Switch an interactive Classic session to 3.0, match V3 Hooks by tool category, and improve reliability in long V3 sessions.
Kiro CLI 2.28.0 offers Classic users a path to switch to 3.0 without leaving their terminal, lets V3 Hooks match tool categories, and makes long V3 chats more reliable.
Switch to 3.0 from an interactive Classic session
When you start an interactive Classic session on a host that can run 3.0, Kiro now offers to switch: choose Switch to 3.0 and upgrade my agent configs to save 3.0 as your default, upgrade your agent configurations, and rerun your command in 3.0. Decline, and Kiro reminds you again about once a week.
Match Hooks by tool category in V3
In V3 sessions, Hooks that run before or after a tool can now match by category, such as shell, read, write, or a specific MCP server or tool, instead of only by internal tool ID.
Claude Sonnet 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 (IAD) and eu-central-1 (FRA). It's Anthropic's fastest Sonnet model to date and a clear upgrade over Sonnet 5: output is more than 30% faster, real-world knowledge work approaches Opus 5.5 performance, and clearer writing makes it a stronger collaborator. Claude Sonnet 5.5 includes a 1M-token context window, adaptive thinking on by default, and a 1.3x credit multiplier. To load the latest model list, restart the IDE or CLI, run kirocrew restart for Crew, or refresh Web in your browser. Learn more ->
Choose how V3 delegates with Workflows, include live file and folder context in Steering, and invoke saved prompts as slash commands.
Kiro CLI 2.27.0 adds control over how V3 delegates when Workflows are enabled, expands Steering with live file and folder context, and exposes saved prompts as slash commands. It also tightens access to local Kiro state and improves terminal rendering and tool reliability.
Choose how chat delegates with Workflows
When Workflows are enabled, the new Workflows: sub-agent tool setting is on by default, so the main chat can delegate directly to sub-agents or through Workflows. Turn it off under /settings features to limit main-chat delegation to Workflows; sub-agents remain available inside workflow steps when their agent configuration permits them.
Whole-file #[[file:...]] references work across surfaces. CLI V3 adds one-line and line-range selectors plus #[[folder:...]] references for a one-level directory listing. In CLI V3, referenced content resolves when the Steering document loads, subject to the session's file-read policy.
V3 exposes workspace, global, and MCP prompts as slash commands. Completion shows argument hints, and invoking a prompt resolves its file template or MCP content before sending the expanded text to the model.
Run reusable, multi-step agent plans in Kiro Web cloud sessions, inspect and guide every step, and keep working in the parent conversation.
Workflows are now available as an opt-in feature in Kiro Web cloud sessions. They run reusable, multi-step agent plans in the background while you continue working in the parent conversation.
Start a Workflow from the conversation
Describe the outcome and how much structure or review you want. Kiro proposes a Workflow, names its steps, agents, and effort, and launches it in the background. Ask Kiro to investigate a codebase for risks, deliver a feature with independent reviewers, or make a failing build green. Each step runs in its own agent session, which you open from the Workflows panel; it sees only what earlier steps hand it, and the run pauses when a step needs your input.
Start with one of three bundled recipes: investigate for read-only investigation, feature-pipeline for staged feature delivery, or publish-pr for opening a pull request and handling review feedback.
Once a Workflow is running, open Workflows from the side panel in the parent conversation and select a run to inspect its nested steps. Select a step to see its status, elapsed time, agent, model, effort, and tool activity. You can Answer this step when it pauses, Steer the agent while it runs, or Message this step's agent for other guidance. You can also pause, resume, or stop a run. After a failure, you can retry the failed steps. Summary, Files, and Artifacts also share the side panel to keep outcomes and evidence in the session.
Open Settings > Workflows and turn on Enable workflows. Use Upload workflow for one .workflow.json, .workflow.yaml, or .workflow.yml recipe, or use Configuration Sync to import a complete .kiro/workflows/ folder. Turning Workflows off hides its surfaces and prevents new launches.
Run reusable multi-agent Workflows in the background, apply stronger safeguards to Kiro configuration, and manage enterprise sign-in options.
IDE 1.2 introduces Workflows, strengthens safeguards for untrusted workspaces, and adds enterprise controls for sign-in methods. This release also reworks session details, keeps enterprise traffic in your profile's Region, and fixes authentication, debugging, and reliability issues.
Run multi-agent Workflows in the background
Ask Kiro to run a reusable, multi-step plan while you continue in the parent chat. Each step runs in its own agent session. Use the Workflows area above the chat to inspect progress, open a step, and pause, resume, or stop the run. Workflows are off by default: turn on Workflows in Workspace Configuration in Agent Focus, or set kiroAgent.workflows.enabled in Settings, then start a new chat session. Learn more ->
Protect Kiro configuration and Workflow recipes
Kiro asks before the agent changes agent, Hook, or Power files, or the Workflow recipes in .kiro/workflows/ that define your Workflows, even when broader file permissions allow the write. In an untrusted workspace, Kiro also asks before changing any other Kiro configuration and before each command runs, even when you previously allowed it. Workflow recipes in an untrusted workspace are not loaded until you trust the workspace. Learn more ->
Run reusable, multi-step Workflows in V3, get clear guidance when Classic sessions start, and use stricter approval checks for files, tools, and shells.
Kiro CLI 2.26.0 adds opt-in Workflows for reusable, multi-step tasks and helps Classic users identify what to change before moving to the terminal UI. V3 also tightens approval checks for Hook and Language Server Protocol (LSP) file writes, for MCP tools and shell commands in untrusted workspaces, and for approvals that change while an action waits.
Run multi-step Workflows
In a V3 session, open /settings, choose Features, and enable Workflows, then restart Kiro CLI to apply the change. Then ask Kiro to create a Workflow from the outcome you want, or launch a recipe with /workflow run, and use the /workflow commands to inspect and manage runs.
Classic sessions now show a deprecation notice. If a flag, environment variable, or saved setting launched Classic, the notice identifies it and points to guidance for switching to the terminal UI.
Claude Opus 5.5 brings stronger agentic coding and clearer communication than Opus 5 at a 2.0x credit multiplier, down from Opus 5's 2.2x.
Claude Opus 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 (IAD) and eu-central-1 (FRA). Anthropic reports stronger performance on long, complex coding tasks and clearer communication than prior models. Claude Opus 5.5 includes a 1M-token context window and has a 2.0x credit multiplier. To load the latest model list, restart the IDE or CLI, run kirocrew restart for Crew, or refresh Web in your browser. Learn more ->
Install and uninstall Powers from chat or the command line, choose V3 output styles, tune fullscreen scrolling, and automate session teardown with a new Hook.
This release lets you manage Powers from a local V3 session or without starting chat, customize how V3 responds, and tune fullscreen scrolling. V3 also adds a SessionEnd Hook, while model notices, session loading, terminal rendering, authentication, and security receive reliability updates.
Install and uninstall Powers
In a local V3 session, run /powers install <name|path> to add a Power from the catalog or a local directory, and /powers uninstall <name> to remove one. Kiro refreshes the available Powers immediately so the current session can use the updated set. To manage Powers without starting chat, run kiro-cli powers install <name|path> or kiro-cli powers uninstall <name>.
Open /settings in a V3 session to choose how Kiro formats its responses. The available choices include output styles supplied by upgraded agents, so each agent can offer styles suited to its work.
Open /settings display, select Full Screen, and set Scroll speed to move the transcript by 1, 2, or 3 rows per mouse-wheel event. The default is 2 rows. The new Full Screen screen also contains the existing Start fullscreen setting.
Use the new SessionEnd trigger to run a Hook when a V3 session shuts down. This gives your session-level automation a reliable teardown event for cleanup and other end-of-session tasks.
IDE 1.1.70 lets you set a default timeout for local agent commands, opens Markdown links to workspace files in the editor, and keeps Agent Focus file and folder context aligned with the active project. Restored Agent Focus sessions now reconnect without leaving a blank chat pane. Background process output cards show their results, Markdown tables keep their styling, and Mermaid diagrams no longer leave stray error graphics while streaming.
Kiro Crew 0.7.0 makes day-to-day work more durable and easier to control. Most settings apply as soon as you save them, accepted background work survives Gateway restarts, and updates wait for active work to finish. Long chats gain a turn minimap, clearer tool-call titles, and direct model and reasoning controls, while pull request watches expand to GitLab, Bitbucket Cloud, and Azure DevOps Services. Windows gets isolated pods and a faster Gateway start, and Preview users can choose more agent backends, let Jev route individual turns, or run remote crews on AWS Fargate.
Settings That Apply While You Work
Most settings now reach the running Gateway as soon as you save config.json or change a value in Settings. Fields that still need a restart identify themselves in the UI; the Slack slash-command field is the current boot-only setting and carries a Changes need a restart badge.
