app.py

# -*- coding: utf-8 -*-
import streamlit as st
import requests
import json
import re
import os
import operator
import traceback
from functools import lru_cache
from dotenv import load_dotenv

from langchain_groq import ChatGroq
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_core.messages import HumanMessage, SystemMessage, AIMessage, ToolMessage
# from langchain_core.prompts import ChatPromptTemplate # Not explicitly used
from langchain_core.pydantic_v1 import BaseModel, Field
from langchain_core.tools import tool
from langgraph.prebuilt import ToolExecutor
from langgraph.graph import StateGraph, END

from typing import Optional, List, Dict, Any, TypedDict, Annotated

# --- Environment Variable Loading & Validation ---
load_dotenv()
UMLS_API_KEY = os.environ.get("UMLS_API_KEY")
GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
TAVILY_API_KEY = os.environ.get("TAVILY_API_KEY")
missing_keys = []
if not UMLS_API_KEY:
    missing_keys.append("UMLS_API_KEY")
if not GROQ_API_KEY:
    missing_keys.append("GROQ_API_KEY")
if not TAVILY_API_KEY:
    missing_keys.append("TAVILY_API_KEY")
if missing_keys:
    st.error(f"Missing API Key(s): {', '.join(missing_keys)}.")
    st.stop()

# --- Configuration & Constants ---
class ClinicalAppSettings:
    APP_TITLE = "SynapseAI (UMLS/FDA Integrated)"
    PAGE_LAYOUT = "wide"
    MODEL_NAME = "llama3-70b-8192"
    TEMPERATURE = 0.1
    MAX_SEARCH_RESULTS = 3

class ClinicalPrompts:
    SYSTEM_PROMPT = """
    You are SynapseAI, an expert AI clinical assistant engaged in an interactive consultation... [SYSTEM PROMPT REMAINS THE SAME - OMITTED FOR BREVITY]
    """

# --- API Helper Functions (get_rxcui, get_openfda_label, search_text_list) ---
UMLS_AUTH_ENDPOINT = "https://utslogin.nlm.nih.gov/cas/v1/api-key"
RXNORM_API_BASE = "https://rxnav.nlm.nih.gov/REST"
OPENFDA_API_BASE = "https://api.fda.gov/drug/label.json"

@lru_cache(maxsize=256)
def get_rxcui(drug_name: str) -> Optional[str]:
    if not drug_name or not isinstance(drug_name, str):
        return None
    drug_name = drug_name.strip()
    if not drug_name:
        return None
    print(f"RxNorm Lookup for: '{drug_name}'")
    try:
        params = {"name": drug_name, "search": 1}
        response = requests.get(f"{RXNORM_API_BASE}/rxcui.json", params=params, timeout=10)
        response.raise_for_status()
        data = response.json()
        if data and "idGroup" in data and "rxnormId" in data["idGroup"]:
            rxcui = data["idGroup"]["rxnormId"][0]
            print(f"  Found RxCUI: {rxcui} for '{drug_name}'")
            return rxcui
        else:
            params = {"name": drug_name}
            response = requests.get(f"{RXNORM_API_BASE}/drugs.json", params=params, timeout=10)
            response.raise_for_status()
            data = response.json()
            if data and "drugGroup" in data and "conceptGroup" in data["drugGroup"]:
                for group in data["drugGroup"]["conceptGroup"]:
                    if group.get("tty") in ["SBD", "SCD", "GPCK", "BPCK", "IN", "MIN", "PIN"]:
                        if "conceptProperties" in group and group["conceptProperties"]:
                            rxcui = group["conceptProperties"][0].get("rxcui")
                        if rxcui:
                            print(f"  Found RxCUI (via /drugs): {rxcui} for '{drug_name}'")
                            return rxcui
        print(f"  RxCUI not found for '{drug_name}'.")
        return None
    except requests.exceptions.RequestException as e:
        print(f"  Error fetching RxCUI for '{drug_name}': {e}")
        return None
    except json.JSONDecodeError as e:
        print(f"  Error decoding RxNorm JSON response for '{drug_name}': {e}")
        return None
    except Exception as e:
        print(f"  Unexpected error in get_rxcui for '{drug_name}': {e}")
        return None

