diff --git a/benchmarks/computer_use/cases/leabench_easily_clean_2026-06-12.jsonl b/benchmarks/computer_use/cases/leabench_easily_clean_2026-06-12.jsonl new file mode 100644 index 000000000..a9941a1b4 --- /dev/null +++ b/benchmarks/computer_use/cases/leabench_easily_clean_2026-06-12.jsonl @@ -0,0 +1,21 @@ +{"case_id": "easily_rec_shot_0001_72_538", "screenshot_path": "/tmp/easily_session/shots/shot_0001_full.png", "task": {"intent": "cliquer sur « 25003362 »", "target_text": "25003362", "current_window": "Dossier 25003284 — MOREL Catherine — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « 25003362 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0281, "y_pct": 0.3362, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "25003362", "ocr_dist": 0.0067, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0002_380_919", "screenshot_path": "/tmp/easily_session/shots/shot_0002_full.png", "task": {"intent": "cliquer sur « iméicamentset-substancs »", "target_text": "iméicamentset-substancs", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « iméicamentset-substancs » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.1484, "y_pct": 0.5744, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "iméicamentset-substancs", "ocr_dist": 0.0107, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0003_388_380", "screenshot_path": "/tmp/easily_session/shots/shot_0003_full.png", "task": {"intent": "cliquer sur « cliniques »", "target_text": "cliniques", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « cliniques » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.1516, "y_pct": 0.2375, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "cliniques", "ocr_dist": 0.0075, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0004_552_381", "screenshot_path": "/tmp/easily_session/shots/shot_0004_full.png", "task": {"intent": "cliquer sur « Imagerie »", "target_text": "Imagerie", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Imagerie » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2156, "y_pct": 0.2381, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Imagerie", "ocr_dist": 0.009, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0005_685_385", "screenshot_path": "/tmp/easily_session/shots/shot_0005_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2676, "y_pct": 0.2406, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "médicales", "ocr_dist": 0.0127, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0007_947_381", "screenshot_path": "/tmp/easily_session/shots/shot_0007_full.png", "task": {"intent": "cliquer sur « Urgences »", "target_text": "Urgences", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Urgences » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3699, "y_pct": 0.2381, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Urgences", "ocr_dist": 0.0057, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0011_72_288", "screenshot_path": "/tmp/easily_session/shots/shot_0011_full.png", "task": {"intent": "cliquer sur « Patients »", "target_text": "Patients", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Patients » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0281, "y_pct": 0.18, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Patients", "ocr_dist": 0.0109, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0012_95_613", "screenshot_path": "/tmp/easily_session/shots/shot_0012_full.png", "task": {"intent": "cliquer sur « 25003451 »", "target_text": "25003451", "current_window": "Dossier 25003284 — MOREL Catherine — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « 25003451 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0371, "y_pct": 0.3831, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "25003451", "ocr_dist": 0.0111, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0014_910_378", "screenshot_path": "/tmp/easily_session/shots/shot_0014_full.png", "task": {"intent": "cliquer sur « Synthèse »", "target_text": "Synthèse", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Synthèse » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3555, "y_pct": 0.2362, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Synthèse", "ocr_dist": 0.0172, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0015_638_381", "screenshot_path": "/tmp/easily_session/shots/shot_0015_full.png", "task": {"intent": "cliquer sur « Notes »", "target_text": "Notes", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Notes » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2492, "y_pct": 0.2381, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Notes", "ocr_dist": 0.0051, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0016_970_393", "screenshot_path": "/tmp/easily_session/shots/shot_0016_full.png", "task": {"intent": "cliquer sur « Urgences »", "target_text": "Urgences", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Urgences » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3789, "y_pct": 0.2456, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Urgences", "ocr_dist": 0.008, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0020_695_379", "screenshot_path": "/tmp/easily_session/shots/shot_0020_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2715, "y_pct": 0.2369, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "médicales", "ocr_dist": 0.0057, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0021_127_395", "screenshot_path": "/tmp/easily_session/shots/shot_0021_full.png", "task": {"intent": "cliquer sur « d'admission »", "target_text": "d'admission", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « d'admission » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0496, "y_pct": 0.2469, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "d'admission", "ocr_dist": 