Make Claude runs parallel-safe by moving the hard timeout to the chunk subprocess

Claude models are forced to --parallel 1 (SERIAL_ONLY_MODEL_PREFIXES in chunked_eval.py) because the last-resort wall-clock timeout in eval_no_tools._run_request_with_wall_timeout uses SIGALRM, which Python only delivers on the main thread. In worker threads the guard silently disappears, and a provider call that outlives its client timeout wedges the run.

Each chunk already executes as a subprocess (chunked_eval.run_chunk → subprocess.run). Moving the hard bound there makes parallelism safe without signals:

• pass timeout= to subprocess.run, sized as rows_in_chunk × wall_timeout + slack
• treat TimeoutExpired as an infrastructure failure: kill the chunk, leave it incomplete, let resume retry it
• drop the SIGALRM path (or keep it main-thread-only as a secondary bound)
• lift the serial restriction so claude-* can run --parallel 4+

A full Claude model run currently takes ~2–3h serial at chunk size 5; at --parallel 4 it's ~30–40 min. Ran into this again adding Sonnet 5 (2026-07-02).

🤖 Generated with Claude Code

Start with chunked_eval.py, especially run_chunk and its subprocess.run call, then inspect eval_no_tools._run_request_with_wall_timeout and SERIAL_ONLY_MODEL_PREFIXES. Implement the subprocess hard timeout so an expired chunk is killed and left incomplete for resume, remove or limit the SIGALRM path, and verify that claude-* runs can use parallel workers.