← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d2_none_s404 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d2_none_s404conditionlivescenariopending_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
1531 ms1,134 ms
0.60 s
{"action": "wait"}
wait—
——7
21,161 ms1,773 ms
0.61 s
{"action": "wait"}
wait—
——7
31,801 ms2,412 ms
0.61 s
{"action": "wait"}
wait—
——7
42,440 ms3,052 ms
0.61 s
{"action": "wait"}
wait—
——7
53,081 ms3,688 ms
0.61 s
{"action": "wait"}
wait—
——7
63,717 ms4,335 ms
0.62 s
{"action": "wait"}
wait—
——7
74,364 ms4,978 ms
0.61 s
{"action": "wait"}
wait—
——7
85,006 ms5,617 ms
0.61 s
{"action": "wait"}
wait—
——7
95,645 ms6,256 ms
0.61 s
{"action": "wait"}
wait—
——7
106,283 ms6,893 ms
0.61 s
{"action": "wait"}
wait—
——7
116,921 ms7,538 ms
0.62 s
{"action": "wait"}
wait—
——7
127,567 ms8,181 ms
0.61 s
{"action": "wait"}
wait—
——7
138,210 ms8,822 ms
0.61 s
{"action": "wait"}
wait—
——7
148,849 ms9,458 ms
0.61 s
{"action": "wait"}
wait—
——7
159,486 ms10,095 ms
0.61 s
{"action": "wait"}
wait—
——7
1610,122 ms10,734 ms
0.61 s
{"action": "wait"}
wait—
——7
1710,762 ms11,372 ms
0.61 s
{"action": "wait"}
wait—
——7
1811,399 ms12,008 ms
0.61 s
{"action": "wait"}
wait—
——7
1912,036 ms12,649 ms
0.61 s
{"action": "wait"}
wait—
——7
2012,677 ms13,291 ms
0.61 s
{"action": "wait"}
wait—
——7
2113,319 ms13,928 ms
0.61 s
{"action": "wait"}
wait—
——7
2213,956 ms14,566 ms
0.61 s
{"action": "wait"}
wait—
——7
2314,594 ms15,208 ms
0.61 s
{"action": "wait"}
wait—
——7
2415,236 ms15,846 ms
0.61 s
{"action": "wait"}
wait—
——7
2515,873 ms16,487 ms
0.61 s
{"action": "wait"}
wait—
——7
2616,516 ms17,131 ms
0.62 s
{"action": "wait"}
wait—
——7
2717,148 ms17,705 ms
0.56 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_s404.jsonl.