evalvault 1.64.0__py3-none-any.whl → 1.65.0__py3-none-any.whl

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 (43) hide show
  1. evalvault/adapters/inbound/cli/commands/__init__.py +14 -7
  2. evalvault/adapters/inbound/cli/commands/artifacts.py +107 -0
  3. evalvault/adapters/inbound/cli/commands/calibrate_judge.py +283 -0
  4. evalvault/adapters/inbound/cli/commands/compare.py +290 -0
  5. evalvault/adapters/inbound/cli/commands/history.py +13 -85
  6. evalvault/adapters/inbound/cli/commands/ops.py +110 -0
  7. evalvault/adapters/inbound/cli/commands/profile_difficulty.py +160 -0
  8. evalvault/adapters/inbound/cli/commands/regress.py +251 -0
  9. evalvault/adapters/outbound/analysis/comparison_pipeline_adapter.py +49 -0
  10. evalvault/adapters/outbound/artifact_fs.py +16 -0
  11. evalvault/adapters/outbound/filesystem/__init__.py +3 -0
  12. evalvault/adapters/outbound/filesystem/difficulty_profile_writer.py +50 -0
  13. evalvault/adapters/outbound/filesystem/ops_snapshot_writer.py +13 -0
  14. evalvault/adapters/outbound/judge_calibration_adapter.py +36 -0
  15. evalvault/adapters/outbound/judge_calibration_reporter.py +57 -0
  16. evalvault/adapters/outbound/tracker/langfuse_adapter.py +12 -7
  17. evalvault/adapters/outbound/tracker/phoenix_adapter.py +39 -12
  18. evalvault/domain/entities/__init__.py +10 -0
  19. evalvault/domain/entities/judge_calibration.py +50 -0
  20. evalvault/domain/entities/stage.py +11 -3
  21. evalvault/domain/services/artifact_lint_service.py +268 -0
  22. evalvault/domain/services/benchmark_runner.py +1 -6
  23. evalvault/domain/services/dataset_preprocessor.py +26 -0
  24. evalvault/domain/services/difficulty_profile_reporter.py +25 -0
  25. evalvault/domain/services/difficulty_profiling_service.py +304 -0
  26. evalvault/domain/services/evaluator.py +2 -0
  27. evalvault/domain/services/judge_calibration_service.py +495 -0
  28. evalvault/domain/services/ops_snapshot_service.py +159 -0
  29. evalvault/domain/services/regression_gate_service.py +199 -0
  30. evalvault/domain/services/run_comparison_service.py +159 -0
  31. evalvault/domain/services/stage_event_builder.py +6 -1
  32. evalvault/domain/services/stage_metric_service.py +83 -18
  33. evalvault/ports/outbound/__init__.py +4 -0
  34. evalvault/ports/outbound/artifact_fs_port.py +12 -0
  35. evalvault/ports/outbound/comparison_pipeline_port.py +22 -0
  36. evalvault/ports/outbound/difficulty_profile_port.py +15 -0
  37. evalvault/ports/outbound/judge_calibration_port.py +22 -0
  38. evalvault/ports/outbound/ops_snapshot_port.py +8 -0
  39. {evalvault-1.64.0.dist-info → evalvault-1.65.0.dist-info}/METADATA +1 -1
  40. {evalvault-1.64.0.dist-info → evalvault-1.65.0.dist-info}/RECORD +43 -17
  41. {evalvault-1.64.0.dist-info → evalvault-1.65.0.dist-info}/WHEEL +0 -0
  42. {evalvault-1.64.0.dist-info → evalvault-1.65.0.dist-info}/entry_points.txt +0 -0
  43. {evalvault-1.64.0.dist-info → evalvault-1.65.0.dist-info}/licenses/LICENSE.md +0 -0
@@ -16,26 +16,32 @@ evalvault/adapters/inbound/api/routers/pipeline.py,sha256=8UgQzNFHcuqS61s69mOrPe
16
16
  evalvault/adapters/inbound/api/routers/runs.py,sha256=rydOvwWk24QIYafu3XYS3oL_VVCE_jHDmjADhA19T1s,40059
