* CLI: stop `unsloth connect` from leaking Studio credentials to unverified servers
`unsloth connect` (and `unsloth chat`) discovered a Studio base URL from
UNSLOTH_STUDIO_URL or the default localhost port after only an unauthenticated
/api/health probe, then sent credentials to it:
- keyless connect iterated every cached API key and sent each as a bearer token
to {base}/v1/models, so a malicious or port-preempting endpoint could harvest
all of them;
- with no cached key it self-issued a Studio JWT and POSTed it to
{base}/api/auth/api-keys;
- unsloth chat sent the same self-issued JWT to the discovered base.
The key cache was a flat, global list with no binding to a server identity, so a
key minted for one Studio could be replayed to any other.
Changes:
- Scope the agent key cache per base URL so a key is only ever replayed to the
exact server it was minted for. Pre-scoping flat caches are ignored rather
than replayed (at most one extra local mint on the next launch).
- Gate every automatic credential flow to loopback bases. A non-loopback
UNSLOTH_STUDIO_URL now requires an explicit --api-key and nothing is sent
automatically. SSH-tunnelled Studios that land on 127.0.0.1 keep working.
- Mint the API key locally against the Studio auth DB instead of POSTing a
self-issued JWT over the network, so no bearer token leaves the process on the
local path.
- Apply the same loopback gate to connect_studio_server (used by unsloth chat).
Fully closing same-host loopback-port preemption needs a signed /api/health
handshake so the client can verify the server identity before sending anything;
that is tracked as a server-side follow-up.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* CLI: verify Studio server identity before auto-sending credentials
Adds a challenge-response so `unsloth connect` and `unsloth chat` can confirm a
discovered loopback endpoint is really this install's Studio (not a process
that preempted the port) before sending it a cached or freshly minted
credential. This closes the same-host loopback-preemption gap left open by the
previous commit, which could only limit the blast radius.
Server:
- storage.get_or_create_identity_secret(): a dedicated server-wide secret in
app_secrets (kept separate from the per-user JWT secret), readable only by
the same OS user.
- storage.compute_identity_proof(nonce) = HMAC-SHA256(identity secret, nonce).
- GET /api/auth/identity?nonce=<base64url>: unauthenticated, returns the proof.
The nonce is opaque to the server and the proof reveals nothing about the
secret, so answering is safe.
Client:
- verify_studio_identity(base): sends a fresh 32-byte nonce, recomputes the
expected HMAC from the local same-user secret, and constant-time compares.
Fails closed on any error.
- connect._agent_api_key gates the loopback cached-key replay and the local
mint on it; connect_studio_server (used by unsloth chat) gates the
self-issued JWT on it.
A server that cannot read this install's secret (a different OS user, or a
remote/fake endpoint) cannot produce a matching proof, so the client refuses
and falls back to an explicit --api-key.
Tests: studio/backend/tests/test_identity.py (proof determinism, secret
persistence and caching, route response and nonce validation) and additions to
test_connect.py (the verify gate refuses when unverified, an explicit key skips
the check, and an end-to-end client plus server handshake against a stub HTTP
server).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* CLI: mint through the verified server instead of the local auth DB
CodeQL (py/clear-text-storage-sensitive-data) flagged the API key written to
the per-server cache and the agent config files once it was sourced from
storage.create_api_key(); the original HTTP-minted key did not trip the query.
Now that the identity handshake cryptographically confirms the loopback
responder really is this Studio before anything is sent, minting through the
server's /api/auth/api-keys endpoint with a self-issued JWT is safe again and
restores the original, CodeQL-clean data flow. The local-DB mint path is
removed.
The security properties are unchanged: discovery is still loopback-gated and
identity-verified, the key cache is still scoped per server, and a credential
reaches the server only after the handshake has proven its identity. The only
difference from the previous commit is that the self-issued JWT is sent to the
already-verified loopback server rather than the key being minted in-process.
Tests updated to mint through the fake server again.
