chore: tighten deploy checklist and lint setup

.cursorrules

@@ -35,12 +35,14 @@ pnpm test:ui          # Vitest UI dashboard
 pnpm test:coverage    # Generate coverage report
 
 # Deployment to Cloudflare
-npx @opennextjs/cloudflare build  # REQUIRED before deploy
+pnpm build                         # Standard Next.js production build
+pnpm lint                          # Fix lint errors before packaging
+npx @opennextjs/cloudflare build   # REQUIRED before deploy
 npx wrangler deploy                # Deploy to Cloudflare
 npx wrangler tail                  # View live logs
 ```
 
-**CRITICAL**: Always run `npx @opennextjs/cloudflare build` before deploying. Standard `next build` is insufficient.
+**CRITICAL**: Always run the full deployment sequence above—`pnpm build`, `pnpm lint`, and `npx @opennextjs/cloudflare build`—before deploying. Skipping any step can push stale or broken assets.
 
 ## Agent Configuration
 
@@ -322,6 +324,7 @@ return { json: { output: actual } };
 ### Deploying to Cloudflare
 ```bash
 pnpm build
+pnpm lint
 npx @opennextjs/cloudflare build
 npx wrangler deploy
 ```
@@ -332,13 +335,24 @@ npx wrangler deploy
 
 1. **Never use npm.** Always run commands with pnpm (e.g. `pnpm install`, `pnpm dev`, `pnpm build`).
 
-2. **Before every deploy, run the Cloudflare build step:**
+2. **Run the standard Next.js build to catch compile issues early:**
+   ```bash
+   pnpm build
+   ```
+
+3. **Fix lint errors before packaging for Cloudflare:**
+   ```bash
+   pnpm lint
+   ```
+   Warnings are acceptable, but errors must be resolved before moving on.
+
+4. **Before every deploy, run the Cloudflare build step:**
    ```bash
    npx @opennextjs/cloudflare build
    ```
    If this fails, fix the error before proceeding—Wrangler deploys without this step will push stale assets.
 
-3. **Deploy only after a successful OpenNext build using:**
+5. **Deploy only after a successful OpenNext build using:**
    ```bash
    npx wrangler deploy
    ```

CLAUDE.md

@@ -25,24 +25,61 @@ npx wrangler deploy                # Deploy to Cloudflare (requires OpenNext bui
 npx wrangler tail                  # View live logs from deployed worker
 ```
 
-**Critical**: 
+**Critical Deployment Checklist (must be followed exactly):**
-- Always run `npx @opennextjs/cloudflare build` before deploying. The standard `next build` alone is insufficient for Cloudflare deployment.
+
-- Always use `npx wrangler deploy` without any `--env` flags. The deployment uses the default configuration from `wrangler.jsonc` with route `agents.nicholai.work`.
+1. **Never use npm.** Always run commands with pnpm (e.g., `pnpm install`, `pnpm dev`, `pnpm build`).
+
+2. **Run the standard Next.js production build:**
+   ```bash
+   pnpm build
+   ```
+   Do not skip this step—it’s the fastest way to catch type or compile issues before packaging for Cloudflare.
+
+3. **Fix lint errors before deploying:**
+   ```bash
+   pnpm lint
+   ```
+   Resolve every reported error (warnings are acceptable) before proceeding so Cloudflare builds don’t fail mid-process.
+
+4. **Before every deploy, run the Cloudflare build step:**
+   ```bash
+   npx @opennextjs/cloudflare build
+   ```
+   If this fails, fix the error before proceeding—Wrangler deploys without this step will push stale assets.
+
+5. **Deploy only after a successful OpenNext build:**
+   ```bash
+   npx wrangler deploy
+   ```
+   **Do NOT use `--env` flags.** The deployment uses the default configuration from `wrangler.jsonc` with route `agents.nicholai.work`.
+
+**Troubleshooting:**
+- "No updated asset files to upload": you skipped the Cloudflare build; rerun step 2
+- ESLint config errors during build: they're informational—build still succeeds, but address them separately
+- Viewport metadata warning: move viewport values from metadata to generateViewport per Next.js docs
+
+**No deploy is compliant unless each step above is completed and verified.**
 
 ## Architecture
 
 ### Agent Configuration
-- Agents are defined via environment variables: `AGENT_N_URL`, `AGENT_N_NAME`, `AGENT_N_DESCRIPTION` (where N = 1, 2, 3...)
+- **Standard agents** defined via environment variables: `AGENT_N_URL`, `AGENT_N_NAME`, `AGENT_N_DESCRIPTION` (where N = 1, 2, 3...)
-- `/api/agents` dynamically discovers agents by iterating through numbered environment variables
+- **Custom agents** use special environment variables:
+  - `CUSTOM_AGENT_WEBHOOK` - n8n webhook for custom agent message processing
+  - `CUSTOM_AGENT_REGISTRATION_WEBHOOK` - n8n webhook for storing agent prompts
+- `/api/agents` dynamically discovers standard agents by iterating through numbered environment variables
 - Each agent has a webhook URL pointing to an n8n workflow
 - Agent selection is persisted to localStorage using agent-specific keys
+- Custom agents (created via Morgan) have `agentId` format: `custom-{uuid}`
 
