从 Anthropic 迁移

- export ANTHROPIC_API_KEY=sk-ant-...
+ export ANTHROPIC_BASE_URL=https://llm.bytespike.ai
+ export ANTHROPIC_API_KEY=sk-byts-...

- client = Anthropic()  # reads env vars
+ client = Anthropic(
+   base_url="https://llm.bytespike.ai",
+   api_key="sk-byts-...",
+ )

# 原来:
from anthropic import Anthropic
client = Anthropic()  # reads ANTHROPIC_API_KEY
r = client.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)

# 现在: 环境变量切换
# (ANTHROPIC_BASE_URL=https://llm.bytespike.ai, ANTHROPIC_API_KEY=sk-byts-...)
client = Anthropic()
r = client.messages.create(
    model="claude-sonnet-4-6",   # newer Anthropic id
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)

tools = [{
    "name": "get_weather",
    "description": "Get current weather",
    "input_schema": {
        "type": "object",
        "properties": {"city": {"type": "string"}},
        "required": ["city"]
    }
}]

r = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "weather in Tokyo?"}],
    tools=tools,
)

r = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    system=[
        {"type": "text", "text": "You are a helpful assistant."},
        {
            "type": "text",
            "text": LARGE_KNOWLEDGE_BASE,
            "cache_control": {"type": "ephemeral"},
        },
    ],
    messages=[{"role": "user", "content": "..."}],
)

# usage.cache_read_input_tokens and usage.cache_creation_input_tokens
# are populated and billed per the documented discount.

r = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=4096,
    thinking={"type": "enabled", "budget_tokens": 2000},
    messages=[{"role": "user", "content": "..."}],
)

# Response contains thinking blocks followed by text blocks.