Update app.py

app.py

@@ -1,373 +1,267 @@
-import time
-from dataclasses import dataclass, field
-from typing import Optional, Dict, Tuple, List
-
 import gradio as gr
-import numpy as np
+from openai import OpenAI
+from huggingface_hub import InferenceClient
+import os
+import time
+import requests
+import urllib.parse
+import pandas as pd
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
 from PIL import Image
-
-from deepface import DeepFace
-
-
-# =========================
-# 參數（可微調）
-# =========================
-ANALYZE_EVERY_SEC = 0.8
-DOWNSAMPLE_W = 720
-EMA_ALPHA = 0.45
-CONF_TH = 40.0
-SWITCH_CONFIRM_SEC = 2.5
-IOU_TH = 0.25
-
-# 建議改為 "opencv" 穩定性較高，若想維持原狀可改回 "mtcnn"
-DETECTOR_BACKEND = "opencv" 
-ALIGN_FACE = True
-
-
-# =========================
-# 情緒中文 + 分數映射
-# =========================
-EMO_ZH = {
-    "angry": "生氣",
-    "disgust": "厭惡",
-    "fear": "害怕",
-    "happy": "開心",
-    "sad": "難過",
-    "surprise": "驚訝",
-    "neutral": "平靜",
-    "unknown": "未知",
-}
-
-EMO_TO_SCORE = {
-    "angry": 1,
-    "disgust": 1,
-    "fear": 1,
-    "sad": 2,
-    "neutral": 3,
-    "surprise": 4,
-    "happy": 5,
-    "unknown": 3,
-}
-
-# ### [整合需求 新增] ###
-def get_emotion_score(emo: str) -> int:
-    return EMO_TO_SCORE.get(emo, 3)
-# ######################
-
-SCORE_LABELS = {
-    1: "1（心情差）",
-    2: "2（不太好）",
-    3: "3（普通）",
-    4: "4（不錯）",
-    5: "5（超棒）",
-}
-SCORE_CHOICES = [SCORE_LABELS[i] for i in [1, 2, 3, 4, 5]]
-
-
-# =========================
-# 狀態
-# =========================
-@dataclass
-class AppState:
-    mode: str = "攝影機辨識"
-
-    running: bool = True
-    finished: bool = False
-    last_analyze_t: float = 0.0
-
-    # tracking
-    track_bbox: Optional[Tuple[int, int, int, int]] = None
-
-    # smoothing
-    ema_scores: Optional[np.ndarray] = None
-    emo_keys: List[str] = field(default_factory=list)
-
-    # stable/candidate
-    stable_emo: str = "unknown"
-    candidate_emo: Optional[str] = None
-    candidate_since: Optional[float] = None
-
-    # final
-    final_emo: Optional[str] = None
-    final_conf: Optional[float] = None
-
-    # ### [整合需求 新增] 用來儲存整數分數 ###
-    final_score: int = 3  
-    # ######################
-
-
-# =========================
-# UI HTML
-# =========================
-def _hint_html(msg: str) -> str:
-    return f"""<div style="border-radius:14px;padding:14px;border:1px dashed #DADADA;background:#FAFAFA;color:#111;">{msg}</div>"""
-
-def _camera_hint_before_start() -> str:
-    return _hint_html("請先按「Click to access webcam / 允許」開啟攝影機；接著，請按「錄製（Record）」開始。")
-
-def _camera_hint_done() -> str:
-    return _hint_html("已完成辨識，可按「重新攝影機辨識」再次進行辨識。")
-
-def _camera_hint_stopped() -> str:
-    return _hint_html("已停止辨識。可按「重新攝影機辨識」再試一次。")
-
-def _upload_hint_before() -> str:
-    return _hint_html("請上傳一張清楚的臉部照片（臉越大越準）。")
-
-def _upload_hint_done() -> str:
-    return _hint_html("已完成圖片辨識，可按「重新上傳圖片辨識」再次辨識。")
-
-def _upload_hint_stopped() -> str:
-    return _hint_html("已停止圖片辨識。可按「重新上傳圖片辨識」再試一次。")
-
-def _result_card_html(emo_key: str, conf: Optional[float]) -> str:
-    zh = EMO_ZH.get(emo_key, emo_key)
-    score = EMO_TO_SCORE.get(emo_key, 3)
-    conf_txt = "" if conf is None else f"{conf:.1f}%"
-    score_desc = SCORE_LABELS[score].split("（")[1].rstrip("）")
-
-    return f"""
-    <div style="border-radius:16px;padding:20px;border:1px solid #E6E6E6;background:#FFFFFF;color:#111;">
-      <div style="font-size:14px;color:#444;margin-bottom:8px;">辨識結果</div>
-      <div style="font-size:42px;font-weight:800;line-height:1.1;margin-bottom:14px;color:#000;">{zh}</div>
-      <div style="font-size:16px;color:#111;margin-bottom:6px;">心情分數：<b>{score}</b>（{score_desc}）</div>
-      <div style="font-size:14px;color:#111;">信心值：{conf_txt}</div>
-    </div>
-    """
-
-def _score_radio_value(score: int) -> str:
-    score = int(score)
-    score = min(5, max(1, score))
-    return SCORE_LABELS[score]
-
-def _downsample_rgb(frame: np.ndarray, target_w: int) -> np.ndarray:
-    if frame is None: return None
