openadapt-ml 0.2.0__py3-none-any.whl → 0.2.2__py3-none-any.whl

openadapt_ml/training/viewer_components.py

@@ -0,0 +1,180 @@
+"""Adapter module for openadapt-viewer components.
+
+This module provides wrapper functions that adapt openadapt-viewer components
+for openadapt-ml specific use cases, particularly for training visualization.
+
+Migration Approach:
+------------------
+Phase 1 (Foundation): Create this adapter module to establish patterns
+Phase 2 (Integration): Gradually migrate viewer.py to use these adapters
+Phase 3 (Consolidation): Remove duplicate code from viewer.py
+Phase 4 (Completion): Full dependency on openadapt-viewer
+
+Design Principles:
+-----------------
+1. Each function wraps openadapt-viewer components with ML-specific context
+2. Functions accept openadapt-ml data structures (TrainingState, predictions, etc.)
+3. No breaking changes to existing viewer.py code
+4. Can be incrementally adopted in future phases
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+# Import openadapt-viewer components
+from openadapt_viewer.components import (
+    screenshot_display as _screenshot_display,
+    playback_controls as _playback_controls,
+    metrics_grid as _metrics_grid,
+    badge as _badge,
+)
+
+
+def screenshot_with_predictions(
+    screenshot_path: str | Path,
+    human_action: dict[str, Any] | None = None,
+    predicted_action: dict[str, Any] | None = None,
+    step_number: int | None = None,
+    show_difference: bool = True,
+) -> str:
+    """Generate screenshot display with human and AI action overlays."""
+    overlays = []
+
+    if human_action:
+        overlays.append(
+            {
+                "type": human_action.get("type", "click"),
+                "x": human_action.get("x", 0),
+                "y": human_action.get("y", 0),
+                "label": "H",
+                "variant": "human",
+                "color": "#34d399",
+            }
+        )
+
+    if predicted_action:
+        overlays.append(
+            {
+                "type": predicted_action.get("type", "click"),
+                "x": predicted_action.get("x", 0),
+                "y": predicted_action.get("y", 0),
+                "label": "AI",
+                "variant": "predicted",
+                "color": "#00d4aa",
+            }
+        )
+
+    caption = f"Step {step_number}" if step_number is not None else None
+
+    return _screenshot_display(
+        image_path=str(screenshot_path),
+        overlays=overlays,
+        caption=caption,
+    )
+
+
+def training_metrics(
+    epoch: int | None = None,
+    loss: float | None = None,
+    accuracy: float | None = None,
+    elapsed_time: float | None = None,
+    learning_rate: float | None = None,
+    **additional_metrics: Any,
+) -> str:
+    """Generate metrics grid for training statistics."""
+    metrics = []
+
+    if epoch is not None:
+        metrics.append({"label": "Epoch", "value": epoch})
+
+    if loss is not None:
+        color = "success" if loss < 0.1 else "warning" if loss < 0.5 else "error"
+        metrics.append({"label": "Loss", "value": f"{loss:.4f}", "color": color})
+
+    if accuracy is not None:
+        color = (
+            "success" if accuracy > 0.9 else "warning" if accuracy > 0.7 else "error"
+        )
+        metrics.append(
+            {"label": "Accuracy", "value": f"{accuracy:.2%}", "color": color}
+        )
+
+    if elapsed_time is not None:
+        hours = int(elapsed_time // 3600)
+        minutes = int((elapsed_time % 3600) // 60)
+        seconds = int(elapsed_time % 60)
+        time_str = f"{hours}h {minutes}m {seconds}s"
+        metrics.append({"label": "Elapsed", "value": time_str})
+
+    if learning_rate is not None:
+        metrics.append({"label": "LR", "value": f"{learning_rate:.2e}"})
+
+    for key, value in additional_metrics.items():
+        label = key.replace("_", " ").title()
+        metrics.append({"label": label, "value": str(value)})
+
+    return _metrics_grid(metrics)
+
+
+def playback_controls(
+    step_count: int,
+    initial_step: int = 0,
+) -> str:
+    """Generate playback controls for step-by-step viewer."""
+    return _playback_controls(
+        step_count=step_count,
+        initial_step=initial_step,
+    )
+
+
+def correctness_badge(is_correct: bool, show_label: bool = True) -> str:
+    """Generate a badge indicating prediction correctness."""
+    if is_correct:
+        text = "Correct" if show_label else "✓"
+        color = "success"
+    else:
+        text = "Incorrect" if show_label else "✗"
+        color = "error"
+
+    return _badge(text=text, color=color)
+
+
+def generate_comparison_summary(
+    total_steps: int,
+    correct_steps: int,
+    model_name: str | None = None,
+) -> str:
+    """Generate a summary card for model comparison results."""
+    accuracy = correct_steps / total_steps if total_steps > 0 else 0
+    incorrect_steps = total_steps - correct_steps
+
+    metrics = [
+        {"label": "Total Steps", "value": total_steps},
+        {"label": "Correct", "value": correct_steps, "color": "success"},
+        {
+            "label": "Incorrect",
+            "value": incorrect_steps,
+            "color": "error" if incorrect_steps > 0 else "muted",
+        },
+        {
+            "label": "Accuracy",
+            "value": f"{accuracy:.1%}",
+            "color": "success" if accuracy > 0.9 else "warning",
+        },
+    ]
+
+    if model_name:
+        metrics.insert(0, {"label": "Model", "value": model_name})
+
+    return _metrics_grid(metrics)
+
+
+__all__ = [
+    "screenshot_with_predictions",
+    "training_metrics",
+    "playback_controls",
+    "correctness_badge",
+    "generate_comparison_summary",
+]

