feat: add offline OSHA safety compliance tool for vision models

[anadya-s]

Summary

This PR introduces osha_safety_tool.py, a localized reasoning tool designed to bridge computer vision models (like YOLOv8) with the Aden framework for automated safety compliance.

Why this is needed

Currently, handling continuous video frame anomalies (e.g., missing PPE on a job site) requires routing every detection through an LLM, which rapidly burns through API rate limits.

This tool provides a hardcoded, offline reasoning layer. It allows a vision model to pass a simple anomaly string ("no hard hat") to the agent, which then cross-references an internal database to return the exact official OSHA standard (e.g., OSHA 1926.100(a)) and protocol without hitting external APIs.

Changes Made

• Created osha_safety_tool.py using the FastMCP pattern.
• Added a foundational database of critical construction edge cases (headgear, fall protection, scaffolding).
• Registered the tool in the _TOOL_MODULES and unverified tool registries.

Tested locally via a simulated YOLO-to-Agent bridge script.

Fixes #6172

[github-actions]

PR Requirements Warning

This PR does not meet the contribution requirements.
If the issue is not fixed within ~24 hours, it may be automatically closed.

Missing: No linked issue found.

To fix:

1. Create or find an existing issue for this work
2. Assign yourself to the issue
3. Re-open this PR and add Fixes #123 in the description

Exception: To bypass this requirement, you can:

• Add the micro-fix label or include micro-fix in your PR title for trivial fixes
• Add the documentation label or include doc/docs in your PR title for documentation changes

Micro-fix requirements (must meet ALL):

Qualifies	Disqualifies
< 20 lines changed	Any functional bug fix
Typos & Documentation & Linting	Refactoring for "clean code"
No logic/API/DB changes	New features (even tiny ones)

Why is this required? See #472 for details.