0.0089, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0022_73_304", "screenshot_path": "/tmp/easily_session/shots/shot_0022_full.png", "task": {"intent": "cliquer sur « IPP: »", "target_text": "IPP:", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « IPP: » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0285, "y_pct": 0.19, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "IPP:", "ocr_dist": 0.0147, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0024_84_269", "screenshot_path": "/tmp/easily_session/shots/shot_0024_full.png", "task": {"intent": "cliquer sur « Patients »", "target_text": "Patients", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Patients » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0328, "y_pct": 0.1681, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Patients", "ocr_dist": 0.0018, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0025_67_790", "screenshot_path": "/tmp/easily_session/shots/shot_0025_full.png", "task": {"intent": "cliquer sur « 25012257 »", "target_text": "25012257", "current_window": "Dossier 25003284 — MOREL Catherine — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « 25012257 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0262, "y_pct": 0.4938, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "25012257", "ocr_dist": 0.0053, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0028_770_385", "screenshot_path": "/tmp/easily_session/shots/shot_0028_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3008, "y_pct": 0.2406, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "médicales", "ocr_dist": 0.0166, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0029_766_378", "screenshot_path": "/tmp/easily_session/shots/shot_0029_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2992, "y_pct": 0.2362, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "médicales", "ocr_dist": 0.0196, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0032_954_375", "screenshot_path": "/tmp/easily_session/shots/shot_0032_full.png", "task": {"intent": "cliquer sur « Urgences »", "target_text": "Urgences", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Urgences » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3727, "y_pct": 0.2344, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Urgences", "ocr_dist": 0.0095, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0037_2028_1290", "screenshot_path": "/tmp/easily_session/shots/shot_0037_full.png", "task": {"intent": "cliquer sur « terminé »", "target_text": "terminé", "current_window": "unknown_window", "expected_next_window": "", "question": "L'élément « terminé » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.7922, "y_pct": 0.8063, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "terminé", "ocr_dist": 0.0395, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0041_2010_1013", "screenshot_path": "/tmp/easily_session/shots/shot_0041_full.png", "task": {"intent": "cliquer sur « mémorisées »", "target_text": "mémorisées", "current_window": "unknown_window", "expected_next_window": "", "question": "L'élément « mémorisées » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.7852, "y_pct": 0.6331, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "mémorisées", "ocr_dist": 0.0454, "needs_human_check": false}} diff --git a/benchmarks/computer_use/cases/leabench_easily_clean_v2.jsonl b/benchmarks/computer_use/cases/leabench_easily_clean_v2.jsonl new file mode 100644 index 000000000..03ed9b02d --- /dev/null +++ b/benchmarks/computer_use/cases/leabench_easily_clean_v2.jsonl @@ -0,0 +1,15 @@ +{"case_id": "easily_shot_0001_72_538", "screenshot_path": "/tmp/easily_session/shots/shot_0001_full.png", "task": {"intent": "cliquer sur « 25003362 »", "target_text": "25003362", "current_window": "Dossier 25003284 — MOREL Catherine — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « 25003362 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0281, "y_pct": 0.3362, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0003_388_380", "screenshot_path": "/tmp/easily_session/shots/shot_0003_full.png", "task": {"intent": "cliquer sur « cliniques »", "target_text": "cliniques", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « cliniques » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.1516, "y_pct": 0.2375, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0004_552_381", "screenshot_path": "/tmp/easily_session/shots/shot_0004_full.png", "task": {"intent": "cliquer sur « Imagerie »", "target_text": "Imagerie", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Imagerie » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2156, "y_pct": 0.2381, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0005_685_385", "screenshot_path": "/tmp/easily_session/shots/shot_0005_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2676, "y_pct": 0.2406, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0012_95_613", "screenshot_path": "/tmp/easily_session/shots/shot_0012_full.png", "task": {"intent": "cliquer sur « 25003451 »", "target_text": "25003451", "current_window": "Dossier 25003284 — MOREL Catherine — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « 25003451 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0371, "y_pct": 0.3831, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0013_2393_1215", "screenshot_path": "/tmp/easily_session/shots/shot_0013_full.png", "task": {"intent": "cliquer sur « Oui »", "target_text": "Oui", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Oui » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9348, "y_pct": 0.7594, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0014_910_378", "screenshot_path": "/tmp/easily_session/shots/shot_0014_full.png", "task": {"intent": "cliquer