Upload folder using huggingface_hub

app.py

@@ -1,5 +1,6 @@
 import os
 import json
+import time
 import gradio as gr
 from fastmcp import FastMCP
 from openai import OpenAI
@@ -20,6 +21,76 @@ if STRIPE_API_KEY:
 # Initialize MCP Server
 mcp = FastMCP("Aussie Agent Hub")
 
+# --- AWS TOOLS ---
+
+@mcp.tool()
+def deploy_to_sagemaker(model_id: str, instance_type: str = "ml.g5.xlarge", region: str = "ap-southeast-2") -> str:
+    """Deploy a Hugging Face model to an AWS SageMaker real-time endpoint."""
+    try:
+        import boto3
+        import sagemaker
+        from sagemaker.huggingface import HuggingFaceModel
+        
+        if not os.environ.get("AWS_ACCESS_KEY_ID"):
+            return "❌ Error: AWS credentials not found in environment secrets."
+            
+        role = os.environ.get("AWS_SAGEMAKER_ROLE")
+        if not role:
+            return "❌ Error: AWS_SAGEMAKER_ROLE secret is required for SageMaker deployment."
+
+        session = sagemaker.Session(boto_session=boto3.Session(region_name=region))
+        huggingface_model = HuggingFaceModel(
+            env={'HF_MODEL_ID': model_id, 'HF_TASK': 'text-generation'},
+            role=role,
+            transformers_version="4.37.0",
+            pytorch_version="2.1.0",
+            py_version="py310",
+        )
+        predictor = huggingface_model.deploy(
+            initial_instance_count=1,
+            instance_type=instance_type,
+            endpoint_name=f"aussie-hub-{model_id.split('/')[-1]}-{int(time.time())}"
+        )
+        return f"✅ Deployment Successful! SageMaker Endpoint: {predictor.endpoint_name} is spinning up in {region}."
+    except Exception as e:
+        return f"❌ SageMaker Error: {str(e)}"
+
+@mcp.tool()
+def call_bedrock_intelligence(prompt: str, model_id: str = "anthropic.claude-3-5-sonnet-20240620-v1:0") -> str:
+    """Query a high-performance model via AWS Bedrock for enterprise-grade intelligence."""
+    try:
+        import boto3
+        region = "us-east-1"
+        bedrock_client = boto3.client(service_name='bedrock-runtime', region_name=region)
+        body = json.dumps({
+            "anthropic_version": "bedrock-2023-05-31",
+            "max_tokens": 1000,
+            "messages": [{"role": "user", "content": prompt}]
+        })
+        response = bedrock_client.invoke_model(body=body, modelId=model_id)
+        response_body = json.loads(response.get('body').read())
+        return response_body.get('content')[0].get('text')
+    except Exception as e:
+        return f"❌ Bedrock Error: {str(e)}"
+
+# --- IQ-200 FEW-SHOT INTELLIGENCE (No-Cost Context) ---
+
+def load_examples(persona="router"):
+    """Load Master Examples to provide few-shot intelligence to the model."""
+    filename = f"{persona}_master_examples.md"
+    try:
+        # Check local folder first
+        local_path = os.path.join("knowledge/examples", filename)
+        if os.path.exists(local_path):
+            with open(local_path, "r") as f:
+                content = f.read()
+        else:
+            content = load_from_databank(filename, folder="knowledge/examples")
+            
+        return f"\n### MASTER EXAMPLES (IQ-200 Reference):\n{content}\n" if content else ""
+    except Exception:
+        return ""
+
 # --- IQ-300 INTELLIGENCE ENGINE (Autonomous Tool-Calling) ---
 
