scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-14 23:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 102

ci: run the Redis timeout e2e test from its own weekly workflow

Browse source 
It is a functional e2e test, not a load test, so give it its own workflow instead of a job
inside the load anomaly run. It keeps the Saturday 12:00 UTC cadence and manual dispatch, and
boots the timeout-config proxy with Postgres and Valkey services exactly as before.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014ZDULyJPp17ZFiJenRxs2T
This commit is contained in:
Kerry Lu 2026-09-09 15:51:11 -07:00
parent 058ff8c63c
commit d9e822d256
4 changed files with 96 additions and 86 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

94
.github/workflows/test-e2e-redis-timeout.yml vendored Normal file
View file

@ -0,0 +1,94 @@
name: "Weekly Redis Timeout E2E"
on:
schedule:
- cron: "0 12 * * 6"
workflow_dispatch:
permissions:
contents: read
jobs:
redis-timeout-e2e:
if: github.event_name != 'schedule' || github.repository == 'BerriAI/litellm'
runs-on: ubuntu-latest
timeout-minutes: 30
services:
postgres:
image: postgres:16.6
env:
POSTGRES_USER: llmproxy
POSTGRES_PASSWORD: dbpassword9090
POSTGRES_DB: litellm
ports:
- 5432:5432
options: >-
--health-cmd "pg_isready -U llmproxy"
--health-interval 5s
--health-timeout 5s
--health-retries 10
valkey:
image: valkey/valkey:8.1.4@sha256:81db6d39e1bba3b3ff32bd3a1b19a6d69690f94a3954ec131277b9a26b95b3aa
ports:
- 6379:6379
options: >-
--health-cmd "valkey-cli ping"
--health-interval 5s
--health-timeout 5s
--health-retries 10
env:
DATABASE_URL: postgresql://llmproxy:dbpassword9090@localhost:5432/litellm
LITELLM_MASTER_KEY: sk-redis-timeout-e2e
LITELLM_LOG: WARNING
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: ./.github/actions/setup-uv-with-retries
with:
version: "0.10.9"
- name: Cache the Rust build
uses: ./.github/actions/cache-cargo-build
- name: Install dependencies
run: |
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra proxy
- name: Cache Prisma binaries
uses: ./.github/actions/cache-prisma-binaries
- name: Generate Prisma client
run: |
uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
- name: Start the proxy with a Redis that times out on every command
run: |
nohup uv run --no-sync litellm --config tests/e2e/gateway/redis_timeout_ci_config.yml --port 4000 > proxy.log 2>&1 &
for _ in $(seq 1 90); do
if curl -fs http://localhost:4000/health/liveliness > /dev/null; then
exit 0
fi
sleep 2
done
echo "proxy never became live"
tail -n 100 proxy.log
exit 1
- name: Run the Redis timeout e2e test
env:
E2E_REDIS_TIMEOUT: "1"
LITELLM_PROXY_URL: http://localhost:4000
run: |
uv run --no-sync pytest tests/e2e/router/test_redis_timeout_e2e.py -v --tb=short -rA
- name: Show proxy log on failure
if: failure()
run: tail -n 300 proxy.log

84
.github/workflows/weekly_load_anomaly.yml vendored
View file

@ -83,87 +83,3 @@ jobs:
- name: Show proxy log on failure
if: failure()
run: tail -n 300 proxy.log
redis-timeout-e2e:
if: github.event_name != 'schedule' || github.repository == 'BerriAI/litellm'
runs-on: ubuntu-latest
timeout-minutes: 30
services:
postgres:
image: postgres:16.6
env:
POSTGRES_USER: llmproxy
POSTGRES_PASSWORD: dbpassword9090
POSTGRES_DB: litellm
ports:
- 5432:5432
options: >-
--health-cmd "pg_isready -U llmproxy"
--health-interval 5s
--health-timeout 5s
--health-retries 10
valkey:
image: valkey/valkey:8.1.4@sha256:81db6d39e1bba3b3ff32bd3a1b19a6d69690f94a3954ec131277b9a26b95b3aa
ports:
- 6379:6379
options: >-
--health-cmd "valkey-cli ping"
--health-interval 5s
--health-timeout 5s
--health-retries 10
env:
DATABASE_URL: postgresql://llmproxy:dbpassword9090@localhost:5432/litellm
LITELLM_MASTER_KEY: sk-redis-timeout-e2e
LITELLM_LOG: WARNING
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: ./.github/actions/setup-uv-with-retries
with:
version: "0.10.9"
- name: Cache the Rust build
uses: ./.github/actions/cache-cargo-build
- name: Install dependencies
run: |
.github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra proxy
- name: Cache Prisma binaries
uses: ./.github/actions/cache-prisma-binaries
- name: Generate Prisma client
run: |
uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
- name: Start the proxy with a Redis that times out on every command
run: |
nohup uv run --no-sync litellm --config tests/e2e/gateway/redis_timeout_ci_config.yml --port 4000 > proxy.log 2>&1 &
for _ in $(seq 1 90); do
if curl -fs http://localhost:4000/health/liveliness > /dev/null; then
exit 0
fi
sleep 2
done
echo "proxy never became live"
tail -n 100 proxy.log
exit 1
- name: Run the Redis timeout e2e test
env:
E2E_REDIS_TIMEOUT: "1"
LITELLM_PROXY_URL: http://localhost:4000
run: |
uv run --no-sync pytest tests/e2e/router/test_redis_timeout_e2e.py -v --tb=short -rA
- name: Show proxy log on failure
if: failure()
run: tail -n 300 proxy.log

2
tests/e2e/CLAUDE.md
View file

@ -17,7 +17,7 @@ Each subdirectory under `tests/e2e/` is one suite, scoped to an endpoint family
- `mcp/` - the MCP server surface over api_key auth against the real Datadog remote MCP server (see "MCP suite: real Datadog only" below); plus the gateway-managed OAuth (authorization_code) path exercised through `/chat/completions`, the one behavior Datadog's static-header auth cannot reach, seeding the per-user upstream token via the interactive authorize dance driven with the mcp SDK's own OAuth client (headless-browser consent from a saved session) and asserting the completion lists and executes the server's tools with the stored per-user token
- `logging/` - logging-integration delivery (datadog and friends)
- `security/` - secret handling and log-leak protection
- `router/` - routing and reliability behavior (fallbacks, cooldowns). Also holds `test_redis_timeout_e2e.py`, which needs a proxy booted from `gateway/redis_timeout_ci_config.yml` (real Redis, `socket_timeout: 0.001`, so every command times out); it is marked `redis_timeout`, deselected unless `E2E_REDIS_TIMEOUT` is set, excluded from the per-PR check, and driven by `.github/workflows/weekly_load_anomaly.yml`
- `router/` - routing and reliability behavior (fallbacks, cooldowns). Also holds `test_redis_timeout_e2e.py`, which needs a proxy booted from `gateway/redis_timeout_ci_config.yml` (real Redis, `socket_timeout: 0.001`, so every command times out); it is marked `redis_timeout`, deselected unless `E2E_REDIS_TIMEOUT` is set, excluded from the per-PR check, and driven weekly by `.github/workflows/test-e2e-redis-timeout.yml`
- `load/` - performance-category tests, kept OUT of the main suite: throughput/load SLO tests are a different testing category from functional e2e (variance-driven, historically flaky) and live outside this suite until re-implemented as their own pipeline (LIT-5163); do not add a live load test that runs in the default collection. What remains here: the weekly session-anomaly test (`test_weekly_session_anomaly_e2e.py`, Claude Code-shaped multi-turn sessions against real providers with ceilings on error rate, cache read/write, turn time, and spend; marked `weekly` and deselected unless `E2E_WEEKLY_ANOMALY` is set, driven by `.github/workflows/weekly_load_anomaly.yml`) and markerless harness unit tests for the Locust/session-anomaly aggregation logic
- `other/` - the holding-pen suite for the `other.*` registry cluster with no home of its own yet: the master-key auth gate and the process-lifecycle health probes (liveness, public readiness, authenticated readiness diagnostics). Promote a cluster out once it is large/stable enough for its own suite
- `gateway/` - proxy configuration only (`litellm-config.yml`); no tests

