feat(minimax): Thinking-Parsing, 1h-Cache-TTL, Null-Safety, Provider-Integration

- Thinking-Streaming: Parse 'reasoning_details' (MiniMax mit reasoning_split),
  'reasoning' (Nvidia), 'reasoning_content' (DeepSeek/OpenAI-Compat),
  und inline <think>...</think>-Tags aus delta.content (Fallback)
- MiniMax: max_tokens=32768, stream_options={include_usage}, reasoning_split=true
- 1h-Prompt-Cache-TTL für API (extended-cache-ttl-2025-04-11 Header,
  Cache-Breakpoints auf System-Prompt + letztes Tool) und CLI (ENABLE_PROMPT_CACHING_1H=1)
- Null-Safety: choices/delta/tool_calls/usage null-Checks in Streaming + Non-Streaming
- finish_reason='length' → warning-Event + stopReason='max_tokens'
- MiniMax-Provider: BaseUrl, MinimaxApiKey-Setting, /api/models/minimax-Endpoint,
  Model-Dropdown, statische Fallback-Modelle, Cache-Laden mit Fallback
- Safety-Net: InvalidOperationException-Catch um SSE-Zeilen-Block

wwwroot/index.html

@@ -220,6 +220,9 @@
           <optgroup label="Nvidia" id="nvidiaOptgroup">
             <option value="" disabled>Wird geladen...</option>
           </optgroup>
+          <optgroup label="MiniMax" id="minimaxOptgroup">
+            <option value="" disabled>Wird geladen...</option>
+          </optgroup>
         </select>
         <div class="more">
           <a>Weitere Einstellungen</a>