Files
CyberGril/tests/test_voice_custom.py
T

511 lines
25 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""Custom voice tests (HEL-899): reference-audio registration, preview,
selection persistence, call-time capture — all against the real router and
real services with fake panel/TTS transports. Zero network, zero real
LLM/embedding/ASR/TTS calls."""
from __future__ import annotations
import io
import json
import sys
import wave
from pathlib import Path
import httpx
import pytest
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "tests"))
from test_r2 import R2LLM # noqa: E402
from cybergril.api.app import create_app # noqa: E402
from cybergril.life.runtime import LifeConfig # noqa: E402
from cybergril.think.router import build_router # noqa: E402
from cybergril.think.scenes import Tier # noqa: E402
from cybergril.voice.custom import CustomVoiceConfig, CustomVoiceService # noqa: E402
from cybergril.voice.session import VoiceConfig, VoiceSessionService # noqa: E402
CREATE = {"name": "语音测试", "birth": "2000-10-18", "hour": "亥时", "relation": "朋友"}
BUILTIN = ["bailu", "bajie", "default", "female_soft", "haimianbaobao", "jiaojiao",
"male_warm", "nezha", "rain", "sunwukong", "xiaoyun"]
def make_wav(seconds: float = 3.0, rate: int = 16000, channels: int = 1) -> bytes:
buffer = io.BytesIO()
with wave.open(buffer, "wb") as wav:
wav.setnchannels(channels)
wav.setsampwidth(2)
wav.setframerate(rate)
wav.writeframes(b"\x00\x01" * int(rate * channels * seconds))
return buffer.getvalue()
class FakeVoiceStack:
""".12 语音面板(8090) + CosyVoice(9880) 的只读桩:记录每一次调用."""
def __init__(self, tmp: Path) -> None:
self.ids: list[str] = list(BUILTIN)
self.registry_file = tmp / "voices.json"
self.uploads: list[dict] = []
self.tts_calls: list[dict] = []
self.panel_down = False
self.tts_down = False
self.reject_upload = "" # 面板 400 detail(如"自动转写失败")
self.swallow = False # 谎报成功:回 ok 但不进列表(测登记后核验)
self.generic_voice_writes = 0 # POST /api/voice —— 必须永远是 0
self.deletes: list[str] = []
self.transport = httpx.MockTransport(self._handle)
def _registry(self) -> dict:
return json.loads(self.registry_file.read_text(encoding="utf-8")) \
if self.registry_file.exists() else {}
def _write_registry(self, data: dict) -> None:
self.registry_file.write_text(json.dumps(data, ensure_ascii=False, indent=1),
encoding="utf-8")
def _handle(self, request: httpx.Request) -> httpx.Response:
host, path = request.url.host, request.url.path
if host == "panel.test":
if self.panel_down:
raise httpx.ConnectError("panel down")
if path == "/api/voices" and request.method == "GET":
return httpx.Response(200, json={"voices": sorted(self.ids)})
if path == "/api/voices/upload":
name = self._form_name(request)
prompt_text = self._form_text(request)
if self.reject_upload:
return httpx.Response(400, json={"detail": self.reject_upload})
if not prompt_text: # 面板在参考文本为空时走 FunASR(桩:固定转写)
prompt_text = "这是自动转写出的参考文本,内容与音频一致。"
registry = self._registry()
registry[name] = {"prompt_text": prompt_text,
"prompt_wav": f"/opt/voice-agent/cosyvoice/voice_samples/{name}.wav"}
self._write_registry(registry)
self.uploads.append({"name": name, "prompt_text": prompt_text,
"bytes": len(request.content)})
if not self.swallow:
self.ids.append(name)
return httpx.Response(200, json={"ok": True, "voice": name})
if path.startswith("/api/voices/") and request.method == "DELETE":
self.deletes.append(path.rsplit("/", 1)[-1])
return httpx.Response(200, json={"ok": True})
if path == "/api/voice": # 通用助手自己的状态 —— CyberGril 绝不写
self.generic_voice_writes += 1
return httpx.Response(200, json={"ok": True})
return httpx.Response(404)
if host == "tts.test":
if path == "/health":
if self.tts_down:
return httpx.Response(503)
return httpx.Response(200, json={"ok": True, "voices": sorted(self.ids)})
if path == "/tts":
if self.tts_down:
return httpx.Response(503)
body = json.loads(request.content)
self.tts_calls.append(body)
marker = f"{body['voice']}|{body['text']}".encode()
return httpx.Response(200, content=marker + b"\x01\x00" * 240)
return httpx.Response(404)
return httpx.Response(404)
@staticmethod
def _form_name(request: httpx.Request) -> str:
return _multipart_field(request.content, b"name") or ""
@staticmethod
def _form_text(request: httpx.Request) -> str:
return _multipart_field(request.content, b"prompt_text") or ""
def _multipart_field(body: bytes, field: bytes) -> str | None:
"""极简 multipart 取字段(只为桩服务;产品代码不解析 multipart)."""
