openadapt-ml 0.1.0__py3-none-any.whl → 0.2.1__py3-none-any.whl

openadapt_ml-0.2.1.dist-info/RECORD

@@ -0,0 +1,116 @@
+openadapt_ml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+openadapt_ml/config.py,sha256=eH5WTKRPkkidjkNb25Wn_dUAizUQTsVPMYLDq_ekPJQ,1865
+openadapt_ml/baselines/__init__.py,sha256=psXRe8N-TTum0Io09miXQdPx4wxEFnmqjbamK6M-KaE,3137
+openadapt_ml/baselines/adapter.py,sha256=sfJuHfrr-o2jWwFEBKyujXvhzbZ9jHeO92CcqcQIysM,5975
+openadapt_ml/baselines/cli.py,sha256=T0LN2XcJcL-YingNxLoU3LCjDsjIoGyjFPX3xdPmfY4,7868
+openadapt_ml/baselines/config.py,sha256=R2mf-H687l6njQK4Ugyr7QMwjlk5vfUhgvsFDtW4ljY,14085
+openadapt_ml/baselines/parser.py,sha256=xMRFoqXdOYvO0bV92vGoUJ1Jewv_HzTcIjBg97SALb4,31191
+openadapt_ml/baselines/prompts.py,sha256=w7N2jrfmf-FYHfuv1vGT7QtXMF1Ahuy3uAsfjPoo6Ho,24453
+openadapt_ml/benchmarks/__init__.py,sha256=FaEGc7pRM-eLUXEEpJXcIckwkIWKhfaDkaxGM9VC4Os,877
+openadapt_ml/benchmarks/agent.py,sha256=8UcS9skCy6l18fGYaYt0JzJmYSGNB_WxDWhApbM7QH0,26940
+openadapt_ml/benchmarks/azure.py,sha256=dCrxi90X5NmFNMTT-2WG4AF3-IOO4zQs7yPpnqR-jLc,28238
+openadapt_ml/benchmarks/azure_ops_tracker.py,sha256=NOW21LPagOWIThSCIotI5cBvve92dtIktRIDLuyJ2CI,19309
+openadapt_ml/benchmarks/cli.py,sha256=t4cIGN68GdphCX0AGkWJa_M6D4oUO_M0rfJDzD_POGA,62730
+openadapt_ml/benchmarks/trace_export.py,sha256=Zx-pryEuLe734YHY8MgJsNdj3I3TcTY61OQ9iurgGB0,21746
+openadapt_ml/benchmarks/viewer.py,sha256=Jztt_IoDW1u0WjPqlikfR8dunYzj66xCx0bMDDzJHQ8,41586
+openadapt_ml/benchmarks/vm_monitor.py,sha256=FzmRrzqm0sZTcydfqMtRefBLfTr4fjoyWCxdHLovUj0,35733
+openadapt_ml/benchmarks/waa_deploy/Dockerfile,sha256=F4GzVUoAUHvGlTFj-gGIPSlncG-JIz1_JyeaHvTnLpA,10853
+openadapt_ml/benchmarks/waa_deploy/__init__.py,sha256=KV71HrrgETytfY0i4vFSi-yM0KjoQP2hd9Bl03cZ9yc,320
+openadapt_ml/benchmarks/waa_deploy/api_agent.py,sha256=A5ZFhtBTKz0Q1GarNV51JhkEJwAgJfm9tK4CTJ1UEnE,20040
+openadapt_ml/benchmarks/waa_deploy/start_waa_server.bat,sha256=YxgrSWh76zLijlpxEpulWf9To2JtJ-yR42lr2WyTXiY,1496
+openadapt_ml/cloud/__init__.py,sha256=XYrvxivJeZ8qYnuGod5kodMlm3iT2OK2GAApO3CNB0c,133
+openadapt_ml/cloud/azure_inference.py,sha256=2EQ9fCGJA2hzH7mEcSXVK1U2mO4PwBrQHxUCsGCDJVM,15696
+openadapt_ml/cloud/lambda_labs.py,sha256=NGjVHjpY2nO8F9dHHFi_CVjY1nAwk5kOiguOSSYZkCw,107872
