fix: limit concurrent Modal sandbox creations to avoid deadlocks

- Add max_concurrent_tasks config (default 8) with semaphore in TB2 eval
- Pass cwd: /app via register_task_env_overrides for TB2 tasks
- Add /home/ to host path prefixes as safety net for container backends

When all 86 TerminalBench2 tasks fire simultaneously, each creates a Modal sandbox
via asyncio.run() inside a thread pool worker. Modal's blocking calls deadlock
when too many are created at once. The semaphore ensures max 8 concurrent creations.

Co-Authored-By: hermes-agent[bot] <hermes-agent[bot]@users.noreply.github.com>

environments/benchmarks/terminalbench_2/default.yaml

@@ -29,6 +29,10 @@ env:
   wandb_name: "terminal-bench-2"
   ensure_scores_are_not_same: false
   data_dir_to_save_evals: "environments/benchmarks/evals/terminal-bench-2"
+  # CRITICAL: Limit concurrent Modal sandbox creations to avoid deadlocks.
+  # Modal's blocking calls (App.lookup, etc.) deadlock when too many sandboxes
+  # are created simultaneously inside thread pool workers via asyncio.run().
+  max_concurrent_tasks: 8
 
 openai:
   base_url: "https://openrouter.ai/api/v1"