Merge branch 'litellm_internal_staging' into fix/litellm-prisma-generate-oob

2026-09-06 08:16:43 +00:00 · 2026-07-12 10:37:13 +02:00 · 2026-07-12 10:37:13 +02:00 · 528653d4c2
commit 528653d4c2
parent 4ddcc8bd32 3e9e52042a
2468 changed files with 148258 additions and 22238 deletions
--- a/.circleci/config.yml
+++ b/.circleci/config.yml
@ -5,6 +5,16 @@ orbs:
  win: circleci/windows@5.0 # Add Windows orb

 commands:
+  skip_if_unrelated_changes:
+    parameters:
+      category:
+        type: enum
+        enum: ["backend", "client"]
+        default: "backend"
+    steps:
+      - run:
+          name: "Skip job when no << parameters.category >>-relevant files changed"
+          command: bash .circleci/scripts/path_filter.sh << parameters.category >>
  setup_google_dns:
    steps:
      - run:
@ -282,6 +292,7 @@ jobs:
    parallelism: 4
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - restore_cache:
          keys:
@ -354,6 +365,7 @@ jobs:
    parallelism: 4
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - restore_cache:
          keys:
@ -427,6 +439,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - restore_cache:
          keys:
@ -480,6 +493,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -545,6 +559,7 @@ jobs:
      DATABASE_URL: "postgresql://postgres:postgres@localhost:5432/litellm_test"
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -584,6 +599,7 @@ jobs:
      DATABASE_URL: "postgresql://postgres:postgres@localhost:5432/litellm_test"
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -624,6 +640,7 @@ jobs:
      DATABASE_URL: "postgresql://postgres:postgres@localhost:5432/litellm_test"
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -656,6 +673,7 @@ jobs:
      FAKE_OPENAI_API_BASE: http://127.0.0.1:8190
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - restore_cache:
@ -705,6 +723,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - restore_cache:
@ -755,6 +774,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -787,6 +807,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - restore_cache:
@ -832,6 +853,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -877,6 +899,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -918,6 +941,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -963,6 +987,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1004,9 +1029,12 @@ jobs:
      - *python312_image
    working_directory: ~/project
    resource_class: large
+    environment:
+      REQUEST_TIMEOUT: "180"

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - restore_cache:
@ -1032,7 +1060,8 @@ jobs:
                -v -x \
                --junitxml=test-results/junit.xml \
                --durations=5 \
-                -n 8"
+                -n 8 \
+                --reruns 1 --only-rerun Timeout"
          no_output_timeout: 15m

      # Store test results
@ -1045,6 +1074,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1089,6 +1119,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1132,6 +1163,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1163,6 +1195,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1205,6 +1238,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1248,6 +1282,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1291,6 +1326,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1321,6 +1357,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1366,6 +1403,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1407,6 +1445,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - restore_cache:
          keys:
@ -1459,6 +1498,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1482,6 +1522,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1507,6 +1548,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1531,6 +1573,7 @@ jobs:

    steps:
      - checkout
+      - skip_if_unrelated_changes
      - attach_workspace:
          at: ~/project
      - setup_google_dns
@ -1570,14 +1613,14 @@ jobs:
      - run:
          name: Run helm lint
          command: |
-            helm lint ./deploy/charts/litellm-helm
+            helm lint ./helm/litellm-helm

      # Run helm tests
      - run:
          name: Run helm tests
          command: |
            IMAGE_TAG=${CIRCLE_SHA1:-ci}
-            helm install litellm ./deploy/charts/litellm-helm -f ./deploy/charts/litellm-helm/ci/test-values.yaml \
+            helm install litellm ./helm/litellm-helm -f ./helm/litellm-helm/ci/test-values.yaml \
              --set image.repository=litellm-ci \
              --set image.tag=${IMAGE_TAG} \
              --set image.pullPolicy=Never
@ -1606,6 +1649,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1698,6 +1742,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - attach_workspace:
          at: ~/project
      - setup_google_dns
@ -1746,13 +1791,13 @@ jobs:
              -e LANGFUSE_PROJECT1_SECRET=$LANGFUSE_PROJECT1_SECRET \
              -e LANGFUSE_PROJECT2_SECRET=$LANGFUSE_PROJECT2_SECRET \
              -e RECORDER_OPENAI_BASE_URL=http://host.docker.internal:8090/v1 \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app \
              -v $(pwd)/proxy_server_config.yaml:/app/config.yaml \
              my-app:latest \
              --config /app/config.yaml \
-              --port 4000 \
-              --detailed_debug \
+              --port 4000
      - run:
          name: Start outputting logs
          command: docker logs -f my-app
@ -1787,6 +1832,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1832,13 +1878,13 @@ jobs:
              -e LANGFUSE_PROJECT2_PUBLIC=$LANGFUSE_PROJECT2_PUBLIC \
              -e LANGFUSE_PROJECT1_SECRET=$LANGFUSE_PROJECT1_SECRET \
              -e LANGFUSE_PROJECT2_SECRET=$LANGFUSE_PROJECT2_SECRET \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app \
              -v $(pwd)/litellm/proxy/example_config_yaml/oai_misc_config.yaml:/app/config.yaml \
              litellm-docker-database:ci \
              --config /app/config.yaml \
-              --port 4000 \
-              --detailed_debug \
+              --port 4000
      - run:
          name: Start outputting logs
          command: docker logs -f my-app
@ -1869,6 +1915,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -1911,14 +1958,14 @@ jobs:
              -e COHERE_API_KEY=$COHERE_API_KEY \
              -e RECORDER_COHERE_BASE_URL=http://host.docker.internal:8090/__recorder_upstream/api.cohere.com \
              -e GCS_FLUSH_INTERVAL="1" \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app \
              -v $(pwd)/litellm/proxy/example_config_yaml/otel_test_config.yaml:/app/config.yaml \
              -v $(pwd)/litellm/proxy/example_config_yaml/custom_guardrail.py:/app/custom_guardrail.py \
              litellm-docker-database:ci \
              --config /app/config.yaml \
-              --port 4000 \
-              --detailed_debug \
+              --port 4000
      - run:
          name: Start outputting logs
          command: docker logs -f my-app
@ -1960,13 +2007,13 @@ jobs:
              -e OPENAI_API_KEY=$OPENAI_API_KEY \
              -e FAKE_OPENAI_API_BASE=http://host.docker.internal:8190 \
              -e LITELLM_LICENSE="bad-license" \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app-3 \
              -v $(pwd)/litellm/proxy/example_config_yaml/enterprise_config.yaml:/app/config.yaml \
              litellm-docker-database:ci \
              --config /app/config.yaml \
-              --port 4000 \
-              --detailed_debug
+              --port 4000

      - run:
          name: Start outputting logs for second container
@ -2000,6 +2047,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -2041,13 +2089,13 @@ jobs:
              -e DD_SITE=$DD_SITE \
              -e AWS_REGION_NAME=$AWS_REGION_NAME \
              -e PROXY_BATCH_WRITE_AT=2 \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app \
              -v $(pwd)/litellm/proxy/example_config_yaml/spend_tracking_config.yaml:/app/config.yaml \
              litellm-docker-database:ci \
              --config /app/config.yaml \
-              --port 4000 \
-              --detailed_debug \
+              --port 4000
      - run:
          name: Start outputting logs
          command: docker logs -f my-app
@ -2085,6 +2133,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -2117,13 +2166,13 @@ jobs:
              -e USE_DDTRACE=True \
              -e DD_API_KEY=$DD_API_KEY \
              -e DD_SITE=$DD_SITE \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app \
              -v $(pwd)/litellm/proxy/example_config_yaml/multi_instance_simple_config.yaml:/app/config.yaml \
              litellm-docker-database:ci \
              --config /app/config.yaml \
-              --port 4000 \
-              --detailed_debug \
+              --port 4000
      - run:
          name: Run Docker container 2
          command: |
@ -2139,13 +2188,13 @@ jobs:
              -e USE_DDTRACE=True \
              -e DD_API_KEY=$DD_API_KEY \
              -e DD_SITE=$DD_SITE \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app-2 \
              -v $(pwd)/litellm/proxy/example_config_yaml/multi_instance_simple_config.yaml:/app/config.yaml \
              litellm-docker-database:ci \
              --config /app/config.yaml \
-              --port 4001 \
-              --detailed_debug
+              --port 4001
      - run:
          name: Start outputting logs
          command: docker logs -f my-app
@ -2180,6 +2229,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -2201,19 +2251,20 @@ jobs:
          # the OTEL test - should get this as a trace
          command: |
            docker run -d \
+              --restart on-failure \
              -p 4000:4000 \
              -e DATABASE_URL=postgresql://postgres:postgres@host.docker.internal:5432/circle_test \
              -e STORE_MODEL_IN_DB="True" \
              -e LITELLM_MASTER_KEY="sk-1234" \
              -e FAKE_OPENAI_API_BASE=http://host.docker.internal:8190 \
              -e LITELLM_LICENSE=$LITELLM_LICENSE \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app \
              -v $(pwd)/litellm/proxy/example_config_yaml/store_model_db_config.yaml:/app/config.yaml \
              litellm-docker-database:ci \
              --config /app/config.yaml \
-              --port 4000 \
-              --detailed_debug \
+              --port 4000
      - run:
          name: Start outputting logs
          command: docker logs -f my-app
@ -2252,6 +2303,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      # Remove Docker CLI installation since it's already available in machine executor
      - install_uv
@ -2289,13 +2341,13 @@ jobs:
              -e DD_API_KEY=$DD_API_KEY \
              -e DD_SITE=$DD_SITE \
              -e GCS_FLUSH_INTERVAL="1" \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app \
              -v $(pwd)/docker/build_from_pip/litellm_config.yaml:/app/config.yaml \
              my-app:latest \
              --config /app/config.yaml \
-              --port 4000 \
-              --detailed_debug \
+              --port 4000
      - run:
          name: Start outputting logs
          command: docker logs -f my-app
@ -2333,6 +2385,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -2365,14 +2418,14 @@ jobs:
              -e DD_SITE=$DD_SITE \
              -e LITELLM_LICENSE=$LITELLM_LICENSE \
              -e LITELLM_USE_CHAT_COMPLETIONS_URL_FOR_ANTHROPIC_MESSAGES=true \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app \
              -v $(pwd)/litellm/proxy/example_config_yaml/pass_through_config.yaml:/app/config.yaml \
              -v $(pwd)/litellm/proxy/example_config_yaml/custom_auth_basic.py:/app/custom_auth_basic.py \
              litellm-docker-database:ci \
              --config /app/config.yaml \
-              --port 4000 \
-              --detailed_debug \
+              --port 4000
      - run:
          name: Start outputting logs
          command: docker logs -f my-app
@ -2471,6 +2524,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - setup_google_dns
      - install_uv
      - run:
@ -2499,13 +2553,13 @@ jobs:
              -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
              -e AWS_REGION_NAME="us-east-1" \
              -e LITELLM_LOCAL_ANTHROPIC_BETA_HEADERS="True" \
+              -e LITELLM_LOG=ERROR \
              --add-host host.docker.internal:host-gateway \
              --name my-app \
              -v $(pwd)/tests/proxy_e2e_anthropic_messages_tests/test_config.yaml:/app/config.yaml \
              litellm-docker-database:ci \
              --config /app/config.yaml \
-              --port 4000 \
-              --detailed_debug
+              --port 4000
      - run:
          name: Start outputting logs
          command: docker logs -f my-app
@ -2537,6 +2591,7 @@ jobs:
      - *python312_image
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - attach_workspace:
          at: .
      # Check file locations
@ -2567,6 +2622,8 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes:
+          category: client
      - setup_google_dns
      - restore_cache:
          keys:
@ -2609,6 +2666,8 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes:
+          category: client
      - setup_google_dns
      - restore_cache:
          keys:
@ -2629,7 +2688,7 @@ jobs:
            cd ui/litellm-dashboard

            CI=true npm run test -- --run \
-              --pool forks --poolOptions.forks.maxForks=8
+              --pool forks --poolOptions.forks.maxForks=6

  e2e_ui_testing:
    docker:
@ -2654,6 +2713,8 @@ jobs:
      PROXY_LOGOUT_URL: "https://www.example.com"
    steps:
      - checkout
+      - skip_if_unrelated_changes:
+          category: client
      - setup_google_dns
      - install_uv
      - restore_cache:
@ -2791,6 +2852,8 @@ jobs:
      SERVER_ROOT_PATH: "/litellm"
    steps:
      - checkout
+      - skip_if_unrelated_changes:
+          category: client
      - setup_google_dns
      - install_uv
      - restore_cache:
@ -2892,6 +2955,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes

      - run:
          name: Build Docker image
@ -2917,6 +2981,7 @@ jobs:
    working_directory: ~/project
    steps:
      - checkout
+      - skip_if_unrelated_changes
      - attach_workspace:
          at: ~/project
      - setup_google_dns
--- a/.circleci/scripts/classify_changes.sh
+++ b/.circleci/scripts/classify_changes.sh
@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+set -uo pipefail
+
+category="${1:?usage: classify_changes.sh <backend|client>}"
+
+has_client=false
+has_backend=false
+while IFS= read -r file || [ -n "$file" ]; do
+  [ -n "$file" ] || continue
+  case "$file" in
+    ui/*) has_client=true ;;
+    docs/* | *.md | *.mdx) : ;;
+    *) has_backend=true ;;
+  esac
+done
+
+case "$category" in
+  backend)
+    [ "$has_backend" = true ] && echo run || echo skip
+    ;;
+  client)
+    { [ "$has_client" = true ] || [ "$has_backend" = true ]; } && echo run || echo skip
+    ;;
+  *)
+    echo run
+    ;;
+esac
--- a/.circleci/scripts/path_filter.sh
+++ b/.circleci/scripts/path_filter.sh
@ -0,0 +1,40 @@
+#!/usr/bin/env bash
+set -uo pipefail
+
+category="${1:?usage: path_filter.sh <backend|client>}"
+here="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+run_full() {
+  echo "path-filter[$category]: running job ($1)"
+  exit 0
+}
+
+[ -n "${CIRCLE_PULL_REQUEST:-}" ] || run_full "not a pull request"
+
+candidate_bases="main litellm_internal_staging litellm_oss_staging"
+merge_base=""
+for base in $candidate_bases; do
+  git fetch --quiet origin "$base" 2>/dev/null || continue
+  candidate="$(git merge-base HEAD FETCH_HEAD 2>/dev/null)" || continue
+  [ -n "$candidate" ] || continue
+  if [ -z "$merge_base" ] || git merge-base --is-ancestor "$merge_base" "$candidate" 2>/dev/null; then
+    merge_base="$candidate"
+  fi
+done
+
+[ -n "$merge_base" ] || run_full "could not resolve a merge base against $candidate_bases"
+
+changed="$(git diff --name-only "$merge_base" HEAD 2>/dev/null)" || run_full "git diff failed"
+[ -n "$changed" ] || run_full "no files changed vs $merge_base"
+
+echo "path-filter[$category]: changed files vs ${merge_base}:"
+printf '%s\n' "$changed" | sed 's/^/  /' || true
+
+decision="$(printf '%s\n' "$changed" | bash "$here/classify_changes.sh" "$category")" || run_full "classify_changes.sh failed"
+
+if [ "$decision" = run ]; then
+  run_full "$category-relevant changes detected"
+fi
+
+echo "path-filter[$category]: only unrelated (docs/client) changes detected; halting job as successful"
+circleci-agent step halt
--- a/.git-blame-ignore-revs
+++ b/.git-blame-ignore-revs
@ -13,7 +13,7 @@
 7edf3a9cb55548b143df1692f4ed7c4681d7fcf7

 # style: reformat litellm/ with ruff format (#31317)
-430b5b8f1b12dc261a49fda99ac5d1b22381a428
+17bfd415aeb5a57fb646b5cc67da1c730aa7c50b

 # style: unify ruff format width on 120 (#31518)
-3dfbeabe626d203ac9de86024519d9a96c484ce4
+48b5a5a0cc5a694a11219416ee0b6eb6e620e74e
--- a/.github/actions/detect-backend-changes/action.yml
+++ b/.github/actions/detect-backend-changes/action.yml
@ -0,0 +1,48 @@
+name: "Detect backend-relevant changes"
+description: >-
+  Classify the pull request's changed files with .circleci/scripts/classify_changes.sh
+  and expose decision=run|skip. decision=skip means only ui/**, **.md or **.mdx files
+  changed, so callers can short-circuit expensive steps while the job still completes
+  successfully and satisfies its required status check. The decision defaults to run for
+  any non pull_request event or whenever the changed set cannot be resolved, so tests are
+  never skipped when the classification is uncertain.
+
+outputs:
+  decision:
+    description: "run when backend-relevant files changed, otherwise skip"
+    value: ${{ steps.classify.outputs.decision }}
+
+runs:
+  using: composite
+  steps:
+    - id: classify
+      shell: bash
+      env:
+        BASE_SHA: ${{ github.event.pull_request.base.sha }}
+      run: |
+        set -uo pipefail
+        if [ -z "${BASE_SHA:-}" ]; then
+          echo "detect-backend-changes: not a pull_request event; running job"
+          echo "decision=run" >> "${GITHUB_OUTPUT}"
+          exit 0
+        fi
+        if ! git fetch --no-tags --depth=1 origin "${BASE_SHA}" >/dev/null 2>&1; then
+          echo "detect-backend-changes: could not fetch base ${BASE_SHA}; running job"
+          echo "decision=run" >> "${GITHUB_OUTPUT}"
+          exit 0
+        fi
+        changed="$(git diff --name-only "${BASE_SHA}" HEAD 2>/dev/null)" || {
+          echo "detect-backend-changes: git diff failed; running job"
+          echo "decision=run" >> "${GITHUB_OUTPUT}"
+          exit 0
+        }
+        if [ -z "${changed}" ]; then
+          echo "detect-backend-changes: no changed files vs ${BASE_SHA}; skipping job"
+          echo "decision=skip" >> "${GITHUB_OUTPUT}"
+          exit 0
+        fi
+        echo "detect-backend-changes: changed files vs ${BASE_SHA}:"
+        printf '%s\n' "${changed}" | sed 's/^/  /'
+        decision="$(printf '%s\n' "${changed}" | bash .circleci/scripts/classify_changes.sh backend)" || decision="run"
+        echo "detect-backend-changes: decision=${decision}"
+        echo "decision=${decision}" >> "${GITHUB_OUTPUT}"
--- a/.github/pull_request_template.md
+++ b/.github/pull_request_template.md
@ -4,7 +4,7 @@

 ## Linear ticket

-<!-- if you are an internal contributor (e.g., your username is postfixed with -berri or -berriai), add "Resolves " followed by the Linear ticket e.g., "Resolves LIT-1234" to magically link the Linear ticket to the GitHub PR -->
+<!-- if you are an internal contributor, add "Resolves " followed by the Linear ticket e.g., "Resolves LIT-1234" to link the Linear ticket to the GitHub PR. If you don't have one, leave the section blank rather than guessing -->

 ## Pre-Submission checklist

@ -13,7 +13,7 @@
 - [ ] I have added meaningful tests
 - [ ] My PR passes all CI/CD checks (e.g., lint, format, unit tests)
 - [ ] My PR's scope is as isolated as possible; it only solves 1 specific problem
- [ ] I have requested a Greptile review by commenting `@greptileai` and received a **Confidence Score of at least 4/5** before requesting a maintainer review
+- [ ] I have received a Greptile **Confidence Score of at least 4/5** before requesting a maintainer review (Greptile reviews automatically once the PR is opened; only comment `@greptileai` to re-request a review after pushing changes)

 ## Delays in PR merge?

@ -24,6 +24,7 @@ If you're seeing a delay in your PR being merged, ping the LiteLLM Team on [Slac
 <!-- 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
     For new features: show the feature working end-to-end
     For UI changes: include before/after screenshots -->

@ -40,3 +41,27 @@ If you're seeing a delay in your PR being merged, ping the LiteLLM Team on [Slac
 ✅ Test

 ## Changes
+
+## QA runbook
+
+<!-- Only needed when your PR edits tests/e2e; delete this section otherwise
+
+For each e2e test you added or changed, list the manual steps a reviewer can follow to reproduce it by hand against a live proxy, mapping 1:1 to what the test asserts: one top-level bullet per test giving its pytest node id followed by what it proves in plain words, then a nested "- [ ]" checklist where each item is a concrete action (route, request body, expected response) and the final item is the sanity-check step shown in the examples. Note environment prerequisites (provider credentials, config flags) and any nuances a manual run will hit. See PRs #32914 and #32963 for full examples
+
+Example checklists:
+
+- tests/e2e/quota_management/ratelimit/test_rate_limit_e2e.py::TestKeyRateLimits::test_rpm_limit_blocks_over_limit - a key allowed 2 requests a minute serves exactly 2 and refuses the 3rd
+  - [ ] Generate a limited key: curl -X POST http://localhost:4000/key/generate -H "Authorization: Bearer sk-1234" -d '{"rpm_limit": 2}'
+  - [ ] Send three /v1/chat/completions requests with that key inside one minute
+  - [ ] Expect the first two to return 200 and the third to return 429 naming the rpm limit
+  - [ ] Sanity check: this test makes sense to add and is not hand-wavey (e.g., assert actual expected spend instead of just spend > 0) or potentially flaky
+
+- tests/e2e/management/test_management_e2e.py::TestModelRoutes::test_model_create_appears_in_ui - a deployment created through the API shows up on the Admin UI models page
+  - [ ] POST /model/new with the master key, a bedrock model, and aws_region_name (needs STORE_MODEL_IN_DB=True and AWS credentials)
+  - [ ] Open http://localhost:4000/ui/?page=models and expect a deployment row showing the returned model id
+  - [ ] Sanity check: this test makes sense to add and is not hand-wavey (e.g., assert actual expected spend instead of just spend > 0) or potentially flaky
+-->
+
+### Final Attestation
+
+- [ ] The tests check the right things, including the edge cases, and regressions in the respective real-world customer use-cases are not possible after this PR
--- a/.github/workflows/_test-unit-base.yml
+++ b/.github/workflows/_test-unit-base.yml
@ -45,12 +45,18 @@ jobs:
    name: Run tests
    runs-on: ubuntu-latest
    timeout-minutes: ${{ inputs.timeout-minutes }}
+    outputs:
+      decision: ${{ steps.changes.outputs.decision }}

    steps:
      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          persist-credentials: false

+      - name: Detect backend-relevant changes
+        id: changes
+        uses: ./.github/actions/detect-backend-changes
+
      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
        with:
@ -72,16 +78,19 @@ jobs:
            ${{ runner.os }}-uv-

      - name: Install dependencies
+        if: steps.changes.outputs.decision != 'skip'
        run: |
          .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router

      - name: Generate Prisma client
+        if: steps.changes.outputs.decision != 'skip'
        env:
          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
        run: |
          uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma

      - name: Run tests
+        if: steps.changes.outputs.decision != 'skip'
        env:
          TEST_PATH: ${{ inputs.test-path }}
          MAX_FAILURES: ${{ inputs.max-failures }}
@ -114,7 +123,7 @@ jobs:
          fi

      - name: Save coverage report
-        if: always()
+        if: always() && steps.changes.outputs.decision != 'skip'
        uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
        with:
          name: coverage-${{ inputs.artifact-name }}-${{ github.run_id }}-${{ github.run_attempt }}
@ -124,7 +133,7 @@ jobs:
  upload-coverage:
    name: Upload coverage to Codecov
    needs: run
-    if: always()
+    if: always() && needs.run.outputs.decision != 'skip'
    runs-on: ubuntu-latest
    permissions:
      contents: read
--- a/.github/workflows/codspeed.yml
+++ b/.github/workflows/codspeed.yml
@ -4,9 +4,11 @@ on:
  push:
    branches:
      - main
+      - litellm_internal_staging
  pull_request:
    branches:
      - main
+      - litellm_internal_staging
  # Allow CodSpeed to trigger backtest performance analysis
  # in order to generate initial data
  workflow_dispatch:
@ -21,8 +23,8 @@ concurrency:

 jobs:
  benchmarks:
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
+    runs-on: ubuntu-24.04
+    timeout-minutes: 60

    steps:
      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
@ -48,6 +50,8 @@ jobs:
            uv run --frozen --no-default-groups
            --with pytest==8.3.5
            --with pytest-codspeed==4.3.0
+            --with "mcp>=1.26.0,<2.0"
+            --with "a2a-sdk>=1.1.0,<2.0"
            pytest
            -p pytest_codspeed.plugin
            tests/benchmarks/
--- a/.github/workflows/create-release.yml
+++ b/.github/workflows/create-release.yml
@ -122,10 +122,28 @@ jobs:
                makeLatest = (!latestVersion || isAtLeast(newVersion, latestVersion)) ? "true" : "false";
              }

+              try {
+                await github.rest.git.createRef({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  ref: `refs/tags/${tag}`,
+                  sha: commitHash,
+                });
+              } catch (error) {
+                if (error.status !== 422) throw error;
+                const existing = await github.rest.git.getRef({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  ref: `tags/${tag}`,
+                });
+                if (existing.data.object.sha !== commitHash) {
+                  throw new Error(`Tag ${tag} already exists at ${existing.data.object.sha}, expected ${commitHash}`);
+                }
+              }
+
              const response = await github.rest.repos.createRelease({
                draft: true,
                generate_release_notes: true,
-                target_commitish: commitHash,
                name: tag,
                owner: context.repo.owner,
                prerelease: isPrerelease,
@ -138,11 +156,21 @@ jobs:
                owner: context.repo.owner,
                repo: context.repo.repo,
                release_id: response.data.id,
+                tag_name: tag,
                body: updatedBody,
                draft: false,
-                make_latest: makeLatest,
              });

+              if (!isPrerelease) {
+                await github.rest.repos.updateRelease({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  release_id: response.data.id,
+                  tag_name: tag,
+                  make_latest: makeLatest,
+                });
+              }
+
            } catch (error) {
              core.setFailed(error.message);
            }
--- a/.github/workflows/create_daily_oss_branch.yml
+++ b/.github/workflows/create_daily_oss_branch.yml
@ -0,0 +1,61 @@
+name: Create Daily OSS Branch
+
+on:
+  schedule:
+    - cron: "0 16 * * 1-5" # 9am PT during daylight saving time, weekdays.
+  workflow_dispatch:
+    inputs:
+      date:
+        description: "Branch date in YYYY_MM_DD format. Defaults to today's UTC date."
+        required: false
+        type: string
+
+permissions:
+  contents: write
+
+jobs:
+  create-oss-branch:
+    if: github.repository == 'BerriAI/litellm'
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Create dated OSS branch
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          REQUESTED_DATE: ${{ inputs.date }}
+        run: |
+          set -euo pipefail
+
+          if [ -n "${REQUESTED_DATE}" ]; then
+            if ! echo "${REQUESTED_DATE}" | grep -Eq '^[0-9]{4}_[0-9]{2}_[0-9]{2}$'; then
+              echo "::error::date must use YYYY_MM_DD format, got '${REQUESTED_DATE}'"
+              exit 1
+            fi
+            BRANCH_DATE="${REQUESTED_DATE}"
+          else
+            BRANCH_DATE="$(date -u +'%Y_%m_%d')"
+          fi
+
+          BRANCH_NAME="litellm_oss_daily_${BRANCH_DATE}"
+          echo "Creating branch: ${BRANCH_NAME}"
+
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+
+          git fetch origin main "${BRANCH_NAME}" || true
+
+          if git show-ref --verify --quiet "refs/remotes/origin/${BRANCH_NAME}"; then
+            echo "Branch ${BRANCH_NAME} already exists. Skipping creation."
+            exit 0
+          fi
+
+          git checkout -b "${BRANCH_NAME}" origin/main
+          git push "https://x-access-token:${GITHUB_TOKEN}@github.com/${GITHUB_REPOSITORY}.git" "${BRANCH_NAME}"
+          echo "Successfully created and pushed branch: ${BRANCH_NAME}"
--- a/.github/workflows/guard-main-branch.yml
+++ b/.github/workflows/guard-main-branch.yml
@ -31,12 +31,12 @@ jobs:
          echo "PR head repo: $HEAD_REPO"
          echo "PR head branch: $HEAD_REF"
          if [ "$HEAD_REPO" != "$BASE_REPO" ]; then
-            echo "::error::PRs to main must originate from the canonical repository ($BASE_REPO), not a fork ($HEAD_REPO). External contributors should open PRs against the 'litellm_oss_staging' branch instead."
+            echo "::error::PRs to main must originate from the canonical repository ($BASE_REPO), not a fork ($HEAD_REPO). External contributors should open PRs against the current daily OSS branch (named litellm_oss_daily_YYYY_MM_DD; a fresh one is cut each weekday, so target the most recent) instead."
            exit 1
          fi
          if [ "$HEAD_REF" = "litellm_internal_staging" ] || [[ "$HEAD_REF" == litellm_hotfix_?* ]]; then
            echo "Allowed source branch."
            exit 0
          fi
-          echo "::error::PRs to main must originate from 'litellm_internal_staging' or a 'litellm_hotfix_*' branch. Got: '$HEAD_REF'. If this is a contribution, retarget the PR against 'litellm_oss_staging' instead."
+          echo "::error::PRs to main must originate from 'litellm_internal_staging' or a 'litellm_hotfix_*' branch. Got: '$HEAD_REF'. If this is a contribution, retarget the PR against the current daily OSS branch (named litellm_oss_daily_YYYY_MM_DD; a fresh one is cut each weekday, so target the most recent) instead."
          exit 1
--- a/.github/workflows/helm_unit_test.yml
+++ b/.github/workflows/helm_unit_test.yml
@ -38,4 +38,6 @@ jobs:
          echo "Helm unittest plugin integrity verified: $ACTUAL_SHA"

      - name: Run unit tests
-        run: helm unittest -f 'tests/*.yaml' deploy/charts/litellm-helm
+        run: |
+          helm unittest -f 'tests/*.yaml' helm/litellm-helm
+          helm unittest -f 'tests/*.yaml' helm/litellm
--- a/.github/workflows/oss_daily_guardrails.yml
+++ b/.github/workflows/oss_daily_guardrails.yml
@ -0,0 +1,50 @@
+name: OSS Daily Guardrails
+
+on:
+  push:
+    branches:
+      - "litellm_oss_daily_20*"
+  pull_request:
+    branches:
+      - "litellm_oss_daily_20*"
+      - litellm_internal_staging
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  oss-safe-checks:
+    name: Run OSS daily safe checks
+    if: startsWith(github.ref_name, 'litellm_oss_daily_20') || startsWith(github.head_ref, 'litellm_oss_daily_20') || startsWith(github.base_ref, 'litellm_oss_daily_20')
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
+
+      - name: Run secret scan test
+        run: |
+          uv run --frozen --with 'pytest==9.0.2' pytest tests/litellm/test_no_hardcoded_secrets.py -v
+
+      - name: Run Ruff
+        run: |
+          uv sync --frozen
+          cd litellm
+          uv run --no-sync ruff check .
--- a/.github/workflows/test-linting.yml
+++ b/.github/workflows/test-linting.yml
@ -48,7 +48,7 @@ jobs:

      - name: Install dependencies
        run: |
-          uv sync --frozen --group proxy-dev
+          uv sync --frozen --group proxy-dev --group e2e-dev

      # basedpyright resolves Prisma's generated client (litellm/proxy/schema.prisma)
      # only after `prisma generate` writes prisma/client.py et al. Without this the
@ -63,7 +63,7 @@ jobs:
        env:
          BASE_SHA: ${{ github.event.pull_request.base.sha }}
        run: |
-          git diff --name-only "$BASE_SHA"...HEAD -- 'litellm/**/*.py' | grep -v '^litellm/enterprise/' > "$RUNNER_TEMP/ruff_format_files.txt" || true
+          git diff --name-only --diff-filter=ACMR "$BASE_SHA"...HEAD -- 'litellm/**/*.py' | grep -v '^litellm/enterprise/' > "$RUNNER_TEMP/ruff_format_files.txt" || true
          if [ ! -s "$RUNNER_TEMP/ruff_format_files.txt" ]; then
            echo "No changed litellm Python files to check with ruff format."
            exit 0
@ -107,6 +107,16 @@ jobs:
        run: |
          (uv run --no-sync basedpyright --outputjson || true) | uv run --no-sync python scripts/type_check_gate.py --base "$BASE_SHA"

+      - name: Check tests/e2e basedpyright (zero errors)
+        env:
+          BASE_SHA: ${{ github.event.pull_request.base.sha }}
+        run: |
+          if git diff --name-only --diff-filter=ACMRD "$BASE_SHA"...HEAD -- 'tests/e2e/**/*.py' | grep -q .; then
+            uv run --no-sync basedpyright tests/e2e
+          else
+            echo "No changed tests/e2e Python files; skipping."
+          fi
+
      - name: Check for circular imports
        run: |
          cd litellm
--- a/.github/workflows/test-litellm-ui-build.yml
+++ b/.github/workflows/test-litellm-ui-build.yml
@ -36,79 +36,3 @@ jobs:

      - name: Build
        run: npm run build
-
-  frontend-lint:
-    runs-on: ubuntu-latest
-    timeout-minutes: 8
-    defaults:
-      run:
-        working-directory: ui/litellm-dashboard
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
-        with:
-          fetch-depth: 0
-          persist-credentials: false
-
-      - name: Collect changed files
-        id: changed
-        env:
-          BASE_SHA: ${{ github.event.pull_request.base.sha }}
-        run: |
-          : > "$RUNNER_TEMP/prettier_files.txt"
-          : > "$RUNNER_TEMP/eslint_files.txt"
-          while IFS= read -r f; do
-            [ -f "$f" ] || continue
-            case "$f" in
-              *.js | *.jsx | *.ts | *.tsx | *.mjs | *.cjs)
-                printf '%s\n' "$f" >> "$RUNNER_TEMP/prettier_files.txt"
-                printf '%s\n' "$f" >> "$RUNNER_TEMP/eslint_files.txt" ;;
-              *.json | *.css | *.scss | *.md | *.mdx | *.yml | *.yaml | *.html)
-                printf '%s\n' "$f" >> "$RUNNER_TEMP/prettier_files.txt" ;;
-            esac
-          done < <(git diff --name-only --diff-filter=ACMR --relative "$BASE_SHA"...HEAD -- .)
-          if [ -s "$RUNNER_TEMP/prettier_files.txt" ] || [ -s "$RUNNER_TEMP/eslint_files.txt" ]; then
-            echo "has_files=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "has_files=false" >> "$GITHUB_OUTPUT"
-            echo "No lintable UI files changed in this PR; nothing to check."
-          fi
-
-      - name: Setup Node.js
-        if: steps.changed.outputs.has_files == 'true'
-        uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0.0
-        with:
-          node-version: "20"
-          cache: "npm"
-          cache-dependency-path: ui/litellm-dashboard/package-lock.json
-
-      - name: Install dependencies
-        if: steps.changed.outputs.has_files == 'true'
-        run: npm ci
-
-      - name: Lint changed files (prettier + eslint)
-        if: steps.changed.outputs.has_files == 'true'
-        run: |
-          prettier_files=()
-          eslint_files=()
-          while IFS= read -r f; do prettier_files+=("$f"); done < "$RUNNER_TEMP/prettier_files.txt"
-          while IFS= read -r f; do eslint_files+=("$f"); done < "$RUNNER_TEMP/eslint_files.txt"
-          status=0
-          if [ ${#prettier_files[@]} -gt 0 ]; then
-            echo "::group::Prettier (${#prettier_files[@]} files)"
-            npx prettier --check "${prettier_files[@]}" || { status=1; echo "::error::Unformatted files. Fix with: npm run format"; }
-            echo "::endgroup::"
-          fi
-          if [ ${#eslint_files[@]} -gt 0 ]; then
-            echo "::group::ESLint (${#eslint_files[@]} files)"
-            npx eslint --no-warn-ignored --pass-on-unpruned-suppressions "${eslint_files[@]}" || status=1
-            echo "::endgroup::"
-          fi
-          exit $status
-
-      - name: Check lint budgets
-        if: ${{ !cancelled() && steps.changed.outputs.has_files == 'true' }}
-        run: |
-          npx eslint . -f json -o "$RUNNER_TEMP/lint-report.json" || true
-          node scripts/check-lint-budgets.mjs "$RUNNER_TEMP/lint-report.json" eslint-budgets.json --check eslint-metrics.json
--- a/.github/workflows/test-litellm-ui-lint.yml
+++ b/.github/workflows/test-litellm-ui-lint.yml
@ -0,0 +1,92 @@
+name: UI Lint
+permissions:
+  contents: read
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_staging
+      - "litellm_**"
+
+jobs:
+  frontend-lint:
+    runs-on: ubuntu-latest
+    timeout-minutes: 8
+    defaults:
+      run:
+        working-directory: ui/litellm-dashboard
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Collect changed files
+        id: changed
+        env:
+          BASE_SHA: ${{ github.event.pull_request.base.sha }}
+        run: |
+          : > "$RUNNER_TEMP/prettier_files.txt"
+          : > "$RUNNER_TEMP/eslint_files.txt"
+          while IFS= read -r f; do
+            [ -f "$f" ] || continue
+            case "$f" in
+              *.js | *.jsx | *.ts | *.tsx | *.mjs | *.cjs)
+                printf '%s\n' "$f" >> "$RUNNER_TEMP/prettier_files.txt"
+                printf '%s\n' "$f" >> "$RUNNER_TEMP/eslint_files.txt" ;;
+              *.json | *.css | *.scss | *.md | *.mdx | *.yml | *.yaml | *.html)
+                printf '%s\n' "$f" >> "$RUNNER_TEMP/prettier_files.txt" ;;
+            esac
+          done < <(git diff --name-only --diff-filter=ACMR --relative "$BASE_SHA"...HEAD -- .)
+          if [ -s "$RUNNER_TEMP/prettier_files.txt" ] || [ -s "$RUNNER_TEMP/eslint_files.txt" ]; then
+            echo "has_files=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "has_files=false" >> "$GITHUB_OUTPUT"
+            echo "No lintable UI files changed in this PR; nothing to check."
+          fi
+
+      - name: Setup Node.js
+        if: steps.changed.outputs.has_files == 'true'
+        uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0.0
+        with:
+          node-version: "20"
+          cache: "npm"
+          cache-dependency-path: ui/litellm-dashboard/package-lock.json
+
+      - name: Install dependencies
+        if: steps.changed.outputs.has_files == 'true'
+        run: npm ci
+
+      - name: Lint changed files (prettier + eslint)
+        if: steps.changed.outputs.has_files == 'true'
+        run: |
+          prettier_files=()
+          eslint_files=()
+          while IFS= read -r f; do prettier_files+=("$f"); done < "$RUNNER_TEMP/prettier_files.txt"
+          while IFS= read -r f; do eslint_files+=("$f"); done < "$RUNNER_TEMP/eslint_files.txt"
+          status=0
+          if [ ${#prettier_files[@]} -gt 0 ]; then
+            echo "::group::Prettier (${#prettier_files[@]} files)"
+            npx prettier --check "${prettier_files[@]}" || { status=1; echo "::error::Unformatted files. Fix with: npm run format"; }
+            echo "::endgroup::"
+          fi
+          if [ ${#eslint_files[@]} -gt 0 ]; then
+            echo "::group::ESLint (${#eslint_files[@]} files)"
+            npx eslint --no-warn-ignored --pass-on-unpruned-suppressions "${eslint_files[@]}" || status=1
+            echo "::endgroup::"
+          fi
+          exit $status
+
+      - name: Check lint budgets
+        if: ${{ !cancelled() && steps.changed.outputs.has_files == 'true' }}
+        run: |
+          npx eslint . -f json -o "$RUNNER_TEMP/lint-report.json" || true
+          node scripts/check-lint-budgets.mjs "$RUNNER_TEMP/lint-report.json" eslint-budgets.json
+
+      - name: Check for dead code (knip)
+        if: ${{ !cancelled() && steps.changed.outputs.has_files == 'true' }}
+        run: npm run knip
--- a/.github/workflows/test-terraform-provider.yml
+++ b/.github/workflows/test-terraform-provider.yml
@ -0,0 +1,113 @@
+name: Terraform Provider
+
+on:
+  push:
+    paths:
+      - "terraform/provider/**"
+      - ".github/workflows/test-terraform-provider.yml"
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_staging
+      - "litellm_**"
+    paths:
+      - "terraform/provider/**"
+      - "litellm/proxy/**"
+      - ".github/workflows/test-terraform-provider.yml"
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  provider-checks:
+    name: gofmt, vet, build, test
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    defaults:
+      run:
+        working-directory: terraform/provider
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
+        with:
+          go-version-file: terraform/provider/go.mod
+          cache: true
+          cache-dependency-path: terraform/provider/go.sum
+
+      - name: gofmt
+        run: |
+          UNFORMATTED=$(gofmt -l .)
+          if [ -n "${UNFORMATTED}" ]; then
+            echo "::error::gofmt required for: ${UNFORMATTED}"
+            exit 1
+          fi
+
+      - name: go vet
+        run: go vet ./...
+
+      - name: Build
+        run: go build ./...
+
+      - name: Test
+        run: go test -timeout 120s ./...
+
+  endpoint-drift:
+    name: Provider endpoints vs proxy OpenAPI schema
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
+
+      - name: Cache uv dependencies
+        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
+        with:
+          path: |
+            ~/.cache/uv
+            .venv
+          key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-uv-
+
+      - name: Install dependencies
+        run: |
+          .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
+
+      - name: Generate Prisma client
+        env:
+          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
+        run: |
+          uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
+
+      - name: Generate proxy OpenAPI schema
+        run: |
+          uv run --no-sync python terraform/provider/tools/dump_openapi.py "${RUNNER_TEMP}/openapi.json"
+
+      - uses: actions/setup-go@7a3fe6cf4cb3a834922a1244abfce67bcef6a0c5 # v6.2.0
+        with:
+          go-version-file: terraform/provider/go.mod
+          cache: true
+          cache-dependency-path: terraform/provider/go.sum
+
+      - name: Audit provider endpoints against the schema
+        working-directory: terraform/provider
+        run: go run ./tools/endpointaudit -provider-dir ./litellm -spec "${RUNNER_TEMP}/openapi.json"
--- a/.github/workflows/test-unit-documentation.yml
+++ b/.github/workflows/test-unit-documentation.yml
@ -32,6 +32,10 @@ jobs:
          path: docs/my-website
          persist-credentials: false