+openadapt_ml/cloud/local.py,sha256=s3grqrpTkcT73tIoDt-HJonoCRwx0zBL7M8vSNYL3nU,166047
+openadapt_ml/cloud/ssh_tunnel.py,sha256=PTcyl9cDmbszTJbOD2MAj21AWXqoJt-2Iz26HAPdxRE,21740
+openadapt_ml/datasets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+openadapt_ml/datasets/next_action.py,sha256=2u1fRtOQzYdWZ6N_ebmOtPqWL9LnDun5STGuLmkcxrE,21252
+openadapt_ml/evals/__init__.py,sha256=Kx7bSvPHwmoGVI3q1wS_lC17W2S32YHj0459JRqu6Ow,573
+openadapt_ml/evals/grounding.py,sha256=tqjNWdinbj190vt_mPdc_w452z0AwgR81FDhkmKjDvs,8542
+openadapt_ml/evals/plot_eval_metrics.py,sha256=GO-zhYpUJijb4Hp6fI-8lBR3TgjIDpCaOC4iQ-v9VO0,5259
+openadapt_ml/evals/trajectory_matching.py,sha256=eiWPjMZAAWFmdDwQHVM689I98Kw5ensnAJrfEo_QZZ4,20764
+openadapt_ml/experiments/demo_prompt/__init__.py,sha256=dwS0bI53jXMzHE-DPhb_mhmPdoqSZRIcNbV79wt8KPM,454
+openadapt_ml/experiments/demo_prompt/format_demo.py,sha256=baXgqR-oJG9_hanlDPcPYKdMFLw2KSxJ5ERvl3FAwZ8,6691
+openadapt_ml/experiments/demo_prompt/run_experiment.py,sha256=q_8k6WJeR50vrhS_jPmx_TkbPsk1OrTkwUrRkT_PqLM,16574
+openadapt_ml/experiments/demo_prompt/results/experiment_20251231_002125.json,sha256=08oryOF126toTQDN9xciodavvfsaWNnXuBs0aULwpfI,5326
+openadapt_ml/experiments/demo_prompt/results/experiment_n30_20251231_165958.json,sha256=u03VgYTQia_HzilzNjxdGLpUSdbo4SzmHqI-GXlvurg,26915
+openadapt_ml/experiments/demo_prompt/results/multistep_20251231_025051.json,sha256=FA1JgXXLor6on3lHlfJdNSuKzBca30ggH8IWSJEmmfA,11517
+openadapt_ml/experiments/representation_shootout/__init__.py,sha256=flQ8VdNGZ-Nc5sDofSPpGh65O9Iytwk-9DsOVmTMcHE,1874
+openadapt_ml/experiments/representation_shootout/conditions.py,sha256=77AUh2U1t1ZGTHNLoLUO0WDp_17hLp3uZMUkTb2JYow,22866
+openadapt_ml/experiments/representation_shootout/config.py,sha256=df29SNCSPYXsUK2aYQhvRpb9DtmKtoGmCDlp1rWafZU,13043
+openadapt_ml/experiments/representation_shootout/evaluator.py,sha256=ijza5ky-r0CVBfw-amyztX_122N5ZRZsy_rCzMWLELw,22947
+openadapt_ml/experiments/representation_shootout/runner.py,sha256=gvZkq3Opl_6i5pjc-danV-Q7PLLBdwMmnrwVxQ5fNlI,23413
+openadapt_ml/experiments/waa_demo/__init__.py,sha256=9M8iLxO9GWAw-FIB-0tzsqaweLcO5EVP1Sc5BoK16iU,363
+openadapt_ml/experiments/waa_demo/demos.py,sha256=UwO0EYy8wUEggaBaI_cXuYe_jwSB1hx3ZtPf-z9bhjc,13796
