The size-vs-prompt mismatch
Small models (1B–3B) struggle with long, layered system prompts. They follow them poorly, drift, and often output meta-commentary instead of doing the task. Large models (32B+) handle dense system prompts naturally. Your adapter has to know which size it's talking to and adapt the system prompt accordingly.
Mini mode
"Mini mode" is the convention: when the active model is small, swap to a stripped-down system prompt. Keep the plan, drop the philosophy. Keep the format, drop the tone calibration.
Where the metadata comes from
/api/tags returns each installed model's details.parameter_size ("7B", "32B", "1.5B"). Parse that, classify into mini / standard / large, and route prompts accordingly.
Don't reinvent classification
Three buckets is enough: mini (≤3B), standard (4–14B), large (≥15B). More buckets = more if/else chains for marginal benefit.