 ### Message Flow
 1. User submits message through `ChatInterface` component
 2. POST `/api/chat` receives message with agentId, sessionId, timestamp, and optional base64 images
-3. Route extracts webhook URL from environment variables based on agentId format (`agent-N`)
+3. Route extracts webhook URL:
-4. Message forwarded to n8n webhook with all metadata
+   - Standard agents (`agent-N`): Uses `AGENT_N_URL` from environment variables
-5. Response parsed from n8n (supports streaming chunks and diff tool calls)
+   - Custom agents (`custom-*`): Uses `CUSTOM_AGENT_WEBHOOK` from environment variables
+4. Message forwarded to n8n webhook with all metadata (including systemPrompt for custom agents)
+5. Response parsed from n8n (supports streaming chunks, tool calls, and regular messages)
 6. Messages stored in localStorage per agent (`chat-messages-{agentId}`)
 
 ### Session Management
@@ -57,16 +94,45 @@ npx wrangler tail                  # View live logs from deployed worker
 - `MarkdownRenderer` parses diff-tool blocks and renders via `DiffTool` → `DiffDisplay` components
 - Diff props: `oldCode`, `newCode`, `title`, `language`
 
+### Agent Forge Feature
+- **Morgan (Agent Architect)** - Typically `agent-2`, creates custom agents users can pin or use immediately
+- System prompt: `.fortura-core/web-agents/agent-architect-web.md`
+- **Custom Agent Creation Flow:**
+  1. User asks Morgan to create an agent
+  2. Morgan outputs `messageType: "tool_call"` with `create_agent_package` payload
+  3. Client displays `AgentForgeCard` with animated reveal
+  4. User actions: **Use now** (registers + switches), **Pin for later** (saves to localStorage), **Share** (copies to clipboard)
+- **Storage:** Custom agents stored in localStorage `pinned-agents` array with structure:
+  ```typescript
+  {
+    agentId: "custom-{uuid}",
+    displayName: string,
+    summary: string,
+    tags: string[],
+    systemPrompt: string,
+    recommendedIcon: string,
+    whenToUse: string,
+    pinnedAt: string,
+    note?: string
+  }
+  ```
+- Custom agents use `CUSTOM_AGENT_WEBHOOK` instead of numbered agent URLs
+- Registration webhook (`CUSTOM_AGENT_REGISTRATION_WEBHOOK`) stores prompts when user pins/uses agents
+
 ## Code Structure
 
 ### API Routes
 - `src/app/api/agents/route.ts` - Discovers and returns configured agents from environment variables
+- `src/app/api/agents/create/route.ts` - Registers custom agents with n8n via registration webhook
 - `src/app/api/chat/route.ts` - Proxies chat messages to agent webhooks, handles streaming responses and diff tool calls
+- `src/app/api/flags/route.ts` - Returns feature flags from environment variables
 
 ### Core Components
 - `src/app/page.tsx` - Main page with agent selection/persistence and chat interface mounting
 - `src/components/chat-interface.tsx` - Full chat UI: message history, input composer, agent dropdown, image attachments
 - `src/components/markdown-renderer.tsx` - Renders markdown with syntax highlighting and custom diff-tool blocks
+- `src/components/agent-forge-card.tsx` - Displays custom agent creation UI with animated reveal
+- `src/components/pinned-agents-drawer.tsx` - Sliding drawer for managing pinned custom agents
 - `src/components/diff-tool.tsx` - Wrapper for diff display functionality
 - `src/components/diff-display.tsx` - Side-by-side diff visualization
 
@@ -82,24 +148,70 @@ npx wrangler tail                  # View live logs from deployed worker
 ## Important Patterns
 
 ### Environment Variable Access
-Always extract agent index from agentId before accessing env vars:
+Always check agent type and extract appropriate webhook URL:
 ```typescript
+// For standard agents
 const match = agentId.match(/agent-(\d+)/)
-const agentIndex = match[1]
+if (match) {
-const webhookUrl = process.env[`AGENT_${agentIndex}_URL`]
+  const agentIndex = match[1]
+  const webhookUrl = process.env[`AGENT_${agentIndex}_URL`]
+}
+
+// For custom agents
+if (agentId.startsWith('custom-')) {
+  const webhookUrl = process.env.CUSTOM_AGENT_WEBHOOK
+}
 ```
 
