ai-kefu-jc/app/api/routes/chat_rest.py

"""REST shell for the HESU app (non-streaming, JSON-in/JSON-out).

These routes wrap `ConversationManager`, shared with the existing `/ws/chat`
widget path. The app uses HTTP because it lacks a WebSocket client and is fine
with a 3-8s "AI is typing" affordance covering the round trip.

Red lines (see spec):
- WS path (`app/api/routes/chat.py`) shares `ConversationManager` with these
  routes; both paths stay drift-free.
- `context` seeding is conditional + whitelist (handled in
  `ConversationManager.create_conversation`).
- The message route consumes `stream_process_message`; lead email is
  triggered inside `ConversationManager` when contact info is detected
  (contact-driven-lead-email plan).
"""
from fastapi import APIRouter, HTTPException, Request
from pydantic import BaseModel
from sqlalchemy import select

from app.main import async_session
from app.models.database import ConversationSource, ConversationStatus, Message
from app.services.conversation import ConversationManager
from app.services.rate_limit import check as rate_check

router = APIRouter(prefix="/api/chat", tags=["chat-rest"])


class SessionRequest(BaseModel):
    session_id: str | None = None
    context: dict | None = None
    client_info: dict | None = None


@router.post("/session")
async def chat_session(req: SessionRequest):
    """Resume an active conversation by session_id, or create a new app one.

    `context` flows into `create_conversation` where it is whitelisted into
    `raw_info` (only when non-None). `client_info` is stored for analytics only
    (ip/ua/device-id/lang) and never fed to the AI prompt.
    """
    async with async_session() as db:
        manager = ConversationManager(db)
        if req.session_id:
            conv = await manager.get_by_session(req.session_id)
            if conv and conv.status == ConversationStatus.active:
                return {
                    "session_id": conv.session_id,
                    "is_new": False,
                    "ended": False,
                }
        conv = await manager.create_conversation(
            source=ConversationSource.app,
            client_info=req.client_info,
            context=req.context,
        )
        return {
            "session_id": conv.session_id,
            "is_new": True,
            "ended": False,
        }


@router.get("/{session_id}/messages")
async def chat_history(session_id: str):
    """Public history endpoint for session replay. App-source only, to narrow
    the read surface; an unknown or non-app session yields 404.
    """
    async with async_session() as db:
        manager = ConversationManager(db)
        conv = await manager.get_by_session(session_id)
        if not conv or conv.source != ConversationSource.app:
            raise HTTPException(status_code=404, detail="session not found")
        result = await db.execute(
            select(Message)
            .where(Message.conversation_id == conv.id)
            .order_by(Message.created_at)
        )
        msgs = result.scalars().all()
        return [
            {
                "role": m.role.value,
                "content": m.content,
                "created_at": m.created_at.isoformat(),
            }
            for m in msgs
        ]


class MessageRequest(BaseModel):
    session_id: str
    content: str


@router.post("/message")
async def chat_message(req: MessageRequest, request: Request):
    """Process one app turn: stream-collect the AI reply, then evaluate.

    🔴 Consumes `stream_process_message` so the REST path shares one code
    path with the WS widget and never drifts. Lead email is triggered inside
    `ConversationManager` when contact info is detected
    (contact-driven-lead-email plan) — this route carries no email logic.

    A light in-memory rate limit (per ip + X-Device-Id, 30/h) guards GLM
    spend; only this route is throttled.
    """
    ip = request.client.host if request.client else ""
    dev = request.headers.get("X-Device-Id", "")
    if not rate_check(ip, dev):
        raise HTTPException(status_code=429, detail="rate limit exceeded")

    async with async_session() as db:
        manager = ConversationManager(db)
        conv = await manager.get_by_session(req.session_id)
        if not conv:
            raise HTTPException(status_code=404, detail="session not found")
        if conv.status != ConversationStatus.active:
            raise HTTPException(status_code=409, detail="conversation ended")

        reply_parts: list[str] = []
        ended = False
        intent_level = "pending"
        async for event in manager.stream_process_message(
            req.session_id, req.content
        ):
            t = event.get("type")
            if t == "stream_chunk":
                reply_parts.append(event.get("content", ""))
            elif t == "evaluated":
                ended = bool(event.get("ended"))
                intent_level = event.get("intent_level", "pending")
            elif t == "error":
                msg = event.get("message", "error")
                raise HTTPException(
                    status_code=409 if "ended" in msg else 404, detail=msg
                )

        return {
            "reply": "".join(reply_parts),
            "ended": ended,
            "intent_level": intent_level,
        }