Cleaner error logging: sanic loggers at INFO, 499/503 for cancelled requests, shortened preview error reasons

- Force sanic.root/error/server back to INFO from before_server_start, after
  dev mode's runtime setLevel(DEBUG) — kills the useless 'Error Page:' noise
- Silence mediapreview.pool WARNINGs (timeouts already in access log extra);
  they previously fell to logging.lastResort with no level prefix
- Handle CancelledError with 499 (client disconnect / RequestCancelled) or
  503 (server shutdown) instead of Sanic's default 500 error page
- 422 preview failures now log 'backend: reason' in the access log, with
  upstream error text shortened (first line, no [Errno] prefix, cut at ': ');
  dev mode prints the full original error to console

cista/app.py

@@ -13,7 +13,7 @@ from blake3 import blake3
 from mediapreview.office import close_oo_client, log_reachable_info
 from mediapreview.pool import shutdown_preview_workers, start_preview_workers
 from sanic import Sanic, empty, raw, redirect
-from sanic.exceptions import Forbidden, NotFound
+from sanic.exceptions import Forbidden, NotFound, RequestCancelled
 from sanic.log import logger
 from setproctitle import setproctitle
 from stream_zip import ZIP_AUTO, stream_zip
@@ -35,6 +35,7 @@ from cista.sanic_logging import (
     configure_access_logging,
     configure_main_logging,
     format_access_log,
+    reset_sanic_log_levels,
 )
 from cista.sanic_logging import logger as access_logger
 from cista.util.apphelpers import handle_sanic_exception
@@ -124,11 +125,28 @@ app.blueprint(fileserver.bp)
 app.exception(Exception)(handle_sanic_exception)
 
 
+@app.exception(asyncio.CancelledError)
+async def request_cancelled(req, e):
+    """Request cancelled mid-flight (client disconnect or server shutdown).
+
+    Sanic wraps this as RequestCancelled (client disconnect only) — a
+    BaseException, so the generic Exception handler above never sees it — and
+    its default handler renders a 500 error page. Report 499 for client
+    disconnects and 503 for server-side cancellation instead; no traceback
+    (quiet=True), since there is nothing to fix. The connection is usually
+    already gone.
+    """
+    if not getattr(req.ctx, "log_extra", None):
+        req.ctx.log_extra = "cancelled"
+    return empty(499 if isinstance(e, RequestCancelled) else 503)
+
+
 setproctitle("cista-main")
 
 
 @app.before_server_start
 async def main_start(app):
+    reset_sanic_log_levels()
     config.load_config()
     onlyoffice.configure()
     setproctitle(f"cista {config.config.path.name}")

cista/preview.py

@@ -6,6 +6,7 @@ Sanic with auth, etag negotiation and the in-memory response cache.
 """
 
 import asyncio
+import re
 import urllib.parse
 from pathlib import PurePosixPath
 from urllib.parse import unquote
@@ -38,6 +39,21 @@ bp = Blueprint("preview", url_prefix="/preview")
 _preview_cache = PreviewCache(capacity=500)
 
 
+def _shorten_error(detail: str) -> str:
+    """Shorten an upstream backend error for the single-line access log.
+
+    Backend errors arrive verbatim from ffmpeg/pyvips/pymupdf and often carry
+    an '[Errno N]' prefix, the input file path, and multi-line library noise —
+    all redundant with the URL already in the log line. Keep the first line,
+    drop the bracket prefix, and cut at the first ': ' separator.
+    """
+    lines = detail.splitlines()
+    if not lines:
+        return ""
+    first_line = re.sub(r"^\[[^\]]*\]\s*", "", lines[0].strip())
+    return first_line.split(": ", 1)[0]
+
+
 @bp.on_request
 async def verify_preview(request):
     """Verify access to preview routes."""
@@ -125,8 +141,16 @@ async def preview(req, path):
             if captured:
                 detail = captured.splitlines()[0]
         # The worker already logged the failure (with traceback where the
-        # error occurred) — annotate the access log instead of re-logging.
+        # error occurred) — annotate the access log instead of re-logging,
-        req.ctx.log_extra = e.backend or detail
+        # with a shortened reason. In dev mode, print the full error too.
+        backend = e.backend or _expected_preview_backend(filepath)
+        if req.app.debug:
+            full = detail
+            if e.stderr and e.stderr.strip() not in detail:
+                full = f"{detail}\n{e.stderr.strip()}"
+            logger.warning("[%s] preview failed: %s", backend, full.strip())
+        short = _shorten_error(detail)
+        req.ctx.log_extra = f"{backend}: {short}" if short else backend
         return empty(422)
     except asyncio.CancelledError:
         # Server shutdown or client disconnect: the connection is being torn

cista/sanic_logging.py

@@ -294,7 +294,23 @@ def configure_main_logging() -> None:
     # Patch the config defaults too, so the level survives Sanic's dictConfig.
     LOGGING_CONFIG_DEFAULTS["loggers"]["sanic.websockets"]["level"] = "ERROR"
     logging.getLogger("sanic.websockets").setLevel(logging.ERROR)
+    # Preview worker timeouts are already annotated in the access log extra;
+    # the pool's WARNING would otherwise fall to logging.lastResort, printing
+    # a bare message with no level prefix.
+    logging.getLogger("mediapreview.pool").setLevel(logging.ERROR)
     # Also reformat any handlers already attached (covers the initial Sanic() call)
     for name in ("sanic.root", "sanic.error", "sanic.server", "sanic.websockets"):
         for handler in logging.getLogger(name).handlers:
             handler.setFormatter(_EmojiFormatter())
+
+
+def reset_sanic_log_levels() -> None:
+    """Force Sanic's loggers back to INFO in debug/dev mode.
+
+    Debug mode enables DEBUG on sanic.root at runtime
+    (ApplicationState.set_mode calls logger.setLevel(DEBUG)), which unleashes
+    useless noise like the 'Error Page:' content-negotiation messages. Call
+    from before_server_start so the override lands after Sanic's own setup.
+    """
+    for name in ("sanic.root", "sanic.error", "sanic.server"):
+        logging.getLogger(name).setLevel(logging.INFO)