Skip to content

fix: 修复文档编码，语音功能 #130

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
AeBoPi merged 1 commit into from
May 18, 2026
+21 −10
Merged

fix: 修复文档编码，语音功能 #130

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 20 additions & 8 deletions backend/api/routes/voice.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -396,20 +396,31 @@ async def device_voice_ws(
):
mac = validate_mac_param(mac)
x_device_token = websocket.headers.get("x-device-token") or websocket.query_params.get("token")

# Accept immediately so the client (ESP32) gets HTTP 101 without waiting for DB queries.
# Auth and session setup happen right after; if they fail we close with an error code.
await websocket.accept()
logger.info("[VOICE_WS] accepted mac=%s has_token=%s", mac, bool(x_device_token))

try:
await require_device_token(mac, x_device_token, websocket.headers.get("accept-language"))
except HTTPException as exc:
logger.warning("[VOICE_WS] auth failed mac=%s status=%d detail=%s", mac, exc.status_code, exc.detail)
await websocket.close(code=1008, reason=str(exc.detail)[:120])
return

settings = await _resolve_device_voice_runtime_settings(mac)
session = create_voice_ws_session(
settings=settings,
access_user_id=None,
access_mac=mac,
)
await websocket.accept()
logger.info("[VOICE_WS] accepted mac=%s session_id=%s", mac, session.session_id)
try:
settings = await _resolve_device_voice_runtime_settings(mac)
session = create_voice_ws_session(
settings=settings,
access_user_id=None,
access_mac=mac,
)
logger.info("[VOICE_WS] session ready mac=%s session_id=%s provider=%s", mac, getattr(session, "session_id", "?"), getattr(settings, "llm_provider", "?"))
except Exception:
logger.exception("[VOICE_WS] session setup failed mac=%s", mac)
await websocket.close(code=1011, reason="internal error")
return

async def _sender() -> None:
async for event in iter_voice_ws_events(session):
Expand All @@ -430,6 +441,7 @@ async def _sender() -> None:
ws_message.get("type"),
)
if ws_message.get("type") == "websocket.disconnect":
logger.info("[VOICE_WS] client disconnected mac=%s code=%s", mac, ws_message.get("code"))
break

if "bytes" in ws_message and ws_message["bytes"]:
Expand Down
Binary file modified docs/en/voice-mode.md
View file
Open in desktop
Binary file not shown.
Binary file modified docs/voice-mode.md
View file
Open in desktop
Binary file not shown.
3 changes: 1 addition & 2 deletions firmware/src/network.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1431,9 +1431,8 @@ bool voiceWsOpen(int sampleRate, int screenW, int screenH, bool includeImage) {
}

String mac = WiFi.macAddress();
String path = basePath + "/api/device/" + mac + "/voice/ws";
String path = basePath + "/api/device/" + mac + "/voice/ws?token=" + cfgDeviceToken;
String extraHeaders = String("X-Device-Token: ") + cfgDeviceToken;

String startMsg = String("{\"type\":\"session.start\",\"sample_rate\":") + sampleRate
+ ",\"w\":" + screenW
+ ",\"h\":" + screenH
Expand Down
Loading