-    h, w = frame.shape[:2]
-    if w <= target_w: return frame
-    scale = target_w / w
-    new_h = max(1, int(h * scale))
-    img = Image.fromarray(frame)
-    img = img.resize((target_w, new_h))
-    return np.array(img)
-
-def _iou(a, b) -> float:
-    ax, ay, aw, ah = a
-    bx, by, bw, bh = b
-    ax2, ay2 = ax + aw, ay + ah
-    bx2, by2 = bx + bw, by + bh
-    ix1, iy1 = max(ax, bx), max(ay, by)
-    ix2, iy2 = min(ax2, bx2), min(ay2, by2)
-    iw, ih = max(0, ix2 - ix1), max(0, iy2 - iy1)
-    inter = iw * ih
-    if inter <= 0: return 0.0
-    union = aw * ah + bw * bh - inter
-    return inter / max(1e-6, union)
-
-def _pick_face_by_tracking(faces, prev_bbox):
-    if not faces: return None, None
-    cand = []
-    for f in faces:
-        fa = f.get("facial_area", {}) or {}
-        x, y, w, h = int(fa.get("x",0)), int(fa.get("y",0)), int(fa.get("w",0)), int(fa.get("h",0))
-        if w > 0 and h > 0 and f.get("face") is not None:
-            cand.append((f, (x, y, w, h), w * h))
-    if not cand: return None, None
-    if prev_bbox is not None:
-        best, best_i = None, 0.0
-        for f, bb, area in cand:
-            i = _iou(prev_bbox, bb)
-            if i > best_i: best_i = i; best = (f, bb)
-        if best is not None and best_i >= IOU_TH: return best[0], best[1]
-    cand.sort(key=lambda x: x[2], reverse=True)
-    return cand[0][0], cand[0][1]
-
-def _reset_state_for_camera(st: AppState) -> AppState:
-    st.running = True; st.finished = False; st.last_analyze_t = 0.0
-    st.track_bbox = None; st.ema_scores = None; st.emo_keys = []
-    st.stable_emo = "unknown"; st.candidate_emo = None; st.candidate_since = None
-    st.final_emo = None; st.final_conf = None
-    # ### [整合需求] 重置分數
-    st.final_score = 3
-    return st
-
-def _reset_state_for_upload(st: AppState) -> AppState:
-    st.running = False; st.finished = False; st.last_analyze_t = 0.0
-    st.track_bbox = None; st.ema_scores = None; st.emo_keys = []
-    st.stable_emo = "unknown"; st.candidate_emo = None; st.candidate_since = None
-    st.final_emo = None; st.final_conf = None
-    # ### [整合需求] 重置分數
-    st.final_score = 3
-    return st
-
-
-# =========================
-# Camera streaming
-# =========================
-def on_stream(frame_rgb: np.ndarray, st: AppState):
-    if st.mode != "攝影機辨識":
-        return gr.update(), gr.update(), gr.update(), gr.update(value=_upload_hint_before()), st, gr.update(value="重新上傳圖片辨識")
-
-    if st.finished or (not st.running):
-        cam_visible = False
-        if st.final_emo:
-            result_html = _result_card_html(st.final_emo, st.final_conf)
-            mood_val = _score_radio_value(EMO_TO_SCORE.get(st.final_emo, 3))
-            hint_html = _camera_hint_done()
-        else:
-            result_html = _hint_html("尚未完成辨識。")
-            mood_val = _score_radio_value(3)
-            hint_html = _camera_hint_stopped()
-        return gr.update(visible=cam_visible), gr.update(value=result_html), gr.update(value=mood_val), gr.update(value=hint_html), st, gr.update(value="重新攝影機辨識")
-
-    if frame_rgb is None:
-        return gr.update(visible=True), gr.update(value=_hint_html("等待影像…（尚未開始串流）")), gr.update(value=_score_radio_value(3)), gr.update(value=_camera_hint_before_start()), st, gr.update(value="重新攝影機辨識")
-
-    now = time.time()
-    if now - st.last_analyze_t < ANALYZE_EVERY_SEC:
-        show = st.stable_emo or "unknown"
-        return gr.update(visible=True), gr.update(value=_result_card_html(show, st.final_conf)), gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))), gr.update(value=_camera_hint_before_start()), st, gr.update(value="重新攝影機辨識")
-
-    st.last_analyze_t = now
-    small = _downsample_rgb(frame_rgb, DOWNSAMPLE_W)
-    faces = DeepFace.extract_faces(img_path=small, detector_backend=DETECTOR_BACKEND, enforce_detection=False, align=ALIGN_FACE)
-    pick, bbox = _pick_face_by_tracking(faces, st.track_bbox)
-
-    if pick is None or bbox is None or pick.get("face") is None:
-        show = st.stable_emo or "unknown"
