agentevals-cli 0.7.2__tar.gz → 0.7.3__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 (239) hide show
  1. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.github/workflows/release.yml +27 -18
  2. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/PKG-INFO +7 -3
  3. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/README.md +6 -2
  4. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/docs/streaming.md +12 -6
  5. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/kubernetes/README.md +1 -2
  6. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/pyproject.toml +1 -1
  7. agentevals_cli-0.7.3/samples/tempo_export_with_batches.json +1 -0
  8. agentevals_cli-0.7.2/src/agentevals/_static/assets/index-7YPfPT4N.js → agentevals_cli-0.7.3/src/agentevals/_static/assets/index-Cl6S2lcn.js +64 -65
  9. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/_static/index.html +1 -1
  10. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/routes.py +4 -26
  11. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/cli.py +4 -3
  12. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/config.py +7 -4
  13. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/converter.py +19 -6
  14. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/eval_config_loader.py +1 -1
  15. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/extraction.py +51 -2
  16. agentevals_cli-0.7.3/src/agentevals/loader/__init__.py +29 -0
  17. agentevals_cli-0.7.3/src/agentevals/loader/auto.py +108 -0
  18. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/loader/otlp.py +38 -12
  19. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/mcp_server.py +5 -6
  20. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/runner.py +3 -15
  21. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_api.py +50 -6
  22. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_converter.py +33 -0
  23. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_extraction.py +74 -0
  24. agentevals_cli-0.7.3/tests/test_loader_auto.py +241 -0
  25. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_otlp_loader.py +125 -0
  26. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/api/client.ts +1 -4
  27. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/builder/TraceUploadZone.tsx +1 -1
  28. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/upload/TraceEditorDrawer.tsx +2 -2
  29. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/upload/UploadView.tsx +2 -1
  30. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/context/TraceProvider.tsx +20 -2
  31. agentevals_cli-0.7.3/ui/src/lib/trace-loader.ts +320 -0
  32. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/uv.lock +1 -1
  33. agentevals_cli-0.7.2/src/agentevals/loader/__init__.py +0 -7
  34. agentevals_cli-0.7.2/ui/src/lib/trace-loader.ts +0 -249
  35. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.claude/skills/eval/SKILL.md +0 -0
  36. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.claude/skills/eval/evals/evals.json +0 -0
  37. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.claude/skills/inspect/SKILL.md +0 -0
  38. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.claude/skills/inspect/evals/evals.json +0 -0
  39. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.dockerignore +0 -0
  40. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.github/ISSUE_TEMPLATE/bug_report.yml +0 -0
  41. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.github/ISSUE_TEMPLATE/config.yml +0 -0
  42. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.github/ISSUE_TEMPLATE/feature_request.yml +0 -0
  43. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.github/workflows/ci.yml +0 -0
  44. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.github/workflows/publish-evaluator-sdk.yml +0 -0
  45. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.gitignore +0 -0
  46. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/.mcp.json +0 -0
  47. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/CONTRIBUTING.md +0 -0
  48. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/DEVELOPMENT.md +0 -0
  49. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/Dockerfile +0 -0
  50. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/LICENSE +0 -0
  51. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/Makefile +0 -0
  52. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/charts/agentevals/Chart.yaml +0 -0
  53. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/charts/agentevals/templates/NOTES.txt +0 -0
  54. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/charts/agentevals/templates/_helpers.tpl +0 -0
  55. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/charts/agentevals/templates/deployment.yaml +0 -0
  56. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/charts/agentevals/templates/service.yaml +0 -0
  57. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/charts/agentevals/templates/serviceaccount.yaml +0 -0
  58. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/charts/agentevals/values.yaml +0 -0
  59. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/docs/assets/logo-color-on-transparent.svg +0 -0
  60. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/docs/assets/logo-color.png +0 -0
  61. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/docs/assets/logo-dark-on-transparent.svg +0 -0
  62. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/docs/custom-evaluators.md +0 -0
  63. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/docs/eval-set-format.md +0 -0
  64. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/docs/otel-compatibility.md +0 -0
  65. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/README.md +0 -0
  66. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/custom_evaluators/eval_config.yaml +0 -0
  67. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/custom_evaluators/response_quality.py +0 -0
  68. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/custom_evaluators/tool_call_checker.py +0 -0
  69. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/dice_agent/README.md +0 -0
  70. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/dice_agent/agent.py +0 -0
  71. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/dice_agent/eval_set.json +0 -0
  72. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/dice_agent/main.py +0 -0
  73. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/dice_agent/test_streaming.py +0 -0
  74. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/langchain_agent/README.md +0 -0
  75. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/langchain_agent/agent.py +0 -0
  76. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/langchain_agent/eval_set.json +0 -0
  77. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/langchain_agent/main.py +0 -0
  78. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/langchain_agent/requirements.txt +0 -0
  79. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/langchain_agent/test_streaming.py +0 -0
  80. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/sdk_example/async_example.py +0 -0
