unsloth/studio/backend/main.py
Wasim Yousef Said e35cbfb454
Add native GGUF intake to Studio (#5246)
* feat(studio): add Tauri native GGUF intake

* feat(studio): polish native GGUF intake

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix(studio): load backend helpers during local setup

* fix(studio): acquire native load lease before unload

* Studio: harden native path lease verification and Tauri intake

- Wrap path.resolve(strict=True) and Path.stat() in NativePathLeaseError so a deleted or unmounted GGUF returns 400 instead of leaking the full filesystem path through the generic load_model/validate_model handler.
- Re-apply _reject_network_or_device_path to the resolved canonical path for defense in depth after symlink resolution.
- Replace try/except ValueError pattern in the device-path guard with Path.is_relative_to; the previous shape silently swallowed NativePathLeaseError (which subclasses ValueError) so /dev,/proc,/sys were never actually rejected.
- Broaden the lease redaction regex and dict-key check (Python and Rust diagnostics) to cover both native_path_lease and nativePathLease so the camelCase form emitted by Tauri/frontend payloads is also redacted.
- Hoist the redact_native_paths import to module top in loggers/handlers; the recursive filter no longer pays a per-record import lookup.
- Persist activeNativePathToken in the chat runtime store so the rollback branch can mint a fresh lease and reload the previous native GGUF when a new load fails after unload; clear it in clearCheckpoint and overwrite it on each successful load.
- use-native-drop: read options through a ref so the Tauri onDragDropEvent listener is registered once and stays attached across option changes; reject ambiguous multi-file drops up front instead of silently registering only the first GGUF.
- pick_native_model: use an async pick_file with a tokio oneshot channel instead of blocking_pick_file so the Tokio worker is not held for the duration of the OS dialog.
- registerNativeModelPath: drop the duplicate sourceKind argument; the Rust command parameter is source_kind.
- install_python_stack: insert the script directory (studio/) on sys.path; the previous insert pointed at studio/backend/ which does not satisfy `from backend.utils.wheel_utils import ...`.

* install_python_stack: keep _BACKEND_DIR on sys.path

Restore the studio/backend insertion. Although the immediately following `from backend.utils.wheel_utils import (...)` is satisfied by studio/ already being on sys.path[0] when invoked as `python studio/install_python_stack.py`, wheel_utils itself runs `from utils.native_path_leases import ...`, which requires studio/backend/ to be importable. Without the backend insertion, the existing tests/python/test_install_python_stack.py collection fails with ModuleNotFoundError: No module named 'utils'.

* Studio: tighten native path lease lifecycle and Tauri intake IPC

- register_native_model_path now hardcodes NativePathSourceKind::Drop on the Rust side and the frontend stops sending source_kind. The previous JS payload (source_kind only) never reached the Rust deserializer because Tauri's default ArgumentCase::Camel maps the Rust parameter source_kind to the JS key sourceKind, so drag/drop registration silently failed. Hardcoding the source kind also keeps audit metadata trustworthy on this command.
- Add native_path_secret_removed_for_child_start context manager and wrap multiprocessing.Process.start() at the inference, export, training, and data-recipe job spawn sites. The previous wrapper-only scrub left UNSLOTH_STUDIO_NATIVE_PATH_LEASE_SECRET visible to spawn-platform import-time worker code. The wrapper run_without_native_path_secret stays as defense-in-depth inside the child.
- Stop passing exc_info=True from the native-grant load/validate error logs in routes/inference.py. The structlog filter_sensitive_data processor runs before the renderer, so ConsoleRenderer formatted tracebacks bypassed redaction; the redacted str(e) preserves the message text.
- Replace the os.path.normcase string equality on the resolved canonical path with Path.samefile (with a normcase fallback) so Windows leases that differ only in extended-length \\?\ prefix or short-name spelling are accepted.
- Wrap consumeNativePathToken in its own try/catch in the chat runtime rollback. If the previous native-model token has aged out of TOKEN_TTL we now surface a clear modelsError instead of silently swallowing the rollback inside the outer catch.
- Reject non-ASCII lease strings in _split_lease and convert UnicodeEncodeError / binascii.Error / ValueError raised by _b64decode into NativePathLeaseError so verify_native_path_lease never escapes raw exceptions to the route handler.
- Tighten dropStateForPaths to mark multi-file payloads invalid so the overlay matches the post-fix drop handler that rejects the same payload.
- Replace the one-shot fetch in useNativePathLeasesSupported with a delayed-retry loop so the picker/drop becomes available once the backend is up rather than staying disabled for the rest of the session after a transient failure.
- Drop the unused setActiveNativePathToken setter; the value is set via setState directly in use-chat-model-runtime.
- Add a toast on auto-load failure in use-native-drop so a collapsed model selector does not hide the error.
- Burn the lease nonce before _validate_current_stat so a stat-failed lease is single-use even if a later state change happens to match the original size/mtime.

