Add ollama-local support to Microbots

[Copilot]

Adds Ollama Local as an LLM provider for Microbots, enabling locally-hosted language models alongside Azure OpenAI.

Changes

New OllamaLocal provider (src/microbots/llm/ollama_local.py)

• Implements LLMInterface for local Ollama server communication
• JSON extraction handling for responses with extra text

Test infrastructure (test/llm/)

• Pytest fixtures for Ollama server lifecycle management
• Unit tests with mocked responses
• Integration tests marked with @pytest.mark.ollama_local

Usage

from microbots import MicroBot

bot = MicroBot(
    model="ollama-local/codellama:latest",
    folder_to_mount="/path/to/repo"
)

Environment variables: LOCAL_MODEL_NAME, LOCAL_MODEL_PORT (default: 11434)

Code review fixes

• Grammar/capitalization corrections in comments and prompts
• Fixed incorrect default value {} → "" for missing response handling
• Removed unused imports
• Simplified test assertions

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.