fix(docs): rett README-statusen — to usanne paastander paa offentlig flate (ORDRE 20260825T122454Z)

"no live-model run yet" var falskt siden 14.08 (docs/2026-08-14-fase1b-forste-levende-kjoring.md):
en live koersel mot gpt-4.1-mini konkluderte "rejected" — korrekt utfall, men modellen fant opp
en kostkode. "sibling built in parallel" stemte ikke: po-claude er PARKERT (STATE.md). Begge
punkt verifisert mot primaerkilde foer retting (Verifiseringsloven ansikt 3).

Statusavsnittet er ogsaa gjort mer noekternt: ingen validerte forslag mot levende modell enna,
ingen ekte ekspertdommer i treet (kun AI-forfattede froe, merket som saadan).

Utvidet test_public_surface_claims_loadbearing.py med to nye rode->groenne gater (Iron Law):
begge paastandene kan ikke gjeninnfores usett. Fant og fikset en linjebrudd-felle i egen test
underveis (blockquote-wrap gjorde "no live-model run yet" usynlig for et raatt substring-soek).

Ingen kodeendring i src/. Ingen push til open (Azure-gatet, egen ordre). 1025 passed / 5 skipped.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RF8QXXBWJ917Uj9zMf18nz

README.md

@@ -261,16 +261,24 @@ per amount, before anything is summed.
 - **Not a model benchmark.** The end-to-end proof runs offline against a scripted stand-in client:
   it shows that the loop closes, not how well a given LLM proposes or judges.
 
-> **Status:** the full 8-step agentic loop is wired and proven with load-bearing tests, and the
-> end-to-end proof is an **offline simulation** with a scripted stand-in client — no live-model
-> run yet. The **ingest layer** (real data sources) is implemented — file/CSV and SQL on both
-> stacks with bit-identical golden extractions from the shared spec, plus HTTP as a MAF-only
-> demonstrated extension point against a local mock — but exercised only against committed
-> fixtures: no bundle has yet been materialized from a live source. Ingested content passes a
-> **content gate** (`materialize_gated`) that scans every generated concept with
+> **Status:** the full 8-step agentic loop is wired and proven with load-bearing tests. The
+> end-to-end proof is primarily an **offline simulation** with a scripted stand-in client, but one
+> **live run** against a real endpoint (`gpt-4.1-mini`, 2026-08-14) has also completed: it ended
+> in a correct `rejected` outcome — the deterministic validator caught a cost line the model had
+> invented outright (a code absent from the knowledge base), on the tolerance gate rather than the
+> stricter existence gate, because the bundle it ran against ships no cost baseline to anchor
+> against. No run has yet produced a **validated** proposal against a live model, and every
+> human-in-the-loop verdict currently seeded into the knowledge base is a synthetic, AI-authored
+> seed marked as such — no genuine expert verdict has entered the tree yet. The **ingest layer**
+> (real data sources) is implemented — file/CSV and SQL on both stacks with bit-identical golden
+> extractions from the shared spec, plus HTTP as a MAF-only demonstrated extension point against a
+> local mock — but exercised only against committed fixtures: no bundle has yet been materialized
+> from a live source. Ingested content passes a **content gate** (`materialize_gated`) that scans
+> every generated concept with
 > [`llm-ingestion-guard`](https://git.fromaitochitta.com/open/llm-ingestion-pipeline-security)
 > before any of it reaches the bundle; a refused run writes nothing. A sibling implementation of
-> the same method on the **Claude Agents SDK** is built in parallel from the same shared spec.
+> the same method on the **Claude Agents SDK** exists in a separate repository but is currently
+> **parked**, not developed in parallel.
 
 > **Disclaimer — technical framework only.** Deploying organizations own their processing
 > purposes and assessments (DPIA, risk/ROS, security review). The framework ships the technical