Baixar Kiro 0.11.28 per a Windows

MCP Registry Governance, Model Governance, and Document Attachments
This release gives enterprise teams centralized control over MCP server access and model availability, and adds document attachment support to chat.
MCP Registry Governance
Enterprise administrators using IAM Identity Center can now control which MCP servers their organization is allowed to use. Create a JSON registry file listing approved servers, host it over HTTPS, and configure the URL in the Kiro console. The registry supports remote (HTTP) and local (stdio) servers across npm, PyPI, and OCI package types, with ${VAR} placeholders for user-specific values like auth tokens. Kiro syncs with the registry every 24 hours, enforces version-pinned access, and works alongside the existing MCP on/off toggle to give you full control at the org or account level.
Model Governance
Enterprise administrators can now control which AI models are available to users in their organization. Toggle on model access management in the Kiro console under Settings > Shared settings > Model availability, then curate an approved list of models. You can also set a default model that auto-applies across all clients. This is especially relevant for data residency requirements — experimental models using global cross-region inference can be removed from the approved list until they move to GA with regional inference. Once enabled, only approved models appear in the model selector across both the IDE and CLI.
Document Attachments
You can now attach documents directly to chat messages by pasting or dragging files into the input. Supported formats include PDF, CSV, DOC, DOCX, XLS, XLSX, HTML, TXT, and Markdown. Documents are sent to the model as native document blocks, so the agent can read and reason over their contents. You can attach up to 5 documents per message and mix them with text and images in the same prompt.
Improvements
- Subagent context: Subagents now receive richer context from parent sessions, including file tree structure, for more accurate responses
- Chat performance: Reduced re-renders and improved responsiveness in large chat sessions
- Session storage cleanup: Least-recently-modified sessions are automatically evicted when storage exceeds 500 MB
- Streaming animation: Agent responses render with a smoother streaming animation
- Rename symbol: The rename symbol tool now supports accept/reject in supervised mode, consistent with other file-modifying tools
- Code editing accuracy: Improved how the agent targets and modifies code, with better accuracy for Java and fewer misplaced edits
- Web fetch rendered mode: A new rendered fetch mode uses a browser engine to extract content from JavaScript-heavy pages that return empty results with standard fetching
- Web fetch: Web fetch now supports `text/plain` content type responses.
- MCP connection sharing: MCP server connections are now shared across chat sessions instead of created per session, reducing resource usage
- In-chat search: Search within chat conversations using Cmd+F (Ctrl+F on Windows/Linux)
- Kiro Powers progress: Power operations now appear in the execution snackbar so you can track their progress
- Protected file approval: Kiro now prompts for confirmation before modifying sensitive workspace files like mcp.json, .kiroignore, .vscode/ settings, .git/, and .code-workspace files, regardless of autonomy mode
- Support link: Updated the IDE support link to point to the new support form
Fixes
- Fixed duplicate agent messages appearing when multiple chat sessions were open simultaneously
- Fixed chat input text being lost when navigating to History and back
- Fixed hook command execution approval not working properly for multi-line shell commands
- Fixed spec generation latency increasing due to subagents
- Fixed a token refresh loop that could cause repeated login prompts
- Fixed prompt text being lost when navigating through history or switching sessions
- Fixed markdown re-render performance and overly broad URI matching in chat messages.
- Fixed hook commands not auto-approving on save; restored trusted command list fallback
- Fixed refresh token grant missing required scopes
- Fixed debug logging writing to an incorrect filepath
- Replaced misleading Image type not supported error with accurate file type and MIME information.
- Fixed prework tool resolving to the wrong requirements path for bugfix specs
- Fixed configuration not resolving correctly for social login users