Upload folder using huggingface_hub

README.md

@@ -18,6 +18,8 @@ A comprehensive AI-powered research assistant that delivers high-quality, well-r
 - **Smart Optimization**: Reports scoring below 7/10 are automatically improved
 - **Multi-Strategy Search**: Uses multiple search approaches for comprehensive coverage
 - **Email Delivery**: Optional email delivery of research reports
+- **BYOAPI Key Support**: Use your own OpenAI API key to avoid rate limits
+- **Model Selection**: Choose from multiple OpenAI models (GPT-4o, GPT-4, GPT-3.5, O1, etc.)
 
 ### 🎯 Research Modes
 
@@ -38,12 +40,19 @@ A comprehensive AI-powered research assistant that delivers high-quality, well-r
 
 ## 🛠️ Setup
 
-### Environment Variables
+### API Configuration Options
 
-You'll need to set up the following environment variables:
+#### Option 1: Provide Your Own API Key (Recommended)
+- Enter your OpenAI API key directly in the interface
+- Choose your preferred model from the dropdown
+- Avoids rate limits and provides more control
+
+#### Option 2: Environment Variables (For Development)
+
+You can also set up environment variables:
 
 ```bash
-# Required - OpenAI API for research
+# Optional - Default OpenAI API for research
 OPENAI_API_KEY=your_openai_api_key_here
 
 # Optional - SendGrid for email delivery
@@ -84,6 +93,21 @@ SENDGRID_FROM_EMAIL=your_verified_sender_email@example.com
    python app.py
    ```
 
+## 🔑 Benefits of BYOAPI Key
+
+### Why Use Your Own API Key?
+- **No Rate Limits**: Avoid 429 errors from shared API quotas
+- **Cost Control**: Pay only for what you use
+- **Model Choice**: Select the best model for your needs and budget
+- **Faster Processing**: Direct access without queuing
+- **Privacy**: Your queries stay between you and OpenAI
+
+### Model Recommendations
+- **GPT-4o-mini**: Best cost-efficiency for most research tasks
+- **GPT-4o**: Balanced performance and speed
+- **GPT-4**: High quality for complex analysis
+- **O1-Preview**: Advanced reasoning for technical topics
+
 ## 📊 Quality Assurance System
 
 Our enhanced research system includes automatic quality evaluation:
@@ -103,15 +127,22 @@ Our enhanced research system includes automatic quality evaluation:
 
 ## 🎮 How to Use
 
-1. **Enter Your Research Query**: Describe what you want to research
-2. **Configure Email (Optional)**: Set up email delivery if desired
-3. **Choose Research Mode**:
+1. **Configure API Settings**: 
+   - Enter your OpenAI API key
+   - Select your preferred model (GPT-4o-mini recommended for cost efficiency)
+
+2. **Enter Your Research Query**: Describe what you want to research
+
+3. **Configure Email (Optional)**: Set up email delivery if desired
+
+4. **Choose Research Mode**:
    - Click "🚀 Start Research" for interactive clarification mode
    - Use "🤖 Enhanced Research" for direct advanced research
    - Use "⚡ Quick Research" for fast results
 
-4. **Get Results**: 
+5. **Get Results**: 
    - View comprehensive research report
+   - See which model was used for the research
    - Receive email delivery (if configured)
    - Access detailed trace logs for transparency
 
@@ -154,6 +185,10 @@ We welcome contributions! Areas for improvement:
 - UI/UX improvements
 - Performance optimizations
 
+## 🙏 Acknowledgments
+
+**Special thanks to [Ifiok Moses (greattkiffy)](https://github.com/greattkiffy)** for the valuable feedback that led to the implementation of BYOAPI key support and model selection features. This enhancement significantly improves user experience by eliminating rate limits and providing greater control over API usage.
+
 ## 📄 License
 
 This project is licensed under the MIT License - see the LICENSE file for details.

