docs(mandate): how a domain expert commissions a run — and one honesty fix the run itself exposed

`docs/bestille-en-kjoring.md` is the commissioning half of the expert-facing pair
(`ekspert-svar.md` is the judging half): the mandate file field by field, how to
run it, and — separated deliberately — what a commission does NOT do. It directs
what is evaluated, never what is approved.

Registered in _LIVE_DOCS, so it cannot silently fall behind the code.

The example output in it is COPIED FROM A REAL RUN, not composed, and running
that run is what found the defect fixed here: three approaches against the same
cost line each validated at 30000 NOK, and the settlement printed
"Validated total: 90000 NOK". Commissioned approaches are ALTERNATIVES — they
usually attack the same line — so summing them reports money the project cannot
realise. A domain expert reading that total would reasonably believe the run
found 90k.

The settlement now reports how many approaches held and which one the run
carries: a selection, not an arithmetic claim. That also removes the last money
addition from this module, which is the right place for it not to be.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ULCqjLF61rehj5cZmdUoR3

tests/test_doc_constant_sync_loadbearing.py

@@ -50,6 +50,7 @@ _LIVE_DOCS = (
     "README.md",
     "docs/extending.md",
     "docs/ekspert-svar.md",
+    "docs/bestille-en-kjoring.md",
     "docs/knowledge-base-recipe.md",
 )
 

tests/test_mandate.py

@@ -260,11 +260,29 @@ def test_settle_carries_the_rejection_reason() -> None:
     assert "claimed 200000 exceeds feasible 90000" in settle(_ROWS)
 
 
-def test_settle_totals_only_the_validated_savings() -> None:
-    """The total is what passed the validator — never the claimed sum of everything attempted."""
+def test_settle_never_sums_alternative_approaches() -> None:
+    """Commissioned approaches are ALTERNATIVES, not additive savings — several of them usually
+    attack the same cost line. Summing them would report a figure the project cannot realise.
+
+    MEASURED on a real run: three approaches against one cost line each validated at 30000 and the
+    settlement claimed a 90000 total. What is honest is how many passed and which one the run
+    carries — a selection, not an arithmetic claim.
+    """
+    rows = (
+        ApproachOutcome(id="a", label="A", status="validated", saving_nok=30_000.0),
+        ApproachOutcome(id="b", label="B", status="validated", saving_nok=20_000.0),
+    )
+    text = settle(rows)
+    assert "50000" not in text  # the sum is never formed
+    assert "30000" in text  # the best one is named
+    assert "2 of 2" in text
+
+
+def test_settle_counts_the_rejected_out_of_the_validated_tally() -> None:
+    """A rejected approach counts toward how many were commissioned, never toward how many held."""
     text = settle(_ROWS)
-    assert "30000" in text
-    assert "200000 NOK" not in text  # the rejected claim is never folded into a total
+    assert "1 of 3" in text
+    assert "200000 NOK" not in text  # the rejected claim is never presented as a saving
 
 
 def test_settle_states_whether_the_target_was_reached() -> None: