← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d2_none_s407 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d2_none_s407conditionlivescenariopending_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 ms1,127 ms
0.60 s
{"action": "wait"}
wait—
——7
21,142 ms1,764 ms
0.62 s
{"action": "wait"}
wait—
——7
31,780 ms2,400 ms
0.62 s
{"action": "wait"}
wait—
——7
42,416 ms3,040 ms
0.62 s
{"action": "wait"}
wait—
——7
53,056 ms3,677 ms
0.62 s
{"action": "wait"}
wait—
——7
63,693 ms4,314 ms
0.62 s
{"action": "wait"}
wait—
——7
74,330 ms4,952 ms
0.62 s
{"action": "wait"}
wait—
——7
84,968 ms5,597 ms
0.63 s
{"action": "wait"}
wait—
——7
95,613 ms6,234 ms
0.62 s
{"action": "wait"}
wait—
——7
106,250 ms6,872 ms
0.62 s
{"action": "wait"}
wait—
——7
116,888 ms7,510 ms
0.62 s
{"action": "wait"}
wait—
——7
127,526 ms8,147 ms
0.62 s
{"action": "wait"}
wait—
——7
138,164 ms8,788 ms
0.62 s
{"action": "wait"}
wait—
——7
148,805 ms9,424 ms
0.62 s
{"action": "wait"}
wait—
——7
159,440 ms10,060 ms
0.62 s
{"action": "wait"}
wait—
——7
1610,075 ms10,697 ms
0.62 s
{"action": "wait"}
wait—
——7
1710,714 ms11,333 ms
0.62 s
{"action": "wait"}
wait—
——7
1811,348 ms11,970 ms
0.62 s
{"action": "wait"}
wait—
——7
1911,986 ms12,605 ms
0.62 s
{"action": "wait"}
wait—
——7
2012,621 ms13,241 ms
0.62 s
{"action": "wait"}
wait—
——7
2113,257 ms13,877 ms
0.62 s
{"action": "wait"}
wait—
——7
2213,893 ms14,515 ms
0.62 s
{"action": "wait"}
wait—
——7
2314,531 ms15,155 ms
0.62 s
{"action": "wait"}
wait—
——7
2415,171 ms15,791 ms
0.62 s
{"action": "wait"}
wait—
——7
2515,807 ms16,429 ms
0.62 s
{"action": "wait"}
wait—
——7
2616,445 ms17,065 ms
0.62 s
{"action": "wait"}
wait—
——7
2717,077 ms17,641 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_s407.jsonl.