diff --git a/.gitignore b/.gitignore index 5d6ab22..baf5539 100644 --- a/.gitignore +++ b/.gitignore @@ -30,6 +30,8 @@ benchmark_live.json # Cost reports (generated during evaluation runs) cost_report.json -# WAA recordings (PNGs + meta.json from record-waa sessions) -# Gitignored to protect from `git stash -u` and `git clean -f` -waa_recordings/ +# WAA recordings are tracked in git (research data). +# External backup to ~/oa/recordings/ protects against git stash -u. + +# Generated artifacts from generate_demo_review.py (regenerable) +docs/artifacts/full/ diff --git a/benchmark_results/waa-mock_eval_20260116_154343/metadata.json b/benchmark_results/waa-mock_eval_20260116_154343/metadata.json deleted file mode 100644 index 2592ba7..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154343/metadata.json +++ /dev/null @@ -1,6 +0,0 @@ -{ - "benchmark_name": "waa-mock", - "run_name": "waa-mock_eval_20260116_154343", - "model_id": "unknown", - "created_at": "2026-01-16T15:43:43.182784" -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154343/summary.json b/benchmark_results/waa-mock_eval_20260116_154343/summary.json deleted file mode 100644 index 1a28ee0..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154343/summary.json +++ /dev/null @@ -1,34 +0,0 @@ -{ - "benchmark_name": "waa-mock", - "run_name": "waa-mock_eval_20260116_154343", - "model_id": "unknown", - "num_tasks": 3, - "num_success": 3, - "success_rate": 1.0, - "avg_score": 1.0, - "avg_steps": 1.0, - "avg_time_seconds": 0.19648794467017675, - "tasks": [ - { - "task_id": "browser_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - }, - { - "task_id": "office_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - }, - { - "task_id": "coding_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/execution.json b/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/execution.json deleted file mode 100644 index 79274ee..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "browser_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.2386476250103442, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596223.329411 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596223.421621 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/screenshots/step_000.png deleted file mode 100644 index 05ab44d..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/screenshots/step_001.png deleted file mode 100644 index 1af63b2..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/task.json b/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/task.json deleted file mode 100644 index 3dfc721..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154343/tasks/browser_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "browser_1", - "instruction": "Mock task 1 in browser domain", - "domain": "browser", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/execution.json b/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/execution.json deleted file mode 100644 index a1f9ccb..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "coding_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.17749166699650232, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596223.6836 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596223.773221 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/screenshots/step_000.png deleted file mode 100644 index 0f5e838..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/screenshots/step_001.png deleted file mode 100644 index 501970c..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/task.json b/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/task.json deleted file mode 100644 index 69afec4..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154343/tasks/coding_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "coding_1", - "instruction": "Mock task 1 in coding domain", - "domain": "coding", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/execution.json b/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/execution.json deleted file mode 100644 index ea50248..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "office_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.17332454200368375, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596223.508001 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596223.59536 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/screenshots/step_000.png deleted file mode 100644 index 90b990d..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/screenshots/step_001.png deleted file mode 100644 index 6869877..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/task.json b/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/task.json deleted file mode 100644 index 5b472c8..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154343/tasks/office_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "office_1", - "instruction": "Mock task 1 in office domain", - "domain": "office", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154403/metadata.json b/benchmark_results/waa-mock_eval_20260116_154403/metadata.json deleted file mode 100644 index 64142d3..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154403/metadata.json +++ /dev/null @@ -1,6 +0,0 @@ -{ - "benchmark_name": "waa-mock", - "run_name": "waa-mock_eval_20260116_154403", - "model_id": "unknown", - "created_at": "2026-01-16T15:44:03.010790" -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154403/summary.json b/benchmark_results/waa-mock_eval_20260116_154403/summary.json deleted file mode 100644 index f1a70c5..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154403/summary.json +++ /dev/null @@ -1,34 +0,0 @@ -{ - "benchmark_name": "waa-mock", - "run_name": "waa-mock_eval_20260116_154403", - "model_id": "unknown", - "num_tasks": 3, - "num_success": 3, - "success_rate": 1.0, - "avg_score": 1.0, - "avg_steps": 1.0, - "avg_time_seconds": 0.2002551109956888, - "tasks": [ - { - "task_id": "browser_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - }, - { - "task_id": "office_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - }, - { - "task_id": "coding_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/execution.json b/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/execution.json deleted file mode 100644 index 3f810fb..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "browser_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.23708733299281448, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596243.157867 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596243.248106 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/screenshots/step_000.png deleted file mode 100644 index 05ab44d..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/screenshots/step_001.png deleted file mode 100644 index 1af63b2..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/task.json b/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/task.json deleted file mode 100644 index 3dfc721..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154403/tasks/browser_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "browser_1", - "instruction": "Mock task 1 in browser domain", - "domain": "browser", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/execution.json b/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/execution.json deleted file mode 100644 index 2e0406b..