Руководство Claude по кэшированию промптов

# ❌ Wrong: plain string is never cached
"content": "a long passage..."

# ✅ Right: content block + cache_control
"content": [
    {
        "type": "text",
        "text": "a long passage...",
        "cache_control": {"type": "ephemeral"},
    },
    {"type": "text", "text": "the question"},
]

# ❌ Wrong: question first means the prefix changes every turn; never hits
content = [
    {"type": "text", "text": "Please answer this question: " + question},  # volatile
    {"type": "text", "text": long_doc, "cache_control": {"type": "ephemeral"}},
]

# ✅ Right: long stable content first with marker, question after
content = [
    {"type": "text", "text": long_doc, "cache_control": {"type": "ephemeral"}},  # stable
    {"type": "text", "text": question},                                            # volatile
]

import json, os, requests

URL = "https://api.apiyi.com/v1/messages"
KEY = os.environ["APIYI_API_KEY"]
HEADERS = {
    "content-type": "application/json",
    "x-api-key": KEY,
    "anthropic-version": "2023-06-01",
}

# Must be long enough. Sonnet 4.6 needs >= 1,024 tokens (~770+ English words).
LONG_TEXT = open("long_document.txt").read()


def ask(question: str, label: str):
    payload = {
        "model": "claude-sonnet-4-6",
        "max_tokens": 256,
        "messages": [{
            "role": "user",
            "content": [
                {"type": "text", "text": LONG_TEXT, "cache_control": {"type": "ephemeral"}},
                {"type": "text", "text": question},
            ],
        }],
    }
    r = requests.post(URL, headers=HEADERS, data=json.dumps(payload), timeout=120)
    u = r.json().get("usage", {})
    print(f"[{label}] input={u.get('input_tokens')} "
          f"write={u.get('cache_creation_input_tokens')} "
          f"read={u.get('cache_read_input_tokens')}")


ask("Summarize the main idea", "1st")  # expect write>0, read=0
ask("Give 3 keywords",        "2nd")    # expect write=0, read>0

[1st] input=35 write=6512 read=0
[2nd] input=22 write=0    read=6512

# When constructing the Nth turn's request
messages[-1]["content"][-1]["cache_control"] = {"type": "ephemeral"}