evalvault 1.63.1__py3-none-any.whl → 1.65.0__py3-none-any.whl

{evalvault-1.63.1.dist-info → evalvault-1.65.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: evalvault
-Version: 1.63.1
+Version: 1.65.0
 Summary: RAG evaluation system using Ragas with Phoenix/Langfuse tracing
 Project-URL: Homepage, https://github.com/ntts9990/EvalVault
 Project-URL: Documentation, https://github.com/ntts9990/EvalVault#readme
@@ -111,6 +111,10 @@ Requires-Dist: opentelemetry-exporter-otlp>=1.20.0; extra == 'phoenix'
 Requires-Dist: opentelemetry-sdk>=1.20.0; extra == 'phoenix'
 Provides-Extra: postgres
 Requires-Dist: psycopg[binary]>=3.0.0; extra == 'postgres'
+Provides-Extra: secrets
+Requires-Dist: boto3; extra == 'secrets'
+Requires-Dist: google-cloud-secret-manager; extra == 'secrets'
+Requires-Dist: hvac; extra == 'secrets'
 Provides-Extra: timeseries
 Requires-Dist: aeon>=1.3.0; extra == 'timeseries'
 Requires-Dist: numba>=0.55.0; extra == 'timeseries'
@@ -175,6 +179,9 @@ uv run evalvault run --mode simple tests/fixtures/e2e/insurance_qa_korean.json \
   --auto-analyze
 ```
 
+- API 인증을 쓰려면 `.env`에 `API_AUTH_TOKENS`를 설정하세요.
+- `secret://` 참조를 쓰면 `SECRET_PROVIDER`와 `--extra secrets`가 필요합니다.
+- 레이트리밋은 `RATE_LIMIT_ENABLED`로 활성화합니다.
 - 결과는 기본 DB(`data/db/evalvault.db`)에 저장되어 `history`, Web UI, 비교 분석에서 재사용됩니다.
 - `--db`를 생략해도 기본 경로로 저장되며, 모든 데이터가 자동으로 엑셀로 내보내집니다.
 - `--auto-analyze`는 요약 리포트 + 모듈별 아티팩트를 함께 생성합니다.

{evalvault-1.63.1.dist-info → evalvault-1.65.0.dist-info}/RECORD

@@ -6,36 +6,42 @@ evalvault/adapters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuF
 evalvault/adapters/inbound/__init__.py,sha256=SG1svel1PwqetnqVpKFLSv612_WwGwLTbFpYgwk6FMw,166
 evalvault/adapters/inbound/api/__init__.py,sha256=LeVVttCA3tLKoHA2PO4z3y8VkfVcf3Bq8CZSzo91lf4,34
 evalvault/adapters/inbound/api/adapter.py,sha256=tYkJciUUFOK80QcSwzrqkXP1G4qUFItFV7uBYbjBGqU,68473
-evalvault/adapters/inbound/api/main.py,sha256=KdlAxKn0QfGI3UuoTrBDBbUs2xCvP8lnWOY1ce3svcU,2619
+evalvault/adapters/inbound/api/main.py,sha256=lRuyg3aBs5jIk7tq4p4d7jrRkFpV_brZypoOq8s56Rk,6896
 evalvault/adapters/inbound/api/routers/__init__.py,sha256=q07_YF9TnBl68bqcRCvhPU4-zRTyvmPoHVehwO6W7QM,19
 evalvault/adapters/inbound/api/routers/benchmark.py,sha256=yevntbZcNtMvbVODsITUBgR1Ka4pdFQrXBJJ4K4Jyr4,4477
-evalvault/adapters/inbound/api/routers/config.py,sha256=CN-FH2cn0Ive-BD3WacWY6PFfuMtZEHP5_out3fvST4,3957
+evalvault/adapters/inbound/api/routers/config.py,sha256=LygN0fVMr8NFtj5zuQXnVFhoafx56Txa98vpwtPa4Jc,4104
 evalvault/adapters/inbound/api/routers/domain.py,sha256=RsR7GIFMjccDN7vpG1uDyk9n1DnCTH18JDGAX7o4Qqc,3648
-evalvault/adapters/inbound/api/routers/knowledge.py,sha256=7mgyoUM1PepFb4X8_Ntn0vd7ZZYcNbM3_9nyD10g4Aw,5307
+evalvault/adapters/inbound/api/routers/knowledge.py,sha256=yb_e7OEPtwldOAzHTGiWe7jShHw2JdpOFnzGPMceRsg,7109
 evalvault/adapters/inbound/api/routers/pipeline.py,sha256=8UgQzNFHcuqS61s69mOrPee4OMwfxVdvRWHJ2_qYBF0,17175
 evalvault/adapters/inbound/api/routers/runs.py,sha256=rydOvwWk24QIYafu3XYS3oL_VVCE_jHDmjADhA19T1s,40059
 evalvault/adapters/inbound/cli/__init__.py,sha256=a42flC5NK-VfbdbBrE49IrUL5zAyKdXZYJVM6E3NTE0,675
