feat(linkedin-studio): N14 — foldIns-fangst + Step 11 retro + background-headless + språkregel-akkumulering [skip-docs]

Lukker sløyfen pluginen manglet: en rettelse operatøren gjør i utgave N
håndheves i N+1 i stedet for å bli gjenoppdaget. Maskineriet fantes
(foldIns-skjema + promote→ratify siden fix #1); det som manglet var wiring —
ingenting skrev til køen og ingen fase tømte den.

- Fangst (A2-F7): Steps 2.5/3a/5.5/6.5 appender rettelsen ordrett med trigger,
  decision "pending". Ubetinget og bevisst dum — å avgjøre ved fangst om noe
  "fortjener" en regel er nettopp slik køen holder seg tom og sløyfen dør.
- Step 11 retro (A2-F8), ≤5 min ETTER scheduling: promoter køen med eksplisitt
  JA/NEI (mekanisk → atomisk contract-gate-promotering, teller kun med grønn
  --ratify; dømmekraft → operatørens språkregelfil; NEI → rejected, beholdes),
  effort-oppsummering fra MÅLT phaseLog (aldri re-estimert), og ÉN
  friksjons-spørring som besvares tilbake til operatøren. Faser 18 → 19;
  resumption-tabellen ruter scheduling → Step 11, retro → complete.
- articles.NN.retro: additiv-valgfri (default null), schemaVersion forblir 1.
- Background-headless (A2-F6): --background kjører pakken i en bakgrunnsagent
  som skriver rapporten til disk; drafting-sesjonen leser fila. Samme isolasjon
  som fersk sesjon, uten copy-paste-sømmen. Inline fan-out = eksplisitt fallback.
- Språkregler (C-10): ${DATA}/language-rules/<lang>.md (opt-in, template).
  Leses TO ganger — av language-reviewer (fanger) og av Step 4 (forebygger).
  Shippet banliste forblir baseline; brukerfila utvider.
- references/fold-in-loop.md (A2-F9): loopen dokumentert domene-generelt in-tree,
  så en adopter uten ekstern skrivekontrakt har hele sløyfen. Refs 28 → 29.

Suiter (alle grønne): test-runner 197 → 217 (Section 16u: 18 ubetingede greps +
non-vacuity self-test; fase-sveip 16 → 17 faser; floor 179 → 198) · hooks 174 ·
trends 300 · brain 134 · editions 72 · specifics-bank 45 · contract-gate 33 ·
tests 35 · render 60.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QxvWAjte7vPcF79QeSRvRJ

agents/language-reviewer.md

@@ -140,6 +140,26 @@ chronicle**, not a saksframlegg — judge against that register.
 L1, L2, L5 are partly countable — report the count where you have one. L3, L4
 need a read but are still crisp yes/no findings.
 
+### L6 — the operator's accumulated rules (read this file first)
+
+Before judging, read
+`${LINKEDIN_STUDIO_DATA:-$HOME/.claude/linkedin-studio}/language-rules/<lang>.md`
+(`<lang>` = the `language` input; e.g. `no.md`, `en.md`). It holds the language
+corrections **this operator already made and confirmed** in earlier editions,
+promoted there by `/linkedin:newsletter` Step 11 (the fold-in loop —
+`references/fold-in-loop.md`). A defect this file names is one the operator has
+already paid to fix once: **flag it at REWORK or higher**, and cite the rule.
+
+- The file **extends** the five checks above; it never replaces them. Where a
+  rule there and a check here disagree, the stricter one wins.
+- It also has a *Deliberate exceptions* section — a baseline rule the operator
+  consciously overturned. **Do not flag against an exception listed there.**
+- **Absent file (the default — it is opt-in): judge on L1–L5 alone and say
+  nothing about it.** Its absence is not a gap and never a flag.
+
+This is what stops the review being Groundhog Day: without it, every edition
+re-earns the same correction from scratch.
+
 ## Severity scale — BLOCK / REWORK / NICE
 
 Every flag carries exactly one severity (mirrors `editorial-reviewer`, adapted to