iAOP/core/llm-gateway/backends.py

# -*- coding: utf-8 -*-
"""推理后端实现 —— 本地 70B 模型接入与推理封装（issue #44）。

在 `gateway.InferenceBackend` 抽象之上交付**真实可用的本地后端**：
- OpenAI 兼容接口（vLLM / TGI 等本地推理服务，`/v1/chat/completions`），
  仅用标准库 urllib，无第三方依赖；
- 参数化：endpoint / model / timeout / max_tokens / temperature / context 引用注入；
- **数据不出厂**（PRD 5.4）：敏感/核心内容走本地后端，云端仅接收脱敏内容；
- 未配置 endpoint 时进入 dry-run 占位模式（保持与旧 LocalBackend 一致的
  可测试行为，供端到端演示与联调）。

业务代码只依赖 `gateway.InferenceBackend.generate(prompt, context)`，
切换后端 = 换实现（见 `LLMGateway(local=...)`）。
"""
from __future__ import annotations

import json
import os
import time
import urllib.request
from typing import Callable, Optional, Sequence

from .gateway import InferenceBackend


class Local70BBackend(InferenceBackend):
    """本地 70B 推理后端（OpenAI 兼容 vLLM/TGI，参数化）。"""

    name = "local-70b"

    def __init__(
        self,
        endpoint: str = "",
        model: str = "iaop-local-70b",
        timeout_seconds: float = 60.0,
        max_tokens: int = 1024,
        temperature: float = 0.1,
        echo_context: bool = True,
    ) -> None:
        self.endpoint = (endpoint or "").rstrip("/")
        self.model = model
        self.timeout = float(timeout_seconds)
        self.max_tokens = int(max_tokens)
        self.temperature = float(temperature)
        self.echo_context = echo_context

    # ------------------------------------------------------------------
    def generate(self, prompt: str, context: Sequence[str]) -> str:
        """根据 prompt 与 RAG 上下文生成回答。

        - 未配置 endpoint：dry-run 占位（回显 prompt 前 40 字符 + 来源引用）；
        - 已配置：调用本地 OpenAI 兼容服务（/v1/chat/completions）。
        """
        if not self.endpoint:
            return self._dry_run(prompt, context)

        payload = {
            "model": self.model,
            "messages": [
                {"role": "system", "content": self._system_prompt(context)},
                {"role": "user", "content": prompt},
            ],
            "max_tokens": self.max_tokens,
            "temperature": self.temperature,
        }
        body = self._post_json("/v1/chat/completions", payload)
        try:
            return body["choices"][0]["message"]["content"]
        except (KeyError, IndexError, TypeError):
            raise RuntimeError(
                f"本地推理服务响应格式异常: {str(body)[:200]}")

    # ------------------------------------------------------------------
    def _system_prompt(self, context: Sequence[str]) -> str:
        """把 RAG 引用注入 system 提示（引用溯源，PRD 5.4）。"""
        refs = "\n".join(f"- {c}" for c in (context or []))
        base = "你是工业 AI 助手。回答须基于给定资料并标注来源。"
        return f"{base}\n参考资料：\n{refs}" if refs else base

    def _dry_run(self, prompt: str, context: Sequence[str]) -> str:
        head = f"[本地70B占位] {prompt[:40]}"
        if self.echo_context:
            for i, src in enumerate(context[:3], 1):
                head += f"\n[来源: {src}]"
        return head

    def _post_json(self, path: str, payload: dict) -> dict:
        """向后端推理服务发起 JSON POST（标准库 urllib）。"""
        url = self.endpoint + path
        data = json.dumps(payload).encode("utf-8")
        req = urllib.request.Request(
            url, data=data,
            headers={"Content-Type": "application/json"})
        with urllib.request.urlopen(req, timeout=self.timeout) as resp:
            raw = resp.read().decode("utf-8")
        return json.loads(raw) if raw else {}

    def health(self) -> dict:
        """后端健康信息（本地推理服务可探测 /health）。"""
        base = {
            "backend": self.name, "model": self.model,
            "endpoint": self.endpoint or "(dry-run)",
        }
        if not self.endpoint:
            base["status"] = "dry-run"
            return base
        try:
            started = time.monotonic()
            with urllib.request.urlopen(
                    self.endpoint + "/health", timeout=self.timeout) as resp:
                base["status"] = "ok" if resp.status == 200 else f"http-{resp.status}"
            base["latency_ms"] = round((time.monotonic() - started) * 1000, 2)
        except Exception as exc:  # noqa: BLE001 - 健康探测失败仅记录
            base["status"] = f"error: {exc}"
        return base


class CloudApiBackend(InferenceBackend):
    """云端 API 推理后端（Qwen / DeepSeek 等 OpenAI 兼容）—— issue #45。

