{ "accepted": true, "base_commit": "6673dd97de169d8c500031c4ac4c64a95bb71656", "candidate_commit": "a3c71c1915ae7465306eb7106511bc1307ba162c", "caveat": "Synthetic Tk task over real FreeRDP-transported pixels + input, but NOT Citrix ICA/HDX, NOT the aardwolf transport, NOT a Windows application qualification, and the drift is simulated on the real protocol session (not WAN capture).", "contract": { "drift_false_completions": 0, "drift_safely_halted": 3, "drift_silent_writes": 0, "drift_trials": 3, "healthy_effects_confirmed": 3, "healthy_identity_verified": 3, "healthy_over_halts": 0, "healthy_policy_admitted": 3, "healthy_runtime_effects_verified": 3, "healthy_silent_incorrect_successes": 0, "healthy_structural_rung_used": 0, "healthy_trials": 3, "healthy_visual_rungs_used": { "template": 15 }, "healthy_zero_model_calls": true, "wrong_record_false_completions": 0, "wrong_record_identity_mismatches": 3, "wrong_record_safely_halted": 3, "wrong_record_silent_writes": 0, "wrong_record_trials": 3 }, "environment": { "backend": "openadapt_flow FreeRDPBackend (pixel-only, use_structural off)", "fixture_package_versions": { "freerdp3-shadow-x11": "3.30.0+dfsg-0ubuntu0.24.04.2", "freerdp3-x11": "3.30.0+dfsg-0ubuntu0.24.04.2", "imagemagick": "8:6.9.12.98+dfsg1-5.2build2", "openbox": "3.6.1-12build5", "xdotool": "1:3.20160805.1-5build1" }, "governed_policy": "policy.yaml", "note": "aardwolf (the product's Windows-RDP transport) cannot connect to Linux RDP servers; see fixture README. The aardwolf-over-Windows transport is qualified separately in benchmark/rdp (PR #142).", "pixel_identity_verify": "enabled for this synthetic qualification only", "rdp_client": "xfreerdp3 (FreeRDP3 client, fullscreen)", "rdp_server": "freerdp-shadow-cli3 (FreeRDP3 server)", "runtime_effect_verifier": "SqlRecordVerifier over a separate read-only SQLite connection", "surface": "Tk kiosk app served over RDP; observed on client display", "transport": "DockerX11RdpTransport (screenshot+xdotool over the RDP client)", "viewport": [ 1280, 800 ] }, "failure_taxonomy": [ "connect_or_frame_failure", "healthy_contract_violation", "silent_incorrect_success", "healthy_over_halt", "effect_not_confirmed", "identity_not_verified", "effect_not_runtime_verified", "policy_not_admitted", "drift_contract_violation", "wrong_record_contract_violation", "reset_not_acknowledged" ], "generated_at": "2026-07-30T20:45:29.227149+00:00", "model_calls": 0, "oracle": "host read of the bind-mounted appointment database, plus the runtime read-only SQL exactly-one-new-record and status gates", "run_count": 9, "schema_version": "openadapt.rdp-ladder-qualification.v3", "substrate": "real-rdp-freerdp3-roundtrip-linux-kiosk", "successes": 9, "task": "record->compile->replay an appointment booking through the vision-only resolver ladder over a real RDP round-trip, with no structural backend; confirm the write through read-only SQL; halt under injected DPI/theme/JPEG drift; and halt when the active patient changes before the write", "total_s": 548.514, "trials": [ { "condition_trial": 1, "effect_confirmed": true, "effect_expected": { "appointment_slot": "2026-08-14 10:45", "patient_mrn": "MRN A1001", "request_id": "REQ-LIVE-2048-1", "status": "scheduled", "visit_type": "Intake consultation" }, "effect_observed": { "appointment_id": "APT-90F5510C", "appointment_slot": "2026-08-14 10:45", "patient_mrn": "MRN A1001", "patient_name": "Ada Lovelace", "request_id": "REQ-LIVE-2048-1", "status": "scheduled", "visit_type": "Intake consultation" }, "failure_class": null, "identity_diagnostics": { "step_000": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 335, 190 ], "resolution": { "confidence": 1.0, "point": [ 335, 190 ], "rung": "template" }, "status": "verified" }, "step_001": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 590, 268 ], "resolution": { "confidence": 1.0, "point": [ 590, 268 ], "rung": "template" }, "status": "verified" }, "step_003": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 590, 388 ], "resolution": { "confidence": 1.0, "point": [ 590, 388 ], "rung": "template" }, "status": "verified" }, "step_005": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 590, 508 ], "resolution": { "confidence": 0.9999768733978271, "point": [ 590, 508 ], "rung": "template" }, "status": "verified" }, "step_007": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 720, 590 ], "resolution": { "confidence": 0.9999994039535522, "point": [ 720, 590 ], "rung": "template" }, "status": "verified" } }, "identity_required": true, "identity_statuses": { "step_000": "verified", "step_001": "verified", "step_003": "verified", "step_005": "verified", "step_007": "verified" }, "identity_verified": true, "kind": "healthy_record_compile_replay", "model_calls": 0, "over_halt": false, "passed": true, "policy_admitted": true, "required_identity_step_ids": [ "step_000", "step_001", "step_003", "step_005", "step_007" ], "rung_counts": { "template": 5 }, "runtime_effect_verified": true, "silent_incorrect_success": false, "step_diagnostics": [ { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_000" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_001" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": true, "ok": true, "postconditions_ok": null, "resolution_rung": null, "safety_halt": false, "step_id": "step_002" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_003" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": true, "ok": true, "postconditions_ok": null, "resolution_rung": null, "safety_halt": false, "step_id": "step_004" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_005" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": true, "ok": true, "postconditions_ok": null, "resolution_rung": null, "safety_halt": false, "step_id": "step_006" }, { "effect_verified": true, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_007" } ], "structural_rung_used": 0, "success": true, "trial": 1, "visual_rungs_used": { "template": 5 } }, { "condition_trial": 2, "effect_confirmed": true, "effect_expected": { "appointment_slot": "2026-08-14 10:45", "patient_mrn": "MRN A1001", "request_id": "REQ-LIVE-2048-2", "status": "scheduled", "visit_type": "Intake consultation" }, "effect_observed": { "appointment_id": "APT-3160BFA6", "appointment_slot": "2026-08-14 10:45", "patient_mrn": "MRN A1001", "patient_name": "Ada Lovelace", "request_id": "REQ-LIVE-2048-2", "status": "scheduled", "visit_type": "Intake consultation" }, "failure_class": null, "identity_diagnostics": { "step_000": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 335, 190 ], "resolution": { "confidence": 1.0, "point": [ 335, 190 ], "rung": "template" }, "status": "verified" }, "step_001": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 590, 268 ], "resolution": { "confidence": 1.0, "point": [ 590, 268 ], "rung": "template" }, "status": "verified" }, "step_003": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 590, 388 ], "resolution": { "confidence": 1.0, "point": [ 590, 388 ], "rung": "template" }, "status": "verified" }, "step_005": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 590, 508 ], "resolution": { "confidence": 0.9999768733978271, "point": [ 590, 508 ], "rung": "template" }, "status": "verified" }, "step_007": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 720, 590 ], "resolution": { "confidence": 1.0, "point": [ 720, 590 ], "rung": "template" }, "status": "verified" } }, "identity_required": true, "identity_statuses": { "step_000": "verified", "step_001": "verified", "step_003": "verified", "step_005": "verified", "step_007": "verified" }, "identity_verified": true, "kind": "healthy_record_compile_replay", "model_calls": 0, "over_halt": false, "passed": true, "policy_admitted": true, "required_identity_step_ids": [ "step_000", "step_001", "step_003", "step_005", "step_007" ], "rung_counts": { "template": 5 }, "runtime_effect_verified": true, "silent_incorrect_success": false, "step_diagnostics": [ { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_000" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_001" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": true, "ok": true, "postconditions_ok": null, "resolution_rung": null, "safety_halt": false, "step_id": "step_002" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_003" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": true, "ok": true, "postconditions_ok": null, "resolution_rung": null, "safety_halt": false, "step_id": "step_004" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_005" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": true, "ok": true, "postconditions_ok": null, "resolution_rung": null, "safety_halt": false, "step_id": "step_006" }, { "effect_verified": true, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_007" } ], "structural_rung_used": 0, "success": true, "trial": 2, "visual_rungs_used": { "template": 5 } }, { "condition_trial": 3, "effect_confirmed": true, "effect_expected": { "appointment_slot": "2026-08-14 10:45", "patient_mrn": "MRN A1001", "request_id": "REQ-LIVE-2048-3", "status": "scheduled", "visit_type": "Intake consultation" }, "effect_observed": { "appointment_id": "APT-F98C16FC", "appointment_slot": "2026-08-14 10:45", "patient_mrn": "MRN A1001", "patient_name": "Ada Lovelace", "request_id": "REQ-LIVE-2048-3", "status": "scheduled", "visit_type": "Intake consultation" }, "failure_class": null, "identity_diagnostics": { "step_000": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 335, 190 ], "resolution": { "confidence": 1.0, "point": [ 335, 190 ], "rung": "template" }, "status": "verified" }, "step_001": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 590, 268 ], "resolution": { "confidence": 1.0, "point": [ 