deploy-epoch: deployment topology — one binary, three blessed shapes (#27)

deploy-epoch: deployment topology — one binary, three blessed shapes

The full deploy-epoch integration: deployment topology spec + 4 implementation slices
(69 files, +14771/-36). Adds Docker image build pipeline (4 named --target stages),
container smoke CI (all-in-one TLS + compose + caddy reload-during-call), rustls
Phase 1 in-process TLS, /metrics endpoint, ValkeyEventSink, engine hygiene fixes
(TCP_NODELAY + TCP_QUICKACK-suppression + WS pings + trunk config), and the slice-F
tag-push image publish workflow. ADR-0011 (deployment topology) Proposed.

Pre-tag verification (PM-executed on integration tip c772485):
- Seam gate intact (loop_driver + rtc_session hashes unchanged)
- cargo fmt/clippy/test/doc all exit 0
- cargo deny bans+licenses FAILED pre-existing at main 6340e63 (CI authoritative
  via cargo-deny-action@v2 with cargo-deny 0.19.x)

PRs merged into this commit: #23 (dev-d/G), #24 (dev-a/A), #25 (dev-c/C+D+E), #26 (dev-b/B+F)
Integration PR: #27

Signed-off-by: Aaron D. Lee <himself@adlee.work>
Co-authored-by: Aaron D. Lee <himself@adlee.work>
Co-committed-by: Aaron D. Lee <himself@adlee.work>

.github/workflows/ci.yml

@@ -29,6 +29,18 @@ jobs:
 
   clippy:
     runs-on: ubuntu-latest
+    services:
+      valkey:
+        image: valkey/valkey:latest
+        ports:
+          - 6379:6379
+        options: >-
+          --health-cmd "valkey-cli ping"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 3
+    env:
+      VALKEY_URL: redis://127.0.0.1:6379/
     steps:
       - uses: actions/checkout@v4
       - uses: dtolnay/rust-toolchain@stable
@@ -41,9 +53,21 @@ jobs:
 
   test:
     runs-on: ubuntu-latest
+    services:
+      valkey:
+        image: valkey/valkey:latest
+        ports:
+          - 6379:6379
+        options: >-
+          --health-cmd "valkey-cli ping"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 3
     strategy:
       matrix:
         toolchain: [stable, "1.85"]
+    env:
+      VALKEY_URL: redis://127.0.0.1:6379/
     steps:
       - uses: actions/checkout@v4
 
