liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
65 lines
2.1 KiB
JSON
65 lines
2.1 KiB
JSON
{
|
|
"schema_version": "chapter3-evidence-v1",
|
|
"experiment": "4-2",
|
|
"run_id": "20260729T185433Z-4_2-e028c9db",
|
|
"created_at": "2026-07-29T18:54:33.367744+00:00",
|
|
"status": "passed",
|
|
"run_dir": "/Users/boj/book/ai-agent-book/chapter4/multimodal-agent/validation/runs/20260729T185433Z-4_2-e028c9db",
|
|
"artifacts": {
|
|
"evidence.json": "024358e7b58266eedbedda3cc880a61462c119a89c58e475f4c007dbcb8ff144",
|
|
"receipts.json": "2aa961a1f7527417dd0d25ac6e542aaad9dc2ffaa7b40a4a450cb5fffe86ceac"
|
|
},
|
|
"inputs": [
|
|
{
|
|
"path": "/Users/boj/book/ai-agent-book/chapter4/multimodal-agent/campaign.py",
|
|
"sha256": "6f8162a0e124cef1acada4fbfadc6a1427aa487be24670aaceba2d668820ee3c",
|
|
"bytes": 16104
|
|
},
|
|
{
|
|
"path": "/Users/boj/book/ai-agent-book/chapter4/multimodal-agent/create_sample.py",
|
|
"sha256": "1f4fcd0e119a76a74c06744a585d31bc4bd4f755f813f8b2518f77127eaa1e72",
|
|
"bytes": 4846
|
|
},
|
|
{
|
|
"path": "/Users/boj/book/ai-agent-book/chapter4/multimodal-agent/test_files/sample_chart.png",
|
|
"sha256": "eaf8ac53fbc65a4e6ce0611d441cd12ddd2ed48ef8a727a9d6f22aef70605f39",
|
|
"bytes": 38417
|
|
},
|
|
{
|
|
"path": "/Users/boj/book/ai-agent-book/chapter4/multimodal-agent/test_files/sample_report.pdf",
|
|
"sha256": "db4828a20a12ad70dab5c196d23e4fa407f75c4e3cff2bda22c401de65cb9c2e",
|
|
"bytes": 46368
|
|
}
|
|
],
|
|
"summary": {
|
|
"native-multimodal": {
|
|
"cases": 4,
|
|
"exact_accuracy": 1.0,
|
|
"judge_accuracy": 1.0,
|
|
"mean_latency_ms": 8011.01425
|
|
},
|
|
"extract-to-text": {
|
|
"cases": 4,
|
|
"exact_accuracy": 0.0,
|
|
"judge_accuracy": 0.0,
|
|
"mean_latency_ms": 10867.427
|
|
},
|
|
"tool-on-demand": {
|
|
"cases": 4,
|
|
"exact_accuracy": 1.0,
|
|
"judge_accuracy": 1.0,
|
|
"mean_latency_ms": 29794.60875
|
|
}
|
|
},
|
|
"acceptance": {
|
|
"same_two_questions_all_paradigms_and_artifacts": true,
|
|
"png_and_pdf_used": true,
|
|
"chart_answers_absent_from_pdf_body_text": true,
|
|
"real_native_vision_calls": true,
|
|
"tool_selected_on_demand": true,
|
|
"real_tool_vision_calls": true,
|
|
"external_moonshot_judge": true,
|
|
"all_calls_checkpointed": true
|
|
}
|
|
}
|