Both now use consistent sections:
- Goal
- Constraints & Preferences
- Progress (Done/In Progress/Blocked)
- Key Decisions
- Next Steps
- Critical Context (compaction only)
Prompts instruct LLM to use EXACT format and preserve file paths/function names.
- BranchPreparation now uses AgentMessage[] instead of custom type
- Reuse getMessageFromEntry pattern from compaction.ts
- Add BranchSummarySettings with reserveFraction to settings.json
- Add getBranchSummarySettings() to SettingsManager
- Use settings for reserveFraction instead of hardcoded value
- Add ReadonlySessionManager interface to session-manager.ts
- Re-export from hooks/index.ts
- Add collectEntriesForBranchSummary() to extract entries for summarization
- Don't stop at compaction boundaries (include their summaries as context)
- Add token budget support to prepareBranchEntries()
- Walk entries newest-to-oldest to prioritize recent context
- Use options object for generateBranchSummary()
- Handle compaction entries as context summaries
- Export new types: CollectEntriesResult, GenerateBranchSummaryOptions
- Move compaction.ts to src/core/compaction/compaction.ts
- Extract branch summarization to src/core/compaction/branch-summarization.ts
- Add index.ts to re-export all compaction utilities
- Update all imports across the codebase
- Add test/utilities.ts with shared helpers (API_KEY, userMsg, assistantMsg, createTestSession)
- Add agent-session-tree-navigation.test.ts with e2e tests for tree navigation
- Add getChildren() method to SessionManager
- Add summaryEntry to navigateTree return type
- Update existing tests to use shared utilities
- Check response.stopReason instead of catching errors for abort detection
- Return result object from _generateBranchSummary instead of throwing
- Fix summary attachment: attach to navigation target position, not old branch
- Support root-level summaries (parentId=null) in branchWithSummary
- Remove setTimeout hack for re-showing tree selector on abort
- Add TreeSelectorComponent with ASCII tree visualization
- Add AgentSession.navigateTree() for switching branches
- Add session_before_tree/session_tree hook events
- Add SessionManager.resetLeaf() for navigating to root
- Change leafId from string to string|null for consistency with parentId
- Support optional branch summarization when switching
- Update buildSessionContext() to handle null leafId
- Add /tree to slash commands in interactive mode
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.
- agentLoop now accepts AgentMessage[] instead of single message
- agent.prompt() accepts AgentMessage | AgentMessage[]
- Emits message_start/end for each message in the array
- AgentSession.prompt() builds array with hook message + user message
- TUI now receives events for before_agent_start injected messages
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.
- Add BeforeAgentStartEvent and BeforeAgentStartEventResult types
- Add emitBeforeAgentStart to HookRunner
- Call in AgentSession.prompt() before agent.prompt()
- Hook can return a message to inject into context (persisted + visible)
- Add test hook demonstrating custom message rendering and before_agent_start
- addMessageToChat: exhaustive switch for all AgentMessage roles
- renderSessionContext: delegates to addMessageToChat, special handling for assistant tool calls and tool results
- export-html formatMessage: exhaustive switch for all AgentMessage roles
- Removed isHookMessage, isBashExecutionMessage type guards in favor of role checks
- Fixed imports and removed unused getLatestCompactionEntry
Two bugs:
1. createCustomMessage was returning role: 'user' instead of preserving
the hook message structure (role: 'hookMessage', customType, etc.)
2. rebuildChatFromMessages wasn't clearing the container before rebuilding
- 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
- Renamed AppMessage to AgentMessage throughout
- New agent-loop.ts with AgentLoopContext, AgentLoopConfig
- Removed transport abstraction, Agent now takes streamFn directly
- Extracted streamProxy to proxy.ts utility
- Removed agent-loop from pi-ai (now in agent package)
- Updated consumers (coding-agent, mom) for AgentMessage rename
- Tests updated but some consumers still need migration
Known issues:
- AgentTool, AgentToolResult not exported from pi-ai
- Attachment not exported from pi-agent-core
- ProviderTransport removed but still referenced
- messageTransformer -> convertToLlm migration incomplete
- CustomMessages declaration merging not working properly
HookMessage.content can be string or array, but LLM Message.content
must be an array. This was causing 'messages: at least one message
is required' errors when hooks sent string content.
