Configure ANN query concurrency

[joyemang33]

Summary

• Move Vector DB ANN query concurrency into config.yaml and make the evaluator read it as the default.
• Set the task to 8 concurrent workers with 64 timed queries per worker.
• Update the agent-facing README files so agents see the actual CPU/memory/query budget.

Please read CONTRIBUTING.md before submitting.

Type of Change

• New research problem
• New algorithmic problem
• New Frontier-CS 2.0 problem
• Bug fix
• Documentation update
• Other:

Testing

• python3 -m py_compile 2.0/problems/vector_db_ann/evaluator.py
• git diff --check
• Harbor smoke trial with Codex subscription auth: Vector DB ANN produced a valid iterative score with concurrency=8, n_queries=512, and recall_at_10=1.0; verifier used best iterative submission.

Checklist

• Code follows the project structure and conventions
• Self-review completed
• Documentation updated (if applicable)

CI Validation (for new problems)

Not a new problem; this updates an existing Frontier-CS 2.0 task.