rope
a927cf6ba9
Profiled the second model call visible in modelUsage: it is `source=generate_session_title`, inventing a title for a session that --no-session-persistence immediately discards. It costs no wall time — both requests dispatch ~1ms apart and run concurrently, which is why duration_api_ms was roughly double duration_ms — but it spent 507 input tokens against 153 for the actual question. --name qs-ask removes it: one request instead of two, 660 input tokens down to 153 per question. No latency change, 77% less input token spend, which is what actually matters when the budget is a subscription rate limit rather than a bill. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| hardware | ||
| FredOS-Gaming.nix | ||
| FredOS-Macbook.nix | ||
| FredOS-Mediaserver.nix | ||