rope aee59ff0b2 qs-ask: disable thinking — 2.4x faster, same answers ... Profiled where the ~6s actually went, and it was not where I assumed. Haiku defaults to extended thinking, so it spent 225 output tokens and 1.9s deliberating before emitting an 80-character answer about the height of a tower. MAX_THINKING_TOKENS=0: 43 output tokens, time-to-first-text 2657ms -> 1122ms, wall clock 5.7s -> ~2.4s, answer unchanged. Two things measured NOT to be the bottleneck, recorded in the comment so nobody optimises them later: process startup (0.12s boot plus 28ms to fire the request, so a warm/persistent process saves nothing) and prompt size (184 input tokens, no bloat to trim). Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>		2026-08-01 17:49:44 +01:00
..
hardware	gaming: drop dead garnix cache	2026-07-28 20:38:46 +01:00
FredOS-Gaming.nix	gaming: clamp DP-3 gamut to DCI-P3 in compositor	2026-07-29 12:20:02 +01:00
FredOS-Macbook.nix	macbook: cap nix download concurrency to stop wl wifi drops	2026-07-29 17:24:25 +01:00
FredOS-Mediaserver.nix	qs-ask: disable thinking — 2.4x faster, same answers	2026-08-01 17:49:44 +01:00