 evalvault/adapters/inbound/cli/app.py,sha256=ytNgHRg9ZTAl33AkB1wIL8RKfQ_Cf8fsy0gSsLTs7Ew,1603
-evalvault/adapters/inbound/cli/commands/__init__.py,sha256=cNPPhsudTQWdlh_OJm9mU8LGBnJLGMswJBcIV9MAlkI,3530
+evalvault/adapters/inbound/cli/commands/__init__.py,sha256=kw0SAEwOce1v92Pd6YpQjSYsdwLU95TQqbKGM44fNhY,3995
 evalvault/adapters/inbound/cli/commands/agent.py,sha256=YlOYMEzzS1aSKDKD_a7UK3St18X6GXGkdTatrzyd8Zc,7555
 evalvault/adapters/inbound/cli/commands/analyze.py,sha256=aMi1BEDOX3yhN-ppBftDssPQLB5TdzIfpx9U7CZEgWo,48932
 evalvault/adapters/inbound/cli/commands/api.py,sha256=YdbJ_-QEajnFcjTa7P2heLMjFKpeQ4nWP_p-HvfYkEo,1943
+evalvault/adapters/inbound/cli/commands/artifacts.py,sha256=bE8FQxmnU0mMIAPx5en8aKrtfNNkrbWoLxIX4ZT9D5c,3776
 evalvault/adapters/inbound/cli/commands/benchmark.py,sha256=RZ4nRTF7d6hDZug-Pw8dGcFEyWdOKclwqkvS-gN4VWo,41097
 evalvault/adapters/inbound/cli/commands/calibrate.py,sha256=-UnT0LQH40U5lzMLqMJ7DOTLa3mt5P_fJL2XzqIkvu4,4223
+evalvault/adapters/inbound/cli/commands/calibrate_judge.py,sha256=hJBlNl9Rt-ZtoIu-HKfudhZb2j2HOoEnRbiG4n5TOTE,10348
+evalvault/adapters/inbound/cli/commands/compare.py,sha256=X_uyJoT_yQP43RTWMLCwMuHwhOb8wCqFShjy477V-2c,10384
 evalvault/adapters/inbound/cli/commands/config.py,sha256=Mv9IQHBFHZ3I2stUzHDgLDn-Znt_Awdy3j-sk5ruUmw,6069
 evalvault/adapters/inbound/cli/commands/debug.py,sha256=KU-hL1gLhpjV2ZybDQgGMwRfm-hCynkrqY4UzETfL9k,2234
 evalvault/adapters/inbound/cli/commands/domain.py,sha256=dL9iqBlnr5mDeS1unXW6uxE0qp6yfnxj-ls6k3EenwI,27279
 evalvault/adapters/inbound/cli/commands/experiment.py,sha256=jficaFOsZ9EMHrPHCOZjq6jpFrgmqCwmIo--wA_OcvQ,10389
 evalvault/adapters/inbound/cli/commands/gate.py,sha256=SxBSHALhekw9OVuJcuk64tkS8YMDDsgmhMALTE38wwY,9956
 evalvault/adapters/inbound/cli/commands/generate.py,sha256=7IPvd0WAwPxt9uaxmzqWCwt0b2VC_wXiVxyJ3lP-xys,8562
-evalvault/adapters/inbound/cli/commands/history.py,sha256=P8rK_nRJrmtG3y9obq3OSYtDZGZt2o3660_9JtbSPkg,11100
+evalvault/adapters/inbound/cli/commands/history.py,sha256=3xf1l-I8IW-1Vtne9ypepDMDRRbwOpEvAjh4Qf9tV2w,8420
 evalvault/adapters/inbound/cli/commands/init.py,sha256=7q86fUeBVA08fU_N0lAV6Lakxirq4val2jIyALlDy3E,8822
 evalvault/adapters/inbound/cli/commands/kg.py,sha256=ycV9Xj6SUUJLTyTfLZcjXDVLcZqwo7Gw878ZhZAeDoc,19155
 evalvault/adapters/inbound/cli/commands/langfuse.py,sha256=aExhZ5WYT0FzJI4v1sF-a1jqy9b1BF46_HBtfiQjVGI,4085
 evalvault/adapters/inbound/cli/commands/method.py,sha256=OWdoofhvsDJchgNKnGGjXfIsZ-IHKZEo6RlmTsZRRYM,19124
+evalvault/adapters/inbound/cli/commands/ops.py,sha256=2r6hdrZ7STnWMhtzYmv8jF_ukBq4HuKB1El6YnyxwrY,4035
 evalvault/adapters/inbound/cli/commands/phoenix.py,sha256=LQi3KTLq1ybjjBuz92oQ6lYyBS3mHrCHk0qe-7bqB4U,15611
 evalvault/adapters/inbound/cli/commands/pipeline.py,sha256=NeqWLzO9kRDuZd0pHAIHglP3F7VzoNOU4JI0QcSZ120,7788
+evalvault/adapters/inbound/cli/commands/profile_difficulty.py,sha256=nOJH3iqgLAlXq4keLBj5oqpiRCg0jjGgT-7Q57HxEh8,6665
 evalvault/adapters/inbound/cli/commands/prompts.py,sha256=lddde5VbjYaqN_9gHPLNu6DWpg5fE-KqZzjN-XYwvJw,27153
+evalvault/adapters/inbound/cli/commands/regress.py,sha256=Dy8hUOdjapxOW9Hoov0DHHblkMaExiqWfYS14CaC9Kk,8806