for part in body.split(b"--"):
header, _, value = part.partition(b"\r\n\r\n")
if field + b'"' in header:
return value.strip(b"\r\n-").decode()
return None
class FakeLiveKit:
def __init__(self) -> None:
self.dispatches: list[str] = []
self.deleted_rooms: list[str] = []
self.transport = httpx.MockTransport(self._handle)
def _handle(self, request: httpx.Request) -> httpx.Response:
if request.url.path == "/twirp/livekit.AgentDispatchService/CreateDispatch":
self.dispatches.append(request.url.path)
return httpx.Response(200, json={"id": "AD_1", "room": "r"})
if request.url.path == "/twirp/livekit.RoomService/DeleteRoom":
self.deleted_rooms.append(request.url.path)
return httpx.Response(200, content=b"")
return httpx.Response(404)
def build_app(tmp: Path, stack: FakeVoiceStack, livekit: FakeLiveKit | None = None):
livekit = livekit or FakeLiveKit()
voice = VoiceSessionService(
config=VoiceConfig(
livekit_url="ws://voice.test:7880", livekit_internal="http://livekit.test",
api_key="devkey", api_secret="test-secret-not-real",
tts_health_url="http://tts.test/health"),
http=httpx.AsyncClient(transport=httpx.MockTransport(
lambda request: stack._handle(request) if request.url.host == "tts.test"
else livekit._handle(request))))
worker_state = tmp / "voice_state_cybergril.json"
custom = CustomVoiceService(
config=CustomVoiceConfig(
panel_url="https://panel.test", tts_url="http://tts.test",
registry_file=str(stack.registry_file),
worker_state_file=str(worker_state)),
http=httpx.AsyncClient(transport=stack.transport, verify=False),
selection_path=tmp / "sel.json", registry_path=tmp / "custom.json",
journal_path=tmp / "usage.jsonl")
provider = R2LLM()
router = build_router(providers={t: provider for t in (Tier.HIGH, Tier.STANDARD, Tier.LOW)})
app = create_app(db_path=":memory:", router=router,
life_config=LifeConfig(enabled=True, poll_seconds=3600),
semantic_mode="stub", voice_service=voice,
custom_voice_service=custom)
return app, custom, worker_state
@pytest.fixture
def stack(tmp_path):
return FakeVoiceStack(tmp_path)
@pytest.fixture
def instance(tmp_path, stack):
from fastapi.testclient import TestClient
app, custom, worker_state = build_app(tmp_path, stack)
with TestClient(app) as client:
client.post("/api/companion", json=CREATE)
yield client, stack, custom, worker_state
def test_register_list_and_selection_flow(instance):
client, stack, custom, worker_state = instance
audio = make_wav(3)
registered = client.post(
"/api/voice/voices",
params={"label": "她的声音", "prompt_text": "这是参考文字"},
content=audio, headers={"Content-Type": "audio/wav"})
assert registered.status_code == 201
record = registered.json()
assert record["id"].startswith("cg-") and len(record["id"]) == 11
assert record["label"] == "她的声音"
assert record["prompt_text"] == "这是参考文字"
assert record["prompt_text_source"] == "user"
# 上传到达面板的是服务端生成的 cg- 专属 ID,不带用户文件名
assert stack.uploads[-1]["name"] == record["id"]
assert stack.uploads[-1]["bytes"] > 0
listing = client.get("/api/voice/voices").json()
by_id = {v["id"]: v for v in listing["voices"]}
assert set(by_id) == set(BUILTIN) | {record["id"]}
assert by_id[record["id"]]["source"] == "custom"
assert by_id[record["id"]]["label"] == "她的声音"
assert by_id["rain"]["source"] == "builtin"
assert listing["selection"]["voice"] is None
preview = client.post("/api/voice/preview", json={"voice": record["id"]})
