Qoder CN CLI Update Log

Performance and Reliability Improvements

• Improved responsiveness and reduced CPU usage when resuming large sessions and rendering long streaming output
• Limited transcript loading in the session picker to improve performance with large session histories
• Fixed persisted scheduled tasks failing to run after session changes or when multiple sessions are open in the same project
• Labeled scheduled tasks owned by the current session in the OWNER column
• Increased the default /goal maximum interaction turn limit from 20 to 100
• Limited subagent spawning to one nested level by default
• Quest Skills can only be manually triggered by the user via the /quest command

Stability Improvements

• Bug fixes and stability improvements

Permission Mode Behavior Adjustments

• Adjusted permission validation behavior in Auto mode

External Providers and Reliability Improvements

• Supported correct Notification hook triggering during authorization prompts
• Fixed startup progress appearing in the session feed and canceled compaction leaving its progress indicator visible
• Fixed transcript lookup when Windows path casing differs
• Improved recovery after model output reaches the maximum token limit

MCP Authentication and Compaction Fixes

• Fixed MCP authentication expiration not being recognized correctly, and improved the pending-authentication hints in /mcp
• Fixed automatic compaction failing on oversized images

Permission System Fixes

• ACP sessions now offer the same selectable permission modes as the TUI
• Fixed several known permission issues

Permission System Consistency Overhaul

• The permission modes available over ACP now match those in the TUI
• Fixed several known permission issues

Terminal Setup and Input Experience Improvements

• Added the /terminal-setup command in the TUI: it automatically detects and configures the terminal's multiline input capability
• Improved inline command hints and completions
• Improved startup time

Stability Improvements

• Bug fixes and stability improvements

Skills Command Improvements and Context Accuracy

• Improved the skills command: -s and --scope are now consistently supported, and project can be used for the project-level scope
• Fixed skills install, skills link, skills uninstall, skills enable, and skills disable giving no feedback after running
• Improved the accuracy of usage statistics and categorization in /context
• Improved the usability of running /compact manually after switching models
• Fixed custom models (BYOK) being unable to handle images

UltraCode Mode and Startup Speedup

• Added UltraCode mode: Workflow multi-agent orchestration can be triggered with the /effort ultracode command or the ultracode keyword
• Fixed automatic compaction failing
• Improved the parallel tool execution experience: tools in the same parallel batch now show their status as soon as they finish

Auto-Compaction Accounting and Subagent Limits

• Fixed auto-compaction not being triggered
• Added a concurrency limit for subagents, configurable via the QODER_CLI_MAX_CONCURRENT_SUBAGENTS environment variable

Permission Coverage and Search Defaults

• Fixed directories configured with read deny rules still being searchable
• Fixed WebFetch deny/ask rules not taking effect
• Fixed settings.skills.disabled not applying to built-in bundled skills
• Fixed --max-turns not taking effect
• Fixed missing @-file completions and corrected case-sensitivity semantics

History Rewind After Compaction

• Fixed being unable to fork and rewind history messages after compaction

Skills Auto-loading for Added Directories and MCP Approval Fix

• Added automatic loading of skills in a directory added with /add-dir
• Fixed MCP tool calls being approved without a prompt in acceptEdits mode

Auto Mode Upgrade and Spell Checking

• Added an optional spellcheck setting that underlines misspelled English words as you type in the composer
• Improved the Auto mode classifier with a two-stage classification strategy, increasing classification speed and accuracy
• Improved the /mcp and /skills layout: entries are shown one per row, with descriptions displayed at the bottom, so more entries fit on screen
• Fixed the Auto mode classifier silently rejecting all subsequent authorizations after a certain number of consecutive rejections of dangerous actions
• Fixed the skills list being injected twice after resuming from a compaction
• Fixed uninstalled plugins being reinstalled by automatic plugin updates
• Fixed the failure message for an invalid PAT so it names the environment variable it came from and the priority that applied
• Fixed MCP tool result metadata and tool status display being lost

Goal Command, Tab Completion, and Worktree Improvements

• Added support for setting goals directly with /goal <objective>
• Improved slash-command Tab completion
• Improved session saving, restoration, and lifecycle management

Session Mentions, Settings Redesign, and Login Fixes

• Added @-mention of other live sessions in the composer, so you can reference a peer session alongside files and agents
• Improved the /settings layout: settings are shown one per row, with descriptions displayed at the bottom, so more settings fit on screen
• Changed /goal to no longer bind to Auto mode
• Fixed a stream truncated during the model's thinking phase not being retried, which interrupted the task
• Fixed login being blocked for a long time by a credential lock held by another process, and leftover locks are now recovered automatically with a retryable prompt

Tool Call and Session Resume Fixes

• Fixed compatibility issues with streaming tool call events on some models, improving the stability of parallel tool calls
• Fixed session resume taking too long in some worktree scenarios

Tool-Call Compatibility and Display Improvements

• Improved compatibility with some model service APIs, fixing some tool calls being skipped when tool_call_id values were reused
• Improved handling of host names containing non-ASCII characters, such as Chinese host names, with more accurate error messages
• Improved the TaskStop tool call card display, making the task stop status easier to read

Command Guardrails and Tool-Call Reliability

• Added parsing of wrapper commands such as xargs and watch in the Bash tool, so the real command is correctly identified and intercepted
• Fixed pkill -f possibly killing the CLI's own process in interactive sessions on Linux
• Fixed tool calls that take no arguments failing to execute in certain interruption scenarios under interleaved thinking, such as some MCP tools
• Fixed reasoning steps arriving out of order and losing their mapping in streaming output with interleaved thinking and parallel tool calls
• Fixed /goal set failing when the objective description contains command-line options
• Fixed scheduled upgrades still running after auto update was turned off

Plan Confirmations, Cross-Session Messages, and Long-Task Reliability

• Restored the confirmation dialog when entering and exiting Plan mode under auto and yolo modes
• Cross-session messages now show the sender and the message body inline
• Fixed shell task output files growing without limit, which could exhaust disk space
• Improved request timeout handling to resolve long-running tasks being interrupted incorrectly
• Improved diagnostics for abnormal responses, so real upstream errors are no longer hidden
• Improved the stability of multi-agent collaboration

Prompt Draft Stashing and Session Reliability Fixes

• Added Ctrl+S to stash the current prompt draft and restore it later
• Fixed teammate agents losing memory after being woken up
• Fixed EPERM errors when running /branch
• Fixed subagent tasks failing early when their state directory was not readable or writable
• Fixed prompt rendering glitches right after a session resume finished

Cross-Session Messaging and Scheduled Task Budgets

• Added cross-session messaging, so sessions can discover each other and send messages
• Added task budgets for scheduled tasks: set turn and credit limits with parameters, or change them in the panel
• Changed the default theme to auto, which picks the theme from your terminal background and keeps following it as the background changes at runtime
• Improved startup speed
• Fixed marketplace plugin installation failing
• Fixed input starting with an absolute path being misread as a command
• Fixed errors when switching to a non-vision model with image context
• Fixed automatic compaction using the wrong context window size

Cleaner Status Hints and Stability Fixes

• Improved memory saving notices to be less intrusive
• Added ESC to revert an accepted next-step suggestion
• Fixed the TUI possibly freezing when dragging in images that are slow to read or inaccessible
• Fixed some historical sessions failing to resume
• Fixed task failures caused by request interruptions during the model's thinking phase
• Fixed the AbortError crash caused by canceling a request

Status Line Enhancements

• Improved status line performance, with the option to display credits information
• Improved the startup guidance shown for the remote control daemon
• Fixed the subagent display in the TUI task panel
• Fixed /resume possibly hanging for up to 30 seconds

Auto Memory and Stability Improvements

• Added the auto memory switch, which can be enabled in the /settings panel or in settings.json. Once enabled, it automatically saves information worth reusing from conversations for later sessions
• Removed the length limit on custom system prompts passed with --system-prompt
• Improved the model queueing experience
• Improved login reliability

Agent Teams and Long-Session Reliability

• Added Agent Teams for multi-agent collaboration
• Improved task reminders in long sessions
• Fixed automatic context compaction not being triggered
• Fixed the Remote URL display issue
• Improved the Thinking status and Hook display interaction

Model Preferences and Progress Display

• Added per-model memory for reasoning effort and context window settings, which are restored automatically when you switch models
• Added remote ZIP plugin installation, and fixed the plugin status not updating after uninstall
• Added the security scan subcommand, which runs security scan tasks in Headless mode
• Improved the next-step suggestion feature, offering suggestions that better match the current conversation
• Improved session status hints, distinguishing between the Thinking and Generating reply phases
• Improved image paste responsiveness on Windows and macOS
• Fixed resuming a session whose worktree had already been deleted
• Fixed unreadable error messages when context compaction failed

Session Browsing and Scheduled Tasks

• Improved the /resume session browser: aligned shortcuts and clearer session metadata
• Improved the /crontab task panel: added a table header and clearer schedule interval descriptions
• Improved worktree stability
• Improved plugin loading logic
• Fixed duplicated image content when dragging multiple images at once
• Fixed session-level approval of plan mode not persisting

Display Improvements and Stability

• Improved the display pages
• Bug fixes and stability improvements

Service Account Auth and Session-Scoped Tasks

• Fixed persistent scheduled tasks being activated by unrelated sessions, and their owning session can now be managed in /crontab
• Goal creation is no longer globally unique: each session can have its own goal, and /goal take has been removed
• Entering and exiting plan mode no longer triggers a permission popup in Yolo and Auto modes
• The .agents/skills compatibility source is now enabled by default
• Removed the "Memorying..." progress indicator from the UI
• Improved the message shown when a streaming connection is interrupted
• Fixed remote artifacts failing to download on Bun binaries
• Added support for remote-controlled artifact display and download

Session Credits and OAuth Notice

• Added server-reported session credits usage display
• Added a manual authorization reminder before MCP servers start
• Improved keyboard shortcuts for external editor operations
• Improved Bash tool execution efficiency
• Fixed /clear and /new not resetting the persistent Bash working directory back to the startup root
• Added turn progress display in goal mode to improve the interaction experience

Rename, Skill Scanning, and Startup Improvements

• Added support for running /rename while a task is in progress
• Skill directories are now scanned recursively, with a visible warning when a declared directory contains no skills
• Improved startup speed by prewarming the shell snapshot and avoiding repeated loading of slow shell configs
• /logout now clears the login state immediately
• Fixed the external editor (Ctrl+X) failing to open in some integrated terminals such as Cursor
• Fixed input conflicts while a GUI external editor was open — the terminal is no longer handed over
• Improved the Ctrl+O detailed view toggle logic
• Improved /compact command error messages

Loop Scheduling Upgrade and Workflow Improvements

• Upgraded /loop: the agent can now decide wakeup intervals on its own, with support for task persistence
• Added the /crontab command dashboard for viewing and managing scheduled tasks
• Added inline ghost-text completion for skill and slash commands in the input box
• The TaskStop tool now supports stopping running workflows
• Improved the Workflow TUI panel display logic
• Fixed false stall warnings while workflow agents were streaming
• The default permission mode in /settings can now be selected via options
• Fixed known issues with slash command parsing and completion
• Fixed the terminal title being lost on Windows
• Fixed skill directories failing to load when a root-level SKILL.md was present

Prompt Suggestion Toggle and Stability Fixes

• Added a settings toggle to enable or disable prompt suggestions
• Added the .agents/skills compatibility toggle to /settings
• Fixed slash commands being reported as unknown before the command catalog finished loading, and reduced redundant catalog rebuilds
• Showed the full Bash command in the expanded shell output view
• Improved Markdown table row boundary rendering
• Fixed UI freezes when resuming long sessions
• Fixed Monitor notifications not being delivered in time
• Fixed Grep/Glob tool cross-platform compatibility issues

