feat(demo): add OrcaRouter as a named LLM provider in the demo app

[armyluki-wq]

Add OrcaRouter as a named LLM provider in the Agent Demo, mirroring how the existing Llama 4 (Groq) and Qwen 3 options wire an OpenAI-compatible endpoint into openai_llm2_python.

OrcaRouter is an OpenAI-compatible AI gateway built for both models and agents. Like OpenRouter, it exposes a provider/model namespace across many models — but it also combines adaptive routing, automatic failover, zero-markup inference, observability, guardrails, and agent-tool governance behind the same endpoint. Adding orcarouter as a first-class provider means TEN users can use that stack directly, without treating OrcaRouter as an anonymous custom base URL. It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.

Changes:

• Add an orcarouter predefined graph (base_url: https://api.orcarouter.ai/v1, model orcarouter/fusion) to the demo property.json
• Expose it as a selectable option in the demo frontend graph dropdown with an OrcaRouter icon
• Document ORCAROUTER_API_KEY in the demo README

Verification:

• next build (compiles + type-checks) passes for the demo frontend
• Live-tested https://api.orcarouter.ai/v1/chat/completions with model orcarouter/fusion (stream + non-stream) → HTTP 200 with valid content
• property.json validated as JSON

Discord: discord.gg/YEubt8enRA · X: https://x.com/OrcaRouter

I'm an engineer on the OrcaRouter team.