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "coding_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.181889040992246, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596243.522792 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596243.612757 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/screenshots/step_000.png deleted file mode 100644 index 0f5e838..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/screenshots/step_001.png deleted file mode 100644 index 501970c..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/task.json b/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/task.json deleted file mode 100644 index 69afec4..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154403/tasks/coding_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "coding_1", - "instruction": "Mock task 1 in coding domain", - "domain": "coding", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/execution.json b/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/execution.json deleted file mode 100644 index 0f8d217..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "office_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.18178895900200587, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596243.340576 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768596243.4305 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/screenshots/step_000.png deleted file mode 100644 index 90b990d..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/screenshots/step_001.png deleted file mode 100644 index 6869877..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/task.json b/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/task.json deleted file mode 100644 index 5b472c8..0000000 --- a/benchmark_results/waa-mock_eval_20260116_154403/tasks/office_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "office_1", - "instruction": "Mock task 1 in office domain", - "domain": "office", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173434/metadata.json b/benchmark_results/waa-mock_eval_20260116_173434/metadata.json deleted file mode 100644 index 5b79922..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173434/metadata.json +++ /dev/null @@ -1,6 +0,0 @@ -{ - "benchmark_name": "waa-mock", - "run_name": "waa-mock_eval_20260116_173434", - "model_id": "unknown", - "created_at": "2026-01-16T17:34:34.546728" -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173434/summary.json b/benchmark_results/waa-mock_eval_20260116_173434/summary.json deleted file mode 100644 index b0fb29d..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173434/summary.json +++ /dev/null @@ -1,34 +0,0 @@ -{ - "benchmark_name": "waa-mock", - "run_name": "waa-mock_eval_20260116_173434", - "model_id": "unknown", - "num_tasks": 3, - "num_success": 3, - "success_rate": 1.0, - "avg_score": 1.0, - "avg_steps": 1.0, - "avg_time_seconds": 0.029882624667758744, - "tasks": [ - { - "task_id": "browser_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - }, - { - "task_id": "office_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - }, - { - "task_id": "coding_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/execution.json b/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/execution.json deleted file mode 100644 index 615db2f..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "browser_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.03932516599888913, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768602874.574004 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768602874.586244 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/screenshots/step_000.png deleted file mode 100644 index 5723d1b..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/screenshots/step_001.png deleted file mode 100644 index 90542ac..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/task.json b/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/task.json deleted file mode 100644 index 3dfc721..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173434/tasks/browser_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "browser_1", - "instruction": "Mock task 1 in browser domain", - "domain": "browser", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/execution.json b/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/execution.json deleted file mode 100644 index 3314a47..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "coding_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.025248000005376525, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768602874.625577 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768602874.637558 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/screenshots/step_000.png deleted file mode 100644 index 6266031..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/screenshots/step_001.png deleted file mode 100644 index ea7ef35..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/task.json b/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/task.json deleted file mode 100644 index 69afec4..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173434/tasks/coding_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "coding_1", - "instruction": "Mock task 1 in coding domain", - "domain": "coding", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/execution.json b/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/execution.json deleted file mode 100644 index ccef4fd..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "office_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.02507470799901057, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768602874.599663 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768602874.611877 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/screenshots/step_000.png deleted file mode 100644 index 307f4dd..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/screenshots/step_001.png deleted file mode 100644 index ab53eec..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/task.json b/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/task.json deleted file mode 100644 index 5b472c8..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173434/tasks/office_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "office_1", - "instruction": "Mock task 1 in office domain", - "domain": "office", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173532/metadata.json b/benchmark_results/waa-mock_eval_20260116_173532/metadata.json deleted file mode 100644 index e65863e..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173532/metadata.json +++ /dev/null @@ -1,6 +0,0 @@ -{ - "benchmark_name": "waa-mock", - "run_name": "waa-mock_eval_20260116_173532", - "model_id": "unknown", - "created_at": "2026-01-16T17:35:32.997110" -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173532/summary.json b/benchmark_results/waa-mock_eval_20260116_173532/summary.json deleted file mode 100644 index dc3f624..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173532/summary.json +++ /dev/null @@ -1,27 +0,0 @@ -{ - "benchmark_name": "waa-mock", - "run_name": "waa-mock_eval_20260116_173532", - "model_id": "unknown", - "num_tasks": 2, - "num_success": 2, - "success_rate": 1.0, - "avg_score": 1.0, - "avg_steps": 1.0, - "avg_time_seconds": 0.031142332998570055, - "tasks": [ - { - "task_id": "browser_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - }, - { - "task_id": "office_1", - "success": true, - "score": 1.0, - "num_steps": 1, - "error": null - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/execution.json b/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/execution.json deleted file mode 100644 index b3d62c3..