17
17
  evalvault/adapters/inbound/cli/__init__.py,sha256=a42flC5NK-VfbdbBrE49IrUL5zAyKdXZYJVM6E3NTE0,675
18
18
  evalvault/adapters/inbound/cli/app.py,sha256=ytNgHRg9ZTAl33AkB1wIL8RKfQ_Cf8fsy0gSsLTs7Ew,1603
19
- evalvault/adapters/inbound/cli/commands/__init__.py,sha256=cNPPhsudTQWdlh_OJm9mU8LGBnJLGMswJBcIV9MAlkI,3530
19
+ evalvault/adapters/inbound/cli/commands/__init__.py,sha256=kw0SAEwOce1v92Pd6YpQjSYsdwLU95TQqbKGM44fNhY,3995
20
20
  evalvault/adapters/inbound/cli/commands/agent.py,sha256=YlOYMEzzS1aSKDKD_a7UK3St18X6GXGkdTatrzyd8Zc,7555
21
21
  evalvault/adapters/inbound/cli/commands/analyze.py,sha256=aMi1BEDOX3yhN-ppBftDssPQLB5TdzIfpx9U7CZEgWo,48932
22
22
  evalvault/adapters/inbound/cli/commands/api.py,sha256=YdbJ_-QEajnFcjTa7P2heLMjFKpeQ4nWP_p-HvfYkEo,1943
23
+ evalvault/adapters/inbound/cli/commands/artifacts.py,sha256=bE8FQxmnU0mMIAPx5en8aKrtfNNkrbWoLxIX4ZT9D5c,3776
23
24
  evalvault/adapters/inbound/cli/commands/benchmark.py,sha256=RZ4nRTF7d6hDZug-Pw8dGcFEyWdOKclwqkvS-gN4VWo,41097
24
25
  evalvault/adapters/inbound/cli/commands/calibrate.py,sha256=-UnT0LQH40U5lzMLqMJ7DOTLa3mt5P_fJL2XzqIkvu4,4223
26
+ evalvault/adapters/inbound/cli/commands/calibrate_judge.py,sha256=hJBlNl9Rt-ZtoIu-HKfudhZb2j2HOoEnRbiG4n5TOTE,10348
27
+ evalvault/adapters/inbound/cli/commands/compare.py,sha256=X_uyJoT_yQP43RTWMLCwMuHwhOb8wCqFShjy477V-2c,10384
25
28
  evalvault/adapters/inbound/cli/commands/config.py,sha256=Mv9IQHBFHZ3I2stUzHDgLDn-Znt_Awdy3j-sk5ruUmw,6069
26
29
  evalvault/adapters/inbound/cli/commands/debug.py,sha256=KU-hL1gLhpjV2ZybDQgGMwRfm-hCynkrqY4UzETfL9k,2234
27
30
  evalvault/adapters/inbound/cli/commands/domain.py,sha256=dL9iqBlnr5mDeS1unXW6uxE0qp6yfnxj-ls6k3EenwI,27279
28
31
  evalvault/adapters/inbound/cli/commands/experiment.py,sha256=jficaFOsZ9EMHrPHCOZjq6jpFrgmqCwmIo--wA_OcvQ,10389
29
32
  evalvault/adapters/inbound/cli/commands/gate.py,sha256=SxBSHALhekw9OVuJcuk64tkS8YMDDsgmhMALTE38wwY,9956
30
33
  evalvault/adapters/inbound/cli/commands/generate.py,sha256=7IPvd0WAwPxt9uaxmzqWCwt0b2VC_wXiVxyJ3lP-xys,8562
31
- evalvault/adapters/inbound/cli/commands/history.py,sha256=P8rK_nRJrmtG3y9obq3OSYtDZGZt2o3660_9JtbSPkg,11100
34
+ evalvault/adapters/inbound/cli/commands/history.py,sha256=3xf1l-I8IW-1Vtne9ypepDMDRRbwOpEvAjh4Qf9tV2w,8420
32
35
  evalvault/adapters/inbound/cli/commands/init.py,sha256=7q86fUeBVA08fU_N0lAV6Lakxirq4val2jIyALlDy3E,8822
33
36
  evalvault/adapters/inbound/cli/commands/kg.py,sha256=ycV9Xj6SUUJLTyTfLZcjXDVLcZqwo7Gw878ZhZAeDoc,19155
34
37
  evalvault/adapters/inbound/cli/commands/langfuse.py,sha256=aExhZ5WYT0FzJI4v1sF-a1jqy9b1BF46_HBtfiQjVGI,4085
35
38
  evalvault/adapters/inbound/cli/commands/method.py,sha256=OWdoofhvsDJchgNKnGGjXfIsZ-IHKZEo6RlmTsZRRYM,19124
39
+ evalvault/adapters/inbound/cli/commands/ops.py,sha256=2r6hdrZ7STnWMhtzYmv8jF_ukBq4HuKB1El6YnyxwrY,4035
36
40
  evalvault/adapters/inbound/cli/commands/phoenix.py,sha256=LQi3KTLq1ybjjBuz92oQ6lYyBS3mHrCHk0qe-7bqB4U,15611
37
41
  evalvault/adapters/inbound/cli/commands/pipeline.py,sha256=NeqWLzO9kRDuZd0pHAIHglP3F7VzoNOU4JI0QcSZ120,7788
42
+ evalvault/adapters/inbound/cli/commands/profile_difficulty.py,sha256=nOJH3iqgLAlXq4keLBj5oqpiRCg0jjGgT-7Q57HxEh8,6665
