NVIDIA fix: - Replace parse_vlm_json (requires full schema: global_summary/entities_json/ frame_details/compute_provider) with lightweight _parse_single_frame_json that only extracts per-frame fields (person/action/clothing/etc) - Root cause: NVIDIA adapter does per-frame analysis returning single-frame JSON, but parse_vlm_json rejected it for missing full-schema fields - Verified: task 297 → 6/6 frames parsed successfully, first SUCCESS Gemini + circuit breaker tuning: - Gemini timeout: 30s → 90s (multi-image vision analysis needs more time) - NVIDIA timeout: 20s → 30s (per-frame API call) - Circuit breaker threshold: 3 → 5 (less aggressive tripping) - Circuit breaker cooldown: 600s → 300s (faster recovery)
2.7 KiB
2.7 KiB