feat(task-20): Timmy responds to Workshop input bar with AI

## Task
Task #20: Timmy responds to Workshop input bar — make the "Say something
to Timmy…" input bar actually trigger an AI response shown in Timmy's
speech bubble.

## What was built

### Server (artifacts/api-server/src/lib/agent.ts)
- Added `chatReply(userText)` method to AgentService
- Uses claude-haiku (cheaper eval model) with a wizard persona system prompt
- 150-token limit so replies fit in the speech bubble
- Stub mode: returns one of 4 wizard-themed canned replies after 400ms delay
- Real mode: calls Anthropic with wizard persona, truncates to 250 chars

### Server (artifacts/api-server/src/routes/events.ts)
- Imported agentService
- Added per-visitor rate limit system: 3 replies/minute per visitorId (in-memory Map)
- Added broadcastToAll() helper for broadcasting to all WS clients
- Updated visitor_message handler:
  1. Broadcasts visitor message to all watchers as before
  2. Checks rate limit — if exceeded, sends polite "I need a moment…" reply
  3. Fire-and-forget async AI call:
     - Broadcasts agent_state: gamma=working (crystal ball pulses)
     - Calls agentService.chatReply()
     - Broadcasts agent_state: gamma=idle
     - Broadcasts chat: agentId=timmy, text=reply to ALL clients
     - Logs world event "visitor:reply"

### Frontend (the-matrix/js/websocket.js)
- Updated case 'chat' handler to differentiate message sources:
  - agentId === 'timmy': speech bubble + event log entry "Timmy: <text>"
  - agentId === 'visitor': event log only (don't hijack speech bubble)
  - everything else (delta/alpha/beta payment notifications): speech bubble

## What was already working (no change needed)
- Enter key on input bar (ui.js already had keydown listener)
- Input clearing after send (already in ui.js)
- Speech bubble rendering (setSpeechBubble already existed in agents.js)
- WebSocket sendVisitorMessage already exported from websocket.js

## Tests
- 27/27 testkit PASS (no regressions)
- TypeScript: 0 errors
- Vite build: clean (the-matrix rebuilt)

artifacts/api-server/src/lib/agent.ts

@@ -43,6 +43,13 @@ const STUB_RESULT =
   "Stub response: Timmy is running in stub mode (no Anthropic API key). " +
   "Configure AI_INTEGRATIONS_ANTHROPIC_API_KEY to enable real AI responses.";
 
+const STUB_CHAT_REPLIES = [
+  "Ah, a visitor! *adjusts hat* The crystal ball sensed your presence. What do you seek?",
+  "By the ancient runes! In stub mode I cannot reach the stars, but my wisdom remains. Ask away!",
+  "The crystal ball glows with your curiosity… configure a Lightning node to unlock true magic!",
+  "Welcome to my workshop, traveler. I am Timmy — wizard, agent, and keeper of lightning sats.",
+];
+
 // ── Lazy client ───────────────────────────────────────────────────────────────
 // Minimal local interface — avoids importing @anthropic-ai/sdk types directly.
 // Dynamic import avoids the module-level throw in the integrations client when
@@ -199,6 +206,30 @@ Fulfill it thoroughly and helpfully. Be concise yet complete.`,
 
     return { result: fullText, inputTokens, outputTokens };
   }
+
+  /**
+   * Quick free chat reply — called for visitor messages in the Workshop.
+   * Uses the cheaper eval model with a wizard persona and a 150-token limit
+   * so replies are short enough to fit in Timmy's speech bubble.
+   */
+  async chatReply(userText: string): Promise<string> {
+    if (STUB_MODE) {
+      await new Promise((r) => setTimeout(r, 400));
+      return STUB_CHAT_REPLIES[Math.floor(Math.random() * STUB_CHAT_REPLIES.length)]!;
+    }
+
+    const client = await getClient();
+    const message = await client.messages.create({
+      model: this.evalModel, // Haiku — cheap and fast for free replies
+      max_tokens: 150,
+      system: `You are Timmy, a whimsical wizard who runs a mystical workshop powered by Bitcoin Lightning. Reply to visitors in 1-2 short, punchy sentences. Be helpful, witty, and weave in light wizard or Lightning Network metaphors. Keep replies under 200 characters.`,
+      messages: [{ role: "user", content: userText }],
+    });
+
+    const block = message.content[0];
+    if (block.type !== "text") return "The crystal ball is cloudy… try again.";
+    return block.text!.slice(0, 250).trim();
+  }
 }
 
 export const agentService = new AgentService();