Files
interactive-story/backend/app/main.py
T
parththakkar106andClaude Opus 5 1dd31086c1 Add power-user AI Chat page; centralize demo-key model pinning
AI Chat is a plain scratchpad for talking to a model directly — no story
context, scripts or world state — for poking at models, prompts and endpoints
without starting an adventure. Power users only: the router 404s (rather than
403s) for everyone else and the nav link is hidden. The conversation lives in
localStorage, so there's no new table or migration.

is_power_user() now also returns True in local mode: it's the operator's own
machine and their own key, the same reasoning that makes the provider debug log
local-only.

Alongside that, the rule keeping the shared demo key off paid models now lives
in exactly one place. It had been duplicated into the chat router, which is how
one copy eventually drifts:

- resolve_provider_config() takes an optional model_override and is the only
  place the whitelist is applied, so turns, AI Chat and the connection test all
  inherit it. An override is a per-request preference, never a grant.
- ProviderConfig.__post_init__ refuses to exist when api_key is the demo key
  and the model isn't whitelisted. It keys on the key itself rather than the
  using_demo flag, so a mislabelled config can't slip past, and it raises so a
  future path that bypasses the resolver fails loudly instead of billing.
- The demo branch still pins endpoint_url too — a user-controlled endpoint
  would leak the key itself, which is worse than spending it.

Provider gained chat(messages, ...) beside generate(), both delegating to a
shared _stream(url, body); completion-mode endpoints get the messages flattened
into a labelled transcript. Settings' /models fetch moved to
list_endpoint_models() and is shared with /api/chat/config.

Tests: 10 new in tests/test_chat.py (70 total). These deliberately do not stub
resolve_provider_config — the point is to exercise the real BYOK-vs-demo
decision and assert on what the provider actually received: off-whitelist
override pinned, off-whitelist Settings.model pinned, redirected endpoint
pinned, BYOK passed through untouched.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FGY1yvzSeKgTtRfeVtDmx
2026-07-26 20:16:56 +05:30

120 lines
3.8 KiB
Python

import os
from pathlib import Path
from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from fastapi.staticfiles import StaticFiles
from starlette.exceptions import HTTPException as StarletteHTTPException
from .auth import MULTI_USER
from .database import engine
from .limits import BodySizeLimitMiddleware
from .migrations import bootstrap
from .routers import adventures, auth, chat, debug, scenarios, scripts, settings, story_cards
from .seed import seed_public_scenarios
bootstrap(engine)
seed_public_scenarios(engine)
# Production serves the SPA same-origin, so CORS only matters for the Vite dev
# server; AIDND_CORS_ORIGINS overrides for any other cross-origin setup.
CORS_ORIGINS = [
o.strip()
for o in os.environ.get("AIDND_CORS_ORIGINS", "").split(",")
if o.strip()
] or ["http://localhost:5173", "http://127.0.0.1:5173"]
# The interactive API docs stay local-only: in multi-user mode they just hand
# strangers a map of the API surface.
app = FastAPI(
title="AI D&D",
docs_url=None if MULTI_USER else "/docs",
redoc_url=None,
openapi_url=None if MULTI_USER else "/openapi.json",
)
app.add_middleware(
CORSMiddleware,
allow_origins=CORS_ORIGINS,
allow_methods=["*"],
allow_headers=["*"],
)
app.add_middleware(BodySizeLimitMiddleware)
class SecurityHeadersMiddleware:
"""Standard hardening headers on every response. Pure ASGI (wraps `send`)
so SSE streams pass through unbuffered. The CSP allows exactly what the
SPA uses: same-origin everything, inline styles (React), Google Fonts."""
_HEADERS = [
(b"x-content-type-options", b"nosniff"),
(b"referrer-policy", b"same-origin"),
(b"x-frame-options", b"DENY"),
(
b"content-security-policy",
b"default-src 'self'; "
b"script-src 'self'; "
b"style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; "
b"font-src https://fonts.gstatic.com; "
b"img-src 'self' data:; "
b"connect-src 'self'; "
b"frame-ancestors 'none'",
),
]
def __init__(self, app):
self.app = app
async def __call__(self, scope, receive, send):
if scope["type"] != "http":
return await self.app(scope, receive, send)
async def send_with_headers(message):
if message["type"] == "http.response.start":
message.setdefault("headers", [])
message["headers"] = list(message["headers"]) + self._HEADERS
await send(message)
await self.app(scope, receive, send_with_headers)
app.add_middleware(SecurityHeadersMiddleware)
app.include_router(auth.router)
app.include_router(scenarios.router)
app.include_router(adventures.router)
app.include_router(story_cards.router)
app.include_router(scripts.router)
app.include_router(settings.router)
app.include_router(chat.router)
app.include_router(debug.router)
@app.get("/api/health")
def health():
return {"ok": True}
# In production, serve the built frontend (frontend/dist) as static files.
class SPAStaticFiles(StaticFiles):
"""Serve index.html for unknown paths so client-side routes (/play/3)
survive a page reload. API routes are matched before this mount."""
async def get_response(self, path, scope):
try:
response = await super().get_response(path, scope)
except StarletteHTTPException as exc:
if exc.status_code != 404:
raise
return await super().get_response("index.html", scope)
if response.status_code == 404:
return await super().get_response("index.html", scope)
return response
frontend_dist = Path(__file__).resolve().parent.parent.parent / "frontend" / "dist"
if frontend_dist.is_dir():
app.mount("/", SPAStaticFiles(directory=frontend_dist, html=True), name="frontend")