litellm/tests/integration/_support/process.py
Mateo Wang 622daf3cdf
fix(scim): write a group's roster in one locked transaction instead of one member at a time (#45197)
* fix(scim): write a group's roster in one locked transaction instead of one member at a time

POST, PUT and PATCH /scim/v2/Groups resolve every member in one query and write the roster, the
membership rows and the users' team tags in one transaction under the team's advisory lock, so a
500-member push runs a fixed number of statements instead of thousands. PUT now answers with the
roster it just wrote

* test(scim): assert the roster the IdP gets back and boot the bulk roster cell with two workers

* fix(scim): skip the team lock for a rename-only PATCH and lock member rows in id order before the roster write

A PATCH naming no members opened the roster transaction and took the team advisory lock for nothing. A SIGKILLed worker then left its orphaned query engine holding that lock until the 60 s transaction timeout, and /team/delete, which takes the same lock, timed out behind it. An empty delta is now answered from a plain team read, with no transaction and no lock

Two groups trading members in parallel locked user rows in opposite orders, and one request died with a Postgres deadlock. Every user row a push touches is now locked with SELECT ... ORDER BY user_id FOR UPDATE before the first write, so the two requests serialize

The bulk roster cell gets a 120 s client through a new owned_proxy_process client_timeout, so an unfixed push fails on the statement count instead of the harness clock, requires positive counts on both pushes, and gains a parallel roster-trade test that answered 500 before the lock

* fix(scim): evict the cached team on a group rename and read a no-op roster from the writer

A rename-only PUT or PATCH wrote the new alias and left the team cached under
its id and old alias on every worker, so keys kept logging spend against the
old team alias until the TTL expired. The group write now evicts the cached
team (and broadcasts the eviction) right after the alias or metadata update.

sync_team_roster reads the team from the writer when the plan names nobody,
so a replica cannot hand back the pre-rename row; a plan already matching the
roster returns inside the lock without writing, evicting, or emitting the
members metric; the response is built from the written row, so lastModified
reflects the roster write; and detaching a removed member bumps the user's
updated_at like every other user write.

* fix(scim): bump detached members' updated_at in UTC

The detach UPDATE wrote updated_at = CURRENT_TIMESTAMP, which Postgres casts
into Prisma's naive timestamp column in the session timezone, so on a database
whose session is not UTC the removed member's row landed hours away from the
UTC instants Prisma itself writes. Write NOW() AT TIME ZONE 'UTC' instead, and
have the bulk roster cell assert the bumped row sits between two reads of the
database's own UTC clock taken around the replace.

* fix(scim): chunk the group write's member lookups under the bind cap

Every Prisma "in" filter the group write issues bound one parameter per
member with nothing bounding the list, which check_unbounded_in_lists
reports as 11 new findings. The single-field lookups now go through
litellm.repositories.chunked_in (caller_transaction inside the roster
transaction, per_chunk_ok for the role recompute), and the one
cross-field OR read slices its values at IN_LIST_CHUNK_SIZE and records
the bound. A push of IN_LIST_CHUNK_SIZE + 1 members now reads in two
slices, and a member named only in the last slice still resolves.

* fix(proxy): send bulk cache evictions in slices so the broadcaster drops none

Veria pointed out that the invalidation publisher caps its pending tasks at
1,024 and drops the excess with a warning, and that a group push now detaches
every removed member's keys in one call instead of one member at a time, so a
removal of more than roughly 340 members (three cache keys each) silently left
stale key objects on the other replicas. The merge base never hit the cap
because each member was a separate request.

Bulk evictions (team, user, organization, and session key deletes, plus the
roster settle) now publish in slices of 256 and wait, bounded at two seconds,
for the backlog already handed to the event loop before each slice. A Redis
that never answers costs a bulk caller at most that wait per slice instead of
wedging the request, and single-key callers are untouched. Regression tests
push 1,500 keys and a 500-member removal through a slow publisher and assert
every eviction reaches Redis; both fail against the previous tip.

* fix(proxy): clear this worker's cache before pacing bulk eviction broadcasts

Greptile pointed out that pacing the broadcasts in slices also paced the
local eviction: a bulk delete waited for the publish backlog before dropping
the next slice from this worker's own memory, so on a Redis that accepts
connections but never answers a key deleted from the database kept
authenticating on the handling worker for up to two seconds per slice. The
merge base cleared every key locally at once.

Bulk evictions now drop every affected entry from this worker's memory first,
through the cache's own partition lookup since key objects live apart from
the other auth objects, and only then publish in paced slices. The roster
settle does the same for the deleted tokens, the JWT mapping keys and every
changed member's user and membership entries before any step that can wait.
Regression tests run both paths against a publisher that never answers and
check that nothing is still cached on this worker before the first bound
elapses; both fail with the local eviction removed.

* fix(proxy): drop the Redis copies of bulk-evicted auth objects before pacing the broadcasts

* docs(proxy): drop the module docstring that repeated the PR description

* fix(scim): bound bulk cache evictions to one Redis round trip and close lock-order gaps

Bulk key evictions now drop entries from memory, delete them from Redis in one
chunked DEL, and broadcast every key in one pipelined publish, so a large roster
removal no longer overflows the publisher's pending cap or costs a Redis round
trip per member. A push waits for in-flight membership loads before evicting.

User rows are locked in byte order to match the spend writer, a bulk user delete
takes every team lock before its first user write, and a POST whose roster write
fails deletes the empty team so the IdP retry creates it again.

