Fix flaky TestDatagrams by increasing wait time 10x

[Copilot]

TestDatagrams fails intermittently when only ~64/100 datagrams are received before session closure, below the 80% threshold.

Changes

• Increased wait time from 10ms to 100ms (50ms → 500ms in CI with scaleDuration multiplier)

The original timing was insufficient for datagram delivery through the network stack, particularly under CI resource constraints. UDP datagrams need time to traverse the stack before the session closes.

// Before
time.Sleep(scaleDuration(10 * time.Millisecond))

// After  
time.Sleep(scaleDuration(100 * time.Millisecond))

Original prompt

---

This section details on the original issue you should resolve

<issue_title>flaky TestDatgrams</issue_title>
<issue_description>```
=== RUN TestDatagrams
webtransport_test.go:710: sent: 100, received: 64
webtransport_test.go:711:
Error Trace: /Users/runner/work/webtransport-go/webtransport-go/webtransport_test.go:711
Error: "64" is not greater than "80"
Test: TestDatagrams
--- FAIL: TestDatagrams (0.06s)</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes flaky TestDatgrams #237

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

[macroscopeapp]

Adjust blank-line formatting in TestDatagrams to prepare threshold fix for flaky behavior

Modify only whitespace by changing blank lines in test files related to TestDatagrams.

📍Where to Start

Start with the TestDatagrams test definition in tests/datagrams_test.go.

---

Macroscope summarized 4276b97. (Automatic summaries will resume when PR exits draft mode or review begins).