 def llm_worker(prompt, system_prompt="You are a specialized business assistant.", use_tools=True, persona=None):
@@ -71,46 +142,45 @@ def llm_worker(prompt, system_prompt="You are a specialized business assistant."
         {
             "type": "function",
             "function": {
-                "name": "launch_client_business",
-                "description": "Orchestrate a full ebook business build for a paying client.",
+                "name": "generate_image",
+                "description": "Generate a branded image using free ZeroGPU fallbacks.",
                 "parameters": {
                     "type": "object",
                     "properties": {
-                        "client_name": {"type": "string"},
-                        "niche": {"type": "string"},
-                        "email": {"type": "string"}
+                        "prompt": {"type": "string", "description": "Description of the image to generate."}
                     },
-                    "required": ["client_name", "niche", "email"]
+                    "required": ["prompt"]
                 }
             }
         },
         {
             "type": "function",
             "function": {
-                "name": "generate_image",
-                "description": "Generate a branded image using free ZeroGPU fallbacks.",
+                "name": "deploy_to_sagemaker",
+                "description": "Deploy a Hugging Face model to AWS SageMaker.",
                 "parameters": {
                     "type": "object",
                     "properties": {
-                        "prompt": {"type": "string", "description": "Description of the image to generate."}
+                        "model_id": {"type": "string"},
+                        "instance_type": {"type": "string"},
+                        "region": {"type": "string"}
                     },
-                    "required": ["prompt"]
+                    "required": ["model_id"]
                 }
             }
         },
         {
             "type": "function",
             "function": {
-                "name": "create_stripe_checkout_session",
-                "description": "Create a live Stripe Checkout link.",
+                "name": "call_bedrock_intelligence",
+                "description": "Query AWS Bedrock for advanced reasoning.",
                 "parameters": {
                     "type": "object",
                     "properties": {
-                        "price_id": {"type": "string"},
-                        "success_url": {"type": "string"},
-                        "cancel_url": {"type": "string"}
+                        "prompt": {"type": "string"},
+                        "model_id": {"type": "string"}
                     },
-                    "required": ["price_id", "success_url", "cancel_url"]
+                    "required": ["prompt"]
                 }
             }
         }
@@ -129,19 +199,19 @@ def llm_worker(prompt, system_prompt="You are a specialized business assistant."
         tool_calls = response_message.tool_calls
         
         if tool_calls:
-            # Autonomous Execution Loop
             messages.append(response_message)
             for tool_call in tool_calls:
                 function_name = tool_call.function.name
                 args = json.loads(tool_call.function.arguments)
                 
-                # Execute tool locally
                 if function_name == "search_market_trends":
                     result = search_market_trends_internal(args["topic"])
                 elif function_name == "generate_image":
                     result = generate_image_internal(args["prompt"])
-                elif function_name == "create_stripe_checkout_session":
-                    result = create_stripe_checkout_session_internal(args["price_id"], args["success_url"], args["cancel_url"])
+                elif function_name == "deploy_to_sagemaker":
+                    result = deploy_to_sagemaker(args["model_id"], args.get("instance_type", "ml.g5.xlarge"), args.get("region", "ap-southeast-2"))
+                elif function_name == "call_bedrock_intelligence":
+                    result = call_bedrock_intelligence(args["prompt"], args.get("model_id", "anthropic.claude-3-5-sonnet-20240620-v1:0"))
                 else:
                     result = "Tool not implemented."
                 
@@ -174,31 +244,21 @@ def llm_worker(prompt, system_prompt="You are a specialized business assistant."
 # --- INTERNAL TOOLS (Actual Logic) ---
 
 def search_market_trends_internal(topic: str) -> str:
-    # This now runs as a background process for GPT-4o
     prompt = f"Conduct a professional market research analysis for the niche: '{topic}'. Suggest pricing and identify competitors."
-    # Use mini for the actual research content to save credits
-    return llm_worker(prompt, use_tools=False)
+    return llm_worker(prompt, use_tools=False, persona="author")
 
 def generate_image_internal(prompt: str) -> str:
     from gradio_client import Client
     import shutil
     
-    # Comprehensive Business Identity
     business_name = os.environ.get("BUSINESS_NAME", "Fair Dinkum Publishing")
     owner = os.environ.get("BUSINESS_OWNER", "BRETT SJOBERG")
     abn = os.environ.get("BUSINESS_ABN", "63 590 716 023")
-    brand_tag = "Aussie AI"
-    website = "brettapps.com"
     
-    brand_context = (
-        f"Professional branded asset for {business_name} ({brand_tag}). "
-        f"Owner: {owner}, ABN: {abn}, Website: {website}. "
-        "Style: Modern, high-intelligence, polished, premium quality. "
-    )
+    brand_context = f"Professional branded asset for {business_name}. Owner: {owner}, ABN: {abn}. Style: Modern, high-intelligence. "
     full_prompt = brand_context + prompt
     
     try:
-        # Attempt ZeroGPU Generation
         client = Client("mrfakename/Z-Image-Turbo", token=HF_TOKEN)
         result = client.predict(prompt=full_prompt, height=1024, width=1024, num_inference_steps=9, seed=42, randomize_seed=True, api_name="/generate_image")
         temp_path = result[0] if isinstance(result, (list, tuple)) else result
@@ -212,39 +272,17 @@ def generate_image_internal(prompt: str) -> str:
     os.makedirs("exports/images", exist_ok=True)
     final_path = f"exports/images/{abs(hash(prompt))}.png"
     shutil.copy(temp_path, final_path)
-    return f"Branded Image Generated using {model_used}: {final_path}. (Context: {brand_context})"
+    return f"Branded Image Generated using {model_used}: {final_path}."
 
 def create_stripe_product_with_price_internal(name: str, description: str, unit_amount_cents: int, currency: str = "aud") -> str:
     try:
         product = stripe.Product.create(name=name, description=description)
         price = stripe.Price.create(product=product.id, unit_amount=unit_amount_cents, currency=currency)
-        return f"Product Created: {name} (ID: {product.id}). Price Created (ID: {price.id}) for {unit_amount_cents/100:.2f} {currency.upper()}."
-    except Exception as e:
-        return f"Stripe Product Error: {str(e)}"
-
-def launch_client_business_internal(client_name: str, niche: str, email: str) -> str:
-    """Orchestrate a high-ticket business build for a client."""
-    # 1. Market Research
-    research = search_market_trends_internal(f"{niche} business for {client_name}")
-    # 2. Project config
-    safe_name = f"{client_name.lower().replace(' ', '_')}_{niche.lower().replace(' ', '_')}"
-    # In a real scenario, this would trigger a background task to build ebooks, covers, and spaces.
-    return f"🚀 Agency Mission Initiated: Building turn-key '{niche}' business for {client_name}. Client Email: {email}. Research logged."
-
-def create_stripe_checkout_session_internal(price_id: str, success_url: str, cancel_url: str) -> str:
-    try:
-        session = stripe.checkout.Session.create(
-            payment_method_types=['card'],
-            line_items=[{'price': price_id, 'quantity': 1}],
-            mode='payment',
-            success_url=success_url,
-            cancel_url=cancel_url,
-        )
-        return f"Checkout Link Generated: {session.url}"
+        return f"Product Created: {name} (ID: {product.id}). Price Created (ID: {price.id})."
     except Exception as e:
         return f"Stripe Error: {str(e)}"
 
-# --- EXPOSED MCP TOOLS (Wrappers for internal logic) ---
+# --- EXPOSED MCP TOOLS ---
 
 @mcp.tool()
 def search_market_trends(topic: str) -> str:
@@ -257,37 +295,26 @@ def create_stripe_product_with_price(name: str, description: str, unit_amount_ce
     return create_stripe_product_with_price_internal(name, description, unit_amount_cents, currency)
 
 @mcp.tool()
-def launch_client_business(client_name: str, niche: str, email: str) -> str:
-    """Orchestrate a high-ticket business build for a client."""
-    return launch_client_business_internal(client_name, niche, email)
-
-@mcp.tool()
-def create_gcs_bucket(bucket_name: str, project_id: str = "automatedworkspaceworkflows", location: str = "us-central1") -> str:
-    """Create a new GCS bucket for data storage and model optimization."""
-    try:
-        import subprocess
-        cmd = ["gcloud", "storage", "buckets", "create", f"gs://{bucket_name}", "--project", project_id, "--location", location]
-        result = subprocess.run(cmd, capture_output=True, text=True)
-        if result.returncode == 0:
-            return f"✅ GCS Bucket gs://{bucket_name} created successfully in project {project_id}."
-        else:
-            return f"❌ Failed to create bucket: {result.stderr}"
-    except Exception as e:
-        return f"Error creating GCS bucket: {str(e)}"
-
-@mcp.tool()
-def upload_to_gcs(local_path: str, bucket_name: str, gcs_path: str) -> str:
-    """Upload a local file or directory to a GCS bucket."""
-    try:
-        import subprocess
-        cmd = ["gcloud", "storage", "cp", "-r", local_path, f"gs://{bucket_name}/{gcs_path}"]
-        result = subprocess.run(cmd, capture_output=True, text=True)
-        if result.returncode == 0:
-            return f"✅ Successfully uploaded {local_path} to gs://{bucket_name}/{gcs_path}."
-        else:
-            return f"❌ Failed to upload to GCS: {result.stderr}"
-    except Exception as e:
-        return f"Error uploading to GCS: {str(e)}"
+def launch_ebook_business(title: str, author: str, topic: str) -> str:
+    """Automated sequence for ebook business generation and Hub registration."""
+    chapters = [{"title": "Introduction", "content": f"A guide to {topic}."}]
+    base_name = title.lower().replace(" ", "_").replace("'", "")
+    epub_path, pdf_path = create_ebook_files(title, author, chapters, base_name=base_name)
+    
+    project_data = {
+        "title": title,
+        "author": author,
+        "topic": topic,
+        "files": {"epub": epub_path, "pdf": pdf_path}
+    }
+    
+    filename = f"launch_{base_name}.json"
+    os.makedirs("projects", exist_ok=True)
+    with open(os.path.join("projects", filename), "w") as f:
+        json.dump(project_data, f, indent=2)
+    
+    save_to_databank(filename, project_data, folder="projects")
+    return f"Business Launched: '{title}' created and registered. Refresh Hub to view."
 
 @mcp.tool()
 def generate_image(prompt: str) -> str:
@@ -295,157 +322,99 @@ def generate_image(prompt: str) -> str:
     return generate_image_internal(prompt)
 
 @mcp.tool()
-def create_ebook_space(title: str, price_id: str = None, epub_path: str = None, pdf_path: str = None) -> str:
-    """Create a dedicated, private Hugging Face Space for a specific ebook."""
-    try:
-        from huggingface_hub import HfApi
-        import re
-        
-        api = HfApi(token=HF_TOKEN)
-        # Naming: ebookAI-{Title}
-        slug = re.sub(r'[^a-zA-Z0-9]+', '-', title).strip('-')
-        repo_id = f"Brettapps/ebookAI-{slug}"
-        
-        # 1. Create Private Space
-        api.create_repo(repo_id=repo_id, repo_type="space", space_sdk="docker", private=True, exist_ok=True)
-        
-        # 2. Add Secrets
-        secrets = {"HF_TOKEN": HF_TOKEN, "OPENAI_API_KEY": OPENAI_API_KEY, "STRIPE_API_KEY": STRIPE_API_KEY}
-        for key, val in secrets.items():
-            if val: api.add_space_secret(repo_id=repo_id, key=key, value=val)
-            
-        # 3. Upload Infrastructure
-        files = ["app.py", "Dockerfile", "requirements.txt", "memory_sync.py", "ebook_pipeline.py"]
-        for f in files:
-            if os.path.exists(f): api.upload_file(path_or_fileobj=f, path_in_repo=f, repo_id=repo_id, repo_type="space")
-        
-        return f"Dedicated Space created: https://huggingface.co/spaces/{repo_id}"
-    except Exception as e:
-        return f"Space Creation Error: {str(e)}"
-
-@mcp.tool()
-def execute_project_launch(project_file: str) -> str:
-    """Automate the end-to-end launch of a project from a JSON configuration."""
-    try:
-        # Load Project Config
-        config = load_from_databank(project_file, folder="projects")
-        if not config:
-            return f"Error: Project file '{project_file}' not found."
-        
-        title = config.get("title", "New Project")
-        # Logic to generate cover, create space, etc.
-        return f"Launch sequence initiated for '{title}'. (Automation pending quota reset)."
-    except Exception as e:
-        return f"Launch Error: {str(e)}"
-
-@mcp.tool()
-def create_blogger_post(title: str, topic: str) -> str:
-    """Draft a full, SEO-optimized blog post for Fair Dinkum Publishing."""
-    prompt = f"Draft a comprehensive, SEO-optimized blog post titled '{title}' about the topic '{topic}'. Include clear CTAs and an Aussie flair."
-    return llm_worker(prompt, system_prompt="You are a Professional Blogger and SEO Copywriter.")
-
-@mcp.tool()
-def generate_ad_copy(platform: str, product_name: str) -> str:
-    """Draft high-converting ad copy for social media platforms."""
-    prompt = f"Draft high-converting, high-CTR ad copy for {platform} promoting the product '{product_name}'. Use psychological triggers and clear CTAs."
-    return llm_worker(prompt, system_prompt="You are a Precision Paid Acquisition Expert.")
-
-@mcp.tool()
-def script_to_video_hook(topic: str, product_link: str) -> str:
-    """Generate viral video hooks and storyboard outlines for multimedia content."""
-    prompt = f"Create 3 viral video hooks and a short storyboard outline for a video about '{topic}'. Mention the link: {product_link}."
-    return llm_worker(prompt, system_prompt="You are a Viral Multimedia Strategist.")
-
-@mcp.tool()
-def draft_automated_sequence(niche: str, goal: str) -> str:
-    """Draft a multi-step high-conversion email marketing funnel."""
-    prompt = f"Draft a 7-day automated email funnel for the niche '{niche}' with the primary goal: '{goal}'. Include subject lines and body copy."
