Add Runloop devbox lifecycle cookbook

[tode-rl]

Summary

Adds a registered Agents SDK cookbook for running stateful workflows on Runloop devboxes. The new example includes a notebook walkthrough, reusable CLI script, deterministic tax helper scripts, sample PDFs, offline tests, requirements, and registry/author metadata.

Motivation

This demonstrates how to use the OpenAI Agents SDK with a persistent Runloop devbox lifecycle: create, stage documents, suspend while idle, wake and resume for follow-up work, verify persisted artifacts with another agent, snapshot the final workspace, and clean up.

Validation

• python3 -m py_compile examples/agents_sdk/runloop-devbox-lifecycle/runloop_w2filer_devbox_lifecycle.py examples/agents_sdk/runloop-devbox-lifecycle/data/*.py
• uv run --with nbformat python .github/scripts/check_notebooks.py
• uv run --with pytest --with pytest-asyncio pytest examples/agents_sdk/runloop-devbox-lifecycle/tests (43 passed)
• uv run --with pyyaml python -c 'import yaml; [yaml.safe_load(open(path, encoding="utf-8")) for path in ("registry.yaml", "authors.yaml")]; print("yaml valid")'

For new content

• I have added a new entry in registry.yaml and authors.yaml so that my content renders on the cookbook website.
• I have conducted a self-review of my content based on the contribution guidelines:
  • Relevance: This content is related to building with OpenAI technologies and is useful to others.
  • Uniqueness: I have searched for related examples in the OpenAI Cookbook, and verified that my content offers new insights or unique information compared to existing documentation.
  • Spelling and Grammar: I have checked for spelling or grammatical mistakes.
  • Clarity: I have done a final read-through and verified that my submission is well-organized and easy to understand.
  • Correctness: The information I include is correct and all of my code executes successfully.
  • Completeness: I have explained everything fully, including all necessary references and citations.