← all runs · ← report

wi007_qwen3_vl_8b_instruct_wi006 / live_d2_harness_pending_s401 not valid

What this trial was

runwi007_qwen3_vl_8b_instruct_wi006triallive_d2_harness_pending_s401conditionlivescenariopending_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 clicks1suppressed proposals0waits24decisions25exact 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 — 25 decisions

#Bmodel done
B→D
model response (raw)parsedaction (canvas px)D (commit)A (receipt)out tokens
1531 ms1,065 ms
0.53 s
{"action": "wait"}
wait—
——7
21,197 ms1,729 ms
0.53 s
{"action": "wait"}
wait—
——7
31,742 ms2,304 ms
0.56 s
{"action": "wait"}
wait—
——7
42,318 ms2,943 ms
0.63 s
{"action": "wait"}
wait—
——7
52,959 ms3,579 ms
0.62 s
{"action": "wait"}
wait—
——7
63,595 ms4,216 ms
0.62 s
{"action": "wait"}
wait—
——7
74,232 ms4,855 ms
0.62 s
{"action": "wait"}
wait—
——7
84,871 ms5,430 ms
0.56 s
{"action": "wait"}
wait—
——7
95,443 ms6,068 ms
0.62 s
{"action": "wait"}
wait—
——7
106,084 ms6,705 ms
0.62 s
{"action": "wait"}
wait—
——7
116,720 ms7,341 ms
0.62 s
{"action": "wait"}
wait—
——7
127,356 ms7,976 ms
0.62 s
{"action": "wait"}
wait—
——7
137,992 ms8,614 ms
0.62 s
{"action": "wait"}
wait—
——7
148,630 ms9,187 ms
0.56 s
{"action": "wait"}
wait—
——7
159,201 ms9,827 ms
0.63 s
{"action": "wait"}
wait—
——7
169,842 ms10,465 ms
0.62 s
{"action": "wait"}
wait—
——7
1710,481 ms11,102 ms
0.62 s
{"action": "wait"}
wait—
——7
1811,117 ms11,740 ms
0.62 s
{"action": "wait"}
wait—
——7
1911,756 ms12,380 ms
0.62 s
{"action": "wait"}
wait—
——7
2012,395 ms13,017 ms
0.62 s
{"action": "wait"}
wait—
——7
2113,033 ms13,653 ms
0.62 s
{"action": "wait"}
wait—
——7
2213,668 ms14,227 ms
0.56 s
{"action": "wait"}
wait—
——7
2314,241 ms14,866 ms
0.62 s
{"action": "wait"}
wait—
——7
2414,882 ms16,643 ms
1.76 s
{"action": "click", "x": 919, "y": 197}
click
img (919, 197)
{'kind': 'click', 'x': 294, 'y': 47}
16,643 ms16,663 ms · invalid23
2516,692 ms17,223 ms
0.53 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_s401.jsonl.