+      - name: Detect backend-relevant changes
+        id: changes
+        uses: ./.github/actions/detect-backend-changes
+
      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
        with:
@ -53,10 +57,12 @@ jobs:
            ${{ runner.os }}-uv-

      - name: Install dependencies
+        if: steps.changes.outputs.decision != 'skip'
        run: |
          .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router

      - name: Generate Prisma client
+        if: steps.changes.outputs.decision != 'skip'
        env:
          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
        run: |
@ -64,6 +70,7 @@ jobs:

      # Run the same documentation tests that CircleCI ran (as direct Python scripts)
      - name: Run documentation validation tests
+        if: steps.changes.outputs.decision != 'skip'
        run: |
          uv run --no-sync python ./tests/documentation_tests/test_env_keys.py
          uv run --no-sync python ./tests/documentation_tests/test_router_settings.py
--- a/.github/workflows/test-unit-proxy-legacy.yml
+++ b/.github/workflows/test-unit-proxy-legacy.yml
@ -49,6 +49,10 @@ jobs:
        with:
          persist-credentials: false

+      - name: Detect backend-relevant changes
+        id: changes
+        uses: ./.github/actions/detect-backend-changes
+
      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
        with:
@ -70,16 +74,19 @@ jobs:
            ${{ runner.os }}-uv-

      - name: Install dependencies
+        if: steps.changes.outputs.decision != 'skip'
        run: |
          .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router

      - name: Generate Prisma client
+        if: steps.changes.outputs.decision != 'skip'
        env:
          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
        run: |
          uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma

      - name: Run tests - ${{ matrix.test-group.name }}
+        if: steps.changes.outputs.decision != 'skip'
        env:
          TEST_PATH: ${{ matrix.test-group.path }}
        run: |
--- a/.github/workflows/test_server_root_path.yml
+++ b/.github/workflows/test_server_root_path.yml
@ -16,6 +16,7 @@ jobs:
    timeout-minutes: 30

    strategy:
+      fail-fast: false
      matrix:
        root_path: ["/api/v1", "/llmproxy"]

@ -108,8 +109,26 @@ jobs:
      - name: Install UI deps and Chromium
        working-directory: ui/litellm-dashboard
        run: |
-          npm ci
-          npx playwright install --with-deps chromium
+          retry() {
+            local attempt=1
+            local max_attempts=4
+            until "$@"; do
+              if [ "$attempt" -ge "$max_attempts" ]; then
+                echo "Command failed after $attempt attempts: $*"
+                return 1
+              fi
+              echo "Attempt $attempt failed: $*. Retrying in $((attempt * 15))s..."
+              sleep $((attempt * 15))
+              attempt=$((attempt + 1))
+            done
+          }
+
+          npm config set fetch-retries 5
+          npm config set fetch-retry-mintimeout 20000
+          npm config set fetch-retry-maxtimeout 120000
+
+          retry npm ci
+          retry npx playwright install --with-deps chromium

      - name: Run SERVER_ROOT_PATH redirect e2e
        working-directory: ui/litellm-dashboard
--- a/.gitignore
+++ b/.gitignore
@ -50,9 +50,10 @@ litellm/proxy/tests/package-lock.json
 ui/litellm-dashboard/.next
 ui/litellm-dashboard/node_modules
 ui/litellm-dashboard/next-env.d.ts
-deploy/charts/litellm/*.tgz
-deploy/charts/litellm/charts/*
-deploy/charts/*.tgz
+ui/litellm-dashboard/package.json
+ui/litellm-dashboard/package-lock.json
+helm/litellm-helm/*.tgz
+helm/*.tgz
 litellm/proxy/vertex_key.json
 **/.vim/
 **/node_modules
@ -85,12 +86,17 @@ litellm/proxy/db/migrations/*
 litellm/proxy/migrations/*config.yaml
 litellm/proxy/migrations/*
 litellm/proxy/to_delete_loadtest_work/*
+config.yaml
 tests/litellm/litellm_core_utils/llm_cost_calc/log.txt
 tests/test_custom_dir/*
+test.py

+litellm_config.yaml
+!.github/observatory/litellm_config.yaml
 .cursor
 litellm/proxy/to_delete_loadtest_work/*
 update_model_cost_map.py
+tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_server_manager.py
 scripts/test_vertex_ai_search.py
 LAZY_LOADING_IMPROVEMENTS.md
 STABILIZATION_TODO.md
@ -124,6 +130,4 @@ crash.*.log
 # pytest coverage data
 .coverage

-# _experimental/out UI build output
-# (both componentized and non-componentized build the UI on project release)
-litellm/proxy/_experimental/out/
+ui/litellm-dashboard/out/
--- a/CLAUDE.md
+++ b/CLAUDE.md
@ -1,8 +1,7 @@
-Do not write comments unless they are absolutely necessary to explain some very complex business logic. Please clean up if there are comments that are not absolutely necessary. Do not remove comments that are unrelated to the addition of the code of this PR
-
-Explanation: code comments are, in a way, a violation of DRY code. You must update logic in two locations to change the code and "hard to change" is literally the definition of tech debt. We should instead aim to write code that is intuitive to the reader, while being both easy to maintain and high performance
+Do not write any comments (existing comments can stay) unless explicitly asked to in a user (not system) prompt

 Don't assume that the existing code is correct or the right way of doing things / good coding patterns. In fact, there are a lot of bad coding practices, overly complex code, code smells, etc. If something doesn't look right, speak up. Feel free to break existing patterns or question weird existing code to make new code high quality, as in:
+
 - correct
 - secure
 - performant
@ -18,11 +17,15 @@ Same thing for bug fixes. The tests should make it so that this specific bug can

 `tests/test_litellm/` mirrors `litellm/` in a parallel path (see `tests/test_litellm/readme.md`). Name tests `test_<filename>.py`, but always match the existing test file in the directory you touch — many provider dirs use longer descriptive names (e.g. `test_anthropic_chat_transformation.py`) to avoid ambiguity across sibling folders. For bug fixes, extend the existing mapped test file rather than creating a new one. Only create a new test file for a new feature (provider, endpoint, or transformation module) that has no mapped test yet, following that directory's naming convention (or `test_<filename>.py` if you're the first test there). One focused regression test beats many shallow ones

-When creating PRs, don't set base to `main`. `litellm_internal_staging` serves that purpose
+End-to-end tests belong in `tests/e2e/` and must follow the harness conventions documented in that directory's `CLAUDE.md`

-Always use @.github/pull_request_template.md as a guide for your PR body
+When creating PRs, don't set base to `main`. `litellm_internal_staging` serves that purpose for internal contributors; external / OSS contributions target the current daily OSS branch instead, named `litellm_oss_daily_YYYY_MM_DD` (a fresh one is cut each weekday, so use the most recent)

-Never use `pytest` commands or the like as "Screenshots / Proof of Fix". We prefer curl'ing a live proxy instance running on localhost:4000 (I like to run it with `python litellm/proxy/proxy_cli.py --config litellm/proxy/dev_config.yaml --detailed_debug --reload --use_v2_migration_resolver 2>&1 | tee litellm.log`) and showing both the command run and the output. Also, it should hit real LLM provider APIs, not mocks, and cost real $$$ because that is the most realistic test. The proof of fix should be exactly what the end user / customer would see / do. The run logs in PR #27703 is a prime example of how to do it (not a huge fan of using a python test script that future me and the team will have no visibility into; I prefer just curl commands or a short list of bash commands (e.g., using `for`)). If it's a UI thing, just tell me which URLs to go to (e.g., http://localhost:4000/ui/?page=logs), where to click, what fields to fill out, etc. along with the other commands to run in an ordered list, and I'll do it myself and post the screenshots after you make the PR
+When writing a PR body, treat the comments and imperative instructions inside @.github/pull_request_template.md as rules to follow, not just layout. Agent harnesses may strip HTML comments from copies of that file injected into context, so read .github/pull_request_template.md from disk before writing a PR body to make sure you see every comment rule
+
+If you're resolving a linear ticket, in the "## Linear ticket" section of the PR, say "Resolves LIT-1234", replacing "LIT-1234" with the actual ticket id that you're resolving. If you don't have the ticket id, don't make one up or search for it. Just leave the section blank
+
+Never use `pytest` commands or the like as "Screenshots / Proof of Fix". We prefer curl'ing a live proxy instance running on localhost:4000 (I like to run it with `python litellm/proxy/proxy_cli.py --config litellm/proxy/dev_config.yaml --detailed_debug --reload --use_v2_migration_resolver 2>&1 | tee litellm.log`; the Admin UI dev server is `npm run dev` in `ui/litellm-dashboard`, served on port 3000) and showing both the command run and the output. Also, it should hit real LLM provider APIs, not mocks, and cost real $$$ because that is the most realistic test. The proof of fix should be exactly what the end user / customer would see / do. The run logs in PR #27703 is a prime example of how to do it (not a huge fan of using a python test script that future me and the team will have no visibility into; I prefer just curl commands or a short list of bash commands (e.g., using `for`)). If it's a UI thing, just tell me which URLs to go to (e.g., http://localhost:4000/ui/?page=logs), where to click, what fields to fill out, etc. along with the other commands to run in an ordered list, and I'll do it myself and post the screenshots after you make the PR

 If you ever make public-facing PR descriptions, comments, issues, commit messages, etc., always follow these guidelines to sound less AI-y:
 - don't use emojis
@ -34,17 +37,23 @@ If you ever make public-facing PR descriptions, comments, issues, commit message

 Don't hesitate to use values in .env to get needed API keys and other secrets, as long as you never add them to conversation history, commit them, or include them in GitHub issues / PRs

-Run tests, format your code, and lint your code before each commit
+Python max line length is 120, not 88

-When you fix violations gated by `ruff-strict-budget.json` or `basedpyright-code-budget.json`, run `make lint-budget-update` and commit the lowered baselines so the ceilings ratchet down instead of leaving stale headroom
+On a fresh worktree or clone, run `make bootstrap` before anything else. It provisions everything tests, `make pre-commit`, and a local proxy need
+
+Run tests before you commit. Also, run `make pre-commit` right before each commit, which generates types (as needed) and formats/lints your code. Any errors found must be fixed. It only runs when there are staged frontend and/or backend changes and calculates violations, generates types, etc. based on the worktree, so stage what you need or stash/delete unwanted files in litellm/ or ui/ (where backend and frontend lint run, respectively) before running it. If it fails because dashboard api types are stale, it already regenerated them for you. You just need to stage the schema.d.ts, re-run `make pre-commit` to confirm it passes, and commit
+
+When you fix violations gated by `ruff-strict-budget.json`, `type-discipline-budget.json`, or `basedpyright-code-budget.json`, run `make lint-budget-update` and commit the lowered limits so the ceilings ratchet down instead of leaving stale headroom. It measures the working tree, so it must contain exactly the fixes you're committing

 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()` / `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

-Ask to commit and push your work when you're done (or if you're confident that your code is good and works, just do it)
+Every lint or type suppression must name the exact rule inside brackets and carry a reason comment, e.g. `# pyright: ignore[reportArgumentType]  # stubs lack async overload` or `# noqa: TID251  # <reason>`. `# type: ignore` is banned (LIT009): pyrightconfig.json sets `enableTypeIgnoreComments` to false, so it silently does nothing

-When you must use real LLM models to, for example, write e2e tests, write a QA runbook, etc., make sure to use the latest models (doesn't have to be smartest, can also be a modern small, fast one. No strong preference for smart vs fast here, just use something modern) as of the year and month of the current date. Do a web search as necessary to figure that out
+Commit and push your work when you're done without asking
+
+When referencing or running models (coding, QA'ing, writing docs, writing tests, etc.), use the latest model in that model family unless otherwise specified; treat your training knowledge, memories, configs, and tests as stale, and determine the family's latest with model_prices_and_context_window.json or the web

 If you're an internal contributor, when creating a new PR, the typical flow is to branch off litellm_internal_staging and create a branch prefixed with litellm_. Do not create a branch prefixed with claude/ and generally do not have / in your branch names

@ -70,6 +79,7 @@ Follow these coding conventions for new/updated code (a three-line fix in a lega
 - No monster files or god objects
 - No file sprawl: deliberate file and folder structure
 - Standard over hand-rolled: use the official SDK or a library where one exists; where none does, follow industry standards instead of inventing local conventions
+- API-fragmentation-aware: when logic must branch on which API surface produced or consumes data (e.g. chat completions vs Anthropic Messages vs Responses API shapes), proactively look for an existing shared helper (e.g. `litellm_core_utils/prompt_templates/factory.py`) before writing per-surface parsing in the new module; if none exists, add one there instead of duplicating the same format-detection logic in every new guardrail/integration

 Follow conventional commits for commit names and PR titles

--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@ -322,7 +322,7 @@ npm run build
 ## Submitting Your PR

 1. **Push your branch**: `git push origin your-feature-branch`
-2. **Create a PR**: Go to GitHub and create a pull request
+2. **Create a PR**: Go to GitHub and open a pull request against the current daily OSS branch, named `litellm_oss_daily_YYYY_MM_DD`. A fresh one is cut each weekday, so pick the most recent from the [branch list](https://github.com/BerriAI/litellm/branches/all?query=litellm_oss_daily). Do not target `main`.
 3. **Fill out the PR template**: Provide clear description of changes
 4. **Wait for review**: Maintainers will review and provide feedback
 5. **Address feedback**: Make requested changes and push updates
--- a/4
+++ b/4
@ -1,10 +1,10 @@
 # syntax=docker/dockerfile:1.7

 # Base image for building
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:c61ac6919b811ea53c4782d69f1fe05218ba3c25d53f01b6ab7892e621bd4370
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f

 # Runtime image
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:c61ac6919b811ea53c4782d69f1fe05218ba3c25d53f01b6ab7892e621bd4370
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f
 ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a
 # Pinned by digest like the other base images; bump explicitly on Node upgrades.
 ARG UI_BUILD_IMAGE=node:20.18-alpine3.20@sha256:3488b10bf958af7125a176419d2d8a9937d895bf124012aae811651988d2ffe6
--- a/124
+++ b/124
@ -4,15 +4,17 @@
 .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 format \
-	lint-basedpyright lint-basedpyright-budget-update \
+	info lint 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
+	install-helm-unittest check-circular-imports check-import-safety pre-commit \
+	lint-install lint-fetch-base bootstrap

 # Default target
 help:
 	@echo "Available commands:"
+	@echo "  make bootstrap          - Provision a fresh clone/worktree"
 	@echo "  make install-dev        - Install development dependencies"
 	@echo "  make install-proxy-dev  - Install proxy development dependencies"
 	@echo "  make install-dev-ci     - Install dev dependencies (CI-compatible, pins OpenAI)"
@ -20,17 +22,19 @@ help:
 	@echo "  make install-test-deps  - Install the full local test environment"
 	@echo "  make install-helm-unittest - Install helm unittest plugin"
 	@echo "  make install-hooks      - Install git hooks (Conventional Commits + Branches)"
+	@echo "  make pre-commit         - Run CI-equivalent lint on staged files (run before committing)"
 	@echo "  make format             - Apply ruff format code formatting"
 	@echo "  make format-check       - Check ruff format code formatting (matches CI)"
 	@echo "  make lint               - Run all linting (Ruff, basedpyright, format check, circular imports, import safety)"
 	@echo "  make lint-ruff          - Run Ruff linting only"
 	@echo "  make lint-basedpyright  - Run basedpyright strict, gated by per-rule error counts"
-	@echo "  make lint-basedpyright-budget-update - Re-capture the basedpyright per-rule budget (ratchet)"
+	@echo "  make lint-e2e-basedpyright - Run basedpyright over tests/e2e (zero errors allowed)"
+	@echo "  make lint-basedpyright-budget-update - Ratchet basedpyright limits down by what this branch fixed"
 	@echo "  make lint-format        - Check ruff format formatting (matches CI)"
-	@echo "  make lint-ruff-budget - Gate the codebase total of each strict ruff rule against its ceiling"
+	@echo "  make lint-ruff-budget - Gate the codebase total of each strict ruff rule against its limit"
 	@echo "  make lint-gate        - Strict ruff gate in CI-parity mode (fetches staging, simulates the merge)"
-	@echo "  make lint-ruff-budget-update - Re-capture per-rule baselines in ruff-strict-budget.json (ratchet)"
-	@echo "  make lint-budget-update - Re-capture all ratchet budgets (ruff + basedpyright)"
+	@echo "  make lint-ruff-budget-update - Ratchet ruff-strict-budget.json limits down by what this branch fixed"
+	@echo "  make lint-budget-update - Ratchet all budgets down (ruff + type-discipline + basedpyright)"
 	@echo "  make check-circular-imports - Check for circular imports"
 	@echo "  make check-import-safety - Check import safety"
 	@echo "  make test               - Run all tests"
@ -51,13 +55,34 @@ help:
 UV := uv
 UV_RUN := $(UV) run --no-sync

+LINT_DEP_INSTALL ?= install-dev
+LINT_E2E_DEP_INSTALL ?= lint-install
+LINT_DEP_BASE ?= lint-fetch-base
+LINT_JOBS := $(shell sysctl -n hw.ncpu 2>/dev/null || nproc 2>/dev/null || echo 4)
+LINT_OUTPUT_SYNC := $(if $(filter output-sync,$(.FEATURES)),--output-sync=target,)
+
 # Show info
 info:
 	@echo "UV: $(UV)"

 # Installation targets
+# --inexact: sync the locked deps without pruning anything already installed, so running
+# a lint/format target doesn't tear the proxy extras (prisma, websockets, ...) out from
+# under a dev's venv (CI installs its own env per job, so it is unaffected by this).
 install-dev:
-	$(UV) sync --frozen
+	$(UV) sync --inexact --frozen
+
+bootstrap:
+	$(UV) sync --inexact --frozen --extra proxy --group proxy-dev --group e2e-dev
+	$(UV_RUN) python scripts/prisma_generate_if_needed.py
+	cd ui/litellm-dashboard && npm ci --no-audit --no-fund
+	@main_root=$$(git worktree list --porcelain | head -1 | sed 's/^worktree //'); \
+	if [ "$$main_root" != "$$(git rev-parse --show-toplevel)" ] && [ -f "$$main_root/.env" ] && [ ! -f .env ]; then \
+		cp "$$main_root/.env" .env && echo "bootstrap: copied .env from $$main_root"; \
+	else \
+		echo "bootstrap: .env left untouched"; \
+	fi
+	@echo "bootstrap: done"

 install-proxy-dev:
 	$(UV) sync --frozen --group proxy-dev --extra proxy
@ -83,15 +108,40 @@ install-hooks:

 # Formatting
 # Wrap width is ruff.toml's single source of truth (line-length = 120), shared by the
-# formatter, E501, and the import sorter so there's no 88-vs-120 split to reconcile.
+# formatter and the import sorter so there's no 88-vs-120 split to reconcile.
 format: install-dev
 	cd litellm && $(UV_RUN) ruff format --exclude '/enterprise/' . && cd ..

 format-check: install-dev
 	cd litellm && $(UV_RUN) ruff format --check --exclude '/enterprise/' . && cd ..

+# Single fetch of the PR base so the delta-based gates below share one network round
+# trip instead of each re-fetching when chained from `lint`.
+lint-fetch-base:
+	git fetch origin litellm_internal_staging
+
+# Mirror test-linting.yml's lint job environment: the proxy-dev group plus a generated
+# Prisma client, so basedpyright resolves the same modules CI does (without the generated
+# client the DB wrappers typed against it degrade to Unknown, drifting the budget from
+# CI's). --inexact tops up the venv instead of pruning the proxy extras gen:api and the
+# running proxy need.
+lint-install:
+	$(UV) sync --inexact --frozen --group proxy-dev --group e2e-dev
+	$(UV_RUN) python scripts/prisma_generate_if_needed.py
+
+# Diff-scoped format check, identical to test-linting.yml's "Check ruff format" step:
+# only the litellm Python files changed vs the base are checked, so a pre-existing
+# format issue elsewhere doesn't block an unrelated commit.
+lint-format-check-changed: $(LINT_DEP_INSTALL) $(LINT_DEP_BASE)
+	@files=$$(git diff --name-only origin/litellm_internal_staging...HEAD -- 'litellm/**/*.py' | grep -v '^litellm/enterprise/' || true); \
+	if [ -z "$$files" ]; then \
+		echo "No changed litellm Python files to format-check."; \
+	else \
+		echo "$$files" | xargs $(UV_RUN) ruff format --check --exclude '/enterprise/'; \
+	fi
+
 # Linting targets
-lint-ruff: install-dev
+lint-ruff: $(LINT_DEP_INSTALL)
 	cd litellm && $(UV_RUN) ruff check . && cd ..

 # faster linter for developing ...
@ -126,11 +176,20 @@ lint-ruff-FULL-dev: install-dev
 	if [ -n "$$files" ]; then echo "$$files" | xargs $(UV_RUN) ruff check; \
 	else echo "No changed .py files to check."; fi

-lint-basedpyright: install-dev
-	git fetch origin litellm_internal_staging
+lint-basedpyright: $(LINT_DEP_INSTALL) $(LINT_DEP_BASE)
 	($(UV_RUN) basedpyright --outputjson || true) | $(UV_RUN) python scripts/type_check_gate.py --base origin/litellm_internal_staging

-lint-basedpyright-budget-update: install-dev
+lint-e2e-basedpyright: $(LINT_E2E_DEP_INSTALL)
+	$(UV_RUN) basedpyright tests/e2e
+
+# Type-discipline budget (mutable collections / casts / type guards / kwargs /
+# unexplained suppressions), the test-linting.yml step `make lint` used to omit.
+lint-type-discipline: $(LINT_DEP_INSTALL) $(LINT_DEP_BASE)
+	$(UV_RUN) python scripts/type_discipline_gate.py --base origin/litellm_internal_staging
+
+# --update lowers each limit by what this branch fixed since its branch point, so
+# it needs the base ref fetched to resolve the merge-base.
+lint-basedpyright-budget-update: install-dev lint-fetch-base
 	($(UV_RUN) basedpyright --outputjson || true) | $(UV_RUN) python scripts/type_check_gate.py --update

 lint-format: format-check
@ -140,28 +199,47 @@ lint-ruff-budget: install-dev

 # Strict gate, invoked the same way CI does in test-linting.yml so a local pass
 # means the CI check will pass too.
-lint-gate: install-dev
-	git fetch origin litellm_internal_staging
+lint-gate: $(LINT_DEP_INSTALL) $(LINT_DEP_BASE)
 	$(UV_RUN) python scripts/ruff_strict_gate.py --base origin/litellm_internal_staging

-lint-ruff-budget-update: install-dev
+lint-ruff-budget-update: install-dev lint-fetch-base
 	$(UV_RUN) python scripts/ruff_strict_gate.py --update

-# Ratchet all budgets in one shot (ruff strict + basedpyright)
-lint-budget-update: lint-ruff-budget-update lint-basedpyright-budget-update
+lint-type-discipline-budget-update: install-dev lint-fetch-base
+	$(UV_RUN) python scripts/type_discipline_gate.py --update

-check-circular-imports: install-dev
+# Ratchet all budgets in one shot (ruff strict + type-discipline + basedpyright)
+lint-budget-update: lint-ruff-budget-update lint-type-discipline-budget-update lint-basedpyright-budget-update
+
+check-circular-imports: $(LINT_DEP_INSTALL)
 	cd litellm && $(UV_RUN) python ../tests/documentation_tests/test_circular_imports.py && cd ..

-check-import-safety: install-dev
+check-import-safety: $(LINT_DEP_INSTALL)
 	@$(UV_RUN) python -c "from litellm import *; print('[from litellm import *] OK! no issues!');" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)

-# Combined linting (matches test-linting.yml workflow)
-lint: format-check lint-ruff lint-basedpyright check-circular-imports check-import-safety lint-ruff-budget
+# Combined linting, isomorphic to test-linting.yml's lint job so a local pass means a
+# green CI lint: it installs the same env (proxy-dev + generated Prisma client) and then
+# runs the diff-scoped ruff format check, whole-tree ruff check, the strict-rule /
+# type-discipline / basedpyright budgets as a delta vs the base, then the circular-import
+# and import-safety checks. Steps that compare against the base resolve it the same way CI
+# 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
+	$(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

 # Faster linting for local development (only checks changed code)
 lint-dev: lint-format-changed check-circular-imports check-import-safety

+# Run the gating CI checks against your staged files right before committing. Mirrors
+# 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 you didn't stage.
+# Not auto-installed as a git hook so it never slows an unrelated human commit.
+pre-commit:
+	./scripts/pre_commit_lint.sh
+
 # Testing targets
 test: install-test-deps
 	$(UV_RUN) pytest tests/
@ -205,7 +283,7 @@ test-integration: install-test-deps
 	$(UV_RUN) pytest tests/ -k "not test_litellm"

 test-unit-helm: install-helm-unittest
-	helm unittest -f 'tests/*.yaml' deploy/charts/litellm-helm
+	helm unittest -f 'tests/*.yaml' helm/litellm-helm

 # LLM Translation testing targets
 test-llm-translation: install-test-deps
--- a/README.md
+++ b/README.md
@ -552,17 +552,12 @@ The Terraform modules live at [`terraform/litellm/aws/`](./terraform/litellm/aws
 2. Run dependent services `docker-compose up db prometheus`

 #### Backend
-1. (In root) create virtual environment `python -m venv .venv`
-2. Activate virtual environment `source .venv/bin/activate`
-3. Install dependencies `uv sync --all-extras --group proxy-dev`
-4. `uv run prisma generate`
-5. `prisma generate`
-6. Start proxy backend `python litellm/proxy/proxy_cli.py`
+1. Run `make bootstrap`
+2. Start proxy backend: `uv run python litellm/proxy/proxy_cli.py`

 #### Frontend
-1. Navigate to `ui/litellm-dashboard`
-2. Install dependencies `npm install`
-3. Run `npm run dev` to start the dashboard
+1. Navigate to `ui/litellm-dashboard` (dependencies were already installed w/ `make bootstrap`)
+2. Start dashboard: `npm run dev`

 ### Verify Docker Image Signatures

--- a/backend/Dockerfile
+++ b/backend/Dockerfile
@ -1,5 +1,5 @@
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:c61ac6919b811ea53c4782d69f1fe05218ba3c25d53f01b6ab7892e621bd4370
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:c61ac6919b811ea53c4782d69f1fe05218ba3c25d53f01b6ab7892e621bd4370
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f
 ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a

 FROM $UV_IMAGE AS uvbin
--- a/backend/routes/allowlist.py
+++ b/backend/routes/allowlist.py
@ -46,6 +46,7 @@ BACKEND_PATH_PREFIXES: tuple[str, ...] = (
    "/fallback",
    "/fallbacks",
    "/cache_settings",
+    "/coordination_redis/",
    "/cost_tracking",
    "/cost/",
    "/credentials",
--- a/basedpyright-code-budget.json
+++ b/basedpyright-code-budget.json
@ -1,194 +1,146 @@
 {
  "reportAny": {
-    "baseline": 24989,
-    "slack": 2500
+    "limit": 37484
  },
  "reportArgumentType": {
-    "baseline": 1814,
-    "slack": 180
+    "limit": 2704
  },
  "reportAssignmentType": {
-    "baseline": 220,
-    "slack": 22
+    "limit": 330
  },
  "reportAttributeAccessIssue": {
-    "baseline": 346,
-    "slack": 35
+    "limit": 516
  },
  "reportCallIssue": {
-    "baseline": 87,
-    "slack": 10
+    "limit": 124
  },
  "reportConstantRedefinition": {
-    "baseline": 39,
-    "slack": 4
+    "limit": 59
  },
  "reportDeprecated": {
-    "baseline": 217,
-    "slack": 22
+    "limit": 326
  },
  "reportDuplicateImport": {
-    "baseline": 28,
-    "slack": 3
+    "limit": 42
  },
  "reportExplicitAny": {
-    "baseline": 6931,
-    "slack": 700
+    "limit": 10397
  },
  "reportFunctionMemberAccess": {
-    "baseline": 7,
-    "slack": 3
+    "limit": 11
  },
  "reportGeneralTypeIssues": {
-    "baseline": 151,
-    "slack": 15
+    "limit": 227
  },
  "reportIncompatibleMethodOverride": {
-    "baseline": 52,
-    "slack": 5
+    "limit": 78
  },
  "reportIncompatibleVariableOverride": {
-    "baseline": 8,
-    "slack": 3
+    "limit": 12
  },
  "reportInconsistentOverload": {
-    "baseline": 12,
-    "slack": 3
+    "limit": 18
  },
  "reportIndexIssue": {
-    "baseline": 26,
-    "slack": 3
+    "limit": 37
  },
  "reportInvalidTypeForm": {
-    "baseline": 23,
-    "slack": 3
+    "limit": 35
  },
  "reportInvalidTypeVarUse": {
-    "baseline": 2,
-    "slack": 3
+    "limit": 5
  },
  "reportMatchNotExhaustive": {
-    "baseline": 1,
-    "slack": 0
+    "limit": 0
  },
  "reportMissingParameterType": {
-    "baseline": 3933,
-    "slack": 390
+    "limit": 5900
  },
  "reportMissingTypeArgument": {
-    "baseline": 10612,
-    "slack": 1000
+    "limit": 15903
  },
  "reportMissingTypeStubs": {
-    "baseline": 27,
-    "slack": 10
+    "limit": 41
  },
  "reportOperatorIssue": {
-    "baseline": 6,
-    "slack": 3
+    "limit": 0
  },
  "reportOptionalCall": {
-    "baseline": 4,
-    "slack": 3
+    "limit": 0
  },
  "reportOptionalIterable": {
-    "baseline": 3,
-    "slack": 3
+    "limit": 0
  },
  "reportOptionalMemberAccess": {
-    "baseline": 724,
-    "slack": 72
+    "limit": 1085
  },
  "reportOptionalOperand": {
-    "baseline": 3,
-    "slack": 3
+    "limit": 0
  },
  "reportOptionalSubscript": {
-    "baseline": 11,
-    "slack": 3
+    "limit": 0
  },
  "reportPossiblyUnboundVariable": {
-    "baseline": 52,
-    "slack": 10
+    "limit": 77
  },
  "reportPrivateUsage": {
-    "baseline": 1625,
-    "slack": 160
+    "limit": 2438
  },
  "reportRedeclaration": {
-    "baseline": 8,
-    "slack": 3
+    "limit": 12
  },
  "reportReturnType": {
-    "baseline": 126,
-    "slack": 100
+    "limit": 225
  },
  "reportTypedDictNotRequiredAccess": {
-    "baseline": 20,
-    "slack": 3
+    "limit": 27
  },
  "reportUndefinedVariable": {
-    "baseline": 2,
-    "slack": 3
+    "limit": 0
  },
  "reportUnknownArgumentType": {
-    "baseline": 30603,
-    "slack": 3000
+    "limit": 45894
  },
  "reportUnknownLambdaType": {
-    "baseline": 75,
-    "slack": 10
+    "limit": 113
  },
  "reportUnknownMemberType": {
-    "baseline": 27037,
-    "slack": 2500
+    "limit": 40539
  },
  "reportUnknownParameterType": {
-    "baseline": 13612,
-    "slack": 1000
+    "limit": 20403
  },
  "reportUnknownVariableType": {
-    "baseline": 21445,
-    "slack": 2000
+    "limit": 32141
  },
  "reportUnnecessaryCast": {
-    "baseline": 118,
-    "slack": 10
+    "limit": 177
  },
  "reportUnnecessaryComparison": {
-    "baseline": 683,
-    "slack": 100
+    "limit": 1025
  },
  "reportUnnecessaryContains": {
-    "baseline": 4,
-    "slack": 3
+    "limit": 7
  },
  "reportUnnecessaryIsInstance": {
-    "baseline": 808,
-    "slack": 80
+    "limit": 1209
  },
  "reportUntypedBaseClass": {
-    "baseline": 110,
-    "slack": 11
+    "limit": 165
  },
  "reportUntypedFunctionDecorator": {
-    "baseline": 22,
-    "slack": 3
+    "limit": 33
  },
  "reportUnusedClass": {
-    "baseline": 22,
-    "slack": 3
+    "limit": 33
  },
  "reportUnusedFunction": {
-    "baseline": 137,
-    "slack": 10
+    "limit": 206
  },
  "reportUnusedImport": {
-    "baseline": 670,
-    "slack": 50
+    "limit": 1005
  },
  "reportUnusedVariable": {
-    "baseline": 865,
-    "slack": 50
+    "limit": 1297
  }
 }
--- a/codecov.yaml
+++ b/codecov.yaml
@ -15,6 +15,16 @@ ignore:
 flag_management:
  default_rules:
    carryforward: true
+  # Dead flags no CI job uploads anymore: their carried-forward sessions were
+  # measured against old revisions, and the stale line maps mark comment lines
+  # of since-edited files as missed, sinking patch coverage on unrelated PRs.
+  individual_flags:
+    - name: proxy-mgmt-behavior
+      carryforward: false
+    - name: security
+      carryforward: false
+    - name: proxy-db-schema-migration
+      carryforward: false

 component_management:
  individual_components:
--- a/deploy/azure_resource_manager/azure_marketplace.zip
+++ b/deploy/azure_resource_manager/azure_marketplace.zip
--- a/deploy/azure_resource_manager/azure_marketplace/createUiDefinition.json
+++ b/deploy/azure_resource_manager/azure_marketplace/createUiDefinition.json
@ -1,15 +0,0 @@
-{
-    "$schema": "https://schema.management.azure.com/schemas/0.1.2-preview/CreateUIDefinition.MultiVm.json#",
-    "handler": "Microsoft.Azure.CreateUIDef",
-    "version": "0.1.2-preview",
-    "parameters": {
-        "config": {
-            "isWizard": false,
-            "basics": { }
-        },
-        "basics": [ ],
-        "steps": [ ],
-        "outputs": { },
-        "resourceTypes": [ ]
-    }
-}
--- a/deploy/azure_resource_manager/azure_marketplace/mainTemplate.json
+++ b/deploy/azure_resource_manager/azure_marketplace/mainTemplate.json
@ -1,63 +0,0 @@
-{
-    "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#",
-    "contentVersion": "1.0.0.0",
-    "parameters": {
-      "imageName": {
-        "type": "string",
-        "defaultValue": "ghcr.io/berriai/litellm:main-latest"
-      },
-      "containerName": {
-        "type": "string",
-        "defaultValue": "litellm-container"
-      },
-      "dnsLabelName": {
-        "type": "string",
-        "defaultValue": "litellm"
-      },
-      "portNumber": {
-        "type": "int",
-        "defaultValue": 4000
-      }
-    },
-    "resources": [
-      {
-        "type": "Microsoft.ContainerInstance/containerGroups",
-        "apiVersion": "2021-03-01",
-        "name": "[parameters('containerName')]",
-        "location": "[resourceGroup().location]",
-        "properties": {
-          "containers": [
-            {
-              "name": "[parameters('containerName')]",
-              "properties": {
-                "image": "[parameters('imageName')]",
-                "resources": {
-                  "requests": {
-                    "cpu": 1,
-                    "memoryInGB": 2
-                  }
-                },
-                "ports": [
-                  {
-                    "port": "[parameters('portNumber')]"
-                  }
-                ]
-              }
-            }
-          ],
-          "osType": "Linux",
-          "restartPolicy": "Always",
-          "ipAddress": {
-            "type": "Public",
-            "ports": [
-              {
-                "protocol": "tcp",
-                "port": "[parameters('portNumber')]"
-              }
-            ],
-            "dnsNameLabel": "[parameters('dnsLabelName')]"
-          }
-        }
-      }
-    ]
-  }
--- a/deploy/azure_resource_manager/main.bicep
+++ b/deploy/azure_resource_manager/main.bicep
@ -1,42 +0,0 @@
-param imageName string = 'ghcr.io/berriai/litellm:main-latest'
-param containerName string = 'litellm-container'
-param dnsLabelName string = 'litellm'
-param portNumber int = 4000
-
-resource containerGroupName 'Microsoft.ContainerInstance/containerGroups@2021-03-01' = {
-  name: containerName
-  location: resourceGroup().location
-  properties: {
-    containers: [
-      {
-        name: containerName
-        properties: {
-          image: imageName
-          resources: {
-            requests: {
-              cpu: 1
-              memoryInGB: 2
-            }
-          }
-          ports: [
-            {
-              port: portNumber
-            }
-          ]
-        }
-      }
-    ]
-    osType: 'Linux'
-    restartPolicy: 'Always'
-    ipAddress: {
-      type: 'Public'
-      ports: [
-        {
-          protocol: 'tcp'
-          port: portNumber
-        }
-      ]
-      dnsNameLabel: dnsLabelName
-    }
-  }
-}
--- a/deploy/charts/litellm-helm/templates/configmap-litellm.yaml
+++ b/deploy/charts/litellm-helm/templates/configmap-litellm.yaml
@ -1,9 +0,0 @@
-{{- if .Values.proxyConfigMap.create }}
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: {{ include "litellm.fullname" . }}-config
-data:
-  config.yaml: |
-{{ .Values.proxy_config | toYaml | indent 6 }}
-{{- end }}
--- a/docker/Dockerfile.database
+++ b/docker/Dockerfile.database
@ -1,10 +1,10 @@
 # syntax=docker/dockerfile:1.7

 # Base image for building
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:c61ac6919b811ea53c4782d69f1fe05218ba3c25d53f01b6ab7892e621bd4370
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f

 # Runtime image
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:c61ac6919b811ea53c4782d69f1fe05218ba3c25d53f01b6ab7892e621bd4370
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f
 ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a
 # Pinned by digest like the other base images; bump explicitly on Node upgrades.
 ARG UI_BUILD_IMAGE=node:20.18-alpine3.20@sha256:3488b10bf958af7125a176419d2d8a9937d895bf124012aae811651988d2ffe6
--- a/docker/Dockerfile.non_root
+++ b/docker/Dockerfile.non_root
@ -1,8 +1,8 @@
 # syntax=docker/dockerfile:1.7

 # Base images
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:c61ac6919b811ea53c4782d69f1fe05218ba3c25d53f01b6ab7892e621bd4370
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:c61ac6919b811ea53c4782d69f1fe05218ba3c25d53f01b6ab7892e621bd4370
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f
 ARG PROXY_EXTRAS_SOURCE=published
 ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a
 # Pinned by digest like the other base images; bump explicitly on Node upgrades.
--- a/docker/build_admin_ui.sh
+++ b/docker/build_admin_ui.sh
@ -57,8 +57,6 @@ source ~/.nvm/nvm.sh
 nvm install v18.17.0
 nvm use v18.17.0

-# copy _enterprise.json from this directory to /ui/litellm-dashboard, and rename it to ui_colors.json
-cp enterprise/enterprise_ui/enterprise_colors.json ui/litellm-dashboard/ui_colors.json