Subtask Command, Feedback Enhancements, and Configurable Directories

• Added the /subtask command for dispatching background subtasks from the current session: the subagent inherits the session context, runs asynchronously, and reports back its result.
• Added /feedback argument support to prefill feedback content
• Added settings configuration to control skill loading from the .agents directory
• Adjusted the default maximum turns of local subagents to 150
• Fixed mobile conversation display issues
• Fixed long MCP user config paths not being fully displayed

MCP Enhancements, Task Management, and Reliability Fixes

• Improved plugin validation and update logic
• Improved Ctrl+B shortcut compatibility
• Added persistent task management
• Improved WebFetch timeout error surfacing
• Adjusted model display name in headless mode
• Improved command-hook process tree teardown

Background Tasks, Terminal Titles, and Input Enhancements

• Improved background task control with monitoring, stopping, and clearer status feedback
• Added the useProxyFromEnvironment setting to toggle reading proxy configuration from environment variables via /settings
• Improved terminal session window title updates
• Added Ctrl+K / Ctrl+U / Ctrl+W line-editing shortcuts in dialog and settings text inputs
• Improved the /resume session picker
• Surfaced argument parsing errors on stderr and aligned unknown-option output
• Fixed the subagent thinking depth setting
• Fixed image reading failures on Linux

Compression, MCP, and TUI Improvements

• Added compression progress display in the TUI to improve the interaction experience
• Added configuration for shell command model responses, disabled by default
• Added timeout control for MCP tools
• Improved permission behavior for referenced files
• Fixed MCP list names being collapsed
• Fixed the viewport not restoring after the suggestion list closes

Workflow Refinements

• Improved workflow pause and resume logic
• Improved Deep Research delivery and queued task dispatch
• Improved startup header and update notification display
• Improved prompts on model refusal

Improvements

• Improved error message display
• Enhanced code security scanning reliability

Security Scan & Model Management

• Officially released native code security capabilities
• Support refreshing the model list on demand via Ctrl + R

Shell & TUI Experience, and Fixes

• Optimized !bash mode execution and output behavior
• Improved the built-in Deep Research workflow
• Optimized underlying network requests to improve reliability and stability

Command Execution, Shell Experience, Exit Cleanup, and Hook Fixes

• Optimized UI rendering during command execution
• Optimized the auto-allow detection logic for read-only shell commands
• Cleaned up unfinished background tasks when the CLI exits
• Fixed an issue where the PreToolUse hook did not take effect in headless and SDK modes

Input Experience and Stability Improvements

• Optimized CLI terminal rendering logic
• Ensured subagents honor the disallowed tools configuration
• Optimized memory usage

Interaction Experience and Startup Stability Improvements

• Improved TUI rendering stability
• Improved the interaction experience for subagent, feedback, remote control, and other features
• Fixed some known startup blocking issues

BYOK configuration and rendering improvements

• BYOK models now support context window and reasoning depth adjustments.
• Added a Plan mode toggle to the /settings dialog.
• Improved streaming rendering performance by caching stable Markdown blocks.
• Fixed color display anomalies between TUI rendering frames.
• Reduced the impact of the status bar marquee on usability.
• Improved worktree stability.

Thinking stability enhancements

• Improved the stability of model thinking processes.

Startup performance and worktree experience improvements

• Optimized the startup mechanism for faster launch.
• Improved the worktree experience.

Workflow, Skills, and permission improvements

• Improved the workflow orchestration experience.
• Added support for installing remote Skill packages over HTTPS.
• Refined the detection scope for redirect commands in the Bash tool.
• Improved error messages.
• Improved the tool-calling experience.

Custom models and model selector enhancements

• BYOK models now support custom model names.
• Improved product interactions and onboarding experience.

Feedback image attachments and experience improvements

• Added image attachment support to the /feedback dialog.
• Improved the exit options for Plan mode.
• Streamlined permission checks for the worktree tool.
• Added a toggle in /settings to enable or disable code usage statistics.

Optimized status bar and model prompts

• Improved UI notification display, including status bar prompts and model list prompts.

Optimized input and display

• On macOS, you can now delete pasted images as a whole block.
• Reduced the impact of status bar promotional messages on scroll control.
• Fixed the display of context usage when resuming a compressed session.
• Improved the default effort label display in the model list.

Improved stability and user experience

• Fixed an issue where a tool's oversized single-line output degraded TUI rendering performance.
• Improved plugin marketplace management.
• Improved TUI display and refined some error messages.

Plugin marketplace and permission mode improvements

• Added support for the plugin marketplace.
• Upgraded the Qoder CN CLI rules type to support both autonomous model decisions and manual inclusion.
• Fixed an issue where the Plan and Ask tools were not correctly disabled in headless mode.
• Fixed an issue where AskUser was silently rejected in auto mode.
• Fixed an issue where the ECS key could not switch from INSERT to NORMAL during streaming output in Vim mode.
• Fixed an issue where secure slash commands did not respond when idle.

Enhanced default permission mode configuration and improved user experience

• The default permission mode now supports `yolo` and `dontask` configurations.
• Fixed an issue where interruption records were rendered repeatedly in the TUI.
• Improved the display of the Background Agent.

Improved Plan mode and model experience

• Added the `--config-dir` parameter to support custom configuration directories.
• Fixed an issue where Plan mode did not support Shell read commands.
• Improved the stability of model requests.

Improved stability and UI experience

• Improved API error messages.
• Improved exception handling for tool calling.
• Improved the UI display and user experience.

