[Responses API] Function calling (#1587)

Built on top of #1576.

Based on https://platform.openai.com/docs/api-reference/responses/create
and
https://platform.openai.com/docs/guides/function-calling?api-mode=responses#streaming

Works both with and without streaming.

**Note:** implementation starts to be a completely messy, especially in
streaming mode. Complexity increases as we add new event types. I do
think a refactoring would be beneficial e.g. with an internal state
object that keeps track of the current state and "knows" what to emit
and when (typically to emit the "done"/"completed" events each time a
new output/content is generated). Food for thoughts for a future PR.

## Non-stream

**Run**
```bash
pnpm run example function
```

**Output**

```js
{
  created_at: 1751467285177,
  error: null,
  id: 'resp_0b2ab98168a9813e0f7373f940221da4ef3211f43c9faac8',
  instructions: null,
  max_output_tokens: null,
  metadata: null,
  model: 'meta-llama/Llama-3.3-70B-Instruct',
  object: 'response',
  output: [
    {
      type: 'function_call',
      id: 'fc_f40ac964165602e2fcb2f955777acff8c4b9359d49eaf79b',
      call_id: '9cd167c7f',
      name: 'get_current_weather',
      arguments: '{"location": "Boston, MA", "unit": "fahrenheit"}',
      status: 'completed'
    }
  ],
  status: 'completed',
  tool_choice: 'auto',
  tools: [
    {
      name: 'get_current_weather',
      parameters: [Object],
      strict: true,
      type: 'function',
      description: 'Get the current weather in a given location'
    }
  ],
  temperature: 1,
  top_p: 1,
  output_text: ''
}
```

## Stream

**Run:**

```
pnpm run example function_streaming
```

**Output:**


```js
{
  type: 'response.created',
  response: {
    created_at: 1751467334073,
    error: null,
    id: 'resp_8d86745178f2b9fc0da000156655956181c76a7701712a05',
    instructions: null,
    max_output_tokens: null,
    metadata: null,
    model: 'meta-llama/Llama-3.3-70B-Instruct',
    object: 'response',
    output: [],
    status: 'in_progress',
    tool_choice: 'auto',
    tools: [ [Object] ],
    temperature: 1,
    top_p: 1
  },
  sequence_number: 0
}
{
  type: 'response.in_progress',
  response: {
    created_at: 1751467334073,
    error: null,
    id: 'resp_8d86745178f2b9fc0da000156655956181c76a7701712a05',
    instructions: null,
    max_output_tokens: null,
    metadata: null,
    model: 'meta-llama/Llama-3.3-70B-Instruct',
    object: 'response',
    output: [],
    status: 'in_progress',
    tool_choice: 'auto',
    tools: [ [Object] ],
    temperature: 1,
    top_p: 1
  },
  sequence_number: 1
}
{
  type: 'response.output_item.added',
  output_index: 0,
  item: {
    type: 'function_call',
    id: 'fc_9bdc8945b9cb6c95c5c248db4203f0707ba9fd338dee2454',
    call_id: '83a9d4baf',
    name: 'get_weather',
    arguments: ''
  },
  sequence_number: 2
}
{
  type: 'response.function_call_arguments.delta',
  item_id: 'fc_9bdc8945b9cb6c95c5c248db4203f0707ba9fd338dee2454',
  output_index: 0,
  delta: '{"latitude": 48.8567, "longitude": 2.3508}',
  sequence_number: 3
}
{
  type: 'response.function_call_arguments.done',
  item_id: 'fc_9bdc8945b9cb6c95c5c248db4203f0707ba9fd338dee2454',
  output_index: 0,
  arguments: '{"latitude": 48.8567, "longitude": 2.3508}',
  sequence_number: 4
}
{
  type: 'response.output_item.done',
  output_index: 0,
  item: {
    type: 'function_call',
    id: 'fc_9bdc8945b9cb6c95c5c248db4203f0707ba9fd338dee2454',
    call_id: '83a9d4baf',
    name: 'get_weather',
    arguments: '{"latitude": 48.8567, "longitude": 2.3508}',
    status: 'completed'
  },
  sequence_number: 5
}
{
  type: 'response.completed',
  response: {
    created_at: 1751467334073,
    error: null,
    id: 'resp_8d86745178f2b9fc0da000156655956181c76a7701712a05',
    instructions: null,
    max_output_tokens: null,
    metadata: null,
    model: 'meta-llama/Llama-3.3-70B-Instruct',
    object: 'response',
    output: [ [Object] ],
    status: 'completed',
    tool_choice: 'auto',
    tools: [ [Object] ],
    temperature: 1,
    top_p: 1
  },
  sequence_number: 6
}
```

Author: Wauplin

packages/responses-server/examples/function.js

@@ -0,0 +1,32 @@
+import OpenAI from "openai";
+
+const openai = new OpenAI({ baseURL: "http://localhost:3000/v1", apiKey: process.env.HF_TOKEN });
+
+const tools = [
+	{
+		type: "function",
+		name: "get_current_weather",
+		description: "Get the current weather in a given location",
+		parameters: {
+			type: "object",
+			properties: {
+				location: {
+					type: "string",
+					description: "The city and state, e.g. San Francisco, CA",
+				},
+				unit: { type: "string", enum: ["celsius", "fahrenheit"] },
+			},
+			required: ["location", "unit"],
+		},
+	},
+];
+
+const response = await openai.responses.create({
+	model: "meta-llama/Llama-3.3-70B-Instruct",
+	provider: "cerebras",
+	tools: tools,
+	input: "What is the weather like in Boston today?",
+	tool_choice: "auto",
+});
+
+console.log(response);

packages/responses-server/examples/function_streaming.js

@@ -0,0 +1,33 @@
+import { OpenAI } from "openai";
+
+const openai = new OpenAI({ baseURL: "http://localhost:3000/v1", apiKey: process.env.HF_TOKEN });
+
+const tools = [
+	{
+		type: "function",
+		name: "get_weather",
+		description: "Get current temperature for provided coordinates in celsius.",
+		parameters: {
+			type: "object",
+			properties: {
+				latitude: { type: "number" },
+				longitude: { type: "number" },
+			},
+			required: ["latitude", "longitude"],
+			additionalProperties: false,
+		},
+		strict: true,
+	},
+];
+
+const stream = await openai.responses.create({
+	model: "meta-llama/Llama-3.3-70B-Instruct",
+	provider: "cerebras",
+	input: [{ role: "user", content: "What's the weather like in Paris today?" }],
+	tools,
+	stream: true,
+});
+
+for await (const event of stream) {
+	console.log(event);
+}