init

services/llm.py

@@ -0,0 +1,75 @@
+from __future__ import annotations
+
+import logging
+from typing import Optional
+from collections import deque
+
+from config import settings
+
+logger = logging.getLogger(__name__)
+
+
+class LLMService:
+    def __init__(self) -> None:
+        self._ready = False
+        self._error: Optional[str] = None
+        self._client = None
+        self._model = (settings.llm_model or "").strip()
+        self._history: deque[dict] = deque(maxlen=12)  # 6 turns (user+assistant)
+        self._system_prompt = "请用中文口语化简短回复，1-2句。"
+
+        if not settings.llm_api_key:
+            return
+        if not self._model:
+            base = (settings.llm_base_url or "").lower()
+            self._model = "deepseek-chat" if "deepseek.com" in base else "gpt-4o-mini"
+        try:
+            from openai import AsyncOpenAI
+
+            self._client = AsyncOpenAI(
+                api_key=settings.llm_api_key,
+                base_url=settings.llm_base_url,
+                timeout=settings.llm_timeout,
+            )
+            self._ready = True
+        except Exception as exc:  # pragma: no cover
+            self._error = str(exc)
+            logger.warning("LLM online mode unavailable: %s", exc)
+
+    async def reply_with_meta(self, text: str) -> tuple[str, str]:
+        if not self._ready or self._client is None:
+            return f"收到：{text}。这是本地兜底回复。", "fallback"
+
+        try:
+            resp = await self._client.chat.completions.create(
+                model=self._model,
+                messages=[{"role": "system", "content": self._system_prompt}, *list(self._history), {"role": "user", "content": text}],
+                max_tokens=settings.llm_max_tokens,
+                temperature=0.7,
+            )
+            content = (resp.choices[0].message.content or "").strip()
+            if content:
+                self._history.append({"role": "user", "content": text})
+                self._history.append({"role": "assistant", "content": content})
+                return content, "online"
+        except Exception as exc:  # pragma: no cover
+            self._error = str(exc)
+            logger.warning("LLM request failed, fallback used: %s", exc)
+
+        return f"收到：{text}。这是本地兜底回复。", "fallback"
+
+    async def reply(self, text: str) -> str:
+        content, _ = await self.reply_with_meta(text)
+        return content
+
+    @property
+    def health(self) -> dict:
+        return {
+            "ready": self._ready,
+            "model": self._model,
+            "history_items": len(self._history),
+            "error": self._error,
+        }
+
+    def clear_history(self) -> None:
+        self._history.clear()