### Start Development Server

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/README.md

Installs Mintlify globally and starts the development server with hot reloading from the docs directory.

```bash
npm i -g mintlify
mintlify dev --port 3333
```

--------------------------------

### Combined Setup Commands

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/sandboxes/setup-commands.mdx

A combination of commands to set a Node.js version, install dependencies using npm ci, and run a build script.

```bash
# Or a combination of commands
nvm use 18
npm ci
npm run build
```

--------------------------------

### Available Installation Methods

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

Lists the different methods supported for installing or updating the codegen CLI.

```APIDOC
## InstallMethod Enum

### Description
Represents the various methods by which the codegen CLI can be installed or updated.

### Members

- **PIP**: Installation using pip.
- **PIPX**: Installation using pipx.
- **UV_TOOL**: Installation using uv.
- **HOMEBREW**: Installation using Homebrew.
- **DEVELOPMENT**: Installation from a development source.
- **UNKNOWN**: An unrecognized installation method.
```

--------------------------------

### Available Installation Methods

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

Lists the different installation methods supported by the CLI's update mechanism. Requires importing InstallMethod.

```python
from codegen.cli.commands.update.updater import InstallMethod

methods = [
    InstallMethod.PIP,
    InstallMethod.PIPX,
    InstallMethod.UV_TOOL,
    InstallMethod.HOMEBREW,
    InstallMethod.DEVELOPMENT,
    InstallMethod.UNKNOWN
]
```

--------------------------------

### Install Codegen Package

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/introduction/sdk.mdx

Install the codegen package from PyPI using pip, pipx, or uv.

```bash
# Using pip
pip install codegen
```

```bash
# Using pipx (for CLI usage)
pipx install codegen
```

```bash
# Using uv
uv pip install codegen
```

```bash
# or
uv tool install codegen
```

--------------------------------

### Set Up Development Environment with UV

Source: https://github.com/codegen-sh/codegen/blob/develop/CONTRIBUTING.md

Sets up a Python virtual environment and installs development dependencies using UV. Ensure UV is installed and activated before running these commands.

```bash
uv venv
source .venv/bin/activate
uv sync --dev
```

--------------------------------

### Start Node.js Development Server

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/sandboxes/web-preview.mdx

Use this command to start a Node.js development server using npm. Ensure your project has a `dev` script defined in `package.json`.

```bash
# For a Node.js/npm project
npm run dev
```

--------------------------------

### Install Codegen CLI

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/capabilities/claude-code.mdx

Install the Codegen CLI tool. This is the first step to integrating Claude Code with Codegen.

```bash
uv tool install codegen
```

--------------------------------

### Install Codegen SDK

Source: https://github.com/codegen-sh/codegen/blob/develop/README.md

Install the Codegen SDK using pip, pipx, or uv. Choose the command that best suits your Python environment management.

```bash
pip install codegen
# or
pipx install codegen
# or
uv tool install codegen
```

--------------------------------

### Enhance claude/main.py with Logging

Source: https://github.com/codegen-sh/codegen/blob/develop/QUICK_START_LOGGING.md

Integrate logging into the `_run_claude_interactive` function to record the start, completion, or failure of a Claude session. This example demonstrates logging session-specific details and outcomes.

```python
logger = get_logger(__name__)

def _run_claude_interactive(resolved_org_id: int, no_mcp: bool | None) -> None:
    session_id = generate_session_id()
    
    # ADD: Log session start
    logger.info("Claude session started", extra={
        "operation": "claude.session_start",
        "session_id": session_id[:8],  # Short version for privacy
        "org_id": resolved_org_id
    })
    
    # Your existing code...
    
    try:
        process = subprocess.Popen([claude_path, "--session-id", session_id])
        returncode = process.wait()
        
        # ADD: Log session end
        logger.info("Claude session completed", extra={
            "operation": "claude.session_complete",
            "session_id": session_id[:8],
            "exit_code": returncode,
            "status": "COMPLETE" if returncode == 0 else "ERROR"
        })
        
    except Exception as e:
        # ADD: Log session error
        logger.error("Claude session failed", extra={
            "operation": "claude.session_error",
            "session_id": session_id[:8],
            "error": str(e)
        })
```

--------------------------------

### Setup Python Environment with pyenv

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/sandboxes/setup-commands.mdx

Configure a specific Python version and install project dependencies using pip. This is useful for projects requiring compatibility with older Python versions.

```bash
# Setup with specific Python version for compatibility
pyenv install 3.12.0
pyenv local 3.12.0
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
```

--------------------------------

### Install Codegen Agent SDK

Source: https://github.com/codegen-sh/codegen/blob/develop/src/codegen/agents/README.md

Install the Codegen Agent SDK using pip. Ensure you have the latest version.

```bash
pip install codegen
```

--------------------------------

### Initialize TokenManager and Get Token

Source: https://github.com/codegen-sh/codegen/blob/develop/src/codegen/cli/auth/token_manager.ipynb

Demonstrates how to initialize the TokenManager and retrieve an authentication token. Ensure the TokenManager class is imported.

```python
from codegen.cli.auth.token_manager import TokenManager


token_manager = TokenManager()
print(token_manager.get_token())
```

--------------------------------

### Install Codegen via pipx

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

Use this command to install Codegen using pipx. To update, use the `upgrade` subcommand.

```bash
pipx install codegen
# Updates via: pipx upgrade codegen
```

--------------------------------

### Install Codegen via UV Tool

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

Use this command to install Codegen using the UV tool. To update, use the `--upgrade` flag.

```bash
uv tool install codegen
# Updates via: uv tool install --upgrade codegen
```

--------------------------------

### Install npm Dependencies

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/sandboxes/setup-commands.mdx

Use this command to install project dependencies using npm. Ensure Node.js is available in the environment.

```bash
# Switch to Node.js version 20
nvm use 20

# Install npm dependencies
npm install
```

--------------------------------

### Install pyenv and Configure Python

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/sandboxes/setup-commands.mdx

Install pyenv, add it to the PATH, and configure it to manage Python versions. This is a prerequisite for using pyenv to manage Python environments.

```bash
# Install pyenv
curl https://pyenv.run | bash

# Add pyenv to PATH (for current session)
export PATH="$HOME/.pyenv/bin:$PATH"
eval "$(pyenv init -)"
eval "$(pyenv virtualenv-init -)"

# Install Python 3.12 (or your desired version)
pyenv install 3.12.0

# Set Python 3.12 as the local version for your project
pyenv local 3.12.0

# Create a virtual environment with Python 3.12
python -m venv venv
source venv/bin/activate

# Install your dependencies
pip install -r requirements.txt
```

--------------------------------

### Start Ruby on Rails Development Server

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/sandboxes/web-preview.mdx

Use this command to start a Ruby on Rails development server. It binds to `127.0.0.1` and specifies port 3000 for Codegen's Web Preview.

```bash
# For a Ruby on Rails project
bundle exec rails server -b 127.0.0.1 -p 3000
```

--------------------------------

### Install Codegen via pip

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

Use this command to install Codegen using pip. To update, use the `--upgrade` flag.

```bash
pip install codegen
# Updates via: pip install --upgrade codegen
```

--------------------------------

### Install UV Package Manager on macOS

Source: https://github.com/codegen-sh/codegen/blob/develop/CONTRIBUTING.md

Installs the UV package manager using Homebrew on macOS. For other platforms, refer to the official UV installation documentation.

```bash
brew install uv
```

--------------------------------

### Start Python Django Development Server

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/sandboxes/web-preview.mdx

Use this command to start a Python Django development server. It binds to `127.0.0.1` and listens on port 3000, which is required for Codegen's Web Preview.

```bash
# For a Python/Django project
python manage.py runserver 127.0.0.1:3000
```

--------------------------------

### Manage Python Versions with uv

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/sandboxes/setup-commands.mdx

Use the `uv` package manager to install a specific Python version and create a virtual environment, then install project dependencies.

```bash
# Install Python 3.12 and create a virtual environment
uv venv --python=3.12

# Activate the virtual environment
source .venv/bin/activate

# Install dependencies
uv pip install -r requirements.txt --refresh --upgrade
```

--------------------------------

### Install Codegen via Homebrew (macOS)

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

Use this command to install Codegen using Homebrew on macOS. To update, use the `upgrade` command.

```bash
brew install codegen
# Updates via: brew upgrade codegen
```