@lru_cache(maxsize=128)
def get_openfda_label(rxcui: Optional[str] = None, drug_name: Optional[str] = None) -> Optional[dict]:
    if not rxcui and not drug_name:
        return None
    print(f"OpenFDA Label Lookup for: RXCUI={rxcui}, Name={drug_name}")
    search_terms = []
    if rxcui:
        search_terms.append(f'spl_rxnorm_code:"{rxcui}" OR openfda.rxcui:"{rxcui}"')
    if drug_name:
        search_terms.append(f'(openfda.brand_name:"{drug_name.lower()}" OR openfda.generic_name:"{drug_name.lower()}")')
    search_query = " OR ".join(search_terms)
    params = {"search": search_query, "limit": 1}
    try:
        response = requests.get(OPENFDA_API_BASE, params=params, timeout=15)
        response.raise_for_status()
        data = response.json()
        if data and "results" in data and data["results"]:
            print(f"  Found OpenFDA label for query: {search_query}")
            return data["results"][0]
        print(f"  No OpenFDA label found for query: {search_query}")
        return None
    except requests.exceptions.RequestException as e:
        print(f"  Error fetching OpenFDA label: {e}")
        return None
    except json.JSONDecodeError as e:
        print(f"  Error decoding OpenFDA JSON response: {e}")
        return None
    except Exception as e:
        print(f"  Unexpected error in get_openfda_label: {e}")
        return None

def search_text_list(text_list: Optional[List[str]], search_terms: List[str]) -> List[str]:
    found_snippets = []
    if not text_list or not search_terms:
        return found_snippets
    search_terms_lower = [str(term).lower() for term in search_terms if term]
    for text_item in text_list:
        if not isinstance(text_item, str):
            continue
        text_item_lower = text_item.lower()
        for term in search_terms_lower:
            if term in text_item_lower:
                start_index = text_item_lower.find(term)
                snippet_start = max(0, start_index - 50)
                snippet_end = min(len(text_item), start_index + len(term) + 100)
                snippet = text_item[snippet_start:snippet_end]
                snippet = snippet.replace(term, f"**{term}**", 1)
                found_snippets.append(f"...{snippet}...")
                break
    return found_snippets

# --- Other Helper Functions (parse_bp, check_red_flags, format_patient_data_for_prompt) ---
def parse_bp(bp_string: str) -> Optional[tuple[int, int]]:
    if not isinstance(bp_string, str):
        return None
    match = re.match(r"(\d{1,3})\s*/\s*(\d{1,3})", bp_string.strip())
    if match:
        return int(match.group(1)), int(match.group(2))
    return None

def check_red_flags(patient_data: dict) -> List[str]:
    flags = []
    if not patient_data:
        return flags
    symptoms = patient_data.get("hpi", {}).get("symptoms", [])
    vitals = patient_data.get("vitals", {})
    history = patient_data.get("pmh", {}).get("conditions", "")
    symptoms_lower = [str(s).lower() for s in symptoms if isinstance(s, str)]
    
    if "chest pain" in symptoms_lower:
        flags.append("Red Flag: Chest Pain reported.")
    if "shortness of breath" in symptoms_lower:
        flags.append("Red Flag: Shortness of Breath reported.")
    if "severe headache" in symptoms_lower:
        flags.append("Red Flag: Severe Headache reported.")
    if "sudden vision loss" in symptoms_lower:
        flags.append("Red Flag: Sudden Vision Loss reported.")
    if "weakness on one side" in symptoms_lower:
        flags.append("Red Flag: Unilateral Weakness reported (potential stroke).")
    if "hemoptysis" in symptoms_lower:
        flags.append("Red Flag: Hemoptysis (coughing up blood).")
    if "syncope" in symptoms_lower:
        flags.append("Red Flag: Syncope (fainting).")
    
    if vitals:
        temp = vitals.get("temp_c")
        hr = vitals.get("hr_bpm")
        rr = vitals.get("rr_rpm")
        spo2 = vitals.get("spo2_percent")
        bp_str = vitals.get("bp_mmhg")
        
        if temp is not None and temp >= 38.5:
            flags.append(f"Red Flag: Fever ({temp}°C).")
        if hr is not None and hr >= 120:
            flags.append(f"Red Flag: Tachycardia ({hr} bpm).")
        if hr is not None and hr <= 50:
            flags.append(f"Red Flag: Bradycardia ({hr} bpm).")
        if rr is not None and rr >= 24:
            flags.append(f"Red Flag: Tachypnea ({rr} rpm).")
        if spo2 is not None and spo2 <= 92:
            flags.append(f"Red Flag: Hypoxia ({spo2}%).")
    
