OpenAI

Requirements

• An OpenAI API key loaded into the TapPass vault by your platform team (OPENAI_API_KEY).
• Your tp_ key and the TapPass gateway URL.

Option A — SDK

from tappass import Agent

agent = Agent("https://tappass.example.com", "tp_...")
response = agent.chat("Hello", model="gpt-4o-mini")

Option B — OpenAI SDK, zero-code

export OPENAI_BASE_URL=https://tappass.example.com/v1
export OPENAI_API_KEY=tp_...

from openai import OpenAI

client = OpenAI()  # picks up env vars
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello"}],
)

What’s supported

• chat.completions (streaming + non-streaming)
• completions (legacy)
• embeddings
• Tool calls / function calling
• Vision (gpt-4o, gpt-4-turbo image inputs)
• Structured outputs (JSON mode, schema-typed outputs)

What changes

Header	Purpose
Authorization: Bearer tp_...	Your TapPass key — replaces the OpenAI key
X-Agent-Id: <your-agent>	Optional — attaches audit events to an agent
X-Governance-Flags: mode=strict	Optional — per-request flag override

Nothing else in the request changes — it’s the standard OpenAI schema.