* CLI: address review feedback on connect credential handling
- Reuse a saved per-server key before the loopback/identity gate. Keys are
scoped per base URL, so a key the user saved with --api-key for a remote or
SSH-tunnelled Studio (whose identity secret the local handshake can't match)
is replayed only to that exact server. The loopback + identity-handshake gate
now guards just auto-minting (self-issuing a JWT and creating a new key),
which is the path that needs a cryptographically verified local Studio. Fixes
keyless reuse being impossible for remote/tunnelled Studios the user had
saved a key for.
- connect_studio_server (unsloth chat / inference): when the user explicitly set
UNSLOTH_STUDIO_URL but the server can't be safely attached (non-loopback, or
identity unverifiable), fail with a clear message instead of silently loading
the model locally. Opportunistic discovery of the local default still falls
back to a local load.
- Harden cache parsing: tolerate a corrupt or hand-edited cache where a base
maps to a non-list (which would otherwise iterate a string into
single-character "keys"), and read the cache as UTF-8.
Tests updated and added: saved-key replay without the handshake for both local
and remote bases, keyless mint still refused when the loopback server is
unverified, and connect_studio_server erroring on an explicit remote while
falling back locally on default discovery.
* CLI: harden connect handshake against relay and gate cached minted keys
Addresses review feedback on the credential handshake:
- Refuse HTTP redirects on credential-bearing requests (the identity handshake,
/v1/models, key minting, and the chat HTTP backend). A process squatting the
discovered port could 302 /api/auth/identity to the real Studio and relay its
valid proof, or bounce a bearer-token request to another base, and urllib
follows redirects by default. A shared no-redirect opener now treats any 3xx
as an error.
- Give cached keys provenance. Keys the user supplied with --api-key are "saved"
and replay without the handshake (needed for remote or SSH-tunnelled Studios
whose secret the local handshake can't match). Keys we auto-mint are "minted"
and replay only after the identity handshake, so a port squatter can't collect
a previously minted localhost key just by answering the health check. New cache
shape: servers[base] = {"saved": [...], "minted": [...]}.
Known residual: a different-OS-user process that squats the port and can also
reach a genuine same-secret Studio elsewhere on loopback can still manually relay
the identity challenge. Fully closing that needs the proof bound to the server's
real listening port, or OS-level peer-credential checks; tracked as follow-up. A
same-user attacker is out of scope, since it can already read the 0600 key cache.
Tests: redirect rejection in the handshake, minted-cache requiring the handshake
while saved-cache bypasses it, and the existing suites updated for the new cache
shape. unsloth_cli (206) and test_identity.py (5) pass.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* CLI: keep urllib imports function-local in the no-redirect opener
The repo's import-hoist safety linter (scripts/verify_import_hoist.py) flags
hoisting urllib to module level because it re-points the 'urllib' name in the
pre-existing HttpChatBackend._request scope. Build the no-redirect opener lazily
with function-local urllib imports instead, matching this module's convention,
and restore the local 'import urllib.request' in _request and
verify_studio_identity.
* test(identity): skip route tests when routes.auth import chain is unavailable
The identity route tests build a TestClient from routes.auth, which pulls the
whole routes package (routes/__init__ -> inference -> llama_cpp, ...). In a
minimal test matrix without the heavy backend deps, or when another test in the
same process has already broken that import chain, importing it raised and the
two route tests hard-failed. Skip in that case instead: the proof crypto is
covered by the storage-level tests, and the full backend CI still exercises the
route. No behaviour change where the deps are present (5 passed in isolation).
* test(connect): make connect tests pass on native Windows
unsloth connect supports Windows: --no-launch prints PowerShell ($env:X =
"v" / Remove-Item Env:X) instead of POSIX (export/unset), and the launch
path bridges env into a Windows agent .exe over WSLENV. The tests hardcoded
the POSIX shell forms, so on a real windows-latest runner 12 of them failed on
the assertion string even though every command exited 0.
Add OS-aware assertion helpers (_assert_env_set / _assert_env_unset) that check
the right shell syntax for the host OS, and skip the two WSL-from-Linux shim
tests on native Windows (os.name is 'posix' inside WSL, so that path can't run
there). No change on Linux/macOS (57 passed); the connect command's behaviour
is untouched. Validated on a windows-latest staging runner.
* style(connect): tighten comments in the credential-leak fix
Condense the verbose explanatory comments and multi-line docstrings added by
this PR to one or two lines each, drop a few that just restated the code, and
keep the security rationale where it is load-bearing. Comment/whitespace only;
verified with unslothai/scripts comment_tools.py (check --strip-docstrings:
6/6 'code unchanged'). Tests unchanged: connect 57 passed, identity 5 passed.
* CLI/Studio: harden the identity handshake (review round)
Addresses the latest Codex/Gemini review of the handshake:
- Store the identity secret privately. sqlite3.connect created the auth DB
world-readable under a 022 umask, so another OS user could read app_secrets
and forge proofs, defeating the same-user assumption the handshake rests on.
The auth dir and DB are now restricted to owner-only (0700/0600); the JWT
secret and password hashes there get the same protection.
- Bind the proof to the server's listening port. The stateless HMAC(secret,
nonce) was relayable: a process squatting the discovered port could proxy the
challenge to the real Studio on another port and pass it back. The proof now
covers the port the server actually listens on (from the socket, never the
Host header) and the client checks it against the port it connected to, so a
relayed proof from a different port no longer matches. Closes the manual-relay
residual left after the redirect fix.
- Cap the identity response read (the server is still unverified at that point)
and serve the identity route from a sync def so its first-call SQLite read
runs in the threadpool instead of the event loop.
Tests: port-bound proof + relayed-proof rejection added; identity (5) and
unsloth_cli (58) suites pass. Verified end to end against a real backend
(auth DB owner-only, handshake + mint still succeed).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* CLI/Studio: bind the identity proof to the connection address, not just port
Follow-up to the port binding from the last review. Binding only to the port
left a cross-address relay: a squatter on a different loopback address but the
same port (for example localhost resolving to a squatter on ::1 while the real
Studio is on 127.0.0.1) could proxy the nonce to the real Studio and pass back
a proof that still matched, since both share the port.
The proof now covers the address and the port the connection landed on:
- Server: takes the address+port from request.scope, which uvicorn populates
from getsockname, so it is the real local address the client reached even
when Studio is bound to 0.0.0.0 (verified empirically), never the
client-controlled Host header.
- Client: resolves the base host to one concrete IP, talks to exactly that IP,
and binds the proof to (IP, port). A proof relayed from a Studio on a
different address or port was computed for that other endpoint and no longer
matches the one the client dialed.
Both sides normalise the address through ipaddress so equivalent forms compare
equal. Together with the private-secret and redirect fixes, this closes the
cross-user loopback relay an attacker can mount without reading the secret.
Tests: proof now bound to host+port; relayed-proof rejection retained; identity
(5) and unsloth_cli (58) suites pass. Verified end to end against a real backend
(handshake + mint still succeed).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* CLI: pick the loopback address at discovery so localhost does not regress
find_studio_server now resolves a bare localhost base to its concrete loopback
addresses and returns the first that answers /api/health, IPv4 127.0.0.1 first
(where unsloth studio binds by default). The whole flow (health probe, identity
check, credential send) then targets that one address instead of racing
IPv4/IPv6 resolution, where localhost could resolve ::1-first and hide a Studio
bound to 127.0.0.1. A literal IP or remote name is unchanged.
* [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>
456 lines
17 KiB
Python
456 lines
17 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
|
|
|
|
"""Authentication API routes."""
|
|
|
|
from fastapi import APIRouter, Depends, HTTPException, Request, Response, status
|
|
|
|
import base64
|
|
import ipaddress
|
|
import os
|
|
import shlex
|
|
import sys
|
|
import threading
|
|
import time
|
|
from collections import deque
|
|
from datetime import datetime, timedelta, timezone
|
|
|
|
from models.auth import (
|
|
ApiKeyListResponse,
|
|
ApiKeyResponse,
|
|
AuthLoginRequest,
|
|
AuthStatusResponse,
|
|
ChangePasswordRequest,
|
|
CreateApiKeyRequest,
|
|
CreateApiKeyResponse,
|
|
DesktopLoginRequest,
|
|
RefreshTokenRequest,
|
|
)
|
|
from models.users import Token
|
|
from auth import storage, hashing
|
|
from auth.authentication import (
|
|
create_access_token,
|
|
create_refresh_token,
|
|
get_current_subject,
|
|
get_current_subject_allow_password_change,
|
|
refresh_access_token,
|
|
)
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
def _reset_password_command() -> str:
|
|
"""Shell command shown in the 'incorrect password' hint.
|
|
|
|
Prefer the absolute path to this install's ``unsloth`` launcher (sibling of
|
|
the running interpreter) so the hint works even when its dir isn't on PATH.
|
|
|
|
POSIX paths are shell-quoted. On Windows we use the bare absolute path only
|
|
when it has no spaces (a quoted path differs between cmd and PowerShell);
|
|
otherwise, or if the launcher can't be located, fall back to the PATH form.
|
|
"""
|
|
try:
|
|
bin_dir = os.path.dirname(os.path.abspath(sys.executable))
|
|
if os.name == "nt":
|
|
exe = os.path.join(bin_dir, "unsloth.exe")
|
|
if os.path.isfile(exe) and " " not in exe:
|
|
return f"{exe} studio reset-password"
|
|
else:
|
|
exe = os.path.join(bin_dir, "unsloth")
|
|
if os.path.isfile(exe):
|
|
return f"{shlex.quote(exe)} studio reset-password"
|
|
except Exception:
|
|
pass
|
|
return "unsloth studio reset-password"
|
|
|
|
|
|
# Per-(ip, username) bucket + per-IP aggregate. Account bucket stops one user's
|
|
# typos from blocking others; the aggregate stops username-rotation spray.
|
|
# Single-process only; multi-worker deployments need a shared store.
|
|
_LOGIN_BUCKETS: dict[tuple[str, str], deque] = {}
|
|
_LOGIN_IP_BUCKETS: dict[str, deque] = {}
|
|
_LOGIN_BUCKETS_LOCK = threading.Lock()
|
|
_LOGIN_WINDOW_SECONDS = 60.0
|
|
_LOGIN_MAX_FAILS = 5
|
|
_LOGIN_IP_MAX_FAILS = 30
|
|
_LOGIN_LOCKOUT_SECONDS = 60
|
|
# Bucket-dict cap. On overflow, prune stale entries; if still full the failure
|
|
# folds into the per-IP aggregate only.
|
|
_LOGIN_MAX_BUCKETS = 4096
|
|
# Unrepresentable as a real username (leading NUL); folds unknown-user attempts
|
|
# into one slot so attacker cardinality can't blow the bucket dict.
|
|
_UNKNOWN_LOGIN_USER = "\x00unknown-user"
|
|
|
|
|
|
def _trust_forwarded_for() -> bool:
|
|
"""Honour X-Forwarded-For only when UNSLOTH_STUDIO_TRUST_FORWARDED is set.
|
|
|
|
Off by default so a direct caller can't spoof the header.
|
|
"""
|
|
return os.environ.get("UNSLOTH_STUDIO_TRUST_FORWARDED", "").lower() in (
|
|
"1",
|
|
"true",
|
|
"yes",
|
|
)
|
|
|
|
|
|
def _normalize_forwarded_addr(value: str) -> str:
|
|
"""Parse an XFF / Forwarded `for=` value into a bare IP (port-stripped)."""