 evalvault/adapters/inbound/cli/commands/run.py,sha256=X19rgXhajhvZNA4c0JMmzmPatTxhZgfapuW07bZL9xA,119265
 evalvault/adapters/inbound/cli/commands/run_helpers.py,sha256=hu2TioocitUZzGR7HUwZ6gOeEJSvt5tGNjwXOlo4Eic,40336
 evalvault/adapters/inbound/cli/commands/stage.py,sha256=oRC9c5CysLX90Iy5Ba1pc_00DaOBS78lcBvzkbdrGRM,17123
@@ -52,6 +58,9 @@ evalvault/adapters/inbound/mcp/__init__.py,sha256=kctJsmaP4fY94T3WCOhgANk3TCLdfb
 evalvault/adapters/inbound/mcp/schemas.py,sha256=KUKm4gEc-UDyF8sUbyzAnAIzyZ6DcXsaCEIVR3oESNQ,4469
 evalvault/adapters/inbound/mcp/tools.py,sha256=fnvkWS5p93o3FNmUSbh3EW4jCAVwtBKHX6kDuEbXkK8,24219
 evalvault/adapters/outbound/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalvault/adapters/outbound/artifact_fs.py,sha256=nySk7-10B9rQpV9EslBmRUr0gFIi9V1E_E_wdC1WpIU,439
+evalvault/adapters/outbound/judge_calibration_adapter.py,sha256=vu5dVJVo5AXa5ULcx8WE-6YgfD718BC8Ci1_HAdwy20,1155
+evalvault/adapters/outbound/judge_calibration_reporter.py,sha256=R0nId6P1jYQ3M3636knPNFztuc8kewDBKsg2LLcUw58,2005
 evalvault/adapters/outbound/analysis/__init__.py,sha256=TLuS-eKfXg97_Db5td1nTZkD3BErRLZLic1v2EAM2sA,6185
 evalvault/adapters/outbound/analysis/analysis_report_module.py,sha256=xah3wgJErHD_Hpb1YAwWRsxr8xaC8SW--CpNA7IgfxI,3957
 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
 evalvault/adapters/outbound/analysis/causal_adapter.py,sha256=Rt5QcoLDEjx8u_yidACz3u8SbAVYSJO6lLu6udwnd4U,27410
 evalvault/adapters/outbound/analysis/causal_analyzer_module.py,sha256=hBcTx7ZyUZ6HQ6I6W2VvSZ1ndatlgMen2KjKXk_Ltx4,6780
 evalvault/adapters/outbound/analysis/common.py,sha256=H1RqNBiOt7WRcHUM3jFydd3850GFQhEDUu8WBEhtMws,5734
+evalvault/adapters/outbound/analysis/comparison_pipeline_adapter.py,sha256=D_ZPVgQHz3Cn3fxxl-TgLEoo_RNbhsOJCvqH-cJ2Lf4,1577
 evalvault/adapters/outbound/analysis/comparison_report_module.py,sha256=0tTMZB5qpGMaxlcWtTtTln7Y_jFEDFaaW7V-UyboBDM,2343
 evalvault/adapters/outbound/analysis/data_loader_module.py,sha256=6X0-ZcFtEfonQnbJ0POqmHXstJ1Wq1NvpijtbKSeEm0,3749
 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
 evalvault/adapters/outbound/domain_memory/__init__.py,sha256=ksMX1IkNiDqQHLtJe9TOXiLC1iouGt6_QSdPLiALHHs,229
 evalvault/adapters/outbound/domain_memory/domain_memory_schema.sql,sha256=APlNhJNFZdcm7Sb2tvr7V8JMiLinmXkx1gd6pgTf9ZI,11268
 evalvault/adapters/outbound/domain_memory/sqlite_adapter.py,sha256=RWobnFgvxiItxFAr6niY89sT19O-cnExTbP0I7UAY78,85186
+evalvault/adapters/outbound/filesystem/__init__.py,sha256=eTQLuVPMpEctE92TtegKQT3wuJTIhiBS38BzfxRV-N0,122
+evalvault/adapters/outbound/filesystem/difficulty_profile_writer.py,sha256=9qO9_3E-SL6ngDOia6zcw680S1fQloxo32f6hx76YHs,1626
+evalvault/adapters/outbound/filesystem/ops_snapshot_writer.py,sha256=sOuUk8VD8yWwG8508uw1zqSnNsp3dQrF9bp9T2z-n48,448
 evalvault/adapters/outbound/improvement/__init__.py,sha256=tXA6vaZOLvqwJpyjGMiC8WrvszMmvUPzJnHjvJhQxSI,1143
 evalvault/adapters/outbound/improvement/insight_generator.py,sha256=U16l0euCZy0_08Zb_i0eijXSjS5t-iq0iMUfttwPqgI,17636
 evalvault/adapters/outbound/improvement/pattern_detector.py,sha256=uFFjWNy8A4KIihw_ANtL6At73RirwNnFnN4rFsEvcXk,24602