assert preview.status_code == 200
assert preview.headers["content-type"] == "audio/wav"
with wave.open(io.BytesIO(preview.content)) as wav:
assert wav.getframerate() == 24000 and wav.getnchannels() == 1
assert stack.tts_calls[-1] == {"text": "你好,这是我的声音,以后就用它陪你说话。",
"voice": record["id"]}
applied = client.post("/api/voice/selection", json={"voice": record["id"]})
assert applied.status_code == 200 and applied.json()["voice"] == record["id"]
assert json.loads(worker_state.read_text())["voice"] == record["id"]
assert client.get("/api/voice/selection").json()["voice"] == record["id"]
listing = client.get("/api/voice/voices").json()
assert {v["id"] for v in listing["voices"] if v["selected"]} == {record["id"]}
# 备份清单字段在列表里(CG-009 承接)
entry = [v for v in listing["voices"] if v["id"] == record["id"]][0]
assert entry["prompt_wav"].endswith(record["id"] + ".wav")
def test_register_requires_explicit_asr_consent(instance):
client, stack, _, _ = instance
refusal = client.post("/api/voice/voices", content=make_wav(3))
assert refusal.status_code == 422
assert "转写" in refusal.json()["detail"] or "参考文字" in refusal.json()["detail"]
assert stack.uploads == [] # 未获明确准许,不触发任何 ASR/上传
allowed = client.post("/api/voice/voices", params={"allow_asr": "true"},
content=make_wav(3))
assert allowed.status_code == 201
assert allowed.json()["prompt_text_source"] == "asr"
journal = [json.loads(ln) for ln in
Path(instance[3].parent, "usage.jsonl").read_text().splitlines()]
assert any(e["kind"] == "register_asr" and e["voice"] == allowed.json()["id"]
for e in journal)
def test_register_rejects_bad_formats(instance):
client, stack, _, _ = instance
assert client.post("/api/voice/voices", params={"prompt_text": "x"},
content=b"ID3-not-a-wav").status_code == 422
assert client.post("/api/voice/voices", params={"prompt_text": "x"},
content=make_wav(1.0)).status_code == 422 # <2s
header_only = b"RIFF" + (9999).to_bytes(4, "little") + b"WAVE" + b"junk" * 10
assert client.post("/api/voice/voices", params={"prompt_text": "x"},
content=header_only).status_code == 422 # WAV magic 但头不完整
too_big = make_wav(2) + b"\x00" * (15 * 1024 * 1024 + 1)
response = client.post("/api/voice/voices", params={"prompt_text": "x"}, content=too_big)
assert response.status_code == 422 and "15MB" in response.json()["detail"]
assert stack.uploads == []
def test_register_ids_never_collide_with_builtin_or_each_other(instance, monkeypatch):
client, stack, _, _ = instance
first = client.post("/api/voice/voices", params={"prompt_text": "一"},
content=make_wav(2)).json()
second = client.post("/api/voice/voices", params={"prompt_text": "二"},
content=make_wav(2)).json()
assert first["id"] != second["id"]
assert not any(v.startswith("cg-") for v in BUILTIN)
# 强制撞名:第一次生成的 ID 已在注册表里 → 必须换新 ID,而不是覆盖
registry = stack._registry()
registry["cg-deadbeef"] = {"prompt_text": "旧条目", "prompt_wav": "/old.wav"}
stack._write_registry(registry)
stack.ids.append("cg-deadbeef") # 让首撞成立
calls = iter(["deadbeef", "cafef00d"])
monkeypatch.setattr("secrets.token_hex", lambda n: next(calls))
forced = client.post("/api/voice/voices", params={"prompt_text": "三"},
content=make_wav(2)).json()
assert forced["id"] == "cg-cafef00d"
assert stack._registry()["cg-deadbeef"]["prompt_text"] == "旧条目" # 未被覆盖
async def test_concurrent_registers_are_serialized_and_distinct(tmp_path, stack):
"""并发登记同名同音频:锁串行化 + 随机 ID,各自成立、互不覆盖."""