|
|
value = (value or "").strip().strip('"')
|
|
if not value or value.lower() == "unknown":
|
|
return ""
|
|
if value.startswith("["):
|
|
# Bracketed IPv6, optionally with port.
|
|
end = value.find("]")
|
|
if end <= 0:
|
|
return ""
|
|
host = value[1:end]
|
|
elif value.count(":") == 1:
|
|
# IPv4:port. Bare IPv6 has multiple colons → else branch.
|
|
head, _, tail = value.rpartition(":")
|
|
host = head if tail.isdigit() and head else value
|
|
else:
|
|
host = value
|
|
try:
|
|
return str(ipaddress.ip_address(host))
|
|
except ValueError:
|
|
return ""
|
|
|
|
|
|
def _forwarded_for_from_element(element: str) -> str:
|
|
"""Pick the `for=` token out of a single ``Forwarded`` element."""
|
|
for tok in element.split(";"):
|
|
key, sep, val = tok.strip().partition("=")
|
|
if sep and key.lower() == "for":
|
|
return _normalize_forwarded_addr(val)
|
|
return ""
|
|
|
|
|
|
def _client_ip(request: Request | None) -> str:
|
|
if request is None:
|
|
return "_unknown"
|
|
if _trust_forwarded_for():
|
|
xff = request.headers.get("x-forwarded-for", "")
|
|
if xff:
|
|
# First entry is the originating client.
|
|
normalized = _normalize_forwarded_addr(xff.split(",", 1)[0])
|
|
if normalized:
|
|
return normalized
|
|
fwd = request.headers.get("forwarded", "")
|
|
if fwd:
|
|
# First element only; multi-element headers can't fork buckets.
|
|
normalized = _forwarded_for_from_element(fwd.split(",", 1)[0])
|
|
if normalized:
|
|
return normalized
|
|
return (request.client.host if request.client else None) or "_unknown"
|
|
|
|
|
|
def _bucket_key(request: Request | None, username: str) -> tuple[str, str]:
|
|
return (_client_ip(request), (username or "").casefold())
|
|
|
|
|
|
def _unknown_user_key(request: Request | None) -> tuple[str, str]:
|
|
return (_client_ip(request), _UNKNOWN_LOGIN_USER)
|
|
|
|
|
|
def _prune_bucket(bucket: deque, now: float) -> None:
|
|
while bucket and now - bucket[0] > _LOGIN_WINDOW_SECONDS:
|
|
bucket.popleft()
|
|
|
|
|
|
def _prune_stale_buckets(now: float) -> None:
|
|
"""Drop empty / expired account buckets to bound memory under spray."""
|
|
stale: list[tuple[str, str]] = []
|
|
for key, bucket in _LOGIN_BUCKETS.items():
|
|
_prune_bucket(bucket, now)
|
|
if not bucket:
|
|
stale.append(key)
|
|
for key in stale:
|
|
_LOGIN_BUCKETS.pop(key, None)
|
|
|
|
|
|
def _record_login_failure(key: tuple[str, str]) -> int:
|
|
now = time.monotonic()
|
|
ip, _username = key
|
|
with _LOGIN_BUCKETS_LOCK:
|
|
ip_bucket = _LOGIN_IP_BUCKETS.setdefault(ip, deque())
|
|
_prune_bucket(ip_bucket, now)
|
|
ip_bucket.append(now)
|
|
|
|
if key not in _LOGIN_BUCKETS and len(_LOGIN_BUCKETS) >= _LOGIN_MAX_BUCKETS:
|
|
_prune_stale_buckets(now)
|
|
if key in _LOGIN_BUCKETS or len(_LOGIN_BUCKETS) < _LOGIN_MAX_BUCKETS:
|
|
account_bucket = _LOGIN_BUCKETS.setdefault(key, deque())
|
|
_prune_bucket(account_bucket, now)
|
|
account_bucket.append(now)
|
|
return len(account_bucket)
|
|
# Bucket dict at cap; per-IP cap still applies via ip_bucket.
|
|
return len(ip_bucket)
|
|
|
|
|
|
def _blocked_for(bucket: deque | None, now: float, max_fails: int) -> int:
|
|
if not bucket:
|
|
return 0
|
|
_prune_bucket(bucket, now)
|
|
if len(bucket) >= max_fails:
|
|
return max(1, int(_LOGIN_WINDOW_SECONDS - (now - bucket[0])))
|
|
return 0
|
|
|
|
|
|
def _login_blocked(key: tuple[str, str]) -> int:
|
|
"""Return seconds until the next attempt is allowed, or 0."""
