fix release publishing pipelines (#1417)

Make deployment consume the exact published sensing-server image, publish the two Python packages in lock-step, and enforce the production witness gate.

.github/workflows/cd.yml

@@ -1,14 +1,10 @@
 name: Continuous Deployment
 
 on:
-  push:
-    branches: [ main ]
-    tags: [ 'v*' ]
   workflow_run:
-    workflows: ["Continuous Integration"]
+    workflows: ["wifi-densepose sensing-server → Docker Hub + ghcr.io"]
     types:
       - completed
-    branches: [ main ]
   workflow_dispatch:
     inputs:
       environment:
@@ -19,6 +15,11 @@ on:
         options:
         - staging
         - production
+      image_tag:
+        description: 'Existing ghcr.io/ruvnet/wifi-densepose tag to deploy'
+        required: true
+        default: 'latest'
+        type: string
       force_deploy:
         description: 'Force deployment (skip checks)'
         required: false
@@ -27,7 +28,7 @@ on:
 
 env:
   REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}
+  IMAGE_NAME: ruvnet/wifi-densepose
   KUBE_CONFIG_DATA: ${{ secrets.KUBE_CONFIG_DATA }}
 
 jobs:
@@ -35,7 +36,9 @@ jobs:
   pre-deployment:
     name: Pre-deployment Checks
     runs-on: ubuntu-latest
-    if: github.event.workflow_run.conclusion == 'success' || github.event_name == 'workflow_dispatch'
+    if: |
+      (github.event_name == 'workflow_run' && github.event.workflow_run.conclusion == 'success') ||
+      github.event_name == 'workflow_dispatch'
     outputs:
       deploy_env: ${{ steps.determine-env.outputs.environment }}
       image_tag: ${{ steps.determine-tag.outputs.tag }}
@@ -43,6 +46,7 @@ jobs:
     - name: Checkout code
       uses: actions/checkout@v4
       with:
+        ref: ${{ github.event.workflow_run.head_sha || github.sha }}
         submodules: recursive
 
     - name: Determine deployment environment
@@ -50,14 +54,12 @@ jobs:
       env:
         # Use environment variable to prevent shell injection
         GITHUB_EVENT_NAME: ${{ github.event_name }}
-        GITHUB_REF: ${{ github.ref }}
+        PUBLISHED_REF: ${{ github.event.workflow_run.head_branch }}
         GITHUB_INPUT_ENVIRONMENT: ${{ github.event.inputs.environment }}
       run: |
         if [[ "$GITHUB_EVENT_NAME" == "workflow_dispatch" ]]; then
           echo "environment=$GITHUB_INPUT_ENVIRONMENT" >> $GITHUB_OUTPUT
-        elif [[ "$GITHUB_REF" == "refs/heads/main" ]]; then
-          echo "environment=staging" >> $GITHUB_OUTPUT
-        elif [[ "$GITHUB_REF" == refs/tags/v* ]]; then
+        elif [[ "$PUBLISHED_REF" == v* ]]; then
           echo "environment=production" >> $GITHUB_OUTPUT
         else
           echo "environment=staging" >> $GITHUB_OUTPUT
@@ -65,16 +67,23 @@ jobs:
 
     - name: Determine image tag
       id: determine-tag
+      env:
+        GITHUB_EVENT_NAME: ${{ github.event_name }}
+        PUBLISHED_REF: ${{ github.event.workflow_run.head_branch }}
+        PUBLISHED_SHA: ${{ github.event.workflow_run.head_sha }}
+        INPUT_IMAGE_TAG: ${{ github.event.inputs.image_tag }}
       run: |
-        if [[ "${{ github.ref }}" == refs/tags/v* ]]; then
-          echo "tag=${GITHUB_REF#refs/tags/}" >> $GITHUB_OUTPUT
+        if [[ "$GITHUB_EVENT_NAME" == "workflow_dispatch" ]]; then
+          echo "tag=$INPUT_IMAGE_TAG" >> $GITHUB_OUTPUT
+        elif [[ "$PUBLISHED_REF" == v* ]]; then
+          echo "tag=$PUBLISHED_REF" >> $GITHUB_OUTPUT
         else
-          echo "tag=${{ github.sha }}" >> $GITHUB_OUTPUT
+          echo "tag=sha-${PUBLISHED_SHA:0:7}" >> $GITHUB_OUTPUT
         fi
 
     - name: Verify image exists
       run: |
-        docker manifest inspect ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.determine-tag.outputs.tag }}
+        docker manifest inspect "${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.determine-tag.outputs.tag }}"
 
