ai-kefu-admin/app/engine/services/ai_service.py

import json
import logging
from collections.abc import AsyncGenerator
from dataclasses import dataclass
from pathlib import Path

from app.engine.providers.base import AIProvider
from app.engine.providers.glm import GLMProvider
from app.engine.services.boundary_filter import DEFAULT_WALL
from app.engine.wall_schema import CompiledWall
# Task 10: AI 参数 resolver 收拢至 config_views(单一定义点)
from app.platform.config_views import resolve_ai_settings

logger = logging.getLogger(__name__)


def _format_messages(messages: list[dict]) -> str:
    lines = []
    for m in messages:
        role = m.get("role", "unknown")
        content = m.get("content", "")
        label = {"user": "客户", "assistant": "顾问"}.get(role, role)
        lines.append(f"{label}: {content}")
    return "\n".join(lines)


# 话术池注入的语言行序(确定性输出;未列语言按字典序补位,不丢池)
_DEFLECTION_LANG_ORDER = ("en", "zh", "es")


def _format_deflection_pool(deflections) -> str:
    """wall.json deflections 池 → system.md $DEFLECTION_POOL 注入块。

    按语言分组一行("- EN: …" / "- ZH: …"),条目引号包裹 " / " 分隔——
    紧凑不膨胀(设计 R1: 话术单一事实源,提示词侧只引用不复制)。
    只渲染主池(deflections);deflections_contact 是已留资态的墙替换池,
    本就不属于 system.md 教学内容,不注入。
    已知边界(审查 Minor-1 注记): 条目自身含双引号/换行时暂不转义——
    现网池线均为单行纯文本,Phase 2 后台编辑器批次统一处理(输入校验+转义)。
    """
    pools = dict(deflections or {})
    langs = [l for l in _DEFLECTION_LANG_ORDER if pools.get(l)]
    langs += sorted(l for l in pools
                    if l not in _DEFLECTION_LANG_ORDER and pools.get(l))
    return "\n".join(
        f"- {lang.upper()}: " + " / ".join(f'"{line}"' for line in pools[lang])
        for lang in langs
    )


# 四件套键名(单一事实源): PromptProvider 构造校验 / FileTenantSource 读盘
# / DbTenantSource 快照组形态, 三处消费同一清单
PROMPTS_KEYS = ("system", "company_facts", "extractor", "evaluator")


@dataclass(frozen=True)
class PromptProvider:
    """租户提示词四件套持有者(Task 6, R1 话术单一事实源)。

    frozen(Task 9 收口, Task 6 审查遗留): 实例跨租户运行时/模块级
    DEFAULT_PROVIDER 共享, 不可变防共享单例被毒化。

    - from_dir(dir): 读 system/company_facts/extractor/evaluator 四个 md
      委托 from_config——提示词属于租户(seed_profiles/<slug>/prompts/),
      不再有代码级 app/engine/prompts 副本;
    - from_config(md: dict)(Phase 2 Task 4): 快照 prompts 组(dict 四键)
      直接构造——registry 对文件/DB 两源的统一入口(文件源读盘入快照,
      DB 源嵌 config_json);缺键/值非字符串 → 显性 ValueError 带键名;
    - build_system(wall_deflections): system.md 的 $DEFLECTION_POOL 占位符
      替换为按语言枚举的话术清单 + "\\n\\n" + company_facts(行为 prompt
      在前、事实卡居中、当轮提醒最后拼接——拼接位在 AIService 内);
    - build_extractor/build_evaluator: $existing_info/$messages/$profile/
      $recent_messages 替换逻辑自 AIService 原样搬入(行为等价)。
    """
    system: str
    company_facts: str
    extractor: str
    evaluator: str

    @classmethod
    def from_config(cls, md: dict) -> "PromptProvider":
        """快照 prompts 组 → PromptProvider。缺键/非字符串显性炸带键名
        (DB 快照坏数据不留到 build_system 才炸)。"""
        if not isinstance(md, dict):
            # 入口类型守卫(Task 6 的 PUT prompts 会接请求体): 字符串/
            # 列表进来给 ValueError,不让 .get 的 AttributeError 漏成 500
            raise ValueError(
                f"prompts 必须是 dict: {{{', '.join(PROMPTS_KEYS)}}}: "
                f"实际 {type(md).__name__}")
        bad = [k for k in PROMPTS_KEYS if not isinstance(md.get(k), str)]
        if bad:
            raise ValueError(f"prompts 配置缺少(或非字符串)键: {', '.join(bad)}")
        return cls(
            system=md["system"],
            company_facts=md["company_facts"],
            extractor=md["extractor"],
            evaluator=md["evaluator"])

