Multi-turn conversation, stop generation, SSE fix, and UI improvements

- Multi-turn context: all council stages now receive conversation history
  (user messages + Stage 3 chairman responses) for coherent follow-ups
- Stop generation: abort streaming mid-request, recover query to input box
- SSE parsing: buffer-based chunking to prevent JSON split across packets
- Atomic storage: user + assistant messages saved together after completion,
  preventing dangling messages on abort
- GFM markdown: tables, strikethrough via remark-gfm plugin + table styles
- Performance: memo user messages and completed assistant messages, only
  re-render the active streaming message
- Model config: gpt-5.2, claude-opus-4.6 as chairman
- Always show input box for multi-turn conversations

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

1 files changed, 22 insertions, 0 deletions

diff --git a/frontend/src/index.css b/frontend/src/index.css
index 698f393..b7b4ed7 100644
--- a/frontend/src/index.css
+++ b/frontend/src/index.css
@@ -96,3 +96,25 @@ body {
   border-left: 4px solid #ddd;
   color: #666;
 }
+
+.markdown-content table {
+  border-collapse: collapse;
+  margin: 0 0 12px 0;
+  width: 100%;
+}
+
+.markdown-content th,
+.markdown-content td {
+  border: 1px solid #d0d0d0;
+  padding: 8px 12px;
+  text-align: left;
+}
+
+.markdown-content th {
+  background: #f5f5f5;
+  font-weight: 600;
+}
+
+.markdown-content tr:nth-child(even) {
+  background: #fafafa;
+}