host:   Darwin 25.5.0 / docker 29.7.2 / 11cpu
image:  pfk-fixture-good
tool:   0.1.0.dev0 (648891e)
runs:   8 attempted, 8 with a report
command: uv run --project . preflightkit test --format json --config fixtures/good-fastapi-prestop/preflightkit.yaml
label:   full

duration
  wall is the whole process; tool is what the run itself timed; phases in ms
  run  exit  wall s  tool s  probe_image_preparation  dependencies  target_start  baseline  calibration  experiment  teardown
  ---  ----  ------  ------  -----------------------  ------------  ------------  --------  -----------  ----------  --------
    1     0   22.32   22.06                      867             0           286     15140           83        5455       227
    2     0   22.39   22.05                      802             0           301     15108           86        5542       206
    3     0   22.45   22.12                      876             0           292     15099           85        5557       206
    4     0   22.40   22.05                      862             0           289     15103           82        5496       215
    5     0   22.44   22.08                      857             0           293     15098           87        5514       222
    6     0   22.37   22.09                      868             0           302     15106           87        5507       216
    7     0   22.35   22.01                      819             0           290     15116           85        5485       207
    8     0   22.62   22.30                      944             0           358     15150           97        5522       227
  med         22.39   22.07                      864             0           293     15107           86        5511       215

resolution
  ok is ratio >= 10 (MIN_JITTER_RATIO as this build has it)
  run  jitter   source  n   p50   max  ratio  ok      target  load1
  ---  ------  -------  -  ----  ----  -----  --  ----------  -----
    1   0.147  sidecar  5  0.37  0.90   2.52  no  configured   2.51
    2   0.157  sidecar  5  0.37  0.91   2.37  no  configured   2.13
    3   0.139  sidecar  5  0.36  0.95   2.62  no  configured   1.87
    4   0.159  sidecar  5  0.34  1.19   2.15  no  configured   3.78
    5   0.148  sidecar  5  0.34  1.26   2.28  no  configured   2.83
    6   0.133  sidecar  5  0.35  0.92   2.59  no  configured   2.28
    7   0.143  sidecar  5  0.31  0.81   2.19  no  configured   2.27
    8   0.149  sidecar  5  0.40  0.96   2.69  no  configured   2.45
  med   0.147              0.36         2.45                       

teardown floor
  the other half of the same question: what this daemon costs to stop, in ms. A run only calibrates when a budget is close enough to need it, so not_calibrated is a normal row, not a missing measurement
  run  n  floor  stddev  k  threshold          status
  ---  -  -----  ------  -  ---------  --------------
    1  -      -       -  -          -  not_calibrated
    2  -      -       -  -          -  not_calibrated
    3  -      -       -  -          -  not_calibrated
    4  -      -       -  -          -  not_calibrated
    5  -      -       -  -          -  not_calibrated
    6  -      -       -  -          -  not_calibrated
    7  -      -       -  -          -  not_calibrated
    8  -      -       -  -          -  not_calibrated
  med         -                                      