 ### LocalStorage Keys
 - Agent selection: `selected-agent` (full object), `selected-agent-id` (string)
 - Per-agent session: `chat-session-{agentId}`
 - Per-agent messages: `chat-messages-{agentId}`
+- Custom agents: `pinned-agents` (array of PinnedAgent objects)
 
 ### Response Parsing in /api/chat
 The route handles multiple n8n response formats:
 1. Streaming chunks (newline-delimited JSON with `type: "item"`)
-2. Tool calls (`type: "tool_call", name: "show_diff"`)
+2. Tool calls (`type: "tool_call"`)
-3. Regular JSON with various fields (`response`, `message`, `output`, `text`)
+3. Code node output (`[{ output: { messageType, content, toolCall? } }]`)
-4. Plain text fallback
+4. Regular JSON with various fields (`response`, `message`, `output`, `text`)
+5. Plain text fallback
+
+### n8n Response Format Requirements
+**CRITICAL:** For proper tool call handling (especially Morgan), n8n workflows must output in this exact format:
+
+```json
+[{
+  "output": {
+    "messageType": "regular_message" | "tool_call",
+    "content": "Message text (always present)",
+    "toolCall": {  // Only when messageType is "tool_call"
+      "type": "tool_call",
+      "name": "create_agent_package" | "show_diff",
+      "payload": {
+        // Tool-specific data structure
+      }
+    }
+  }
+}]
+```
+
+**Implementation in n8n:**
+- Use a **Code node** (NOT structured output parser) after the LLM node
+- The Code node unwraps nested `output` fields and ensures clean JSON:
+  ```javascript
+  const llmOutput = $input.item.json.output || $input.item.json;
+  let actual = llmOutput;
+  while (actual.output && typeof actual.output === 'object') {
+    actual = actual.output;  // Unwrap nested output
+  }
+  return { json: { output: actual } };
+  ```
+
+**Morgan-specific requirements:**
+- System prompt must instruct LLM to output valid JSON matching the schema above
+- For `create_agent_package`, payload must include: `agentId`, `displayName`, `summary`, `tags`, `systemPrompt`, `hints.recommendedIcon`, `hints.whenToUse`
+- The `systemPrompt` should be wrapped in Web Agent Bundle format
 
 ### Image Handling
 - Images converted to base64 via FileReader in browser
@@ -184,6 +296,7 @@ The route handles multiple n8n response formats:
 ### Available Flags
 - `IMAGE_UPLOADS_ENABLED` (default: true) - Controls image attachment UI and API validation
 - `DIFF_TOOL_ENABLED` (default: true) - Controls diff visualization rendering
+- `VOICE_INPUT_ENABLED` (default: false) - Future feature for voice input (not yet implemented)
 
 ### Flag Checking Patterns
 
@@ -298,3 +411,46 @@ expect(response.status).toBe(403)
 - No database - all state in localStorage and n8n workflows
 - Mobile-first responsive design with specific mobile breakpoint styling
 - Vitest for testing with Testing Library for React components
+
+## Debugging and Troubleshooting
+
+### Checking Agent Configuration
+```bash
+# View live logs from deployed worker
+npx wrangler tail
+
+# Test agent webhook directly
+curl -X POST $AGENT_1_URL \
+  -H "Content-Type: application/json" \
+  -d '{"message":"test","sessionId":"test-session"}'
+```
+
+### Checking n8n Response Format
+Look for these log patterns in `npx wrangler tail`:
+- `[v0] Webhook response body` - Shows raw n8n response
+- `[v0] Parsed webhook data` - Shows parsed response object
+- `[v0] parsedOutput messageType` - Shows detected message type (regular_message or tool_call)
+
+### Checking LocalStorage
+```javascript
+// Browser console
+localStorage.getItem('pinned-agents')          // Custom agents array
+localStorage.getItem('chat-messages-agent-2')  // Morgan's chat history
+localStorage.getItem('selected-agent')         // Currently selected agent
+```
+
+### Common Issues
+
+**Custom agents not working:**
+- Verify `CUSTOM_AGENT_WEBHOOK` is set in `wrangler.jsonc` vars
+- Check browser console for agentId format (`custom-{uuid}`)
+- Ensure custom agent has systemPrompt in localStorage
+
+**Morgan not creating agents:**
+- Verify Morgan's n8n workflow has Code node for output unwrapping
+- Check response format matches schema (messageType, content, toolCall)
+- System prompt must instruct to output valid JSON
+
+**Deployment shows "No updated asset files":**
+- You skipped `npx @opennextjs/cloudflare build` step
+- Run the OpenNext build before deploying again

