Project-aware assist, link suggestions, project-scoped RAG, semantic search tool, SSE race fix

- Writing assistant: inject project notes as context (definition-tagged first), wikilink suggestions
- Link suggestions: server-side endpoint finds unlinked term occurrences, NoteEditorView sidebar panel
- Project-scoped RAG: ChatView ProjectSelector filters semantic+keyword search to selected project
- Semantic search tool: LLM search_notes upgraded to hybrid semantic (0.40 threshold) + keyword merge
- SSE race condition fix: drain remaining events after stream loop exits in chat.py and notes.py
- RAG_AUTO_SNIPPET raised 800→4000; sidebar include uses full note body; MAX_BODY_CHARS 8000→24000
- Enter-to-submit on writing assistant instruction textareas (note and task editors)
- DiffView: equal-line collapsing with 3-line context around changes

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

frontend/src/stores/chat.ts

@@ -155,6 +155,7 @@ export const useChatStore = defineStore("chat", () => {
     think = false,
     contextNoteTitle?: string,
     excludeNoteIds?: number[],
+    ragProjectId?: number | null,
   ) {
     if (!currentConversation.value) return;
 
@@ -204,6 +205,7 @@ export const useChatStore = defineStore("chat", () => {
           include_note_ids: includeNoteIds?.length ? includeNoteIds : undefined,
           excluded_note_ids: excludeNoteIds?.length ? excludeNoteIds : undefined,
           think,
+          rag_project_id: ragProjectId ?? undefined,
         },
       );
       assistantMessageId = resp.assistant_message_id;
@@ -348,6 +350,37 @@ export const useChatStore = defineStore("chat", () => {
     }
   }
 
+  async function reconnectIfGenerating(convId: number): Promise<void> {
+    // Skip if a stream is already active for this conversation
+    if (isStreamingConv(convId)) return;
+
+    const conv = currentConversation.value;
+    if (!conv || conv.id !== convId) return;
+
+    // Find the last assistant message still in generating state
+    const lastMsg = [...conv.messages].reverse().find(
+      (m) => m.role === "assistant" && m.status === "generating"
+    );
+    if (!lastMsg) return;
+
+    // Remove the partial message — the done event will re-add the final version
+    conv.messages = conv.messages.filter((m) => m.id !== lastMsg.id);
+
+    const s = _getOrInitStream(convId);
+    s.streaming = true;
+    s.content = "";
+    s.thinking = "";
+    s.toolCalls = [];
+    s.status = "Reconnecting...";
+    s.pendingTool = null;
+    s.contextMeta = null;
+
+    // Reconnect from the beginning — the buffer replays all buffered events.
+    // If the buffer is gone (>60s stale), _streamGeneration will exhaust retries
+    // then fall back to fetchConversation to show the final saved content.
+    await _streamGeneration(convId, lastMsg.id);
+  }
+
   async function confirmTool(confirmed: boolean) {
     const convId = currentConversation.value?.id;
     if (!convId) return;
@@ -461,6 +494,7 @@ export const useChatStore = defineStore("chat", () => {
     deleteConversation,
     updateTitle,
     sendMessage,
+    reconnectIfGenerating,
     confirmTool,
     cancelGeneration,
     saveMessageAsNote,