-        return gr.update(visible=True), gr.update(value=_result_card_html(show, st.final_conf)), gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))), gr.update(value=_camera_hint_before_start()), st, gr.update(value="重新攝影機辨識")
-
-    st.track_bbox = bbox
-    face = pick["face"]
-    if face.dtype != np.uint8: face = np.clip(face * 255.0, 0, 255).astype(np.uint8)
-
-    result = DeepFace.analyze(img_path=face, actions=["emotion"], enforce_detection=False)
-    if isinstance(result, list): result = result[0]
-    emo_dict = result.get("emotion", None)
-
-    if not isinstance(emo_dict, dict) or len(emo_dict) == 0:
-        show = st.stable_emo or "unknown"
-        return gr.update(visible=True), gr.update(value=_result_card_html(show, st.final_conf)), gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))), gr.update(value=_camera_hint_before_start()), st, gr.update(value="重新攝影機辨識")
-
-    top_key = max(emo_dict, key=lambda k: float(emo_dict[k]))
-    top_conf = float(emo_dict[top_key])
-
-    if top_conf < CONF_TH:
-        show = st.stable_emo or "unknown"
-        return gr.update(visible=True), gr.update(value=_result_card_html(show, st.final_conf)), gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))), gr.update(value=_camera_hint_before_start()), st, gr.update(value="重新攝影機辨識")
-
-    keys = list(emo_dict.keys())
-    vec = np.array([float(emo_dict[k]) for k in keys], dtype=np.float32)
-
-    if st.ema_scores is None or st.emo_keys != keys:
-        st.ema_scores = vec; st.emo_keys = keys
+from dotenv import load_dotenv
+
+# --- 匯入組員的模組 ---
+import emotion 
+# ---------------------------
+
+load_dotenv()
+
+# ==========================================
+# 0. 環境變數 & 1. 系統初始化 (保持不變)
+# ==========================================
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+global_df = None
+global_mood_df = None
+global_retriever = None
+rag_initialized = False
+
+def init_rag_system():
+    global global_df, global_mood_df, global_retriever, rag_initialized
+    if rag_initialized: return
+    try:
+        global_df = pd.read_csv('restaurants.csv')
+        global_df['RAG_Content'] = global_df['RAG_Content'].fillna("")
+        global_df['Category'] = global_df['Category'].fillna("其他")
+        global_mood_df = pd.read_csv('mood_food_guide.csv')
+    except Exception: pass
+    if os.path.exists("faiss_index"):
+        try:
+            embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+            vectorstore = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+            global_retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
+        except Exception: pass
+    rag_initialized = True
+
+# ==========================================
+# 2. 核心功能 (保持不變)
+# ==========================================
+def get_restaurant_data(mood_score_str, food_choice):
+    init_rag_system()
+    if global_df is None or global_df.empty: return None, True, "資料庫未載入", "無建議"
+    try: score = int(str(mood_score_str).split(' ')[0])
+    except: score = 3
+    mood_info = global_mood_df[global_mood_df['分數'] == score]
+    if not mood_info.empty:
+        rec_categories = mood_info.iloc[0]['推薦料理類別']
+        mood_reason = mood_info.iloc[0]['原因']
     else:
-        st.ema_scores = EMA_ALPHA * vec + (1.0 - EMA_ALPHA) * st.ema_scores
-
-    stable_idx = int(np.argmax(st.ema_scores))
-    stable_key = st.emo_keys[stable_idx]
-    st.stable_emo = stable_key
-
-    if st.candidate_emo != stable_key:
-        st.candidate_emo = stable_key; st.candidate_since = now
+        rec_categories = ""
+        mood_reason = "隨意探索"
+    candidates = global_df.copy()
+    if rec_categories:
+        candidates = candidates[candidates['Category'].apply(lambda x: str(x) in str(rec_categories) or str(rec_categories) in str(x))]
+    food_keyword = "飯" if food_choice == "吃飯" else "麵" if food_choice == "吃麵" else ""
+    if food_keyword:
+        candidates = candidates[candidates['Name'].str.contains(food_keyword, case=False, na=False) | candidates['RAG_Content'].str.contains(food_keyword, case=False, na=False)]
