feat: implement fuzzy search and replace functionality with Levenshtein distance

- Added `applySearchReplace` function to handle search and replace operations with fuzzy matching capabilities.
- Introduced tests for various scenarios including fuzzy matching with typos, exact matches, and handling whitespace differences.
- Created a parser for search/replace blocks to facilitate the new functionality.
- Updated prompts for search-replace operations to clarify usage and examples.
- Added utility functions for text normalization and language detection based on file extensions.
- Implemented a minimal stdio MCP server for local testing with tools for adding numbers and printing environment variables.

drizzle/0012_bouncy_fenris.sql

@@ -0,0 +1,23 @@
+CREATE TABLE `mcp_servers` (
+	`id` integer PRIMARY KEY AUTOINCREMENT NOT NULL,
+	`name` text NOT NULL,
+	`transport` text NOT NULL,
+	`command` text,
+	`args` text,
+	`env_json` text,
+	`url` text,
+	`enabled` integer DEFAULT 0 NOT NULL,
+	`created_at` integer DEFAULT (unixepoch()) NOT NULL,
+	`updated_at` integer DEFAULT (unixepoch()) NOT NULL
+);
+--> statement-breakpoint
+CREATE TABLE `mcp_tool_consents` (
+	`id` integer PRIMARY KEY AUTOINCREMENT NOT NULL,
+	`server_id` integer NOT NULL,
+	`tool_name` text NOT NULL,
+	`consent` text DEFAULT 'ask' NOT NULL,
+	`updated_at` integer DEFAULT (unixepoch()) NOT NULL,
+	FOREIGN KEY (`server_id`) REFERENCES `mcp_servers`(`id`) ON UPDATE no action ON DELETE cascade
+);
+--> statement-breakpoint
+CREATE UNIQUE INDEX `uniq_mcp_consent` ON `mcp_tool_consents` (`server_id`,`tool_name`);