- Filter out old [PLAN MODE ACTIVE] and [EXECUTING PLAN] messages
- Fresh context injected via before_agent_start with current state
- Agent now correctly sees tools are enabled when executing
- Reverted to ID-based tracking with [DONE:id] tags
- Simplified execution message (no need to override old context)
- Add explicit [PLAN MODE DISABLED - EXECUTE NOW] message
- Emphasize FULL access to all tools in execution context
- List remaining steps in execution context
- Prevents agent from thinking it's still restricted
- Remove ugly [DONE:id] tags - users no longer see IDs
- Track progress via keyword matching on tool results
- Extract significant keywords from todo text
- Match tool name + input against todo keywords
- Sequential preference: first uncompleted item gets bonus score
- Much cleaner UX - progress tracked silently in background
- New text_delta hook event fires for each chunk of streaming text
- Enables real-time monitoring of agent output
- Plan-mode hook now updates todo progress as [DONE:id] tags stream in
- Each todo item has unique ID for reliable tracking
- Each todo item gets a unique ID (e.g., abc123)
- Agent marks items complete by outputting [DONE:id]
- IDs shown in chat and in execution context
- Agent instructed to output [DONE:id] after each step
- Removed unreliable tool-counting heuristics
- After agent creates plan: show todo list as a message in chat
- During execution: show widget under Working indicator with checkboxes
- Check off items as they complete with strikethrough
- ctx.ui.setWidget(key, lines) for multi-line displays above editor
- Widgets appear below 'Working...' indicator, above editor
- Supports ANSI styling including strikethrough
- Added theme.strikethrough() method
- Plan-mode hook now shows todo list with checkboxes
- Completed items show checked box and strikethrough text
- Extract numbered steps from agent's plan response
- Track progress during execution with footer indicator (📋 2/5)
- /todos command to view current plan progress
- State persists across sessions including todo progress
- Agent prompted to format plans as numbered lists for tracking
Hook API additions:
- pi.getTools() / pi.setTools(toolNames) - dynamically enable/disable tools
- pi.registerFlag(name, options) / pi.getFlag(name) - register custom CLI flags
- pi.registerShortcut(shortcut, options) - register keyboard shortcuts
Plan mode hook (examples/hooks/plan-mode.ts):
- /plan command or Shift+P shortcut to toggle
- --plan CLI flag to start in plan mode
- Read-only tools: read, bash, grep, find, ls
- Bash restricted to non-destructive commands (blocks rm, mv, git commit, etc.)
- Interactive prompt after each response: execute, stay, or refine
- Shows plan indicator in footer when active
- State persists across sessions
- Add pi.getTools() and pi.setTools(toolNames) to HookAPI
- Hooks can now enable/disable tools dynamically
- Changes take effect on next agent turn
New example hook: plan-mode.ts
- Claude Code-style read-only exploration mode
- /plan command toggles plan mode on/off
- Plan mode tools: read, bash, grep, find, ls
- Edit/write tools disabled in plan mode
- Injects context telling agent about restrictions
- After each response, prompts to execute/stay/refine
- State persists across sessions
- pi.sendMessage(msg, options?) now accepts { triggerTurn?, deliverAs? }
- deliverAs: 'steer' (default) or 'followUp' controls delivery timing
- Update all mode handlers to pass options through
- Update file-trigger example to use new API
- Update CHANGELOG
- /todos command displays all todos on current branch with custom UI
- Update hooks.md to clarify components must not be wrapped in Box/Container
- Cross-reference tool and hook in example READMEs
Move line count from header to footer to avoid changing the first line
during streaming, which was triggering full screen re-renders in the
TUI's differential rendering logic.
Transfers context to a new focused session instead of compacting.
User provides a goal, hook generates a prompt with relevant context,
creates a new session with parent tracking, and loads the prompt
as a draft in the editor for review.
Inspired by Amp's handoff feature.
