60 lines
1.7 KiB
JSON
60 lines
1.7 KiB
JSON
{
|
|
"trial": "bug20-startup-batch-20261020",
|
|
"snapshot": "g00000067",
|
|
"account_eur": {
|
|
"start": 12.55,
|
|
"final": 12.7,
|
|
"difference": 0.15,
|
|
"scope": "Complete ten-dispatch trial snapshot, not startup calls alone"
|
|
},
|
|
"comparison": {
|
|
"baseline": "bug20-joint-planning-20261019",
|
|
"old_three_start_calls_input_tokens": 23929,
|
|
"new_three_start_calls_input_tokens": 33087,
|
|
"new_joint_review_input_tokens": 9442,
|
|
"new_startup_total_input_tokens": 42529
|
|
},
|
|
"request_component_characters": {
|
|
"measurement": "Compact JSON sections; section sizes do not sum to serialized request size",
|
|
"old_h1": {
|
|
"system": 5950,
|
|
"user": 13730,
|
|
"output_schema": 2279,
|
|
"tool_schema": 3020,
|
|
"hypotheses": 2107,
|
|
"interpretation": 3371
|
|
},
|
|
"new_h1": {
|
|
"system": 2162,
|
|
"user": 22922,
|
|
"output_schema": 6718,
|
|
"tool_schema": 9535,
|
|
"hypothesis": 346,
|
|
"interpretation": 2715
|
|
},
|
|
"old_evidence_by_hypothesis": [
|
|
2,
|
|
5466,
|
|
6211
|
|
],
|
|
"new_evidence_by_hypothesis": [
|
|
2,
|
|
7065,
|
|
11644
|
|
]
|
|
},
|
|
"findings": [
|
|
"Shorter instructions were offset by larger strict response and tool schemas.",
|
|
"The startup builder duplicates output_schema.properties.next in input.tool_schema.request_contract.",
|
|
"Later startup calls also carry larger shared evidence payloads.",
|
|
"The joint review is an additional call performing assessment work deferred by the baseline.",
|
|
"Input totals include cached tokens; they are not equivalent to uncached billable input."
|
|
],
|
|
"uncached_input_tokens": {
|
|
"old_three": 8554,
|
|
"new_three": 9534,
|
|
"new_joint_review": 7382,
|
|
"new_total": 16916
|
|
}
|
|
}
|