    if bp_str:
        bp = parse_bp(bp_str)
        if bp:
            if bp[0] >= 180 or bp[1] >= 110:
                flags.append(f"Red Flag: Hypertensive Urgency/Emergency (BP: {bp_str} mmHg).")
            if bp[0] <= 90 or bp[1] <= 60:
                flags.append(f"Red Flag: Hypotension (BP: {bp_str} mmHg).")
    
    if history and isinstance(history, str):
        history_lower = history.lower()
        if "history of mi" in history_lower and "chest pain" in symptoms_lower:
            flags.append("Red Flag: History of MI with current Chest Pain.")
        if "history of dvt/pe" in history_lower and "shortness of breath" in symptoms_lower:
            flags.append("Red Flag: History of DVT/PE with current Shortness of Breath.")
    
    return list(set(flags))

def format_patient_data_for_prompt(data: dict) -> str:
    if not data:
        return "No patient data provided."
    prompt_str = ""
    for key, value in data.items():
        section_title = key.replace('_', ' ').title()
        if isinstance(value, dict) and value:
            has_content = any(sub_value for sub_value in value.values())
            if has_content:
                prompt_str += f"**{section_title}:**\n"
                for sub_key, sub_value in value.items():
                    if sub_value:
                        prompt_str += f"  - {sub_key.replace('_', ' ').title()}: {sub_value}\n"
        elif isinstance(value, list) and value:
            prompt_str += f"**{section_title}:** {', '.join(map(str, value))}\n"
        elif value and not isinstance(value, dict):
            prompt_str += f"**{section_title}:** {value}\n"
    return prompt_str.strip()

# --- Tool Definitions ---
class LabOrderInput(BaseModel):
    test_name: str = Field(...)
    reason: str = Field(...)
    priority: str = Field("Routine")

class PrescriptionInput(BaseModel):
    medication_name: str = Field(...)
    dosage: str = Field(...)
    route: str = Field(...)
    frequency: str = Field(...)
    duration: str = Field("As directed")
    reason: str = Field(...)

class InteractionCheckInput(BaseModel):
    potential_prescription: str = Field(...)
    current_medications: Optional[List[str]] = Field(None)
    allergies: Optional[List[str]] = Field(None)

class FlagRiskInput(BaseModel):
    risk_description: str = Field(...)
    urgency: str = Field("High")

@tool("order_lab_test", args_schema=LabOrderInput)
def order_lab_test(test_name: str, reason: str, priority: str = "Routine") -> str:
    """
    Orders a lab test with the specified test name, reason, and priority.
    """
    print(f"Executing order_lab_test: {test_name}, Reason: {reason}, Priority: {priority}")
    return json.dumps({
        "status": "success",
        "message": f"Lab Ordered: {test_name} ({priority})",
        "details": f"Reason: {reason}"
    })

@tool("prescribe_medication", args_schema=PrescriptionInput)
def prescribe_medication(medication_name: str, dosage: str, route: str, frequency: str, duration: str, reason: str) -> str:
    """
    Prepares a prescription for the specified medication including dosage, route, frequency, and duration.
    """
    print(f"Executing prescribe_medication: {medication_name} {dosage}...")
    return json.dumps({
        "status": "success",
        "message": f"Prescription Prepared: {medication_name} {dosage} {route} {frequency}",
        "details": f"Duration: {duration}. Reason: {reason}"
    })