* Studio: cache lease secret, harden native path stat checks, polish intake UX

- Cache the decoded UNSLOTH_STUDIO_NATIVE_PATH_LEASE_SECRET on first verify and validate that it is base64-decodable and at least 32 bytes. Subsequent _decode_secret calls return from the cache and never touch os.environ, so concurrent /api/inference/load and /api/health requests no longer race with native_path_secret_removed_for_child_start scrubbing the env. native_path_leases_supported now wraps _decode_secret so the health flag matches what verify_native_path_lease actually accepts.
- Replace path.is_file()/is_dir() + path.stat() with os.lstat() in _validate_current_stat and explicitly reject S_ISLNK; size and mtime checks now refer to the link itself, closing the same-size+same-mtime symlink-swap window that the prior follow-symlink stat() left open.
- Add an issued_at_ms < expires_at_ms sanity check in _validate_payload to reject internally inconsistent (HMAC-protected) lease payloads.
- Sort _NATIVE_PATH_REDACTIONS by length (descending) before iterating in redact_native_paths so a longer registered path is replaced before a shorter prefix path; otherwise logs containing /foo/X.gguf.bak after only /foo/X.gguf was registered would leak the .bak suffix.
- classify_existing_path now re-checks the canonical path with symlink_metadata after canonicalize, so a regular file that is replaced with a symlink in the small canonicalize window is rejected at registration.
- ModelSelector renders the local file picker as its own block (not in the eject ternary), so a user with an active model can still replace it via the picker rather than only via drag/drop.
- useNativePathLeasesSupported caps the readiness probe at MAX_READINESS_POLLS (60 = ~5 minutes) and aborts the in-flight fetch on unmount via AbortController, so a permanently-disabled backend stops generating sustained traffic and hot-reload no longer leaks open connections.
- useChooseNativeModel returns a stable useCallback closure and guards the OS dialog with a useRef so rapid double-clicks cannot open multiple dialogs and orphan Rust tokens.
- Branch the multi-file drop toast: if no GGUF was present we say "Only .gguf model files can be dropped here." and otherwise "Drop a single .gguf model file." so users dropping non-GGUF attachments get an accurate explanation.

* native_path_leases: lstat the signed canonical path before resolving

The earlier change to lstat inside _validate_current_stat operates on grant.canonical_path, which is the post-resolve target. If the user atomically replaces the originally-signed file with a symlink to a different file of identical size and mtime, path.resolve(strict=True) follows the symlink, samefile returns True (both ends share the new inode), and the lstat in _validate_current_stat sees the regular target file rather than the symlink, so the swap goes undetected.

Add an os.lstat on the signed canonical path before path.resolve(strict=True), and reject S_ISLNK there. The lstat in _validate_current_stat stays as defense-in-depth for swaps that occur strictly between resolve and stat.

* Studio: scrub native lease secret before mp.Queue spawn and tighten lease lifecycle

