{"command":"eval benchmark agentic artifact --run-id swift-tp2-r3-agentic","context":{"command":null,"command_host":null,"command_runtime":null,"controller_endpoint":null,"controller_endpoint_kind":null,"execution_host":null,"execution_runtime":null,"gpu_role":null,"gpu_uuid":null,"overlay":null,"resource":null,"resource_endpoint":null,"resource_endpoint_kind":null,"resource_host":null,"resource_runtime":null,"target":null,"topology":null,"transport":null},"data":"{\"data\": {\"created_at\": \"2026-09-26T17:56:51.139732Z\", \"failure\": null, \"partial\": false, \"provenance\": {\"endpoint\": {\"base_url\": \"http://127.0.0.1:39146/v1\", \"model\": \"swift15-flash-next-nvfp4-tp2-327k-r3\"}, \"finished_at\": \"2026-09-26T17:56:51.139667Z\", \"started_at\": \"2026-09-26T17:55:02.134378Z\", \"submitted_at\": \"2026-09-26T17:50:34.238778+00:00\", \"worker\": {\"id\": \"local-benchmark\"}}, \"results\": {\"evidence\": {\"completeness\": \"completed\", \"created_at\": \"2026-09-26T17:56:51.130695Z\", \"evidence_kind\": \"measured\", \"failure\": null, \"identities\": {\"concurrency\": {\"requests\": 1, \"workers\": 1}, \"context\": {\"configured_tokens\": 327680}, \"dataset\": {\"name\": \"deterministic-native\", \"profile_sha256\": \"fce0e6e1e7497585bdfc6f76507d3baaff99a6b4f174d841d268de20c68de7f6\"}, \"hardware\": {\"gpu\": \"2x RTX PRO 6000 Blackwell Max-Q\", \"tensor_parallel_size\": 2, \"vram_mib_per_gpu\": 97887}, \"harnesses\": {\"native\": {\"schema\": \"anvil-serving.agentic/v1\"}}, \"image\": {\"status\": \"not-applicable\"}, \"model\": {\"repository\": \"ukisai/Swift-1.5-Qwen3.8-Flash-Next-NVFP4\", \"revision\": \"3ff0520224f264a2d0ac4ab56ece8f2f13aadb38\", \"served_name\": \"swift15-flash-next-nvfp4-tp2-327k-r3\"}, \"runtime\": {\"engine_revision\": \"ced6857afa0ea7b2e3f0846a62e1394e90f15607\", \"image_id\": \"sha256:8a69ffad015f138d7170c4ddc429e230a3bc1c1719f67e14324749df200a4b90\"}, \"served_model\": {\"configured_context\": 327680, \"id\": \"swift15-flash-next-nvfp4-tp2-327k-r3\"}, \"topology\": {\"kind\": \"co-resident-benchmark-client\", \"worker_id\": \"local-benchmark\"}}, \"promotion\": {\"authorized\": false, \"message\": \"Benchmark evidence does not authorize model promotion; promotion is a separate human decision.\"}, \"run\": {\"ownership_id\": \"swift-tp2-20260926\", \"profile\": \"scout\", \"run_id\": \"swift-tp2-r3-agentic\", \"spec_sha256\": \"9ab4f29f13aca64b23465ef5c67a4b1a6ede77c73f79b9adf6c2a93ba6dc3e7c\", \"suite\": \"agentic\"}, \"schema\": \"anvil-serving.benchmark-evidence/v1\", \"stages\": [{\"evidence\": [{\"bytes\": 542, \"path\": \"evidence/0-assets.json\", \"sha256\": \"7614bf22a0ec8957646ef110eac0d450922c2667fedbb6d725aa560100db71f2\"}], \"name\": \"asset_preparation\", \"sequence\": 0, \"status\": \"completed\"}, {\"evidence\": [{\"bytes\": 1999, \"path\": \"evidence/0-preflight.json\", \"sha256\": \"8733e0ec6ece30190573f5caf7ab0e6db3bd1ac049b0d92aad1169cd3ea76d87\"}], \"name\": \"preflight\", \"sequence\": 1, \"status\": \"completed\"}, {\"evidence\": [{\"bytes\": 36301, \"path\": \"evidence/0-agentic.json\", \"sha256\": \"d6fdc705c925b9fd586d0cd3ba7a4c517adaf6a71ce7fb5e1ca029f46ec2a414\"}], \"name\": \"agentic\", \"sequence\": 2, \"status\": \"completed\"}], \"summary\": {\"attempted\": 18, \"pass_rate\": 1.0, \"passed\": 18, \"required_pass_rate\": 0.75}}}, \"run\": {\"ownership_id\": \"swift-tp2-20260926\", \"profile\": \"scout\", \"run_id\": \"swift-tp2-r3-agentic\", \"spec_sha256\": \"9ab4f29f13aca64b23465ef5c67a4b1a6ede77c73f79b9adf6c2a93ba6dc3e7c\", \"suite\": \"agentic\"}, \"schema\": \"anvil-serving.benchmark-result/v1\", \"status\": \"completed\"}, \"ok\": true}\n","error":null,"ok":true,"warnings":[]}
