What does this PR do?

Fixes holographic memory auto_extract so matched user messages are stored as derived facts instead of verbatim chat text.

For example, a message like:

Hey, for future work I prefer concise PR comments with no hype.

now stores:

User prefers concise PR comments with no hype.

instead of saving the full original message.

Related Issue

Fixes #22907

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

• plugins/memory/holographic/__init__.py
  • builds auto-extracted facts from regex capture groups instead of content[:400]
  • keeps the existing categories (user_pref, project)
• tests/plugins/memory/test_holographic_auto_extract.py
  • adds regression coverage for preference and project-decision extraction

How to Test

1. Run:

   python -m pytest -o addopts='' tests/plugins/memory/test_holographic_auto_extract.py -q

2. Run the focused memory plugin suite:

   python -m pytest -o addopts='' tests/plugins/memory -q

3. Run ruff on the changed files:

   ruff check plugins/memory/holographic/__init__.py tests/plugins/memory/test_holographic_auto_extract.py

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: Ubuntu/Linux

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 -o addopts='' tests/plugins/memory/test_holographic_auto_extract.py -q
..                                                                       [100%]
2 passed

$ python -m pytest -o addopts='' tests/plugins/memory -q
162 passed

$ ruff check plugins/memory/holographic/__init__.py tests/plugins/memory/test_holographic_auto_extract.py
All checks passed!

I did not run the full local suite for this small plugin change. The current upstream Tests workflow is already red on main, so I kept validation focused on the affected memory plugin area.