 # cd in to /ui/litellm-dashboard
 cd ui/litellm-dashboard
--- a/enterprise/README.md
+++ b/enterprise/README.md
@ -6,4 +6,4 @@ Code in this folder is licensed under a commercial license. Please review the [L

 👉 **Using in an Enterprise / Need specific features ?** Meet with us [here](https://enterprise.litellm.ai/demo?month=2024-02)

-See all Enterprise Features here 👉 [Docs](https://docs.litellm.ai/docs/proxy/enterprise)
+See all Enterprise Features here 👉 [Docs](https://docs.litellm.ai/docs/enterprise)
--- a/enterprise/litellm_enterprise/enterprise_callbacks/send_emails/base_email.py
+++ b/enterprise/litellm_enterprise/enterprise_callbacks/send_emails/base_email.py
@ -239,6 +239,7 @@ class BaseEmailLogger(CustomLogger):
            max_budget_info=max_budget_info,
            base_url=email_params.base_url,
            email_support_contact=email_params.support_contact,
+            email_footer=email_params.signature,
        )
        await self.send_email(
            from_email=self.DEFAULT_LITELLM_EMAIL,
@ -311,6 +312,7 @@ class BaseEmailLogger(CustomLogger):
            max_budget_info=max_budget_info,
            base_url=email_params.base_url,
            email_support_contact=email_params.support_contact,
+            email_footer=email_params.signature,
        )

        # Send email to all recipients
@ -379,6 +381,7 @@ class BaseEmailLogger(CustomLogger):
                alert_threshold=alert_threshold_str,
                base_url=email_params.base_url,
                email_support_contact=email_params.support_contact,
+                email_footer=email_params.signature,
            )
            await self.send_email(
                from_email=self.DEFAULT_LITELLM_EMAIL,
@ -403,6 +406,7 @@ class BaseEmailLogger(CustomLogger):
                alert_threshold=alert_threshold_str,
                base_url=email_params.base_url,
                email_support_contact=email_params.support_contact,
+                email_footer=email_params.signature,
            )
            await self.send_email(
                from_email=self.DEFAULT_LITELLM_EMAIL,
@ -473,9 +477,12 @@ class BaseEmailLogger(CustomLogger):
                    _id = user_info.token or user_info.user_id or "default_id"
                _cache_key = f"email_budget_alerts:soft_budget_crossed:{_id}"

-                # Check if we've already sent this alert
-                result = await _cache.async_get_cache(key=_cache_key)
-                if result is None:
+                send_count = await _cache.async_increment_cache(
+                    key=_cache_key,
+                    value=1,
+                    ttl=EMAIL_BUDGET_ALERT_TTL,
+                )
+                if send_count is None or send_count <= 1:
                    # Create WebhookEvent for soft budget alert
                    event_message = f"Soft Budget Crossed - Total Soft Budget: ${user_info.soft_budget}"
                    webhook_event = WebhookEvent(
@ -504,18 +511,12 @@ class BaseEmailLogger(CustomLogger):
                            await self.send_team_soft_budget_alert_email(webhook_event)
                        else:
                            await self.send_soft_budget_alert_email(webhook_event)
-
-                        # Cache the alert to prevent duplicate sends
-                        await _cache.async_set_cache(
-                            key=_cache_key,
-                            value="SENT",
-                            ttl=EMAIL_BUDGET_ALERT_TTL,
-                        )
                    except Exception as e:
                        verbose_proxy_logger.error(
                            f"Error sending soft budget alert email: {e}",
                            exc_info=True,
                        )
+                        await self._release_budget_alert_claim(_cache, _cache_key)
            return

        # For max_budget_alert, check if we've already sent an alert
@ -541,9 +542,12 @@ class BaseEmailLogger(CustomLogger):
                    _id = user_info.token or user_info.user_id or "default_id"
                    _cache_key = f"email_budget_alerts:max_budget_alert:{_id}"

-                    # Check if we've already sent this alert
-                    result = await _cache.async_get_cache(key=_cache_key)
-                    if result is None:
+                    send_count = await _cache.async_increment_cache(
+                        key=_cache_key,
+                        value=1,
+                        ttl=EMAIL_BUDGET_ALERT_TTL,
+                    )
+                    if send_count is None or send_count <= 1:
                        # Calculate percentage
                        percentage = int(
                            EMAIL_BUDGET_ALERT_MAX_SPEND_ALERT_PERCENTAGE * 100
@ -572,18 +576,12 @@ class BaseEmailLogger(CustomLogger):

                        try:
                            await self.send_max_budget_alert_email(webhook_event)
-
-                            # Cache the alert to prevent duplicate sends
-                            await _cache.async_set_cache(
-                                key=_cache_key,
-                                value="SENT",
-                                ttl=EMAIL_BUDGET_ALERT_TTL,
-                            )
                        except Exception as e:
                            verbose_proxy_logger.error(
                                f"Error sending max budget alert email: {e}",
                                exc_info=True,
                            )
+                            await self._release_budget_alert_claim(_cache, _cache_key)
            return

    async def _handle_multi_threshold_max_budget_alert(
@ -613,10 +611,6 @@ class BaseEmailLogger(CustomLogger):
                f"email_budget_alerts:max_budget_alert:{threshold_pct}:{_id}"
            )

-            result = await _cache.async_get_cache(key=_cache_key)
-            if result is not None:
-                continue
-
            # Parse emails + auto-include owner
            emails = _parse_email_list(raw_emails)
            if user_info.user_email:
@ -630,6 +624,14 @@ class BaseEmailLogger(CustomLogger):
                continue
            recipient_emails = list(set(emails))

+            send_count = await _cache.async_increment_cache(
+                key=_cache_key,
+                value=1,
+                ttl=EMAIL_BUDGET_ALERT_TTL,
+            )
+            if send_count is not None and send_count > 1:
+                continue
+
            event_message = f"Max Budget Alert - {threshold_pct}% of Maximum Budget Reached"
            webhook_event = WebhookEvent(
                event="max_budget_alert",
@ -656,16 +658,21 @@ class BaseEmailLogger(CustomLogger):
                    threshold_pct=threshold_pct,
                    recipient_emails=recipient_emails,
                )
-                await _cache.async_set_cache(
-                    key=_cache_key,
-                    value="SENT",
-                    ttl=EMAIL_BUDGET_ALERT_TTL,
-                )
            except Exception as e:
                verbose_proxy_logger.error(
                    f"Error sending multi-threshold max budget alert email for {threshold_pct}%: {e}",
                    exc_info=True,
                )
+                await self._release_budget_alert_claim(_cache, _cache_key)
+
+    async def _release_budget_alert_claim(self, cache: DualCache, cache_key: str) -> None:
+        try:
+            await cache.async_delete_cache(key=cache_key)
+        except Exception:
+            verbose_proxy_logger.debug(
+                "Failed to release budget alert claim for %s; it expires with the TTL",
+                cache_key,
+            )

    async def _get_email_params(
        self,
@ -912,9 +919,9 @@ class BaseEmailLogger(CustomLogger):
        """
        Construct invitation link for the user

-        # http://localhost:4000/ui?invitation_id=7a096b3a-37c6-440f-9dd1-ba22e8043f6b
+        # http://localhost:4000/ui/onboarding?invitation_id=7a096b3a-37c6-440f-9dd1-ba22e8043f6b
        """
-        return f"{base_url}/ui?invitation_id={invitation_id}"
+        return f"{base_url}/ui/onboarding?invitation_id={invitation_id}"

    async def send_email(
        self,
--- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py
+++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py
@ -13,8 +13,11 @@ from litellm.constants import (
 )

 if TYPE_CHECKING:
+    from litellm.integrations.prometheus import PrometheusLogger
+    from litellm.proxy._types import LiteLLM_ManagedObjectTable
    from litellm.proxy.utils import PrismaClient, ProxyLogging
    from litellm.router import Router
+    from litellm.types.utils import LiteLLMBatch


 CHECK_BATCH_COST_USER_AGENT = "LiteLLM Proxy/CheckBatchCost"
@ -26,6 +29,7 @@ class CheckBatchCost:
        proxy_logging_obj: "ProxyLogging",
        prisma_client: "PrismaClient",
        llm_router: "Router",
+        track_unmanaged_vertex_batch_cost: bool = False,
    ):
        from litellm.proxy.utils import PrismaClient, ProxyLogging
        from litellm.router import Router
@ -33,6 +37,7 @@ class CheckBatchCost:
        self.proxy_logging_obj: ProxyLogging = proxy_logging_obj
        self.prisma_client: PrismaClient = prisma_client
        self.llm_router: Router = llm_router
+        self._track_unmanaged_vertex_batch_cost = track_unmanaged_vertex_batch_cost
        # Cached after the first poll cycle. Once we know the column is absent we skip
        # the guaranteed-failing primary query on every subsequent cycle.
        self._has_batch_processed_column: bool = True
@ -97,13 +102,196 @@ class CheckBatchCost:
            order={"created_at": "asc"},
        )

-    async def check_batch_cost(self):
+    @staticmethod
+    def _record_error(
+        prom_logger: Optional["PrometheusLogger"], error_type: str
+    ) -> None:
+        if prom_logger is not None:
+            prom_logger.record_check_batch_cost_error(error_type)
+
+    def _resolve_job_routing(
+        self,
+        job: "LiteLLM_ManagedObjectTable",
+        prom_logger: Optional["PrometheusLogger"],
+    ) -> Optional[Tuple[str, str]]:
        """
-        Check if the batch JOB has been tracked.
-        - get all status="validating" and file_purpose="batch" jobs
-        - check if batch is now complete
-        - if not, return False
-        - if so, return True
+        Resolve (model_id, batch_id) for a managed-object row, where model_id is a router
+        deployment id and batch_id is the raw provider batch id.
+
+        Managed batches encode both in a base64 unified id. Unmanaged Vertex batches, created with
+        a raw gs:// input_file_id, store the raw provider job id as unified_object_id; when
+        track_unmanaged_vertex_batch_cost is enabled the model is derived from the gs:// path and
+        mapped to a configured vertex_ai deployment. Returns None (recording a metric) when the row
+        can't be routed.
+        """
+        from litellm.proxy.openai_files_endpoints.common_utils import (
+            _is_base64_encoded_unified_file_id,
+            get_batch_id_from_unified_batch_id,
+            get_model_id_from_unified_batch_id,
+        )
+
+        unified_object_id = job.unified_object_id
+        decoded = _is_base64_encoded_unified_file_id(unified_object_id)
+        if decoded:
+            model_id = get_model_id_from_unified_batch_id(decoded)
+            if model_id is None:
+                verbose_proxy_logger.info(
+                    f"Skipping job {unified_object_id} because it is not a valid model id"
+                )
+                self._record_error(prom_logger, "invalid_model_id")
+                return None
+            return model_id, get_batch_id_from_unified_batch_id(decoded)
+
+        if self._track_unmanaged_vertex_batch_cost:
+            return self._resolve_unmanaged_vertex_routing(job, prom_logger)
+
+        verbose_proxy_logger.info(
+            f"Skipping job {unified_object_id} because it is not a valid unified object id"
+        )
+        self._record_error(prom_logger, "invalid_unified_id")
+        return None
+
+    def _resolve_unmanaged_vertex_routing(
+        self,
+        job: "LiteLLM_ManagedObjectTable",
+        prom_logger: Optional["PrometheusLogger"],
+    ) -> Optional[Tuple[str, str]]:
+        from litellm.llms.vertex_ai.batches.transformation import (
+            VertexAIBatchTransformation,
+        )
+
+        input_file_id = self._get_input_file_id(job)
+        if not VertexAIBatchTransformation.is_unmanaged_gcs_batch_input_file_id(
+            input_file_id
+        ):
+            verbose_proxy_logger.info(
+                f"Skipping job {job.unified_object_id}: not an unmanaged vertex batch "
+                "(no gs:// input_file_id with a publishers/ model path)"
+            )
+            self._record_error(prom_logger, "invalid_unified_id")
+            return None
+        assert input_file_id is not None  # narrowed by is_unmanaged_gcs_batch_input_file_id
+
+        bare_model_name = VertexAIBatchTransformation.get_bare_model_name_from_gcs_file(
+            input_file_id
+        )
+        deployment_id = self._get_vertex_ai_deployment_id_for_bare_model(
+            bare_model_name
+        )
+        if deployment_id is None:
+            verbose_proxy_logger.info(
+                f"Skipping unmanaged vertex batch {job.unified_object_id}: no vertex_ai "
+                f"deployment configured for model {bare_model_name}"
+            )
+            self._record_error(prom_logger, "unmanaged_no_matching_deployment")
+            return None
+
+        return deployment_id, job.unified_object_id
+
+    def _get_vertex_ai_deployment_id_for_bare_model(
+        self, bare_model_name: str
+    ) -> Optional[str]:
+        model_group = self.llm_router.resolve_model_name_from_model_id(bare_model_name)
+        deployment_id = (
+            self._get_vertex_ai_deployment_id(model_group) if model_group else None
+        )
+        if deployment_id is not None:
+            return deployment_id
+
+        return self._get_vertex_ai_deployment_id_from_matching_deployments(
+            bare_model_name
+        )
+
+    def _get_vertex_ai_deployment_id_from_matching_deployments(
+        self, bare_model_name: str
+    ) -> Optional[str]:
+        from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
+
+        for deployment in self.llm_router.get_model_list(model_name=None) or []:
+            litellm_params = deployment.get("litellm_params") or {}
+            actual_model = litellm_params.get("model")
+            if not isinstance(actual_model, str):
+                continue
+            if not self._is_bare_model_match(actual_model, bare_model_name):
+                continue
+            try:
+                _, llm_provider, _, _ = get_llm_provider(
+                    model=actual_model,
+                    custom_llm_provider=litellm_params.get("custom_llm_provider"),
+                )
+            except Exception:
+                continue
+            if llm_provider != "vertex_ai":
+                continue
+            model_info = deployment.get("model_info") or {}
+            deployment_id = model_info.get("id")
+            if isinstance(deployment_id, str):
+                return deployment_id
+        return None
+
+    @staticmethod
+    def _is_bare_model_match(actual_model: str, bare_model_name: str) -> bool:
+        return (
+            actual_model == bare_model_name
+            or actual_model.endswith(f"/{bare_model_name}")
+            or actual_model.endswith(f":{bare_model_name}")
+        )
+
+    def _get_vertex_ai_deployment_id(self, model_group: str) -> Optional[str]:
+        """
+        Returns the first deployment id for `model_group` whose provider is vertex_ai,
+        skipping deployments from other providers that happen to share the model group name.
+        """
+        from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
+
+        for deployment_id in self.llm_router.get_model_ids(model_name=model_group):
+            deployment_info = self.llm_router.get_deployment(model_id=deployment_id)
+            if deployment_info is None:
+                continue
+            try:
+                _, llm_provider, _, _ = get_llm_provider(
+                    model=deployment_info.litellm_params.model,
+                    custom_llm_provider=deployment_info.litellm_params.custom_llm_provider,
+                )
+            except Exception:
+                continue
+            if llm_provider == "vertex_ai":
+                return deployment_id
+        return None
+
+    @staticmethod
+    def _get_input_file_id(job: "LiteLLM_ManagedObjectTable") -> Optional[str]:
+        import json
+
+        from litellm.types.utils import LiteLLMBatch
+
+        file_object = job.file_object
+        if isinstance(file_object, str):
+            try:
+                file_object = json.loads(file_object)
+            except (json.JSONDecodeError, ValueError):
+                return None
+        if not isinstance(file_object, dict):
+            return None
+        try:
+            return LiteLLMBatch.model_validate(file_object).input_file_id
+        except Exception:
+            return None
+
+    async def _track_completed_batch_cost(
+        self,
+        job: "LiteLLM_ManagedObjectTable",
+        response: "LiteLLMBatch",
+        model_id: str,
+        batch_id: str,
+        prom_logger: Optional["PrometheusLogger"],
+    ) -> Optional[Tuple[Optional[str], Optional[str]]]:
+        """
+        Fetch a completed batch's results, compute cost/usage, and emit the
+        aretrieve_batch spend log. Returns (model_name, llm_provider) on
+        success, None when the job can't be routed to a deployment. Raises on
+        results-fetch or cost-computation failures so the caller can leave the
+        job unprocessed and retry it on a later poll.
        """
        from litellm.batches.batch_utils import (
            _get_file_content_as_dictionary,
@ -114,10 +302,186 @@ class CheckBatchCost:
        from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLogging
        from litellm.proxy.openai_files_endpoints.common_utils import (
            _is_base64_encoded_unified_file_id,
-            get_batch_id_from_unified_batch_id,
-            get_model_id_from_unified_batch_id,
        )

+        verbose_proxy_logger.info(
+            f"Batch ID: {batch_id} is complete, tracking cost and usage"
+        )
+
+        # aretrieve_batch is called with the raw provider batch ID, so response.id
+        # is the raw provider value (e.g. "batch_20260223-0518.234"). We need the
+        # unified base64 ID in the S3 log so downstream consumers can correlate it
+        # back to the batch they submitted via the proxy.
+        #
+        # CheckBatchCost builds its own LiteLLMLogging object (logging_obj below) and
+        # calls async_success_handler(result=response) directly. That handler calls
+        # _build_standard_logging_payload(response, ...) which reads response.id at
+        # that point — so setting response.id here is sufficient.
+        #
+        # The HTTP endpoint does this substitution via the managed files hook
+        # (async_post_call_success_hook). CheckBatchCost bypasses that hook entirely,
+        # so we do it explicitly here.
+        response.id = job.unified_object_id
+
+        # This background job runs as default_user_id, so going through the HTTP endpoint
+        # would trigger check_managed_file_id_access and get 403. Instead, extract the raw
+        # provider file ID and call afile_content directly with deployment credentials.
+        raw_output_file_id = response.output_file_id
+        decoded = _is_base64_encoded_unified_file_id(raw_output_file_id)
+        if decoded:
+            try:
+                raw_output_file_id = decoded.split("llm_output_file_id,")[1].split(";")[0]
+            except (IndexError, AttributeError):
+                pass
+
+        credentials = self.llm_router.get_deployment_credentials_with_provider(model_id) or {}
+        _file_content = await afile_content(
+            file_id=raw_output_file_id,
+            **credentials,
+        )
+
+        # Access content - handle both direct attribute and method call
+        if hasattr(_file_content, 'content'):
+            content_bytes = _file_content.content  # type: ignore[union-attr]
+        elif hasattr(_file_content, 'read'):
+            content_bytes = await _file_content.read()  # type: ignore[misc]
+        else:
+            content_bytes = _file_content  # type: ignore[assignment]
+
+        file_content_as_dict = _get_file_content_as_dictionary(
+            content_bytes  # type: ignore[arg-type]
+        )
+
+        # Record output file size
+        if prom_logger and content_bytes:
+            try:
+                prom_logger.record_managed_file_size(
+                    size_bytes=len(content_bytes),  # type: ignore
+                    purpose="batch",
+                    file_type="output",
+                    model=model_id,
+                )
+            except Exception:
+                pass
+
+        deployment_info = self.llm_router.get_deployment(model_id=model_id)
+        if deployment_info is None:
+            verbose_proxy_logger.info(
+                f"Skipping job {job.unified_object_id} because it is not a valid deployment info"
+            )
+            self._record_error(prom_logger, "deployment_not_found")
+            return None
+        custom_llm_provider = deployment_info.litellm_params.custom_llm_provider
+        litellm_model_name = deployment_info.litellm_params.model
+
+        model_name, llm_provider, _, _ = get_llm_provider(
+            model=litellm_model_name,
+            custom_llm_provider=custom_llm_provider,
+        )
+
+        # CheckBatchCost bypasses async_post_call_success_hook, so convert raw
+        # output/error file IDs to managed base64 IDs before the DB write here.
+        managed_files_hook = self.proxy_logging_obj.get_proxy_hook("managed_files")
+        if managed_files_hook is not None:
+            from litellm.proxy._types import UserAPIKeyAuth
+            _minimal_auth = UserAPIKeyAuth(
+                user_id=job.created_by or "default-user-id",
+                team_id=getattr(job, "team_id", None),
+            )
+            for _file_attr in ["output_file_id", "error_file_id"]:
+                _raw_file_id = getattr(response, _file_attr, None)
+                if _raw_file_id and not _is_base64_encoded_unified_file_id(_raw_file_id):
+                    try:
+                        _unified_file_id = managed_files_hook.get_unified_output_file_id(
+                            output_file_id=_raw_file_id,
+                            model_id=model_id,
+                            model_name=str(model_name) if model_name else deployment_info.model_name or None,
+                        )
+                        await managed_files_hook.store_unified_file_id(
+                            file_id=_unified_file_id,
+                            file_object=None,
+                            litellm_parent_otel_span=None,
+                            model_mappings={model_id: _raw_file_id},
+                            user_api_key_dict=_minimal_auth,
+                        )
+                        setattr(response, _file_attr, _unified_file_id)
+                        verbose_proxy_logger.info(
+                            f"CheckBatchCost: converted {_file_attr} "
+                            f"{_raw_file_id!r} -> managed ID for batch {batch_id}"
+                        )
+                    except Exception as _e:
+                        verbose_proxy_logger.warning(
+                            f"CheckBatchCost: failed to create managed file ID for "
+                            f"{_file_attr}={_raw_file_id!r}: {_e}"
+                        )
+
+        # Pass deployment model_info so custom batch pricing
+        # (input_cost_per_token_batches etc.) is used for cost calc
+        deployment_model_info = deployment_info.model_info.model_dump() if deployment_info.model_info else {}
+        batch_cost, batch_usage, batch_models = (
+            await calculate_batch_cost_and_usage(
+                file_content_dictionary=file_content_as_dict,
+                custom_llm_provider=llm_provider,  # type: ignore
+                model_name=model_name,
+                model_info=deployment_model_info,  # type: ignore[arg-type]
+            )
+        )
+        logging_obj = LiteLLMLogging(
+            model=batch_models[0],
+            messages=[{"role": "user", "content": "<retrieve_batch>"}],
+            stream=False,
+            call_type="aretrieve_batch",
+            start_time=datetime.now(),
+            litellm_call_id=str(uuid.uuid4()),
+            function_id=str(uuid.uuid4()),
+        )
+
+        creator_user_id = job.created_by
+        user_info = await self._get_user_info(batch_id, job.created_by)
+
+        logging_obj.update_environment_variables(
+            litellm_params={
+                # set the user-agent header so that S3 callback consumers can easily identify CheckBatchCost callbacks
+                "proxy_server_request": {
+                    "headers": {
+                        "user-agent": CHECK_BATCH_COST_USER_AGENT,
+                    }
+                },
+                "metadata": {
+                    "user_api_key_user_id": creator_user_id,
+                    **user_info,
+                },
+            },
+            optional_params={},
+        )
+
+        await logging_obj.async_success_handler(
+            result=response,
+            batch_cost=batch_cost,
+            batch_usage=batch_usage,
+            batch_models=batch_models,
+        )
+
+        # Record batch duration (completed_at - created_at)
+        if prom_logger and response.completed_at and response.created_at:
+            duration_seconds = float(response.completed_at - response.created_at)
+            if duration_seconds >= 0:
+                prom_logger.record_managed_batch_duration(
+                    duration_seconds=duration_seconds,
+                    model=model_name,
+                    api_provider=str(llm_provider) if llm_provider else None,
+                )
+
+        return model_name, str(llm_provider) if llm_provider else None
+
+    async def check_batch_cost(self):
+        """
+        Check if the batch JOB has been tracked.
+        - get all status="validating" and file_purpose="batch" jobs
+        - check if batch is now complete
+        - if not, return False
+        - if so, return True
+        """
        try:
            from litellm.integrations.prometheus import PrometheusLogger
            prom_logger = PrometheusLogger.get_instance()
@ -172,31 +536,10 @@ class CheckBatchCost:
        else:
            jobs = await self._fallback_find_jobs()
        for job in jobs:
-            # get the model from the job
-            unified_object_id = job.unified_object_id
-            decoded_unified_object_id = _is_base64_encoded_unified_file_id(
-                unified_object_id
-            )
-            if not decoded_unified_object_id:
-                verbose_proxy_logger.info(
-                    f"Skipping job {unified_object_id} because it is not a valid unified object id"
-                )
-                if prom_logger:
-                    prom_logger.record_check_batch_cost_error("invalid_unified_id")
-                continue
-            else:
-                unified_object_id = decoded_unified_object_id
-
-            model_id = get_model_id_from_unified_batch_id(unified_object_id)
-            batch_id = get_batch_id_from_unified_batch_id(unified_object_id)
-
-            if model_id is None:
-                verbose_proxy_logger.info(
-                    f"Skipping job {unified_object_id} because it is not a valid model id"
-                )
-                if prom_logger:
-                    prom_logger.record_check_batch_cost_error("invalid_model_id")
+            routing = self._resolve_job_routing(job, prom_logger)
+            if routing is None:
                continue
+            model_id, batch_id = routing

            verbose_proxy_logger.info(
                f"Querying model ID: {model_id} for cost and usage of batch ID: {batch_id}"
@ -213,7 +556,7 @@ class CheckBatchCost:
                )
            except Exception as e:
                verbose_proxy_logger.info(
-                    f"Skipping job {unified_object_id} because of error querying model ID: {model_id} for cost and usage of batch ID: {batch_id}: {e}"
+                    f"Skipping job {job.unified_object_id} because of error querying model ID: {model_id} for cost and usage of batch ID: {batch_id}: {e}"
                )
                if prom_logger:
                    prom_logger.record_check_batch_cost_error("provider_retrieval_error")
@ -224,177 +567,26 @@ class CheckBatchCost:
                response.status == "completed"
                and response.output_file_id is not None
            ):
-                verbose_proxy_logger.info(
-                    f"Batch ID: {batch_id} is complete, tracking cost and usage"
-                )
-
-                # aretrieve_batch is called with the raw provider batch ID, so response.id
-                # is the raw provider value (e.g. "batch_20260223-0518.234"). We need the
-                # unified base64 ID in the S3 log so downstream consumers can correlate it
-                # back to the batch they submitted via the proxy.
-                #
-                # CheckBatchCost builds its own LiteLLMLogging object (logging_obj below) and
-                # calls async_success_handler(result=response) directly. That handler calls
-                # _build_standard_logging_payload(response, ...) which reads response.id at
-                # that point — so setting response.id here is sufficient.
-                #
-                # The HTTP endpoint does this substitution via the managed files hook
-                # (async_post_call_success_hook). CheckBatchCost bypasses that hook entirely,
-                # so we do it explicitly here.
-                response.id = job.unified_object_id
-
-                # This background job runs as default_user_id, so going through the HTTP endpoint
-                # would trigger check_managed_file_id_access and get 403. Instead, extract the raw
-                # provider file ID and call afile_content directly with deployment credentials.
-                raw_output_file_id = response.output_file_id
-                decoded = _is_base64_encoded_unified_file_id(raw_output_file_id)
-                if decoded:
-                    try:
-                        raw_output_file_id = decoded.split("llm_output_file_id,")[1].split(";")[0]
-                    except (IndexError, AttributeError):
-                        pass
-
-                credentials = self.llm_router.get_deployment_credentials_with_provider(model_id) or {}
-                _file_content = await afile_content(
-                    file_id=raw_output_file_id,
-                    **credentials,
-                )
-
-                # Access content - handle both direct attribute and method call
-                if hasattr(_file_content, 'content'):
-                    content_bytes = _file_content.content  # type: ignore[union-attr]
-                elif hasattr(_file_content, 'read'):
-                    content_bytes = await _file_content.read()  # type: ignore[misc]
-                else:
-                    content_bytes = _file_content  # type: ignore[assignment]
-
-                file_content_as_dict = _get_file_content_as_dictionary(
-                    content_bytes  # type: ignore[arg-type]
-                )
-
-                # Record output file size
-                if prom_logger and content_bytes:
-                    try:
-                        prom_logger.record_managed_file_size(
-                            size_bytes=len(content_bytes),  # type: ignore
-                            purpose="batch",
-                            file_type="output",
-                            model=model_id,
-                        )
-                    except Exception:
-                        pass
-
-                deployment_info = self.llm_router.get_deployment(model_id=model_id)
-                if deployment_info is None:
-                    verbose_proxy_logger.info(
-                        f"Skipping job {unified_object_id} because it is not a valid deployment info"
+                try:
+                    tracked = await self._track_completed_batch_cost(
+                        job=job,
+                        response=response,
+                        model_id=model_id,
+                        batch_id=batch_id,
+                        prom_logger=prom_logger,
                    )
-                    if prom_logger:
-                        prom_logger.record_check_batch_cost_error("deployment_not_found")
+                except Exception as tracking_err:
+                    verbose_proxy_logger.error(
+                        f"CheckBatchCost: failed to track cost for batch {batch_id} "
+                        f"(job {job.id}); leaving it unprocessed so the next poll retries: {tracking_err}"
+                    )
+                    self._record_error(prom_logger, "cost_tracking_error")
+                    continue
+                if tracked is None:
                    continue
-                custom_llm_provider = deployment_info.litellm_params.custom_llm_provider
-                litellm_model_name = deployment_info.litellm_params.model
-
-                model_name, llm_provider, _, _ = get_llm_provider(
-                    model=litellm_model_name,
-                    custom_llm_provider=custom_llm_provider,
-                )
-
-                # CheckBatchCost bypasses async_post_call_success_hook, so convert raw
-                # output/error file IDs to managed base64 IDs before the DB write here.
-                managed_files_hook = self.proxy_logging_obj.get_proxy_hook("managed_files")
-                if managed_files_hook is not None:
-                    from litellm.proxy._types import UserAPIKeyAuth
-                    _minimal_auth = UserAPIKeyAuth(
-                        user_id=job.created_by or "default-user-id",
-                        team_id=getattr(job, "team_id", None),
-                    )
-                    for _file_attr in ["output_file_id", "error_file_id"]:
-                        _raw_file_id = getattr(response, _file_attr, None)
-                        if _raw_file_id and not _is_base64_encoded_unified_file_id(_raw_file_id):
-                            try:
-                                _unified_file_id = managed_files_hook.get_unified_output_file_id(
-                                    output_file_id=_raw_file_id,
-                                    model_id=model_id,
-                                    model_name=str(model_name) if model_name else deployment_info.model_name or None,
-                                )
-                                await managed_files_hook.store_unified_file_id(
-                                    file_id=_unified_file_id,
-                                    file_object=None,
-                                    litellm_parent_otel_span=None,
-                                    model_mappings={model_id: _raw_file_id},
-                                    user_api_key_dict=_minimal_auth,
-                                )
-                                setattr(response, _file_attr, _unified_file_id)
-                                verbose_proxy_logger.info(
-                                    f"CheckBatchCost: converted {_file_attr} "
-                                    f"{_raw_file_id!r} -> managed ID for batch {batch_id}"
-                                )
-                            except Exception as _e:
-                                verbose_proxy_logger.warning(
-                                    f"CheckBatchCost: failed to create managed file ID for "
-                                    f"{_file_attr}={_raw_file_id!r}: {_e}"
-                                )
-
-                # Pass deployment model_info so custom batch pricing
-                # (input_cost_per_token_batches etc.) is used for cost calc
-                deployment_model_info = deployment_info.model_info.model_dump() if deployment_info.model_info else {}
-                batch_cost, batch_usage, batch_models = (
-                    await calculate_batch_cost_and_usage(
-                        file_content_dictionary=file_content_as_dict,
-                        custom_llm_provider=llm_provider,  # type: ignore
-                        model_name=model_name,
-                        model_info=deployment_model_info,  # type: ignore[arg-type]
-                    )
-                )
-                logging_obj = LiteLLMLogging(
-                    model=batch_models[0],
-                    messages=[{"role": "user", "content": "<retrieve_batch>"}],
-                    stream=False,
-                    call_type="aretrieve_batch",
-                    start_time=datetime.now(),
-                    litellm_call_id=str(uuid.uuid4()),
-                    function_id=str(uuid.uuid4()),
-                )
-
-                creator_user_id = job.created_by
-                user_info = await self._get_user_info(batch_id, job.created_by)
-
-                logging_obj.update_environment_variables(
-                    litellm_params={
-                        # set the user-agent header so that S3 callback consumers can easily identify CheckBatchCost callbacks
-                        "proxy_server_request": {
-                            "headers": {
-                                "user-agent": CHECK_BATCH_COST_USER_AGENT,
-                            }
-                        },
-                        "metadata": {
-                            "user_api_key_user_id": creator_user_id,
-                            **user_info,
-                        },
-                    },
-                    optional_params={},
-                )
-
-                await logging_obj.async_success_handler(
-                    result=response,
-                    batch_cost=batch_cost,
-                    batch_usage=batch_usage,
-                    batch_models=batch_models,
-                )
-
-                # Record batch duration (completed_at - created_at)
-                if prom_logger and response.completed_at and response.created_at:
-                    duration_seconds = float(response.completed_at - response.created_at)
-                    if duration_seconds >= 0:
-                        prom_logger.record_managed_batch_duration(
-                            duration_seconds=duration_seconds,
-                            model=model_name,
-                            api_provider=str(llm_provider) if llm_provider else None,
-                        )

                # Track this job for the final metrics summary
-                processed_models.append((model_name, str(llm_provider) if llm_provider else None))
+                processed_models.append(tracked)

                # mark the job as complete
                try:
@ -413,6 +605,26 @@ class CheckBatchCost:
                        f"CheckBatchCost: failed to mark job {job.id} complete in DB: {db_err}"
                    )

+            elif response.status in ("failed", "expired", "cancelled"):
+                try:
+                    update_data = {
+                        "status": response.status,
+                        "file_object": response.model_dump_json(),
+                    }
+                    if self._has_batch_processed_column:
+                        update_data["batch_processed"] = True
+                    await self.prisma_client.db.litellm_managedobjecttable.update(
+                        where={"id": job.id},
+                        data=update_data,
+                    )
+                    verbose_proxy_logger.info(
+                        f"CheckBatchCost: marked job {job.id} as {response.status} in DB"
+                    )
+                except Exception as db_err:
+                    verbose_proxy_logger.error(
+                        f"CheckBatchCost: failed to mark job {job.id} as {response.status} in DB: {db_err}"
+                    )
+
        # Record polling run metrics (always, even if nothing was processed)
        if prom_logger:
            prom_logger.record_check_batch_cost_run(
--- a/enterprise/litellm_enterprise/proxy/hooks/managed_files.py
+++ b/enterprise/litellm_enterprise/proxy/hooks/managed_files.py
@ -125,23 +125,33 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints):
            "team_id": user_api_key_dict.team_id,
            "updated_by": user_api_key_dict.user_id,
        }
+        update_data = {
+            "model_mappings": json.dumps(model_mappings),
+            "flat_model_file_ids": list(model_mappings.values()),
+            "updated_by": user_api_key_dict.user_id,
+        }

        if file_object is not None:
-            db_data["file_object"] = file_object.model_dump_json()
+            file_object_json = file_object.model_dump_json()
+            db_data["file_object"] = file_object_json
+            update_data["file_object"] = file_object_json
            # Extract storage metadata from hidden params if present
            hidden_params = getattr(file_object, "_hidden_params", {}) or {}
            if "storage_backend" in hidden_params:
                db_data["storage_backend"] = hidden_params["storage_backend"]
+                update_data["storage_backend"] = hidden_params["storage_backend"]
            if "storage_url" in hidden_params:
                db_data["storage_url"] = hidden_params["storage_url"]
+                update_data["storage_url"] = hidden_params["storage_url"]

            verbose_logger.debug(
                f"Storage metadata: storage_backend={db_data.get('storage_backend')}, "
                f"storage_url={db_data.get('storage_url')}"
            )

-        result = await self.prisma_client.db.litellm_managedfiletable.create(
-            data=db_data
+        result = await self.prisma_client.db.litellm_managedfiletable.upsert(
+            where={"unified_file_id": file_id},
+            data={"create": db_data, "update": update_data},
        )
        verbose_logger.debug(
            f"LiteLLM Managed File object with id={file_id} stored in db: {result}"
--- a/enterprise/pyproject.toml
+++ b/enterprise/pyproject.toml
@ -1,6 +1,6 @@
 [project]
 name = "litellm-enterprise"
-version = "0.1.44"
+version = "0.1.49"
 description = "Package for LiteLLM Enterprise features"
 readme = "README.md"
 requires-python = ">=3.9"
@ -26,7 +26,7 @@ required-version = ">=0.10.9"
 module-root = ""

 [tool.commitizen]
-version = "0.1.44"
+version = "0.1.49"
 version_files = [
    "pyproject.toml:^version",
    "../pyproject.toml:litellm-enterprise==",
--- a/gateway/Dockerfile
+++ b/gateway/Dockerfile
@ -1,5 +1,5 @@
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:c61ac6919b811ea53c4782d69f1fe05218ba3c25d53f01b6ab7892e621bd4370
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:c61ac6919b811ea53c4782d69f1fe05218ba3c25d53f01b6ab7892e621bd4370
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:42df77a9974d6ec8b17a5ee8bc23b532600a44d705acef2409e0933c1251b45f
 ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:240fb85ab0f263ef12f492d8476aa3a2e4e1e333f7d67fbdd923d00a506a516a

 FROM $UV_IMAGE AS uvbin
--- a/gateway/main.py
+++ b/gateway/main.py
@ -25,17 +25,25 @@ DatabaseURLSettings.from_env().apply_to_env()

 from litellm.proxy.proxy_server import app

-from gateway.routes.allowlist import GATEWAY_EXACT_PATHS, GATEWAY_PATH_PREFIXES
+from gateway.routes.allowlist import (
+    GATEWAY_EXACT_PATHS,
+    GATEWAY_MOUNT_PATHS,
+    GATEWAY_PATH_PREFIXES,
+)


 def _is_gateway_route(route) -> bool:
-    """Keep the route on the gateway if its path is in the LLM data-plane surface."""
+    """Keep the route on the gateway if its path is in the LLM data-plane surface.
+
+    Prometheus registers /metrics as a Mount (``app.mount("/metrics", make_asgi_app())``),
+    so Mounts are matched against GATEWAY_MOUNT_PATHS instead of being dropped with
+    the UI static mounts.
+    """
    path = getattr(route, "path", None)
    if path is None:
        return False
    if isinstance(route, Mount):
-        # Gateway never serves the static UI or its asset bundles.
-        return False
+        return path in GATEWAY_MOUNT_PATHS
    if path in GATEWAY_EXACT_PATHS:
        return True
    return any(path.startswith(prefix) for prefix in GATEWAY_PATH_PREFIXES)
--- a/gateway/routes/allowlist.py
+++ b/gateway/routes/allowlist.py
@ -106,7 +106,7 @@ GATEWAY_PATH_PREFIXES: tuple[str, ...] = (
    # Health & ops
    "/health",
    "/metrics",
-    "/watsonx"
+    "/watsonx",
 )

 GATEWAY_EXACT_PATHS: frozenset[str] = frozenset(
@ -120,3 +120,9 @@ GATEWAY_EXACT_PATHS: frozenset[str] = frozenset(
        "/test",
    }
 )
+
+GATEWAY_MOUNT_PATHS: frozenset[str] = frozenset(
+    {
+        "/metrics",
+    }
+)
--- a/deploy/charts/litellm-helm/.helmignore
+++ b/deploy/charts/litellm-helm/.helmignore
--- a/deploy/charts/litellm-helm/Chart.lock
+++ b/deploy/charts/litellm-helm/Chart.lock
--- a/deploy/charts/litellm-helm/Chart.yaml
+++ b/deploy/charts/litellm-helm/Chart.yaml
--- a/deploy/charts/litellm-helm/README.md
+++ b/deploy/charts/litellm-helm/README.md
--- a/deploy/charts/litellm-helm/charts/postgresql-14.3.1.tgz
+++ b/deploy/charts/litellm-helm/charts/postgresql-14.3.1.tgz
--- a/deploy/charts/litellm-helm/charts/redis-18.19.1.tgz
+++ b/deploy/charts/litellm-helm/charts/redis-18.19.1.tgz
--- a/deploy/charts/litellm-helm/ci/test-values.yaml
+++ b/deploy/charts/litellm-helm/ci/test-values.yaml
--- a/deploy/charts/litellm-helm/templates/NOTES.txt
+++ b/deploy/charts/litellm-helm/templates/NOTES.txt
--- a/deploy/charts/litellm-helm/templates/_helpers.tpl
+++ b/deploy/charts/litellm-helm/templates/_helpers.tpl
@ -76,10 +76,13 @@ so fall back to "default" (or an explicit override) to avoid a cyclic dependency
 {{- end }}

