Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
import asyncio
import json
import httpx
import pytest
from core.inference import external_provider as ep
@pytest.mark.parametrize("stream", [True, False])
@pytest.mark.parametrize(
"base_url", ["https://opencode.ai/inference/go/v1", "https://opencode.ai/zen/go/v1"]
)
def test_opencode_go_chat_sends_conversation_session(monkeypatch, stream, base_url):
requests = []
def handler(request):
requests.append(request)
if stream:
return httpx.Response(
200, headers = {"content-type": "text/event-stream"}, content = "data: [DONE]\n\n"
)
return httpx.Response(
200, json = {"choices": [{"message": {"role": "assistant", "content": "ok"}}]}
)
async def run():
async with httpx.AsyncClient(transport = httpx.MockTransport(handler)) as http:
monkeypatch.setattr(ep, "_client", lambda: http)
client = ep.ExternalProviderClient("custom", base_url, "key")
for thread_id in ("conversation-1", "conversation-1", "conversation-2"):
async for _ in client.stream_chat_completion(
messages = [{"role": "user", "content": "hi"}],
model = "test-model",
stream = stream,
thread_id = thread_id,
):
pass
asyncio.run(run())
sessions = [request.headers.get("x-opencode-session") for request in requests]
assert len(sessions) == 3
assert sessions[0] and sessions[0] == sessions[1]
assert sessions[2] and sessions[2] != sessions[0]
@pytest.mark.parametrize(
"base_url",
["https://example.org/v1", "https://opencode.ai/inference/v1", "https://opencode.ai/zen/v1"],
)
def test_other_providers_do_not_receive_opencode_session(monkeypatch, base_url):
requests = []
def handler(request):
requests.append(request)
return httpx.Response(
200, headers = {"content-type": "text/event-stream"}, content = "data: [DONE]\n\n"
)
async def run():
async with httpx.AsyncClient(transport = httpx.MockTransport(handler)) as http:
monkeypatch.setattr(ep, "_client", lambda: http)
client = ep.ExternalProviderClient("custom", base_url, "key")
async for _ in client.stream_chat_completion(
messages = [{"role": "user", "content": "hi"}],
model = "test-model",
thread_id = "conversation-1",
):
pass
asyncio.run(run())
assert len(requests) == 1
assert "x-opencode-session" not in requests[0].headers
def test_opencode_go_responses_sends_conversation_session(monkeypatch):
requests = []
def handler(request):
requests.append(request)
return httpx.Response(200, json = {"id": "resp_test", "status": "completed", "output": []})
async def run():
async with httpx.AsyncClient(transport = httpx.MockTransport(handler)) as http:
monkeypatch.setattr(ep, "_client", lambda: http)
client = ep.ExternalProviderClient(
"custom", "https://opencode.ai/inference/go/openai/v1", "key", api_type = "responses"
)
async for _ in client.stream_chat_completion(
messages = [{"role": "user", "content": "hi"}],
model = "test-model",
stream = False,
thread_id = "conversation-1",
):
pass
asyncio.run(run())
assert len(requests) == 1
assert requests[0].headers.get("x-opencode-session")
def test_opencode_go_request_without_thread_still_sends_session(monkeypatch):
requests = []
def handler(request):
requests.append(request)
if json.loads(request.content).get("stream"):
return httpx.Response(
200, headers = {"content-type": "text/event-stream"}, content = "data: [DONE]\n\n"
)
return httpx.Response(
200, json = {"choices": [{"message": {"role": "assistant", "content": "ok"}}]}
)
async def run():
async with httpx.AsyncClient(transport = httpx.MockTransport(handler)) as http:
monkeypatch.setattr(ep, "_client", lambda: http)
client = ep.ExternalProviderClient(
"custom", "https://opencode.ai/inference/go/v1", "key"
)
async for _ in client.stream_chat_completion(
messages = [{"role": "user", "content": "title this"}],
model = "test-model",
):
pass
await client.chat_completion(
messages = [{"role": "user", "content": "ping"}], model = "test-model"
)
asyncio.run(run())
assert len(requests) == 2
assert all(request.headers.get("x-opencode-session") for request in requests)