A LiteLLM virtual key in the Authorization header admits the caller but is not an Entra assertion the guardrail can exchange, so the connect-time RFC 9728 challenge now fires unless the bearer is a compact JWS. The guardrail parses the inbound bearer with the same predicate
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Building the guardrail's tool metadata from the local registry entry that
dispatch resolved, instead of re-deriving it from the tool name, keeps an
OpenAPI operation whose name starts with its own server prefix from being
reported with the shorter operation's description and schema. The registry
branch in get_listed_tool is gone with it, and the test doubles for the
local registry now carry a string description and dict schema like the real
entries do
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The sequential version sent one request at a time, so a Redis outage never
reached the concurrency where the failed-tracking alert body actually grows.
This drives the proxy with locust against one model group of three mock
deployments, two failing at order 1 and one serving at order 2, so every
request spends its retries on the failing pair and lands on the serving
deployment through the order-based fallback. Two phases, a healthy baseline
and a CLIENT PAUSE WRITE window, and every request must succeed in both.
Latency, RSS and CPU are reported as p50/p90/p99 per phase rather than
asserted on: RSS and CPU come from psutil on the proxy's process tree, since
a multi-worker proxy serves /metrics from the prometheus multiprocess
collector and that drops the process collector's series. Thresholds stay open
until weekly runs give real baselines.
Co-Authored-By: Claude Code <noreply@anthropic.com>
OpenAPI-generated and legacy local-registry tools dispatch through execute_mcp_tool's
local branch, which called pre_call_tool_check without the cached MCPTool. Agent 365
therefore received bare {"name"} payloads for those tools while managed-server tools
carried description and inputSchema. Both local call sites now pass get_listed_tool
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The recursion detector flags any unignored recursive function, so the
timeout classification now walks the explicit cause chain with a
bounded generator instead of calling itself
Scopeless Agent 365 gated servers now advertise api://<client_id>/access_as_user instead of
staying silent, so a client can still sign in. Entra rejecting the gateway's own credentials
(invalid_client, unauthorized_client, invalid_scope, invalid_resource) follows unreachable_fallback
rather than telling the caller to sign in again with a 401
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
redis-py's blocking pool reports a saturated pool as ConnectionError chained
from asyncio.TimeoutError. The circuit breaker classified that as a hard
connectivity failure and opened at once while Redis was healthy. Follow the
explicit cause chain so it counts as a timeout and stays behind the
timeout_min_duration gate
Each checkpoint now samples until no new worker has answered for the settle
window, and the growth assertion refuses a worker set that changed between the
warm and after checkpoints instead of comparing only the intersection, so a
leaking worker reached by one checkpoint alone cannot drop out of the gate
The provider budget push runs inside the request success callback, so
awaiting the Redis pipeline there made every request wait for the round
trip. Hand it back to a task whose failure is logged through the breaker
aware logger, so an open breaker stays a debug line and a real Redis error
is one error line instead of an unretrieved task traceback
The release image installs only the proxy extras, and psutil is a locust and mirakuru dev
dependency, so /debug/memory/summary answered with an error and no ram_usage_mb on the e2e
gate. Fall back to /proc/self/statm and /proc/meminfo on Linux when psutil cannot be imported