+openadapt_ml/experiments/waa_demo/runner.py,sha256=qe0iP6bvI65-FPpw6--yGZ83ASKKtTGlEL7EoO24MiM,24399
+openadapt_ml/experiments/waa_demo/tasks.py,sha256=jw1QwbOt8xmWBW2lmBWcJzKBXssjv_e0j49MlC2rVJY,5425
+openadapt_ml/export/__init__.py,sha256=mKehKHOio4jGcK-3r0-pb446GdKMPs0O9hAu4S0_R7s,266
+openadapt_ml/export/__main__.py,sha256=0ObtWcdzf6p7gPwhNlCKpNm2FIhmusdYNkuk8tyt77U,149
+openadapt_ml/export/cli.py,sha256=goTKNq9cOO9wsdNluLMH_-f9kdWShH3FPP8sCZ6KaPI,2331
+openadapt_ml/export/parquet.py,sha256=oQfyRAhUUS-EpiOWa7S7s8HaHibhfTSoNPYfKb2HDrA,9897
+openadapt_ml/grounding/__init__.py,sha256=uMvcALFRXmKD6PHhqLZ24Y6zhRUs46_PnWYqiqJP5cM,1412
+openadapt_ml/grounding/base.py,sha256=mnjT25nxltZCD0VBzgIgj2kuCcB4sgXBN97MBaW5P6c,7688
+openadapt_ml/grounding/detector.py,sha256=gu-clpHfHNsbeeVwuM54yxF23lAUPThOZStnOdq8-Es,19890
+openadapt_ml/ingest/__init__.py,sha256=P1Z9-rEBZC8wviMlmu6Fgc-R_83Ku7scVDs5YRejMVE,1481
+openadapt_ml/ingest/capture.py,sha256=hiUTbvGGF90KMUNof-z58azywNcHi-xJxQwHYIRb_4Q,10342
+openadapt_ml/ingest/loader.py,sha256=T3gE4EP-SYXmpeOFCK-VCku1lvzfa6AbPJ5hMBDdAVc,9866
+openadapt_ml/ingest/synthetic.py,sha256=ZX3eoMS08fpCFas07kYKUIMb7Bkp1zsaI9Bnuhis-I8,40482
+openadapt_ml/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+openadapt_ml/models/api_adapter.py,sha256=G7S847hmYl6AQ8_4oTP5aMV4YhYBN_k-Sj3RVo1w9Bs,6679
+openadapt_ml/models/base_adapter.py,sha256=vvasd-WhFxQNc2utqnXC_YMHABouXXNF4SwK9CUxpOc,2113
+openadapt_ml/models/dummy_adapter.py,sha256=h4Zu-rjWgtG1r8jRtcsrX-FZm8iImrhrTQ7TsLfjE8A,1581
+openadapt_ml/models/qwen_vl.py,sha256=0QcYqTraUMzT6W6No5aomeat9aUxpRqHai9aCX9-6dM,17652
+openadapt_ml/models/providers/__init__.py,sha256=SBd4ZDSi3tYf7DBxTUOFw66Qr15idjuk45TM0bGAKOQ,8216
+openadapt_ml/models/providers/anthropic.py,sha256=iUZceqn4yrD0s0FlMhgcENze4_AgJJ5u8du_1Ke7qy8,8348
+openadapt_ml/models/providers/base.py,sha256=iGVEYSdzP9w3WRE7LM_vbG9ESXWKoJ5qSLx-ZB2ZcOw,8178
+openadapt_ml/models/providers/google.py,sha256=OGXTaQwWonPy-3kLrBC8wLgIQytPtPDQiDkVqsUf70Y,12081
+openadapt_ml/models/providers/openai.py,sha256=1LJJoWxkVNouowebs_N7iI4i8iSCHAjKvPOSAovC3p0,10487
+openadapt_ml/perception/__init__.py,sha256=goR5qA_O7jvO8-gK5XPwib9TsqYfWIbljcmXao8mzRw,847