    @classmethod
    def from_dir(cls, prompts_dir) -> "PromptProvider":
        d = Path(prompts_dir)
        return cls.from_config({
            "system": (d / "system.md").read_text(encoding="utf-8"),
            "company_facts": (d / "company_facts.md").read_text(encoding="utf-8"),
            "extractor": (d / "extractor.md").read_text(encoding="utf-8"),
            "evaluator": (d / "evaluator.md").read_text(encoding="utf-8"),
        })

    def build_system(self, wall_deflections=None) -> str:
        system = self.system
        if "$DEFLECTION_POOL" in system:
            system = system.replace(
                "$DEFLECTION_POOL", _format_deflection_pool(wall_deflections))
        return system + "\n\n" + self.company_facts

    def build_extractor(self, existing_info: dict, messages: list[dict]) -> str:
        return self.extractor.replace(
            "$existing_info", json.dumps(existing_info or {}, ensure_ascii=False)
        ).replace("$messages", _format_messages(messages))

    def build_evaluator(self, profile: dict, recent_messages: list[dict]) -> str:
        return self.evaluator.replace(
            "$profile", json.dumps(profile, ensure_ascii=False)
        ).replace("$recent_messages",
                  _format_messages(recent_messages[-6:]))


# 代码级默认 = jiancai 出厂(路径锚定模块位置,与 cwd 无关): 旧测试与
# 无租户上下文的默认路径用;租户路径一律经 TenantRuntime.prompts 注入。
DEFAULT_PROVIDER = PromptProvider.from_dir(
    Path(__file__).resolve().parents[3] / "seed_profiles" / "jiancai" / "prompts")


def create_provider(config_data: dict | None = None) -> AIProvider:
    """provider 工厂(Task 9: 按租户配置实例化 glm;None 走 env 平台默认)。"""
    cfg = resolve_ai_settings(config_data)
    if cfg["provider"] == "glm":
        return GLMProvider(
            api_key=cfg["api_key"],
            model=cfg["model"],
            base_url=cfg["base_url"],
        )
    raise ValueError(f"Unknown AI provider: {cfg['provider']}")


class AIService:
    def __init__(self, provider: AIProvider | None = None,
                 prompts: PromptProvider | None = None,
                 wall: CompiledWall | None = None,
                 config_data: dict | None = None):
        self.provider = provider or create_provider(config_data)
        # Task 6: 提示词经 PromptProvider 注入(租户四件套);默认 = jiancai
        # 出厂 + 出厂墙话术池(与 DEFAULT_PROVIDER 同源,单一事实源 wall.json)
        self.prompts = prompts or DEFAULT_PROVIDER
        # Task 9 收口: wall 参数定型为 CompiledWall(话术池只取 .deflections,
        # 与 prompts 同为租户运行时产物);缺省 = jiancai 出厂墙
        self.wall_deflections = (wall.deflections if wall is not None
                                 else DEFAULT_WALL.deflections)
        # 对话基座: 行为 prompt 在前(红线显著性),事实卡居中(参考资料),
        # 当轮 context 提醒最后拼接(在 chat/stream_chat 内,保持最新鲜)
        self._base_chat_prompt = self.prompts.build_system(self.wall_deflections)

    async def chat(self, messages: list[dict], context: str = "") -> str:
        """Main conversation: get AI reply to user message."""
        prompt = self._base_chat_prompt + ("\n\n" + context if context else "")
        return await self.provider.chat(messages, prompt)

    async def stream_chat(self, messages: list[dict], context: str = "") -> AsyncGenerator[str, None]:
        """Stream AI reply token by token."""
        prompt = self._base_chat_prompt + ("\n\n" + context if context else "")
        async for token in self.provider.stream_chat(messages, prompt):
            yield token

    async def extract_info(
        self, messages: list[dict], existing_info: dict
    ) -> dict:
        """Extract structured info from conversation history."""
        prompt = self.prompts.build_extractor(existing_info, messages)
        _, extracted = await self.provider.chat_with_extraction(
            messages=[], system_prompt=prompt
        )
        return extracted

    async def evaluate(
        self, profile: dict, recent_messages: list[dict]
    ) -> dict:
        """Evaluate customer intent level."""
        prompt = self.prompts.build_evaluator(profile, recent_messages)
        _, result = await self.provider.chat_with_extraction(
            messages=[], system_prompt=prompt
        )
        return self._normalize_evaluation(result)

    @staticmethod
    def _normalize_evaluation(result: dict) -> dict:
        intent = result.get("intent_level", "pending")
        if intent not in ("interested", "not_interested", "pending"):
            intent = "pending"
        return {
            "intent_level": intent,
            "reasoning": result.get("reasoning", ""),
            "contact_info": result.get("contact_info", {}),
            "info_sufficient": result.get("info_sufficient", False),
        }