mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-30 06:43:27 +00:00
ci: run the integration groups on GitHub Actions (#48985)
* test: add a manually dispatched integration trial on larger runners Runs the providers, database and management integration groups on 16-core GitHub-hosted runners with Postgres and Redis as service containers, to measure wall time and how far each group scales with more workers run_integration.sh now keeps a preset INTEGRATION_WORKERS, takes the service container names from the environment, and seeds test order from the GitHub run when there is no CircleCI one * test: run the integration trial on push to this branch * test: give integration trial workers a local redis-server * test: run the providers trial on a 64-core runner with 32 workers The 16-core run reached 53% of providers in 45 minutes with 16 workers, which points at CPU. Postgres gets max_connections=1000 and a 1 GB shm because one server now backs 32 worker proxies, where each CircleCI machine backs 4 * test: run every integration group in the trial on sized runners * test: add a scan that refuses to upload integration results holding the license * test: drop the member-name pass the archive byte scan already covers * test: use a secret whose base64 and base64url encodings differ * ci: run integration groups on run-ci pull requests and scheduled main runs * ci: scope the integration license to a protected environment
This commit is contained in:
parent
ffcc4f7a70
commit
62b8ee78de
6 changed files with 460 additions and 12 deletions
|
|
@ -1,14 +1,14 @@
|
|||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
if [ "${GITHUB_ACTIONS:-}" = true ]; then
|
||||
echo "Integration contracts are owned by CircleCI" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
suite="${1:?integration suite required}"
|
||||
mode="${2:-standard}"
|
||||
side="${3:-}"
|
||||
requested_workers="${INTEGRATION_WORKERS:-}"
|
||||
license_env=()
|
||||
if [ -n "${LITELLM_LICENSE:-}" ]; then
|
||||
license_env=("LITELLM_LICENSE=$LITELLM_LICENSE")
|
||||
fi
|
||||
if [ "$mode" = replica ]; then
|
||||
results="test-results/integration-${suite}-replica"
|
||||
elif [ "$mode" = parity ]; then
|
||||
|
|
@ -84,7 +84,7 @@ if [ "$suite" = browser ]; then
|
|||
export LITELLM_UI_PATH="$PWD/ui/litellm-dashboard/out"
|
||||
test -f "$LITELLM_UI_PATH/index.html"
|
||||
fi
|
||||
export INTEGRATION_SEED="$(.venv/bin/python -c 'import hashlib,os; print(int(hashlib.sha256((os.environ.get("CIRCLE_SHA1", "local") + os.environ.get("CIRCLE_WORKFLOW_ID", "local")).encode()).hexdigest()[:8],16))')"
|
||||
export INTEGRATION_SEED="$(.venv/bin/python -c 'import hashlib,os; print(int(hashlib.sha256(((os.environ.get("CIRCLE_SHA1") or os.environ.get("GITHUB_SHA") or "local") + (os.environ.get("CIRCLE_WORKFLOW_ID") or os.environ.get("GITHUB_RUN_ID") or "local")).encode()).hexdigest()[:8],16))')"
|
||||
export INTEGRATION_ORDER_SEED="$INTEGRATION_SEED"
|
||||
|
||||
uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma > "$results/prisma-generate.log" 2>&1
|
||||
|
|
@ -107,7 +107,7 @@ sudo iptables -N integration_only
|
|||
guard_created=true
|
||||
sudo iptables -A integration_only -o lo -j ACCEPT
|
||||
sudo iptables -A integration_only -m conntrack --ctstate ESTABLISHED,RELATED -j ACCEPT
|
||||
for service in postgres-db redis-cache; do
|
||||
for service in "${INTEGRATION_POSTGRES_CONTAINER:-postgres-db}" "${INTEGRATION_REDIS_CONTAINER:-redis-cache}"; do
|
||||
address="$(docker inspect --format '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$service")"
|
||||
sudo iptables -A integration_only -d "$address" -j ACCEPT
|
||||
done
|
||||
|
|
@ -145,6 +145,9 @@ fi
|
|||
if [ "$suite" = mcp ]; then
|
||||
export INTEGRATION_WORKERS=2 INTEGRATION_COVERAGE=1
|
||||
fi
|
||||
if [ -n "$requested_workers" ]; then
|
||||
export INTEGRATION_WORKERS="$requested_workers"
|
||||
fi
|
||||
isolated_workers=false
|
||||
if [ "${INTEGRATION_WORKERS:-1}" -gt 1 ]; then
|
||||
isolated_workers=true
|
||||
|
|
@ -185,7 +188,7 @@ start_proxy() {
|
|||
"${database_env[@]}" REDIS_HOST="$REDIS_HOST" REDIS_PORT="$REDIS_PORT" \
|
||||
INTEGRATION_UPSTREAM_URL="$INTEGRATION_UPSTREAM_URL" \
|
||||
LITELLM_MASTER_KEY="$LITELLM_MASTER_KEY" LITELLM_SALT_KEY="$LITELLM_SALT_KEY" LITELLM_UI_PATH="$LITELLM_UI_PATH" PROXY_BASE_URL="http://127.0.0.1:$port" \
|
||||
LITELLM_LICENSE="${LITELLM_LICENSE:-}" \
|
||||
"${license_env[@]}" \
|
||||
LITELLM_MODE=PRODUCTION STORE_MODEL_IN_DB=True LITELLM_ENABLE_MCP_STDIO=true "${cost_map_env[@]}" \
|
||||
AWS_EC2_METADATA_DISABLED=true DO_NOT_TRACK=1 COVERAGE_FILE="$coverage_data" \
|
||||
"${proxy_command[@]}" --config tests/integration/proxy_config.yaml \
|
||||
|
|
@ -257,7 +260,7 @@ env -i PATH="$PATH" HOME="$HOME" PYTHONPATH="$PYTHONPATH" \
|
|||
"${shared_services[@]}" "${worker_coverage[@]}" \
|
||||
INTEGRATION_WORKERS="${INTEGRATION_WORKERS:-1}" \
|
||||
LITELLM_MODE=PRODUCTION \
|
||||
LITELLM_LICENSE="${LITELLM_LICENSE:-}" \
|
||||
"${license_env[@]}" \
|
||||
INTEGRATION_SEED="$INTEGRATION_SEED" \
|
||||
INTEGRATION_ORDER_SEED="$INTEGRATION_ORDER_SEED" \
|
||||
INTEGRATION_CASE_SHARDS="${CIRCLE_NODE_TOTAL:-1}" INTEGRATION_CASE_SHARD_INDEX="${CIRCLE_NODE_INDEX:-0}" \
|
||||
|
|
|
|||
119
.github/scripts/assert_secret_absent.py
vendored
Normal file
119
.github/scripts/assert_secret_absent.py
vendored
Normal file
|
|
@ -0,0 +1,119 @@
|
|||
import base64
|
||||
import io
|
||||
import os
|
||||
import sys
|
||||
import urllib.parse
|
||||
import zipfile
|
||||
from collections.abc import Callable, Iterator, Mapping
|
||||
from dataclasses import dataclass
|
||||
from functools import reduce
|
||||
from itertools import chain
|
||||
from pathlib import Path
|
||||
from types import MappingProxyType
|
||||
from typing import Final, TextIO
|
||||
|
||||
SECRET_VARIABLE: Final = "SCANNED_SECRET"
|
||||
MIN_ENCODED_LENGTH: Final = 12
|
||||
MAX_ARCHIVE_DEPTH: Final = 3
|
||||
MASK: Final = "***"
|
||||
|
||||
Forms = tuple[tuple[str, str], ...]
