e2e flow

.github/workflows/test.yml

@@ -14,6 +14,14 @@ on:
         options:
           - 'false'
           - 'true'
+      run_windows_e2e:
+        description: 'Run Windows E2E tests (tauri-driver)'
+        required: false
+        default: 'false'
+        type: choice
+        options:
+          - 'false'
+          - 'true'
 
 permissions:
   contents: read
@@ -191,66 +199,149 @@ jobs:
           mkdir -p ~/.local/share/applications
           export RUST_BACKTRACE=1
           cd app
-          # Core specs — must pass on Linux CI
-          FAILED=0
-          for spec in \
-            test/e2e/specs/login-flow.spec.ts \
-            test/e2e/specs/smoke.spec.ts \
-            test/e2e/specs/navigation.spec.ts \
-            test/e2e/specs/telegram-flow.spec.ts; do
-            SPEC_NAME=$(basename "$spec" .spec.ts)
-            echo "=== Running $SPEC_NAME ==="
-            bash scripts/e2e-run-spec.sh "$spec" "$SPEC_NAME" || {
-              echo "FAILED: $SPEC_NAME"
-              cat /tmp/tauri-driver-e2e-${SPEC_NAME}.log 2>/dev/null || true
-              FAILED=1
-            }
-          done
-          # Extended specs (auth, billing, gmail, notion, payments) are skipped
-          # on Linux CI — webkit2gtk text matching differences cause Settings
-          # page navigation timeouts. Full suite runs on macOS locally.
-          if [ "$FAILED" -eq 1 ]; then
-            echo "Core E2E specs failed"
-            exit 1
+          bash scripts/e2e-run-all-flows.sh
+
+  e2e-macos:
+    name: E2E (macOS / Appium)
+    if: >-
+      github.event_name == 'pull_request' ||
+      github.event_name == 'push' ||
+      (github.event_name == 'workflow_dispatch' && github.event.inputs.run_macos_e2e == 'true')
+    runs-on: macos-latest
+    timeout-minutes: 90
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+          submodules: recursive
+
+      - name: Setup Node.js 24.x
+        uses: actions/setup-node@v4
+        with:
+          node-version: 24.x
+          cache: "yarn"
+
+      - name: Install Rust (rust-toolchain.toml)
+        uses: dtolnay/rust-toolchain@1.93.0
+
+      - name: Cargo.lock fingerprint (deps only)
+        id: cargo-lock-fingerprint
+        shell: bash
+        run: |
+          echo "hash=$(tail -n +8 Cargo.lock | openssl dgst -sha256 | awk '{print $2}')" >> "$GITHUB_OUTPUT"
+
+      - name: Cache Cargo registry and build
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            target
+          key: ${{ runner.os }}-e2e-cargo-${{ steps.cargo-lock-fingerprint.outputs.hash }}
+          restore-keys: |
+            ${{ runner.os }}-e2e-cargo-
+
+      - name: Install dependencies
+        run: yarn install --frozen-lockfile
+
+      - name: Ensure .env exists for E2E build
+        run: |
+          touch .env
+          touch app/.env
+
+      - name: Install Appium and mac2 driver
+        run: |
+          npm install -g appium
+          appium driver install mac2
+
+      - name: Build E2E app bundle
+        run: yarn workspace openhuman-app test:e2e:build
+
+      - name: Run E2E specs
+        run: |
+          cd app
+          bash scripts/e2e-run-all-flows.sh
+
+  e2e-windows:
+    name: E2E (Windows / tauri-driver)
+    if: >-
+      github.event_name == 'pull_request' ||
+      github.event_name == 'push' ||
+      (github.event_name == 'workflow_dispatch' && github.event.inputs.run_windows_e2e == 'true')
+    runs-on: windows-latest
+    timeout-minutes: 90
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+          submodules: recursive
