3 Commits

Author	SHA1	Message	Date
alvis	0fbdbf3a5e	Add run_routing_benchmark.py — dedicated routing-only benchmark ... Tests routing accuracy for all tiers with no_inference=True hardcoded. Fast (QUERY_TIMEOUT=30s), no GPU check, shares benchmark.json dataset. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-03-24 07:25:16 +00:00
alvis	98095679be	Fix benchmark log extraction: first tier match, increase log tail to 300 ... - Remove reversed() from extract_tier_from_logs: first match = routing decision (dry-run complex logs tier=complex early, then overwrites with tier=medium at done) - Increase log tail from 80→300 to handle concurrent log activity Fixes #7, #10 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-03-24 02:42:27 +00:00
Alvis	bd951f943f	Move benchmark scripts into benchmarks/ subdir ... - benchmarks/run_benchmark.py (was run_benchmark.py) - benchmarks/run_voice_benchmark.py (was run_voice_benchmark.py) - Scripts use Path(__file__).parent so paths resolve correctly in subdir - .gitignore updated: ignore benchmarks/benchmark.json, results_latest.json, voice_results*.json, voice_audio/ Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-03-24 02:02:46 +00:00