Mode WebSocket

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24from openai import OpenAI

client = OpenAI()

with client.responses.connect() as connection:
    connection.response.create(
        stream_id="main",
        model="gpt-6-astra",
        store=False,
        input=[
            {
                "type": "message",
                "role": "user",
                "content": [{"type": "input_text", "text": "Find fizz_buzz()"}],
            }
        ],
        tools=[],
    )
    for event in connection:
        if event.type == "response.completed":
            print(event.response.output_text)
            break
        if event.type in {"response.failed", "response.incomplete", "error"}:
            raise RuntimeError(event.to_json())

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31require "async"
require "openai"

def wait_for_response(connection)
  while (event = connection.receive)
    case event.type.to_s
    when "response.completed" then return event.response
    when "response.failed", "response.incomplete", "error"
      raise "Response failed: #{event.to_json}"
    end
  end
  raise "Connection closed before the response finished"
end

client = OpenAI::Client.new
Sync do |task|
  task.with_timeout(120) do
    client.responses.connect(request_options: { timeout: 10 }) do |connection|
      connection.response.create(
        stream_id: "main", model: "gpt-6-astra", store: false,
        input: [
          {
            role: "user",
            content: "Find fizz_buzz()"
          }
        ], tools: []
      )
      puts(wait_for_response(connection).output_text)
    end
  end
end

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74import json

from openai import OpenAI
from openai.resources.responses.responses import ResponsesConnection
from openai.types.responses import FunctionToolParam, Response

client = OpenAI()
model = "gpt-6-astra"
tools: list[FunctionToolParam] = [
    {
        "type": "function",
        "name": "get_test_results",
        "description": "Read the demo test results.",
        "parameters": {
            "type": "object",
            "properties": {},
            "required": [],
            "additionalProperties": False,
        },
        "strict": True,
    }
]


def get_test_results():
    # Demo data. Replace this function with your test runner.
    return {
        "test": "test_fizz_buzz",
        "failure": 'Expected "FizzBuzz" for 15, got "Fizz".',
    }


def wait_for_response(connection: ResponsesConnection) -> Response:
    for event in connection:
        if event.type == "response.completed":
            return event.response
        if event.type in {"response.failed", "response.incomplete", "error"}:
            raise RuntimeError(event.to_json())
    raise RuntimeError("Connection closed before the response finished.")


with client.responses.connect() as connection:
    connection.response.create(
        stream_id="main",
        model=model,
        store=False,
        input="Find the failing test and suggest a fix.",
        tools=tools,
        tool_choice={"type": "function", "name": "get_test_results"},
        parallel_tool_calls=False,
    )
    response = wait_for_response(connection)
    call = next(item for item in response.output if item.type == "function_call")
    if call.name != "get_test_results" or json.loads(call.arguments) != {}:
        raise ValueError("Expected a get_test_results call with no arguments")

    # Continue on the same connection using the actual response and tool-call IDs.
    connection.response.create(
        stream_id="main",
        model=model,
        store=False,
        previous_response_id=response.id,
        input=[
            {
                "type": "function_call_output",
                "call_id": call.call_id,
                "output": json.dumps(get_test_results()),
            },
            {"role": "user", "content": "Now optimize it."},
        ],
        tools=tools,
        tool_choice="none",
    )
    print(wait_for_response(connection).output_text)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73require "async"
require "openai"
require "json"

def wait_for_response(connection)
  while (event = connection.receive)
    case event.type.to_s
    when "response.completed" then return event.response
    when "response.failed", "response.incomplete", "error"
      raise "Response failed: #{event.to_json}"
    end
  end
  raise "Connection closed before the response finished"
end

tools = [
  {
    type: "function",
    name: "get_test_results",
    description: "Read the demo test results.",
    parameters: {
      type: "object",
      properties: {},
      required: [],
      additionalProperties: false
    },
    strict: true
  }
]