+    if candidates.empty:
+        result = global_df.sample(1).iloc[0]; is_random = True
     else:
-        if st.candidate_since is None: st.candidate_since = now
-
-    confirmed = (st.candidate_since is not None and (now - st.candidate_since) >= SWITCH_CONFIRM_SEC)
-
-    if confirmed and st.final_emo is None:
-        st.final_emo = stable_key; st.final_conf = top_conf
+        result = candidates.sample(1).iloc[0]; is_random = False
+    return result, is_random, rec_categories, mood_reason
+
+def generate_content_with_groq(restaurant_name, restaurant_detail, user_diary, mood_score, mood_guide_reason, debug_mode=False):
+    if not GROQ_API_KEY: return "⚠️ 請設定 GROQ_API_KEY"
+    client = OpenAI(api_key=GROQ_API_KEY, base_url="https://api.groq.com/openai/v1")
+    system_prompt = "你是一個幽默、懂吃且善解人意的 AI 朋友..."
+    user_msg = f"【狀態】心情分數：{mood_score}\n【日記】{user_diary}\n【建議原因】{mood_guide_reason}\n【餐廳】{restaurant_name}\n資料：{restaurant_detail}"
+    try:
+        response = client.chat.completions.create(model="llama-3.3-70b-versatile", messages=[{"role": "system", "content": system_prompt}, {"role": "user", "content": user_msg}])
+        return response.choices[0].message.content
+    except Exception as e: return f"Groq Error: {str(e)}"
+
+def generate_image_huggingface(prompt):
+    if not HF_TOKEN: return None
+    try:
+        hf_client = InferenceClient(token=HF_TOKEN)
+        return hf_client.text_to_image(prompt=prompt, model="stabilityai/stable-diffusion-xl-base-1.0")
+    except: return None
+
+def mood_agent_logic(score_input, food_input, diary_input, debug_mode):
+    restaurant, is_random, rec_categories, mood_reason = get_restaurant_data(score_input, food_input)
+    if restaurant is None: yield "資料庫讀取錯誤", None, ""; return
+    name = restaurant['Name']; address = restaurant['Address']; url = restaurant['URL']; img_prompt = restaurant.get('Visual_prompt')
+    rag_info = str(restaurant.get('RAG_Content', ''))
+    if global_retriever:
+        docs = global_retriever.invoke(name)
+        if docs: rag_info = "\n".join([d.page_content for d in docs])
+    ai_text = generate_content_with_groq(name, rag_info, diary_input, score_input, mood_reason, debug_mode)
+    final_response = f"### 🍽️ 推薦：{name}\n\n{ai_text}"
+    map_html = f'<div style="text-align:center"><a href="{url}" target="_blank" style="background:#4CAF50;color:white;padding:8px 16px;border-radius:20px;text-decoration:none">🗺️ Google Map 導航</a></div>'
+    yield final_response, None, map_html
+    image_output = generate_image_huggingface(img_prompt)
+    yield final_response, image_output, map_html
+
+
+# ==========================================
+# 3. [修正版] 橋接邏輯 (Bridge Functions)
+# ==========================================
+
+# 這是 app.py 自己的格式 (注意：這裡是半形括號)
+def _score_to_radio_value(score):
+    mapping = {1: "1 (心情差)", 2: "2 (不太好)", 3: "3 (普通)", 4: "4 (不錯)", 5: "5 (超棒)"}
+    # 預防萬一 score 是 None 或其他怪怪的值
+    try:
+        score = int(score)
+    except:
+        score = 3
+    return mapping.get(score, "3 (普通)")
+
+# 橋接 1：開始
+def bridge_start_click(st):
+    res = emotion.on_restart(st)
+    return res[1], res[0], gr.update(visible=True), res[5], res[4]
+
+# 橋接 2：停止
+def bridge_stop_click(st):
+    res = emotion.on_stop(st)
+    return res[1], res[0], gr.update(visible=False), res[5], res[4]
+
+# 橋接 3：Webcam 串流 (修正分數填入問題)
+def bridge_predict_frame(frame, st):
+    res = emotion.on_stream(frame, st)
+    
+    out_cam = res[0]
+    out_result = res[1]
+    # out_mood = res[2] # ❌ 我們不使用隊友回傳的 UI 更新，因為括號格式不同
+    out_st = res[4]
+    out_btn_start = res[5]
+    
+    score_update = gr.update()
+    tabs_update = gr.update()
+    out_btn_stop = gr.update()
+
+    # 如果辨識完成，我們自己產生一個符合 app.py 格式的 UI 更新
+    if out_st.finished and hasattr(out_st, 'final_score'):
+        # ✅ 使用 _score_to_radio_value 將整數轉換為半形括號字串
+        new_val = _score_to_radio_value(out_st.final_score)
+        score_update = gr.update(value=new_val)
         