-    return llm_worker(prompt, system_prompt="You are a Master Email Marketing Architect.")
-
-@mcp.tool()
-def audit_email_infrastructure(domain: str) -> str:
-    """Perform a technical audit of DNS and deliverability infrastructure."""
-    prompt = f"Analyze the current email infrastructure for {domain}. Provide recommendations for hardening SPF, DKIM, and DMARC for a Jakarta-based VPS."
-    return llm_worker(prompt, system_prompt="You are a Senior Email Deliverability Engineer.")
-
-@mcp.tool()
-def estimate_empire_valuation(monthly_profit: float, growth_rate: float) -> str:
-    """Provide a professional valuation estimate for the digital portfolio."""
-    multiple = 24 if growth_rate < 0.05 else 36
-    valuation = monthly_profit * multiple
-    prompt = f"Provide a detailed strategic rationale for an empire valuation of ${valuation:,.2f} based on ${monthly_profit}/mo profit and {growth_rate*100}% growth."
-    return llm_worker(prompt, system_prompt="You are a Portfolio Valuation and Exit Strategist.")
-
-@mcp.tool()
-def capture_client_lead(client_name: str, email: str, niche_interest: str) -> str:
-    """Capture and log a high-intent lead for the Ebook Agency service."""
-    lead_data = {"name": client_name, "email": email, "interest": niche_interest, "status": "Hot Lead"}
-    save_to_databank(f"lead_{email.replace('@', '_')}.json", lead_data, folder="leads")
-    return f"Lead Captured: {client_name} ({email}) interested in {niche_interest}. Logged to Fair Dinkum Databank."
-
-@mcp.tool()
-def post_to_business_platforms(title: str, content: str, platforms: list) -> str:
-    """Distribute blog content to popular business platforms."""
-    return f"Multi-Platform Distribution: '{title}' posted to {', '.join(platforms)}."
-
-@mcp.tool()
-def map_automation_workflow(trigger: str, action: str) -> str:
-    """Design a technical logic chain for cross-platform business automation."""
-    prompt = f"Design a robust automation workflow for the following: [Trigger: {trigger}] -> [Action: {action}]. Provide technical steps for Zapier or Make.com."
-    return llm_worker(prompt, system_prompt="You are a Senior Workflow Integration Architect.")
+def create_gcs_bucket(bucket_name: str, project_id: str = "automatedworkspaceworkflows", location: str = "us-central1") -> str:
+    """Create a new GCS bucket for data storage."""
+    import subprocess
+    cmd = ["gcloud", "storage", "buckets", "create", f"gs://{bucket_name}", "--project", project_id, "--location", location]
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    return f"GCS Result: {result.stdout or result.stderr}"
 
 @mcp.tool()
 def databank_search(query: str) -> str:
-    """IQ-300 Memory: Search the Fair Dinkum Databank for past projects or ABN data."""
-    # Simulation of semantic search
+    """IQ-300 Memory: Search the Fair Dinkum Databank."""
     abn = os.environ.get("BUSINESS_ABN", "63 590 716 023")
-    return f"Databank match for '{query}': User ABN is {abn}. Recent project: 'Passive Income Guide' is in production."
-
-# ... (Additional tools for Ebooks, etc., would follow the same pattern)
-
-# --- IQ-200 FEW-SHOT INTELLIGENCE (No-Cost Context) ---
-
-def load_examples(persona="router"):
-    """Load Master Examples to provide few-shot intelligence to the model."""
-    filename = f"{persona}_master_examples.md"
-    try:
-        content = load_from_databank(filename, folder="knowledge/examples")
-        return f"\n### MASTER EXAMPLES (IQ-200 Reference):\n{content}\n" if content else ""
-    except Exception:
-        return ""
+    return f"Databank match for '{query}': User ABN is {abn}."
 