README.md

@@ -206,21 +206,33 @@ Where N = 1, 2, 3, etc. The application will discover all configured agents auto
 
 Deploy to Cloudflare Workers:
 
-1. **Build for Cloudflare**
+1. **Run the standard Next.js build**
+   ```bash
+   pnpm build
+   ```
+   This catches type errors before packaging for Workers.
+
+2. **Fix lint errors**
+   ```bash
+   pnpm lint
+   ```
+   Resolve every reported error (warnings are OK) so the Cloudflare build doesn't fail mid-deploy.
+
+3. **Build for Cloudflare**
    ```bash
    npx @opennextjs/cloudflare build
    ```
 
    **Important:** Always run this before deploying. Standard `next build` alone is insufficient.
 
-2. **Deploy**
+4. **Deploy**
    ```bash
    npx wrangler deploy
    ```
 
    **Note:** The deployment uses the default configuration from `wrangler.jsonc` with route `agents.nicholai.work`. Do not use `--env` flags.
 
-3. **View logs**
+5. **View logs**
    ```bash
    npx wrangler tail
    ```

eslint.config.mjs

@@ -1,16 +1,3 @@
-import { dirname } from "path";
+import nextConfig from "eslint-config-next";
-import { fileURLToPath } from "url";
-import { FlatCompat } from "@eslint/eslintrc/dist/eslintrc.cjs";
 
-const __filename = fileURLToPath(import.meta.url);
+export default nextConfig;
-const __dirname = dirname(__filename);
-
-const compat = new FlatCompat({
-  baseDirectory: __dirname,
-});
-
-const eslintConfig = [
-  ...compat.extends("next/core-web-vitals", "next/typescript"),
-];
-
-export default eslintConfig;

package.json

@@ -80,6 +80,7 @@
     "@types/react-dom": "^18",
     "@vitejs/plugin-react": "^5.1.1",
     "eslint": "^9.39.1",
+    "eslint-config-next": "^16.0.3",
     "jsdom": "^27.2.0",
     "postcss": "^8.5",
     "tailwindcss": "^4.1.9",

src/components/pinned-agents-drawer.tsx

@@ -10,9 +10,10 @@ interface PinnedAgentsDrawerProps {
   isOpen: boolean
   onClose: () => void
   onSelectAgent: (agent: PinnedAgent) => void
+  activeAgentId?: string  // Highlight the currently active agent
 }
 
-export function PinnedAgentsDrawer({ isOpen, onClose, onSelectAgent }: PinnedAgentsDrawerProps) {
+export function PinnedAgentsDrawer({ isOpen, onClose, onSelectAgent, activeAgentId }: PinnedAgentsDrawerProps) {
   const [agents, setAgents] = useState<PinnedAgent[]>([])
   const [isMobile, setIsMobile] = useState(true) // Assume mobile until we can check
   const [draggingId, setDraggingId] = useState<string | null>(null)
@@ -37,7 +38,9 @@ export function PinnedAgentsDrawer({ isOpen, onClose, onSelectAgent }: PinnedAge
       if (stored) {
         try {
           const parsed = JSON.parse(stored)
-          setAgents(parsed)
+          setTimeout(() => {
+            setAgents(parsed)
+          }, 0)
         } catch (error) {
           console.error("Failed to parse pinned agents:", error)
         }
@@ -182,10 +185,10 @@ export function PinnedAgentsDrawer({ isOpen, onClose, onSelectAgent }: PinnedAge
                           </div>
 
                         {/* Action button */}
-                        <div className="mt-0 max-h-0 overflow-hidden opacity-0 transition-all duration-300 group-hover:mt-2 group-hover:max-h-20 group-hover:opacity-100 sm:group-hover:mt-2.5">
+                        <div className="mt-0 max-h-0 overflow-hidden opacity-0 transition-all duration-300 group-hover:mt-2 group-hover:max-h-20 group-hover:opacity-100 sm:group-hover:mt-2.5 pointer-events-auto">
                           <Button
                             onClick={() => handleStartChat(agent)}
-                            className="w-full rounded-lg bg-[rgba(60,60,60,0.95)] py-1.5 text-xs font-medium text-white shadow-md transition-all hover:bg-gradient-to-r hover:from-burnt-orange hover:to-terracotta hover:scale-[1.01] hover:shadow-lg sm:rounded-xl sm:text-sm"
+                            className="w-full rounded-lg bg-white/90 text-charcoal py-1.5 text-xs font-medium shadow-md transition-all hover:bg-white hover:scale-[1.01] hover:shadow-lg active:brightness-125 border border-white/80 sm:rounded-xl sm:text-sm"
                           >
                             <MessageSquare className="mr-1.5 h-3 w-3 sm:mr-2 sm:h-3.5 sm:w-3.5" />
                             Start chat