feat(linkedin-studio): N15 — do-next-kontrakt (recordDoNext + skrivere/lesere + forrige-utgave-kalibrering) [skip-docs]

Måling som ikke endrer neste utgave er teater: report/analyze/ab-test/48h-monitor
endte alle i chat (grep do.next = 0 i hele repoet). N15 gjør kanalen til en kontrakt.

- recordDoNext i hooks/scripts/state-updater.mjs (TDD, 17 nye tester): seksjonen
  Do-Next Directives, rader "[dato] (kilde) direktiv — evidence: peker".
  Levetid = erstatt-per-kilde + 60-dagers aldersgulv, maks 3 per skriv, additiv
  scalar last_donext_date, $-sikre replacement-funksjoner. CLI: --record-do-next.
- Skrivere: report Step 7b, analyze Step 6b, ab-test 2c.6 (kun Adopt),
  post-feedback-monitor (kun 48h-sjekken); analytics-interpreter emitterer nå
  anbefalinger på do-next-form (imperativ + evidens).
- Lesere: post/quick/batch/create Step 0 + newsletter Step 1, som i tillegg
  kalibrerer på forrige utgaves MÅLTE tall via queue-id-match (queue.json →
  analytics/posts) med eksplisitt honest-miss — aldri estimert.
- Guards: test-runner Section 16v (15 ubetingede sjekker, floor 198 → 213),
  $-safety-batteriet dekker recordDoNext (coverage-gate fanget den nye eksporten).

Suiter: test-runner 232/0, hooks 191/0, trends 300/0, brain 134/0, editions 72/0,
specifics-bank 45/0, contract-gate 33/0, tests 35/0, render 60/0.

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

CLAUDE.md

@@ -17,6 +17,7 @@ Full-spectrum LinkedIn content engine — short-form feed posts, carousels, vide
 - **Publishing slots:** `hooks/scripts/slots.mjs` — the weekly production grid. Slots are **operator config** in the per-user data dir (`profile/publishing-slots.json`, schema + opt-in template in `config/publishing-slots.template.json`); absent config ⇒ every slot surface stays silent, and the plugin hardcodes no publishing times. Coverage of a slot counts the short-form queue (`scheduled`/`published`) **and** editions-register rows claiming that date, so long-form and short-form cannot be double-booked. Zero-dep (SessionStart may not spawn tsx) and imported identically by the hook and by the commands (`queue-manager.mjs` pattern), so session-start's vacancy warning and `/linkedin:newsletter` Step 10's slot default are the same computation
 - **Contract-gate:** `scripts/contract-gate/` (TypeScript, needs `tsx` + `npm install`) — deterministic §B/§C1 rule-gate on the full draft (`/linkedin:newsletter` Step 4.5, before the AI sweeps); ratifies `rules.ts` against the edition's §E-manifest, then gates with BLOCK/WARN
 - **Fold-in loop:** capture → classify → promote → enforce, documented domain-generally in `references/fold-in-loop.md`. The four `/linkedin:newsletter` steps where operator judgment enters the text (2.5, 3a, 5.5, 6.5) append corrections to `articles.NN.foldIns[]` (`decision: "pending"`); **Step 11 (retro)** empties the queue with an explicit operator JA/NEI — mechanical → an atomic contract-gate promotion (only counts when `--ratify` is green), judgment → the operator's opt-in language-rules file (`${DATA}/language-rules/<lang>.md`, template `config/language-rules.template.md`), which Step 4 reads while drafting (prevent) and `language-reviewer` reads at Step 6.5 (catch). Rejected rows are kept, never deleted. Step 11 also reports effort from the **measured** `phaseLog` and asks one friction question whose answer goes back to the operator — the plugin never writes their register
+- **Do-next contract:** `recordDoNext()` in `hooks/scripts/state-updater.mjs` — the one channel from measurement to creation. `/linkedin:report`, `/linkedin:analyze`, an `/linkedin:ab-test` **Adopt** verdict and the `post-feedback-monitor`'s 48h learning each persist 2–3 directives (imperative + evidence pointer, tagged with their source) to `## Do-Next Directives` in the state file; the create surfaces (`post`/`quick`/`batch`/`create` Step 0, `newsletter` Step 1) read them before drafting, so a recommendation changes the next piece instead of dying in chat. Lifetime is **replace-by-source + a 60-day age floor**: each writer supersedes only its own rows, so the section is a live steering signal, never a backlog. `newsletter` Step 1 additionally calibrates on the **previous edition's measured numbers** via the queue-id match (`drafts/queue.json` → `analytics/posts/*.json` by publish date), with an explicit honest-miss branch — an unmeasured edition is stated as such, never estimated
 - **Analytics metrics (S16):** parsed CSV columns + an optional, manually-entered `saves` count (count-only in native LinkedIn analytics since ~Sept 2025, no CSV export; the Marketing API exposes `POST_SAVE` on `/memberCreatorPostAnalytics` from v202604, but access is partner-gated — so manual entry remains the right UX). `parseOptionalCount()`: blank / non-numeric / negative → `undefined` (`unknown`, never 0), a genuine `0` is kept; saves surfaced per-post + as `totalSaves`, but **not** folded into `engagementRate`. `dwell` stays **explicitly unmeasurable** (internal to LinkedIn, no export/API). All analytics I/O routes through the `getAnalyticsRoot()` seam (M0 per-user data-dir).
 
 ## Hooks