@tool("check_drug_interactions", args_schema=InteractionCheckInput)
def check_drug_interactions(potential_prescription: str, current_medications: Optional[List[str]] = None, allergies: Optional[List[str]] = None) -> str:
    """
    Checks for potential drug interactions and allergy risks for the given prescription.
    """
    print(f"\n--- Executing REAL check_drug_interactions ---")
    print(f"Checking potential prescription: '{potential_prescription}'")
    warnings = []
    potential_med_lower = potential_prescription.lower().strip()
    current_meds_list = current_medications or []
    allergies_list = allergies or []
    current_med_names_lower = []
    for med in current_meds_list:
        match = re.match(r"^\s*([a-zA-Z\-]+)", str(med))
        if match:
            current_med_names_lower.append(match.group(1).lower())
    allergies_lower = [str(a).lower().strip() for a in allergies_list if a]
    print(f"  Against Current Meds (names): {current_med_names_lower}")
    print(f"  Against Allergies: {allergies_lower}")
    print(f"  Step 1: Normalizing '{potential_prescription}'...")
    potential_rxcui = get_rxcui(potential_prescription)
    potential_label = get_openfda_label(rxcui=potential_rxcui, drug_name=potential_prescription)
    if not potential_rxcui and not potential_label:
        warnings.append(f"INFO: Could not reliably identify '{potential_prescription}'. Checks may be incomplete.")
    print("  Step 2: Performing Allergy Check...")
    for allergy in allergies_lower:
        if allergy == potential_med_lower:
            warnings.append(f"CRITICAL ALLERGY (Name Match): Patient allergic to '{allergy}'. Potential prescription is '{potential_prescription}'.")
        elif allergy in ["penicillin", "pcns"] and potential_med_lower in ["amoxicillin", "ampicillin", "augmentin", "piperacillin"]:
            warnings.append(f"POTENTIAL CROSS-ALLERGY: Patient allergic to Penicillin. High risk with '{potential_prescription}'.")
        elif allergy == "sulfa" and potential_med_lower in ["sulfamethoxazole", "bactrim", "sulfasalazine"]:
            warnings.append(f"POTENTIAL CROSS-ALLERGY: Patient allergic to Sulfa. High risk with '{potential_prescription}'.")
        elif allergy in ["nsaids", "aspirin"] and potential_med_lower in ["ibuprofen", "naproxen", "ketorolac", "diclofenac"]:
            warnings.append(f"POTENTIAL CROSS-ALLERGY: Patient allergic to NSAIDs/Aspirin. Risk with '{potential_prescription}'.")
    if potential_label:
        contraindications = potential_label.get("contraindications")
        warnings_section = potential_label.get("warnings_and_cautions") or potential_label.get("warnings")
        if contraindications:
            allergy_mentions_ci = search_text_list(contraindications, allergies_lower)
            if allergy_mentions_ci:
                warnings.append(f"ALLERGY RISK (Contraindication Found): Label for '{potential_prescription}' mentions contraindication potentially related to patient allergies: {'; '.join(allergy_mentions_ci)}")
        if warnings_section:
            allergy_mentions_warn = search_text_list(warnings_section, allergies_lower)
            if allergy_mentions_warn:
                warnings.append(f"ALLERGY RISK (Warning Found): Label for '{potential_prescription}' mentions warnings potentially related to patient allergies: {'; '.join(allergy_mentions_warn)}")
    print("  Step 3: Performing Drug-Drug Interaction Check...")
    if potential_rxcui or potential_label:
        for current_med_name in current_med_names_lower:
            if not current_med_name or current_med_name == potential_med_lower:
                continue
            print(f"    Checking interaction between '{potential_prescription}' and '{current_med_name}'...")
            current_rxcui = get_rxcui(current_med_name)
            current_label = get_openfda_label(rxcui=current_rxcui, drug_name=current_med_name)
            search_terms_for_current = [current_med_name]
            if current_rxcui:
                search_terms_for_current.append(current_rxcui)
            search_terms_for_potential = [potential_med_lower]
            if potential_rxcui:
                search_terms_for_potential.append(potential_rxcui)
            interaction_found_flag = False
            if potential_label and potential_label.get("drug_interactions"):
                interaction_mentions = search_text_list(potential_label.get("drug_interactions"), search_terms_for_current)
                if interaction_mentions:
                    warnings.append(f"Potential Interaction ({potential_prescription.capitalize()} Label): Mentions '{current_med_name.capitalize()}'. Snippets: {'; '.join(interaction_mentions)}")
                    interaction_found_flag = True
            if current_label and current_label.get("drug_interactions") and not interaction_found_flag:
                interaction_mentions = search_text_list(current_label.get("drug_interactions"), search_terms_for_potential)
                if interaction_mentions:
                    warnings.append(f"Potential Interaction ({current_med_name.capitalize()} Label): Mentions '{potential_prescription.capitalize()}'. Snippets: {'; '.join(interaction_mentions)}")
    else:
        warnings.append(f"INFO: Drug-drug interaction check skipped for '{potential_prescription}' as it could not be identified via RxNorm/OpenFDA.")
    final_warnings = list(set(warnings))
    status = "warning" if any("CRITICAL" in w or "Interaction" in w or "RISK" in w for w in final_warnings) else "clear"
    if not final_warnings:
        status = "clear"
        message = f"Interaction/Allergy check for '{potential_prescription}': {len(final_warnings)} potential issue(s) identified using RxNorm/OpenFDA." if final_warnings else f"No major interactions or allergy issues identified for '{potential_prescription}' based on RxNorm/OpenFDA lookup."
    print(f"--- Interaction Check Complete for '{potential_prescription}' ---")
    return json.dumps({
        "status": status,
        "message": message,
        "warnings": final_warnings
    })