+openadapt_ml/perception/integration.py,sha256=F9X4ysYn2RdFN6Wh3rXt5kl-cq0tf_6KdFViz2lAAnA,13296
+openadapt_ml/retrieval/README.md,sha256=j4gXhTo6yH-5cuw4ER4174V-U6TQakOVT6Hj4kj7B0I,5696
+openadapt_ml/retrieval/USAGE.md,sha256=XDIrX-94Z5nC-wvnBY5yF5gTqUYixxCC3wwUFvQx5YM,9278
+openadapt_ml/retrieval/__init__.py,sha256=xocb84riKLUCezUioKssFRhAQsnvexh4W932o368_qg,2726
+openadapt_ml/retrieval/demo_retriever.py,sha256=C4pLZ0HaJGkZ9H3_pQdeQcaQOOAU_YzGukx79WaFyZI,29493
+openadapt_ml/retrieval/embeddings.py,sha256=B2tQq4VwN166H-P3s1kvOrhVlLvi4SAfXsMoxhXV8HE,19239
+openadapt_ml/retrieval/index.py,sha256=UBFnSxp5T5eKt2txFcd0FytKCw1qxONZfxnFJVrduRQ,5710
+openadapt_ml/retrieval/retriever.py,sha256=nDWeVLpfsHWWp2TE9dI_w56FebKI5bNXZPsh79BiQos,4609
+openadapt_ml/runtime/__init__.py,sha256=Lpu29HgUvAVPW_dkRHRkk18BeMHlwZD-gQ3dZYNGzGo,1294
+openadapt_ml/runtime/policy.py,sha256=RUB4AqObz-1FPpEZNQ-XUsmxro2RkgTJDAztzM2B_oE,6839
+openadapt_ml/runtime/safety_gate.py,sha256=qODkdgx4HB2t-NL_iGPQbDZ_9hR2SZso_nTQ6KuMSfo,16729
+openadapt_ml/schema/__init__.py,sha256=bL6Mi0z-qBV3cw-rfEaVP-sfzzZOvywO0H9IPWtSdN8,3097
+openadapt_ml/schema/converters.py,sha256=ftXPNngd27PkALQyqukMsGpHdpB2sWBOlVz69rGyNkM,19157
+openadapt_ml/schema/episode.py,sha256=2WFCdnIkcCRodvJiR6irmBaGhKzMB5XEQzS6iQJk2gY,15501
+openadapt_ml/scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+openadapt_ml/scripts/capture_screenshots.py,sha256=qVxMuIBuH8jT035tQqjfqLRm6OkLhwRvoGBooPGm09E,15283
+openadapt_ml/scripts/compare.py,sha256=rPe_fQrHyINCbqkO9FXtjRsbQGwzlppEnmCK5YfGjgg,57316
+openadapt_ml/scripts/demo_policy.py,sha256=luALfaJhPIh5aFHXdubSMCzPJk04dNzwfdwcCJeNhUk,2120
+openadapt_ml/scripts/eval_policy.py,sha256=DHfQOIyO-mvrsA_zzlVEVwfsX1mLedFVsYvEpgITB5k,10397
+openadapt_ml/scripts/make_gif.py,sha256=fg6jX2BwW4CIVLfWvq3WHjDE5H7tbRYnhZOHSIxhGWo,4433
+openadapt_ml/scripts/prepare_synthetic.py,sha256=2luW436IejDDR2re73yUhtF5Zjf9McAqi2I0z4zs_CE,1123
+openadapt_ml/scripts/run_qwen_login_benchmark.py,sha256=NWIhCAFSX5pYKFRCec7RkrYtzvz2LNMqhDfXcKxlagM,5655
+openadapt_ml/scripts/train.py,sha256=1clpSt07fiMl1sMW57DO5Gco6LV8Oz2_SNGyiwRqcrQ,6759
+openadapt_ml/segmentation/README.md,sha256=lBb3bkOh5Je2Ba_3MMuhB0QUeY44zLROA_S5JTbf7So,26055
+openadapt_ml/segmentation/__init__.py,sha256=iodD7_Is5oLZm4oZttQd_CnLDofzRGbIhkCV1sgBjEU,2567