sur « Synthèse »", "target_text": "Synthèse", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Synthèse » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3555, "y_pct": 0.2362, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0015_638_381", "screenshot_path": "/tmp/easily_session/shots/shot_0015_full.png", "task": {"intent": "cliquer sur « Notes »", "target_text": "Notes", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Notes » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2492, "y_pct": 0.2381, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0020_695_379", "screenshot_path": "/tmp/easily_session/shots/shot_0020_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2715, "y_pct": 0.2369, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0021_127_395", "screenshot_path": "/tmp/easily_session/shots/shot_0021_full.png", "task": {"intent": "cliquer sur « d'admission »", "target_text": "d'admission", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « d'admission » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0496, "y_pct": 0.2469, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0022_73_304", "screenshot_path": "/tmp/easily_session/shots/shot_0022_full.png", "task": {"intent": "cliquer sur « IPP: »", "target_text": "IPP:", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « IPP: » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0285, "y_pct": 0.19, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": false, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0023_73_304", "screenshot_path": "/tmp/easily_session/shots/shot_0023_full.png", "task": {"intent": "cliquer sur « IPP »", "target_text": "IPP", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « IPP » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0285, "y_pct": 0.19, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": false, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0025_67_790", "screenshot_path": "/tmp/easily_session/shots/shot_0025_full.png", "task": {"intent": "cliquer sur « 25012257 »", "target_text": "25012257", "current_window": "Dossier 25003284 — MOREL Catherine — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « 25012257 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0262, "y_pct": 0.4938, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0028_770_385", "screenshot_path": "/tmp/easily_session/shots/shot_0028_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3008, "y_pct": 0.2406, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": true, "ocr_occurrences": 1}} +{"case_id": "easily_shot_0037_2028_1290", "screenshot_path": "/tmp/easily_session/shots/shot_0037_full.png", "task": {"intent": "cliquer sur « terminé »", "target_text": "terminé", "current_window": "unknown_window", "expected_next_window": "", "question": "L'élément « terminé » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.7922, "y_pct": 0.8063, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "contained_in_line": false, "ocr_occurrences": 1}} diff --git a/benchmarks/computer_use/cases/leabench_easily_record_2026-06-12.jsonl b/benchmarks/computer_use/cases/leabench_easily_record_2026-06-12.jsonl new file mode 100644 index 000000000..992392380 --- /dev/null +++ b/benchmarks/computer_use/cases/leabench_easily_record_2026-06-12.jsonl @@ -0,0 +1,41 @@ +{"case_id": "easily_rec_shot_0001_72_538", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0001_full.png", "task": {"intent": "cliquer sur « 25003362 »", "target_text": "25003362", "current_window": "Dossier 25003284 — MOREL Catherine — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « 25003362 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0281, "y_pct": 0.3362, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "25003362", "ocr_dist": 0.0067, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0002_380_919", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0002_full.png", "task": {"intent": "cliquer sur « iméicamentset-substancs »", "target_text": "iméicamentset-substancs", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « iméicamentset-substancs » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.1484, "y_pct": 0.5744, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "iméicamentset-substancs", "ocr_dist": 0.0107, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0003_388_380", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0003_full.png", "task": {"intent": "cliquer sur « cliniques »", "target_text": "cliniques", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « cliniques » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.1516, "y_pct": 0.2375, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "cliniques", "ocr_dist": 0.0075, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0004_552_381", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0004_full.png", "task": {"intent": "cliquer sur « Imagerie »", "target_text": "Imagerie", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Imagerie » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2156, "y_pct": 0.2381, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Imagerie", "ocr_dist": 0.009, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0005_685_385", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0005_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2676, "y_pct": 0.2406, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "médicales", "ocr_dist": 0.0127, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0006_2547_962", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0006_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9949, "y_pct": 