|
||||
|
||||
|
||||
@dataclass(frozen=True, slots=True)
|
||||
class Hit:
|
||||
location: str
|
||||
form: str
|
||||
|
||||
|
||||
def _aligned_encodings(raw: bytes, name: str, encode: Callable[[bytes], bytes]) -> Iterator[tuple[str, str]]:
|
||||
for offset in range(3):
|
||||
chunk: Final = raw[offset:]
|
||||
yield f"{name} offset {offset}", encode(chunk[: len(chunk) - len(chunk) % 3]).decode()
|
||||
|
||||
|
||||
def secret_forms(secret: str) -> Forms:
|
||||
encoded: Final = (
|
||||
("url-encoded", urllib.parse.quote(secret, safe="")),
|
||||
*_aligned_encodings(secret.encode(), "base64", base64.b64encode),
|
||||
*_aligned_encodings(secret.encode(), "base64url", base64.urlsafe_b64encode),
|
||||
)
|
||||
by_value: Final = MappingProxyType(
|
||||
{value: name for name, value in encoded if value != secret and len(value) >= MIN_ENCODED_LENGTH}
|
||||
)
|
||||
return (("raw", secret), *((name, value) for value, name in by_value.items()))
|
||||
|
||||
|
||||
def mask(text: str, forms: Forms) -> str:
|
||||
return reduce(lambda masked, form: masked.replace(form[1], MASK), forms, text)
|
||||
|
||||
|
||||
def _name_hits(location: str, name: str, forms: Forms) -> Iterator[Hit]:
|
||||
for form, value in forms:
|
||||
if value in name:
|
||||
yield Hit(mask(location, forms), f"{form} in name")
|
||||
|
||||
|
||||
def _content_hits(location: str, data: bytes, forms: Forms, depth: int) -> Iterator[Hit]:
|
||||
for form, value in forms:
|
||||
if value.encode() in data:
|
||||
yield Hit(mask(location, forms), form)
|
||||
if depth >= MAX_ARCHIVE_DEPTH or not zipfile.is_zipfile(io.BytesIO(data)):
|
||||
return
|
||||
with zipfile.ZipFile(io.BytesIO(data)) as archive:
|
||||
for member in archive.infolist():
|
||||
if member.is_dir():
|
||||
continue
|
||||
yield from _content_hits(f"{location}!{member.filename}", archive.read(member), forms, depth + 1)
|
||||
|
||||
|
||||
def _walk(root: Path) -> Iterator[tuple[Path, bool]]:
|
||||
for directory, subdirectories, files in os.walk(root):
|
||||
yield from ((Path(directory, name), True) for name in subdirectories if Path(directory, name).is_symlink())
|
||||
yield from ((Path(directory, name), False) for name in files)
|
||||
|
||||
|
||||
def _path_hits(root: Path, path: Path, linked_directory: bool, forms: Forms) -> Iterator[Hit]:
|
||||
location: Final = str(path.relative_to(root))
|
||||
if linked_directory:
|
||||
yield Hit(mask(location, forms), "directory symlink, not scanned")
|
||||
return
|
||||
yield from _name_hits(location, location, forms)
|
||||
yield from _content_hits(location, path.read_bytes(), forms, 0)
|
||||
|
||||
|
||||
def scan(root: Path, secret: str) -> tuple[int, tuple[Hit, ...]]:
|
||||
forms: Final = secret_forms(secret)
|
||||
entries: Final = tuple(_walk(root))
|
||||
hits: Final = tuple(chain.from_iterable(_path_hits(root, path, linked, forms) for path, linked in entries))
|
||||
return len(entries), hits
|
||||
|
||||
|
||||
def main(argv: tuple[str, ...], environ: Mapping[str, str], out: TextIO) -> int:
|
||||
if len(argv) != 1:
|
||||
print(f"usage: assert_secret_absent.py <directory>, with the secret in ${SECRET_VARIABLE}", file=out)
|
||||
return 2
|
||||
secret: Final = environ.get(SECRET_VARIABLE, "")
|
||||
root: Final = Path(argv[0])
|
||||
if not secret:
|
||||
print(f"{SECRET_VARIABLE} is empty, nothing to scan for", file=out)
|
||||
return 0
|
||||
if not root.is_dir():
|
||||
print(f"{root} is not a directory, nothing to scan", file=out)
|
||||
return 0
|
||||
try:
|
||||
scanned, hits = scan(root, secret)
|
||||
except Exception as error:
|
||||
print(f"scan failed with {type(error).__name__}, treating the results as unsafe", file=out)
|
||||
return 1
|
||||
for hit in hits:
|
||||
print(f"secret found: {hit.location} ({hit.form})", file=out)
|
||||
if hits:
|
||||
print(f"{len(hits)} copies of the secret under {root}, refusing to upload", file=out)
|
||||
return 1
|
||||
print(f"no copy of the secret in {scanned} files under {root}", file=out)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main(tuple(sys.argv[1:]), os.environ, sys.stdout))
|
||||
199
.github/workflows/test-integration.yml
vendored
Normal file
199
.github/workflows/test-integration.yml
vendored
Normal file
|
|
@ -0,0 +1,199 @@
|
|||
name: integration
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
types: [labeled]
|
||||
schedule:
|
||||
- cron: "5 8-20/3 * * 1-6"
|
||||
timezone: America/Los_Angeles
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
suite:
|
||||
description: Integration group to run
|
||||
type: choice
|
||||
options:
|
||||
- all
|
||||
- providers
|
||||
- extensions
|
||||
- accounting
|
||||
- management
|
||||
- management-replica
|
||||
- database
|
||||
- database-replica
|
||||
- mcp
|
||||
- security
|
||||
- cost
|
||||
- sdk
|
||||
- browser
|
||||
default: all
|
||||
workers:
|
||||
description: Workers per group, blank keeps each group's default
|
||||
type: string
|
||||
default: ""
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-${{ github.event.label.name }}-${{ inputs.suite }}-${{ inputs.workers }}
|
||||
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
|
||||
|
||||
jobs:
|
||||
integration:
|
||||
name: integration ${{ matrix.suite }}
|
||||
if: github.event_name != 'pull_request' || github.event.label.name == 'run-ci'
|
||||
environment: integration-license
|
||||
runs-on: ${{ fromJSON('{"providers":"ubuntu-latest-64-cores","extensions":"ubuntu-latest-64-cores","accounting":"ubuntu-latest-32-cores","management":"ubuntu-latest-32-cores","management-replica":"ubuntu-latest-32-cores"}')[matrix.suite] || 'ubuntu-latest-16-cores' }}
|
||||
timeout-minutes: 60
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
suite: ${{ fromJSON((inputs.suite || 'all') == 'all' && '["providers","extensions","accounting","management","management-replica","database","database-replica","mcp","security","cost","sdk","browser"]' || format('["{0}"]', inputs.suite)) }}
|
||||
env:
|
||||
UV_PYTHON: "3.12"
|
||||
INTEGRATION_WORKERS: ${{ inputs.workers || fromJSON('{"providers":"32","extensions":"32","accounting":"16","management":"16","management-replica":"16","cost":"16","mcp":"8","security":"8","database":"4","database-replica":"4"}')[matrix.suite] || '' }}
|
||||
services:
|
||||
postgres:
|
||||
image: postgres:16@sha256:e17e86066e5ef83e0952a9347f5c792b7ece00972e2aa787a6986f471b3dd3d5
|
||||
command: -c max_connections=1000 -c shared_preload_libraries=pg_stat_statements -c pg_stat_statements.track=all -c pg_stat_statements.max=20000
|
||||
env:
|
||||
POSTGRES_USER: postgres
|
||||
POSTGRES_PASSWORD: postgres
