feat: enhance openai-compatible provider support and patch responses API instructions handling

- Add compatibility patch for langchain-openai responses API to ensure system messages are extracted as top-level instructions, addressing Codex endpoint requirements.
- Update provider list: add Alibaba, Volcengine, and Tencent TokenHub; adjust SiliconFlow and MiniMax endpoints; refine provider ordering and model list strategies.
- Extend models.dev-only listing logic for providers lacking stable models.list endpoints.
- Increase models.dev cache TTL for improved efficiency.
- Add tests for openai responses API and streaming compatibility patches.

test_openai_copilot_patch.py

@@ -0,0 +1,9 @@
+from app.agent.llm.helper import _patch_openai_responses_instructions_support
+from langchain_openai import ChatOpenAI
+from langchain_core.messages import SystemMessage, HumanMessage
+import json
+
+_patch_openai_responses_instructions_support()
+model = ChatOpenAI(model="gpt-4o", openai_api_key="sk-123", base_url="https://api.githubcopilot.com", stream_usage=True)
+payload = model._get_request_payload([SystemMessage(content="Hello system"), HumanMessage(content="Hello user")])
+print(json.dumps(payload, indent=2))