Merge branch 'origin/develop' into develop

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: lalalune

.codefactor.yml

@@ -2,6 +2,7 @@
 # https://docs.codefactor.io/configuration/customization/
 exclude:
   # Long-lived runtime and integration surfaces are covered by focused tests.
+  - "packages/agent/src/api/server.ts"
   - "plugins/plugin-workflow/**"
   - "packages/agent/src/api/health-routes.ts"
   - "packages/agent/src/runtime/eliza.ts"
@@ -14,6 +15,7 @@ exclude:
   - "packages/app-core/src/services/local-inference/__stress__/cache-stress-helpers.ts"
   - "packages/app-core/src/services/local-inference/dflash-cache-flow.test.ts"
   - "packages/app-core/src/state/startup-phase-restore.ts"
+  - "packages/scripts/capability-router-fixture-server.ts"
   - "packages/ui/src/api/client-agent.ts"
   - "packages/ui/src/api/client-chat.ts"
   - "packages/ui/src/navigation/index.ts"

.github/workflows/elizaos-os-release.yml

@@ -42,6 +42,13 @@ jobs:
           bun run --cwd packages/os/usb-installer typecheck
           bun run --cwd packages/os/usb-installer test
           bun run --cwd packages/os/usb-installer build
+          bunx playwright install --with-deps chromium
+          bun run --cwd packages/os/usb-installer test:e2e
+          if modinfo scsi_debug >/dev/null 2>&1; then
+            bun run --cwd packages/os/usb-installer test:linux-virtual-usb
+          else
+            echo "::notice::scsi_debug kernel module is unavailable on this runner; skipping virtual block-device USB proof."
+          fi
 
       - name: Validate Android installer
         run: |

.github/workflows/lifeops-bench-python.yml

@@ -120,6 +120,10 @@ jobs:
         working-directory: ${{ env.BENCH_DIR }}
         run: uv sync --extra test --extra anthropic
 
+      - name: Build deterministic LifeWorld snapshots
+        working-directory: ${{ env.BENCH_DIR }}
+        run: uv run python -m eliza_lifeops_bench.lifeworld.snapshots --rebuild
+
       - name: Run pytest
         id: pytest
         working-directory: ${{ env.BENCH_DIR }}
@@ -180,6 +184,10 @@ jobs:
         working-directory: ${{ env.BENCH_DIR }}
         run: uv sync --extra test --extra anthropic
 
+      - name: Build deterministic LifeWorld snapshots
+        working-directory: ${{ env.BENCH_DIR }}
+        run: uv run python -m eliza_lifeops_bench.lifeworld.snapshots --rebuild
+
       - name: Run smoke bench (in-process, no API keys)
         id: smoke
         working-directory: ${{ env.BENCH_DIR }}
@@ -341,6 +349,11 @@ jobs:
         working-directory: ${{ env.BENCH_DIR }}
         run: uv sync --extra test --extra anthropic
 
+      - name: Build deterministic LifeWorld snapshots
+        if: steps.gate.outputs.skip != 'true'
+        working-directory: ${{ env.BENCH_DIR }}
+        run: uv run python -m eliza_lifeops_bench.lifeworld.snapshots --rebuild
+
       - name: Run live bench
         if: steps.gate.outputs.skip != 'true'
         id: live

.github/workflows/release-usb-installer.yml

@@ -33,6 +33,16 @@ jobs:
       - run: bun run --cwd packages/os/usb-installer build
       - run: bun run --cwd packages/os/usb-installer typecheck
       - run: bun run --cwd packages/os/usb-installer test
+      - name: Validate USB installer browser and virtual block-device proof
+        if: matrix.platform == 'linux'
+        run: |
+          bunx playwright install --with-deps chromium
+          bun run --cwd packages/os/usb-installer test:e2e
+          if modinfo scsi_debug >/dev/null 2>&1; then
+            bun run --cwd packages/os/usb-installer test:linux-virtual-usb
+          else
+            echo "::notice::scsi_debug kernel module is unavailable on this runner; skipping virtual block-device USB proof."
+          fi
       - name: Package desktop app
         run: bun run --cwd packages/os/usb-installer package:${{ matrix.platform }}
       - uses: actions/upload-artifact@v4

.github/workflows/test.yml

@@ -122,6 +122,9 @@ jobs:
       - name: Remote capability GitHub live evidence self-test
         run: bun run test:remote-capabilities:github-live-evidence:self-test
 
+      - name: Remote capability GitHub live artifact self-test
+        run: bun run test:remote-capabilities:github-live-artifacts:self-test
+
       - name: Remote capability Docker smoke
         run: bun run test:remote-capabilities:docker
 
