chore(ci): promote internal staging to main

.circleci/config.yml

@@ -2744,84 +2744,6 @@ jobs:
           file: ./coverage.xml
           flags: circleci
 
-  ui_build:
-    docker:
-      - image: cimg/node:24.19@sha256:8966565f07189a67d64d6808a2b127f31dafae566508e3547f55640e1070bfad
-        auth:
-          username: ${DOCKERHUB_USERNAME}
-          password: ${DOCKERHUB_PASSWORD}
-    resource_class: medium+
-    working_directory: ~/project
-    steps:
-      - checkout
-      - skip_if_unrelated_changes:
-          category: client
-      - setup_google_dns
-      - restore_cache:
-          keys:
-            - ui-build-deps-v1-{{ checksum "ui/litellm-dashboard/package-lock.json" }}
-            - ui-build-deps-v1-
-      - restore_cache:
-          keys:
-            - ui-nextjs-cache-v1-{{ checksum "ui/litellm-dashboard/package-lock.json" }}
-            - ui-nextjs-cache-v1-
-      - run:
-          name: Install dependencies
-          command: |
-            cd ui/litellm-dashboard
-            npm ci
-      - save_cache:
-          key: ui-build-deps-v1-{{ checksum "ui/litellm-dashboard/package-lock.json" }}
-          paths:
-            - ui/litellm-dashboard/node_modules
-      - run:
-          name: Build UI
-          command: |
-            cd ui/litellm-dashboard
-            source ./build_ui.sh
-      - save_cache:
-          key: ui-nextjs-cache-v1-{{ checksum "ui/litellm-dashboard/package-lock.json" }}
-          paths:
-            - ui/litellm-dashboard/.next/cache
-      - persist_to_workspace:
-          root: .
-          paths:
-            - litellm/proxy/_experimental/out
-
-  ui_unit_tests:
-    docker:
-      - image: cimg/node:24.19@sha256:8966565f07189a67d64d6808a2b127f31dafae566508e3547f55640e1070bfad
-        auth:
-          username: ${DOCKERHUB_USERNAME}
-          password: ${DOCKERHUB_PASSWORD}
-    resource_class: xlarge
-    working_directory: ~/project
-    steps:
-      - checkout
-      - skip_if_unrelated_changes:
-          category: client
-      - setup_google_dns
-      - restore_cache:
-          keys:
-            - ui-unit-deps-v1-{{ checksum "ui/litellm-dashboard/package-lock.json" }}
-            - ui-unit-deps-v1-
-      - run:
-          name: Install dependencies
-          command: |
-            cd ui/litellm-dashboard
-            npm ci
-      - save_cache:
-          key: ui-unit-deps-v1-{{ checksum "ui/litellm-dashboard/package-lock.json" }}
-          paths:
-            - ui/litellm-dashboard/node_modules
-      - run:
-          name: Run UI unit tests (Vitest)
-          command: |
-            cd ui/litellm-dashboard
-
-            CI=true npm run test -- --run \
-              --pool forks --poolOptions.forks.maxForks=6
-
   e2e_ui_testing:
     docker:
       - image: cimg/python:3.12-browsers@sha256:b432899af01c9a311bf74f4f22e9ada2e5306d4b1b4383f8d29e1228a5844ef2
@@ -3181,12 +3103,6 @@ workflows:
           filters: *main_branches
       - litellm_router_unit_testing:
           filters: *main_branches
-      - ui_build:
-          filters: *main_branches
-      - ui_unit_tests:
-          requires:
-            - ui_build
-          filters: *main_branches
       - auth_ui_unit_tests:
           filters: *main_branches
       - proxy_behavior_tests:

.github/pull_request_template.md

@@ -64,12 +64,36 @@ If you're seeing a delay in your PR being merged, ping the LiteLLM Team on [Slac
 ## Screenshots / Proof of Fix
 
