coder-eval 0.8.4__tar.gz → 0.8.5__tar.gz

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 (545) hide show
  1. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/dependabot.yml +27 -1
  2. {coder_eval-0.8.4 → coder_eval-0.8.5}/CHANGELOG.md +56 -0
  3. {coder_eval-0.8.4 → coder_eval-0.8.5}/PKG-INFO +2 -2
  4. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/package.json +13 -3
  5. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/pnpm-lock.yaml +308 -189
  6. {coder_eval-0.8.4 → coder_eval-0.8.5}/pyproject.toml +2 -2
  7. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/__init__.py +1 -1
  8. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/cli/run_command.py +7 -3
  9. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/orchestration/experiment.py +109 -46
  10. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/orchestrator.py +24 -4
  11. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_dataset_expansion.py +170 -0
  12. coder_eval-0.8.5/tests/test_teardown_interrupt.py +90 -0
  13. {coder_eval-0.8.4 → coder_eval-0.8.5}/uv.lock +11 -5
  14. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/commands/coder-eval-code-review-full.md +0 -0
  15. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/commands/coder-eval-code-review-wf.md +0 -0
  16. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/commands/coder-eval-code-review.md +0 -0
  17. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/commands/coder-eval-create-plan.md +0 -0
  18. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/commands/coder-eval-implement-plan.md +0 -0
  19. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/commands/coder-eval-review.md +0 -0
  20. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/commands/coder-eval-run-analysis.md +0 -0
  21. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/commands/coder-eval-task-create.md +0 -0
  22. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/harness-candidates.md +0 -0
  23. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/shared/axes.md +0 -0
  24. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/shared/multi-model-review.md +0 -0
  25. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/shared/review-rubric.md +0 -0
  26. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/shared/run-layout.md +0 -0
  27. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/workflows/cr-axis.js +0 -0
  28. {coder_eval-0.8.4 → coder_eval-0.8.5}/.claude/workflows/cr-parent.js +0 -0
  29. {coder_eval-0.8.4 → coder_eval-0.8.5}/.env.example +0 -0
  30. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/CODEOWNERS +0 -0
  31. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/ISSUE_TEMPLATE/bug_report.yml +0 -0
  32. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/ISSUE_TEMPLATE/config.yml +0 -0
  33. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/code_review.md +0 -0
  34. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/workflows/claude-pr-review.yml +0 -0
  35. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/workflows/codeql.yml +0 -0
  36. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/workflows/conventional-commits.yml +0 -0
  37. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/workflows/docker-publish.yml +0 -0
  38. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/workflows/pr-checks.yml +0 -0
  39. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/workflows/publish-testpypi.yml +0 -0
  40. {coder_eval-0.8.4 → coder_eval-0.8.5}/.github/workflows/release.yml +0 -0
  41. {coder_eval-0.8.4 → coder_eval-0.8.5}/.gitignore +0 -0
  42. {coder_eval-0.8.4 → coder_eval-0.8.5}/.pre-commit-config.yaml +0 -0
  43. {coder_eval-0.8.4 → coder_eval-0.8.5}/.python-version +0 -0
  44. {coder_eval-0.8.4 → coder_eval-0.8.5}/CLAUDE.md +0 -0
  45. {coder_eval-0.8.4 → coder_eval-0.8.5}/CODE_OF_CONDUCT.md +0 -0
  46. {coder_eval-0.8.4 → coder_eval-0.8.5}/CONTRIBUTING.md +0 -0
  47. {coder_eval-0.8.4 → coder_eval-0.8.5}/LICENSE +0 -0
  48. {coder_eval-0.8.4 → coder_eval-0.8.5}/Makefile +0 -0
  49. {coder_eval-0.8.4 → coder_eval-0.8.5}/NOTICE +0 -0
  50. {coder_eval-0.8.4 → coder_eval-0.8.5}/README.md +0 -0
  51. {coder_eval-0.8.4 → coder_eval-0.8.5}/SECURITY.md +0 -0
  52. {coder_eval-0.8.4 → coder_eval-0.8.5}/docker/Dockerfile +0 -0
  53. {coder_eval-0.8.4 → coder_eval-0.8.5}/docker/Dockerfile.runtime +0 -0
  54. {coder_eval-0.8.4 → coder_eval-0.8.5}/docker/coder_eval_entrypoint.sh +0 -0
  55. {coder_eval-0.8.4 → coder_eval-0.8.5}/docker/coder_eval_runtime_entrypoint.sh +0 -0
  56. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/AB_EXPERIMENTS.md +0 -0
  57. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/BYOD.md +0 -0
  58. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/CODEX_AGENT_GUIDE.md +0 -0
  59. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/DOCKER_ISOLATION.md +0 -0
  60. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/IDEAS.md +0 -0
  61. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/TASK_DEFINITION_GUIDE.md +0 -0
  62. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/USER_GUIDE.md +0 -0
  63. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/assets/hero.gif +0 -0
  64. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/tutorials/01-first-evaluation.md +0 -0
  65. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/tutorials/02-ci-pipeline.md +0 -0
  66. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/tutorials/03-evalboard-local.md +0 -0
  67. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/tutorials/04-writing-a-task.md +0 -0
  68. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/tutorials/05-comparing-models.md +0 -0
  69. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/tutorials/06-use-docker-isolation.md +0 -0
  70. {coder_eval-0.8.4 → coder_eval-0.8.5}/docs/tutorials/README.md +0 -0
  71. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/.gitignore +0 -0
  72. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/README.md +0 -0
  73. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_components/__tests__/search-box.test.tsx +0 -0
  74. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_components/col-help.tsx +0 -0
  75. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_components/collapsible-rail.tsx +0 -0
  76. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_components/harness-badge.tsx +0 -0
  77. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_components/scroll-table.tsx +0 -0
  78. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_components/search-box.tsx +0 -0
  79. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_components/unit-toggle.tsx +0 -0
  80. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_components/version-list.tsx +0 -0
  81. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_components/window-selector.tsx +0 -0