+openadapt_ml/segmentation/annotator.py,sha256=d50yyxk3HTY1vP_-WXl5aLdmFk3EkdmoMiTqlkIsL78,21648
+openadapt_ml/segmentation/cache.py,sha256=--1M4aoDdWOUYPBIfEnPdNkn9kfoECESs9JwNq5B_NQ,8696
+openadapt_ml/segmentation/cli.py,sha256=L3YbxqTKAE797RYoZj5mxB9s50F7onAnGjbp4GbN-1M,24187
+openadapt_ml/segmentation/deduplicator.py,sha256=aniwrp9IpcrMKfZh6Rx0Ihj_pu_4LepU_RT_eYiRGHI,22826
+openadapt_ml/segmentation/frame_describer.py,sha256=LhgrdEsQ_tMQE7GiwECXWVY0WozEC6Z1Pr8CRTqtINI,26963
+openadapt_ml/segmentation/pipeline.py,sha256=3ztfKt8xZ011xGL5rIIW6dmOyfJp7Af32XdgXuN-QYc,11890
+openadapt_ml/segmentation/schemas.py,sha256=HKf5ImcXRpjM1hB6vJ825OJjUF5QDA5ITSJwcZklscM,19989
+openadapt_ml/segmentation/segment_extractor.py,sha256=R2fI-sD5JsDE9Y3o4o9rpmldrq-TkRsmGrUJEg413vY,22213
+openadapt_ml/segmentation/adapters/__init__.py,sha256=QOLlVvzjmZJP0fhtEZ4yXCvnJSNbWHZP8pV56Zs_5e4,171
+openadapt_ml/segmentation/adapters/capture_adapter.py,sha256=8QDe9pyiRr3e2xuvvYowlNgBsz-NI3xepFL1ZFIAeAU,14353
+openadapt_ml/training/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+openadapt_ml/training/azure_ops_viewer.py,sha256=B_Tlye1Z86xdTwc99nGtPqQzcJoDYOU4n7bQI0L-D0E,37679
+openadapt_ml/training/benchmark_viewer.py,sha256=CVQa7c3rts_-a-xarwZ9EneR2i0G0n66f4RiK6wKcjg,174367
+openadapt_ml/training/shared_ui.py,sha256=Ghjpx02k_HuZsyyOnZo6LD08ZIHD5ze7fU4centDMNY,4823
+openadapt_ml/training/stub_provider.py,sha256=wyK4ApK88CCzgjZGl0jkNUrUfuSY-axA_XZMYzeeUpg,10932
+openadapt_ml/training/trainer.py,sha256=yGK79alY9Z0xGRQ2r9EaiWbzGlmE5WZJQL_2TWgc8jU,91358
+openadapt_ml/training/trl_trainer.py,sha256=AL1KFWXMub4vWE2w8eoAoQbSgm2fXO82CIqXULLYwVo,13223
+openadapt_ml/training/viewer.py,sha256=rXpREFbDK_tsu719VUej6iXrgnB8eNP0SEuvB9NUUhA,128104
+openadapt_ml/training/viewer_components.py,sha256=XilaX7r4YXFMT1QkooNnPWqR14SpsiTf7YbrN_g-Lq0,5478
+openadapt_ml-0.2.1.dist-info/METADATA,sha256=4mdYMpWiRht3LWtCTXU7I1qTdjl70bKiLdnzpTKJaFI,36696
+openadapt_ml-0.2.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+openadapt_ml-0.2.1.dist-info/licenses/LICENSE,sha256=2E5UY67RVLedJuNnwGudkAMtfM3LZNUcHgmaL89TAfw,1068
+openadapt_ml-0.2.1.dist-info/RECORD,,

openadapt_ml/benchmarks/base.py

@@ -1,366 +0,0 @@
-"""Base classes for benchmark integration.
-
-This module provides the core abstractions for integrating GUI agent benchmarks
-into openadapt-ml. It supports both interactive environments (WAA, OSWorld) and
-static trajectory datasets (Mind2Web).
-
-Example:
-    from openadapt_ml.benchmarks import WAAAdapter, evaluate_agent_on_benchmark
-
-    adapter = WAAAdapter(waa_repo_path="/path/to/WAA")
-    results = evaluate_agent_on_benchmark(agent, adapter, max_steps=50)
-"""
-
-from __future__ import annotations
-
-from abc import ABC, abstractmethod
-from dataclasses import dataclass, field
-from typing import TYPE_CHECKING, Any, Iterator
-
-if TYPE_CHECKING:
-    pass
-
-
-@dataclass
-class BenchmarkTask:
-    """Canonical task representation.
-
-    Attributes:
-        task_id: Unique identifier for the task.
-        instruction: Natural language task instruction.
-        domain: Task domain ("web", "desktop", "mobile").
-        initial_state_ref: Reference to initial state (VM snapshot, URL, etc.).
-        time_limit_steps: Maximum steps allowed for the task.
-        raw_config: Original benchmark config (lossless preservation).
-        evaluation_spec: Benchmark-native evaluation specification.
-    """
-
-    task_id: str
-    instruction: str
-    domain: str  # "web", "desktop", "mobile"
-
-    # Environment setup
-    initial_state_ref: str | None = None  # VM snapshot, storage_state, start URL
-    time_limit_steps: int | None = None
-
-    # Preserve original config losslessly
-    raw_config: dict[str, Any] = field(default_factory=dict)
-
-    # Evaluation spec (benchmark-native)
-    evaluation_spec: dict[str, Any] | None = None
-
-
-@dataclass
-class BenchmarkObservation:
-    """Canonical observation at each step.
-
-    Supports multiple observation modalities:
-    - Visual: screenshots with viewport info
-    - Structured UI: accessibility tree (UIA/AXTree/DOM)
-    - Context: URL, window title, focused element
-
-    Attributes:
-        screenshot: PNG image bytes.
-        screenshot_path: Path to saved screenshot.
-        viewport: (width, height) of the viewport.
-        accessibility_tree: Platform-specific UI tree (UIA/AXTree/DOM).
-        dom_html: Raw HTML for web tasks.
-        url: Current URL for web tasks.
-        window_title: Active window title for desktop tasks.
-        focused_element: Currently focused UI element.
-        raw_observation: Original benchmark observation (lossless).
-    """
-
-    # Visual
-    screenshot: bytes | None = None  # PNG image bytes
-    screenshot_path: str | None = None
-    viewport: tuple[int, int] | None = None  # (width, height)
-
-    # Structured UI (format varies by platform)
-    accessibility_tree: dict | None = None  # UIA (Windows), AXTree (macOS), DOM (web)
-    dom_html: str | None = None  # Raw HTML for web
-
-    # Context
-    url: str | None = None  # For web tasks
-    window_title: str | None = None  # For desktop tasks
-    app_name: str | None = None  # Active application
-    focused_element: dict | None = None  # {node_id, bbox, text}
-
-    # Raw benchmark-specific data (lossless)
-    raw_observation: dict[str, Any] | None = None
-
-
-@dataclass
-class BenchmarkAction:
-    """Canonical action representation.
-
-    Supports multiple action types with both coordinate-based and element-based
-    grounding. The "grounding-first" approach stores both when available.
-
-    Attributes:
-        type: Action type ("click", "type", "scroll", "key", "drag", "answer", "done").
-        x: X coordinate (normalized [0,1] or pixels).
-        y: Y coordinate (normalized [0,1] or pixels).
-        target_node_id: Element ID from accessibility tree.
-        target_bbox: Element bounding box.
-        target_role: Element role (button, textfield, etc.).
-        target_name: Element accessible name.
-        text: Text to type (for "type" action).
-        key: Single key (for "key" action, e.g., "Enter", "Tab").
