Update src/streamlit_app.py

src/streamlit_app.py

@@ -17,7 +17,7 @@ os.environ["TRANSFORMERS_CACHE"] = "/tmp"
 openai.api_key = os.getenv("OPENAI_API_KEY")
 
 # إعداد صفحة Streamlit
-st.set_page_config(page_title="Unleash the AI Agent", layout="wide")
+st.set_page_config(page_title="Health Matrix AI Command Center", layout="wide")
 
 # تحميل ملف CSS من نفس مجلد هذا الملف
 current_dir = pathlib.Path(__file__).resolve().parent
@@ -41,7 +41,7 @@ st.markdown(
     unsafe_allow_html=True,
 )
 
-# عرض شعار Health Matrix في الزاوية اليسرى العليا باستخدام الصورة المحلية
+# عرض شعار Health Matrix في الزاوية العلوية اليسرى باستخدام الصورة المحلية
 logo_path = current_dir / "logo.jpg"
 if logo_path.exists():
     logo_url = str(logo_path.as_posix())
@@ -54,23 +54,48 @@ if logo_path.exists():
         unsafe_allow_html=True,
     )
 
-# بيانات الشفتات (يمكن استبدالها بقراءة من API في المستقبل)
+# --------------------
+# محتوى الصفحة الرئيسية (Landing Page)
+
+# عنوان وتعريف قصير
+st.markdown(
+    """
+<div style="margin-top:5rem; text-align:center;">
+  <h1 style="font-size:3rem; font-weight:600; margin-bottom:0.5rem; color:#36ba01;">Welcome to the AI‑Powered Command Center</h1>
+  <h2 style="font-size:1.8rem; font-weight:500; margin-top:0; color:#004c97;">by Health Matrix</h2>
+  <p style="max-width:700px; margin:0 auto; font-size:1.1rem; line-height:1.5; color:#cad8e5;">
+    This smart assistant leverages AI to automate decisions, schedule actions, and provide real‑time updates – all while you relax.
+  </p>
+</div>
+""",
+    unsafe_allow_html=True,
+)
+
+# تحضير مكان لعرض الخط الزمني للمهام
+timeline_container = st.container()
+
+# تخصيص الأسماء الافتراضية للموظفين والشفتات
+employee_ids_default = [850]
 shift_data = """
 ShiftID,Department,RequiredSkill,RequiredCert,ShiftTime
 S101,ICU,ICU,ACLS,2025-06-04 07:00
 """
-df_shifts = pd.read_csv(StringIO(shift_data))
-
-# جلب بيانات الموظفين عبر الدالة من schedule.py
-employee_ids = [850]  # يمكنك تغيير الأرقام حسب الحاجة
-df_employees = fetch_employees(employee_ids)
+df_shifts_default = pd.read_csv(StringIO(shift_data))
 
-# دالة التحقق من الأهلية بناءً على الـ JobRole فقط
 def is_eligible(row, shift):
+    """Check if employee's job role matches shift requirement."""
     return row.get("JobRole", "").strip().lower() == shift["RequiredSkill"].strip().lower()
 
-# دالة GPT لتحديد القرار المناسب (تعيين، إشعار، تجاهل)
 def gpt_decide(shift, eligible_df):
+    """Call GPT model to decide assignment or notification.
+
+    The function returns a dict with keys action and employee, defaulting to skip if any error occurs
+    or the API key isn't configured.
+    """
+    # If API key is not set, skip decision automatically
+    if not openai.api_key:
+        return {"action": "skip"}
+    # Build prompt listing eligible employees
     emp_list = (
         eligible_df[["fullName", "phoneNumber", "organizationPath"]].to_dict(orient="records")
         if not eligible_df.empty
@@ -104,40 +129,95 @@ def gpt_decide(shift, eligible_df):
             temperature=0.4,
             max_tokens=200,
         )
-        # نتوقع أن يرجع ChatGPT JSON صالحاً، لذلك نستخدم literal_eval بشكل آمن
         import ast
-
         return ast.literal_eval(response["choices"][0]["message"]["content"])
     except Exception as e:
         st.error(f"❌ GPT Error: {e}")
         return {"action": "skip"}
 
-# زر واحد لتنفيذ الوكيل الذكي وعرض النتائج
-if st.button("🤖 Unleash the AI Agent"):
+def render_timeline(events):
+    """Return HTML string rendering a list of timeline events."""
+    html = '<div class="timeline">'
+    for event in events:
+        icon = event.get("icon", "")
+        title = event.get("title", "")
+        desc = event.get("desc", "")
+        html += f"""
+        <div class="timeline-card">
+          <span class="icon">{icon}</span>
+          <div>
+            <h4>{title}</h4>
+            <p>{desc}</p>
+          </div>
+        </div>
+        """
+    html += "</div>"
+    return html
+
+def run_agent(employee_ids, df_shifts):
+    """Execute the AI agent workflow and return events, summary, reasoning."""
+    events = []
     shift_assignment_results = []
     reasoning_rows = []
 
