Files
FabledScribe/src/scribe/app.py
T
bvandeusen dd1b5e5ddb
CI & Build / Python lint (push) Successful in 3s
CI & Build / TypeScript typecheck (push) Successful in 12s
CI & Build / integration (push) Failing after 27s
CI & Build / Python tests (push) Successful in 50s
CI & Build / Build & push image (push) Successful in 1m42s
feat(snippets): reverse lookup — find snippets by repo/path/symbol
"What canonical helpers already live in this file?" was unanswerable:
location lived only in the body markdown. It is now a jsonpath containment
query over the `notes.data` mirror added by migration 0070.

- One predicate in two dialects in services/knowledge.py: SQL (`data @?`,
  applied in the browse arm and the keyword arm before count/pagination, so
  totals stay honest) and Python (`location_matches`, for the semantic arm
  which post-filters candidates it already holds). Both must change together.
- Parts are ANDed within a SINGLE locations entry — repo A in one entry and
  path B in another is not "recorded at A/B". `path` also matches as a
  directory prefix, via jsonpath `starts with` rather than `@>`, which the
  same GIN index serves.
- `repo`/`path`/`symbol` reach the service, the REST list and the MCP tool
  under one name with one default (rule #33); the MCP docstring teaches the
  place form, and so does the reusing-code skill (plugin.json bumped).
- UI: a Location disclosure beside the snippet search, with its own empty
  state — "nothing kept there, so what you're about to write is new."

Settles #2083's open question (pre-0070 NULL `data`) by backfilling after
all: `backfill_snippet_data` runs at startup, deriving the mirror from the
body with the same parser the read path trusts. 0070's caution was about
mangling a hand-edited body; this never touches the body. The alternative
was a permanent second body-regex arm, or a query that silently answers
"nothing here" for an old snippet and gets the helper written twice.