|
|
now = time.monotonic()
|
|
ip, _username = key
|
|
with _LOGIN_BUCKETS_LOCK:
|
|
return max(
|
|
_blocked_for(_LOGIN_BUCKETS.get(key), now, _LOGIN_MAX_FAILS),
|
|
_blocked_for(_LOGIN_IP_BUCKETS.get(ip), now, _LOGIN_IP_MAX_FAILS),
|
|
)
|
|
|
|
|
|
def _clear_login_bucket(key: tuple[str, str]) -> None:
|
|
ip, _username = key
|
|
with _LOGIN_BUCKETS_LOCK:
|
|
_LOGIN_BUCKETS.pop(key, None)
|
|
_LOGIN_IP_BUCKETS.pop(ip, None)
|
|
|
|
|
|
# Sync def (not async): compute_identity_proof touches SQLite on the first call,
|
|
# so FastAPI runs it in the threadpool rather than blocking the event loop.
|
|
@router.get("/identity")
|
|
def identity(nonce: str, request: Request) -> dict:
|
|
"""Challenge-response proof this is the real local Studio: caller sends a nonce,
|
|
gets HMAC(install identity secret, nonce, connection address + port).
|
|
Unauthenticated and side-effect free; a process that can't read the same-user
|
|
secret can't forge a proof, and binding to the address/port the connection
|
|
landed on stops a squatter relaying a proof from the real Studio elsewhere."""
|
|
try:
|
|
raw = base64.urlsafe_b64decode(nonce)
|
|
except Exception:
|
|
raise HTTPException(
|
|
status_code = status.HTTP_400_BAD_REQUEST, detail = "nonce must be base64url"
|
|
)
|
|
if not 16 <= len(raw) <= 128:
|
|
raise HTTPException(
|
|
status_code = status.HTTP_400_BAD_REQUEST, detail = "nonce must decode to 16-128 bytes"
|
|
)
|
|
# The address + port the connection actually landed on, from the socket
|
|
# (request.scope is getsockname, so it is the real local address even when
|
|
# bound to 0.0.0.0), never the client-controlled Host header.
|
|
server = request.scope.get("server") or ("", 0)
|
|
host = server[0] or ""
|
|
port = server[1] if server[1] is not None else 0
|
|
return {"proof": storage.compute_identity_proof(raw, host, port)}
|
|
|
|
|
|
@router.get("/status", response_model = AuthStatusResponse)
|
|
async def auth_status() -> AuthStatusResponse:
|
|
"""Auth initialization state; ``default_username`` is exposed for first-boot UI prefill only."""
|
|
return AuthStatusResponse(
|
|
initialized = storage.is_initialized(),
|
|
default_username = storage.DEFAULT_ADMIN_USERNAME,
|
|
requires_password_change = storage.requires_password_change(storage.DEFAULT_ADMIN_USERNAME)
|
|
if storage.is_initialized()
|
|
else True,
|
|
)
|
|
|
|
|
|
@router.post("/login", response_model = Token)
|
|
async def login(payload: AuthLoginRequest, request: Request) -> Token:
|
|
"""Login with username/password. Per-account + per-IP rate-limited."""
