T3 Code · Performance over time

MCP request authentication p95

All metrics
70 / 120
MCP request authentication p95 (lower is better)
52.2ms
18 Nov+21.9% vs the median of up to 7 previous complete nightlies, within noiseFork perf.9 1.32 ms, −96.7% vs its upstream base
AgentsRange

When upstream merges a fix, the lines meet.

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

As agents grow.

95th percentile of the server span McpHttpServer.authenticateRequest.

Lower is better. Noise band 77.1% on Linux x64 (n = 6), so a change counts beyond 82.1%.

Unit
ms
Better
lower
Noise band
77.1%, threshold 82.1% (n = 6)
Recorded from
17 Oct 2026; before that the series is a gap, never a zero
Platforms
Linux x64
Lane
Every record, inside the agent ladder
Upstream builds
Every upstream build
Source
result.json: metrics.spans["McpHttpServer.authenticateRequest"].p95_ms

MCP request authentication p95 (lower is better) at 1 to 250 agents, Linux x64

against
Records, 50 agents
DateTagMedianMin to maxValidvs up to 7 previousVerdict
18 Nov 2026v0.1.11-nightly.20261118.490352.2 ms30.4 to 54.53+21.9%within noise
17 Nov 2026v0.1.11-nightly.20261117.485141.5 ms33.7 to 42.03−26.6%within noise
16 Nov 2026v0.1.10-nightly.20261116.480032.8 ms31.5 to 38.93−76.9%improved beyond noise
15 Nov 2026v0.1.10-nightly.20261115.474939.5 ms27.6 to 43.73−82.6%improved beyond noise
14 Nov 2026v0.1.10-nightly.20261114.470942.8 ms39.0 to 47.13−83.3%improved beyond noise
13 Nov 2026v0.1.10-nightly.20261113.465656.5 ms53.4 to 64.73−80.3%improved beyond noise
12 Nov 2026v0.1.10-nightly.20261112.4606283 ms215 to 3673−1.1%within noise
11 Nov 2026v0.1.10-nightly.20261111.454466.7 ms16.5 to 88.53−76.7%improved beyond noise
10 Nov 2026v0.1.9-nightly.20261110.449162.9 ms54.1 to 80.83−78.0%improved beyond noise
9 Nov 2026v0.1.9-nightly.20261109.444345.8 ms28.9 to 50.23−84.0%improved beyond noise
8 Nov 2026v0.1.8-nightly.20261108.438066.6 ms15.7 to 90.63−76.8%improved beyond noise
7 Nov 2026v0.1.8-nightly.20261107.434023.7 ms17.9 to 39.23−91.7%improved beyond noise
6 Nov 2026v0.1.8-nightly.20261106.428868.2 ms52.8 to 78.93−76.2%improved beyond noise
5 Nov 2026v0.1.8-nightly.20261105.4234227 ms217 to 2793−20.6%within noise, thin reference
4 Nov 2026v0.1.8-nightly.20261104.4192286 ms226 to 3483−29.6%within noise, thin reference
3 Nov 2026v0.1.7-nightly.20261103.4138407 ms209 to 4453no reference yet
2 Nov 2026v0.1.7-nightly.20261102.4093483 ms449 to 5823no reference yet
1 Nov 2026v0.1.7-nightly.20261101.4048754 ms391 to 7723no reference yet
31 Oct 2026v0.1.7-nightly.20261031.4004599 ms531 to 7403no reference yet
30 Oct 2026v0.1.6-nightly.20261030.3940689 ms518 to 7383no reference yet
29 Oct 2026v0.1.6-nightly.20261029.38921,105 ms1,088 to 1,1463no reference yet
28 Oct 2026v0.1.4-nightly.20261028.3841980 ms889 to 1,0983no reference yet
27 Oct 2026v0.1.4-nightly.20261027.37961,251 ms1,149 to 1,3163no reference yet
26 Oct 2026v0.1.3-nightly.20261026.37401,037 ms1,015 to 1,1153no reference yet
25 Oct 2026v0.1.3-nightly.20261025.3682770 ms731 to 9323no reference yet
24 Oct 2026v0.1.3-nightly.20261024.36431,054 ms763 to 1,0723no reference yet
23 Oct 2026v0.1.3-nightly.20261023.35921,020 ms814 to 1,1103no reference yet
22 Oct 2026v0.1.2-nightly.20261022.3541118 ms110 to 1353no reference yet
21 Oct 2026v0.1.2-nightly.20261021.3499119 ms91.7 to 1293no reference yet
20 Oct 2026v0.1.1-nightly.20261020.3438107 ms100 to 1103no reference yet
19 Oct 2026v0.1.1-nightly.20261019.3373123 ms120 to 1273no noise band yet, no verdict
18 Oct 2026v0.1.1-nightly.20261018.3335133 ms106 to 1663no noise band yet, no verdict
17 Oct 2026v0.1.1-nightly.20261017.3272107 ms102 to 1153no noise band yet, no verdict
Ladder as a table
AgentsNightly 18 NovFork perf.9
1––
5052.2 ms1.32 ms
10053.8 ms4.49 ms
15051.2 ms2.77 ms
20051.2 ms6.53 ms
25052.8 ms5.32 ms
Download this series