← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d2_none_s405 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d2_none_s405conditionlivescenariopending_effectskinnotificationcanvas320×240 px (target 24 px)event at500 msresponse window16 sframe period16.67 msobservation publication delay30 msdeliverysimulated_fixed_delay, 20 msclockmonotonic_nseffect_delay_ns2000000000irrelevant_motionFalse

Controller: {"enable_thinking": false, "image_scale": 2, "invoke_on": "frame_change", "kind": "vlm_pending", "max_tokens": 64, "memory": "none", "model_id": "Qwen/Qwen3-VL-8B-Instruct", "pending_radius_px": 10, "pending_timeout_ns": 10000000000, "prompt_version": 4, "reasoning_effort": null, "temperature": 0.0}

Result for this trial

first click acceptedFalsefirst E→A—duplicates0invalid clicks0suppressed proposals0waits27decisions27exact successFalsedropped0contract 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.

Decision by decision — 27 decisions

#Bmodel done
B→D
model response (raw)parsedaction (canvas px)D (commit)A (receipt)out tokens
1532 ms1,139 ms
0.61 s
{"action": "wait"}
wait—
——7
21,165 ms1,777 ms
0.61 s
{"action": "wait"}
wait—
——7
31,805 ms2,418 ms
0.61 s
{"action": "wait"}
wait—
——7
42,446 ms3,060 ms
0.61 s
{"action": "wait"}
wait—
——7
53,087 ms3,701 ms
0.61 s
{"action": "wait"}
wait—
——7
63,729 ms4,339 ms
0.61 s
{"action": "wait"}
wait—
——7
74,367 ms4,978 ms
0.61 s
{"action": "wait"}
wait—
——7
85,006 ms5,620 ms
0.61 s
{"action": "wait"}
wait—
——7
95,649 ms6,260 ms
0.61 s
{"action": "wait"}
wait—
——7
106,289 ms6,899 ms
0.61 s
{"action": "wait"}
wait—
——7
116,928 ms7,539 ms
0.61 s
{"action": "wait"}
wait—
——7
127,567 ms8,179 ms
0.61 s
{"action": "wait"}
wait—
——7
138,207 ms8,832 ms
0.62 s
{"action": "wait"}
wait—
——7
148,861 ms9,475 ms
0.61 s
{"action": "wait"}
wait—
——7
159,503 ms10,121 ms
0.62 s
{"action": "wait"}
wait—
——7
1610,151 ms10,761 ms
0.61 s
{"action": "wait"}
wait—
——7
1710,788 ms11,401 ms
0.61 s
{"action": "wait"}
wait—
——7
1811,430 ms12,046 ms
0.62 s
{"action": "wait"}
wait—
——7
1912,074 ms12,687 ms
0.61 s
{"action": "wait"}
wait—
——7
2012,716 ms13,331 ms
0.62 s
{"action": "wait"}
wait—
——7
2113,360 ms13,970 ms
0.61 s
{"action": "wait"}
wait—
——7
2213,986 ms14,607 ms
0.62 s
{"action": "wait"}
wait—
——7
2314,623 ms15,244 ms
0.62 s
{"action": "wait"}
wait—
——7
2415,260 ms15,880 ms
0.62 s
{"action": "wait"}
wait—
——7
2515,897 ms16,518 ms
0.62 s
{"action": "wait"}
wait—
——7
2616,534 ms17,156 ms
0.62 s
{"action": "wait"}
wait—
——7
2717,165 ms17,731 ms
0.57 s
{"action": "wait"}
wait—
——7

Events and observations

ideventtask timeharness time
1target_appears500 ms500 ms
2window_closes16,500 ms16,500 ms

1020 observations published; first frame depicting the target published at 530 ms. Raw trace: live_d2_none_s405.jsonl.