Dahawa Life Plan
- An intelligent programming assistant who understands you
- An intelligent assistant who understands you
- An assistant who understands you
One is the bottom line you leave for yourself
Version History
1.37.4 (2026-06-07)
- Optimized hands tool local rendering
1.37.0 (2026-06-03)
- Support Goal slash command
- Stop Hook added last_assistant_message parameter
1.36.0 (2026-05-24)
- Support built-in Hands tool, directly launch with hands command without installing mcp
1.35.5 (2026-05-21)
- Fixed Edit tool code line misalignment bug during file comparison
- Support Http request strong proxy
- Support custom use agent, support authorization, x-api-key
- Support enabling hawa code built-in computer use via environment variables
1.35.0 (2026-05-16)
- Support setting openai image detail via environment variables
1.32.0 (2026-05-08)
- hawa code fully supports windows, skill, slash commands, user instructions all support powershell
- Fixed image paste bug
1.31.4 (2026-05-08)
- Optimized hawa code update performance on windows
1.31.3 (2026-05-08)
- Optimized Shell execution performance
1.31.2 (2026-05-07)
- Optimized tool lazy loading performance
- Fixed openai response request bug
1.31.0 (2026-05-07)
- Support automatic tool unloading in tool lazy-loading mode
- Support switching thinking depth
- Compatible with OpenAI Responses API search
- Fixed OpenAI Chat Completions thinking protocol conversion bug
- Optimized multi-model token compression estimation
- Support multi-model load balancing
1.28.0
- Support PowerShell tool
- Support memory recall during query
- Agent Team idle messages suppression
- Memory slash command supports manual memory clearing
1.27.0
- autoDream supports team memory
- autoMemory supports automatically recalling up to 5 relevant memories before Query
- Support
/memoryslash command to manage memory feature toggle and memory files - Support auto permission mode, where the model autonomously judges and authorizes tool execution
- Support
/autoslash command to quickly enable auto mode - Support switching auto mode via terminal shortcut
- Optimized error log output
1.26.0
- Support session memory auto-extraction (autoMemory), currently disabled by default
- Support session memory auto-consolidation (autoDream), currently disabled by default
1.25.3
- Support session summary compression mode
- Fixed resume slash command displaying duplicate messages BUG
1.24.0
- Support git worktree tool
- Subagent supports git worktree
- Fixed agent team tab switching loading position exception error
1.23.0
- Fixed Agent Team Tab logo not displaying issue
- Optimized terminal rendering performance
1.22.8
- Fixed auto-compression bug
- Fixed bash path issue
1.22.5
- Fixed tree-sitter-bash test session not working
1.22.3
- Optimized compression messages
- Fixed TreeSitterNode path bug
1.22.2
- Added permission bypass in acceptEdits mode, allowing all files without file restrictions
- Fixed permission path matching issues
1.22.1
- Message logs support linked list association
- Fixed error log printing BUG
- Fixed Kimi process crash BUG
1.22.0
- Optimized message log storage performance
- Fixed terminal message display disorder BUG
1.21.0
- Fixed some tool configuration permission exception bugs
1.20.0
- Support autoAllowBashIfSandboxed parameter, if sandbox is enabled, Bash no longer requires verification
- Permission configuration supports ask setting, can force tool execution to require user confirmation
- In bypassPermissions mode, writing to .git, .hcode, .vscode, and .idea directories will still prompt for confirmation, but writing to .hcode/commands, .hcode/agents, and .hcode/skills is exempted
- Support disableBypassPermissionsMode parameter to disable bypassPermissions mode
- Use tree-sitter-bash to interpret shell, optimizing parsing performance
- Fixed shell prefix matching BUG
- Support saving shell as multiple subcommands, no longer a single named exact match
1.19.0
- Support sandbox, which can isolate network and disk files. Users can specify safely accessible domains and allowed disk file methods.
- Support sandbox slash commands.
1.18.0
- Skill dynamic parameter replacement: $ARGUMENTS, $ARGUMENTS[N], $N, ${HCODE_SESSION_ID}, ${HCODE_SKILL_DIR}
- Skill supports disable-model-invocation and user-invocable parameter configuration
- Skill supports !
commanddynamic shell execution
1.17.0
- Skill supports context fork parameter using subagent execution, supports agent parameter
1.16.0
- Plan mode supports local file storage, storage path is ~/.hcode/plan
- Added plan command, can enter plan mode via plan command
- Agent Team supports mode parameter
- Support Read and Edit tool permission configuration
1.15.0
- Support scheduled task scheduling
1.14.0
- Support automatic memory - Hawa Code will automatically extract memories from conversations, and memories support cross-session persistence.
1.13.5
- Fixed bug where enabling Agent Team but Tasks were not enabled
1.13.4
- Optimized Agent Team list display
1.13.2
- Support displaying Agent Team member messages in terminal
1.13.1
- Agent Team automatically enables Tasks feature
- Tasks list now displays owner information
1.13.0
- Support Agent Team
1.12.2
- Added support for SessionEnd Hook
1.12.1
- Added support for SessionStart Hook
- Fixed TODO restoration bug
1.12.0
- Task planning mode upgraded from TodoWrite to Tasks, supporting local file storage and cross-session communication
- Fixed terminal title display anomaly
- Optimized tool name usage
1.11.3
- Fixed Subagent deadlock issue
- Optimized log output performance
1.11.2
- Added PostToolUse Hook to support triggering custom actions after successful tool execution
- Added PostToolUseFailure Hook to support triggering custom actions when tool execution fails
- Optimized Hook Matcher matching performance
1.11.1
- Support lazy loading of tool inputScheme to optimize startup time
- Optimized Task Tool progress display to resolve terminal flickering issues
- Support disabling Prompt hint functionality
- Fixed bug with duplicate message publishing
- Fixed bug with duplicate system reminder messages
- Optimized tool execution performance
1.11.0
- Support PreToolUse Hook
1.10.2
- Added keyboard shortcut to move tasks to background execution
- Added support for toggling background task notifications
- Improved Markdown rendering
- Added real-time output display for shell execution
- Fixed inaccurate background shell task count display
1.10.0
- Added TaskStop tool to support stopping background subagent tasks and shell task execution
- Removed KillShell tool
- Support re-initiating conversation after background shell tasks complete
- Support displaying background shell task count
- Fixed background subagent conversation re-initiation freeze issue
1.9.3
- Support SubagentStart hook
1.9.2
- Support Stop and SubagentStop hooks
1.9.0
- Support user-level rules, project-level rules, and on-demand loading by path
- Support startup commands
- Optimized message notifications
1.8.0
- Optimized terminal MCP automatic authorization configuration
1.7.0
- Remote MCP supports automatic authorization
- Improved usage in GitHub Codespaces
- MCP Tool permissions.allow supports wildcard settings
- Enhanced compatibility with non-standard JSON and incorrect JSON formats in Tool input and Qwen-code-plus
1.6.0
- Support MCP Tool lazy loading
- Fixed Task Tool verbose mode crash bug
- Optimized network request retry performance
1.5.0
- Support settings.json configuration with hot reload
1.4.0
- AskUserQuestion tool supports multiple questions and custom input
- Enhanced Grep Tool functionality
1.3.0
- Support providing prompt suggestions at the end of conversations
1.2.0
- Support submitting prompt statements during conversation
1.1.0
- Support subagent background execution
- Support subagent resume execution
- Optimize LSP tool file path validation
1.0.16
- Optimized tool lazy loading performance
- Optimized LSP tool terminal display
1.0.15 Restore TODO LIST along with session