|
||||
POSTGRES_DB: circle_test
|
||||
ports:
|
||||
- 5432:5432
|
||||
options: >-
|
||||
--shm-size 1g
|
||||
--health-cmd "pg_isready -U postgres"
|
||||
--health-interval 5s
|
||||
--health-timeout 5s
|
||||
--health-retries 20
|
||||
redis:
|
||||
image: redis:7-alpine@sha256:7aec734b2bb298a1d769fd8729f13b8514a41bf90fcdd1f38ec52267fbaa8ee6
|
||||
ports:
|
||||
- 6379:6379
|
||||
options: >-
|
||||
--health-cmd "redis-cli ping"
|
||||
--health-interval 5s
|
||||
--health-timeout 5s
|
||||
--health-retries 20
|
||||
steps:
|
||||
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Python
|
||||
timeout-minutes: 3
|
||||
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
|
||||
with:
|
||||
python-version: ${{ env.UV_PYTHON }}
|
||||
|
||||
- name: Set up uv
|
||||
timeout-minutes: 3
|
||||
uses: ./.github/actions/setup-uv-with-retries
|
||||
with:
|
||||
version: "0.10.9"
|
||||
|
||||
- name: Cache the Rust build
|
||||
timeout-minutes: 5
|
||||
uses: ./.github/actions/cache-cargo-build
|
||||
|
||||
- name: Cache Prisma binaries
|
||||
timeout-minutes: 5
|
||||
uses: ./.github/actions/cache-prisma-binaries
|
||||
|
||||
- name: Install dependencies
|
||||
timeout-minutes: 20
|
||||
run: .github/scripts/uv_sync_with_retries.sh --frozen --all-groups --all-extras
|
||||
|
||||
- name: Install redis-server 7.2.16
|
||||
timeout-minutes: 3
|
||||
run: |
|
||||
mkdir -p "$RUNNER_TEMP/redis-bin"
|
||||
cid="$(docker create redis:7.2.16@sha256:0637954999d01b7c9ce9167db2da50656e2590d3b884f1c600c5f63bb6e6773c)"
|
||||
docker cp "${cid}:/usr/local/bin/redis-server" "$RUNNER_TEMP/redis-bin/redis-server"
|
||||
docker rm "$cid"
|
||||
"$RUNNER_TEMP/redis-bin/redis-server" --version | grep -q 'v=7.2.16'
|
||||
echo "$RUNNER_TEMP/redis-bin" >> "$GITHUB_PATH"
|
||||
|
||||
- name: Install MCP SDK1 peer
|
||||
if: matrix.suite == 'mcp'
|
||||
timeout-minutes: 5
|
||||
run: |
|
||||
uv venv --python 3.12 .venv-mcp-peer
|
||||
uv pip install --no-config --exclude-newer "3 days" --python .venv-mcp-peer 'mcp==1.28.1' 'langchain-mcp-adapters==0.2.1'
|
||||
echo "MCP_TEST_PEER_PYTHON=$PWD/.venv-mcp-peer/bin/python" >> "$GITHUB_ENV"
|
||||
|
||||
- name: Set up Node.js
|
||||
if: matrix.suite == 'browser'
|
||||
timeout-minutes: 5
|
||||
uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0.0
|
||||
with:
|
||||
node-version-file: ui/litellm-dashboard/.nvmrc
|
||||
cache: "npm"
|
||||
cache-dependency-path: |
|
||||
ui/litellm-dashboard/package-lock.json
|
||||
tests/e2e/ui/package-lock.json
|
||||
|
||||
- name: Install browser dependencies and build the dashboard
|
||||
if: matrix.suite == 'browser'
|
||||
timeout-minutes: 20
|
||||
run: |
|
||||
(cd ui/litellm-dashboard && npm ci)
|
||||
(cd tests/e2e/ui && npm ci)
|
||||
sudo env PATH="$PATH" DEBIAN_FRONTEND=noninteractive \
|
||||
node tests/e2e/ui/node_modules/@playwright/test/cli.js install-deps chromium
|
||||
node tests/e2e/ui/node_modules/@playwright/test/cli.js install chromium
|
||||
(cd ui/litellm-dashboard && NEXT_TELEMETRY_DISABLED=1 npm run build)
|
||||
|
||||
- name: Run integration contracts
|
||||
timeout-minutes: 45
|
||||
env:
|
||||
SUITE: ${{ matrix.suite }}
|
||||
INTEGRATION_POSTGRES_CONTAINER: ${{ job.services.postgres.id }}
|
||||
INTEGRATION_REDIS_CONTAINER: ${{ job.services.redis.id }}
|
||||
