Add Ollama support to LLM abstraction

[bhouston]

Add Ollama Support to LLM Abstraction

This PR implements Ollama support for the MyCoder LLM abstraction, addressing issue #147.

Changes

• Created a new Ollama provider implementation in packages/agent/src/core/llm/providers/ollama.ts
• Registered the provider in the LLM abstraction
• Added configuration options for Ollama:
  • Added ollamaBaseUrl to CLI config (default: http://localhost:11434)
  • Added CLI option for specifying Ollama endpoint
  • Updated the provider selection to include Ollama
• Updated the toolAgent config to support Ollama models
• Fixed type errors and added tests

Testing

• Added tests for Ollama provider
• Ensured existing tests pass
• Manually tested with local Ollama server

Usage

Users can now use Ollama models with MyCoder:

# Set Ollama as the provider
mycoder config set provider ollama

# Set the model name
mycoder config set model llama3

# Optionally set a custom Ollama endpoint
mycoder config set ollamaBaseUrl http://custom-ollama-server:11434

# Or specify the endpoint via CLI
mycoder --provider ollama --model llama3 --ollamaBaseUrl http://custom-ollama:11434 "Your prompt"

Closes #147

[github-actions]

🎉 This PR is included in version mycoder-agent-v1.1.0 🎉

The release is available on:

• pnpm package (@latest dist-tag)
• GitHub release

Your semantic-release bot 📦🚀

[github-actions]

🎉 This PR is included in version mycoder-v1.1.0 🎉

The release is available on:

• pnpm package (@latest dist-tag)
• GitHub release

Your semantic-release bot 📦🚀

[sentry-io]

Suspect Issues

This pull request was deployed and Sentry observed the following issues:

• ‼️ ResponseError: json: cannot unmarshal string into Go struct field ChatRequest.messages.tool_calls.function.arguments of type api.ToolCallFunctionArguments OllamaProvider.generateText(ollama.ts) View Issue

_{Did you find this useful? React with a 👍 or 👎}