  82. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_overview/daily-chart.tsx +0 -0
  83. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_overview/tag-rail.tsx +0 -0
  84. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_overview/turn-budget-chart.tsx +0 -0
  85. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/_overview/window-summary.tsx +0 -0
  86. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/api/download/route.ts +0 -0
  87. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/api/file/route.ts +0 -0
  88. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/api/refresh/__tests__/route.test.ts +0 -0
  89. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/api/refresh/route.ts +0 -0
  90. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/error.tsx +0 -0
  91. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/globals.css +0 -0
  92. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/icon.png +0 -0
  93. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/layout.tsx +0 -0
  94. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/page.tsx +0 -0
  95. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/path-to-ga/page.tsx +0 -0
  96. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/trends/__tests__/trends-view.test.tsx +0 -0
  97. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/trends/actions.ts +0 -0
  98. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/trends/page.tsx +0 -0
  99. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/trends/trends-view.tsx +0 -0
  100. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/watchlist/__tests__/watchlist-view.test.tsx +0 -0
  101. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/watchlist/page.tsx +0 -0
  102. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/app/watchlist/watchlist-view.tsx +0 -0
  103. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/next-env.d.ts +0 -0
  104. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/next.config.mjs +0 -0
  105. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/postcss.config.mjs +0 -0
  106. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/public/harness/antigravity.png +0 -0
  107. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/public/harness/claude-code.png +0 -0
  108. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/public/harness/codex.png +0 -0
  109. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/public/uipath.png +0 -0
  110. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/tailwind.config.ts +0 -0
  111. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/tsconfig.json +0 -0
  112. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/vitest.config.ts +0 -0
  113. {coder_eval-0.8.4 → coder_eval-0.8.5}/evalboard/vitest.setup.ts +0 -0
  114. {coder_eval-0.8.4 → coder_eval-0.8.5}/experiments/default.yaml +0 -0
  115. {coder_eval-0.8.4 → coder_eval-0.8.5}/experiments/early-stop-ab.yaml +0 -0
  116. {coder_eval-0.8.4 → coder_eval-0.8.5}/experiments/model-comparison.yaml +0 -0
  117. {coder_eval-0.8.4 → coder_eval-0.8.5}/experiments/permissions-smoke.yaml +0 -0
  118. {coder_eval-0.8.4 → coder_eval-0.8.5}/experiments/plugin-comparison.yaml +0 -0
  119. {coder_eval-0.8.4 → coder_eval-0.8.5}/experiments/prompt-mutations-example.yaml +0 -0
  120. {coder_eval-0.8.4 → coder_eval-0.8.5}/experiments/smoke_variants.yaml +0 -0
  121. {coder_eval-0.8.4 → coder_eval-0.8.5}/osv-scanner.toml +0 -0
  122. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/.gitattributes +0 -0
  123. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/agent.py +0 -0
  124. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/agents/__init__.py +0 -0
  125. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/agents/_logging.py +0 -0
  126. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/agents/antigravity_agent.py +0 -0
  127. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/agents/claude_code_agent.py +0 -0
  128. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/agents/codex_agent.py +0 -0
  129. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/agents/noop_agent.py +0 -0
  130. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/agents/registry.py +0 -0
  131. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/agents/watchdog.py +0 -0
  132. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/analysis.py +0 -0
  133. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/cli/__init__.py +0 -0
  134. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/cli/aggregate_command.py +0 -0
  135. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/cli/console.py +0 -0
  136. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/cli/evaluate_command.py +0 -0
  137. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/cli/plan_command.py +0 -0
  138. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/cli/report_command.py +0 -0
  139. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/cli/run_helpers.py +0 -0
  140. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/cli/run_task_internal_command.py +0 -0
  141. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/cli/utils.py +0 -0
  142. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/config.py +0 -0
  143. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/__init__.py +0 -0
  144. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/_classification_aggregate.py +0 -0
  145. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/agent_judge.py +0 -0
  146. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/base.py +0 -0
  147. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/classification_match.py +0 -0
  148. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/command_executed.py +0 -0
  149. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/commands_efficiency.py +0 -0
  150. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/file_check.py +0 -0
  151. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/file_contains.py +0 -0
  152. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/file_exists.py +0 -0
  153. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/file_matches_regex.py +0 -0
  154. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/json_check.py +0 -0
  155. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/llm_judge.py +0 -0
  156. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/reference_comparison.py +0 -0
  157. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/run_command.py +0 -0
  158. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/skill_triggered.py +0 -0
  159. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/criteria/uipath_eval.py +0 -0
  160. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/errors/__init__.py +0 -0
  161. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/errors/agent.py +0 -0