Enhanced dynamic workflows and memory function

• Added support for the dynamic workflow feature.
• Added support for `.qoder/rules/**.md`.
• Added user-level Memory and improved the Memory experience in Plan mode.
• Improved the startup speed of Headless mode.

Improved network proxy

• Improved the network proxy mechanism. It now supports HTTP_PROXY, HTTPS_PROXY, and SOCKS5 proxies.

Improved startup performance and model reliability

• Added configuration items for first-packet timeout and stream idle timeout for model Server-Sent Events (SSE) responses.
• Improved the context window backoff policy for models.
• Improved the timeout for the SessionEnd Hook and the failure shutdown policy for PreToolUse.
• Hook validation: Added the required `hookEventName` field to `hookSpecificOutput`.
• Improved the performance of the SDK when retrieving the model list.

Improved model list caching

• Improved the model list caching mechanism.

Improved permissions and command stability

• Fixed an issue where commands were truncated.
• Fixed an issue where Git-related environment variables were cleared during command execution.
• The `/resume` command now adheres to the current permission mode.

Improved welcome page and fixed stability issues

• Improved the welcome page display by adding a marketing and promotion module and model discount notifications.
• Fixed a parsing failure caused by redundant parameters in the Read tool.
• Refactored the download and installation process for Windows Git Bash to improve stability.

Workflow orchestration

• Improved the notification experience for background tasks.
• Fixed an issue with the speech input termination process.

Improved model panel experience and fixed session recovery

• Improved the model selection page.
• Fixed an issue where interruption records were not displayed after using `resume`.

Improved session interruption and permission experience

• Added a session interruption feature. Messages entered during a conversation are now sent immediately.
• Enriched the authorization information displayed in the `/permissions` command panel.
• Improved the loading performance when using `/resume` for very large sessions.
• Fixed an issue where the permission pop-up was incorrectly auto-approved after switching modes.

UI improvements

• Improved the display style of Hook messages in the session stream.
• Improved the interactive experience for model parameter settings.
• Improved the tool permission reminder logic for certain paths.
• The input box content is now retained when you press ECS to exit a terminal dialog.
• Removed the timeout limit for permission requests on the ACP side.

Enhanced Skill commands and models

• Added the built-in skill commands `/run`, `/verify`, and `/run-skill-generator`.
• Added the `/effort` command.
• Aligned the Subagent frontmatter configuration with the existing permission system.
• Fixed an issue where the image recognition tool failed in Node SEA products.

Fixed context warning threshold

• Fixed inconsistent context warning thresholds.

Queue progress and issue fixes

• Added a model queue progress bar chart that shows the elapsed wait time and the estimated maximum wait time.
• Improved the auto compression experience.
• Fixed an issue where the `/context` and status bar percentages were inconsistent in long sessions.
• Improved the display style of Subagents.
• Fixed an issue with the display of error messages when an MCP tool calling exception occurred.
• Improved error detection and prompts for excessive input length.

Improved TLS trust, TUI, and stability

• Added trust for the operating system certificate store and support for custom CA certificates.
• Improved the display of Subagents using event-driven transcript rendering.
• Fixed TUI support for `sendString` input in IDE integrations.
• Improved compatibility with the `screen` terminal multiplexer.
• Performance optimization for `/plan`
• Improved the TUI display performance when resuming large sessions.
• Fixed the Bash stdin redirection behavior.
• Added an error message for HTTPS proxy TLS handshake failures.

Agent sessions enabled by default, Permissions upgrade, and SOCKS5 proxy

• The Agent session feature is now enabled by default.
• Upgraded the `/permissions` command with directory completion, a workspace dialog box, scope-colored labels, and a delete confirmation.
• Added support for SOCKS5 proxy.
• The AskUser dialog box now supports CJK input, and an issue with the cursor reset has been fixed.
• Refactored the background task details panel for structured display and fixed an issue with empty output.
• Plugin hooks are no longer affected by the `--setting-sources` filter.
• Enhanced `asyncRewake` hooks with support for custom messages, automatic fallback in non-interactive mode, and prefix matching.
• `/memory` no longer exposes the actual file path pointed to by a symbolic link.
• Ownership is now restored for `/goal` across `resume`. The goal and permission mode are reset when using `/clear` or `/new`.
• The restored session history is now retained when switching models or inference strengths.
• Fixed a mismatch between MCP environment variable VAR expansion and OAuth discovery resources.

Stability improvements

• Fixed a dependency issue in the npm version.

Plugin path placeholders and issue fixes

• Added `PLUGIN_ROOT` and `PLUGIN_DATA` path placeholder substitution in plugin content.
• Fixed an issue with duplicate warnings when switching permission modes.
• Fixed an issue where project permission rules did not take effect immediately after granting workspace trust.
• Fixed an issue with incorrect control character parsing on Windows.
• Improved startup speed.

Standalone Plan mode and stability improvements

• Plan mode is now independent of the permission loop. Use `/plan` to enter and exit. Shift+Tab now only cycles through permission modes.
• Added a "Start goal execution" option when exiting Plan mode to seamlessly transition to the Goal flow.
• Fixed an issue where a session would permanently freeze if a Hook child process timed out or was aborted.
• Fixed an issue where Goal and Plan states were not correctly restored after a process restart.
• Fixed an issue with incorrect modules in the npm release package.
• Improved the prompt text for switching permission modes and the options for exiting Plan mode.

Model list, activity recommendations, and plugin improvements

• Added the `--model-list` parameter to enumerate available models without a UI.
• Added polling for the model service queue status. The service automatically resumes when it becomes available again.
• Fixed an issue where `Agent(name)` deny rules in the permission configuration were not effective.
• Fixed an issue that occasionally caused session recovery to fail.

