4 Commits

Author	SHA1	Message	Date
Xinmin Zeng	b431053ef0	fix(frontend): stop rendering reasoning twice for reasoning+answer messages (#3870) ... A reasoning+content AI message with no tool calls was grouped into both an `assistant:processing` group (the ChainOfThought panel above the bubble) and an `assistant` group (the bubble's own Reasoning collapsible), so its reasoning rendered twice. Such a message now becomes only the assistant bubble; the ChainOfThought panel keeps handling intermediate reasoning and tool steps. Closes #3868	2026-07-01 23:35:48 +08:00
Jiahan Chen	6fb22bb311	test(frontend): migrate unit tests to rstest (#3703) ... * test(frontend): migrate unit tests to rstest * docs: updates AGENTS.md * test(frontend): fix rstest lint formatting	2026-06-22 16:12:49 +08:00
YuJitang	417416087b	fix: use backend thread token usage for header total (#2800) ... * fix: use backend thread token usage for header total * Refactor thread token usage fetch	2026-05-09 19:40:32 +08:00
YuJitang	530bda7107	fix: dedupe token usage aggregation by message id (#2770)	2026-05-08 09:54:20 +08:00