mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-27 01:22:18 +00:00
* feat(proxy): email alerts at configured percentages of a team member budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(alerting): label team member budget crossings as team member budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(auth): cover the team member alert dispatch from _check_team_member_budget
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(email): drop the emoji from the team member budget alert template
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): ignore team member alert thresholds outside 1 to 100 on both the backend and the dashboard
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): bound team member alert threshold key length before int parsing
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): drop the legacy covers marker from the team member alert test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(team): reject malformed team_member_max_budget_alert_emails on team writes
Thresholds outside 1-100, non-list recipients, and invalid emails now return 422 on
/team/new, /team/update and PATCH /team/{id} instead of being stored and silently
ignored. The value is stored canonically. Read-side LiteLLM_TeamTable is unchanged,
and the PATCH body stays a raw merge patch so a null threshold still deletes it.
* fix(auth): enforce and alert on team member budgets only in common_checks
The builder re-checked the team member budget inline before common_checks ran the same
check, so one request that crossed a team_member_max_budget_alert_emails threshold
dispatched two alerts. Drop the inline check; common_checks is the single authorization
point and already covers per-member rows, the team default member budget, zero-cost
skips and the cross-pod spend counter. Its 422 message now uses the TeamMember=user:team
form the builder and budget reservation already returned.
* Revert "fix(team): reject malformed team_member_max_budget_alert_emails on team writes"
This reverts commit 703e754b46.
* fix(alerting): keep BaseBudgetAlertType.get_event_message zero-arg
Requiring user_info broke existing callers and out-of-tree subclasses. The team member
label now comes from SlackAlerting.budget_alerts, so the interface and its Readme are
unchanged from main.
* fix(mcp): keep team member budget enforcement on the MCP OAuth auth dependency
The MCP OAuth dependency stops at _user_api_key_auth_builder and never reaches common_checks, so removing the builder's inline member budget check would have let over-budget members through there. Enforce it explicitly for that caller.
* fix(auth): keep main's team member budget enforcement, alert once per request
Restore the builder's team member budget check and 422 message exactly as on main and drop the MCP-only gate. The builder sends the member alert only on the request it rejects; common_checks sends it for requests that get past the builder, so no request alerts twice.
* test(integration): read team member alert deliveries without a shared accumulator
* test(integration): match team member alert deliveries by subject so other alerts cannot race the count
* refactor(proxy): build the team member alert threshold config without mutable collections
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(proxy): collapse the alert recipient isinstance checks into one call
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): read the SMTP sink through lock-guarded snapshots and assert the exact deliveries
---------
Co-authored-by: ryan <ryan@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
127 lines
4.4 KiB
Python
127 lines
4.4 KiB
Python
from __future__ import annotations
|
|
|
|
import socketserver
|
|
import threading
|
|
from collections.abc import Generator
|
|
from contextlib import contextmanager
|
|
from dataclasses import dataclass
|
|
from email import message_from_bytes
|
|
from email.message import Message
|
|
from queue import SimpleQueue
|
|
from typing import Final
|
|
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class Delivery:
|
|
sender: str
|
|
recipients: tuple[str, ...]
|
|
message: Message
|
|
|
|
@property
|
|
def subject(self) -> str:
|
|
return str(self.message["Subject"])
|
|
|
|
@property
|
|
def html(self) -> str:
|
|
for part in self.message.walk():
|
|
if part.get_content_type() == "text/html":
|
|
return part.get_payload(decode=True).decode()
|
|
return ""
|
|
|
|
|
|
class Mailbox:
|
|
def __init__(self, host: str, port: int) -> None:
|
|
self.host: Final = host
|
|
self.port: Final = port
|
|
self._lock: Final = threading.Lock()
|
|
self._deliveries: tuple[Delivery, ...] = ()
|
|
|
|
def record(self, delivery: Delivery) -> None:
|
|
with self._lock:
|
|
self._deliveries = (*self._deliveries, delivery)
|
|
|
|
def deliveries(self) -> tuple[Delivery, ...]:
|
|
with self._lock:
|
|
return self._deliveries
|
|
|
|
|
|
def _address(argument: str) -> str:
|
|
return argument.split(":", 1)[1].strip().strip("<>")
|
|
|
|
|
|
@contextmanager
|
|
def smtp_sink() -> Generator[Mailbox, None, None]:
|
|
"""Owned plaintext SMTP peer; deliveries traverse the proxy's real smtplib client."""
|
|
errors: Final[SimpleQueue[Exception]] = SimpleQueue()
|
|
|
|
class Handler(socketserver.StreamRequestHandler):
|
|
timeout = 5
|
|
|
|
def handle(self) -> None:
|
|
try:
|
|
self._session()
|
|
except Exception as error:
|
|
errors.put(error)
|
|
|
|
def _reply(self, line: str) -> None:
|
|
self.wfile.write(f"{line}\r\n".encode())
|
|
self.wfile.flush()
|
|
|
|
def _session(self) -> None:
|
|
self._reply("220 integration-smtp ready")
|
|
# rebind-ok: the SMTP envelope is built across MAIL/RCPT lines and reset after DATA or RSET.
|
|
sender = ""
|
|
recipients: tuple[str, ...] = ()
|
|
while True:
|
|
raw: Final = self.rfile.readline()
|
|
if not raw:
|
|
return
|
|
line: Final = raw.decode().rstrip("\r\n")
|
|
verb: Final = line.split(" ", 1)[0].upper()
|
|
if verb in {"EHLO", "HELO"}:
|
|
self._reply("250 integration-smtp")
|
|
elif verb == "MAIL":
|
|
sender = _address(line)
|
|
self._reply("250 OK")
|
|
elif verb == "RCPT":
|
|
recipients = (*recipients, _address(line))
|
|
self._reply("250 OK")
|
|
elif verb == "DATA":
|
|
self._reply("354 End data with <CR><LF>.<CR><LF>")
|
|
body = bytearray()
|
|
while True:
|
|
chunk: Final = self.rfile.readline()
|
|
if not chunk or chunk == b".\r\n":
|
|
break
|
|
body.extend(chunk[1:] if chunk.startswith(b"..") else chunk)
|
|
mailbox.record(Delivery(sender, recipients, message_from_bytes(bytes(body))))
|
|
sender, recipients = "", ()
|
|
self._reply("250 OK queued")
|
|
elif verb == "RSET":
|
|
sender, recipients = "", ()
|
|
self._reply("250 OK")
|
|
elif verb == "NOOP":
|
|
self._reply("250 OK")
|
|
elif verb == "QUIT":
|
|
self._reply("221 Bye")
|
|
return
|
|
else:
|
|
self._reply("502 Command not implemented")
|
|
|
|
class OwnedServer(socketserver.ThreadingTCPServer):
|
|
allow_reuse_address = True
|
|
daemon_threads = False
|
|
|
|
with OwnedServer(("127.0.0.1", 0), Handler) as server:
|
|
mailbox: Final = Mailbox("127.0.0.1", server.server_address[1])
|
|
thread: Final = threading.Thread(target=server.serve_forever, kwargs={"poll_interval": 0.05})
|
|
thread.start()
|
|
try:
|
|
yield mailbox
|
|
finally:
|
|
server.shutdown()
|
|
thread.join(timeout=6)
|
|
assert not thread.is_alive(), "Owned SMTP server survived cleanup"
|
|
server.server_close()
|
|
failure: Final = None if errors.empty() else errors.get_nowait()
|
|
assert failure is None, f"Owned SMTP peer failed: {failure!r}"
|