Fix percentage mismatch between chat messages and OBS overlay

[Copilot]

Chat was displaying different similarity percentages than the overlay for the same guess (e.g. "maison: 47%" in chat vs 48% on overlay) due to inconsistent rounding strategies.

Root cause

• Chat (bot/bot.py): int(score * 100) — truncates toward zero
• Overlay (index.html): Math.round(score * 100) — rounds to nearest integer

For a score like 0.475, this produces 47% in chat and 48% in the overlay.

Changes

• bot/bot.py: Replace int(score * 100) with round(score * 100) in all four display sites — guess (new guess + already-cited), hint, and status commands
• tests/test_commands.py: Add regression test using a scorer returning 0.475 to assert chat shows 48%, not 47%

# Before
pct = int(result.entry.score * 100)   # 0.475 → 47

# After
pct = round(result.entry.score * 100) # 0.475 → 48

Original prompt

---

This section details on the original issue you should resolve

<issue_title>The percentage is not always the same in the chat and in the overlay.</issue_title>
<issue_description></issue_description>

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

• Fixes The percentage is not always the same in the chat and in the overlay. #32

---

📱 Kick off Copilot coding agent tasks wherever you are with GitHub Mobile, available on iOS and Android.