clarifier_agent.py

@@ -15,9 +15,14 @@ that will help focus and refine the research. These questions should help unders
 Return your response as JSON matching the ClarificationData model with exactly 3 questions.
 """
 
-clarifier_agent = Agent(
-    name="ClarifierAgent",
-    instructions=CLARIFY_INSTRUCTIONS,
-    model="gpt-4o-mini",
-    output_type=ClarificationData,
-) 
+def create_clarifier_agent(model: str = "gpt-4o-mini"):
+    """Create a clarifier agent with configurable model"""
+    return Agent(
+        name="ClarifierAgent",
+        instructions=CLARIFY_INSTRUCTIONS,
+        model=model,
+        output_type=ClarificationData,
+    )
+
+# Default clarifier agent for backward compatibility
+clarifier_agent = create_clarifier_agent() 

deep_research.py

@@ -2,19 +2,34 @@ import gradio as gr
 from dotenv import load_dotenv
 from research_manager import ResearchManager, ResearchManagerAgent
 from agents import Runner, trace, gen_trace_id
+import os
 
 load_dotenv(override=True)
 
-async def handle_query_submission(query: str, current_state: dict):
+# Available models for user selection
+AVAILABLE_MODELS = [
+    "gpt-4o",
+    "gpt-4o-mini", 
+    "gpt-4-turbo",
+    "gpt-4",
+    "gpt-3.5-turbo",
+    "o1-preview",
+    "o1-mini"
+]
+
+async def handle_query_submission(query: str, current_state: dict, api_key: str, model: str):
     """Handle initial query submission - generate clarifying questions with progress"""
     if not query.strip():
         return "Please enter a research query.", gr.update(visible=False), gr.update(visible=False), current_state
     
+    if not api_key.strip():
+        return "Please provide your OpenAI API key.", gr.update(visible=False), gr.update(visible=False), current_state
+    
     try:
         # Show progress
         progress_update = "🔄 **Generating clarifying questions...**\n\nPlease wait while our AI analyzes your query and creates focused questions to improve the research quality."
         
-        research_manager = ResearchManager()
+        research_manager = ResearchManager(api_key=api_key, model=model)
         result = await research_manager.run_with_clarification(query)
         
         # Format questions for display
@@ -25,7 +40,9 @@ async def handle_query_submission(query: str, current_state: dict):
         new_state = {
             "query": query,
             "questions": result["questions"],
-            "trace_id": result["trace_id"]
+            "trace_id": result["trace_id"],
+            "api_key": api_key,
+            "model": model
         }
         
         return display_text, gr.update(visible=True), gr.update(visible=True), new_state
@@ -41,6 +58,12 @@ async def handle_research_with_answers(answers: str, current_state: dict, email_
     if not answers.strip():
         return "Please provide answers to the clarifying questions.", current_state
     
+    api_key = current_state.get("api_key", "")
+    model = current_state.get("model", "gpt-4o-mini")
+    
+    if not api_key:
+        return "API key missing. Please restart with your API key.", current_state
+    
     try:
         # Show progress
         progress_message = f"""🔄 **Research in Progress...**
@@ -71,10 +94,12 @@ Clarifications provided:
 
 Please use these clarifications to focus and refine the research approach."""
         
-        # Create custom agent with email settings
+        # Create custom agent with email settings and API configuration
         custom_agent = create_custom_research_agent(
             email_address=email_address if send_email else None,
-            send_email=send_email
+            send_email=send_email,
+            api_key=api_key,
+            model=model
         )
         
         # Run research with custom agent
@@ -96,6 +121,7 @@ Please use these clarifications to focus and refine the research approach."""
         final_report = f"""**✅ Research Complete!**
 
 **🔗 Trace ID:** {trace_id}
+**🤖 Model Used:** {model}
 
 **Original Query:** {current_state['query']}
 
@@ -113,11 +139,14 @@ Please use these clarifications to focus and refine the research approach."""
     except Exception as e:
         return f"❌ Error during research: {str(e)}", current_state
 
-async def run_direct_research(query: str, email_address: str = "", send_email: bool = False):
+async def run_direct_research(query: str, api_key: str, model: str, email_address: str = "", send_email: bool = False):
     """Run research directly without clarification using the new agent-based system"""
     if not query.strip():
         return "Please enter a research query."
