fix(mcp): harden project context issue provider and prove shared audit path

- Share cursor decoding in foundation.decode_offset_cursor so both tools
  reject an invalid cursor identically, before any upstream call.
- Add regression coverage that a malformed repo slug (owner/repo/extra,
  missing owner, empty segment) is refused before any network call.
- Add evidence that BOTH project context tools inherit the shared MCP
  client audit record and untrusted-content fence, instead of each tool
  shipping its own. No audit subsystem is duplicated.

mcp_servers/project_context/foundation.py

@@ -62,6 +62,23 @@ class ProviderError(RuntimeError):
         self.retryable = retryable
 
 
+def decode_offset_cursor(cursor: str | None) -> int:
+    """Shared opaque-cursor decoding for every paginated provider.
+
+    Rejected before any backend call so an invalid cursor never costs an
+    upstream request.
+    """
+    if cursor is None:
+        return 0
+    try:
+        offset = int(cursor)
+    except ValueError as exc:
+        raise ProviderError("INVALID_INPUT", "cursor is not valid.", retryable=False) from exc
+    if offset < 0:
+        raise ProviderError("INVALID_INPUT", "cursor is not valid.", retryable=False)
+    return offset
+
+
 ToolHandler = Callable[[ContractModel, Any], dict[str, Any]]