feat: implement English Style Converter

- SvelteKit project scaffolded with TypeScript
- Type definitions for Style, StyleCategory, ConversionRequest, ConversionResponse, LLMConfig
- Style definitions with 6 categories and 25 sub-styles
- Intensity mapping (1-5) with prompt modifier placeholders
- LLM client using OpenAI-compatible API (Ollama default)
- POST /api/convert endpoint with input validation
- Animated loading modal with per-letter animations
- Main page UI with category/style selectors, intensity slider
- Copy to clipboard, collapsible prompt display
- Vitest tests for styles, LLM prompt building, and API validation
- Environment configuration for LLM settings

src/lib/llm.ts

@@ -0,0 +1,77 @@
+import { env } from '$env/dynamic/private';
+import type { LLMConfig } from './types';
+
+const DEFAULT_CONFIG: LLMConfig = {
+	baseUrl: 'http://localhost:11434/v1',
+	apiKey: 'ollama',
+	model: 'llama3'
+};
+
+function getConfig(): LLMConfig {
+	return {
+		baseUrl: env.OPENAI_BASE_URL || DEFAULT_CONFIG.baseUrl,
+		apiKey: env.OPENAI_API_KEY || DEFAULT_CONFIG.apiKey,
+		model: env.OPENAI_MODEL || DEFAULT_CONFIG.model
+	};
+}
+
+export interface ConvertResult {
+	converted: string;
+	systemPrompt: string;
+	userMessage: string;
+}
+
+export function buildSystemPrompt(styleModifier: string, intensityInstruction: string): string {
+	const intensityFilled = intensityInstruction.replace('{style}', styleModifier);
+	return `You are an expert English style converter.
+${intensityFilled}.
+${styleModifier}
+Preserve the core meaning but fully transform the voice and tone.
+Output ONLY the converted text — no explanations, no labels, no quotes.`;
+}
+
+export function buildUserMessage(text: string): string {
+	return text;
+}
+
+export async function convertText(
+	text: string,
+	styleModifier: string,
+	intensityInstruction: string,
+overrides?: Partial<LLMConfig>
+): Promise<ConvertResult> {
+	const merged: LLMConfig = { ...DEFAULT_CONFIG, ...getConfig(), ...overrides };
+
+	const systemPrompt = buildSystemPrompt(styleModifier, intensityInstruction);
+	const userMessage = buildUserMessage(text);
+
+	const response = await fetch(`${merged.baseUrl}/chat/completions`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${merged.apiKey}`
+		},
+		body: JSON.stringify({
+			model: merged.model,
+			messages: [
+				{ role: 'system', content: systemPrompt },
+				{ role: 'user', content: userMessage }
+			],
+			temperature: 0.8
+		})
+	});
+
+	if (!response.ok) {
+		const errorText = await response.text().catch(() => 'Unknown error');
+		throw new Error(`LLM request failed (${response.status}): ${errorText}`);
+	}
+
+	const data = await response.json();
+	const converted = data.choices?.[0]?.message?.content?.trim();
+
+	if (!converted) {
+		throw new Error('LLM returned empty response');
+	}
+
+	return { converted, systemPrompt, userMessage };
+}