Skip to content

[Feat]: Signal-Decision Driven Semantic Routing with Dynamic Plugin Architecture #1772

[Feat]: Signal-Decision Driven Semantic Routing with Dynamic Plugin Architecture

[Feat]: Signal-Decision Driven Semantic Routing with Dynamic Plugin Architecture #1772

name: Test And Build
on:
schedule:
# Run nightly at 2:00 AM UTC
- cron: "0 2 * * *"
workflow_dispatch: # Allow manual triggering
pull_request: # Run on all pull requests
jobs:
test-and-build:
if: github.repository == 'vllm-project/semantic-router'
runs-on: ubuntu-latest
steps:
- name: Check out the repo
uses: actions/checkout@v4
- name: Set up Rust
uses: dtolnay/rust-toolchain@stable
with:
toolchain: 1.90
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version: "1.24"
- name: Install system dependencies
run: |
sudo apt-get update
sudo apt-get install -y \
make \
build-essential \
pkg-config
curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/HEAD/install.sh | sh -s -- -b $(go env GOPATH)/bin v2.5.0
- name: Cache Rust dependencies
uses: actions/cache@v4
with:
path: |
~/.cargo/bin/
~/.cargo/registry/index/
~/.cargo/registry/cache/
~/.cargo/git/db/
candle-binding/target/
key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock', '**/Cargo.toml') }}
restore-keys: |
${{ runner.os }}-cargo-
- name: Cache Go dependencies
uses: actions/cache@v4
with:
path: |
~/go/pkg/mod
key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
restore-keys: |
${{ runner.os }}-go-
- name: Cache Models
uses: actions/cache@v4
with:
path: |
models/
key: ${{ runner.os }}-models-v1-${{ hashFiles('tools/make/models.mk') }}
restore-keys: |
${{ runner.os }}-models-v1-
continue-on-error: true # Don't fail the job if caching fails
- name: Check go mod tidy
run: make check-go-mod-tidy
- name: Build Rust library (CPU-only, no CUDA)
run: make rust-ci
- name: Install HuggingFace CLI
run: |
pip install -U "huggingface_hub[cli]" hf_transfer
- name: Download models (minimal on PRs)
env:
CI_MINIMAL_MODELS: ${{ github.event_name == 'pull_request' }}
HF_HUB_ENABLE_HF_TRANSFER: 1
HF_HUB_DISABLE_TELEMETRY: 1
run: make download-models
- name: Start Milvus service
run: |
echo "Starting Milvus vector database..."
docker run -d \
--name milvus-semantic-cache \
--security-opt seccomp:unconfined \
-e ETCD_USE_EMBED=true \
-e ETCD_DATA_DIR=/var/lib/milvus/etcd \
-e ETCD_CONFIG_PATH=/milvus/configs/advanced/etcd.yaml \
-e COMMON_STORAGETYPE=local \
-e CLUSTER_ENABLED=false \
-p 19530:19530 \
-p 9091:9091 \
milvusdb/milvus:v2.3.3 \
milvus run standalone
echo "Waiting for Milvus to be ready..."
sleep 20
# Verify Milvus is responsive
timeout 30 bash -c 'until docker logs milvus-semantic-cache 2>&1 | grep -q "Proxy successfully started"; do sleep 2; done' || true
echo "Milvus is ready at localhost:19530"
docker ps --filter "name=milvus-semantic-cache"
- name: Run semantic router tests
run: make test
env:
CI: true
CI_MINIMAL_MODELS: ${{ github.event_name == 'pull_request' }}
CGO_ENABLED: 1
LD_LIBRARY_PATH: ${{ github.workspace }}/candle-binding/target/release
MILVUS_URI: localhost:19530
SKIP_MILVUS_TESTS: false
- name: Stop Milvus service
if: always()
run: |
echo "Stopping Milvus container..."
docker stop milvus-semantic-cache || true
docker rm milvus-semantic-cache || true
echo "Milvus container cleaned up"
- name: Upload test artifacts on failure
if: failure()
uses: actions/upload-artifact@v4
with:
name: test-logs
path: |
**/*.log
**/test-output.*
retention-days: 7
- name: Notify on failure
if: failure()
run: |
echo "::error::Test and build failed. Check the workflow run for details."
# Trigger Docker publishing on successful nightly runs
publish-docker:
needs: test-and-build
if: github.repository == 'vllm-project/semantic-router' && success() && github.event_name == 'schedule'
uses: ./.github/workflows/docker-publish.yml
with:
tag_suffix: nightly-$(date +'%Y%m%d')
is_nightly: true
secrets: inherit