Refs #2083, milestone #232.
2026-07-27 23:09:37 -04:00

299 lines
12 KiB
Python

import logging
import time
import traceback as tb_module
from pathlib import Path
from quart import Quart, g, jsonify, make_response, request, send_from_directory
from scribe.config import Config
from scribe.routes.admin import admin_bp
from scribe.routes.api import api
from scribe.routes.auth import auth_bp
from scribe.routes.export import export_bp
from scribe.routes.notes import notes_bp
from scribe.routes.milestones import milestones_bp
from scribe.routes.task_logs import task_logs_bp
from scribe.routes.projects import projects_bp
from scribe.routes.settings import settings_bp
from scribe.routes.tasks import tasks_bp
from scribe.routes.groups import groups_bp
from scribe.routes.shares import shares_bp
from scribe.routes.in_app_notifications import notifications_bp
from scribe.routes.users import users_bp
from scribe.routes.api_keys import api_keys_bp
from scribe.routes.search import search_bp
from scribe.routes.profile import profile_bp
from scribe.routes.knowledge import knowledge_bp
from scribe.routes.rulebooks import rulebooks_bp
from scribe.routes.plugin import plugin_bp
from scribe.routes.trash import trash_bp
from scribe.routes.dashboard import dashboard_bp
from scribe.routes.systems import systems_bp
from scribe.routes.snippets import snippets_bp
from scribe.mcp import mount_mcp
STATIC_DIR = Path(__file__).parent / "static"
logger = logging.getLogger(__name__)
def create_app() -> Quart:
# Configure logging
logging.basicConfig(
format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
level=getattr(logging, Config.LOG_LEVEL.upper(), logging.INFO),
)
# Validate config early so misconfigurations surface immediately with clear messages
try:
Config.validate()
except ValueError as exc:
logging.getLogger(__name__).error("Invalid configuration:\n%s", exc)
raise
app = Quart(__name__, static_folder=None)
app.secret_key = Config.SECRET_KEY
app.config["SESSION_COOKIE_HTTPONLY"] = True
app.config["SESSION_COOKIE_SAMESITE"] = "Lax"
app.config["SESSION_COOKIE_SECURE"] = Config.SECURE_COOKIES
if Config.SECRET_KEY == "dev-secret-change-me":
logger.warning(
"SECRET_KEY is set to the default value — session cookies are insecure. "
"Set SECRET_KEY or SECRET_KEY_FILE for production use."
)
if not Config.TRUST_PROXY_HEADERS:
logger.warning(
"TRUST_PROXY_HEADERS is not set. If this instance is behind a reverse proxy "
"(nginx, Caddy, Traefik) set TRUST_PROXY_HEADERS=true so rate limiting uses "
"real client IPs rather than the proxy IP."
)
app.register_blueprint(admin_bp)
app.register_blueprint(api)
app.register_blueprint(auth_bp)
app.register_blueprint(export_bp)
app.register_blueprint(milestones_bp)
app.register_blueprint(notes_bp)
app.register_blueprint(projects_bp)
app.register_blueprint(settings_bp)
app.register_blueprint(task_logs_bp)
app.register_blueprint(tasks_bp)
app.register_blueprint(groups_bp)
app.register_blueprint(shares_bp)
app.register_blueprint(notifications_bp)
app.register_blueprint(users_bp)
app.register_blueprint(api_keys_bp)
app.register_blueprint(search_bp)
app.register_blueprint(profile_bp)
app.register_blueprint(knowledge_bp)
app.register_blueprint(rulebooks_bp)
app.register_blueprint(plugin_bp)
app.register_blueprint(trash_bp)
app.register_blueprint(dashboard_bp)
app.register_blueprint(systems_bp)
app.register_blueprint(snippets_bp)
@app.before_request
async def before_request():
g.request_start = time.monotonic()
@app.after_request
async def after_request(response):
duration = time.monotonic() - getattr(g, "request_start", time.monotonic())
duration_ms = round(duration * 1000, 1)
# Downgrade noisy high-frequency / static paths to DEBUG
_quiet = (
request.path in {"/api/health", "/api/chat/status"}
or request.path.startswith(("/static/", "/assets/", "/sw.js", "/manifest.json"))
)
log_fn = logger.debug if _quiet else logger.info
log_fn(
"%s %s %s %.1fms",
request.method,
request.path,
response.status_code,
duration_ms,
)
# Log usage for API requests (skip logs endpoint to avoid recursion)
if request.path.startswith("/api/") and not request.path.startswith("/api/admin/logs"):
try:
from scribe.services.logging import log_usage
user = getattr(g, "user", None)
await log_usage(
user_id=user.id if user else None,
username=user.username if user else None,
endpoint=request.path,
method=request.method,
status_code=response.status_code,
duration_ms=duration_ms,
)
except Exception:
logger.debug("Failed to log usage", exc_info=True)
response.headers.setdefault("X-Content-Type-Options", "nosniff")
response.headers.setdefault("X-Frame-Options", "DENY")
response.headers.setdefault("Referrer-Policy", "strict-origin-when-cross-origin")
response.headers.setdefault(
"Content-Security-Policy",
"default-src 'self'; "
"script-src 'self' 'unsafe-inline' 'wasm-unsafe-eval'; "
"style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; "
"img-src 'self' data: blob:; "
"connect-src 'self'; "
"font-src 'self' data: https://fonts.gstatic.com; "
"object-src 'none'; "
