缓存诊断

client = anthropic.Anthropic()

SYSTEM = "You are an AI assistant analyzing a large document. <document>...</document>"

# 第 1 轮：通过 previous_message_id=None 选择加入
r1 = client.beta.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    cache_control={"type": "ephemeral"},
    system=SYSTEM,
    messages=[{"role": "user", "content": "Summarize section 1."}],
    diagnostics={"previous_message_id": None},
    betas=["cache-diagnosis-2026-04-07"],
)

# 第 2 轮：引用上一个响应的 id
r2 = client.beta.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    cache_control={"type": "ephemeral"},
    system=SYSTEM,
    messages=[
        {"role": "user", "content": "Summarize section 1."},
        {"role": "assistant", "content": r1.content},
        {"role": "user", "content": "Now summarize section 2."},
    ],
    diagnostics={"previous_message_id": r1.id},
    betas=["cache-diagnosis-2026-04-07"],
)

diagnostics = r2.diagnostics
if diagnostics is None:
    print("No divergence detected.")
elif diagnostics.cache_miss_reason is None:
    print("Comparison still pending.")
else:
    print(f"cache_miss_reason: {diagnostics.cache_miss_reason.type}")

# 第 2 轮：流式传输，引用上一个响应的 id
with client.beta.messages.stream(
    model="claude-opus-4-8",
    max_tokens=1024,
    cache_control={"type": "ephemeral"},
    system=SYSTEM,
    messages=[
        {"role": "user", "content": "Summarize section 1."},
        {"role": "assistant", "content": r1.content},
        {"role": "user", "content": "Now summarize section 2."},
    ],
    diagnostics={"previous_message_id": r1.id},
    betas=["cache-diagnosis-2026-04-07"],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)
    print()
    r2 = stream.get_final_message()

diagnostics = r2.diagnostics
if diagnostics is None:
    print("No divergence detected.")
elif diagnostics.cache_miss_reason is None:
    print("Comparison still pending.")
else:
    print(f"cache_miss_reason: {diagnostics.cache_miss_reason.type}")