import asyncio
service = CustomVoiceService(
config=CustomVoiceConfig(panel_url="https://panel.test", tts_url="http://tts.test",
registry_file=str(stack.registry_file),
worker_state_file=str(tmp_path / "w.json")),
http=httpx.AsyncClient(transport=stack.transport, verify=False),
selection_path=tmp_path / "sel.json", registry_path=tmp_path / "custom.json",
journal_path=tmp_path / "usage.jsonl")
try:
records = await asyncio.gather(*[
service.register(data=make_wav(2), label="", prompt_text="并发", allow_asr=False)
for _ in range(4)])
ids = [record["id"] for record in records]
assert len(set(ids)) == 4 and all(v.startswith("cg-") for v in ids)
assert len(stack.uploads) == 4
assert set(service.custom_voices()) == set(ids)
finally:
await service.aclose()
def test_register_panel_down_or_rejecting_leaves_no_half_option(instance):
client, stack, custom, _ = instance
stack.panel_down = True
assert client.post("/api/voice/voices", params={"prompt_text": "x"},
content=make_wav(2)).status_code == 503
stack.panel_down = False
stack.reject_upload = "自动转写失败(boom), 请手动填写参考文本"
assert client.post("/api/voice/voices", params={"allow_asr": "true"},
content=make_wav(2)).status_code == 422
assert custom.custom_voices() == {}
stack.reject_upload = ""
# 面板谎报成功(列表里没出现)也要拒绝,不登记元数据
stack.swallow = True
lying = client.post("/api/voice/voices", params={"prompt_text": "x"},
content=make_wav(2))
assert lying.status_code in (422, 503)
assert custom.custom_voices() == {}
def test_preview_unknown_voice_never_reaches_tts(instance):
client, stack, _, _ = instance
response = client.post("/api/voice/preview", json={"voice": "ghost"})
assert response.status_code == 404
assert stack.tts_calls == [] # CosyVoice 对未知音色静默回落 default,必须前置拦住
assert client.post("/api/voice/preview", json={}).status_code == 422
def test_preview_tts_down_honest(instance):
client, stack, _, _ = instance
registered = client.post("/api/voice/voices", params={"prompt_text": "x"},
content=make_wav(2)).json()
stack.tts_down = True
response = client.post("/api/voice/preview", json={"voice": registered["id"]})
assert response.status_code == 503
assert "声音服务" in response.json()["detail"]
def test_preview_writes_no_chat_memory_or_receipts(instance):
client, stack, _, _ = instance
registered = client.post("/api/voice/voices", params={"prompt_text": "x"},
content=make_wav(2)).json()
app = client.app
counts = {table: app.state.store.query_one(f"SELECT COUNT(*) c FROM {table}")["c"]
for table in ("chat_message", "mem_episodic", "sharing_attempt", "life_event")}
assert client.post("/api/voice/preview",
json={"voice": registered["id"], "text": "自定义试听句"}).status_code == 200
assert stack.tts_calls[-1]["text"] == "自定义试听句"
after = {table: app.state.store.query_one(f"SELECT COUNT(*) c FROM {table}")["c"]
for table in counts}
assert after == counts
def test_apply_rules(instance):
client, stack, _, worker_state = instance
registered = client.post("/api/voice/voices", params={"prompt_text": "x"},
content=make_wav(2)).json()
# 自定义音色未试听 → 拒绝
unpreviewed = client.post("/api/voice/selection", json={"voice": registered["id"]})
assert unpreviewed.status_code == 409 and "试听" in unpreviewed.json()["detail"]
# 未知音色 → 404
assert client.post("/api/voice/selection", json={"voice": "ghost"}).status_code == 404
