ci(e2e): run PR-changed e2e tests against a stage-mirror stack

This commit is contained in:
mateo-berri 2026-07-28 11:37:16 -07:00
parent b930e2fc2b
commit 19c5ad760c
5 changed files with 463 additions and 0 deletions

17
.github/e2e-stack/down.sh vendored Executable file
View file

@ -0,0 +1,17 @@
#!/usr/bin/env bash
set -uo pipefail
STACK_DIR="${E2E_STACK_DIR:-${RUNNER_TEMP:-/tmp}/litellm-e2e-stack}"
for pid_file in "${STACK_DIR}"/pids/*.pid; do
[[ -f "${pid_file}" ]] || continue
pkill -TERM -P "$(cat "${pid_file}")" 2>/dev/null
kill -TERM "$(cat "${pid_file}")" 2>/dev/null
rm -f "${pid_file}"
done
for container in e2e-nginx e2e-valkey e2e-jaeger e2e-postgres; do
docker rm -f "${container}" >/dev/null 2>&1
done
exit 0

28
.github/e2e-stack/secrets_to_env.py vendored Normal file
View file

@ -0,0 +1,28 @@
import sys
from pathlib import Path
from pydantic import TypeAdapter
secrets_adapter: TypeAdapter[dict[str, str]] = TypeAdapter(dict[str, str])
def main() -> int:
env_path = Path(sys.argv[1])
secrets = secrets_adapter.validate_json(sys.stdin.read())
unwritable = tuple(
key for key, value in secrets.items() if "'" in value or "\n" in value or "\r" in value
)
if unwritable:
_ = sys.stderr.write(f"values contain characters unsafe for both bash and dotenv: {', '.join(unwritable)}\n")
return 1
lines = tuple(f"{key}='{value}'" for key, value in secrets.items() if value)
with env_path.open("a") as handle:
_ = handle.write("\n".join(lines) + "\n")
for value in secrets.values():
if value:
_ = sys.stdout.write(f"::add-mask::{value}\n")
return 0
if __name__ == "__main__":
sys.exit(main())

