feat/ollama llm provider

[virinchiv]

Description

Adds Ollama as a built-in LLM provider under pkg/llm/ollama, implementing interfaces.LLMClient alongside the existing providers. Supports both a local Ollama daemon and Ollama Cloud:

• Local — no API key required. llm.BuildConfigKeyless (new, additive) lets the client construct without an APIKey; defaults to http://localhost:11434/v1.
• Ollama Cloud — supplying an API key (llm.WithAPIKey or the OLLAMA_API_KEY env var) auto-switches the default base URL to https://ollama.com/v1. llm.WithBaseURL always overrides, for remote/self-hosted daemons or auth proxies.
• Standalone client using openai-go as OpenAI-compatible transport (no new dependency), following the DeepSeek pattern — the OpenAI adapter is untouched.
• New interfaces.LLMProviderOllama constant, wired into the cmd and examples config factories (provider: ollama / LLM_PROVIDER=ollama).

Type of change

New feature (non-breaking change which adds functionality)

Related issues

Fixes #38

Checklist

• [ Y ] I have run make check
• [ Y ] I have run task examples:all
• [ Y ] I have run make tidy if I added or removed dependencies
• [ Y ] Commit messages follow conventional commits (e.g. feat:, fix:, docs:)
• [ Y ] I have added/updated tests for my changes
• [ Y ] Documentation is updated if needed

[codecov]

Codecov Report

❌ Patch coverage is 67.29858% with 69 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
pkg/llm/ollama/client.go	67.31%	62 Missing and 5 partials ⚠️
pkg/llm/config.go	66.66%	1 Missing and 1 partial ⚠️

📢 Thoughts on this report? Let us know!

[vinodvx]

Changes looks good to me. Thanks for the contribution, Merging now.