Add OrcaRouter agent example

[JinhaoSong322]

Summary

Adds a new example, examples/orcarouter-agent/, that shows how to build a small
stateful chat agent with Burr backed by OrcaRouter.

OrcaRouter is an OpenAI-compatible gateway (https://api.orcarouter.ai/v1) that
routes to a wide range of models through a single API key. 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.

Because the endpoint is OpenAI-compatible, the example uses the standard openai
client with base_url pointed at OrcaRouter and the orcarouter/auto model
alias. The agent loops between human_input and ai_response actions,
accumulating a chat_history in state.

Changes

• examples/orcarouter-agent/application.py — Burr state machine with two
  actions (human_input, ai_response) calling https://api.orcarouter.ai/v1
  via the openai client (ORCAROUTER_API_KEY, optional
  ORCAROUTER_BASE_URL/ORCAROUTER_MODEL).
• examples/orcarouter-agent/README.md, notebook.ipynb,
  requirements.txt, __init__.py, statemachine.png — standard example
  contents (mirrors examples/simple-chatbot-intro/).
• examples/README.md — added the example to the index.
• docs/ecosystem.rst — added an OrcaRouter row to the LLM & AI Frameworks table.

How I tested this

• python -m pytest validate_examples.py in examples/ — 48 passed (includes
  orcarouter-agent).
• black, isort, flake8 clean on the new example.
• scripts/check_asf_headers.py — clean.
• Live test with a real OrcaRouter key through the example's code path
  (application.run(..., halt_after=["ai_response"])) — returned a valid
  completion from https://api.orcarouter.ai/v1.

Notes

No existing Burr code was changed; this only adds a new example and two doc
index entries.

Checklist

• PR has an informative and human-readable title (this will be pulled into the release notes)
• Changes are limited to a single goal (no scope creep)
• Code passed the pre-commit check & code is left cleaner/nicer than when first encountered.
• Any change in functionality is tested
• New functions are documented (with a description, list of inputs, and expected output)
• Placeholder code is flagged / future TODOs are captured in comments
• Project documentation has been updated if adding/changing functionality.

Disclosure: I'm an engineer on the OrcaRouter team.