[fix] Resolve N1N model strings - #7948

Summary

Adds the missing n1n provider mapping to agno.models.utils.get_model() so model-string paths such as Agent(model="n1n:gpt-4o") resolve to the existing N1N provider.

Related to #5036.

Type of change

• Bug fix
• New feature
• Breaking change
• Improvement
• Model update
• Other:

Checklist

• Code complies with style guidelines
• Ran format/validation scripts (./scripts/format.sh and ./scripts/validate.sh)
• Self-review completed
• Documentation updated (comments, docstrings)
• Examples and guides: Relevant cookbook examples have been included or updated (if applicable)
• Tested in clean environment
• Tests added/updated (if applicable)

Duplicate and AI-Generated PR Check

• I have searched existing open pull requests and confirmed that no other PR already addresses this issue
• If a similar PR exists, I have explained below why this PR is a better approach
• Check if this PR was entirely AI-generated (by Copilot, Claude Code, Cursor, etc.)

Additional Notes

Focused validation run from libs/agno using a minimal local venv because uv run --extra dev pytest tests/unit/utils/test_model_string.py could not resolve all package extras in this environment (brave-search and a2a-sdk require incompatible httpx versions across supported Python splits).

Validation passed:

• TMPDIR=/home/ubuntu/gh-pr/agno-worker-next/.tmp .venv/bin/python -m pytest -p no:cacheprovider tests/unit/utils/test_model_string.py
• TMPDIR=/home/ubuntu/gh-pr/agno-worker-next/.tmp .venv/bin/python -m pytest -p no:cacheprovider tests/unit/models/test_n1n.py
• .venv/bin/ruff format --check agno/models/utils.py tests/unit/utils/test_model_string.py
• .venv/bin/ruff check agno/models/utils.py tests/unit/utils/test_model_string.py
• git diff --check