feat(llm): add built-in Ollama Cloud provider preset

[chethanuk]

Description

Adds a built-in ollama-cloud provider preset to the registry in internal/llm/providers.go, so Ollama Cloud can be selected directly instead of hand-configured as a custom provider.

The preset uses the OpenAI-compatible protocol against https://ollama.com/v1, reading the API key from OLLAMA_API_KEY (sent as Authorization: Bearer <key>, the shared default for OpenAI-protocol entries — no per-provider AuthHeader). It ships two models, gpt-oss:120b and gpt-oss:20b. The base URL, env var, and model naming match Ollama Cloud's documented OpenAI-compatible endpoint.

Opened against my own fork first as a staging/review step.

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Refactoring (no functional changes)
• Documentation update
• CI / Build / Tooling

How Has This Been Tested?

gofmt -l reports no diffs, go vet ./internal/llm/ is clean, and go test ./internal/llm/ passes (176 tests). Coverage includes the existing TestListProviders_Order (updated for the new sorted position) and a new TestLookupProvider_OllamaCloudDetails that pins Protocol, BaseURL, EnvVar, empty AuthHeader, and each model name individually.

Whether Ollama Cloud's OpenAI endpoint reliably supports the tool-calls flow that ocr review needs is a runtime/e2e concern, out of scope for this preset addition.

• make test passes locally
• Manual testing (describe below)

Checklist

• My code follows the project's coding style (go fmt, go vet)
• I have performed a self-review of my code
• I have added tests that prove my fix is effective or my feature works
• New and existing unit tests pass locally with my changes
• I have updated the documentation accordingly (if applicable)
• I have signed the CLA

Related Issues

Closes #305

[CLAassistant]

All committers have signed the CLA.

[github-actions]

🔍 OpenCodeReview found 1 issue(s) in this PR.

• ✅ 1 posted as inline comment(s)
• 📝 0 posted as summary

[github-actions]

Potential issue: The BaseURL https://ollama.com/v1 does not appear to be a documented or verified Ollama Cloud API endpoint. Ollama is primarily known as a local LLM runtime (default http://localhost:11434), and there is no well-known public cloud API at this URL. Similarly, the model names gpt-oss:120b and gpt-oss:20b do not correspond to any known publicly available models.

Please verify:

1. Is this BaseURL correct and currently active?
2. Are these model names accurate for this provider?

If this is a placeholder or speculative entry, consider adding a comment or marking it accordingly to avoid confusion.