@tool("flag_risk", args_schema=FlagRiskInput)
def flag_risk(risk_description: str, urgency: str) -> str:
    """
    Flags a clinical risk with the provided description and urgency.
    """
    print(f"Executing flag_risk: {risk_description}, Urgency: {urgency}")
    st.error(f"🚨 **{urgency.upper()} RISK FLAGGED by AI:** {risk_description}", icon="🚨")
    return json.dumps({
        "status": "flagged",
        "message": f"Risk '{risk_description}' flagged with {urgency} urgency."
    })

search_tool = TavilySearchResults(max_results=ClinicalAppSettings.MAX_SEARCH_RESULTS, name="tavily_search_results")

# --- LangGraph Setup ---
class AgentState(TypedDict):
    messages: Annotated[list[Any], operator.add]
    patient_data: Optional[dict]

tools = [order_lab_test, prescribe_medication, check_drug_interactions, flag_risk, search_tool]
tool_executor = ToolExecutor(tools)
model = ChatGroq(temperature=ClinicalAppSettings.TEMPERATURE, model=ClinicalAppSettings.MODEL_NAME)
model_with_tools = model.bind_tools(tools)

# --- Graph Nodes (agent_node, tool_node) ---
def agent_node(state: AgentState):
    print("\n---AGENT NODE---")
    current_messages = state['messages']
    if not current_messages or not isinstance(current_messages[0], SystemMessage):
        print("Prepending System Prompt.")
        current_messages = [SystemMessage(content=ClinicalPrompts.SYSTEM_PROMPT)] + current_messages
    print(f"Invoking LLM with {len(current_messages)} messages.")
    try:
        response = model_with_tools.invoke(current_messages)
        print(f"Agent Raw Response Type: {type(response)}")
        if hasattr(response, 'tool_calls') and response.tool_calls:
            print(f"Agent Response Tool Calls: {response.tool_calls}")
        else:
            print("Agent Response: No tool calls.")
    except Exception as e:
        print(f"ERROR in agent_node: {e}")
        traceback.print_exc()
        error_message = AIMessage(content=f"Error: {e}")
        return {"messages": [error_message]}
    return {"messages": [response]}

def tool_node(state: AgentState):
    print("\n---TOOL NODE---")
    tool_messages = []
    last_message = state['messages'][-1]
    if not isinstance(last_message, AIMessage) or not getattr(last_message, 'tool_calls', None):
        print("Warning: Tool node called unexpectedly.")
        return {"messages": []}
    tool_calls = last_message.tool_calls
    print(f"Tool calls received: {json.dumps(tool_calls, indent=2)}")
    prescriptions_requested = {}
    interaction_checks_requested = {}
    for call in tool_calls:
        tool_name = call.get('name')
        tool_args = call.get('args', {})
        if tool_name == 'prescribe_medication':
            med_name = tool_args.get('medication_name', '').lower()
            if med_name:
                prescriptions_requested[med_name] = call
        elif tool_name == 'check_drug_interactions':
            potential_med = tool_args.get('potential_prescription', '').lower()
            if potential_med:
                interaction_checks_requested[potential_med] = call
    valid_tool_calls_for_execution = []
    blocked_ids = set()
    for med_name, prescribe_call in prescriptions_requested.items():
        if med_name not in interaction_checks_requested:
            st.error(f"**Safety Violation:** AI tried to prescribe '{med_name}' without check.")
            error_msg = ToolMessage(content=json.dumps({
                "status": "error",
                "message": f"Interaction check needed for '{med_name}'."
            }), tool_call_id=prescribe_call['id'], name=prescribe_call['name'])
            tool_messages.append(error_msg)
            blocked_ids.add(prescribe_call['id'])
    valid_tool_calls_for_execution = [call for call in tool_calls if call['id'] not in blocked_ids]
    patient_data = state.get("patient_data", {})
    patient_meds_full = patient_data.get("medications", {}).get("current", [])
    patient_allergies = patient_data.get("allergies", [])
    for call in valid_tool_calls_for_execution:
        if call['name'] == 'check_drug_interactions':
            if 'args' not in call:
                call['args'] = {}
            call['args']['current_medications'] = patient_meds_full
            call['args']['allergies'] = patient_allergies
            print(f"Augmented interaction check args for call ID {call['id']}")
    if valid_tool_calls_for_execution:
        print(f"Attempting execution: {[c['name'] for c in valid_tool_calls_for_execution]}")
    try:
        responses = tool_executor.batch(valid_tool_calls_for_execution, return_exceptions=True)
        for call, resp in zip(valid_tool_calls_for_execution, responses):
            tool_call_id = call['id']
            tool_name = call['name']
            if isinstance(resp, Exception):
                error_type = type(resp).__name__
                error_str = str(resp)
                print(f"ERROR executing tool '{tool_name}': {error_type} - {error_str}")
                traceback.print_exc()
                st.error(f"Error: {error_type}")
                error_content = json.dumps({"status": "error", "message": f"Failed: {error_type} - {error_str}"})
                tool_messages.append(ToolMessage(content=error_content, tool_call_id=tool_call_id, name=tool_name))
            else:
                print(f"Tool '{tool_name}' executed.")
                content_str = str(resp)
                tool_messages.append(ToolMessage(content=content_str, tool_call_id=tool_call_id, name=tool_name))
    except Exception as e:
        print(f"CRITICAL TOOL NODE ERROR: {e}")
        traceback.print_exc()
        st.error(f"Critical error: {e}")
        error_content = json.dumps({"status": "error", "message": f"Internal error: {e}"})
        processed_ids = {msg.tool_call_id for msg in tool_messages}
        [tool_messages.append(ToolMessage(content=error_content, tool_call_id=call['id'], name=call['name']))
         for call in valid_tool_calls_for_execution if call['id'] not in processed_ids]
    print(f"Returning {len(tool_messages)} tool messages.")
    return {"messages": tool_messages}

