fix(tools): read_file paa en KATALOG nektes ved navn og peker paa read_dir

Funn (c) fra oekt 94s levende K2-maaling (docs/2026-09-06-major2-levende-k2.md
§ 3/§ 4): en levende modell gikk stigen list_bundles -> read_bundle -> read_dir
-> read_file, naadde et nivaa med underkataloger (30-1, 30-7, 521-001 ...) og
kalte read_file paa en av dem. Tre slike kall i EN kjoering.

SJEKKET FOERST, som ordren ber om: ordren aapner for to aarsaker. Det er den
ANDRE. En listing SKILLER allerede de to slagene strukturelt - hver
directory_listing-payload svarer med "directories" (oppfoeringer noeklet "path",
med subtre-telling) og "documents" (noeklet "name", med type/title/chars) som TO
distinkte noekler, og en katalog opptrer aldri blant dokumentene. Arm (4) pinner
det, fordi det er en egenskap denne fila naa HVILER paa. Derfor ingen
trailing-/-markoer: formen sier allerede hva som er hva, og aa endre payloaden
ville flyttet en listing tre eldre gates maaler byte for byte.

Det som MANGLET var den andre halvdelen. MAALT foer arbeidet, paa den shippede
nestede eksempelbasen:

    read_file(id, "a") -> IsADirectoryError: [Errno 21] Is a directory: <abs sti>

En OSError, altsaa krasj-kanalen i stedet for CLI-ens nekt-tuppel og hostings
400-arm, og den navnga verken hva stien VAR eller hvilken sprosse kalleren
skulle brukt. DirectoryPathRefused (ValueError, BundlePathNotFound- og
DimensionScopeRefused-presedensen) navngir begge. Regelen bor i VERKTOEYET, saa
den gjelder begge kallere (utforskningen, og siden S2c debatten) - samme
plassering som verdict-gaten, og FOER den: declares_verdict_type leser stiens
frontmatter, saa paa en katalog ville den reist noeyaktig den OSError-en denne
grenen finnes for aa erstatte.

MAALT, RAPPORTERT, IKKE FIKSET (utenfor ordren): det levende kallet var
read_file(".../30-7.md") - modellen la .md paa et katalogNAVN, som resolverer
til en sti som ikke finnes i det hele tatt, ikke til katalogen. Maalt paa samme
base gir den FileNotFoundError, altsaa samme form (OSError paa krasj-kanalen der
en navngitt nekt hoerer hjemme). Denne ordren fikser katalog-tilfellet; arm (5)
pinner maalingen av naboen, saa gapet er et faktum i suiten og ikke en setning i
en rapport.

RoedT foerst: import-feil paa DirectoryPathRefused (klassen fantes ikke).
Ingen endring i prompter.

Suite 1381 passed / 5 skipped (fra 1368/5; +13, 0 fjernet - strengt supersett).
ruff + mypy rene. Golden demo-transcript.stdout BYTE-UENDRET,
shasum -a 1 av INNHOLDET = ea8c534773acdbe41ae68f2c55724d69aaf8be4f.

Ordre 20260906T212735Z-2448754-from-.claude, funn (c).

Co-Authored-By: Claude <claude-opus-5>

src/portfolio_optimiser/explore.py

@@ -242,6 +242,22 @@ class DimensionScopeRefused(ValueError):
     """
 
 
+class DirectoryPathRefused(ValueError):
+    """``read_file`` was asked for a DIRECTORY — the wrong rung of the navigation ladder.
+
+    Measured against a live model on K2 (``docs/2026-09-06-major2-levende-k2.md`` § 3/§ 4, finding
+    (c)): a listing hands back subdirectories and concept documents as two distinct keys, and the
+    model asked ``read_file`` for one of the directories anyway, three times in one run. Before
+    this the answer was ``IsADirectoryError`` — an ``OSError``, so it left by the crash channel,
+    and it named neither what the path was nor which tool reads it.
+
+    A ``ValueError``, the ``BundlePathNotFound``/``DimensionScopeRefused`` precedent: the caller is
+    a model choosing a path, so a refusal belongs on the CLI's refusal tuple and hosting's 400 arm.
+    The message names ``read_dir`` because a refusal that only says "no" leaves the caller with the
+    same next move it just made.
+    """
+
+
 @dataclass(frozen=True)
 class LedgerEntry:
     """One progress-ledger round, reduced to the five fields the manager steers on (C.2).
@@ -1030,6 +1046,15 @@ def navigator_tools(
         # model-chosen path is untrusted input by definition, so it goes through the same gate the
         # navigation walk uses rather than a second, laxer check.
         resolved = Path(safe_resolve(bundle_dir, path))
+        # The wrong RUNG, answered as such (finding (c) of the live K2 run). This is BEFORE the
+        # verdict gate for a mechanical reason as well as a readable one: ``declares_verdict_type``
+        # reads the path's frontmatter, so on a directory it would raise ``IsADirectoryError``
+        # first and the caller would get the OSError this branch exists to replace.
+        if resolved.is_dir():
+            raise DirectoryPathRefused(
+                f"{path!r} in knowledge base {bundle_id!r} is a directory, not a document; "
+                "use read_dir to list what it holds, then read_file on one of the names it gives"
+            )
         # The verdict layer, refused HOWEVER the path was found (order 20260904T172353Z). No
         # listing names it — ``context_files`` drops it at every level, so ``read_bundle`` and
         # ``read_dir`` never mention one — but a GUESSED path reached it, and reaching it that way