LITELLM_LICENSE: ${{ secrets.LITELLM_LICENSE }}
|
||||
run: |
|
||||
case "$SUITE" in
|
||||
*-replica) bash .circleci/scripts/run_integration.sh "${SUITE%-replica}" replica ;;
|
||||
*) bash .circleci/scripts/run_integration.sh "$SUITE" ;;
|
||||
esac
|
||||
|
||||
- name: Verify every case ran exactly once
|
||||
if: ${{ !cancelled() && matrix.suite != 'browser' }}
|
||||
timeout-minutes: 2
|
||||
run: |
|
||||
record="$(find test-results -mindepth 2 -maxdepth 2 -name execution.json -print -quit)"
|
||||
test -n "$record"
|
||||
mkdir -p "$RUNNER_TEMP/shards/0"
|
||||
cp "$record" "$RUNNER_TEMP/shards/0/execution.json"
|
||||
.venv/bin/python -m tests.integration._support.sharding "$RUNNER_TEMP/shards" --shards 1
|
||||
|
||||
- name: Report MCP coverage
|
||||
if: ${{ !cancelled() && matrix.suite == 'mcp' }}
|
||||
timeout-minutes: 5
|
||||
run: |
|
||||
coverage_dir=test-results/integration-mcp/coverage
|
||||
test -f "$coverage_dir/coverage.txt" && exit 0
|
||||
export COVERAGE_FILE="$PWD/$coverage_dir/data"
|
||||
.venv/bin/python -m coverage combine --rcfile=tests/integration/mcp_coverage.toml
|
||||
.venv/bin/python -m coverage report --rcfile=tests/integration/mcp_coverage.toml > "$coverage_dir/coverage.txt"
|
||||
.venv/bin/python -m coverage html --rcfile=tests/integration/mcp_coverage.toml -d "$coverage_dir/html"
|
||||
tail -n 1 "$coverage_dir/coverage.txt"
|
||||
|
||||
- name: Check results for the license
|
||||
id: secret-scan
|
||||
if: ${{ !cancelled() }}
|
||||
timeout-minutes: 5
|
||||
env:
|
||||
SCANNED_SECRET: ${{ secrets.LITELLM_LICENSE }}
|
||||
run: python .github/scripts/assert_secret_absent.py test-results
|
||||
|
||||
- name: Upload results
|
||||
if: ${{ !cancelled() && steps.secret-scan.outcome == 'success' }}
|
||||
timeout-minutes: 10
|
||||
uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
|
||||
with:
|
||||
name: integration-${{ matrix.suite }}-${{ github.run_id }}-${{ github.run_attempt }}
|
||||
path: test-results/
|
||||
retention-days: 14
|
||||
|
|
@ -27,8 +27,11 @@ tests. A product bug the test exposes is `pytest.skip("BUG: <symptom>")` at the
|
|||
fix in the test and not a deletion. Needs no network, proxy, DB or Redis: `tests/unit`
|
||||
|
||||
CircleCI's integration groups run every file here except the OCI and sandbox tests, which no CI runs, and
|
||||
the files in `GITHUB_FILES` in `run.py`. CircleCI runs on main, not on pull requests, so a new file here
|
||||
first runs after its PR merges. Wanting a file to run before merge is no reason to change CI, and a new
|
||||
the files in `GITHUB_FILES` in `run.py`. `test-integration.yml` runs the same groups through the same
|
||||
`run_integration.sh` on GitHub Actions, on main every three hours from 8am to 8pm Pacific Monday to Saturday,
|
||||
and on a pull request when someone adds the `run-ci` label. Neither runs every pull request, so a new file here
|
||||
first runs on main after its PR merges, or earlier if the PR gets `run-ci`. Wanting a file to run before merge
|
||||
is no reason to change CI, and a new
|
||||
dedicated workflow for it is the same mistake as a shared shard. Write the file, leave `GITHUB_FILES` and
|
||||
every workflow alone, and tell the user it first runs on main. `GITHUB_FILES` is only for a file that
|
||||
