← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d2_harness_pending_s405 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d2_harness_pending_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": "harness_pending", "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 ms1,066 ms
0.53 s
{"action": "wait"}
wait—
——7
21,079 ms1,639 ms
0.56 s
{"action": "wait"}
wait—
——7
31,653 ms2,274 ms
0.62 s
{"action": "wait"}
wait—
——7
42,290 ms2,912 ms
0.62 s
{"action": "wait"}
wait—
——7
52,927 ms3,549 ms
0.62 s
{"action": "wait"}
wait—
——7
63,564 ms4,185 ms
0.62 s
{"action": "wait"}
wait—
——7
74,200 ms4,822 ms
0.62 s
{"action": "wait"}
wait—
——7
84,837 ms5,397 ms
0.56 s
{"action": "wait"}
wait—
——7
95,411 ms6,032 ms
0.62 s
{"action": "wait"}
wait—
——7
106,048 ms6,668 ms
0.62 s
{"action": "wait"}
wait—
——7
116,684 ms7,319 ms
0.64 s
{"action": "wait"}
wait—
——7
127,335 ms7,955 ms
0.62 s
{"action": "wait"}
wait—
——7
137,971 ms8,591 ms
0.62 s
{"action": "wait"}
wait—
——7
148,607 ms9,226 ms
0.62 s
{"action": "wait"}
wait—
——7
159,253 ms9,869 ms
0.62 s
{"action": "wait"}
wait—
——7
169,885 ms10,509 ms
0.62 s
{"action": "wait"}
wait—
——7
1710,524 ms11,145 ms
0.62 s
{"action": "wait"}
wait—
——7
1811,160 ms11,810 ms
0.65 s
{"action": "wait"}
wait—
——7
1911,838 ms12,450 ms
0.61 s
{"action": "wait"}
wait—
——7
2012,466 ms13,092 ms
0.63 s
{"action": "wait"}
wait—
——7
2113,108 ms13,731 ms
0.62 s
{"action": "wait"}
wait—
——7
2213,747 ms14,369 ms
0.62 s
{"action": "wait"}
wait—
——7
2314,385 ms15,005 ms
0.62 s
{"action": "wait"}
wait—
——7
2415,021 ms15,645 ms
0.62 s
{"action": "wait"}
wait—
——7
2515,661 ms16,283 ms
0.62 s
{"action": "wait"}
wait—
——7
2616,299 ms16,921 ms
0.62 s
{"action": "wait"}
wait—
——7
2716,934 ms17,494 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_harness_pending_s405.jsonl.