Hitonabi/mission-control-v2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Voice: Thinking fuer Lucys Sprach-Pfad aus (enable_thinking:false)

Browse Source 
Qwen3.6 ist ein Thinking-Modell; ohne Abschaltung 11k Reasoning-Token vor jeder kurzen Antwort (~30s TTFB). voice.py umging die Gateway-Lane -> gleiches chat_template_kwargs-Muster nachgezogen, env MC_VOICE_NO_THINK. Gemessen ~30s -> ~3s.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
2026-07-01 21:53:54 +02:00
parent a341d254e1
commit 7e857a546b
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/routers/voice.py
+4
View File
@@ -208,6 +208,10 @@ async def voice_chat(body: ChatIn) -> StreamingResponse:
user_text = f"[Bildschirm-Sicht — das ist gerade auf dem/den Schirm(en) zu sehen:\n{safe_desc}\n]\n\n{body.text}" user_text = f"[Bildschirm-Sicht — das ist gerade auf dem/den Schirm(en) zu sehen:\n{safe_desc}\n]\n\n{body.text}"
messages.append({"role": "user", "content": user_text}) messages.append({"role": "user", "content": user_text})
payload = {"model": body.model or HERMES_API_MODEL, "messages": messages, "stream": True} payload = {"model": body.model or HERMES_API_MODEL, "messages": messages, "stream": True}
# Lucy-Hirn ist Thinking-Modell -> fuer die gesprochene Assistentin Thinking AUS (sonst 11k
# Reasoning-Token vor der kurzen Antwort, gemessen ~30s TTFB). Muster wie gateway_proxy/mem0.
if os.environ.get("MC_VOICE_NO_THINK", "1") not in ("0", "false", "False"):
payload["chat_template_kwargs"] = {"enable_thinking": False}
headers = { headers = {
"Authorization": f"Bearer {HERMES_API_KEY}", "Authorization": f"Bearer {HERMES_API_KEY}",
"X-Hermes-Session-Id": body.session_id, "X-Hermes-Session-Id": body.session_id,