open/repo-mailbox
1
0
Fork 0
Code Issues Releases 2 Activity

fix(route): --last-model learns Fable 5.1, and the set stays closed

Browse source 
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>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-01 21:42:28 +02:00
commit 2bec7fe2fb
2 changed files with 74 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

28
scripts/route.sh
View file

@ -113,7 +113,7 @@
# route.sh --path <v> --verification <v> --reversibility <v> --scope <v>
# --rationale <text>
#
# route.sh ... --last-model <Sonnet 5|Opus 5|Fable 5>
# route.sh ... --last-model <Sonnet 5|Opus 5|Fable 5|Fable 5.1>
# --last-effort <low|medium|high|xhigh|max>
# --last-completed <yes|no> --last-corrections <n>
#
@ -208,9 +208,31 @@ if [ "$L_SET" -eq 1 ]; then
# this record back as evidence months from now, so a drifted spelling
# ("opus 5" for "Opus 5") rebuilds the reader-versus-writer drift this whole
# script exists to remove, one field over.
# THE SET IS CLOSED, AND STAYS CLOSED - decided 2026-09-01 when Fable 5.1
# shipped and was refused here. Both boundary questions were live:
#
# (a) "Fable 5" is KEPT alongside the point release. The reason is not
# backward compatibility with the one STATE.md on this machine that still
# carries it (measured: 1 of 45 route-last lines) - it is that the row
# table above spells rows 5-6 "Fable 5/high" and "Fable 5/xhigh".
# Dropping the value would make this script refuse to record a name its
# own spec writes.
#
# (b) The set was WIDENED rather than replaced by form validation. A pattern
# like "<family> <digits>[.<digits>]" would still catch a misspelled
# family and a drifted case, and would stop catching A VERSION THAT DOES
# NOT EXIST: "Fable 5.2" and "Opus 7" would both pass and read back
# months later as evidence that a model ran when it never shipped. This
# field is telemetry read as evidence, so a silently-accepted lie is
# worse than a loud refusal.
#
# The cost of that choice is real and was paid before it was made: a session
# that genuinely ran Fable 5.1 could not record it, so its record was omitted
# or lied. The list must therefore be extended the day a model ships, and the
# die message says so rather than leaving the caller to guess.
case "$L_MODEL" in
"Sonnet 5"|"Opus 5"|"Fable 5") ;;
*) die "--last-model: '$L_MODEL' is not a row-table model (Sonnet 5|Opus 5|Fable 5)" ;;
"Sonnet 5"|"Opus 5"|"Fable 5"|"Fable 5.1") ;;
*) die "--last-model: '$L_MODEL' is not a row-table model (Sonnet 5|Opus 5|Fable 5|Fable 5.1) - a newly shipped model must be added to this list in route.sh, never approximated to a name that is already in it" ;;
esac
case "$L_EFFORT" in
low|medium|high|xhigh|max) ;;