Fine-tuned Qwen3 models for knaif: they turn a natural-language request into a strict JSON action plan ({"plan": [...]}) that deterministic code then validates, expands, confirms, and executes through skill packages. The model only proposes the plan — it never runs anything itself.

These are SFT fine-tunes trained on the ffmpeg and documents skills.

Public release names are v1; the underlying fine-tune was training cycle sft-v3-flat.

Structured plan generation for knaif skills, not open-ended chat. Given the knaif prompt (available tools + the user request), the model emits only a {"plan": [...]} envelope naming declared tools and arguments. Unknown tools and unsupported arguments are rejected downstream, so the model's job is intent → validated plan, not command execution.

Via the knaif runtime (recommended — it supplies the prompt and validates/executes the plan):