+
+      - name: Setup Node.js 24.x
+        uses: actions/setup-node@v4
+        with:
+          node-version: 24.x
+          cache: "yarn"
+
+      - name: Install Rust (rust-toolchain.toml)
+        uses: dtolnay/rust-toolchain@1.93.0
+        with:
+          targets: x86_64-pc-windows-msvc
+
+      - name: Cargo.lock fingerprint (deps only)
+        id: cargo-lock-fingerprint
+        shell: bash
+        run: |
+          echo "hash=$(tail -n +8 Cargo.lock | openssl dgst -sha256 | awk '{print $2}')" >> "$GITHUB_OUTPUT"
+
+      - name: Cache Cargo registry and build
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            target
+          key: ${{ runner.os }}-e2e-cargo-${{ steps.cargo-lock-fingerprint.outputs.hash }}
+          restore-keys: |
+            ${{ runner.os }}-e2e-cargo-
+
+      - name: Install tauri-driver
+        run: cargo install tauri-driver --version 2.0.5
+
+      - name: Install JS dependencies
+        run: yarn install --frozen-lockfile
+
+      - name: Ensure .env exists for E2E build
+        run: |
+          echo.> .env
+          echo.> app\.env
+        shell: cmd
+
+      - name: Build E2E app
+        run: yarn workspace openhuman-app test:e2e:build
+        shell: bash
+
+      - name: Stage sidecar next to app binary
+        shell: bash
+        run: |
+          # Copy the sidecar so the app can find it at runtime
+          SIDECAR_SRC="$(ls app/src-tauri/binaries/openhuman-core-*.exe 2>/dev/null | head -1)"
+          if [ -z "$SIDECAR_SRC" ]; then
+            echo "WARNING: No Windows sidecar found in binaries/, attempting to stage from target/"
+            SIDECAR_SRC="$(ls target/debug/openhuman-core.exe 2>/dev/null | head -1)"
           fi
-          echo "Core E2E specs passed"
-
-#   e2e-macos:
-#     name: E2E (macOS / Appium)
-#     if: github.event_name == 'workflow_dispatch' && github.event.inputs.run_macos_e2e == 'true'
-#     runs-on: macos-latest
-#     timeout-minutes: 90
-#     steps:
-#       - name: Checkout code
-#         uses: actions/checkout@v4
-#         with:
-#           fetch-depth: 1
-#           submodules: recursive
-
-#       - name: Setup Node.js 24.x
-#         uses: actions/setup-node@v4
-#         with:
-#           node-version: 24.x
-#           cache: "yarn"
-
-#       - name: Install Rust (rust-toolchain.toml)
-#         uses: dtolnay/rust-toolchain@1.93.0
-
-#       - name: Install dependencies
-#         run: yarn install --frozen-lockfile
-
-#       - name: Ensure .env exists for E2E build
-#         run: |
-#           touch .env
-#           touch app/.env
-
-#       - name: Install Appium and mac2 driver
-#         run: |
-#           npm install -g appium
-#           appium driver install mac2
-
-#       - name: Build E2E app bundle
-#         run: yarn workspace openhuman-app test:e2e:build
-
-#       - name: Run all E2E flows
-#         run: yarn workspace openhuman-app test:e2e:all:flows
+          if [ -n "$SIDECAR_SRC" ]; then
+            cp "$SIDECAR_SRC" app/src-tauri/target/debug/openhuman-core-x86_64-pc-windows-msvc.exe
+            echo "Sidecar staged:"
+            ls -la app/src-tauri/target/debug/openhuman-core-*.exe app/src-tauri/target/debug/OpenHuman.exe
+          else
+            echo "WARNING: No sidecar binary found — tests that require core RPC will fail"
+          fi
+
+      - name: Run E2E tests
+        shell: bash
+        run: |
+          export RUST_BACKTRACE=1
+          cd app
+          bash scripts/e2e-run-all-flows.sh