-        # ### [整合需求] 存入分數 ###
-        st.final_score = EMO_TO_SCORE.get(stable_key, 3)
-        # #######################
+        tabs_update = gr.Tabs(selected=1)
+        out_btn_stop = gr.update(visible=False)
         
-        st.running = False; st.finished = True
-        return gr.update(visible=False), gr.update(value=_result_card_html(stable_key, top_conf)), gr.update(value=_score_radio_value(EMO_TO_SCORE.get(stable_key, 3))), gr.update(value=_camera_hint_done()), st, gr.update(value="重新攝影機辨識")
-
-    return gr.update(visible=True), gr.update(value=_result_card_html(stable_key, top_conf)), gr.update(value=_score_radio_value(EMO_TO_SCORE.get(stable_key, 3))), gr.update(value=_camera_hint_before_start()), st, gr.update(value="重新攝影機辨識")
-
+    return out_cam, out_result, out_st, out_btn_stop, out_btn_start, score_update, tabs_update
 
-# =========================
-# Upload image
-# =========================
-def on_upload(img: np.ndarray, st: AppState):
-    if st.mode != "上傳圖片辨識":
-        return gr.update(), gr.update(), st, gr.update(value=_camera_hint_before_start()), gr.update(value="重新攝影機辨識")
-
-    st = _reset_state_for_upload(st)
-    if img is None:
-        return gr.update(value=_upload_hint_before()), gr.update(value=_score_radio_value(3)), st, gr.update(value=_upload_hint_before()), gr.update(value="重新上傳圖片辨識")
-
-    # ### [修正] 圖片格式處理 (解決 PNG/灰階 問題) ###
-    if img.ndim == 2:
-        img = np.stack([img, img, img], axis=-1)
-    if img.shape[-1] == 4:
-        img = img[:, :, :3]
-    # ###########################################
+# 橋接 4：圖片上傳 (修正分數填入問題)
+def bridge_predict_upload(img, st):
+    res = emotion.on_upload(img, st)
+    
+    out_result = res[0]
+    # out_mood = res[1] # ❌ 同樣忽略隊友的格式
+    out_st = res[2]
+    
+    score_update = gr.update()
+    tabs_update = gr.update()
 
-    small = _downsample_rgb(img, DOWNSAMPLE_W)
-    faces = DeepFace.extract_faces(img_path=small, detector_backend=DETECTOR_BACKEND, enforce_detection=False, align=ALIGN_FACE)
-    pick, bbox = _pick_face_by_tracking(faces, None)
+    if out_st.finished and hasattr(out_st, 'final_score'):
+        # ✅ 使用 _score_to_radio_value 將整數轉換為半形括號字串
+        new_val = _score_to_radio_value(out_st.final_score)
+        score_update = gr.update(value=new_val)
+        
+        tabs_update = gr.Tabs(selected=1)
     