- Move _CTX.Queue / _CTX.Event / _CTX.Process construction inside native_path_secret_removed_for_child_start at the inference, export, training and data-recipe spawn sites. The first Queue creation lazily spawns Python's multiprocessing.resource_tracker child, so when it ran outside the scrub context the tracker process inherited the lease secret. Reproduced via the proc filesystem environ entry; the wrapped order keeps the tracker clean.
- native_path_secret_removed_for_child_start now refcounts entries: the env var is popped on the first entry and restored only when the last context exits. Concurrent training/inference/export starts no longer serialize on the env lock across the entire proc.start yield, while still guaranteeing the env stays empty for the duration of every overlapping spawn.
- run_without_native_path_secret now also nulls the module-level cached lease secret. With the existing spawn-only multiprocessing context the cache is irrelevant in practice, but a future fork caller would otherwise inherit the in-memory secret even though the env var was scrubbed.
- filter_sensitive_data now applies the native lease key check on the top-level event_dict, not only on nested dicts, so a logger call that includes a lease value as a top-level keyword field actually redacts it (the bare value does not match the prefix-anchored regex).
- chat-page loadNativeModelIntent now passes intent.id to clearModelIntent so a second drag-drop during an in-flight first auto-load is not wiped from the chip area when the first resolves.
- Bump useNativePathLeasesSupported's MAX_READINESS_POLLS from 60 to 720 so first-run installs that compile llama.cpp from source or download large CUDA wheels (well past 5 minutes) don't permanently disable the native picker.

* native_path_leases: serialize first-decode against scrub context

_decode_secret used a separate _SECRET_INIT_LOCK from the env scrub's _NATIVE_PATH_ENV_LOCK, so the very first decode (before the cache is populated) could race a concurrent native_path_secret_removed_for_child_start and read os.environ during the env-empty window, raising "Native path grants require the managed desktop backend." Subsequent calls hit the cache and were already safe.

Acquire _NATIVE_PATH_ENV_LOCK around the env read inside _SECRET_INIT_LOCK and fall back to _SCRUB_SAVED_SECRET when the scrub has temporarily popped the env var. Lock ordering (init then env) is consistent with no other caller, so no deadlock.

* Studio: surface native model load errors and harden native path label cache

- Native model load and validate now bubble up the actual exception (with
  paths redacted) and apply the same friendly-error rewrite the non-native
  path uses, so users see "CUDA OOM", "trust_remote_code required", etc.
  instead of a generic "Failed to load native model: <label>".
- run_without_native_path_secret now also nulls _SCRUB_SAVED_SECRET so a
  forked grandchild that imports native_path_leases cannot recover the
  secret via the scrub-aware fallback in _decode_secret.
- _NATIVE_PATH_LABELS now has its own 10000-entry cap independent of the
  100-entry redaction list, so display_label_for_native_path no longer
  falls back to returning the raw canonical path after 101 native paths
  in one session. Redaction list keeps the 100-entry cap for log-scan
  performance.
- _validate_payload now also rejects null bytes in display_label, which
  is echoed back in HTTP responses and log lines.

* Studio: harden native path lease validation and chained native rollback

- child_env_without_native_path_secret now copies os.environ under
  _NATIVE_PATH_ENV_LOCK so a concurrent scrub-context env pop cannot
  raise RuntimeError: dictionary changed size during iteration in a
  background hardware scan or other env reader.
- _validate_payload and grant construction route every signed numeric
  field (version, issued_at_ms, expires_at_ms, size_bytes, modified_ms)
  through new _required_int / _optional_int helpers that wrap raw int()
  ValueError into NativePathLeaseError. The single upstream catcher
  produces 400 instead of 500 for malformed signed payloads.
- verify_native_path_lease now runs _validate_current_stat before
  _consume_nonce, so a transient stat error on the canonical path no
  longer permanently burns the nonce. Concurrent verifies still
  serialize through _consume_nonce, so single-use is preserved.
- Chained native model rollback now restores activeNativePathToken in
  the chat runtime store after a successful rollback loadModel. Without
  this, a second consecutive failed switch could not re-roll-back
  because the store token had been overwritten by the failed attempt.
- validate_model now applies the same not_supported_hints friendly
  rewrite to native model errors that load_model already does, so a
  native .gguf that fails validation with an upstream "is not supported"
  message gets the same actionable wording as the non-native branch.

