111 lines
3.2 KiB
JSON
111 lines
3.2 KiB
JSON
{
|
|
"measurement": "bug20_working_brief_live_v1",
|
|
"commit": "22fe68c",
|
|
"workspace": "service-data\\trials\\bug20-working-brief-20261016",
|
|
"identity": {
|
|
"case_id": "BUG-000020",
|
|
"package_id": "trial-working-brief-BUG-000020-20261016",
|
|
"package_generation": 86,
|
|
"state": "OUTPUT_READY"
|
|
},
|
|
"duration_seconds": 439.0303,
|
|
"calls": 15,
|
|
"investigation_calls": 9,
|
|
"phase_calls": {
|
|
"INTERPRETING_CASE": 3,
|
|
"GENERATING_HYPOTHESES": 1,
|
|
"INVESTIGATING_HYPOTHESES": 9,
|
|
"BUILDING_DIAGNOSIS": 2
|
|
},
|
|
"usage": {
|
|
"input_tokens": 366105,
|
|
"output_tokens": 46794,
|
|
"reasoning_tokens": 33638,
|
|
"cached_input_tokens": 213030,
|
|
"cache_created_tokens": 23670,
|
|
"elapsed_seconds": 328.67100000000005,
|
|
"estimated_cost": 0.14828924999999998,
|
|
"estimated_cache_storage_cost": 0.00098625,
|
|
"estimated_cost_scope": "Known subtotal only; 9 of 15 calls have complete estimated_cost."
|
|
},
|
|
"investigation_usage": {
|
|
"input_tokens": 255771,
|
|
"output_tokens": 26735,
|
|
"reasoning_tokens": 20562,
|
|
"cached_input_tokens": 213030,
|
|
"cache_created_tokens": 23670,
|
|
"elapsed_seconds": 197.45199999999997,
|
|
"estimated_cost": 0.14828924999999998,
|
|
"estimated_cache_storage_cost": 0.00098625
|
|
},
|
|
"cache_statuses": {
|
|
"created": 1,
|
|
"reused": 8
|
|
},
|
|
"cached_tokens_per_inv": {
|
|
"23670": 9
|
|
},
|
|
"errors": [
|
|
{
|
|
"hypothesis": "H3",
|
|
"code": "LLM_OUTPUT_SCHEMA",
|
|
"kind": "invalid_response",
|
|
"llm_ref": "llm/operations/b7f2e84e7ce1ab15fea771e71ef5c71f3321d1b419eefa7f3f69f110b5c356c6/round-0001.json"
|
|
}
|
|
],
|
|
"call_statuses": {
|
|
"SUCCESS": 14,
|
|
"ERROR": 1
|
|
},
|
|
"cost_eur_start": 7.71,
|
|
"cost_eur_end": 7.89,
|
|
"cost_eur_delta": 0.18,
|
|
"early_stop": {
|
|
"countercheck_refs": [
|
|
"E000004",
|
|
"E000005"
|
|
],
|
|
"deferred_hypotheses": [],
|
|
"evidence_refs": [
|
|
"E000001",
|
|
"E000002",
|
|
"E000004",
|
|
"E000005"
|
|
],
|
|
"fingerprint": "aefa64a8f813a1df46cfa3cc84f8be3339bceebefe7627610c636d139def6843",
|
|
"hypothesis_id": "H1",
|
|
"number": 1,
|
|
"reason": "Investigation of creature and game_event_creature tables confirms that Wild Wolpertinger (entry 23487) only has spawn entries on map 1 (Durotar) tied to Brewfest event 24, while Dun Morogh (map 0) has zero spawn entries for either 23487 or 22943.",
|
|
"status": "requested"
|
|
},
|
|
"hypotheses": {
|
|
"H1": {
|
|
"confidence": "strongly_supported",
|
|
"disposition": "active",
|
|
"iterations": 3
|
|
},
|
|
"H2": {
|
|
"confidence": "weakened",
|
|
"disposition": "reject",
|
|
"iterations": 2
|
|
},
|
|
"H3": {
|
|
"confidence": "weakened",
|
|
"disposition": "reject",
|
|
"iterations": 3
|
|
}
|
|
},
|
|
"hypothesis_remaining_budget": {
|
|
"H1": 92,
|
|
"H2": 97,
|
|
"H3": 93
|
|
},
|
|
"limitations": [
|
|
"Reported account delta, subject to billing latency.",
|
|
"No direct equal-progress comparison to the earlier interrupted BUG-17 trial.",
|
|
"Token output includes reasoning; cached input is part of total input.",
|
|
"Correct reference cause, but dynamic paths were not exhaustively excluded.",
|
|
"Estimated costs are incomplete: only investigation calls have configured input rates; do not treat their sum as a total analysis estimate."
|
|
]
|
|
}
|