 <!-- Include screenshots, screen recordings, or command (e.g., curl) + output demonstrating that your changes work as expected
-     The proof must be completely e2e with no mocks, using, for example, actual LLM calls costing real $. `pytest` commands are not enough
-     For bug fixes: show reproduction before the fix and passing behavior after
-     Include the commit hash each proof was captured at, for both the before and the after runs
-     If the change applies to all three LLM endpoints (/v1/responses, /v1/chat/completions, /v1/messages), include proof for every single one of them, not just one
-     For new features: show the feature working end-to-end
-     For UI changes: include before/after screenshots -->
+     The proof must be completely e2e with no mocks, using actual LLM calls costing real $$$ if applicable. `pytest` commands are not enough
+     Show ONLY the latest run: capture Before at the merge base and After at the PR's current tip, and when new commits change behavior, replace this whole section with the fresh run instead of stacking it on top of older ones. The run must be up to date. As soon as a new commit is made and it makes this PR description's after sha stale (it's no longer tip of PR), you must re-run the QA
+     Structure the section exactly as below: Before and After one heading level below this section, each naming the commit hash it was captured at, one lower-level heading per case inside each, the same case names in the same order on both sides, and numbered steps (command, observed output) under every case, never loose prose; shared setup (config, payloads) goes above Before, and with a single case, drop the case headings and number the steps directly
+
+### Before (<hash>)
+
+#### <case 1>
+
+1. ...
+2. ...
+
+#### <case 2>
+
+1. ...
+
+### After (<hash>)
+
+#### <case 1>
+
+1. ...
+2. ...
+
+#### <case 2>
+
+1. ...
+
+     For bug fixes: Before shows the reproduction, After shows the same steps passing
+     For new features: Before shows the capability missing, After shows it working end-to-end
+     If the change applies to all three LLM endpoints (/v1/responses, /v1/chat/completions, /v1/messages), make each endpoint its own case, not just one
+     For UI changes: before/after screenshots under the same headings -->
 
 ## Type
 

CLAUDE.md

@@ -53,6 +53,8 @@ When you fix violations gated by `ruff-strict-budget.json`, `type-discipline-bud
 
 `make check` (f.k.a. `make pre-commit`, which still works identically as an alias) saves its complete output to a log file in .git (overwriting previous logs) and prints that path as its first and last output lines. To inspect a run, read or grep that log instead of re-running the multi-minute checks just to see a different slice
 
+`make check`, `make lint`, `scripts/pre_commit_lint.sh`, and the standalone budget gates (`scripts/ruff_strict_gate.py`, `scripts/type_discipline_gate.py`, `scripts/type_check_gate.py`) each hold one of 2 machine-wide slots, so when other sessions or worktrees on the same box are already running heavy work, yours prints "all N machine-wide slots are busy; queueing" and then stays quiet until a slot frees. Give the command a long timeout and let it wait rather than killing it, retrying it, or assuming it hung. Don't change the # of machine-wide slots or make it unlimited by setting `LITELLM_GATE_SLOTS=0`
+
 If you're trying to create a new function that relies on untyped stuff, instead of adding more Any's and pushing `reportAny` / `reportExplicitAny` closer to their basedpyright ceilings, just validate it in the caller with Pydantic (a model or `TypeAdapter` that returns the typed thing or raises will do) and then pass the now typed variable in
 
 If you get an LIT001 or LIT002 fail, refactor the code to follow functional programming best practices rather than introducing mutable data structures. For example, build values in one shot with comprehensions or generators wrapped in `tuple()` / `MappingProxyType()` / `frozenset()` instead of seeding an empty `list`/`dict`/`set` and mutating it over time. Ideally, `# mutable-ok` is never used; reach for it only as a genuine last resort when an immutable rewrite is truly impossible, and always pair it with a real reason
@@ -83,7 +85,8 @@ Follow these coding conventions for new/updated code (a three-line fix in a lega
 - Never-nester: early returns over deep nesting
 - Don't throw; model failures as values (One function (e.g., raise_public) maps error union to existing public exception contracts via exhaustive match + assert_never)
 - No mutation; don't reassign variables, global or local. Instead of mutable lists and dicts, prefer tuples, frozen dataclasses (with slots=True), `MappingProxyType`, etc.
-  - Annotate every variable with `: Final` (LIT010). Unpacking and walrus targets cannot carry the annotation, so they are implicitly final. Don't rebind them. Never rebind or mutate function parameters (LIT011); `self`/`cls` attribute stores are the exception. If rebinding or in-place mutation is truly unavoidable, suppress with `# rebind-ok: <reason>` explaining why
+  - Annotate every variable with `: Final` (LIT010). Unpacking and walrus targets cannot carry the annotation, so they are implicitly final. Don't rebind them. Never rebind or mutate function parameters (LIT011); `self`/`cls` attribute stores are the exception. If rebinding or in-place mutation is truly unavoidable, suppress with `# rebind-ok: <reason>`
+  - Qualify every TypedDict field with `ReadOnly[...]` (LIT012), which nests freely with `Required` / `NotRequired` / `Annotated` in any order. If making the key writable is truly unavoidable, suppress with `# writable-ok: <reason>`
 - Use dependency injection
 - Fully typed; no `Any` or coarse types like `dict[str, Any]` or just `dict`. Every function parameter must be strongly typed
 - Use tagged unions + match