  162. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/errors/budget.py +0 -0
  163. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/errors/categories.py +0 -0
  164. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/errors/categorization.py +0 -0
  165. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/errors/executor.py +0 -0
  166. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/errors/judge.py +0 -0
  167. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/errors/retry.py +0 -0
  168. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/errors/timeout.py +0 -0
  169. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/__init__.py +0 -0
  170. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/checker.py +0 -0
  171. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/judge_anthropic.py +0 -0
  172. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/judge_bedrock.py +0 -0
  173. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/judge_context.py +0 -0
  174. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/judge_models.py +0 -0
  175. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/judge_persistence.py +0 -0
  176. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/judge_usage.py +0 -0
  177. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/sub_agent.py +0 -0
  178. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/summaries.py +0 -0
  179. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/evaluation/verdict_tool.py +0 -0
  180. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/formatting.py +0 -0
  181. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/isolation/__init__.py +0 -0
  182. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/isolation/docker_runner.py +0 -0
  183. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/logging_config.py +0 -0
  184. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/__init__.py +0 -0
  185. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/agent_config.py +0 -0
  186. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/container_paths.py +0 -0
  187. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/criteria.py +0 -0
  188. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/enums.py +0 -0
  189. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/experiment.py +0 -0
  190. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/judge.py +0 -0
  191. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/judge_defaults.py +0 -0
  192. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/limits.py +0 -0
  193. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/merge_strategy.py +0 -0
  194. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/mutations.py +0 -0
  195. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/results.py +0 -0
  196. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/routing.py +0 -0
  197. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/sandbox.py +0 -0
  198. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/tasks.py +0 -0
  199. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/telemetry.py +0 -0
  200. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/models/templates.py +0 -0
  201. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/orchestration/__init__.py +0 -0
  202. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/orchestration/batch.py +0 -0
  203. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/orchestration/config.py +0 -0
  204. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/orchestration/config_merge.py +0 -0
  205. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/orchestration/early_stop.py +0 -0
  206. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/orchestration/evaluation.py +0 -0
  207. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/orchestration/overrides.py +0 -0
  208. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/orchestration/task_loader.py +0 -0
  209. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/path_utils.py +0 -0
  210. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/plugins.py +0 -0
  211. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/pricing.py +0 -0
  212. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/py.typed +0 -0
  213. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/reports.py +0 -0
  214. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/reports_experiment.py +0 -0
  215. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/reports_html.py +0 -0
  216. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/reports_stats.py +0 -0
  217. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/resources/__init__.py +0 -0
  218. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/resources/default_ignore_patterns.yaml +0 -0
  219. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/resources/tags.yaml +0 -0
  220. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/sandbox.py +0 -0
  221. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/scoring/__init__.py +0 -0
  222. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/scoring/ast_similarity.py +0 -0
  223. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/scoring/complexity.py +0 -0
  224. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/scoring/quality.py +0 -0
  225. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/scoring/signature_similarity.py +0 -0
  226. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/scoring/similarity.py +0 -0
  227. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/scoring/token_similarity.py +0 -0
  228. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/simulation/__init__.py +0 -0
  229. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/simulation/termination.py +0 -0
  230. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/simulation/user_simulator.py +0 -0
  231. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/streaming/__init__.py +0 -0
  232. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/streaming/callbacks.py +0 -0
  233. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/streaming/collector.py +0 -0
  234. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/streaming/events.py +0 -0
  235. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/streaming/renderers.py +0 -0
  236. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/streaming/wire.py +0 -0
  237. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/telemetry.py +0 -0
  238. {coder_eval-0.8.4 → coder_eval-0.8.5}/src/coder_eval/utils.py +0 -0
  239. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/README.md +0 -0
  240. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agentless_smoke_test.yaml +0 -0
  241. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/antigravity_hello_world.yaml +0 -0