+    # Step 1: Fetch employees
+    events.append({"icon": "🔍", "title": "Fetching employee data", "desc": "Loading employee information from UKG API..."})
+    timeline_container.markdown(render_timeline(events), unsafe_allow_html=True)
+    # Attempt to fetch employee data
+    df_employees = fetch_employees(employee_ids)
+    if df_employees.empty:
+        events.append({
+            "icon": "⚠️",
+            "title": "No Employee Data",
+            "desc": "No employees were returned or credentials are invalid."
+        })
+        # even if no employees, proceed to next steps with empty DataFrame
+    else:
+        events.append({
+            "icon": "✅",
+            "title": "Employee Data Loaded",
+            "desc": f"{len(df_employees)} employee(s) loaded successfully."
+        })
+    timeline_container.markdown(render_timeline(events), unsafe_allow_html=True)
+
+    # Step 2: Evaluate each shift
+    events.append({"icon": "📋", "title": "Evaluating Shifts", "desc": "Matching employees to shift requirements..."})
+    timeline_container.markdown(render_timeline(events), unsafe_allow_html=True)
+    # Loop through shifts
     for _, shift in df_shifts.iterrows():
-        # حدد الموظفين المؤهلين بناءً على JobRole
+        # Determine eligible employees based on JobRole
         eligible = df_employees[
             df_employees.apply(lambda r: is_eligible(r, shift), axis=1)
         ] if not df_employees.empty else pd.DataFrame()
-
-        # استخدام GPT لاتخاذ القرار
+        # Step 3: Ask GPT or fallback
+        events.append({"icon": "🤖", "title": "Running AI Decision", "desc": "Determining best action for the shift..."})
+        timeline_container.markdown(render_timeline(events), unsafe_allow_html=True)
         decision = gpt_decide(shift, eligible)
-
         if decision.get("action") == "assign":
             emp = decision.get("employee")
-            st.success(f"✅ {emp} assigned to {shift['Department']} at {shift['ShiftTime']}")
+            events.append({
+                "icon": "✅",
+                "title": f"Assigned {emp}",
+                "desc": f"{emp} assigned to {shift['Department']} at {shift['ShiftTime']}"
+            })
             shift_assignment_results.append((emp, shift["ShiftID"], "✅ Auto-Filled"))
         elif decision.get("action") == "notify":
             emp = decision.get("employee")
-            st.info(f"📬 Notify {emp} to take the shift")
+            events.append({
+                "icon": "📬",
+                "title": f"Notify {emp}",
+                "desc": f"Send notification to {emp} to take the shift"
+            })
             shift_assignment_results.append((emp, shift["ShiftID"], "📨 Notify"))
         else:
+            events.append({
+                "icon": "⚠️",
+                "title": "Skipped",
+                "desc": "No eligible employees available or decision skipped."
+            })
             shift_assignment_results.append(("❌ No eligible", shift["ShiftID"], "⚠️ Skipped"))
-
-        # أسباب الأهلية/الرفض لكل موظف (مؤقتاً نعتبر الشهادات والتوفر وساعات الإضافي متاحة)
+        timeline_container.markdown(render_timeline(events), unsafe_allow_html=True)
+        # Add reasoning for each employee
         for _, emp_row in df_employees.iterrows():
             role_match = shift["RequiredSkill"].strip().lower() == emp_row.get("JobRole", "").strip().lower()
             cert_ok = True
@@ -159,14 +239,25 @@ if st.button("🤖 Unleash the AI Agent"):
                     ),
                 }
             )
+    events.append({"icon": "📊", "title": "Summary Ready", "desc": "The AI has finished processing the shifts."})
+    timeline_container.markdown(render_timeline(events), unsafe_allow_html=True)
+    return events, shift_assignment_results, reasoning_rows
 
-    # عرض ملخص توزيع المناوبات
+# زر رئيسي لتشغيل الوكيل الذكي
+if st.button("▶️ Start AI Agent", key="start_agent", help="Click to unleash the AI"):
+    # تنفيذ الوكيل وعرض النتائج على شكل خط زمني
+    events, shift_assignment_results, reasoning_rows = run_agent(employee_ids_default, df_shifts_default)
+    # عرض الملخص والشرح بعد الانتهاء
     st.subheader("📊 Shift Fulfillment Summary")
-    st.dataframe(pd.DataFrame(shift_assignment_results, columns=["Employee", "ShiftID", "Status"]))
-
-    # عرض جدول لشرح أسباب الاختيار أو الرفض
+    if shift_assignment_results:
+        st.dataframe(pd.DataFrame(shift_assignment_results, columns=["Employee", "ShiftID", "Status"]))
+    else:
+        st.write("No assignments to display.")
     st.subheader("📋 Reasoning Behind Selections")
-    st.dataframe(pd.DataFrame(reasoning_rows))
+    if reasoning_rows:
+        st.dataframe(pd.DataFrame(reasoning_rows))
+    else:
+        st.write("No reasoning data available.")
 
 # تذييل الصفحة
 st.markdown(