client = OpenAI::Client.new
Sync do |task|
  task.with_timeout(120) do
    client.responses.connect(request_options: { timeout: 10 }) do |connection|
      connection.response.create(
        stream_id: "main", model: "gpt-6-astra", store: false,
        input: "Find the failing test and suggest a fix.", tools: tools,
        tool_choice: {
          type: "function",
          name: "get_test_results"
        }, parallel_tool_calls: false
      )
      response = wait_for_response(connection)
      call = response.output.grep(OpenAI::Responses::ResponseFunctionToolCall).first
      unless call && call.name == "get_test_results" && JSON.parse(call.arguments) == {}
        raise "Expected a get_test_results call with no arguments"
      end

      # Demo data. Replace this with your test runner.
      result = {
        test: "test_fizz_buzz",
        failure: 'Expected "FizzBuzz" for 15, got "Fizz".'
      }
      connection.response.create(
        stream_id: "main", model: "gpt-6-astra", store: false,
        previous_response_id: response.id,
        input: [
          {
            type: "function_call_output",
            call_id: call.call_id,
            output: JSON.generate(result)
          },
          {
            role: "user",
            content: "Now optimize it."
          }
        ],
        tools: tools, tool_choice: "none"
      )
      puts(wait_for_response(connection).output_text)
    end
  end
end

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37from typing import cast

from openai import OpenAI
from openai.types.responses import ResponseInputParam

# Compact your current window (HTTP call).
compacted = client.responses.compact(
    model="gpt-6-astra",
    input=long_input_items_array,
)
next_input = cast(
    ResponseInputParam,
    [item.to_dict() for item in compacted.output],
)
next_input.append(
    {
        "type": "message",
        "role": "user",
        "content": [{"type": "input_text", "text": "Continue from here."}],
    }
)

# Start a new response on the WebSocket using the compacted window.
with client.responses.connect() as connection:
    connection.response.create(
        stream_id="main",
        model="gpt-6-astra",
        store=False,
        input=next_input,
        tools=[],
    )
    for event in connection:
        if event.type == "response.completed":
            print(event.response.output_text)
            break
        if event.type in {"response.failed", "response.incomplete", "error"}:
            raise RuntimeError(event.to_json())

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41require "async"
require "openai"

def wait_for_response(connection)
  while (event = connection.receive)
    case event.type.to_s
    when "response.completed" then return event.response
    when "response.failed", "response.incomplete", "error"
      raise "Response failed: #{event.to_json}"
    end
  end
  raise "Connection closed before the response finished"
end

client = OpenAI::Client.new
compacted = client.responses.compact(
  model: "gpt-6-astra",
  input: [
    {
      role: :user,
      content: "Find the failing test."
    }
  ]
)
next_input = compacted.output.map(&:to_h)
next_input << {
  role: :user,
  content: "Continue from here."
}

Sync do |task|
  task.with_timeout(120) do
    client.responses.connect(request_options: { timeout: 10 }) do |connection|
      connection.response.create(
        stream_id: "main", model: "gpt-6-astra", store: false,
        input: next_input, tools: []
      )
      puts(wait_for_response(connection).output_text)
    end
  end
end

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93from openai import OpenAI
from openai.resources.responses.responses import ResponsesConnection

client = OpenAI()
latest_response_id_by_lane: dict[str, str] = {}


def send_create(
    connection: ResponsesConnection,
    stream_id: str,
    text: str,
    previous_response_id: str | None = None,
):
    if previous_response_id is None:
        previous_response_id = latest_response_id_by_lane.get(stream_id)
    connection.response.create(
        stream_id=stream_id,
        model="gpt-6-astra",
        store=False,
        input=[
            {
                "type": "message",
                "role": "user",
                "content": [{"type": "input_text", "text": text}],
            }
        ],
        previous_response_id=previous_response_id,
    )