@@ -148,7 +161,7 @@ evalvault/adapters/outbound/llm/token_aware_chat.py,sha256=yYmynaniNrYxtvXL6ejTE
 evalvault/adapters/outbound/llm/vllm_adapter.py,sha256=OKb3Nda9OLMmHdvLjvkeJcQVeXf-B8TDibmAs7PS7kg,5157
 evalvault/adapters/outbound/methods/__init__.py,sha256=3vyE9w3Ex2oMaO4ZE7Fy6xlHhJ6YQXHQNCvBiW9X2lM,345
 evalvault/adapters/outbound/methods/baseline_oracle.py,sha256=oUsF5sIiPY5vuDtrz0Ki05SnPlnVzn7APERP5v1KpPM,1308
-evalvault/adapters/outbound/methods/external_command.py,sha256=gR2mlgr-SCAO3cS3I7pYgS8hL8JE8Y-0VZIhg7USazY,5287
+evalvault/adapters/outbound/methods/external_command.py,sha256=hsWaqMG0u2JhsS736n0t8sobrGSJMNNp1tUL_M4zgyg,6118
 evalvault/adapters/outbound/methods/registry.py,sha256=Znd35eouoe8k2E0NfDpVlDBSNAAWmyQkqBhAwVWllGI,7635
 evalvault/adapters/outbound/nlp/__init__.py,sha256=9MQMIjEUU03T0ZZtG-Wjz0Bt2-esGEcfv1kT9W6_CBY,40
 evalvault/adapters/outbound/nlp/korean/__init__.py,sha256=3ZVFHDxS6jzXat-WhTvW3hnbGNaeFhhWVVN1TtEOlnE,2267
@@ -180,9 +193,10 @@ evalvault/adapters/outbound/tracer/open_rag_trace_decorators.py,sha256=LFnk-3FSL
 evalvault/adapters/outbound/tracer/open_rag_trace_helpers.py,sha256=D48Mbj-ioDKztjhV9513Q5DiUNiVdO60B_2sWMFEmnI,3520
 evalvault/adapters/outbound/tracer/phoenix_tracer_adapter.py,sha256=inmTAolAVsm0IrszE9VTJoI7HSvGGAnGNZVu_vZRAGg,741
 evalvault/adapters/outbound/tracker/__init__.py,sha256=Suu5BznOK5uTuD5_jS8JMZd8RPfQNlddLxHCBvMTm_4,358
-evalvault/adapters/outbound/tracker/langfuse_adapter.py,sha256=Gejd3fOBwShfjbtjVcZK9sCJKRz6oB3OaN6KukOYN38,17782
-evalvault/adapters/outbound/tracker/mlflow_adapter.py,sha256=Wee1S7OPemPt5SoIdwBHuBdnXmLxNd3lcgQ9NNMKcDQ,7000
-evalvault/adapters/outbound/tracker/phoenix_adapter.py,sha256=TNGU1RqpWwEEw5uQfx7-ClAh4C7wITwu_-X-fyVsCgc,22888
+evalvault/adapters/outbound/tracker/langfuse_adapter.py,sha256=oi6bnz2qjDSXEea_bACFRUEKk-tKw53d1xMfL4FE5dI,18749
+evalvault/adapters/outbound/tracker/log_sanitizer.py,sha256=ilKTTSzsHslQYc-elnWu0Z3HKNNw1D1iI0_cCvYbo1M,2653
+evalvault/adapters/outbound/tracker/mlflow_adapter.py,sha256=m4xj3XBULFYg27U3twKrldLhbLyLNefezmb2pCpHJrw,7180
+evalvault/adapters/outbound/tracker/phoenix_adapter.py,sha256=VmGkVuBX5Nae6zTaaSbpcA94spFJGmwjW0gOh2vIxnk,25332
 evalvault/config/__init__.py,sha256=UCgeDx62M2gOuFvdN29wWwny2fdH4bPY_uUC3-42eDw,1297
 evalvault/config/agent_types.py,sha256=EP2Pv3ZtOzDXIvIa-Hnd1to9JIbMUtGitrlwzZtx0Ys,13418
 evalvault/config/domain_config.py,sha256=rOgNA2T8NWlDzcEFC0shdUCCww0lI1E5fUm5QrKQSZI,9264
@@ -190,10 +204,11 @@ evalvault/config/instrumentation.py,sha256=L8on9HjB6Ji8cSOJ6Pepsopfg9okDNMWF7LKZ
 evalvault/config/langfuse_support.py,sha256=DEzVMfMGGf1V45W_2oUG-NCDfsYI4UUdnYJIgBSrN2o,582
 evalvault/config/model_config.py,sha256=KlzDbGyDLeOGE7ElekFFk5YjjT5u8i6KO2B4EyZkLnI,3542
 evalvault/config/phoenix_support.py,sha256=e6RPWd6Qb7KU6Q8pLaYTpJGWULtvEEU6B0xHWyVyOH0,13604
-evalvault/config/settings.py,sha256=T92GShlYKDaVinwbsbWX2DmNfm91Cvcvh8Te8pNOTsw,12875
+evalvault/config/secret_manager.py,sha256=YjPMuNqeBrAR2BzCJvsBNUExaU4TBSFyZ8kVYZZifqA,4172
+evalvault/config/settings.py,sha256=JKJf8t20sOHYnHoCfTxqupQixNgfmWYJhChiGMNz-W0,17617
 evalvault/config/playbooks/improvement_playbook.yaml,sha256=9F9WVVCydFfz6zUuGYzZ4PKdW1LLtcBKVF36T7xT764,26965
