Context window fix:
- Derive initial contextWindow from model selection (haiku=200K, else=1M)
- Use limitContext flag from request
- Updated to exact value from modelUsage on result.success
- Formula: input_tokens + cache_creation + cache_read (all three needed)
TokenUsageDisplay:
- New contextWindowSize prop → shows "X% of context" (not "X% of input")
Graph improvements:
- Pending approval: pulsing amber ring on member nodes
- Working spinner: spinning arc when member has active task
- Current task indicator in popover (Loader2 + "working on" + task name)
- GraphNode: added currentTaskId, currentTaskSubject, pendingApproval, activeTool fields
- Adapter: passes pendingApprovalAgents + currentTaskId from store
- Added functionality to track member spawn statuses during team provisioning, including marking members as online when their first inbox message arrives.
- Introduced new IPC channels and handlers for fetching member spawn statuses.
- Enhanced TeamProvisioningService to manage spawn status updates and emit events for changes.
- Updated UI components to reflect member spawn statuses, improving visibility of member activity during provisioning.
- Added CSS animations for member spawn effects to enhance user experience.
- Eliminated the calculation of thinking and text output tokens from AIChatGroup, simplifying the component.
- Updated TokenUsageDisplay to reflect changes, removing unnecessary props and adjusting context calculations.
- Ensured that context percentages are now based solely on total input tokens for improved accuracy.