@@ -548,6 +551,7 @@ jobs:
       - desktop-contract
       - cloud-live-e2e
       - provider-live-e2e
+      - github-live-artifacts
     runs-on: ubuntu-24.04
     steps:
       - name: Check test results
@@ -561,6 +565,7 @@ jobs:
           echo "desktop-contract: ${{ needs.desktop-contract.result }}"
           echo "cloud-live-e2e:   ${{ needs.cloud-live-e2e.result }}"
           echo "provider-live-e2e:${{ needs.provider-live-e2e.result }}"
+          echo "github-live-artifacts:${{ needs.github-live-artifacts.result }}"
           echo "==================================="
           strict_results="${{ github.event_name == 'workflow_dispatch' || github.event_name == 'schedule' }}"
           bad=0
@@ -570,7 +575,8 @@ jobs:
             "plugin-tests:${{ needs.plugin-tests.result }}" \
             "desktop-contract:${{ needs.desktop-contract.result }}" \
             "cloud-live-e2e:${{ needs.cloud-live-e2e.result }}" \
-            "provider-live-e2e:${{ needs.provider-live-e2e.result }}"; do
+            "provider-live-e2e:${{ needs.provider-live-e2e.result }}" \
+            "github-live-artifacts:${{ needs.github-live-artifacts.result }}"; do
             name="${pair%%:*}"
             result="${pair##*:}"
             if [ "$result" = "skipped" ] && [ "$strict_results" != "true" ]; then

bun.lock

@@ -0,0 +1,41 @@
+# Desktop Release Heavy Inventory
+
+The release regression matrix keeps hardware, OS-lifecycle, and subjective visual checks out of the deterministic PR gate. These items remain tracked here so release owners can cover them manually or through heavier packaged-app jobs.
+
+- gameOpenWindow — full round-trip with openGameWindow mock (needs canvas mock update)
+- Abnormal window position (off-screen) is corrected to safe defaults (e2e)
+- Microphone input works after permission is granted (hardware)
+- Swabble fires 'wakeWordDetected' event when wake word is spoken (hardware)
+- Audio transcription produces non-empty text for clear speech (hardware)
+- Camera preview renders in the UI when stream is started (hardware)
+- Switching between front/rear camera works (hardware)
+- takeScreenshot returns a non-empty base64 PNG (hardware)
+- Frame capture mode streams frames at configured interval (hardware)
+- Deep link received while app is closed causes app to launch (e2e)
+- Deep link received while app is open does not launch second instance (e2e)
+- Shortcuts survive window focus changes (e2e)
+- App launches automatically after system restart (e2e)
+- Auto-launch survives app updates (e2e)
+- Keyboard shortcut Cmd+Q triggers quit (e2e)
+- Keyboard shortcut Cmd+R triggers reload (e2e)
+- Keyboard shortcut Cmd+Option+I opens devtools (e2e)
+- Gateway discovery sends gatewayDiscovery push event to renderer (integration)
+- Canvas window is sandboxed — cannot access main app origin (integration)
+- Canvas navigate blocks external URLs (integration)
+- Agent port is reachable via HTTP after status reaches 'running' (integration)
+- Agent crash triggers automatic restart (integration)
+- Stopping agent while starting does not leave zombie process (integration)
+- Check for updates contacts the release server (network)
+- Applying update relaunches the app (e2e)
+- Update check works on both canary and stable channels (network)
+- Tray icon persists after main window is closed (e2e)
+- Main window has native vibrancy effect on macOS (e2e)
+- Context menu closes when clicking elsewhere (e2e)
+- Left-clicking the tray icon opens the companion window (visual)
+- Right-clicking the tray icon shows the tray context menu (visual)
+- Window can be dragged by clicking the header region (visual)
+- Photo quality is acceptable at default settings (hardware)
+- Requesting accessibility opens System Preferences (OS interaction)
+- Permission status reflects actual system state (OS interaction)
+- Context menu appears at cursor position (visual)
+- Power state reflects actual battery status (hardware)

docs/apps/desktop/release-heavy-inventory.md

@@ -0,0 +1,12 @@
+# Desktop Release Regression Checklist
+
+Use this checklist for desktop release checks that still require human visual confirmation, host OS dialogs, or real hardware state. Deterministic coverage belongs in the packaged desktop tests; keep only non-automated confirmation here.
+
+- Left-clicking the tray icon opens the companion window (visual)
+- Right-clicking the tray icon shows the tray context menu (visual)
+- Window can be dragged by clicking the header region (visual)
+- Photo quality is acceptable at default settings (hardware)
+- Requesting accessibility opens System Preferences (OS interaction)
+- Permission status reflects actual system state (OS interaction)
+- Context menu appears at cursor position (visual)
+- Power state reflects actual battery status (hardware)

docs/apps/desktop/release-regression-checklist.md

@@ -129,6 +129,7 @@
     "test:remote-capabilities:naming-audit:self-test": "bun packages/scripts/audit-capability-router-naming.self-test.ts",
     "test:remote-capabilities:fixture-server": "bun packages/scripts/capability-router-fixture-conformance-smoke.ts",
     "test:remote-capabilities:github-live-artifacts": "bun packages/scripts/validate-capability-router-github-live-artifacts.ts",
+    "test:remote-capabilities:github-live-artifacts:self-test": "bun packages/scripts/validate-capability-router-github-live-artifacts.self-test.ts",
     "test:remote-capabilities:github-live-evidence": "bun packages/scripts/validate-capability-router-github-live-evidence.ts",
     "test:remote-capabilities:github-live-evidence:self-test": "bun packages/scripts/validate-capability-router-github-live-evidence.self-test.ts",
     "test:remote-capabilities:validate-live-reports": "bun packages/scripts/validate-capability-router-live-reports.ts",