- Rename HookAppMessage to HookMessage, isHookAppMessage to isHookMessage
- Remove entries array from SessionContext (use isHookMessage type guard instead)
- HookMessage.content now accepts string directly (not just array)
- Fix streamMessage type in AgentState (AppMessage, not Message)
- Rename CustomMessageComponent to HookMessageComponent
- Fix test hook to use pi.sendMessage
- Change from contextTransform (runs once at agent start) to preprocessor
- preprocessor runs before EACH LLM call inside the agent loop
- ContextEvent now uses Message[] (pi-ai format) instead of AppMessage[]
- Deep copy handled by pi-ai preprocessor, not Agent
This enables:
- Pruning rules applied on every turn (not just agent start)
- /prune during long agent loop takes effect immediately
- Compaction can use same transforms (future work)
- Add contextTransform option to Agent (runs before messageTransformer)
- Deep copy messages before passing to contextTransform (modifications are ephemeral)
- Add ContextEvent and ContextEventResult types
- Add emitContext() to HookRunner (chains multiple handlers)
- Wire up in sdk.ts when creating Agent with hooks
Enables dynamic context pruning: hooks can modify messages sent to LLM
without changing session data. See discussion #330.
- Extract execCommand to src/core/exec.ts, shared by hooks and custom-tools
- Rename CustomMessageRenderer -> HookMessageRenderer
- Rename registerCustomMessageRenderer -> registerMessageRenderer
- Renderer now receives HookMessage instead of CustomMessageEntry
- CustomMessageComponent now has setExpanded() and responds to Ctrl+E toggle
- Re-export ExecOptions/ExecResult from exec.ts for backward compatibility
- compaction-hooks-example.test.ts: get sessionManager/modelRegistry from ctx
- compaction-hooks.test.ts:
- Pass sessionManager/modelRegistry to HookRunner constructor
- Remove setSessionFile call
- Update tests to use session.sessionManager instead of event.sessionManager
Instead of using continue() which validates roles, prompt() now accepts
an AppMessage directly. This allows hook messages with role: 'hookMessage'
to trigger proper agent loop with message events.
- Add overloads: prompt(AppMessage) and prompt(string, attachments?)
- sendHookMessage uses prompt(appMessage) instead of appendMessage+continue
Following the same pattern as BashExecutionMessage:
- HookAppMessage has role: 'hookMessage' with customType, content, display, details
- isHookAppMessage() type guard for checking message type
- messageTransformer converts to user message for LLM context
- TUI checks isHookAppMessage() for rendering as CustomMessageComponent
This makes the API clean for anyone building on AgentSession - they can
use the type guard instead of knowing about internal marker fields.
When calling continue() with emitLastMessage=true, the agent loop
emits message_start/message_end events for the last message in context.
This allows messages added outside the loop (e.g., hook messages via
sendHookMessage) to trigger proper TUI rendering.
Changes across packages:
- packages/ai: agentLoopContinue() accepts emitLastMessage parameter
- packages/agent: Agent.continue(), transports updated to pass flag
- packages/coding-agent: sendHookMessage passes true when triggerTurn
- Command handler now returns Promise<void> instead of Promise<string | undefined>
- To trigger LLM response, use sendMessage() with triggerTurn: true
- Simplify _tryExecuteHookCommand to return boolean
Added example hook and slash command in .pi/:
- .pi/hooks/test-command.ts - /greet command using sendMessage
- .pi/commands/review.md - file-based /review command
Hook commands registered via pi.registerCommand() are now handled in
AgentSession.prompt() alongside file-based slash commands. This:
- Removes duplicate tryHandleHookCommand from interactive-mode and rpc-mode
- All modes (interactive, RPC, print) share the same command handling logic
- AgentSession._tryExecuteHookCommand() builds CommandContext using:
- UI context from hookRunner (set by mode)
- sessionManager, modelRegistry from AgentSession
- sendMessage via sendHookMessage
- exec via exported execCommand
- Handler returning string uses it as prompt, undefined returns early
Also:
- Export execCommand from hooks/runner.ts
- Add getUIContext() and getHasUI() to HookRunner
- Make HookRunner.emitError() public for error reporting
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
- Add getMessageFromEntry helper to extract AppMessage from any context-producing entry
- Update findValidCutPoints to treat branch_summary/custom_message as valid cut points
- Update findTurnStartIndex to recognize branch_summary/custom_message as turn starters
- Update all message extraction loops to use getMessageFromEntry
- Add renderCustomMessage to HookAPI for registering custom renderers
- Add CustomMessageRenderer type and CustomMessageRenderOptions
- Store customMessageRenderers in LoadedHook
- Add getCustomMessageRenderer(customType) to HookRunner
- SessionContext.entries now aligned with messages (same length, corresponding indices)
TUI can now correlate messages with their source entries to identify
custom_message entries and use hook-provided renderers.
content: string | (TextContent | ImageContent)[]
This matches the UserMessage type from pi-ai, so content can be
passed directly to AppMessage without conversion.
- CustomMessageEntry<T> type with customType, content, display, details
- appendCustomMessageEntry() in SessionManager
- buildSessionContext() includes custom_message entries as user messages
- Exported CustomEntry and CustomMessageEntry from main index
CustomEntry is for hook state (not in context).
CustomMessageEntry is for hook-injected content (in context).
