feat(import): user-extensible BOR_IMPORT_EXTENSIONS — any well-formed extension, A9 family stays the default

app/config.py

@@ -6,18 +6,22 @@ Every setting can be overridden with an environment variable prefixed
 from __future__ import annotations
 
 import os
+import re
 from functools import lru_cache
 
 from pydantic import field_validator
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
-#: The A9 import formats (PLAN anchor A9, revised 2026-08-21; revised
-#: 2026-08-27, owner permission — the full Podman quadlet family
+#: The built-in DEFAULT import formats (PLAN anchor A9, revised 2026-08-21;
+#: revised 2026-08-27, owner permission — the full Podman quadlet family
 #: ``container, network, volume, image, pod, kube, swap, os, endpoint``
-#: plus Jinja templates ``j2`` join the allowed set, chunked as plain
-#: text). ``BOR_IMPORT_EXTENSIONS`` may narrow — but never widen — this
-#: set.
-_ALLOWED_IMPORT_EXTENSIONS: frozenset[str] = frozenset(
+#: plus Jinja templates ``j2`` join the default, chunked as plain text).
+#: This is the default scope AND the ``.env.example`` example — it is NOT
+#: a ceiling: ``BOR_IMPORT_EXTENSIONS`` may name **any** well-formed
+#: extension (lowercase letters/digits, no dot) or narrow to a subset
+#: (owner permission 2026-08-31, phase 56); see
+#: :py:attr:`Settings.import_extensions`.
+_DEFAULT_IMPORT_EXTENSIONS: frozenset[str] = frozenset(
     {
         "md", "markdown", "txt", "yaml", "yml", "json", "py",
         # A9 revised 2026-08-27 (owner permission): quadlet family + jinja.
@@ -136,13 +140,18 @@ class Settings(BaseSettings):
     session_max_age: int = 43_200
     session_cookie: str = "bor_session"
 
-    # --- Import scope (A9, revised 2026-08-21 and 2026-08-27) ---
+    # --- Import scope (A9 default; any extension allowed — phase 56) ---
     # Comma-separated list of lowercased file extensions (no dot) imported
-    # by ``scripts/import_docs.py``. Hidden (dot) path components are always
+    # by ``scripts/import_docs.py``. **Any** well-formed extension is
+    # allowed (lowercase letters/digits, 1-16 chars — the shape guard
+    # doubles as the typo guard); the value below is the built-in default
+    # (the A9 family, incl. the quadlet family + ``j2``) and the documented
+    # example in ``.env.example``. Hidden (dot) path components are always
     # skipped, plus the importer's exclusion list.
     # Stored as a raw CSV string (env-native — no JSON) and parsed on demand
-    # via :py:meth:`import_extension_set`. ``mode="after"`` validation runs
-    # against the raw string so a typo fails loudly at startup.
+    # via :py:meth:`import_extension_set`. The validator rejects an empty
+    # list and malformed tokens so a typo fails loudly at startup (it can
+    # no longer reject a novel extension).
     import_extensions: str = (
         "md,markdown,txt,yaml,yml,json,py,"
         "container,network,volume,image,pod,kube,swap,os,endpoint,j2"
@@ -172,16 +181,21 @@ class Settings(BaseSettings):
     @field_validator("import_extensions")
     @classmethod
     def _import_extensions_known(cls, v: str) -> str:
-        """Reject unknown/empty formats loudly instead of silently importing
-        nothing (a typo like ``md,jsonn`` would otherwise walk zero files)."""
+        """Reject an empty list or malformed tokens loudly instead of
+        silently importing nothing (a typo like ``md,jsonn`` would
+        otherwise walk zero files). Any well-formed extension is accepted —
+        the A9 family is the default, not a ceiling (owner permission
+        2026-08-31, phase 56)."""
         exts = {part.strip().lstrip(".").lower() for part in v.split(",") if part.strip()}
         if not exts:
             raise ValueError("import_extensions must name at least one format")
-        unknown = exts - _ALLOWED_IMPORT_EXTENSIONS
-        if unknown:
+        malformed = sorted(
+            ext for ext in exts if re.fullmatch(r"[a-z0-9]{1,16}", ext) is None
+        )
+        if malformed:
             raise ValueError(
-                f"unknown import extension(s): {', '.join(sorted(unknown))} — "
-                f"allowed: {', '.join(sorted(_ALLOWED_IMPORT_EXTENSIONS))}"
+                f"import_extensions contains malformed token(s): {', '.join(malformed)} — "
+                "each extension must be lowercase letters/digits only, 1-16 chars, no dot"
             )
         return v