Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_batch_enqueued_token_limit

Author: mateo-berri

.circleci/scripts/classify_changes.sh

@@ -1,15 +1,17 @@
 #!/usr/bin/env bash
 set -uo pipefail
 
-category="${1:?usage: classify_changes.sh <backend|client>}"
+category="${1:?usage: classify_changes.sh <backend|client|ui>}"
 
 has_client=false
 has_backend=false
+has_ci=false
 while IFS= read -r file || [ -n "$file" ]; do
   [ -n "$file" ] || continue
   case "$file" in
     ui/* | tests/e2e/ui/*) has_client=true ;;
     docs/* | *.md | *.mdx) : ;;
+    .github/* | .circleci/*) has_ci=true; has_backend=true ;;
     *) has_backend=true ;;
   esac
 done
@@ -21,6 +23,9 @@ case "$category" in
   client)
     { [ "$has_client" = true ] || [ "$has_backend" = true ]; } && echo run || echo skip
     ;;
+  ui)
+    { [ "$has_client" = true ] || [ "$has_ci" = true ]; } && echo run || echo skip
+    ;;
   *)
     echo run
     ;;

.github/CODEOWNERS

@@ -1,3 +1,5 @@
 /ui/ @yuneng-jiang @ryan-crabbe-berri
 /litellm/proxy/_experimental/out/ @yuneng-jiang @ryan-crabbe-berri
 /ui/litellm-dashboard/src/lib/http/schema.d.ts
+/model_prices_and_context_window.json @mateo-berri
+/litellm/model_prices_and_context_window_backup.json @mateo-berri

.github/actions/detect-backend-changes/action.yml

@@ -0,0 +1,41 @@
+name: "Detect relevant changes"
+description: >-
+  Classify the pull request's changed files with .circleci/scripts/classify_changes.sh
+  and expose decision=run|skip for one category. backend means anything outside ui/,
+  docs/ and markdown; ui means the dashboard sources alone. decision=skip lets callers
+  short-circuit expensive steps while the job still completes successfully and satisfies
+  its required status check, which a paths: filter cannot do because a workflow that
+  never starts never reports. The file list comes from the pull request itself rather
+  than from a git diff, because the checked-out merge ref is recomputed as the base
+  branch advances and would otherwise attribute the base branch's own commits to the
+  pull request. The decision defaults to run for any non pull_request event or whenever
+  the changed set cannot be resolved, so jobs are never skipped when the classification
+  is uncertain.
+
+inputs:
+  category:
+    description: "Which classification to apply: backend, client or ui"
+    required: false
+    default: backend
+  github-token:
+    description: "Token used to list the pull request's files; needs pull-requests: read"
+    required: false
+    default: ${{ github.token }}
+
+outputs:
+  decision:
+    description: "run when category-relevant files changed, otherwise skip"
+    value: ${{ steps.classify.outputs.decision }}
+
+runs:
+  using: composite
+  steps:
+    - id: classify
+      shell: bash
+      env:
+        GH_TOKEN: ${{ inputs.github-token }}
+        CATEGORY: ${{ inputs.category }}
+        REPO: ${{ github.repository }}
+        PR_NUMBER: ${{ github.event.pull_request.number }}
+        CHANGED_FILE_COUNT: ${{ github.event.pull_request.changed_files }}
+      run: bash "${GITHUB_ACTION_PATH}/../../scripts/detect_changes.sh"

.github/actions/detect-changes/action.yml

@@ -53,7 +53,8 @@ After: the same request comes back with real token counts, so the dashboard show
 **Please complete all items before asking a LiteLLM maintainer to review your PR**
 
 - [ ] I have added meaningful tests
-- [ ] My PR passes all CI/CD checks (e.g., lint, format, unit tests)
+- [ ] The handful of test files covering my change pass locally, e.g. `uv run pytest tests/test_litellm/<your_test_file>.py -v`. Leave the suites (`make test-unit-*`, `make test-unit`) to CI: it finishes in ~15 minutes where a laptop takes an hour or more
+- [ ] My PR passes all required CI/CD checks (e.g., lint, schema.d.ts sync check, etc.)
 - [ ] My PR's scope is as isolated as possible; it only solves 1 specific problem
 - [ ] 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)
 