"base-uri 'self'; worker-src 'self' blob:;"
)
return response
@app.before_serving
async def startup():
import asyncio
from scribe.services.auth import start_auth_token_retention_loop
from scribe.services.embeddings import backfill_note_embeddings
from scribe.services.logging import start_log_retention_loop
from scribe.services.notifications import start_notification_loop
start_log_retention_loop()
start_notification_loop()
start_auth_token_retention_loop()
# Backfill embeddings for any notes that don't have one. Runs in the
# background so it never blocks the server from accepting requests.
async def _delayed_backfill() -> None:
try:
await backfill_note_embeddings()
except Exception:
logger.warning("Embedding backfill failed", exc_info=True)
# Snippets written before migration 0070 have no `notes.data` mirror,
# and the location reverse lookup queries that column — an unfilled
# row would read as "no snippet here" rather than as a gap. Separate
# try block so neither backfill can skip the other.
try:
from scribe.services.snippets import backfill_snippet_data
await backfill_snippet_data()
except Exception:
logger.warning("Snippet data backfill failed", exc_info=True)
asyncio.create_task(_delayed_backfill())
# Recurrence scheduler (recurring-task spawn every 15m)
from scribe.services.recurrence_scheduler import start_recurrence_scheduler
start_recurrence_scheduler(asyncio.get_running_loop())
# Version-pinning scheduler (daily auto-pin scan at 03:00 UTC)
from scribe.services.version_pinning_scheduler import (
start_version_pinning_scheduler,
)
start_version_pinning_scheduler(asyncio.get_running_loop())
# Trash retention scheduler (daily expired-trash purge at 03:30 UTC)
from scribe.services.trash_scheduler import start_trash_scheduler
start_trash_scheduler(asyncio.get_running_loop())
# DB maintenance scheduler (daily targeted VACUUM ANALYZE, default 04:00 UTC)
from scribe.services.db_maintenance_scheduler import (
get_maintenance_hour,
start_db_maintenance_scheduler,
)
start_db_maintenance_scheduler(
asyncio.get_running_loop(), await get_maintenance_hour()
)
# Diagnostic instrumentation — heartbeat, signal handlers, asyncio
# exception hook. Cheap (~1 log line/min), high diagnostic value when
# the app crashes mysteriously. See services/diagnostics.py.
from scribe.services.diagnostics import start_diagnostics
start_diagnostics(asyncio.get_running_loop())
@app.after_serving
async def shutdown():
from scribe.services.recurrence_scheduler import stop_recurrence_scheduler
stop_recurrence_scheduler()
from scribe.services.version_pinning_scheduler import (
stop_version_pinning_scheduler,
)
stop_version_pinning_scheduler()
from scribe.services.trash_scheduler import stop_trash_scheduler
stop_trash_scheduler()
from scribe.services.db_maintenance_scheduler import (
stop_db_maintenance_scheduler,
)
stop_db_maintenance_scheduler()
from scribe.services.diagnostics import stop_diagnostics
stop_diagnostics()
@app.route("/")
async def serve_index():
resp = await make_response(
await send_from_directory(STATIC_DIR, "index.html")
)
resp.headers["Cache-Control"] = "no-cache, no-store, must-revalidate"
return resp
# File extensions that belong to the SPA or its assets.
# Anything else with an extension is not a valid app path and gets a hard 404.
_SPA_EXTENSIONS = {
"", ".html", ".js", ".css", ".ico", ".png", ".jpg", ".jpeg",
".svg", ".webp", ".woff", ".woff2", ".ttf", ".otf", ".map", ".json",
}
@app.errorhandler(404)
async def handle_404(error):
# Return JSON 404 for API routes
if request.path.startswith("/api/"):
return jsonify({"error": "Not found"}), 404
# Try to serve a real static file first
path = request.path.lstrip("/")
file_path = STATIC_DIR / path
if path and file_path.is_file():
return await send_from_directory(STATIC_DIR, path)
# Reject paths with file extensions the app doesn't serve.
# This turns scanner probes (.php, .asp, .cgi, etc.) into honest 404s
# instead of serving them the Vue SPA with a misleading 200.
from pathlib import PurePosixPath
suffix = PurePosixPath(request.path).suffix.lower()
if suffix not in _SPA_EXTENSIONS:
return "", 404
# SPA fallback for clean client-side routes (/notes/123, /chat, etc.)
resp = await make_response(
await send_from_directory(STATIC_DIR, "index.html")
)
resp.headers["Cache-Control"] = "no-cache, no-store, must-revalidate"
return resp
@app.errorhandler(500)
async def handle_500(error):
logger.exception("Internal server error on %s %s", request.method, request.path)
try:
from scribe.services.logging import log_error
user = getattr(g, "user", None)
await log_error(
user_id=user.id if user else None,
username=user.username if user else None,
endpoint=request.path,
method=request.method,
error_type=type(error).__name__,
error_message=str(error),
traceback=tb_module.format_exc(),
)
except Exception:
logger.debug("Failed to log error", exc_info=True)
if request.path.startswith("/api/"):
return jsonify({"error": "Internal server error"}), 500
return "Internal Server Error", 500
mount_mcp(app)
return app