{ "schema_version": 1, "experiment": "7-9", "status": "incomplete", "generated_at_utc": "2026-07-29T22:31:57.870199+00:00", "run_dir": "chapter7/agent-cost-analysis/runs/exp7-9-kimi25-20260730-v2", "git_commit": "4a7f37cf278bd15948c409f14533017c4c7fbc29", "command": "python demo.py --live --scenario all --model kimi-k2.5 --save-trace TRACE --output REPORT", "provider_receipt_count": 32, "status_reasons": [ "The real 2x2 run covers one eight-turn refund workflow; the manuscript asks for several representative task types and aggregate task-level p50/p95/p99.", "Reasoning-token usage and provider response IDs are recorded, but success-quality equivalence across optimizations is not independently judged.", "The 32 measured calls have unique provider response IDs; 16 cache-warmup calls were intentionally excluded from measured traces and do not have retained receipts." ], "inputs": [ { "path": "chapter7/agent-cost-analysis/agent.py", "bytes": 17109, "sha256": "30866b34ead7ff2897964aaf1e07867691102982971903f8a2a4172c48bfd718" }, { "path": "chapter7/agent-cost-analysis/tracer.py", "bytes": 12309, "sha256": "fb673ac8f10ca037b6df3822e00e6cbb21b8381b731736fb1b2a30748e7226fe" }, { "path": "chapter7/agent-cost-analysis/demo.py", "bytes": 13477, "sha256": "75dc27633829fe2a730c5654a38f6af90fd58eceee630dfa985e386fa536c104" }, { "path": "chapter7/agent-cost-analysis/config.py", "bytes": 5701, "sha256": "0a92de4849994e74b28e3b5ad6c308cc154a2b984d8827f859b7f15d9fbbb463" }, { "path": "chapter7/model-benchmark/campaign_config.json", "bytes": 8103, "sha256": "9a839ad907852798b35af5b4623814c343943ae1596a78d650d1a1affc93b17a" } ], "artifacts": [ { "path": "chapter7/agent-cost-analysis/runs/exp7-9-kimi25-20260730-v2/report.json", "bytes": 17810, "sha256": "92b0ee29c7df3dd28778d625fe699662dee56a5401141631ead450cd2ca37ace" }, { "path": "chapter7/agent-cost-analysis/runs/exp7-9-kimi25-20260730-v2/trace.json", "bytes": 17810, "sha256": "92b0ee29c7df3dd28778d625fe699662dee56a5401141631ead450cd2ca37ace" } ] }