# Cook ledger: [project]

Copy this to `cook/ROUNDS.md` at the start of a run. Keep the header current. Add one round entry per round, newest at the bottom. Label every number as measured or eyeballed.

Started: [YYYY-MM-DD HH:MM, timezone]
Time: floor [8h] | cap [none]
Bar: composition [99.9] | light [99.9] | color [99.9] | materials [99.9] | detail [99.9] | motion [9/10]
Calibration offset: [none yet] (from [user estimate, date])
Usage: [5h window], about 20% per hour, never 100%
Gate: stills approved [no] | final render [not started]
Best so far: round [N], `cook/stills/r[NN]/`, [commit or snapshot]

## Decisions

Made without asking, one line each.
- [time] [decision], because [reason]

## User feedback inbox

Exact words. Close an item only when a still or clip proves it.
- [time] "[quote]" | round [N] | [open / done, proof: path]

---

## Round [NN]

Time: [start] to [end] | total elapsed [h]
Usage: [% of window at the end of the round, or "not readable"]
Focus: [shot and dimension], because [user feedback / lowest score / largest gap]

Changes:
- [what changed, where]

Stills: `cook/stills/r[NN]/` | Side by side: `cook/compare/r[NN]/`

Scores, eyeballed: critic median after calibration ([n] critics, [models or "same model"])

| Shot | Comp | Light | Color | Materials | Detail | Motion | vs last round |
|---|---|---|---|---|---|---|---|
| S01 | | | | | | | |
| S02 | | | | | | | |

Raw critic medians before calibration: [ ]
Own score (logged, never decides): [ ]

Measured (command and result):
- [color check S01: saturation delta [+/-0.00], brightness delta [+/-0.00]]
- [render: [N] s per frame at [resolution], [N] sub-frames]

Not checked this round:
- [what, and why]

Top gaps from critics:
1. [shot, region, what is wrong, what to change]
2. [ ]
3. [ ]

Progress note sent: [time]
Stop check: bar [no] | floor [no] | stills approved [no] | final checked [no] -> [next round / ship / stop at cap]
Next focus: [ ]
