moving
Some checks failed
Installer Smoke / installer-smoke (push) Has been cancelled

This commit is contained in:
Oleg Maslov
2026-09-02 10:10:29 +02:00
commit 0c3e2ead3b
3841 changed files with 970576 additions and 0 deletions

View File

@@ -0,0 +1,68 @@
{
"metadata": {
"model": "meta-llama/llama3-70b-instruct",
"model_provider": "mock",
"timestamp": "2026-04-29T21:58:18.864353",
"report_version": "3.0"
},
"statistics": {
"per_capability": {
"mini_standard": {
"capability": "mini (standard)",
"total_runs": 3,
"validated_runs": 3,
"success_runs": 0,
"failed_runs": 3,
"exception_runs": 0,
"no_validation_runs": 0,
"success_rate": 0.0,
"success_rate_std": 0.0,
"success_rate_sem": 0.0,
"pass_at_k": 0,
"pass_at_k_percent": 0.0,
"pass_k": 0,
"pass_k_percent": 0.0,
"total_scenarios": 1,
"avg_run_duration": 0.0,
"avg_run_duration_std": 0.0
}
},
"global": {
"total_runs": 3,
"validated_runs": 3,
"success_runs": 0,
"failed_runs": 3,
"exception_runs": 0,
"no_validation_runs": 0,
"pass_at_k": 0,
"pass_at_k_percent": 0.0,
"pass_k": 0,
"pass_k_percent": 0.0,
"total_scenarios": 1,
"macro_success_rate": 0.0,
"macro_success_rate_std": 0.0,
"macro_success_rate_sem": 0.0,
"micro_success_rate": 0.0,
"micro_success_rate_std": 0.0,
"micro_success_rate_sem": 0.0,
"avg_run_duration": 0.0,
"avg_run_duration_std": 0.0,
"job_duration": 31.784090518951416
}
},
"run_configurations": [
{
"phase_name": "standard",
"config": "mini",
"a2a_app_prop": "0.0",
"has_tool_augmentation": "False",
"has_env_events": "False",
"total_runs": 3,
"validated_runs": 3,
"success_runs": 0,
"failed_runs": 3,
"exception_runs": 0,
"no_validation_runs": 0
}
]
}

View File

@@ -0,0 +1,3 @@
{"task_id": "scenario_universe_21_xvc7uo", "trace_id": null, "score": 0.0, "metadata": {"scenario_id": "scenario_universe_21_xvc7uo", "run_number": 1, "status": "failed", "has_exception": true, "exception_type": "AttributeError", "exception_message": "module 'signal' has no attribute 'SIGALRM'"}}
{"task_id": "scenario_universe_21_xvc7uo", "trace_id": null, "score": 0.0, "metadata": {"scenario_id": "scenario_universe_21_xvc7uo", "run_number": 2, "status": "failed", "has_exception": true, "exception_type": "AttributeError", "exception_message": "module 'signal' has no attribute 'SIGALRM'"}}
{"task_id": "scenario_universe_21_xvc7uo", "trace_id": null, "score": 0.0, "metadata": {"scenario_id": "scenario_universe_21_xvc7uo", "run_number": 3, "status": "failed", "has_exception": true, "exception_type": "AttributeError", "exception_message": "module 'signal' has no attribute 'SIGALRM'"}}