590, 268 ], "rung": "template" }, "status": "verified" }, "step_003": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 590, 388 ], "resolution": { "confidence": 1.0, "point": [ 590, 388 ], "rung": "template" }, "status": "verified" }, "step_005": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 590, 508 ], "resolution": { "confidence": 0.9999768733978271, "point": [ 590, 508 ], "rung": "template" }, "status": "verified" }, "step_007": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 720, 590 ], "resolution": { "confidence": 1.0, "point": [ 720, 590 ], "rung": "template" }, "status": "verified" } }, "identity_required": true, "identity_statuses": { "step_000": "verified", "step_001": "verified", "step_003": "verified", "step_005": "verified", "step_007": "verified" }, "identity_verified": true, "kind": "healthy_record_compile_replay", "model_calls": 0, "over_halt": false, "passed": true, "policy_admitted": true, "required_identity_step_ids": [ "step_000", "step_001", "step_003", "step_005", "step_007" ], "rung_counts": { "template": 5 }, "runtime_effect_verified": true, "silent_incorrect_success": false, "step_diagnostics": [ { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_000" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_001" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": true, "ok": true, "postconditions_ok": null, "resolution_rung": null, "safety_halt": false, "step_id": "step_002" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_003" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": true, "ok": true, "postconditions_ok": null, "resolution_rung": null, "safety_halt": false, "step_id": "step_004" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_005" }, { "effect_verified": null, "error": null, "input_retried": false, "input_verified": true, "ok": true, "postconditions_ok": null, "resolution_rung": null, "safety_halt": false, "step_id": "step_006" }, { "effect_verified": true, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_007" } ], "structural_rung_used": 0, "success": true, "trial": 3, "visual_rungs_used": { "template": 5 } }, { "condition_trial": 1, "drift": "downscale_0.4x_blur + theme_invert + jpeg_q8 (simulated on real session)", "effect_after_drift": [], "failure_class": null, "false_completion": false, "halted": true, "kind": "halt_under_injected_drift", "model_calls": 0, "passed": true, "policy_bound": true, "safety_halt": true, "silent_write": false, "trial": 4 }, { "condition_trial": 2, "drift": "downscale_0.4x_blur + theme_invert + jpeg_q8 (simulated on real session)", "effect_after_drift": [], "failure_class": null, "false_completion": false, "halted": true, "kind": "halt_under_injected_drift", "model_calls": 0, "passed": true, "policy_bound": true, "safety_halt": true, "silent_write": false, "trial": 5 }, { "condition_trial": 3, "drift": "downscale_0.4x_blur + theme_invert + jpeg_q8 (simulated on real session)", "effect_after_drift": [], "failure_class": null, "false_completion": false, "halted": true, "kind": "halt_under_injected_drift", "model_calls": 0, "passed": true, "policy_bound": true, "safety_halt": true, "silent_write": false, "trial": 6 }, { "condition_trial": 1, "effect_after_wrong_record": [], "failure_class": null, "false_completion": false, "fault": "active record changed from Ada Lovelace / MRN A1001 to Grace Hopper / MRN B2002 before the final write", "fault_acquisition_index": 5, "fault_injected": true, "fresh_frame_acquisitions": 5, "halted": true, "identity_mismatch": true, "identity_statuses": [ "verified", "verified", "verified", "verified", "mismatch" ], "kind": "wrong_record_safe_halt", "model_calls": 0, "passed": true, "policy_bound": true, "silent_write": false, "trial": 7 }, { "condition_trial": 2, "effect_after_wrong_record": [], "failure_class": null, "false_completion": false, "fault": "active record changed from Ada Lovelace / MRN A1001 to Grace Hopper / MRN B2002 before the final write", "fault_acquisition_index": 5, "fault_injected": true, "fresh_frame_acquisitions": 5, "halted": true, "identity_mismatch": true, "identity_statuses": [ "verified", "verified", "verified", "verified", "mismatch" ], "kind": "wrong_record_safe_halt", "model_calls": 0, "passed": true, "policy_bound": true, "silent_write": false, "trial": 8 }, { "condition_trial": 3, "effect_after_wrong_record": [], "failure_class": null, "false_completion": false, "fault": "active record changed from Ada Lovelace / MRN A1001 to Grace Hopper / MRN B2002 before the final write", "fault_acquisition_index": 5, "fault_injected": true, "fresh_frame_acquisitions": 5, "halted": true, "identity_mismatch": true, "identity_statuses": [ "verified", "verified", "verified", "verified", "mismatch" ], "kind": "wrong_record_safe_halt", "model_calls": 0, "passed": true, "policy_bound": true, "silent_write": false, "trial": 9 } ] }