feat: multi-provider AI support with per-provider model selection

- Add llm-factory.ts: unified LLM provider abstraction (Google/Claude/OpenAI)
- Install @langchain/anthropic and @langchain/openai packages
- resolveAiProvider picks active provider from DB settings (Claude > OpenAI > Google)
- All AI graphs (reminder, new-patient, reschedule, internal-chat) now accept provider+model params
- Add claudeAiModel, openAiModel, googleAiModel columns to ai_settings table
- New PUT /api/ai/provider-model route to save selected model per provider
- UI model dropdowns for Claude (Haiku/Sonnet/Opus), OpenAI (GPT-5.x series), Google (Gemini 2.5/3.x)
- Google AI section also gets model selector alongside existing API key field

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

apps/Backend/src/ai/internal-chat-graph.ts

@@ -1,4 +1,4 @@
-import { ChatGoogleGenerativeAI } from "@langchain/google-genai";
+import { getLlm, type AiProvider } from "./llm-factory";
 
 // ─── Intent types ─────────────────────────────────────────────────────────────
 
@@ -92,7 +92,9 @@ export async function classifyInternalChat(
   message: string,
   apiKey: string,
   extraSystemPrompt?: string,
-  history: { role: "user" | "assistant"; text: string }[] = []
+  history: { role: "user" | "assistant"; text: string }[] = [],
+  provider: AiProvider = "google",
+  model?: string
 ): Promise<ChatClassification> {
   const fallback: ChatClassification = {
     intent: "general",
@@ -107,7 +109,7 @@ export async function classifyInternalChat(
     : BASE_SYSTEM_PROMPT;
 
   try {
-    const llm = new ChatGoogleGenerativeAI({ model: "gemini-flash-latest", apiKey });
+    const llm = getLlm(provider, apiKey, model);
 
     // Gemini requires conversation to start with a user turn — drop any leading assistant messages
     const trimmedHistory = history.slice(