{openadapt_ml-0.2.0.dist-info → openadapt_ml-0.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openadapt-ml
-Version: 0.2.0
+Version: 0.2.2
 Summary: Model-agnostic, domain-agnostic ML engine for GUI automation agents
 Project-URL: Homepage, https://github.com/OpenAdaptAI/openadapt-ml
 Project-URL: Repository, https://github.com/OpenAdaptAI/openadapt-ml
@@ -13,18 +13,22 @@ Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: >=3.12
+Requires-Python: >=3.10
 Requires-Dist: azure-ai-ml>=1.30.0
 Requires-Dist: azure-identity>=1.25.1
 Requires-Dist: bitsandbytes>=0.41.0
+Requires-Dist: click>=8.1.0
 Requires-Dist: google-generativeai>=0.8.5
 Requires-Dist: matplotlib>=3.10.7
 Requires-Dist: openadapt-capture>=0.1.0
 Requires-Dist: peft>=0.18.0
 Requires-Dist: pillow>=12.0.0
+Requires-Dist: pyautogui>=0.9.54
 Requires-Dist: pydantic-settings>=2.0.0
 Requires-Dist: pytest>=9.0.2
 Requires-Dist: pyyaml>=6.0.3
@@ -38,6 +42,8 @@ Requires-Dist: pydantic-settings>=2.0.0; extra == 'api'
 Provides-Extra: azure
 Requires-Dist: azure-ai-ml>=1.0.0; extra == 'azure'
 Requires-Dist: azure-identity>=1.0.0; extra == 'azure'
+Provides-Extra: benchmarks
+Requires-Dist: openadapt-evals>=0.1.1; extra == 'benchmarks'
 Provides-Extra: dev
 Requires-Dist: pytest>=9.0.0; extra == 'dev'
 Requires-Dist: ruff>=0.1.0; extra == 'dev'
@@ -52,17 +58,19 @@ Description-Content-Type: text/markdown
 
 # OpenAdapt-ML
 
-[![PyPI version](https://badge.fury.io/py/openadapt-ml.svg)](https://badge.fury.io/py/openadapt-ml)
+[![Build Status](https://github.com/OpenAdaptAI/openadapt-ml/actions/workflows/publish.yml/badge.svg)](https://github.com/OpenAdaptAI/openadapt-ml/actions/workflows/publish.yml)
+[![PyPI version](https://img.shields.io/pypi/v/openadapt-ml.svg)](https://pypi.org/project/openadapt-ml/)
+[![Downloads](https://img.shields.io/pypi/dm/openadapt-ml.svg)](https://pypi.org/project/openadapt-ml/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Python Version](https://img.shields.io/badge/python-3.12-blue)](https://www.python.org/)
+[![Python 3.12+](https://img.shields.io/badge/python-3.12%2B-blue)](https://www.python.org/downloads/)
 
