Self-improving AI Employees for everyone
Python ai-agentsai-employeeai-employeesassistantautonomous-agentsco-employeescompanygrok-botinstinctloop-agentsmuseown-your-datapersonalself-hosted
"""Speech runs on the gateway only for providers speech_defaults.json marks
("gateway": true), and only with no key of the install's own (nodes/speech)."""
import io
import json
import struct
import wave
from contextlib import contextmanager
from types import SimpleNamespace
from unittest.mock import MagicMock
import httpx
import respx
from structlog.contextvars import bound_contextvars
from nodes.speech import _handlers
from nodes.speech._base import gateway_serves
from services.gateway.routing import GatewayRouter
from services.llm.config import LLM_DEFAULTS
from tests.nodes._mocks import patched_container, patched_pricing
GATEWAY = "https://gw.example"
@contextmanager
def gateway_container(keys):
"""The node test container with a real, enabled GatewayRouter."""
with patched_container(auth_api_keys=keys) as container, patched_pricing():
settings = SimpleNamespace(gateway_enabled=True, distributed_mode=False, gateway_url=GATEWAY)
router = GatewayRouter(settings=settings, auth_service=container.auth_service(), defaults=LLM_DEFAULTS)
container.gateway_router = MagicMock(return_value=router)
yield container
def _clip(harness, tmp_path):
buffer = io.BytesIO()
with wave.open(buffer, "wb") as handle:
handle.setnchannels(1)
handle.setsampwidth(2)
handle.setframerate(8000)
handle.writeframes(struct.pack("<h", 0) * 4000)
(tmp_path / "a.wav").write_bytes(buffer.getvalue())
return harness.build_context(workspace_dir=str(tmp_path))
def test_only_openai_speech_is_served():
"""Groq's would bill $0 on LiteLLM 1.103.4 (gateway/tests/test_gateway_contract.py)."""
assert gateway_serves("openai")
assert not any(gateway_serves(p) for p in ("groq", "elevenlabs", "deepgram", "sarvam"))
@respx.mock
async def test_speech_without_an_own_key_runs_on_the_gateway(harness, tmp_path):
route = respx.post(f"{GATEWAY}/v1/audio/speech").mock(return_value=httpx.Response(200, content=b"ID3audio"))
# BaseNode.execute binds the run's ids, but tests/conftest.py stubs
# log_context out, so the test binds them.
with gateway_container({"opencompany_gateway": "sk-gateway"}), bound_contextvars(workflow_id="wf-1"):
result = await harness.execute(
"textToSpeech",
{"provider": "openai", "text": "hello"},
context=harness.build_context(workspace_dir=str(tmp_path)),
)
harness.assert_envelope(result, success=True)
request = route.calls.last.request
assert request.headers["authorization"] == "Bearer sk-gateway"
assert json.loads(request.content)["model"] == "openai/gpt-4o-mini-tts"
assert "workflow:wf-1" in request.headers["x-litellm-tags"]
# The prefix stays on the wire.
assert result["result"]["tts_model"] == "gpt-4o-mini-tts"
@respx.mock
async def test_an_own_key_wins_over_the_gateway(harness, tmp_path):
route = respx.post("https://api.openai.com/v1/audio/speech").mock(
return_value=httpx.Response(200, content=b"ID3audio")
)
with gateway_container({"openai": "sk-own", "opencompany_gateway": "sk-gateway"}):
result = await harness.execute(
"textToSpeech",
{"provider": "openai", "text": "hello"},
context=harness.build_context(workspace_dir=str(tmp_path)),
)
harness.assert_envelope(result, success=True)
request = route.calls.last.request
assert request.headers["authorization"] == "Bearer sk-own"
assert json.loads(request.content)["model"] == "gpt-4o-mini-tts"
assert "x-litellm-tags" not in request.headers
@respx.mock
async def test_gateway_transcription_never_asks_for_a_translation(harness, tmp_path):
"""LiteLLM has no /audio/translations route: translate falls back to
in-language transcription, as for a model that cannot translate."""
route = respx.post(f"{GATEWAY}/v1/audio/transcriptions").mock(
return_value=httpx.Response(200, json={"text": "hi", "duration": 3.0})
)
with gateway_container({"opencompany_gateway": "sk-gateway"}):
result = await harness.execute(
"speechToText",
{"provider": "openai", "audio_file": "a.wav", "stt_model": "whisper-1", "translate": True},
context=_clip(harness, tmp_path),
)
harness.assert_envelope(result, success=True)
assert b'name="model"\r\n\r\nopenai/whisper-1\r\n' in route.calls.last.request.content
@respx.mock
async def test_a_spent_allowance_is_worded_as_the_opencompany_allowance(harness, tmp_path):
respx.post(f"{GATEWAY}/v1/audio/speech").mock(
return_value=httpx.Response(429, json={"error": {"type": "budget_exceeded", "message": "Budget has been exceeded!"}})
)
with gateway_container({"opencompany_gateway": "sk-gateway"}):
result = await harness.execute(
"textToSpeech",
{"provider": "openai", "text": "hello"},
context=harness.build_context(workspace_dir=str(tmp_path)),
)
harness.assert_envelope(result, success=False)
assert "Your OpenCompany allowance for this month is used up." in result["error"]
@respx.mock
async def test_unmarked_providers_never_run_on_the_gateway(harness, tmp_path):
"""Groq serves chat on the gateway, but not speech: no own key is still no key."""
route = respx.post(f"{GATEWAY}/v1/audio/transcriptions").mock(return_value=httpx.Response(200, json={"text": "hi"}))
with gateway_container({"opencompany_gateway": "sk-gateway"}):
result = await harness.execute(
"speechToText", {"provider": "groq", "audio_file": "a.wav"}, context=_clip(harness, tmp_path)
)
harness.assert_envelope(result, success=False)
assert not route.called
async def test_dictation_falls_back_to_the_gateway_after_every_own_key():
with gateway_container({"deepgram": "dg-own", "opencompany_gateway": "sk-gateway"}):
assert await _handlers.dictation_provider() == "deepgram"
with gateway_container({"opencompany_gateway": "sk-gateway"}):
assert await _handlers.dictation_provider() == "openai"
with gateway_container({}):
assert await _handlers.dictation_provider() is None