# Local → production pipeline. # # push to main → test → build amd64 images → push to the fleet registry # → move :latest → gw-04's existing 60s rolling timer picks it up. # # The last hop is NOT in this file and does not need to be: gw-04 already runs # `clawmates-deploy.timer` every minute, which pulls # `$REGISTRY/clawmates/:latest`, compares it to the running image id, and # recreates on drift. This workflow's job is to make `:latest` mean the newest # green commit. See deploy/gw-04/clawmates-deploy.sh. # # Runs on the `gw04` runner (host executor, systemd unit act-runner). gw-04 is # the only reachable x86_64 host — web-01 is aarch64 and the fleet build boxes # are packed — and prod images must be linux/amd64, so builds are native here # rather than emulated. name: deploy on: push: branches: [main] # Lets you re-run a deploy without an empty commit. workflow_dispatch: env: REGISTRY: 100.94.185.103:5000 NAMESPACE: clawmates jobs: test: runs-on: gw04 steps: - uses: actions/checkout@v4 # A throwaway Postgres so the integration tests actually run. Without # CM_TEST_DATABASE_URL, cm-testkit tries a default admin URL and the # approvals_api tests die on PoolTimedOut — which looks like a failure but # only means "no database here". - name: Start test Postgres run: | docker rm -f cm-ci-pg 2>/dev/null || true docker run -d --name cm-ci-pg \ -e POSTGRES_PASSWORD=postgres -e POSTGRES_USER=postgres \ -p 127.0.0.1:55432:5432 postgres:16-alpine for i in $(seq 1 30); do docker exec cm-ci-pg pg_isready -U postgres >/dev/null 2>&1 && break sleep 2 done docker exec cm-ci-pg pg_isready -U postgres # Rust lives in a container because gw-04 has no cargo. The named volumes # are the whole reason this is not painfully slow: without them every run # recompiles the world. # Docker socket AND the host's docker binary are mounted: # - cm-files' s3_store test uses testcontainers (socket only). # - cm-runtime/cm-sandbox tests (browser_tool, shell_exec, warm_pool, # security, socket_proxy) shell out to `docker` via std::process, so # they need the CLI on PATH too. Mounting the host binary beats # apt-installing docker.io on every run — that is ~100 MB of download # per job, and the container is fresh each time so nothing caches it. # These tests do NOT skip when the capability is missing; they fail in a # way that reads like broken code (SocketNotFoundError / NotFound), which # is why they are worth wiring up rather than excluding. # # They also need clawmates/agent-{base,browser,terminal}:dev, which are # locally-built images present on gw-04 but in no registry. If this job # ever moves hosts, those images must move with it. # # `cargo test --workspace` builds cm-brain, which pulls clawhdf5 from # git.redclaw.dev — a PRIVATE repo. Two things are needed and neither is # optional: # CARGO_NET_GIT_FETCH_WITH_CLI — libgit2 fails against Gitea's smart-HTTP # with "invalid packet line" (the server Dockerfile sets it for the # same reason). Note it is _GIT_FETCH_WITH_CLI, not _NET_FETCH_. # the insteadOf rewrite — supplies the credential to that CLI fetch. # The token is a repo secret, so it is masked in logs and never in git. - name: Rust tests run: | docker run --rm --network host \ -v "$PWD":/w -w /w \ -v cm-ci-cargo-registry:/usr/local/cargo/registry \ -v cm-ci-cargo-git:/usr/local/cargo/git \ -v cm-ci-target:/w/target \ -v /var/run/docker.sock:/var/run/docker.sock \ -v /usr/bin/docker:/usr/bin/docker:ro \ -e SQLX_OFFLINE=true \ -e CARGO_NET_GIT_FETCH_WITH_CLI=true \ -e FORGE_TOKEN='${{ secrets.FORGE_TOKEN }}' \ -e CM_TEST_DATABASE_URL=postgres://postgres:postgres@127.0.0.1:55432/postgres \ rust:1.96-slim \ sh -c 'set -e apt-get update -qq apt-get install -y -qq pkg-config libssl-dev cmake git >/dev/null git config --global