DoS/quota guardrails for the unauthenticated local APIs: * Body-size middleware rejects oversized requests (Content-Length) before they are buffered/base64-decoded (NEXUS_MAX_REQUEST_MB, default 32). * Document upload enforces a decoded-byte cap (NEXUS_MAX_UPLOAD_MB, default 20) and a PDF page-count cap (NEXUS_MAX_PDF_PAGES, default 500) as backstops for chunked bodies and pathological files. * A counter-based in-flight limiter bounds concurrent chats and document ingests (NEXUS_MAX_CONCURRENT_CHATS/UPLOADS), returning 429 when saturated; the chat slot is held for the whole SSE stream and released on completion or client disconnect. * /models/pull gains an opt-in allowlist (NEXUS_MODEL_ALLOWLIST); empty by default so behaviour is unchanged, otherwise a bare repo name permits all its tags. Co-authored-by: Cursor <cursoragent@cursor.com>
225 lines
8.1 KiB
Python
225 lines
8.1 KiB
Python
# config.py
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from pathlib import Path
|
|
from typing import Dict, Any
|
|
|
|
# --- ENV ---
|
|
try:
|
|
from dotenv import load_dotenv # optional
|
|
load_dotenv()
|
|
except Exception:
|
|
pass
|
|
|
|
# --- PROJECT ROOT ---
|
|
PROJECT_ROOT = Path(__file__).resolve().parent.parent
|
|
|
|
# --- VERSION (single source of truth: the VERSION file at the repo root) ---
|
|
try:
|
|
VERSION = (PROJECT_ROOT / "VERSION").read_text(encoding="utf-8").strip() or "0.0.0"
|
|
except Exception:
|
|
VERSION = "0.0.0"
|
|
|
|
# --- MODEL DEFAULTS ---
|
|
# Single source of truth for the three models NexusOS ships with. The installers
|
|
# pull and pin these, the runtime falls back to them; keeping them in one place
|
|
# is what stops installer and backend from drifting apart.
|
|
#
|
|
# Chat: llama3.1:8b - a strong non-reasoning instruct model (~4.9 GB; overflows a
|
|
# 4 GB GPU into CPU/RAM). Chosen over Qwen3 because Qwen3 is a reasoning model:
|
|
# smart only with its slow <think> step, weak without it.
|
|
# Memory: mistral - the curator that extracts facts and titles conversations.
|
|
# Embed: nomic-embed-text - powers semantic recall of past conversations
|
|
# (OllamaManager.embed / store.semantic_search_conversations). Without it,
|
|
# recall silently degrades to lexical substring matching.
|
|
DEFAULT_CHAT_MODEL = "llama3.1:8b"
|
|
DEFAULT_MEMORY_MODEL = "mistral:latest"
|
|
DEFAULT_EMBED_MODEL = "nomic-embed-text"
|
|
|
|
# --- CORE DIRECTORIES ---
|
|
DATA_DIR = PROJECT_ROOT / "data"
|
|
MODELS_DIR = PROJECT_ROOT / "models"
|
|
RUNTIME_DIR = PROJECT_ROOT / "runtime"
|
|
|
|
MEMORY_DIR = PROJECT_ROOT / "synapse" / "memory"
|
|
|
|
LOGS_DIR = RUNTIME_DIR / "logs"
|
|
CACHE_DIR = RUNTIME_DIR / "cache"
|
|
TEMP_DIR = RUNTIME_DIR / "tmp"
|
|
|
|
# --- APPLICATION SUBSYSTEM DIRECTORIES ---
|
|
PLAYBOOK_DIR = DATA_DIR / "playbooks" # YAML playbook files (PlaybookFileStore)
|
|
UPLOADS_DIR = DATA_DIR / "uploads"
|
|
EXPORTS_DIR = DATA_DIR / "exports"
|
|
|
|
# --- DATABASE / STORAGE FILES (match your repo) ---
|
|
MEMORY_DB = MEMORY_DIR / "memory.db"
|
|
|
|
# --- LOG FILES ---
|
|
BACKEND_LOG = RUNTIME_DIR / "backend.log"
|
|
OLLAMA_LOG = LOGS_DIR / "ollama.log"
|
|
CHAT_LOG = LOGS_DIR / "chat.log"
|
|
|
|
# --- ENSURE REQUIRED DIRECTORIES EXIST ---
|
|
for d in (
|
|
DATA_DIR,
|
|
MODELS_DIR,
|
|
RUNTIME_DIR,
|
|
LOGS_DIR,
|
|
MEMORY_DIR,
|
|
CACHE_DIR,
|
|
TEMP_DIR,
|
|
PLAYBOOK_DIR,
|
|
UPLOADS_DIR,
|
|
EXPORTS_DIR,
|
|
):
|
|
d.mkdir(parents=True, exist_ok=True)
|
|
|
|
# --- PATH ACCESSOR (fail-fast) ---
|
|
def path(name: str) -> Path:
|
|
"""
|
|
Return a Path for a known name. Raises KeyError if name is unknown.