* test(team): observe delete broadcasts at the Redis layer

* fix(scim): lock user rows in id order on every multi-row writer and create unprovisioned members concurrently

* fix(team): chunk the email lookup behind the member row lock

* fix(scim): create a member deleted mid-push again instead of failing the group write

* fix(scim): refuse strict-mode mid-push deletes with 400 and check license seats once per batch

A member deleted mid-push is created again only when scim_upsert_user allows it,
under the verb's own created_via. New group members are checked against the
license seat limit as one batch before any is created. Auth cache publish drops
log the key count instead of the key.

* fix(scim): lock member rows while recomputing admin roles after a group push

* fix(users): re-read teams under the row locks in bulk user delete so a racing group push keeps no deleted member

* fix(users): take /user/delete and SCIM DELETE /Users users off their current teams under the row locks so a racing group push keeps no deleted member

* fix(scim): keep retrying a push while deletes race it, lock rows in member bulk delete, evict removed keys from Redis first

A group push gave up after one retry when SCIM user deletes kept landing between attempts, answering 500 in 9 of 10 race rounds. It now retries while each attempt finds newly deleted members, and gives up only when a member it created again goes missing a second time.

The team member bulk delete now locks the removed members' user rows in the shared order and takes the team off their teams arrays in one array_remove statement, so it no longer writes back a teams array read before a concurrent push added another team.

A push that removes members now drops their deleted team keys from memory and Redis together with the members' other cache entries before the team eviction, so a removed key cannot refill from Redis mid-cleanup.

* fix(user-delete): keep the team alias label on the team members gauge after removals

* test(integration): count relay statements over plaintext so an SSL-enabled Postgres does not hide them

* fix(user-delete): skip a team deleted while the user delete waited on its lock instead of answering 404

* fix(scim): answer 404 and roll back when the team is deleted during a roster write

* test(integration): audit cells for SCIM bulk roster writes, user delete locking and the eviction broadcast
2026-10-15 10:57:00 -07:00

1049 lines
38 KiB
Python

import errno
import json
import threading
import os
import re
import signal
import socket
import subprocess
import sys
import time
import uuid
from collections.abc import Generator, Iterable, Iterator, Mapping
from concurrent.futures import ThreadPoolExecutor
from contextlib import contextmanager, suppress
from dataclasses import dataclass
from enum import Enum
from datetime import UTC, datetime, timedelta
from ipaddress import IPv4Address
from itertools import accumulate
from pathlib import Path
from types import MappingProxyType
from typing import Final
from urllib.parse import urlsplit
import httpx
import psutil
import yaml
from cryptography import x509
from cryptography.hazmat.primitives import hashes, serialization
from cryptography.hazmat.primitives.asymmetric import rsa
from cryptography.x509.oid import NameOID
from pydantic import TypeAdapter
from tests.integration._support.budget import import_seconds, readiness_for, readiness_seconds
from tests.integration._support.client import GATEWAY_LIMITS, Gateway
DB_PUSH: Final = ("--use_prisma_db_push",)
MIGRATE_DEPLOY: Final = ()
LEGACY_MIGRATE_DEPLOY: Final = ("--use_legacy_migration_resolver",)
CONFIGURATION: Final = TypeAdapter(dict[str, object])
_DEPLOYMENT_IDS: Final = TypeAdapter(dict[str, list[str]])
MCP_COVERAGE_CONFIG: Final = Path(__file__).resolve().parents[1] / "mcp_coverage.toml"
def proxy_database_environment(inherited: Mapping[str, str] = os.environ) -> Mapping[str, str]:
writer: Final = inherited.get("INTEGRATION_PROXY_DATABASE_URL", "")
reader: Final = inherited.get("INTEGRATION_PROXY_READ_REPLICA_URL", "")
return MappingProxyType(
{
**({"DATABASE_URL": writer} if writer else {}),
**({"DATABASE_URL_READ_REPLICA": reader} if reader else {}),
}
)
def in_group(process: psutil.Process, group: int) -> bool:
try:
return os.getpgid(process.pid) == group
except ProcessLookupError:
return False
def group_members(group: int) -> tuple[psutil.Process, ...]:
return tuple(process for process in psutil.process_iter() if in_group(process, group))
def signal_group(group: int, action: int) -> None:
try:
os.killpg(group, action)
except ProcessLookupError:
pass
def graceful_stop_seconds() -> float:
return readiness_for(import_seconds(), 1)
def stop_root_process(process: subprocess.Popen[bytes]) -> bool:
if process.poll() is not None:
return True
process.terminate()
try:
process.wait(timeout=graceful_stop_seconds())
except subprocess.TimeoutExpired:
return False
return True
class WorkerHealthcheck(Enum):
STRICT = "strict"
LENIENT = "lenient"
STRICT_HEALTHCHECK_SECONDS: Final = 5
WORKER_ENTRYPOINT: Final = "spawn_main"
def healthcheck_seconds(healthcheck: WorkerHealthcheck) -> int:
match healthcheck:
case WorkerHealthcheck.STRICT:
return STRICT_HEALTHCHECK_SECONDS
case WorkerHealthcheck.LENIENT:
return int(graceful_stop_seconds())
def _is_serving_worker(process: psutil.Process) -> bool:
try:
return _ready_worker_pid(process) is not None and WORKER_ENTRYPOINT in " ".join(process.cmdline())
except psutil.Error:
return False
def _is_gone(process: psutil.Process) -> bool:
try:
return process.status() == psutil.STATUS_ZOMBIE
except psutil.NoSuchProcess:
return True
def _wait_until_gone(process: psutil.Process, seconds: float) -> None:
deadline: Final = time.monotonic() + seconds
while not _is_gone(process):
assert time.monotonic() < deadline, f"Process {process.pid} is still running after {seconds:.0f}s"
time.sleep(0.05)
def _is_stopped(process: psutil.Process) -> bool:
try:
return process.status() == psutil.STATUS_STOPPED
except psutil.NoSuchProcess:
return False
def _suspend(process: psutil.Process) -> None:
process.suspend()
deadline: Final = time.monotonic() + STRICT_HEALTHCHECK_SECONDS
while not _is_stopped(process) and time.monotonic() < deadline:
time.sleep(0.01)
if _is_stopped(process):
return
with suppress(psutil.NoSuchProcess):
process.resume()
raise AssertionError(f"Process {process.pid} did not stop within {STRICT_HEALTHCHECK_SECONDS}s of SIGSTOP")
def _is_reaped(process: psutil.Process) -> bool:
try:
process.status()
except psutil.NoSuchProcess:
return True
return False
def _wait_until_reaped(process: psutil.Process, supervisor: psutil.Process, seconds: float) -> None:
deadline: Final = time.monotonic() + seconds
while not _is_reaped(process) and not _is_stopped(supervisor):
assert time.monotonic() < deadline, f"The supervisor did not reap worker {process.pid} within {seconds:.0f}s"
time.sleep(0.05)
@dataclass(frozen=True, slots=True)
class WorkerKill:
victim: psutil.Process
supervisor: psutil.Process
reap_seconds: float
fired: threading.Event
def freeze(self) -> psutil.Process:
_suspend(self.victim)
return self.victim
def __call__(self) -> None:
assert not self.fired.is_set(), f"Worker {self.victim.pid} was already killed"
with suppress(psutil.NoSuchProcess):
self.victim.kill()
_wait_until_gone(self.victim, STRICT_HEALTHCHECK_SECONDS)
_wait_until_reaped(self.victim, self.supervisor, self.reap_seconds)
self.fired.set()
def replacement_pid(before: frozenset[int], answered: int | None, serving: frozenset[int]) -> int | None:
return answered if answered is not None and answered not in before and answered in serving else None
@dataclass(frozen=True, slots=True)
class OwnedProxy:
gateway: Gateway
process: subprocess.Popen[bytes]
log: Path
healthcheck: WorkerHealthcheck = WorkerHealthcheck.STRICT
