7456525d19
Four pieces of work.
**Installable.** A manifest carrying the instance name, PWA icons rasterised
from the existing mark at design time, a service worker and a themed offline
page. The worker caches the shell only and bails out on /api/, /auth/, /admin/
and anything accepting text/event-stream -- passing a reply stream through a
worker turns it into one delivery at the end, or nothing. It is served from
GET /sw.js rather than the static mount because a worker's scope is the path it
came from.
**Send and Stop are one button.** They were two, and the hidden one was never
hidden: `.btn` is display: inline-flex, which outranks the browser's own
`[hidden] { display: none }`, so Stop sat permanently beside Send. app.css now
forces the attribute to win -- every control toggled with `hidden` depended on
that -- and the composer renders one button carrying both icons, with ui.js
flipping data-composer-action and the type with it.
**Audio.** Speech to text and text to speech against any OpenAI-shaped
/v1/audio/* endpoint: dictate into the composer, have a reply read out.
Instance settings in Admin, per-reader overrides in Settings, with the voice
list discovered from the server where it offers one. Recorded audio is capped
and never written to disk -- it is not an attachment, it has no owner, and
nothing would ever sweep it.
**Web search, as a tool.** This is the tool loop PLAN.md described as the real
work: one reply is now a bounded sequence of requests rather than one. The model
asks, the tool runs, the result goes back and it is asked again, up to three
rounds. Providers are DuckDuckGo (no setup), SearXNG and Firecrawl.
Two decisions worth stating. Tools are only offered to models flagged `tools`,
because an endpoint without support rejects the whole request rather than
ignoring the array -- the same reason images only reach models flagged
`vision`. And tool results are not replayed as context on the next turn, for the
same reasons reasoning is not: the answer already contains what the model made
of them, and replaying stale results into every later request wastes the window
and reliably sends a small model into a search loop. The sources stay visible in
the transcript instead.
Search results are untrusted third-party text and are treated as such: escaped,
and only http/https URLs rendered as links.
338 tests, ruff clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
165 lines
5.6 KiB
Python
165 lines
5.6 KiB
Python
"""Application factory, lifespan and error handling."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from collections.abc import AsyncIterator
|
|
from contextlib import asynccontextmanager
|
|
|
|
from fastapi import FastAPI, Request, status
|
|
from fastapi.responses import JSONResponse, Response
|
|
from fastapi.staticfiles import StaticFiles
|
|
from starlette.exceptions import HTTPException as StarletteHTTPException
|
|
|
|
from lembas import __version__
|
|
from lembas.api import (
|
|
admin,
|
|
admin_audio,
|
|
admin_models,
|
|
admin_search,
|
|
admin_users,
|
|
audio,
|
|
auth,
|
|
chats,
|
|
files,
|
|
folders,
|
|
pages,
|
|
preferences,
|
|
)
|
|
from lembas.api.deps import RedirectToLogin, is_htmx, login_redirect
|
|
from lembas.config import settings
|
|
from lembas.db.session import init_db
|
|
from lembas.web.templating import STATIC_DIR, render
|
|
|
|
log = logging.getLogger("lembas")
|
|
|
|
|
|
def configure_logging() -> None:
|
|
logging.basicConfig(
|
|
level=settings.log_level.upper(),
|
|
format="%(asctime)s %(levelname)-7s %(name)s: %(message)s",
|
|
datefmt="%H:%M:%S",
|
|
)
|
|
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI) -> AsyncIterator[None]:
|
|
configure_logging()
|
|
settings.ensure_dirs()
|
|
init_db()
|
|
|
|
if settings.secret_key_is_ephemeral:
|
|
log.warning(
|
|
"No LEMBAS_SECRET_KEY set, so a temporary one was generated. Every "
|
|
"restart will sign all users out and make stored API keys "
|
|
"unreadable. Generate a permanent key with:\n"
|
|
' python -c "import secrets; print(secrets.token_urlsafe(48))"'
|
|
)
