One line, keep your OpenAI SDK

​

The scenario

​

Step 1 — Repoint the client

llm = OpenAI(
    api_key=os.environ["ANONA_API_KEY"],          # your Anona key, not an OpenAI key
    base_url="https://api.anonalabs.com/v1",
    default_headers={"X-Anona-Space-Id": "support"},
)

​

Step 2 — Use it exactly as before

first = llm.chat.completions.create(
    model="balanced",
    messages=[{"role": "user", "content": "My cat is named Miso and she only eats salmon."}],
)

​

Step 3 — A new conversation still knows

second = llm.chat.completions.create(
    model="balanced",
    messages=[{"role": "user", "content": "What is my cat's name?"}],
)

​

Step 4 — Tune per call, or per space

​

Evals

1. Run two conversations as above. The second must answer from the first.
2. Set X-Anona-Memory: false and confirm it does not — that comparison is your A/B.
3. Set X-Anona-User-Id to two different values and confirm they do not share.

​

Guardrails

• Extraction is not instant. A question asked immediately after the fact was mentioned may miss it; the example sleeps for this reason.
• model is ours, not OpenAI’s. Use a tier alias like balanced or an id from GET /v1/models. An unknown name is a 400, not a silent fallback.
• Anthropic and Responses shapes work too, on /v1/messages and /v1/responses, with the same headers. x-api-key is accepted anywhere Authorization is, because the Anthropic SDK never sets the latter.

​

The script