|
|
"""
|
|
mapping = {
|
|
"root": PROJECT_ROOT,
|
|
"data": DATA_DIR,
|
|
"models": MODELS_DIR,
|
|
"runtime": RUNTIME_DIR,
|
|
"logs": LOGS_DIR,
|
|
"memory": MEMORY_DIR,
|
|
"cache": CACHE_DIR,
|
|
"tmp": TEMP_DIR,
|
|
"playbooks": PLAYBOOK_DIR,
|
|
"uploads": UPLOADS_DIR,
|
|
"exports": EXPORTS_DIR,
|
|
"memory_db": MEMORY_DB,
|
|
"backend_log": BACKEND_LOG,
|
|
"ollama_log": OLLAMA_LOG,
|
|
"chat_log": CHAT_LOG,
|
|
}
|
|
try:
|
|
return mapping[name]
|
|
except KeyError:
|
|
raise KeyError(f"Unknown config path name: {name}")
|
|
|
|
# --- Settings class and exported instance ---
|
|
class Settings:
|
|
"""
|
|
Lightweight settings container. Use `settings` instance for runtime access,
|
|
or `Settings` class for typing/tests.
|
|
"""
|
|
def __init__(self) -> None:
|
|
self.version: str = VERSION
|
|
self.project_root: Path = PROJECT_ROOT
|
|
self.data_dir: Path = DATA_DIR
|
|
self.models_dir: Path = MODELS_DIR
|
|
self.runtime_dir: Path = RUNTIME_DIR
|
|
self.memory_dir: Path = MEMORY_DIR
|
|
self.logs_dir: Path = LOGS_DIR
|
|
|
|
# DB files
|
|
self.memory_db: Path = MEMORY_DB
|
|
|
|
# Logs
|
|
self.backend_log: Path = BACKEND_LOG
|
|
self.ollama_log: Path = OLLAMA_LOG
|
|
self.chat_log: Path = CHAT_LOG
|
|
|
|
# Env overrides
|
|
self.ollama_host: str = os.getenv("OLLAMA_HOST", "http://127.0.0.1:11434")
|
|
self.ollama_timeout: int = int(os.getenv("OLLAMA_TIMEOUT", "120"))
|
|
|
|
def as_dict(self) -> Dict[str, Any]:
