81d4cf6fd8
Bisher wurde `language` zwar an STT/TTS übergeben, aber nie an den LLM.
Lokales Modell antwortete deshalb immer auf Englisch/Deutsch, egal ob
Französisch, Spanisch o.a. eingestellt war.
Lösung: `language`-Parameter durch die gesamte LLM-Schicht gezogen:
- base.py: `lang_instruction()` helper + Signatur erweitert
- local_openai_compatible.py: Sprachanweisung ("Respond in Français.")
wird als letzter System-Part in den Message-Stack eingefügt
- openrouter.py: Explizite Sprachanweisung ergänzt den bestehenden
"Answer in the same language as the user"-Prompt
- fallback.py: FallbackLLMProvider leitet `language` durch
- orchestrator.py: alle 3 LLM-Aufrufstellen übergeben `language`
- Tests: alle Stub-LLMs um `language=None` ergänzt
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
81 lines
2.9 KiB
Python
81 lines
2.9 KiB
Python
from fastapi.testclient import TestClient
|
|
|
|
import app.dependencies as deps
|
|
from app.main import app
|
|
|
|
client = TestClient(app)
|
|
|
|
|
|
def _install_stubs(monkeypatch, captured):
|
|
class MemLLM:
|
|
async def complete(self, text, history=None, session_id=None, language=None):
|
|
captured["history"] = list(history or [])
|
|
return f"Antwort auf: {text}"
|
|
|
|
class StubTTS:
|
|
async def synthesize(self, text, voice=None, audio_format="pcm"):
|
|
return b"AUDIO"
|
|
|
|
monkeypatch.setitem(deps.LLM_REGISTRY, "mem", lambda s: MemLLM())
|
|
monkeypatch.setitem(deps.TTS_REGISTRY, "stub", lambda s: StubTTS())
|
|
return {"llm_provider": "mem", "tts_provider": "stub", "output_endpoint": "loopback"}
|
|
|
|
|
|
def test_history_accumulates_and_flows_to_llm(monkeypatch):
|
|
captured = {}
|
|
base = _install_stubs(monkeypatch, captured)
|
|
|
|
# Turn 1: noch kein Verlauf.
|
|
r1 = client.post("/api/chat?debug=true&session_id=conv1", json={"text": "Hallo", **base})
|
|
assert r1.status_code == 200
|
|
assert r1.json()["history_len"] == 0
|
|
assert captured["history"] == []
|
|
|
|
# Turn 2: Verlauf enthaelt User+Assistant aus Turn 1.
|
|
r2 = client.post("/api/chat?debug=true&session_id=conv1", json={"text": "Und weiter?", **base})
|
|
assert r2.status_code == 200
|
|
assert r2.json()["history_len"] == 2
|
|
assert captured["history"] == [
|
|
{"role": "user", "content": "Hallo"},
|
|
{"role": "assistant", "content": "Antwort auf: Hallo"},
|
|
]
|
|
|
|
|
|
def test_no_session_id_is_stateless(monkeypatch):
|
|
captured = {}
|
|
base = _install_stubs(monkeypatch, captured)
|
|
|
|
client.post("/api/chat?debug=true", json={"text": "A", **base})
|
|
client.post("/api/chat?debug=true", json={"text": "B", **base})
|
|
assert captured["history"] == [] # ohne session_id kein Gedaechtnis
|
|
|
|
|
|
def test_memories_injected_as_context(monkeypatch):
|
|
captured = {}
|
|
base = _install_stubs(monkeypatch, captured)
|
|
|
|
# Erinnerung fuer den (anonymen) Nutzer ablegen.
|
|
deps.get_store().ensure_anonymous_user()
|
|
deps.get_store().add_memory("anonymous", "heisst Anna")
|
|
|
|
# Ohne session_id -> kein Verlauf, aber Erinnerung wird trotzdem injiziert.
|
|
r = client.post("/api/chat?debug=true", json={"text": "Hallo", **base})
|
|
assert r.status_code == 200
|
|
assert r.json()["memories_len"] == 1
|
|
assert captured["history"][0]["role"] == "system"
|
|
assert "heisst Anna" in captured["history"][0]["content"]
|
|
|
|
|
|
def test_history_limited_by_setting(monkeypatch):
|
|
from app.config import settings
|
|
|
|
captured = {}
|
|
base = _install_stubs(monkeypatch, captured)
|
|
monkeypatch.setattr(settings, "history_max_messages", 2)
|
|
|
|
for text in ("eins", "zwei", "drei"):
|
|
client.post("/api/chat?debug=true&session_id=limit", json={"text": text, **base})
|
|
|
|
# Vor dem 3. Turn liegen 4 Nachrichten vor; geladen werden nur die letzten 2.
|
|
assert len(captured["history"]) == 2
|
|
assert captured["history"][-1] == {"role": "assistant", "content": "Antwort auf: zwei"}
|