 evalvault/domain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalvault/domain/entities/__init__.py,sha256=RZi_6oQcq-2-sJcydfKOSr03vFxo-mF7CGHN9Ma4Cdg,3379
+evalvault/domain/entities/__init__.py,sha256=wszRJ1Imdc5NJ1bQPC2udk-mAgFdlw4uZV5IPNjLpHQ,3669
 evalvault/domain/entities/analysis.py,sha256=gcMtumC66g-AIqb2LgfMpm5BMzwJhJkjg-zuybNoJCM,15208
 evalvault/domain/entities/analysis_pipeline.py,sha256=hD9rFHMa4rUq0InRkSKhh6HQ9ZeNYAHKADzs-kWRP04,16845
 evalvault/domain/entities/benchmark.py,sha256=CVbz_eW7Y9eM7wG7xA_xmldTIs72csdoTmu3E0NKoMU,18475
@@ -203,6 +218,7 @@ evalvault/domain/entities/debug.py,sha256=r92lgvOpq2svw70syJIo78muRAvrSn5h1JByH_
 evalvault/domain/entities/experiment.py,sha256=oWjbu0IJZ6oIRcnA-8ppeJDgp57Tv8ZjQ3UOZ0X9KJ8,2576
 evalvault/domain/entities/feedback.py,sha256=xiaZaUQhyuxyW_i2scXt8eKZshMC6tXe3981e-uukw8,1604
 evalvault/domain/entities/improvement.py,sha256=WHI7q1jXRxkuHhBWOrpk8UdLaH0UwjZVjRIDsqVDyZo,19322
+evalvault/domain/entities/judge_calibration.py,sha256=fhQEI7g2nZuG1OliikhxgefcFAJldDqEmfTs9Mp-FPk,1234
 evalvault/domain/entities/kg.py,sha256=8awN1M4vxAGQZk_ZG8i2CXKTizQ8FA1VCLhUWHZq0U8,3001
 evalvault/domain/entities/memory.py,sha256=bfS75q8K8_jNrB7IYh4mjP8Lkyj-I0TVsmHCP0FuICw,8423
 evalvault/domain/entities/method.py,sha256=a3jZi7SjcpK3HeVyVwQkUMwpnmg2RbxCnH4NqYPLCOI,1157
@@ -210,7 +226,7 @@ evalvault/domain/entities/prompt.py,sha256=VzuUzqkqXv0FwTSNGyV5sSCft5sxTbG_Noq6Y
 evalvault/domain/entities/prompt_suggestion.py,sha256=Ep_XSjdYUj7pFSCMyeeZKs8yTnp74AVx05Zqr7829PE,1243
 evalvault/domain/entities/rag_trace.py,sha256=sZgnkG4fK6KOe3Np6TYAZ_tPnsRbOmucDSQns35U1n4,11868
 evalvault/domain/entities/result.py,sha256=OaGHMDLWMW2O4fNVuVTUvWFVBQ1iu93OD_oI3NumrCQ,10697
-evalvault/domain/entities/stage.py,sha256=dbVzhgpP_p2p2eDJBWe7mwyyl6zUTP9kEKN_YRUvufY,7183
+evalvault/domain/entities/stage.py,sha256=UqS59sjoMs_bhMupNtvagbIx8QgHgFjWoRPhJ3uJP2s,7426
 evalvault/domain/metrics/__init__.py,sha256=fxjC5Z_8OuBIeMn80bYgnZZxpNoay2wH-qtG3NqCUvk,797
 evalvault/domain/metrics/analysis_registry.py,sha256=JZpBrBs7-JExHKYuEML6Vg_uYLm-WniBE3BfiU5OtJg,7641
 evalvault/domain/metrics/confidence.py,sha256=AX4oeN28OvmMkwD0pT-jskkOlXh87C1pe2W9P1sF69g,17224
@@ -224,21 +240,24 @@ evalvault/domain/metrics/terms_dictionary.json,sha256=-ZQmpx6yMOYoAOpcLj-xK2LkAe
 evalvault/domain/metrics/text_match.py,sha256=P-YTZs9ekDqEmxLNBP8eXnMRymPdC8V4dJPtwG2ajVM,10219
 evalvault/domain/services/__init__.py,sha256=X5Af1kf_vSt3S3mFwOV6OQdro-lFxwbVdNd7nJznkC8,1024
 evalvault/domain/services/analysis_service.py,sha256=oUEtfJHB3bNJ_Ksygx-pjnLm4CTk7_rDvDbqfkAfFD4,10838
+evalvault/domain/services/artifact_lint_service.py,sha256=80P46weoj9lBxOqg_ViHZEQ6Cfo69XV4cniZlmMsti0,8434
 evalvault/domain/services/async_batch_executor.py,sha256=qYFRl7CGmv56XppeRhInde7Fw0GESCoZh8V-Iv_1hQQ,11140
 evalvault/domain/services/batch_executor.py,sha256=cYA_Q1es46n_PYeyyfm0iM2b7GGVtDoOGoMxexrf6tI,1243
 evalvault/domain/services/benchmark_report_service.py,sha256=IF-zqtvpsJ0ONJWUEw4ghKiC7ka_PWxUBO10lPaDRmI,15083
-evalvault/domain/services/benchmark_runner.py,sha256=iqirGDs-yemSmqLDnCPGA7Wug0ps6z0vRgRsgetypOM,26328