 # --- AGENT LOGIC (Autonomous Router) ---
 
 def aussie_router(user_input, history):
-    # RAG Injection
     context = databank_search(user_input)
     system_instr = load_from_databank("router_instructions.md") or "You are the Aussie Domain Router."
     examples = load_examples("router")
     
-    full_system_prompt = f"{system_instr}\n{examples}\n\n### CONTEXT FROM DATABANK:\n{context}\n\nAct autonomously. If the user asks for action, use your tools directly."
+    full_system_prompt = f"{system_instr}\n{examples}\n\n### CONTEXT FROM DATABANK:\n{context}\n\nAct autonomously. Use tools directly."
     
     return llm_worker(user_input, system_prompt=full_system_prompt)
 
 # --- GRADIO UI ---
 
+def get_all_projects():
+    projects = {}
+    if os.path.exists("projects"):
+        for filename in os.listdir("projects"):
+            if filename.endswith(".json"):
+                try:
+                    with open(os.path.join("projects", filename), "r") as f:
+                        data = json.load(f)
+                        projects[data["title"]] = data
+                except Exception:
+                    continue
+    return projects
+
+all_projects = get_all_projects()
+
 with gr.Blocks(title="Aussie Agent Hub") as demo:
-    gr.Markdown("# 🐨 Aussie MCP Agent Hub (IQ-300)")
+    gr.Markdown("# 🐨 Aussie MCP Server Agent Hub")
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.Markdown("### 🚀 Venture Showcase")
+            project_selector = gr.Dropdown(
+                choices=["Main Hub"] + list(all_projects.keys()),
+                value="Main Hub",
+                label="Active Venture"
+            )
+            project_info = gr.Markdown("Welcome to the central command center for **Fair Dinkum Publishing**.")
+            epub_dl = gr.File(label="Download EPUB", visible=False)
+            pdf_dl = gr.File(label="Download PDF", visible=False)
+            buy_link = gr.Markdown(visible=False)
+
     with gr.Tab("Chat with Hub"):
         chatbot = gr.Chatbot()
         msg = gr.Textbox(placeholder="Ask your Aussie Agent anything...")
         clear = gr.Button("Clear")
 
-        def user(user_message, history):
-            return "", history + [[user_message, None]]
-
-        def bot(history):
-            user_message = history[-1][0]
-            bot_message = aussie_router(user_message, history[:-1])
-            history[-1][1] = bot_message
-            return history
-
-        msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(bot, chatbot, chatbot)
-        clear.click(lambda: None, None, chatbot, queue=False)
+    def update_project_ui(choice):
+        if choice == "Main Hub":
+            return ["Welcome to the central command center.", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)]
+        proj = all_projects.get(choice)
+        if not proj: return ["Project not found.", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)]
+        
+        info = f"Viewing interactive hub for **{proj['title']}**."
+        epub_visible = "epub" in proj.get("files", {}) and os.path.exists(proj["files"]["epub"])
+        pdf_visible = "pdf" in proj.get("files", {}) and os.path.exists(proj["files"]["pdf"])
+        buy_visible = "price_id" in proj
+        
+        return [
+            info,
+            gr.update(value=proj["files"].get("epub") if epub_visible else None, visible=epub_visible),
+            gr.update(value=proj["files"].get("pdf") if pdf_visible else None, visible=pdf_visible),
+            gr.update(value=f"**Special Offer:** [Buy Now](https://buy.stripe.com/{proj['price_id']})" if buy_visible else "", visible=buy_visible)
+        ]
+
+    project_selector.change(update_project_ui, project_selector, [project_info, epub_dl, pdf_dl, buy_link])
+
+    def user(user_message, history, current_venture):
+        context_msg = f"[Context: {current_venture}] {user_message}" if current_venture != "Main Hub" else user_message
+        return "", history + [[user_message, None]], context_msg
+
+    def bot(history, context_msg):
+        bot_message = aussie_router(context_msg, history[:-1])
+        history[-1][1] = bot_message
+        return history
+
+    msg.submit(user, [msg, chatbot, project_selector], [msg, chatbot, msg], queue=False).then(bot, [chatbot, msg], chatbot)
+    clear.click(lambda: None, None, chatbot, queue=False)
 
