"""``POST /agent/chat`` — the vertical slice.

One request exercises: JWT auth → quota reserve → LLM gateway (routing, prompt
version, cache-prefix check, daily budget) → ``ob_ai_call`` cost row → quota
commit/refund → unified envelope. Streaming (SSE, FR-AGT-01) is intentionally
out of scope for the scaffold.
"""

from __future__ import annotations

import uuid

from fastapi import APIRouter

from apps.api.deps import AgentServiceDep, CurrentUserId
from apps.api.schemas import ChatRequest, ChatResponse, ChatUsage
from packages.llm.errors import (
    AllProvidersFailedError,
    CachePrefixViolationError,
    DailyBudgetExceededError,
    StructuredOutputError,
)
from packages.shared.errors import AppError, ErrorCode
from packages.shared.response import ok

router = APIRouter(prefix="/agent", tags=["agent"])


@router.post("/chat", summary="Single-turn styling chat (non-streaming)")
async def chat(
    payload: ChatRequest,
    user_id: CurrentUserId,
    agent: AgentServiceDep,
) -> dict[str, object]:
    request_key = payload.request_key or uuid.uuid4().hex
    try:
        result = await agent.chat(user_id=user_id, message=payload.message, request_key=request_key)
    except DailyBudgetExceededError as exc:
        raise AppError(ErrorCode.LLM_DAILY_BUDGET_EXCEEDED) from exc
    except StructuredOutputError as exc:
        raise AppError(ErrorCode.LLM_STRUCTURED_OUTPUT_FAILED) from exc
    except AllProvidersFailedError as exc:
        raise AppError(ErrorCode.LLM_ALL_PROVIDERS_FAILED) from exc
    except CachePrefixViolationError as exc:
        raise AppError(ErrorCode.LLM_PROMPT_CACHE_VIOLATION) from exc

    return ok(
        ChatResponse(
            reply=result.reply,
            provider=result.provider,
            model=result.model,
            prompt_id=result.prompt_id,
            prompt_version=result.prompt_version,
            call_id=str(result.call_id),
            usage=ChatUsage(
                tokens_in=result.tokens_in,
                tokens_out=result.tokens_out,
                tokens_cached=result.tokens_cached,
                latency_ms=result.latency_ms,
                cost_cents=str(result.cost_cents),
            ),
            quota_remaining=result.quota_remaining,
        ).model_dump()
    )