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "browser_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.03780483300215565, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768602933.023264 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768602933.035149 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/screenshots/step_000.png deleted file mode 100644 index 5723d1b..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/screenshots/step_001.png deleted file mode 100644 index 90542ac..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/task.json b/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/task.json deleted file mode 100644 index 3dfc721..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173532/tasks/browser_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "browser_1", - "instruction": "Mock task 1 in browser domain", - "domain": "browser", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/execution.json b/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/execution.json deleted file mode 100644 index 2d6a6a3..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/execution.json +++ /dev/null @@ -1,60 +0,0 @@ -{ - "task_id": "office_1", - "model_id": "unknown", - "success": true, - "score": 1.0, - "num_steps": 1, - "total_time_seconds": 0.024479832994984463, - "error": null, - "reason": "clicked=['4'], typed=False, done=False", - "steps": [ - { - "step_idx": 0, - "screenshot_path": "screenshots/step_000.png", - "action": { - "type": "click", - "x": null, - "y": null, - "target_node_id": "4", - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768602933.047806 - }, - { - "step_idx": 1, - "screenshot_path": "screenshots/step_001.png", - "action": { - "type": "done", - "x": null, - "y": null, - "target_node_id": null, - "target_bbox": null, - "target_role": null, - "target_name": null, - "text": null, - "key": null, - "modifiers": null, - "scroll_direction": null, - "scroll_amount": null, - "end_x": null, - "end_y": null, - "answer": null, - "raw_action": null - }, - "reasoning": null, - "timestamp": 1768602933.059971 - } - ] -} \ No newline at end of file diff --git a/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/screenshots/step_000.png b/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/screenshots/step_000.png deleted file mode 100644 index 307f4dd..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/screenshots/step_000.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/screenshots/step_001.png b/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/screenshots/step_001.png deleted file mode 100644 index ab53eec..0000000 Binary files a/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/screenshots/step_001.png and /dev/null differ diff --git a/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/task.json b/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/task.json deleted file mode 100644 index 5b472c8..0000000 --- a/benchmark_results/waa-mock_eval_20260116_173532/tasks/office_1/task.json +++ /dev/null @@ -1,11 +0,0 @@ -{ - "task_id": "office_1", - "instruction": "Mock task 1 in office domain", - "domain": "office", - "initial_state_ref": null, - "time_limit_steps": 15, - "raw_config": { - "mock": true - }, - "evaluation_spec": null -} \ No newline at end of file diff --git a/docs/artifacts/full/step_00_after.png b/docs/artifacts/full/step_00_after.png deleted file mode 100644 index 5238ebe..0000000 Binary files a/docs/artifacts/full/step_00_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_00_before.png b/docs/artifacts/full/step_00_before.png deleted file mode 100644 index b28a343..0000000 Binary files a/docs/artifacts/full/step_00_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_01_after.png b/docs/artifacts/full/step_01_after.png deleted file mode 100644 index ac6cead..0000000 Binary files a/docs/artifacts/full/step_01_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_01_before.png b/docs/artifacts/full/step_01_before.png deleted file mode 100644 index 5238ebe..0000000 Binary files a/docs/artifacts/full/step_01_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_02_after.png b/docs/artifacts/full/step_02_after.png deleted file mode 100644 index b707921..0000000 Binary files a/docs/artifacts/full/step_02_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_02_before.png b/docs/artifacts/full/step_02_before.png deleted file mode 100644 index ac6cead..0000000 Binary files a/docs/artifacts/full/step_02_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_03_after.png b/docs/artifacts/full/step_03_after.png deleted file mode 100644 index 9cbbbf4..0000000 Binary files a/docs/artifacts/full/step_03_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_03_before.png b/docs/artifacts/full/step_03_before.png deleted file mode 100644 index b707921..0000000 Binary files a/docs/artifacts/full/step_03_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_04_after.png b/docs/artifacts/full/step_04_after.png deleted file mode 100644 index d4e8d7b..0000000 Binary files a/docs/artifacts/full/step_04_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_04_before.png b/docs/artifacts/full/step_04_before.png deleted file mode 100644 index 9cbbbf4..0000000 Binary files a/docs/artifacts/full/step_04_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_05_after.png b/docs/artifacts/full/step_05_after.png deleted file mode 100644 index 338ed3a..0000000 Binary files a/docs/artifacts/full/step_05_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_05_before.png b/docs/artifacts/full/step_05_before.png deleted file mode 100644 index d4e8d7b..0000000 Binary files a/docs/artifacts/full/step_05_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_06_after.png b/docs/artifacts/full/step_06_after.png deleted file mode 100644 index 45bdc78..0000000 Binary files a/docs/artifacts/full/step_06_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_06_before.png b/docs/artifacts/full/step_06_before.png deleted file mode 100644 index 338ed3a..0000000 Binary files a/docs/artifacts/full/step_06_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_07_after.png b/docs/artifacts/full/step_07_after.png deleted file mode 100644 index 9e8af20..0000000 Binary files a/docs/artifacts/full/step_07_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_07_before.png b/docs/artifacts/full/step_07_before.png deleted file mode 100644 index 45bdc78..0000000 Binary files a/docs/artifacts/full/step_07_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_08_after.png b/docs/artifacts/full/step_08_after.png deleted file mode 100644 index 97a32e8..0000000 Binary files a/docs/artifacts/full/step_08_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_08_before.png b/docs/artifacts/full/step_08_before.png deleted file mode 100644 index 9e8af20..0000000 Binary files a/docs/artifacts/full/step_08_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_09_after.png b/docs/artifacts/full/step_09_after.png deleted