* Studio: harden native path log redaction, status disclosure, and chip lifecycle

- structlog processor chain now runs format_exc_info before
  filter_sensitive_data so traceback strings are produced (and then
  redacted) rather than passed through as untouched (type, value, tb)
  tuples that the JSON or console renderer formats after the redaction
  filter has already finished.
- native_path_secret_removed_for_child_start clears _CACHED_LEASE_SECRET
  in addition to popping the env var, so a fork during the scrub window
  cannot inherit the cached bytes via the parent's heap. Parent verify
  calls during the window keep working through the existing scrub-aware
  fallback in _decode_secret.
- load_model's except ValueError handler now redacts native paths and
  uses the native model log label when native_grant_backed is true.
  Previously a ValueError raised after lease verification (e.g. from
  ModelConfig.from_identifier or downstream GGUF parsing) returned the
  raw exception string in the HTTP response body.
- llama_cpp_backend now records the native display label at GGUF load
  time, and /api/inference/status prefers it over the redaction store.
  After a Python backend restart the redaction store is empty; the
  attribute keeps the friendly label, and an absolute model_identifier
  with no other label source falls back to the basename so the canonical
  path no longer appears in active_model.
- reveal_path_token uses native "reveal and select" commands on macOS
  (open -R) and Windows (explorer /select,) so the file is highlighted
  in the file manager. Linux keeps the existing parent-directory open.
- Native model rollback that fails because the previous token cannot be
  consumed now throws a rollback-specific Error, and the outer empty
  catch was replaced with one that re-throws the rollback error. The
  rollback-specific message now reaches the user instead of being
  overwritten by the original load error message.
- NativeModelChip tracks the Rust token's expiresAtMs on a single
  setTimeout, disables the Load button at expiry, and relabels it
  "Select again" with an explanatory tooltip so users do not click into
  a guaranteed-failure path after the 15-minute TTL elapses.

* Studio: tighten native artifact policy, mmproj sibling check, and intake UX

- is_open_safe_artifact no longer grants Open for directories. Reveal
  already handles directory navigation, so the change closes the
  attack surface where a macOS .app artifact could be launched via
  open_path_token + open::that_detached.
- Display labels are sanitized in classify_existing_path. Control
  characters in filenames (newlines, tabs, NUL et al.) are replaced
  with spaces and the label is trimmed and capped, so a file named
  with embedded newlines cannot inject forged log lines or scramble
  the UI status panel.
- validate_entry_path skips the size_bytes/modified_ms equality check
  when the operation is Reveal or Open. Cloud-sync agents (Dropbox,
  iCloud Drive, OneDrive) routinely rewrite extended-attribute
  metadata which bumps mtime, and the user expects Reveal/Open to
  remain available for files in synced folders.
- llama_cpp_backend gains a _native_grant_backed flag at GGUF load
  success. /api/inference/status only applies the absolute-path
  basename fallback when that flag is true, so a non-native absolute
  local GGUF still reports its canonical model_identifier and unload
  by identifier keeps working.
- Native vision GGUFs now run through _validate_native_mmproj_companion
  before llama-server starts: the companion mmproj must be a regular
  file, not a symlink, and must live in the same resolved directory as
  the granted GGUF. This stops a hostile sibling or symlinked mmproj
  from being loaded under a single-file lease.
- Chained native rollback restructured: the rollback loadModel + state
  + refresh runs inside its own try/catch that swallows so the outer
  throw error surfaces the ORIGINAL load failure. The native-token
  consume-failure case still throws the rollback-specific message
  early, before the inner block runs, so its actionable guidance is
  preserved.
- Loading-model state and the duplicate-load guard in the chat runtime
  hook now compare both the model id and the native path token. Two
  drops or picks with the same basename in different folders no longer
  silently dedup; the second token is honored.
- chat-page loadNativeModelIntent awaits selectModel before clearing
  the pending intent. If selectModel returns early via dedup or
  throws, the chip and its token stay so the user can retry instead
  of losing the selection.
- NativeModelChip's Reveal button is disabled when the lease has
  expired (Rust would reject it anyway), and the Load button label
  reads "Expired" instead of "Select again" so the disabled element
  no longer promises an action it cannot perform.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
2026-05-04 11:46:18 +02:00