Improved YOLO mode and startup performance

• In YOLO mode, `EnterPlanMode`/`ExitPlanMode` no longer triggers a pop-up, and `AskUserQuestion` can be passed through normally.
• Added support for customizing automatic mode classification rules in the settings.
• Fixed a voice reconnection issue to avoid expired WebSocket close events and repeated activation loops, improving stability.
• Improved the experience of launching a browser to log on in Windows.
• Isolated Goal by session to fix crosstalk issues between multiple windows.
• Improved TUI display stability during prompt input completion.
• Reduced the performance impact of automatic updates.

TodoWrite and UI improvements

• Improved the TodoWrite validation recovery mechanism and error messages.
• Unified the color scheme for info messages and fixed the display color of inline code.
• Cancellation prompt messages are now displayed in gray to improve visual hierarchy.
• Fixed several other issues.

Voice polishing and stability improvements

• Added a voice transcription polishing feature to improve input accuracy.
• Improved the experience for Bring-Your-Own-Key (BYOK) providers. Disabled states now show explanations, and model identifiers are clearer.
• Improved the submission confirmation interaction on the Review page.
• Improved the permission denied prompt in YOLO mode.
• Fixed several known issues.

Revamped YOLO mode and permission improvements

• YOLO mode now automatically approves all tool calls without requiring pop-up confirmation.
• The `--tools` parameter now supports multiple values.
• Improved the hierarchy and clarity of the feed stream display.
• Fixed an issue on Windows where a console window would pop up during child process execution.
• Fixed an issue where pasted content in the prompt input was incorrectly parsed as an `@` reference.
• Improved the loading display for Skills and Hooks.

Loop and Hooks are now generally available

• The `/loop` command and scheduled task tool are now generally available.
• The `/hooks` command is now generally available.
• Added support for configuring startup parameters through environment variables.
• Custom Agent names are no longer restricted to the slug format.
• Removed the quantity limit for the `@agents` completion list.
• Improved the status indicator, message spacing, and visual presentation of the chat interface.
• Fixed several other issues.

Performance and stability improvements

• Improved startup performance by reducing startup time through delayed initialization and resource caching.
• Added a TUI interface snapshot to the feedback diagnostic package to provide more complete context information.
• Fixed multiple issues and optimized interactions.

Image search, streaming speech input, and enhanced plugin capabilities

• Added the built-in ImageSearch tool to search for images directly within the Agent.
• Added streaming speech-to-text transcription. Recognized text now flows directly into the input box.
• Improved the experience of the plugin browser for items pending removal and in empty Marketplace scenarios.
• Fixed several other issues and made optimizations.

Stability and experience optimizations

• Added a banner to indicate when the quota is exhausted.
• Improved the stability of network requests and model data transmission.
• Fixed an issue where speech input would terminate recording immediately after disconnection.
• Fixed a parameter schema parsing failure for built-in tools with Qwen series models.
• Fixed several other issues.

Stability improvements

• Fixed a runtime exception in the npm package caused by a tagged template encoding error.

Voice, Remote, and interface fixes

• Fixed an issue where transcribed text flickered during voice recording and changed the behavior to insert the transcribed text at the cursor position.
• Improved the performance of Agent task execution.

Goal, voice, and stability fixes

• Fixed stability issues related to speech input (recording tool detection, termination timeout, multi-segment input handling).
• Improved the stability of the model calling service.
• Fixed an issue where the working directory was not correctly synchronized in Worktree sessions.
• Fixed an issue where a permission confirmation would incorrectly pop up when accessing project configuration files in automatic permission mode.

Voice and stability fixes

• Added the ElicitationResponse Hook notification type.
• Fixed stability issues in voice mode.
• Fixed an issue where session title generation failed when the compact model was unavailable. It now automatically falls back to the chat model.
• Fixed a race condition at startup in the BYOK model directory.

Introducing Qoder CN CLI 1.0

• Cloud runtime: Added support for the `qodercli --remote` flag. Cloud mode lets you submit tasks to a cloud container for one-time execution. The workflow continues to run for hours even if you shut down your machine or lose your network connection.
• RepoWiki: Added support for the `qodercli wiki` subcommand to generate repowiki documents locally without your code leaving your domain.
• Voice: Added support for the `/voice` command. The speech input feature is fully upgraded and available for free.
• Goal: Added support for the `/goal` command to keep long-running, goal-oriented tasks on track.
• Open model parameters: You can now customize `efforts` levels and set a 1M context window.

• Agent SDK: Supports TypeScript and Python. Integrate full Agent capabilities with just a few lines of code. Provides programmatic control, including tool authorization callbacks, pre-execution interception, and parameter modification.
• Cloud Agents: Agents as a Service. Built-in features include sandbox isolation, state management, asynchronous orchestration, credential management, and a long-running platform.

• Orchestration: Tasks are automatically split and executed in parallel by multiple Agents. The main Agent determines the splitting policy, and Subagents run in independent event loops.
• Extensions: Supports five orthogonal extension points: Skills, Hooks, MCP, Subagent, and Command.
• Autonomy: The Agent assesses risks on its own and only requests confirmation for critical nodes. Automatically routes requests to Large Language Models (LLMs), Small Language Models (SLMs), or Vision Language Models (VLMs).
• Integration: Supports three integration modes: Headless (for unattended CI/CD), ACP (for standard bidirectional communication), and SDK (for TypeScript/Python).

MCP Elicitation and stability fixes

• Added MCP elicitation bridge support. The MCP server can now prompt the user for input in remote requests.
• Fixed a TUI rendering crash issue.
• Fixed hook execution and other stability issues.

Automatic mode improvements

• Added an automatic mode option during plan approval. You can now switch to automatic mode directly in the approval dialog box.
• In automatic mode, reading files outside the workspace no longer triggers a permission prompt. Writing to files outside the workspace is now directly denied.
• Fixed an issue where automatic mode was not effective for Subagent tool calls in plan mode.
• Fixed an issue where the denied status was not cleared when the `/permissions` dialog box was closed.