+evalvault/domain/services/benchmark_runner.py,sha256=4tvQEDrfvp2fC2luUPuPBcRjEPLHdrdystLpe3PnBqM,26046
 evalvault/domain/services/benchmark_service.py,sha256=TrmnvBMAPmcs0PewGZcn2rxHbviZ8KxmDvJCeyqm28I,6286
 evalvault/domain/services/cache_metrics.py,sha256=FKNZoxym30lc1SxTGmTn3Pr-PDNoAqgC9_d_IdF_jOQ,3463
 evalvault/domain/services/cluster_map_builder.py,sha256=qPKMPj-eSqECJSCOKvv3ZETgIwxwiKWbU3d6_feCoDg,6885
-evalvault/domain/services/dataset_preprocessor.py,sha256=v-shY5ky1oW0LJwBfdfP4VFh7TXBabpLD5rMOmtS-dQ,14235
+evalvault/domain/services/dataset_preprocessor.py,sha256=PnhLiPk0E9DIzjUr8N75296CCfl1AUXGv-lpaXBi0Ok,14797
 evalvault/domain/services/debug_report_service.py,sha256=SGdFh8tctAIq7RotFbg47eetxdYSS4Yju7-LOzpCMCM,4386
+evalvault/domain/services/difficulty_profile_reporter.py,sha256=uIj9-eiO2dDvQ6tP-DJBddfBq8VT63st0wtNC8Co4NQ,680
+evalvault/domain/services/difficulty_profiling_service.py,sha256=wB3T2iz_dZjvj7wiU2fnM0XT-doMNokV_YqSt24Wc6A,11078
 evalvault/domain/services/document_chunker.py,sha256=u05N1xSBcJuJPUfP7WmpY_EyHuUMuGMsPSM9qs-ID8c,2494
 evalvault/domain/services/document_versioning.py,sha256=M1qZaMpQ2exVT1wkVAmvEPPuoYibJDt0F7pYfTK7mvE,3323
 evalvault/domain/services/domain_learning_hook.py,sha256=rhKBmdnrJyfGzFNsNxzyv8jZO26-WOosHSmBV_9qdJg,7176
 evalvault/domain/services/embedding_overlay.py,sha256=ZTNxUPXpHGbQ3Uri5DD3feTUFn7qrhuNshhyCQEvRuM,3559
 evalvault/domain/services/entity_extractor.py,sha256=f3Rf5saK8QsgetLNK1Hbxzt8PtttJZCicSR63S8DJ5k,14141
-evalvault/domain/services/evaluator.py,sha256=YReil1mokTILyllAbG_QnFhob-15G5tNeWZZMbSc3yo,67551
+evalvault/domain/services/evaluator.py,sha256=cKcPRoqkUFc00lgx_blbIFl0qJyPIDjPeCciWAPm7m8,67669
 evalvault/domain/services/experiment_comparator.py,sha256=IBrxIwux-8GucwlLx6e5lUqB9miSPvBLGJK9ctoW7Y0,3299
 evalvault/domain/services/experiment_manager.py,sha256=2k-qGiAUyZuqqmcp4P-M3Z9HTXwwcqW5HQYKNkcIHuI,4863
 evalvault/domain/services/experiment_reporter.py,sha256=QYlVmCFSx8hKTPMezc7QjJE07b3MSQ82Q4QVucSHLVY,1420
@@ -247,10 +266,12 @@ evalvault/domain/services/experiment_statistics.py,sha256=aOrqbBjB1swHPaFRziID1m
 evalvault/domain/services/holdout_splitter.py,sha256=Sos61Zy_bBjStt8LPHJ3KxDNda-OmX7AVUsT24K1n6Q,1910
 evalvault/domain/services/improvement_guide_service.py,sha256=gMoVFlDsprOEEfRGKmdbk9_Due62J63Q-rL2zr65Q0s,17881
 evalvault/domain/services/intent_classifier.py,sha256=hsWivDXqXJjCJEE-OI7eUGeYrewpYxlz67Z0TI3oskU,11707
+evalvault/domain/services/judge_calibration_service.py,sha256=cOaAsbfMBlaDxoMAXe8MacDDRK0tCD-tXRnYjB6sEPs,19264
 evalvault/domain/services/kg_generator.py,sha256=oEugjPdn8Pb2Q3r5yAZl0dZJibNUkEherlRVquknB6k,24969
 evalvault/domain/services/memory_aware_evaluator.py,sha256=vTiYoxiMfZ_CMjSBjqwkBRdpiXRwQ2zXnQ2pXzVHYts,5249
 evalvault/domain/services/memory_based_analysis.py,sha256=oh2irCy3le7fWiTtL31SMEhPyu7fyBVz-giO2hlNifE,4499
 evalvault/domain/services/method_runner.py,sha256=pABqKZeaALpWZYDfzAbd-VOZt2djQggRNIPuuPQeUSw,3571
+evalvault/domain/services/ops_snapshot_service.py,sha256=1CqJN2p3tM6SgzLCZKcVEM213fd1cDGexTRPG_3e59w,5138
