Merge branch 'develop' into vishal/analyticsguide

vishalshenoy · web-flow · commit d48028d951ca · 2025-03-14T09:29:31.000-07:00
diff --git a/codegen-examples/pyproject.toml b/codegen-examples/pyproject.toml
@@ -27,7 +27,7 @@ dev-dependencies = [
   "pre-commit>=4.0.1",
   "pre-commit-uv>=4.1.4",
   "uv>=0.4.25",
-  "jupyterlab==4.3.5",
+  "jupyterlab==4.3.6",
   "deptry>=0.22.0",
 ]
 
diff --git a/codegen-examples/uv.lock b/codegen-examples/uv.lock
diff --git a/docs/gen/capabilities.mdx b/docs/gen/capabilities.mdx
@@ -0,0 +1,71 @@
+---
+title: "Capabilities"
+icon: "gear"
+---
+
+Codegen is built on an [open-source library](/introduction/overiew.mdx) for code manipulation.
+
+It combines "tools" for code editing with powerful integrations, including Github, Linear and Slack.
+
+<Tip>
+  Learn more about our open source [code agent implementation](/docs/tutorials/build-code-agent)
+</Tip>
+
+## Communication Tools
+
+- **SlackSendMessageTool**: Allows Codegen to send messages in Slack channels and threads, providing responses to your queries and sharing information with your team.
+
+## GitHub Integration Tools
+
+Codegen includes a comprehensive set of GitHub tools:
+
+- **GithubCheckoutPRTool**: Checks out pull requests to your local environment for review and testing.
+
+- **GithubCreatePRTool**: Creates new pull requests from your current branch, including title, description, and target branch.
+
+- **GithubCreatePRCommentTool**: Adds comments to pull requests for feedback and team communication.
+
+- **GithubCreatePRReviewCommentTool**: Provides inline comments on specific code changes within pull requests.
+
+- **GithubEditPRTool**: Modifies existing pull requests, including updating titles, descriptions, and other metadata.
+
+- **GithubSearchIssuesTool**: Searches for GitHub issues based on various criteria like status, assignee, or labels.
+
+- **GithubViewPRTool**: Retrieves and displays information about specific pull requests.
+
+- **GithubViewPRCheckTool**: Checks the status of CI/CD and other automated checks on pull requests.
+
+- **GithubViewCommitHistoryTool**: Shows the commit history of a repository or specific branch.
+
+- **GithubViewCommitTool**: Displays details about specific commits, including changes made.
+
+## Linear Integration Tools (Optional)
+
+For teams using Linear for project management, Codegen offers:
+
+- **LinearGetIssueTool**: Retrieves details about specific Linear issues.
+
+- **LinearGetIssueCommentsTool**: Fetches comments on Linear issues for context and history.
+
+- **LinearCommentOnIssueTool**: Adds comments to Linear issues for team communication.
+
+- **LinearSearchIssuesTool**: Searches for Linear issues based on various criteria.
+
+- **LinearCreateIssueTool**: Creates new issues in Linear with appropriate metadata.
+
+- **LinearGetTeamsTool**: Retrieves information about teams in your Linear organization.
+
+## How Codegen Uses These Tools
+
+Codegen's AI brain (powered by Claude 3.7 Sonnet) intelligently selects and combines these tools to:
+
+1. Understand your requests through natural language in Slack
+2. Determine the most appropriate tools to fulfill your request
+3. Execute the necessary actions across GitHub, Linear, and your codebase
+4. Provide clear, helpful responses back in Slack
+
+This seamless integration allows you to manage your entire development workflow through simple conversations, without having to switch between different platforms and interfaces.
+
+## Getting Started
+
+Ready to experience the power of Codegen? Check out our [Quickstart Guide](/docs/gen/quickstart) to set up Codegen for your team, and explore [Common Commands](/docs/gen/common-commands) to see how to interact with these tools through natural language.
diff --git a/docs/gen/faq.mdx b/docs/gen/faq.mdx
@@ -0,0 +1,18 @@
+---
+title: "Frequently Asked Questions"
+sidebarTitle: "FAQ"
+icon: "square-question"
+iconType: "solid"
+---
+
+<AccordionGroup>
+  <Accordion title="What model does Codegen use?" icon="code">
+    Claude 3.7. Our code agent is roughly comparable with Claude Code.
+  </Accordion>
+  <Accordion title="Is this free?" icon="scale-balanced">
+    Yes! For now. Get it while it's hot.
+  </Accordion>
+  <Accordion title="Where is my data stored?" icon="database">
+    Codegen stores this data in their private cloud. We are SOC-2 compliant. [Learn more](/introduction/about)
+  </Accordion>
+</AccordionGroup> 
diff --git a/docs/gen/introduction.mdx b/docs/gen/introduction.mdx
@@ -0,0 +1,43 @@
+---
+title: "Codegen: AI Development Assistant"
+sidebarTitle: "Introduction"
+icon: "lightbulb"
+---
+
+Codegen is an intelligent code agent powered that seamlessly integrates with Slack, Github and Linear.
+
+<Frame caption="Communicate with codegen via Slack">
+<img src="/images/codegen-bot-intro.png" />
+</Frame>
+
+<Tip>
+  Explore our [Capabilities](/docs/gen/capabilities) page to learn more about
+  Codegen's full feature set and available tools!
+</Tip>
+
+
+# Installation
+
+[Log in with GitHub](https://codegen.sh/start) to install Codegen and set up integrations.
+
+<Card title="Get Started" href={"https://codegen.sh/start"} icon="Gear">
+  Install codegen via OAuth with Github, Slack and Linear
+</Card>
+
+# Common Queries
+
+> *Edit repo X so that the user auth flow uses JWT*  
+Modify the authentication flow in a specified repository to use JSON Web Tokens. This ensures secure and stateless authentication.
+
+> *Show me the recent activity on my repo X*  
+Display the latest commits, pull requests, and other activities in a specified repository. This helps you stay updated with ongoing changes.
+
+> *Can you figure out why my tests are failing on `main`?*  
+Analyze the test failures on the main branch to identify potential issues. This assists in maintaining code quality and stability.
+
+> *Can you review my PR?*  
+Perform a code review on a specified pull request, providing feedback and suggestions. This ensures code quality and adherence to best practices.
+
+> *Do we have any tickets about Y?*  
+Search for tickets related to a specific topic or issue. This helps in tracking and managing tasks effectively.
+
diff --git a/docs/images/codegen-bot-intro.png b/docs/images/codegen-bot-intro.png
diff --git a/docs/mint.json b/docs/mint.json
@@ -378,4 +378,4 @@
 		"x": "https://x.com/codegen",
 		"linkedin": "https://linkedin.com/company/codegen-dot-com"
 	}
-}
+}
diff --git a/src/codegen/sdk/system-prompt.txt b/src/codegen/sdk/system-prompt.txt
@@ -11952,199 +11952,4 @@ LIMIT 20
 
 <Frame caption="Call graph for a codebase">
   <img src="/images/neo4j-call-graph.png" />
-</Frame>
-
----
-title: "Code Attributions"
-sidebarTitle: "Code Attributions"
-description: "Learn how to analyze code statistics and attributions using Codegen"
-icon: "network-wired"
-iconType: "solid"
----
-
-# AI Impact Analysis
-
-This tutorial shows how to use Codegen's attribution extension to analyze the impact of AI on your 
-codebase. You'll learn how to identify which parts of your code were written by AI tools like 
-GitHub Copilot, Devin, or other AI assistants.
-
-Note: the code is flexible - you can track CI pipeline bots, or any other contributor you want.
-
-
-## Overview
-
-The attribution extension analyzes git history to:
-
-1. Identify which symbols (functions, classes, etc.) were authored or modified by AI tools
-2. Calculate the percentage of AI contributions in your codebase
-3. Find high-impact AI-written code (code that many other parts depend on)
-4. Track the evolution of AI contributions over time
-
-## Installation
-
-The attribution extension is included with Codegen. No additional installation is required.
-
-## Basic Usage
-
-### Running the Analysis
-
-You can run the AI impact analysis using the Codegen CLI:
-
-```bash
-codegen analyze-ai-impact
-```
-
-Or from Python code:
-
-```python
-from codegen import Codebase
-from codegen.extensions.attribution.cli import run
-
-# Initialize codebase from current directory
-codebase = Codebase.from_repo("your-org/your-repo", language="python")
-
-# Run the analysis
-run(codebase)
-```
-
-### Understanding the Results
-
-The analysis will print a summary of AI contributions to your console and save detailed results to a JSON file. The summary includes:
-
-- List of all contributors (human and AI)
-- Percentage of commits made by AI
-- Number of files and symbols touched by AI
-- High-impact AI-written code (code with many dependents)
-- Top files by AI contribution percentage
-
-## Advanced Usage
-
-### Accessing Attribution Information
-
-After running the analysis, each symbol in your codebase will have attribution information attached to it:
-
-```python
-from codegen import Codebase
-from codegen.extensions.attribution.main import add_attribution_to_symbols
-
-# Initialize codebase
-codebase = Codebase.from_repo("your-org/your-repo", language="python")
-
-# Add attribution information to symbols
-ai_authors = ['github-actions[bot]', 'dependabot[bot]', 'copilot[bot]']
-add_attribution_to_symbols(codebase, ai_authors)
-
-# Access attribution information on symbols
-for symbol in codebase.symbols:
-    if hasattr(symbol, 'is_ai_authored') and symbol.is_ai_authored:
-        print(f"AI-authored symbol: {symbol.name} in {symbol.filepath}")
-        print(f"Last editor: {symbol.last_editor}")
-        print(f"All editors: {symbol.editor_history}")
-```
-
-### Customizing AI Author Detection
-
-By default, the analysis looks for common AI bot names in commit authors. 
-You can customize this by providing your own list of AI authors:
-
-```python
-from codegen import Codebase
-from codegen.extensions.attribution.main import analyze_ai_impact
-
-# Initialize codebase
-codebase = Codebase.from_repo("your-org/your-repo", language="python")
-
-# Define custom AI authors
-ai_authors = [
-    'github-actions[bot]',
-    'dependabot[bot]',
-    'copilot[bot]',
-    'devin[bot]',
-    'your-custom-ai-email@example.com'
-]
-
-# Run analysis with custom AI authors
-results = analyze_ai_impact(codebase, ai_authors)
-```
-
-## Example: Contributor Analysis
-
-Here's a complete example that analyzes contributors to your codebase and their impact:
-
-```python
-import os
-from collections import Counter
-
-from codegen import Codebase
-from codegen.extensions.attribution.main import add_attribution_to_symbols
-from codegen.git.repo_operator.repo_operator import RepoOperator
-from codegen.git.schemas.repo_config import RepoConfig
-from codegen.sdk.codebase.config import ProjectConfig
-from codegen.shared.enums.programming_language import ProgrammingLanguage
-
-def analyze_contributors(codebase):
-    """Analyze contributors to the codebase and their impact."""
-    print("\n🔍 Contributor Analysis:")
-    
-    # Define which authors are considered AI
-    ai_authors = ['devin[bot]', 'codegen[bot]', 'github-actions[bot]', 'dependabot[bot]']
-    
-    # Add attribution information to all symbols
-    print("Adding attribution information to symbols...")
-    add_attribution_to_symbols(codebase, ai_authors)
-    
-    # Collect statistics about contributors
-    contributor_stats = Counter()
-    ai_contributor_stats = Counter()
-    
-    print("Analyzing symbol attributions...")
-    for symbol in codebase.symbols:
-        if hasattr(symbol, 'last_editor') and symbol.last_editor:
-            contributor_stats[symbol.last_editor] += 1
-            
-            # Track if this is an AI contributor
-            if any(ai in symbol.last_editor for ai in ai_authors):
-                ai_contributor_stats[symbol.last_editor] += 1
-    
-    # Print top contributors overall
-    print("\n👥 Top Contributors by Symbols Authored:")
-    for contributor, count in contributor_stats.most_common(10):
-        is_ai = any(ai in contributor for ai in ai_authors)
-        ai_indicator = "🤖" if is_ai else "👤"
-        print(f"  {ai_indicator} {contributor}: {count} symbols")
-    
-    # Print top AI contributors if any
-    if ai_contributor_stats:
-        print("\n🤖 Top AI Contributors:")
-        for contributor, count in ai_contributor_stats.most_common(5):
-            print(f"  • {contributor}: {count} symbols")
-
-# Initialize codebase from current directory
-if os.path.exists(".git"):
-    repo_path = os.getcwd()
-    repo_config = RepoConfig.from_repo_path(repo_path)
-    repo_operator = RepoOperator(repo_config=repo_config)
-    
-    project = ProjectConfig.from_repo_operator(
-        repo_operator=repo_operator,
-        programming_language=ProgrammingLanguage.PYTHON
-    )
-    codebase = Codebase(projects=[project])
-    
-    # Run the contributor analysis
-    analyze_contributors(codebase)
-```
-
-## Conclusion
-
-The attribution extension provides valuable insights into how AI tools are being used in your 
-development process. By understanding which parts of your codebase are authored by AI, you can:
-
-- Track the adoption of AI coding assistants in your team
-- Identify areas where AI is most effective
-- Ensure appropriate review of AI-generated code
-- Measure the impact of AI on developer productivity
-
-For more advanced usage, check out the [API reference](/api-reference/extensions/attribution)
-for the attribution extension.
-
+</Frame>

Original file line number	Diff line number	Diff line change
`@@ -27,7 +27,7 @@ dev-dependencies = [`
`27`	`27`	`"pre-commit>=4.0.1",`
`28`	`28`	`"pre-commit-uv>=4.1.4",`
`29`	`29`	`"uv>=0.4.25",`
`30`		`- "jupyterlab==4.3.5",`
	`30`	`+ "jupyterlab==4.3.6",`
`31`	`31`	`"deptry>=0.22.0",`
`32`	`32`	`]`
`33`	`33`
Original file line number	Diff line number	Diff line change
`@@ -378,4 +378,4 @@`
`378`	`378`	`"x": "https://x.com/codegen",`
`379`	`379`	`"linkedin": "https://linkedin.com/company/codegen-dot-com"`
`380`	`380`	`}`
`381`		`-}`
	`381`	`+}`