  242. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/antigravity_hello_world_docker.yaml +0 -0
  243. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/claude_hello_world.yaml +0 -0
  244. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/claude_hello_world_docker.yaml +0 -0
  245. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/claude_parallel_single_gen.yaml +0 -0
  246. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/claude_subagent_test.yaml +0 -0
  247. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/codex_disallowed_tools_test.yaml +0 -0
  248. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/codex_hello_world.yaml +0 -0
  249. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/codex_parallel_commands.yaml +0 -0
  250. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/codex_parallel_single_gen.yaml +0 -0
  251. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/codex_skills_test.yaml +0 -0
  252. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/codex_string_utils.yaml +0 -0
  253. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/codex_subagent_test.yaml +0 -0
  254. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/subagent_bash_long_input.yaml +0 -0
  255. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/agents/subagent_merge_sort.yaml +0 -0
  256. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/byod_smoke_test.yaml +0 -0
  257. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/dataset_example.yaml +0 -0
  258. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/datasets/sentiment.jsonl +0 -0
  259. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/dockerfile_build_example/dockerfile_build_example.yaml +0 -0
  260. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/dockerfile_build_example/environment/Dockerfile +0 -0
  261. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/dockerfile_build_example/environment/Dockerfile.workdir +0 -0
  262. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/dockerfile_build_example/environment/input.txt +0 -0
  263. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/dockerfile_build_example/working_dir_auto_example.yaml +0 -0
  264. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/dockerfile_build_example/working_dir_concrete_example.yaml +0 -0
  265. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/fibonacci_with_template.yaml +0 -0
  266. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/hello_date.yaml +0 -0
  267. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/inline_starter_example.yaml +0 -0
  268. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/internal/session_resumption.yaml +0 -0
  269. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/mock_path_dirs_smoke.yaml +0 -0
  270. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/mock_path_dirs_template_dir/mock-cli-bins/README.md +0 -0
  271. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/mock_path_dirs_template_dir/mock-cli-bins/mocks/echo_args +0 -0
  272. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/mock_path_dirs_template_dir/mock-cli-bins/mocks/fixtures/config.json +0 -0
  273. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/mock_path_dirs_template_dir/mock-cli-bins/mocks/say_hello +0 -0
  274. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/mock_path_dirs_template_dir/task.yaml +0 -0
  275. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/python_cli_simulated_judged/echo_simulated_judged.yaml +0 -0
  276. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/3d-scan-calc/3d-scan-calc.yaml +0 -0
  277. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/3d-scan-calc/environment/Dockerfile +0 -0
  278. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/3d-scan-calc/environment/material_density_table.md +0 -0
  279. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/3d-scan-calc/environment/scan_data.stl +0 -0
  280. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/3d-scan-calc/verifier/test.sh +0 -0
  281. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/3d-scan-calc/verifier/test_outputs.py +0 -0
  282. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/README.md +0 -0
  283. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/court-form-filling/court-form-filling.yaml +0 -0
  284. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/court-form-filling/environment/Dockerfile +0 -0
  285. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/court-form-filling/environment/sc100-blank.pdf +0 -0
  286. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/court-form-filling/verifier/test.sh +0 -0
  287. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/court-form-filling/verifier/test_outputs.py +0 -0
  288. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/dialogue-parser/dialogue-parser.yaml +0 -0
  289. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/dialogue-parser/environment/Dockerfile +0 -0
  290. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/dialogue-parser/environment/script.txt +0 -0
  291. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/dialogue-parser/verifier/test.sh +0 -0
  292. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/samples/skillsbench/dialogue-parser/verifier/test_outputs.py +0 -0
  293. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/sentiment_classification.yaml +0 -0
  294. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/smoke_agent_judge.yaml +0 -0
  295. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/smoke_budget_exceeded.yaml +0 -0
  296. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/smoke_cost_budget_exceeded.yaml +0 -0
  297. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/smoke_llm_judge.yaml +0 -0
  298. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/smoke_negative_path.yaml +0 -0
  299. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/smoke_task_timeout.yaml +0 -0
  300. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/smoke_variants.yaml +0 -0
  301. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/test_sandbox.yaml +0 -0
  302. {coder_eval-0.8.4 → coder_eval-0.8.5}/tasks/token_check.yaml +0 -0
  303. {coder_eval-0.8.4 → coder_eval-0.8.5}/templates/byod_smoke_test/Dockerfile +0 -0
  304. {coder_eval-0.8.4 → coder_eval-0.8.5}/templates/fibonacci-starter/README.md +0 -0
  305. {coder_eval-0.8.4 → coder_eval-0.8.5}/templates/fibonacci-starter/src/main.py +0 -0
  306. {coder_eval-0.8.4 → coder_eval-0.8.5}/templates/fibonacci-starter/tests/test_main.py +0 -0
  307. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/__init__.py +0 -0
  308. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/__init__.py +0 -0
  309. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/__init__.py +0 -0
  310. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/_scrub.py +0 -0