 evalvault/domain/services/pipeline_orchestrator.py,sha256=yriVlEVZYDtt0Vwt4Ae6xyW1H6Dj4Hxdn8XQSvQNSoQ,19436
 evalvault/domain/services/pipeline_template_registry.py,sha256=aWqXLQ24grpSZo9M4tZLRo1ysD10c6hUpW3JupZH9e0,28083
 evalvault/domain/services/prompt_candidate_service.py,sha256=Ibyb5EaWK28Ju2HnTqHHGOoiA9Q-VwY3hjxVODALwGY,3997
@@ -260,12 +281,14 @@ evalvault/domain/services/prompt_scoring_service.py,sha256=SlvfuIbhj92RJu4RQAJ1B
 evalvault/domain/services/prompt_status.py,sha256=r1dFLGz4SfRxXaxsULQsr0-HpJkG9YfZ_yLIxF1MMBo,6731
 evalvault/domain/services/prompt_suggestion_reporter.py,sha256=Fc6sCPebUMk8SZVpjoJ6bCEun0ma-YmayEQnulBVv8s,10577
 evalvault/domain/services/ragas_prompt_overrides.py,sha256=4BecYE2KrreUBbIM3ssP9WzHcK_wRc8jW7CE_k58QOU,1412
+evalvault/domain/services/regression_gate_service.py,sha256=qBMODgpizmEzqEL8_JX-FYSVyARiroMW7MFVzlz7gjc,6579
 evalvault/domain/services/retrieval_metrics.py,sha256=dtrQPLMrXSyWLcgF8EGcLNFwzwA59WDzEh41JRToHAY,2980
 evalvault/domain/services/retriever_context.py,sha256=ySQ-GuadiggS0LVAib4AxA_0JpasYz4S9hbjau0eyIA,6482
+evalvault/domain/services/run_comparison_service.py,sha256=_NScltCRcY3zrvdyYDiPmssTxCDv1GyjCLdP3uAxJts,5631
 evalvault/domain/services/satisfaction_calibration_service.py,sha256=H7Z8opOyPHRO5qVIw-XDsNhIwdCteAS9_a3BTlfIqHg,11906
-evalvault/domain/services/stage_event_builder.py,sha256=ScTgyeRiH7z_rnNI_2p-i9szVRIRwUxGSJvpEj3zto4,9645
+evalvault/domain/services/stage_event_builder.py,sha256=FAT34Wmylvd2Yz5rDlhaTh1lqSCDhGApCXMi7Hjkib0,9748
 evalvault/domain/services/stage_metric_guide_service.py,sha256=_JdRsBRWirO24qYFlh6hG-dkoWlX6_XWEYKf_uUlKIQ,8807
-evalvault/domain/services/stage_metric_service.py,sha256=KukIWWhWVOtclrET6uyWJ17jG76LfkKiqrUrDIDJ3gw,15327
+evalvault/domain/services/stage_metric_service.py,sha256=_u6ThZ8rGw8H9h3TNpu0j8XhpIfukHSoyc1ZpCa3Z00,18031
 evalvault/domain/services/stage_summary_service.py,sha256=VVtuAr4vwzvmNFn8rqURJrhKFqAMG4CaBmyGiUk_xG0,1590
 evalvault/domain/services/synthetic_qa_generator.py,sha256=aiOTPoHZbKRTEeodABQ2I5lq8-Vs_kQtuzcGWd4MTGE,16526
 evalvault/domain/services/testset_generator.py,sha256=6IpiZ0pqhKEymo-AlUdfJjDkF2P1n8Md_QKV4nOheyg,4470
@@ -278,22 +301,27 @@ evalvault/ports/inbound/analysis_pipeline_port.py,sha256=RJfKtp22AYEqnmRk6RDawAK
 evalvault/ports/inbound/evaluator_port.py,sha256=rDvouIRUjBD7uICgrpeo11vNPvo27_0CdylRHPodPSE,1323
 evalvault/ports/inbound/learning_hook_port.py,sha256=EeJeMl3chcPHlj5mkLOj6tm8s_qdDRvoCwK1-0l70tI,3297
 evalvault/ports/inbound/web_port.py,sha256=b4uMhwOMLXy3LeILc7ZK3RR-XtoW4p4NzoTpj4syptg,5578
-evalvault/ports/outbound/__init__.py,sha256=0uPE6CXkoK6ECs3O4OZYAmVg5VAAHoF5rdb1eoj1NAc,3367
+evalvault/ports/outbound/__init__.py,sha256=x3LseXtwX0NONM1mnhT3fMchz7U6gEDRUX0TDswpg5E,3591
 evalvault/ports/outbound/analysis_cache_port.py,sha256=zPSdUVK_yw3PMWPII2YvS1WLmCGlg5bDScSuYINW9yc,1386
 evalvault/ports/outbound/analysis_module_port.py,sha256=QYzkvie9-BbONj8ZgiQUjm8I-bn8mgzlXTzIXMhehmQ,1881
 evalvault/ports/outbound/analysis_port.py,sha256=gE-iXToTgdQomj9JwNZJY4nwut8q0J6EurUmJNsnptQ,2127
+evalvault/ports/outbound/artifact_fs_port.py,sha256=SN966vwHiIjLA06MBWePr7V0NmafbiQbSLFlXAN3YKU,273
