What does this PR do?

Registers Ollama Cloud (ollama.com/v1) as a recognized provider in the URL-to-provider and models.dev provider mappings. Without this, all Ollama Cloud models silently default to 128K context length instead of their actual capacity.

The existing get_model_context_length() resolution chain (step 5: provider-aware models.dev lookup) already handles this correctly for every other cloud provider — Ollama Cloud was simply missing from the two mapping dicts that feed it.

Related Issue

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)

Changes Made

• agent/model_metadata.py: Added "ollama.com": "ollama-cloud" to _URL_TO_PROVIDER dict — enables _infer_provider_from_url() to recognize Ollama Cloud base URLs.
• agent/models_dev.py: Added "ollama-cloud": "ollama-cloud" to PROVIDER_TO_MODELS_DEV dict — enables lookup_models_dev_context() to resolve model context lengths from the models.dev cache.

Impact

Affects all users on Ollama Cloud (Free, Pro, Max tiers) who use https://ollama.com/v1 as their base URL. Before this fix, every model on that endpoint reported 128K context regardless of actual capacity:

This caused the status bar to display wrong values and — more critically — could lead to premature context compression or missed compression triggers.

How to Test

1. Configure Ollama Cloud: set OLLAMA_API_KEY and use base_url: https://ollama.com/v1
2. Switch to any Ollama Cloud model (e.g. /model qwen3.5:397b --provider custom)
3. Check status bar — should show ~256K context, not 128K
4. Run existing tests: pytest tests/agent/test_model_metadata.py tests/agent/test_models_dev.py -v

Checklist

Code

• I've read the Contributing Guide
• My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
• I searched for existing PRs to make sure this isn't a duplicate
• My PR contains only changes related to this fix/feature (no unrelated commits)
• I've run pytest tests/ -q and all tests pass
• I've added tests for my changes (required for bug fixes, strongly encouraged for features) — The fix adds dict entries consumed by existing tested code paths. Adding a test for a specific URL→provider mapping entry would test the data, not the logic.
• I've tested on my platform: Ubuntu 24.04 (WSL2)

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — N/A (no new config keys or user-facing API changes)
• I've updated cli-config.yaml.example if I added/changed config keys — N/A
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — N/A
• I've considered cross-platform impact (Windows, macOS) per the compatibility guide — N/A (pure dict additions, no platform-specific code)
• I've updated tool descriptions/schemas if I changed tool behavior — N/A