Makefile

@@ -4,11 +4,11 @@
 .PHONY: help test test-unit test-unit-llms test-unit-proxy-guardrails test-unit-proxy-core test-unit-proxy-misc \
 	test-unit-integrations test-unit-core-utils test-unit-other test-unit-root \
 	test-proxy-unit-a test-proxy-unit-b test-integration test-unit-helm \
-	info lint lint-dev lint-checks format \
+	info lint lint-inner lint-dev lint-checks format \
 	lint-basedpyright lint-e2e-basedpyright lint-basedpyright-budget-update lint-type-discipline lint-type-discipline-budget-update \
 	lint-ruff-budget lint-ruff-budget-update lint-budget-update lint-gate \
 	install-dev install-proxy-dev install-test-deps install-hooks \
-	install-helm-unittest check-circular-imports check-import-safety check pre-commit \
+	install-helm-unittest check-circular-imports check-import-safety check check-inner pre-commit \
 	lint-install lint-fetch-base bootstrap
 
 # Default target
@@ -52,10 +52,17 @@ help:
 	@echo "  make test-proxy-unit-b  - Run proxy_unit_tests (p-z, ~28 files)"
 	@echo "  make test-integration   - Run integration tests"
 	@echo "  make test-unit-helm     - Run helm unit tests"
+	@echo ""
+	@echo "Heavy targets (check, lint) queue for LITELLM_GATE_SLOTS machine-wide"
+	@echo "slots (default 2; 0 disables) so parallel sessions don't thrash one machine."
 
 UV := uv
 UV_RUN := $(UV) run --no-sync
 
+# Machine-wide slot queue for the heavy targets below; python3 + stdlib only, so
+# it runs before any venv exists. See scripts/gate_slot_lock.py.
+GATE_SLOT_LOCK := python3 scripts/gate_slot_lock.py
+
 LINT_DEP_INSTALL ?= install-dev
 LINT_E2E_DEP_INSTALL ?= lint-install
 LINT_DEP_BASE ?= lint-fetch-base
@@ -73,6 +80,8 @@ info:
 install-dev:
 	$(UV) sync --inexact --frozen
 
+# Deliberately unqueued: provisioning is I/O bound, so it doesn't need one of the
+# machine-wide slots the CPU-bound gates below share.
 bootstrap:
 	$(UV) sync --inexact --frozen --extra proxy --group proxy-dev --group e2e-dev
 	$(UV_RUN) python scripts/prisma_generate_if_needed.py
@@ -229,7 +238,10 @@ check-import-safety: $(LINT_DEP_INSTALL)
 # does (merge-base with origin/litellm_internal_staging). Setup (env sync, Prisma client,
 # base fetch) runs once up front; the checks themselves are independent, so a sub-make
 # fans them out with -j and the fast ones finish under basedpyright's shadow.
-lint: lint-install lint-fetch-base
+lint:
+	@$(GATE_SLOT_LOCK) $(MAKE) lint-inner
+
+lint-inner: lint-install lint-fetch-base
 	$(MAKE) -j $(LINT_JOBS) $(LINT_OUTPUT_SYNC) LINT_DEP_INSTALL= LINT_E2E_DEP_INSTALL= LINT_DEP_BASE= lint-checks
 
 lint-checks: lint-format-check-changed lint-ruff lint-gate lint-type-discipline lint-basedpyright lint-e2e-basedpyright check-circular-imports check-import-safety
@@ -244,7 +256,10 @@ lint-dev: lint-format-changed check-circular-imports check-import-safety
 # test-linting.yml (Python), test-litellm-ui-build.yml's frontend-lint (dashboard), and
 # check-ui-api-types.yml (API-type drift), skipping any whose files aren't in scope.
 # Not auto-installed as a git hook so it never slows an unrelated human commit.
-check: bootstrap
+check:
+	@$(GATE_SLOT_LOCK) $(MAKE) check-inner
+
+check-inner: bootstrap
 	./scripts/pre_commit_lint.sh
 
 pre-commit:

backend/routes/allowlist.py

@@ -146,11 +146,13 @@
         "/docs/oauth2-redirect",
         "/redoc",
         "/fallback/login",
+        "/mcp",  # bare spelling of the aggregate MCP endpoint; /mcp/ prefix covers the rest
     }
 )
 
 BACKEND_MOUNT_PATHS: frozenset[str] = frozenset(
     {
         "/swagger",  # API documentation static assets belong to the backend
+        "/mcp",  # lazily-mounted MCP sub-app serves on the backend component
     }
 )