Banned References¶
Rule ID: content-banned-references
Detect banned or deprecated model names, APIs, and custom patterns
| Severity | warning (auto) |
| Autofix | llm |
| Since | v0.7.0 |
Configuration¶
| Parameter | Description | Default |
|---|---|---|
banned |
Additional banned patterns as list of {pattern, message} dicts | [] |
skip-builtins |
Disable built-in deprecated model/API checks | false |
Research Basis¶
Detects deprecated model names, retired APIs, and custom banned patterns.
LLMs trained on older data generate deprecated API calls 70–90% of the time when given outdated context (Wang et al., ICSE 2025). An instruction file that says "use claude-2 for summarization" or "call /v1/complete" becomes that outdated context — the model will generate code targeting APIs that no longer exist.
The rule ships with built-in patterns for deprecated Anthropic and OpenAI models
and supports user-defined patterns via the banned config key.
References:
- Wang et al., LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-based Code (ICSE 2025) — 70–90% deprecated API usage rates with outdated context
- OpenAI Deprecations — Ongoing model and API churn
- Fern: Documentation Maintenance Guide — "AI agents treat documentation as ground truth and cannot detect errors through experience"