ewoooc/services/deepseek_service.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
services/deepseek_service.py
Operation Ollama-First v5.0 / Phase 15 — DeepSeek API 直連備援

設計原則（ADR-030 多供應商策略）：
- DeepSeek API 直連 (api.deepseek.com)，OpenAI-compatible interface
- 取代部分 OpenRouter 路徑（直連 ~30-50% 便宜 + 延遲低）
- 主要備援場景：PPT NIM deepseek-v3.2 失敗時 / Code Review 第三供應商
- feature flag DEEPSEEK_DIRECT_ENABLED 預設 OFF
- 失敗自動 fallback 到 OpenRouter（向下相容）

模型 (2026-05)：
- deepseek-chat (V3.2)         $0.014/$0.28 per M tokens — 通用
- deepseek-reasoner (R1-0528)  $0.14/$2.19 per M tokens — 推理增強
"""

from __future__ import annotations
import os
import time
import logging
from dataclasses import dataclass
from typing import Optional, Dict, Any

import requests

logger = logging.getLogger(__name__)

DEEPSEEK_API_KEY = os.getenv('DEEPSEEK_API_KEY', '')
DEEPSEEK_BASE_URL = os.getenv('DEEPSEEK_BASE_URL', 'https://api.deepseek.com/v1')
DEEPSEEK_DEFAULT_MODEL = os.getenv('DEEPSEEK_MODEL', 'deepseek-chat')
DEEPSEEK_TIMEOUT = int(os.getenv('DEEPSEEK_TIMEOUT', '60'))


def is_deepseek_direct_enabled() -> bool:
    """Runtime check（避免 import-time freeze）"""
    return os.getenv('DEEPSEEK_DIRECT_ENABLED', 'false').strip().lower() in ('true', '1', 'yes', 'on')


@dataclass
class DeepSeekResponse:
    success: bool
    content: str
    model: str
    input_tokens: int = 0
    output_tokens: int = 0
    duration_ms: int = 0
    error: Optional[str] = None


class DeepSeekService:
    """DeepSeek API 直連 — OpenAI-compatible chat completions."""

    def __init__(self, model: str = DEEPSEEK_DEFAULT_MODEL):
        self.model = model

    def is_available(self) -> bool:
        """key 已設且 flag ON"""
        return bool(DEEPSEEK_API_KEY) and is_deepseek_direct_enabled()

    def generate(
        self,
        prompt: str,
        system_prompt: Optional[str] = None,
        max_tokens: int = 4096,
        temperature: float = 0.4,
    ) -> DeepSeekResponse:
        """
        直連 api.deepseek.com/v1/chat/completions
        失敗安全：API key 缺 / flag OFF → 回 success=False 讓 caller fallback。
        """
        start = time.monotonic()

        if not self.is_available():
            return DeepSeekResponse(
                success=False, content='', model=self.model,
                error='DEEPSEEK_DIRECT_ENABLED=false or DEEPSEEK_API_KEY 未設',
            )

        messages = []
        if system_prompt:
            messages.append({'role': 'system', 'content': system_prompt})
        messages.append({'role': 'user', 'content': prompt})

        try:
            resp = requests.post(
                f"{DEEPSEEK_BASE_URL}/chat/completions",
                headers={
                    'Authorization': f'Bearer {DEEPSEEK_API_KEY}',
                    'Content-Type': 'application/json',
                },
                json={
                    'model': self.model,
                    'messages': messages,
                    'max_tokens': max_tokens,
                    'temperature': temperature,
                    'stream': False,
                },
                timeout=DEEPSEEK_TIMEOUT,
            )
            duration_ms = int((time.monotonic() - start) * 1000)

            if resp.status_code != 200:
                return DeepSeekResponse(
                    success=False, content='', model=self.model,
                    duration_ms=duration_ms,
                    error=f'HTTP {resp.status_code}: {resp.text[:200]}',
                )

            data = resp.json()
            choices = data.get('choices', [])
            content = ''
            if choices:
                msg = choices[0].get('message', {})
                content = msg.get('content', '') or ''

            usage = data.get('usage', {}) or {}
            return DeepSeekResponse(
                success=True,
                content=content,
                model=data.get('model', self.model),
                input_tokens=int(usage.get('prompt_tokens', 0) or 0),
                output_tokens=int(usage.get('completion_tokens', 0) or 0),
                duration_ms=duration_ms,
            )

        except requests.Timeout:
            duration_ms = int((time.monotonic() - start) * 1000)
            return DeepSeekResponse(
                success=False, content='', model=self.model,
                duration_ms=duration_ms, error=f'timeout ({DEEPSEEK_TIMEOUT}s)',
            )
        except Exception as e:
            duration_ms = int((time.monotonic() - start) * 1000)
            return DeepSeekResponse(
                success=False, content='', model=self.model,
                duration_ms=duration_ms,
                error=f'{type(e).__name__}: {str(e)[:200]}',
            )

    def check_connection(self) -> bool:
        """輕量檢查：發極短 message 看是否回應"""
        if not self.is_available():
            return False
        try:
            r = self.generate('ping', max_tokens=10, temperature=0)
            return r.success
        except Exception:
            return False


# 全域單例
deepseek_service = DeepSeekService()


__all__ = [
    'DeepSeekService',
    'DeepSeekResponse',
    'deepseek_service',
    'is_deepseek_direct_enabled',
]