424 lines
14 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
"""
Main FastAPI application for Unsloth UI Backend
"""
import os
import sys
from pathlib import Path as _Path
# Suppress annoying C-level dependency warnings globally
os.environ["PYTHONWARNINGS"] = "ignore"
# Ensure backend dir is on sys.path so _platform_compat is importable when
# main.py is launched directly (e.g. `uvicorn main:app`).
_backend_dir = str(_Path(__file__).parent)
if _backend_dir not in sys.path:
sys.path.insert(0, _backend_dir)
# Fix for Anaconda/conda-forge Python: seed platform._sys_version_cache before
# any library imports that trigger attrs -> rich -> structlog -> platform crash.
# See: https://github.com/python/cpython/issues/102396
import _platform_compat # noqa: F401
import mimetypes
import shutil
import warnings
from contextlib import asynccontextmanager
from importlib.metadata import PackageNotFoundError, version as package_version
# Fix broken Windows registry MIME types. Some Windows installs map .js to
# "text/plain" in the registry (HKCR\.js\Content Type). Python's mimetypes
# module reads from the registry, and FastAPI/Starlette's StaticFiles uses
# mimetypes.guess_type() to set Content-Type headers. Browsers enforce strict
# MIME checking for ES module scripts (<script type="module">) and will refuse
# to execute .js files served as text/plain — resulting in a blank page.
# Calling add_type() *before* StaticFiles is instantiated ensures the correct
# types are used regardless of the OS registry.
if sys.platform == "win32":
mimetypes.add_type("application/javascript", ".js")
mimetypes.add_type("text/css", ".css")
# Suppress annoying dependency warnings in production
if os.getenv("ENVIRONMENT_TYPE", "production") == "production":
warnings.filterwarnings("ignore")
# Alternatively, you can be more specific:
# warnings.filterwarnings("ignore", category=DeprecationWarning)
# warnings.filterwarnings("ignore", module="triton.*")
from fastapi import Depends, FastAPI, Request
from fastapi.middleware.cors import CORSMiddleware
from fastapi.staticfiles import StaticFiles
from fastapi.responses import FileResponse, HTMLResponse, Response
from pathlib import Path
from datetime import datetime
# Import routers
from routes import (
auth_router,
data_recipe_router,
datasets_router,
export_router,
inference_router,
inference_studio_router,
models_router,
training_history_router,
training_router,
)
from auth import storage
from auth.authentication import get_current_subject
from utils.hardware import (
detect_hardware,
get_device,
DeviceType,
get_backend_visible_gpu_info,
)
import utils.hardware.hardware as _hw_module
from utils.cache_cleanup import clear_unsloth_compiled_cache
from utils.native_path_leases import native_path_leases_supported
def get_unsloth_version() -> str:
try:
return package_version("unsloth")
except PackageNotFoundError:
pass
version_file = (
_Path(__file__).resolve().parents[2] / "unsloth" / "models" / "_utils.py"
)
try:
for line in version_file.read_text(encoding = "utf-8").splitlines():
if line.startswith("__version__ = "):
return line.split("=", 1)[1].strip().strip('"').strip("'")
except OSError:
pass
return "dev"
UNSLOTH_VERSION = get_unsloth_version()
@asynccontextmanager
async def lifespan(app: FastAPI):
"""Startup: detect hardware, seed default admin if needed. Shutdown: clean up compiled cache."""
# Clean up any stale compiled cache from previous runs
clear_unsloth_compiled_cache()
# Remove stale .venv_overlay from previous versions — no longer used.
# Version switching now uses .venv_t5/ (pre-installed by setup.sh).
overlay_dir = Path(__file__).resolve().parent.parent.parent / ".venv_overlay"
if overlay_dir.is_dir():
shutil.rmtree(overlay_dir, ignore_errors = True)
# Detect hardware first — sets DEVICE global used everywhere
detect_hardware()
from storage.studio_db import cleanup_orphaned_runs
try:
cleanup_orphaned_runs()
except Exception as exc:
import structlog
structlog.get_logger(__name__).warning(
"cleanup_orphaned_runs failed at startup: %s", exc
)
# Pre-cache the helper GGUF model for LLM-assisted dataset detection.
# Runs in a background thread so it doesn't block server startup.
import threading
def _precache():
try:
from utils.datasets.llm_assist import precache_helper_gguf
