z","eval_name":"Decomposition Edge Cases","score":0.775,"run_count":16}
317
- {"timestamp":"2025-12-25T19:00:48.710Z","eval_name":"Compaction Hook Coordinator Resumption","score":0.95,"run_count":16}
318
- {"timestamp":"2025-12-25T19:00:48.710Z","eval_name":"Epic ID Specificity","score":0.5,"run_count":16}
319
- {"timestamp":"2025-12-25T19:00:48.710Z","eval_name":"No False Positives","score":1,"run_count":16}
320
- {"timestamp":"2025-12-25T19:00:48.710Z","eval_name":"Example: Basic scorer test","score":1,"run_count":75}
321
- {"timestamp":"2025-12-25T19:00:48.710Z","eval_name":"Perfect Prompt Scores 100%","score":1,"run_count":16}
322
- {"timestamp":"2025-12-25T19:00:48.711Z","eval_name":"Placeholder Detection","score":0,"run_count":16}
323
- {"timestamp":"2025-12-25T19:00:48.711Z","eval_name":"Generic Instructions Fail","score":0,"run_count":16}
324
- {"timestamp":"2025-12-25T19:00:48.711Z","eval_name":"First Tool Discipline","score":0,"run_count":16}
325
- {"timestamp":"2025-12-25T19:00:48.711Z","eval_name":"Compaction Prompt Quality","score":0.6342857142857142,"run_count":16}
326
- {"timestamp":"2025-12-25T19:00:48.711Z","eval_name":"Coordinator Behavior After Compaction","score":1,"run_count":16}
327
- {"timestamp":"2025-12-25T19:00:48.711Z","eval_name":"Coordinator Resists Direct Implementation","score":1,"run_count":16}
@@ -1,9 +0,0 @@
1
- $ bun build ./src/index.ts --outdir ./dist --target node --external @electric-sql/pglite --external swarm-mail --external vitest --external @vitest/ui --external lightningcss && bun build ./src/plugin.ts --outfile ./dist/plugin.js --target node --external @electric-sql/pglite --external swarm-mail --external vitest --external @vitest/ui --external lightningcss && tsc
2
- Bundled 1350 modules in 208ms
3
-
4
- index.js 4.34 MB (entry point)
5
-
6
- Bundled 1351 modules in 192ms
7
-
8
- plugin.js 4.31 MB (entry point)
9
-