[Docs] Add self-hosted inference provider guides

[roomote-roomote]

Opened on behalf of Bruno Bergher. Follow up by mentioning @roomote-roomote, in the web UI, or in Slack.

Related issue

No linked issue.

Why this PR exists

• I am a maintainer / this is internal Roomote work

What changed

Added public inference-provider documentation for Ollama, vLLM, and LiteLLM.
The guides cover self-hosted endpoint reachability, Docker host networking,
vLLM serving and security flags, LiteLLM proxy keys and cost controls, and
provider-specific security practices. The Models and Inference navigation now
links to each guide.

How it was tested

Ran mise exec -- pnpm --filter @roomote/docs check successfully.

Checklist

• The PR title follows the repo convention: [Fix], [Feat], [Improve], [Refactor], [Docs], or [Chore] followed by a user-facing description
• This PR is small and scoped to one change
• pnpm lint and pnpm check-types pass locally
• I added tests or included a clear manual validation note above
• I removed secrets, tokens, private keys, and customer data from code, logs, and screenshots
• If this change should appear in the changelog, I ran pnpm changeset

[roomote-roomote]

1 issue outstanding. See task

• apps/docs/providers/inference/litellm.mdx:17-19 (also ollama.mdx:25-29 and vllm.mdx:50-54): the guides direct operators to add Ollama or an OpenAI-compatible provider and enter a base URL in Settings > Models, but that UI only exposes SETUP_MODEL_PROVIDER_CATALOG; it has no Ollama/generic provider entry and no endpoint field. These setup flows therefore cannot be completed on the documented product. Add the required custom-provider support or document a configuration path that exists in the current release.

_{Reviewed 612a385}