Add documentation for LLM providers (Anthropic, OpenAI, Ollama)

docs/providers/_category_.json

@@ -0,0 +1,8 @@
+{
+  "label": "Providers",
+  "position": 4,
+  "link": {
+    "type": "doc",
+    "id": "providers/index"
+  }
+}

docs/providers/anthropic.md

@@ -0,0 +1,70 @@
+---
+sidebar_position: 2
+---
+
+# Anthropic (Claude)
+
+[Anthropic](https://www.anthropic.com/) is the company behind the Claude family of large language models, known for their strong reasoning capabilities, long context windows, and robust tool-calling support.
+
+## Setup
+
+To use Claude models with MyCoder, you need an Anthropic API key:
+
+1. Create an account at [Anthropic Console](https://console.anthropic.com/)
+2. Navigate to the API Keys section and create a new API key
+3. Set the API key as an environment variable or in your configuration file
+
+### Environment Variables
+
+You can set the Anthropic API key as an environment variable:
+
+```bash
+export ANTHROPIC_API_KEY=your_api_key_here
+```
+
+### Configuration
+
+Configure MyCoder to use Anthropic's Claude in your `mycoder.config.js` file:
+
+```javascript
+export default {
+  // Provider selection
+  provider: 'anthropic',
+  model: 'claude-3-7-sonnet-20250219',
+
+  // Optional: Set API key directly (environment variable is preferred)
+  // anthropicApiKey: 'your_api_key_here',
+
+  // Other MyCoder settings
+  maxTokens: 4096,
+  temperature: 0.7,
+  // ...
+};
+```
+
+## Supported Models
+
+Anthropic offers several Claude models with different capabilities and price points:
+
+- `claude-3-7-sonnet-20250219` (recommended) - Strong reasoning and tool-calling capabilities with 200K context
+- `claude-3-5-sonnet-20240620` - Balanced performance and cost with 200K context
+- `claude-3-opus-20240229` - Most capable model with 200K context
+- `claude-3-haiku-20240307` - Fastest and most cost-effective with 200K context
+
+## Best Practices
+
+- Claude models excel at complex reasoning tasks and multi-step planning
+- They have strong tool-calling capabilities, making them ideal for MyCoder workflows
+- Claude models have a 200K token context window, allowing for large codebases to be processed
+- For cost-sensitive applications, consider using Claude Haiku for simpler tasks
+
+## Troubleshooting
+
+If you encounter issues with Anthropic's Claude:
+
+- Verify your API key is correct and has sufficient quota
+- Check that you're using a supported model name
+- For tool-calling issues, ensure your functions are properly formatted
+- Monitor your token usage to avoid unexpected costs
+
+For more information, visit the [Anthropic Documentation](https://docs.anthropic.com/).

docs/providers/index.mdx

@@ -0,0 +1,54 @@
+---
+sidebar_position: 1
+---
+
+# LLM Providers
+
+MyCoder supports multiple Language Model (LLM) providers, giving you flexibility to choose the best solution for your needs. This section documents how to configure and use the various supported providers.
+
+## Supported Providers
+
+MyCoder currently supports the following LLM providers:
+
+- [**Anthropic**](./anthropic.md) - Claude models from Anthropic
+- [**OpenAI**](./openai.md) - GPT models from OpenAI
+- [**Ollama**](./ollama.md) - Self-hosted open-source models via Ollama
+
+## Configuring Providers
+
+Each provider has its own specific configuration requirements, typically involving:
+
+1. Setting API keys or connection details
+2. Selecting a specific model
+3. Configuring provider-specific parameters
+
+You can configure the provider in your `mycoder.config.js` file. Here's a basic example:
+
+```javascript
+export default {
+  // Provider selection
+  provider: 'anthropic',
+  model: 'claude-3-7-sonnet-20250219',
+
+  // Other MyCoder settings
+  // ...
+};
+```
+
+## Provider Selection Considerations
+
+When choosing which provider to use, consider:
+
+- **Performance**: Different providers have different capabilities and performance characteristics
+- **Cost**: Pricing varies significantly between providers
+- **Features**: Some models have better support for specific features like tool calling
+- **Availability**: Self-hosted options like Ollama provide more control but require setup
+- **Privacy**: Self-hosted options may offer better privacy for sensitive work
+
+## Provider-Specific Documentation
+
+For detailed instructions on setting up each provider, see the provider-specific pages:
+
+- [Anthropic Configuration](./anthropic.md)
+- [OpenAI Configuration](./openai.md)
+- [Ollama Configuration](./ollama.md)

docs/providers/ollama.md

@@ -0,0 +1,107 @@
+---
+sidebar_position: 4
+---
+
+# Ollama
+
+[Ollama](https://ollama.ai/) is a platform for running open-source large language models locally. It allows you to run various models on your own hardware, providing privacy and control over your AI interactions.
+
+## Setup
+
+To use Ollama with MyCoder:
+
+1. Install Ollama from [ollama.ai](https://ollama.ai/)
+2. Start the Ollama service
+3. Pull a model that supports tool calling
+4. Configure MyCoder to use Ollama
+
+### Installing Ollama
+
+Follow the installation instructions on the [Ollama website](https://ollama.ai/) for your operating system.
+
+For macOS:
+```bash
+curl -fsSL https://ollama.ai/install.sh | sh
+```
+
+For Linux:
+```bash
+curl -fsSL https://ollama.ai/install.sh | sh
+```
+
+For Windows, download the installer from the Ollama website.
+
+### Pulling a Model
+
+After installing Ollama, you need to pull a model that supports tool calling. **Important: Most Ollama models do not support tool calling**, which is required for MyCoder.
+
+A recommended model that supports tool calling is:
+
+```bash
+ollama pull medragondot/Sky-T1-32B-Preview:latest
+```
+
+### Environment Variables
+
+You can set the Ollama base URL as an environment variable (defaults to http://localhost:11434 if not set):
+
+```bash
+export OLLAMA_BASE_URL=http://localhost:11434
+```
+
+### Configuration
+
+Configure MyCoder to use Ollama in your `mycoder.config.js` file:
+
+```javascript
+export default {
+  // Provider selection
+  provider: 'ollama',
+  model: 'medragondot/Sky-T1-32B-Preview:latest',
+
+  // Optional: Custom base URL (defaults to http://localhost:11434)
+  // ollamaBaseUrl: 'http://localhost:11434',
+
+  // Other MyCoder settings
+  maxTokens: 4096,
+  temperature: 0.7,
+  // ...
+};
+```
+
+## Tool Calling Support
+
+**Important**: For MyCoder to function properly, the Ollama model must support tool calling (function calling). Most open-source models available through Ollama **do not** support this feature yet.
+
+Confirmed models with tool calling support:
+
+- `medragondot/Sky-T1-32B-Preview:latest` - Recommended for MyCoder
+
+If using other models, verify their tool calling capabilities before attempting to use them with MyCoder.
+
+## Hardware Requirements
+
+Running large language models locally requires significant hardware resources:
+
+- Minimum 16GB RAM (32GB+ recommended)
+- GPU with at least 8GB VRAM for optimal performance
+- SSD storage for model files (models can be 5-20GB each)
+
+## Best Practices
+
+- Start with smaller models if you have limited hardware
+- Ensure your model supports tool calling before using with MyCoder
+- Run on a machine with a dedicated GPU for better performance
+- Consider using a cloud provider's API for resource-intensive tasks if local hardware is insufficient
+
+## Troubleshooting
+
+If you encounter issues with Ollama:
+
+- Verify the Ollama service is running (`ollama serve`)
+- Check that you've pulled the correct model
+- Ensure the model supports tool calling
+- Verify your hardware meets the minimum requirements
+- Check Ollama logs for specific error messages
+
+For more information, visit the [Ollama Documentation](https://github.com/ollama/ollama/tree/main/docs).

docs/providers/openai.md

@@ -0,0 +1,77 @@
+---
+sidebar_position: 3
+---
+
+# OpenAI
+
+[OpenAI](https://openai.com/) provides a suite of powerful language models, including the GPT family, which offer strong capabilities for code generation, analysis, and tool use.
+
+## Setup
+
+To use OpenAI models with MyCoder, you need an OpenAI API key:
+
+1. Create an account at [OpenAI Platform](https://platform.openai.com/)
+2. Navigate to the API Keys section and create a new API key
+3. Set the API key as an environment variable or in your configuration file
+
+### Environment Variables
+
+You can set the OpenAI API key as an environment variable:
+
+```bash
+export OPENAI_API_KEY=your_api_key_here
+```
+
+Optionally, if you're using an organization-based account:
+
+```bash
+export OPENAI_ORGANIZATION=your_organization_id
+```
+
+### Configuration
+
+Configure MyCoder to use OpenAI in your `mycoder.config.js` file:
+
+```javascript
+export default {
+  // Provider selection
+  provider: 'openai',
+  model: 'gpt-4o',
+
+  // Optional: Set API key directly (environment variable is preferred)
+  // openaiApiKey: 'your_api_key_here',
+  // openaiOrganization: 'your_organization_id',
+
+  // Other MyCoder settings
+  maxTokens: 4096,
+  temperature: 0.7,
+  // ...
+};
+```
+
+## Supported Models
+
+OpenAI offers several models with different capabilities:
+
+- `gpt-4o` (recommended) - Latest model with strong reasoning and tool-calling capabilities
+- `gpt-4-turbo` - Strong performance with 128K context window
+- `gpt-4` - Original GPT-4 model with 8K context window
+- `gpt-3.5-turbo` - More affordable option for simpler tasks
+
+## Best Practices
+
+- GPT-4o provides the best balance of performance and cost for most MyCoder tasks
+- For complex programming tasks, use GPT-4 models rather than GPT-3.5
+- The tool-calling capabilities in GPT-4o are particularly strong for MyCoder workflows
+- Use the JSON response format for structured outputs when needed
+
+## Troubleshooting
+
+If you encounter issues with OpenAI:
+
+- Verify your API key is correct and has sufficient quota
+- Check that you're using a supported model name
+- For rate limit issues, implement exponential backoff in your requests
+- Monitor your token usage to avoid unexpected costs
+
+For more information, visit the [OpenAI Documentation](https://platform.openai.com/docs/).