Guardian Review Supports Tracing Early Instructions Without Losing Handover Context
When you have AI execute multi-step tasks or rotate collaboration across different agents, the biggest concern is that subsequent stages might overlook initial instructions. The newly added Guardian review (an opt-in safety mechanism that verifies whether operations comply with security rules) is an optional feature. It can now proactively retrieve user instructions provided earlier in the conversation, incorporating full agent handover context into its checks.
In the past, passing only the current progress during handovers could lead to misjudgments in safety checks due to missing background context. Once enabled, the review module captures the complete picture, ensuring that multi-agent execution remains aligned with your original requirements.
FEATURE
Support Starting Sessions Outside Projects with Automatic Permission Restoration
Sometimes you simply want to ask quick questions or handle miscellaneous files when the current directory is not a project folder. As long as system policy permits, you can now launch a session (a conversational environment for continuous interaction with AI) directly outside project directories while applying default workspace settings. Furthermore, when you resume the session later to continue work, the system also restores previously stored authorizations and permissions.
Previously, starting outside a project might fail, and reconnecting required re-authorizing permissions. Now, even outside project directories, operational flexibility and permission persistence remain intact.
FEATURE
Agent Control Center Adds Keyboard Navigation for Past Tasks with Precise Terminal History
When frequently switching tasks or inspecting history in the terminal, operational smoothness directly affects your workflow pace. The Agent Control Center now introduces a keyboard-accessible "Show more" action, letting you easily browse earlier task records. On local Linux X11 terminals that support this operation, full-screen mode now also allows selecting conversation transcript text and pasting quickly with a middle click. For settings and state persistence, the terminal interface fully preserves preferences such as server provider, reasoning summaries, and verbosity, displaying the correct session when resuming conversations or branching into new history.
With these refined interface details, daily operations become much smoother.
FEATURE
Reconnection Automatically Verifies Delivery Status to Prevent Duplicate Queued Messages
When conversing over an unstable network, the biggest concern is that pending messages waiting to be sent might be duplicated during disconnections. Unsent messages in the queue (a pending list waiting to be processed in order) now benefit from an improved reconnection mechanism. Upon reconnecting after network drops, the system first verifies whether earlier submissions in an uncertain state succeeded before continuing with subsequent messages, completely preventing the same message from being sent twice.
After reconnecting, the system resumes processing unsent queued messages without duplication.
BUGFIX
Windows Sandbox Solidifies PowerShell Fallback while Fixing Long Paths and Background Windows
When executing isolated commands inside sandboxes on Windows, you might previously have encountered execution failures or distracting pop-up windows. This release fixes the PowerShell fallback mechanism within Windows sandbox (a technology that isolates programs within a secure environment) and resolves permission repair issues with very long paths. Background helper processes also no longer pop up redundant console windows during operation.
With these issues resolved, sandbox execution on Windows is no longer obstructed, and your screen remains undisturbed by sudden pop-up windows.
FEATURE
Subagents Retain Starting Environments and Clearly Receive Setup Failure Reasons
When you have AI delegate subtasks to multiple subagents, tracking could become unclear if the execution environment was still being prepared. A subagent (a helper agent dispatched by the main program to run specific subtasks independently) now properly retains execution environments that are still starting up. If any errors occur during configuration or setup, the subagent accurately receives the concrete reason for failure.
This makes multi-agent initialization much more reliable, allowing you to instantly see where things stalled when issues arise.
FEATURE
SQLite Database Eliminates Connection Jank with Genuine Error Reporting and Space Reclamation
During long runs or frequent logging, underlying database stability and disk space management are important. This release prevents SQLite (a lightweight embedded database system) from experiencing jank when establishing connections and writing records. If an error occurs during database initialization, the system displays the genuine error message directly instead of masking it as a connection timeout. Meanwhile, a background automatic reclamation mechanism has been added to free unused space in the log database, reducing disk consumption.
FEATURE
Model List Filters Stale Items with Clearer Credential Configuration and Faster Plugin Loading
When connecting external custom models or loading multiple plugin extensions, configuration clarity and loading efficiency directly impact startup speed. The explicitly specified model provider list no longer contains unsupported built-in entries, nor does it reuse stale data when refreshes fail. The update further clarifies how provider credentials work with storage backends and explains using the env_key setting to designate the environment variable for API keys. For plugins, the system caches parsed manifests and reuses existing HTTP connections during remote requests, reducing plugin reloading time.
Overall integration is cleaner and operates more smoothly.
Original changelog
Original changelogGuardian Review Supports Tracing Early Instructions Without Losing Handover Context
Added opt-in Guardian review capabilities to retrieve earlier user instructions and include context from agent handoffs. (#49036, #49057)
Original changelogSupport Starting Sessions Outside Projects with Automatic Permission Restoration
Start sessions outside a project with workspace defaults when policy permits, and restore saved permissions when resuming. (#49160)
Original changelogAgent Control Center Adds Keyboard Navigation for Past Tasks with Precise Terminal History
Browse older tasks in the agent command center with a keyboard-accessible “Show more” action. (#49106)
Select transcript text and paste with middle-click in fullscreen mode on supported local Linux X11 terminals. (#49112)
The terminal UI now preserves server provider, reasoning-summary, and verbosity settings and shows the correct sessions in resume and fork history. (#49144, #49161, #49171)
Original changelogReconnection Automatically Verifies Delivery Status to Prevent Duplicate Queued Messages
Unsent queued messages now resume after reconnection once uncertain submissions are resolved, avoiding duplicate sends. (#49105)
Original changelogWindows Sandbox Solidifies PowerShell Fallback while Fixing Long Paths and Background Windows
Fixed Windows sandbox PowerShell fallbacks and long-path permission repairs, and suppressed unwanted console windows from background helpers. (#49019, #49058, #49098, #49164, #49386)
Original changelogSubagents Retain Starting Environments and Clearly Receive Setup Failure Reasons
Subagents now retain environments that are still starting and receive their configuration or preparation failure. (#49075)
Original changelogSQLite Database Eliminates Connection Jank with Genuine Error Reporting and Space Reclamation
Prevented SQLite stalls during connection setup and logging, and surfaced initialization errors instead of masking them as timeouts. (#49032, #49102)
Added background reclamation of unused log database space to reduce disk usage. (#49069)
Original changelogModel List Filters Stale Items with Clearer Credential Configuration and Faster Plugin Loading
Explicit provider model catalogs no longer include unsupported bundled models or reuse stale entries after refresh failures. (#49135)
Clarified how provider credentials use the configured storage backend and how `env_key` identifies the API-key environment variable. (#49118)
Reduced repeated plugin-loading work by caching parsed manifests and reusing HTTP connections for remote plugin requests. (#49099, #49100)