{"version":"2.1.219","anchor":"mcp-reconnect-failure-text-is-sanitized-and-length-capped","canonical_anchor":"mcp-reconnect-failure-text-is-sanitized-and-length-capped","heading":"MCP reconnect failure text is sanitized and length-capped","tier":"notice","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.219\/e\/mcp-reconnect-failure-text-is-sanitized-and-length-capped","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.219","markdown":"### MCP reconnect failure text is sanitized and length-capped\n\nMCP reconnect errors now show cleaned-up, shortened text instead of raw messy error output.\n\n**What**\n\nThe two \/mcp reconnect failure messages no longer interpolate a raw error string.\n\n**Details**\n\n- Covers \"Tried reconnecting to \u2026, but the connection failed:\" and \"Got new credentials, but reconnecting to \u2026\", both assembled at runtime.\n- The extracted error now passes through the shared display sanitizer, which NFKC-normalizes, strips angle brackets, quotes and assorted bracket characters, collapses whitespace, and truncates with an ellipsis at 200 characters.\n\n**Evidence**\n\n`Reconnection failed after authentication`\n\n- Area: MCP\n- Names: `\/mcp`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 0\/5"}