def worker_pids(self) -> frozenset[int]:
try:
children: Final = psutil.Process(self.process.pid).children()
except psutil.NoSuchProcess:
return frozenset()
return frozenset(child.pid for child in children if _is_serving_worker(child))
def _answering_pid(self) -> int | None:
try:
with httpx.Client(
base_url=str(self.gateway.client.base_url),
timeout=2,
trust_env=False,
limits=httpx.Limits(max_keepalive_connections=0),
) as client:
response: Final = client.get("/health/integration-readiness")
except httpx.TransportError:
return None
identity: Final = response.headers.get("x-integration-worker-pid", "")
return int(identity) if response.status_code == 200 and identity.isdecimal() else None
def _deployment_ids_on_a_worker(self, model_name: str) -> tuple[int, frozenset[str]] | None:
try:
with httpx.Client(
base_url=str(self.gateway.client.base_url),
timeout=2,
trust_env=False,
limits=httpx.Limits(max_keepalive_connections=0),
) as client:
response: Final = client.get("/health/integration-deployment-ids", params={"model_name": model_name})
except httpx.TransportError:
return None
identity: Final = response.headers.get("x-integration-worker-pid", "")
if response.status_code != 200 or not identity.isdecimal():
return None
return int(identity), frozenset(_DEPLOYMENT_IDS.validate_python(response.json())["model_ids"])
def serves_only_on_every_worker(self, model_name: str, model_id: str) -> bool:
with ThreadPoolExecutor(max_workers=8) as pool:
answers: Final = tuple(pool.map(self._deployment_ids_on_a_worker, (model_name,) * 16))
samples: Final = tuple(answer for answer in answers if answer is not None)
workers: Final = self.worker_pids()
return (
bool(workers)
and workers <= frozenset(pid for pid, _ in samples)
and all(model_ids == {model_id} for _, model_ids in samples)
)
def _await_replacement(self, before: frozenset[int]) -> int:
budget: Final = readiness_seconds(1)
deadline: Final = time.monotonic() + budget
while (replacement := replacement_pid(before, self._answering_pid(), self.worker_pids())) is None:
assert self.process.poll() is None, "Owned proxy exited while a worker was being replaced"
assert time.monotonic() < deadline, f"No replacement worker served within {budget:.0f}s"
time.sleep(0.05)
return replacement
def _victim(self, pid: int) -> tuple[psutil.Process, frozenset[int]]:
before: Final = self.worker_pids()
assert pid in before, f"{pid} is not a serving worker of this proxy: {sorted(before)}"
return psutil.Process(pid), before
def _worker_kill(self, victim: psutil.Process) -> WorkerKill:
reap_seconds: Final = healthcheck_seconds(self.healthcheck) + STRICT_HEALTHCHECK_SECONDS
return WorkerKill(victim, psutil.Process(self.process.pid), reap_seconds, threading.Event())
@contextmanager
def replacing_worker(self, pid: int) -> Iterator[WorkerKill]:
victim, before = self._victim(pid)
kill: Final = self._worker_kill(victim)
yield kill
assert kill.fired.is_set(), f"replacing_worker({pid}) exited without killing the worker"
self._await_replacement(before)
def kill_worker(self, pid: int) -> int:
victim, before = self._victim(pid)
self._worker_kill(victim)()
return self._await_replacement(before)
@contextmanager
def suspended(self, pid: int) -> Iterator[psutil.Process]:
assert self.healthcheck is WorkerHealthcheck.LENIENT, (
"uvicorn kills a suspended worker after the strict worker healthcheck; "
"launch this proxy with healthcheck=WorkerHealthcheck.LENIENT"
)
assert pid == self.process.pid or pid in self.worker_pids(), f"{pid} is not part of this proxy"
target: Final = psutil.Process(pid)
_suspend(target)
try:
yield target
finally:
with suppress(psutil.NoSuchProcess):
target.resume()
assert not _is_gone(target), (
f"Process {pid} died while suspended under a {healthcheck_seconds(self.healthcheck)}s worker healthcheck"
)
def stall_worker(self, pid: int) -> int:
assert self.healthcheck is WorkerHealthcheck.STRICT, "Only the strict worker healthcheck replaces a stall"
victim, before = self._victim(pid)
victim.suspend()
try:
replacement: Final = self._await_replacement(before)
_wait_until_gone(victim, readiness_seconds(1))
return replacement
finally:
with suppress(psutil.NoSuchProcess):
victim.kill()
def begin_shutdown(self) -> None:
self.process.terminate()
def kill_supervisor(self) -> int:
self.process.kill()
return self.process.wait(timeout=STRICT_HEALTHCHECK_SECONDS)
def stop_child(process: subprocess.Popen[bytes] | subprocess.Popen[str], grace_seconds: float = 10) -> int:
if process.poll() is None:
process.terminate()
try:
return process.wait(timeout=grace_seconds)
except subprocess.TimeoutExpired:
process.kill()
return process.wait(timeout=grace_seconds)
def stop_processes(processes: Iterable[psutil.Process], grace_seconds: float = 5) -> None:
members: Final = tuple(processes)
for member in members:
with suppress(psutil.NoSuchProcess):
member.terminate()
_stopped, alive = psutil.wait_procs(members, timeout=grace_seconds)
for member in alive:
with suppress(psutil.NoSuchProcess):
member.kill()
psutil.wait_procs(alive, timeout=grace_seconds)
def stop_process_group(process: subprocess.Popen[bytes] | subprocess.Popen[str], grace_seconds: float) -> None:
if process.poll() is None:
signal_group(process.pid, signal.SIGTERM)
try:
process.wait(timeout=grace_seconds)
except subprocess.TimeoutExpired:
signal_group(process.pid, signal.SIGKILL)
process.wait(timeout=grace_seconds)