Automatic permission mode, Insights, and Windows stability improvements

• Added an automatic permission mode. The LLM classifier automatically approves safe tool calls to reduce permission pop-ups.
• Session recovery now supports Worktree state persistence and cross-Worktree discovery.
• External commands can now receive workspace paths, authentication contexts, and Registry environment variables.
• Fixed an issue on Windows where ConPTY would freeze in text input dialog boxes (AskUserQuestion, BYOK wizard).
• Fixed an issue on Windows where Shift+Tab was unusable in VT mode (reverted to Meta+M).
• Fixed an issue on Windows where Ctrl+V pasting failed in the BYOK wizard under conhost.
• Fixed an issue where left and right arrow keys were not working in AskUserQuestion text input.
• Fixed an issue where ECS could not cancel a running `/insights` execution.
• Fixed an issue where MCP tool calls failed if the parameter name contained special characters (key name filtering and reverse mapping).
• Fixed an issue where MCP images were lost when output was truncated.
• Fixed an issue where custom model keys (BYOK) were not sent correctly to API requests.
• Fixed an issue with empty user messages caused by the memory injection order at startup.
• Fixed an issue with incorrect QR code rendering in older Windows consoles (compact ASCII fallback).
• Fixed an issue where `--setting-sources` did not support an empty string to disable all sources.
• Fixed a WSL 1 compatibility issue by upgrading Bun to 1.3.14.

Side questions, automatic approval for read-only commands, and platform fixes

• Added the `/btw` side question feature to ask quick questions without interrupting the main conversation.
• Read-only Shell commands are now automatically approved, reducing redundant permission pop-ups for some tools.
• The Worktree isolation feature is now enabled by default.
• Fixed an issue where the context progress bar chart was not updated after `/compact`.
• Fixed an issue where the input box was not cleared after executing the `/compact` command.
• Fixed a color overflow issue when moving the cursor in macOS Terminal.app.
• Fixed an issue with garbled QR code rendering on Windows.
• Fixed an issue on Windows where batch text input caused character loss or incorrect character order.
• Fixed an issue where unsupported shells such as fish were incorrectly used as the Bash tool backend.
• Fixed an issue where the behavior of the `-w` parameter was inconsistent with `--workspace`.
• Fixed an issue in the TUI where deleting a hook mistakenly deleted all hooks with the same command.

Worktree isolation mode and context progress bar improvements

• Added Agent worktree isolation mode. Subagents can now run in an independent git worktree, with support for the `-w` parameter, an interactive exit dialog box, and automatic cleanup on exit.
• Added a default context token usage progress bar chart to the status bar to display real-time context window usage.
• Fixed an issue where the context window progress bar chart would reset to zero, flicker, or display incorrect values during compression, Subagent execution, and session recovery.
• Fixed an issue where Hook permission decisions did not correctly follow the rule configuration in `settings.json`.
• Fixed an issue where the session was incorrectly interrupted when the model returned an empty response. It is now handled as a normal termination.
• Fixed a session title generation timeout on slow networks. The timeout has been extended to 180 seconds.

Network reliability improvements

• Improved network degradation handling. The system now attempts the original URL before falling back to the resolved IP address.

Connection stability and interface fixes

• Added automatic retry for 504 Gateway Timeout.
• Improved the path display in the permission dialog box to unify the three-level path format.
• Improved the status display for unauthorized servers in the MCP list.
• Fixed an issue where content was duplicated when the terminal was resized in full screen mode.
• Fixed an issue where the status was not correctly persisted after canceling a Subagent with ECS.
• Fixed an issue where double-dot prefix directory names were incorrectly handled in the workspace boundary check.

Automatic backgrounding, Status command, and stability fixes

• Added the `status` subcommand to view CLI connection and session status.
• Timed-out Bash commands are now automatically moved to run in the background, and a notification is sent upon completion.
• Improved the help text for the `--model` option with clearer usage instructions.
• Fixed an issue in Vim mode where ECS could not cancel a running session or Shell execution.
• Fixed a UI stacking issue when resizing the terminal window on Windows.
• Fixed an issue where reading a file still required authorization after adding a trusted directory with `/add-dir`.
• Fixed an issue where re-authentication was not possible after revoking an MCP OAuth token (401 token residue).
• Fixed an issue where the status indicator did not disappear after a Hook execution finished.
• Fixed an issue where the compression summary was mistakenly displayed in the TUI after `/resume`.
• Fixed an issue where Subagents in remote control mode did not correctly handle session reconnection.
• Fixed an issue where reading files through symbolic links could bypass permission boundaries.

HTTP proxy support and Shell mode fixes

• Added HTTP proxy support for users in corporate proxy environments.
• Added support for canceling running commands in bash mode with Ctrl+C and ECS.
• The slash command suggestion list is now sorted alphabetically.
• Improved the status display for unauthorized MCP servers.
• Fixed an issue where duplicate output in bash mode caused the UI to freeze.
• Fixed an issue where content could not be pasted into shell mode.
• Fixed an issue where vim ECS failed to exit INSERT mode.
• Fixed an issue where `/resume` loaded too much history beyond the compression boundary.
• Fixed an Apple Silicon architecture detection error when the installation script was run under Rosetta.

Stability and issue fixes

• Fixed a process crash issue caused by network jitter (connection-level retry + runtime avoidance).
• Fixed an issue where the Bash tool output file grew indefinitely.
• Fixed an issue where the PermissionRequest hook was triggered twice.
• Fixed a navigation freeze issue in the `/hooks` TUI caused by a duplicate key.
• Fixed an issue where the input box disappeared and messages were lost during TUI compression.

TUI permission dialog box improvements

• Improved the interaction experience and rendering stability of the TUI permission dialog box.
• Fixed an incorrect display of the Subagent running status indicator.

BYOK, permissions, and remote control

• BYOK custom URL: You can now bring your own API key and specify a custom inference endpoint.
• Remote control is now enabled by default.
• TUI improvements: Cursor handling, authentication manager, and interface optimizations.
• A dots animation status is now displayed during Subagent runtime.
• The `-m` model parameter is now strictly validated at startup (case-sensitive matching).
• Added support for subcommand-level permission checks for composite Bash commands.
• Disabled the auto-memory feature.
• Fixed an issue where the Hook process would suspend.
• Fixed an issue where Hook permission decisions were discarded on partial failure.
• Windows: Fixed a `stderr` leak from `where.exe` when `rg` is not in the PATH.
• Fixed several other bugs and improved stability.

Hotpatching

• Switched to an OSS accelerated domain name to improve download speeds.

Plugins and stability

• Plugin variable substitution: Added support for `PLUGIN_ROOT`/`PLUGIN_DATA` variables in hooks and MCP configurations.
• Improved the precision and display of the `/context` panel.
• Added `getEffectiveContext()` to Hook output, with support for `systemMessage` fallback.
• Fixed an issue where the `--agent` system prompt was not effective in TUI/headless mode.
• Fixed an issue where the model selector did not display all options.
• Fixed a crash issue with `/resume` when the diff format was incorrect.
• Fixed an issue where reading a plan file in Plan mode required permission confirmation.
• Fixed a listener overflow warning triggered during concurrent tool confirmations.
• Fixed an issue where the active version was mistakenly cleaned up after a cross-channel update.
• Added a Linux x64-baseline build target to support CPUs without AVX instruction sets.
• Fixed several other bugs and improved stability.

Command stability

• Fixed an issue where the `/tasks` command could not be exited.
• Fixed other known issues to improve stability.

Hook and platform fixes

• Fixed a Hook execution failure issue.
• Fixed an issue where the line break keyboard shortcut was invalid in the default macOS terminal.
• Fixed an issue where Hook JSON output was not effective.
• Fixed a logon error when using `xdg-open`.
• Fixed an issue where built-in Skills were missing during packaging.

Upgrades for multi-model support, extensibility, new experience, and more

• New TUI interactive interface: Supports a wide range of keyboard input operations and lets you freely customize your favorite status bar.
• New permission management system: Flexibly switch between Plan Mode and multi-project management (`/add-dir`).
• Multi-model support: Integrates with leading state-of-the-art (SOTA) models, supports BYOK, and is no longer tied to a single model.
• Comprehensive built-in commands: Over 50 built-in shortcut commands to easily handle daily work tasks.
• Conversational configuration creation: Generate MCP, Subagent, Skill, or Hook configurations with a single sentence, eliminating the need to write JSON by hand.

Startup performance and stability improvements

• Implemented permission request queuing and sequential display for concurrent Subagents.
• Fixed a startup block issue on slow network responses.
• Fixed an issue where the CLI could not start if the `.qoder.json` configuration file was corrupted.
• Added support for image data output in SDK mode.

Removed Code Review limits

• Free subscription users can now use the `/review` and `/setup-github` features.
• Fixed several issues.

Thinking rendering and support

• Added rendering for the Thinking inference process to display the model's thought process in the conversation.
• Adjusted hooks to be executed through git bash on Windows.
• Improved the download and installation method for git bash on Windows to increase installation speed.

Support for custom models

• Added support for custom models. You can now connect to the Coding Plan of model providers such as Alibaba Cloud Model Studio.

Skills and MCP enhancements

• Added support for loading Skills from the `.agents` directory.
• Added support for Skills through symbolic links.
• Added the ability to automatically infer the MCP Server type.
• The results of the `/compact` command are now hidden. You can press Ctrl+R to expand and view them.

New model support

• Added support for Alibaba's latest model, Qwen 3.5 Plus.

New model support

• Added support for the new MiniMax model.
• Fixed a WebFetch tool execution error.

New model support

• Added support for a new model.
• Improved the generation rules for Todo tasks.
• Improved the logic for viewing MCP tool execution results.

Configuration loading optimization

• Improved the loading order of resources such as skills and commands.

Enhanced configuration capabilities

• Added the ability to create Subagent Skills.
• Added the `mcp auth` subcommand for identity verification with MCP servers that support OAuth.
• Added the `--mcp-config` parameter to load MCP server configuration from a JSON string.

BUG fixes

• Refactored the implementation method of the Glob tool.
• Fixed an issue where a session could not continue due to an abnormal image.
• Fixed an issue where a request would fail because a tool execution occasionally produced no result.
• Fixed an issue where switching accounts in a multi-process runtime would affect each other.
• Fixed an issue where executing the `/upgrade` command under the Teams plan resulted in a permission error.

BUG fixes and optimizations

• Improved the estimation logic for token usage by images in the context.
• Fixed an `rg` execution error in the Linux ARM64 environment.
• Fixed a panic issue caused by an MCP configuration error.
• Fixed a display issue with the `mcp query` subcommand.

BUG fixes

• Added the `--with-claude-config` parameter to support loading Claude Code Skills, Commands, and Subagents.
• Increased the priority of using the zsh shell on the macOS platform.
• Fixed some TUI execution panic issues.

BUG fixes

• Fixed a file retrieval error on macOS with some Arm chips.
• Fixed an issue where the Glob tool could not be canceled during a file search.
• Addressed a potential context limit issue caused by switching models.
• Added logic for Bash tool execution log persistence and viewing.
• Improved the AskUserQuestion implementation to increase model calling accuracy.
• Fixed a relative path recognition error with the `-w` parameter.

Skills support

• Added the `/skills` command to view user and project-level Skill configurations.
• Added the `--agents` parameter to pass subagents configuration at startup.
• Improved the TUI Markdown content rendering style.
• Fixed an issue where the trailing line feed was lost after editing a file with the Edit tool.
• Fixed a Bash tool execution exception on some older Windows systems.
• Fixed a TUI Bash Mode command streaming output issue.
• Fixed an issue where TUI Bash Mode could not execute multi-line commands.
• Removed the minimum TUI window size limit.
• Fixed an issue where some historical sessions could not be restored with the `/resume` command.