-        modifiers: Key modifiers (["ctrl", "shift", "alt"]).
-        scroll_direction: Scroll direction ("up", "down", "left", "right").
-        scroll_amount: Scroll amount (pixels or normalized).
-        end_x: Drag end X coordinate.
-        end_y: Drag end Y coordinate.
-        answer: Answer string (for benchmarks that score by answer).
-        raw_action: Original benchmark action (lossless).
-    """
-
-    type: str  # "click", "type", "scroll", "key", "drag", "answer", "done"
-
-    # Pointer actions - coordinates
-    x: float | None = None  # Normalized [0,1] or pixel
-    y: float | None = None
-
-    # Element grounding (when available)
-    target_node_id: str | None = None  # DOM/AX/UIA node ID
-    target_bbox: tuple[float, float, float, float] | None = None
-    target_role: str | None = None  # "button", "textfield", etc.
-    target_name: str | None = None  # Accessible name
-
-    # Keyboard actions
-    text: str | None = None  # For "type" action - text to type
-    key: str | None = None  # For "key" action - single key
-    modifiers: list[str] | None = None  # ["ctrl", "shift", "alt"]
-
-    # Scroll actions
-    scroll_direction: str | None = None  # "up", "down", "left", "right"
-    scroll_amount: float | None = None  # Pixels or normalized
-
-    # Drag actions
-    end_x: float | None = None
-    end_y: float | None = None
-
-    # Answer action (some benchmarks score by final answer)
-    answer: str | None = None
-
-    # Raw benchmark-specific format (lossless)
-    raw_action: dict[str, Any] | None = None
-
-
-@dataclass
-class BenchmarkResult:
-    """Result of a single task evaluation.
-
-    Attributes:
-        task_id: ID of the evaluated task.
-        success: Whether the task was completed successfully.
-        score: Score between 0.0 and 1.0.
-        steps: List of (observation, action) pairs from the trajectory.
-        num_steps: Number of steps taken.
-        error: Error message if task failed due to error.
-        reason: Explanation of success/failure.
-        total_time_seconds: Total time taken for the task.
-    """
-
-    task_id: str
-    success: bool
-    score: float  # 0.0 to 1.0
-
-    # Trajectory
-    steps: list[tuple[BenchmarkObservation, BenchmarkAction]] = field(
-        default_factory=list
-    )
-    num_steps: int = 0
-
-    # Diagnostics
-    error: str | None = None
-    reason: str | None = None  # Why success/fail
-
-    # Timing
-    total_time_seconds: float = 0.0
-
-
-@dataclass
-class UIElement:
-    """Normalized UI element for cross-platform use.
-
-    Provides a common representation for UI elements across platforms
-    (Windows UIA, macOS AXTree, web DOM).
-
-    Attributes:
-        node_id: Unique identifier for the element.
-        role: Element role (button, textfield, link, etc.).
-        name: Accessible name/label.
-        bbox: Bounding box (normalized [0,1] or pixels).
-        text: Text content.
-        value: Current value (for inputs).
-        children: Child elements.
-        attributes: Additional platform-specific attributes.
-    """
-
-    node_id: str
-    role: str  # "button", "textfield", "link", etc.
-    name: str | None = None  # Accessible name/label
-    bbox: tuple[float, float, float, float] | None = None  # (x1, y1, x2, y2)
-    text: str | None = None  # Text content
-    value: str | None = None  # Current value (for inputs)
-    children: list[UIElement] | None = None
-    attributes: dict[str, Any] | None = None  # Platform-specific
-
-
-class BenchmarkAdapter(ABC):
-    """Abstract interface for benchmark integration.
-
-    Subclasses implement this interface to integrate specific benchmarks
-    (WAA, OSWorld, WebArena, etc.) with openadapt-ml.
-
-    Two types of adapters:
-    - Interactive: Run environment, step through tasks (WAA, OSWorld)
-    - Static: Load trajectories for offline training/eval (Mind2Web)
-    """
-
-    @property
-    @abstractmethod
-    def name(self) -> str:
-        """Benchmark name (e.g., 'waa', 'osworld', 'webarena')."""