precache_helper_gguf()
except Exception:
pass # non-critical
threading.Thread(target = _precache, daemon = True).start()
if storage.ensure_default_admin():
bootstrap_pw = storage.get_bootstrap_password()
app.state.bootstrap_password = bootstrap_pw
bootstrap_path = storage.DB_PATH.parent / ".bootstrap_password"
print("\n" + "=" * 60)
print("DEFAULT ADMIN ACCOUNT CREATED")
print(f" username: {storage.DEFAULT_ADMIN_USERNAME}")
print(f" password saved to: {bootstrap_path}")
print(" Open the Studio UI to sign in and change it.")
print("=" * 60 + "\n")
else:
app.state.bootstrap_password = storage.get_bootstrap_password()
yield
# Cleanup
_hw_module.DEVICE = None
clear_unsloth_compiled_cache()
# Create FastAPI app
app = FastAPI(
title = "Unsloth UI Backend",
version = UNSLOTH_VERSION,
description = "Backend API for Unsloth UI - Training and Model Management",
lifespan = lifespan,
)
# Initialize structured logging
from loggers.config import LogConfig
from loggers.handlers import LoggingMiddleware
logger = LogConfig.setup_logging(
service_name = "unsloth-studio-backend",
env = os.getenv("ENVIRONMENT_TYPE", "production"),
)
app.add_middleware(LoggingMiddleware)
# CORS middleware
_api_only = os.environ.get("UNSLOTH_API_ONLY") == "1"
_cors_origins = ["*"]
if _api_only:
_cors_origins = [
"tauri://localhost", # Linux/macOS Tauri webview
"http://tauri.localhost", # Windows Tauri webview
"http://localhost", # dev fallback
"http://localhost:5173", # Tauri dev/Vite
"http://127.0.0.1:5173", # Tauri dev/Vite fallback
]
_cors_origin_regex = None
else:
_cors_origin_regex = None
app.add_middleware(
CORSMiddleware,
allow_origins = _cors_origins,
allow_origin_regex = _cors_origin_regex,
allow_credentials = True,
allow_methods = ["*"],
allow_headers = ["*"],
)
# ============ Register API Routes ============
# Register routers
app.include_router(auth_router, prefix = "/api/auth", tags = ["auth"])
app.include_router(training_router, prefix = "/api/train", tags = ["training"])
app.include_router(models_router, prefix = "/api/models", tags = ["models"])
app.include_router(inference_router, prefix = "/api/inference", tags = ["inference"])
# Studio-only inference endpoints (cancel, etc.) are intentionally NOT
# exposed on the /v1 OpenAI-compat prefix below.
app.include_router(inference_studio_router, prefix = "/api/inference", tags = ["inference"])
# OpenAI-compatible endpoints: mount the same inference router at /v1
# so external tools (Open WebUI, SillyTavern, etc.) can use the
# standard /v1/chat/completions path.
app.include_router(inference_router, prefix = "/v1", tags = ["openai-compat"])
app.include_router(datasets_router, prefix = "/api/datasets", tags = ["datasets"])
app.include_router(data_recipe_router, prefix = "/api/data-recipe", tags = ["data-recipe"])
app.include_router(export_router, prefix = "/api/export", tags = ["export"])
app.include_router(
training_history_router, prefix = "/api/train", tags = ["training-history"]
)
# ============ Health and System Endpoints ============
@app.get("/api/health")
async def health_check():
"""Health check endpoint"""
platform_map = {"darwin": "mac", "win32": "windows", "linux": "linux"}
device_type = platform_map.get(sys.platform, sys.platform)
return {
"status": "healthy",
"timestamp": datetime.now().isoformat(),
"service": "Unsloth UI Backend",
"version": UNSLOTH_VERSION,
"device_type": device_type,
"chat_only": _hw_module.CHAT_ONLY,
"desktop_protocol_version": 1,
"supports_desktop_auth": True,
"native_path_leases_supported": native_path_leases_supported(),
}
@app.post("/api/shutdown")
async def shutdown_server(
request: Request,
current_subject: str = Depends(get_current_subject),
):
"""Gracefully shut down the Unsloth Studio server.
Called by the frontend quit dialog so users can stop the server from the UI
without needing to use the CLI or kill the process manually.
"""
import asyncio
async def _delayed_shutdown():
await asyncio.sleep(0.2) # Let the HTTP response return first
trigger = getattr(request.app.state, "trigger_shutdown", None)
if trigger is not None:
trigger()
else:
# Fallback when not launched via run_server() (e.g. direct uvicorn)
import signal
import os
os.kill(os.getpid(), signal.SIGTERM)
