--workspace is required with no environment fall-back: this process runs
unsandboxed, and a status run that quietly picked a workspace is one nobody
can audit. --check exits 1 on a stale cache, distinct from 2 for a failed run.
Byte-stability is measured, not asserted: the CLI is run twice under two
PYTHONHASHSEED values and the bytes compared, in both output formats. The
write boundary gets two digest tests rather than one -- without --oppdater
every byte stays put, with it exactly the diverging case's four cached keys
move and logg.jsonl, the body and every other file are byte-identical.
Co-Authored-By: Claude <claude-opus-5>
Status derives from logg.jsonl alone; sak.md frontmatter is a cache and the
log wins where they disagree (risk H3). --oppdater is the only writer of the
four cached keys, and it leaves a key alone when the derivation is None --
neste_frist in vurderer/soker is the operator's application deadline and no
refresh may eat it.
Two rows of the plan's table are not 5.3 events. Decision ja and operator
close reach the case log as the decision-log records build-brief 5.7 already
mirrors there, so the event enum stays closed at eleven.
Co-Authored-By: Claude <claude-opus-5>