 OpenAdapt-ML is a **model-agnostic, domain-agnostic ML engine** for GUI
 automation agents. It sits above **TRL + Unsloth** (which we use directly for training performance) and provides the GUI-specific layer:
 
 - **Episode semantics**: Step/action/observation alignment, screenshot-action coupling, termination handling
-- **Demo-conditioned inference**: Retrieval-augmented prompting (validated: 33% → 100% first-action accuracy)
+- **Demo-conditioned inference**: Retrieval-augmented prompting (in early experiments: 46.7% -> 100% first-action accuracy on a controlled macOS benchmark where all 45 tasks share the same navigation entry point - see [publication roadmap](https://github.com/OpenAdaptAI/OpenAdapt/blob/main/docs/publication-roadmap.md) for methodology and limitations)
 - **Benchmark adapters**: WAA today, OSWorld/WebArena planned
-- **VLM adapters**: Updated with leading GUI-agent SOTA open-source models
+- **VLM adapters**: Supports open-source GUI-agent models (Qwen3-VL, Qwen2.5-VL)
 - **Training pipeline**: TRL + Unsloth integration for 2x faster training with 50% less VRAM
 
 OpenAdapt-ML is **not** a training framework, optimizer, hardware orchestrator, or experiment manager. We use TRL/Unsloth, Lambda Labs/Azure, and W&B/MLflow for those.
@@ -254,7 +262,9 @@ simple login flow.
 ### 5.1 Synthetic scenarios
 
 OpenAdapt-ML includes synthetic UI generators for structured GUI automation benchmarks.
-Currently two scenarios are supported:
+Currently two scenarios are supported.
+
+> **Note:** These are **synthetic, controlled benchmarks** designed for rapid iteration and debugging, not real-world evaluation. The 100% accuracy results below demonstrate that fine-tuning works on simple scenarios with known ground truth - they do not represent performance on production UIs or standard benchmarks like WAA. See section 14 (Limitations) for details.
 
 #### Login Scenario (6 steps, 3 elements)
 
@@ -437,15 +447,18 @@ It exposes step-level performance metrics, which let us visually answer the ques
 | Claude Sonnet 4.5   | API          | 0.121           | 0.757       | 0.000          |
 | GPT-5.1             | API          | 0.183           | 0.057       | 0.600          |
 
-**Key findings:**
-1. **Fine-tuning delivers massive gains**: Both 2B and 8B models show 2-3x improvement in action accuracy after fine-tuning
-2. **Small fine-tuned models beat large APIs**: Qwen3-VL-2B FT (469% base) outperforms both Claude Sonnet 4.5 (121%) and GPT-5.1 (183%)
-3. **Precision matters**: Fine-tuned models have excellent click precision (85-100% hit rate, <0.05 coord error) while API models struggle with the action format
-4. **Size vs specialization**: The fine-tuned 2B model outperforms the general-purpose Claude Sonnet 4.5, showing that domain-specific fine-tuning trumps raw model size
+**Observations on synthetic login benchmark:**
+
+> **Important:** These findings are from a synthetic benchmark with ~3 UI elements and a fixed action sequence. They demonstrate the training pipeline works, but should not be extrapolated to real-world GUI automation performance. Evaluation on standard benchmarks (WAA, WebArena) is ongoing.
+
+1. **Fine-tuning improves synthetic task performance**: Both 2B and 8B models show 2-3x improvement in action accuracy after fine-tuning on this specific task
+2. **On this synthetic benchmark, fine-tuned models outperform zero-shot API calls**: This is expected since the task is simple and the models are trained on it directly
+3. **Coordinate precision is learnable**: Fine-tuned models achieve low coordinate error on training distribution
+4. **API models struggle with custom action format**: Without fine-tuning on the specific DSL (CLICK/TYPE/DONE), API models have high format-error rates
 
-### 6.4 Set-of-Marks (SoM) Mode: 100% Accuracy
+### 6.4 Set-of-Marks (SoM) Mode: 100% Accuracy on Synthetic Benchmarks
 
