refactor(iflow): 🔨 reorganize model registry and integrate new LLM options

New model integrations:
- minimax-m2: added to expand provider capabilities
- kimi-k2-thinking: reasoning-focused variant now available
- deepseek-v3.2-chat: latest conversational model version included

Model removals:
- qwen3-coder: removed from supported models list

Author: Mirrowel

src/rotator_library/providers/iflow_provider.py

@@ -95,16 +95,18 @@ def log_final_response(self, response_data: Dict[str, Any]):
 # Model list can be expanded as iFlow supports more models
 HARDCODED_MODELS = [
     "glm-4.6",
+    "minimax-m2",
     "qwen3-coder-plus",
+    "kimi-k2",
     "kimi-k2-0905",
+    "kimi-k2-thinking",
     "qwen3-max",
     "qwen3-235b-a22b-thinking-2507",
-    "qwen3-coder",
-    "kimi-k2",
+    "deepseek-v3.2-chat",
     "deepseek-v3.2",
     "deepseek-v3.1",
-    "deepseek-r1",
     "deepseek-v3",
+    "deepseek-r1",
     "qwen3-vl-plus",
     "qwen3-235b-a22b-instruct",
     "qwen3-235b",