.github/pull_request_template.md

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+set -uo pipefail
+
+readonly API_FILE_CEILING=3000
+readonly CATEGORY="${CATEGORY:-backend}"
+
+decide() {
+  echo "detect-changes[${CATEGORY}]: decision=$1"
+  [ -z "${GITHUB_OUTPUT:-}" ] || echo "decision=$1" >>"${GITHUB_OUTPUT}"
+  exit 0
+}
+
+run_full() {
+  echo "detect-changes[${CATEGORY}]: $1; running job"
+  decide run
+}
+
+here="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+classify="${here}/../../.circleci/scripts/classify_changes.sh"
+
+[ -n "${PR_NUMBER:-}" ] || run_full "not a pull_request event"
+[ -n "${REPO:-}" ] || run_full "no repository in the environment"
+
+case "${CHANGED_FILE_COUNT:-}" in
+'' | *[!0-9]*) run_full "the event payload carries no changed_files count" ;;
+esac
+[ "${CHANGED_FILE_COUNT}" -le "${API_FILE_CEILING}" ] ||
+  run_full "PR #${PR_NUMBER} changes ${CHANGED_FILE_COUNT} files, past the ${API_FILE_CEILING}-file listing ceiling"
+
+changed="$(gh api "repos/${REPO}/pulls/${PR_NUMBER}/files" --paginate --jq '.[].filename')" ||
+  run_full "could not list the files on PR #${PR_NUMBER}"
+[ -n "${changed}" ] || run_full "the API listed no files on PR #${PR_NUMBER}"
+
+echo "detect-changes[${CATEGORY}]: files changed by PR #${PR_NUMBER}:"
+printf '%s\n' "${changed}" | sed 's/^/  /'
+
+decision="$(printf '%s\n' "${changed}" | bash "${classify}" "${CATEGORY}")" ||
+  run_full "classify_changes.sh failed"
+case "${decision}" in
+run | skip) decide "${decision}" ;;
+*) run_full "classify_changes.sh printed an unexpected decision: ${decision}" ;;
+esac

.github/scripts/detect_changes.sh

@@ -60,6 +60,9 @@ jobs:
     name: Run tests
     runs-on: ubuntu-latest
     timeout-minutes: ${{ inputs.job-timeout-minutes }}
+    permissions:
+      contents: read
+      pull-requests: read
     outputs:
       decision: ${{ steps.changes.outputs.decision }}
 
@@ -69,24 +72,27 @@ jobs:
         with:
           persist-credentials: false
 
-      - name: Detect backend-relevant changes
+      - name: Detect relevant changes
         id: changes
         timeout-minutes: 2
-        uses: ./.github/actions/detect-backend-changes
+        uses: ./.github/actions/detect-changes
 
       - name: Set up Python
+        if: steps.changes.outputs.decision != 'skip'
         timeout-minutes: 3
         uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: "3.12"
 
       - name: Set up uv
+        if: steps.changes.outputs.decision != 'skip'
         timeout-minutes: 3
         uses: ./.github/actions/setup-uv-with-retries
         with:
           version: "0.10.9"
 
       - name: Cache uv dependencies
+        if: steps.changes.outputs.decision != 'skip'
         timeout-minutes: 5
         uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:

.github/workflows/_test-unit-base.yml

@@ -24,6 +24,7 @@ jobs:
     # re-running basedpyright over the merge-base tree.
     permissions:
       contents: read
+      pull-requests: read
       actions: read
 
     steps:
@@ -37,7 +38,12 @@ jobs:
           clean: true
           persist-credentials: false
 
+      - name: Detect relevant changes
+        id: changes
+        uses: ./.github/actions/detect-changes
+
       - name: Fetch gate base (merge-base with target branch)
+        if: steps.changes.outputs.decision != 'skip'
         env:
           GH_TOKEN: ${{ github.token }}
           BASE_SHA: ${{ github.event.pull_request.base.sha }}
@@ -50,39 +56,47 @@ jobs:
           echo "GATE_BASE_SHA=$MERGE_BASE" >> "$GITHUB_ENV"
 
       - name: Set up Python
+        if: steps.changes.outputs.decision != 'skip'
         uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: "3.12"
 
       - name: Set up uv
+        if: steps.changes.outputs.decision != 'skip'
         uses: ./.github/actions/setup-uv-with-retries
         with:
           version: "0.10.9"
 