0.6012, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0007_947_381", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0007_full.png", "task": {"intent": "cliquer sur « Urgences »", "target_text": "Urgences", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Urgences » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3699, "y_pct": 0.2381, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Urgences", "ocr_dist": 0.0057, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0008_903_552", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0008_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3527, "y_pct": 0.345, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0009_903_552", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0009_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3527, "y_pct": 0.345, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0010_2546_1042", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0010_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9945, "y_pct": 0.6512, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0011_72_288", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0011_full.png", "task": {"intent": "cliquer sur « Patients »", "target_text": "Patients", "current_window": "Dossier 25003362 — LAFFONT Alice — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Patients » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0281, "y_pct": 0.18, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Patients", "ocr_dist": 0.0109, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0012_95_613", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0012_full.png", "task": {"intent": "cliquer sur « 25003451 »", "target_text": "25003451", "current_window": "Dossier 25003284 — MOREL Catherine — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « 25003451 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0371, "y_pct": 0.3831, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "25003451", "ocr_dist": 0.0111, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0013_2393_1215", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0013_full.png", "task": {"intent": "cliquer sur « Oui »", "target_text": "Oui", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Oui » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9348, "y_pct": 0.7594, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Oui", "ocr_dist": 0.0036, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0014_910_378", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0014_full.png", "task": {"intent": "cliquer sur « Synthèse »", "target_text": "Synthèse", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Synthèse » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3555, "y_pct": 0.2362, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Synthèse", "ocr_dist": 0.0172, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0015_638_381", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0015_full.png", "task": {"intent": "cliquer sur « Notes »", "target_text": "Notes", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Notes » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2492, "y_pct": 0.2381, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Notes", "ocr_dist": 0.0051, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0016_970_393", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0016_full.png", "task": {"intent": "cliquer sur « Urgences »", "target_text": "Urgences", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Urgences » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3789, "y_pct": 0.2456, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Urgences", "ocr_dist": 0.008, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0017_2506_1205", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0017_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9789, "y_pct": 0.7531, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0018_2549_1203", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0018_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9957, "y_pct": 0.7519, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0019_2557_244", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0019_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9988, "y_pct": 0.1525, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0020_695_379", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0020_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2715, "y_pct": 0.2369, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "médicales", "ocr_dist": 0.0057, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0021_127_395", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0021_full.png", "task": {"intent": "cliquer sur « d'admission »", "target_text": "d'admission", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « d'admission » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0496, "y_pct": 0.2469, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "d'admission", "ocr_dist": 0.0089, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0022_73_304", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0022_full.png", "task": {"intent": "cliquer sur « IPP: »", "target_text": "IPP:", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « IPP: » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0285, "y_pct": 0.19, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "IPP:", "ocr_dist": 0.0147, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0023_73_304", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0023_full.png", "task": {"intent": "cliquer sur « IPP »", "target_text": "IPP", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « IPP » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0285, "y_pct": 