← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d2_none_s402 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d2_none_s402conditionlivescenariopending_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 clicks4suppressed proposals0waits17decisions21exact 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 — 21 decisions

#Bmodel done
B→D
model response (raw)parsedaction (canvas px)D (commit)A (receipt)out tokens
1531 ms1,130 ms
0.60 s
{"action": "wait"}
wait—
——7
21,144 ms1,762 ms
0.62 s
{"action": "wait"}
wait—
——7
31,778 ms2,396 ms
0.62 s
{"action": "wait"}
wait—
——7
42,412 ms3,030 ms
0.62 s
{"action": "wait"}
wait—
——7
53,046 ms3,663 ms
0.62 s
{"action": "wait"}
wait—
——7
63,680 ms4,298 ms
0.62 s
{"action": "wait"}
wait—
——7
74,313 ms4,932 ms
0.62 s
{"action": "wait"}
wait—
——7
84,948 ms5,567 ms
0.62 s
{"action": "wait"}
wait—
——7
95,583 ms6,202 ms
0.62 s
{"action": "wait"}
wait—
——7
106,218 ms6,835 ms
0.62 s
{"action": "wait"}
wait—
——7
116,850 ms7,471 ms
0.62 s
{"action": "wait"}
wait—
——7
127,486 ms8,104 ms
0.62 s
{"action": "wait"}
wait—
——7
138,120 ms8,738 ms
0.62 s
{"action": "wait"}
wait—
——7
148,753 ms9,369 ms
0.62 s
{"action": "wait"}
wait—
——7
159,384 ms10,005 ms
0.62 s
{"action": "wait"}
wait—
——7
1610,021 ms10,640 ms
0.62 s
{"action": "wait"}
wait—
——7
1710,656 ms12,413 ms
1.76 s
{"action": "click", "x": 901, "y": 197}
click
img (901, 197)
{'kind': 'click', 'x': 288, 'y': 47}
12,413 ms12,433 ms · invalid23
1812,460 ms14,197 ms
1.74 s
{"action": "click", "x": 901, "y": 197}
click
img (901, 197)
{'kind': 'click', 'x': 288, 'y': 47}
14,197 ms14,217 ms · invalid23
1914,241 ms15,975 ms
1.73 s
{"action": "click", "x": 901, "y": 197}
click
img (901, 197)
{'kind': 'click', 'x': 288, 'y': 47}
15,975 ms15,995 ms · invalid23
2016,018 ms17,756 ms
1.74 s
{"action": "click", "x": 919, "y": 187}
click
img (919, 187)
{'kind': 'click', 'x': 294, 'y': 44}
17,756 ms17,776 ms · invalid23
2117,779 ms18,330 ms
0.55 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_s402.jsonl.