   # Deploy to staging
   deploy-staging:
@@ -129,7 +138,10 @@ jobs:
     name: Deploy to Production
     runs-on: ubuntu-latest
     needs: [pre-deployment, deploy-staging]
-    if: needs.pre-deployment.outputs.deploy_env == 'production' || (github.ref == 'refs/tags/v*' && needs.deploy-staging.result == 'success')
+    if: |
+      always() &&
+      needs.pre-deployment.result == 'success' &&
+      needs.pre-deployment.outputs.deploy_env == 'production'
     environment:
       name: production
       url: https://wifi-densepose.com
@@ -210,7 +222,7 @@ jobs:
         # kubectl scale rs -n wifi-densepose -l app=wifi-densepose,version!=green --replicas=0
 
     - name: Upload deployment artifacts
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
         name: production-deployment-${{ github.run_number }}
         path: |
@@ -260,7 +272,7 @@ jobs:
   post-deployment:
     name: Post-deployment Monitoring
     runs-on: ubuntu-latest
-    needs: [deploy-staging, deploy-production]
+    needs: [pre-deployment, deploy-staging, deploy-production]
     if: always() && (needs.deploy-staging.result == 'success' || needs.deploy-production.result == 'success')
     steps:
     - name: Monitor deployment health
@@ -281,7 +293,7 @@ jobs:
         done
 
     - name: Update deployment status
-      uses: actions/github-script@v6
+      uses: actions/github-script@v7
       with:
         script: |
           const deployEnv = '${{ needs.pre-deployment.outputs.deploy_env }}';
@@ -300,7 +312,7 @@ jobs:
   notify:
     name: Notify Deployment Status
     runs-on: ubuntu-latest
-    needs: [deploy-staging, deploy-production, post-deployment]
+    needs: [pre-deployment, deploy-staging, deploy-production, post-deployment]
     if: always()
     steps:
     - name: Notify Slack on success
@@ -332,7 +344,7 @@ jobs:
 
     - name: Create deployment issue on failure
       if: needs.deploy-production.result == 'failure'
-      uses: actions/github-script@v6
+      uses: actions/github-script@v7
       with:
         script: |
           github.rest.issues.create({
@@ -355,4 +367,4 @@ jobs:
             **Logs:** Check the workflow run for detailed error messages.
             `,
             labels: ['deployment', 'production', 'urgent']
-          })
+          })

.github/workflows/pip-release.yml

@@ -34,9 +34,8 @@
 # dedicated follow-up commit (drop `password:`, add the OIDC id-token
 # permission + `environment: pypi`) so there is no capability gap between.
 #
-# Q3 (witness hash v2 — open in ADR-117 §11.3) MUST be resolved
-# before the first v2.0.0 publish. When v2 lands, add a parallel
-# step that verifies the v2 hash against the Rust pipeline.
+# Production publishing fails closed until the ADR-117 §11.3 v2 witness
+# hash exists. TestPyPI remains usable to validate release artifacts.
 
 name: pip-release
 
@@ -83,7 +82,7 @@ jobs:
             arch: x86_64
           - os: ubuntu-latest
             arch: aarch64
-          - os: macos-13          # x86_64 runner
+          - os: macos-15-intel    # x86_64 runner
             arch: x86_64
           - os: macos-14          # arm64 runner
             arch: arm64
@@ -152,6 +151,46 @@ jobs:
           path: sdist/*.tar.gz
           if-no-files-found: error
 
+  build-ruview:
+    name: Build ruview meta-package
+    if: |
+      github.event_name == 'workflow_dispatch' && inputs.target == 'v2-wheels' ||
+      startsWith(github.ref, 'refs/tags/v2.')
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v6
+        with:
+          python-version: '3.12'
+      - name: Verify lock-step package versions
+        shell: python
+        run: |
+          import pathlib
+          import tomllib
+
+          root = pathlib.Path("python")
+          core = tomllib.loads((root / "pyproject.toml").read_text(encoding="utf-8"))
+          meta = tomllib.loads((root / "ruview-meta" / "pyproject.toml").read_text(encoding="utf-8"))
+          core_version = core["project"]["version"]
+          meta_version = meta["project"]["version"]
+          expected_dependency = f"wifi-densepose=={core_version}"
+          if meta_version != core_version:
+              raise SystemExit(
+                  f"package versions differ: wifi-densepose={core_version}, ruview={meta_version}"
+              )
+          if expected_dependency not in meta["project"]["dependencies"]:
+              raise SystemExit(f"ruview must depend on {expected_dependency}")
+          print(f"lock-step version: {core_version}")
+      - name: Build ruview wheel and sdist
+        run: |
+          python -m pip install --upgrade pip build
+          python -m build python/ruview-meta --outdir ruview-dist
+      - uses: actions/upload-artifact@v4
+        with:
+          name: ruview
+          path: ruview-dist/*
+          if-no-files-found: error
+
   # ────────────────────────────────────────────────────────────────
   # v1.99.0 — tombstone wheel (pure Python, single sdist + wheel)
   # ────────────────────────────────────────────────────────────────
@@ -236,18 +275,29 @@ jobs:
   # ────────────────────────────────────────────────────────────────
 
