[ArthurFouquet]

Updated the quickstart guide to include configuration of model IDs and use of a custom benchmark class.

Description

While following the quickstart guide with a fresh maseval[openai] install (v0.5.1), the "Using a default agent" and "Plugging in your own agent" examples under Existing Benchmarks did not run as written:

• DefaultAgentTau2Benchmark cannot be instantiated directly since get_model_adapter is abstract — the example needs a subclass implementing it.
• agent_data is not accepted by the Tau2Benchmark constructor; it belongs in .run(tasks, agent_data=...).
• The user simulator's model_id must be set via configure_model_ids() after load_tasks(), or .run() raises a ValueError.

This PR updates both code examples to reflect the current API, verified against a real run.

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Code quality improvement (refactoring, formatting, etc.)

Checklist

Contribution

• I have read the CONTRIBUTING.md guide.
• Commits follow "How to write a good git commit message"

Documentation

• Added/updated docstrings for new/modified functions as instructed CONTRIBUTING.md
• Updated relevant documentation in docs/ (if applicable)
• Tag github issue with this PR (if applicable)

Changelog

• Added entry to CHANGELOG.md under [Unreleased] section
• OR this is a documentation-only change (no changelog needed)

Architecture (if applicable)

• Core/Interface separation: Changes in maseval/core/ do NOT import from maseval/interface/
• Dependencies: New core dependencies added sparingly; framework integrations go to optional dependencies

Additional Notes

Only fixed the two Tau2Benchmark-based examples, which I tested end-to-end. Did not touch the generic MyBenchmark(Benchmark) example at the top of the page since I haven't verified whether the base Benchmark class has the same agent_data signature issue — flagging in case a maintainer wants to check that separately.