def kill_stray_process(pid: int) -> None:
with suppress(psutil.NoSuchProcess):
stray: Final = psutil.Process(pid)
stray.kill()
_wait_until_gone(stray, STRICT_HEALTHCHECK_SECONDS)
@contextmanager
def paused(process: subprocess.Popen[bytes] | subprocess.Popen[str]) -> Iterator[None]:
target: Final = psutil.Process(process.pid)
_suspend(target)
try:
yield
finally:
with suppress(psutil.NoSuchProcess):
target.resume()
@contextmanager
def owned_proxy(
gateway: Gateway,
directory: Path,
overrides: Mapping[str, str],
*,
config: Path | None = None,
remove_environment: tuple[str, ...] = (),
workers: int = 1,
database_setup: tuple[str, ...] = DB_PUSH,
coverage_file: Path | None = None,
inherited: Mapping[str, str] = os.environ,
) -> Iterator[Gateway]:
with owned_proxy_process(
gateway,
directory,
overrides,
config=config,
remove_environment=remove_environment,
workers=workers,
database_setup=database_setup,
coverage_file=coverage_file,
inherited=inherited,
) as owned:
yield owned.gateway
def _stop(process: subprocess.Popen[bytes]) -> None:
try:
root_stopped: Final = stop_root_process(process)
residual: Final = group_members(process.pid)
if residual:
signal_group(process.pid, signal.SIGTERM)
psutil.wait_procs(residual, timeout=5)
remaining: Final = group_members(process.pid)
if remaining:
signal_group(process.pid, signal.SIGKILL)
psutil.wait_procs(remaining, timeout=3)
process.wait(timeout=3)
survivors: Final = group_members(process.pid)
assert not survivors, "Owned proxy child survived cleanup"
assert root_stopped and not remaining, "Owned proxy required forced cleanup"
except BaseException:
signal_group(process.pid, signal.SIGKILL)
process.wait(timeout=3)
psutil.wait_procs(group_members(process.pid), timeout=3)
assert not group_members(process.pid), "Owned proxy child survived emergency cleanup"
raise
_PORT_ATTEMPTS: Final = 3
_BIND_COLLISION: Final = os.strerror(errno.EADDRINUSE).lower()
def _free_port() -> int:
with socket.socket() as reserve:
reserve.bind(("127.0.0.1", 0))
return reserve.getsockname()[1]
@dataclass(frozen=True, slots=True)
class _Launch:
process: subprocess.Popen[bytes]
port: int
log: Path
started: float
def _wall_clock(monotonic: float) -> float:
return time.time() - (time.monotonic() - monotonic)
def _stop_launch(launch: _Launch) -> None:
started: Final = time.monotonic()
stop_started_at: Final = time.time()
exit_before: Final = launch.process.poll()
exception_before: Final = sys.exc_info()[0]
try:
_stop(launch.process)
finally:
exception_at_record: Final = sys.exc_info()[0]
launch.log.with_suffix(".exit.json").write_text(
json.dumps(
{
"root_pid": launch.process.pid,
"exit_before_stop": exit_before,
"exit_after_stop": launch.process.poll(),
"exception_before_stop": exception_before.__name__ if exception_before else None,
"exception_at_record": exception_at_record.__name__ if exception_at_record else None,
"cleanup_seconds": time.monotonic() - started,
"process_lifetime_seconds": time.monotonic() - launch.started,
"spawned_at": _wall_clock(launch.started),
"stop_started_at": stop_started_at,
"stopped_at": time.time(),
},
indent=2,
)
+ "\n"
)
def _launch(command: tuple[str, ...], root: Path, environment: Mapping[str, str], output: Path) -> _Launch:
port: Final = _free_port()
log_path: Final = output / f"owned-proxy-{uuid.uuid4().hex}.log"
started: Final = time.monotonic()
with log_path.open("w") as log:
process: Final = subprocess.Popen(
[*command, "--port", str(port)],
cwd=root,
env=environment,
stdout=log,
stderr=subprocess.STDOUT,
start_new_session=True,
)
return _Launch(process, port, log_path, started)
def _lost_port_race(exit_code: int | None, log: Path) -> bool:
return exit_code is not None and _BIND_COLLISION in log.read_text().lower()
def _owns_listener(launch: _Launch) -> bool:
for member in group_members(launch.process.pid):
try:
if any(
connection.status == psutil.CONN_LISTEN and connection.laddr.port == launch.port
for connection in member.net_connections(kind="inet")
):
return True
except (psutil.NoSuchProcess, psutil.AccessDenied):
continue
return False
@dataclass(frozen=True, slots=True)
class BootPhases:
prisma_started: float | None = None
prisma_finished: float | None = None
listening: float | None = None
first_ready: float | None = None
ready_pids: frozenset[int] = frozenset()
@dataclass(frozen=True, slots=True)
class _Probe:
elapsed: float
listening: bool
prisma: bool
ready_pid: int | None
def _runs_prisma(process: psutil.Process) -> bool:
try:
return any(Path(part).name == "prisma" for part in process.cmdline())
except psutil.Error:
return False
def _prisma_running(launch: _Launch) -> bool:
try:
children: Final = psutil.Process(launch.process.pid).children()
except psutil.Error:
return False
return any(_runs_prisma(child) for child in children)
def _answer(client: httpx.Client, launch: _Launch) -> tuple[bool, int | None]:
if not _owns_listener(launch):
return False, None
try:
response: Final = client.get("/health/integration-readiness", timeout=2)
except httpx.ConnectError:
return False, None
except httpx.TransportError:
return True, None
identity: Final = response.headers.get("x-integration-worker-pid", "")
ready: Final = response.status_code == 200 and identity.isdecimal()
return True, int(identity) if ready else None
def _probes(launch: _Launch, workers: int) -> Iterator[_Probe]:
with httpx.Client(
base_url=f"http://127.0.0.1:{launch.port}",