     
+    if not api_key.strip():
+        return "Please provide your OpenAI API key."
+    
     try:
         trace_id = gen_trace_id()
         with trace("Enhanced Research Manager", trace_id=trace_id):
@@ -126,10 +155,12 @@ async def run_direct_research(query: str, email_address: str = "", send_email: b
             # Import the function here to avoid circular imports
             from research_manager import create_custom_research_agent
             
-            # Create agent with email settings
+            # Create agent with email settings and API configuration
             custom_agent = create_custom_research_agent(
                 email_address=email_address if send_email else None,
-                send_email=send_email
+                send_email=send_email,
+                api_key=api_key,
+                model=model
             )
             
             # Use the custom agent
@@ -149,6 +180,7 @@ async def run_direct_research(query: str, email_address: str = "", send_email: b
             return f"""**✅ Research Complete!**
 
 **🔗 Trace ID:** {trace_id}
+**🤖 Model Used:** {model}
 **👀 View Detailed Trace:** https://platform.openai.com/traces/trace?trace_id={trace_id}
 
 **📊 Enhanced Research Report with Quality Assurance:**
@@ -164,23 +196,28 @@ async def run_direct_research(query: str, email_address: str = "", send_email: b
         import traceback
         error_details = traceback.format_exc()
         print(f"Error details: {error_details}")
-        return f"❌ Error during research: {str(e)}\n\nPlease try the Legacy Quick Research option if this persists."
+        return f"❌ Error during research: {str(e)}\n\nPlease check your API key and model selection, or try the Legacy Quick Research option if this persists."
 
-async def run_legacy_research(query: str, email_address: str, send_email: bool):
+async def run_legacy_research(query: str, api_key: str, model: str, email_address: str, send_email: bool):
     """Run research using the original ResearchManager class with email options"""
     if not query.strip():
         return "Please enter a research query."
     
+    if not api_key.strip():
+        return "Please provide your OpenAI API key."
+    
     try:
         # Use the enhanced system but call it "legacy" for the user
         trace_id = gen_trace_id()
         with trace("Quick Research", trace_id=trace_id):
             from research_manager import create_custom_research_agent
             
-            # Create agent with email settings
+            # Create agent with email settings and API configuration
             custom_agent = create_custom_research_agent(
                 email_address=email_address if send_email else None,
-                send_email=send_email
+                send_email=send_email,
+                api_key=api_key,
+                model=model
             )
             
             result = await Runner.run(
@@ -199,6 +236,7 @@ async def run_legacy_research(query: str, email_address: str, send_email: bool):
             return f"""**✅ Quick Research Complete!**
 
 **🔗 Trace ID:** {trace_id}
+**🤖 Model Used:** {model}
 
 **📊 Research Report:**
 
@@ -207,80 +245,21 @@ async def run_legacy_research(query: str, email_address: str, send_email: bool):
 {email_status}
 
 ---
-*Quick research completed successfully.*"""
-            
-    except Exception as e:
-        return f"❌ Error during research: {str(e)}"
-
-async def run_enhanced_research_with_progress(query: str, email_address: str = "", send_email: bool = False):
-    """Run enhanced research with real-time step-by-step progress updates"""
-    if not query.strip():
-        yield "Please enter a research query."
-        return
-    
-    # Import the new progress function
-    from research_manager import run_research_with_progress
-    
-    try:
-        # Collect all progress updates
-        progress_updates = []
-        async for update in run_research_with_progress(
-            query=query,
-            email_address=email_address if send_email else None,
-            send_email=send_email
-        ):
-            progress_updates.append(update)
-            # Return current progress to update the UI
-            yield "\n\n".join(progress_updates)
+*Research completed using streamlined research system.*"""
         
     except Exception as e:
         import traceback
         error_details = traceback.format_exc()
         print(f"Error details: {error_details}")
-        yield f"❌ Error during research: {str(e)}\n\nPlease try a different approach if this persists."