|
|
key = _bucket_key(request, payload.username)
|
|
unknown_key = _unknown_user_key(request)
|
|
blocked_for = max(_login_blocked(key), _login_blocked(unknown_key))
|
|
if blocked_for > 0:
|
|
raise HTTPException(
|
|
status_code = status.HTTP_429_TOO_MANY_REQUESTS,
|
|
# IP not interpolated into the body; behind a proxy/NAT it's
|
|
# misleading or an info leak.
|
|
detail = (f"Too many failed login attempts. " f"Try again in {blocked_for} seconds."),
|
|
headers = {"Retry-After": str(blocked_for)},
|
|
)
|
|
|
|
record = storage.get_user_and_secret(payload.username)
|
|
if record is None:
|
|
# Record under one sentinel key per IP so attacker-controlled username
|
|
# cardinality can't allocate unbounded buckets.
|
|
_record_login_failure(unknown_key)
|
|
raise HTTPException(
|
|
status_code = status.HTTP_401_UNAUTHORIZED,
|
|
detail = f"Incorrect password. To reset it, run this in your terminal: {_reset_password_command()}",
|
|
)
|
|
|
|
salt, pwd_hash, _jwt_secret, must_change_password = record
|
|
if not hashing.verify_password(payload.password, salt, pwd_hash):
|
|
_record_login_failure(key)
|
|
raise HTTPException(
|
|
status_code = status.HTTP_401_UNAUTHORIZED,
|
|
detail = f"Incorrect password. To reset it, run this in your terminal: {_reset_password_command()}",
|
|
)
|
|
|
|
_clear_login_bucket(key)
|
|
_clear_login_bucket(unknown_key)
|
|
access_token = create_access_token(subject = payload.username)
|
|
refresh_token = create_refresh_token(subject = payload.username)
|
|
return Token(
|
|
access_token = access_token,
|
|
refresh_token = refresh_token,
|
|
token_type = "bearer",
|
|
must_change_password = must_change_password,
|
|
)
|
|
|
|
|
|
@router.post("/logout", status_code = status.HTTP_204_NO_CONTENT)
|
|
async def logout(
|
|
request: Request, current_subject: str = Depends(get_current_subject_allow_password_change)
|
|
) -> Response:
|
|
"""Revoke refresh tokens for the subject; the access token is stateless and expires on its own."""
|
|
try:
|
|
storage.revoke_user_refresh_tokens(current_subject)
|
|
except Exception:
|
|
pass
|
|
try:
|
|
request.app.state.bootstrap_password = None
|
|
except AttributeError:
|
|
pass
|
|
return Response(status_code = status.HTTP_204_NO_CONTENT)
|
|
|
|
|
|
@router.post("/desktop-login", response_model = Token)
|
|
async def desktop_login(payload: DesktopLoginRequest) -> Token:
|
|
"""Exchange a local desktop secret for normal admin-subject tokens."""
|
|
username = storage.validate_desktop_secret(payload.secret)
|
|
if username is None:
|
|
raise HTTPException(
|
|
status_code = status.HTTP_401_UNAUTHORIZED,
|
|
detail = "Desktop authentication failed",
|
|
)
|
|
|
|
return Token(
|
|
access_token = create_access_token(subject = username, desktop = True),
|
|
refresh_token = create_refresh_token(subject = username, desktop = True),
|
|
token_type = "bearer",
|
|
must_change_password = False,
|
|
)
|
|
|
|
|
|
@router.post("/refresh", response_model = Token)
|
|
async def refresh(payload: RefreshTokenRequest) -> Token:
|
|
"""Exchange a refresh token for a new access+refresh pair (single-use)."""
|
|
consumed = storage.consume_refresh_token(payload.refresh_token)
|
|
if consumed is None:
|
|
raise HTTPException(
|
|
status_code = status.HTTP_401_UNAUTHORIZED,
|
|
detail = "Invalid or expired refresh token",
|
|
)
|
|
username, is_desktop = consumed
|
|
new_access_token = create_access_token(subject = username, desktop = is_desktop)
|
|
new_refresh_token = create_refresh_token(subject = username, desktop = is_desktop)
|
|
|
|
return Token(
|
|
access_token = new_access_token,
|
|
refresh_token = new_refresh_token,
|
|
token_type = "bearer",
|
|
must_change_password = False if is_desktop else storage.requires_password_change(username),
|
|
)
|
|
|
|
|
|
@router.post("/change-password", response_model = Token)
|
|
async def change_password(
|
|
payload: ChangePasswordRequest,
|
|
request: Request,
|
|
current_subject: str = Depends(get_current_subject_allow_password_change),
|
|
) -> Token:
|
|
"""Allow the authenticated user to replace the default password."""
