feat(translate): 加星火 Spark(Lite)作为优先翻译引擎

- 新增 app/services/translation/spark.py: OpenAI 兼容协议客户端, URL = https://spark-api-open.xf-yun.com/v1/chat/completions, 鉴权 = Bearer <APIPassword>, model = lite(默认)/generalv3.5/4.0Ultra 可切换 - service.py 引擎链路调整为: spark → tencent(配额)→ maas → agnes → local。优先级降序: spark 配了 key 就用它,失败再走 tencent(继续吃配额,不绕过)。要完全绕开 tencent,把 TENCENTCLOUD_SECRET_ID 留空即可。 - 配置: 新增 SPARK_API_PASSWORD / SPARK_BASE_URL / SPARK_MODEL / SPARK_INTERVAL_SEC (留空 SPARK_API_PASSWORD = 走原 tencent 主链路,向后兼容) - 缓存白名单 / 配额计数逻辑保持原行为,只把 spark 加入允许缓存的引擎集合
2026-06-10 23:14:20 +08:00
parent 759eefabc3
commit b27643123e
4 changed files with 172 additions and 20 deletions
--- a/backend/app/services/translation/spark.py
+++ b/backend/app/services/translation/spark.py
@@ -0,0 +1,114 @@
+"""星火 Spark 翻译(OpenAI 兼容协议)。
+
+- 端点:https://spark-api-open.xf-yun.com/v1/chat/completions
+- 模型:lite(也支持 generalv3.5 等,但该项目用 Lite,免费额度)
+- 鉴权:Bearer token(APIPassword 直接当 Bearer 用)
+- 请求:POST /chat/completions,system prompt 告诉模型做翻译
+
+设计上独立于 LlmClient,专门走 spark_* 配置,避免和 LLM 智能增强共用 client 的节流。
+"""
+from __future__ import annotations
+
+import asyncio
+import logging
+import random
+
+import httpx
+
+from app.config import settings
+from app.services.translation.base import BaseTranslator, TranslationResult
+
+logger = logging.getLogger("news.translate.spark")
+
+
+# 经过实测,这套 prompt 在 Spark Lite 上输出稳定(不夹带 reasoning / 注释)。
+# Lite 不支持 system 角色(早期 Lite 模型),但 v1 OpenAI 兼容的 Lite 接受 system;
+# 保留 system prompt 走 4.0Ultra/Max/Pro 时也通用。
+_SYSTEM_PROMPT = """你是一个即时翻译助手。对于用户输入的英文或日文文章,请直接输出对应的简体中文译文。严格遵守:
+
+不要进行任何分步思考、不要输出分析、不要添加注释或说明。
+
+只输出中文译文本身,不包含任何额外文字(如"翻译结果:"、"以下是中文:"等)。
+
+如果输入内容既非英文也非日文,仅回复:"仅支持英文或日文翻译为中文。" """
+
+
+class SparkTranslator(BaseTranslator):
+    """星火 Spark 翻译(OpenAI 兼容协议,模型 lite / generalv3.5 等)。"""
+
+    name = "spark"
+
+    def __init__(self):
+        if not settings.spark_api_password:
+            raise RuntimeError("Spark APIPassword missing")
+        self.api_password = settings.spark_api_password
+        self.base_url = settings.spark_base_url.rstrip("/")
+        self.model = settings.spark_model
+        self.interval_sec = settings.spark_interval_sec
+
+    def is_configured(self) -> bool:
+        return bool(self.api_password)
+
+    async def translate(
+        self, text: str, source: str = "auto", target: str = "zh"
+    ) -> TranslationResult:
+        """翻译接口。source/target 当前固定 EN/JA → ZH(由 prompt 控制)。"""
+        if not text.strip():
+            return TranslationResult(text=text, engine=self.name, chars=0)
+
+        if not self.is_configured():
+            raise RuntimeError("Spark APIPassword missing")
+
+        system = _SYSTEM_PROMPT
+        user = text
+
+        url = f"{self.base_url}/chat/completions"
+        payload = {
+            "model": self.model,
+            "messages": [
+                {"role": "system", "content": system},
+                {"role": "user", "content": user},
+            ],
+            "temperature": 0.0,
+            "max_tokens": max(256, len(text) * 3),
+        }
+        headers = {
+            "Authorization": f"Bearer {self.api_password}",
+            "Content-Type": "application/json",
+        }
+
+        # 简单串行 + 重试 1 次
+        last_exc: Exception | None = None
+        for attempt in range(2):
+            try:
+                async with httpx.AsyncClient(timeout=60.0) as client:
+                    r = await client.post(url, json=payload, headers=headers)
+                if r.status_code >= 500:
+                    raise RuntimeError(f"Spark 5xx: {r.status_code} {r.text[:200]}")
+                if r.status_code != 200:
+                    raise RuntimeError(f"Spark {r.status_code}: {r.text[:300]}")
+                data = r.json()
+                # 错误响应:{"error": {...}}
+                if "error" in data:
+                    raise RuntimeError(f"Spark error: {data['error']}")
+                content = (
+                    data.get("choices", [{}])[0]
+                    .get("message", {})
+                    .get("content", "")
+                    .strip()
+                )
+                if not content:
+                    raise RuntimeError(f"Spark empty content: {r.text[:300]}")
+                await asyncio.sleep(self.interval_sec)
+                return TranslationResult(
+                    text=content, engine=self.name, chars=len(text), cached=False
+                )
+            except Exception as e:
+                last_exc = e
+                logger.warning("spark attempt %s failed: %s", attempt, e)
+                if attempt == 0:
+                    await asyncio.sleep(0.5 + random.random())
+                else:
+                    raise
+        assert last_exc is not None
+        raise last_exc