app/package.json

@@ -32,7 +32,7 @@
     "test:e2e:auth": "bash ./scripts/e2e-auth.sh",
     "test:e2e:service-connectivity": "OPENHUMAN_SERVICE_MOCK=1 bash ./scripts/e2e-run-spec.sh test/e2e/specs/service-connectivity-flow.spec.ts service-connectivity",
     "test:e2e:skills-registry": "bash ./scripts/e2e-run-spec.sh test/e2e/specs/skills-registry.spec.ts skills-registry",
-    "test:e2e:skill-execution": "bash ./scripts/e2e-run-spec.sh test/e2e/specs/skill-execution-flow.spec.ts skill-execution",
+    "test:e2e:text-autocomplete": "bash ./scripts/e2e-run-spec.sh test/e2e/specs/text-autocomplete-flow.spec.ts text-autocomplete",
     "test:e2e": "yarn test:e2e:build && yarn test:e2e:login && yarn test:e2e:auth",
     "test:e2e:all:flows": "bash ./scripts/e2e-run-all-flows.sh",
     "test:e2e:all": "yarn test:e2e:build && yarn test:e2e:all:flows",

app/scripts/e2e-auth.sh

@@ -1,4 +1,4 @@
 #!/usr/bin/env bash
 # Run E2E auth & access control tests only. See app/scripts/e2e-run-spec.sh.
 set -euo pipefail
-exec "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/e2e-run-spec.sh" "test/e2e/specs/auth-access-control.spec.ts" "auth"
+exec "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/e2e-run-spec.sh" "test/e2e/specs/auth-session-management.spec.ts" "auth"

app/scripts/e2e-build.sh

@@ -2,8 +2,9 @@
 #
 # Build the app for E2E tests with the mock server URL baked in.
 #
-# - macOS: builds a .app bundle (Appium Mac2)
-# - Linux: builds a debug binary (tauri-driver)
+# - macOS:   builds a .app bundle (Appium Mac2)
+# - Linux:   builds a debug binary (tauri-driver)
+# - Windows: builds a debug binary (tauri-driver)
 #
 # Cargo incremental builds are used by default for faster iteration.
 #
@@ -45,14 +46,22 @@ TAURI_CONFIG_OVERRIDE='{"bundle":{"createUpdaterArtifacts":false}}'
 case "${CI:-}" in 1) export CI=true ;; 0) export CI=false ;; esac
 
 OS="$(uname)"
-if [ "$OS" = "Linux" ]; then
-  # Linux: build debug binary only (no bundle needed for tauri-driver)
-  echo "Building for Linux (debug binary, no bundle)..."
-  npx tauri build -c "$TAURI_CONFIG_OVERRIDE" --debug --no-bundle
-else
-  # macOS: build .app bundle for Appium Mac2
-  echo "Building for macOS (.app bundle)..."
-  npx tauri build -c "$TAURI_CONFIG_OVERRIDE" --bundles app --debug
-fi
+case "$OS" in
+  Linux)
+    # Linux: build debug binary only (no bundle needed for tauri-driver)
+    echo "Building for Linux (debug binary, no bundle)..."
+    npx tauri build -c "$TAURI_CONFIG_OVERRIDE" --debug --no-bundle
+    ;;
+  MINGW*|MSYS*|CYGWIN*|Windows_NT)
+    # Windows: build debug binary only (tauri-driver, like Linux)
+    echo "Building for Windows (debug binary, no bundle)..."
+    npx tauri build -c "$TAURI_CONFIG_OVERRIDE" --debug --no-bundle
+    ;;
+  *)
+    # macOS: build .app bundle for Appium Mac2
+    echo "Building for macOS (.app bundle)..."
+    npx tauri build -c "$TAURI_CONFIG_OVERRIDE" --bundles app --debug
+    ;;
+esac
 
 echo "E2E build complete."

app/scripts/e2e-resolve-node-appium.sh

@@ -25,9 +25,10 @@ if [ "${NODE_MAJOR:-0}" -lt 24 ]; then
   exit 1
 fi
 
-APPIUM_BIN="$(command -v appium 2>/dev/null || true)"
-if [ -z "${APPIUM_BIN:-}" ] || [ ! -x "$APPIUM_BIN" ]; then
-  APPIUM_BIN="$(dirname "$NODE24")/appium"
+# Prefer the appium binary that lives next to the resolved Node 24 binary.
+APPIUM_BIN="$(dirname "$NODE24")/appium"
+if [ ! -x "$APPIUM_BIN" ]; then
+  APPIUM_BIN="$(command -v appium 2>/dev/null || true)"
 fi
 if [ ! -x "$APPIUM_BIN" ]; then
   echo "ERROR: appium not found. Install with: npm install -g appium" >&2

app/scripts/e2e-run-all-flows.sh

@@ -3,30 +3,65 @@
 # Run all E2E WDIO specs sequentially (Appium restarted per spec).
 # Requires a prior E2E app build: yarn test:e2e:build
 #
-set -euo pipefail
+# Failure policy: specs are independent, so one failing spec must NOT abort
+# subsequent specs. We collect every failure and exit non-zero at the end
+# with a summary, so CI sees the full picture instead of bailing on spec #1.
+#
+set -uo pipefail
 
