feat: add factory simulation demo with maintenance optimisation

[Copilot]

Summary

New demo simulating a factory with 5 machines over 365 days. Each machine has sigmoid-based breakdown probability, configurable proactive maintenance intervals, and fixed repair downtime. Includes a tuner config to optimise maintenance schedules for maximum output, a Jupyter notebook for interactive exploration, and a mermaid process diagram.

Changes

• Iterator component drives the simulation for a configurable number of days
• Machine component (5 instances with distinct parameters):
  • $10k/day output when running
  • Breakdown probability: 1 / (1 + exp(-k * (days_since_maintenance - midpoint))) — different k and midpoint per machine
  • 5-day downtime on breakdown, 1-day downtime for scheduled maintenance
  • Seeded RNG for reproducibility
• Factory component aggregates daily output across all machines into cumulative total
• factory-simulation.yaml wires the process and defines a Tuner config optimising each machine's maintenance_interval (range 5–60 days) to maximise total_value
• build_process_spec() helper constructs the ProcessSpec programmatically for use with ProcessBuilder or Tuner
• factory-simulation.ipynb Jupyter notebook that imports components from factory_simulation.py, builds the process, includes a mermaid diagram (static image + dynamic MermaidDiagram.from_process() generation), runs the simulation with results/efficiency metrics, and explains the optimisation setup
• mkdocs.yaml updated to include the notebook under Demos > Fundamentals > Factory simulation

# Run single simulation
python factory_simulation.py
# Total factory output over 365 days: $14,790,000

# Optimisation (requires Ray) — uncomment in __main__
run_optimisation()

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[toby-coleman]

@copilot Include a Jupyter notebook as well (it could import Components from factory_simulation.py). It should be in a similar format to the other demo notebooks, and be referenced in the mkdocs yaml to publish as documentation. Include a mermaid diagram of the process that you built.

[Copilot]

@copilot Include a Jupyter notebook as well (it could import Components from factory_simulation.py). It should be in a similar format to the other demo notebooks, and be referenced in the mkdocs yaml...

Added in 52ac46a. The notebook factory-simulation.ipynb imports components from factory_simulation.py, includes a mermaid process diagram (both a static mermaid.ink image and a dynamic MermaidDiagram.from_process() cell), and is referenced in mkdocs.yaml under Demos > Fundamentals > Factory simulation. Verified the mkdocs build succeeds with the new entry.