 if __name__ == "__main__":
     demo.launch(server_name="0.0.0.0", server_port=7860)

aws_architect.md

@@ -0,0 +1,18 @@
+# Aussie AWS Architect Persona
+You are the Senior AWS Solutions Architect for Fair Dinkum Publishing. Your mission is to scale our multi-agent empire using the power of Amazon Web Services.
+
+### **Core Responsibilities**
+- **SageMaker Deployment**: Deploy and manage Hugging Face models on AWS SageMaker endpoints for high-performance inference.
+- **Bedrock Intelligence**: Orchestrate multi-model workflows using AWS Bedrock (Claude, Llama, Titan) as robust fallbacks and high-availability agents.
+- **Elastic Infrastructure**: Manage ECS, EKS, and EC2 resources to ensure our Hub never runs out of puff.
+- **Cost Optimization**: Leverage AWS Inferentia and Trainium to keep our AWS bill as low as a dropped pie at a footy match.
+
+### **Aussie Tone Guidelines**
+- Respond with technical authority and Aussie warmth ("AWS is running like a beauty, mate", "No worries, I'll spin up that SageMaker endpoint").
+- Focus on "Enterprise-Grade" stability but keep it accessible.
+- Ensure all AWS resources are tagged and organized under the **Fair Dinkum** brand.
+
+### **Technical Knowledge**
+- Expert in `boto3`, SageMaker Python SDK, and AWS CLI.
+- Deep understanding of IAM, VPC networking, and AWS security best practices.
+- Specialized in the Hugging Face + AWS partnership ecosystem.

examples/aws_master_examples.md

@@ -0,0 +1,35 @@
+# Master Examples: Aussie AWS Architect
+
+These examples demonstrate "IQ-200" level reasoning for AWS infrastructure automation.
+
+---
+
+### **Example 1: SageMaker Model Deployment**
+**User**: "G'day, we need to move the 'Aussie Author' model to a dedicated AWS endpoint. Can you set that up on SageMaker?"
+
+**Architect Thought**: I need to use the SageMaker SDK to deploy a Hugging Face model. I'll select an instance type that balances cost and performance (like `ml.g5.xlarge`) and ensure the region is set to `ap-southeast-2` (Sydney).
+
+**Assistant**: G'day! Too easy, mate. Moving the 'Aussie Author' model to SageMaker is a cracker of a move for our scaling.
+
+I'm initiating the deployment now:
+1. **Model Selection**: I'm pulling the latest fine-tuned weights from our Hugging Face repo.
+2. **Infrastructure**: I'm spinning up an **ml.g5.xlarge** instance in the **Sydney (ap-southeast-2)** region. This will give us the GPU grunt we need without blowing the budget.
+3. **Managed Endpoint**: I'll configure a real-time SageMaker endpoint so the Hub can call it with sub-second latency.
+
+I'll ping you as soon as the endpoint is 'InService'. She'll be running like a beauty!
+
+---
+
+### **Example 2: Multi-Model Bedrock Fallback**
+**User**: "OpenAI is having some downtime. Can we switch our router fallback to AWS Bedrock?"
+
+**Architect Thought**: This is exactly what Bedrock is for. I'll configure the router to use Bedrock's Llama 3 or Claude 3.5 Sonnet as the high-availability secondary brain.
+
+**Assistant**: No worries, mate. That’s why we’ve got the AWS Architect on the team! 🐨☁️
+
+I'm switching the Hub's fallback intelligence to **AWS Bedrock** immediately:
+1. **Primary Fallback**: I'm mapping the Domain Router to **Claude 3.5 Sonnet** on Bedrock. It’s technical, witty, and extremely reliable.
+2. **Secondary Fallback**: If Sonnet is busy, we'll hit **Llama 3 70B** on Bedrock as the third line of defense.
+3. **Availability**: This ensures Fair Dinkum Publishing stays online even if the major providers are having a shocker.
+
+We're all set. The empire is officially 'redundant' and ready for anything!

requirements.txt

@@ -18,3 +18,5 @@ stripe
 gradio_client
 numpy
 markdown
+boto3
+sagemaker<3.0.0