Add Kind for CI E2E testing, improve local test workflow

.claude/agents/playwright-test-generator.md

@@ -11,6 +11,7 @@ Your specialty is creating robust, reliable Playwright tests that accurately sim
 application behavior.
 
 # For each test you generate
+
 - Obtain the test plan with all the steps and verification specification
 - Run the `generator_setup_page` tool to set up page for the scenario
 - For each step and verification in the scenario, do the following:
@@ -29,31 +30,36 @@ application behavior.
    <example-generation>
    For following plan:
 
-   ```markdown file=specs/plan.md
-   ### 1. Adding New Todos
-   **Seed:** `tests/seed.spec.ts`
+  ```markdown file=specs/plan.md
+  ### 1. Adding New Todos
+
+  **Seed:** `tests/seed.spec.ts`
+
+  #### 1.1 Add Valid Todo
+
+  **Steps:**
+
+  1. Click in the "What needs to be done?" input field
+
+  #### 1.2 Add Multiple Todos
 
-   #### 1.1 Add Valid Todo
-   **Steps:**
-   1. Click in the "What needs to be done?" input field
+  ...
+  ```
 
-   #### 1.2 Add Multiple Todos
-   ...
-   ```
+  Following file is generated:
 
-   Following file is generated:
+  ```ts file=add-valid-todo.spec.ts
+  // spec: specs/plan.md
+  // seed: tests/seed.spec.ts
 
-   ```ts file=add-valid-todo.spec.ts
-   // spec: specs/plan.md
-   // seed: tests/seed.spec.ts
+  test.describe('Adding New Todos', () => {
+    test('Add Valid Todo', async { page } => {
+      // 1. Click in the "What needs to be done?" input field
+      await page.click(...);
 
-   test.describe('Adding New Todos', () => {
-     test('Add Valid Todo', async { page } => {
-       // 1. Click in the "What needs to be done?" input field
-       await page.click(...);
+      ...
+    });
+  });
+  ```
 
-       ...
-     });
-   });
-   ```
-   </example-generation>
+   </example-generation>

.claude/agents/playwright-test-healer.md

@@ -11,6 +11,7 @@ resolving Playwright test failures. Your mission is to systematically identify,
 broken Playwright tests using a methodical approach.
 
 Your workflow:
+
 1. **Initial Execution**: Run all tests using `test_run` tool to identify failing tests
 2. **Debug failed tests**: For each failing test run `test_debug`.
 3. **Error Investigation**: When the test pauses on errors, use available Playwright MCP tools to:
@@ -31,6 +32,7 @@ Your workflow:
 7. **Iteration**: Repeat the investigation and fixing process until the test passes cleanly
 
 Key principles:
+
 - Be systematic and thorough in your debugging approach
 - Document your findings and reasoning for each fix
 - Prefer robust, maintainable solutions over quick hacks
@@ -42,4 +44,4 @@ Key principles:
   so that it is skipped during the execution. Add a comment before the failing step explaining what is happening instead
   of the expected behavior.
 - Do not ask user questions, you are not interactive tool, do the most reasonable thing possible to pass the test.
-- Never wait for networkidle or use other discouraged or deprecated apis
+- Never wait for networkidle or use other discouraged or deprecated apis

.claude/agents/playwright-test-planner.md

@@ -44,9 +44,10 @@ You will:
    Submit your test plan using `planner_save_plan` tool.
 
 **Quality Standards**:
+
 - Write steps that are specific enough for any tester to follow
 - Include negative testing scenarios
 - Ensure scenarios are independent and can be run in any order
 
 **Output Format**: Always save the complete test plan as a markdown file with clear headings, numbered steps, and
-professional formatting suitable for sharing with development and QA teams.
+professional formatting suitable for sharing with development and QA teams.