38
43
  evalvault/adapters/inbound/cli/commands/prompts.py,sha256=lddde5VbjYaqN_9gHPLNu6DWpg5fE-KqZzjN-XYwvJw,27153
44
+ evalvault/adapters/inbound/cli/commands/regress.py,sha256=Dy8hUOdjapxOW9Hoov0DHHblkMaExiqWfYS14CaC9Kk,8806
39
45
  evalvault/adapters/inbound/cli/commands/run.py,sha256=X19rgXhajhvZNA4c0JMmzmPatTxhZgfapuW07bZL9xA,119265
40
46
  evalvault/adapters/inbound/cli/commands/run_helpers.py,sha256=hu2TioocitUZzGR7HUwZ6gOeEJSvt5tGNjwXOlo4Eic,40336
41
47
  evalvault/adapters/inbound/cli/commands/stage.py,sha256=oRC9c5CysLX90Iy5Ba1pc_00DaOBS78lcBvzkbdrGRM,17123
@@ -52,6 +58,9 @@ evalvault/adapters/inbound/mcp/__init__.py,sha256=kctJsmaP4fY94T3WCOhgANk3TCLdfb
52
58
  evalvault/adapters/inbound/mcp/schemas.py,sha256=KUKm4gEc-UDyF8sUbyzAnAIzyZ6DcXsaCEIVR3oESNQ,4469
53
59
  evalvault/adapters/inbound/mcp/tools.py,sha256=fnvkWS5p93o3FNmUSbh3EW4jCAVwtBKHX6kDuEbXkK8,24219
54
60
  evalvault/adapters/outbound/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
61
+ evalvault/adapters/outbound/artifact_fs.py,sha256=nySk7-10B9rQpV9EslBmRUr0gFIi9V1E_E_wdC1WpIU,439
62
+ evalvault/adapters/outbound/judge_calibration_adapter.py,sha256=vu5dVJVo5AXa5ULcx8WE-6YgfD718BC8Ci1_HAdwy20,1155
63
+ evalvault/adapters/outbound/judge_calibration_reporter.py,sha256=R0nId6P1jYQ3M3636knPNFztuc8kewDBKsg2LLcUw58,2005
55
64
  evalvault/adapters/outbound/analysis/__init__.py,sha256=TLuS-eKfXg97_Db5td1nTZkD3BErRLZLic1v2EAM2sA,6185
56
65
  evalvault/adapters/outbound/analysis/analysis_report_module.py,sha256=xah3wgJErHD_Hpb1YAwWRsxr8xaC8SW--CpNA7IgfxI,3957
57
66
  evalvault/adapters/outbound/analysis/base_module.py,sha256=eUN77SSD2KR4WKU7gLY8TlVewETx_YIZvPT4LUnBv4o,2523
@@ -59,6 +68,7 @@ evalvault/adapters/outbound/analysis/bm25_searcher_module.py,sha256=I8BsXrHaOVxg
59
68
  evalvault/adapters/outbound/analysis/causal_adapter.py,sha256=Rt5QcoLDEjx8u_yidACz3u8SbAVYSJO6lLu6udwnd4U,27410
60
69
  evalvault/adapters/outbound/analysis/causal_analyzer_module.py,sha256=hBcTx7ZyUZ6HQ6I6W2VvSZ1ndatlgMen2KjKXk_Ltx4,6780
61
70
  evalvault/adapters/outbound/analysis/common.py,sha256=H1RqNBiOt7WRcHUM3jFydd3850GFQhEDUu8WBEhtMws,5734
71
+ evalvault/adapters/outbound/analysis/comparison_pipeline_adapter.py,sha256=D_ZPVgQHz3Cn3fxxl-TgLEoo_RNbhsOJCvqH-cJ2Lf4,1577
62
72
  evalvault/adapters/outbound/analysis/comparison_report_module.py,sha256=0tTMZB5qpGMaxlcWtTtTln7Y_jFEDFaaW7V-UyboBDM,2343
63
73
  evalvault/adapters/outbound/analysis/data_loader_module.py,sha256=6X0-ZcFtEfonQnbJ0POqmHXstJ1Wq1NvpijtbKSeEm0,3749
64
74
  evalvault/adapters/outbound/analysis/detailed_report_module.py,sha256=59CjuNQthlroJyGEhQap3PgahWfzXciKx_DD10gHXjM,3897
@@ -125,6 +135,9 @@ evalvault/adapters/outbound/documents/ocr/paddleocr_backend.py,sha256=AORA9JUV5u
125
135
  evalvault/adapters/outbound/domain_memory/__init__.py,sha256=ksMX1IkNiDqQHLtJe9TOXiLC1iouGt6_QSdPLiALHHs,229
126
136
  evalvault/adapters/outbound/domain_memory/domain_memory_schema.sql,sha256=APlNhJNFZdcm7Sb2tvr7V8JMiLinmXkx1gd6pgTf9ZI,11268
127
137
  evalvault/adapters/outbound/domain_memory/sqlite_adapter.py,sha256=RWobnFgvxiItxFAr6niY89sT19O-cnExTbP0I7UAY78,85186
138