-        pass
-
-    @property
-    @abstractmethod
-    def benchmark_type(self) -> str:
-        """Benchmark type: 'interactive' or 'static'."""
-        pass
-
-    @property
-    def supports_parallel(self) -> bool:
-        """Whether the adapter supports parallel task execution."""
-        return False
-
-    @abstractmethod
-    def list_tasks(self, domain: str | None = None) -> list[BenchmarkTask]:
-        """List available tasks, optionally filtered by domain.
-
-        Args:
-            domain: Optional domain filter (e.g., "browser", "office").
-
-        Returns:
-            List of BenchmarkTask objects.
-        """
-        pass
-
-    @abstractmethod
-    def load_task(self, task_id: str) -> BenchmarkTask:
-        """Load a specific task by ID.
-
-        Args:
-            task_id: Task identifier.
-
-        Returns:
-            BenchmarkTask object.
-
-        Raises:
-            KeyError: If task_id not found.
-        """
-        pass
-
-    @abstractmethod
-    def reset(self, task: BenchmarkTask) -> BenchmarkObservation:
-        """Reset environment to task's initial state.
-
-        Args:
-            task: Task to initialize.
-
-        Returns:
-            Initial observation.
-        """
-        pass
-
-    @abstractmethod
-    def step(
-        self, action: BenchmarkAction
-    ) -> tuple[BenchmarkObservation, bool, dict[str, Any]]:
-        """Execute action and return new observation.
-
-        Args:
-            action: Action to execute.
-
-        Returns:
-            Tuple of (observation, done, info).
-        """
-        pass
-
-    @abstractmethod
-    def evaluate(self, task: BenchmarkTask) -> BenchmarkResult:
-        """Run benchmark's native evaluation on current state.
-
-        Args:
-            task: Task to evaluate.
-
-        Returns:
-            BenchmarkResult with success/score.
-        """
-        pass
-
-    def close(self) -> None:
-        """Clean up resources (VMs, browser, etc.)."""
-        pass
-
-    def __enter__(self) -> BenchmarkAdapter:
-        """Context manager entry."""
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
-        """Context manager exit."""
-        self.close()
-
-
-class StaticDatasetAdapter(BenchmarkAdapter):
-    """Base for static trajectory datasets (Mind2Web, demos).
-
-    Static adapters load pre-recorded trajectories for offline training
-    or evaluation, rather than running an interactive environment.
-    """
-
-    @property
-    def benchmark_type(self) -> str:
-        """Static datasets are not interactive."""
-        return "static"
-
-    @abstractmethod
-    def load_trajectories(
-        self, split: str = "test"
-    ) -> Iterator[tuple[BenchmarkTask, list[tuple[BenchmarkObservation, BenchmarkAction]]]]:
-        """Iterate over expert trajectories.
-
-        Args:
-            split: Dataset split ("train", "val", "test").
-
-        Yields:
-            Tuples of (task, trajectory) where trajectory is a list of
-            (observation, action) pairs.
-        """
-        pass
-
-    def reset(self, task: BenchmarkTask) -> BenchmarkObservation:
-        """Not supported for static datasets."""
-        raise NotImplementedError(
-            "Static datasets don't support interactive reset. "
-            "Use load_trajectories() instead."
-        )
-
-    def step(
-        self, action: BenchmarkAction
-    ) -> tuple[BenchmarkObservation, bool, dict[str, Any]]:
-        """Not supported for static datasets."""
-        raise NotImplementedError(
-            "Static datasets don't support interactive stepping. "
-            "Use load_trajectories() instead."
-        )
-
-    def evaluate(self, task: BenchmarkTask) -> BenchmarkResult:
-        """Not supported for static datasets."""
-        raise NotImplementedError(
-            "Static datasets don't support execution-based evaluation. "
-            "Use offline metrics instead."
-        )