    **安全网关约束（PRD 5.4）**：
    - 仅接收 **DLP 放行**的脱敏/通用内容（上游 `LLMGateway` 主编排出站检查 +
      cloud 分支输出 DLP 复查）；
    - API Key 从**环境变量**读取（`api_key_env`），不硬编码、不落日志；
    - 可选 `safety_checker` 出站复查钩子（fail-closed：复查拒绝 → 拦截占位，
      不调用上游）。
    """

    name = "cloud-api"

    def __init__(
        self,
        endpoint: str = "",
        api_key_env: str = "",
        model: str = "deepseek-chat",
        timeout_seconds: float = 60.0,
        max_tokens: int = 1024,
        temperature: float = 0.1,
        safety_checker: Optional[Callable[[str], bool]] = None,
    ) -> None:
        self.endpoint = (endpoint or "").rstrip("/")
        self.api_key_env = api_key_env
        self.model = model
        self.timeout = float(timeout_seconds)
        self.max_tokens = int(max_tokens)
        self.temperature = float(temperature)
        # 出站安全复查：返回 False 即拦截（fail-closed）
        self.safety_checker = safety_checker
        self._api_key = os.environ.get(api_key_env, "") if api_key_env else ""

    # ------------------------------------------------------------------
    def generate(self, prompt: str, context: Sequence[str]) -> str:
        """生成回答。安全网关：safety_checker 拒绝 → 拦截占位，不调用上游。"""
        if self.safety_checker is not None and not self.safety_checker(prompt):
            return "[云端安全网关拦截] 出站复查未通过，已拦截（数据不出厂）。"

        if not self.endpoint:
            return self._dry_run(prompt, context)

        payload = {
            "model": self.model,
            "messages": [
                {"role": "system", "content": self._system_prompt(context)},
                {"role": "user", "content": prompt},
            ],
            "max_tokens": self.max_tokens,
            "temperature": self.temperature,
        }
        body = self._post_json("/v1/chat/completions", payload)
        try:
            return body["choices"][0]["message"]["content"]
        except (KeyError, IndexError, TypeError):
            raise RuntimeError(
                f"云端 API 响应格式异常: {str(body)[:200]}")

    # ------------------------------------------------------------------
    def _system_prompt(self, context: Sequence[str]) -> str:
        refs = "\n".join(f"- {c}" for c in (context or []))
        base = "你是工业 AI 助手。回答须基于给定资料并标注来源。"
        return f"{base}\n参考资料：\n{refs}" if refs else base

    def _dry_run(self, prompt: str, context: Sequence[str]) -> str:
        head = f"[云端API占位] {prompt[:40]}"
        for i, src in enumerate(context[:3], 1):
            head += f"\n[来源: {src}]"
        if self.safety_checker is not None:
            head += "\n[安全网关: 已复查放行]"
        return head

    def _post_json(self, path: str, payload: dict) -> dict:
        """向后端推理服务发起 JSON POST（Bearer 认证，Key 来自环境变量）。"""
        url = self.endpoint + path
        data = json.dumps(payload).encode("utf-8")
        headers = {"Content-Type": "application/json"}
        if self._api_key:
            headers["Authorization"] = f"Bearer {self._api_key}"
        req = urllib.request.Request(url, data=data, headers=headers)
        with urllib.request.urlopen(req, timeout=self.timeout) as resp:
            raw = resp.read().decode("utf-8")
        return json.loads(raw) if raw else {}

    def health(self) -> dict:
        """后端健康信息（含安全网关状态，不含密钥）。"""
        return {
            "backend": self.name, "model": self.model,
            "endpoint": self.endpoint or "(dry-run)",
            "api_key_configured": bool(self._api_key),
            "safety_checker": self.safety_checker is not None,
            "status": "dry-run" if not self.endpoint else "configured",
        }