Feat: add Qwen3 and OpenAI o series (#7415)

### What problem does this PR solve?

Qwen3 and more LLMs.

Close #7296

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

conf/llm_factories.json

             "tags": "LLM,TEXT EMBEDDING,TTS,TEXT RE-RANK,SPEECH2TEXT,MODERATION",
             "status": "1",
             "llm": [
+                {
+                    "llm_name": "gpt-4.5-preview",
+                    "tags": "LLM,CHAT,128K",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "o3",
+                    "tags": "LLM,CHAT,200K,IMAGE2TEXT",
+                    "max_tokens": 200000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "o4-mini",
+                    "tags": "LLM,CHAT,200K,IMAGE2TEXT",
+                    "max_tokens": 200000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "o4-mini-high",
+                    "tags": "LLM,CHAT,200K,IMAGE2TEXT",
+                    "max_tokens": 200000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
                 {
                     "llm_name": "gpt-4o-mini",
                     "tags": "LLM,CHAT,128K,IMAGE2TEXT",
                     "model_type": "chat",
                     "is_tools": true
                 },
+                {
+                    "llm_name": "qwen3-30b-a3b",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen3-235b-a22b",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen3-0.6b",
+                    "tags": "LLM,CHAT,32k",
+                    "max_tokens": 32000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen3-1.7b",
+                    "tags": "LLM,CHAT,32k",
+                    "max_tokens": 32000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen3-4b",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen3-8b",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen3-14b",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen3-32b",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
                 {
                     "llm_name": "qwen-long",
                     "tags": "LLM,CHAT,10000K",
                 },
                 {
                     "llm_name": "qwen-turbo",
-                    "tags": "LLM,CHAT,8K",
-                    "max_tokens": 8191,
+                    "tags": "LLM,CHAT,1M",
+                    "max_tokens": 1000000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen-turbo-2025-04-28",
+                    "tags": "LLM,CHAT,1M",
+                    "max_tokens": 1000000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "qwen-turbo-latest",
+                    "tags": "LLM,CHAT,1M",
+                    "max_tokens": 1000000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                     "model_type": "chat",
                     "is_tools": true
                 },
+                {
+                    "llm_name": "qwen-plus-2025-04-28",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
                 {
                     "llm_name": "qwen-plus-latest",
                     "tags": "LLM,CHAT,132k",
             "tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",
             "status": "1",
             "llm": [
+                {
+                    "llm_name": "gemini-2.5-flash-preview-04-17",
+                    "tags": "LLM,CHAT,1024K,IMAGE2TEXT",
+                    "max_tokens": 1048576,
+                    "model_type": "image2text",
+                    "is_tools": true
+                },
                 {
                     "llm_name": "gemini-2.0-flash-001",
                     "tags": "LLM,CHAT,1024K",