   publish-v2:
-    name: Publish v2 wheels
-    needs: [build-wheels, build-sdist]
+    name: Publish wifi-densepose + ruview
+    needs: [build-wheels, build-sdist, build-ruview]
     if: |
       always() &&
       needs.build-wheels.result == 'success' &&
       needs.build-sdist.result == 'success' &&
+      needs.build-ruview.result == 'success' &&
       (
         github.event_name == 'workflow_dispatch' && inputs.target == 'v2-wheels' ||
         startsWith(github.ref, 'refs/tags/v2.')
       )
     runs-on: ubuntu-latest
     steps:
+      - uses: actions/checkout@v4
+      - name: Enforce production witness gate
+        if: |
+          startsWith(github.ref, 'refs/tags/v2.') ||
+          (github.event_name == 'workflow_dispatch' && inputs.publish_to == 'pypi')
+        run: |
+          test -s archive/v1/data/proof/expected_features_v2.sha256 || {
+            echo "::error::ADR-117 §11.3 release gate is incomplete: archive/v1/data/proof/expected_features_v2.sha256 is missing or empty"
+            exit 1
+          }
       - name: Gather all artifacts into dist/
         uses: actions/download-artifact@v4
         with:
@@ -264,7 +314,7 @@ jobs:
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           repository-url: https://test.pypi.org/legacy/
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          password: ${{ secrets.TESTPYPI_API_TOKEN }}
           packages-dir: dist
           skip-existing: true
       - name: Publish to PyPI
@@ -275,6 +325,7 @@ jobs:
         with:
           password: ${{ secrets.PYPI_API_TOKEN }}
           packages-dir: dist
+          verbose: true
 
   publish-tombstone:
     name: Publish v1.99 tombstone
@@ -299,7 +350,7 @@ jobs:
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           repository-url: https://test.pypi.org/legacy/
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          password: ${{ secrets.TESTPYPI_API_TOKEN }}
           packages-dir: dist
           skip-existing: true
       - name: Publish to PyPI

CHANGELOG.md

@@ -8,8 +8,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 ### Changed
-- **`wifi-densepose` promoted to `2.0.0` stable; `ruview` `2.0.0` first stable publish (ADR-184 P2).** Dropped the `a1` alpha suffix on both sibling packages (`python/pyproject.toml`, `python/ruview-meta/pyproject.toml`) and flipped their trove classifier `Development Status :: 3 - Alpha` → `5 - Production/Stable`; the `ruview` meta-package's `wifi-densepose==2.0.0a1` dependency pins (base + `[client]`) were repointed to `==2.0.0`. Pip-release now authenticates via Trusted Publishing (see the entry below). **Version-metadata prep only — nothing is published by this change**: the actual PyPI upload (ADR-184 P3) is still gated on the one-time manual Trusted Publisher registration on pypi.org that only the repo owner can perform. Justified as "stable": the default (no-extras) wheel builds at 279 KB (`maturin build --release --strip`) and the base non-SOTA suite is green — `pytest python/tests/` (excluding the `[aether]`/`[meridian]`/`[mat]` extra modules) = **185 passed, 0 failed** (smoke / keypoint / pose / vitals / bfld / security / WS+MQTT client).
-- **CI (ADR-184): `pip-release.yml` publish job migrated to PyPI OIDC Trusted Publishing** (commit `cc153e8b5`; refs #785, completes ADR-117). The release workflow now authenticates to PyPI via short-lived OIDC tokens (`id-token: write`) instead of a long-lived `PYPI_API_TOKEN` secret. **Not yet active**: publishing will fail until the matching Trusted Publisher is registered manually on pypi.org (a one-time, per-project step that cannot be automated from CI) — ADR-184 P1 tracks this as the remaining gate (status recorded in `dfc4c1abd`).
+- **`wifi-densepose` promoted to `2.0.0` stable; `ruview` `2.0.0` prepared for its first stable publish (ADR-184 P2).** Dropped the `a1` alpha suffix on both sibling packages (`python/pyproject.toml`, `python/ruview-meta/pyproject.toml`) and flipped their trove classifier `Development Status :: 3 - Alpha` → `5 - Production/Stable`; the `ruview` meta-package's `wifi-densepose==2.0.0a1` dependency pins (base + `[client]`) were repointed to `==2.0.0`. **Version-metadata prep only — nothing is published by this change**: the actual PyPI upload remains gated on the ADR-117 v2 witness hash. Justified as "stable": the default (no-extras) wheel builds at 279 KB (`maturin build --release --strip`) and the base non-SOTA suite is green — `pytest python/tests/` (excluding the `[aether]`/`[meridian]`/`[mat]` extra modules) = **185 passed, 0 failed** (smoke / keypoint / pose / vitals / bfld / security / WS+MQTT client).
+- **CI (ADR-184): `pip-release.yml` keeps token-based PyPI authentication until Trusted Publishing is registered.** An OIDC migration was attempted in `cc153e8b5` and reverted in `82d5c7339` so releases would not enter a half-configured state. Production currently uses `PYPI_API_TOKEN`; TestPyPI uses its independent `TESTPYPI_API_TOKEN`. The workflow now builds and publishes `wifi-densepose` and `ruview` together, verifies their versions and dependency pin match, and fails closed before production upload when `expected_features_v2.sha256` is absent.
 - **`@ruvnet/rvagent` startup optimization — stdio time-to-first-response ~242 ms → ~189 ms (−22%; MEASURED, median of repeated `initialize` round-trips against `dist/index.js`, this container, reproduce with a piped-stdin timer).** Two changes: (1) `./http-transport.js` is now imported **lazily** inside the `RVAGENT_HTTP_PORT` branch — it chain-loads the MCP SDK's `streamableHttp` module (~48 ms MEASURED via per-module `import()` timing), which the default stdio path never uses; (2) the advertised JSON Schemas generated from the Zod sources are memoized per tool instead of re-walking the Zod tree on every `tools/list` (matters under the session-per-server HTTP model where each session lists tools). No behavior change: 99/99 jest tests, HTTP session flow re-smoke-tested through the lazy path. The `@ruvnet/ruview` harness CLI was profiled too and left alone — 50 ms vs the ~29 ms bare `node -e ''` floor on the same box (MEASURED), i.e. already near the interpreter floor with zero dependencies.
 