  311. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/claude_fixtures.py +0 -0
  312. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/codex_fixtures.py +0 -0
  313. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/claude_a_single_text_turn.json +0 -0
  314. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/claude_b_tool_use_result.json +0 -0
  315. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/claude_c_multi_emission_delta.json +0 -0
  316. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/claude_d_subagent_terminal.json +0 -0
  317. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/claude_e_model_usage_and_backfill.json +0 -0
  318. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/claude_f_orphaned_tool.json +0 -0
  319. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/claude_g_crash_format_placeholder.json +0 -0
  320. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/claude_h1_timeout_process_error.json +0 -0
  321. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/claude_h2_process_error_crash.json +0 -0
  322. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/claude_i_in_loop_deadline_break.json +0 -0
  323. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/codex_a_agent_message_only.json +0 -0
  324. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/codex_b_command_execution.json +0 -0
  325. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/codex_c_reasoning_placeholder.json +0 -0
  326. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/codex_d_cross_flush_is_error.json +0 -0
  327. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/codex_e_orphan_tool.json +0 -0
  328. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/codex_f_collab_fallback.json +0 -0
  329. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/codex_g_items_rebuild.json +0 -0
  330. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/golden_streams/expected/codex_h_no_turn_completed_crash.json +0 -0
  331. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/report_snapshots/__init__.py +0 -0
  332. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/report_snapshots/_snapshot.py +0 -0
  333. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/report_snapshots/experiment_2variant.md +0 -0
  334. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/report_snapshots/experiment_3variant.md +0 -0
  335. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/report_snapshots/experiment_replicates.md +0 -0
  336. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/report_snapshots/run_full.md +0 -0
  337. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_fixtures/report_snapshots/run_minimal.md +0 -0
  338. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/_path_helpers.py +0 -0
  339. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/conftest.py +0 -0
  340. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/fixtures/__init__.py +0 -0
  341. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/fixtures/byoa_demo_plugin/byoa_demo.py +0 -0
  342. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/fixtures/byoa_demo_plugin/pyproject.toml +0 -0
  343. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/fixtures/mock_agent.py +0 -0
  344. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/fixtures/tasks/test_task_multiple_criteria.yaml +0 -0
  345. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/fixtures/tasks/test_task_pass.yaml +0 -0
  346. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/fixtures/text_stub_agent.py +0 -0
  347. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/__init__.py +0 -0
  348. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/__init__.py +0 -0
  349. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/base.py +0 -0
  350. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce014_merge_strategy_declared.py +0 -0
  351. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce015_create_subprocess_limit.py +0 -0
  352. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce016_no_computed_tokenusage_kwargs.py +0 -0
  353. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce017_models_lazy_agent_imports.py +0 -0
  354. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce018_no_final_status_name_denylist.py +0 -0
  355. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce019_telemetry_non_fatal.py +0 -0
  356. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce020_no_sdk_typed_base_agent_fields.py +0 -0
  357. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce021_guarded_evaluationresult_parse.py +0 -0
  358. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce022_dialog_loop_statement_cap.py +0 -0
  359. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce023_no_proxy_shim_import.py +0 -0
  360. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce024_discriminated_unions.py +0 -0
  361. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/ce025_live_verdict_consistency.py +0 -0
  362. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/no_agent_timing_access.py +0 -0
  363. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/no_blocking_io_in_async.py +0 -0
  364. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/no_cli_imports_in_core.py +0 -0
  365. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/no_silent_except.py +0 -0
  366. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/no_submodule_model_imports.py +0 -0
  367. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/no_top_level_run_limits_access.py +0 -0
  368. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/no_transcript_regex_in_eval.py +0 -0
  369. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/no_type_name_string_dispatch.py +0 -0
  370. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/open_explicit_encoding.py +0 -0
  371. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/read_text_explicit_encoding.py +0 -0
  372. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/register_criterion_required.py +0 -0
  373. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/subprocess_run_explicit_encoding.py +0 -0
  374. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/rules/yaml_models_forbid_extras.py +0 -0
  375. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/runner.py +0 -0
  376. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/lint/violation.py +0 -0
  377. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agent.py +0 -0
  378. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agent_config_no_timing_fields.py +0 -0
  379. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agent_config_optional_type.py +0 -0
  380. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agent_config_registry_dispatch.py +0 -0
  381. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agent_config_sdk_decoupling.py +0 -0