-With **Set-of-Marks** visual prompting, fine-tuned Qwen3-VL-2B achieves **100% accuracy** on both login (6-step) and registration (12-step) scenarios:
+With **Set-of-Marks** visual prompting, fine-tuned Qwen3-VL-2B achieves **100% accuracy** on both login (6-step) and registration (12-step) synthetic scenarios. Note that these are controlled, toy benchmarks with a small number of UI elements:
 
 | Scenario | Steps | Elements | Action Acc | Element Acc | Episode Success |
 |----------|-------|----------|------------|-------------|-----------------|
@@ -826,6 +839,194 @@ uv run python -m openadapt_ml.cloud.local serve --port 8080 --open
 
 *View benchmark evaluation results with task-level filtering, success/failure status, and run comparison. Shows Claude achieving 30% on mock evaluation tasks (simulated environment for testing the pipeline - real WAA evaluation requires Windows VMs).*
 
+### 13.4 VM Monitoring Dashboard
+
+For managing Azure VMs used in benchmark evaluations, the `vm monitor` command provides a comprehensive dashboard:
+
+```bash
+# Start VM monitoring dashboard (auto-opens browser)
+uv run python -m openadapt_ml.benchmarks.cli vm monitor
+
+# Show detailed information (evaluation history, daily/weekly costs)
+uv run python -m openadapt_ml.benchmarks.cli vm monitor --details
+```
+
+**VM Monitor Dashboard (Full View):**
+
+![VM Monitor Dashboard](docs/screenshots/vm_monitor_dashboard_full.png)
+
+*The VM monitor dashboard shows: (1) VM status (name, IP, size, state), (2) Current activity (idle/benchmark running), (3) Cost tracking (uptime, hourly rate, total cost), (4) Recent Azure ML jobs from last 7 days, and (6) Dashboard & access URLs.*
+
+**VM Monitor Dashboard (With --details Flag):**
+
+![VM Monitor Dashboard Details](docs/screenshots/vm_monitor_details.png)
+
+*The --details flag adds: (5) Evaluation history with success rates and agent types, plus extended cost information (daily/weekly projections).*
+
+**Features:**
+- **Real-time VM status** - Shows VM size, power state, and IP address
+- **Activity detection** - Identifies if VM is idle, running benchmarks, or in setup
+- **Cost tracking** - Displays uptime hours, hourly rate, and total cost for current session
+- **Azure ML jobs** - Lists recent jobs from last 7 days with status indicators
+- **Evaluation history** - Shows past benchmark runs with success rates (with --details flag)
+- **Dashboard & tunnels** - Auto-starts web dashboard and SSH/VNC tunnels for accessing Windows VM
+
+**Mock mode for testing:**
+```bash
+# Generate screenshots or test dashboard without a VM running
+uv run python -m openadapt_ml.benchmarks.cli vm monitor --mock
+```
+
+**Auto-shutdown option:**
+```bash
+# Automatically deallocate VM after 2 hours to prevent runaway costs
+uv run python -m openadapt_ml.benchmarks.cli vm monitor --auto-shutdown-hours 2
+```
+
+### 13.5 Benchmark Execution Logs
+
+View benchmark execution progress and logs:
+
+```bash
+# View WAA container status and Docker logs
+uv run python -m openadapt_ml.benchmarks.cli logs
+
+# View WAA benchmark execution logs (task progress, agent actions)
+uv run python -m openadapt_ml.benchmarks.cli logs --run
+
+# Stream execution logs live
+uv run python -m openadapt_ml.benchmarks.cli logs --run -f
+
+# Show last N lines of execution logs
+uv run python -m openadapt_ml.benchmarks.cli logs --run --tail 100
+
+# Show benchmark progress and ETA
+uv run python -m openadapt_ml.benchmarks.cli logs --progress
+```
+
+**Example: Container status (`logs`)**
+```
+WAA Status (20.12.180.208)
+============================================================
+
+[Docker Images]
+REPOSITORY              TAG       SIZE
+waa-auto                latest    25.4GB
+windowsarena/winarena   latest    25.8GB
+
+[Container]
+  Status: Up 49 minutes
+
+[Storage]
+  Total: 21G
+  Disk image: 64G
+