 ### Deprecated

docs/integrations/pypi-release.md

@@ -4,9 +4,12 @@ Operations doc for the `.github/workflows/pip-release.yml` CI workflow.
 
 ## Auth
 
-The workflow uses one GitHub Actions secret named `PYPI_API_TOKEN`.
-It's a project-token issued by the rUv PyPI account with upload
-scope for both `wifi-densepose` and `ruview`.
+Production uses the GitHub Actions secret `PYPI_API_TOKEN`. It is a
+project token issued by the rUv PyPI account with upload scope for both
+`wifi-densepose` and `ruview`.
+
+TestPyPI uses a separate `TESTPYPI_API_TOKEN` secret issued by
+test.pypi.org. PyPI and TestPyPI accounts and tokens are independent.
 
 ## Refreshing the token
 
@@ -47,16 +50,19 @@ Per ADR-117 §7.3, the tombstone publishes first so it claims the
    tombstone live at `https://pypi.org/project/wifi-densepose/1.99.0/`
 2. Verify: `pip install wifi-densepose==1.99.0; python -c "import
    wifi_densepose"` → ImportError with migration URL.
-3. `git tag v2.0.0-pip && git push origin v2.0.0-pip` → v2 wheel
-   matrix live at `https://pypi.org/project/wifi-densepose/2.0.0/`.
-4. (Optional, in lock-step) build + publish a matching `ruview`
-   release from `python/ruview-meta/` so the meta-package version
-   stays pinned to the same wifi-densepose version.
+3. Confirm `archive/v1/data/proof/expected_features_v2.sha256` is
+   committed and non-empty. Production publishing fails closed without it.
+4. `git tag v2.0.0-pip && git push origin v2.0.0-pip` → the v2
+   `wifi-densepose` wheel matrix and matching `ruview` wheel/sdist are
+   published together. Their versions and dependency pin are checked in CI.
+5. Verify both `https://pypi.org/project/wifi-densepose/2.0.0/` and
+   `https://pypi.org/project/ruview/2.0.0/`.
 
 ## Off-loop manual gates
 
-- **Q3** (ADR-117 §11.3) — generate `expected_features_v2.sha256`
-  from the v2 Rust pipeline before any v2 publish.
+- **Q3** (ADR-117 §11.3) — generate
+  `archive/v1/data/proof/expected_features_v2.sha256` from the v2 Rust
+  pipeline before a production v2 publish. The workflow enforces this gate.
 - **OIDC Trusted Publisher** — not used. The workflow is token-based;
   this is a deliberate choice to keep the secret refresh entirely in
   GCP. If the project migrates to OIDC later, remove `password:`