Changelog

Claude Opus 5.5 and GPT-5.6 Sol are generally available with full Kiro support. Expanded capacity supports more dependable access for production workloads. Their current plans, regions, surfaces, context windows, credit multipliers, and inference scopes remain unchanged.

Both models' Experimental labels no longer apply. The Kiro Excluded Models indemnity exception also no longer applies to these models. To load the latest model list, restart the IDE or CLI, run kirocrew restart for Crew, or refresh Web in your browser. Learn more ->

This release adds Approve for me to interactive V3 sessions. Kiro approves routine actions for you, blocks risky ones, and asks when unsure, so work no longer stops at every routine prompt. Existing deny, ask, and allow rules decide first; Approve for me handles only unsettled actions and marks each action it approves Approved for you. Turn it on under /permissions when available.

In an interactive V3 session, run /permissions and choose Policies. When the page offers approve for me, choose it. The choice you make here is stored per workspace: Kiro adds the approve-for-me policy preset to the workspace permissions file, so it stays with that repository and does not follow you to others. When the page says instead that Approve for me is unavailable in your session, Kiro keeps asking. Choose ask for approval to go back to prompts for every action your rules do not cover. Learn more

Kiro Web can now keep a short recap for each session and separates agent settings from account settings. Workflows now ask for input during planning and review. Schedule replaces Automations, and reopened sessions stay usable while their sandbox starts.

The sidebar now separates Agent Config for choices that shape the agent from Settings for your account and environment. Agent Config includes Cloud Config, Steering, Skills, Workflows, Powers & MCP, Model fallback, and Memory; Settings includes Account & plan, Appearance, Integrations, AWS access, Sandbox, API keys, Privacy & data, and Help & support. MCP servers are under Powers & MCP, the IAM role under AWS access, themes under Appearance, and model fallback under Agent Config > Model fallback. Learn more ->

With Workflows turned on, a workflow created from a prompt starts with a create-workflow step you can open and guide. If details are missing, it asks instead of guessing. Its plan shows each step's agent, model, effort, and first task. Changes requested after a rejected plan carry into approved steps. Review loops that used to run three to five passes and fail now pause after two rejected passes by default. A workflow's own pass limit still wins. Active runs stay pinned above chat. Learn more ->

This release adds Windows system-wide installers for x64 and ARM64 devices. It also brings drag-and-drop file attachments to chat without holding Shift, and framed Mermaid diagrams that stay readable on dark themes. It fixes slash commands that did not run when you typed right after them, and hook toggles that failed without an error.

This release adds a faster way to reconnect when an IAM Identity Center or AWS Builder ID session expires, without choosing a sign-in method or re-entering your Start URL. Markdown Review now lets you copy selected text and send comments from the keyboard. Kiro also now tells you when a file edit fails to save.

This release warns you when Kiro CLI starts as root or Administrator and makes V3 sessions follow your organization's MCP and web tools settings. It also lets you jump back to the prompt from a long answer in fullscreen, shows which MCP servers your registry hid in V3, and fixes model fallback, session resume, dictation, and MCP connection issues.

Kiro CLI now warns you when a session starts as root on macOS and Linux or as Administrator on Windows. Tools, shell commands, Hooks, and MCP servers can run with those privileges and create root-owned files or change system settings. The warning does not block anything. If you intentionally run Kiro CLI with elevated privileges, turn the warning off with kiro-cli settings app.warnOnElevatedPrivileges false. Learn more

V3 sessions now turn MCP servers and the web_search and web_fetch tools on or off according to your organization's Kiro settings. Learn more

Claude Haiku 5.5 is now available with experimental support across the Kiro IDE, CLI, Crew, and Web for Pro, Pro+, Pro Max, and Power customers in us-east-1 (N. Virginia) and eu-central-1 (Frankfurt). Haiku 5.5 is designed for high-volume work requiring quick responses. It has a 1M-token context window. Requests up to 100K tokens have a 0.06x credit multiplier; requests that exceed 100K tokens are billed at 0.3x. To load the latest model list, restart the IDE or CLI, run kirocrew restart for Crew, or refresh Web in your browser. Learn more ->

This release lets V3 MCP tools ask for input, gives you more control over Workflows, and lets you delete memories from /memories. It also adds a model picker editor and improves workflow recovery, headless MCP sign-in, saved sessions, accessibility, and more.

In local V3 sessions, MCP tools can now pause and show a form or link when they need more information. Enter the requested details, complete an action on another page, or decline the request. The tool continues without restarting its call. Learn more

This release adds the Use workflows control, so you can choose how often Kiro starts workflows in a chat. It also makes installed Powers more reliable across the IDE and Kiro CLI, applies the Memory setting's Off default, and improves terminal and in-product feedback behavior.

Claude Fable 5.1, Claude Sonnet 5.5, GPT-5.6 Terra, and GPT-5.6 Luna are generally available with full Kiro support. Expanded capacity supports more dependable access for production workloads. GPT-5.6 Sol remains Experimental. Fable 5.1 remains available to Kiro Enterprise organizations in US East (N. Virginia) (us-east-1). Sonnet 5.5 remains available across the Kiro IDE, CLI, Crew, and Web. GPT-5.6 Terra and Luna remain available in the Kiro IDE, CLI, and Web. Sonnet 5.5, GPT-5.6 Terra, and GPT-5.6 Luna are available for Pro, Pro+, Pro Max, and Power customers in the US and EU geographies. The Preview label for Fable 5.1 and Experimental labels for Sonnet 5.5, Terra, and Luna no longer apply. The Kiro Excluded Models indemnity exception also no longer applies to these models. To load the latest model list, restart the IDE or CLI, run kirocrew restart for Crew, or refresh Web in your browser. Learn more ->