0.19, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "IPP", "ocr_dist": 0.0163, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0024_84_269", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0024_full.png", "task": {"intent": "cliquer sur « Patients »", "target_text": "Patients", "current_window": "Dossier 25003451 — ROUX Lou — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Patients » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0328, "y_pct": 0.1681, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Patients", "ocr_dist": 0.0018, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0025_67_790", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0025_full.png", "task": {"intent": "cliquer sur « 25012257 »", "target_text": "25012257", "current_window": "Dossier 25003284 — MOREL Catherine — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « 25012257 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.0262, "y_pct": 0.4938, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "25012257", "ocr_dist": 0.0053, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0026_2545_1356", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0026_full.png", "task": {"intent": "cliquer sur « 95 »", "target_text": "95", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « 95 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9941, "y_pct": 0.8475, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "95", "ocr_dist": 0.0291, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0027_2541_284", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0027_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9926, "y_pct": 0.1775, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0028_770_385", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0028_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3008, "y_pct": 0.2406, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "médicales", "ocr_dist": 0.0166, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0029_766_378", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0029_full.png", "task": {"intent": "cliquer sur « médicales »", "target_text": "médicales", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « médicales » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.2992, "y_pct": 0.2362, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "médicales", "ocr_dist": 0.0196, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0030_2546_595", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0030_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9945, "y_pct": 0.3719, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0031_2558_1415", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0031_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9992, "y_pct": 0.8844, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0032_954_375", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0032_full.png", "task": {"intent": "cliquer sur « Urgences »", "target_text": "Urgences", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « Urgences » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.3727, "y_pct": 0.2344, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "Urgences", "ocr_dist": 0.0095, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0033_2544_704", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0033_full.png", "task": {"intent": "cliquer sur la cible", "target_text": "", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "Clique sur l'élément ciblé."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.9938, "y_pct": 0.44, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "", "ocr_dist": null, "needs_human_check": true}} +{"case_id": "easily_rec_shot_0034_2188_1570", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0034_full.png", "task": {"intent": "cliquer sur « a »", "target_text": "a", "current_window": "Dossier 25012257 — BRUNEL Henri — DPI (maquette POC) - Google Chrome", "expected_next_window": "", "question": "L'élément « a » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.8547, "y_pct": 0.9812, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "a", "ocr_dist": 0.0391, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0035_2166_1296", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0035_full.png", "task": {"intent": "cliquer sur « 0 »", "target_text": "0", "current_window": "Fenêtre de dépassement de capacité de la barre d’état système.", "expected_next_window": "", "question": "L'élément « 0 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.8461, "y_pct": 0.81, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "0", "ocr_dist": 0.0133, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0036_2196_1285", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0036_full.png", "task": {"intent": "cliquer sur « - »", "target_text": "-", "current_window": "Fenêtre de dépassement de capacité de la barre d’état système.", "expected_next_window": "", "question": "L'élément « - » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.8578, "y_pct": 0.8031, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "-", "ocr_dist": 0.0239, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0037_2028_1290", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0037_full.png", "task": {"intent": "cliquer sur « terminé »", "target_text": "terminé", "current_window": "unknown_window", "expected_next_window": "", "question": "L'élément « terminé » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.7922, "y_pct": 0.8063, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "terminé", "ocr_dist": 0.0395, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0038_2031_1283", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0038_full.png", "task": {"intent": "cliquer