 evalvault/ports/outbound/benchmark_port.py,sha256=pgo3rNbvvJS8x03UxBVQPBBgxc7X5kfG70ZlIf3sopE,7173
 evalvault/ports/outbound/causal_analysis_port.py,sha256=IsyVdFrs66mHcOc-_VbxrZQriwMrDxx-5a_4ElX5Bp0,941
+evalvault/ports/outbound/comparison_pipeline_port.py,sha256=IOLK6vZdzjSV6Qcvkl9GD-wRxx6Waa3dsYOCFdD1mXY,503
 evalvault/ports/outbound/dataset_port.py,sha256=OpEBlkvFwpSRbmi-Lt3wK7n0wljmQ6m985mjyNn_qFk,990
+evalvault/ports/outbound/difficulty_profile_port.py,sha256=hQY-TR64WyUNnCxD9Mw-QraO3ZBw0VUP8KoCmVsQYBE,347
 evalvault/ports/outbound/domain_memory_port.py,sha256=SZFurqsoBmTw1Kt_pej-YpMbooVeyV35jekhaDRojus,23320
 evalvault/ports/outbound/embedding_port.py,sha256=ZHeKRMRBNjpZKWxsLKrD8jJz0M66JTwNcrJbkRaklK4,2034
 evalvault/ports/outbound/improvement_port.py,sha256=fIXhcG4n6OJ1hdvWeqEoLBrVsCNdHZRgtEZjR8lf3qA,2325
 evalvault/ports/outbound/intent_classifier_port.py,sha256=gqMIk0rH6Z43ceuMMRX4vqXurgHZz-CJX2bR5PVAkjQ,2253
+evalvault/ports/outbound/judge_calibration_port.py,sha256=kShZ2MZGvgQZaY7XxwkmLXtquK_RFKcwuWRBfJOrILA,602
 evalvault/ports/outbound/korean_nlp_port.py,sha256=mJCnxBAkV8a5Nd_VX6QcjfDucY62er8GlaNO4HQA8q8,1572
 evalvault/ports/outbound/llm_factory_port.py,sha256=lzoDJi6A6ltk-t3N4oY8DSwMBMfnvXGgSduILOpzoas,305
 evalvault/ports/outbound/llm_port.py,sha256=YAW0i-41yT8KzMuzZGEO5yPDkHN0onGxj55eL0cdPHY,4393
 evalvault/ports/outbound/method_port.py,sha256=sntcKgwagAdJGxp0dI-S_bhBQcOW9QpnND3fOjrsX9E,1377
 evalvault/ports/outbound/nlp_analysis_port.py,sha256=QDJHAsSpynTenuaKp78t1s--U036mtYeUEX0p5vQw24,3046
+evalvault/ports/outbound/ops_snapshot_port.py,sha256=6v72W41tlnxjkJfbfHhFiJMPlRSAQ-BvrI2T09_yddk,214
 evalvault/ports/outbound/relation_augmenter_port.py,sha256=cMcHQnmK111WzZr50vYr7affeHhOtpFZxPARwkg9xbk,651
 evalvault/ports/outbound/report_port.py,sha256=wgReSYL4SupXIoALFh0QFWfX2kzPftXpWTvGLCMd2B8,1315
 evalvault/ports/outbound/stage_storage_port.py,sha256=Nlf9upsXxgCABQB5cJdpLQYsoZNiGRAU5zE5D-Ptp2I,1201
@@ -304,8 +332,8 @@ evalvault/reports/__init__.py,sha256=Bb1X4871msAN8I6PM6nKGED3psPwZt88hXZBAOdH06Y
 evalvault/reports/release_notes.py,sha256=pZj0PBFT-4F_Ty-Kv5P69BuoOnmTCn4kznDcORFJd0w,4011
 evalvault/scripts/__init__.py,sha256=NwEeIFQbkX4ml2R_PhtIoNtArDSX_suuoymgG_7Kwso,89
 evalvault/scripts/regression_runner.py,sha256=SxZori5BZ8jVQ057Mf5V5FPgIVDccrV5oRONmnhuk8w,8438
-evalvault-1.63.1.dist-info/METADATA,sha256=wkxUE5VIFBr2zmdSpRtcGs8Xwbry3ydY7U2XJFEEzjo,23879
-evalvault-1.63.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-evalvault-1.63.1.dist-info/entry_points.txt,sha256=Oj9Xc5gYcyUYYNmQfWI8NYGw7nN-3M-h2ipHIMlVn6o,65
-evalvault-1.63.1.dist-info/licenses/LICENSE.md,sha256=3RNWY4jjtrQ_yYa-D-7I3XO12Ti7YzxsLV_dpykujvo,11358
-evalvault-1.63.1.dist-info/RECORD,,
+evalvault-1.65.0.dist-info/METADATA,sha256=1f23dU3LtSQwrlalym1j8mH-vZaM7HWMzDh-ByjVOjo,24276
+evalvault-1.65.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+evalvault-1.65.0.dist-info/entry_points.txt,sha256=Oj9Xc5gYcyUYYNmQfWI8NYGw7nN-3M-h2ipHIMlVn6o,65
+evalvault-1.65.0.dist-info/licenses/LICENSE.md,sha256=3RNWY4jjtrQ_yYa-D-7I3XO12Ti7YzxsLV_dpykujvo,11358
+evalvault-1.65.0.dist-info/RECORD,,