deepcode-hku 1.0.5__tar.gz → 1.0.6__tar.gz

{deepcode_hku-1.0.5/deepcode_hku.egg-info → deepcode_hku-1.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepcode-hku
-Version: 1.0.5
+Version: 1.0.6
 Summary: AI Research Engine - Transform research papers into working code automatically
 Home-page: https://github.com/HKUDS/DeepCode
 Author: DeepCodeTeam
@@ -27,6 +27,7 @@ Requires-Dist: docling
 Requires-Dist: mcp-agent
 Requires-Dist: mcp-server-git
 Requires-Dist: nest_asyncio
+Requires-Dist: openai
 Requires-Dist: pathlib2
 Requires-Dist: PyPDF2>=2.0.0
 Requires-Dist: reportlab>=3.5.0
@@ -96,6 +97,15 @@ Dynamic: summary
   </a>
 </div>
 
+<div align="center" style="margin-top: 10px;">
+  <a href="README.md">
+    <img src="https://img.shields.io/badge/English-00d4ff?style=for-the-badge&logo=readme&logoColor=white&labelColor=1a1a2e" alt="English">
+  </a>
+  <a href="README_ZH.md">
+    <img src="https://img.shields.io/badge/中文-00d4ff?style=for-the-badge&logo=readme&logoColor=white&labelColor=1a1a2e" alt="中文">
+  </a>
+</div>
+
 ### 🖥️ **Interface Showcase**
 
 <table align="center" width="100%" style="border: none; border-collapse: collapse; margin: 30px 0;">
@@ -177,14 +187,30 @@ Dynamic: summary
 
 ## 📑 Table of Contents
 
+- [📰 News](#-news)
 - [🚀 Key Features](#-key-features)
 - [🏗️ Architecture](#️-architecture)
+- [📊 Experimental Results](#-experimental-results)
 - [🚀 Quick Start](#-quick-start)
 - [💡 Examples](#-examples)
   - [🎬 Live Demonstrations](#-live-demonstrations)
 - [⭐ Star History](#-star-history)
 - [📄 License](#-license)
 
+
+---
+
+## 📰 News
+
+🎉 **[2025-10] 🎉 [2025-10-28] DeepCode Achieves SOTA on PaperBench!**
+
+DeepCode sets new benchmarks on OpenAI's PaperBench Code-Dev across all categories:
+
+- 🏆 **Surpasses Human Experts**: **75.9%** (DeepCode) vs Top Machine Learning PhDs 72.4% (+3.5%).
+- 🥇 **Outperforms SOTA Commercial Code Agents**: **84.8%** (DeepCode) vs Leading Commercial Code Agents (+26.1%) (Cursor, Claude Code, and Codex).
+- 🔬 **Advances Scientific Coding**: **73.5%** (DeepCode) vs PaperCoder 51.1% (+22.4%).
+- 🚀 **Beats LLM Agents**: **73.5%** (DeepCode) vs best LLM frameworks 43.3% (+30.2%).
+
 ---
 
 ## 🚀 Key Features
@@ -261,7 +287,58 @@ Dynamic: summary
 
 <br/>
 
-### 🎯 **Autonomous Multi-Agent Workflow**
+---
+
+## 📊 Experimental Results
+
+<div align="center">
+    <img src='./assets/result_main02.jpg' /><br>
+</div>
+<br/>
+
+We evaluate **DeepCode** on the [*PaperBench*](https://openai.com/index/paperbench/) benchmark (released by OpenAI), a rigorous testbed requiring AI agents to independently reproduce 20 ICML 2024 papers from scratch. The benchmark comprises 8,316 gradable components assessed using SimpleJudge with hierarchical weighting.
+
+Our experiments compare DeepCode against four baseline categories: **(1) Human Experts**, **(2) State-of-the-Art Commercial Code Agents**, **(3) Scientific Code Agents**, and **(4) LLM-Based Agents**.
+
+### ① 🧠 Human Expert Performance (Top Machine Learning PhD)
+
+**DeepCode: 75.9% vs. Top Machine Learning PhD: 72.4% (+3.5%)**
+
+DeepCode achieves **75.9%** on the 3-paper human evaluation subset, **surpassing the best-of-3 human expert baseline (72.4%) by +3.5 percentage points**. This demonstrates that our framework not only matches but exceeds expert-level code reproduction capabilities, representing a significant milestone in autonomous scientific software engineering.
+
+### ② 💼 State-of-the-Art Commercial Code Agents
+
+**DeepCode: 84.8% vs. Best Commercial Agent: 58.7% (+26.1%)**
+
+On the 5-paper subset, DeepCode substantially outperforms leading commercial coding tools:
+- Cursor: 58.4%
+- Claude Code: 58.7%
+- Codex: 40.0%
+- **DeepCode: 84.8%**
+
+This represents a **+26.1% improvement** over the leading commercial code agent. All commercial agents utilize Claude Sonnet 4.5 or GPT-5 Codex-high, highlighting that **DeepCode's superior architecture**—rather than base model capability—drives this performance gap.
+
+### ③ 🔬 Scientific Code Agents
+
+**DeepCode: 73.5% vs. PaperCoder: 51.1% (+22.4%)**
+
+Compared to PaperCoder (**51.1%**), the state-of-the-art scientific code reproduction framework, DeepCode achieves **73.5%**, demonstrating a **+22.4% relative improvement**. This substantial margin validates our multi-module architecture combining planning, hierarchical task decomposition, code generation, and iterative debugging over simpler pipeline-based approaches.
+
+### ④ 🤖 LLM-Based Agents
+
+**DeepCode: 73.5% vs. Best LLM Agent: 43.3% (+30.2%)**
+
+DeepCode significantly outperforms all tested LLM agents:
+- Claude 3.5 Sonnet + IterativeAgent: 27.5%
+- o1 + IterativeAgent (36 hours): 42.4%
+- o1 BasicAgent: 43.3%
+- **DeepCode: 73.5%**
+
+The **+30.2% improvement** over the best-performing LLM agent demonstrates that sophisticated agent scaffolding, rather than extended inference time or larger models, is critical for complex code reproduction tasks.
+
+---
+
+### 🎯 **Autonomous Self-Orchestrating Multi-Agent Architecture**
 
 **The Challenges**:
 
@@ -489,6 +566,7 @@ Implementation Generation • Testing • Documentation
 
 ---
 
+
 ## 🚀 Quick Start
 
 

{deepcode_hku-1.0.5 → deepcode_hku-1.0.6}/README.md

@@ -52,6 +52,15 @@
   </a>
 </div>
 
+<div align="center" style="margin-top: 10px;">
+  <a href="README.md">
+    <img src="https://img.shields.io/badge/English-00d4ff?style=for-the-badge&logo=readme&logoColor=white&labelColor=1a1a2e" alt="English">
+  </a>
+  <a href="README_ZH.md">
+    <img src="https://img.shields.io/badge/中文-00d4ff?style=for-the-badge&logo=readme&logoColor=white&labelColor=1a1a2e" alt="中文">
+  </a>
+</div>
+
 ### 🖥️ **Interface Showcase**
 
 <table align="center" width="100%" style="border: none; border-collapse: collapse; margin: 30px 0;">
@@ -133,14 +142,30 @@
 
 ## 📑 Table of Contents
 
+- [📰 News](#-news)
 - [🚀 Key Features](#-key-features)
 - [🏗️ Architecture](#️-architecture)
+- [📊 Experimental Results](#-experimental-results)
 - [🚀 Quick Start](#-quick-start)
 - [💡 Examples](#-examples)
   - [🎬 Live Demonstrations](#-live-demonstrations)
 - [⭐ Star History](#-star-history)
 - [📄 License](#-license)
 
+
+---
+
+## 📰 News
+
+🎉 **[2025-10] 🎉 [2025-10-28] DeepCode Achieves SOTA on PaperBench!**
+
+DeepCode sets new benchmarks on OpenAI's PaperBench Code-Dev across all categories:
+
+- 🏆 **Surpasses Human Experts**: **75.9%** (DeepCode) vs Top Machine Learning PhDs 72.4% (+3.5%).
+- 🥇 **Outperforms SOTA Commercial Code Agents**: **84.8%** (DeepCode) vs Leading Commercial Code Agents (+26.1%) (Cursor, Claude Code, and Codex).
+- 🔬 **Advances Scientific Coding**: **73.5%** (DeepCode) vs PaperCoder 51.1% (+22.4%).
+- 🚀 **Beats LLM Agents**: **73.5%** (DeepCode) vs best LLM frameworks 43.3% (+30.2%).
+
 ---
 
 ## 🚀 Key Features
@@ -217,7 +242,58 @@
 
 <br/>
 
-### 🎯 **Autonomous Multi-Agent Workflow**
+---
+
+## 📊 Experimental Results
+
+<div align="center">
+    <img src='./assets/result_main02.jpg' /><br>
+</div>
+<br/>
+
+We evaluate **DeepCode** on the [*PaperBench*](https://openai.com/index/paperbench/) benchmark (released by OpenAI), a rigorous testbed requiring AI agents to independently reproduce 20 ICML 2024 papers from scratch. The benchmark comprises 8,316 gradable components assessed using SimpleJudge with hierarchical weighting.
+
+Our experiments compare DeepCode against four baseline categories: **(1) Human Experts**, **(2) State-of-the-Art Commercial Code Agents**, **(3) Scientific Code Agents**, and **(4) LLM-Based Agents**.
+
+### ① 🧠 Human Expert Performance (Top Machine Learning PhD)
+
+**DeepCode: 75.9% vs. Top Machine Learning PhD: 72.4% (+3.5%)**
+
+DeepCode achieves **75.9%** on the 3-paper human evaluation subset, **surpassing the best-of-3 human expert baseline (72.4%) by +3.5 percentage points**. This demonstrates that our framework not only matches but exceeds expert-level code reproduction capabilities, representing a significant milestone in autonomous scientific software engineering.
+
+### ② 💼 State-of-the-Art Commercial Code Agents
+
+**DeepCode: 84.8% vs. Best Commercial Agent: 58.7% (+26.1%)**
+
+On the 5-paper subset, DeepCode substantially outperforms leading commercial coding tools:
+- Cursor: 58.4%
+- Claude Code: 58.7%
+- Codex: 40.0%
+- **DeepCode: 84.8%**
+
+This represents a **+26.1% improvement** over the leading commercial code agent. All commercial agents utilize Claude Sonnet 4.5 or GPT-5 Codex-high, highlighting that **DeepCode's superior architecture**—rather than base model capability—drives this performance gap.
+
+### ③ 🔬 Scientific Code Agents
+
+**DeepCode: 73.5% vs. PaperCoder: 51.1% (+22.4%)**
+
+Compared to PaperCoder (**51.1%**), the state-of-the-art scientific code reproduction framework, DeepCode achieves **73.5%**, demonstrating a **+22.4% relative improvement**. This substantial margin validates our multi-module architecture combining planning, hierarchical task decomposition, code generation, and iterative debugging over simpler pipeline-based approaches.
+
+### ④ 🤖 LLM-Based Agents
+
+**DeepCode: 73.5% vs. Best LLM Agent: 43.3% (+30.2%)**
+
+DeepCode significantly outperforms all tested LLM agents:
+- Claude 3.5 Sonnet + IterativeAgent: 27.5%
+- o1 + IterativeAgent (36 hours): 42.4%
+- o1 BasicAgent: 43.3%
+- **DeepCode: 73.5%**
+
+The **+30.2% improvement** over the best-performing LLM agent demonstrates that sophisticated agent scaffolding, rather than extended inference time or larger models, is critical for complex code reproduction tasks.
+
+---
+
+### 🎯 **Autonomous Self-Orchestrating Multi-Agent Architecture**
 
 **The Challenges**:
 
@@ -445,6 +521,7 @@ Implementation Generation • Testing • Documentation
 
 ---
 
+
 ## 🚀 Quick Start
 
 

{deepcode_hku-1.0.5 → deepcode_hku-1.0.6}/__init__.py

@@ -5,7 +5,7 @@ DeepCode - AI Research Engine
 ⚡ Transform research papers into working code automatically
 """
 
-__version__ = "1.0.5"
+__version__ = "1.0.6"
 __author__ = "DeepCode Team"
 __url__ = "https://github.com/HKUDS/DeepCode"
 

{deepcode_hku-1.0.5 → deepcode_hku-1.0.6}/cli/cli_interface.py

@@ -39,7 +39,9 @@ class CLIInterface:
         self.uploaded_file = None
         self.is_running = True
         self.processing_history = []
-        self.enable_indexing = True  # Default configuration
+        self.enable_indexing = (
+            False  # Default configuration (matching UI: fast mode by default)
+        )
 
         # Load segmentation config from the same source as UI
         self._load_segmentation_config()

{deepcode_hku-1.0.5 → deepcode_hku-1.0.6}/cli/main_cli.py

@@ -214,15 +214,17 @@ async def main():
         # 创建CLI应用
         app = CLIApp()
 
-        # 设置配置
+        # 设置配置 - 默认禁用索引功能以加快处理速度
         if args.optimized:
             app.cli.enable_indexing = False
             print(
                 f"\n{Colors.YELLOW}⚡ Optimized mode enabled - indexing disabled{Colors.ENDC}"
             )
         else:
+            # 默认也禁用索引功能
+            app.cli.enable_indexing = False
             print(
-                f"\n{Colors.GREEN}🧠 Comprehensive mode enabled - full intelligence analysis{Colors.ENDC}"
+                f"\n{Colors.YELLOW}⚡ Fast mode enabled - indexing disabled by default{Colors.ENDC}"
             )
 
         # Configure document segmentation settings
@@ -248,7 +250,9 @@ async def main():
                 if not os.path.exists(args.file):
                     print(f"{Colors.FAIL}❌ File not found: {args.file}{Colors.ENDC}")
                     sys.exit(1)
-                success = await run_direct_processing(app, args.file, "file")
+                # 使用 file:// 前缀保持与交互模式一致，确保文件被复制而非移动
+                file_url = f"file://{os.path.abspath(args.file)}"
+                success = await run_direct_processing(app, file_url, "file")
             elif args.url:
                 success = await run_direct_processing(app, args.url, "url")
             elif args.chat:

{deepcode_hku-1.0.5 → deepcode_hku-1.0.6}/cli/workflows/cli_workflow_adapter.py

@@ -4,6 +4,14 @@ CLI工作流适配器 - 智能体编排引擎
 
 This adapter provides CLI-optimized interface to the latest agent orchestration engine,
 with enhanced progress reporting, error handling, and CLI-specific optimizations.
+
+Version: 2.0 (Updated to match UI version)
+Changes:
+- Default enable_indexing=False for faster processing (matching UI defaults)
+- Mode-aware progress callback with detailed stage mapping
+- Chat pipeline now accepts enable_indexing parameter
+- Improved error handling and resource management
+- Enhanced progress display for different modes (fast/comprehensive/chat)
 """
 
 import os
@@ -36,7 +44,7 @@ class CLIWorkflowAdapter:
 
     async def initialize_mcp_app(self) -> Dict[str, Any]:
         """
-        Initialize MCP application for CLI usage.
+        Initialize MCP application for CLI usage (improved version matching UI).
 
         Returns:
             dict: Initialization result
@@ -47,7 +55,7 @@ class CLIWorkflowAdapter:
                     "🚀 Initializing Agent Orchestration Engine", 2.0
                 )
 
-            # Initialize MCP application
+            # Initialize MCP application using async context manager (matching UI pattern)
             self.app = MCPApp(name="cli_agent_orchestration")
             self.app_context = self.app.run()
             agent_app = await self.app_context.__aenter__()
@@ -56,8 +64,6 @@ class CLIWorkflowAdapter:
             self.context = agent_app.context
 
             # Configure filesystem access
-            import os
-
             self.context.config.mcp.servers["filesystem"].args.extend([os.getcwd()])
 
             if self.cli_interface:
@@ -93,9 +99,14 @@ class CLIWorkflowAdapter:
                         f"⚠️ Cleanup warning: {str(e)}", "warning"
                     )
 
-    def create_cli_progress_callback(self) -> Callable:
+    def create_cli_progress_callback(self, enable_indexing: bool = True) -> Callable:
         """
-        Create CLI-optimized progress callback function.
+        Create CLI-optimized progress callback function with mode-aware stage mapping.
+
+        This matches the UI version's detailed progress mapping logic.
+
+        Args:
+            enable_indexing: Whether indexing is enabled (affects stage mapping)
 
         Returns:
             Callable: Progress callback function
@@ -103,23 +114,43 @@ class CLIWorkflowAdapter:
 
         def progress_callback(progress: int, message: str):
             if self.cli_interface:
-                # Map progress to CLI stages
-                if progress <= 10:
-                    self.cli_interface.display_processing_stages(1)
-                elif progress <= 25:
-                    self.cli_interface.display_processing_stages(2)
-                elif progress <= 40:
-                    self.cli_interface.display_processing_stages(3)
-                elif progress <= 50:
-                    self.cli_interface.display_processing_stages(4)
-                elif progress <= 60:
-                    self.cli_interface.display_processing_stages(5)
-                elif progress <= 70:
-                    self.cli_interface.display_processing_stages(6)
-                elif progress <= 85:
-                    self.cli_interface.display_processing_stages(7)
+                # Mode-aware stage mapping (matching UI version logic)
+                if enable_indexing:
+                    # Full workflow mapping: Initialize -> Analyze -> Download -> Plan -> References -> Repos -> Index -> Implement
+                    if progress <= 5:
+                        stage = 0  # Initialize
+                    elif progress <= 10:
+                        stage = 1  # Analyze
+                    elif progress <= 25:
+                        stage = 2  # Download
+                    elif progress <= 40:
+                        stage = 3  # Plan
+                    elif progress <= 50:
+                        stage = 4  # References
+                    elif progress <= 60:
+                        stage = 5  # Repos
+                    elif progress <= 70:
+                        stage = 6  # Index
+                    elif progress <= 85:
+                        stage = 7  # Implement
+                    else:
+                        stage = 8  # Complete
                 else:
-                    self.cli_interface.display_processing_stages(8)
+                    # Fast mode mapping: Initialize -> Analyze -> Download -> Plan -> Implement
+                    if progress <= 5:
+                        stage = 0  # Initialize
+                    elif progress <= 10:
+                        stage = 1  # Analyze
+                    elif progress <= 25:
+                        stage = 2  # Download
+                    elif progress <= 40:
+                        stage = 3  # Plan
+                    elif progress <= 85:
+                        stage = 4  # Implement (skip References, Repos, Index)
+                    else:
+                        stage = 4  # Complete
+
+                self.cli_interface.display_processing_stages(stage, enable_indexing)
 
                 # Display status message
                 self.cli_interface.print_status(message, "processing")
@@ -127,14 +158,16 @@ class CLIWorkflowAdapter:
         return progress_callback
 
     async def execute_full_pipeline(
-        self, input_source: str, enable_indexing: bool = True
+        self, input_source: str, enable_indexing: bool = False
     ) -> Dict[str, Any]:
         """
         Execute the complete intelligent multi-agent research orchestration pipeline.
 
+        Updated to match UI version: default enable_indexing=False for faster processing.
+
         Args:
             input_source: Research input source (file path, URL, or preprocessed analysis)
-            enable_indexing: Whether to enable advanced intelligence analysis
+            enable_indexing: Whether to enable advanced intelligence analysis (default: False)
 
         Returns:
             dict: Comprehensive pipeline execution result
@@ -145,16 +178,20 @@ class CLIWorkflowAdapter:
                 execute_multi_agent_research_pipeline,
             )
 
-            # Create CLI progress callback
-            progress_callback = self.create_cli_progress_callback()
+            # Create CLI progress callback with mode awareness
+            progress_callback = self.create_cli_progress_callback(enable_indexing)
 
             # Display pipeline start
             if self.cli_interface:
-                mode = "comprehensive" if enable_indexing else "optimized"
+                if enable_indexing:
+                    mode_msg = "🧠 comprehensive (with indexing)"
+                else:
+                    mode_msg = "⚡ fast (indexing disabled)"
                 self.cli_interface.print_status(
-                    f"🚀 Starting {mode} agent orchestration pipeline...", "processing"
+                    f"🚀 Starting {mode_msg} agent orchestration pipeline...",
+                    "processing",
                 )
-                self.cli_interface.display_processing_stages(0)
+                self.cli_interface.display_processing_stages(0, enable_indexing)
 
             # Execute the pipeline
             result = await execute_multi_agent_research_pipeline(
@@ -166,7 +203,10 @@ class CLIWorkflowAdapter:
 
             # Display completion
             if self.cli_interface:
-                self.cli_interface.display_processing_stages(8)
+                final_stage = 8 if enable_indexing else 4
+                self.cli_interface.display_processing_stages(
+                    final_stage, enable_indexing
+                )
                 self.cli_interface.print_status(
                     "🎉 Agent orchestration pipeline completed successfully!",
                     "complete",
@@ -189,12 +229,17 @@ class CLIWorkflowAdapter:
                 "pipeline_mode": "comprehensive" if enable_indexing else "optimized",
             }
 
-    async def execute_chat_pipeline(self, user_input: str) -> Dict[str, Any]:
+    async def execute_chat_pipeline(
+        self, user_input: str, enable_indexing: bool = False
+    ) -> Dict[str, Any]:
         """
         Execute the chat-based planning and implementation pipeline.
 
+        Updated to match UI version: accepts enable_indexing parameter.
+
         Args:
             user_input: User's coding requirements and description
+            enable_indexing: Whether to enable indexing for enhanced code understanding (default: False)
 
         Returns:
             dict: Chat pipeline execution result
@@ -208,51 +253,45 @@ class CLIWorkflowAdapter:
             # Create CLI progress callback for chat mode
             def chat_progress_callback(progress: int, message: str):
                 if self.cli_interface:
-                    # Map progress to CLI stages for chat mode
+                    # Map progress to CLI stages for chat mode (matching UI logic)
                     if progress <= 5:
-                        self.cli_interface.display_processing_stages(
-                            0, chat_mode=True
-                        )  # Initialize
+                        stage = 0  # Initialize
                     elif progress <= 30:
-                        self.cli_interface.display_processing_stages(
-                            1, chat_mode=True
-                        )  # Planning
+                        stage = 1  # Planning
                     elif progress <= 50:
-                        self.cli_interface.display_processing_stages(
-                            2, chat_mode=True
-                        )  # Setup
+                        stage = 2  # Setup
                     elif progress <= 70:
-                        self.cli_interface.display_processing_stages(
-                            3, chat_mode=True
-                        )  # Save Plan
+                        stage = 3  # Save Plan
                     else:
-                        self.cli_interface.display_processing_stages(
-                            4, chat_mode=True
-                        )  # Implement
+                        stage = 4  # Implement
+
+                    self.cli_interface.display_processing_stages(stage, chat_mode=True)
 
                     # Display status message
                     self.cli_interface.print_status(message, "processing")
 
             # Display pipeline start
             if self.cli_interface:
+                indexing_note = (
+                    " (with indexing)" if enable_indexing else " (fast mode)"
+                )
                 self.cli_interface.print_status(
-                    "🚀 Starting chat-based planning pipeline...", "processing"
+                    f"🚀 Starting chat-based planning pipeline{indexing_note}...",
+                    "processing",
                 )
                 self.cli_interface.display_processing_stages(0, chat_mode=True)
 
-            # Execute the chat pipeline with indexing enabled for enhanced code understanding
+            # Execute the chat pipeline with configurable indexing
             result = await execute_chat_based_planning_pipeline(
                 user_input=user_input,
                 logger=self.logger,
                 progress_callback=chat_progress_callback,
-                enable_indexing=True,  # Enable indexing for better code implementation
+                enable_indexing=enable_indexing,  # Pass through enable_indexing parameter
             )
 
             # Display completion
             if self.cli_interface:
-                self.cli_interface.display_processing_stages(
-                    4, chat_mode=True
-                )  # Final stage for chat mode
+                self.cli_interface.display_processing_stages(4, chat_mode=True)
                 self.cli_interface.print_status(
                     "🎉 Chat-based planning pipeline completed successfully!",
                     "complete",
@@ -268,17 +307,18 @@ class CLIWorkflowAdapter:
             return {"status": "error", "error": error_msg, "pipeline_mode": "chat"}
 
     async def process_input_with_orchestration(
-        self, input_source: str, input_type: str, enable_indexing: bool = True
+        self, input_source: str, input_type: str, enable_indexing: bool = False
     ) -> Dict[str, Any]:
         """
         Process input using the intelligent agent orchestration engine.
 
         This is the main CLI interface to the latest agent orchestration capabilities.
+        Updated to match UI version: default enable_indexing=False.
 
         Args:
-            input_source: Input source (file path or URL)
-            input_type: Type of input ('file' or 'url')
-            enable_indexing: Whether to enable advanced intelligence analysis
+            input_source: Input source (file path, URL, or chat input)
+            input_type: Type of input ('file', 'url', or 'chat')
+            enable_indexing: Whether to enable advanced intelligence analysis (default: False)
 
         Returns:
             dict: Processing result with status and details
@@ -301,7 +341,10 @@ class CLIWorkflowAdapter:
             # Execute appropriate pipeline based on input type
             if input_type == "chat":
                 # Use chat-based planning pipeline for user requirements
-                pipeline_result = await self.execute_chat_pipeline(input_source)
+                # Pass enable_indexing to chat pipeline as well
+                pipeline_result = await self.execute_chat_pipeline(
+                    input_source, enable_indexing=enable_indexing
+                )
             else:
                 # Use traditional multi-agent research pipeline for files/URLs
                 pipeline_result = await self.execute_full_pipeline(