file mode 100644 index ad17079..0000000 Binary files a/docs/artifacts/full/step_09_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_09_before.png b/docs/artifacts/full/step_09_before.png deleted file mode 100644 index 97a32e8..0000000 Binary files a/docs/artifacts/full/step_09_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_10_after.png b/docs/artifacts/full/step_10_after.png deleted file mode 100644 index 57f6fe2..0000000 Binary files a/docs/artifacts/full/step_10_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_10_before.png b/docs/artifacts/full/step_10_before.png deleted file mode 100644 index ad17079..0000000 Binary files a/docs/artifacts/full/step_10_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_11_after.png b/docs/artifacts/full/step_11_after.png deleted file mode 100644 index 0ad4163..0000000 Binary files a/docs/artifacts/full/step_11_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_11_before.png b/docs/artifacts/full/step_11_before.png deleted file mode 100644 index 57f6fe2..0000000 Binary files a/docs/artifacts/full/step_11_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_12_after.png b/docs/artifacts/full/step_12_after.png deleted file mode 100644 index 0b8df70..0000000 Binary files a/docs/artifacts/full/step_12_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_12_before.png b/docs/artifacts/full/step_12_before.png deleted file mode 100644 index 0ad4163..0000000 Binary files a/docs/artifacts/full/step_12_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_13_after.png b/docs/artifacts/full/step_13_after.png deleted file mode 100644 index a033c99..0000000 Binary files a/docs/artifacts/full/step_13_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_13_before.png b/docs/artifacts/full/step_13_before.png deleted file mode 100644 index 0b8df70..0000000 Binary files a/docs/artifacts/full/step_13_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_14_after.png b/docs/artifacts/full/step_14_after.png deleted file mode 100644 index 0d47824..0000000 Binary files a/docs/artifacts/full/step_14_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_14_before.png b/docs/artifacts/full/step_14_before.png deleted file mode 100644 index a033c99..0000000 Binary files a/docs/artifacts/full/step_14_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_15_after.png b/docs/artifacts/full/step_15_after.png deleted file mode 100644 index 6ce2d6f..0000000 Binary files a/docs/artifacts/full/step_15_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_15_before.png b/docs/artifacts/full/step_15_before.png deleted file mode 100644 index 0d47824..0000000 Binary files a/docs/artifacts/full/step_15_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_16_after.png b/docs/artifacts/full/step_16_after.png deleted file mode 100644 index 9f74534..0000000 Binary files a/docs/artifacts/full/step_16_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_16_before.png b/docs/artifacts/full/step_16_before.png deleted file mode 100644 index 6ce2d6f..0000000 Binary files a/docs/artifacts/full/step_16_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_17_after.png b/docs/artifacts/full/step_17_after.png deleted file mode 100644 index 9f74534..0000000 Binary files a/docs/artifacts/full/step_17_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_17_before.png b/docs/artifacts/full/step_17_before.png deleted file mode 100644 index 9f74534..0000000 Binary files a/docs/artifacts/full/step_17_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_18_after.png b/docs/artifacts/full/step_18_after.png deleted file mode 100644 index 69ff4a9..0000000 Binary files a/docs/artifacts/full/step_18_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_18_before.png b/docs/artifacts/full/step_18_before.png deleted file mode 100644 index 9f74534..0000000 Binary files a/docs/artifacts/full/step_18_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_19_after.png b/docs/artifacts/full/step_19_after.png deleted file mode 100644 index 10a824b..0000000 Binary files a/docs/artifacts/full/step_19_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_19_before.png b/docs/artifacts/full/step_19_before.png deleted file mode 100644 index 75af98b..0000000 Binary files a/docs/artifacts/full/step_19_before.png and /dev/null differ diff --git a/docs/artifacts/full/step_20_after.png b/docs/artifacts/full/step_20_after.png deleted file mode 100644 index 81a1f90..0000000 Binary files a/docs/artifacts/full/step_20_after.png and /dev/null differ diff --git a/docs/artifacts/full/step_20_before.png b/docs/artifacts/full/step_20_before.png deleted file mode 100644 index 10a824b..0000000 Binary files a/docs/artifacts/full/step_20_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_00_after.jpg b/docs/artifacts/thumbnails/step_00_after.jpg new file mode 100644 index 0000000..d4e11c8 Binary files /dev/null and b/docs/artifacts/thumbnails/step_00_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_00_after.png b/docs/artifacts/thumbnails/step_00_after.png deleted file mode 100644 index a02cd08..0000000 Binary files a/docs/artifacts/thumbnails/step_00_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_00_before.jpg b/docs/artifacts/thumbnails/step_00_before.jpg new file mode 100644 index 0000000..f412691 Binary files /dev/null and b/docs/artifacts/thumbnails/step_00_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_00_before.png b/docs/artifacts/thumbnails/step_00_before.png deleted file mode 100644 index 629d7e2..0000000 Binary files a/docs/artifacts/thumbnails/step_00_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_01_after.jpg b/docs/artifacts/thumbnails/step_01_after.jpg new file mode 100644 index 0000000..31a4996 Binary files /dev/null and b/docs/artifacts/thumbnails/step_01_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_01_after.png b/docs/artifacts/thumbnails/step_01_after.png deleted file mode 100644 index e97144a..0000000 Binary files a/docs/artifacts/thumbnails/step_01_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_01_before.jpg b/docs/artifacts/thumbnails/step_01_before.jpg new file mode 100644 index 0000000..d4e11c8 Binary files /dev/null and b/docs/artifacts/thumbnails/step_01_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_01_before.png b/docs/artifacts/thumbnails/step_01_before.png deleted file mode 100644 index a02cd08..0000000 Binary files a/docs/artifacts/thumbnails/step_01_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_02_after.jpg b/docs/artifacts/thumbnails/step_02_after.jpg new file mode 100644 index 0000000..0e76209 Binary files /dev/null and b/docs/artifacts/thumbnails/step_02_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_02_after.png b/docs/artifacts/thumbnails/step_02_after.png deleted file mode 100644 index 4a9e03e..0000000 Binary files a/docs/artifacts/thumbnails/step_02_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_02_before.jpg b/docs/artifacts/thumbnails/step_02_before.jpg new file mode 100644 index 0000000..31a4996 Binary files /dev/null and b/docs/artifacts/thumbnails/step_02_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_02_before.png b/docs/artifacts/thumbnails/step_02_before.png deleted file mode 100644 index e97144a..0000000 Binary files a/docs/artifacts/thumbnails/step_02_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_03_after.jpg