|
|
record = storage.get_user_and_secret(current_subject)
|
|
if record is None:
|
|
raise HTTPException(
|
|
status_code = status.HTTP_401_UNAUTHORIZED,
|
|
detail = "User session is invalid",
|
|
)
|
|
|
|
salt, pwd_hash, _jwt_secret, _must_change_password = record
|
|
if not hashing.verify_password(payload.current_password, salt, pwd_hash):
|
|
raise HTTPException(
|
|
status_code = status.HTTP_401_UNAUTHORIZED,
|
|
detail = "Current password is incorrect",
|
|
)
|
|
if payload.current_password == payload.new_password:
|
|
raise HTTPException(
|
|
status_code = status.HTTP_400_BAD_REQUEST,
|
|
detail = "New password must be different from the current password",
|
|
)
|
|
|
|
storage.update_password(current_subject, payload.new_password)
|
|
storage.revoke_user_refresh_tokens(current_subject)
|
|
try:
|
|
request.app.state.bootstrap_password = None
|
|
except AttributeError:
|
|
pass
|
|
access_token = create_access_token(subject = current_subject)
|
|
refresh_token = create_refresh_token(subject = current_subject)
|
|
return Token(
|
|
access_token = access_token,
|
|
refresh_token = refresh_token,
|
|
token_type = "bearer",
|
|
must_change_password = False,
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# API key management
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def _row_to_api_key_response(row: dict) -> ApiKeyResponse:
|
|
return ApiKeyResponse(
|
|
id = row["id"],
|
|
name = row["name"],
|
|
key_prefix = row["key_prefix"],
|
|
created_at = row["created_at"],
|
|
last_used_at = row.get("last_used_at"),
|
|
expires_at = row.get("expires_at"),
|
|
is_active = bool(row["is_active"]),
|
|
)
|
|
|
|
|
|
@router.post("/api-keys", response_model = CreateApiKeyResponse)
|
|
async def create_api_key(
|
|
payload: CreateApiKeyRequest, current_subject: str = Depends(get_current_subject)
|
|
) -> CreateApiKeyResponse:
|
|
"""Create a new API key. The raw key is returned once and cannot be retrieved later."""
|
|
expires_at = None
|
|
if payload.expires_in_days is not None:
|
|
expires_at = (
|
|
datetime.now(timezone.utc) + timedelta(days = payload.expires_in_days)
|
|
).isoformat()
|
|
|
|
raw_key, row = storage.create_api_key(
|
|
username = current_subject,
|
|
name = payload.name,
|
|
expires_at = expires_at,
|
|
)
|
|
return CreateApiKeyResponse(
|
|
key = raw_key,
|
|
api_key = _row_to_api_key_response(row),
|
|
)
|
|
|
|
|
|
@router.get("/api-keys", response_model = ApiKeyListResponse)
|
|
async def list_api_keys(current_subject: str = Depends(get_current_subject)) -> ApiKeyListResponse:
|
|
"""List all API keys for the authenticated user (raw keys are never exposed)."""
|
|
rows = storage.list_api_keys(current_subject)
|
|
return ApiKeyListResponse(
|
|
api_keys = [_row_to_api_key_response(r) for r in rows],
|
|
)
|
|
|
|
|
|
@router.delete("/api-keys/{key_id}")
|
|
async def revoke_api_key(key_id: int, current_subject: str = Depends(get_current_subject)) -> dict:
|
|
"""Revoke (soft-delete) an API key."""
|
|
if not storage.revoke_api_key(current_subject, key_id):
|
|
raise HTTPException(
|
|
status_code = status.HTTP_404_NOT_FOUND,
|
|
detail = "API key not found",
|
|
)
|
|
return {"detail": "API key revoked"}
|