Skip to main content
Use this page when your agent still uses OpenAI Chat Completions. The OpenAI wrappers guard supported chat calls without changing the native client shape.

​
Guarded Methods

MethodJavaScriptPython
client.chat.completions.create(...)SupportedSupported
client.chat.completions.create({ stream: true, ... })SupportedSupported as stream=True

​
Basic Request

const completion = await client.chat.completions.create({
  model: process.env.OPENAI_MODEL ?? "gpt-5.4-mini",
  messages: [
    {
      role: "user",
      content: "Summarize password reset link expiration guidance.",
    },
  ],
});

console.log(completion.choices[0]?.message.content);
Averta checks the message payload before OpenAI sees it. If the response contains final text, Averta checks that output before returning it.

​
Tools

const completion = await client.chat.completions.create({
  model: process.env.OPENAI_MODEL ?? "gpt-5.4-mini",
  messages,
  tools: [
    {
      type: "function",
      function: {
        name: "search_docs",
        description: "Search internal support documentation.",
        strict: true,
        parameters: {
          type: "object",
          properties: {
            query: { type: "string" },
          },
          required: ["query"],
          additionalProperties: false,
        },
      },
    },
  ],
});
For Chat Completions tools, Averta can:
  • normalize function and custom tools
  • remove blocked tools before forwarding the request
  • sanitize tool_choice when the requested tool was blocked
  • check returned tool calls before your app executes them

​
Tool Result Continuation

Send tool results back as tool role messages through the wrapped client. 
const nextCompletion = await client.chat.completions.create({
  model: process.env.OPENAI_MODEL ?? "gpt-5.4-mini",
  messages: [
    ...messages,
    completion.choices[0]!.message,
    {
      role: "tool",
      tool_call_id: "call_123",
      content: JSON.stringify({
        matches: ["Password reset links expire after 24 hours."],
      }),
    },
  ],
  tools,
});
Averta evaluates pure tool-result continuation requests before OpenAI sees them.

​
Streaming

Chat Completions streaming is guarded in both OpenAI wrappers: 
const stream = await client.chat.completions.create({
  model: process.env.OPENAI_MODEL ?? "gpt-5.4-mini",
  messages,
  stream: true,
});
It currently supports one streamed text choice. Requests with streaming enabled and n > 1 fail closed before provider execution.

​
Current Limits

  • Chat Completions streaming supports one streamed text choice.
  • Streaming output rewrite is not supported yet.
  • Rich media request preflight supports Data URL images in image_url.url.
  • Remote image URLs, file content parts, and audio content parts are rejected before preflight.

Tools

Understand OpenAI tool filtering.

Tool results

Screen tool output before continuation.