Add Ollama installation to the setup script

[Copilot]

Ollama is now provisioned alongside the rest of the macOS environment so local model workflows are available out of the box. The setup remains idempotent and skips installation when ollama is already present.

• Install flow

  • Added an Ollama section to install.sh
  • Uses the upstream installer when ollama is missing
  • Preserves the existing skip-on-present pattern

• Coverage

  • Added Bats coverage for both install and skip paths
  • Updated the all-tools-present scenario to include Ollama

• Docs / CI

  • Documented Ollama in the README tool table
  • Added ollama --version to macOS CI verification

if ! command -v ollama &>/dev/null; then
  echo "🦙 Ollama not found. The work needs a local model stack. Installing..."
  curl -fsSL https://ollama.com/install.sh | sh
else
  echo "🦙 Ollama is already running on the Severed Floor."
fi

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: bf9efe2b35

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Use a macOS-compatible Ollama installer

When Ollama is absent on the macOS systems this project targets—including the macos-latest E2E job—the upstream install.sh rejects non-Linux hosts with “This script is intended to run on Linux only.” Because pipefail and set -e are enabled, this command terminates the entire setup without installing Ollama or printing the completion message; use Ollama's macOS package/cask instead.

Useful? React with 👍 / 👎.