Use admin-configured AI model and add GPT-5/o-series options

- Add getConfiguredModel() that reads ai_model from SystemSettings
- AI assignment and mentor matching now use the admin-selected model
- Remove duplicate OpenAI client in mentor-matching (use shared singleton)
- Add GPT-5, GPT-5 Mini, o3, o3 Mini, o4 Mini to model dropdown

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/server/services/mentor-matching.ts

@@ -1,20 +1,5 @@
 import { PrismaClient, OceanIssue, CompetitionCategory } from '@prisma/client'
-import OpenAI from 'openai'
-
-// Lazy initialization to avoid errors when API key is not set
-let openaiClient: OpenAI | null = null
-
-function getOpenAIClient(): OpenAI | null {
-  if (!process.env.OPENAI_API_KEY) {
-    return null
-  }
-  if (!openaiClient) {
-    openaiClient = new OpenAI({
-      apiKey: process.env.OPENAI_API_KEY,
-    })
-  }
-  return openaiClient
-}
+import { getOpenAI, getConfiguredModel } from '@/lib/openai'
 
 interface ProjectInfo {
   id: string
@@ -170,13 +155,15 @@ Respond in JSON format:
   ]
 }`
 
-  const openai = getOpenAIClient()
+  const openai = await getOpenAI()
   if (!openai) {
     throw new Error('OpenAI client not available')
   }
 
+  const model = await getConfiguredModel()
+
   const response = await openai.chat.completions.create({
-    model: 'gpt-4o-mini',
+    model,
     messages: [
       {
         role: 'system',