Add routing benchmark scripts; gitignore dataset and results

- run_benchmark.py: sends queries to /message, extracts tier= from docker
  logs, reports per-tier accuracy, saves results_latest.json
- run_voice_benchmark.py: voice path benchmark
- .gitignore: ignore benchmark.json (dataset) and results_latest.json
  (runtime output); benchmark scripts are tracked, data files are not

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.gitignore

@@ -1,2 +1,6 @@
 __pycache__/
 *.pyc
+logs/*.jsonl
+adolf_tuning_data/voice_audio/
+benchmark.json
+results_latest.json