Streaming chunks can contain multiple tokens. Use reported completion
totals for the final end-to-end average and label live rates as estimates.
Count each client tool turn once and include reasoning in the total.
Assisted-by: Codex:gpt-6
Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>