fix(review): warn (not debug) on shadow-classify failure; tidy pymupdf usage

Address PR #855 round 2:

- 🔴 _shadow_classify swallowed all exceptions at DEBUG, so a systematic
  failure (pymupdf bug, memory pressure) is invisible at LOG_LEVEL=INFO and
  trips SonarQube S2221/S5754. Log at WARNING instead (still best-effort --
  indexing is unaffected).
- classifier: use `with pymupdf.open(...) as doc` instead of manual try/finally.
- tests: release the Pixmap's native memory (del pix) in the image fixtures.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

nextcloud_mcp_server/document_processors/classifier.py

@@ -113,8 +113,7 @@ def classify_pdf(content: bytes) -> DocClassification:
     """
     import pymupdf  # noqa: PLC0415 -- keep the heavy import lazy / off module load
 
-    doc = pymupdf.open("pdf", content)
-    try:
+    with pymupdf.open("pdf", content) as doc:
         page_count = doc.page_count
         indices = _sample_indices(page_count)
         pages: list[PageSignals] = []
@@ -141,8 +140,6 @@ def classify_pdf(content: bytes) -> DocClassification:
             pages.append(
                 PageSignals(n, len(text), round(coverage, 3), quality, needs_ocr)
             )
-    finally:
-        doc.close()
 
     sampled = len(pages)
     total_chars = sum(p.char_count for p in pages)

nextcloud_mcp_server/vector/processor.py

@@ -186,7 +186,14 @@ async def _shadow_classify(content: bytes, content_type: str, file_path: str) ->
             c.mean_text_quality,
         )
     except Exception:
-        logger.debug("Tier-0 classification failed for %s", file_path, exc_info=True)
+        # Best-effort: shadow classification must never break indexing, but log
+        # at WARNING (not DEBUG) so a systematic failure -- a pymupdf bug, memory
+        # pressure on every PDF -- stays visible at the production LOG_LEVEL=INFO.
+        logger.warning(
+            "Tier-0 classification failed for %s (shadow mode, indexing unaffected)",
+            file_path,
+            exc_info=True,
+        )
 
 
 async def process_document(

tests/unit/test_doc_classifier.py

@@ -34,6 +34,7 @@ def _full_page_image_pdf(pages: int = 2) -> bytes:
     pix = pymupdf.Pixmap(pymupdf.csRGB, pymupdf.IRect(0, 0, 600, 850))
     pix.clear_with(255)
     img = pix.tobytes("png")
+    del pix  # Pixmap holds native memory; release it before the loop
     for _ in range(pages):
         page = doc.new_page(width=595, height=842)
         page.insert_image(page.rect, stream=img)
@@ -103,6 +104,7 @@ def _image_with_mashed_text_pdf(pages: int = 2) -> bytes:
     pix = pymupdf.Pixmap(pymupdf.csRGB, pymupdf.IRect(0, 0, 600, 850))
     pix.clear_with(255)
     img = pix.tobytes("png")
+    del pix  # Pixmap holds native memory; release it before the loop
     mashed = "01322234567mobileoutstandingresilienceacademicachievement " * 3
     for _ in range(pages):
         page = doc.new_page(width=595, height=842)