What does this PR do?

_has_natural_response_ending() checks whether the last character of a response is in a hardcoded punctuation charset. Emoji characters (common sign-offs like 🌙, ✅, 👍, 🎉) are not in this charset, so responses ending with emoji are incorrectly classified as "truncated" by _should_treat_stop_as_truncated(). This causes silent retry loops for Ollama/GLM users whose responses naturally end with emoji.

The fix adds a Unicode category check — characters in categories starting with S (Symbol: So, Sk, Sm, Sc) are treated as natural endings.

Related Issue

Fixes #14572

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 🔒 Security fix
• 📝 Documentation update
• ✅ Tests (adding or improving test coverage)
• ♻️ Refactor (no behavior change)
• 🎯 New skill (bundled or hub)

Changes Made

• run_agent.py: After the existing punctuation check, add a Unicode category check — characters in categories starting with S (Symbol: So, Sk, Sm, Sc) are treated as natural endings.

How to Test

1. Run the targeted test:

   python -m pytest tests/run_agent/test_emoji_stop_detection.py -v

2. 18 parametrized cases cover emoji, CJK punctuation, code blocks, and non-endings.

Validation table:

Tested on macOS (Python 3.14).

Checklist

Code

• I've read the Contributing Guide
• My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
• I searched for existing PRs to make sure this isn't a duplicate
• My PR contains only changes related to this fix/feature (no unrelated commits)
• I've run pytest tests/ -q and all tests pass
• I've added tests for my changes (required for bug fixes, strongly encouraged for features)
• I've tested on my platform: macOS 15 (Darwin 24.6.0)

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — or N/A
• I've updated cli-config.yaml.example if I added/changed config keys — or N/A
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A
• I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A
• I've updated tool descriptions/schemas if I changed tool behavior — or N/A

Screenshots / Logs

python -m pytest tests/run_agent/test_emoji_stop_detection.py -v
# 18 parametrized cases pass