interactive-story/backend/app/routers/chat.py

"""AI Chat: a plain scratchpad for talking to the configured model directly.

Deliberately thin. It adds no story context and no world state, and it persists
nothing. The conversation lives in the browser and is posted in full on each
turn. It exists for checking a model, a prompt, or an endpoint without starting
an adventure — which is exactly the kind of thing a local single-user install
wants a page for.

Upstream gated this behind a "power user" email allowlist and pinned the model
when a shared demo key was in play. M2 removed both: there is one local user,
who owns the endpoint, and there is no server-funded key to protect. The model
this page talks to is the one in Settings, or one the user names per request —
either way it is their own Ollama.
"""

from fastapi import APIRouter, Depends, HTTPException
from fastapi.responses import StreamingResponse
from sqlalchemy.orm import Session

from .. import auth, models, schemas
from ..database import get_db
from ..providers import OpenAICompatibleProvider, ProviderError
from ..sse import SSE_HEADERS, sse
from .settings import get_settings, list_endpoint_models

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


@router.get("/config")
async def chat_config(
    db: Session = Depends(get_db),
    user: models.User = Depends(auth.get_current_user),
):
    """Returns what this page can talk to.

    The model listing is best effort: an unreachable endpoint returns an empty
    list and the reason, rather than failing the page.
    """
    settings = get_settings(db, user)
    listing = await list_endpoint_models(settings.endpoint_url)
    return {
        "endpoint_url": settings.endpoint_url,
        "model": settings.model,
        "api_mode": settings.api_mode,
        "temperature": settings.temperature,
        "max_tokens": settings.max_output_tokens,
        # Suggestions from the endpoint, not a restriction.
        "models": listing.get("models", []),
        "models_error": None if listing.get("ok") else listing.get("detail"),
    }


async def run_chat(
    settings: models.Settings, model: str, payload: schemas.ChatRequest
):
    """Streams the reply as SSE, using the turn stream's event shape.

    The generator emits `reasoning` and `chunk` events while generating and then
    a `done` event, so the frontend reuses the same code.
    """
    provider = OpenAICompatibleProvider(
        settings.endpoint_url, model, settings.api_mode
    )
    messages = [m.model_dump() for m in payload.messages]
    chunks: list[str] = []
    reasoning_chunks: list[str] = []
    try:
        async for kind, chunk in provider.chat(
            messages,
            temperature=(
                payload.temperature
                if payload.temperature is not None
                else settings.temperature
            ),
            max_tokens=payload.max_tokens or settings.max_output_tokens,
        ):
            if kind == "reasoning":
                reasoning_chunks.append(chunk)
                yield sse({"type": "reasoning", "text": chunk})
            else:
                chunks.append(chunk)
                yield sse({"type": "chunk", "text": chunk})
    except ProviderError as exc:
        yield sse({"type": "error", "detail": str(exc)})
        return

    text = "".join(chunks).strip()
    if not text:
        detail = (
            "The model used its entire token budget on reasoning and returned no "
            "reply — raise max tokens or use a non-reasoning model."
            if reasoning_chunks
            else "The AI returned an empty response."
        )
        yield sse({"type": "error", "detail": detail})
        return

    yield sse({
        "type": "done",
        "text": text,
        "reasoning": "".join(reasoning_chunks).strip() or None,
        "model": model,
    })


@router.post("/stream")
def chat_stream(
    payload: schemas.ChatRequest,
    db: Session = Depends(get_db),
    user: models.User = Depends(auth.get_current_user),
):
    total = sum(len(m.content) for m in payload.messages)
    if total > schemas.CHAT_TOTAL_MAX:
        raise HTTPException(
            413, f"This conversation is too long to send ({total:,} characters) — "
                 "clear it or start a new one."
        )
    settings = get_settings(db, user)
    model = (payload.model or "").strip() or settings.model
    if not model:
        raise HTTPException(400, "No model configured — set one in Settings or pick one here.")
    return StreamingResponse(
        run_chat(settings, model, payload),
        media_type="text/event-stream",
        headers=SSE_HEADERS,
    )