Open WebUI 0.12.5 fixes inflated tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → counts: when a provider re-sent its usage on every streamed chunk, each report was added up. Usage per reply and in Admin Analytics now matches the provider's final count, so earlier analytics may overstate tokens.
Knowledge base API calls that add, update, remove, rename or share now return only the affected files or an empty list instead of the full file list, so they no longer slow down as a knowledge base grows. Clients needing the full list must use the paginated files endpoint.
Open WebUI 0.12.5 makes knowledge base ls, cat and grep commands up to ten times faster on large bases by listing files without loading their full text, and embeds large documents in batches of 1,000 chunks by default to cut peak memory.
In Open WebUI 0.12.5, an unreachable MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition → server now fails only that tool call instead of stopping the whole chat, and a foreground subagentA separate agent spawned by another to do one scoped piece of work in its own context, returning only the result.Full definition → that hits the tool-call limit hands back its partial output with the error rather than losing it.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
subagent — A separate agent spawned by another to do one scoped piece of work in its own context, returning only the result.