+ evalvault/adapters/outbound/filesystem/__init__.py,sha256=eTQLuVPMpEctE92TtegKQT3wuJTIhiBS38BzfxRV-N0,122
139
+ evalvault/adapters/outbound/filesystem/difficulty_profile_writer.py,sha256=9qO9_3E-SL6ngDOia6zcw680S1fQloxo32f6hx76YHs,1626
140
+ evalvault/adapters/outbound/filesystem/ops_snapshot_writer.py,sha256=sOuUk8VD8yWwG8508uw1zqSnNsp3dQrF9bp9T2z-n48,448
128
141
  evalvault/adapters/outbound/improvement/__init__.py,sha256=tXA6vaZOLvqwJpyjGMiC8WrvszMmvUPzJnHjvJhQxSI,1143
129
142
  evalvault/adapters/outbound/improvement/insight_generator.py,sha256=U16l0euCZy0_08Zb_i0eijXSjS5t-iq0iMUfttwPqgI,17636
130
143
  evalvault/adapters/outbound/improvement/pattern_detector.py,sha256=uFFjWNy8A4KIihw_ANtL6At73RirwNnFnN4rFsEvcXk,24602
@@ -180,10 +193,10 @@ evalvault/adapters/outbound/tracer/open_rag_trace_decorators.py,sha256=LFnk-3FSL
180
193
  evalvault/adapters/outbound/tracer/open_rag_trace_helpers.py,sha256=D48Mbj-ioDKztjhV9513Q5DiUNiVdO60B_2sWMFEmnI,3520
181
194
  evalvault/adapters/outbound/tracer/phoenix_tracer_adapter.py,sha256=inmTAolAVsm0IrszE9VTJoI7HSvGGAnGNZVu_vZRAGg,741
182
195
  evalvault/adapters/outbound/tracker/__init__.py,sha256=Suu5BznOK5uTuD5_jS8JMZd8RPfQNlddLxHCBvMTm_4,358
183
- evalvault/adapters/outbound/tracker/langfuse_adapter.py,sha256=HmuMVUfDYjqNqHZGZMRybhrgca_EmeENuX7DfP-L5Fg,18504
196
+ evalvault/adapters/outbound/tracker/langfuse_adapter.py,sha256=oi6bnz2qjDSXEea_bACFRUEKk-tKw53d1xMfL4FE5dI,18749
184
197
  evalvault/adapters/outbound/tracker/log_sanitizer.py,sha256=ilKTTSzsHslQYc-elnWu0Z3HKNNw1D1iI0_cCvYbo1M,2653
185
198
  evalvault/adapters/outbound/tracker/mlflow_adapter.py,sha256=m4xj3XBULFYg27U3twKrldLhbLyLNefezmb2pCpHJrw,7180
186
- evalvault/adapters/outbound/tracker/phoenix_adapter.py,sha256=sz5TyWC67e3YbQd2y-ogU9_66rilLdf8TbC-7bN_JR0,24316
199
+ evalvault/adapters/outbound/tracker/phoenix_adapter.py,sha256=VmGkVuBX5Nae6zTaaSbpcA94spFJGmwjW0gOh2vIxnk,25332
187
200
  evalvault/config/__init__.py,sha256=UCgeDx62M2gOuFvdN29wWwny2fdH4bPY_uUC3-42eDw,1297
188
201
  evalvault/config/agent_types.py,sha256=EP2Pv3ZtOzDXIvIa-Hnd1to9JIbMUtGitrlwzZtx0Ys,13418
189
202
  evalvault/config/domain_config.py,sha256=rOgNA2T8NWlDzcEFC0shdUCCww0lI1E5fUm5QrKQSZI,9264
@@ -195,7 +208,7 @@ evalvault/config/secret_manager.py,sha256=YjPMuNqeBrAR2BzCJvsBNUExaU4TBSFyZ8kVYZ
195
208
  evalvault/config/settings.py,sha256=JKJf8t20sOHYnHoCfTxqupQixNgfmWYJhChiGMNz-W0,17617
196
209
  evalvault/config/playbooks/improvement_playbook.yaml,sha256=9F9WVVCydFfz6zUuGYzZ4PKdW1LLtcBKVF36T7xT764,26965
197
210
  evalvault/domain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
198
- evalvault/domain/entities/__init__.py,sha256=RZi_6oQcq-2-sJcydfKOSr03vFxo-mF7CGHN9Ma4Cdg,3379
211
+ evalvault/domain/entities/__init__.py,sha256=wszRJ1Imdc5NJ1bQPC2udk-mAgFdlw4uZV5IPNjLpHQ,3669
199
212
  evalvault/domain/entities/analysis.py,sha256=gcMtumC66g-AIqb2LgfMpm5BMzwJhJkjg-zuybNoJCM,15208
200
213
  evalvault/domain/entities/analysis_pipeline.py,sha256=hD9rFHMa4rUq0InRkSKhh6HQ9ZeNYAHKADzs-kWRP04,16845
201
214
  evalvault/domain/entities/benchmark.py,sha256=CVbz_eW7Y9eM7wG7xA_xmldTIs72csdoTmu3E0NKoMU,18475
@@ -205,6 +218,7 @@ evalvault/domain/entities/debug.py,sha256=r92lgvOpq2svw70syJIo78muRAvrSn5h1JByH_
