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
95 lines
2.0 KiB
JSON
95 lines
2.0 KiB
JSON
{
|
|
"schema_version": 1,
|
|
"experiment": "6-8",
|
|
"arm": "open-model-api",
|
|
"status": "passed",
|
|
"checks": [
|
|
{
|
|
"name": "existing_manifest_integrity",
|
|
"passed": true,
|
|
"detail": {
|
|
"failures": [],
|
|
"unmanifested_files": []
|
|
}
|
|
},
|
|
{
|
|
"name": "open_model_identity",
|
|
"passed": true,
|
|
"detail": {
|
|
"requested": "qwen/qwen3-vl-32b-instruct",
|
|
"provider_reported": [
|
|
"qwen/qwen3-vl-32b-instruct"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"name": "real_api_receipts",
|
|
"passed": true,
|
|
"detail": {
|
|
"requests": 16,
|
|
"responses": 16,
|
|
"steps": 16
|
|
}
|
|
},
|
|
{
|
|
"name": "bounded_read_only_actions",
|
|
"passed": true,
|
|
"detail": {
|
|
"one_action_per_step": true,
|
|
"actions": [
|
|
"navigate",
|
|
"input",
|
|
"click",
|
|
"navigate",
|
|
"navigate",
|
|
"click",
|
|
"click",
|
|
"click",
|
|
"input",
|
|
"click",
|
|
"click",
|
|
"click",
|
|
"wait",
|
|
"click",
|
|
"wait",
|
|
"done"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"name": "completed_within_limit",
|
|
"passed": true,
|
|
"detail": {
|
|
"status": "complete",
|
|
"steps": 16,
|
|
"limit": 25
|
|
}
|
|
},
|
|
{
|
|
"name": "answer_grounded_in_final_browser_observation",
|
|
"passed": true,
|
|
"detail": {
|
|
"missing_observation_fragments": [],
|
|
"final_screenshot": "screenshots/step-016.png",
|
|
"final_screenshot_sha256": "3639379122337818d7bef94facdf8110104bca8129f12b10f62d3d3e2678cfcc"
|
|
}
|
|
},
|
|
{
|
|
"name": "step_screenshots_retained",
|
|
"passed": true,
|
|
"detail": {
|
|
"retained": 15,
|
|
"hashes_ok": true
|
|
}
|
|
},
|
|
{
|
|
"name": "credential_scan",
|
|
"passed": true,
|
|
"detail": {
|
|
"findings": []
|
|
}
|
|
}
|
|
],
|
|
"qualification": "The Qwen3-VL browser arm passed. This does not claim that the separate Anthropic native-computer-tool arm in Experiment 6-7 ran."
|
|
}
|