refactor: LLM 直接输出 Markdown，移除 JSON 解析层

服务端:
- prompt 改为要求直接输出 Markdown，不再输出 JSON
- GeneratePR 返回 string 而非 PRDescription 结构体
- 移除 JSON 解析、extractJSON、fixInlineCode 等逻辑
- ChatStream 的 content 事件直接携带 Markdown 片段流式传输

前端:
- generate() 仅处理 content + done + error 三个事件
- content 事件累积 Markdown 文本，实时渲染到两栏
- 移除 parsePartialJSON、buildMarkdown 等中间层
- 代码量从 ~100 行减至 ~50 行

templates/pages/generate.html

@@ -184,85 +184,27 @@
             indicator.classList.remove('hidden');
 
             // Clear previous results
-            document.getElementById('pr-rendered').innerHTML = '<span class="animate-pulse text-gray-400">正在生成...</span>';
+            document.getElementById('pr-rendered').innerHTML = '';
             document.getElementById('pr-markdown').textContent = '';
             markdownContent = '';
 
-            const fields = { title: '', type: '', summary: '', details: '', impact: '' };
-            let rawText = '';
-            let done = false;
-
-            function updateColumns() {
-                markdownContent = buildMarkdown(fields);
-                document.getElementById('pr-rendered').innerHTML = renderMarkdown(markdownContent);
-                document.getElementById('pr-markdown').textContent = markdownContent;
-            }
-
-            // Try to extract completed fields from partial JSON
-            function parsePartialJSON(text) {
-                const result = {};
-                for (const key of ['title', 'type', 'summary', 'details', 'impact']) {
-                    // Match "key": "value" where value's closing quote exists
-                    const re = new RegExp('"' + key + '"\\s*:\\s*"((?:[^"\\\\]|\\\\.)*)"');
-                    const m = text.match(re);
-                    if (m) result[key] = m[1].replace(/\\"/g, '"').replace(/\\n/g, '\n').replace(/\\\\/g, '\\');
-                }
-                return result;
-            }
-
+            // LLM outputs markdown directly — just accumulate and render
             SSE.post(`/api/repos/${repoId}/generate`, {
                 base: baseRef,
                 head: headRef,
             }, {
                 content(data) {
-                    if (done) return;
-                    rawText += data.content || '';
-                    // Parse partial JSON to extract fields progressively
-                    const partial = parsePartialJSON(rawText);
-                    let changed = false;
-                    for (const key of ['title', 'type', 'summary', 'details', 'impact']) {
-                        if (partial[key] && partial[key] !== fields[key]) {
-                            fields[key] = partial[key];
-                            changed = true;
-                        }
-                    }
-                    if (changed) updateColumns();
-                },
-                title(data) {
-                    fields.title = data.content || fields.title;
-                    updateColumns();
-                    document.getElementById('streaming-status').textContent = '解析标题...';
-                },
-                type(data) {
-                    fields.type = data.content || fields.type;
-                    updateColumns();
-                    document.getElementById('streaming-status').textContent = '解析类型...';
-                },
-                summary(data) {
-                    fields.summary = data.content || fields.summary;
-                    updateColumns();
-                    document.getElementById('streaming-status').textContent = '解析摘要...';
-                },
-                detail(data) {
-                    fields.details = data.content || fields.details;
-                    updateColumns();
-                    document.getElementById('streaming-status').textContent = '解析详细说明...';
-                },
-                impact(data) {
-                    fields.impact = data.content || fields.impact;
-                    updateColumns();
-                    document.getElementById('streaming-status').textContent = '解析影响范围...';
+                    markdownContent += data.content || '';
+                    document.getElementById('pr-rendered').innerHTML = Markdown.render(markdownContent);
+                    document.getElementById('pr-markdown').textContent = markdownContent;
                 },
                 done() {
-                    done = true;
-                    updateColumns();
                     indicator.classList.add('hidden');
                     btn.disabled = false;
                     btn.textContent = '生成 PR 描述';
                     btn.classList.remove('opacity-70', 'cursor-not-allowed');
                 },
                 error(data) {
-                    done = true;
                     showToast('生成失败: ' + (data.message || '未知错误'), 'error');
                     indicator.classList.add('hidden');
                     btn.disabled = false;
@@ -272,21 +214,6 @@
             });
         }
 
-        // Markdown rendering (delegates to shared Markdown.render)
-        function renderMarkdown(text) {
-            return Markdown.render(text);
-        }
-
-        function buildMarkdown(f) {
-            const parts = [];
-            if (f.title) parts.push(`# ${f.title}`);
-            if (f.type) parts.push(`**类型**: ${f.type}`);
-            if (f.summary) parts.push(`## 摘要\n${f.summary}`);
-            if (f.details) parts.push(`## 详细说明\n${f.details}`);
-            if (f.impact) parts.push(`## 影响\n${f.impact}`);
-            return parts.join('\n\n');
-        }
-
         function copyMarkdown() {
             const markdown = markdownContent || document.getElementById('pr-markdown').textContent;
             if (!markdown.trim()) {