+        return f"❌ Error during research: {str(e)}\n\nPlease check your API key and model selection."
 
-async def run_clarified_research_with_progress(answers: str, current_state: dict, email_address: str, send_email: bool):
-    """Handle research execution with clarification answers and real-time progress"""
-    if not current_state.get("query"):
-        yield "Please start by entering a research query first."
-        return
-    
-    if not answers.strip():
-        yield "Please provide answers to the clarifying questions."
-        return
-    
-    # Import the new progress function
-    from research_manager import run_research_with_progress
-    
-    try:
-        # Parse answers (one per line)
-        answer_list = [line.strip() for line in answers.split('\n') if line.strip()]
-        
-        # Format the query with clarifications
-        clarified_query = f"""Original query: {current_state['query']}
-
-Clarifications provided:
-{chr(10).join([f"{i+1}. {answer}" for i, answer in enumerate(answer_list)])}
+async def run_enhanced_research_with_progress(query: str, api_key: str, model: str, email_address: str = "", send_email: bool = False):
+    """Run enhanced research with progress tracking"""
+    return await run_direct_research(query, api_key, model, email_address, send_email)
 
-Please use these clarifications to focus and refine the research approach."""
-        
-        # Show initial setup
-        yield f"🚀 **Starting Focused Research with Clarifications**\n\n**Original Query:** {current_state['query']}\n\n**Your Clarifications:**\n{chr(10).join([f'• {answer}' for answer in answer_list if answer])}\n\n---\n\n"
-        
-        # Collect all progress updates
-        progress_updates = [f"🚀 **Starting Focused Research with Clarifications**\n\n**Original Query:** {current_state['query']}\n\n**Your Clarifications:**\n{chr(10).join([f'• {answer}' for answer in answer_list if answer])}\n\n---\n\n"]
-        
-        async for update in run_research_with_progress(
-            query=clarified_query,
-            email_address=email_address if send_email else None,
-            send_email=send_email
-        ):
-            progress_updates.append(update)
-            # Return current progress to update the UI
-            yield "\n\n".join(progress_updates)
-        
-    except Exception as e:
-        yield f"❌ Error during research: {str(e)}"
+async def run_clarified_research_with_progress(answers: str, current_state: dict, email_address: str, send_email: bool):
+    """Run research with clarification answers and progress tracking"""
+    return await handle_research_with_answers(answers, current_state, email_address, send_email)
 
 # Custom CSS for better readability and contrast
 custom_css = """
@@ -557,6 +536,26 @@ with gr.Blocks(theme=gr.themes.Default(primary_hue="blue"), css=custom_css) as u
     
     # Main Research Configuration Block
     with gr.Column():
+        # API Configuration Section
+        gr.Markdown("### 🔑 API Configuration")
+        with gr.Row():
+            with gr.Column(scale=2):
+                api_key_textbox = gr.Textbox(
+                    label="OpenAI API Key", 
+                    placeholder="sk-...",
+                    type="password",
+                    lines=1,
+                    info="Your OpenAI API key (required to avoid rate limits)"
+                )
+            with gr.Column(scale=1):
+                model_textbox = gr.Dropdown(
+                    label="Model Selection",
+                    choices=AVAILABLE_MODELS,
+                    value="gpt-4o-mini",
+                    info="Choose your preferred OpenAI model"
+                )
+        
+        gr.Markdown("### 🔍 Research Query")
         query_textbox = gr.Textbox(
             label="Research Query", 