def drain_until_complete(
    connection: ResponsesConnection, expected_stream_ids: set[str]
):
    completed: set[str] = set()
    for event in connection:
        stream_id = event.stream_id
        if event.type == "error" and stream_id is None:
            raise RuntimeError(f"Connection error: {event.to_json()}")
        if stream_id is None or stream_id not in expected_stream_ids:
            continue

        if event.type == "response.completed":
            latest_response_id_by_lane[stream_id] = event.response.id
            completed.add(stream_id)
            if completed == expected_stream_ids:
                return
        elif event.type in {"response.failed", "response.incomplete", "error"}:
            raise RuntimeError(f"Lane {stream_id} failed: {event.to_json()}")
    raise RuntimeError("Connection closed before all responses finished.")


def wait_for_in_progress(connection: ResponsesConnection, expected_stream_id: str):
    for event in connection:
        if event.type == "error" and event.stream_id is None:
            raise RuntimeError(f"Connection error: {event.to_json()}")
        if event.stream_id != expected_stream_id:
            continue
        if event.type == "response.in_progress":
            return
        if event.type in {"response.failed", "response.incomplete", "error"}:
            raise RuntimeError(f"Lane {expected_stream_id} failed: {event.to_json()}")
    raise RuntimeError("Connection closed before the fork started.")


with client.responses.connect() as connection:
    # 1. Run two independent conversations in parallel.
    send_create(
        connection, "planner", "Draft a deployment plan for a stateless API service."
    )
    send_create(
        connection,
        "research",
        "List common deployment risks for a stateless API service.",
    )
    drain_until_complete(connection, {"planner", "research"})

    # 2. Fork the planner conversation and continue the original branch in parallel.
    planner_response_id = latest_response_id_by_lane["planner"]
    send_create(
        connection,
        "critic",
        "Find gaps in this deployment plan.",
        previous_response_id=planner_response_id,
    )
    # Let the fork bind its parent before advancing the original lane.
    wait_for_in_progress(connection, "critic")
    send_create(
        connection,
        "planner",
        "Add rollback and monitoring steps to the plan.",
        previous_response_id=planner_response_id,
    )
    drain_until_complete(connection, {"critic", "planner"})

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64require "async"
require "openai"
require "json"

def send_create(connection, stream_id, text, previous_response_id = nil)
  payload = {
    stream_id: stream_id,
    model: "gpt-6-astra",
    store: false,
    input: [
      {
        role: "user",
        content: text
      }
    ]
  }
  payload[:previous_response_id] = previous_response_id if previous_response_id
  connection.response.create(**payload)
end

def read_event(connection)
  event = connection.receive or raise "Connection closed before all responses finished"
  if ["response.failed", "response.incomplete", "error"].include?(event.type.to_s)
    raise "Response failed: #{event.to_json}"
  end

  event
end

def drain_responses(connection, lanes, latest_ids)
  remaining = lanes.dup
  until remaining.empty?
    event = read_event(connection)
    next unless event.type.to_s == "response.completed"

    lane = event.stream_id
    next unless remaining.include?(lane)

    latest_ids[lane] = event.response.id
    remaining.delete(lane)
  end
end

client = OpenAI::Client.new
Sync do |task|
  task.with_timeout(120) do
    client.responses.connect(request_options: { timeout: 10 }) do |connection|
      latest_ids = {}
      send_create(connection, "planner", "Draft a deployment plan for a stateless API service.")
      send_create(connection, "research", "List common deployment risks for a stateless API service.")
      drain_responses(connection, ["planner", "research"], latest_ids)
      parent_id = latest_ids.fetch("planner")
      send_create(connection, "critic", "Find gaps in this deployment plan.", parent_id)
      # Let the fork load its parent before advancing the original lane's cache.
      loop do
        event = read_event(connection)
        break if event.type.to_s == "response.in_progress" && event.stream_id == "critic"
      end
      send_create(connection, "planner", "Add rollback and monitoring steps.", parent_id)
      drain_responses(connection, ["critic", "planner"], latest_ids)
      puts(JSON.generate(latest_ids))
    end
  end
end