feat: implement AI bouquet generation flow with Gemini/OpenAI

* feat: scaffold message, generating, and map pages and align header steps

* feat: implement AI bouquet generation flow with Gemini/OpenAI

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

src/routes/api/flower-flow/mood-analysis/+server.js

@@ -0,0 +1,31 @@
+import { createJob, updateJob } from '$lib/server/flowerFlow/jobStore.js';
+import { analyzeImageMood } from '$lib/server/gemini/vision.js';
+import { isGeminiConfigured } from '$lib/server/gemini/client.js';
+import { json, readUserInput, toErrorResponse } from '$lib/server/http.js';
+
+/** @type {import('./$types').RequestHandler} */
+export async function POST({ request }) {
+	try {
+		const formData = await request.formData();
+		const image = formData.get('image');
+
+		if (!(image instanceof File)) {
+			return json({ error: 'image file is required' }, 400);
+		}
+
+		const userInput = readUserInput(formData);
+		const job = createJob(userInput);
+		const imageBytes = new Uint8Array(await image.arrayBuffer());
+		const moodAnalysis = await analyzeImageMood(imageBytes, image.type || 'image/jpeg', userInput);
+
+		updateJob(job.id, { moodAnalysis });
+
+		return json({
+			jobId: job.id,
+			moodAnalysis,
+			mock: !isGeminiConfigured()
+		});
+	} catch (error) {
+		return toErrorResponse(error);
+	}
+}