needs what CircleCI's groups cannot give it, like the images `image-scan.yml` builds or the plain pytest
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Integration contracts
|
||||
|
||||
These tests exercise a running gateway, PostgreSQL and Redis with an owned local upstream. CircleCI owns this suite. Tests are grouped by behavior, with no automatic test retries or fallback to paid provider calls
|
||||
These tests exercise a running gateway, PostgreSQL and Redis with an owned local upstream. CircleCI owns this suite, and `.github/workflows/test-integration.yml` runs the same groups through `run_integration.sh` on GitHub Actions for `run-ci` pull requests and scheduled main runs. Tests are grouped by behavior, with no automatic test retries or fallback to paid provider calls
|
||||
|
||||
The ROI database contracts in `database/test_roi_observed.py` run as plain pytest outside `run_integration.sh` in CircleCI's `roi-database` Postgres job. The job uploads coverage with the `roi-postgres` flag. These contracts own temporary databases and script only the external provider transport
|
||||
|
||||
|
|
|
|||
124
tests/unit/test_assert_secret_absent.py
Normal file
124
tests/unit/test_assert_secret_absent.py
Normal file
|
|
@ -0,0 +1,124 @@
|
|||
import base64
|
||||
import importlib.util
|
||||
import io
|
||||
import sys
|
||||
import urllib.parse
|
||||
import zipfile
|
||||
from collections.abc import Callable, Mapping
|
||||
from itertools import chain, product
|
||||
from pathlib import Path
|
||||
from types import MappingProxyType
|
||||
from typing import Final
|
||||
|
||||
import pytest
|
||||
|
||||
_REPO_ROOT: Final = Path(__file__).resolve().parents[2]
|
||||
_MODULE_PATH: Final = _REPO_ROOT / ".github" / "scripts" / "assert_secret_absent.py"
|
||||
_spec: Final = importlib.util.spec_from_file_location("assert_secret_absent", _MODULE_PATH)
|
||||
scanner: Final = importlib.util.module_from_spec(_spec)
|
||||
sys.modules[_spec.name] = scanner
|
||||
_spec.loader.exec_module(scanner)
|
||||
|
||||
SECRET: Final = "lic/ense+KEY:9f8e~~??>>~?7d6c5b4a3210-zz"
|
||||
PREFIXES: Final = ("", "x", "xy")
|
||||
ENCODERS: Final = (base64.b64encode, base64.urlsafe_b64encode)
|
||||
|
||||
|
||||
def _zip(members: Mapping[str, bytes], compression: int = zipfile.ZIP_DEFLATED) -> bytes:
|
||||
buffer: Final = io.BytesIO()
|
||||
with zipfile.ZipFile(buffer, "w", compression) as archive:
|
||||
for name, data in members.items():
|
||||
archive.writestr(name, data)
|
||||
return buffer.getvalue()
|
||||
|
||||
|
||||
def _blob(prefix: str) -> bytes:
|
||||
return f"{prefix}{SECRET}tail".encode()
|
||||
|
||||
|
||||
def _planted_forms() -> tuple[str, ...]:
|
||||
encoded: Final = tuple(encode(_blob(prefix)).decode() for encode, prefix in product(ENCODERS, PREFIXES))
|
||||
return (SECRET, urllib.parse.quote(SECRET, safe=""), *encoded)
|
||||
|
||||
|
||||
def _assert_nothing_leaked(output: str) -> None:
|
||||
windows: Final = frozenset(
|
||||
chain.from_iterable((form[i : i + 8] for i in range(len(form) - 7)) for form in _planted_forms())
|
||||
)
|
||||
assert not [window for window in windows if window in output]
|
||||
|
||||
|
||||
def _run(root: Path, secret: str = SECRET) -> tuple[int, str]:
|
||||
out: Final = io.StringIO()
|
||||
code: Final = scanner.main((str(root),), {scanner.SECRET_VARIABLE: secret}, out)
|
||||
return code, out.getvalue()
|
||||
|
||||
|
||||
def _encoded_blob(prefix: str, encode: Callable[[bytes], bytes]) -> bytes:
|
||||
return b"trace " + encode(_blob(prefix)) + b" end"
|
||||
|
||||
|
||||
QUOTED: Final = urllib.parse.quote(SECRET, safe="")
|
||||
PLACEMENTS: Final = MappingProxyType(
|
||||
{
|
||||
"raw in a log": {"proxy.log": f"boot with key {SECRET} ok".encode()},
|
||||
"url-encoded in a url": {"upstream.log": f"GET /verify_license/{QUOTED}".encode()},
|
||||
"base64 aligned": {"a.json": _encoded_blob("", base64.b64encode)},
|
||||
"base64 one byte in": {"a.json": _encoded_blob("x", base64.b64encode)},
|
||||
"base64 two bytes in": {"a.json": _encoded_blob("xy", base64.b64encode)},
|
||||
"base64url two bytes in": {"a.json": _encoded_blob("xy", base64.urlsafe_b64encode)},
|
||||
"inside a zip member": {"trace.zip": _zip({"network.json": f'{{"auth": "{SECRET}"}}'.encode()})},
|
||||
"inside a nested zip": {"outer.zip": _zip({"inner.zip": _zip({"env.txt": SECRET.encode()})})},
|
||||
"named after it in a nested zip": {
|
||||
"outer.zip": _zip({"inner.zip": _zip({f"dump-{QUOTED}.txt": SECRET.encode()})})
|
||||
},
|
||||
"in a file name": {f"run-{QUOTED}.log": b"nothing inside"},
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("placement", PLACEMENTS)
|
||||
def test_every_planted_copy_blocks_the_upload_without_printing_the_secret(tmp_path: Path, placement: str) -> None:
|
||||
worker: Final = tmp_path / "gw0"
|
||||
worker.mkdir()
|
||||
for name, data in PLACEMENTS[placement].items():
|
||||
(worker / name).write_bytes(data)
|
||||
code, output = _run(tmp_path)
|
||||
assert code == 1
|
||||
assert "secret found:" in output
|
||||
_assert_nothing_leaked(output)
|
||||
|
||||
|
||||
def test_clean_results_pass_and_count_every_file(tmp_path: Path) -> None:
|
||||
(tmp_path / "junit.xml").write_text("<testsuite/>")
|
||||
(tmp_path / "gw0").mkdir()
|
||||
(tmp_path / "gw0" / "proxy.log").write_text("LITELLM_LICENSE is not set")
|
||||
code, output = _run(tmp_path)
|
||||
assert code == 0
|
||||
assert "no copy of the secret in 2 files" in output
|
||||
|
||||
|
||||
def test_an_unset_secret_has_nothing_to_find(tmp_path: Path) -> None:
|
||||
(tmp_path / "proxy.log").write_text(SECRET)
|
||||
assert _run(tmp_path, secret="")[0] == 0
|
||||
|
||||
|
||||
def test_a_symlinked_directory_fails_closed(tmp_path: Path) -> None:
|
||||
outside: Final = tmp_path / "outside"
|
||||
outside.mkdir()
|
||||
results: Final = tmp_path / "results"
|
||||
results.mkdir()
|
||||
(results / "linked").symlink_to(outside, target_is_directory=True)
|
||||
code, output = _run(results)
|
||||
assert code == 1
|
||||
assert "directory symlink" in output
|
||||
|
||||
|
||||
def test_an_unreadable_archive_fails_without_echoing_its_contents(tmp_path: Path) -> None:
|
||||
archive: Final = _zip({"env.txt": f"LITELLM_LICENSE={SECRET}".encode()}, zipfile.ZIP_STORED)
|
||||
at: Final = archive.index(SECRET.encode())
|
||||
(tmp_path / "trace.zip").write_bytes(archive[:at] + bytes([archive[at] ^ 0xFF]) + archive[at + 1 :])
|
||||
code, output = _run(tmp_path)
|
||||
assert code == 1
|
||||
assert "scan failed with BadZipFile" in output
|
||||
_assert_nothing_leaked(output)
|
||||
Loading…
Add table
Reference in a new issue