# --- Graph Edges (Routing Logic) ---
def should_continue(state: AgentState) -> str:
    print("\n---ROUTING DECISION---")
    last_message = state['messages'][-1] if state['messages'] else None
    if not isinstance(last_message, AIMessage):
        return "end_conversation_turn"
    if "Sorry, an internal error occurred" in last_message.content:
        return "end_conversation_turn"
    if getattr(last_message, 'tool_calls', None):
        return "continue_tools"
    else:
        return "end_conversation_turn"

# --- Graph Definition & Compilation ---
workflow = StateGraph(AgentState)
workflow.add_node("agent", agent_node)
workflow.add_node("tools", tool_node)
workflow.set_entry_point("agent")
workflow.add_conditional_edges("agent", should_continue, {"continue_tools": "tools", "end_conversation_turn": END})
workflow.add_edge("tools", "agent")
app = workflow.compile()
print("LangGraph compiled successfully.")

# --- Streamlit UI ---
def main():
    st.set_page_config(page_title=ClinicalAppSettings.APP_TITLE, layout=ClinicalAppSettings.PAGE_LAYOUT)
    st.title(f"🩺 {ClinicalAppSettings.APP_TITLE}")
    st.caption(f"Interactive Assistant | LangGraph/Groq/Tavily/UMLS/OpenFDA | Model: {ClinicalAppSettings.MODEL_NAME}")
    if "messages" not in st.session_state:
        st.session_state.messages = []
    if "patient_data" not in st.session_state:
        st.session_state.patient_data = None
    if "graph_app" not in st.session_state:
        st.session_state.graph_app = app

    # --- Patient Data Input Sidebar ---
    with st.sidebar:
        st.header("📄 Patient Intake Form")
        # Input fields... (Using shorter versions for brevity, assume full fields are here)
        st.subheader("Demographics")
        age = st.number_input("Age", 0, 120, 55)
        sex = st.selectbox("Sex", ["Male", "Female", "Other"])
        st.subheader("HPI")
        chief_complaint = st.text_input("Chief Complaint", "Chest pain")
        hpi_details = st.text_area("HPI Details", "55 y/o male...", height=100)
        symptoms = st.multiselect("Symptoms", ["Nausea", "Diaphoresis", "SOB", "Dizziness"], default=["Nausea", "Diaphoresis"])
        st.subheader("History")
        pmh = st.text_area("PMH", "HTN, HLD, DM2, History of MI")
        psh = st.text_area("PSH", "Appendectomy")
        st.subheader("Meds & Allergies")
        current_meds_str = st.text_area("Current Meds", "Lisinopril 10mg daily\nMetformin 1000mg BID")
        allergies_str = st.text_area("Allergies", "Penicillin (rash)")
        st.subheader("Social/Family")
        social_history = st.text_area("SH", "Smoker")
        family_history = st.text_area("FHx", "Father MI")
        st.subheader("Vitals & Exam")
        col1, col2 = st.columns(2)
        with col1:
            temp_c = st.number_input("Temp C", 35.0, 42.0, 36.8, format="%.1f")
            hr_bpm = st.number_input("HR", 30, 250, 95)
            rr_rpm = st.number_input("RR", 5, 50, 18)
        with col2:
            bp_mmhg = st.text_input("BP", "155/90")
            spo2_percent = st.number_input("SpO2", 70, 100, 96)
            pain_scale = st.slider("Pain", 0, 10, 8)
        exam_notes = st.text_area("Exam Notes", "Awake, alert...", height=50)

