Kiro Release Notes

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.

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.

Include live context in Steering

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.

Use saved prompts as slash commands

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

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.

Learn more ->

Follow and guide each step

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.

Learn more ->

Turn it on and bring your recipes

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.

Learn more ->

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.

Learn more ->

Move from Classic to the terminal UI

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.

Learn more ->

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 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 .

Learn more ->

Choose a V3 output style

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.

Learn more ->

Tune fullscreen scrolling

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.

Learn more ->

Run a Hook when a V3 session ends

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.

Learn more ->

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 ->

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.

Learn more ->

Chat That Keeps Up With You

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.

Learn more ->

Work That Survives the Gateway

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.

Learn more ->

Pull Request Watches Beyond GitHub

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.

Learn more ->

More Agent Backends (Preview)

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.

Learn more ->

Jev Decides for Each Turn (Preview)

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.

Learn more ->

Fargate Remote Crews

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.

Learn more ->

Updates That Wait for Active Work

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.

Learn more ->

Isolated Pods on Windows

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.

Learn more ->

Skills Discovered by Search

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.

Learn more ->

Use session-wide tool approval in V3, combine session dashboard filters, and control which environment variables your chats and tools inherit.

This release adds session-wide tool approval to V3 and makes /sessions controls easier to discover and combine. Project .env files no longer load automatically into chat sessions, MCP servers, or tools. In V2, image handling now recovers when images exceed supported dimensions. Terminal rendering, settings, and agent config upgrades also receive reliability updates.

Session-wide tool approval (V3)

Run /tools trust-all to automatically approve tool calls for the rest of the current V3 session. By default, Kiro shows a safety warning and asks you to confirm before enabling it, so enable trust-all only in an environment you trust.

Learn more ->

Session dashboard controls (V3)

In /sessions, open the Filter, Sort, or Group control to see its options inline. You can combine the current workspace, main sessions, and bookmarked filters; includes empty reveals empty sessions, which are hidden by default.

Learn more ->

Environment isolation

Project .env files no longer load automatically into chat sessions, MCP servers, or tools. Kiro starts with the environment inherited from your terminal. If your workflow relies on variables from a project .env, export them in your shell before starting Kiro. For MCP servers, reference the exported values in the server configuration.

Learn more ->

More resilient image handling (V2)

In V2, Kiro resizes images that exceed supported dimensions while preserving their aspect ratio, and scales down oversized images in saved history when a session loads. If the model provider still rejects an image, Kiro retries automatically, then replaces the rejected images with a placeholder and shows a notice so the conversation can continue.

Learn more ->

Kiro Web now lets you choose reasoning effort for supported models, and folds reasoning and tool activity into a collapsible timeline so the agent's response stays in view. Document attachments hold up across long sessions, sessions reconnect when you return to a background tab, and Reviews and What's new are easier to find.

Choose the Reasoning Effort for a Model

For models that offer reasoning levels, choose a lower effort for quick edits or a higher one for work that needs more care. The selector appears only when the model supports it, holds its place while levels load, and supports keyboard navigation.

A Timeline That Stays Out of the Way

Consecutive reasoning steps and tool calls now fold into one collapsible block, keeping the agent's response in view. Expand it for the details. Startup actions group under a single Session setup row. Steering, Configuration Sync, and task lists present their results in a more readable form.

Attach Documents Across a Long Session

Uploading a sixth document partway through a long session no longer blocks new attachments. The five-document limit applies to each message instead of accumulating across the session, so earlier uploads no longer block later messages. Affected sessions recover on the next message without a reset or restart.

Sessions Reconnect When You Return to the Tab

A Kiro Web tab left in the background now reconnects when you return and replays session activity that arrived while you were away. This restores the latest session state after sleep or a network change without requiring another message.

Configure thinking and effort from /model and start V3 cloud sessions before connecting a repository.

This release brings reasoning controls into /model and lets V3 cloud sessions start before you connect a repository. Improvements add clearer live progress, smoother streaming, and more efficient fullscreen scrolling. Reliability fixes cover models, sessions, tools, and non-interactive runs.

Reasoning controls in /model

Open /model to switch models and configure the selected model's thinking and effort in one place. The panel shows only the options supported by that model and saves your choices for future sessions. /model is now the primary interface for reasoning settings. In V2, bare /effort is a legacy command: it shows a deprecation warning and opens the Effort setting in /model; /effort remains supported. In V3, /effort continues to open its own picker.

Cloud sessions before repository connection (V3)

You can start a cloud session before connecting a repository. Run /repo when you're ready to attach one. If no source provider is connected, Kiro opens the connection screen, where the repository is marked as optional.

Claude Fable 5.1 is beginning to roll out in Preview across Kiro clients for Kiro Enterprise organizations. Anthropic's most capable agentic coding model traces problems to root causes, maintains context and intent across complex tasks, and improves reliability for multi-file refactors and long autonomous runs. It has a 1M context window and a 6x credit multiplier. Inference runs only in US East (N. Virginia) (us-east-1).

Availability is limited during the Preview rollout. Organizations with access can enable Fable 5.1 through model governance. After model access management is enabled, administrators can add Fable 5.1 from Manage approved list and make it available to their users.

All Fable 5.1 traffic is retained for up to 30 days (unless otherwise required by law) for automated offline abuse detection. Classifier-flagged traffic will be subject to potential human review performed by AWS, and we may review flagged traffic for abuse.

Expand chat to a dedicated terminal screen, browse a streamlined V3 session dashboard, and keep long sessions running reliably.

This release adds fullscreen chat for interactive TUI and Lite sessions, streamlines the V3 session dashboard, and improves reliability during long-running work.

Fullscreen chat

Type /fullscreen to move the current conversation to a dedicated terminal screen with its own scrollable view, independent of your shell history. Type /fullscreen again to return inline. Fullscreen is available in interactive TUI and Lite sessions on both V2 and V3.

Scroll with your mouse, touchpad, or keyboard, and click and drag to copy selected text. To start future interactive TUI sessions in fullscreen, open /settings, choose Display, and turn on Start fullscreen.

Streamlined session dashboard (V3)

/sessions now separates search, filter, sort, and grouping controls from the session list. It opens as a flat list ordered by last use, supports sorting by last use, session name, or message count, and remembers your selection. Use Tab to move between the controls and results.

GPT-5.6 Sol, Terra, and Luna now support a 1M token context window, up from 272K, in the Kiro IDE, CLI, and Web. Entire codebases, long-form documents, and extended multi-turn agent histories fit in a single request, so repository-scale refactors, end-to-end debugging, and long-horizon agentic tasks run without chunking or losing earlier context. Credit multipliers for the GPT-5.6 family are updated with this launch and follow the two-tier context model OpenAI and Amazon Bedrock use: requests up to 272K tokens bill at the short context rate (Sol 4.4x, Terra 2.2x, Luna 1.1x), and requests above 272K tokens bill at double that rate. 1M context is rolling out gradually with experimental support to Kiro Pro, Pro+, Pro Max, and Power customers. Restart your IDE or CLI, or refresh Kiro Web, to see the updated models.