- Added automatic retry logic for OpenAI Codex responses with configurable delay and max retries.
- Added input event handlers for extensions to intercept user input and argument completion support.
- Added Emacs-style kill ring for text deletion operations with Alt+D and Ctrl+Y keybindings.
- Added configurable editor padding via editorPaddingX theme option and setMaxHeight() method.
- Fixed tool prefix handling in Claude provider to use case-insensitive comparison.
- Enhanced Kitty keyboard protocol support for better key detection and shifted symbol handling.
- Converted SettingsManager.create(), loadSettings(), discoverSkills(), loadSlashCommands(), buildSystemPrompt(), loadSkills(), loadProjectContextFiles(), and getShellConfig() from synchronous to asynchronous APIs.
- Changed capability provider load() method from supporting both sync and async to async-only by removing loadSync().
- Removed fs property from LoadContext interface in capability types.
- Added new fs.ts module with caching layer for filesystem operations using readFile, readDirEntries, readDir, walkUp, and cache management functions.
- Refactored all discovery providers (builtin, claude, cline, codex, cursor, gemini, github, mcp-json, ssh, vscode, windsurf) to use async file operations with Promise.all for parallel loading.
- Added setFooter(), setHeader(), and setEditorComponent() methods to ExtensionUIContext for custom UI components.
- Exported InteractiveModeOptions type and numerous UI components for programmatic SDK usage.
- Added --no-tools flag to disable all built-in tools and --no-extensions flag to disable extension discovery.
- Changed bash tool output truncation to recalculate on terminal resize instead of using cached width.
- Fixed Wayland clipboard copy (wl-copy) no longer blocking when the process doesn't exit promptly.
- Updated model pricing and renamed nex-agi/deepseek-v3.1-nex-n1 model removing :free suffix.
- Added calc tool supporting basic mathematical calculations with arithmetic operators, parentheses, and hex/binary/octal literals.
- Added support for multiple API credentials per provider with round-robin distribution across sessions.
- Added file locking on auth.json to prevent concurrent write corruption.
- Added clickable OAuth login URL display in terminal with plain text fallback.
- Updated ask tool prompt to emphasize exhausting other options before asking users.
- Refactored OAuth credential storage to append new credentials instead of replacing existing ones.
- Added retry logic with exponential backoff and model fallback for auto-compaction failures.
- Added support for pi/<role> model aliases and automatic model inheritance for subtasks.
- Enhanced error messages with retry-after timing from rate limit headers across all providers.
- Fixed image attachments being dropped when steering messages are queued during streaming.
- Changed edit tool to merge call and result displays into single block.
- Changed model override behavior to persist in settings when explicitly set via CLI.
- Port pi-ai from upstream with Bun-first approach (source files, no dist)
- Add cli_ prefix to tool names in OAuth mode to avoid collisions
- Improve beta header handling with proper deduplication
- Convert codex-instructions.md to Bun text embed
- Strip .js extensions from all imports
- Added SSH tool for executing commands on remote hosts with project config discovery from ssh.json files.
- Added persistent SSH connection manager with master socket support and automatic cleanup.
- Added SSHFS mount utilities for mounting remote filesystems with automatic unmount on session end.
- Added SSH capability definition with host validation and discovery provider registration.
- Added environment variable management via settings.json with applyEnvironmentVariables() and related methods.
- Enhanced file mentions to support directories, validate boundaries, and truncate large files.
- Added fallback model candidate logic in title generator to retry on model failures.
- Fixed bash output preview to minify JSON content and skip structural-only lines.
- Added Cerebras provider support with thinking block filtering and zai-glm-4.6 model priority.
- Refactored tree rendering to use consistent theme.tree properties instead of boxSharp.
- Added file-based slash commands discovery from commands/ directories.
- Added $ARGUMENTS placeholder support for slash command argument substitution.
- Changed argument substitution order to process positional args before wildcards to prevent re-substitution bugs.
- Integrated slash command expansion into AgentSession initialization flow.
- Added shared render-utils module with standardized formatting functions for truncation, bytes, tokens, duration, and tree rendering.
- Extracted resolveOmpCommand() helper to centralize cross-platform subprocess command resolution.
- Consolidated duplicate utility functions across grep, find, ls, notebook, ask, output, exa, lsp, and web search renderers.
- Updated web search tool to support 'auto' as explicit provider option for auto-detection.
- Added cycleRoleModels() method to cycle through configured role-based models with deduplication.
- Added RoleModelCycleResult interface with model, thinkingLevel, and role properties.
- Added isCtrlY() helper function to detect Ctrl+Y input across raw byte and Kitty protocol.
Task tool now parses NDJSON events from subagent execution and aggregates
token usage (input, output, cache read/write) and costs across all completed
message_end events. Usage is stored in tool result details and included in
session statistics via getUsageStatistics().
Also changed AgentSession.dispose() to async to properly flush pending writes.
- Added Time Traveling Streamed Rules (TTSR) feature for real-time pattern matching and rule injection during streaming.
- Added TtsrManager with configurable settings for context mode, repeat mode, and repeat gap.
- Added TTSR trigger support across all rule discovery sources (builtin, cline, cursor, windsurf).
- Added abort signal handling in agent loop to support stream interruption for TTSR.
- Added TtsrNotificationComponent for displaying rule violation notifications in interactive mode.
- Added `pi update` command for checking and installing CLI updates from GitHub releases or bun.
- Added cross-platform installer scripts (shell and PowerShell) with automatic PATH configuration.
- Changed HTML export to use compile-time bundled templates via Bun macros.
- Changed `exportToHtml` and `exportFromFile` functions to async operations.
- Added mutex-based synchronization to prevent race conditions in LSP client, session context, and RPC mode.
- Fixed resource leaks by ensuring stream reader locks are released in try/finally blocks.
- Fixed duplicate processing issues by tracking in-flight operations in runner creation and message writes.
- Fixed event listener mutation during iteration by copying array before emitting.
- Added abort controller cleanup to prevent memory leaks in auto-compaction and retry logic.
- Added centralized file logger with winston and daily rotation to ~/.pi/logs/ directory.
- Exposed logger property to hook and custom tool APIs for extension logging.
- Replaced silent error suppression with debug/warning logging across 20+ catch blocks.
- Removed separate Exa error logger in favor of centralized logging system.
Files referenced with @path/to/file.ext syntax are automatically read
and injected as synthetic Read tool calls before the agent responds,
eliminating the need for manual file reads.
- Added custom TypeScript slash commands loaded from ~/.pi/commands/ and .pi/commands/ directories.
- Added support for loading markdown slash commands from Claude's ~/.claude/commands/ and .claude/commands/ directories.
- Added commands.enableClaudeUser and commands.enableClaudeProject settings to control Claude command directory loading.
- Implemented CustomCommandAPI with exec, typebox, and pi module injection for command execution context.
- Integrated custom commands into autocomplete provider for interactive mode discovery.
- Added interruptMode option to control when queued messages interrupt tool execution.
- Implemented "immediate" mode (default) to check queue after each tool and interrupt remaining tools.
- Implemented "wait" mode to defer queue processing until the entire turn completes.
- Exposed interruptMode configuration in interactive settings UI with immediate/wait options.
- Wired interrupt mode through AgentSession and SDK to enable runtime configuration and persistence.
- Settings now use modelRoles map (e.g., { default: 'anthropic/claude-sonnet-4-5', small: 'anthropic/claude-haiku-4-5' })
- Session persistence uses 'provider/modelId' string format with optional role field
- Model selector: Enter sets default, S sets small, Escape closes
- Added role markers in selector: checkmark for default, lightning bolt for small
- Task tool supports pi/<role> aliases (e.g., model: pi/small, haiku, flash, mini)
- Title generation uses configured small model with auto-discovery fallback
- Explore agent now uses pi/small as primary model preference
- Renamed npm package scope from @mariozechner to @oh-my-pi across all packages for consistent branding.
- Removed packages/pods directory and all related pod management functionality.
- Updated import paths and module declarations throughout codebase to reflect new package names.
- Reformatted code with consistent trailing comma removal and ternary operator alignment.
CustomToolContext now has:
- isIdle() - check if agent is streaming
- hasQueuedMessages() - check if user has queued messages
- abort() - abort current operation (fire-and-forget)
Changed abort() signature from Promise<void> to void in both
HookContext and CustomToolContext. The abort is fire-and-forget:
it calls session.abort() without awaiting, so the abort signal
is set immediately while waitForIdle() runs in the background.
Fixes#388
HookContext (all events):
- isIdle() - read-only state check
- hasQueuedMessages() - read-only state check
- abort() - fire-and-forget, does not wait
HookCommandContext (slash commands only):
- waitForIdle() - waits for agent to finish
- newSession(options?) - create new session
- branch(entryId) - branch from entry
- navigateTree(targetId, options?) - navigate session tree
Session control methods moved from HookAPI (pi.*) to HookCommandContext (ctx.*)
because they can deadlock when called from event handlers that run inside
the agent loop (tool_call, tool_result, context events).
HookAPI additions:
- pi.newSession(options?) - create new session with optional setup callback
- pi.branch(entryId) - branch from a specific entry
- pi.navigateTree(targetId, options?) - navigate the session tree
HookContext additions:
- ctx.isIdle() - check if agent is streaming
- ctx.waitForIdle() - wait for agent to finish
- ctx.abort() - abort current operation
- ctx.hasQueuedMessages() - check for queued user messages
These enable hooks to programmatically manage sessions (handoff, templates)
and check agent state before showing interactive UI.
Fixes#388
- 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 tree sidebar with search and filter (Default/All/Labels)
- Client-side markdown/syntax highlighting via vendored marked.js + highlight.js
- Base64 encode session data to avoid escaping issues
- Reuse theme.ts color tokens via getResolvedThemeColors()
- Sticky sidebar, responsive mobile layout with overlay
- Click tree node to scroll to message
- Keyboard shortcuts: Esc to reset, Ctrl/Cmd+F to search
- 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
Breaking change: CustomAgentTool.dispose() removed. Use onSession with
reason 'shutdown' instead for cleanup.
- Add 'shutdown' to SessionEvent.reason for custom tools
- Remove dispose() method from CustomAgentTool interface
- Make emitToolSessionEvent() public on AgentSession
- Emit shutdown event to tools in InteractiveMode.shutdown()
- Update custom-tools.md with new API and examples
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
- 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
can1357