205
218
  evalvault/domain/entities/experiment.py,sha256=oWjbu0IJZ6oIRcnA-8ppeJDgp57Tv8ZjQ3UOZ0X9KJ8,2576
206
219
  evalvault/domain/entities/feedback.py,sha256=xiaZaUQhyuxyW_i2scXt8eKZshMC6tXe3981e-uukw8,1604
207
220
  evalvault/domain/entities/improvement.py,sha256=WHI7q1jXRxkuHhBWOrpk8UdLaH0UwjZVjRIDsqVDyZo,19322
221
+ evalvault/domain/entities/judge_calibration.py,sha256=fhQEI7g2nZuG1OliikhxgefcFAJldDqEmfTs9Mp-FPk,1234
208
222
  evalvault/domain/entities/kg.py,sha256=8awN1M4vxAGQZk_ZG8i2CXKTizQ8FA1VCLhUWHZq0U8,3001
209
223
  evalvault/domain/entities/memory.py,sha256=bfS75q8K8_jNrB7IYh4mjP8Lkyj-I0TVsmHCP0FuICw,8423
210
224
  evalvault/domain/entities/method.py,sha256=a3jZi7SjcpK3HeVyVwQkUMwpnmg2RbxCnH4NqYPLCOI,1157
@@ -212,7 +226,7 @@ evalvault/domain/entities/prompt.py,sha256=VzuUzqkqXv0FwTSNGyV5sSCft5sxTbG_Noq6Y
212
226
  evalvault/domain/entities/prompt_suggestion.py,sha256=Ep_XSjdYUj7pFSCMyeeZKs8yTnp74AVx05Zqr7829PE,1243
213
227
  evalvault/domain/entities/rag_trace.py,sha256=sZgnkG4fK6KOe3Np6TYAZ_tPnsRbOmucDSQns35U1n4,11868
214
228
  evalvault/domain/entities/result.py,sha256=OaGHMDLWMW2O4fNVuVTUvWFVBQ1iu93OD_oI3NumrCQ,10697
215
- evalvault/domain/entities/stage.py,sha256=dbVzhgpP_p2p2eDJBWe7mwyyl6zUTP9kEKN_YRUvufY,7183
229
+ evalvault/domain/entities/stage.py,sha256=UqS59sjoMs_bhMupNtvagbIx8QgHgFjWoRPhJ3uJP2s,7426
216
230
  evalvault/domain/metrics/__init__.py,sha256=fxjC5Z_8OuBIeMn80bYgnZZxpNoay2wH-qtG3NqCUvk,797
217
231
  evalvault/domain/metrics/analysis_registry.py,sha256=JZpBrBs7-JExHKYuEML6Vg_uYLm-WniBE3BfiU5OtJg,7641
218
232
  evalvault/domain/metrics/confidence.py,sha256=AX4oeN28OvmMkwD0pT-jskkOlXh87C1pe2W9P1sF69g,17224
@@ -226,21 +240,24 @@ evalvault/domain/metrics/terms_dictionary.json,sha256=-ZQmpx6yMOYoAOpcLj-xK2LkAe
226
240
  evalvault/domain/metrics/text_match.py,sha256=P-YTZs9ekDqEmxLNBP8eXnMRymPdC8V4dJPtwG2ajVM,10219
227
241
  evalvault/domain/services/__init__.py,sha256=X5Af1kf_vSt3S3mFwOV6OQdro-lFxwbVdNd7nJznkC8,1024
228
242
  evalvault/domain/services/analysis_service.py,sha256=oUEtfJHB3bNJ_Ksygx-pjnLm4CTk7_rDvDbqfkAfFD4,10838
243
+ evalvault/domain/services/artifact_lint_service.py,sha256=80P46weoj9lBxOqg_ViHZEQ6Cfo69XV4cniZlmMsti0,8434
229
244
  evalvault/domain/services/async_batch_executor.py,sha256=qYFRl7CGmv56XppeRhInde7Fw0GESCoZh8V-Iv_1hQQ,11140
230
245
  evalvault/domain/services/batch_executor.py,sha256=cYA_Q1es46n_PYeyyfm0iM2b7GGVtDoOGoMxexrf6tI,1243
231
246
  evalvault/domain/services/benchmark_report_service.py,sha256=IF-zqtvpsJ0ONJWUEw4ghKiC7ka_PWxUBO10lPaDRmI,15083
232
- evalvault/domain/services/benchmark_runner.py,sha256=iqirGDs-yemSmqLDnCPGA7Wug0ps6z0vRgRsgetypOM,26328
247
+ evalvault/domain/services/benchmark_runner.py,sha256=4tvQEDrfvp2fC2luUPuPBcRjEPLHdrdystLpe3PnBqM,26046
233
248
  evalvault/domain/services/benchmark_service.py,sha256=TrmnvBMAPmcs0PewGZcn2rxHbviZ8KxmDvJCeyqm28I,6286
234
249
  evalvault/domain/services/cache_metrics.py,sha256=FKNZoxym30lc1SxTGmTn3Pr-PDNoAqgC9_d_IdF_jOQ,3463
235
250
  evalvault/domain/services/cluster_map_builder.py,sha256=qPKMPj-eSqECJSCOKvv3ZETgIwxwiKWbU3d6_feCoDg,6885
236
