Check Model Deprecation in Kiln

Audit libs/core/kiln_ai/adapters/ml_model_list.py to find models that have been deprecated, removed, or are approaching end-of-life across all providers. All checks are free, they use model-listing endpoints, not inference.

---

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 sets deprecated=True on individual provider entries. It never removes models or providers from the list.
• Skip already-deprecated: Only check providers where deprecated=False (the default). Don't re-check entries already marked deprecated.

---

Phase 1, Extract Current Model-Provider Pairs

Run the extraction script from the repo root:

python3 .agents/skills/kiln-check-deprecation/scripts/extract_models.py > /tmp/kiln_extracted.json

This fetches the published model list from https://remote-config.getkiln.ai/kiln_config_v2.json and extracts:

• The provider name
• The model_id
• The parent model's enum name

It skips entries already marked deprecated=True.

Output: JSON to stdout (pipe to file), human summary to stderr.

The JSON contains:

• deprecated_count: number of already-deprecated entries
• providers: dict of provider_name → sorted unique list of model_ids
• entries: list of {enum, provider, model_id} for each non-deprecated entry

---

Phase 2, Check Each Provider

Option A: Check all providers at once