 APP_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 cd "$APP_DIR"
 
+FAILED_SPECS=()
+PASSED_SPECS=()
+
 run() {
-  "$APP_DIR/scripts/e2e-run-spec.sh" "$1" "$2"
+  local spec="$1"
+  local label="$2"
+  echo ""
+  echo "============================================================"
+  echo "[e2e-run-all-flows] START $label ($spec)"
+  echo "============================================================"
+  if "$APP_DIR/scripts/e2e-run-spec.sh" "$spec" "$label"; then
+    echo "[e2e-run-all-flows] PASS  $label"
+    PASSED_SPECS+=("$label")
+  else
+    local rc=$?
+    echo "[e2e-run-all-flows] FAIL  $label (exit=$rc)"
+    FAILED_SPECS+=("$label")
+  fi
 }
 
+run "test/e2e/specs/macos-distribution.spec.ts" "macos-distribution"
+run "test/e2e/specs/auth-session-management.spec.ts" "auth"
+run "test/e2e/specs/permissions-system-access.spec.ts" "permissions-system-access"
+# run "test/e2e/specs/local-model-runtime.spec.ts" "local-model"
+run "test/e2e/specs/system-resource-access.spec.ts" "system-resource-access"
+# run "test/e2e/specs/service-connectivity-flow.spec.ts" "service-connectivity"
+run "test/e2e/specs/memory-system.spec.ts" "memory-system"
+run "test/e2e/specs/automation-scheduling.spec.ts" "automation-scheduling"
+run "test/e2e/specs/chat-interface-flow.spec.ts" "chat-interface"
 run "test/e2e/specs/login-flow.spec.ts" "login"
-run "test/e2e/specs/auth-access-control.spec.ts" "auth"
 run "test/e2e/specs/telegram-flow.spec.ts" "telegram"
+run "test/e2e/specs/discord-flow.spec.ts" "discord"
 run "test/e2e/specs/gmail-flow.spec.ts" "gmail"
 run "test/e2e/specs/notion-flow.spec.ts" "notion"
-run "test/e2e/specs/card-payment-flow.spec.ts" "card-payment"
-run "test/e2e/specs/crypto-payment-flow.spec.ts" "crypto-payment"
-run "test/e2e/specs/conversations-web-channel-flow.spec.ts" "conversations"
-run "test/e2e/specs/local-model-runtime.spec.ts" "local-model"
 run "test/e2e/specs/screen-intelligence.spec.ts" "screen-intelligence"
-OPENHUMAN_SERVICE_MOCK=1 run "test/e2e/specs/service-connectivity-flow.spec.ts" "service-connectivity"
-run "test/e2e/specs/skills-registry.spec.ts" "skills-registry"
-run "test/e2e/specs/skill-execution-flow.spec.ts" "skill-execution"
-run "test/e2e/specs/navigation.spec.ts" "navigation"
-run "test/e2e/specs/smoke.spec.ts" "smoke"
-run "test/e2e/specs/tauri-commands.spec.ts" "tauri-commands"
+run "test/e2e/specs/voice-mode.spec.ts" "voice-mode"
+run "test/e2e/specs/text-autocomplete-flow.spec.ts" "text-autocomplete"
+run "test/e2e/specs/rewards-flow.spec.ts" "rewards-flow"
+run "test/e2e/specs/settings-flow.spec.ts" "settings-flow"
+
+echo ""
+echo "============================================================"
+echo "[e2e-run-all-flows] SUMMARY"
+echo "============================================================"
+echo "  Passed (${#PASSED_SPECS[@]}): ${PASSED_SPECS[*]:-<none>}"
+echo "  Failed (${#FAILED_SPECS[@]}): ${FAILED_SPECS[*]:-<none>}"
+
+if [ "${#FAILED_SPECS[@]}" -gt 0 ]; then
+  echo "[e2e-run-all-flows] One or more specs failed — exiting non-zero."
+  exit 1
+fi
 
 echo "All E2E flows completed."