feat(inference)!: replace managed routes with providers

[varshaprasad96]

Summary

Remove the managed inference-route stack now that provider v2 supplies native provider endpoints, and fold the next service/settings CLI module extraction into the same clean replacement branch. This keeps the #2304 refactor aligned with the architecture established by #3172.

Related Issue

Closes #3172
Relates to #2304
Supersedes #3188

Changes

• Remove the managed inference CLI, gRPC API, router crate, supervisor interception path, SDK clients, generated bindings, and obsolete examples/tests.
• Add SQLite and PostgreSQL migrations that remove legacy inference-route objects while preserving all other stored objects.
• Keep inference access provider-native, including provider type normalization and custom endpoint-bearing profiles, and document the upgrade path.
• Make the built-in AWS Bedrock profile functional through regional runtime endpoints and proxy-side SigV4 signing.
• Preserve OpenAI credential binding for the canonical /v1 base URL, correct provider attach and custom endpoint guidance, and remove stale managed-inference references.
• Add Docker-backed E2E coverage for native OpenAI-compatible and Anthropic-compatible endpoints and the removal of inference.local.
• Extract service and settings command implementations from the CLI run module into dedicated command modules.
• Update architecture, published docs, man pages, agent skills, Go/Python SDK surfaces, and repository metadata.

Testing

• mise run pre-commit passes
• Unit tests added/updated
• Focused Docker-backed provider-native inference E2E passes
• mise run ci passes
• mise run go:ci passes
• Focused Python SDK and wheel tests pass (137 tests)
• Full mise run e2e not run locally; the affected Docker-backed scenario passed

Checklist

• Follows Conventional Commits
• Commits are signed off (DCO)
• Architecture docs updated (if applicable)

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.