* feat(server): report running usage on stream chunks with continuous_usage_stats
* fix(shell): count tokens instead of stream chunks in the live tok/s
* refactor(server): build both openai stream usages from GenUsage
* fix(shell): reset the first-delta count per turn and ignore zero running totals
* fix(sampling): apply presence and frequency penalties
* fix(server): reject non-finite sampling penalties
* fix(server): bound presence and frequency penalties