- evalvault/domain/services/dataset_preprocessor.py,sha256=v-shY5ky1oW0LJwBfdfP4VFh7TXBabpLD5rMOmtS-dQ,14235
251
+ evalvault/domain/services/dataset_preprocessor.py,sha256=PnhLiPk0E9DIzjUr8N75296CCfl1AUXGv-lpaXBi0Ok,14797
237
252
  evalvault/domain/services/debug_report_service.py,sha256=SGdFh8tctAIq7RotFbg47eetxdYSS4Yju7-LOzpCMCM,4386
253
+ evalvault/domain/services/difficulty_profile_reporter.py,sha256=uIj9-eiO2dDvQ6tP-DJBddfBq8VT63st0wtNC8Co4NQ,680
254
+ evalvault/domain/services/difficulty_profiling_service.py,sha256=wB3T2iz_dZjvj7wiU2fnM0XT-doMNokV_YqSt24Wc6A,11078
238
255
  evalvault/domain/services/document_chunker.py,sha256=u05N1xSBcJuJPUfP7WmpY_EyHuUMuGMsPSM9qs-ID8c,2494
239
256
  evalvault/domain/services/document_versioning.py,sha256=M1qZaMpQ2exVT1wkVAmvEPPuoYibJDt0F7pYfTK7mvE,3323
240
257
  evalvault/domain/services/domain_learning_hook.py,sha256=rhKBmdnrJyfGzFNsNxzyv8jZO26-WOosHSmBV_9qdJg,7176
241
258
  evalvault/domain/services/embedding_overlay.py,sha256=ZTNxUPXpHGbQ3Uri5DD3feTUFn7qrhuNshhyCQEvRuM,3559
242
259
  evalvault/domain/services/entity_extractor.py,sha256=f3Rf5saK8QsgetLNK1Hbxzt8PtttJZCicSR63S8DJ5k,14141
243
- evalvault/domain/services/evaluator.py,sha256=YReil1mokTILyllAbG_QnFhob-15G5tNeWZZMbSc3yo,67551
260
+ evalvault/domain/services/evaluator.py,sha256=cKcPRoqkUFc00lgx_blbIFl0qJyPIDjPeCciWAPm7m8,67669
244
261
  evalvault/domain/services/experiment_comparator.py,sha256=IBrxIwux-8GucwlLx6e5lUqB9miSPvBLGJK9ctoW7Y0,3299
245
262
  evalvault/domain/services/experiment_manager.py,sha256=2k-qGiAUyZuqqmcp4P-M3Z9HTXwwcqW5HQYKNkcIHuI,4863
246
263
  evalvault/domain/services/experiment_reporter.py,sha256=QYlVmCFSx8hKTPMezc7QjJE07b3MSQ82Q4QVucSHLVY,1420
@@ -249,10 +266,12 @@ evalvault/domain/services/experiment_statistics.py,sha256=aOrqbBjB1swHPaFRziID1m
249
266
  evalvault/domain/services/holdout_splitter.py,sha256=Sos61Zy_bBjStt8LPHJ3KxDNda-OmX7AVUsT24K1n6Q,1910
250
267
  evalvault/domain/services/improvement_guide_service.py,sha256=gMoVFlDsprOEEfRGKmdbk9_Due62J63Q-rL2zr65Q0s,17881
251
268
  evalvault/domain/services/intent_classifier.py,sha256=hsWivDXqXJjCJEE-OI7eUGeYrewpYxlz67Z0TI3oskU,11707
269
+ evalvault/domain/services/judge_calibration_service.py,sha256=cOaAsbfMBlaDxoMAXe8MacDDRK0tCD-tXRnYjB6sEPs,19264
252
270
  evalvault/domain/services/kg_generator.py,sha256=oEugjPdn8Pb2Q3r5yAZl0dZJibNUkEherlRVquknB6k,24969
253
271
  evalvault/domain/services/memory_aware_evaluator.py,sha256=vTiYoxiMfZ_CMjSBjqwkBRdpiXRwQ2zXnQ2pXzVHYts,5249
254
272
  evalvault/domain/services/memory_based_analysis.py,sha256=oh2irCy3le7fWiTtL31SMEhPyu7fyBVz-giO2hlNifE,4499
255
273
  evalvault/domain/services/method_runner.py,sha256=pABqKZeaALpWZYDfzAbd-VOZt2djQggRNIPuuPQeUSw,3571
274
+ evalvault/domain/services/ops_snapshot_service.py,sha256=1CqJN2p3tM6SgzLCZKcVEM213fd1cDGexTRPG_3e59w,5138
256
275
  evalvault/domain/services/pipeline_orchestrator.py,sha256=yriVlEVZYDtt0Vwt4Ae6xyW1H6Dj4Hxdn8XQSvQNSoQ,19436
257
276
  evalvault/domain/services/pipeline_template_registry.py,sha256=aWqXLQ24grpSZo9M4tZLRo1ysD10c6hUpW3JupZH9e0,28083
258
277
  evalvault/domain/services/prompt_candidate_service.py,sha256=Ibyb5EaWK28Ju2HnTqHHGOoiA9Q-VwY3hjxVODALwGY,3997