  81. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/sdk_example/context_manager_example.py +0 -0
  82. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/sdk_example/decorator_example.py +0 -0
  83. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/sdk_example/requirements.txt +0 -0
  84. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/strands_agent/agent.py +0 -0
  85. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/strands_agent/eval_set.json +0 -0
  86. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/strands_agent/main.py +0 -0
  87. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/strands_agent/requirements.txt +0 -0
  88. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/adk/requirements.txt +0 -0
  89. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/adk/run.py +0 -0
  90. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/langchain/requirements.txt +0 -0
  91. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/langchain/run.py +0 -0
  92. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/ollama/requirements.txt +0 -0
  93. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/ollama/run.py +0 -0
  94. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/openai-agents/requirements.txt +0 -0
  95. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/openai-agents/run.py +0 -0
  96. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/pydantic-ai/requirements.txt +0 -0
  97. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/pydantic-ai/run.py +0 -0
  98. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/strands/requirements.txt +0 -0
  99. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/examples/zero-code-examples/strands/run.py +0 -0
  100. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/flake.lock +0 -0
  101. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/flake.nix +0 -0
  102. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/packages/evaluator-sdk-py/README.md +0 -0
  103. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/packages/evaluator-sdk-py/pyproject.toml +0 -0
  104. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/packages/evaluator-sdk-py/src/agentevals_evaluator_sdk/__init__.py +0 -0
  105. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/packages/evaluator-sdk-py/src/agentevals_evaluator_sdk/decorator.py +0 -0
  106. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/packages/evaluator-sdk-py/src/agentevals_evaluator_sdk/types.py +0 -0
  107. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/samples/eval_set_helm.json +0 -0
  108. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/samples/evalset_helm_3_2026-02-23.json +0 -0
  109. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/samples/evalset_k8s_2026-02-20.json +0 -0
  110. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/samples/helm.json +0 -0
  111. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/samples/helm_2.json +0 -0
  112. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/samples/helm_3.json +0 -0
  113. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/samples/k8s.json +0 -0
  114. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/__init__.py +0 -0
  115. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/_protocol.py +0 -0
  116. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/_static/assets/index-BqibLiHO.css +0 -0
  117. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/_static/logo.svg +0 -0
  118. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/_static/vite.svg +0 -0
  119. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/__init__.py +0 -0
  120. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/app.py +0 -0
  121. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/debug_routes.py +0 -0
  122. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/dependencies.py +0 -0
  123. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/models.py +0 -0
  124. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/otlp_app.py +0 -0
  125. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/otlp_grpc.py +0 -0
  126. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/otlp_processing.py +0 -0
  127. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/otlp_routes.py +0 -0
  128. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/api/streaming_routes.py +0 -0
  129. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/builtin_metrics.py +0 -0
  130. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/custom_evaluators.py +0 -0
  131. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/evaluator/__init__.py +0 -0
  132. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/evaluator/resolver.py +0 -0
  133. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/evaluator/sources.py +0 -0
  134. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/evaluator/templates.py +0 -0
  135. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/evaluator/venv.py +0 -0
  136. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/genai_converter.py +0 -0
  137. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/loader/base.py +0 -0
  138. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/loader/jaeger.py +0 -0
  139. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/openai_eval_backend.py +0 -0
  140. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/output.py +0 -0
  141. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/sdk.py +0 -0
  142. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/streaming/__init__.py +0 -0
  143. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/streaming/incremental_processor.py +0 -0
  144. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/streaming/processor.py +0 -0
  145. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/streaming/session.py +0 -0
  146. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/streaming/ws_server.py +0 -0
  147. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/trace_attrs.py +0 -0
  148. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/trace_metrics.py +0 -0
  149. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/utils/__init__.py +0 -0
  150. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/utils/genai_messages.py +0 -0
  151. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/utils/log_buffer.py +0 -0
  152. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/src/agentevals/utils/log_enrichment.py +0 -0
  153. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/integration/__init__.py +0 -0
  154. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/integration/conftest.py +0 -0
  155. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/integration/test_evaluation_pipeline.py +0 -0
  156. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/integration/test_live_agents.py +0 -0
  157. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/integration/test_otlp_grpc_receiver.py +0 -0
  158. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/integration/test_session_grouping.py +0 -0
  159. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/integration/test_timing_stress.py +0 -0
  160. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_cli.py +0 -0