b/docs/artifacts/thumbnails/step_03_after.jpg new file mode 100644 index 0000000..b0cc5cf Binary files /dev/null and b/docs/artifacts/thumbnails/step_03_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_03_after.png b/docs/artifacts/thumbnails/step_03_after.png deleted file mode 100644 index ce1981c..0000000 Binary files a/docs/artifacts/thumbnails/step_03_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_03_before.jpg b/docs/artifacts/thumbnails/step_03_before.jpg new file mode 100644 index 0000000..0e76209 Binary files /dev/null and b/docs/artifacts/thumbnails/step_03_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_03_before.png b/docs/artifacts/thumbnails/step_03_before.png deleted file mode 100644 index 4a9e03e..0000000 Binary files a/docs/artifacts/thumbnails/step_03_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_04_after.jpg b/docs/artifacts/thumbnails/step_04_after.jpg new file mode 100644 index 0000000..606453f Binary files /dev/null and b/docs/artifacts/thumbnails/step_04_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_04_after.png b/docs/artifacts/thumbnails/step_04_after.png deleted file mode 100644 index 959580e..0000000 Binary files a/docs/artifacts/thumbnails/step_04_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_04_before.jpg b/docs/artifacts/thumbnails/step_04_before.jpg new file mode 100644 index 0000000..b0cc5cf Binary files /dev/null and b/docs/artifacts/thumbnails/step_04_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_04_before.png b/docs/artifacts/thumbnails/step_04_before.png deleted file mode 100644 index ce1981c..0000000 Binary files a/docs/artifacts/thumbnails/step_04_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_05_after.jpg b/docs/artifacts/thumbnails/step_05_after.jpg new file mode 100644 index 0000000..2179447 Binary files /dev/null and b/docs/artifacts/thumbnails/step_05_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_05_after.png b/docs/artifacts/thumbnails/step_05_after.png deleted file mode 100644 index 21cbb1b..0000000 Binary files a/docs/artifacts/thumbnails/step_05_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_05_before.jpg b/docs/artifacts/thumbnails/step_05_before.jpg new file mode 100644 index 0000000..606453f Binary files /dev/null and b/docs/artifacts/thumbnails/step_05_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_05_before.png b/docs/artifacts/thumbnails/step_05_before.png deleted file mode 100644 index 959580e..0000000 Binary files a/docs/artifacts/thumbnails/step_05_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_06_after.jpg b/docs/artifacts/thumbnails/step_06_after.jpg new file mode 100644 index 0000000..6439f38 Binary files /dev/null and b/docs/artifacts/thumbnails/step_06_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_06_after.png b/docs/artifacts/thumbnails/step_06_after.png deleted file mode 100644 index 4e64436..0000000 Binary files a/docs/artifacts/thumbnails/step_06_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_06_before.jpg b/docs/artifacts/thumbnails/step_06_before.jpg new file mode 100644 index 0000000..2179447 Binary files /dev/null and b/docs/artifacts/thumbnails/step_06_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_06_before.png b/docs/artifacts/thumbnails/step_06_before.png deleted file mode 100644 index 21cbb1b..0000000 Binary files a/docs/artifacts/thumbnails/step_06_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_07_after.jpg b/docs/artifacts/thumbnails/step_07_after.jpg new file mode 100644 index 0000000..71d030c Binary files /dev/null and b/docs/artifacts/thumbnails/step_07_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_07_after.png b/docs/artifacts/thumbnails/step_07_after.png deleted file mode 100644 index 2be5e55..0000000 Binary files a/docs/artifacts/thumbnails/step_07_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_07_before.jpg b/docs/artifacts/thumbnails/step_07_before.jpg new file mode 100644 index 0000000..6439f38 Binary files /dev/null and b/docs/artifacts/thumbnails/step_07_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_07_before.png b/docs/artifacts/thumbnails/step_07_before.png deleted file mode 100644 index 4e64436..0000000 Binary files a/docs/artifacts/thumbnails/step_07_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_08_after.jpg b/docs/artifacts/thumbnails/step_08_after.jpg new file mode 100644 index 0000000..8241999 Binary files /dev/null and b/docs/artifacts/thumbnails/step_08_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_08_after.png b/docs/artifacts/thumbnails/step_08_after.png deleted file mode 100644 index e51f42d..0000000 Binary files a/docs/artifacts/thumbnails/step_08_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_08_before.jpg b/docs/artifacts/thumbnails/step_08_before.jpg new file mode 100644 index 0000000..71d030c Binary files /dev/null and b/docs/artifacts/thumbnails/step_08_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_08_before.png b/docs/artifacts/thumbnails/step_08_before.png deleted file mode 100644 index 2be5e55..0000000 Binary files a/docs/artifacts/thumbnails/step_08_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_09_after.jpg b/docs/artifacts/thumbnails/step_09_after.jpg new file mode 100644 index 0000000..4d5636a Binary files /dev/null and b/docs/artifacts/thumbnails/step_09_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_09_after.png b/docs/artifacts/thumbnails/step_09_after.png deleted file mode 100644 index d6ff229..0000000 Binary files a/docs/artifacts/thumbnails/step_09_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_09_before.jpg b/docs/artifacts/thumbnails/step_09_before.jpg new file mode 100644 index 0000000..8241999 Binary files /dev/null and b/docs/artifacts/thumbnails/step_09_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_09_before.png b/docs/artifacts/thumbnails/step_09_before.png deleted file mode 100644 index e51f42d..0000000 Binary files a/docs/artifacts/thumbnails/step_09_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_10_after.jpg b/docs/artifacts/thumbnails/step_10_after.jpg new file mode 100644 index 0000000..41f4d73 Binary files /dev/null and b/docs/artifacts/thumbnails/step_10_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_10_after.png b/docs/artifacts/thumbnails/step_10_after.png deleted file mode 100644 index 10d9751..0000000 Binary files a/docs/artifacts/thumbnails/step_10_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_10_before.jpg b/docs/artifacts/thumbnails/step_10_before.jpg new file mode 100644 index 0000000..4d5636a Binary files /dev/null and b/docs/artifacts/thumbnails/step_10_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_10_before.png b/docs/artifacts/thumbnails/step_10_before.png deleted file mode 100644 index d6ff229..0000000 Binary files a/docs/artifacts/thumbnails/step_10_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_11_after.jpg b/docs/artifacts/thumbnails/step_11_after.jpg new file mode 100644 index 0000000..0041dbe Binary files /dev/null and b/docs/artifacts/thumbnails/step_11_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_11_after.png b/docs/artifacts/thumbnails/step_11_after.png deleted file mode 100644 index 9e488cc..0000000 Binary files a/docs/artifacts/thumbnails/step_11_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_11_before.jpg