Check Fine-Tune Model Deprecation in Kiln

Audit the fine-tunable models listed in Kiln to find base models that are no longer supported for fine-tuning by their providers. This is separate from general model deprecation, a model can still be available for inference but no longer supported as a fine-tuning base.

---

Global Rules

• Sandbox: All curl, uv run, and python3 commands that hit the network MUST use required_permissions: ["all"]. The sandbox blocks network access.
• Env vars: Source .env before running check scripts: export $(grep -v '^#' .env | xargs)
• Vertex AI auth: The Vertex check requires gcloud CLI authentication. Before running, ask the user to run gcloud auth login if they haven't recently. If gcloud auth print-access-token fails, prompt the user to authenticate.
• Non-destructive: This skill only reports findings. It does not automatically remove or deprecate models.

---

Supported Providers

Provider	Env Var	Auth
OpenAI	OPENAI_API_KEY	Bearer
Together AI	TOGETHER_API_KEY	Bearer
Vertex AI	VERTEX_PROJECT_ID + gcloud CLI auth	OAuth (gcloud)
Fireworks AI	FIREWORKS_API_KEY	Bearer

---

Background

Kiln has two types of fine-tunable model entries:

1. Static entries, Models in libs/core/kiln_ai/adapters/ml_model_list.py with provider_finetune_id set. Currently used by Together AI and Vertex AI.
2. Dynamic entries (Fireworks), Fetched at runtime from api.fireworks.ai/v1/accounts/fireworks/models filtering by tunable=True. This list is managed by Fireworks and may include stale/unsupported models.

The API endpoint that serves the fine-tune dropdown is GET /api/finetune_providers in app/desktop/studio_server/finetune_api.py.

---

Phase 1, Check Static Fine-Tune IDs

Run the check script from the repo root: