mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-27 17:58:07 +00:00
a894879d28
Captures medians of 5 runs for multitab and render-churn so tonight's
wins can't silently regress.
idle-cost is deliberately NOT gated. Its render attribution and idle
commit rate are trustworthy and are what the scenario exists for, but the
drag fps it reports (~0.6fps, p95 814ms) contradicts a direct
single-clock probe of the same gesture on the same build (57fps). I ruled
out sash selection, tile setup, render-counter residue, and a 20s soak,
and could not explain the gap — so the metric ships as a report, not a
gate. Gating CI on a number I can't defend would either fire on a phantom
or mask a real stall.
tier: 'report' is outside GATED ('ci','cold'), so the scenario still runs
and prints but neither compares nor writes a baseline.
79 lines
2.2 KiB
JSON
79 lines
2.2 KiB
JSON
{
|
|
"_meta": {
|
|
"note": "Median of 5 runs, darwin-arm64, `--spawn --prod` (PRODUCTION minified renderer, real boot \u2014 no fake-boot). Representative shipped numbers, not dev-inflated. cold-start reuses one profile so the V8 code cache is WARM (what users get after first launch, ~1.0s); a fresh-profile first launch is ~+400ms (measure with `--cold-fresh`). Marks are process-spawn wall clock (spawn_to_*) or renderer nav-relative (dom_*). Re-baseline per device with `--update-baseline`; tolerances loose for cross-machine/disk variance.",
|
|
"platform": "darwin-arm64",
|
|
"node": "v24.11.0",
|
|
"updated": "2026-07-27T00:30:11.290Z"
|
|
},
|
|
"scenarios": {
|
|
"stream": {
|
|
"tolerance": {
|
|
"tolFrac": 0.6,
|
|
"tolAbs": 5
|
|
},
|
|
"metrics": {
|
|
"longtasks_n": 1,
|
|
"longtask_max_ms": 67,
|
|
"frame_p95_ms": 22,
|
|
"frame_p99_ms": 23.7,
|
|
"slow_frames_33": 1,
|
|
"intermut_p95_ms": 36.1
|
|
}
|
|
},
|
|
"keystroke": {
|
|
"tolerance": {
|
|
"tolFrac": 0.6,
|
|
"tolAbs": 4
|
|
},
|
|
"metrics": {
|
|
"keystroke_p50_ms": 2.1,
|
|
"keystroke_p95_ms": 8.7,
|
|
"keystroke_p99_ms": 16.9,
|
|
"keystroke_slow_16": 2
|
|
}
|
|
},
|
|
"transcript": {
|
|
"tolerance": {
|
|
"tolFrac": 0.75,
|
|
"tolAbs": 40
|
|
},
|
|
"metrics": {
|
|
"transcript_mount_ms": 145,
|
|
"transcript_longtask_ms": 82,
|
|
"transcript_longtask_max_ms": 82
|
|
}
|
|
},
|
|
"cold-start": {
|
|
"tolerance": {
|
|
"tolFrac": 0.6,
|
|
"tolAbs": 150
|
|
},
|
|
"metrics": {
|
|
"spawn_to_cdp_ms": 606,
|
|
"spawn_to_driver_ms": 984,
|
|
"dom_interactive_ms": 324,
|
|
"dom_content_loaded_ms": 574,
|
|
"nav_to_read_ms": 721
|
|
}
|
|
},
|
|
"multitab": {
|
|
"metrics": {
|
|
"longtasks_n": 0,
|
|
"longtask_max_ms": 0,
|
|
"frame_p95_ms": 29.1,
|
|
"frame_p99_ms": 36.2,
|
|
"slow_frames_33": 9
|
|
}
|
|
},
|
|
"render-churn": {
|
|
"metrics": {
|
|
"sidebar_renders": 0,
|
|
"sidebar_wasted": 0,
|
|
"wasted_renders": 1704,
|
|
"total_renders": 8221,
|
|
"commits": 1352,
|
|
"wasted_notifies": 0
|
|
}
|
|
}
|
|
}
|
|
}
|