@@ -144,3 +168,243 @@ jobs:
           RUTSTER_TWILIO_TEST_TO: ${{ secrets.TWILIO_TEST_TO }}
           RUTSTER_TWILIO_TEST_FROM: ${{ secrets.TWILIO_TEST_FROM }}
         run: cargo test --all --features=twilio-live -- --include-ignored
+
+  # deploy-B §6.1 image-build — builds all four first-party images via
+  # `docker buildx build --target` against deploy/Dockerfile. Runs AFTER the
+  # fmt/clippy/test/deny/sim-bench matrix gates: the smoke job downstream
+  # depends on these built images.
+  #
+  # Single builder invocation that builds all four --targets would be ideal
+  # (shared cache), but buildx's `--target` is one-per-invocation — so four
+  # build steps share the GHA cache via `cache-from/cache-to: type=gha`.
+  # Warm caches take image-build from ~6 min to ~90s.
+  image-build:
+    name: image-build (4 images)
+    runs-on: ubuntu-latest
+    needs: [fmt, clippy, test, deny, sim-bench]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      # libopus-dev — the headers the `opus` crate's build.rs expects.
+      # (The builder stage of deploy/Dockerfile already installs this
+      # inside the build image; this is a belt-and-braces step so a local
+      # buildx cache root has the headers if the cache misses.)
+      - name: Build-time host deps (belt-and-braces)
+        run: sudo apt-get update && sudo apt-get install -y libopus-dev
+
+      - name: Build rutster-engine image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: deploy/Dockerfile
+          target: rutster-engine
+          tags: rutster-engine:ci-${{ github.sha }}
+          push: false
+          load: true
+          cache-from: type=gha,scope=rutster-engine
+          cache-to: type=gha,mode=max,scope=rutster-engine
+
+      - name: Build rutster-brain image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: deploy/Dockerfile
+          target: rutster-brain
+          tags: rutster-brain:ci-${{ github.sha }}
+          push: false
+          load: true
+          cache-from: type=gha,scope=rutster-brain
+          cache-to: type=gha,mode=max,scope=rutster-brain
+
+      - name: Build rutster-edge image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: deploy/Dockerfile
+          target: rutster-edge
+          tags: rutster-edge:ci-${{ github.sha }}
+          push: false
+          load: true
+          cache-from: type=gha,scope=rutster-edge
+          cache-to: type=gha,mode=max,scope=rutster-edge
+
+      - name: Build rutster-allinone image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: deploy/Dockerfile
+          target: rutster-allinone
+          tags: rutster-allinone:ci-${{ github.sha }}
+          push: false
+          load: true
+          cache-from: type=gha,scope=rutster-allinone
+          cache-to: type=gha,mode=max,scope=rutster-allinone
+
+      - name: Smoke-tag the images for the downstream smoke job
+        # The smoke job references images as `:smoke`
+        # (deploy/smoke/compose_smoke.sh tags images with the
+        # RUTSTER_IMAGES_TAG env). Tag the freshly-built :ci-<sha> images as
+        # :smoke too, so the smoke job picks them up.
+        run: |
+          for img in rutster-engine rutster-brain rutster-edge rutster-allinone; do
+            docker tag "${img}:ci-${{ github.sha }}" "${img}:smoke"
+          done
+          docker images | grep rutster
+
+      - name: caddy validate
+        # Validate the Caddyfile inside the freshly-built rutster-edge image.
+        # Cheap regression against malformed Caddyfile (the local `caddy
+        # validate` in Task 3 is optional; this one is mandatory in CI).
+        run: |
+          docker run --rm \
+            -e RUTSTER_DOMAIN=pbx.example.com \
+            -e RUTSTER_ACME_EMAIL=test@example.com \
+            -v "$PWD/deploy/Caddyfile:/etc/caddy/Caddyfile:ro" \
+            rutster-edge:smoke \
+            caddy validate --config /etc/caddy/Caddyfile --adapter caddyfile
+
+  # deploy-B §9 all-in-one smoke — boots rutster-allinone with
+  # RUTSTER_LOCAL_CERTS=true (Caddy internal CA, no ACME in CI), extracts
+  # the CA root cert from /data, opens wss:// to /twilio/media-stream,
+  # sends Twilio's connected+start handshake frames, streams 200 PCM-zeroed
+  # frames at 20ms cadence, asserts the engine replies with at least one
+  # text frame through the real edge->FOB WS path. Spec §9 acceptance:
+  #   * "boots"
+  #   * "Caddy terminates TLS via its internal CA (no ACME in CI)"
+  #   * "full sim call through the real edge->FOB WS path"
+  # The reload-during-call smoke (Task 9 below) and compose smoke (Task 9)
+  # are separate jobs that depend on this one.
+  smoke:
+    name: smoke (all-in-one TLS sim call)
+    runs-on: ubuntu-latest
+    needs: [image-build]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python (stdlib-only; no pip)
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+
+      # Pull the freshly-built image from the image-build job. Since
+      # jobs run on separate runners + `push: false` in image-build means
+      # the image isn't in any registry, the smoke job rebuilds from the
+      # GHA cache (warm — image-build populated it). This adds ~30s vs
+      # an image-download artifact, but avoids the registry-auth + image-
+      # save/load plumbing.
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Rebuild rutster-allinone:smoke (warm cache from image-build)
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: deploy/Dockerfile
+          target: rutster-allinone
+          tags: rutster-allinone:smoke
+          push: false
+          load: true
+          cache-from: type=gha,scope=rutster-allinone
+
+      - name: Run all-in-one smoke (deploy/smoke/allinone_smoke.py)
+        run: |
+          python3 deploy/smoke/allinone_smoke.py
+        env:
+          RUTSTER_ALLINONE_IMAGE: rutster-allinone:smoke
+          RUTSTER_ALLINONE_PORT: "18443"
+
+  # deploy-B §9 compose smoke — T2 four-service compose stack boots + all
+  # services healthy + Caddy TLS /healthz + /readyz. Lighter than the
+  # all-in-one smoke (which already proved the WS path) — its job is the
+  # orchestrator shape + the network_mode: "service:engine" brain->engine tap
+  # posture across the four services.
+  smoke-compose:
+    name: smoke (T2 compose four-service)
+    runs-on: ubuntu-latest
+    needs: [image-build]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      # Rebuild all three first-party images from the warm GHA cache
+      # populated by image-build. Valkey is upstream (no rebuild needed).
+      - name: Rebuild rutster-edge:smoke
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: deploy/Dockerfile
+          target: rutster-edge
+          tags: rutster-edge:smoke
+          push: false
+          load: true
+          cache-from: type=gha,scope=rutster-edge
+
+      - name: Rebuild rutster-engine:smoke
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: deploy/Dockerfile
+          target: rutster-engine
+          tags: rutster-engine:smoke
+          push: false
+          load: true
+          cache-from: type=gha,scope=rutster-engine
+
+      - name: Rebuild rutster-brain:smoke
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: deploy/Dockerfile
+          target: rutster-brain
+          tags: rutster-brain:smoke
+          push: false
+          load: true
+          cache-from: type=gha,scope=rutster-brain
+
+      # jq is pre-installed on ubuntu-latest GHA runners.
+      - name: Run compose smoke (deploy/smoke/compose_smoke.sh)
+        run: bash deploy/smoke/compose_smoke.sh
+        env:
+          RUTSTER_IMAGES_TAG: smoke
+
+  # deploy-B §9 + spec §3.2 + TLS brief §5 risk 1: Caddy config-reload
+  # during a live simulated call, asserting zero frame drops. The
+  # stream_close_delay 24h mitigation in deploy/Caddyfile is the load-
+  # bearing fixture; caddy #6420 / #7222 are open upstream bugs — the
+  # smoke is "don't trust untested" made CI-regressed.
+  smoke-reload:
+    name: smoke (caddy reload during live call, zero drops)
+    runs-on: ubuntu-latest
+    needs: [smoke]   # reuses the rutster-allinone:smoke image, warm cache
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python (stdlib-only; no pip)
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Rebuild rutster-allinone:smoke (warm cache)
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: deploy/Dockerfile
+          target: rutster-allinone
+          tags: rutster-allinone:smoke
+          push: false
+          load: true
+          cache-from: type=gha,scope=rutster-allinone
+
+      - name: Run reload-during-call smoke (deploy/smoke/reload_during_call.py)
+        run: python3 deploy/smoke/reload_during_call.py
+        env:
+          RUTSTER_ALLINONE_IMAGE: rutster-allinone:smoke
+          RUTSTER_ALLINONE_PORT: "18444"