+[QEMU VM]
+  Status: Running (PID 1471)
+  CPU: 176%, MEM: 51.6%, Uptime: 47:28
+
+[WAA Server]
+  "status": "Probe successful"
+ (READY)
+```
+
+**Example: Benchmark execution logs (`logs --run -f`)**
+```
+Run log: /home/azureuser/cli_logs/run_20260128_175507.log
+------------------------------------------------------------
+Streaming log (Ctrl+C to stop)...
+
+[2026-01-28 23:05:10,303 INFO agent/401-MainProcess] Thinking...
+[2026-01-28 23:05:17,318 INFO python/62-MainProcess] Updated computer successfully
+[2026-01-28 23:05:17,318 INFO lib_run_single/56-MainProcess] Step 9: computer.window_manager.switch_to_application("Summer Trip - File Explorer")
+```
+
+**Example: Benchmark progress (`logs --progress`)**
+```
+=== WAA Benchmark Progress ===
+
+Log: /home/azureuser/cli_logs/run_20260128_175507.log
+Started: 2026-01-28 22:55:14
+Latest:  2026-01-28 23:28:37
+
+Tasks completed: 1 / 154
+Elapsed: 33 minutes
+
+Avg time per task: ~33 min
+Remaining tasks: 153
+Estimated remaining: ~84h 9m
+
+Progress: 0% [1/154]
+```
+
+**Other useful commands:**
+```bash
+# Check WAA server status (probe endpoint)
+uv run python -m openadapt_ml.benchmarks.cli probe
+
+# Check VM/Azure status
+uv run python -m openadapt_ml.benchmarks.cli status
+
+# Download benchmark results from VM
+uv run python -m openadapt_ml.benchmarks.cli download
+
+# Analyze downloaded results
+uv run python -m openadapt_ml.benchmarks.cli analyze
+```
+
+**Running benchmarks:**
+```bash
+# Run full benchmark (154 tasks)
+uv run python -m openadapt_ml.benchmarks.cli run --num-tasks 154
+
+# Run specific domain
+uv run python -m openadapt_ml.benchmarks.cli run --domain notepad --num-tasks 5
+
+# Run single task
+uv run python -m openadapt_ml.benchmarks.cli run --task notepad_1
+```
+
+For complete VM management commands and Azure setup instructions, see [`CLAUDE.md`](CLAUDE.md) and [`docs/azure_waa_setup.md`](docs/azure_waa_setup.md).
+
+### 13.6 Screenshot Capture Tool
+
+Capture screenshots of dashboards and VMs for documentation and PR purposes:
+
+```bash
+# Capture all available targets
+uv run python -m openadapt_ml.benchmarks.cli screenshot
+
+# List available targets
+uv run python -m openadapt_ml.benchmarks.cli screenshot --list
+
+# Capture specific targets
+uv run python -m openadapt_ml.benchmarks.cli screenshot --target terminal
+uv run python -m openadapt_ml.benchmarks.cli screenshot --target azure-ops --target vnc
+
+# Custom output directory
+uv run python -m openadapt_ml.benchmarks.cli screenshot --output /path/to/screenshots
+
+# Without timestamp in filename
+uv run python -m openadapt_ml.benchmarks.cli screenshot --target terminal --no-timestamp
+```
+
+**Available targets:**
+
+| Target | Description |
+|--------|-------------|
+| `azure-ops` | Azure ops dashboard (localhost:8765) |
+| `vnc` | VNC viewer (localhost:8006) - Windows VM |
+| `terminal` | VM monitor terminal output (mock mode) |
+| `terminal-live` | VM monitor terminal output (live, requires running VM) |
+| `training` | Training dashboard (localhost:8080) |
+| `vm-screen` | Windows VM screen capture via QEMU |
+
+**Notes:**
+- Terminal screenshots use PIL to render terminal output as PNG images
+- Web page screenshots work best with playwright installed (`uv add playwright && playwright install chromium`)
+- On macOS, interactive capture using `screencapture` is available as a fallback
+- Screenshots are saved to `docs/screenshots/` by default with timestamps
+
 ---
 
 ## 14. Limitations & Notes

openadapt_ml-0.2.2.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-0.2.2.dist-info/METADATA,sha256=XNDolFy-sWkfPPCZ36qFRUwKzMRLk9WhzLMVufPp8i8,36696
+openadapt_ml-0.2.2.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+openadapt_ml-0.2.2.dist-info/licenses/LICENSE,sha256=2E5UY67RVLedJuNnwGudkAMtfM3LZNUcHgmaL89TAfw,1068
+openadapt_ml-0.2.2.dist-info/RECORD,,