feat(together-ai): update model YAMLs [bot]

[models-bot]

Auto-generated by poc-agent for provider together-ai.

---

Note

Low Risk
Provider model catalog metadata only; no application logic, pricing math, or runtime behavior changes in code.

Overview
Updates Together AI catalog entries for Qwen/Qwen3.5-4B-Lora and Qwen/Qwen3.5-9B-Lora so routing and capability flags match other Qwen entries.

For 4B-Lora, the diff adds function_calling, text-only modalities, and thinking: true (previously only costs and context limits were defined).

For 9B-Lora, it adds json_output to features, and sets status: active alongside the existing multimodal and thinking flags.

^{Reviewed by Cursor Bugbot for commit 1d7c766. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 2
• Passed: 0
• Failed: 0
• Validation failed: 0
• Errored: 0
• Skipped: 2
• Success rate: 0.0%

Provider	Model	Scenarios
together-ai	Qwen/Qwen3.5-4B-Lora	skipped: skip-check
together-ai	Qwen/Qwen3.5-9B-Lora	skipped: skip-check

Skipped (2)

together-ai/Qwen/Qwen3.5-4B-Lora — skip-check (skipped)

Skip reason

Provisioned model

together-ai/Qwen/Qwen3.5-9B-Lora — skip-check (skipped)

Skip reason

Provisioned model