 {{/*
-Get redis service name
+Get redis service name.
+The bundled Redis subchart only serves sentinel in "replication" architecture
+(it rejects standalone + sentinel outright), and in that mode the sentinel
+Service is named "<release>-redis", not "<release>-redis-master".
 */}}
 {{- define "litellm.redis.serviceName" -}}
-{{- if and (eq .Values.redis.architecture "standalone") .Values.redis.sentinel.enabled -}}
+{{- if .Values.redis.sentinel.enabled -}}
 {{- printf "%s-%s" .Release.Name (default "redis" .Values.redis.nameOverride | trunc 63 | trimSuffix "-") -}}
 {{- else -}}
 {{- printf "%s-%s-master" .Release.Name (default "redis" .Values.redis.nameOverride | trunc 63 | trimSuffix "-") -}}
--- a/helm/litellm-helm/templates/configmap-litellm.yaml
+++ b/helm/litellm-helm/templates/configmap-litellm.yaml
@ -0,0 +1,22 @@
+{{- if .Values.proxyConfigMap.create }}
+{{- $config := deepCopy .Values.proxy_config }}
+{{- if and .Values.redis.enabled (dig "coordination" "enabled" true .Values.redis) }}
+{{- $generalSettings := (get $config "general_settings") | default dict }}
+{{- if not (hasKey $generalSettings "coordination_redis") }}
+{{- $coordinationRedis := dict "host" "os.environ/REDIS_HOST" "port" "os.environ/REDIS_PORT" "password" "os.environ/REDIS_PASSWORD" }}
+{{- if .Values.redis.sentinel.enabled }}
+{{- $sentinelNode := list (include "litellm.redis.serviceName" .) (include "litellm.redis.port" . | int) }}
+{{- $coordinationRedis = dict "sentinel_nodes" (list $sentinelNode) "service_name" (default "mymaster" .Values.redis.sentinel.masterSet) "password" "os.environ/REDIS_PASSWORD" }}
+{{- end }}
+{{- $_ := set $generalSettings "coordination_redis" $coordinationRedis }}
+{{- $_ := set $config "general_settings" $generalSettings }}
+{{- end }}
+{{- end }}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "litellm.fullname" . }}-config
+data:
+  config.yaml: |
+{{ $config | toYaml | indent 6 }}
+{{- end }}
--- a/deploy/charts/litellm-helm/templates/deployment.yaml
+++ b/deploy/charts/litellm-helm/templates/deployment.yaml
--- a/deploy/charts/litellm-helm/templates/extra-resources.yaml
+++ b/deploy/charts/litellm-helm/templates/extra-resources.yaml
--- a/deploy/charts/litellm-helm/templates/hpa.yaml
+++ b/deploy/charts/litellm-helm/templates/hpa.yaml
--- a/deploy/charts/litellm-helm/templates/ingress.yaml
+++ b/deploy/charts/litellm-helm/templates/ingress.yaml
--- a/deploy/charts/litellm-helm/templates/keda.yaml
+++ b/deploy/charts/litellm-helm/templates/keda.yaml
--- a/deploy/charts/litellm-helm/templates/migrations-job.yaml
+++ b/deploy/charts/litellm-helm/templates/migrations-job.yaml
--- a/deploy/charts/litellm-helm/templates/poddisruptionbudget.yaml
+++ b/deploy/charts/litellm-helm/templates/poddisruptionbudget.yaml
--- a/deploy/charts/litellm-helm/templates/secret-dbcredentials.yaml
+++ b/deploy/charts/litellm-helm/templates/secret-dbcredentials.yaml
--- a/deploy/charts/litellm-helm/templates/secret-masterkey.yaml
+++ b/deploy/charts/litellm-helm/templates/secret-masterkey.yaml
--- a/deploy/charts/litellm-helm/templates/service.yaml
+++ b/deploy/charts/litellm-helm/templates/service.yaml
--- a/deploy/charts/litellm-helm/templates/serviceaccount.yaml
+++ b/deploy/charts/litellm-helm/templates/serviceaccount.yaml
--- a/deploy/charts/litellm-helm/templates/servicemonitor.yaml
+++ b/deploy/charts/litellm-helm/templates/servicemonitor.yaml
--- a/deploy/charts/litellm-helm/templates/tests/test-connection.yaml
+++ b/deploy/charts/litellm-helm/templates/tests/test-connection.yaml
--- a/deploy/charts/litellm-helm/templates/tests/test-env-vars.yaml
+++ b/deploy/charts/litellm-helm/templates/tests/test-env-vars.yaml
--- a/deploy/charts/litellm-helm/templates/tests/test-servicemonitor.yaml
+++ b/deploy/charts/litellm-helm/templates/tests/test-servicemonitor.yaml
--- a/helm/litellm-helm/tests/coordination_redis_tests.yaml
+++ b/helm/litellm-helm/tests/coordination_redis_tests.yaml
@ -0,0 +1,143 @@
+suite: test coordination redis
+templates:
+  - configmap-litellm.yaml
+  - deployment.yaml
+tests:
+  - it: should not render coordination_redis when redis is disabled
+    template: configmap-litellm.yaml
+    set:
+      redis.enabled: false
+    asserts:
+      - notMatchRegex:
+          path: data["config.yaml"]
+          pattern: coordination_redis
+
+  - it: should not emit redis env vars when redis is disabled
+    template: deployment.yaml
+    set:
+      redis.enabled: false
+    asserts:
+      - notContains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_HOST
+            value: RELEASE-NAME-redis-master
+          any: true
+
+  - it: should render coordination_redis pointing at the bundled redis when enabled
+    template: configmap-litellm.yaml
+    set:
+      redis.enabled: true
+    asserts:
+      - matchRegex:
+          path: data["config.yaml"]
+          pattern: "coordination_redis:\n    host: os.environ/REDIS_HOST\n    password: os.environ/REDIS_PASSWORD\n    port: os.environ/REDIS_PORT\n"
+      - matchRegex:
+          path: data["config.yaml"]
+          pattern: "master_key: os.environ/PROXY_MASTER_KEY"
+
+  - it: should emit redis env vars backing the coordination_redis os.environ refs
+    template: deployment.yaml
+    set:
+      redis.enabled: true
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_HOST
+            value: RELEASE-NAME-redis-master
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_PORT
+            value: "6379"
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_PASSWORD
+            valueFrom:
+              secretKeyRef:
+                name: RELEASE-NAME-redis
+                key: redis-password
+
+  - it: should not render coordination_redis when coordination is opted out
+    template: configmap-litellm.yaml
+    set:
+      redis.enabled: true
+      redis.coordination.enabled: false
+    asserts:
+      - notMatchRegex:
+          path: data["config.yaml"]
+          pattern: coordination_redis
+
+  - it: should keep emitting redis env vars when coordination is opted out
+    template: deployment.yaml
+    set:
+      redis.enabled: true
+      redis.coordination.enabled: false
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_HOST
+            value: RELEASE-NAME-redis-master
+
+  - it: should not clobber a user supplied coordination_redis block
+    template: configmap-litellm.yaml
+    set:
+      redis.enabled: true
+      proxy_config.general_settings.coordination_redis:
+        url: os.environ/COORDINATION_REDIS_URL
+    asserts:
+      - matchRegex:
+          path: data["config.yaml"]
+          pattern: "coordination_redis:\n    url: os.environ/COORDINATION_REDIS_URL\n"
+      - notMatchRegex:
+          path: data["config.yaml"]
+          pattern: "host: os.environ/REDIS_HOST"
+
+  - it: should render sentinel_nodes and service_name in sentinel mode
+    template: configmap-litellm.yaml
+    set:
+      redis.enabled: true
+      redis.architecture: replication
+      redis.sentinel.enabled: true
+    asserts:
+      # The sentinel Service the redis subchart renders is "<release>-redis", and a
+      # plain client cannot speak the sentinel protocol, so host/port must not appear
+      - matchRegex:
+          path: data["config.yaml"]
+          pattern: "coordination_redis:\n    password: os.environ/REDIS_PASSWORD\n    sentinel_nodes:\n    - - RELEASE-NAME-redis\n      - 26379\n    service_name: mymaster\n"
+      - notMatchRegex:
+          path: data["config.yaml"]
+          pattern: "host: os.environ/REDIS_HOST"
+
+  - it: should carry a custom sentinel masterSet into service_name
+    template: configmap-litellm.yaml
+    set:
+      redis.enabled: true
+      redis.architecture: replication
+      redis.sentinel.enabled: true
+      redis.sentinel.masterSet: litellm-master
+    asserts:
+      - matchRegex:
+          path: data["config.yaml"]
+          pattern: "service_name: litellm-master"
+
+  - it: should point REDIS_HOST at the sentinel service in sentinel mode
+    template: deployment.yaml
+    set:
+      redis.enabled: true
+      redis.architecture: replication
+      redis.sentinel.enabled: true
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_HOST
+            value: RELEASE-NAME-redis
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_PORT
+            value: "26379"
--- a/deploy/charts/litellm-helm/tests/deployment_command_args_labels_tests.yaml
+++ b/deploy/charts/litellm-helm/tests/deployment_command_args_labels_tests.yaml
--- a/deploy/charts/litellm-helm/tests/deployment_tests.yaml
+++ b/deploy/charts/litellm-helm/tests/deployment_tests.yaml
--- a/deploy/charts/litellm-helm/tests/hpa_tests.yaml
+++ b/deploy/charts/litellm-helm/tests/hpa_tests.yaml
--- a/deploy/charts/litellm-helm/tests/ingress_tests.yaml
+++ b/deploy/charts/litellm-helm/tests/ingress_tests.yaml
--- a/deploy/charts/litellm-helm/tests/masterkey-secret_tests.yaml
+++ b/deploy/charts/litellm-helm/tests/masterkey-secret_tests.yaml
--- a/deploy/charts/litellm-helm/tests/migrations-job_tests.yaml
+++ b/deploy/charts/litellm-helm/tests/migrations-job_tests.yaml
--- a/deploy/charts/litellm-helm/tests/pdb_tests.yaml
+++ b/deploy/charts/litellm-helm/tests/pdb_tests.yaml
--- a/deploy/charts/litellm-helm/tests/service_tests.yaml
+++ b/deploy/charts/litellm-helm/tests/service_tests.yaml
--- a/deploy/charts/litellm-helm/values.yaml
+++ b/deploy/charts/litellm-helm/values.yaml
@ -331,12 +331,28 @@ postgresql:
    # secretKeys:
    #   userPasswordKey: password

-# requires cache: true in config file
-# either enable this or pass a secret for REDIS_HOST, REDIS_PORT, REDIS_PASSWORD or REDIS_URL
-# with cache: true to use existing redis instance
+# Redis is the proxy's coordination store: cross-pod tpm/rpm rate limits, spend
+# tracking, and the pod lock manager. Enabling this deploys the bundled Redis
+# subchart, wires REDIS_HOST / REDIS_PORT / REDIS_PASSWORD into the proxy, and
+# renders a `general_settings.coordination_redis` block into the proxy config.
+#
+# To point at an existing Redis instead, leave `enabled: false` and pass a
+# secret for REDIS_HOST, REDIS_PORT, REDIS_PASSWORD or REDIS_URL; the proxy
+# falls back to those env vars for coordination. Set `cache: true` in the proxy
+# config only if you also want LLM response caching, which is independent of
+# coordination
+#
+# When `redis.sentinel.enabled` is set, the coordination block is rendered with
+# `sentinel_nodes` and `service_name` (from `redis.sentinel.masterSet`) instead
+# of host/port, because a plain Redis client cannot talk to the sentinel port
 redis:
  enabled: false
  architecture: standalone
+  coordination:
+    # Set to false to keep the bundled Redis for response caching only and leave
+    # `general_settings.coordination_redis` out of the rendered config. A
+    # `coordination_redis` block you define yourself in `proxy_config` always wins
+    enabled: true

 # Prisma migration job settings
 migrationJob:
--- a/helm/litellm/templates/_helpers.tpl
+++ b/helm/litellm/templates/_helpers.tpl
@ -213,6 +213,10 @@ harmless no-op for the Job and authoritative for the app pods.
 */}}
 - name: DISABLE_SCHEMA_UPDATE
  value: "true"
+{{/* These feed the proxy's coordination Redis (cross-pod rate limits, spend
+     tracking, pod lock manager) via its REDIS_* env fallback. An explicit
+     `general_settings.coordination_redis` block in proxy_config takes
+     precedence over anything emitted here. */}}
 {{- if $root.Values.redis.host }}
 - name: REDIS_HOST
  value: {{ $root.Values.redis.host | quote }}
@ -226,10 +230,11 @@ harmless no-op for the Job and authoritative for the app pods.
      key: {{ $root.Values.redis.passwordSecret.passwordKey | default "password" }}
 {{- end }}
 {{- if $root.Values.redis.cluster }}
-{{/* The proxy's Cache() reads REDIS_CLUSTER_NODES as JSON and constructs a
-     RedisClusterCache when it's set (litellm/caching/caching.py:169-192).
-     We seed with the single configured endpoint — the cluster client
-     discovers the remaining nodes from CLUSTER SLOTS at startup. */}}
+{{/* The proxy falls back to REDIS_CLUSTER_NODES (JSON) to build a cluster-mode
+     coordination client when `general_settings.coordination_redis` is absent
+     and no plain-Redis response cache is configured. We seed with the single
+     configured endpoint; the cluster client discovers the remaining nodes from
+     CLUSTER SLOTS at startup. */}}
 - name: REDIS_CLUSTER_NODES
  value: {{ printf "[{\"host\":%q,\"port\":%v}]" $root.Values.redis.host (int $root.Values.redis.port) | quote }}
 {{- end }}
--- a/helm/litellm/templates/backend/deployment.yaml
+++ b/helm/litellm/templates/backend/deployment.yaml
@ -45,11 +45,16 @@ spec:
              value: /app/config/config.yaml
            {{- end }}
          {{- include "litellm.envFrom" .Values.backend | nindent 10 }}
-          {{- if .Values.gateway.config.create }}
+          {{- if or .Values.gateway.config.create .Values.backend.volumeMounts }}
          volumeMounts:
+            {{- if .Values.gateway.config.create }}
            - name: gateway-config
              mountPath: /app/config/config.yaml
              subPath: config.yaml
+            {{- end }}
+            {{- with .Values.backend.volumeMounts }}
+            {{- toYaml . | nindent 12 }}
+            {{- end }}
          {{- end }}
          {{- with .Values.backend.livenessProbe }}
          livenessProbe:
@ -61,11 +66,16 @@ spec:
          {{- end }}
          resources:
            {{- toYaml .Values.backend.resources | nindent 12 }}
-      {{- if .Values.gateway.config.create }}
+      {{- if or .Values.gateway.config.create .Values.backend.volumes }}
      volumes:
+        {{- if .Values.gateway.config.create }}
        - name: gateway-config
          configMap:
            name: {{ include "litellm.gateway.fullname" . }}-config
+        {{- end }}
+        {{- with .Values.backend.volumes }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
      {{- end }}
      {{- with .Values.backend.nodeSelector }}
      nodeSelector:
--- a/helm/litellm/templates/gateway/deployment.yaml
+++ b/helm/litellm/templates/gateway/deployment.yaml
@ -47,11 +47,16 @@ spec:
              value: {{ .Values.gateway.numWorkers | quote }}
            {{- end }}
          {{- include "litellm.envFrom" .Values.gateway | nindent 10 }}
-          {{- if .Values.gateway.config.create }}
+          {{- if or .Values.gateway.config.create .Values.gateway.volumeMounts }}
          volumeMounts:
+            {{- if .Values.gateway.config.create }}
            - name: gateway-config
              mountPath: /app/config/config.yaml
              subPath: config.yaml
+            {{- end }}
+            {{- with .Values.gateway.volumeMounts }}
+            {{- toYaml . | nindent 12 }}
+            {{- end }}
          {{- end }}
          {{- with .Values.gateway.livenessProbe }}
          livenessProbe:
@ -63,11 +68,16 @@ spec:
          {{- end }}
          resources:
            {{- toYaml .Values.gateway.resources | nindent 12 }}
-      {{- if .Values.gateway.config.create }}
+      {{- if or .Values.gateway.config.create .Values.gateway.volumes }}
      volumes:
+        {{- if .Values.gateway.config.create }}
        - name: gateway-config
          configMap:
            name: {{ include "litellm.gateway.fullname" . }}-config
+        {{- end }}
+        {{- with .Values.gateway.volumes }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
      {{- end }}
      {{- with .Values.gateway.nodeSelector }}
      nodeSelector:
--- a/helm/litellm/templates/ui/deployment.yaml
+++ b/helm/litellm/templates/ui/deployment.yaml
@ -46,6 +46,10 @@ spec:
            {{- toYaml . | nindent 12 }}
            {{- end }}
          {{- include "litellm.envFrom" .Values.ui | nindent 10 }}
+          {{- with .Values.ui.volumeMounts }}
+          volumeMounts:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
          {{- with .Values.ui.livenessProbe }}
          livenessProbe:
            {{- toYaml . | nindent 12 }}
@ -56,6 +60,10 @@ spec:
          {{- end }}
          resources:
            {{- toYaml .Values.ui.resources | nindent 12 }}
+      {{- with .Values.ui.volumes }}
+      volumes:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
      {{- with .Values.ui.nodeSelector }}
      nodeSelector:
        {{- toYaml . | nindent 8 }}
--- a/helm/litellm/tests/deployment_volumes_tests.yaml
+++ b/helm/litellm/tests/deployment_volumes_tests.yaml
@ -0,0 +1,172 @@
+suite: test deployment volumes and volumeMounts
+templates:
+  - gateway/deployment.yaml
+  - gateway/configmap.yaml
+  - backend/deployment.yaml
+  - ui/deployment.yaml
+values:
+  - ./values/required.yaml
+tests:
+  - it: gateway renders only the config volume by default
+    template: gateway/deployment.yaml
+    asserts:
+      - equal:
+          path: spec.template.spec.volumes
+          value:
+            - name: gateway-config
+              configMap:
+                name: RELEASE-NAME-litellm-gateway-config
+      - equal:
+          path: spec.template.spec.containers[0].volumeMounts
+          value:
+            - name: gateway-config
+              mountPath: /app/config/config.yaml
+              subPath: config.yaml
+
+  - it: gateway merges user volumes and volumeMounts with the config volume
+    template: gateway/deployment.yaml
+    set:
+      gateway.volumes:
+        - name: custom-callbacks
+          configMap:
+            name: custom-callbacks
+      gateway.volumeMounts:
+        - name: custom-callbacks
+          mountPath: /app/custom_callbacks.py
+          subPath: custom_callbacks.py
+    asserts:
+      - equal:
+          path: spec.template.spec.volumes[0].name
+          value: gateway-config
+      - equal:
+          path: spec.template.spec.volumes[1]
+          value:
+            name: custom-callbacks
+            configMap:
+              name: custom-callbacks
+      - equal:
+          path: spec.template.spec.containers[0].volumeMounts[0].name
+          value: gateway-config
+      - equal:
+          path: spec.template.spec.containers[0].volumeMounts[1]
+          value:
+            name: custom-callbacks
+            mountPath: /app/custom_callbacks.py
+            subPath: custom_callbacks.py
+
+  - it: gateway renders user volumes even when config creation is disabled
+    template: gateway/deployment.yaml
+    set:
+      gateway.config.create: false
+      gateway.volumes:
+        - name: certs
+          secret:
+            secretName: tls-certs
+      gateway.volumeMounts:
+        - name: certs
+          mountPath: /etc/certs
+          readOnly: true
+    asserts:
+      - equal:
+          path: spec.template.spec.volumes
+          value:
+            - name: certs
+              secret:
+                secretName: tls-certs
+      - equal:
+          path: spec.template.spec.containers[0].volumeMounts
+          value:
+            - name: certs
+              mountPath: /etc/certs
+              readOnly: true
+
+  - it: gateway omits volumes when config creation is disabled and no user volumes are set
+    template: gateway/deployment.yaml
+    set:
+      gateway.config.create: false
+    asserts:
+      - isNull:
+          path: spec.template.spec.volumes
+      - isNull:
+          path: spec.template.spec.containers[0].volumeMounts
+
+  - it: backend merges user volumes and volumeMounts with the shared config volume
+    template: backend/deployment.yaml
+    set:
+      backend.volumes:
+        - name: sso-handler
+          configMap:
+            name: sso-handler
+      backend.volumeMounts:
+        - name: sso-handler
+          mountPath: /app/custom_sso.py
+          subPath: custom_sso.py
+    asserts:
+      - equal:
+          path: spec.template.spec.volumes[0].name
+          value: gateway-config
+      - equal:
+          path: spec.template.spec.volumes[1]
+          value:
+            name: sso-handler
+            configMap:
+              name: sso-handler
+      - equal:
+          path: spec.template.spec.containers[0].volumeMounts[1]
+          value:
+            name: sso-handler
+            mountPath: /app/custom_sso.py
+            subPath: custom_sso.py
+
+  - it: backend renders user volumes even when config creation is disabled
+    template: backend/deployment.yaml
+    set:
+      gateway.config.create: false
+      backend.volumes:
+        - name: data
+          emptyDir: {}
+      backend.volumeMounts:
+        - name: data
+          mountPath: /data
+    asserts:
+      - equal:
+          path: spec.template.spec.volumes
+          value:
+            - name: data
+              emptyDir: {}
+      - equal:
+          path: spec.template.spec.containers[0].volumeMounts
+          value:
+            - name: data
+              mountPath: /data
+
+  - it: ui renders no volumes by default
+    template: ui/deployment.yaml
+    asserts:
+      - isNull:
+          path: spec.template.spec.volumes
+      - isNull:
+          path: spec.template.spec.containers[0].volumeMounts
+
+  - it: ui renders user volumes and volumeMounts
+    template: ui/deployment.yaml
+    set:
+      ui.volumes:
+        - name: nginx-config
+          configMap:
+            name: custom-nginx
+      ui.volumeMounts:
+        - name: nginx-config
+          mountPath: /etc/nginx/conf.d
+    asserts:
+      - equal:
+          path: spec.template.spec.volumes
+          value:
+            - name: nginx-config
+              configMap:
+                name: custom-nginx
+      - equal:
+          path: spec.template.spec.containers[0].volumeMounts
+          value:
+            - name: nginx-config
+              mountPath: /etc/nginx/conf.d
--- a/helm/litellm/tests/redis_env_tests.yaml
+++ b/helm/litellm/tests/redis_env_tests.yaml
@ -0,0 +1,109 @@
+suite: test redis coordination env vars
+templates:
+  - gateway/deployment.yaml
+  - gateway/configmap.yaml
+  - backend/deployment.yaml
+values:
+  - ./values/required.yaml
+tests:
+  - it: gateway omits redis env vars when no host is configured
+    template: gateway/deployment.yaml
+    asserts:
+      - notContains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_HOST
+            value: redis.example.com
+          any: true
+      - notContains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_CLUSTER_NODES
+          any: true
+
+  - it: gateway emits host, port and password when redis is configured
+    template: gateway/deployment.yaml
+    set:
+      redis.host: redis.example.com
+      redis.port: 6380
+      redis.passwordSecret.name: redis-secret
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_HOST
+            value: redis.example.com
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_PORT
+            value: "6380"
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_PASSWORD
+            valueFrom:
+              secretKeyRef:
+                name: redis-secret
+                key: password
+
+  - it: backend emits the same redis env vars so both pods coordinate on one redis
+    template: backend/deployment.yaml
+    set:
+      redis.host: redis.example.com
+      redis.passwordSecret.name: redis-secret
+      redis.passwordSecret.passwordKey: redis-password
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_HOST
+            value: redis.example.com
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_PASSWORD
+            valueFrom:
+              secretKeyRef:
+                name: redis-secret
+                key: redis-password
+
+  - it: gateway omits REDIS_PASSWORD for an auth-less redis
+    template: gateway/deployment.yaml
+    set:
+      redis.host: redis.example.com
+    asserts:
+      - notContains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_PASSWORD
+          any: true
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_HOST
+            value: redis.example.com
+
+  - it: gateway seeds REDIS_CLUSTER_NODES from host and port in cluster mode
+    template: gateway/deployment.yaml
+    set:
+      redis.host: redis.example.com
+      redis.port: 6380
+      redis.cluster: true
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_CLUSTER_NODES
+            value: '[{"host":"redis.example.com","port":6380}]'
+
+  - it: gateway omits REDIS_CLUSTER_NODES when cluster mode is off
+    template: gateway/deployment.yaml
+    set:
+      redis.host: redis.example.com
+    asserts:
+      - notContains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: REDIS_CLUSTER_NODES
+          any: true
--- a/helm/litellm/tests/values/required.yaml
+++ b/helm/litellm/tests/values/required.yaml
@ -0,0 +1,4 @@
+database:
+  writer:
+    host: postgres.example.com
+    dbname: litellm
--- a/helm/litellm/values.yaml
+++ b/helm/litellm/values.yaml
@ -100,7 +100,18 @@ database:
      usernameKey: username
      passwordKey: password