url."https://oauth2:$FORGE_TOKEN@git.redclaw.dev/".insteadOf "https://git.redclaw.dev/" cargo test --workspace' - name: Stop test Postgres if: always() run: docker rm -f cm-ci-pg 2>/dev/null || true # node 22 is on the host, so these run directly. - name: Frontend checks working-directory: frontend run: | npm ci --no-audit --no-fund npm run typecheck npm run test # Lint is advisory: the repo currently has pre-existing max-lines and # set-state-in-effect errors that predate this pipeline. Failing the # deploy on them would mean nothing could ship until they are cleared. npm run lint || echo "::warning::lint reported problems (advisory)" build: runs-on: gw04 needs: test steps: - uses: actions/checkout@v4 - name: Build + push images run: | set -eu SHA=$(git rev-parse --short HEAD) echo "SHA=$SHA" >> "$GITHUB_ENV" # The daemon binary the frontend serves at /dl. images/frontend.Dockerfile # expects it staged; rsync-based deploys create it out of band, so build # it here or the image ships without the node installer. mkdir -p frontend/public/dl docker run --rm \ -v "$PWD":/w -w /w \ -v cm-ci-cargo-registry:/usr/local/cargo/registry \ -v cm-ci-cargo-git:/usr/local/cargo/git \ -v cm-ci-target:/w/target \ -e SQLX_OFFLINE=true -e CARGO_NET_GIT_FETCH_WITH_CLI=true \ -e FORGE_TOKEN='${{ secrets.FORGE_TOKEN }}' \ rust:1.96-slim \ sh -c 'set -e apt-get update -qq apt-get install -y -qq pkg-config libssl-dev cmake git >/dev/null git config --global url."https://oauth2:$FORGE_TOKEN@git.redclaw.dev/".insteadOf "https://git.redclaw.dev/" cargo build --release -p clawmates-node cp target/release/clawmates-node frontend/public/dl/clawmates-node-linux-amd64' for svc in server frontend broker; do docker build -f "images/$svc.Dockerfile" \ -t "$REGISTRY/$NAMESPACE/$svc:main-$SHA" \ -t "$REGISTRY/$NAMESPACE/$svc:latest" . docker push "$REGISTRY/$NAMESPACE/$svc:main-$SHA" docker push "$REGISTRY/$NAMESPACE/$svc:latest" done # `docker push :latest` does NOT reliably move the tag on this registry: # when the manifest already exists under another tag (it does — we just # pushed main-$SHA), the push reports a digest but `:latest` keeps # resolving to the OLD image. Writing the manifest to the tag over the # HTTP API is what actually moves it. This is the same trick # scripts/deploy.sh uses, and the reason a "successful" deploy could # previously leave prod on a stale image. - name: Repoint :latest run: | set -eu for svc in server frontend broker; do ct=$(curl -s -o /tmp/m.json -D- \ -H 'Accept: application/vnd.oci.image.index.v1+json,application/vnd.docker.distribution.manifest.list.v2+json,application/vnd.docker.distribution.manifest.v2+json,application/vnd.oci.image.manifest.v1+json' \ "http://$REGISTRY/v2/$NAMESPACE/$svc/manifests/main-$SHA" \ | awk -F': ' '/^[Cc]ontent-[Tt]ype/{print $2}' | tr -d '\r') code=$(curl -s -o /dev/null -w '%{http_code}' -X PUT \ -H "Content-Type: $ct" --data-binary @/tmp/m.json \ "http://$REGISTRY/v2/$NAMESPACE/$svc/manifests/latest") echo "$svc :latest → main-$SHA (HTTP $code)" case "$code" in 20*) ;; *) echo "tag write failed"; exit 1 ;; esac done # Verify the thing that actually matters: what prod is RUNNING, not what # we pushed. A green edge on a stale image is the failure mode this whole # pipeline exists to prevent. - name: Wait for the rolling deploy run: | set -eu want=$(docker image inspect -f '{{.Id}}' "$REGISTRY/$NAMESPACE/server:latest") for i in $(seq 1 30); do got=$(docker inspect -f '{{.Image}}' clawmates_server_1 2>/dev/null || echo none) if [ "$got" = "$want" ]; then echo "prod is running main-$SHA" curl -s -o /dev/null -w "edge HTTP %{http_code}\n" -m 10 https://clawmates.work/ || true exit 0 fi sleep 10 done echo "prod did not roll onto main-$SHA within 5m — check clawmates-deploy.timer" exit 1