timeout=15,
trust_env=False,
limits=httpx.Limits(max_keepalive_connections=0),
) as client:
deadline: Final = time.monotonic() + readiness_seconds(workers)
while launch.process.poll() is None:
elapsed: Final = time.monotonic() - launch.started
listening, ready_pid = _answer(client, launch)
yield _Probe(elapsed, listening, not listening and _prisma_running(launch), ready_pid)
assert time.monotonic() < deadline, "Owned proxy readiness deadline exceeded"
time.sleep(0.1)
def _first(recorded: float | None, observed: bool, elapsed: float) -> float | None:
return recorded if recorded is not None or not observed else elapsed
def _observe(phases: BootPhases, probe: _Probe) -> BootPhases:
prisma_started: Final = _first(phases.prisma_started, probe.prisma, probe.elapsed)
prisma_finished: Final = _first(phases.prisma_finished, prisma_started is not None, probe.elapsed)
return BootPhases(
prisma_started=prisma_started,
prisma_finished=None if probe.prisma else prisma_finished,
listening=_first(phases.listening, probe.listening, probe.elapsed),
first_ready=_first(phases.first_ready, probe.ready_pid is not None, probe.elapsed),
ready_pids=phases.ready_pids | frozenset(() if probe.ready_pid is None else (probe.ready_pid,)),
)
def _ready_worker_pid(member: psutil.Process) -> int | None:
try:
status: Final = member.status()
return (
None
if status in (psutil.STATUS_ZOMBIE, psutil.STATUS_DEAD, psutil.STATUS_STOPPED, psutil.STATUS_TRACING_STOP)
else member.pid
)
except (psutil.NoSuchProcess, psutil.AccessDenied):
return None
def _serves_all(launch: _Launch, phases: BootPhases, workers: int) -> bool:
if len(phases.ready_pids) < max(1, workers):
return False
members: Final = frozenset(
pid for member in group_members(launch.process.pid) if (pid := _ready_worker_pid(member)) is not None
)
return len(phases.ready_pids & members) >= max(1, workers)
def _wait_until_ready(launch: _Launch, workers: int = 1) -> BootPhases | None:
return next(
(
phases
for phases in accumulate(_probes(launch, workers), _observe, initial=BootPhases())
if _serves_all(launch, phases, workers)
),
None,
)
def _launch_until_bound(
command: tuple[str, ...], root: Path, environment: Mapping[str, str], output: Path, attempts: int, workers: int
) -> _Launch:
launch: Final = _launch(command, root, environment, output)
try:
phases: Final = _wait_until_ready(launch, workers)
exit_code: Final = launch.process.poll()
assert exit_code is None or (attempts > 1 and _lost_port_race(exit_code, launch.log)), (
"Owned proxy exited before readiness"
)
except BaseException:
_stop_launch(launch)
raise
if exit_code is None:
assert phases is not None
launch.log.with_suffix(".startup.json").write_text(
json.dumps(
{
"root_pid": launch.process.pid,
"readiness_seconds": time.monotonic() - launch.started,
"logical_cpus": os.cpu_count(),
"workers": workers,
"spawned_at": _wall_clock(launch.started),
"phases": {
"prisma_started": phases.prisma_started,
"prisma_finished": phases.prisma_finished,
"listening": phases.listening,
"first_ready": phases.first_ready,
},
}
)
+ "\n"
)
return launch
_stop_launch(launch)
return _launch_until_bound(command, root, environment, output, attempts - 1, workers)
def _proxy_root() -> Path:
return Path(os.environ.get("INTEGRATION_PROXY_ROOT") or Path(__file__).resolve().parents[3])
def worker_configuration(config: Path, directory: Path, inherited: Mapping[str, str] = os.environ) -> Path:
if inherited.get("INTEGRATION_WORKER_ISOLATION") != "1":
return config
def endpoint(match: re.Match[str]) -> str:
if match.group(1) == "8190":
return inherited["INTEGRATION_UPSTREAM_URL"]
return f"http://127.0.0.1:{inherited['INTEGRATION_PROVIDER_PORT']}"
contents: Final = re.sub(r"http://127[.]0[.]0[.]1:(8190|8191)(?![0-9])", endpoint, config.read_text())
directory.mkdir(parents=True, exist_ok=True)
destination: Final = directory / f"worker-config-{uuid.uuid4().hex}.yaml"
loaded: Final[object] = yaml.safe_load(contents)
if not isinstance(loaded, dict):
destination.write_text(contents)
return destination
settings: Final = CONFIGURATION.validate_python(loaded)
general: Final = settings.get("general_settings", {})
if not isinstance(general, dict):
destination.write_text(contents)
return destination
configured: Final = {
**settings,
"general_settings": {"database_connection_pool_limit": 2, **CONFIGURATION.validate_python(general)},
}
destination.write_text(yaml.safe_dump(configured, sort_keys=False))
return destination
def _proxy_environment(
gateway: Gateway,
overrides: Mapping[str, str],
remove_environment: tuple[str, ...],
source: Mapping[str, str] = os.environ,
) -> Mapping[str, str]:
inherited: Final = {**source, **proxy_database_environment(source)}
writer: Final = overrides.get("DATABASE_URL")
reader: Final = inherited.get("DATABASE_URL_READ_REPLICA")
unpaired_reader: Final = (
writer is not None
and reader is not None
and "DATABASE_URL_READ_REPLICA" not in overrides
and urlsplit(writer).path != urlsplit(reader).path
)
removed: Final = frozenset((*remove_environment, *(("DATABASE_URL_READ_REPLICA",) if unpaired_reader else ())))
configured_hooks: Final = overrides.get(
"LITELLM_WORKER_STARTUP_HOOKS",
inherited.get("LITELLM_WORKER_STARTUP_HOOKS", "") if "LITELLM_WORKER_STARTUP_HOOKS" not in removed else "",
)
return MappingProxyType(
{
**{name: value for name, value in inherited.items() if name not in removed},
"LITELLM_MASTER_KEY": gateway.key,
