4 Commits

Author	SHA1	Message	Date
matevip	6a13cc2f50	perf(chat): throttle streaming markdown render and defer chart mounts ... - add useStreamingMarkdown: cap mid-stream markdown re-render to ~140ms, full-fidelity render once the segment completes - skip code-block language auto-detection while streaming (escaped plain text), restore full highlighting on the final render - defer echarts/mermaid blocks to a lightweight loading placeholder while streaming so their parsers never run on truncated source - bypass the render cache for streaming-mode output - wire into ContentSegment and MessageBubble (content + thinking)	2026-06-15 11:39:24 +08:00
matevip	367dd4bed0	fix(agent): preserve per-subtask results in multi-task answer synthesis, add listAvailableSkills tool	2026-04-10 17:10:02 +08:00
matevip	ba34f1eed3	fix(chat): preserve intermediate reasoning in segments via phase-based splitting	2026-04-10 07:58:19 +08:00
matevip	dafdcb4182	feat(chat): segmented message display, progressive loading, and real-time segment persistence	2026-04-10 07:36:24 +08:00