b/docs/artifacts/thumbnails/step_11_before.jpg new file mode 100644 index 0000000..41f4d73 Binary files /dev/null and b/docs/artifacts/thumbnails/step_11_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_11_before.png b/docs/artifacts/thumbnails/step_11_before.png deleted file mode 100644 index 10d9751..0000000 Binary files a/docs/artifacts/thumbnails/step_11_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_12_after.jpg b/docs/artifacts/thumbnails/step_12_after.jpg new file mode 100644 index 0000000..8957d8a Binary files /dev/null and b/docs/artifacts/thumbnails/step_12_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_12_after.png b/docs/artifacts/thumbnails/step_12_after.png deleted file mode 100644 index 3642d64..0000000 Binary files a/docs/artifacts/thumbnails/step_12_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_12_before.jpg b/docs/artifacts/thumbnails/step_12_before.jpg new file mode 100644 index 0000000..0041dbe Binary files /dev/null and b/docs/artifacts/thumbnails/step_12_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_12_before.png b/docs/artifacts/thumbnails/step_12_before.png deleted file mode 100644 index 9e488cc..0000000 Binary files a/docs/artifacts/thumbnails/step_12_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_13_after.jpg b/docs/artifacts/thumbnails/step_13_after.jpg new file mode 100644 index 0000000..af16186 Binary files /dev/null and b/docs/artifacts/thumbnails/step_13_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_13_after.png b/docs/artifacts/thumbnails/step_13_after.png deleted file mode 100644 index 3ab6e1b..0000000 Binary files a/docs/artifacts/thumbnails/step_13_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_13_before.jpg b/docs/artifacts/thumbnails/step_13_before.jpg new file mode 100644 index 0000000..8957d8a Binary files /dev/null and b/docs/artifacts/thumbnails/step_13_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_13_before.png b/docs/artifacts/thumbnails/step_13_before.png deleted file mode 100644 index 3642d64..0000000 Binary files a/docs/artifacts/thumbnails/step_13_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_14_after.jpg b/docs/artifacts/thumbnails/step_14_after.jpg new file mode 100644 index 0000000..cca1a91 Binary files /dev/null and b/docs/artifacts/thumbnails/step_14_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_14_after.png b/docs/artifacts/thumbnails/step_14_after.png deleted file mode 100644 index c4273dc..0000000 Binary files a/docs/artifacts/thumbnails/step_14_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_14_before.jpg b/docs/artifacts/thumbnails/step_14_before.jpg new file mode 100644 index 0000000..af16186 Binary files /dev/null and b/docs/artifacts/thumbnails/step_14_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_14_before.png b/docs/artifacts/thumbnails/step_14_before.png deleted file mode 100644 index 3ab6e1b..0000000 Binary files a/docs/artifacts/thumbnails/step_14_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_15_after.jpg b/docs/artifacts/thumbnails/step_15_after.jpg new file mode 100644 index 0000000..c7cddbf Binary files /dev/null and b/docs/artifacts/thumbnails/step_15_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_15_after.png b/docs/artifacts/thumbnails/step_15_after.png deleted file mode 100644 index 6343b64..0000000 Binary files a/docs/artifacts/thumbnails/step_15_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_15_before.jpg b/docs/artifacts/thumbnails/step_15_before.jpg new file mode 100644 index 0000000..cca1a91 Binary files /dev/null and b/docs/artifacts/thumbnails/step_15_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_15_before.png b/docs/artifacts/thumbnails/step_15_before.png deleted file mode 100644 index c4273dc..0000000 Binary files a/docs/artifacts/thumbnails/step_15_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_16_after.jpg b/docs/artifacts/thumbnails/step_16_after.jpg new file mode 100644 index 0000000..d4d52cb Binary files /dev/null and b/docs/artifacts/thumbnails/step_16_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_16_after.png b/docs/artifacts/thumbnails/step_16_after.png deleted file mode 100644 index 8d3a369..0000000 Binary files a/docs/artifacts/thumbnails/step_16_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_16_before.jpg b/docs/artifacts/thumbnails/step_16_before.jpg new file mode 100644 index 0000000..c7cddbf Binary files /dev/null and b/docs/artifacts/thumbnails/step_16_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_16_before.png b/docs/artifacts/thumbnails/step_16_before.png deleted file mode 100644 index 6343b64..0000000 Binary files a/docs/artifacts/thumbnails/step_16_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_17_after.jpg b/docs/artifacts/thumbnails/step_17_after.jpg new file mode 100644 index 0000000..d4d52cb Binary files /dev/null and b/docs/artifacts/thumbnails/step_17_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_17_after.png b/docs/artifacts/thumbnails/step_17_after.png deleted file mode 100644 index 8d3a369..0000000 Binary files a/docs/artifacts/thumbnails/step_17_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_17_before.jpg b/docs/artifacts/thumbnails/step_17_before.jpg new file mode 100644 index 0000000..d4d52cb Binary files /dev/null and b/docs/artifacts/thumbnails/step_17_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_17_before.png b/docs/artifacts/thumbnails/step_17_before.png deleted file mode 100644 index 8d3a369..0000000 Binary files a/docs/artifacts/thumbnails/step_17_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_18_after.jpg b/docs/artifacts/thumbnails/step_18_after.jpg new file mode 100644 index 0000000..35e6e7e Binary files /dev/null and b/docs/artifacts/thumbnails/step_18_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_18_after.png b/docs/artifacts/thumbnails/step_18_after.png deleted file mode 100644 index 2a6c757..0000000 Binary files a/docs/artifacts/thumbnails/step_18_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_18_before.jpg b/docs/artifacts/thumbnails/step_18_before.jpg new file mode 100644 index 0000000..d4d52cb Binary files /dev/null and b/docs/artifacts/thumbnails/step_18_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_18_before.png b/docs/artifacts/thumbnails/step_18_before.png deleted file mode 100644 index 8d3a369..0000000 Binary files a/docs/artifacts/thumbnails/step_18_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_19_after.jpg b/docs/artifacts/thumbnails/step_19_after.jpg new file mode 100644 index 0000000..e9a0f51 Binary files /dev/null and b/docs/artifacts/thumbnails/step_19_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_19_after.png b/docs/artifacts/thumbnails/step_19_after.png deleted file mode 100644 index 33456de..0000000 Binary files a/docs/artifacts/thumbnails/step_19_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_19_before.jpg b/docs/artifacts/thumbnails/step_19_before.jpg new file mode 100644 index 0000000..ad691b9 Binary files /dev/null and b/docs/artifacts/thumbnails/step_19_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_19_before.png b/docs/artifacts/thumbnails/step_19_before.png deleted file mode 100644 index 793eedb..0000000 Binary files a/docs/artifacts/thumbnails/step_19_before.