Fable 5.1 shipped 2026-09-01. The closed set at route.sh:212 refused it,
so a session that actually ran it could not record what it ran: the
record was either omitted or LIED, and a lied record reads back months
later as a measurement rather than as the gap it is.
TDD, test first. The exact failure the new check produced before the fix:
route: --last-model: 'Fable 5.1' is not a row-table model (Sonnet 5|Opus 5|Fable 5)
Two boundary decisions, both taken here and both written into the code:
(a) "Fable 5" is KEPT alongside the point release. The reason is not
backward compatibility with existing route-last lines - measured
across the machine, exactly 1 of 45 carries it. It is that route.sh's
OWN row table spells rows 5-6 "Fable 5/high" and "Fable 5/xhigh", so
dropping the value would make the script refuse to record a name its
own spec writes.
(b) The set is WIDENED, never replaced by form validation. A pattern like
"<family> <digits>[.<digits>]" would still catch a misspelled family
and a drifted case, and would stop catching a version that does not
exist: "Fable 5.2" and "Opus 7" would both pass and read back as
evidence that a model ran when it never shipped. This field is
telemetry read as evidence, so a silently-accepted lie is worse than
a loud refusal. The cost is real and was paid before the choice was
made, so the die message now names the repair instead of leaving the
caller to approximate to a value already in the list.
Both edit sites, never one: the usage block (route.sh:116) and the case
itself. Fixing the case alone is the two-copies-of-one-policy defect this
repo names repeatedly.
Selftest, 69 -> 73 checks:
- Fable 5.1 is accepted (was RED)
- route-last carries "Fable 5.1" verbatim into the line (was RED)
- Fable 5.2 / Fable 6 / Fable 5.10 are still REFUSED - the
check that makes "we did not switch to form validation"
machine-verified rather than prose (control)
- board parses back a hand-written Fable 5.1 next-cost (control)
MEASURED GAP, stated rather than closed: "Fable 5.1/xhigh" is 15
characters and overflows board.sh's %-14s KOST column, shifting the rest
of that row one column right. Parsing is unaffected. Widening the column
is a board.sh rendering change nobody ordered in this session, so it is
reported rather than fixed - which is also why the value is deliberately
absent from the widest-value loop in selftest section 6.
Not touched: the row table (still six rows, route.sh still emits only
1-4), and the note that a Fable session runs without an advisor because
the CLI does not enforce it.
Order: 20260901T185028Z-3612729538-from-.claude
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Kjell Tore Guttormsen
2bec7fe2fb