request.app.state._shutdown_task = asyncio.create_task(_delayed_shutdown())
return {"status": "shutting_down"}
@app.get("/api/system")
async def get_system_info():
"""Get system information"""
import platform
import psutil
from utils.hardware import get_device
from utils.hardware.hardware import _backend_label
visibility_info = get_backend_visible_gpu_info()
gpu_info = {
"available": visibility_info["available"],
"devices": visibility_info["devices"],
}
# CPU & Memory
memory = psutil.virtual_memory()
return {
"platform": platform.platform(),
"python_version": platform.python_version(),
# Use the centralized _backend_label helper so the /api/system
# endpoint reports "rocm" on AMD hosts instead of "cuda", matching
# the /api/hardware and /api/gpu-visibility endpoints.
"device_backend": _backend_label(get_device()),
"cpu_count": psutil.cpu_count(),
"memory": {
"total_gb": round(memory.total / 1e9, 2),
"available_gb": round(memory.available / 1e9, 2),
"percent_used": memory.percent,
},
"gpu": gpu_info,
}
@app.get("/api/system/gpu-visibility")
async def get_gpu_visibility(
current_subject: str = Depends(get_current_subject),
):
return get_backend_visible_gpu_info()
@app.get("/api/system/hardware")
async def get_hardware_info():
"""Return GPU name, total VRAM, and key ML package versions."""
from utils.hardware import get_gpu_summary, get_package_versions
return {
"gpu": get_gpu_summary(),
"versions": get_package_versions(),
}
# ============ Serve Frontend (Optional) ============
def _strip_crossorigin(html_bytes: bytes) -> bytes:
"""Remove ``crossorigin`` attributes from script/link tags.
Vite adds ``crossorigin`` by default which forces CORS mode on font
subresource loads. When Studio is served over plain HTTP, Firefox
HTTPS-Only Mode does not exempt CORS font requests -- causing all
@font-face downloads to fail silently. Stripping the attribute
makes them regular same-origin fetches that work on any protocol.
"""
import re as _re
html = html_bytes.decode("utf-8")
html = _re.sub(r'\s+crossorigin(?:="[^"]*")?', "", html)
return html.encode("utf-8")
def _inject_bootstrap(html_bytes: bytes, app: FastAPI) -> bytes:
"""Inject bootstrap credentials into HTML when password change is required.
The script tag is only injected while the default admin account still
has ``must_change_password=True``. Once the user changes the password
the HTML is served clean — no credentials leak.
"""
import json as _json
if not storage.requires_password_change(storage.DEFAULT_ADMIN_USERNAME):
return html_bytes
bootstrap_pw = getattr(app.state, "bootstrap_password", None)
if not bootstrap_pw:
return html_bytes
payload = _json.dumps(
{
"username": storage.DEFAULT_ADMIN_USERNAME,
"password": bootstrap_pw,
}
)
tag = f"<script>window.__UNSLOTH_BOOTSTRAP__={payload}</script>"
html = html_bytes.decode("utf-8")
html = html.replace("</head>", f"{tag}</head>", 1)
return html.encode("utf-8")
def setup_frontend(app: FastAPI, build_path: Path):
"""Mount frontend static files (optional)"""
if not build_path.exists():
return False
# Mount assets
assets_dir = build_path / "assets"
if assets_dir.exists():
app.mount("/assets", StaticFiles(directory = assets_dir), name = "assets")
@app.get("/")
async def serve_root():
content = (build_path / "index.html").read_bytes()
content = _strip_crossorigin(content)
content = _inject_bootstrap(content, app)
return Response(
content = content,
media_type = "text/html",
headers = {"Cache-Control": "no-cache, no-store, must-revalidate"},
)
@app.get("/{full_path:path}")
async def serve_frontend(full_path: str):
if full_path in {"api", "v1"} or full_path.startswith(("api/", "v1/")):
return {"error": "API endpoint not found"}
file_path = (build_path / full_path).resolve()
# Block path traversal — ensure resolved path stays inside build_path
if not file_path.is_relative_to(build_path.resolve()):
return Response(status_code = 403)
if file_path.is_file():
return FileResponse(file_path)
# Serve index.html as bytes — avoids Content-Length mismatch
content = (build_path / "index.html").read_bytes()
content = _strip_crossorigin(content)
content = _inject_bootstrap(content, app)
return Response(
content = content,
media_type = "text/html",
headers = {"Cache-Control": "no-cache, no-store, must-revalidate"},
)
return True