# 内置音色(D1 候选)不强制试听
builtin = client.post("/api/voice/selection", json={"voice": "rain"})
assert builtin.status_code == 200
assert json.loads(worker_state.read_text())["voice"] == "rain"
# 试听后自定义音色可应用
assert client.post("/api/voice/preview", json={"voice": registered["id"]}).status_code == 200
applied = client.post("/api/voice/selection", json={"voice": registered["id"]})
assert applied.status_code == 200 and applied.json()["label"] == registered["id"]
def test_apply_rollback_on_state_write_failure(tmp_path, stack):
from fastapi.testclient import TestClient
(tmp_path / "blocker").write_text("not a dir")
app, custom, _ = build_app(tmp_path, stack)
custom.config.worker_state_file = str(tmp_path / "blocker" / "worker.json")
with TestClient(app) as client:
client.post("/api/companion", json=CREATE)
assert client.post("/api/voice/selection", json={"voice": "rain"}).status_code == 503
assert custom.selection().voice is None
assert client.get("/api/voice/selection").json()["voice"] is None
def test_selection_persists_across_restart(tmp_path, stack):
from fastapi.testclient import TestClient
app, custom, worker_state = build_app(tmp_path, stack)
with TestClient(app) as client:
client.post("/api/companion", json=CREATE)
registered = client.post("/api/voice/voices",
params={"label": "留声", "prompt_text": "x"},
content=make_wav(2)).json()
client.post("/api/voice/preview", json={"voice": registered["id"]})
client.post("/api/voice/selection", json={"voice": registered["id"]})
# “重启”:同一批文件新建服务
app2, custom2, _ = build_app(tmp_path, stack)
with TestClient(app2) as client2:
client2.post("/api/companion", json=CREATE)
selection = client2.get("/api/voice/selection").json()
assert selection["voice"] == registered["id"]
listing = client2.get("/api/voice/voices").json()
entry = [v for v in listing["voices"] if v["id"] == registered["id"]][0]
assert entry["label"] == "留声" and entry["selected"] is True
assert entry["previewed"] is True # 试听凭据也在持久流水里
# 重启后无需重新试听即可再应用
other = client2.post("/api/voice/voices", params={"prompt_text": "y"},
content=make_wav(2)).json()
client2.post("/api/voice/preview", json={"voice": other["id"]})
assert client2.post("/api/voice/selection", json={"voice": other["id"]}).status_code == 200
assert json.loads(Path(worker_state).read_text())["voice"] == other["id"]
def test_session_captures_voice_and_pins_for_the_call(instance):
client, stack, custom, worker_state = instance
registered = client.post("/api/voice/voices", params={"prompt_text": "x"},
content=make_wav(2)).json()
client.post("/api/voice/preview", json={"voice": registered["id"]})
client.post("/api/voice/selection", json={"voice": registered["id"]})
opened = client.post("/api/voice/session").json()
assert opened["voice"] == registered["id"]
assert json.loads(worker_state.read_text())["voice"] == registered["id"]
service_session = client.app.state.voice_service.get(opened["session_id"])
assert service_session.voice == registered["id"]
# 通话中改选:本通话定住,最迟下一通话生效
client.post("/api/voice/selection", json={"voice": "rain"})
assert client.app.state.voice_service.get(opened["session_id"]).voice == registered["id"]
second = client.post("/api/voice/session").json()
assert second["voice"] == "rain"
def test_session_capture_falls_back_when_selection_invalid(instance):
client, stack, custom, worker_state = instance