--------------------------------

### Example AGENTS.md Rule File

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/settings/repo-rules.mdx

This markdown file demonstrates how to structure backend development rules, including database operations and API design conventions. It's automatically detected by Codegen.

```markdown
# Backend Development Rules

## Database

- Use Prisma for database operations
- Always use transactions for multi-step operations
- Include proper error handling for all database calls

## API Design

- Follow REST conventions
- Use proper HTTP status codes
- Include request/response validation
```

--------------------------------

### Log Operation Start and End

Source: https://github.com/codegen-sh/codegen/blob/develop/QUICK_START_LOGGING.md

Use this pattern to log the start and end of an operation, including relevant input and success status. This is useful for tracking the lifecycle of tasks.

```python
logger = get_logger(__name__)

# At start of function
logger.info("Operation started", extra={
    "operation": "command.subcommand",
    "user_input": relevant_input
})

# At end of function  
logger.info("Operation completed", extra={
    "operation": "command.subcommand",
    "success": True
})
```

--------------------------------

### Manual Codegen MCP Server Setup

Source: https://github.com/codegen-sh/codegen/blob/develop/src/codegen/cli/mcp/README.md

Manually add a new MCP server in the Cursor IDE settings. This involves providing a name, type, and the command to run the Codegen MCP server.

```text
Name: codegen-mcp
Type: Command
Command: uv --directory <path to codegen installation>/codegen-sdk/src/codegen/cli/mcp run server.py
```

--------------------------------

### Slack Thread Example

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/capabilities/interrupts.mdx

Demonstrates how a user can interrupt a Codegen task in a Slack thread to add new requirements. The conversation shows iterative refinement of a user registration form.

```text
User: @codegen create a user registration form
Codegen: I'll create a user registration form! 📝 [working...]

User: Make sure it includes email verification
Codegen: Got it! Adding email verification to the registration form 📧

User: And add password strength requirements
Codegen: Perfect! I'll include password strength validation as well 🔒
```

--------------------------------

### Create Virtual Environment for Older Python

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/sandboxes/setup-commands.mdx

Create a virtual environment using a specific older Python version (e.g., 3.12) and activate it to install compatible packages.

```bash
# Create a virtual environment with a specific Python version
python3.12 -m venv venv_312
source venv_312/bin/activate

# Verify the Python version
python --version

# Install packages that require Python 3.12
pip install argis==2.4.0  # Example package that needs older Python

# Deactivate when done
deactivate
```

--------------------------------

### CI/CD Workflow with Codegen Integration

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/api-reference/github-actions.mdx

This example shows how to integrate Codegen reviews into an existing CI/CD pipeline. The Codegen review job runs only after the tests have passed successfully.

```yaml
name: CI/CD with Codegen

on:
  pull_request:
    types: [opened, synchronize]

jobs:
  tests:
    runs-on: ubuntu-latest
    steps:
      - name: Run tests
        run: npm test

  codegen-review:
    needs: tests  # Only run review if tests pass
    if: success()
    runs-on: ubuntu-latest
    steps:
      # ... Codegen review steps

  deploy:
    needs: [tests, codegen-review]
    if: success() && github.ref == 'refs/heads/main'
    runs-on: ubuntu-latest
    steps:
      - name: Deploy
        run: npm run deploy
```

--------------------------------

### Slack Interrupt Example

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/capabilities/interrupts.mdx

Demonstrates how a user can send an interrupt message to Codegen in Slack by mentioning it. This allows for adding new requirements during an ongoing task.

```text
User: @codegen can you fix the login bug?
Codegen: I'll fix the login bug! 🔧 [starts working]
User: Actually, make sure to also handle the password reset flow
Codegen: Got it! I'll include the password reset flow in my fix 👍
```

--------------------------------

### Troubleshoot update failures

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

If updates fail, try the legacy update method or manually update via pip. Verify your installation path and details using 'which' and 'pip show'.

```bash
codegen update --legacy
```

```bash
pip install --upgrade codegen
```

```bash
which codegen
```

```bash
pip show codegen
```

--------------------------------

### Linear Interrupt Example

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/capabilities/interrupts.mdx

Illustrates how a user can interrupt Codegen in Linear by adding a comment to an issue. This allows for providing additional requirements or clarifications while the agent is working.

```text
Issue: Fix authentication system
Codegen: Working on the authentication fix...
[User adds comment]: "Please also add 2FA support"
Codegen: I see you've added 2FA requirements - incorporating that now!
```

--------------------------------

### List Available Codegen CLI Versions

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

This command displays a list of all available stable versions of the Codegen CLI that can be installed. It helps in identifying specific versions for potential upgrades.

```bash
# List available versions
codegen update --list
```

--------------------------------

### Enhance agent/main.py with Logging

Source: https://github.com/codegen-sh/codegen/blob/develop/QUICK_START_LOGGING.md

Add logging statements to track the start, success, and failure of agent creation operations. This snippet shows how to log operation details and errors using `logger.info` and `logger.error`.

```python
from codegen.shared.logging.get_logger import get_logger
logger = get_logger(__name__)

def create(prompt: str, org_id: int | None = None, ...):
    """Create a new agent run with the given prompt."""
    
    # ADD: Log start
    logger.info("Agent creation started", extra={
        "operation": "agent.create",
        "org_id": org_id,
        "prompt_length": len(prompt)
    })
    
    # Your existing code...
    try:
        response = requests.post(url, headers=headers, json=payload)
        agent_run_data = response.json()
        
        # ADD: Log success  
        logger.info("Agent created successfully", extra={
            "operation": "agent.create",
            "agent_run_id": agent_run_data.get("id"),
            "status": agent_run_data.get("status")
        })
        
    except requests.RequestException as e:
        # ADD: Log error
        logger.error("Agent creation failed", extra={
            "operation": "agent.create", 
            "error_type": "api_error",
            "error": str(e)
        })
        # Your existing error handling...
```

--------------------------------

### Initialize and Run Agent with Python SDK

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/introduction/sdk.mdx

Initialize the Agent with your organization ID and API token. Then, run an agent with a prompt and check its status and result.

```python
from codegen import Agent

# Initialize the Agent with your organization ID and API token
agent = Agent(org_id="...", token="...")

# Run an agent with a prompt
task = agent.run(prompt="Leave a review on PR #123")

# Check the initial status
print(task.status)

# Refresh the task to get updated status (tasks can take time)
task.refresh()

if task.status == "completed":
    print(task.result)  # Result often contains code, summaries, or links
```

--------------------------------

### Initialize CodegenSession

Source: https://github.com/codegen-sh/codegen/blob/develop/src/codegen/cli/auth/session.ipynb

Create a session with the current directory as the repository path. Inspects session properties like repo_path, config, and existing session status.

```python
from pathlib import Path
from codegen.cli.auth.session import CodegenSession


# Create a session with the current directory as repo_path
session = CodegenSession(repo_path=Path("."))
print(f"Session: {session}")
print(f"Repo path: {session.repo_path}")
print(f"Config: {session.config}")
print(f"Existing session: {session.existing}")
```

--------------------------------

### Load .env.prod for ENV=prod

Source: https://github.com/codegen-sh/codegen/blob/develop/src/codegen/cli/env/global_env.ipynb

Sets the ENV environment variable to 'prod' and then initializes GlobalEnv, printing the ALGOLIA_SEARCH_KEY. This assumes .env.prod exists and contains the key.

```python
# test: ENV=prod loads .env.prod
import os

os.environ["ENV"] = "prod"
from codegen.cli.env.global_env import GlobalEnv

global_env = GlobalEnv()
print(global_env.ALGOLIA_SEARCH_KEY)
```

--------------------------------

### Initialize and Run Agent

Source: https://github.com/codegen-sh/codegen/blob/develop/README.md

Initialize the Agent with your organization ID and API token, then run a task with a prompt. Refresh the task to check its status and access the result upon completion.

```python
from codegen.agents.agent import Agent

# Initialize the Agent with your organization ID and API token
agent = Agent(
    org_id="YOUR_ORG_ID",  # Find this at codegen.com/token
    token="YOUR_API_TOKEN",  # Get this from codegen.com/token
    # base_url="https://codegen-sh-rest-api.modal.run",  # Optional - defaults to production
)

# Run an agent with a prompt
task = agent.run(prompt="Implement a new feature to sort users by last login.")

# Check the initial status
print(task.status)

# Refresh the task to get updated status (tasks can take time)
task.refresh()

# Check the updated status
print(task.status)

# Once task is complete, you can access the result
if task.status == "completed":
    print(task.result)  # Result often contains code, summaries, or links
```

--------------------------------

### Initialize and Run Agent

Source: https://github.com/codegen-sh/codegen/blob/develop/src/codegen/agents/README.md

Initialize the Agent with organization ID and API token, then run a task with a prompt. Check and refresh task status, and access the result upon completion.

```python
from codegen.agents.agent import Agent

# Initialize the Agent with your organization ID and API token
agent = Agent(
    org_id="11",  # Your organization ID
    token="your_api_token_here",  # Your API authentication token
    base_url="https://codegen-sh-rest-api.modal.run",  # Optional - defaults to this URL
)

# Run an agent with a prompt
task = agent.run(prompt="Which github repos can you currently access?")

# Check the initial status
print(task.status)  # Returns the current status of the task (e.g., "queued", "in_progress", etc.)

# Refresh the task to get updated status
task.refresh()

# Check the updated status
print(task.status)

# Once task is complete, you can access the result
if task.status == "completed":
    print(task.result)
```

--------------------------------

### Update Development Installation

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

For development installs, update Codegen by pulling the latest changes from the main branch and reinstalling in editable mode.

```bash
git pull origin main
pip install -e .
```

--------------------------------

### Create an Agent Run

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/api-reference/overview.mdx

Initiates an agent run with a specific prompt and repository ID. Ensure you replace placeholders with your actual API key, organization ID, and repository ID.

```bash
curl -X POST "https://api.codegen.com/v1/organizations/{org_id}/agent/run" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Add error handling to the user authentication function",
    "repo_id": 123
  }'
```

--------------------------------

### Agent Class Initialization

Source: https://github.com/codegen-sh/codegen/blob/develop/src/codegen/agents/README.md

Instantiate the Agent class with required token and optional organization ID and base URL.

```python
Agent(token: str, org_id: Optional[int] = None, base_url: Optional[str] = CODEGEN_BASE_API_URL)
```

--------------------------------

### Update Codegen CLI to a Specific Version

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

Install a particular version of the Codegen CLI by specifying the version number. This is useful for rolling back or installing a known stable release.

```bash
# Update to specific version
codegen update --version 1.2.3
```

--------------------------------

### Linear Issue Example

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/capabilities/interrupts.mdx

Illustrates how a user can add comments to a Linear issue to interrupt and modify a Codegen task. This example shows the iterative process of implementing search functionality with added filters and sorting.

```text
Linear Issue: "Implement search functionality"
Codegen: Working on search functionality...

[User adds comment]: "Please include filters for date and category"
Codegen: I see you've added filter requirements - implementing date and category filters now!

[User adds comment]: "Also add sorting options"
Codegen: Adding sorting options to the search as well! 📊
```

--------------------------------

### Authenticate with Python SDK

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/api-reference/authentication.mdx

Initialize the Python SDK with your organization ID and API token for automatic authentication.

```python
from codegen import Agent

# Initialize with your credentials
agent = Agent(org_id="YOUR_ORG_ID", token="YOUR_API_TOKEN")

# The SDK handles authentication automatically
task = agent.run(prompt="Fix the bug in user authentication")
```

--------------------------------

### Update Codegen CLI

Source: https://github.com/codegen-sh/codegen/blob/develop/README.md

Manage Codegen CLI versions. Update to the latest version, check for available updates, or specify a version for installation.

```bash
# Update to the latest version
codegen update

# Check for available updates
codegen update --check

# Update to a specific version
codegen update --version 1.2.3
```

--------------------------------

### New Version Notification

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

This is an example of the notification displayed when a new version of the Codegen CLI is available. It prompts the user to run the update command.

```text
ℹ️  A new version of Codegen CLI is available: 1.2.3
Run 'codegen update' to upgrade
```

--------------------------------

### Run Claude with Telemetry

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/capabilities/claude-code.mdx

Execute Claude through the Codegen CLI to enable full telemetry and cloud logging for your session. Ensure Claude is installed locally.

```bash
codegen claude "Help me refactor this authentication module"
```

--------------------------------

### Validate RunCodemodOutput with Correct Data

Source: https://github.com/codegen-sh/codegen/blob/develop/src/codegen/cli/utils/schema.ipynb

Use `model_validate` to validate a dictionary against the `RunCodemodOutput` schema. This example shows successful validation with correct data types.

```python
# with model that should validate
from codegen.cli.api.schemas import RunCodemodOutput


res = RunCodemodOutput.model_validate(
    {
        "success": True,
        "web_link": "https://chadcode.sh/codemod/13264/code/21435/run/28349/playground/diff",
        "logs": "",
        "observation": 'diff --git a/codegen-backend/app/utils/slack/interactive/handlers/BaseSlackActionHandler.py b/codegen-backend/app/utils/slack/interactive/handlers/BaseSlackActionHandler.py\nindex 2dce963196b418caad011d175fb3110e03a8fe73..77c430a5acfb1613ac42c5712cc2859f31d7d773 100644\n--- a/codegen-backend/app/utils/slack/interactive/handlers/BaseSlackActionHandler.py\n+++ b/codegen-backend/app/utils/slack/interactive/handlers/BaseSlackActionHandler.py\n@@ -1,12 +1,1 @@\n-from sqlalchemy.orm import Session\n-\n-\n-class BaseSlackInteractiveActionHandler:\n-    db: Session\n-\n-    def __init__(self, db: Session) -> None:\n-        self.db = db\n-\n-    # TODO: convert the message information into a shared schema\n-    def process_action(self, action_payload: str, channel_id: str, thread_ts: str):\n-        raise NotImplementedError(f"process_action not implemented for {self.__class__.__name__}!")\n+update\n\ No newline at end of file\n',
    },
)
print(res)
```

--------------------------------

### Initialize and Analyze Codebase

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/introduction/how-it-works.mdx

Initialize a Codebase object to perform static analysis on a project directory. Access pre-computed symbol dependencies and usages instantly.

```python
# Initialize and analyze the codebase
from codegen import Codebase
codebase = Codebase("./")

# Access pre-computed relationships
function = codebase.get_symbol("process_data")
print(f"Dependencies: {function.dependencies}")  # Instant lookup
print(f"Usages: {function.usages}")  # No parsing needed
```

--------------------------------

### Resolve permission errors during update

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

For permission errors, consider using pip's user installation or pipx for upgrades. Avoid using sudo if possible.

```bash
pip install --user --upgrade codegen
```

```bash
pipx upgrade codegen
```

--------------------------------

### Check for Codegen CLI Updates

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

Run this command to check if a new version of the Codegen CLI is available without initiating an installation. It will notify you if an update is found.

```bash
# Check for available updates without installing
codegen update --check
```

--------------------------------

### Import and Initialize Logger

Source: https://github.com/codegen-sh/codegen/blob/develop/QUICK_START_LOGGING.md

Import the `get_logger` function and initialize the logger for the current module. This is the first step to enable structured logging.

```python
from codegen.shared.logging.get_logger import get_logger

logger = get_logger(__name__)
```

--------------------------------

### Downgrade codegen to a specific version

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/self-update.md

Use the update command with a specific version to revert to a previous release. Alternatively, use your package manager directly for manual installation.

```bash
codegen update --version 1.2.2
```

```bash
pip install codegen==1.2.2
```

```bash
pipx install codegen==1.2.2 --force
```

```bash
uv tool install codegen==1.2.2 --upgrade
```

--------------------------------

### Agent run() Method

Source: https://github.com/codegen-sh/codegen/blob/develop/src/codegen/agents/README.md

Execute an agent task using the run method with a prompt string.

```python
run(prompt: str) -> AgentTask
```

--------------------------------

### Agent Class Initialization

Source: https://github.com/codegen-sh/codegen/blob/develop/src/codegen/agents/README.md

Initializes the Agent client with your organization ID and API token. The base URL can also be optionally specified.

```APIDOC
## Agent Class

```python
Agent(token: str, org_id: Optional[int] = None, base_url: Optional[str] = CODEGEN_BASE_API_URL)
```

### Parameters

- `token` (required): Your API authentication token
- `org_id` (optional): Your organization ID. If not provided, defaults to environment variable `CODEGEN_ORG_ID` or "1"
- `base_url` (optional): API base URL. Defaults to "https://codegen-sh-rest-api.modal.run"
```

--------------------------------

### Navigate to Image Cache Settings

Source: https://github.com/codegen-sh/codegen/blob/develop/docs/sandboxes/image-snapshots.mdx

Access your repository's image cache settings page to manage snapshot configurations.

```bash
https://codegen.com/repos/{repoName}/image-cache
```