Add qwen3-coder-next to expected models

[juanmichelini]

Summary

Add model litellm_proxy/together_ai/Qwen/Qwen3-Coder-Next-FP8 with id qwen3-coder-next to the expected models in resolve_model_config.py.

Fixes #1891

Checklist

• If the PR is changing/adding functionality, are there tests to reflect this?
• If there is an example, have you run the example to make sure that it works?
• If there are instructions on how to run the code, have you followed the instructions and made sure that it works?
• If the feature is significant enough to require documentation, is there a PR open on the OpenHands/docs repository with the same branch name?
• Is the github CI passing?

@juanmichelini can click here to continue refining the PR

---

Agent Server images for this PR

• GHCR package: https://github.com/OpenHands/agent-sdk/pkgs/container/agent-server

Variants & Base Images

Variant	Architectures	Base Image	Docs / Tags
java	amd64, arm64	eclipse-temurin:17-jdk	Link
python	amd64, arm64	nikolaik/python-nodejs:python3.13-nodejs22	Link
golang	amd64, arm64	golang:1.21-bookworm	Link

Pull (multi-arch manifest)

# Each variant is a multi-arch manifest supporting both amd64 and arm64
docker pull ghcr.io/openhands/agent-server:c0698be-python

Run

docker run -it --rm \
  -p 8000:8000 \
  --name agent-server-c0698be-python \
  ghcr.io/openhands/agent-server:c0698be-python

All tags pushed for this build

ghcr.io/openhands/agent-server:c0698be-golang-amd64
ghcr.io/openhands/agent-server:c0698be-golang_tag_1.21-bookworm-amd64
ghcr.io/openhands/agent-server:c0698be-golang-arm64
ghcr.io/openhands/agent-server:c0698be-golang_tag_1.21-bookworm-arm64
ghcr.io/openhands/agent-server:c0698be-java-amd64
ghcr.io/openhands/agent-server:c0698be-eclipse-temurin_tag_17-jdk-amd64
ghcr.io/openhands/agent-server:c0698be-java-arm64
ghcr.io/openhands/agent-server:c0698be-eclipse-temurin_tag_17-jdk-arm64
ghcr.io/openhands/agent-server:c0698be-python-amd64
ghcr.io/openhands/agent-server:c0698be-nikolaik_s_python-nodejs_tag_python3.13-nodejs22-amd64
ghcr.io/openhands/agent-server:c0698be-python-arm64
ghcr.io/openhands/agent-server:c0698be-nikolaik_s_python-nodejs_tag_python3.13-nodejs22-arm64
ghcr.io/openhands/agent-server:c0698be-golang
ghcr.io/openhands/agent-server:c0698be-java
ghcr.io/openhands/agent-server:c0698be-python

About Multi-Architecture Support

• Each variant tag (e.g., c0698be-python) is a multi-arch manifest supporting both amd64 and arm64
• Docker automatically pulls the correct architecture for your platform
• Individual architecture tags (e.g., c0698be-python-amd64) are also available if needed

[all-hands-bot]

Code Review

Taste Rating: 🟡 Acceptable - Works correctly, minor naming inconsistency noted

The PR correctly adds the new model configuration and includes proper test coverage. The structure follows existing patterns perfectly. One minor naming inconsistency to consider.

Verdict: ✅ Worth merging - Core change is solid, minor improvement suggested below

[all-hands-bot]

🟡 Suggestion: Naming inconsistency detected.

This PR uses "qwen3-coder-next" (no hyphen between "qwen" and "3"), but line 102 has "qwen-3-coder" (with hyphen). This creates inconsistency:

• Existing: qwen-3-coder
• New: qwen3-coder-next

Options:

1. Keep as-is if "Qwen3" is the official model name from Together.ai (which appears to be the case from the model path)
2. Change to qwen-3-coder-next for consistency with the existing entry

The model path shows Qwen3-Coder-Next-FP8, suggesting "Qwen3" is indeed the official name. However, users might find it confusing when browsing the model list. Consider whether consistency with the existing entry or consistency with the provider's naming is more important.

[all-hands-bot]

🟢 Nit: Same naming inconsistency in display name.

Compare:

• Line 104: "Qwen 3 Coder" (space between Qwen and 3)
• Line 124: "Qwen3 Coder Next" (no space)

Consider "Qwen 3 Coder Next" for consistency, unless "Qwen3" is the official branding.

[all-hands-bot]

✅ Good: Test coverage included.

The model ID was correctly added to EXPECTED_MODELS, ensuring the new model config will be validated by existing tests (test_all_expected_models_present, test_expected_models_have_required_fields, etc.).