{ "accepted": true, "base_commit": "bd4c81e7e33353d275d6f4320663e6e187f73198", "candidate_commit": "f23f6c75d3b480b56f195717e04f903714e3b66c", "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": 9 }, "healthy_zero_model_calls": true }, "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": "DocumentHashVerifier over bind-mounted oracle", "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", "reset_not_acknowledged" ], "generated_at": "2026-07-30T18:36:11.714461+00:00", "model_calls": 0, "oracle": "host read of the bind-mounted kiosk document, plus the runtime DocumentHashVerifier exactly-one-new-document gate", "run_count": 6, "schema_version": "openadapt.rdp-ladder-qualification.v2", "substrate": "real-rdp-freerdp3-roundtrip-linux-kiosk", "successes": 6, "task": "record->compile->replay a patient-note write through the vision-only resolver ladder over a real RDP round-trip, with no structural backend; confirm the write via an independent document oracle; and halt under injected DPI/theme/JPEG drift", "total_s": 173.333, "trials": [ { "condition_trial": 1, "effect_confirmed": true, "effect_expected": "MRN A1001\tfollowup in two weeks / healthy-1", "effect_observed": "MRN A1001\tfollowup in two weeks / healthy-1", "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": [ 347, 192 ], "resolution": { "confidence": 0.9999997615814209, "point": [ 347, 192 ], "rung": "template" }, "status": "verified" }, "step_001": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 120, 588 ], "resolution": { "confidence": 0.999997615814209, "point": [ 120, 588 ], "rung": "template" }, "status": "verified" }, "step_003": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 910, 588 ], "resolution": { "confidence": 0.9999989867210388, "point": [ 910, 588 ], "rung": "template" }, "status": "verified" } }, "identity_required": true, "identity_statuses": { "step_000": "verified", "step_001": "verified", "step_003": "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" ], "rung_counts": { "template": 3 }, "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": true, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_003" } ], "structural_rung_used": 0, "success": true, "trial": 1, "visual_rungs_used": { "template": 3 } }, { "condition_trial": 2, "effect_confirmed": true, "effect_expected": "MRN A1001\tfollowup in two weeks / healthy-2", "effect_observed": "MRN A1001\tfollowup in two weeks / healthy-2", "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": [ 347, 192 ], "resolution": { "confidence": 0.9999997615814209, "point": [ 347, 192 ], "rung": "template" }, "status": "verified" }, "step_001": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 120, 588 ], "resolution": { "confidence": 0.999997615814209, "point": [ 120, 588 ], "rung": "template" }, "status": "verified" }, "step_003": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 910, 588 ], "resolution": { "confidence": 0.9999989867210388, "point": [ 910, 588 ], "rung": "template" }, "status": "verified" } }, "identity_required": true, "identity_statuses": { "step_000": "verified", "step_001": "verified", "step_003": "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" ], "rung_counts": { "template": 3 }, "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": true, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_003" } ], "structural_rung_used": 0, "success": true, "trial": 2, "visual_rungs_used": { "template": 3 } }, { "condition_trial": 3, "effect_confirmed": true, "effect_expected": "MRN A1001\tfollowup in two weeks / healthy-3", "effect_observed": "MRN A1001\tfollowup in two weeks / healthy-3", "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": [ 347, 192 ], "resolution": { "confidence": 0.9999997615814209, "point": [ 347, 192 ], "rung": "template" }, "status": "verified" }, "step_001": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 120, 588 ], "resolution": { "confidence": 0.999997615814209, "point": [ 120, 588 ], "rung": "template" }, "status": "verified" }, "step_003": { "error": null, "mode": "pixel", "observed": "live identifier crop matches after alignment (worst window 0.000)", "recorded_click_point": [ 910, 588 ], "resolution": { "confidence": 0.9999989867210388, "point": [ 910, 588 ], "rung": "template" }, "status": "verified" } }, "identity_required": true, "identity_statuses": { "step_000": "verified", "step_001": "verified", "step_003": "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" ], "rung_counts": { "template": 3 }, "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": true, "error": null, "input_retried": false, "input_verified": null, "ok": true, "postconditions_ok": true, "resolution_rung": "template", "safety_halt": false, "step_id": "step_003" } ], "structural_rung_used": 0, "success": true, "trial": 3, "visual_rungs_used": { "template": 3 } }, { "condition_trial": 1, "drift": "downscale_0.4x_blur + theme_invert + jpeg_q8 (simulated on real session)", "effect_after_drift": null, "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": null, "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": null, "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 } ] }