"LITELLM_SALT_KEY": source.get("LITELLM_SALT_KEY", "sk-integration-salt"),
"STORE_MODEL_IN_DB": "True",
"PYTHON_DOTENV_DISABLED": "1",
**overrides,
"LITELLM_WORKER_STARTUP_HOOKS": ",".join(
hook
for hook in (
"integration._support.runtime:configure_executor",
"integration._support.runtime:configure_readiness",
configured_hooks,
)
if hook
),
}
)
def setup_only_proxy_run(
gateway: Gateway,
overrides: Mapping[str, str],
*,
config: Path,
workers: int,
database_setup: tuple[str, ...] = DB_PUSH,
) -> subprocess.CompletedProcess[str]:
"""The proxy CLI's `--skip_server_startup` pass (the image's setup step), run to completion with the
environment an owned proxy gets."""
return subprocess.run( # test-quality-ok: the checkout at the working directory is the proxy under test
(
sys.executable,
"-m",
"integration._support.proxy",
"--config",
str(config),
"--num_workers",
str(workers),
*database_setup,
"--skip_server_startup",
),
cwd=_proxy_root(),
env=dict(_proxy_environment(gateway, overrides, ())),
capture_output=True,
text=True,
timeout=300,
check=False,
)
@contextmanager
def owned_proxy_process(
gateway: Gateway,
directory: Path,
overrides: Mapping[str, str],
*,
config: Path | None = None,
remove_environment: tuple[str, ...] = (),
workers: int = 1,
database_setup: tuple[str, ...] = DB_PUSH,
extra_arguments: tuple[str, ...] = (),
coverage_file: Path | None = None,
healthcheck: WorkerHealthcheck = WorkerHealthcheck.STRICT,
inherited: Mapping[str, str] = os.environ,
client_timeout: float = 15,
) -> Iterator[OwnedProxy]:
assert "--timeout_worker_healthcheck" not in extra_arguments, "Choose the worker healthcheck with `healthcheck`"
root: Final = _proxy_root()
environment: Final = _proxy_environment(
gateway,
{**overrides, **({"COVERAGE_FILE": str(coverage_file)} if coverage_file else {})},
remove_environment,
inherited,
)
output: Final = Path(inherited.get("INTEGRATION_RESULTS_DIR", str(directory)))
output.mkdir(parents=True, exist_ok=True)
command: Final = (
sys.executable,
"-m",
*(("coverage", "run", f"--rcfile={MCP_COVERAGE_CONFIG}", "-m") if coverage_file else ()),
"integration._support.proxy",
"--config",
str(worker_configuration(config or root / "tests/integration/proxy_config.yaml", directory, inherited)),
"--host",
"127.0.0.1",
"--num_workers",
str(workers),
"--timeout_worker_healthcheck",
str(healthcheck_seconds(healthcheck)),
*database_setup,
*extra_arguments,
)
launch: Final = _launch_until_bound(command, root, environment, output, _PORT_ATTEMPTS, workers)
process: Final = launch.process
try:
with httpx.Client(
base_url=f"http://127.0.0.1:{launch.port}", timeout=client_timeout, trust_env=False, limits=GATEWAY_LIMITS
) as client:
yield OwnedProxy(Gateway(client, gateway.key, gateway.upstream_url), process, launch.log, healthcheck)
finally:
_stop_launch(launch)
@contextmanager
def configless_proxy_process(
gateway: Gateway,
directory: Path,
overrides: Mapping[str, str],
*,
model: str,
api_base: str,
workers: int = 1,
) -> Iterator[OwnedProxy]:
environment: Final = _proxy_environment(gateway, {**overrides, "STORE_MODEL_IN_DB": "False"}, ())
output: Final = Path(os.environ.get("INTEGRATION_RESULTS_DIR", str(directory)))
output.mkdir(parents=True, exist_ok=True)
command: Final = (
sys.executable,
"-m",
"integration._support.proxy",
"--model",
model,
"--api_base",
api_base,
"--host",
"127.0.0.1",
"--num_workers",
str(workers),
"--timeout_worker_healthcheck",
str(healthcheck_seconds(WorkerHealthcheck.STRICT)),
*DB_PUSH,
)
launch: Final = _launch_until_bound(command, _proxy_root(), environment, output, _PORT_ATTEMPTS, workers)
try:
with httpx.Client(
base_url=f"http://127.0.0.1:{launch.port}", timeout=15, trust_env=False, limits=GATEWAY_LIMITS
) as client:
yield OwnedProxy(Gateway(client, gateway.key, gateway.upstream_url), launch.process, launch.log)
finally:
_stop_launch(launch)
@contextmanager
def owned_gateway_image(
gateway: Gateway, directory: Path, overrides: Mapping[str, str], *, config: Path, workers: int
) -> Iterator[OwnedProxy]:
"""The componentized gateway started the way its image starts it: `docker/component_entrypoint.sh` running
`python -m gateway.launch`, with the config handed over as `CONFIG_FILE_PATH`. It serves the data plane only,
so keys come from a proxy that shares its database."""
root: Final = _proxy_root()
environment: Final = _proxy_environment(gateway, {**overrides, "CONFIG_FILE_PATH": str(config)}, ())
output: Final = Path(os.environ.get("INTEGRATION_RESULTS_DIR", str(directory)))
output.mkdir(parents=True, exist_ok=True)
command: Final = (
str(root / "docker" / "component_entrypoint.sh"),
sys.executable,
"-m",
"gateway.launch",
"--workers",
str(workers),
"--host",
"127.0.0.1",
"--timeout-worker-healthcheck",
str(int(graceful_stop_seconds())),
)
launch: Final = _launch_until_bound(command, root, environment, output, _PORT_ATTEMPTS, workers)
try:
with httpx.Client(
base_url=f"http://127.0.0.1:{launch.port}", timeout=15, trust_env=False, limits=GATEWAY_LIMITS
) as client:
yield OwnedProxy(Gateway(client, gateway.key, gateway.upstream_url), launch.process, launch.log)
finally:
_stop_launch(launch)
def _is_ready(client: httpx.Client) -> bool:
try:
return client.get("/health/readiness", timeout=2).status_code == 200
except httpx.TransportError:
return False
def refused_boot_log(
gateway: Gateway,
directory: Path,
