Root cause: Each LLM delta (text/thinking) triggered a synchronous
setState via updateMessages → chatStore.setState. With Kimi thinking
model emitting many deltas per frame, this caused a React render storm
that hit the maximum update depth limit.
Fix (two-layer approach):
1. streamStore: Buffer text/thinking deltas locally and flush to store
via setTimeout(0), batching multiple deltas per frame
2. chatStore: Microtask batching in injectChatStore.updateMessages to
coalesce rapid successive updates
Verified: 2-round conversation (4 messages) with Kimi thinking model
completes without crash. Previously crashed 100% on 2nd message.
When the agent writes files via the file_write tool, artifacts are now
automatically created in the artifact panel. The file extension determines
the artifact type (code/markdown/text) and syntax highlighting language.
This connects the existing ArtifactPanel UI to actual tool output data.
Phase 1.0 — Butler Mode UI:
- Hide "自动化" and "技能市场" entries from sidebar navigation
- Remove AutomationPanel and SkillMarket view rendering from App.tsx
- Simplify MainViewType to only 'chat'
- Main interface is now: chat + conversation list + detail panel only
Phase 1.1 — Mode Differentiation:
- Add subagent_enabled field to ChatModeConfig (Rust), StreamChatRequest (Tauri),
gateway-client, kernel-client, saas-relay-client, and streamStore
- TaskTool is now only registered when subagent_enabled=true (Ultra mode)
- System prompt includes sub-agent delegation instructions only in Ultra mode
- Frontend transmits subagent_enabled from ChatMode config through the full stack
This connects the 4-tier mode selector (Flash/Thinking/Pro/Ultra) to actual
backend behavioral differences — Ultra mode now truly enables sub-agent delegation.