-    if pick is None or pick.get("face") is None:
-        return gr.update(value=_hint_html("沒有偵測到人臉，請換一張更清楚、臉更大的照片。")), gr.update(value=_score_radio_value(3)), st, gr.update(value=_upload_hint_before()), gr.update(value="重新上傳圖片辨識")
+    return out_result, score_update, tabs_update, out_st
 
-    face = pick["face"]
-    if face.dtype != np.uint8: face = np.clip(face * 255.0, 0, 255).astype(np.uint8)
 
-    result = DeepFace.analyze(img_path=face, actions=["emotion"], enforce_detection=False)
-    if isinstance(result, list): result = result[0]
-    emo_dict = result.get("emotion", None)
-    if not isinstance(emo_dict, dict) or len(emo_dict) == 0:
-        return gr.update(value=_hint_html("辨識失敗，請換一張照片再試一次。")), gr.update(value=_score_radio_value(3)), st, gr.update(value=_upload_hint_before()), gr.update(value="重新上傳圖片辨識")
+# ==========================================
+# 4. Gradio 介面建構
+# ==========================================
 
-    top_key = max(emo_dict, key=lambda k: float(emo_dict[k]))
-    top_conf = float(emo_dict[top_key])
+combined_css = emotion.css 
 
-    st.final_emo = top_key; st.final_conf = top_conf
-    
-    # ### [整合需求] 存入分數 ###
-    st.final_score = EMO_TO_SCORE.get(top_key, 3)
-    # #######################
+with gr.Blocks(title="AI 心情食堂", css=combined_css) as demo:
     
-    st.finished = True
-    return gr.update(value=_result_card_html(top_key, top_conf)), gr.update(value=_score_radio_value(EMO_TO_SCORE.get(top_key, 3))), st, gr.update(value=_upload_hint_done()), gr.update(value="重新上傳圖片辨識")
-
-
-# =========================
-# Mode / Buttons
-# =========================
-def on_mode_change(mode: str, st: AppState):
-    st.mode = mode
-    if mode == "攝影機辨識":
-        st = _reset_state_for_camera(st)
-        return gr.update(visible=True), gr.update(visible=False, value=None), gr.update(value=_hint_html("等待影像…（尚未開始串流）")), gr.update(value=_score_radio_value(3)), gr.update(value=_camera_hint_before_start()), st, gr.update(value="重新攝影機辨識")
-    else:
-        st = _reset_state_for_upload(st)
-        return gr.update(visible=False), gr.update(visible=True, value=None), gr.update(value=_upload_hint_before()), gr.update(value=_score_radio_value(3)), gr.update(value=_upload_hint_before()), st, gr.update(value="重新上傳圖片辨識")
+    st_state = gr.State(emotion.AppState())
 
