ci(deploy): add Flux GitOps deploy job, mirroring cobalt-dingo's pattern

Fixes silent stale-deploy gap: CI built+pushed images but nothing bumped k3s/apps/tapir/deployment.yaml, so merged features sat CI-green with zero production effect (infra#111, infra#168). Flux native image-automation can't scan localhost:5000 from inside k3s pods, so this patches the infra repo directly via the existing INFRA_DEPLOY_KEY org secret (same key cobalt-dingo and brain-gardener already use) on every push to main. Refs infra#111.
2026-07-25 21:21:02 +00:00
parent 72cb25111f
commit 4b557a4325
1 changed files with 115 additions and 1 deletions
@@ -90,4 +90,118 @@ jobs:
            && echo "Smoke test passed" \
            || echo "Smoke test inconclusive: $OUTPUT"

-  # ── 3. Mirror to GitHub — skipped for now (SSH key rotation pending) ─
+  # ── 3. Deploy via infra repo + Flux ─────────────────────────────────────────
+  # Flux native image-automation can't scan localhost:5000 from inside k3s pods
+  # (mathias/infra k3s/flux/flux-system/image-automation.yaml) — this job
+  # mirrors cobalt-dingo's proven pattern instead: patch the infra repo's
+  # manifest directly on every push to main, then annotate Flux for a fast
+  # reconcile. Fixes infra#111 (image built+pushed but manifest bump was
+  # manual, so merged features silently didn't deploy).
+  deploy:
+    name: Deploy via GitOps
+    needs: build
+    runs-on: self-hosted
+    if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+    environment: staging
+    steps:
+      - name: Update image tag in infra repo
+        env:
+          IMAGE_TAG: ${{ needs.build.outputs.image-tag }}
+          DEPLOY_KEY: ${{ secrets.INFRA_DEPLOY_KEY }}
+        run: |
+          set -euo pipefail
+
+          # INFRA_DEPLOY_KEY is a Gitea org secret (mathias org), already
+          # configured per docs/cd-pipeline.md in the infra repo — same key
+          # cobalt-dingo and brain-gardener use, no new secret needed.
+          mkdir -p ~/.ssh
+          echo "$DEPLOY_KEY" > ~/.ssh/id_infra
+          chmod 600 ~/.ssh/id_infra
+          ssh-keyscan -p 30022 10.0.1.20 >> ~/.ssh/known_hosts 2>/dev/null
+
+          export GIT_SSH_COMMAND="ssh -i ~/.ssh/id_infra -o IdentitiesOnly=yes"
+          rm -rf /tmp/infra
+          git clone -b main ssh://git@10.0.1.20:30022/mathias/infra.git /tmp/infra
+          cd /tmp/infra
+
+          DEPLOYMENT="k3s/apps/tapir/deployment.yaml"
+          # In-place update of the image tag. sed (not yq) so we don't
+          # depend on additional tooling on the runner — same as cobalt-dingo.
+          sed -i "s|image: localhost:5000/tapir:.*|image: localhost:5000/tapir:${IMAGE_TAG}|" "$DEPLOYMENT"
+
+          # Verify the patch took effect.
+          grep -q "localhost:5000/tapir:${IMAGE_TAG}" "$DEPLOYMENT" \
+            || { echo "✗ image tag patch failed"; exit 1; }
+
+          if git diff --quiet "$DEPLOYMENT"; then
+            echo "ℹ image tag unchanged — skipping push"
+          else
+            git -c user.name="tapir CI" \
+                -c user.email="ci@tapir.local" \
+                commit -m "chore(deploy): tapir → ${IMAGE_TAG}" "$DEPLOYMENT"
+            git push origin main
+            echo "✓ pushed to infra repo"
+          fi
+
+          shred -u ~/.ssh/id_infra
+
+      - name: Trigger Flux reconcile (immediate)
+        run: |
+          # Without these annotations, Flux would still pick up the change
+          # within 30s (the apps Kustomization interval). The annotations
+          # cut latency to ~1s.
+          kubectl -n flux-system annotate gitrepository flux-system \
+            reconcile.fluxcd.io/requestedAt="$(date +%s)" --overwrite
+          kubectl -n flux-system annotate kustomization apps \
+            reconcile.fluxcd.io/requestedAt="$(date +%s)" --overwrite
+
+      - name: Wait for Flux to apply new image
+        env:
+          IMAGE_TAG: ${{ needs.build.outputs.image-tag }}
+        run: |
+          # Poll the Deployment spec until it reflects the new tag.
+          # Bound to 60s so a stuck Flux doesn't hang CI.
+          EXPECTED="localhost:5000/tapir:${IMAGE_TAG}"
+          for i in $(seq 1 60); do
+            CURRENT=$(kubectl get deploy tapir -n tapir \
+              -o jsonpath='{.spec.template.spec.containers[0].image}' 2>/dev/null || echo "")
+            if [ "$CURRENT" = "$EXPECTED" ]; then
+              echo "✓ Flux applied new image after ${i}s"
+              break
+            fi
+            sleep 1
+          done
+          # Final assertion (in case the loop exited without matching).
+          kubectl get deploy tapir -n tapir \
+            -o jsonpath='{.spec.template.spec.containers[0].image}' \
+            | grep -qx "$EXPECTED" \
+            || { echo "✗ Flux did not apply new image within 60s"; exit 1; }
+
+      - name: Verify rollout
+        run: |
+          kubectl rollout status deployment/tapir \
+            --namespace tapir \
+            --timeout=120s \
+          || {
+            echo "── pod status ──"
+            kubectl get pods -n tapir -o wide
+            echo "── events ──"
+            kubectl get events -n tapir --sort-by='.lastTimestamp' | tail -20
+            echo "── describe ──"
+            kubectl describe pods -n tapir -l app=tapir | tail -40
+            exit 1
+          }
+
+      - name: Confirm pod running new image
+        env:
+          IMAGE_TAG: ${{ needs.build.outputs.image-tag }}
+        run: |
+          kubectl get pods -n tapir \
+            -l app=tapir \
+            --field-selector=status.phase=Running \
+            -o jsonpath='{.items[*].spec.containers[0].image}' \
+          | grep -q "localhost:5000/tapir:${IMAGE_TAG}" \
+          && echo "✓ pod running new image" \
+          || { echo "✗ pod image mismatch"; exit 1; }
+
+  # ── 4. Mirror to GitHub — skipped for now (SSH key rotation pending) ─