BerriAI/litellm · error · HTTPException
Invalid CLI login session id
Error message
Invalid CLI login session id
What it means
Error "Invalid CLI login session id" thrown in BerriAI/litellm.
Source
Thrown at litellm/proxy/management_endpoints/ui_sso.py:400
)
if current_attempts > _CLI_SSO_START_RATE_LIMIT_MAX_ATTEMPTS:
raise HTTPException(
status_code=429,
detail="Too many CLI login attempts. Try again later.",
)
def _get_cli_sso_flow_or_raise(login_id: str | None, cache: DualCache) -> dict:
if isinstance(login_id, str) and login_id.startswith("sk-"):
raise HTTPException(
status_code=400,
detail=(
"Your litellm CLI is out of date and uses a login flow this proxy no longer supports. "
"Upgrade it with `pip install -U 'litellm[proxy]'` and run `litellm-proxy login` again."
),
)
if not _is_valid_cli_sso_login_id(login_id):
raise HTTPException(status_code=400, detail="Invalid CLI login session id")
cache_key: Final = _get_cli_sso_flow_cache_key(cast(str, login_id))
redis_cache: Final = cache.redis_cache
if redis_cache is not None:
flow = redis_cache.get_cache(key=cache_key)
else:
flow = cache.get_cache(key=cache_key)
if isinstance(flow, str):
try:
flow = _as_object(json.loads(flow))
except ValueError:
flow = None
if not isinstance(flow, dict) or "poll_secret_hash" not in flow:
verbose_proxy_logger.warning(
"CLI SSO login session not found in cache for login_id=%s. If the proxy runs multiple replicas, "
"a shared Redis cache is required for CLI login to work.",
login_id,
)View on GitHub (pinned to 77b7c6c40c)
Solutions
- Run `litellm-proxy login` again to start a fresh CLI login session.
When it happens
Trigger: Thrown at litellm/proxy/management_endpoints/ui_sso.py:400 when the library encounters an invalid state.
Common situations: See trigger scenarios.
AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18).
Data as JSON: /api/errors/ec0d080d19a3201b.
Report an issue: GitHub.