✨ Add opt-in GNN features to the RL predictor

[flowerthrower]

🤖 AI text below 🤖

Description

Adds opt-in GNN circuit embeddings to the RL predictor while leaving PredictorEnv and the default flat MaskablePPO path unchanged.

The implementation preserves the prototype's ordered 52-dimensional node features, ordered 36-dimensional global features, GraphSAGE/attention/shared-trunk topology, separate encoder and policy learning rates, and tuned paper configuration. Seeding follows #797's opt-in contract instead of injecting an implicit seed.

Exact variable-sized PyG graph sidecars pass through a focused rollout buffer and narrow collect_rollouts specialization. Masking, callbacks, numeric rollout state, GAE, PPO training, logging, and .zip serialization remain in SB3; graphs are not padded or truncated.

Torch Geometric remains optional through mqt.predictor[gnn], requiring torch-geometric>=2.7.0 on Python below 3.14 and torch-geometric>=2.8.0 on Python 3.14 or newer. This PR also raises the minimum sb3_contrib version from 2.0.0 to 2.3.0. The prototype checkpoint is not migrated because its action-output schema differs from this stack.

This is position 9 and the top of the stack. It depends on #799. No GNN-specific automated tests are included; external documentation and a dedicated test suite are deferred as requested.

Fixes #669

Checklist

• The pull request only contains commits that are focused and relevant to this change.
• I have added appropriate tests that cover the new/changed functionality.
• I have updated the documentation to reflect these changes.
• I have added entries to the changelog for any noteworthy additions, changes, fixes, or removals.
• I have added migration instructions to the upgrade guide (if needed).
• The changes follow the project's style guidelines and introduce no new warnings.
• The changes are fully tested and pass the CI checks.
• I have reviewed my own code changes.

If PR contains AI-assisted content:

• Any agent that created, edited, or submitted GitHub content was explicitly authorized for that scope, as required by our AI Usage Guidelines.
• Every agent-authored or agent-edited public text body begins with the visible disclosure 🤖 *AI text below* 🤖 (titles are exempt).
• I have disclosed AI assistance in the PR description.
• I confirm that I have personally reviewed and understood all AI-generated content, and accept full responsibility for it.

[codecov]

Codecov Report

❌ Patch coverage is 5.64516% with 351 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/mqt/predictor/rl/gnn.py	0.0%	337 Missing ⚠️
src/mqt/predictor/rl/predictor.py	60.0%	14 Missing ⚠️

📢 Thoughts on this report? Let us know!