registered = client.post("/api/voice/voices", params={"prompt_text": "x"},
content=make_wav(2)).json()
client.post("/api/voice/preview", json={"voice": registered["id"]})
client.post("/api/voice/selection", json={"voice": registered["id"]})
stack.ids.remove(registered["id"]) # 音色从注册表消失
client.app.state.voice_service._tts_health.checked = -1e9 # 重新探测拿新名单
opened = client.post("/api/voice/session").json()
assert opened["voice"] == "default" # 诚实回落,不冒充原音色
def test_session_without_selection_keeps_operator_voice(instance):
client, stack, custom, worker_state = instance
worker_state.write_text(json.dumps({"voice": "rain", "operator_note": "d1"}), encoding="utf-8")
opened = client.post("/api/voice/session").json()
assert opened["voice"] == "rain" # D1/部署域现值如实生效
assert json.loads(worker_state.read_text()) == {"voice": "rain", "operator_note": "d1"}
def test_shared_generic_state_never_touched(instance):
client, stack, custom, worker_state = instance
registered = client.post("/api/voice/voices", params={"prompt_text": "x"},
content=make_wav(2)).json()
client.post("/api/voice/preview", json={"voice": registered["id"]})
client.post("/api/voice/selection", json={"voice": registered["id"]})
client.post("/api/voice/session")
assert stack.generic_voice_writes == 0 # 通用助手 voice_state 从不写
assert stack.deletes == [] # 既有音色从不删
assert all(upload["name"].startswith("cg-") for upload in stack.uploads)
assert not any(v in stack._registry() for v in BUILTIN) # 11 支既有条目原样
def test_no_identity_rewrite(instance):
client, stack, custom, worker_state = instance
app = client.app
registered = client.post("/api/voice/voices", params={"prompt_text": "x"},
content=make_wav(2)).json()
client.post("/api/voice/preview", json={"voice": registered["id"]})
before = {
"identity": app.state.store.query_one("SELECT identity_json FROM companion WHERE id=1"),
"bazi": app.state.store.query_one("SELECT pillars,derived FROM bazi_core WHERE id=1"),
"messages": app.state.store.query("SELECT id,role,text,turn_id,status FROM chat_message"),
}
client.post("/api/voice/selection", json={"voice": registered["id"]})
client.post("/api/voice/session")
after = {
"identity": app.state.store.query_one("SELECT identity_json FROM companion WHERE id=1"),
"bazi": app.state.store.query_one("SELECT pillars,derived FROM bazi_core WHERE id=1"),
"messages": app.state.store.query("SELECT id,role,text,turn_id,status FROM chat_message"),
}
assert before == after # 换声音只换发声:底色/名字/关系/聊天/记忆一概不动
def test_unconfigured_custom_endpoints_honest(tmp_path):
from fastapi.testclient import TestClient
provider = R2LLM()
router = build_router(providers={t: provider for t in (Tier.HIGH, Tier.STANDARD, Tier.LOW)})
app = create_app(db_path=":memory:", router=router,
life_config=LifeConfig(enabled=False), semantic_mode="stub")
with TestClient(app) as client:
listing = client.get("/api/voice/voices")
assert listing.status_code == 200 and listing.json()["configured"] is False
for method, path, kwargs in (
("post", "/api/voice/voices", {"content": make_wav(2)}),
("post", "/api/voice/preview", {"json": {"voice": "rain"}}),
("post", "/api/voice/selection", {"json": {"voice": "rain"}})):
response = getattr(client, method)(path, **kwargs)
assert response.status_code == 503
assert client.get("/api/voice/selection").status_code == 503