  161. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_genai_converter.py +0 -0
  162. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_jaeger_loader.py +0 -0
  163. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_log_enrichment.py +0 -0
  164. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_mcp_server.py +0 -0
  165. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_otlp_receiver.py +0 -0
  166. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_output.py +0 -0
  167. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_protocol.py +0 -0
  168. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_runner.py +0 -0
  169. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_sdk.py +0 -0
  170. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/tests/test_trace_metrics.py +0 -0
  171. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/.gitignore +0 -0
  172. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/README.md +0 -0
  173. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/eslint.config.js +0 -0
  174. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/index.html +0 -0
  175. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/package-lock.json +0 -0
  176. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/package.json +0 -0
  177. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/public/logo.svg +0 -0
  178. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/public/vite.svg +0 -0
  179. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/App.css +0 -0
  180. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/App.tsx +0 -0
  181. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/assets/react.svg +0 -0
  182. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/annotation-queue/AnnotationDetailPanel.tsx +0 -0
  183. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/annotation-queue/AnnotationQueueView.tsx +0 -0
  184. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/annotation-queue/AnnotationTable.tsx +0 -0
  185. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/bug-report/BugReportModal.tsx +0 -0
  186. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/builder/BuilderHeader.tsx +0 -0
  187. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/builder/BuilderView.tsx +0 -0
  188. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/builder/EvalCaseCard.tsx +0 -0
  189. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/builder/EvalCasesList.tsx +0 -0
  190. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/builder/InvocationEditor.tsx +0 -0
  191. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/builder/JsonPreview.tsx +0 -0
  192. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/builder/MetadataEditor.tsx +0 -0
  193. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/builder/index.ts +0 -0
  194. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/dashboard/DashboardView.tsx +0 -0
  195. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/dashboard/MetricScoreCard.tsx +0 -0
  196. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/dashboard/PerformanceCard.tsx +0 -0
  197. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/dashboard/PerformanceCharts.tsx +0 -0
  198. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/dashboard/SummaryStats.tsx +0 -0
  199. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/dashboard/TraceCard.tsx +0 -0
  200. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/dashboard/TraceTable.tsx +0 -0
  201. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/ComparisonPanel.tsx +0 -0
  202. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/DataSection.tsx +0 -0
  203. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/InspectorHeader.tsx +0 -0
  204. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/InspectorLayout.tsx +0 -0
  205. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/InspectorView.tsx +0 -0
  206. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/InvocationCard.tsx +0 -0
  207. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/InvocationSummaryPanel.tsx +0 -0
  208. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/MetricResultsSection.tsx +0 -0
  209. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/MetricsComparisonSection.tsx +0 -0
  210. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/PerformanceSection.tsx +0 -0
  211. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/ToolCallList.tsx +0 -0
  212. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/inspector/TrajectoryComparisonDetails.tsx +0 -0
  213. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/sidebar/Sidebar.tsx +0 -0
  214. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/streaming/LiveConversationPanel.tsx +0 -0
  215. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/streaming/LiveMessage.tsx +0 -0
  216. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/streaming/LiveStreamingView.tsx +0 -0
  217. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/streaming/SessionCard.tsx +0 -0
  218. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/streaming/SessionMetadata.tsx +0 -0
  219. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/upload/EvalSetEditorDrawer.tsx +0 -0
  220. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/upload/FileDropZone.tsx +0 -0
  221. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/upload/MetricSelector.tsx +0 -0
  222. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/upload/RawJsonPreview.tsx +0 -0
  223. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/components/welcome/WelcomeView.tsx +0 -0
  224. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/config.ts +0 -0
  225. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/context/TraceContext.tsx +0 -0
  226. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/index.css +0 -0
  227. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/lib/console-capture.ts +0 -0
  228. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/lib/evalset-builder.ts +0 -0
  229. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/lib/network-capture.ts +0 -0
  230. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/lib/trace-helpers.ts +0 -0
  231. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/lib/trace-metadata.ts +0 -0
  232. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/lib/trace-patcher.ts +0 -0
  233. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/lib/types.ts +0 -0
  234. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/lib/utils.ts +0 -0
  235. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/src/main.tsx +0 -0
  236. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/tsconfig.app.json +0 -0
  237. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/tsconfig.json +0 -0
  238. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/tsconfig.node.json +0 -0
  239. {agentevals_cli-0.7.2 → agentevals_cli-0.7.3}/ui/vite.config.ts +0 -0
@@ -18,6 +18,8 @@ jobs:
18
18
  runs-on: ubuntu-latest
19
19
  steps:
20
20
  - uses: actions/checkout@v6
21
+ with:
22
+ ref: ${{ github.event.inputs.tag || github.ref_name }}
21
23
 
