← all runs · ← report

wi006_qwen38_nothink / live_d4_model_informed_s406 valid

What this trial was

runwi006_qwen38_nothinktriallive_d4_model_informed_s406conditionlivescenariopending_effectskinnotificationcanvas320×240 px (target 24 px)event at500 msresponse window16 sframe period16.67 msobservation publication delay30 msdeliverysimulated_fixed_delay, 20 msclockmonotonic_nseffect_delay_ns4000000000irrelevant_motionFalse

Controller: {"enable_thinking": false, "image_scale": 2, "invoke_on": "frame_change", "kind": "vlm_pending", "max_tokens": 64, "memory": "model_informed", "model_id": "Qwen/Qwen3.8-27B", "pending_radius_px": 10, "pending_timeout_ns": 10000000000, "prompt_version": 4, "reasoning_effort": null, "temperature": 0.0}

Result for this trial

first click acceptedTruefirst E→A5.31 sduplicates0invalid clicks1suppressed proposals0waits1decisions3exact successTruedropped0contract violationsnone

Replay

key frames

Key frames: each decision's starting frame with the click it produced (amber = proposal before binding, red = committed, grey = suppressed), then the screen at each arrival A (green = valid).

The prompt sent with every frame

You control a desktop by clicking. You are shown one screenshot. At some point a notification card with a blue button appears at an unknown position and expires shortly after. If the card is visible, answer with action "click" and the coordinates of the center of its blue button on a 0-1000 grid (x: 0 = left edge, 1000 = right edge; y: 0 = top edge, 1000 = bottom edge). If no card is visible, answer with action "wait". Answer with the JSON object only.

[user] Screenshot attached. Click the target's center or wait. (+ pending note when a click is pending)

Decision by decision — 3 decisions

#Bmodel done
B→D
model response (raw)parsedaction (canvas px)D (commit)A (receipt)out tokens
1530 ms5,787 ms
5.26 s
{"action": "click", "x": 774, "y": 702}
click
img (774, 702)
{'kind': 'click', 'x': 247, 'y': 168}
5,787 ms5,807 ms · accepted23
25,988 ms11,306 ms
5.32 s
{"action": "click", "x": 774, "y": 704}
click
img (774, 704)
{'kind': 'click', 'x': 247, 'y': 168}
11,306 ms11,326 ms · invalid23
311,445 ms13,263 ms
1.82 s
{"action": "wait"}
wait—
——7

Events and observations

ideventtask timeharness time
1target_appears500 ms500 ms
3effect_visible9,807 ms9,807 ms

794 observations published; first frame depicting the target published at 530 ms. Raw trace: live_d4_model_informed_s406.jsonl.