resolutionflow/backend/app/services/assistant_chat_service.py

"""Standalone AI assistant chat service with RAG context.

Provides persistent conversation history for general IT questions
with semantic search over the team's flow library.
"""
import logging
from typing import Optional, Any
from uuid import UUID

from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession

from app.core.ai_provider import get_ai_provider
from app.models.assistant_chat import AssistantChat
from app.services.rag_service import search as rag_search, build_rag_context, extract_suggested_flows

logger = logging.getLogger(__name__)

ASSISTANT_SYSTEM_PROMPT = """You are a Senior Systems and Network Engineer with 15+ years of experience working in Managed Service Provider (MSP) environments. You specialize in:
- Windows Server, Active Directory, Group Policy, and Hybrid Identity (Entra ID)
- Networking (TCP/IP, DNS, DHCP, VPN, firewall troubleshooting, Cisco/Fortinet)
- Virtualization (VMware, Hyper-V) and cloud platforms (Azure, AWS, M365)
- Endpoint management, RMM tools, and PSA platforms (ConnectWise, Datto, Kaseya)
- PowerShell scripting and automation

When answering:
- Be direct and actionable — MSP engineers need fast, practical answers
- Include specific commands, paths, and config values when relevant
- Mention potential risks or gotchas before suggesting changes
- If a relevant troubleshooting flow exists in the team's library, reference it
- Keep responses concise but thorough — prefer bullet points and code blocks
- Format code with proper markdown code blocks
"""


def _auto_title(message: str) -> str:
    """Generate a short title from the first user message."""
    title = message.strip()[:100]
    if len(message) > 100:
        title = title.rsplit(" ", 1)[0] + "..."
    return title


async def create_chat(
    user_id: UUID,
    account_id: UUID,
    db: AsyncSession,
) -> AssistantChat:
    """Create a new empty chat."""
    chat = AssistantChat(
        user_id=user_id,
        account_id=account_id,
        messages=[],
    )
    db.add(chat)
    await db.flush()
    return chat


async def send_message(
    chat_id: UUID,
    user_id: UUID,
    account_id: UUID,
    message: str,
    db: AsyncSession,
) -> tuple[str, list[dict[str, Any]], AssistantChat]:
    """Send a user message and get AI response.

    Returns (ai_content, suggested_flows, chat).
    """
    result = await db.execute(
        select(AssistantChat).where(
            AssistantChat.id == chat_id,
            AssistantChat.user_id == user_id,
        )
    )
    chat = result.scalar_one_or_none()
    if not chat:
        raise ValueError("Chat not found")

    # Auto-title from first message
    if chat.message_count == 0:
        chat.title = _auto_title(message)

    # RAG search
    rag_results = await rag_search(
        query=message,
        account_id=account_id,
        db=db,
        limit=8,
    )

    # Build system prompt
    system_prompt = ASSISTANT_SYSTEM_PROMPT + build_rag_context(rag_results)

    # Build messages for AI
    ai_messages = []
    for msg in chat.messages:
        if msg["role"] in ("user", "assistant"):
            ai_messages.append({"role": msg["role"], "content": msg["content"]})
    ai_messages.append({"role": "user", "content": message})

    # Call AI
    provider = get_ai_provider()
    ai_content, input_tokens, output_tokens = await provider.generate_text(
        system_prompt=system_prompt,
        messages=ai_messages,
        max_tokens=4096,
    )

    # Update chat
    msgs = list(chat.messages)
    msgs.append({"role": "user", "content": message})
    msgs.append({"role": "assistant", "content": ai_content})
    chat.messages = msgs
    chat.message_count += 2
    chat.total_input_tokens += input_tokens
    chat.total_output_tokens += output_tokens

    suggested_flows = extract_suggested_flows(rag_results)

    return ai_content, suggested_flows, chat