        if st.button("Start/Update Consultation"):
            current_meds_list = [med.strip() for med in current_meds_str.split('\n') if med.strip()]
            current_med_names_only = []
            for med in current_meds_list:
                match = re.match(r"^\s*([a-zA-Z\-]+)", med)
                if match:
                    current_med_names_only.append(match.group(1).lower())
            allergies_list = []
            for a in allergies_str.split(','):
                cleaned_allergy = a.strip()
                if cleaned_allergy:
                    match = re.match(r"^\s*([a-zA-Z\-\s/]+)(?:\s*\(.*\))?", cleaned_allergy)
                    name_part = match.group(1).strip().lower() if match else cleaned_allergy.lower()
                    allergies_list.append(name_part)
            st.session_state.patient_data = {
                "demographics": {"age": age, "sex": sex},
                "hpi": {"chief_complaint": chief_complaint, "details": hpi_details, "symptoms": symptoms},
                "pmh": {"conditions": pmh},
                "psh": {"procedures": psh},
                "medications": {"current": current_meds_list, "names_only": current_med_names_only},
                "allergies": allergies_list,
                "social_history": {"details": social_history},
                "family_history": {"details": family_history},
                "vitals": {
                    "temp_c": temp_c,
                    "hr_bpm": hr_bpm,
                    "bp_mmhg": bp_mmhg,
                    "rr_rpm": rr_rpm,
                    "spo2_percent": spo2_percent,
                    "pain_scale": pain_scale
                },
                "exam_findings": {"notes": exam_notes}
            }
            red_flags = check_red_flags(st.session_state.patient_data)
            st.sidebar.markdown("---")
            if red_flags:
                st.sidebar.warning("**Initial Red Flags:**")
                [st.sidebar.warning(f"- {flag.replace('Red Flag: ','')}") for flag in red_flags]
            else:
                st.sidebar.success("No immediate red flags.")
            initial_prompt = "Initiate consultation. Review patient data and begin analysis."
            st.session_state.messages = [HumanMessage(content=initial_prompt)]
            st.success("Patient data loaded/updated.")

    # --- Main Chat Interface Area ---
    st.header("💬 Clinical Consultation")
    # Display loop - SyntaxError Fixed
    for msg in st.session_state.messages:
        if isinstance(msg, HumanMessage):
            with st.chat_message("user"):
                st.markdown(msg.content)  # No key
        elif isinstance(msg, AIMessage):
            with st.chat_message("assistant"):
                ai_content = msg.content
                structured_output = None
                try:
                    json_match = re.search(r"```json\s*(\{.*?\})\s*```", ai_content, re.DOTALL | re.IGNORECASE)
                    if json_match:
                        json_str = json_match.group(1)
                        prefix = ai_content[:json_match.start()].strip()
                        suffix = ai_content[json_match.end():].strip()
                        if prefix:
                            st.markdown(prefix)
                        structured_output = json.loads(json_str)
                        if suffix:
                            st.markdown(suffix)
                    elif ai_content.strip().startswith("{") and ai_content.strip().endswith("}"):
                        structured_output = json.loads(ai_content)
                        ai_content = ""
                    else:
                        st.markdown(ai_content)
                except Exception as e:
                    st.markdown(ai_content)
                    print(f"Error parsing/displaying AI JSON: {e}")
                if structured_output and isinstance(structured_output, dict):
                    st.divider()
                    st.subheader("📊 AI Analysis & Recommendations")
                    cols = st.columns(2)
                    with cols[0]:
                        st.markdown("**Assessment:**")
                        st.markdown(f"> {structured_output.get('assessment', 'N/A')}")
                        st.markdown("**Differential Diagnosis:**")
                        ddx = structured_output.get('differential_diagnosis', [])
                        if ddx:
                            [st.expander(f"{'🥇🥈🥉'[('High','Medium','Low').index(item.get('likelihood','Low')[0])] if item.get('likelihood','?')[0] in 'HML' else '?'} {item.get('diagnosis', 'Unknown')} ({item.get('likelihood','?')})").write(f"**Rationale:** {item.get('rationale', 'N/A')}") for item in ddx]
                        else:
                            st.info("No DDx provided.")
                        st.markdown("**Risk Assessment:**")
                        risk = structured_output.get('risk_assessment', {})
                        flags = risk.get('identified_red_flags', [])
                        concerns = risk.get("immediate_concerns", [])
                        comps = risk.get("potential_complications", [])
                        if flags:
                            st.warning(f"**Flags:** {', '.join(flags)}")
                        if concerns:
                            st.warning(f"**Concerns:** {', '.join(concerns)}")
                        if comps:
                            st.info(f"**Potential Complications:** {', '.join(comps)}")
                        if not flags and not concerns:
                            st.success("No major risks highlighted.")
                    with cols[1]:
                        st.markdown("**Recommended Plan:**")
                        plan = structured_output.get('recommended_plan', {})
                        for section in ["investigations","therapeutics","consultations","patient_education"]:
                            st.markdown(f"_{section.replace('_',' ').capitalize()}:_")
                            items = plan.get(section)
                            if items and isinstance(items, list):
                                [st.markdown(f"- {item}") for item in items]
                            elif items:
                                st.markdown(f"- {items}")
                            else:
                                st.markdown("_None_")
                            st.markdown("")
                        st.markdown("**Rationale & Guideline Check:**")
                        st.markdown(f"> {structured_output.get('rationale_summary', 'N/A')}")
                        interaction_summary = structured_output.get("interaction_check_summary", "")
                        if interaction_summary:
                            st.markdown("**Interaction Check Summary:**")
                            st.markdown(f"> {interaction_summary}")
                        st.divider()