       - name: Clean Python cache
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           find . -type d -name "__pycache__" -exec rm -rf {} + || true
           find . -name "*.pyc" -delete || true
 
       - name: Check uv.lock is up to date
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           uv lock --check || (echo "❌ uv.lock is out of sync with pyproject.toml. Run 'uv lock' locally and commit the result." && exit 1)
 
       - name: Install dependencies
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           uv sync --frozen --group proxy-dev --group e2e-dev
 
       - name: Cache Prisma binaries
+        if: steps.changes.outputs.decision != 'skip'
         uses: ./.github/actions/cache-prisma-binaries
 
       # basedpyright resolves Prisma's generated client (litellm/proxy/schema.prisma)
       # only after `prisma generate` writes prisma/client.py et al. Without this the
       # DB wrappers typed against the generated client would degrade to Unknown.
       - name: Generate Prisma client
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 
       - name: Check ruff format
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           git diff --name-only --diff-filter=ACMR "$GATE_BASE_SHA" HEAD -- 'litellm/**/*.py' | grep -v '^litellm/enterprise/' > "$RUNNER_TEMP/ruff_format_files.txt" || true
           if [ ! -s "$RUNNER_TEMP/ruff_format_files.txt" ]; then
@@ -92,6 +106,7 @@ jobs:
           xargs uv run --no-sync ruff format --check --exclude '/enterprise/' < "$RUNNER_TEMP/ruff_format_files.txt"
 
       - name: Debug - Check file state
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           echo "Current branch:"
           git branch --show-current
@@ -101,30 +116,36 @@ jobs:
           head -50 litellm/litellm_core_utils/custom_logger_registry.py | tail -10
 
       - name: Run Ruff linting
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           cd litellm
           uv run --no-sync ruff check .
           cd ..
 
       - name: Check strict-rule budget (delta vs base)
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           uv run --no-sync python scripts/ruff_strict_gate.py --base "$GATE_BASE_SHA"
 
       - name: Check type-discipline budget (mutable collections / casts / type guards / kwargs / unexplained suppressions, delta vs base)
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           uv run --no-sync python scripts/type_discipline_gate.py --base "$GATE_BASE_SHA"
 
       - name: Print OpenAI version
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           uv run --no-sync python -c "import openai; print(f'OpenAI version: {openai.__version__}')"
 
       - name: Check basedpyright budget (delta vs base)
+        if: steps.changes.outputs.decision != 'skip'
         env:
           GH_TOKEN: ${{ github.token }}
         run: |
           uv run --no-sync python scripts/type_check_gate.py --base "$GATE_BASE_SHA"
 
       - name: Check tests/e2e basedpyright (zero errors)
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           if git diff --name-only --diff-filter=ACMRD "$GATE_BASE_SHA" HEAD -- 'tests/e2e/**/*.py' | grep -q .; then
             uv run --no-sync basedpyright tests/e2e
@@ -133,12 +154,14 @@ jobs:
           fi
 
       - name: Check for circular imports
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           cd litellm
           uv run --no-sync python ../tests/documentation_tests/test_circular_imports.py
           cd ..
 
       - name: Check import safety
+        if: steps.changes.outputs.decision != 'skip'
         run: |
           uv run --no-sync python -c "from litellm import *" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)
 

.github/workflows/test-linting.yml

@@ -1,6 +1,7 @@
 name: UI Build Check
 permissions:
   contents: read
+  pull-requests: read
 
 on:
   pull_request:
@@ -28,15 +29,24 @@ jobs:
         with:
           persist-credentials: false
 
+      - name: Detect relevant changes
+        id: changes
+        uses: ./.github/actions/detect-changes
+        with:
+          category: ui
+
       - name: Setup Node.js
+        if: steps.changes.outputs.decision != 'skip'
         uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0.0
         with:
           node-version-file: ui/litellm-dashboard/.nvmrc
           cache: "npm"
           cache-dependency-path: ui/litellm-dashboard/package-lock.json
 
       - name: Install dependencies
+        if: steps.changes.outputs.decision != 'skip'
         run: npm ci
 
       - name: Build
+        if: steps.changes.outputs.decision != 'skip'
         run: npm run build