execdiff-git-ai 1.0.0__tar.gz → 1.0.2__tar.gz

{execdiff_git_ai-1.0.0 → execdiff_git_ai-1.0.2}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: execdiff-git-ai
-Version: 1.0.0
-Summary: Local-first tool for analyzing AI-driven code changes. Analyzes Git diffs and assesses impact of changes made by AI coding assistants.
+Version: 1.0.2
+Summary: AI Impact Assessment for git changes - understand what your AI copilot changed before you commit.
 Author-email: Anup Moncy <n93181165@gmail.com>
 License: Apache License
         Version 2.0, January 2004
@@ -21,10 +21,10 @@ License: Apache License
         See the License for the specific language governing permissions and
         limitations under the License.
         
-Project-URL: Homepage, https://github.com/yourusername/execdiff-git-ai
-Project-URL: Bug Tracker, https://github.com/yourusername/execdiff-git-ai/issues
-Project-URL: Documentation, https://github.com/yourusername/execdiff-git-ai#readme
-Keywords: git,ai,copilot,code-analysis,diff,impact-assessment,execdiff
+Project-URL: Homepage, https://github.com/anupmoncy/execdiff-git-ai
+Project-URL: Bug Tracker, https://github.com/anupmoncy/execdiff-git-ai/issues
+Project-URL: Documentation, https://github.com/anupmoncy/execdiff-git-ai#readme
+Keywords: git,ai,copilot,code-analysis,diff,impact-assessment
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: Apache Software License
@@ -35,10 +35,10 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Version Control :: Git
-Classifier: Topic :: Software Development :: Quality Assurance
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: requests>=2.25.0
 Dynamic: license-file
 
 # ExecDiff Git AI
@@ -47,7 +47,7 @@ AI Impact Assessment for git changes - understand what your AI copilot changed b
 
 ## Overview
 
-ExecDiff Git AI is a Python CLI tool that helps developers understand the scope and implications of code changes made by AI coding assistants (like GitHub Copilot, Cursor, or Replit AI) by analyzing git diffs and extracting modified symbols (functions, classes, variables). It can optionally use a local LLM (Ollama) to assess the risk of each change.
+ExecDiff Git AI is a Python CLI tool that helps developers understand the scope and implications of code changes made by AI coding assistants (like GitHub Copilot, Cursor, or Replit AI) by analyzing git diffs and extracting modified symbols (functions, classes, variables). It can optionally use a local LLM (Ollama) to assess the business impact of each change.
 
 ## Privacy
 
@@ -56,24 +56,23 @@ ExecDiff Git AI runs **entirely locally**.
 - ✅ No code is uploaded
 - ✅ No cloud calls required
 - ✅ No telemetry
-- ✅ Works offline with local LLM (Ollama)
+- ✅ Works offline with optional local LLM (Ollama)
 - ✅ All analysis happens on your machine
 
 ## Features
 
 - **Local-first**: Runs entirely on your machine with no cloud calls or telemetry
 - **Impact Assessment**: Detects specific changes to functions, classes, and variables and provides human-readable summaries
-- **AI-powered risk assessment**: Utilizes local Ollama for intelligent impact analysis and scoring (optional)
+- **Two modes**: Fast analysis (non-AI) or deep AI-powered analysis (optional)
 - **CLI-first**: `execdiff-git scan` and `execdiff-git scan-ai`
 - **Works offline**, no telemetry
 
 ## Installation
 
-### Prerequisites
+### Prerequisites (Required)
 
 - Python 3.8+
 - Git
-- Ollama (optional, for AI risk assessment)
 
 ### Initial Setup
 
@@ -83,8 +82,12 @@ Install from PyPI:
 pip install execdiff-git-ai
 ```
 
+That's it! You can now use the non-AI mode immediately.
+
 ## How to Use
 
+### Quick Start (No AI Required)
+
 1. **Make your code change** (or let your AI copilot make changes)
 
 2. **Stage your changes with git**
@@ -95,32 +98,89 @@ pip install execdiff-git-ai
    git add -N .
    ```
 
-3. **Run the assessment (no AI)**
+3. **Run the assessment**
 
    ```bash
    execdiff-git scan
    ```
 
-   Or, to use AI-powered risk assessment (requires Ollama):
+**Note**: For newly created files, you must run `git add -N .` (intent-to-add) so that `execdiff-git scan` can detect them. This is a git limitation for diff tools.
 
-   ```bash
-   execdiff-git scan-ai
-   ```
+---
+
+## AI-Powered Assessment (Optional)
+
+**AI mode is completely optional.** The non-AI mode works great for most use cases.
+
+### Requirements for AI Mode
+
+| Component | Size | Description |
+|-----------|------|-------------|
+| **Ollama** | ~50MB | Local AI runtime (one-time install) |
+| **tinyllama model** | ~637MB | Smallest AI model (one-time download) |
+
+**Total: ~700MB one-time download**
+
+- ✅ 100% local - no data sent to cloud
+- ✅ Works offline after initial setup
+- ✅ User permission required before any downloads
+
+### How AI Mode Works
+
+When you run `execdiff-git scan-ai`:
+
+1. **Ollama check** - Checks if Ollama is installed
+2. **Model check** - Checks if AI model is available
+3. **User permission** - Asks before downloading anything
+4. **Auto-start** - Starts Ollama server automatically
+5. **Analysis** - Runs local AI analysis on your changes
+6. **Auto-stop** - Stops Ollama server when done
+
+### Install Ollama (One-Time)
+
+**macOS:**
+```bash
+brew install ollama
+```
+
+**macOS/Linux:**
+```bash
+curl -fsSL https://ollama.ai/install.sh | sh
+```
+
+**Or download from:** https://ollama.ai/
+
+### Use AI Mode
+
+Simply run:
+
+```bash
+execdiff-git scan-ai
+```
+
+If the AI model is not installed, you'll be asked:
 
-**Note**: For newly created files, you must run `git add -N .` (intent-to-add) so that `execdiff-git scan` or `execdiff-git scan-ai` can detect them. This is a git limitation for diff tools.
+```
+⚠️  Model 'tinyllama' (~637MB) is not installed locally.
+✅ Everything stays local - no data is sent to the cloud.
+
+Download 'tinyllama' now? (yes/no): 
+```
+
+**Say "yes" to download, or "no" to skip AI analysis.**
+
+---
 
 ## Usage
 
 ### Basic Commands
 
-Analyze changes in the current repository:
-
+**Non-AI mode (fast, always available, no setup):**
 ```bash
 execdiff-git scan
 ```
 
-Analyze with AI-powered risk assessment:
-
+**AI mode (optional, requires Ollama ~700MB total):**
 ```bash
 execdiff-git scan-ai
 ```
@@ -135,44 +195,21 @@ execdiff-git scan-ai
 ==============================
 File                            +Lines  -Lines
 ------------------------------------------------
-shopping_cart.py                     10       2
-checkout.py                           7       1
-email/notifications.py                5       0
-
---------------------------------
+test_feature.py                     14       0
 
 ================================================================================
 📋 Impact Summary
 ================================================================================
 Symbol                    Change Type          Impact  
 --------------------------------------------------------
-add_to_cart               function modified    MEDIUM  
-remove_from_cart          function modified    LOW     
-checkout                  function modified    HIGH    
-send_order_email          function added       LOW     
+authenticate_user         function added       LOW     
+create_session            function added       LOW     
+validate_token            function added       LOW     
 
 ✅ Assessment complete!
 ```
 
-## Optional: Install Ollama for AI Risk Assessment
-
-Ollama enables intelligent risk scoring. Install and configure:
-
-```bash
-# macOS / Linux
-curl -fsSL https://ollama.ai/install.sh | sh
-
-# Or use Homebrew (macOS)
-brew install ollama
-
-# Pull the model
-ollama pull llama2
-
-# Start the server (runs on localhost:11434)
-ollama serve
-```
-
-With Ollama running, you'll also get AI-powered impact assessment:
+**AI Mode (with Ollama):**
 
 ```
 ==============================
@@ -180,72 +217,74 @@ With Ollama running, you'll also get AI-powered impact assessment:
 ==============================
 File                            +Lines  -Lines
 ------------------------------------------------
-shopping_cart.py                     10       2
-checkout.py                           7       1
-email/notifications.py                5       0
-
---------------------------------
+test_feature.py                     14       0
 
 ================================================================================
 📋 Impact Summary
 ================================================================================
 Symbol                    Change Type          Impact  
 --------------------------------------------------------
-add_to_cart               function modified    MEDIUM  
-remove_from_cart          function modified    LOW     
-checkout                  function modified    HIGH    
-send_order_email          function added       LOW     
+authenticate_user         function added       LOW     
+create_session            function added       LOW     
+validate_token            function added       LOW     
 
 ================================================================================
 🤖 AI Impact Assessment
 ================================================================================
 
-📋 What Changed:
-  🔴 Critical: Checkout now supports Apple Pay, Google Pay, and PayPal in addition to credit cards, and changes the order completion flow. Payment processing reliability and customer purchase experience are directly affected.
-  🟡 Important: Cart logic now merges duplicate items and updates product quantities in one step. This changes how users see totals and manage products in their cart.
-  🟢 Low Risk: Order confirmation emails improved. Cart item removal is more reliable.
+🚀 Starting Ollama server...
+⏳ Waiting for Ollama server to start...
+✅ Ollama server is ready!
+🧠 Analyzing with AI (tinyllama, 100% local)...
 
-  Scope: 3 files modified (22 additions, 3 removals)
-
-Detailed Analysis:
-
-File: shopping_cart.py - Symbol: add_to_cart
+Symbol: authenticate_user
 Impact: MEDIUM
-Summary: Cart logic updated to better handle product quantities and merging duplicate items.
+Summary: Added user authentication logic. This affects user access and security.
 
-File: shopping_cart.py - Symbol: remove_from_cart
+Symbol: create_session
 Impact: LOW
-Summary: Improved item removal to prevent accidental deletion of unrelated products.
+Summary: Added session creation. Improves user experience and session management.
 
-File: checkout.py - Symbol: checkout
-Impact: HIGH
-Summary: Checkout flow changed to support Apple Pay, Google Pay, PayPal, and credit cards, and to update order completion steps.
-
-File: email/notifications.py - Symbol: send_order_email
+Symbol: validate_token
 Impact: LOW
-Summary: Confirmation emails are now sent after every successful order.
+Summary: Added token validation. Enhances security by validating session tokens.
 
-⚠️  ALERT: 1 critical change detected!
-Please review carefully before deploying to production.
+🛑 Ollama server stopped
 
 ✅ Assessment complete!
 ```
 
+---
+
+## Comparison: Non-AI vs AI Mode
+
+| Feature | Non-AI Mode | AI Mode |
+|---------|-------------|---------|
+| **Setup** | None | Ollama + model (~700MB) |
+| **Speed** | Instant | 5-30 seconds |
+| **Analysis** | Symbol detection | Business-facing summaries |
+| **Privacy** | 100% local | 100% local |
+| **Offline** | Yes | Yes (after setup) |
+
+---
+
 ## How It Works
 
-1. **Reads git diff** - Gets all staged and unstaged changes
+1. **Reads git diff** - Gets all staged changes (`git diff --cached`)
 2. **Extracts symbols** - Finds functions, classes, and variables
 3. **Detects change type** - Identifies what kind of change was made
-4. **Assesses impact** - Uses local AI (Ollama) or heuristics
-5. **Generates recommendations** - Suggests testing and review actions (AI mode only)
+4. **Assesses impact** - Uses local AI (Ollama) if available, or quick heuristics
+5. **Generates business summary** - Specific, non-technical impact summary (AI mode only)
 6. **Advisory warnings** - Critical impact changes trigger warnings (AI mode only)
 
+---
+
 ## Development
 
 Install in editable mode:
 
 ```bash
-git clone https://github.com/yourusername/execdiff-git-ai.git
+git clone https://github.com/anupmoncy/execdiff-git-ai.git
 cd execdiff-git-ai
 pip install -e .
 ```
@@ -266,7 +305,7 @@ from execdiff_git_ai.agent import run_agent, run_agent_with_ai
 # Non-AI mode (default)
 run_agent()
 
-# AI-powered mode (optional, requires Ollama)
+# AI-powered mode (optional, automatically manages Ollama)
 run_agent_with_ai()
 ```
 

{execdiff_git_ai-1.0.0 → execdiff_git_ai-1.0.2}/README.md

@@ -4,7 +4,7 @@ AI Impact Assessment for git changes - understand what your AI copilot changed b
 
 ## Overview
 
-ExecDiff Git AI is a Python CLI tool that helps developers understand the scope and implications of code changes made by AI coding assistants (like GitHub Copilot, Cursor, or Replit AI) by analyzing git diffs and extracting modified symbols (functions, classes, variables). It can optionally use a local LLM (Ollama) to assess the risk of each change.
+ExecDiff Git AI is a Python CLI tool that helps developers understand the scope and implications of code changes made by AI coding assistants (like GitHub Copilot, Cursor, or Replit AI) by analyzing git diffs and extracting modified symbols (functions, classes, variables). It can optionally use a local LLM (Ollama) to assess the business impact of each change.
 
 ## Privacy
 
@@ -13,24 +13,23 @@ ExecDiff Git AI runs **entirely locally**.
 - ✅ No code is uploaded
 - ✅ No cloud calls required
 - ✅ No telemetry
-- ✅ Works offline with local LLM (Ollama)
+- ✅ Works offline with optional local LLM (Ollama)
 - ✅ All analysis happens on your machine
 
 ## Features
 
 - **Local-first**: Runs entirely on your machine with no cloud calls or telemetry
 - **Impact Assessment**: Detects specific changes to functions, classes, and variables and provides human-readable summaries
-- **AI-powered risk assessment**: Utilizes local Ollama for intelligent impact analysis and scoring (optional)
+- **Two modes**: Fast analysis (non-AI) or deep AI-powered analysis (optional)
 - **CLI-first**: `execdiff-git scan` and `execdiff-git scan-ai`
 - **Works offline**, no telemetry
 
 ## Installation
 
-### Prerequisites
+### Prerequisites (Required)
 
 - Python 3.8+
 - Git
-- Ollama (optional, for AI risk assessment)
 
 ### Initial Setup
 
@@ -40,8 +39,12 @@ Install from PyPI:
 pip install execdiff-git-ai
 ```
 
+That's it! You can now use the non-AI mode immediately.
+
 ## How to Use
 
+### Quick Start (No AI Required)
+
 1. **Make your code change** (or let your AI copilot make changes)
 
 2. **Stage your changes with git**
@@ -52,32 +55,89 @@ pip install execdiff-git-ai
    git add -N .
    ```
 
-3. **Run the assessment (no AI)**
+3. **Run the assessment**
 
    ```bash
    execdiff-git scan
    ```
 
-   Or, to use AI-powered risk assessment (requires Ollama):
+**Note**: For newly created files, you must run `git add -N .` (intent-to-add) so that `execdiff-git scan` can detect them. This is a git limitation for diff tools.
 
-   ```bash
-   execdiff-git scan-ai
-   ```
+---
+
+## AI-Powered Assessment (Optional)
+
+**AI mode is completely optional.** The non-AI mode works great for most use cases.
+
+### Requirements for AI Mode
+
+| Component | Size | Description |
+|-----------|------|-------------|
+| **Ollama** | ~50MB | Local AI runtime (one-time install) |
+| **tinyllama model** | ~637MB | Smallest AI model (one-time download) |
+
+**Total: ~700MB one-time download**
+
+- ✅ 100% local - no data sent to cloud
+- ✅ Works offline after initial setup
+- ✅ User permission required before any downloads
+
+### How AI Mode Works
+
+When you run `execdiff-git scan-ai`:
+
+1. **Ollama check** - Checks if Ollama is installed
+2. **Model check** - Checks if AI model is available
+3. **User permission** - Asks before downloading anything
+4. **Auto-start** - Starts Ollama server automatically
+5. **Analysis** - Runs local AI analysis on your changes
+6. **Auto-stop** - Stops Ollama server when done
+
+### Install Ollama (One-Time)
+
+**macOS:**
+```bash
+brew install ollama
+```
+
+**macOS/Linux:**
+```bash
+curl -fsSL https://ollama.ai/install.sh | sh
+```
+
+**Or download from:** https://ollama.ai/
+
+### Use AI Mode
+
+Simply run:
+
+```bash
+execdiff-git scan-ai
+```
+
+If the AI model is not installed, you'll be asked:
 
-**Note**: For newly created files, you must run `git add -N .` (intent-to-add) so that `execdiff-git scan` or `execdiff-git scan-ai` can detect them. This is a git limitation for diff tools.
+```
+⚠️  Model 'tinyllama' (~637MB) is not installed locally.
+✅ Everything stays local - no data is sent to the cloud.
+
+Download 'tinyllama' now? (yes/no): 
+```
+
+**Say "yes" to download, or "no" to skip AI analysis.**
+
+---
 
 ## Usage
 
 ### Basic Commands
 
-Analyze changes in the current repository:
-
+**Non-AI mode (fast, always available, no setup):**
 ```bash
 execdiff-git scan
 ```
 
-Analyze with AI-powered risk assessment:
-
+**AI mode (optional, requires Ollama ~700MB total):**
 ```bash
 execdiff-git scan-ai
 ```
@@ -92,44 +152,21 @@ execdiff-git scan-ai
 ==============================
 File                            +Lines  -Lines
 ------------------------------------------------
-shopping_cart.py                     10       2
-checkout.py                           7       1
-email/notifications.py                5       0
-
---------------------------------
+test_feature.py                     14       0
 
 ================================================================================
 📋 Impact Summary
 ================================================================================
 Symbol                    Change Type          Impact  
 --------------------------------------------------------
-add_to_cart               function modified    MEDIUM  
-remove_from_cart          function modified    LOW     
-checkout                  function modified    HIGH    
-send_order_email          function added       LOW     
+authenticate_user         function added       LOW     
+create_session            function added       LOW     
+validate_token            function added       LOW     
 
 ✅ Assessment complete!
 ```
 
-## Optional: Install Ollama for AI Risk Assessment
-
-Ollama enables intelligent risk scoring. Install and configure:
-
-```bash
-# macOS / Linux
-curl -fsSL https://ollama.ai/install.sh | sh
-
-# Or use Homebrew (macOS)
-brew install ollama
-
-# Pull the model
-ollama pull llama2
-
-# Start the server (runs on localhost:11434)
-ollama serve
-```
-
-With Ollama running, you'll also get AI-powered impact assessment:
+**AI Mode (with Ollama):**
 
 ```
 ==============================
@@ -137,72 +174,74 @@ With Ollama running, you'll also get AI-powered impact assessment:
 ==============================
 File                            +Lines  -Lines
 ------------------------------------------------
-shopping_cart.py                     10       2
-checkout.py                           7       1
-email/notifications.py                5       0
-
---------------------------------
+test_feature.py                     14       0
 
 ================================================================================
 📋 Impact Summary
 ================================================================================
 Symbol                    Change Type          Impact  
 --------------------------------------------------------
-add_to_cart               function modified    MEDIUM  
-remove_from_cart          function modified    LOW     
-checkout                  function modified    HIGH    
-send_order_email          function added       LOW     
+authenticate_user         function added       LOW     
+create_session            function added       LOW     
+validate_token            function added       LOW     
 
 ================================================================================
 🤖 AI Impact Assessment
 ================================================================================
 
-📋 What Changed:
-  🔴 Critical: Checkout now supports Apple Pay, Google Pay, and PayPal in addition to credit cards, and changes the order completion flow. Payment processing reliability and customer purchase experience are directly affected.
-  🟡 Important: Cart logic now merges duplicate items and updates product quantities in one step. This changes how users see totals and manage products in their cart.
-  🟢 Low Risk: Order confirmation emails improved. Cart item removal is more reliable.
+🚀 Starting Ollama server...
+⏳ Waiting for Ollama server to start...
+✅ Ollama server is ready!
+🧠 Analyzing with AI (tinyllama, 100% local)...
 
-  Scope: 3 files modified (22 additions, 3 removals)
-
-Detailed Analysis:
-
-File: shopping_cart.py - Symbol: add_to_cart
+Symbol: authenticate_user
 Impact: MEDIUM
-Summary: Cart logic updated to better handle product quantities and merging duplicate items.
+Summary: Added user authentication logic. This affects user access and security.
 
-File: shopping_cart.py - Symbol: remove_from_cart
+Symbol: create_session
 Impact: LOW
-Summary: Improved item removal to prevent accidental deletion of unrelated products.
+Summary: Added session creation. Improves user experience and session management.
 
-File: checkout.py - Symbol: checkout
-Impact: HIGH
-Summary: Checkout flow changed to support Apple Pay, Google Pay, PayPal, and credit cards, and to update order completion steps.
-
-File: email/notifications.py - Symbol: send_order_email
+Symbol: validate_token
 Impact: LOW
-Summary: Confirmation emails are now sent after every successful order.
+Summary: Added token validation. Enhances security by validating session tokens.
 
-⚠️  ALERT: 1 critical change detected!
-Please review carefully before deploying to production.
+🛑 Ollama server stopped
 
 ✅ Assessment complete!
 ```
 
+---
+
+## Comparison: Non-AI vs AI Mode
+
+| Feature | Non-AI Mode | AI Mode |
+|---------|-------------|---------|
+| **Setup** | None | Ollama + model (~700MB) |
+| **Speed** | Instant | 5-30 seconds |
+| **Analysis** | Symbol detection | Business-facing summaries |
+| **Privacy** | 100% local | 100% local |
+| **Offline** | Yes | Yes (after setup) |
+
+---
+
 ## How It Works
 
-1. **Reads git diff** - Gets all staged and unstaged changes
+1. **Reads git diff** - Gets all staged changes (`git diff --cached`)
 2. **Extracts symbols** - Finds functions, classes, and variables
 3. **Detects change type** - Identifies what kind of change was made
-4. **Assesses impact** - Uses local AI (Ollama) or heuristics
-5. **Generates recommendations** - Suggests testing and review actions (AI mode only)
+4. **Assesses impact** - Uses local AI (Ollama) if available, or quick heuristics
+5. **Generates business summary** - Specific, non-technical impact summary (AI mode only)
 6. **Advisory warnings** - Critical impact changes trigger warnings (AI mode only)
 
+---
+
 ## Development
 
 Install in editable mode:
 
 ```bash
-git clone https://github.com/yourusername/execdiff-git-ai.git
+git clone https://github.com/anupmoncy/execdiff-git-ai.git
 cd execdiff-git-ai
 pip install -e .
 ```
@@ -223,7 +262,7 @@ from execdiff_git_ai.agent import run_agent, run_agent_with_ai
 # Non-AI mode (default)
 run_agent()
 
-# AI-powered mode (optional, requires Ollama)
+# AI-powered mode (optional, automatically manages Ollama)
 run_agent_with_ai()
 ```