  382. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agent_golden_master.py +0 -0
  383. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agent_judge_criterion.py +0 -0
  384. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agent_telemetry.py +0 -0
  385. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agent_telemetry_advanced.py +0 -0
  386. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agent_timeout.py +0 -0
  387. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_agentless.py +0 -0
  388. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_aggregate.py +0 -0
  389. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_antigravity_agent.py +0 -0
  390. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_byoa_plugin.py +0 -0
  391. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_byoa_plugin_live.py +0 -0
  392. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_byod_feature.py +0 -0
  393. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_checker_logging.py +0 -0
  394. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_classification_match.py +0 -0
  395. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_claude_settings_enforcement_live.py +0 -0
  396. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_cleanup_preservation_guard.py +0 -0
  397. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_cli_backend_flag.py +0 -0
  398. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_cli_empty_glob.py +0 -0
  399. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_cli_sdk_options.py +0 -0
  400. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_cli_set_overrides.py +0 -0
  401. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_cli_telemetry.py +0 -0
  402. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_cli_type_flag.py +0 -0
  403. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_code_review_bugs.py +0 -0
  404. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_codex_agent.py +0 -0
  405. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_codex_agent_live.py +0 -0
  406. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_codex_agent_unit.py +0 -0
  407. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_codex_token_mapping.py +0 -0
  408. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_command_executed.py +0 -0
  409. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_command_statistics.py +0 -0
  410. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_command_telemetry_result_data.py +0 -0
  411. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_commands_efficiency.py +0 -0
  412. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_config_lineage.py +0 -0
  413. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_config_merge_engine.py +0 -0
  414. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_config_precedence.py +0 -0
  415. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_continuous_scoring.py +0 -0
  416. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_criterion_result_round_trip.py +0 -0
  417. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_custom_lint.py +0 -0
  418. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_debug_logging.py +0 -0
  419. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_docker_build_failure.py +0 -0
  420. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_docker_runner_container_death.py +0 -0
  421. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_docker_runner_mounts.py +0 -0
  422. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_docker_runner_stream_limit.py +0 -0
  423. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_docker_wildcard_env.py +0 -0
  424. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_docker_workdir_live.py +0 -0
  425. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_driver_resolver.py +0 -0
  426. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_early_stop.py +0 -0
  427. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_error_handling.py +0 -0
  428. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_evaluate_command.py +0 -0
  429. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_evaluator.py +0 -0
  430. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_event_collector.py +0 -0
  431. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_experiment_cli.py +0 -0
  432. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_experiment_loader.py +0 -0
  433. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_experiment_models.py +0 -0
  434. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_experiment_reports.py +0 -0
  435. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_experiment_resolver.py +0 -0
  436. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_experiment_runner.py +0 -0
  437. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_file_check.py +0 -0
  438. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_file_contains_scoring.py +0 -0
  439. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_formatting.py +0 -0
  440. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_git_clone_failure.py +0 -0
  441. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_heartbeat_watchdog.py +0 -0
  442. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_ignore_patterns_negation.py +0 -0
  443. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_image_from_dockerfiles.py +0 -0
  444. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_integration.py +0 -0
  445. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_json_check.py +0 -0
  446. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_judge_anthropic.py +0 -0
  447. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_judge_bedrock.py +0 -0
  448. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_judge_burn_in_live.py +0 -0
  449. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_judge_context_builder.py +0 -0
  450. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_judge_models.py +0 -0
  451. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_judge_persistence.py +0 -0
  452. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_lint_no_top_level_run_limits.py +0 -0
  453. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_lint_runner.py +0 -0
  454. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_llm_judge_criterion.py +0 -0
  455. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_log_tail_buffer.py +0 -0
  456. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_logging.py +0 -0
  457. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_logging_isolation.py +0 -0
  458. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_merge_characterization.py +0 -0
  459. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_merge_strategy_annotations.py +0 -0