overrides: Mapping[str, str],
*,
config: Path | None = None,
) -> str:
"""Start the proxy and return its log once it exits non-zero instead of becoming ready."""
root: Final = _proxy_root()
environment: Final = _proxy_environment(gateway, overrides, ())
output: Final = Path(os.environ.get("INTEGRATION_RESULTS_DIR", str(directory)))
output.mkdir(parents=True, exist_ok=True)
command: Final = (
sys.executable,
"-m",
"integration._support.proxy",
"--config",
str(config or "tests/integration/proxy_config.yaml"),
"--host",
"127.0.0.1",
"--num_workers",
"1",
*DB_PUSH,
)
launch: Final = _launch(command, root, environment, output)
try:
with httpx.Client(base_url=f"http://127.0.0.1:{launch.port}", timeout=15, trust_env=False) as client:
deadline: Final = time.monotonic() + readiness_seconds(1)
while launch.process.poll() is None:
assert not (_owns_listener(launch) and _is_ready(client)), (
f"Proxy became ready instead of refusing to boot:\n{launch.log.read_text()}"
)
assert time.monotonic() < deadline, "Proxy neither exited nor became ready within the deadline"
time.sleep(0.1)
assert launch.process.returncode != 0, f"Proxy exited 0 instead of refusing to boot:\n{launch.log.read_text()}"
return launch.log.read_text()
finally:
_stop_launch(launch)
_UPSTREAM_READY_SECONDS: Final = 60
_LOOPBACK: Final = "127.0.0.1"
@dataclass(frozen=True, slots=True)
class UpstreamCertificate:
certificate: Path
key: Path
def self_signed_certificate(directory: Path) -> UpstreamCertificate:
"""A one-day self-signed certificate for 127.0.0.1, for an owned upstream a provider only reaches over TLS."""
private_key: Final = rsa.generate_private_key(public_exponent=65537, key_size=2048)
name: Final = x509.Name([x509.NameAttribute(NameOID.COMMON_NAME, _LOOPBACK)])
issued: Final = datetime.now(UTC)
certificate: Final = (
x509.CertificateBuilder()
.subject_name(name)
.issuer_name(name)
.public_key(private_key.public_key())
.serial_number(x509.random_serial_number())
.not_valid_before(issued - timedelta(minutes=5))
.not_valid_after(issued + timedelta(days=1))
.add_extension(x509.SubjectAlternativeName([x509.IPAddress(IPv4Address(_LOOPBACK))]), critical=False)
.sign(private_key, hashes.SHA256())
)
certificate_path: Final = directory / f"owned-upstream-{uuid.uuid4().hex}.crt"
key_path: Final = directory / f"owned-upstream-{uuid.uuid4().hex}.key"
certificate_path.write_bytes(certificate.public_bytes(serialization.Encoding.PEM))
key_path.write_bytes(
private_key.private_bytes(
serialization.Encoding.PEM, serialization.PrivateFormat.PKCS8, serialization.NoEncryption()
)
)
return UpstreamCertificate(certificate_path, key_path)
class UpstreamSlot:
"""A scripted upstream a test module owns on a fixed port, so a cell can take it down and bring it back.
It runs from the harness's own checkout, never ``INTEGRATION_PROXY_ROOT``: the double belongs to the tests,
the proxy root only names the litellm under test."""
__slots__ = ("certificate", "directory", "inherited", "port", "process", "root")
def __init__(
self,
directory: Path,
port: int,
root: Path,
certificate: UpstreamCertificate | None = None,
inherited: Mapping[str, str] = os.environ,
) -> None:
self.directory = directory
self.port = port
self.root = root
self.certificate = certificate
self.inherited = inherited
self.process: subprocess.Popen[bytes] | None = None
@property
def url(self) -> str:
scheme: Final = "http" if self.certificate is None else "https"
return f"{scheme}://{_LOOPBACK}:{self.port}"
def _tls_arguments(self) -> tuple[str, ...]:
if self.certificate is None:
return ()
return ("--ssl-certfile", str(self.certificate.certificate), "--ssl-keyfile", str(self.certificate.key))
def start(self) -> None:
assert self.process is None, "Owned upstream is already running"
output: Final = Path(self.inherited.get("INTEGRATION_RESULTS_DIR") or self.directory)
log_path: Final = output / f"owned-upstream-{self.port}-{uuid.uuid4().hex}.log"
with log_path.open("w") as log:
process: Final = subprocess.Popen(
[
sys.executable,
"-m",
"integration._support.upstream",
"--port",
str(self.port),
*self._tls_arguments(),
],
cwd=self.root,
env=dict(self.inherited),
stdout=log,
stderr=subprocess.STDOUT,
start_new_session=True,
)
self.process = process
try:
deadline: Final = time.monotonic() + _UPSTREAM_READY_SECONDS
while process.poll() is None:
try:
probe: Final = httpx.get(
f"{self.url}/health", timeout=2, trust_env=False, verify=self.certificate is None
)
if probe.status_code == 200:
return
except httpx.TransportError:
pass
assert time.monotonic() < deadline, f"Owned upstream readiness deadline exceeded: {log_path}"
time.sleep(0.1)
raise AssertionError(f"Owned upstream exited before readiness: {log_path}")
except BaseException:
self.stop()
raise
def stop(self) -> None:
process: Final = self.process
assert process is not None, "Owned upstream is not running"
self.process = None
_stop(process)
def _harness_root() -> Path:
return Path(__file__).resolve().parents[3]
@contextmanager
def owned_upstream(
directory: Path, *, tls: bool = False, port: int | None = None, inherited: Mapping[str, str] = os.environ
) -> Generator[UpstreamSlot]:
certificate: Final = self_signed_certificate(directory) if tls else None
slot: Final = UpstreamSlot(directory, port or _free_port(), _harness_root(), certificate, inherited)
try:
slot.start()
yield slot
finally:
if slot.process is not None:
slot.stop()