Lataa Kiro 1.0.89

Session Restore, Performance Optimizations, and Custom Agent Enhancements
Note: To get the latest 1.0.x release (1.0.89 or later), download it directly from kiro.dev/downloads. Auto-updates are paused at this time and we are working on re-enabling them.
This release brings performance improvements and Agent Focus Mode polish. Sessions restore automatically on launch, idle resource consumption is lower, prepaid credit packs appear in the account dashboard, and several fixes ensure permissions, hooks, and steering behave correctly across windows and custom agent profiles.
Improvements
- Agent Focus session restore: Kiro restores your last active Agent Focus Mode session when you reopen the IDE, so you pick up where you left off without manually reopening a session
- Rename Agent Focus sessions: Rename sessions directly from the session rail for better organization
- Lower idle CPU usage: Telemetry, battery monitoring, and status bar updates are optimized to reduce background resource consumption when Kiro is idle.
- Faster permissions evaluation: Permission checks run faster for users with many allow/deny rules
- More accurate context usage: Context usage percentage now reflects your model's actual window size rather than a fixed estimate
- Prepaid credits visible in the IDE: Organization prepaid credit packs now appear in the Account Dashboard with remaining balance and expiration, so you can track consumption without leaving Kiro
- Triggered hooks visible in chat: When a hook fires, its name appears in the tool-call collapser so you can see which hook ran and why
- Custom agent commands update live: Adding or modifying agent profiles in .kiro/agents/ immediately updates the agent selector in chat. No restart needed
- Mode descriptions in picker: Agent modes now show their description in the mode selector, making it easier to pick the right mode
- Spec tasks respect model choice: Spec workflow tasks now use the model you selected rather than defaulting to a fixed model
- Richer terminal output in chat: Terminal content is embedded as a structured block in chat, improving readability for multi-line command results
- Run Command reliability: The standalone Run Command action no longer completes prematurely for commands with buffered output.
- Paginated MCP List calls: The MCP client now paginates List calls, supporting servers that expose many resources or tools without hitting size limits
- Policy bundles in agent profiles: Reference built-in permission presets like read-shell, edit-workspace, or dev-shell from your agent profiles, so you don't have to write individual rules from scratch
- Safer trust migration: File read/write grants from legacy permission formats are no longer auto-migrated. These are covered by the edit-workspace preset instead, preventing overly broad inherited rules
- Thinking mode defaults: Models that support extended thinking no longer have it forced on by default. Your model and effort selection is respected as-is
Fixes