What does this PR do?

Adds an external-editor draft workflow to the CLI so long prompts can be edited in $EDITOR without abandoning the current draft buffer.

Related Issue

Fixes #TBD

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

• Added external-editor draft support in cli.py.
• Added editor workflow coverage in tests/cli/test_cli_external_editor.py.

How to Test

1. Run source /Volumes/Shared/turbo/hermes-agent/venv/bin/activate && scripts/run_tests.sh.
2. Start hermes, type a multi-line draft, press Ctrl+G, and verify the active draft opens in $EDITOR.
3. Save and exit the editor, then verify the edited draft is restored into the CLI prompt.

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

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

• Full suite on branch feat/external-editor (6b415c935830): 27 failed, 12923 passed, 38 skipped.
• Clean upstream/main baseline on this machine: 34 failed, 12909 passed, 38 skipped.
• This editor-only split reduced the observed repo-wide failure count by 7 on this machine.