22
24
  - uses: astral-sh/setup-uv@v7
23
25
  with:
@@ -42,29 +44,13 @@ jobs:
42
44
  dist/core/*.whl
43
45
  dist/bundle/*.whl
44
46
 
45
- github-release:
46
- needs: build
47
- runs-on: ubuntu-latest
48
- permissions:
49
- contents: write
50
-
51
- steps:
52
- - uses: actions/download-artifact@v8
53
- with:
54
- name: wheels
55
- path: dist/
56
-
57
- - uses: softprops/action-gh-release@v2.5.0
58
- with:
59
- tag_name: ${{ github.event.inputs.tag || github.ref_name }}
60
- files: dist/**/*.whl
61
- generate_release_notes: true
62
-
63
47
  publish:
64
48
  needs: build
65
49
  runs-on: ubuntu-latest
66
50
  steps:
67
51
  - uses: actions/checkout@v6
52
+ with:
53
+ ref: ${{ github.event.inputs.tag || github.ref_name }}
68
54
 
69
55
  - uses: astral-sh/setup-uv@v7
70
56
  with:
@@ -93,13 +79,34 @@ jobs:
93
79
  uv publish dist/* --token ${{ secrets.PYPI_TOKEN }}
94
80
  rm -rf src/agentevals/_static
95
81
 
82
+ github-release:
83
+ needs: publish
84
+ runs-on: ubuntu-latest
85
+ permissions:
86
+ contents: write
87
+
88
+ steps:
89
+ - uses: actions/download-artifact@v8
90
+ with:
91
+ name: wheels
92
+ path: dist/
93
+
94
+ - uses: softprops/action-gh-release@v2.5.0
95
+ with:
96
+ tag_name: ${{ github.event.inputs.tag || github.ref_name }}
97
+ files: dist/**/*.whl
98
+ generate_release_notes: true
99
+
96
100
  push-docker:
101
+ needs: github-release
97
102
  runs-on: ubuntu-latest
98
103
  permissions:
99
104
  contents: read
100
105
  packages: write
101
106
  steps:
102
107
  - uses: actions/checkout@v6
108
+ with:
109
+ ref: ${{ github.event.inputs.tag || github.ref_name }}
103
110
 
104
111
  - name: Login to GitHub Container Registry
105
112
  uses: docker/login-action@v4
@@ -131,6 +138,8 @@ jobs:
131
138
  packages: write
132
139
  steps:
133
140
  - uses: actions/checkout@v6
141
+ with:
142
+ ref: ${{ github.event.inputs.tag || github.ref_name }}
134
143
 
135
144
  - name: Login to GitHub Container Registry
136
145
  uses: docker/login-action@v4
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: agentevals-cli
3
- Version: 0.7.2
3
+ Version: 0.7.3
4
4
  Summary: Standalone framework to evaluate agent correctness based on portable OpenTelemetry traces
5
5
  License-File: LICENSE
6
6
  Requires-Python: >=3.11
@@ -300,12 +300,16 @@ docker run -p 8001:8001 -p 4317:4317 -p 4318:4318 agentevals
300
300
 
301
301
  ### Helm
302
302
 
303
- A Helm chart is available in [`charts/agentevals/`](charts/agentevals/):
303
+ The Helm chart is published as an OCI artifact to GitHub Container Registry:
304
304
 
305
305
  ```bash
306
- helm install agentevals ./charts/agentevals
306
+ helm install agentevals oci://ghcr.io/agentevals-dev/agentevals/helm/agentevals
307
307
  ```
308
308
 