-# Optional Redis (caching, rate limiting). Leave host empty to disable.
+# Optional Redis. Leave host empty to disable.
+#
+# This is the proxy's coordination store: cross-pod tpm/rpm rate limits, spend
+# tracking, and the pod lock manager. The chart emits REDIS_HOST / REDIS_PORT /
+# REDIS_PASSWORD, which the proxy picks up through its coordination Redis env
+# fallback. Response caching is separate and off unless you enable it in
+# `proxy_config.litellm_settings.cache`.
+#
+# For full control, define `general_settings.coordination_redis` in
+# `proxy_config` (host/port/password/username/url/ssl/startup_nodes/
+# sentinel_nodes/sentinel_password/service_name, each accepting os.environ/VAR
+# refs). An explicit block overrides these env vars.
 #
 # Set `cluster: true` for Redis Cluster mode (e.g. AWS ElastiCache Cluster,
 # self-hosted Redis Cluster). The chart emits REDIS_CLUSTER_NODES from
@ -124,6 +135,11 @@ gateway:
  extraEnv: [] # Add extra environment variables to the gateway
  envConfigMaps: [] # Add extra environment variables to the gateway from config maps
  envSecrets: [] # Add extra environment variables to the gateway from secrets
+  # Additional volumes on the gateway Deployment (e.g. a ConfigMap holding
+  # custom callback / SSO handler code, mounted next to the proxy config).
+  volumes: []
+  # Additional volumeMounts on the gateway container.
+  volumeMounts: []
  config:
    create: true
    proxy_config: {}
@ -167,6 +183,10 @@ backend:
  extraEnv: []
  envConfigMaps: []
  envSecrets: []
+  # Additional volumes on the backend Deployment.
+  volumes: []
+  # Additional volumeMounts on the backend container.
+  volumeMounts: []
  image:
    repository: ghcr.io/berriai/litellm-backend
    tag: ""
@ -206,6 +226,10 @@ ui:
  extraEnv: []
  envConfigMaps: []
  envSecrets: []
+  # Additional volumes on the ui Deployment.
+  volumes: []
+  # Additional volumeMounts on the ui container.
+  volumeMounts: []
  image:
    repository: ghcr.io/berriai/litellm-ui
    tag: ""
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260626120000_add_mcp_tool_search_enabled/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260626120000_add_mcp_tool_search_enabled/migration.sql
@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "LiteLLM_ObjectPermissionTable" ADD COLUMN "mcp_tool_search_enabled" BOOLEAN;
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260629000000_add_max_concurrent_requests_to_mcp_server_table/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260629000000_add_max_concurrent_requests_to_mcp_server_table/migration.sql
@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "LiteLLM_MCPServerTable" ADD COLUMN     "max_concurrent_requests" INTEGER;
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260630120000_add_token_exchange_to_mcp_servers/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260630120000_add_token_exchange_to_mcp_servers/migration.sql
@ -0,0 +1,8 @@
+-- Timestamp sorts before some already-applied migrations; this is safe: the
+-- runner is `prisma migrate deploy`, which applies every pending migration
+-- regardless of name order (utils.py has an informational check for exactly
+-- this), and IF NOT EXISTS keeps a re-apply idempotent.
+-- AlterTable
+ALTER TABLE "LiteLLM_MCPServerTable" ADD COLUMN IF NOT EXISTS "token_exchange_endpoint" TEXT;
+ALTER TABLE "LiteLLM_MCPServerTable" ADD COLUMN IF NOT EXISTS "audience" TEXT;
+ALTER TABLE "LiteLLM_MCPServerTable" ADD COLUMN IF NOT EXISTS "subject_token_type" TEXT;
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260630190000_add_budget_fallbacks_to_litellm_verification_token/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260630190000_add_budget_fallbacks_to_litellm_verification_token/migration.sql
@ -0,0 +1,5 @@
+-- AlterTable
+ALTER TABLE "LiteLLM_VerificationToken" ADD COLUMN IF NOT EXISTS "budget_fallbacks" JSONB NOT NULL DEFAULT '{}';
+
+-- AlterTable
+ALTER TABLE "LiteLLM_DeletedVerificationToken" ADD COLUMN IF NOT EXISTS "budget_fallbacks" JSONB NOT NULL DEFAULT '{}';
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260703120000_add_token_exchange_profile_to_mcp_servers/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260703120000_add_token_exchange_profile_to_mcp_servers/migration.sql
@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "LiteLLM_MCPServerTable" ADD COLUMN IF NOT EXISTS "token_exchange_profile" TEXT;
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260710000000_add_dcr_bridge_to_mcp_server_table/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260710000000_add_dcr_bridge_to_mcp_server_table/migration.sql
@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "LiteLLM_MCPServerTable" ADD COLUMN     "dcr_bridge" BOOLEAN;
--- a/litellm-proxy-extras/litellm_proxy_extras/schema.prisma
+++ b/litellm-proxy-extras/litellm_proxy_extras/schema.prisma
@ -279,6 +279,7 @@ model LiteLLM_ObjectPermissionTable {
  blocked_tools         String[]       @default([]) // Tool names blocked for any key/team/user with this permission
  mcp_toolsets          String[]       @default([]) // Toolset IDs granted to this key/team/user
  search_tools          String[]       @default([]) // search_tool_name values this key/team/user may call
+  mcp_tool_search_enabled Boolean?
  teams                 LiteLLM_TeamTable[]
  projects              LiteLLM_ProjectTable[]
  verification_tokens   LiteLLM_VerificationToken[]
@ -328,15 +329,23 @@ model LiteLLM_MCPServerTable {
  token_url          String?
  registration_url   String?
  oauth2_flow        String?
+  token_exchange_endpoint String?
+  // Named for the RFC 8693 "audience" token-exchange request parameter (that flow only).
+  // RFC 8707 resource indicators are a separate concept, named "resource" in the v2 egress types.
+  audience           String?
+  subject_token_type String?
+  token_exchange_profile String?
  allow_all_keys Boolean @default(false)
  available_on_public_internet Boolean @default(true)
  delegate_auth_to_upstream Boolean @default(false)
  oauth_passthrough Boolean @default(false)
+  dcr_bridge Boolean?
  is_byok               Boolean  @default(false)
  byok_description      String[] @default([])
  byok_api_key_help_url String?
  source_url            String?
  timeout               Float?
+  max_concurrent_requests Int?
  // BYOM submission lifecycle
  approval_status  String?   @default("active")
  submitted_by     String?
@ -417,6 +426,7 @@ model LiteLLM_VerificationToken {
    access_group_ids String[] @default([])
    model_spend      Json @default("{}")
    model_max_budget Json @default("{}")
+    budget_fallbacks Json @default("{}")
    budget_id String?
    organization_id String?
    object_permission_id String?
@ -510,6 +520,7 @@ model LiteLLM_DeletedVerificationToken {
    access_group_ids String[] @default([])
    model_spend             Json     @default("{}")
    model_max_budget        Json     @default("{}")
+    budget_fallbacks        Json     @default("{}")
    router_settings  Json? @default("{}")
    budget_id               String?
    organization_id         String?
--- a/litellm-proxy-extras/pyproject.toml
+++ b/litellm-proxy-extras/pyproject.toml
@ -1,6 +1,6 @@
 [project]
 name = "litellm-proxy-extras"
-version = "0.4.74"
+version = "0.4.76"
 description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package."
 readme = "README.md"
 requires-python = ">=3.9"
@ -26,7 +26,7 @@ required-version = ">=0.10.9"
 module-root = ""

 [tool.commitizen]
-version = "0.4.74"
+version = "0.4.76"
 version_files = [
    "pyproject.toml:^version",
    "../pyproject.toml:litellm-proxy-extras==",
--- a/litellm/init.py
+++ b/litellm/init.py
@ -263,6 +263,8 @@ azure_key: Optional[str] = None
 anthropic_key: Optional[str] = None
 replicate_key: Optional[str] = None
 bytez_key: Optional[str] = None
+gdc_key: Optional[str] = None
+gdc_api_base: Optional[str] = None
 cohere_key: Optional[str] = None
 infinity_key: Optional[str] = None
 clarifai_key: Optional[str] = None
@ -377,6 +379,7 @@ budget_duration: Optional[str] = (
    None  # proxy only - resets budget after fixed duration. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").
 )
 default_soft_budget: float = DEFAULT_SOFT_BUDGET  # by default all litellm proxy keys have a soft budget of 50.0
+budget_exceeded_throttle_percentage: Optional[float] = None
 forward_traceparent_to_llm_provider: bool = False


@ -586,6 +589,7 @@ gemini_models: Set = set()
 xai_models: Set = set()
 zai_models: Set = set()
 deepseek_models: Set = set()
+tencent_models: Set = set()
 runwayml_models: Set = set()
 azure_ai_models: Set = set()
 jina_ai_models: Set = set()
@ -799,6 +803,8 @@ def add_known_models(model_cost_map: Optional[Dict] = None):
            fal_ai_models.add(key)
        elif value.get("litellm_provider") == "deepseek":
            deepseek_models.add(key)
+        elif value.get("litellm_provider") == "tencent":
+            tencent_models.add(key)
        elif value.get("litellm_provider") == "runwayml":
            runwayml_models.add(key)
        elif value.get("litellm_provider") == "meta_llama":
@ -1091,6 +1097,7 @@ models_by_provider: dict = {
    "zai": zai_models,
    "fal_ai": fal_ai_models,
    "deepseek": deepseek_models,
+    "tencent": tencent_models,
    "runwayml": runwayml_models,
    "mistral": mistral_chat_models,
    "azure_ai": azure_ai_models,
@ -1787,6 +1794,7 @@ if TYPE_CHECKING:
    from .llms.nvidia_nim.embed import (
        NvidiaNimEmbeddingConfig as NvidiaNimEmbeddingConfig,
    )
+    from .llms.gdc.chat.transformation import GDCGeminiConfig as GDCGeminiConfig

    # Type stubs for lazy-loaded config instances
    openaiOSeriesConfig: OpenAIOSeriesConfig
@ -1801,6 +1809,9 @@ if TYPE_CHECKING:
    from .llms.deepseek.chat.transformation import (
        DeepSeekChatConfig as _DeepSeekChatConfig,
    )
+    from .llms.tencent.chat.transformation import (
+        TencentChatConfig as _TencentChatConfig,
+    )
    from .llms.sap.chat.transformation import (
        GenAIHubOrchestrationConfig as _GenAIHubOrchestrationConfig,
    )
@ -1843,6 +1854,7 @@ if TYPE_CHECKING:
    # Type stubs for lazy-loaded config classes (to help mypy understand types)
    VLLMConfig: Type[_VLLMConfig]
    DeepSeekChatConfig: Type[_DeepSeekChatConfig]
+    TencentChatConfig: Type[_TencentChatConfig]
    GenAIHubOrchestrationConfig: Type[_GenAIHubOrchestrationConfig]
    GenAIHubEmbeddingConfig: Type[_GenAIHubEmbeddingConfig]
    AzureOpenAIO1Config: Type[_AzureOpenAIO1Config]
--- a/litellm/_lazy_imports_registry.py
+++ b/litellm/_lazy_imports_registry.py
@ -284,6 +284,7 @@ LLM_CONFIG_NAMES = (
    "LiteLLMProxyChatConfig",
    "VLLMConfig",
    "DeepSeekChatConfig",
+    "TencentChatConfig",
    "LMStudioChatConfig",
    "LmStudioEmbeddingConfig",
    "NscaleConfig",
@ -323,6 +324,7 @@ LLM_CONFIG_NAMES = (
    "SnowflakeEmbeddingConfig",
    "AmazonNovaChatConfig",
    "SonioxAudioTranscriptionConfig",
+    "GDCGeminiConfig",
 )

 # Types that support lazy loading via _lazy_import_types
@ -1095,6 +1097,7 @@ _LLM_CONFIGS_IMPORT_MAP = {
    ),
    "VLLMConfig": (".llms.vllm.completion.transformation", "VLLMConfig"),
    "DeepSeekChatConfig": (".llms.deepseek.chat.transformation", "DeepSeekChatConfig"),
+    "TencentChatConfig": (".llms.tencent.chat.transformation", "TencentChatConfig"),
    "LMStudioChatConfig": (".llms.lm_studio.chat.transformation", "LMStudioChatConfig"),
    "LmStudioEmbeddingConfig": (
        ".llms.lm_studio.embed.transformation",
@ -1157,6 +1160,10 @@ _LLM_CONFIGS_IMPORT_MAP = {
        ".llms.dashscope.chat.transformation",
        "DashScopeChatConfig",
    ),
+    "GDCGeminiConfig": (
+        ".llms.gdc.chat.transformation",
+        "GDCGeminiConfig",
+    ),
    "ModelScopeChatConfig": (
        ".llms.modelscope.chat.transformation",
        "ModelScopeChatConfig",
--- a/litellm/_redis.py
+++ b/litellm/_redis.py
@ -23,7 +23,11 @@ from litellm._redis_credential_provider import (
    GCPIAMCredentialProvider,
    _generate_gcp_iam_access_token,
 )
-from litellm.constants import REDIS_CONNECTION_POOL_TIMEOUT, REDIS_SOCKET_TIMEOUT
+from litellm.constants import (
+    REDIS_CLUSTER_HEALTH_CHECK_INTERVAL,
+    REDIS_CONNECTION_POOL_TIMEOUT,
+    REDIS_SOCKET_TIMEOUT,
+)
 from litellm.litellm_core_utils.sensitive_data_masker import SensitiveDataMasker

 from ._logging import verbose_logger
@ -102,6 +106,8 @@ def _get_redis_cluster_kwargs(client=None):
        "max_connections",
        "socket_timeout",
        "socket_connect_timeout",
+        "health_check_interval",
+        "socket_keepalive",
    }

    return available_args
@ -319,8 +325,19 @@ def _get_redis_client_logic(**env_overrides):
            value = get_secret(v)  # type: ignore
            env_overrides[k] = value

+    environment_kwargs = _redis_kwargs_from_environment()
+
+    # An explicitly configured connection target outranks REDIS_URL from the
+    # environment. Without this, the url branch below strips the caller's
+    # host/port/password and silently connects to whatever REDIS_URL names.
+    caller_named_a_target = any(
+        env_overrides.get(key) is not None for key in ("host", "startup_nodes", "sentinel_nodes")
+    )
+    if caller_named_a_target and env_overrides.get("url") is None:
+        environment_kwargs.pop("url", None)
+
    redis_kwargs = {
-        **_redis_kwargs_from_environment(),
+        **environment_kwargs,
        **env_overrides,
    }

@ -579,6 +596,13 @@ def get_redis_async_client(
            new_startup_nodes.append(ClusterNode(**item))
        cluster_kwargs.pop("startup_nodes", None)

+        # Default to a periodic health check + TCP keepalive so a connection silently dropped
+        # by a cluster restart (e.g. ElastiCache Serverless maintenance) is revalidated and
+        # reconnected before reuse instead of stalling in re-initialization; an explicit value
+        # from config still wins.
+        cluster_kwargs.setdefault("health_check_interval", REDIS_CLUSTER_HEALTH_CHECK_INTERVAL)
+        cluster_kwargs.setdefault("socket_keepalive", True)
+
        # Create async RedisCluster with IAM token as password if available
        cluster_client = async_redis.RedisCluster(
            startup_nodes=new_startup_nodes,
@ -665,9 +689,8 @@ def get_redis_connection_pool(
        redis_kwargs["credential_provider"] = GCPIAMCredentialProvider(redis_connect_func._gcp_service_account)

    connection_class = async_redis.Connection
-    if "ssl" in redis_kwargs:
+    if redis_kwargs.pop("ssl", False):
        connection_class = async_redis.SSLConnection
-        redis_kwargs.pop("ssl", None)
        redis_kwargs["connection_class"] = connection_class
    return async_redis.BlockingConnectionPool(timeout=REDIS_CONNECTION_POOL_TIMEOUT, **redis_kwargs)

--- a/Show more
+++ b/Show more