@@ -262,12 +281,14 @@ evalvault/domain/services/prompt_scoring_service.py,sha256=SlvfuIbhj92RJu4RQAJ1B
262
281
  evalvault/domain/services/prompt_status.py,sha256=r1dFLGz4SfRxXaxsULQsr0-HpJkG9YfZ_yLIxF1MMBo,6731
263
282
  evalvault/domain/services/prompt_suggestion_reporter.py,sha256=Fc6sCPebUMk8SZVpjoJ6bCEun0ma-YmayEQnulBVv8s,10577
264
283
  evalvault/domain/services/ragas_prompt_overrides.py,sha256=4BecYE2KrreUBbIM3ssP9WzHcK_wRc8jW7CE_k58QOU,1412
284
+ evalvault/domain/services/regression_gate_service.py,sha256=qBMODgpizmEzqEL8_JX-FYSVyARiroMW7MFVzlz7gjc,6579
265
285
  evalvault/domain/services/retrieval_metrics.py,sha256=dtrQPLMrXSyWLcgF8EGcLNFwzwA59WDzEh41JRToHAY,2980
266
286
  evalvault/domain/services/retriever_context.py,sha256=ySQ-GuadiggS0LVAib4AxA_0JpasYz4S9hbjau0eyIA,6482
287
+ evalvault/domain/services/run_comparison_service.py,sha256=_NScltCRcY3zrvdyYDiPmssTxCDv1GyjCLdP3uAxJts,5631
267
288
  evalvault/domain/services/satisfaction_calibration_service.py,sha256=H7Z8opOyPHRO5qVIw-XDsNhIwdCteAS9_a3BTlfIqHg,11906
268
- evalvault/domain/services/stage_event_builder.py,sha256=ScTgyeRiH7z_rnNI_2p-i9szVRIRwUxGSJvpEj3zto4,9645
289
+ evalvault/domain/services/stage_event_builder.py,sha256=FAT34Wmylvd2Yz5rDlhaTh1lqSCDhGApCXMi7Hjkib0,9748
269
290
  evalvault/domain/services/stage_metric_guide_service.py,sha256=_JdRsBRWirO24qYFlh6hG-dkoWlX6_XWEYKf_uUlKIQ,8807
270
- evalvault/domain/services/stage_metric_service.py,sha256=KukIWWhWVOtclrET6uyWJ17jG76LfkKiqrUrDIDJ3gw,15327
291
+ evalvault/domain/services/stage_metric_service.py,sha256=_u6ThZ8rGw8H9h3TNpu0j8XhpIfukHSoyc1ZpCa3Z00,18031
271
292
  evalvault/domain/services/stage_summary_service.py,sha256=VVtuAr4vwzvmNFn8rqURJrhKFqAMG4CaBmyGiUk_xG0,1590
272
293
  evalvault/domain/services/synthetic_qa_generator.py,sha256=aiOTPoHZbKRTEeodABQ2I5lq8-Vs_kQtuzcGWd4MTGE,16526
273
294
  evalvault/domain/services/testset_generator.py,sha256=6IpiZ0pqhKEymo-AlUdfJjDkF2P1n8Md_QKV4nOheyg,4470
@@ -280,22 +301,27 @@ evalvault/ports/inbound/analysis_pipeline_port.py,sha256=RJfKtp22AYEqnmRk6RDawAK
280
301
  evalvault/ports/inbound/evaluator_port.py,sha256=rDvouIRUjBD7uICgrpeo11vNPvo27_0CdylRHPodPSE,1323
281
302
  evalvault/ports/inbound/learning_hook_port.py,sha256=EeJeMl3chcPHlj5mkLOj6tm8s_qdDRvoCwK1-0l70tI,3297
282
303
  evalvault/ports/inbound/web_port.py,sha256=b4uMhwOMLXy3LeILc7ZK3RR-XtoW4p4NzoTpj4syptg,5578
283
- evalvault/ports/outbound/__init__.py,sha256=0uPE6CXkoK6ECs3O4OZYAmVg5VAAHoF5rdb1eoj1NAc,3367
304
+ evalvault/ports/outbound/__init__.py,sha256=x3LseXtwX0NONM1mnhT3fMchz7U6gEDRUX0TDswpg5E,3591
284
305
  evalvault/ports/outbound/analysis_cache_port.py,sha256=zPSdUVK_yw3PMWPII2YvS1WLmCGlg5bDScSuYINW9yc,1386
285
306
  evalvault/ports/outbound/analysis_module_port.py,sha256=QYzkvie9-BbONj8ZgiQUjm8I-bn8mgzlXTzIXMhehmQ,1881
286
307
  evalvault/ports/outbound/analysis_port.py,sha256=gE-iXToTgdQomj9JwNZJY4nwut8q0J6EurUmJNsnptQ,2127
308
+ evalvault/ports/outbound/artifact_fs_port.py,sha256=SN966vwHiIjLA06MBWePr7V0NmafbiQbSLFlXAN3YKU,273
287
309
  evalvault/ports/outbound/benchmark_port.py,sha256=pgo3rNbvvJS8x03UxBVQPBBgxc7X5kfG70ZlIf3sopE,7173
288
310
  evalvault/ports/outbound/causal_analysis_port.py,sha256=IsyVdFrs66mHcOc-_VbxrZQriwMrDxx-5a_4ElX5Bp0,941
