feat: convert models API to use a FastAPI router

[nathan-weinberg]

What does this PR do?

Migrate from @webmethod decorators to FastAPI router pattern

Closes #4347

[github-actions]

✱ Stainless preview builds

This PR will update the llama-stack-client SDKs with the following commit message.

feat: convert models API to use a FastAPI router

Edit this comment to update it. It will appear in the SDK's changelogs.

✅ llama-stack-client-kotlin studio · code · diff

Your SDK built successfully.
generate ⚠️ → lint ✅ → test ❗

✅ llama-stack-client-node studio · code · diff

Your SDK built successfully.
generate ⚠️ → build ✅ → lint ✅ → test ✅

npm install https://pkg.stainless.com/s/llama-stack-client-node/6328b748f9015433f07fcf762cdf507031fff186/dist.tar.gz

⚡ llama-stack-client-python studio · conflict

There was a conflict between your custom code and your generated changes.
You don't need to resolve this conflict right now, but you will need to resolve it for your changes to be released to your users. Read more about why this happened here.

⚡ llama-stack-client-go studio · conflict

There was a conflict between your custom code and your generated changes.
You don't need to resolve this conflict right now, but you will need to resolve it for your changes to be released to your users. Read more about why this happened here.

---

This comment is auto-generated by GitHub Actions and is automatically kept up to date as you push.
Last updated: 2025-12-20 01:49:39 UTC

[gyliu513]

Hi @nathan-weinberg , are you going to update unit test at https://github.com/llamastack/llama-stack/tree/main/tests/unit in follow up PR? Thanks

[nathan-weinberg]

Hi @nathan-weinberg , are you going to update unit test at https://github.com/llamastack/llama-stack/tree/main/tests/unit in follow up PR? Thanks

What needs updating?

[gyliu513]

@nathan-weinberg For example, in https://github.com/llamastack/llama-stack/tree/main/tests/unit/core/routers
there aren’t any inference router tests yet (e.g., test_inference_router.py). I think this is just legacy/tech-debt, looks like not all router tests were kept up to date.

[nathan-weinberg]

@nathan-weinberg For example, in https://github.com/llamastack/llama-stack/tree/main/tests/unit/core/routers there aren’t any inference router tests yet (e.g., test_inference_router.py). I think this is just legacy/tech-debt, looks like not all router tests were kept up to date.

That would be done as a separate PR then, since it does not pertain to what this PR is doing

could you open an issue to track it?

[mergify]

This pull request has merge conflicts that must be resolved before it can be merged. @nathan-weinberg please rebase it. https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[leseb]

This should be a separate if: model_id may be assigned in the branches above, so validation shouldn’t be part of the same elif chain.

        if model_id is None:
            raise ValueError("Either request or model_id must be provided")

[leseb]

ditto?

[leseb]

Suggested change

	if isinstance(request_or_model_id, str):
	if isinstance(request_or_model_id, GetModelRequest):
	model_id = request_or_model_id.model_id
	else:
	model_id = request_or_model_id

you could also use *, in the signature to be extra strict.