sur « 0 »", "target_text": "0", "current_window": "Fenêtre de dépassement de capacité de la barre d’état système.", "expected_next_window": "", "question": "L'élément « 0 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.7934, "y_pct": 0.8019, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "0", "ocr_dist": 0.0407, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0039_2192_1298", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0039_full.png", "task": {"intent": "cliquer sur « 0 »", "target_text": "0", "current_window": "Fenêtre de dépassement de capacité de la barre d’état système.", "expected_next_window": "", "question": "L'élément « 0 » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.8562, "y_pct": 0.8113, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "0", "ocr_dist": 0.0235, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0040_2131_1290", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0040_full.png", "task": {"intent": "cliquer sur « 9 0 - »", "target_text": "9 0 -", "current_window": "Fenêtre de dépassement de capacité de la barre d’état système.", "expected_next_window": "", "question": "L'élément « 9 0 - » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.8324, "y_pct": 0.8063, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "9 0 -", "ocr_dist": 0.0125, "needs_human_check": false}} +{"case_id": "easily_rec_shot_0041_2010_1013", "screenshot_path": "../../../../tmp/easily_session/shots/shot_0041_full.png", "task": {"intent": "cliquer sur « mémorisées »", "target_text": "mémorisées", "current_window": "unknown_window", "expected_next_window": "", "question": "L'élément « mémorisées » est-il visible ? Clique uniquement dessus."}, "expectation": {"decision": "click", "click_region": {"x_pct": 0.7852, "y_pct": 0.6331, "radius_pct": 0.05}, "accepted_reasons": ["human_click_groundtruth"]}, "metadata": {"source": "easily_record", "session": "easily_session", "click_type": "mouse_click", "ocr_target": "mémorisées", "ocr_dist": 0.0454, "needs_human_check": false}} diff --git a/deploy/dgx/vm_launch.sh b/deploy/dgx/vm_launch.sh new file mode 100755 index 000000000..ee3040161 --- /dev/null +++ b/deploy/dgx/vm_launch.sh @@ -0,0 +1,60 @@ +#!/bin/bash +# Persistent VM launch — starts swtpm first, waits for socket, then QEMU +# VNC only, no SPICE (POC configuration) +VMROOT=/home/aivanov/quickemu-win11-arm-lea +SWTPM_SOCK="$VMROOT/windows-11-arm-lea.swtpm-sock" + +/usr/bin/swtpm socket \ + --ctrl type=unixio,path="$SWTPM_SOCK" \ + --terminate \ + --tpmstate dir="$VMROOT" \ + --tpm2 & + +# Wait for swtpm socket (up to 10s) +for _i in $(seq 1 100); do + if [ -S "$SWTPM_SOCK" ]; then break; fi + sleep 0.1 +done + +if [ ! -S "$SWTPM_SOCK" ]; then + echo "ERROR: swtpm socket not ready after 10s" + exit 1 +fi + +exec /usr/bin/qemu-system-aarch64 \ + -name windows-11-arm-lea \ + -machine virt,highmem=on,pflash0=rom,pflash1=efivars,accel=kvm \ + -global kvm-pit.lost_tick_policy=discard \ + -cpu host \ + -smp cores=8,threads=1,sockets=1 \ + -m 8G \ + -device virtio-balloon \ + -pidfile "$VMROOT/windows-11-arm-lea.pid" \ + -rtc base=utc,clock=host \ + -device ramfb \ + -vga none \ + -device virtio-gpu-pci,id=video0,xres=1280,yres=800 \ + -display none \ + -vnc 127.0.0.1:2,password=on \ + -device virtio-serial-pci \ + -chardev socket,id=agent0,path="$VMROOT/windows-11-arm-lea-agent.sock",server=on,wait=off \ + -device virtserialport,chardev=agent0,name=org.qemu.guest_agent.0 \ + -device virtio-rng-pci,rng=rng0 \ + -object rng-random,id=rng0,filename=/dev/urandom \ + -device qemu-xhci,id=input \ + -device usb-kbd,bus=input.0 \ + -k fr \ + -device usb-tablet,bus=input.0 \ + -device virtio-net-pci,netdev=nic \ + -netdev user,hostname=windows-11-arm-lea,hostfwd=tcp::22220-:22,id=nic \ + -blockdev node-name=rom,driver=file,filename=/usr/share/AAVMF/AAVMF_CODE.no-secboot.fd,read-only=true \ + -blockdev node-name=efivars,driver=file,filename="$VMROOT/OVMF_VARS.fd" \ + -device virtio-scsi-pci,id=scsi0 \ + -device scsi-hd,drive=SystemDisk,bus=scsi0.0,bootindex=2 \ + -drive id=SystemDisk,if=none,format=qcow2,file="$VMROOT/disk.qcow2",discard=unmap,detect-zeroes=unmap,cache=writeback,aio=threads \ + -chardev socket,id=chrtpm,path="$SWTPM_SOCK" \ + -tpmdev emulator,id=tpm0,chardev=chrtpm \ + -device tpm-tis-device,tpmdev=tpm0 \ + -monitor unix:"$VMROOT/windows-11-arm-lea-monitor.socket",server,nowait \ + -serial unix:"$VMROOT/windows-11-arm-lea-serial.socket",server,nowait \ + 2>"$VMROOT/qemu.log" diff --git a/deploy/dgx/vm_stop.sh b/deploy/dgx/vm_stop.sh new file mode 100755 index 000000000..05bbc87df --- /dev/null +++ b/deploy/dgx/vm_stop.sh @@ -0,0 +1,50 @@ +#!/bin/bash +# Persistent VM stop — ACPI poweroff via QEMU monitor, then SIGTERM, then SIGKILL +# Kill swtpm after QEMU exits. Cleanup PID/sockets. + +VMROOT=/home/aivanov/quickemu-win11-arm-lea +MONITOR_SOCKET="$VMROOT/windows-11-arm-lea-monitor.socket" +PIDFILE="$VMROOT/windows-11-arm-lea.pid" + +# Step 1: Send ACPI poweroff via QEMU monitor +if [ -S "$MONITOR_SOCKET" ]; then + echo "system_powerdown" | socat - UNIX-CONNECT:"$MONITOR_SOCKET" - > /dev/null 2>&1 + echo "ACPI poweroff sent, waiting 30s..." + for i in $(seq 1 30); do + if [ ! -f "$PIDFILE" ] || ! ps -p "$(cat "$PIDFILE" 2>/dev/null)" > /dev/null 2>&1; then + echo "QEMU exited gracefully" + exit 0 + fi + sleep 1 + done +fi + +# Step 2: SIGTERM (10s more) +QEMU_PID=$(cat "$PIDFILE" 2>/dev/null) +if [ -n "$QEMU_PID" ] && ps -p "$QEMU_PID" > /dev/null 2>&1; then + echo "Still running, sending SIGTERM..." + kill "$QEMU_PID" 2>/dev/null + for i in $(seq 1 10); do + if ! ps -p "$QEMU_PID" > /dev/null 2>&1; then + echo "QEMU exited after SIGTERM" + break + fi + sleep 1 + done +fi + +# Step 3: SIGKILL +QEMU_PID=$(cat "$PIDFILE" 2>/dev/null) +if [ -n "$QEMU_PID" ] && ps -p "$QEMU_PID" > /dev/null 2>&1; then + echo "Still running, SIGKILL..." + kill -9 "$QEMU_PID" 2>/dev/null + sleep 2 +fi + +# Step 4: Kill swtpm +pkill -f "swtpm.