195
.github/e2e-stack/up.sh vendored Executable file
View file

@ -0,0 +1,195 @@
#!/usr/bin/env bash
set -euo pipefail
REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
STACK_DIR="${E2E_STACK_DIR:-${RUNNER_TEMP:-/tmp}/litellm-e2e-stack}"
CERTS_DIR="${STACK_DIR}/certs"
LOGS_DIR="${STACK_DIR}/logs"
PIDS_DIR="${STACK_DIR}/pids"
POSTGRES_IMAGE="${E2E_POSTGRES_IMAGE:-postgres:16.6}"
VALKEY_IMAGE="${E2E_VALKEY_IMAGE:-valkey/valkey:8.1}"
JAEGER_IMAGE="${E2E_JAEGER_IMAGE:-jaegertracing/jaeger:2.10.0}"
NGINX_IMAGE="${E2E_NGINX_IMAGE:-nginx:1.29-alpine}"
LB_PORT="${E2E_LB_PORT:-4000}"
GATEWAY_PORT_1="${E2E_GATEWAY_PORT_1:-4010}"
GATEWAY_PORT_2="${E2E_GATEWAY_PORT_2:-4011}"
BACKEND_PORT="${E2E_BACKEND_PORT:-4001}"
REDIS_PORT="${E2E_REDIS_PORT:-6379}"
DATABASE_HOST="${E2E_DATABASE_HOST:-127.0.0.1}"
DATABASE_PORT="${E2E_DATABASE_PORT:-5432}"
DATABASE_USER="${E2E_DATABASE_USER:-litellm}"
DATABASE_PASSWORD="${E2E_DATABASE_PASSWORD:-dbpassword9090}"
DATABASE_NAME="${E2E_DATABASE_NAME:-litellm}"
JAEGER_OTLP_PORT="${E2E_JAEGER_OTLP_PORT:-4318}"
JAEGER_QUERY_PORT="${E2E_JAEGER_QUERY_PORT:-16686}"
MASTER_KEY="${LITELLM_MASTER_KEY:-sk-e2e-$(openssl rand -hex 16)}"
mkdir -p "${CERTS_DIR}" "${LOGS_DIR}" "${PIDS_DIR}"
log() { printf 'e2e-stack: %s\n' "$*"; }
port_open() { (exec 3<>"/dev/tcp/127.0.0.1/$1") 2>/dev/null; }
wait_for() {
local label="$1" check="$2" deadline=$((SECONDS + ${3:-120}))
until eval "${check}"; do
if ((SECONDS >= deadline)); then
log "timed out waiting for ${label}"
tail -n 60 "${LOGS_DIR}"/*.log 2>/dev/null || true
exit 1
fi
sleep 2
done
log "${label} is up"
}
if [[ -f "${REPO_ROOT}/tests/e2e/.env" ]]; then
set -a
source "${REPO_ROOT}/tests/e2e/.env"
set +a
fi
if ! port_open "${DATABASE_PORT}"; then
docker run -d --name e2e-postgres -p "${DATABASE_PORT}:5432" \
-e "POSTGRES_USER=${DATABASE_USER}" -e "POSTGRES_PASSWORD=${DATABASE_PASSWORD}" -e "POSTGRES_DB=${DATABASE_NAME}" \
"${POSTGRES_IMAGE}" >/dev/null
fi
wait_for "postgres" "port_open ${DATABASE_PORT}"
if ! port_open "${JAEGER_QUERY_PORT}"; then
docker run -d --name e2e-jaeger -p "${JAEGER_OTLP_PORT}:4318" -p "${JAEGER_QUERY_PORT}:16686" \
"${JAEGER_IMAGE}" >/dev/null
fi
wait_for "jaeger" "curl -fs http://127.0.0.1:${JAEGER_QUERY_PORT}/api/services >/dev/null"
openssl genrsa -out "${CERTS_DIR}/ca.key" 2048 2>/dev/null
openssl req -x509 -new -nodes -key "${CERTS_DIR}/ca.key" -sha256 -days 7 \
-subj "/CN=litellm-e2e-ca" -out "${CERTS_DIR}/ca.crt" 2>/dev/null
openssl genrsa -out "${CERTS_DIR}/server.key" 2048 2>/dev/null
openssl req -new -key "${CERTS_DIR}/server.key" -subj "/CN=localhost" -out "${CERTS_DIR}/server.csr" 2>/dev/null
openssl x509 -req -in "${CERTS_DIR}/server.csr" -CA "${CERTS_DIR}/ca.crt" -CAkey "${CERTS_DIR}/ca.key" \
-CAcreateserial -days 7 -sha256 \
-extfile <(printf 'subjectAltName=DNS:localhost,IP:127.0.0.1') \
-out "${CERTS_DIR}/server.crt" 2>/dev/null
chmod 644 "${CERTS_DIR}"/*.key "${CERTS_DIR}"/*.crt
CERTIFI_BUNDLE="$(cd "${REPO_ROOT}" && uv run --no-sync python -c 'import certifi; print(certifi.where())')"
cat "${CERTIFI_BUNDLE}" "${CERTS_DIR}/ca.crt" > "${CERTS_DIR}/ca-bundle.pem"
docker rm -f e2e-valkey >/dev/null 2>&1 || true
docker run -d --name e2e-valkey -p "${REDIS_PORT}:${REDIS_PORT}" -v "${CERTS_DIR}:/certs:ro" \
"${VALKEY_IMAGE}" valkey-server \
--cluster-enabled yes --port 0 --tls-port "${REDIS_PORT}" \
--tls-cert-file /certs/server.crt --tls-key-file /certs/server.key --tls-ca-cert-file /certs/ca.crt \
--tls-auth-clients no --cluster-announce-ip 127.0.0.1 >/dev/null
VALKEY_CLI="docker exec e2e-valkey valkey-cli --tls --cacert /certs/ca.crt -h 127.0.0.1 -p ${REDIS_PORT}"
wait_for "valkey" "${VALKEY_CLI} ping 2>/dev/null | grep -q PONG"
${VALKEY_CLI} cluster addslotsrange 0 16383 >/dev/null
wait_for "valkey cluster" "${VALKEY_CLI} cluster info 2>/dev/null | grep -q cluster_state:ok"
CONFIG_PATH="${REPO_ROOT}/tests/e2e/gateway/litellm-config.yml"
if [[ "${REDIS_PORT}" != "6379" ]]; then
CONFIG_PATH="${STACK_DIR}/litellm-config.yml"
sed "s/port: 6379/port: ${REDIS_PORT}/" "${REPO_ROOT}/tests/e2e/gateway/litellm-config.yml" > "${CONFIG_PATH}"
fi
SERVER_ENV=(
"LITELLM_MASTER_KEY=${MASTER_KEY}"
"DATABASE_HOST=${DATABASE_HOST}"
"DATABASE_PORT=${DATABASE_PORT}"
"DATABASE_USER=${DATABASE_USER}"
"DATABASE_PASSWORD=${DATABASE_PASSWORD}"
"DATABASE_NAME=${DATABASE_NAME}"
"DISABLE_SCHEMA_UPDATE=true"
"REDIS_HOST=127.0.0.1"
"REDIS_PORT=${REDIS_PORT}"
"REDIS_CLUSTER_NODES=[{\"host\":\"127.0.0.1\",\"port\":${REDIS_PORT}}]"
"CONFIG_FILE_PATH=${CONFIG_PATH}"
"STORE_MODEL_IN_DB=True"
"OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf"
"OTEL_EXPORTER_OTLP_ENDPOINT=http://127.0.0.1:${JAEGER_OTLP_PORT}"
"SSL_CERT_FILE=${CERTS_DIR}/ca-bundle.pem"
"PYTHONPATH=${REPO_ROOT}"
)
if [[ -n "${VERTEXAI_CREDENTIALS:-}" ]]; then
printf '%s' "${VERTEXAI_CREDENTIALS}" > "${STACK_DIR}/vertex-adc.json"
SERVER_ENV+=("GOOGLE_APPLICATION_CREDENTIALS=${STACK_DIR}/vertex-adc.json")
fi
cd "${REPO_ROOT}"
log "running migrations"
env "${SERVER_ENV[@]}" uv run --no-sync python migrations/run.py >"${LOGS_DIR}/migrations.log" 2>&1
start_server() {
local name="$1"; shift
env "${SERVER_ENV[@]}" "$@" >"${LOGS_DIR}/${name}.log" 2>&1 &
echo $! > "${PIDS_DIR}/${name}.pid"
}
start_server backend uv run --no-sync uvicorn backend.main:app --host 0.0.0.0 --port "${BACKEND_PORT}"
start_server gateway-1 uv run --no-sync uvicorn gateway.main:app --workers 1 --host 0.0.0.0 --port "${GATEWAY_PORT_1}"
start_server gateway-2 uv run --no-sync uvicorn gateway.main:app --workers 1 --host 0.0.0.0 --port "${GATEWAY_PORT_2}"
if [[ "$(uname)" == "Linux" ]]; then
NGINX_UPSTREAM_HOST=127.0.0.1
NGINX_DOCKER_ARGS=(--network host)
else
NGINX_UPSTREAM_HOST=host.docker.internal
NGINX_DOCKER_ARGS=(-p "${LB_PORT}:${LB_PORT}")
fi
cat > "${STACK_DIR}/nginx.conf" <<EOF
events {}
http {
map \$http_upgrade \$connection_upgrade {
default upgrade;
'' close;
}
upstream litellm_gateways {
server ${NGINX_UPSTREAM_HOST}:${GATEWAY_PORT_1};
server ${NGINX_UPSTREAM_HOST}:${GATEWAY_PORT_2};
}
server {
listen ${LB_PORT};
client_max_body_size 100m;
location / {
proxy_pass http://litellm_gateways;
proxy_http_version 1.1;
proxy_set_header Host \$host;
proxy_set_header X-Forwarded-For \$proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto \$scheme;
proxy_set_header Upgrade \$http_upgrade;
proxy_set_header Connection \$connection_upgrade;
proxy_buffering off;
proxy_read_timeout 600s;
proxy_send_timeout 600s;
}
}
}
EOF
docker rm -f e2e-nginx >/dev/null 2>&1 || true
docker run -d --name e2e-nginx "${NGINX_DOCKER_ARGS[@]}" \
-v "${STACK_DIR}/nginx.conf:/etc/nginx/nginx.conf:ro" "${NGINX_IMAGE}" >/dev/null
wait_for "backend" "curl -fs http://127.0.0.1:${BACKEND_PORT}/health/liveliness >/dev/null" 300
wait_for "gateway-1" "curl -fs http://127.0.0.1:${GATEWAY_PORT_1}/health/liveliness >/dev/null" 300
wait_for "gateway-2" "curl -fs http://127.0.0.1:${GATEWAY_PORT_2}/health/liveliness >/dev/null" 300
wait_for "load balancer" "curl -fs http://127.0.0.1:${LB_PORT}/health/liveliness >/dev/null" 60
cat > "${STACK_DIR}/stack.env" <<EOF
LITELLM_PROXY_URL=http://127.0.0.1:${LB_PORT}
LITELLM_CONTROL_PLANE_URL=http://127.0.0.1:${BACKEND_PORT}
LITELLM_MASTER_KEY=${MASTER_KEY}
REDIS_HOST=127.0.0.1
REDIS_PORT=${REDIS_PORT}
E2E_OTEL_QUERY_URL=http://127.0.0.1:${JAEGER_QUERY_PORT}
SSL_CERT_FILE=${CERTS_DIR}/ca-bundle.pem
DATABASE_URL=postgresql://${DATABASE_USER}:${DATABASE_PASSWORD}@${DATABASE_HOST}:${DATABASE_PORT}/${DATABASE_NAME}
EOF
log "stack is up; pytest env written to ${STACK_DIR}/stack.env"

160
.github/workflows/test-e2e-changed.yml vendored Normal file
View file

@ -0,0 +1,160 @@
name: e2e-changed-tests
on:
pull_request:
paths:
- "tests/e2e/**"
concurrency:
group: e2e-changed-${{ github.event.pull_request.number }}
cancel-in-progress: true
permissions:
contents: read
jobs:
detect:
name: Detect changed e2e tests
runs-on: ubuntu-latest
timeout-minutes: 5
outputs:
tests: ${{ steps.changed.outputs.tests }}
any: ${{ steps.changed.outputs.any }}
steps:
- name: List added or modified test files
id: changed
env:
GH_TOKEN: ${{ github.token }}
REPO: ${{ github.repository }}
PR_NUMBER: ${{ github.event.pull_request.number }}
run: |
tests="$(gh api "repos/${REPO}/pulls/${PR_NUMBER}/files" --paginate \
--jq '.[] | select(.status != "removed") | .filename' \
| grep -E '^tests/e2e/([A-Za-z0-9_.-]+/)*test_[A-Za-z0-9_.-]+\.py$' \
| grep -v '^tests/e2e/ui/' | sort -u | tr '\n' ' ' | sed 's/ $//')" || true
echo "tests=${tests}" >> "${GITHUB_OUTPUT}"
if [ -n "${tests}" ]; then
echo "any=true" >> "${GITHUB_OUTPUT}"
echo "changed e2e tests: ${tests}"
else
echo "any=false" >> "${GITHUB_OUTPUT}"
echo "no changed e2e test files"
fi
run:
name: Run changed e2e tests against the stage-mirror stack
needs: detect
if: needs.detect.outputs.any == 'true' && github.event.pull_request.head.repo.full_name == github.repository
runs-on: ubuntu-latest
timeout-minutes: 60
permissions:
contents: read
id-token: write
services:
postgres:
image: postgres:16.6
env:
POSTGRES_USER: litellm
POSTGRES_PASSWORD: dbpassword9090
POSTGRES_DB: litellm
ports:
- 5432:5432
options: >-
--health-cmd "pg_isready -U litellm"
--health-interval 5s
--health-timeout 5s
--health-retries 10
jaeger:
image: jaegertracing/jaeger:2.10.0
ports:
- 4318:4318
- 16686:16686
steps:
- name: Checkout
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: "3.13"
- name: Set up uv
uses: ./.github/actions/setup-uv-with-retries
with:
version: "0.10.9"
- name: Install dependencies
run: |
.github/scripts/uv_sync_with_retries.sh --frozen \
--extra proxy --extra proxy-runtime --extra extra_proxy \
--extra semantic-router --extra bedrock-realtime \
--group ci --group e2e-dev
uv pip install redis==7.4.1 prometheus-client "pipecat-ai[openai]==1.4.0"
- 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: Install Playwright chromium
run: uv run --no-sync playwright install --with-deps chromium
- name: Validate configuration
env:
ROLE: ${{ vars.E2E_AWS_ROLE_TO_ASSUME }}
run: test -n "${ROLE}" || { echo "::error::Set repo variable E2E_AWS_ROLE_TO_ASSUME to an OIDC role with read access to the e2e secrets"; exit 1; }
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@e7f100cf4c008499ea8adda475de1042d6975c7b # v6.2.0
with:
role-to-assume: ${{ vars.E2E_AWS_ROLE_TO_ASSUME }}
aws-region: us-east-1
role-session-name: litellm-e2e-changed-${{ github.run_id }}
- name: Fetch provider credentials from AWS Secrets Manager
run: |
aws secretsmanager get-secret-value --secret-id berrie-litellm-stage-provider-keys \
--query SecretString --output text \
| uv run --no-sync python .github/e2e-stack/secrets_to_env.py tests/e2e/.env
aws secretsmanager get-secret-value --secret-id litellm-license \
--query SecretString --output text \
| jq -R -s '{"LITELLM_LICENSE": rtrimstr("\n")}' \
| uv run --no-sync python .github/e2e-stack/secrets_to_env.py tests/e2e/.env
- name: Boot the stage-mirror stack
run: bash .github/e2e-stack/up.sh
- name: Export stack environment
run: |
master_key="$(grep '^LITELLM_MASTER_KEY=' "${RUNNER_TEMP}/litellm-e2e-stack/stack.env" | cut -d= -f2-)"
echo "::add-mask::${master_key}"
cat "${RUNNER_TEMP}/litellm-e2e-stack/stack.env" >> "${GITHUB_ENV}"
- name: Run the changed tests
env:
TESTS: ${{ needs.detect.outputs.tests }}
run: |
read -r -a test_files <<< "${TESTS}"
set +e
uv run --no-sync pytest "${test_files[@]}" -v -rA --tb=short -p no:cacheprovider
status=$?
set -e
if [ "${status}" = "5" ]; then
echo "changed files collected no runnable tests"
exit 0
fi
exit "${status}"
- name: Show stack logs on failure
if: failure()
run: tail -n 200 "${RUNNER_TEMP}/litellm-e2e-stack/logs"/*.log
- name: Upload stack logs
if: failure()
uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
with:
name: e2e-stack-logs
path: ${{ runner.temp }}/litellm-e2e-stack/logs/
retention-days: 7

