Adds budget_source (team_default, custom, none) to each membership in /team/info and a
POST /team/{team_id}/member/{user_id}/reset_budget route that relinks a member to the team's
shared team_member_budget row without touching their spend. The Admin UI team members table
shows a Team default or Custom badge next to each member's budget and offers a
Use team default action on customized members
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Resolves the conflicts with the WebSocket request defaults from main (PR #41881):
the relay keeps both custom_llm_provider and request_defaults, and a masked
response.create frame is re-serialized when the defaults changed it.
Keeps the first-frame routing hints (input, previous_response_id) out of the
deployment request defaults so they never get injected into later frames on the
same connection, with a regression test.
Drop the core ocr() facade so VertexAuth and the http pool stay out of litellm-core's
public API, move the http Error enum to error.rs, and inject the media DNS resolver into
HttpClientPool instead of a per-call builder hook the cache key ignored.
The bridge now reads litellm.* HTTP settings only through litellm/rust_bridge/settings.py,
pinned by python_settings.json, while env overrides stay in Rust. This adds the Python
default User-Agent, parses string ssl_verify globals like get_ssl_verify, drops per-call
ssl_verify that Python OCR never honored, and removes the unused request_timeout.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Unprefixed release bullets now count as other_updates, concurrent cache misses share one upstream GitHub request through an injected asyncio.Lock, and the dashboard upgrade banner is announced as status rather than alert
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Format the ported files, annotate mutable wire payloads, give the e2e
OAuth client the SDK 2 httpx2/AuthorizationCodeResult API, tighten the
transport-streams alias to the two-stream SDK 2 shape, and add a
test-quality reason for the MockTransport factory injection.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
New matrix job across Python 3.10-3.14 verifies uv.lock against the
declared floors, installs the locked mcp+proxy extras and runs the MCP
unit suites, then resolves the same extras with uv's lowest-direct
strategy into a clean venv and runs scripts/check_mcp_sdk_install.py to
prove the floor still imports the SDK 2 API surface.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Call handlers with ServerRequestContext and params models, seed the
litellm contextvar instead of the removed SDK request_ctx, forward
headers/auth through the httpx2 MockTransport factory, and add
regressions for handler registration, context propagation, and modern
protocol-version rejection.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Port the proxy MCP server off the removed SDK1 decorator API. Handlers now
take (ctx, params), are registered via add_request_handler, and return full
result models. Request-scoped session/context propagation moves to a
litellm-owned active_mcp_request_ctx_var ContextVar set at handler entry.
Reject MCP-Protocol-Version values outside the SDK2 handshake set with a
400 before session-manager delegation. Fold SDK2 MCPError-wrapped parse
and content-type failures into the existing connection diagnostics.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
A V1 CustomGuardrail with moderation_check pre_call returned out of
during_call_hook before asyncio.gather, abandoning already-queued
CustomLogger moderation coroutines and skipping every later callback.
Skip only that guardrail instead.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
