1d3f6c450b
Four features, plus the schema machinery they needed. **Schema sync.** The first live instance had data in it, and create_all only creates missing *tables* -- a new column silently never appeared. db/migrations.py now diffs the declared models against the database and ALTER TABLE ... ADD COLUMN for what is missing, deriving a backfill default from the column type (SQLite refuses a NOT NULL column without one, and a Python-side `default=dict` cannot be expressed in DDL). Verified against a copy of the live database: eight changes applied, all rows preserved, second run a no-op. Renames, drops and retypes are still manual and say so. **Permissions.** A flat set of named booleans: an instance baseline widened by each group the user belongs to. A group grants and never denies -- with denies, "why can this user not do X" cannot be answered without simulating every group. Admins bypass entirely, because an admin can grant it back to themselves in two clicks and pretending otherwise is theatre. Model *access* is separate: public, or granted to groups. The picker is not the boundary -- switching a chat to a model you cannot reach is a 403. **Model settings.** Ordering, pinned-first, an instance default and a per-user default, display names, descriptions, capability flags, and uploaded images. Images are stored and served locally rather than by URL: a remote URL makes every page render a request to a third party. Uploads are validated by magic number, not the declared content type, and stored under a random name. Models with no image get a generated initial whose hue is derived from the model id, so it is stable. **Reasoning display.** Streams into its own collapsible block above the answer, labelled "Thought for 14 seconds", collapsed once finished, and never replayed as context on the next turn. Two sources: the reasoning_content delta field, and <think> tags inline in content -- the latter needs a streaming splitter because the tags arrive split across chunks. Models emitting no reasoning show nothing, via a :has() rule rather than JavaScript. Verified against qwen35-9b on llama-swap: 694 reasoning events, 52 answer tokens, cleanly separated. Two bugs found and fixed while testing: - A bare `Mapped[list]` relationship is treated by SQLAlchemy as a scalar and returns None instead of []. It needs the element type. - FastAPI substitutes the default for an empty form value, so with `x: str | None = Form(None)` a submitted `x=` is indistinguishable from an absent field. That silently broke clearing a system prompt or a temperature. update_chat now reads the raw form and checks key presence. 143 tests, ruff clean. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
140 lines
4.7 KiB
Python
140 lines
4.7 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_models,
|
|
admin_users,
|
|
auth,
|
|
chats,
|
|
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))"'
|
|
)
|
|
|
|
log.info("LLeMbas %s starting on http://%s:%s", __version__, settings.host, settings.port)
|
|
log.info("data directory: %s", settings.data_dir.resolve())
|
|
yield
|
|
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(folders.router)
|
|
app.include_router(admin.router)
|
|
app.include_router(admin_users.router)
|
|
app.include_router(admin_models.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()
|