← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d2_harness_pending_s404 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d2_harness_pending_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": "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 ms1,641 ms
0.56 s
{"action": "wait"}
wait—
——7
31,655 ms2,279 ms
0.62 s
{"action": "wait"}
wait—
——7
42,295 ms2,914 ms
0.62 s
{"action": "wait"}
wait—
——7
52,930 ms3,552 ms
0.62 s
{"action": "wait"}
wait—
——7
63,567 ms4,187 ms
0.62 s
{"action": "wait"}
wait—
——7
74,203 ms4,822 ms
0.62 s
{"action": "wait"}
wait—
——7
84,837 ms5,397 ms
0.56 s
{"action": "wait"}
wait—
——7
95,421 ms6,037 ms
0.62 s
{"action": "wait"}
wait—
——7
106,052 ms6,674 ms
0.62 s
{"action": "wait"}
wait—
——7
116,689 ms7,325 ms
0.64 s
{"action": "wait"}
wait—
——7
127,341 ms7,967 ms
0.63 s
{"action": "wait"}
wait—
——7
137,983 ms8,604 ms
0.62 s
{"action": "wait"}
wait—
——7
148,619 ms9,243 ms
0.62 s
{"action": "wait"}
wait—
——7
159,259 ms9,880 ms
0.62 s
{"action": "wait"}
wait—
——7
169,895 ms10,454 ms
0.56 s
{"action": "wait"}
wait—
——7
1710,468 ms11,092 ms
0.62 s
{"action": "wait"}
wait—
——7
1811,108 ms11,729 ms
0.62 s
{"action": "wait"}
wait—
——7
1911,745 ms12,367 ms
0.62 s
{"action": "wait"}
wait—
——7
2012,383 ms13,005 ms
0.62 s
{"action": "wait"}
wait—
——7
2113,020 ms13,644 ms
0.62 s
{"action": "wait"}
wait—
——7
2213,660 ms14,282 ms
0.62 s
{"action": "wait"}
wait—
——7
2314,298 ms14,917 ms
0.62 s
{"action": "wait"}
wait—
——7
2414,933 ms15,556 ms
0.62 s
{"action": "wait"}
wait—
——7
2515,572 ms16,194 ms
0.62 s
{"action": "wait"}
wait—
——7
2616,210 ms16,834 ms
0.62 s
{"action": "wait"}
wait—
——7
2716,848 ms17,408 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_s404.jsonl.