A turn minimap in the left gutter of a desktop chat shows one marker per loaded turn, with hover previews, click-to-jump navigation, and an end cap that loads older history. The model chip now puts model and reasoning-effort choices in one place, and Selectable Models controls which options appear. When the agent is working, choose Steer to redirect the current turn or Queue to wait for the next one; Cmd or Ctrl plus Enter performs the other action for one send.
Side Chat opens from /side or /btw for an ephemeral question beside the main conversation. On sessions using the Kiro CLI backend, it can run read-only lookups without approval; changes and MCP tools are refused. Tables can be copied as Markdown or CSV, and long code blocks repeat their actions at the bottom.
Accepted subagent work, Task Runner steps, and workflow calls now enter a durable queue before they run. A Gateway restart restores queued work instead of dropping it, and the System page shows the active queue and the concurrency capacity currently in force.
For long-horizon work, the optional Crew log records an append-only session trail and powers a durable session ledger across context compaction. Set KIROCREW_CREW_LOG=1 in ~/.kiro/crew/.env and restart the Gateway to enable its status, usage, timeline, tools, and approvals views. The kirocrew-crew-log MCP server provides read-only access for agents.
The structured pull request watch now accepts GitHub, GitLab, Bitbucket Cloud, and Azure DevOps Services URLs. GitLab uses glab; Azure DevOps uses az with the azure-devops extension and either an az login session or AZURE_DEVOPS_EXT_PAT; private Bitbucket pull requests can use BITBUCKET_EMAIL and BITBUCKET_API_TOKEN.
Azure DevOps Server and Bitbucket Data Center are not supported. Azure DevOps and private Bitbucket watches must start from a dashboard conversation. Stop and inspect actions now work across plain timer loops, pull request watches, and workflow watches, including from Webex.
OpenCode and goose join Kiro CLI, Claude Code, Codex, and KAS in the Agent Backend selector. Crew verifies each backend's permission path before the first prompt and shows missing installation components in the selector. Codex and OpenCode sessions can compact, and Crew's own tools reach OpenCode and goose sessions.
Pi is also available when both pi and pi-acp are installed. Pi sessions do not carry Kiro Crew's MCP tools, so choose another backend when you need Crew subagents, scheduling, memory, or other MCP capabilities. kirocrew doctor reports this limitation.
Enable Decisions (Jev) under Settings > Developer > Feature Previews, then choose Auto (Jev) in a chat's model picker to classify each message as simple, medium, or complex and route it through decisions.model_route. Choose Auto (Jev) on the busy send button to let Jev decide whether a mid-turn message should steer or queue. Each decision appears on the message it shaped, with feedback controls.
The Preview is opt-in. Model routing and busy-send decisions start only when you select Auto (Jev) in the corresponding control. The settings card explains what content can be sent to the configured provider; separate consent switches govern tool arguments, compaction inputs, and recalled-memory snippets.
AWS Fargate joins SSH and AWS Systems Manager Session Manager (SSM) as a remote-crew connection method. Crew reaches the task through SSM with no inbound network rule, using the AWS CLI and Session Manager plugin on your laptop. Tasks live for six hours by default and the runtime admits at most ten at once. Change the lifetime with fargate.task_ttl_seconds in cloud.json; the ten-task ceiling is fixed.
The Gateway now checks for updates at startup and every twelve hours. An automatic update pauses new work and waits for active turns, scheduled runs, subagents, Task Runner steps, and workflows to become idle before applying, then restarts the Gateway. If a source update needs a newer Python than the current virtual environment provides, Crew refuses before moving the checkout and names the interpreter that needs attention.
Managed installs can also arm an update from the update and What's New dialogs, using the same time-limited host approval shown under Settings > About.
The isolated-pod workflow now runs on Windows through Task Scheduler. kirocrew pod up, down, ls, status, token, url, logs, prune, and provision cover the pod lifecycle for a Kiro Crew source worktree. pod api remains unavailable on Windows because the private request channel requires a Unix-domain socket.
With Dev Fleet enabled under Apps > Library, an agent can start or stop a worktree pod and receive its address, port, and short-lived token without leaving the chat.
skills.max_triggered now defaults to 0. Sessions receive a short skill index and agents use skill_search to load relevant instructions, instead of injecting every trigger match automatically. Set a positive value to allow up to that many matched skills to inject per message.