                if getattr(msg, 'tool_calls', None):
                    with st.expander("🛠️ AI requested actions", expanded=False):
                        if msg.tool_calls:
                            for tc in msg.tool_calls:
                                try:
                                    st.code(f"Action: {tc.get('name', 'Unknown Tool')}\nArgs: {json.dumps(tc.get('args', {}), indent=2)}", language="json")
                                except Exception as display_e:
                                    st.error(f"Could not display tool call arguments properly: {display_e}", icon="⚠️")
                                    st.code(f"Action: {tc.get('name', 'Unknown Tool')}\nRaw Args: {tc.get('args')}")
                        else:
                            st.caption("_No actions requested in this turn._")
        elif isinstance(msg, ToolMessage):
            tool_name_display = getattr(msg, 'name', 'tool_execution')
            with st.chat_message(tool_name_display, avatar="🛠️"):
                try:
                    tool_data = json.loads(msg.content)
                    status = tool_data.get("status", "info")
                    message = tool_data.get("message", msg.content)
                    details = tool_data.get("details")
                    warnings = tool_data.get("warnings")
                    if status == "success" or status == "clear" or status == "flagged":
                        st.success(f"{message}", icon="✅" if status != "flagged" else "🚨")
                    elif status == "warning":
                        st.warning(f"{message}", icon="⚠️")
                    if warnings and isinstance(warnings, list):
                        st.caption("Details:")
                        [st.caption(f"- {warn}") for warn in warnings]
                    else:
                        st.error(f"{message}", icon="❌")
                    if details:
                        st.caption(f"Details: {details}")
                except json.JSONDecodeError:
                    st.info(f"{msg.content}")
                except Exception as e:
                    st.error(f"Error displaying tool message: {e}", icon="❌")
                    st.caption(f"Raw content: {msg.content}")

    # --- Chat Input Logic ---
    if prompt := st.chat_input("Your message or follow-up query..."):
        if not st.session_state.patient_data:
            st.warning("Please load patient data first.")
            st.stop()
        user_message = HumanMessage(content=prompt)
        st.session_state.messages.append(user_message)
        with st.chat_message("user"):
            st.markdown(prompt)
        current_state = AgentState(messages=st.session_state.messages, patient_data=st.session_state.patient_data)
        with st.spinner("SynapseAI is thinking..."):
            try:
                final_state = st.session_state.graph_app.invoke(current_state, {"recursion_limit": 15})
                st.session_state.messages = final_state['messages']
            except Exception as e:
                print(f"CRITICAL ERROR: {e}")
                traceback.print_exc()
                st.error(f"Error: {e}")
        st.rerun()

    # Disclaimer
    st.markdown("---")
    st.warning("**Disclaimer:** SynapseAI is for demonstration...")

if __name__ == "__main__":
    main()