|
|
|
|
# Files chosen in a composer that was never sent would otherwise sit on
|
|
# disk forever. Cheap, and startup is the natural moment for it.
|
|
try:
|
|
from lembas.db.session import session_scope
|
|
from lembas.services.files import sweep_orphans
|
|
|
|
with session_scope() as db:
|
|
sweep_orphans(db)
|
|
except Exception: # noqa: BLE001 - housekeeping must never block startup
|
|
log.exception("orphaned upload sweep failed")
|
|
|
|
log.info("LLeMbas %s starting on http://%s:%s", __version__, settings.host, settings.port)
|
|
log.info("data directory: %s", settings.data_dir.resolve())
|
|
yield
|
|
|
|
# Replies still being written are cancelled and persisted with whatever
|
|
# they have, rather than left as permanently unfinished rows.
|
|
from lembas.services.generation import shutdown as stop_generations
|
|
|
|
await stop_generations()
|
|
log.info("LLeMbas stopped")
|
|
|
|
|
|
def create_app() -> FastAPI:
|
|
app = FastAPI(
|
|
title="LLeMbas",
|
|
version=__version__,
|
|
lifespan=lifespan,
|
|
# The API is an implementation detail of the UI, not a product surface.
|
|
docs_url="/api/docs" if settings.log_level == "debug" else None,
|
|
redoc_url=None,
|
|
)
|
|
|
|
app.mount("/static", StaticFiles(directory=str(STATIC_DIR)), name="static")
|
|
|
|
app.include_router(pages.router)
|
|
app.include_router(auth.router)
|
|
app.include_router(preferences.router)
|
|
app.include_router(chats.router)
|
|
app.include_router(audio.router)
|
|
app.include_router(files.router)
|
|
app.include_router(folders.router)
|
|
app.include_router(admin.router)
|
|
app.include_router(admin_users.router)
|
|
app.include_router(admin_models.router)
|
|
app.include_router(admin_audio.router)
|
|
app.include_router(admin_search.router)
|
|
|
|
register_error_handlers(app)
|
|
return app
|
|
|
|
|
|
def register_error_handlers(app: FastAPI) -> None:
|
|
@app.exception_handler(RedirectToLogin)
|
|
async def _not_signed_in(request: Request, exc: RedirectToLogin) -> Response:
|
|
# An htmx request must not swap a login page into a fragment of the
|
|
# chat UI, so tell the browser to navigate instead.
|
|
if is_htmx(request):
|
|
response = Response(status_code=status.HTTP_204_NO_CONTENT)
|
|
response.headers["HX-Redirect"] = "/auth/login"
|
|
return response
|
|
return login_redirect(exc.next_url)
|
|
|
|
@app.exception_handler(StarletteHTTPException)
|
|
async def _http_error(request: Request, exc: StarletteHTTPException) -> Response:
|
|
# JSON callers and htmx fragments want the bare status; humans loading a
|
|
# page want a themed page they can navigate away from.
|
|
wants_page = "text/html" in request.headers.get("accept", "") and not is_htmx(request)
|
|
if not wants_page:
|
|
return JSONResponse({"detail": exc.detail}, status_code=exc.status_code)
|
|
|
|
return render(
|
|
request,
|
|
"error.html",
|
|
{
|
|
"status_code": exc.status_code,
|
|
"detail": exc.detail,
|
|
"flavour": ERROR_FLAVOUR.get(exc.status_code, ERROR_FLAVOUR[500]),
|
|
},
|
|
status_code=exc.status_code,
|
|
)
|
|
|
|
@app.exception_handler(Exception)
|
|
async def _unhandled(request: Request, exc: Exception) -> Response:
|
|
log.exception("unhandled error at %s", request.url.path)
|
|
if is_htmx(request) or "text/html" not in request.headers.get("accept", ""):
|
|
return JSONResponse({"detail": "Internal server error"}, status_code=500)
|
|
return render(
|
|
request,
|
|
"error.html",
|
|
{"status_code": 500, "detail": "Something went wrong.",
|
|
"flavour": ERROR_FLAVOUR[500]},
|
|
status_code=500,
|
|
)
|
|
|
|
|
|
# Flavour lives in error pages, empty states and theme names -- never in the
|
|
# functional UI. See CLAUDE.md.
|
|
ERROR_FLAVOUR = {
|
|
403: "Speak, friend, and enter. This door is not yours to open.",
|
|
404: "Not all those who wander are lost. This page, however, is.",
|
|
500: "The Road goes ever on, but this stretch of it has washed out.",
|
|
}
|
|
|
|
|
|
app = create_app()
|