-def on_restart(st: AppState):
-    if st.mode == "攝影機辨識":
-        st = _reset_state_for_camera(st)
-        return gr.update(visible=True), gr.update(value=_hint_html("等待影像…（尚未開始串流）")), gr.update(value=_score_radio_value(3)), gr.update(value=_camera_hint_before_start()), st, gr.update(value="重新攝影機辨識"), gr.update()
-    else:
-        st = _reset_state_for_upload(st)
-        return gr.update(), gr.update(value=_upload_hint_before()), gr.update(value=_score_radio_value(3)), gr.update(value=_upload_hint_before()), st, gr.update(value="重新上傳圖片辨識"), gr.update(value=None)
-
-def on_stop(st: AppState):
-    if st.mode == "攝影機辨識":
-        st.running = False; st.finished = True
-        if st.final_emo is None:
-            return gr.update(visible=False), gr.update(value=_hint_html("已停止辨識。")), gr.update(value=_score_radio_value(3)), gr.update(value=_camera_hint_stopped()), st, gr.update(value="重新攝影機辨識"), gr.update()
-        return gr.update(visible=False), gr.update(value=_result_card_html(st.final_emo, st.final_conf)), gr.update(value=_score_radio_value(EMO_TO_SCORE.get(st.final_emo, 3))), gr.update(value=_camera_hint_done()), st, gr.update(value="重新攝影機辨識"), gr.update()
-    
-    st = _reset_state_for_upload(st)
-    return gr.update(), gr.update(value=_hint_html("已停止圖片辨識。")), gr.update(value=_score_radio_value(3)), gr.update(value=_upload_hint_stopped()), st, gr.update(value="重新上傳圖片辨識"), gr.update(value=None)
-
-css = """#app_container { max-width: 960px; margin: 0 auto; } .gradio-container { background: #f1f5f9 !important; }"""
+    with gr.Tabs() as tabs:
+        
+        # Tab 1: 情緒辨識
+        with gr.TabItem("😊 情緒辨識 (Step 1)", id=0):
+            with gr.Column(elem_id="app_container"):
+                gr.Markdown("### 第一步：測測你的心情能量\n讓 AI 看看你的表情，自動幫你決定心情分數！(辨識完畢會自動跳轉)")
+                
+                with gr.Row():
+                    btn_start = gr.Button("📸 開啟攝影機辨識", variant="primary")
+                    btn_stop  = gr.Button("⏹️ 停止", variant="secondary", visible=False)
+
+                cam = gr.Image(sources=["webcam"], streaming=True, type="numpy", label="攝影機畫面", visible=False)
+                result_markdown = gr.Markdown(emotion._hint_html("請按「開啟攝影機辨識」或下方上傳照片。"))
+                
+                gr.Markdown("---")
+                gr.Markdown("### 或者：上傳照片")
+                upload_img = gr.Image(sources=["upload"], type="numpy", label="上傳照片")
+
+        # Tab 2: 主功能區
+        with gr.TabItem("🍽️ AI 心情食堂 (Step 2)", id=1):
+            with gr.Column():
+                gr.Markdown(f"## 🍱 今天想吃點什麼？")
+                with gr.Row():
+                    with gr.Column(scale=1):
+                        # 这里的 Radio 选项使用的是半形括号
+                        score_input = gr.Radio(
+                            ["1 (心情差)", "2 (不太好)", "3 (普通)", "4 (不錯)", "5 (超棒)"], 
+                            label="1. 心情分數 (由 Tab 1 自動填入)", 
+                            value="3 (普通)"
+                        )
+                        food_input = gr.Radio(["吃飯", "吃麵", "隨便"], label="2. 想吃什麼", value="隨便")
+                        diary_input = gr.Textbox(lines=4, label="3. 心情日記", placeholder="寫下今天發生的事...")
+                        debug_mode_btn = gr.Checkbox(label="🔧 開啟除錯模式", value=False)
+                        submit_btn = gr.Button("🍱 送出給 Agent", variant="primary")
+                    
+                    with gr.Column(scale=1):
+                        agent_output = gr.Markdown(label="AI 回應")
+                        image_output = gr.Image(label="AI 推薦美食圖", type="pil", width=400)
+                        map_output = gr.HTML(label="地圖導航")
+
+    # ==========================================
+    # 事件綁定
+    # ==========================================
+
+    btn_start.click(
+        fn=bridge_start_click,
+        inputs=[st_state],
+        outputs=[result_markdown, cam, btn_stop, btn_start, st_state],
+        show_progress="minimal"
+    )
+
+    btn_stop.click(
+        fn=bridge_stop_click,
+        inputs=[st_state],
+        outputs=[result_markdown, cam, btn_stop, btn_start, st_state],
+        show_progress="minimal"
+    )
+
+    cam.stream(
+        fn=bridge_predict_frame,
+        inputs=[cam, st_state],
+        outputs=[cam, result_markdown, st_state, btn_stop, btn_start, score_input, tabs], 
+        show_progress="minimal"
+    )
+
+    upload_img.change(
+        fn=bridge_predict_upload,
+        inputs=[upload_img, st_state],
+        outputs=[result_markdown, score_input, tabs, st_state], 
+        show_progress="minimal"
+    )
+
+    submit_btn.click(
+        fn=mood_agent_logic,
+        inputs=[score_input, food_input, diary_input, debug_mode_btn],
+        outputs=[agent_output, image_output, map_output]
+    )
 
 if __name__ == "__main__":
-    with gr.Blocks(title="Emotion Detector", css=css) as demo:
-        # 隊友的單獨測試介面 (略)
-        pass 
-    # demo.launch()
+    demo.launch(ssr_mode=False)