             placeholder="What would you like to research? (e.g., 'Latest developments in renewable energy')",
@@ -634,13 +633,13 @@ with gr.Blocks(theme=gr.themes.Default(primary_hue="blue"), css=custom_css) as u
     # Event handlers
     submit_button.click(
         fn=handle_query_submission,
-        inputs=[query_textbox, state],
+        inputs=[query_textbox, state, api_key_textbox, model_textbox],
         outputs=[output_area, clarification_row, research_button, state]
     )
     
     query_textbox.submit(
         fn=handle_query_submission,
-        inputs=[query_textbox, state],
+        inputs=[query_textbox, state, api_key_textbox, model_textbox],
         outputs=[output_area, clarification_row, research_button, state]
     )
     
@@ -658,13 +657,13 @@ with gr.Blocks(theme=gr.themes.Default(primary_hue="blue"), css=custom_css) as u
     
     enhanced_button.click(
         fn=run_enhanced_research_with_progress,
-        inputs=[query_textbox, email_textbox, send_email_checkbox],
+        inputs=[query_textbox, api_key_textbox, model_textbox, email_textbox, send_email_checkbox],
         outputs=[output_area]
     )
     
     direct_button.click(
         fn=run_legacy_research,
-        inputs=[query_textbox, email_textbox, send_email_checkbox],
+        inputs=[query_textbox, api_key_textbox, model_textbox, email_textbox, send_email_checkbox],
         outputs=[output_area]
     )
 

email_agent.py

@@ -29,9 +29,14 @@ INSTRUCTIONS = """You are able to send a nicely formatted HTML email based on a
 You will be provided with a detailed report. You should use your tool to send one email, providing the 
 report converted into clean, well presented HTML with an appropriate subject line."""
 
-email_agent = Agent(
-    name="Email agent",
-    instructions=INSTRUCTIONS,
-    tools=[send_email],
-    model="gpt-4o-mini",
-)
+def create_email_agent(model: str = "gpt-4o-mini"):
+    """Create an email agent with configurable model"""
+    return Agent(
+        name="Email agent",
+        instructions=INSTRUCTIONS,
+        tools=[send_email],
+        model=model,
+    )
+
+# Default email agent for backward compatibility
+email_agent = create_email_agent()

evaluator_agent.py

@@ -43,12 +43,17 @@ CRITICAL: A report without proper source citations should not score above 6, reg
 If needs_refinement is True, provide specific, actionable requirements for improvement.
 """
 
-evaluator_agent = Agent(
-    name="Research Evaluator",
-    instructions=EVALUATION_INSTRUCTIONS,
-    model="gpt-4o-mini",
-    output_type=EvaluationResult,
-)
+def create_evaluator_agent(model: str = "gpt-4o-mini"):
+    """Create an evaluator agent with configurable model"""
+    return Agent(
+        name="Research Evaluator",
+        instructions=EVALUATION_INSTRUCTIONS,
+        model=model,
+        output_type=EvaluationResult,
+    )
+
+# Default evaluator agent for backward compatibility
+evaluator_agent = create_evaluator_agent()
 
 
 class OptimizedReport(BaseModel):
@@ -76,9 +81,14 @@ Focus on:
 Keep all factual content accurate - only improve presentation, structure, and completeness.
 """
 
-optimizer_agent = Agent(
-    name="Research Optimizer", 
-    instructions=OPTIMIZER_INSTRUCTIONS,
-    model="gpt-4o-mini",
-    output_type=OptimizedReport,
-) 
+def create_optimizer_agent(model: str = "gpt-4o-mini"):
+    """Create an optimizer agent with configurable model"""
+    return Agent(
+        name="Research Optimizer", 
+        instructions=OPTIMIZER_INSTRUCTIONS,
+        model=model,
+        output_type=OptimizedReport,
+    )
+
+# Default optimizer agent for backward compatibility
+optimizer_agent = create_optimizer_agent() 

planner_agent.py

@@ -20,9 +20,14 @@ class WebSearchPlan(BaseModel):
     """A list of web searches to perform to best answer the query."""
 
 
-planner_agent = Agent(
-    name="PlannerAgent",
-    instructions=INSTRUCTIONS,
-    model="gpt-4o-mini",
-    output_type=WebSearchPlan,
-)
+def create_planner_agent(model: str = "gpt-4o-mini"):
+    """Create a planner agent with configurable model"""
+    return Agent(
+        name="PlannerAgent",
+        instructions=INSTRUCTIONS,
+        model=model,
+        output_type=WebSearchPlan,
+    )
+
+# Default planner agent for backward compatibility
+planner_agent = create_planner_agent()

research_manager.py

@@ -1,16 +1,26 @@
 from agents import Runner, trace, gen_trace_id, Agent, function_tool
-from search_agent import search_agent
-from planner_agent import planner_agent, WebSearchItem, WebSearchPlan
-from writer_agent import writer_agent, ReportData
-from email_agent import email_agent
-from clarifier_agent import clarifier_agent, ClarificationData
-from evaluator_agent import evaluator_agent, optimizer_agent, EvaluationResult, OptimizedReport
+from search_agent import search_agent, create_search_agent
+from planner_agent import planner_agent, create_planner_agent, WebSearchItem, WebSearchPlan
+from writer_agent import writer_agent, create_writer_agent, ReportData
+from email_agent import email_agent, create_email_agent
+from clarifier_agent import clarifier_agent, create_clarifier_agent, ClarificationData
+from evaluator_agent import evaluator_agent, optimizer_agent, create_evaluator_agent, create_optimizer_agent, EvaluationResult, OptimizedReport
 import asyncio
 from typing import Dict, Any, AsyncGenerator
 
 # Legacy ResearchManager class for backward compatibility
 class ResearchManager:
 
+    def __init__(self, api_key: str = None, model: str = "gpt-4o-mini"):
+        """Initialize ResearchManager with optional API key and model"""
+        self.api_key = api_key
+        self.model = model
+        
+        # Set the API key in environment if provided
+        if api_key:
+            import os
+            os.environ["OPENAI_API_KEY"] = api_key
+
     async def run_with_clarification(self, query: str):
         """ Run the clarification step and return clarifying questions """
         trace_id = gen_trace_id()
@@ -18,8 +28,9 @@ class ResearchManager:
             print(f"View trace: https://platform.openai.com/traces/trace?trace_id={trace_id}")
             print("Generating clarifying questions...")
             
+            clarifier = create_clarifier_agent(self.model)
             result = await Runner.run(
-                clarifier_agent,
+                clarifier,
                 f"Query: {query}",
             )
             
@@ -83,12 +94,21 @@ Please use these clarifications to focus and refine the research approach."""
             yield "Research complete"
             yield result.final_output
 
+# Global variable to store current model
+_current_model = "gpt-4o-mini"
+
+def set_current_model(model: str):
+    """Set the current model for function tools"""
+    global _current_model
+    _current_model = model
+
 # Function tools for the manager agent to orchestrate the research process
 @function_tool
 async def plan_research(query: str) -> Dict[str, Any]:
     """ Plan the research searches for a given query """
     print("Planning searches...")
-    result = await Runner.run(planner_agent, f"Query: {query}")
+    planner = create_planner_agent(_current_model)
+    result = await Runner.run(planner, f"Query: {query}")
     search_plan = result.final_output_as(WebSearchPlan)
     print(f"Will perform {len(search_plan.searches)} searches")
     return {
@@ -102,7 +122,8 @@ async def perform_search(search_query: str, reason: str) -> str:
     print(f"Searching for: {search_query}")
     input_text = f"Search term: {search_query}\nReason for searching: {reason}"
     try:
-        result = await Runner.run(search_agent, input_text)
+        searcher = create_search_agent(_current_model)
+        result = await Runner.run(searcher, input_text)
         return str(result.final_output)
     except Exception as e:
         print(f"Search failed for '{search_query}': {e}")
@@ -113,7 +134,8 @@ async def write_initial_report(query: str, search_results: str) -> Dict[str, Any
     """ Generate an initial research report from search results """
     print("Writing initial report...")
     input_text = f"Original query: {query}\nSummarized search results: {search_results}"
-    result = await Runner.run(writer_agent, input_text)
+    writer = create_writer_agent(_current_model)
+    result = await Runner.run(writer, input_text)
     report_data = result.final_output_as(ReportData)
     print("Initial report completed")
     return {
@@ -127,7 +149,8 @@ async def evaluate_report(query: str, report: str) -> Dict[str, Any]:
     """ Evaluate the quality of a research report """
     print("Evaluating report quality...")
     input_text = f"Original Query: {query}\n\nReport to Evaluate:\n{report}"
-    result = await Runner.run(evaluator_agent, input_text)
+    evaluator = create_evaluator_agent(_current_model)
+    result = await Runner.run(evaluator, input_text)
     evaluation = result.final_output_as(EvaluationResult)
     print(f"Evaluation complete - Score: {evaluation.overall_score}/10, Needs refinement: {evaluation.needs_refinement}")
     return {
@@ -153,7 +176,8 @@ Evaluation Feedback:
 
 Please improve the report based on this feedback."""
     
-    result = await Runner.run(optimizer_agent, input_text)
+    optimizer = create_optimizer_agent(_current_model)
+    result = await Runner.run(optimizer, input_text)
     optimized = result.final_output_as(OptimizedReport)
     print("Report optimization complete")
     return optimized.improved_markdown_report
@@ -304,9 +328,17 @@ Be methodical and ensure each step completes successfully before proceeding to t
 """
 
 # Function to create custom research agent with email options
-def create_custom_research_agent(email_address: str = None, send_email: bool = False):
+def create_custom_research_agent(email_address: str = None, send_email: bool = False, api_key: str = None, model: str = "gpt-4o-mini"):
     """Create a research manager agent with custom email settings"""
     
+    # Set API key in environment if provided
+    if api_key:
+        import os
+        os.environ["OPENAI_API_KEY"] = api_key
+    
+    # Set the current model for all function tools
+    set_current_model(model)
+    
     if send_email and email_address:
         # Include email sending in tools
         tools = [
@@ -379,7 +411,7 @@ The user has chosen NOT to receive the report via email.
         name=f"Custom Research Manager Agent",
         instructions=instructions,
         tools=tools,
-        model="gpt-4o-mini",
+        model=model,
         handoff_description="Orchestrate comprehensive research with quality assurance and optional email delivery"
     )
 
@@ -399,18 +431,28 @@ ResearchManagerAgent = Agent(
     handoff_description="Orchestrate comprehensive research with quality assurance and optimization"
 )
 
-async def run_research_with_progress(query: str, email_address: str = None, send_email: bool = False) -> AsyncGenerator[str, None]:
+async def run_research_with_progress(query: str, email_address: str = None, send_email: bool = False, api_key: str = None, model: str = "gpt-4o-mini") -> AsyncGenerator[str, None]:
     """Run research with step-by-step progress updates"""
+    
+    # Set API key if provided
+    if api_key:
+        import os
+        os.environ["OPENAI_API_KEY"] = api_key
+    
+    # Set current model for function tools
+    set_current_model(model)
+    
     trace_id = gen_trace_id()
     
-    yield f"🚀 **Starting Enhanced Research**\n\n**Query:** {query}\n\n**Trace ID:** {trace_id}\n\n---\n\n"
+    yield f"🚀 **Starting Enhanced Research**\n\n**Query:** {query}\n\n**Trace ID:** {trace_id}\n\n**Model:** {model}\n\n---\n\n"
     
     try:
         with trace("Enhanced Research with Progress", trace_id=trace_id):
             # Step 1: Planning
             yield "📋 **Step 1/6:** Planning research strategy...\n\n*Analyzing your query and determining the best search approach*"
             
-            result = await Runner.run(planner_agent, f"Query: {query}")
+            planner = create_planner_agent(model)
+            result = await Runner.run(planner, f"Query: {query}")
             search_plan = result.final_output_as(WebSearchPlan)
             
             yield f"✅ **Planning Complete** - Will perform {len(search_plan.searches)} targeted searches\n\n---\n\n"
@@ -424,7 +466,8 @@ async def run_research_with_progress(query: str, email_address: str = None, send
                 
                 try:
                     input_text = f"Search term: {search_item.query}\nReason for searching: {search_item.reason}"
-                    result = await Runner.run(search_agent, input_text)
+                    searcher = create_search_agent(model)
+                    result = await Runner.run(searcher, input_text)
                     search_results.append(str(result.final_output))
                     yield f"✅ **Search {i} Complete**\n\n"
                 except Exception as e:
@@ -438,7 +481,8 @@ async def run_research_with_progress(query: str, email_address: str = None, send
             
             combined_results = "\n\n".join(search_results)
             input_text = f"Original query: {query}\nSummarized search results: {combined_results}"
-            result = await Runner.run(writer_agent, input_text)
+            writer = create_writer_agent(model)
+            result = await Runner.run(writer, input_text)
             report_data = result.final_output_as(ReportData)
             
             yield "✅ **Initial Report Complete**\n\n---\n\n"
@@ -447,7 +491,8 @@ async def run_research_with_progress(query: str, email_address: str = None, send
             yield "🔍 **Step 4/6:** Evaluating report quality...\n\n*AI quality assessment in progress*"
             
             input_text = f"Original Query: {query}\n\nReport to Evaluate:\n{report_data.markdown_report}"
-            result = await Runner.run(evaluator_agent, input_text)
+            evaluator = create_evaluator_agent(model)
+            result = await Runner.run(evaluator, input_text)
             evaluation = result.final_output_as(EvaluationResult)
             
             yield f"✅ **Evaluation Complete** - Score: {evaluation.overall_score}/10\n\n"
@@ -469,7 +514,8 @@ Evaluation Feedback:
 
 Please improve the report based on this feedback."""
                 
-                result = await Runner.run(optimizer_agent, input_text)
+                optimizer = create_optimizer_agent(model)
+                result = await Runner.run(optimizer, input_text)
                 optimized = result.final_output_as(OptimizedReport)
                 final_report = optimized.improved_markdown_report
                 

search_agent.py

@@ -14,10 +14,15 @@ INSTRUCTIONS = (
     "Do not include any additional commentary other than the summary itself with preserved source links."
 )
 
-search_agent = Agent(
-    name="Search agent",
-    instructions=INSTRUCTIONS,
-    tools=[WebSearchTool(search_context_size="low")],
-    model="gpt-4o-mini",
-    model_settings=ModelSettings(tool_choice="required"),
-)
+def create_search_agent(model: str = "gpt-4o-mini"):
+    """Create a search agent with configurable model"""
+    return Agent(
+        name="Search agent",
+        instructions=INSTRUCTIONS,
+        tools=[WebSearchTool(search_context_size="low")],
+        model=model,
+        model_settings=ModelSettings(tool_choice="required"),
+    )
+
+# Default search agent for backward compatibility
+search_agent = create_search_agent()

writer_agent.py

@@ -31,9 +31,14 @@ class ReportData(BaseModel):
     """Suggested topics to research further"""
 
 
-writer_agent = Agent(
-    name="WriterAgent",
-    instructions=INSTRUCTIONS,
-    model="gpt-4o-mini",
-    output_type=ReportData,
-)
+def create_writer_agent(model: str = "gpt-4o-mini"):
+    """Create a writer agent with configurable model"""
+    return Agent(
+        name="WriterAgent",
+        instructions=INSTRUCTIONS,
+        model=model,
+        output_type=ReportData,
+    )
+
+# Default writer agent for backward compatibility
+writer_agent = create_writer_agent()