T3 Code · Performance over time

First turn after a cold start

All metrics
100 / 120
First turn after a cold start (lower is better)
7,654ms
18 Nov+0.2% vs the median of up to 7 previous complete nightlies, within noiseFork perf.9 7,449 ms, −3.1% vs its upstream baseOnce per record, at start-up: the agents control does not apply.
DatabaseRange

When upstream merges a fix, the lines meet.

Upstream nightlyPerformance forkNoise bandRange of attempts green = better, red = worse, beyond the noise band

Once per record.

End-to-end time of the first turn after a cold server start.

Lower is better. Noise band 3.1% on Linux x64 (n = 3), so a change counts beyond 8.1%.

Unit
ms
Better
lower
Noise band
3.1%, threshold 8.1% (n = 3)
Recorded from
17 Oct 2026; before that the series is a gap, never a zero
Platforms
Linux x64
Lane
Once per record, outside the ladder
Upstream builds
Every upstream build
Source
first-turn.json: turn_ms

First turn after a cold start (lower is better)

Measured once per record, outside the agent ladder: on the large fixture after its migration, and on an empty database where the catalogue says so.

Records, once per record
DateTagMedianMin to maxValidvs up to 7 previousVerdict
18 Nov 2026v0.1.11-nightly.20261118.49037,654 ms7,654 to 7,6541+0.2%within noise
17 Nov 2026v0.1.11-nightly.20261117.48517,637 ms7,637 to 7,6371+0.1%within noise
16 Nov 2026v0.1.10-nightly.20261116.48007,648 ms7,648 to 7,6481+0.6%within noise
15 Nov 2026v0.1.10-nightly.20261115.47497,627 ms7,627 to 7,6271+0.5%within noise
14 Nov 2026v0.1.10-nightly.20261114.47097,654 ms7,654 to 7,6541+0.9%within noise
13 Nov 2026v0.1.10-nightly.20261113.46567,736 ms7,736 to 7,7361+2.1%within noise
12 Nov 2026v0.1.10-nightly.20261112.46067,558 ms7,558 to 7,5581−0.3%within noise
11 Nov 2026v0.1.10-nightly.20261111.45447,612 ms7,612 to 7,6121+0.4%within noise
10 Nov 2026v0.1.9-nightly.20261110.44917,516 ms7,516 to 7,5161−0.8%within noise
9 Nov 2026v0.1.9-nightly.20261109.44437,484 ms7,484 to 7,4841−1.3%within noise
8 Nov 2026v0.1.8-nightly.20261108.43807,554 ms7,554 to 7,5541−0.3%within noise
7 Nov 2026v0.1.8-nightly.20261107.43407,507 ms7,507 to 7,5071−0.9%within noise
6 Nov 2026v0.1.8-nightly.20261106.42887,524 ms7,524 to 7,5241−0.7%within noise
5 Nov 2026v0.1.8-nightly.20261105.42347,579 ms7,579 to 7,5791−0.1%within noise, thin reference
4 Nov 2026v0.1.8-nightly.20261104.41927,586 ms7,586 to 7,5861+0.1%within noise, thin reference
3 Nov 2026v0.1.7-nightly.20261103.41387,575 ms7,575 to 7,5751no reference yet
2 Nov 2026v0.1.7-nightly.20261102.40937,548 ms7,548 to 7,5481no reference yet
1 Nov 2026v0.1.7-nightly.20261101.40487,555 ms7,555 to 7,5551no reference yet
31 Oct 2026v0.1.7-nightly.20261031.40047,589 ms7,589 to 7,5891no reference yet
30 Oct 2026v0.1.6-nightly.20261030.39407,586 ms7,586 to 7,5861no reference yet
29 Oct 2026v0.1.6-nightly.20261029.38927,591 ms7,591 to 7,5911no reference yet
28 Oct 2026v0.1.4-nightly.20261028.38417,626 ms7,626 to 7,6261no reference yet
27 Oct 2026v0.1.4-nightly.20261027.37967,659 ms7,659 to 7,6591no reference yet
26 Oct 2026v0.1.3-nightly.20261026.37407,655 ms7,655 to 7,6551no reference yet
25 Oct 2026v0.1.3-nightly.20261025.36827,601 ms7,601 to 7,6011no reference yet
24 Oct 2026v0.1.3-nightly.20261024.36437,621 ms7,621 to 7,6211no reference yet
23 Oct 2026v0.1.3-nightly.20261023.35927,661 ms7,661 to 7,6611no reference yet
22 Oct 2026v0.1.2-nightly.20261022.35417,548 ms7,548 to 7,5481no reference yet
21 Oct 2026v0.1.2-nightly.20261021.34997,509 ms7,509 to 7,5091no reference yet
20 Oct 2026v0.1.1-nightly.20261020.34387,544 ms7,544 to 7,5441no reference yet
19 Oct 2026v0.1.1-nightly.20261019.33737,514 ms7,514 to 7,5141no noise band yet, no verdict
18 Oct 2026v0.1.1-nightly.20261018.33357,508 ms7,508 to 7,5081no noise band yet, no verdict
17 Oct 2026v0.1.1-nightly.20261017.32727,507 ms7,507 to 7,5071no noise band yet, no verdict
Download this series