- Remove session_before_new and session_new hook events
- Add reason: 'new' | 'resume' to session_before_switch and session_switch events
- Remove 'new' reason from custom tool onSession (use 'switch' for both /new and /resume)
- Rename reset() to newSession(options?) in AgentSession
- Add NewSessionOptions with optional parentSession for lineage tracking
- Rename branchedFrom to parentSession in SessionHeader
- Rename RPC reset command to new_session with optional parentSession
- Update example hooks to use new event structure
- Update documentation and changelog
Based on discussion in #293
- Add theme property to HookUIContext interface
- Implement in interactive, RPC, and no-op contexts
- Add status-line.ts example hook
- Document styling with theme colors in hooks.md
- Add setEditorText() and getEditorText() to HookUIContext for prompt generator pattern
- custom() now accepts async factories for fire-and-forget work
- Add CancellableLoader component to tui package
- Add BorderedLoader component for hooks with cancel UI
- Export HookAPI, HookContext, HookFactory from main package
- Update all examples to import from packages instead of relative paths
- Update hooks.md and custom-tools.md documentation
fixes#350
- CustomAgentTool renamed to CustomTool
- ToolAPI renamed to CustomToolAPI
- ToolContext renamed to CustomToolContext
- ToolSessionEvent renamed to CustomToolSessionEvent
- Added CustomToolContext parameter to execute() and onSession()
- CustomToolFactory now returns CustomTool<any, any> for type compatibility
- dispose() replaced with onSession({ reason: 'shutdown' })
- Added wrapCustomTool() to convert CustomTool to AgentTool
- Session exposes setToolUIContext() instead of leaking internals
- Fix ToolExecutionComponent to sync with toolOutputExpanded state
- Update all custom tool examples for new API
Compaction API:
- prepareCompaction() now takes (pathEntries, settings) only
- CompactionPreparation restructured: removed cutPoint/messagesToKeep/boundaryStart, added turnPrefixMessages/isSplitTurn/previousSummary/fileOps/settings
- compact() now takes (preparation, model, apiKey, customInstructions?, signal?)
- Fixed token overflow by using getPath() instead of getEntries()
Hook types:
- HookEventContext renamed to HookContext
- HookCommandContext removed, RegisteredCommand.handler takes (args, ctx)
- HookContext now includes model field
- SessionBeforeCompactEvent: removed previousCompactions/model, added branchEntries
- SessionBeforeTreeEvent: removed model (use ctx.model)
- HookRunner.initialize() added for modes to set up callbacks
Major changes:
- Replace monolithic SessionEvent with reason discriminator with individual
event types: session_start, session_before_switch, session_switch,
session_before_new, session_new, session_before_branch, session_branch,
session_before_compact, session_compact, session_shutdown
- Each event has dedicated result type (SessionBeforeSwitchResult, etc.)
- HookHandler type now allows bare return statements (void in return type)
- HookAPI.on() has proper overloads for each event with correct typing
Additional fixes:
- AgentSession now always subscribes to agent in constructor (was only
subscribing when external subscribe() called, breaking internal handlers)
- Standardize on undefined over null throughout codebase
- HookUIContext methods return undefined instead of null
- SessionManager methods return undefined instead of null
- Simplify hook exports to 'export type * from types.js'
- Add detailed JSDoc for skipConversationRestore vs cancel
- Fix createBranchedSession to rebuild index in persist mode
- newSession() now returns the session file path
Updated all example hooks, tests, and emission sites to use new event types.
Hook commands now always execute immediately, even during streaming.
If a command needs to interact with the LLM, it uses pi.sendMessage()
which handles queueing automatically.
This simplifies the API and eliminates the issue of queued slash
commands being sent to the LLM instead of executing.
- Removed Attachment from agent package (now in web-ui/coding-agent)
- Agent.prompt now takes (text, images?: ImageContent[])
- Removed transports from web-ui (duplicate of agent package)
- Updated coding-agent to use local message types
- Updated mom package for new agent API
Remaining: Fix AgentInterface.ts to compose UserMessageWithAttachments
- Full box border around title, game area, and instructions
- ESC pauses and saves state to session via pi.appendEntry()
- Resume shows 'PAUSED - press any key to continue'
- Q quits and clears saved state
- High score persists across games
- Rounded box corners (╭╮╰╯)
- Better characters: ● head, ○ body, ◆ food, · empty
- Colored title with emoji
- Dimmed borders and help text
- Bold highlights for score and controls
Breaking changes to Hook API:
- pi.send(text, attachments?) replaced with pi.sendMessage(message, triggerTurn?)
- Creates CustomMessageEntry instead of user messages
- Properly handles queuing during streaming via agent loop
- Supports optional turn triggering when idle
- New pi.appendEntry(customType, data?) for hook state persistence
- New pi.registerCommand(name, options) for custom slash commands
- Handler types renamed: SendHandler -> SendMessageHandler, new AppendEntryHandler
Implementation:
- AgentSession.sendHookMessage() handles all three cases:
- Streaming: queues message with _hookData marker, agent loop processes it
- Not streaming + triggerTurn: appends to state/session, calls agent.continue()
- Not streaming + no trigger: appends to state/session only
- message_end handler routes based on _hookData presence to correct persistence
- HookRunner gains getRegisteredCommands() and getCommand() methods
New types: HookMessage<T>, RegisteredCommand, CommandContext
- getEnvApiKey: ANTHROPIC_OAUTH_TOKEN now takes precedence over ANTHROPIC_API_KEY
- findCutPoint: Stop scan-backwards loop at session header (was decrementing past it causing null preparation)
- generateSummary/generateTurnPrefixSummary: Throw on stopReason=error instead of returning empty string
- Test files: Fix API key priority order, use keepRecentTokens=1 for small test conversations