311
+ evalvault/ports/outbound/comparison_pipeline_port.py,sha256=IOLK6vZdzjSV6Qcvkl9GD-wRxx6Waa3dsYOCFdD1mXY,503
289
312
  evalvault/ports/outbound/dataset_port.py,sha256=OpEBlkvFwpSRbmi-Lt3wK7n0wljmQ6m985mjyNn_qFk,990
313
+ evalvault/ports/outbound/difficulty_profile_port.py,sha256=hQY-TR64WyUNnCxD9Mw-QraO3ZBw0VUP8KoCmVsQYBE,347
290
314
  evalvault/ports/outbound/domain_memory_port.py,sha256=SZFurqsoBmTw1Kt_pej-YpMbooVeyV35jekhaDRojus,23320
291
315
  evalvault/ports/outbound/embedding_port.py,sha256=ZHeKRMRBNjpZKWxsLKrD8jJz0M66JTwNcrJbkRaklK4,2034
292
316
  evalvault/ports/outbound/improvement_port.py,sha256=fIXhcG4n6OJ1hdvWeqEoLBrVsCNdHZRgtEZjR8lf3qA,2325
293
317
  evalvault/ports/outbound/intent_classifier_port.py,sha256=gqMIk0rH6Z43ceuMMRX4vqXurgHZz-CJX2bR5PVAkjQ,2253
318
+ evalvault/ports/outbound/judge_calibration_port.py,sha256=kShZ2MZGvgQZaY7XxwkmLXtquK_RFKcwuWRBfJOrILA,602
294
319
  evalvault/ports/outbound/korean_nlp_port.py,sha256=mJCnxBAkV8a5Nd_VX6QcjfDucY62er8GlaNO4HQA8q8,1572
295
320
  evalvault/ports/outbound/llm_factory_port.py,sha256=lzoDJi6A6ltk-t3N4oY8DSwMBMfnvXGgSduILOpzoas,305
296
321
  evalvault/ports/outbound/llm_port.py,sha256=YAW0i-41yT8KzMuzZGEO5yPDkHN0onGxj55eL0cdPHY,4393
297
322
  evalvault/ports/outbound/method_port.py,sha256=sntcKgwagAdJGxp0dI-S_bhBQcOW9QpnND3fOjrsX9E,1377
298
323
  evalvault/ports/outbound/nlp_analysis_port.py,sha256=QDJHAsSpynTenuaKp78t1s--U036mtYeUEX0p5vQw24,3046
324
+ evalvault/ports/outbound/ops_snapshot_port.py,sha256=6v72W41tlnxjkJfbfHhFiJMPlRSAQ-BvrI2T09_yddk,214
299
325
  evalvault/ports/outbound/relation_augmenter_port.py,sha256=cMcHQnmK111WzZr50vYr7affeHhOtpFZxPARwkg9xbk,651
300
326
  evalvault/ports/outbound/report_port.py,sha256=wgReSYL4SupXIoALFh0QFWfX2kzPftXpWTvGLCMd2B8,1315
301
327
  evalvault/ports/outbound/stage_storage_port.py,sha256=Nlf9upsXxgCABQB5cJdpLQYsoZNiGRAU5zE5D-Ptp2I,1201
@@ -306,8 +332,8 @@ evalvault/reports/__init__.py,sha256=Bb1X4871msAN8I6PM6nKGED3psPwZt88hXZBAOdH06Y
306
332
  evalvault/reports/release_notes.py,sha256=pZj0PBFT-4F_Ty-Kv5P69BuoOnmTCn4kznDcORFJd0w,4011
307
333
  evalvault/scripts/__init__.py,sha256=NwEeIFQbkX4ml2R_PhtIoNtArDSX_suuoymgG_7Kwso,89
308
334
  evalvault/scripts/regression_runner.py,sha256=SxZori5BZ8jVQ057Mf5V5FPgIVDccrV5oRONmnhuk8w,8438
309
- evalvault-1.64.0.dist-info/METADATA,sha256=DcFREpjg4tyoNf8FXTK632rgrOsWuFjSGnVBBQ4LeQ4,24276
310
- evalvault-1.64.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
311
- evalvault-1.64.0.dist-info/entry_points.txt,sha256=Oj9Xc5gYcyUYYNmQfWI8NYGw7nN-3M-h2ipHIMlVn6o,65
312
- evalvault-1.64.0.dist-info/licenses/LICENSE.md,sha256=3RNWY4jjtrQ_yYa-D-7I3XO12Ti7YzxsLV_dpykujvo,11358
313
- evalvault-1.64.0.dist-info/RECORD,,
335
+ evalvault-1.65.0.dist-info/METADATA,sha256=1f23dU3LtSQwrlalym1j8mH-vZaM7HWMzDh-ByjVOjo,24276
336
+ evalvault-1.65.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
337
+ evalvault-1.65.0.dist-info/entry_points.txt,sha256=Oj9Xc5gYcyUYYNmQfWI8NYGw7nN-3M-h2ipHIMlVn6o,65
338
+ evalvault-1.65.0.dist-info/licenses/LICENSE.md,sha256=3RNWY4jjtrQ_yYa-D-7I3XO12Ti7YzxsLV_dpykujvo,11358
339
+ evalvault-1.65.0.dist-info/RECORD,,