125 lines
4.3 KiB
JSON
125 lines
4.3 KiB
JSON
{
|
|
"kind": "offline_rendering_comparison",
|
|
"paid_api_calls": 0,
|
|
"legacy_requests_exact_messages_schema_version": 7,
|
|
"target": 10000,
|
|
"limit": 20000,
|
|
"note": "Counts include system, stable cache prefix and live input. Local schema is not duplicated as text in v2. No quality or cost claim from offline rendering. Existing v1 contexts unchanged.",
|
|
"measurements": [
|
|
{
|
|
"trial": "bug20-bounded-window-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H1-0001.json",
|
|
"legacy_policy": 1,
|
|
"old_characters": 8992,
|
|
"v2_characters": 8460
|
|
},
|
|
{
|
|
"trial": "bug20-bounded-window-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H1-0001-attempt-0001.json",
|
|
"legacy_policy": 1,
|
|
"old_characters": 9036,
|
|
"v2_characters": 8504
|
|
},
|
|
{
|
|
"trial": "bug20-bounded-window-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H1-0001-attempt-0002.json",
|
|
"legacy_policy": 1,
|
|
"old_characters": 9036,
|
|
"v2_characters": 8504
|
|
},
|
|
{
|
|
"trial": "bug20-bounded-window-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H2-0001.json",
|
|
"legacy_policy": 1,
|
|
"old_characters": 12126,
|
|
"v2_characters": 11594
|
|
},
|
|
{
|
|
"trial": "bug20-bounded-window-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H3-0001.json",
|
|
"legacy_policy": 1,
|
|
"old_characters": 15189,
|
|
"v2_characters": 14657
|
|
},
|
|
{
|
|
"trial": "bug20-bounded-window-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H3-0001-attempt-0001.json",
|
|
"legacy_policy": 1,
|
|
"old_characters": 15233,
|
|
"v2_characters": 14701
|
|
},
|
|
{
|
|
"trial": "bug20-bounded-window-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H3-0001-attempt-0002.json",
|
|
"legacy_policy": 1,
|
|
"old_characters": 15349,
|
|
"v2_characters": 14817
|
|
},
|
|
{
|
|
"trial": "bug20-bounded-window-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H3-0001-attempt-0003.json",
|
|
"legacy_policy": 1,
|
|
"old_characters": 15233,
|
|
"v2_characters": 14701
|
|
},
|
|
{
|
|
"trial": "bug20-startup-batch-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H1-0001.json",
|
|
"legacy_policy": 0,
|
|
"old_characters": 25910,
|
|
"v2_characters": 8483
|
|
},
|
|
{
|
|
"trial": "bug20-startup-batch-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H2-0001.json",
|
|
"legacy_policy": 0,
|
|
"old_characters": 33693,
|
|
"v2_characters": 11648
|
|
},
|
|
{
|
|
"trial": "bug20-startup-batch-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H3-0001.json",
|
|
"legacy_policy": 0,
|
|
"old_characters": 39998,
|
|
"v2_characters": 14693
|
|
},
|
|
{
|
|
"trial": "bug20-startup-batch-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H1-0002.json",
|
|
"legacy_policy": 0,
|
|
"old_characters": 24422,
|
|
"v2_characters": 9331
|
|
},
|
|
{
|
|
"trial": "bug20-startup-batch-20261020",
|
|
"context": "analysis/investigation/0001/contexts/H1-0003.json",
|
|
"legacy_policy": 0,
|
|
"old_characters": 52425,
|
|
"v2_characters": 12064
|
|
}
|
|
],
|
|
"source_sha256": {
|
|
"src/viano_bug_analysis/analysis/investigation_contract.py": "3b034fe557abf004d104525a0b771dfb8b45b6e4dd273f0993fc0c680df71537",
|
|
"src/viano_bug_analysis/analysis/investigation_window.py": "d468d896d81c4eb49f2eccf640e45ed378cdde2df1c934fbce3893dec5d537d8",
|
|
"src/viano_bug_analysis/llm/gemini.py": "9933052061298218bf574875cc8e9eb96de349e167fbc2e11379023f20d0d962",
|
|
"config/investigation.bounded.toml": "b3693a0eab479b67af1049dd0725e8d8e18b30d70eea176fa6c30a7bba723cf9"
|
|
},
|
|
"storage_audit": {
|
|
"limit_bytes": 20000000000,
|
|
"measured_roots": {
|
|
"service-data\\trials": 11174795619,
|
|
"service-data\\benchmarks": 498385,
|
|
"service-data\\test-archive": 1401997078,
|
|
"tests\\fixtures\\llm_rejections": 2268510,
|
|
"C:\\Users\\User\\AppData\\Local\\Temp\\pytest-of-User": 843846710
|
|
},
|
|
"note": "Read-only audit; no trial data deleted."
|
|
},
|
|
"local_tests": {
|
|
"passed": 307,
|
|
"elapsed_seconds": 171.87,
|
|
"paid_api_calls": 0,
|
|
"scope": "bounded v1/v2, startup, lean loop, gateway, caching, stable context, recovery, diagnostics, tool feedback"
|
|
}
|
|
}
|