View file

@ -0,0 +1,63 @@
general_settings:
store_prompts_in_spend_logs: true
database_connection_pool_limit: 10
forward_client_headers_to_llm_api: false
maximum_spend_logs_retention_period: "60d"
maximum_spend_logs_cleanup_cron: "0 1 * * *"
proxy_budget_rescheduler_min_time: 15
proxy_budget_rescheduler_max_time: 20
litellm_settings:
drop_params: true
default_redis_ttl: 20
request_timeout: 600
num_retries: 3
json_logs: true
store_audit_logs: true
cache: true
cache_params:
type: redis
host: 127.0.0.1
port: 6379
redis_startup_nodes:
- host: 127.0.0.1
port: 6379
ssl: true
callbacks: ["arize_phoenix", "datadog", "smtp_email", "prometheus", "otel"]
require_auth_for_metrics_endpoint: false
router_settings:
routing_strategy: simple-shuffle
num_retries: 3
allowed_fails: 5
cooldown_time: 30
model_list:
- model_name: gpt-5.5
litellm_params:
model: openai/gpt-5.5
api_key: os.environ/OPENAI_API_KEY
- model_name: claude-haiku-4-5
litellm_params:
model: anthropic/claude-haiku-4-5
api_key: os.environ/ANTHROPIC_API_KEY
- model_name: gemini-2.5-flash-vertex
litellm_params:
model: vertex_ai/gemini-2.5-flash
vertex_project: os.environ/VERTEXAI_PROJECT
vertex_location: us-central1
vertex_credentials: os.environ/VERTEXAI_CREDENTIALS
- model_name: gemini-2.5-flash
litellm_params:
model: gemini/gemini-2.5-flash
api_key: os.environ/GEMINI_API_KEY
- model_name: gemini-2.5-flash
litellm_params:
model: gemini/gemini-2.5-flash
api_key: os.environ/GEMINI_API_KEY
mcp_servers:
devin:
url: "https://mcp.devin.ai/mcp"
auth_type: api_key
auth_value: os.environ/DEVIN_API_KEY