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_20_after.jpg b/docs/artifacts/thumbnails/step_20_after.jpg new file mode 100644 index 0000000..77f15e9 Binary files /dev/null and b/docs/artifacts/thumbnails/step_20_after.jpg differ diff --git a/docs/artifacts/thumbnails/step_20_after.png b/docs/artifacts/thumbnails/step_20_after.png deleted file mode 100644 index 2151cd8..0000000 Binary files a/docs/artifacts/thumbnails/step_20_after.png and /dev/null differ diff --git a/docs/artifacts/thumbnails/step_20_before.jpg b/docs/artifacts/thumbnails/step_20_before.jpg new file mode 100644 index 0000000..e9a0f51 Binary files /dev/null and b/docs/artifacts/thumbnails/step_20_before.jpg differ diff --git a/docs/artifacts/thumbnails/step_20_before.png b/docs/artifacts/thumbnails/step_20_before.png deleted file mode 100644 index 33456de..0000000 Binary files a/docs/artifacts/thumbnails/step_20_before.png and /dev/null differ diff --git a/docs/demo_review.md b/docs/demo_review.md index 85c8fa1..6acd564 100644 --- a/docs/demo_review.md +++ b/docs/demo_review.md @@ -18,7 +18,7 @@ ### Step 1: Right-click on the "Sheet1" tab at the bottom and select "Insert Sheet" or "New Sheet" -[![before](artifacts/thumbnails/step_00_before.png)](artifacts/full/step_00_before.png) [![after](artifacts/thumbnails/step_00_after.png)](artifacts/full/step_00_after.png) +[![before](artifacts/thumbnails/step_00_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_00_before.png) [![after](artifacts/thumbnails/step_00_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_00_after.png) **Ground truth:** Right-click on the "Sheet1" tab at the bottom and select "Insert Sheet" or "New Sheet" @@ -35,7 +35,7 @@ ### Step 2: Click cell A1 and type "Year" -[![before](artifacts/thumbnails/step_01_before.png)](artifacts/full/step_01_before.png) [![after](artifacts/thumbnails/step_01_after.png)](artifacts/full/step_01_after.png) +[![before](artifacts/thumbnails/step_01_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_01_before.png) [![after](artifacts/thumbnails/step_01_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_01_after.png) **Ground truth:** Click cell A1 and type "Year" @@ -52,7 +52,7 @@ ### Step 3: Press Tab and type "CA changes" -[![before](artifacts/thumbnails/step_02_before.png)](artifacts/full/step_02_before.png) [![after](artifacts/thumbnails/step_02_after.png)](artifacts/full/step_02_after.png) +[![before](artifacts/thumbnails/step_02_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_02_before.png) [![after](artifacts/thumbnails/step_02_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_02_after.png) **Ground truth:** Press Tab and type "CA changes" @@ -69,7 +69,7 @@ ### Step 4: Press Tab and type "FA changes" -[![before](artifacts/thumbnails/step_03_before.png)](artifacts/full/step_03_before.png) [![after](artifacts/thumbnails/step_03_after.png)](artifacts/full/step_03_after.png) +[![before](artifacts/thumbnails/step_03_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_03_before.png) [![after](artifacts/thumbnails/step_03_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_03_after.png) **Ground truth:** Press Tab and type "FA changes" @@ -86,7 +86,7 @@ ### Step 5: Press Tab and type "OA changes" -[![before](artifacts/thumbnails/step_04_before.png)](artifacts/full/step_04_before.png) [![after](artifacts/thumbnails/step_04_after.png)](artifacts/full/step_04_after.png) +[![before](artifacts/thumbnails/step_04_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_04_before.png) [![after](artifacts/thumbnails/step_04_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_04_after.png) **Ground truth:** Press Tab and type "OA changes" @@ -103,7 +103,7 @@ ### Step 6: Click cell A2 and type "2015" -[![before](artifacts/thumbnails/step_05_before.png)](artifacts/full/step_05_before.png) [![after](artifacts/thumbnails/step_05_after.png)](artifacts/full/step_05_after.png) +[![before](artifacts/thumbnails/step_05_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_05_before.png) [![after](artifacts/thumbnails/step_05_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_05_after.png) **Ground truth:** Click cell A2 and type "2015" @@ -120,7 +120,7 @@ ### Step 7: Press Enter and type "2016" -[![before](artifacts/thumbnails/step_06_before.png)](artifacts/full/step_06_before.png) [![after](artifacts/thumbnails/step_06_after.png)](artifacts/full/step_06_after.png) +[![before](artifacts/thumbnails/step_06_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_06_before.png) [![after](artifacts/thumbnails/step_06_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_06_after.png) **Ground truth:** Press Enter and type "2016" @@ -137,7 +137,7 @@ ### Step 8: Press Enter and type "2017" -[![before](artifacts/thumbnails/step_07_before.png)](artifacts/full/step_07_before.png) [![after](artifacts/thumbnails/step_07_after.png)](artifacts/full/step_07_after.png) +[![before](artifacts/thumbnails/step_07_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_07_before.png) [![after](artifacts/thumbnails/step_07_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_07_after.png) **Ground truth:** Press Enter and type "2017" @@ -154,7 +154,7 @@ ### Step 9: Press Enter and type "2018" -[![before](artifacts/thumbnails/step_08_before.png)](artifacts/full/step_08_before.png) [![after](artifacts/thumbnails/step_08_after.png)](artifacts/full/step_08_after.png) +[![before](artifacts/thumbnails/step_08_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_08_before.png) [![after](artifacts/thumbnails/step_08_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_08_after.png) **Ground truth:** Press Enter and type "2018" @@ -171,7 +171,7 @@ ### Step 10: Press Enter and type "2019" -[![before](artifacts/thumbnails/step_09_before.png)](artifacts/full/step_09_before.png) [![after](artifacts/thumbnails/step_09_after.png)](artifacts/full/step_09_after.png) +[![before](artifacts/thumbnails/step_09_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_09_before.png) [![after](artifacts/thumbnails/step_09_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_09_after.png) **Ground truth:** Press Enter and type "2019" @@ -188,7 +188,7 @@ ### Step 11: Click cell B2 and type "=(Sheet1.B3-Sheet1.B2)/Sheet1.B2" -[![before](artifacts/thumbnails/step_10_before.png)](artifacts/full/step_10_before.png) [![after](artifacts/thumbnails/step_10_after.png)](artifacts/full/step_10_after.png) +[![before](artifacts/thumbnails/step_10_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_10_before.png) [![after](artifacts/thumbnails/step_10_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_10_after.png) **Ground truth:** Click cell B2 and type "=(Sheet1.B3-Sheet1.B2)/Sheet1.B2" @@ -205,7 +205,7 @@ ### Step 12: Press Enter -[![before](artifacts/thumbnails/step_11_before.png)](artifacts/full/step_11_before.png) [![after](artifacts/thumbnails/step_11_after.png)](artifacts/full/step_11_after.png) +[![before](artifacts/thumbnails/step_11_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_11_before.png) [![after](artifacts/thumbnails/step_11_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_11_after.png) **Ground truth:** Press Enter @@ -222,7 +222,7 @@ ### Step 13: Click cell B2, then drag the fill handle down to B6 -[![before](artifacts/thumbnails/step_12_before.png)](artifacts/full/step_12_before.png) [![after](artifacts/thumbnails/step_12_after.png)](artifacts/full/step_12_after.png) +[![before](artifacts/thumbnails/step_12_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_12_before.png) [![after](artifacts/thumbnails/step_12_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_12_after.png) **Ground truth:** Click cell B2, then drag the fill handle down to B6 @@ -239,7 +239,7 @@ ### Step 14: Click cell C2 and type "=(Sheet1.C3-Sheet1.C2)/Sheet1.C2" -[![before](artifacts/thumbnails/step_13_before.png)](artifacts/full/step_13_before.png) [![after](artifacts/thumbnails/step_13_after.png)](artifacts/full/step_13_after.png) +[![before](artifacts/thumbnails/step_13_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_13_before.png) [![after](artifacts/thumbnails/step_13_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_13_after.png) **Ground truth:** Click cell C2 and type "=(Sheet1.C3-Sheet1.C2)/Sheet1.C2" @@ -256,7 +256,7 @@ ### Step 15: Press Enter -[![before](artifacts/thumbnails/step_14_before.png)](artifacts/full/step_14_before.png) [![after](artifacts/thumbnails/step_14_after.png)](artifacts/full/step_14_after.png) +[![before](artifacts/thumbnails/step_14_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_14_before.png) [![after](artifacts/thumbnails/step_14_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_14_after.png) **Ground truth:** Press Enter @@ -273,7 +273,7 @@ ### Step 16: Click cell C2, then drag the fill handle down to C6 -[![before](artifacts/thumbnails/step_15_before.png)](artifacts/full/step_15_before.png) [![after](artifacts/thumbnails/step_15_after.png)](artifacts/full/step_15_after.png) +[![before](artifacts/thumbnails/step_15_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_15_before.png) [![after](artifacts/thumbnails/step_15_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_15_after.png) **Ground truth:** Click cell C2, then drag the fill handle down to C6 @@ -290,7 +290,7 @@ ### Step 17: Click cell D2 and type "=(Sheet1.D3-Sheet1.D2)/Sheet1.D2" -[![before](artifacts/thumbnails/step_16_before.png)](artifacts/full/step_16_before.png) [![after](artifacts/thumbnails/step_16_after.png)](artifacts/full/step_16_after.png) +[![before](artifacts/thumbnails/step_16_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_16_before.png) [![after](artifacts/thumbnails/step_16_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_16_after.png) **Ground truth:** Click cell D2 and type "=(Sheet1.D3-Sheet1.D2)/Sheet1.D2" @@ -307,7 +307,7 @@ ### Step 18: Press Enter -[![before](artifacts/thumbnails/step_17_before.png)](artifacts/full/step_17_before.png) [![after](artifacts/thumbnails/step_17_after.png)](artifacts/full/step_17_after.png) +[![before](artifacts/thumbnails/step_17_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_17_before.png) [![after](artifacts/thumbnails/step_17_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_17_after.png) **Ground truth:** Press Enter @@ -324,7 +324,7 @@ ### Step 19: Click cell D2, then drag the fill handle down to D6 -[![before](artifacts/thumbnails/step_18_before.png)](artifacts/full/step_18_before.png) [![after](artifacts/thumbnails/step_18_after.png)](artifacts/full/step_18_after.png) +[![before](artifacts/thumbnails/step_18_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_18_before.png) [![after](artifacts/thumbnails/step_18_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_18_after.png) **Ground truth:** Click cell D2, then drag the fill handle down to D6 @@ -341,7 +341,7 @@ ### Step 20: Click and drag to select cells B2:D6 -[![before](artifacts/thumbnails/step_19_before.png)](artifacts/full/step_19_before.png) [![after](artifacts/thumbnails/step_19_after.png)](artifacts/full/step_19_after.png) +[![before](artifacts/thumbnails/step_19_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_19_before.png) [![after](artifacts/thumbnails/step_19_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_19_after.png) **Ground truth:** Click and drag to select cells B2:D6 @@ -358,7 +358,7 @@ ### Step 21: Click the % button in the toolbar (or press Ctrl+Shift+5) -[![before](artifacts/thumbnails/step_20_before.png)](artifacts/full/step_20_before.png) [![after](artifacts/thumbnails/step_20_after.png)](artifacts/full/step_20_after.png) +[![before](artifacts/thumbnails/step_20_before.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_20_before.png) [![after](artifacts/thumbnails/step_20_after.jpg)](../waa_recordings/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f-WOS/step_20_after.png) **Ground truth:** Click the % button in the toolbar (or press Ctrl+Shift+5) diff --git a/scripts/generate_demo_review.py b/scripts/generate_demo_review.py index 8c741c5..bb874b5 100644 --- a/scripts/generate_demo_review.py +++ b/scripts/generate_demo_review.py @@ -17,8 +17,8 @@ from __future__ import annotations import json +import os import re -import shutil import sys from pathlib import Path @@ -54,15 +54,21 @@ def _parse_demo_steps(demo_text: str) -> dict[int, str]: def _create_thumbnail(src: Path, dst: Path, width: int = THUMBNAIL_WIDTH) -> None: - """Resize an image to the given width, preserving aspect ratio.""" + """Resize an image to the given width, preserving aspect ratio. + + Saves as JPEG for smaller file sizes (thumbnails are for preview only). + """ with Image.open(src) as img: if img.width <= width: - shutil.copy2(src, dst) + out = img.convert("RGB") if img.mode in ("RGBA", "P") else img + out.save(dst, format="JPEG", quality=80, optimize=True) return ratio = width / img.width new_height = int(img.height * ratio) resized = img.resize((width, new_height), Image.LANCZOS) - resized.save(dst, optimize=True) + if resized.mode in ("RGBA", "P"): + resized = resized.convert("RGB") + resized.save(dst, format="JPEG", quality=80, optimize=True) def _relpath(target: Path, start: Path) -> str: @@ -70,7 +76,6 @@ def _relpath(target: Path, start: Path) -> str: try: return str(target.resolve().relative_to(start.resolve())) except ValueError: - import os return os.path.relpath(target.resolve(), start.resolve()) @@ -138,13 +143,10 @@ def main( else: print(f"Warning: VLM demo not found at {vlm_demo_path}") - # --- Create thumbnails and copy full-res originals --- + # --- Create JPEG thumbnails and reference originals for full-res --- thumb_dir = output_path.parent / "artifacts" / "thumbnails" thumb_dir.mkdir(parents=True, exist_ok=True) - full_dir = output_path.parent / "artifacts" / "full" - full_dir.mkdir(parents=True, exist_ok=True) - thumbnail_map: dict[str, Path] = {} full_map: dict[str, Path] = {} for i in range(num_steps): @@ -152,17 +154,13 @@ def main( name = f"step_{i:02d}_{suffix}" src = recording_dir / f"{name}.png" if src.exists(): - dst = thumb_dir / f"{name}.png" + dst = thumb_dir / f"{name}.jpg" _create_thumbnail(src, dst, width=thumbnail_width) thumbnail_map[name] = dst - # Copy full-resolution original - full_dst = full_dir / f"{name}.png" - shutil.copy2(src, full_dst) - full_map[name] = full_dst + # Link to the original in waa_recordings/ (no copy needed) + full_map[name] = src print(f"Created {len(thumbnail_map)} thumbnails in {thumb_dir}") - if full_map: - print(f"Copied {len(full_map)} full-resolution images to {full_dir}") # --- Build markdown --- md_dir = output_path.parent