portal/runs/tomtervel-opener-2026-09-23/README.md

Tomter Vel: the doors stay, the opener comes first, 2026-09-23

The flat front door (runs/tomtervel-flat-2026-09-23) scored worse than the live doored site: ten offers on one page put the close pairs next to each other. So the plan keeps its four doors and gains what the flat build was for: the opener (two cards, membership and neighbour help, each with a move of the person's own afterwards), the look-around (the three public lists), the mails on the stages that matter to the sender, and the member's own way out. Words lifted from the live repo by card identity - the lift now follows a card across pages - with the opener in Norwegian by hand (opener-only.json).

Scored with the scorer that treats a card with no button as what the page says, not as an option (iris after 2026-09-23). The first run (r1/) lifted from the wrong checkout and had the scorer counting opener picks as misroutes; it is kept for the record.

Front door	With descriptions	Headings only
Live, four doors (tomtervel-cards-2026-09-23)	32 of 40	29 of 40
Flat, ten offers (tomtervel-flat-2026-09-23)	12 of 20	9 of 20
Four doors with the opener, this run	30 of 38	26 of 38

Level with the live site within the visitor's noise, with everything new on top. Merged to tomtervel/questions main the same evening. The mails are the builder's fallbacks; a model has not reworded them.

Round 2: the mails, in Norwegian

build --llm-for aggregates.yaml with Sonnet, every other word as merged. Six mails, all in Norwegian, both links to the sender's own move kept (the builder puts a lost link back). Readability level with the fallbacks, LIX 7 to 33 against 13 to 20, and the text says what happened: "Vi har funnet en nabo som kan hjelpe. De tar kontakt med deg direkte." On vel.klingenbergbygg.no the same evening. The builder now refuses a reply in the wrong language for the plan and keeps the words it had.

Round 3: the doors reworded, and rejected

Sonnet rewrote the four door cards (words-r3.json, site-r3/), and the result was scored with descriptions across three seeds against the live doors: 29, 25, 28 of 38 against 30, 29, 29. Worse, outside the spread. "Få hjelp av naboer eller gi en hånd selv" takes the volunteers as well as the neighbours, because "gi en hånd selv" reads as volunteering. The live doors stay. What survives every round is the same four: hearing input read as a report, a committee read as a hearing, and volunteering read as neighbour help - which says the doors' seams are the plan's, not the words'.

Round 4: the neighbour-help desk reworded, and rejected

The first desk score said this desk got 2 of 4 buttons right. Sonnet reworded its labels (/tmp only); the score got worse with both a small and a strong picker, and the strong one showed why: told a case "has just become ikke lost", it pressed "Meld ordnet" - it read the accent-stripped state id as English. The scorer also offered every button of the bucket where a row shows only its own state's. With the row's buttons only, the live desk scores 3 of 4 and the vel 24 of 26 over all desks. The labels stay as they were.

The rejected doors, judged rather than routed

prefer between the live doors (A) and the rejected rewrite (B), qwen3:8b, both orders: "clearer" goes to B on 5 of 10 needs and to A on none; "friendlier" is no preference on all 10. So the rewrite reads clearer to a judge and routes worse for a visitor: what a reader calls clear and what sends a persona to the right card are not the same measure, and routing is the one that matters. The friendliness question never discriminated here, on any need; it may be too weak for a small judge, or the two versions may be alike.

The friendliness judge, given a positive control

Sonnet wrote a cold, bureaucratic twin of the front door's words ("Vedrørende medlemskap og endring av registrerte opplysninger", cold-front.json, site-cold/). prefer live (A) against cold (B), qwen3:8b, both orders: friendlier goes to A on 9 of 10 needs and to B on none; clearer to A on 5 and B on none; LIX 23 against 36. The judge can tell warmth apart when it is there to tell, so the "no preference" between the live doors and the rejected rewrite stands: those two were alike in tone and differed in routing.