  460. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_merge_unification.py +0 -0
  461. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_models.py +0 -0
  462. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_mutations.py +0 -0
  463. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_new_criteria.py +0 -0
  464. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_node_env_config.py +0 -0
  465. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_optional_dependencies.py +0 -0
  466. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_orchestrator.py +0 -0
  467. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_orchestrator_error_log_tail.py +0 -0
  468. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_orchestrator_telemetry.py +0 -0
  469. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_overrides_engine.py +0 -0
  470. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_parallel.py +0 -0
  471. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_path_utils.py +0 -0
  472. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_plan_command.py +0 -0
  473. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_plugin_processing.py +0 -0
  474. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_plugins.py +0 -0
  475. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_post_run.py +0 -0
  476. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_pr_review_workflow.py +0 -0
  477. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_pre_run.py +0 -0
  478. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_preservation_mode.py +0 -0
  479. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_pricing_registry.py +0 -0
  480. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_reference_comparison_scoring.py +0 -0
  481. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_reference_evaluator.py +0 -0
  482. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_reference_missing_file.py +0 -0
  483. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_reference_models.py +0 -0
  484. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_reference_orchestrator.py +0 -0
  485. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_registry.py +0 -0
  486. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_replicate_stats.py +0 -0
  487. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_report_command.py +0 -0
  488. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_reports.py +0 -0
  489. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_reports_experiment.py +0 -0
  490. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_reports_html.py +0 -0
  491. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_reports_stats.py +0 -0
  492. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_resolve_task_files.py +0 -0
  493. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_resume.py +0 -0
  494. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_retry_logic_comprehensive.py +0 -0
  495. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_routing.py +0 -0
  496. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_run_command_stdout.py +0 -0
  497. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_run_limits_models.py +0 -0
  498. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_run_limits_orchestrator.py +0 -0
  499. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_run_limits_resolver.py +0 -0
  500. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_runtime_tool_versions.py +0 -0
  501. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_sandbox.py +0 -0
  502. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_sandbox_layer_builder.py +0 -0
  503. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_sandbox_optional.py +0 -0
  504. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_sandbox_security.py +0 -0
  505. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_sandbox_symlink_preservation.py +0 -0
  506. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_sandbox_templates.py +0 -0
  507. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_scorers.py +0 -0
  508. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_scoring_quality.py +0 -0
  509. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_sdk_option_classification.py +0 -0
  510. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_simulation_config.py +0 -0
  511. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_simulation_integration.py +0 -0
  512. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_simulation_termination.py +0 -0
  513. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_simulation_trials.py +0 -0
  514. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_skill_triggered.py +0 -0
  515. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_streaming_agent_integration.py +0 -0
  516. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_streaming_batch.py +0 -0
  517. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_streaming_callbacks.py +0 -0
  518. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_streaming_cli.py +0 -0
  519. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_streaming_events.py +0 -0
  520. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_streaming_orchestrator.py +0 -0
  521. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_streaming_renderers.py +0 -0
  522. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_streaming_wire.py +0 -0
  523. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_sub_agent_runner.py +0 -0
  524. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_success_criterion_union.py +0 -0
  525. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_suite_rollup.py +0 -0
  526. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_summaries.py +0 -0
  527. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_tags.py +0 -0
  528. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_task_definition_unknown_fields.py +0 -0
  529. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_telemetry.py +0 -0
  530. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_template_env_expansion.py +0 -0
  531. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_threshold_enforcement.py +0 -0
  532. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_timeout_batch.py +0 -0
  533. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_timeout_categorization.py +0 -0
  534. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_timeout_exceptions.py +0 -0
  535. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_timeout_models.py +0 -0
  536. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_timeout_orchestrator.py +0 -0
  537. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_token_usage.py +0 -0
  538. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_uipath_eval.py +0 -0
  539. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_user_simulator.py +0 -0
  540. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_utils.py +0 -0
  541. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_utterance_extraction.py +0 -0
  542. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_variant_prompt_file.py +0 -0
  543. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_verdict_tool.py +0 -0
  544. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_watchdog.py +0 -0
  545. {coder_eval-0.8.4 → coder_eval-0.8.5}/tests/test_yaml_migration.py +0 -0
@@ -26,7 +26,7 @@ updates:
26
26
  directory: "/"
27
27
  schedule:
28
28
  interval: "monthly"
29
- open-pull-requests-limit: 3 # Raised from 1: actions are SHA-pinned, so SHA bumps come as patch/minor PRs.
29
+ open-pull-requests-limit: 3 # Grouped below into one PR; headroom in case a major is held out of the group.
30
30
  labels:
31
31
  - "dependencies"
32
32
  - "github-actions"
@@ -36,3 +36,29 @@ updates:
36
36
  prefix: "chore"
37
37
  # No ignore block — keep SHA pins current for patch and minor releases too,
38
38
  # otherwise SHA pinning fossilizes the actions in place.
39
+ # One batched PR instead of one per action, matching the npm block below.
40
+ groups:
41
+ actions-all:
42
+ patterns: ["*"]
43
+
44
+ # evalboard frontend (npm). Without this block nothing routinely refreshes the
45
+ # Next.js app, so it drifts until a CVE fires and alerts pile up. Monthly,
46
+ # grouped bumps keep next/React/Azure ahead of most advisories.
47
+ - package-ecosystem: "npm"
48
+ directory: "/evalboard"
49
+ schedule:
50
+ interval: "monthly"
51
+ open-pull-requests-limit: 3
52
+ labels:
53
+ - "dependencies"
54
+ - "javascript"
55
+ # `chore` keeps the commit + PR title within the Conventional Commits
56
+ # allowed-type set enforced by conventional-commits.yml (see pip block).
57
+ commit-message:
58
+ prefix: "chore"
59
+ include: "scope"
60
+ # One batched PR instead of N noisy ones, matching the low-noise style of
61
+ # the pip/actions blocks above.
62
+ groups:
63
+ npm-all:
64
+ patterns: ["*"]
@@ -2,6 +2,62 @@
2
2
 
3
3
  <!-- version list -->
4
4
 
5
+ ## v0.8.5 (2026-07-20)
6
+
7
+ ### Bug Fixes
8
+
9
+ - **deps**: Bump mcp to >=1.28.1 for CVE-2026-52869/52870/59950
10
+ ([#25](https://github.com/UiPath/coder_eval/pull/25),
11
+ [`fb1ad4c`](https://github.com/UiPath/coder_eval/commit/fb1ad4cba2973414a6a883468f62c908deee532b))
12
+
13
+ - **orchestration**: Isolate per-task config-resolution failures from the suite
14
+ ([#25](https://github.com/UiPath/coder_eval/pull/25),
15
+ [`fb1ad4c`](https://github.com/UiPath/coder_eval/commit/fb1ad4cba2973414a6a883468f62c908deee532b))
16
+
17
+ - **orchestration**: Normalize the all-fail config-resolution abort to ValueError
18
+ ([#25](https://github.com/UiPath/coder_eval/pull/25),
19
+ [`fb1ad4c`](https://github.com/UiPath/coder_eval/commit/fb1ad4cba2973414a6a883468f62c908deee532b))
20
+
21
+ - **orchestration**: Re-raise ValueError verbatim in the all-fail abort
22
+ ([#25](https://github.com/UiPath/coder_eval/pull/25),
23
+ [`fb1ad4c`](https://github.com/UiPath/coder_eval/commit/fb1ad4cba2973414a6a883468f62c908deee532b))
24
+
25
+ - **orchestrator**: Interrupt-proof teardown so a timeout can't drop task.json
26
+ ([#29](https://github.com/UiPath/coder_eval/pull/29),
27
+ [`89ec0d0`](https://github.com/UiPath/coder_eval/commit/89ec0d0eda74616d21a87302680e3099473119bc))
28
+
29
+ - **sandbox**: Prune capture-ignored entries on every preservation path; interrupt-proof teardown
30
+ ([#29](https://github.com/UiPath/coder_eval/pull/29),
31
+ [`89ec0d0`](https://github.com/UiPath/coder_eval/commit/89ec0d0eda74616d21a87302680e3099473119bc))
32
+
33
+ ### Chores
34
+
35
+ - **evalboard**: Address npm Dependabot alerts ([#18](https://github.com/UiPath/coder_eval/pull/18),
36
+ [`3d5e7b7`](https://github.com/UiPath/coder_eval/commit/3d5e7b7d2358e10d95d59487c54596df7da1bef2))
37
+
38
+ - **evalboard**: Batch github-actions bumps into one grouped PR
39
+ ([#18](https://github.com/UiPath/coder_eval/pull/18),
40
+ [`3d5e7b7`](https://github.com/UiPath/coder_eval/commit/3d5e7b7d2358e10d95d59487c54596df7da1bef2))
41
+
42
+ ### Documentation
43
+
44
+ - **orchestrator**: Correct teardown comment to scope of the fix
45
+ ([#29](https://github.com/UiPath/coder_eval/pull/29),
46
+ [`89ec0d0`](https://github.com/UiPath/coder_eval/commit/89ec0d0eda74616d21a87302680e3099473119bc))
47
+
48
+ ### Features
49
+
50
+ - **evalboard**: Show conversation transcript for simulation tasks
51
+ ([#23](https://github.com/UiPath/coder_eval/pull/23),
52
+ [`252722a`](https://github.com/UiPath/coder_eval/commit/252722ab17edf3dbc1b68a7ca3a357b2dd3cb0d3))
53
+
54
+ ### Refactoring
55
+
56
+ - **orchestrator**: Trim to interrupt-proof teardown; drop preservation-prune
57
+ ([#29](https://github.com/UiPath/coder_eval/pull/29),
58
+ [`89ec0d0`](https://github.com/UiPath/coder_eval/commit/89ec0d0eda74616d21a87302680e3099473119bc))
59
+
60
+
5
61
  ## v0.8.4 (2026-07-13)
6
62
 
7
63
  ### Bug Fixes
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: coder-eval
3
- Version: 0.8.4
3
+ Version: 0.8.5
4
4
  Summary: Evaluate, benchmark, and A/B-test AI coding agents (Claude Code, Codex, Gemini/Antigravity) with sandboxed, reproducible YAML task suites.
5
5
  Project-URL: Homepage, https://github.com/UiPath/coder_eval
6
6
  Project-URL: Repository, https://github.com/UiPath/coder_eval
@@ -46,7 +46,7 @@ Provides-Extra: codex
46
46
  Requires-Dist: openai-codex>=0.1.0b3; extra == 'codex'
47
47
  Provides-Extra: dev
48
48
  Requires-Dist: bandit[toml]>=1.9.4; extra == 'dev'
49
- Requires-Dist: mcp>=1.26.0; extra == 'dev'
49
+ Requires-Dist: mcp>=1.28.1; extra == 'dev'
50
50
  Requires-Dist: pip-audit>=2.10.0; extra == 'dev'
51
51
  Requires-Dist: pre-commit>=4.5.1; extra == 'dev'
52
52
  Requires-Dist: pyright>=1.1.408; extra == 'dev'
@@ -12,15 +12,17 @@
12
12
  "verify": "tsc --noEmit && vitest run && next build"
13
13
  },
14
14
  "dependencies": {
15
- "@azure/identity": "^4.13.1",
16
- "@azure/storage-blob": "^12.31.0",
17
- "next": "^15.1.0",
15
+ "next": "^15.5.20",
18
16
  "react": "^19.0.0",
19
17
  "react-dom": "^19.0.0",
20
18
  "react-markdown": "^10.1.0",
21
19
  "recharts": "^2.15.0",
22
20
  "remark-gfm": "^4.0.1"
23
21
  },
22
+ "optionalDependencies": {
23
+ "@azure/identity": "^4.13.1",
24
+ "@azure/storage-blob": ">=12.31.0 <12.33.0"
25
+ },
24
26
  "devDependencies": {
25
27
  "@tailwindcss/typography": "^0.5.19",
26
28
  "@testing-library/jest-dom": "^6.0.0",
@@ -36,5 +38,13 @@
36
38
  "tailwindcss": "^3.4.17",
37
39
  "typescript": "^5.6.3",
38
40
  "vitest": "^2.1.0"
41
+ },
42
+ "pnpm": {
43
+ "overrides": {
44
+ "postcss": "^8.5.10",
45
+ "fast-xml-builder": "^1.1.7",
46
+ "@babel/core": "^7.29.6",
47
+ "uuid": "^11.1.1"
48
+ }
39
49
  }
40
50
  }