fix assistant reasoning mount lifecycle

This commit is contained in:
ajnart committed 2026-08-13 19:56:58 +02:00
1 parent 7a8b37c906
commit f61e07ae58
5 files changed
+185 -34

No files matched your search

+4 -3
View File
@@ -155,11 +155,12 @@ another message starts. A compact dot matrix distinguishes an initial thinking p
settles into waiting, success, or error states in the minimized activity bar. The state always keeps its text label,
and the animation is disabled when the operating system requests reduced motion.
A compact context control beside the model selector gives a quick glance at cumulative conversation tokens and
cost. Its popover keeps the latest complete context reading while a new response starts and lists every request
A circular context ring beside the model selector gives a quick glance at cumulative conversation usage without
expanding the composer toolbar. Its accessible label includes cumulative tokens and cost when available, while
its popover keeps the latest complete context reading as a new response starts and lists every request
turn with its model, provider, input, output, cached-input and reasoning tokens, context use, duration, speed,
agent steps, routing details, and cost when reported. Before usage is available, the control remains a compact
circle instead of showing a redundant missing-data label. Closing and reopening the popover reads persisted
ring instead of showing a redundant missing-data label. Closing and reopening the popover reads persisted
conversation metadata instead of resetting the display to zero.
Each assistant response places a small provider logo in the same stable action toolbar as copy, export,