feat(model): Support claude proxy models

[fangyinc]

Description

Closes #2106

How Has This Been Tested?

1. Using claude proxyllm in DB-GPT webserver

# .env
LLM_MODEL=claude_proxyllm
ANTHROPIC_MODEL_VERSION=claude-3-5-sonnet-20241022
ANTHROPIC_BASE_URL=https://api.openai-proxy.org/anthropic
ANTHROPIC_API_KEY={your-claude-api-key}

2. Using ClaudeLLMClient
   Create python file test_proxyllm.py

import asyncio

from dbgpt.core import ModelRequest
from dbgpt.model.proxy import ClaudeLLMClient

client = ClaudeLLMClient(model_alias="claude-3-5-sonnet-20241022")
print(
    asyncio.run(
        client.generate(
            ModelRequest._build("claude-3-5-sonnet-20241022", "Hi, claude!")
        )
    )
)

Run test_proxyllm.py

ANTHROPIC_API_KEY={your-claude-api-key} python test_proxyllm.py

The output like this:

ModelOutput(text="Hi! I'm Claude. How can I help you today?", error_code=0, incremental=False, model_context=None, finish_reason='end_turn', usage={'prompt_tokens': 11, 'completion_tokens': 16}, metrics=None)

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

Snapshots:

Include snapshots for easier review.

Checklist:

• My code follows the style guidelines of this project
• I have already rebased the commits and make the commit message conform to the project standard.
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• Any dependent changes have been merged and published in downstream modules

[Aries-ckt]

LGTM

[Aries-ckt]

test success

[csunny]

r+