|
|
return {
|
|
"version": self.version,
|
|
"project_root": str(self.project_root),
|
|
"data_dir": str(self.data_dir),
|
|
"models_dir": str(self.models_dir),
|
|
"runtime_dir": str(self.runtime_dir),
|
|
"memory_dir": str(self.memory_dir),
|
|
"memory_db": str(self.memory_db),
|
|
"ollama_host": self.ollama_host,
|
|
"ollama_timeout": self.ollama_timeout,
|
|
}
|
|
|
|
# --- local-access allowlists (shared by the backend + memory FastAPI apps) ---
|
|
# The REST APIs are unauthenticated, so they are meant to be reached only from
|
|
# this machine. Two independent browser-side defenses depend on these lists:
|
|
# * ALLOWED_ORIGINS drives CORS — blocks a malicious page from *reading*
|
|
# responses cross-origin (was previously "*", which let any site read them).
|
|
# * ALLOWED_HOSTS drives TrustedHostMiddleware — rejects a foreign Host header,
|
|
# which is what stops DNS-rebinding (same-origin from the browser's view, so
|
|
# CORS can't help there).
|
|
# Both accept a comma-separated env override for the intentional-LAN case, to be
|
|
# paired with real auth. NEXUS_ALLOWED_HOSTS=* disables the Host check.
|
|
def _csv_env(name: str, default: list) -> list:
|
|
raw = os.getenv(name, "").strip()
|
|
return [p.strip() for p in raw.split(",") if p.strip()] if raw else list(default)
|
|
|
|
_LOCAL_HOSTS = ["localhost", "127.0.0.1", "[::1]", "::1", "testserver"]
|
|
_LOCAL_ORIGINS = [
|
|
f"http://{h}:{p}"
|
|
for h in ("localhost", "127.0.0.1")
|
|
for p in (8000, 8001, 5173)
|
|
]
|
|
ALLOWED_HOSTS = _csv_env("NEXUS_ALLOWED_HOSTS", _LOCAL_HOSTS)
|
|
ALLOWED_ORIGINS = _csv_env("NEXUS_ALLOWED_ORIGINS", _LOCAL_ORIGINS)
|
|
|
|
|
|
# --- resource limits (DoS guardrails for the unauthenticated local APIs) ---
|
|
# Even local-only, an unbounded base64 upload or a flood of concurrent inference
|
|
# requests can exhaust RAM/CPU. These are generous defaults for single-user use,
|
|
# all env-overridable.
|
|
def _int_env(name: str, default: int) -> int:
|
|
try:
|
|
return int((os.getenv(name) or "").strip() or default)
|
|
except ValueError:
|
|
return default
|
|
|
|
MAX_REQUEST_BYTES = _int_env("NEXUS_MAX_REQUEST_MB", 32) * 1024 * 1024
|
|
MAX_UPLOAD_BYTES = _int_env("NEXUS_MAX_UPLOAD_MB", 20) * 1024 * 1024
|
|
MAX_PDF_PAGES = _int_env("NEXUS_MAX_PDF_PAGES", 500)
|
|
MAX_CONCURRENT_CHATS = _int_env("NEXUS_MAX_CONCURRENT_CHATS", 4)
|
|
MAX_CONCURRENT_UPLOADS = _int_env("NEXUS_MAX_CONCURRENT_UPLOADS", 2)
|
|
|
|
# Opt-in allowlist for /models/pull. Empty (default) = unrestricted, preserving
|
|
# current behaviour. Set NEXUS_MODEL_ALLOWLIST=mistral,llama3 to bound which
|
|
# models can be downloaded; a bare repo name (before the ':tag') matches all of
|
|
# its tags, so "mistral" permits "mistral:latest", "mistral:7b", etc.
|
|
MODEL_ALLOWLIST = _csv_env("NEXUS_MODEL_ALLOWLIST", [])
|
|
|
|
|
|
def model_pull_allowed(name: str) -> bool:
|
|
"""True if `name` may be pulled: always when no allowlist is configured,
|
|
otherwise when the full name or its repo part (before the first ':') is
|
|
listed. Case-insensitive."""
|
|
if not MODEL_ALLOWLIST:
|
|
return True
|
|
n = (name or "").strip().lower()
|
|
if not n:
|
|
return False
|
|
allow = {a.lower() for a in MODEL_ALLOWLIST}
|
|
return n in allow or n.split(":", 1)[0] in allow
|
|
|
|
# exported instance
|
|
settings = Settings()
|
|
|
|
# explicit exports for static checkers and IDEs
|
|
__all__ = ["Settings", "settings", "path", "VERSION",
|
|
"DEFAULT_CHAT_MODEL", "DEFAULT_MEMORY_MODEL", "DEFAULT_EMBED_MODEL",
|
|
"PROJECT_ROOT", "DATA_DIR", "MODELS_DIR", "RUNTIME_DIR",
|
|
"MEMORY_DIR", "LOGS_DIR", "PLAYBOOK_DIR", "UPLOADS_DIR",
|
|
"EXPORTS_DIR", "MEMORY_DB",
|
|
"BACKEND_LOG", "OLLAMA_LOG", "CHAT_LOG",
|
|
"ALLOWED_HOSTS", "ALLOWED_ORIGINS",
|
|
"MAX_REQUEST_BYTES", "MAX_UPLOAD_BYTES", "MAX_PDF_PAGES",
|
|
"MAX_CONCURRENT_CHATS", "MAX_CONCURRENT_UPLOADS",
|
|
"MODEL_ALLOWLIST", "model_pull_allowed"]
|
|
|
|
# --- quick runtime sanity check when run directly (no side effects on import) ---
|
|
if __name__ == "__main__":
|
|
print("Config paths:")
|
|
for key in ("root", "data", "models", "runtime", "memory", "memory_db"):
|
|
print(f" {key}: {path(key)}")
|