refactor: read settings directly instead of getattr with a second default

About 85 call sites read a setting as getattr(settings, "NAME", fallback),
each carrying its own copy of the default. Every one of those names is a
field with a default on the model, so the fallback could never apply to
the real settings object; it only masked drift. Two had drifted:

- OPENAI_PROMPT_CACHE_KEY defaults to True on the model but the reader
  fell back to False, and two test stubs relied on that.
- SharePoint's MICROSOFT_AUTHORITY fallback to
  https://login.microsoftonline.com/<tenant> never fired, because the
  attribute always exists (as None), so MSAL got authority=None. The
  connector now derives the tenant authority when the setting is unset,
  as its test always assumed.

Four places read EMBEDDINGS_KEY straight from os.environ, skipping the
"None"/"" normalisation the model applies; they read the setting now.
Test stubs that replaced a module's settings with a SimpleNamespace list
every setting the code under test reads.

docsgpt/parser/connectors/share_point/auth.py

@@ -41,7 +41,7 @@ class SharePointAuth(BaseConnectorAuth):
 
         self.redirect_uri = settings.CONNECTOR_REDIRECT_BASE_URI
         self.tenant_id = settings.MICROSOFT_TENANT_ID
-        self.authority = getattr(settings, "MICROSOFT_AUTHORITY", f"https://login.microsoftonline.com/{self.tenant_id}")
+        self.authority = settings.MICROSOFT_AUTHORITY or f"https://login.microsoftonline.com/{self.tenant_id}"
 
         self.auth_app = ConfidentialClientApplication(
             client_id=self.client_id,

docsgpt/parser/document_reader.py

@@ -97,10 +97,10 @@ def bound_parse_payload(payload: Dict[str, Any], max_chars: Optional[int] = None
 
 def _max_input_bytes() -> int:
     """Return the size cap for a parsed document (its own setting, else the sandbox cap)."""
-    explicit = int(getattr(settings, "DOCUMENT_PARSE_MAX_BYTES", 0) or 0)
+    explicit = int(settings.DOCUMENT_PARSE_MAX_BYTES or 0)
     if explicit > 0:
         return explicit
-    return int(getattr(settings, "SANDBOX_MAX_INPUT_BYTES", 25 * 1024 * 1024))
+    return int(settings.SANDBOX_MAX_INPUT_BYTES)
 
 
 # Every zip-packaged format a parser map can route: OOXML and its macro/
@@ -127,8 +127,8 @@ def _zip_bomb_reason(source: Union[bytes, str, Path], suffix: str) -> Optional[s
     """
     if suffix not in _ZIP_CONTAINER_EXTENSIONS:
         return None
-    max_entries = int(getattr(settings, "DOCUMENT_MAX_ARCHIVE_ENTRIES", 10000))
-    cap = int(getattr(settings, "DOCUMENT_MAX_DECOMPRESSED_BYTES", 300 * 1024 * 1024))
+    max_entries = int(settings.DOCUMENT_MAX_ARCHIVE_ENTRIES)
+    cap = int(settings.DOCUMENT_MAX_DECOMPRESSED_BYTES)
     opened = io.BytesIO(source) if isinstance(source, bytes) else source
     try:
         with zipfile.ZipFile(opened) as zf:
@@ -169,14 +169,14 @@ def _resolve_ocr_enabled(ocr: str) -> bool:
         return True
     if ocr == "off":
         return False
-    return bool(getattr(settings, "OCR_ENABLED", False))
+    return bool(settings.OCR_ENABLED)
 
 
 def _effective_engine(engine: str) -> str:
     """Resolve ``auto`` to the server's ``DOC_PARSER_ENGINE``; other values pass through."""
     if engine != "auto":
         return engine
-    configured = getattr(settings, "DOC_PARSER_ENGINE", None) or "anydoc"
+    configured = settings.DOC_PARSER_ENGINE or "anydoc"
     return str(configured).strip().lower()
 
 

docsgpt/parser/embedding_pipeline.py

@@ -53,7 +53,7 @@ def _resolve_batch_size() -> int:
     Returns:
         Chunks per embed request, always >= 1.
     """
-    raw = getattr(settings, "EMBEDDINGS_BATCH_SIZE", None)
+    raw = settings.EMBEDDINGS_BATCH_SIZE
     # Explicit type check rather than a bare ``int(raw)``: ``int(MagicMock())``
     # succeeds and yields 1, which would silently drop ingest back to the
     # per-chunk behaviour this batching replaces.
@@ -326,7 +326,7 @@ def embed_and_store_documents(
             store = VectorCreator.create_vectorstore(
                 settings.VECTOR_STORE,
                 source_id=source_id,
-                embeddings_key=os.getenv("EMBEDDINGS_KEY"),
+                embeddings_key=settings.EMBEDDINGS_KEY,
             )
             loop_start = resume_index
         else:
@@ -336,7 +336,7 @@ def embed_and_store_documents(
                 settings.VECTOR_STORE,
                 docs_init=[docs[0]],
                 source_id=source_id,
-                embeddings_key=os.getenv("EMBEDDINGS_KEY"),
+                embeddings_key=settings.EMBEDDINGS_KEY,
             )
             # Record the seeded chunk so single-doc ingests don't fail
             # ``assert_index_complete`` — the loop never runs for
@@ -351,7 +351,7 @@ def embed_and_store_documents(
         store = VectorCreator.create_vectorstore(
             settings.VECTOR_STORE,
             source_id=source_id,
-            embeddings_key=os.getenv("EMBEDDINGS_KEY"),
+            embeddings_key=settings.EMBEDDINGS_KEY,
         )
         # Only wipe the index on a fresh run — a resume must keep the
         # chunks that earlier attempts already embedded.

docsgpt/parser/file/bulk.py

@@ -344,7 +344,7 @@ def get_default_file_extractor(
     """
     if ocr_enabled is None:
         ocr_enabled = settings.OCR_ENABLED
-    selected = (engine or getattr(settings, "DOC_PARSER_ENGINE", None) or "anydoc")
+    selected = (engine or settings.DOC_PARSER_ENGINE or "anydoc")
     selected = str(selected).strip().lower()
     if selected == "docling":
         return _docling_file_extractor(ocr_enabled, pdf_text_fast_path)

docsgpt/parser/file/docling_parser.py

@@ -335,11 +335,7 @@ def _ocr_min_chars_per_page() -> int:
 
     try:
         return int(
-            getattr(
-                settings,
-                "OCR_MIN_CHARS_PER_PAGE",
-                _DEFAULT_OCR_MIN_CHARS_PER_PAGE,
-            )
+            settings.OCR_MIN_CHARS_PER_PAGE
         )
     except (TypeError, ValueError):
         return _DEFAULT_OCR_MIN_CHARS_PER_PAGE

docsgpt/parser/file/ocr_parser.py

@@ -124,7 +124,7 @@ def resolve_ocr_backend(requested: Optional[str] = None) -> str:
     """
     from docsgpt.core.settings import settings
 
-    backend = str(requested or getattr(settings, "OCR_BACKEND", None) or "auto").strip().lower()
+    backend = str(requested or settings.OCR_BACKEND or "auto").strip().lower()
     if backend not in VALID_OCR_BACKENDS:
         logger.warning(f"Unknown OCR_BACKEND {backend!r}; using auto")
         backend = "auto"
@@ -154,7 +154,7 @@ def resolve_native_ocr_engine(requested: Optional[str] = None) -> str:
     """
     from docsgpt.core.settings import settings
 
-    engine = str(requested or getattr(settings, "OCR_ENGINE", None) or "tesseract").strip().lower()
+    engine = str(requested or settings.OCR_ENGINE or "tesseract").strip().lower()
     if engine in NATIVE_OCR_ENGINES:
         return engine
     if engine in VALID_OCR_ENGINES:
@@ -172,7 +172,7 @@ def ocr_min_chars_per_page() -> int:
     from docsgpt.core.settings import settings
 
     try:
-        return int(getattr(settings, "OCR_MIN_CHARS_PER_PAGE", _DEFAULT_MIN_CHARS_PER_PAGE))
+        return int(settings.OCR_MIN_CHARS_PER_PAGE)
     except (TypeError, ValueError):
         return _DEFAULT_MIN_CHARS_PER_PAGE
 
@@ -182,7 +182,7 @@ def render_dpi() -> int:
     from docsgpt.core.settings import settings
 
     try:
-        dpi = int(getattr(settings, "OCR_RENDER_DPI", _DEFAULT_RENDER_DPI))
+        dpi = int(settings.OCR_RENDER_DPI)
     except (TypeError, ValueError):
         dpi = _DEFAULT_RENDER_DPI
     return max(_MIN_RENDER_DPI, min(_MAX_RENDER_DPI, dpi))
@@ -299,7 +299,7 @@ class TesseractEngine:
         else:
             from docsgpt.core.settings import settings
 
-            configured = str(getattr(settings, "OCR_LANGS", "") or "eng")
+            configured = str(settings.OCR_LANGS or "eng")
             langs = [lang.strip() for lang in configured.split("+") if lang.strip()]
         return "+".join(langs) or "eng"
 
@@ -388,7 +388,7 @@ class DeepseekOcrEngine:
 
         self.url = url or settings.OCR_DEEPSEEK_URL
         self.model = model or settings.OCR_DEEPSEEK_MODEL
-        self.timeout = float(timeout if timeout is not None else getattr(settings, "OCR_DEEPSEEK_TIMEOUT", 300))
+        self.timeout = float(timeout if timeout is not None else settings.OCR_DEEPSEEK_TIMEOUT)
         self.prompt = prompt
         self.max_tokens = max_tokens
 

docsgpt/parser/remote/github_loader.py

@@ -129,7 +129,7 @@ class GitHubLoader(BaseRemote):
 
     def _max_file_bytes(self) -> int:
         """Resolve the per-blob size cap; ``0`` disables it."""
-        raw = getattr(settings, "GITHUB_INGEST_MAX_FILE_BYTES", None)
+        raw = settings.GITHUB_INGEST_MAX_FILE_BYTES
         if isinstance(raw, bool) or not isinstance(raw, (int, str)):
             return 1048576
         try:
@@ -139,7 +139,7 @@ class GitHubLoader(BaseRemote):
 
     def _max_workers(self) -> int:
         """Resolve the parallel-fetch width, clamped to a sane range."""
-        raw = getattr(settings, "GITHUB_INGEST_MAX_WORKERS", None)
+        raw = settings.GITHUB_INGEST_MAX_WORKERS
         if isinstance(raw, bool) or not isinstance(raw, (int, str)):
             return 8
         try:

docsgpt/parser/tokenization.py

@@ -267,7 +267,7 @@ def get_token_counter(embeddings_name: Optional[str] = None) -> TokenCounter:
         A :class:`HuggingFaceCounter` for a model whose tokenizer could be
         loaded, else a :class:`TiktokenCounter`.
     """
-    name = embeddings_name or getattr(settings, "EMBEDDINGS_NAME", None)
+    name = embeddings_name or settings.EMBEDDINGS_NAME
     key = name or "__default__"
     with _cache_lock:
         if key in _cache: