Add per-sub-agent provider routing

[heyparth1]

This PR introduces explicit per-role/type provider routing for sub-agents, allowing different sub-agents to run on different providers (e.g., LM Studio for quick edits, DeepSeek for complex reasoning) within the same session.

Changes:

• Adds the [subagents.routes.<role>] configuration table to pin a sub-agent role or type to a specific provider and an optional model.
• Normalizes route keys to lowercase and trims whitespace from provider and model names.
• Passes the routing configuration to the sub-agent runtime, so matching sub-agents spawn on the assigned provider instead of inheriting the parent session's active provider.
• Adds unit tests for parsing and normalizing the new configuration.

Closes #3965

[github-actions]

Thanks @heyparth1 for taking the time to contribute.

This repository is observing a maintainer-managed PR intake gate in dry-run mode, so this pull request is staying open. This note helps maintainers prepare the allowlist before any enforcement is considered.

Please read CONTRIBUTING.md for the expected contribution shape. A maintainer can grant recurring PR access by commenting /lgtm on a pull request.

[heyparth1]

Thanks @JayBeest! Yes, this pins any sub-agent to any configured provider/model (not just local vs cloud); smart/keyword routing is a good follow-up but out of scope here.