.github/workflows/ci.yml

@@ -0,0 +1,214 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+  actions: read
+
+env:
+  KIND_CLUSTER_NAME: mainloop-test
+
+jobs:
+  lint:
+    name: Lint
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    permissions:
+      checks: write # Required for trunk-action to post annotations
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+      - uses: trunk-io/trunk-action@v1
+
+  build:
+    name: Build ${{ matrix.image }}
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - image: backend
+            file: backend/Dockerfile
+            context: .
+            tag: mainloop-backend:test
+          - image: frontend
+            file: frontend/Dockerfile
+            context: .
+            tag: mainloop-frontend:test
+            build-args: VITE_API_URL=http://localhost:8000
+          - image: agent
+            file: claude-agent/Dockerfile
+            context: ./claude-agent
+            tag: mainloop-agent-controller:test
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build image
+        uses: docker/build-push-action@v6
+        with:
+          context: ${{ matrix.context }}
+          file: ${{ matrix.file }}
+          build-args: ${{ matrix.build-args }}
+          tags: ${{ matrix.tag }}
+          outputs: type=docker,dest=/tmp/${{ matrix.image }}.tar
+          cache-from: type=gha,scope=${{ matrix.image }}
+          cache-to: type=gha,mode=max,scope=${{ matrix.image }}
+
+      - name: Upload image artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.image }}-image
+          path: /tmp/${{ matrix.image }}.tar
+          retention-days: 1
+
+  e2e:
+    name: E2E Tests
+    needs: [lint, build]
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 9
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+          cache: pnpm
+          cache-dependency-path: pnpm-lock.yaml
+
+      - name: Install dependencies
+        run: pnpm install
+
+      - name: Cache Playwright browsers
+        id: playwright-cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/ms-playwright
+          key: playwright-${{ runner.os }}-${{ hashFiles('frontend/package.json') }}
+          restore-keys: |
+            playwright-${{ runner.os }}-
+
+      - name: Install Playwright browsers
+        if: steps.playwright-cache.outputs.cache-hit != 'true'
+        run: pnpm exec playwright install --with-deps chromium
+        working-directory: frontend
+
+      - name: Install Playwright deps (if cached)
+        if: steps.playwright-cache.outputs.cache-hit == 'true'
+        run: pnpm exec playwright install-deps chromium
+        working-directory: frontend
+
+      - name: Setup Kind
+        uses: helm/kind-action@v1.12.0
+        with:
+          cluster_name: ${{ env.KIND_CLUSTER_NAME }}
+          config: ./scripts/kind/cluster-config.yaml
+
+      - name: Download all image artifacts
+        uses: actions/download-artifact@v4
+        with:
+          pattern: '*-image'
+          path: /tmp/images
+          merge-multiple: true
+
+      - name: Load images into Docker and Kind
+        run: |
+          # Load into Docker (parallel)
+          docker load --input /tmp/images/backend.tar &
+          docker load --input /tmp/images/frontend.tar &
+          docker load --input /tmp/images/agent.tar &
+          wait
+
+          # Load into Kind (parallel)
+          kind load docker-image mainloop-backend:test --name ${{ env.KIND_CLUSTER_NAME }} &
+          kind load docker-image mainloop-frontend:test --name ${{ env.KIND_CLUSTER_NAME }} &
+          kind load docker-image mainloop-agent-controller:test --name ${{ env.KIND_CLUSTER_NAME }} &
+          wait
+
+      - name: Create secrets
+        env:
+          CLAUDE_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          kubectl create namespace mainloop
+          kubectl create secret generic mainloop-secrets \
+            --namespace mainloop \
+            --from-literal=claude-secret-token="${CLAUDE_TOKEN}" \
+            --from-literal=github-token="${GH_TOKEN}"
+
+      - name: Deploy to Kind
+        run: |
+          kubectl apply -k k8s/apps/mainloop/overlays/test --server-side
+          kubectl rollout status deployment/mainloop-backend -n mainloop --timeout=180s
+          kubectl rollout status deployment/mainloop-frontend -n mainloop --timeout=180s
+          kubectl rollout status statefulset/postgres -n mainloop --timeout=120s
+
+      - name: Wait for services
+        run: |
+          # Wait for endpoints to be ready (more reliable than just pod ready)
+          kubectl wait --for=jsonpath='{.subsets[0].addresses[0].ip}' \
+            endpoints/mainloop-backend -n mainloop --timeout=120s || true
+          kubectl wait --for=jsonpath='{.subsets[0].addresses[0].ip}' \
+            endpoints/mainloop-frontend -n mainloop --timeout=120s || true
+
+          # Verify HTTP endpoints are responding
+          curl -sf --retry 10 --retry-delay 3 --retry-all-errors \
+            http://localhost:8000/health || {
+            echo "Backend failed to start"
+            kubectl logs -n mainloop deployment/mainloop-backend --tail=50
+            exit 1
+          }
+          echo "Backend healthy"
+
+          curl -sf --retry 10 --retry-delay 3 --retry-all-errors \
+            http://localhost:3000 || {
+            echo "Frontend failed to start"
+            kubectl logs -n mainloop deployment/mainloop-frontend --tail=50
+            exit 1
+          }
+          echo "Frontend healthy"
+
+      - name: Run Playwright tests
+        run: |
+          cd frontend
+          PLAYWRIGHT_BASE_URL=http://localhost:3000 pnpm exec playwright test
+        env:
+          CI: true
+
+      - name: Upload test results
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: playwright-report
+          path: frontend/playwright-report/
+          retention-days: 7
+
+      - name: Upload failure screenshots
+        uses: actions/upload-artifact@v4
+        if: failure()
+        with:
+          name: test-screenshots
+          path: frontend/test-results/
+          retention-days: 7

.gitignore

@@ -1,7 +1,6 @@
 # Dependencies
 node_modules/
 .pnpm-debug.log
-pnpm-lock.yaml
 
 # Python
 __pycache__/

.mcp.json

@@ -2,10 +2,7 @@
   "mcpServers": {
     "playwright-test": {
       "command": "bash",
-      "args": [
-        "-c",
-        "cd frontend && npx playwright run-test-mcp-server"
-      ]
+      "args": ["-c", "cd frontend && npx playwright run-test-mcp-server"]
     }
   }
-}
+}

.trunk/trunk.yaml

@@ -11,6 +11,13 @@ runtimes:
     - python@3.10.8
 # This is the section where you manage your linters. (https://docs.trunk.io/check/configuration)
 lint:
+  definitions:
+    - name: prettier
+      runtime: node
+      package: prettier
+      extra_packages:
+        - prettier-plugin-svelte
+        - prettier-plugin-tailwindcss
   ignore:
     # K8s security best practices - remaining issues are acceptable for internal Tailscale-only services
     # Fixed: container security contexts, health probes, RBAC over-permissions