The sandbox read user_api_key_* off the top level of request_data, where the proxy never writes them, and only forwarded request_data["metadata"], which is empty on /v1/messages, /v1/responses, batches and files because those routes keep proxy state in litellm_metadata. Merge both buckets (litellm_metadata wins) and resolve ids from the merged dict
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Prompt Security reports a queued sanitization job as status "created" before
it moves to "in progress" and "done". The poller treated anything other than
those two known strings as an error and returned HTTP 500 on the first poll, so
every image or file request through the guardrail failed while the vendor job was
still queued.
Only "done" is terminal now. Every other status is logged and polled again until
max_poll_attempts or the outer file_sanitization_timeout, after which the existing
fail-open or fail-closed (408) policy applies.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
A not_run entry from the base guardrail only carries guardrail_name, while the
content filter's evaluated entry carries guardrail_id. Keyed apart, one request
listed twice in the monitor for a logging_only guardrail (Not run and Passed).
Resolve the id from a same-name sibling in the payload so the severity pick applies
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Importing the fallback from litellm.proxy.hooks.rate_limiter_utils at the top
of litellm/integrations/prometheus.py closed an import cycle CodeQL flagged on
#41059 (rate_limiter_utils -> litellm -> ... -> prometheus). Hoist the constant
into litellm/constants.py so both modules read it from a leaf module.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The virtual key created by AUTO_REGISTER replaced the JWT principal without
the agent_id auth_builder had resolved from agent_id_jwt_field, so agent
policies were skipped on that request and every later mapped-key request.
Pass the bound agent_id into generate_key_helper_fn and onto the returned
principal.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Releasing the slot unconditionally from the route raced the limiter's own
success handler on the logging worker: both could read the same stashed
acquisition before either cleared it, and under the integer in-memory
fallback that double-decrements the counter. The route now releases only on
exits without a success callback (pre-call rejection, pre-call cancellation,
and Phase 2 exits without the success stamp), matching the HTTP disconnect
path's ownership rule.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
CodeQL py/ineffectual-statement flags the bare ellipsis body of the
@property declaration on the RealtimeClientWebSocket protocol. A plain
attribute annotation states the same structural contract without an
expression statement.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Pre-call limiters reject before a deployment is attached to request_data, so
the failure hook could not resolve api_provider for router aliases and emitted
api_provider="None" on litellm_proxy_failed_requests_metric_total and
litellm_proxy_total_requests_metric_total. Fall back to the provider the
limiter already resolved onto RateLimitError.llm_provider, keeping request
data as the first source and ignoring the proxy placeholder.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
_client_async_logging_helper re-submitted logging_obj.success_handler to the
executor after _dispatch_success_logging had already done so, running the same
success pipeline twice per async request and racing on shared logging state.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