309
+ Pass `--version <x.y.z>` to pin to a specific release. Available versions are listed under [packages](https://github.com/agentevals-dev/agentevals/pkgs/container/agentevals%2Fhelm%2Fagentevals).
310
+
311
+ The source for the chart lives in [`charts/agentevals/`](charts/agentevals/) if you want to install from a local checkout instead.
312
+
309
313
  See the [Kubernetes example](examples/kubernetes/README.md) for an end-to-end walkthrough deploying agentevals alongside kagent and an OTel Collector on Kubernetes.
310
314
 
311
315
  ## MCP Server
@@ -274,12 +274,16 @@ docker run -p 8001:8001 -p 4317:4317 -p 4318:4318 agentevals
274
274
 
275
275
  ### Helm
276
276
 
277
- A Helm chart is available in [`charts/agentevals/`](charts/agentevals/):
277
+ The Helm chart is published as an OCI artifact to GitHub Container Registry:
278
278
 
279
279
  ```bash
280
- helm install agentevals ./charts/agentevals
280
+ helm install agentevals oci://ghcr.io/agentevals-dev/agentevals/helm/agentevals
281
281
  ```
282
282
 
283
+ Pass `--version <x.y.z>` to pin to a specific release. Available versions are listed under [packages](https://github.com/agentevals-dev/agentevals/pkgs/container/agentevals%2Fhelm%2Fagentevals).
284
+
285
+ The source for the chart lives in [`charts/agentevals/`](charts/agentevals/) if you want to install from a local checkout instead.
286
+
283
287
  See the [Kubernetes example](examples/kubernetes/README.md) for an end-to-end walkthrough deploying agentevals alongside kagent and an OTel Collector on Kubernetes.
284
288
 
285
289
  ## MCP Server
@@ -66,13 +66,18 @@ See [examples/README.md](../examples/README.md) for details on supported instrum
66
66
 
67
67
  ### OTLP/JSON Support
68
68
 
69
- Native OpenTelemetry format no conversion to Jaeger needed:
69
+ Native OpenTelemetry format. The CLI auto-detects Jaeger vs OTLP from
70
+ file contents, so `.json` and `.jsonl` exports from Tempo, Jaeger, or
71
+ the OTel collector all work without a `--format` flag:
70
72
 
71
73
  ```bash
72
- # Load OTLP files directly
73
- agentevals run trace.otlp.json --format otlp-json --eval-set eval.json
74
+ # Load any trace file directly; format is auto-detected
75
+ agentevals run trace.otlp.json --eval-set eval.json
74
76
  ```
75
77
 
78
+ Pass `--format otlp-json` (or `jaeger-json`) only as an override when
79
+ auto-detection fails on a non-standard export.
80
+
76
81
  ### Real-time Span Streaming
77
82
 
78
83
  The `AgentEvalsStreamingProcessor` is an OTel `SpanProcessor` that streams spans over WebSocket as they complete:
@@ -311,6 +316,7 @@ This installs `opentelemetry-sdk>=1.20.0`. Agent code also needs `websockets` fo
311
316
  ## Compatibility
312
317
 
313
318
  All existing workflows continue to work:
314
- - Jaeger JSON files still supported: `agentevals run trace.json --eval-set ...`
315
- - OTLP/JSON files: `agentevals run trace.otlp.json --format otlp-json --eval-set ...`
316
- - Web UI upload flow unchanged
319
+ - Trace files (Jaeger or OTLP, including Tempo exports) auto-detect by
320
+ content: `agentevals run trace.json --eval-set ...`
321
+ - Pass `--format` only to override detection on non-standard exports.
322
+ - Web UI upload flow unchanged.
@@ -25,8 +25,7 @@ kagent (gRPC :4317) --> OTel Collector( optional ) --> agentevals (gRPC :4317 /
25
25
  ### 1. agentevals
26
26
 
27
27
  ```bash
28
- helm install agentevals ./charts/agentevals \
29
- --set tag=0.6.3
28
+ helm install agentevals oci://ghcr.io/agentevals-dev/agentevals/helm/agentevals
30
29
  ```
31
30
 
32
31
  This creates a single pod exposing:
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
4
4
 
5
5
  [project]
6
6
  name = "agentevals-cli"
7
- version = "0.7.2"
7
+ version = "0.7.3"
8
8
  description = "Standalone framework to evaluate agent correctness based on portable OpenTelemetry traces"
9
9
  readme = "README.md"
10
10
  requires-python = ">=3.11"