Enforcement treats max_budget 0 on the team default as "no cap" and only
honors 0 as an explicit disable on a member's own row, so reporting an
inheriting member as capped at 0 said the opposite of what happens on their
next request.
Adds POST /management/v1/teams/{team_id}/members/bulk_update, a merge patch
over per-member limits (max_budget_in_team, tpm_limit, rpm_limit,
budget_duration, allowed_models) for up to 500 members in one transaction.
Editing a team's default member budget has never reached members who already
have a budget row, because /team/member_add clones the default per member.
This gives admins one call to roll a new cap out across the roster, and each
result carries max_budget_source so a caller can see whether a member is on
their own cap or on the team default.
Reads run on the writer inside the batch transaction, and any budget row more
than one membership points at is cloned before it is written, so raising one
member's cap never moves another's.
A service-account key can now carry end_user_budget_id in its metadata. When a request through that key names a customer that does not exist yet, the key's budget is applied to the new customer from the first request and wins over the proxy-wide max_end_user_budget_id. A customer with an explicitly assigned budget keeps it. The Admin UI exposes the setting on service-account key creation and key edit, and only proxy admins may set or clear it.
Resolves LIT-7996
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
StartTranscriptionJob was logged with response_cost 0.0, so key, team and proxy
budgets never stopped repeated jobs on the proxy's AWS credentials. The success
handler now polls GetTranscriptionJob to completion, reads the audio duration
from the transcript artifact and charges whole seconds at the cost map rate,
charging the longest media AWS accepts when the duration cannot be read. The
route refuses job classes and surcharge features the cost map does not price
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Deepgram charges for the total processed audio across channels, so a stereo /listen session with multichannel=true costs twice its duration. The handler now multiplies the session duration by a validated channel count taken from Metadata.channels, then the widest Results channel_index, then the channels query parameter, defaulting to one. Booleans, floats, strings, zero and negative values are ignored
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The streaming wrapper caught every exception crossing its boundary and named its own
callback, so a block by an inner guardrail or a provider stream failure also named every
outer guardrail. The wrapper now runs the hook over an upstream boundary that remembers
the exception it raised, and skips attribution when the same exception passes through
Pipeline blocks converted from SensitiveDataRouteException or ModifyResponseException into
a generic guardrail_pipeline_error now still record the blocking step's guardrail
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Adds temp_budget_increase and temp_budget_expiry to the team member edit form with pair validation,
seeds stored values into edit mode, sends both through /team/member_update, and adds cached-key auth
and reservation regression tests for active and expired increases
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Adds the mcp_allowed_clients general setting, enforced against the
clientInfo.name each MCP client sends in its initialize request. A client
not on the list, or one that does not identify itself, is rejected with
403 before any stateful session is created. The setting is configurable
from config.yaml and from the Admin UI MCP network settings page
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
With callback or callback_method in the query, Deepgram sends every Results and Metadata frame to the caller's URL and only a request id down this socket, so the proxy would meter zero seconds of audio while its own Deepgram credential paid for the transcription. The route now closes such connections with 1008 before contacting Deepgram, naming the offending parameters in the close reason. Adds helper and route tests for both parameters and a nine mutation sweep, all killed
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Replace the per-deployment asyncio.Semaphore with MaxParallelRequestsLimit, which admits a call synchronously or raises the router's RateLimitError (429) right away. Nothing waits for a slot any more, so the max_parallel_requests_queue_size and default_max_parallel_requests_queue_size settings from the earlier commits are dropped along with their proxy validation, dashboard control and generated schema entries. The rpm/tpm derivation of the cap is unchanged. Every router endpoint family now enters the slot through one _deployment_slot context, and the provider coroutine is only created once the slot is held
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
DELETE /v1/files/{id} only lets a proxy admin key delete a raw s3:// or
gs:// file id, because such ids skip the managed-file owner check. The
batch lifecycle cleanup deleted the vertex_ai raw ids with the test's
own virtual key and got a 403 at teardown on every build since #194
Raw cloud-storage ids now go through the master key; managed and
provider-native ids keep using the creating key
The team access-group fixture polled a 403 until its message enumerated
the team's allow-list, because registering a team-scoped deployment
appends that deployment to the list and the fixture has to wait for the
reset to land. #41310 replaced that message with a fixed client-facing
one, so the poll never matched and both tests errored at setup
The allow-list is now read back from /team/info until it holds exactly
the access group
The check spins up a hypercorn TLS peer and drives the SDK's own httpx
handlers at it, so it needs litellm importable, hypercorn installed and a
loopback socket. It lived under tests/e2e, whose Buildkite runner image
installs neither litellm nor hypercorn by design (the suite drives a
remote proxy over HTTP), so every scheduled e2e build since #230 failed
to import the module and pytest reported it as a collection error. The
unit tree bans sockets, so it does not belong there either
tests/integration is the CircleCI tier built for real TCP against local
protocol peers. This adds an sdk shard to it for cases that exercise the
SDK's clients with no gateway in the path, registers the two HTTP/2
nodes in the contracts manifest, and adds the shard to the CircleCI
matrix. The test now flips the feature through LITELLM_HTTP2 (the user
surface) instead of patching module attributes, and asserts the version
the peer observed on the wire next to the one the client reports
The Rust bridge imported httpx to construct the provider error response, which
fails in the isolated wheel check where httpx is absent. Rust now raises
RustUpstreamError with a headers attribute and the Python lifecycle wraps it in
a typed UpstreamFailure carrying the httpx.Response before legacy mapping.
Test helpers gained call_native so pytest.raises blocks hold a single call
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