*windows-11-arm-lea" 2>/dev/null +sleep 2 + +# Step 5: Cleanup +rm -f "$PIDFILE" "$VMROOT"/*.sock "$VMROOT"/*.socket 2>/dev/null +echo "VM stop complete" diff --git a/deploy/windows-rdp-launcher/Connexion-VM-Lea.cmd b/deploy/windows-rdp-launcher/Connexion-VM-Lea.cmd new file mode 100644 index 000000000..732a6cf7b --- /dev/null +++ b/deploy/windows-rdp-launcher/Connexion-VM-Lea.cmd @@ -0,0 +1,44 @@ +@echo off +chcp 65001 >nul +title Connexion VM Lea (via DGX) + +REM ============================================================ +REM Connexion Bureau a distance a la VM Windows (Lea) du DGX. +REM Ouvre un tunnel SSH, lance le RDP (presse-papier actif), +REM puis referme le tunnel quand la session RDP est fermee. +REM ============================================================ + +REM --- Parametres (ajuste si besoin) --- +set "DGX_USER=aivanov" +set "DGX_HOST=192.168.1.45" +REM En deplacement (WireGuard, plus tard) : mettre DGX_HOST=10.10.0.1 +set "LOCAL_PORT=13389" +set "RDP_FILE=%~dp0VM-Lea.rdp" + +echo. +echo [1/3] Ouverture du tunnel SSH vers %DGX_USER%@%DGX_HOST% ... +echo (si un mot de passe est demande, saisis-le dans la fenetre "Tunnel") +start "Tunnel-DGX-VMLea" ssh -o StrictHostKeyChecking=accept-new -o ExitOnForwardFailure=yes -N -L %LOCAL_PORT%:127.0.0.1:3390 %DGX_USER%@%DGX_HOST% + +echo [2/3] Attente de l'etablissement du tunnel (max ~30s)... +set /a tries=0 +:wait +timeout /t 1 /nobreak >nul +powershell -NoProfile -Command "try{(New-Object Net.Sockets.TcpClient).Connect('127.0.0.1',%LOCAL_PORT%);exit 0}catch{exit 1}" >nul 2>&1 +if not errorlevel 1 goto ready +set /a tries+=1 +if %tries% lss 30 goto wait +echo ! Tunnel non etabli. Verifie l'acces SSH au DGX (mot de passe / reseau). +pause +goto cleanup + +:ready +echo [3/3] Connexion Bureau a distance (localhost:%LOCAL_PORT%) ... +mstsc "%RDP_FILE%" + +:cleanup +echo. +echo Fermeture du tunnel SSH... +taskkill /FI "WINDOWTITLE eq Tunnel-DGX-VMLea*" /T /F >nul 2>&1 +echo Termine. +timeout /t 2 /nobreak >nul diff --git a/deploy/windows-rdp-launcher/LISEZMOI.txt b/deploy/windows-rdp-launcher/LISEZMOI.txt new file mode 100644 index 000000000..e31260bed --- /dev/null +++ b/deploy/windows-rdp-launcher/LISEZMOI.txt @@ -0,0 +1,35 @@ +CONNEXION BUREAU A DISTANCE - VM Lea (DGX) +========================================== + +CONTENU + - Connexion-VM-Lea.cmd : le lanceur (double-clic) + - VM-Lea.rdp : le profil de connexion RDP (presse-papier active) + +INSTALLATION (sur ton laptop Windows) + 1. Copie les DEUX fichiers dans le MEME dossier (ex: le Bureau). + 2. (Optionnel) clic droit sur Connexion-VM-Lea.cmd > Envoyer vers > Bureau + (creer un raccourci), pour un acces rapide. + +UTILISATION + - Double-clic sur "Connexion-VM-Lea.cmd". + - Une fenetre "Tunnel" s'ouvre : si un mot de passe SSH est demande, + saisis le mot de passe du compte aivanov du DGX. + - Le Bureau a distance s'ouvre ensuite : saisis ton identifiant + mot de + passe WINDOWS de la VM. + - Copier-coller (texte ET fichiers) fonctionne dans les deux sens. + - Ferme la fenetre RDP pour finir : le tunnel se referme automatiquement. + +PRE-REQUIS + - Etre sur le reseau du labo (meme WiFi) pour joindre 192.168.1.45. + - OpenSSH client (inclus dans Windows 10/11). + - Le Bureau a distance doit etre active dans la VM (deja fait). + +EN DEPLACEMENT (plus tard) + - Quand WireGuard sera en place, edite Connexion-VM-Lea.cmd et remplace + DGX_HOST=192.168.1.45 par DGX_HOST=10.10.0.1 + - Tout le reste est identique. L'adresse RDP reste localhost:13389. + +CONFORT (optionnel, recommande) + - Pour ne plus saisir le mot de passe SSH a chaque fois : on signe la cle + SSH de ton laptop avec la CA (acces par certificat). Demande-le moi et + envoie-moi la cle publique de ton laptop. diff --git a/deploy/windows-rdp-launcher/VM-Lea.rdp b/deploy/windows-rdp-launcher/VM-Lea.rdp new file mode 100644 index 000000000..ff66f0762 --- /dev/null +++ b/deploy/windows-rdp-launcher/VM-Lea.rdp @@ -0,0 +1,18 @@ +full address:s:localhost:13389 +prompt for credentials:i:1 +redirectclipboard:i:1 +redirectdrives:i:1 +drivestoredirect:s:* +redirectprinters:i:0 +redirectsmartcards:i:0 +audiomode:i:2 +authentication level:i:0 +negotiate security layer:i:1 +enablecredsspsupport:i:1 +screen mode id:i:2 +dynamic resolution:i:1 +desktopwidth:i:1280 +desktopheight:i:800 +session bpp:i:32 +compression:i:1 +username:s: diff --git a/deploy/windows-rdp-launcher/connexion-vm-lea.sh b/deploy/windows-rdp-launcher/connexion-vm-lea.sh new file mode 100755 index 000000000..b13c50139 --- /dev/null +++ b/deploy/windows-rdp-launcher/connexion-vm-lea.sh @@ -0,0 +1,32 @@ +#!/usr/bin/env bash +# RDP vers la VM Windows (Lea) du DGX, depuis ce serveur Linux (.40). +# Ouvre un tunnel SSH (par certificat) puis lance xfreerdp. +# Presse-papier + dossier $HOME partage. Tunnel ferme a la sortie. +# +# Usage: +# ./connexion-vm-lea.sh # labo (DGX = 192.168.1.45) +# ./connexion-vm-lea.sh 10.10.0.1 # en deplacement (via WireGuard) +# ./connexion-vm-lea.sh 192.168.1.45 /u:MonUserWindows +set -euo pipefail + +DGX_HOST="${1:-192.168.1.45}" +[ $# -gt 0 ] && shift || true +LOCAL_PORT=13389 +CTL="$(mktemp -u /tmp/rdp-vmlea-ctl.XXXXXX)" + +cleanup(){ ssh -S "$CTL" -O exit "aivanov@${DGX_HOST}" >/dev/null 2>&1 || true; } +trap cleanup EXIT INT TERM + +echo "[1/3] Tunnel SSH (cert) vers aivanov@${DGX_HOST} ..." +ssh -o ExitOnForwardFailure=yes -fN -M -S "$CTL" -L "${LOCAL_PORT}:127.0.0.1:3390" "aivanov@${DGX_HOST}" + +echo "[2/3] Attente du tunnel ..." +for _i in $(seq 1 40); do + ss -tlnp 2>/dev/null | grep -q "127.0.0.1:${LOCAL_PORT} " && break + sleep 0.25 +done + +echo "[3/3] Connexion RDP (localhost:${LOCAL_PORT}) — presse-papier + dossier $HOME ..." +xfreerdp /v:localhost:${LOCAL_PORT} /cert:ignore /clipboard /dynamic-resolution /drive:home,"$HOME" "$@" || true + +echo "Session RDP terminee, fermeture du tunnel." diff --git a/deploy/windows-rdp-launcher/unblock_nomachine.ps1 b/deploy/windows-rdp-launcher/unblock_nomachine.ps1 new file mode 100644 index 000000000..1bd2ead7a --- /dev/null +++ b/deploy/windows-rdp-launcher/unblock_nomachine.ps1 @@ -0,0 +1,59 @@ +# Unblock NoMachine on Windows 11 — run as Administrator +# Adds firewall rules for port 4000 (TCP+UDP) and verifies NoMachine service + +Write-Host "=== Unblock NoMachine ===" -ForegroundColor Cyan + +# 1. Add firewall inbound rules for NoMachine (port 4000 TCP + UDP) +$ruleName = "NoMachine Server (Port 4000)" +$existing = Get-NetFirewallRule -DisplayName $ruleName -ErrorAction SilentlyContinue +if ($existing) { + Write-Host "Firewall rule '$ruleName' already exists — enabling it" -ForegroundColor Yellow + Enable-NetFirewallRule -DisplayName $ruleName +} else { + Write-Host "Creating firewall rule '$ruleName' for port 4000 TCP+UDP" -ForegroundColor Green + New-NetFirewallRule -DisplayName $ruleName -Direction Inbound -Protocol TCP -LocalPort 4000 -Action Allow -Profile Any -Enabled True -Description "Allow NoMachine remote desktop connections" + New-NetFirewallRule -DisplayName "$ruleName (UDP)" -Direction Inbound -Protocol UDP -LocalPort 4000 -Action Allow -Profile Any -Enabled True -Description "Allow NoMachine UDP discovery" +} + +# 2. Check NoMachine service is running +$svc = Get-Service -Name "nxsrv" -ErrorAction SilentlyContinue +if (-not $svc) { + $svc = Get-Service -Name "NoMachine Server" -ErrorAction SilentlyContinue + if (-not $svc) { + $svc = Get-Service | Where-Object { $_.DisplayName -like "*NoMachine*" -and $_.DisplayName -like "*Server*" } | Select-Object -First 1 + } +} + +if ($svc) { + Write-Host "NoMachine service: $($svc.Name) — Status: $($svc.Status)" -ForegroundColor $(if ($svc.Status -eq 'Running') {'Green'} else {'Red'}) + if ($svc.Status -ne 'Running') { + Write-Host "Starting NoMachine service..." -ForegroundColor Yellow + Start-Service -Name $svc.Name -ErrorAction SilentlyContinue + $svc = Get-Service -Name $svc.Name + Write-Host "After start: $($svc.Status)" -ForegroundColor $(if ($svc.Status -eq 'Running') {'Green'} else {'Red'}) + } +} else { + Write-Host "WARNING: NoMachine server service not found!" -ForegroundColor Red +} + +# 3. Verify port 4000 is listening +Write-Host "" +Write-Host "Checking port 4000..." -ForegroundColor Cyan +$port4000 = Get-NetTCPConnection -LocalPort 4000 -ErrorAction SilentlyContinue +if ($port4000) { + Write-Host "Port 4000 is LISTENING on $($port4000.LocalAddress):$($port4000.LocalPort) — State: $($port4000.State)" -ForegroundColor Green +} else { + Write-Host "WARNING: Port 4000 NOT listening — NoMachine server may not be active" -ForegroundColor Red + Write-Host "Try: restart NoMachine from the Start Menu or Services app" -ForegroundColor Yellow +} + +# 4. Show this machine's IP for remote connection +$ip = (Get-NetIPAddress -AddressFamily IPv4 | Where-Object { $_.InterfaceAlias -notlike '*Loopback*' -and $_.IPAddress -notlike '127.*' -and $_.IPAddress -match '192\.168' } | Select-Object -First 1).IPAddress +if ($ip) { + Write-Host "" + Write-Host "Laptop IP on LAN: $ip" -ForegroundColor Green + Write-Host "From workstation: connect NoMachine to $ip" -ForegroundColor Green +} + +Write-Host "" +Write-Host "=== Done ===" -ForegroundColor Cyan diff --git a/scripts/ops/dgx_m2_r1_enable_agent_chat.sh b/scripts/ops/dgx_m2_r1_enable_agent_chat.sh new file mode 100644 index 000000000..c1ca85c4a --- /dev/null +++ b/scripts/ops/dgx_m2_r1_enable_agent_chat.sh @@ -0,0 +1,104 @@ +#!/usr/bin/env bash +set -euo pipefail + +ROOT="/home/aivanov/ai/rpa_vision_v3" +VENV="$ROOT/venv_v3" +WIN_IP="${WIN_IP:-192.168.1.11}" +ENV_FILE="$ROOT/.env.local" +SERVICE_FILE="/etc/systemd/system/rpa-agent-chat.service" + +if [[ "${EUID:-$(id -u)}" -ne 0 ]]; then + echo "ERROR: run as root with sudo" >&2 + exit 1 +fi + +if [[ ! -d "$ROOT" || ! -x "$VENV/bin/python3" || ! -f "$ROOT/agent_chat/app.py" ]]; then + echo "ERROR: DGX RPA tree or venv missing under $ROOT" >&2 + exit 1 +fi + +if [[ ! -f "$ENV_FILE" ]]; then + echo "ERROR: missing $ENV_FILE" >&2 + exit 1 +fi + +ts="$(date +%Y%m%d_%H%M%S)" +cp -a "$ENV_FILE" "$ENV_FILE.bak_m2_r1_$ts" + +python3 - "$ENV_FILE" <<'PY' +from pathlib import Path +import sys + +path = Path(sys.argv[1]) +lines = path.read_text().splitlines() +seen = False +out = [] +for line in lines: + if line.startswith("RPA_BIND_HOST="): + out.append("RPA_BIND_HOST=0.0.0.0") + seen = True + else: + out.append(line) +if not seen: + out.append("RPA_BIND_HOST=0.0.0.0") +path.write_text("\n".join(out) + "\n") +PY + +install -m 0644 /dev/stdin "$SERVICE_FILE" </dev/null; then + iptables -A INPUT "$@" + fi +} + +ensure_iptables_rule -i lo -p tcp -m multiport --dports 5004,5005 -j ACCEPT +ensure_iptables_rule -p tcp -s "$WIN_IP" -m multiport --dports 5004,5005 -j ACCEPT +ensure_iptables_rule -p tcp -m multiport --dports 5004,5005 -j DROP + +echo "--- services ---" +systemctl is-active rpa-agent-chat.service rpa-streaming.service +echo "--- ports ---" +ss -ltnp | grep -E ':(5004|5005)\b' || true +echo "--- local health ---" +curl -sS -m 5 http://127.0.0.1:5005/health +echo +curl -sS -m 5 -o /dev/null -w 'agent_chat_status=%{http_code}\n' http://127.0.0.1:5004/api/status +echo "--- firewall rules ---" +iptables -S INPUT | grep -E 'dports 5004,5005|dport (5004|5005)' || true