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

openadapt_ml/benchmarks/__init__.py

@@ -1,125 +1,31 @@
 """Benchmark integration for openadapt-ml.
 
-This module provides interfaces and utilities for evaluating GUI agents
-on standardized benchmarks like Windows Agent Arena (WAA), OSWorld,
-WebArena, and others.
+This module provides ML-specific agents for benchmark evaluation.
+These agents wrap openadapt-ml internals (trained policies, API adapters).
 
-Core classes:
-    - BenchmarkAdapter: Abstract interface for benchmark integration
-    - BenchmarkAgent: Abstract interface for agents to be evaluated
-    - BenchmarkTask, BenchmarkObservation, BenchmarkAction: Data classes
-
-Agent implementations:
-    - PolicyAgent: Wraps openadapt-ml AgentPolicy
-    - APIBenchmarkAgent: Uses hosted VLM APIs (Claude, GPT-5.1)
-    - ScriptedAgent: Follows predefined action sequence
-    - RandomAgent: Takes random actions (baseline)
-
-Evaluation:
-    - evaluate_agent_on_benchmark: Run agent on benchmark tasks
-    - compute_metrics: Compute aggregate metrics from results
-
-Example:
+For benchmark infrastructure (adapters, runners, viewers), use openadapt-evals:
     ```python
-    from openadapt_ml.benchmarks import (
-        BenchmarkAdapter,
-        PolicyAgent,
-        APIBenchmarkAgent,
+    from openadapt_evals import (
+        WAAMockAdapter,
+        WAALiveAdapter,
         evaluate_agent_on_benchmark,
-        compute_metrics,
     )
-
-    # Create adapter for specific benchmark
-    adapter = WAAAdapter(waa_repo_path="/path/to/WAA")
-
-    # Wrap policy as benchmark agent
-    agent = PolicyAgent(policy)
-
-    # Or use API-backed agent for baselines
-    agent = APIBenchmarkAgent(provider="anthropic")  # Claude
-    agent = APIBenchmarkAgent(provider="openai")     # GPT-5.1
-
-    # Run evaluation
-    results = evaluate_agent_on_benchmark(agent, adapter, max_steps=50)
-
-    # Compute metrics
-    metrics = compute_metrics(results)
-    print(f"Success rate: {metrics['success_rate']:.1%}")
     ```
+
+ML-specific agents (only available in openadapt-ml):
+    - PolicyAgent: Wraps openadapt_ml.runtime.policy.AgentPolicy
+    - APIBenchmarkAgent: Uses openadapt_ml.models.api_adapter.ApiVLMAdapter
+    - UnifiedBaselineAgent: Uses openadapt_ml.baselines adapters
 """
 
 from openadapt_ml.benchmarks.agent import (
     APIBenchmarkAgent,
-    BenchmarkAgent,
     PolicyAgent,
-    RandomAgent,
-    ScriptedAgent,
-)
-from openadapt_ml.benchmarks.base import (
-    BenchmarkAction,
-    BenchmarkAdapter,
-    BenchmarkObservation,
-    BenchmarkResult,
-    BenchmarkTask,
-    StaticDatasetAdapter,
-    UIElement,
+    UnifiedBaselineAgent,
 )
-from openadapt_ml.benchmarks.runner import (
-    EvaluationConfig,
-    compute_domain_metrics,
-    compute_metrics,
-    evaluate_agent_on_benchmark,
-)
-from openadapt_ml.benchmarks.waa import WAAAdapter, WAAConfig, WAAMockAdapter
-
-# Azure orchestration (lazy import to avoid requiring azure-ai-ml)
-def _get_azure_classes():
-    from openadapt_ml.benchmarks.azure import (
-        AzureConfig,
-        AzureWAAOrchestrator,
-        estimate_cost,
-    )
-    return AzureConfig, AzureWAAOrchestrator, estimate_cost
-
 
 __all__ = [
-    # Base classes
-    "BenchmarkAdapter",
-    "BenchmarkTask",
-    "BenchmarkObservation",
-    "BenchmarkAction",
-    "BenchmarkResult",
-    "StaticDatasetAdapter",
-    "UIElement",
-    # Agents
-    "BenchmarkAgent",
     "PolicyAgent",
     "APIBenchmarkAgent",
-    "ScriptedAgent",
-    "RandomAgent",
-    # Evaluation
-    "EvaluationConfig",
-    "evaluate_agent_on_benchmark",
-    "compute_metrics",
-    "compute_domain_metrics",
-    # WAA
-    "WAAAdapter",
-    "WAAConfig",
-    "WAAMockAdapter",
-    # Azure (lazy-loaded)
-    "AzureConfig",
-    "AzureWAAOrchestrator",
-    "estimate_cost",
+    "UnifiedBaselineAgent",
 ]
-
-
-# Lazy loading for Azure classes (avoids requiring azure-ai-ml for basic usage)
-def __getattr__(name: str):
-    if name in ("AzureConfig", "AzureWAAOrchestrator", "estimate_cost"):
-        from openadapt_ml.benchmarks.azure import (
-            AzureConfig,
-            AzureWAAOrchestrator,
-            estimate_cost,
-        )
-        return {"AzureConfig": AzureConfig, "AzureWAAOrchestrator": AzureWAAOrchestrator, "estimate_cost": estimate_cost}[name]
-    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")