Conversation export support

• Added the `/export` command to export conversation history.
• Added a mechanism to automatically download and configure the git-bash environment on Windows.
• The status bar now displays the current working path.
• Enhanced the TUI interaction for the AskUserQuestion tool.
• Enhanced the context compression mechanism.
• Fixed some known issues.

BUG fixes and experience optimizations

• The `/usage` command now displays the expiration date of the user's plan.
• Improved the Bash command parsing logic.
• Fixed an issue where the conversation could not continue after canceling a task under some models.
• Fixed an issue where the http/https protocol prefix was missing from TUI tool parameters.
• Fixed an Init command issue with Zed integration.

ACP support

• Added support for the ACP protocol, which can be enabled with `--acp`.
• Added support for streaming loading of TUI tool parameters.
• Fixed a Subagent configuration file parsing error.

Enhanced model configuration

• Added support for setting the maximum output token length (with the `--max-output-tokens` parameter and the `/config` configuration item).
• Added the `--model` parameter to support specifying a model at startup.
• Fixed an issue where OAuth authorization failed for some MCP Servers.
• Optimized TUI display for the /model command

Model tier support

• Added the `/model` command to support switching between model tiers.
• Improved the Edit tool validation logic to increase file modification efficiency.
• Improved some TUI content display effects.
• Fixed an issue where input records containing `@` file references could not be restored.

BUG fixes and experience optimizations

• Added the `attachments` startup parameter in Headless mode to support adding image attachments.
• Removed the logic that automatically generates a permission configuration file when a new working directory is opened.
• Added a retry mechanism for failed inference requests.
• Fixed other known issues and made product optimizations.

TUI performance optimization

• Improved the conversation message caching mechanism to enhance TUI rendering performance.
• Fixed a panic issue after the Webfetch tool was denied.
• Fixed a TUI rendering issue in the Windows WSL environment.

Github CodeReview feature released

• The Github CodeReview feature is now officially released.
• Added version and other field information to message records.
• Made some issue fixes and product optimizations.

Tool permission improvements

• Permission is now requested when the execution result of a tool (including MCP tools) is too large.
• Fixed an issue where the built-in ripgrep executed abnormally in the Linux environment.
• Adjusted the log output location and fixed some other known issues.

BUG fixes and general improvements

• Removed incremental messages from the stream-json format output in Headless mode.
• Removed the write back of environment variables such as QODER_CURRENT_WORKDIR in the configuration file.
• Fixed a display error caused by multi-line descriptions in Subagent and Command.
• Fixed an issue on the Windows platform where added attachments could not be deleted.

Streaming output and Ultra subscription plan support

• Added support for the Ultra subscription plan.
• Added a code syntax highlighting feature.
• Implemented streaming output and improved TUI rendering performance.
• Added support for executing `/` commands in headless mode.
• Improved the error handling mechanism of the Read tool when processing image files.
• Fixed a path compatibility issue with the Read tool in the Cygwin environment.
• Fixed a long-running block issue with the WebFetch tool when processing large web pages.

Feature improvements and error fixes

• Added support for reporting Credits usage.
• Added version update notifications to the welcome page.
• Changed the default permission path for initialization to a relative path.
• Fixed an error that occurred when the Glob tool search results exceeded 200 items.

Qoder personal access token support

• Added support for logging on with a Qoder personal access token.
• Improved the performance of pasting large blocks of text on the Windows platform.

Windows compatibility fixes

• Fixed a Windows file modification failure issue caused by CRLF line feeds.
• Enhanced the error messages for failures in custom Subagent and Command.

Unlocked Windows Terminal usage limits

• Removed the usage restrictions for CMD and PowerShell terminals on Windows.
• Improved the line feed insertion logic to achieve auto wrap at any position.
• Fixed a panic error that occurred when using the `/resume` command in a new project directory.
• Enhanced the Command and Subagent generation process to improve the accuracy of result parsing.

OAuth MCP support

• Added OAuth MCP integration support for the `/mcp` command.
• Increased the default output token limit from 8K to 16K.
• Updated the `/bashes` command to display only background tasks.

Unlock IDE Terminal usage limits

• Improved the interactive interface of the `/login` command.
• Removed the usage restrictions for JetBrains and VS Code terminals on Windows.
• Fixed an issue where the WebFetch tool caused the Agent loop to exit unexpectedly.
• Improved the error messages for request-related failure scenarios.

Model accuracy and user experience optimizations

• Removed `@` symbol references from sent content to improve model accuracy.
• Fixed an issue where the agent loop could still run after Bash-related tools were denied permission.
• Added user-friendly prompts for common abnormal scenarios.

Installation fixes and some improvements

• Fixed npm package installation issues on Windows and Linux platforms.
• Fixed a crash issue after logon for some long-time users.
• Fixed an abnormal Backspace key behavior in special modes when the cursor is at the beginning of a line.
• Enhanced the TUI display and improved the text content to enhance the overall user experience.

Welcome to Qoder CN CLI!

• Quest Mode: Hand off complex tasks to me. Just describe your needs, and I will design solutions, implement code across files, run tests, and deliver runnable results. This lets you focus on what matters most while I handle the rest.
• Agent Mode: Code through conversation. Ask me anything about your project. I can help you debug, refactor, or implement new features, with you in full control. I provide instant, accurate answers with full code context.
• Custom Commands & Subagents: Turn repetitive workflows into executable commands. Whether it is generating database migration scripts, updating documentation, or running security checks, your team's knowledge becomes automated power.
• Seamless Integration: I fit perfectly into your existing workflow. I support Git by default, am natively compatible with Shell, and can be easily integrated into CI/CD pipelines. I work with the tools you love.