Local AI
Choosing an Ollama Upgrade-Evidence Boundary for Usage Telemetry
A practical policy for keeping Ollama usage records while withholding post-upgrade labels until an application event is evidenced.
Topic
6 articles
Local AI
A practical policy for keeping Ollama usage records while withholding post-upgrade labels until an application event is evidenced.
Local AI
A practical recording boundary for Ollama usage: keep requested context, observed prompt tokens, cache-read tokens, and prompt-evaluation time in separate fields, and collect streaming usage only from the terminal chunk.
Local AI
A troubleshooting architecture for keeping model-warming activity distinct from user inference telemetry while collecting streaming usage only at completion.
Local AI
Use response usage fields to describe work within a request, and use a separate ollama ps observation to record where a loaded model resides.
Local AI
A practical review separates network reachability, cloud-feature state, and response telemetry so that timing and token fields are not mistaken for privacy evidence.
Local AI
A policy guide for separating model-residency choices from per-response evidence, with a four-case decision record and a hypothetical failure review.