2
tests/e2e/CONTRIBUTING.md
View file

@ -65,7 +65,7 @@ A couple of logging destinations are configured on the proxy rather than by the
### The pull request check
Every same-repository PR that adds, modifies, or renames a `tests/e2e/**/test_*.py` file runs those changed files three times. A change to the harness itself, meaning a root-level `tests/e2e/*.py` file or `pytest.ini`, `tests/e2e/gateway/`, `.github/e2e-stack/`, or the workflow, also runs the `access_control` suite as a canary, because those files have no test of their own that exercises the stack. `.github/e2e-stack/select_tests.py` applies both rules. The stack config at `tests/e2e/gateway/stage_mirror_ci_config.yml` must declare every model the selected suites use; a missing one shows up as a failed test id in the public log. The suite's own single rerun for network errors and 5xx responses (see `pytest.ini`) applies on every pass, so a transport blip does not fail the check while a race inside a test still does. The stage-mirror stack has a control-plane backend, two gateways behind nginx, Postgres, Jaeger, and TLS cluster-mode Valkey. The stack exports every gateway address in `LITELLM_PROXY_REPLICA_URLS`, so model registration waits until each gateway lists the new model rather than whichever one the load balancer answered from. Documentation, deleted-file, and application-only changes do not start the stack or request environment approval. The `ui/`, `claude_code/`, and `load/` directories, `batches/test_managed_files_enforcement_e2e.py`, `llm_translation/realtime/test_realtime_pipecat_audio_e2e.py`, `guardrails/test_presidio_masking_e2e.py`, and `router/test_redis_timeout_e2e.py` remain outside this check because they use separate tooling or need a differently configured stack: the pipecat audio suite skips itself at import time unless the NLTK `punkt_tab` data is installed, and the presidio suite fails without the analyzer and anonymizer services this stack does not start, and the Redis timeout test needs a proxy whose Redis times out on every command (`gateway/redis_timeout_ci_config.yml`), which the weekly load workflow boots
Every same-repository PR that adds, modifies, or renames a `tests/e2e/**/test_*.py` file runs those changed files three times. A change to the harness itself, meaning a root-level `tests/e2e/*.py` file or `pytest.ini`, `tests/e2e/gateway/`, `.github/e2e-stack/`, or the workflow, also runs the `access_control` suite as a canary, because those files have no test of their own that exercises the stack. `.github/e2e-stack/select_tests.py` applies both rules. The stack config at `tests/e2e/gateway/stage_mirror_ci_config.yml` must declare every model the selected suites use; a missing one shows up as a failed test id in the public log. The suite's own single rerun for network errors and 5xx responses (see `pytest.ini`) applies on every pass, so a transport blip does not fail the check while a race inside a test still does. The stage-mirror stack has a control-plane backend, two gateways behind nginx, Postgres, Jaeger, and TLS cluster-mode Valkey. The stack exports every gateway address in `LITELLM_PROXY_REPLICA_URLS`, so model registration waits until each gateway lists the new model rather than whichever one the load balancer answered from. Documentation, deleted-file, and application-only changes do not start the stack or request environment approval. The `ui/`, `claude_code/`, and `load/` directories, `batches/test_managed_files_enforcement_e2e.py`, `llm_translation/realtime/test_realtime_pipecat_audio_e2e.py`, `guardrails/test_presidio_masking_e2e.py`, and `router/test_redis_timeout_e2e.py` remain outside this check because they use separate tooling or need a differently configured stack: the pipecat audio suite skips itself at import time unless the NLTK `punkt_tab` data is installed, and the presidio suite fails without the analyzer and anonymizer services this stack does not start, and the Redis timeout test needs a proxy whose Redis times out on every command (`gateway/redis_timeout_ci_config.yml`), which `.github/workflows/test-e2e-redis-timeout.yml` boots on a weekly schedule
Every selected file must execute at least one passing test in each pass, and any test failure, collection error, or entirely skipped or deselected file fails the check. A file whose tests are all marked skip therefore cannot pass this check, so unskip at least one of them, or add the file to `UNSUPPORTED` in `select_tests.py` with the reason, before changing one. A failed pass stops the run. The public log prints pytest's one-line summary for each pass, including the rerun count, and names each failed or errored test as `classname::name`, so a retried network error or a failing test is visible without the raw output. The final `e2e-changed-tests` job succeeds only when no supported test files changed or the approved run completed all three passes. Fork PRs with selected tests fail this gate until a maintainer brings the reviewed change onto a same-repository branch