tuning error recognition

backend/app/services/gallery_dl.py

@@ -316,23 +316,52 @@ class GalleryDLService:
         return config
 
     def _categorize_error(self, return_code: int, stdout: str, stderr: str) -> tuple[ErrorType, str]:
-        """Categorize the error based on output and return code."""
+        """Categorize the error based on output and return code.
+
+        Priority order:
+        1. Check for skip messages (# prefixed lines or text patterns) → NO_NEW_CONTENT
+        2. Check for actual errors (auth, rate limit, 404, network, etc.)
+        3. Fall back to UNKNOWN_ERROR
+
+        This ordering prevents false positives where debug output matches error patterns.
+        """
         combined = f"{stdout} {stderr}".lower()
 
-        # Check for "no new content" FIRST for any non-zero return code
-        # Gallery-dl returns 1 when all files are skipped or no new content found
-        # This check must run before other error checks to avoid false positives
-        skip_indicators = ["skipping", "skip", "already exists", "archive"]
-        if any(indicator in combined for indicator in skip_indicators):
-            # If we see skip messages and no actual error messages, it's just "no new content"
-            actual_errors = ["error", "failed", "exception", "traceback"]
-            if not any(err in combined for err in actual_errors):
-                return ErrorType.NO_NEW_CONTENT, "No new content to download"
+        # === PHASE 1: Detect skip/no-new-content scenarios ===
+        # Gallery-dl indicates skipped files two ways:
+        # 1. Lines starting with '#' in stdout (e.g., "# /data/downloads/Artist/file.png")
+        # 2. Text patterns like "skipping", "already exists"
+
+        # Count lines starting with '#' (skip messages)
+        skip_line_count = len([
+            line for line in stdout.split('\n')
+            if line.strip().startswith('#')
+        ])
+
+        # Text-based skip indicators
+        skip_text_indicators = ["skipping", "already exists", "archive"]
+        has_skip_text = any(ind in combined for ind in skip_text_indicators)
+
+        # Actual error indicators that override skip detection
+        actual_error_indicators = [
+            "][error]",      # gallery-dl error log level: [patreon][error]
+            "exception",     # Python exceptions
+            "traceback",     # Python tracebacks
+            "download failed",
+            "extraction failed",
+        ]
+        has_actual_error = any(err in combined for err in actual_error_indicators)
+
+        # If we have skip evidence and no real errors, it's no_new_content
+        if (skip_line_count > 0 or has_skip_text) and not has_actual_error:
+            return ErrorType.NO_NEW_CONTENT, "No new content to download"
 
         # Empty output with low return codes often means nothing to download
         if return_code in (0, 1) and not stdout.strip():
             return ErrorType.NO_NEW_CONTENT, "No new content to download"
 
+        # === PHASE 2: Check for specific error types ===
+
         # Auth errors - look for error context, not just HTTP codes that appear in debug logs
         # HTTP debug lines look like: '"GET /path HTTP/1.1" 401 None' - we need to detect actual errors
         auth_error_patterns = [
@@ -370,29 +399,50 @@ class GalleryDLService:
         if any(pattern in combined for pattern in rate_limit_patterns):
             return ErrorType.RATE_LIMITED, "Rate limited by server - try increasing sleep time"
 
-        # 404 Not Found - check for HTTP 404 responses, not just "404" anywhere
+        # 404 Not Found - check for HTTP 404 responses with error context
+        # Be specific to avoid matching "not found" in debug messages like "archive entry not found"
         not_found_patterns = [
-            '" 404 ',  # HTTP response
-            "error 404",
-            "status: 404",
-            "not found",
-            "does not exist",
-            "no longer available",
+            '" 404 ',           # HTTP response log line
+            "error 404",        # Explicit error 404
+            "status: 404",      # Status code indicator
+            "status code: 404", # Status code indicator
+            "404 not found",    # Standard 404 message
+            "page not found",   # Common 404 page text
+            "user not found",   # User doesn't exist
+            "creator not found",
+            "artist not found",
+            "content no longer available",
+            "has been deleted",
+            "account.*deleted",
+            "profile.*not.*exist",
         ]
-        if any(pattern in combined for pattern in not_found_patterns):
+        # Also require error-level context for generic patterns to avoid false positives
+        generic_not_found = ["does not exist", "no longer available"]
+        has_specific_404 = any(pattern in combined for pattern in not_found_patterns)
+        has_generic_with_error = any(
+            pattern in combined and "][error]" in combined
+            for pattern in generic_not_found
+        )
+        if has_specific_404 or has_generic_with_error:
             return ErrorType.NOT_FOUND, "URL not found - artist may have changed username or deleted content"
 
-        # Network errors
+        # Network errors - use specific patterns to avoid matching config values
+        # (e.g., "timeout": 30.0 in debug output should not trigger network_error)
         network_error_patterns = [
-            "timeout",
-            "timed out",
+            "timed out",           # Actual timeout occurred
+            "read timed out",      # urllib3/requests timeout
+            "connect timed out",   # Connection timeout
+            "connection timed out",
             "connection refused",
             "connection reset",
             "network unreachable",
-            "name resolution",
-            "dns",
-            "ssl error",
-            "certificate verify",
+            "name resolution failed",
+            "name or service not known",
+            "nodename nor servname provided",
+            "ssl: certificate_verify_failed",
+            "ssl: wrong_version_number",
+            "certificate verify failed",
+            "[errno",              # Socket errors like [Errno 111]
         ]
         if any(pattern in combined for pattern in network_error_patterns):
             return ErrorType.NETWORK_ERROR, "Network error - check internet connection"
@@ -418,10 +468,12 @@ class GalleryDLService:
         if "no suitable" in combined or "unsupported" in combined or "no extractor" in combined:
             return ErrorType.UNSUPPORTED_URL, "URL format not supported by gallery-dl"
 
-        # If we got here with return code 1 and saw some activity, it might just be no new content
-        if return_code == 1:
+        # If we got here with return code 1 and saw some activity but no error patterns matched,
+        # it's likely just no new content (gallery-dl returns 1 when nothing to download)
+        if return_code == 1 and stdout.strip() and not has_actual_error:
             return ErrorType.NO_NEW_CONTENT, "No new content to download"
 
+        # Final fallback - genuine unknown error
         return ErrorType.UNKNOWN_ERROR, f"Unknown error (return code: {return_code})"
 
     def _count_downloaded_files(self, stdout: str) -> int: