- Merge branch event into session with before_branch/branch reasons
- Add before_switch, before_clear, shutdown reasons
- before_* events can be cancelled with { cancel: true }
- Update RPC commands to return cancelled status
- Add shutdown event on process exit
- New example hooks: confirm-destructive, dirty-repo-guard, auto-commit-on-exit
fixes#278
Use visual line counting (accounting for line wrapping) instead of logical
line counting for bash tool output in collapsed mode. Now consistent with
bash-execution.ts behavior.
- Add shared truncateToVisualLines utility
- Update tool-execution.ts to use Box for bash with visual truncation
- Update bash-execution.ts to use shared utility
- Pass TUI to ToolExecutionComponent for terminal width access
Fixes#275
Core tools now properly use the cwd passed to createAgentSession().
Added tool factory functions for SDK users who specify custom cwd with explicit tools.
Fixes#279
- createAgentSession() factory with full control
- SessionManager/SettingsManager static factories
- Project-specific settings support
- 12 examples and comprehensive docs
Fixes#272
- SettingsManager now loads .pi/settings.json from cwd (project settings)
- Project settings merge with global settings (deep merge for objects)
- Setters only modify global settings, project settings are read-only
- Add static factories: SettingsManager.create(cwd?, agentDir?), SettingsManager.inMemory(settings?)
- Add applyOverrides() for programmatic overrides
- Replace 'settings' option with 'settingsManager' in CreateAgentSessionOptions
- Update examples to use new pattern
Incorporates PR #276 approach
- SessionManager: add flushed flag, _persist() flushes all entries when first assistant seen
- SessionManager: reset() now creates session header
- MomSessionManager: same pattern, remove pendingEntries/sessionInitialized/startSession/shouldInitializeSession
- Use default params instead of resolvedAgentDir pattern in loaders
- Remove unused DiscoverAndLoadHooksOptions interface
- Remove redundant github-copilot special casing in getAvailableModels
- loadAndMergeModels(agentDir) - loads models.json from agentDir
- getAvailableModels(agentDir) - uses agentDir for model discovery
- findModel(provider, id, agentDir) - uses agentDir for model lookup
- configureOAuthStorage(agentDir) - configures OAuth to use agentDir/oauth.json
- createAgentSession calls configureOAuthStorage with options.agentDir
- Export configureOAuthStorage from SDK
- Add factory methods: create(cwd), open(path), continueRecent(cwd), inMemory()
- Add static list(cwd) for session listing
- Make constructor private, pass cwd explicitly
- Update SDK to take sessionManager instead of sessionFile options
- Update main.ts to create SessionManager based on CLI flags
- Update SessionSelectorComponent to take sessions[] instead of SessionManager
- Update tests to use factory methods
- Add continueSession, restoreFromSession, additionalHookPaths,
additionalCustomToolPaths, scopedModels to CreateAgentSessionOptions
- Return CreateAgentSessionResult with session, customToolsResult,
and modelFallbackMessage
- main.ts now focuses on CLI arg parsing and mode routing
- Reduced main.ts from ~490 to ~340 lines
Adds glob pattern support for skill filtering:
- --skills <patterns> CLI flag (comma-separated glob patterns)
- includeSkills setting in settings.json
- ignoredSkills now supports glob patterns
- ignoredSkills takes precedence over includeSkills and --skills
Closes#268
- Event-based architecture: agent forwards AgentSessionEvent to adapters
- Multi-adapter support via single config.json
- Access control: admins, DM permissions per adapter
- Channel namespacing by adapter name
- Channel isolation via bubblewrap in Linux/Docker environments
- Simplified directory structure and interfaces
- Fix //tmp issue: distinguish slash commands from file paths by checking if anything precedes the /
- Fix symlinks to directories (like /tmp) not getting trailing slash
- Add setOAuthStorage() and resetOAuthStorage() to pi-ai for custom storage backends
- Configure coding-agent to use its own configurable OAuth path via getOAuthPath()
- Model selector (/model command) now only shows models from --models scope when set
- Rewrite OAuth documentation in pi-ai README with examples
Fixes#255
When a user interrupts a tool call flow (sends a message without providing
tool results), APIs like OpenAI Responses and Anthropic fail because:
- OpenAI requires tool outputs for function calls
- OpenAI requires reasoning items to have their following items
- Anthropic requires non-empty content for error tool results
Instead of filtering out orphaned tool calls (which breaks thinking signatures),
we now insert synthetic empty tool results with isError: true and content
'No result provided'. This preserves the conversation structure and satisfies
all API requirements.
Use correct API response format (cloudaicompanionProject) and proper
onboarding flow with tierId and metadata. Add retry logic for project
provisioning which may take time.
- Add OAuth handler with PKCE flow and local callback server
- Automatic project discovery via loadCodeAssist/onboardUser endpoints
- Store credentials with projectId for API calls
- Encode token+projectId as JSON for provider to decode
- Register as 'google-cloud-code-assist' OAuth provider
- Add new API type 'google-cloud-code-assist' for Gemini CLI / Antigravity auth
- Extract shared Google utilities to google-shared.ts
- Implement streaming provider for Cloud Code Assist endpoint
- Add 7 models: gemini-3-pro-high/low, gemini-3-flash, claude-sonnet/opus, gpt-oss
Models use OAuth authentication and have sh cost (uses Google account quota).
OAuth flow will be implemented in coding-agent in a follow-up.
- setThinkingLevel() now clamps xhigh to high when model doesn't support it
- Model changes automatically re-clamp the current thinking level
- Fixed /model command to use session.setModel() instead of agent.setModel()
- Footer and editor border color update after model/thinking changes
Closes#253
The cell size query response parser was incorrectly holding back Kitty
keyboard protocol sequences, thinking they might be incomplete cell size
responses. This caused Ctrl+C/Ctrl+D to require multiple presses in iTerm2.
Fixed by only waiting for more data if the buffer doesn't end with a
terminal escape sequence terminator character.
Fixed arrow key and Enter detection in selector components to work
with Kitty protocol when Caps Lock or Num Lock is enabled.
Updated: oauth-selector, user-message-selector, hook-selector,
hook-input, model-selector, session-selector
Extended the Kitty protocol parser to handle functional keys with
~ terminator (Delete, Insert, PageUp, PageDown) and Home/End keys.
Updated editor.ts and input.ts to use the new helpers.
Exports getAvailableModels, getApiKeyForModel, findModel, login, logout,
and getOAuthProviders from @mariozechner/pi-coding-agent so scripts using
AgentSession directly can reuse OAuth token storage and model resolution.
Fixes#245
Backspace, Delete, and arrow keys now use Intl.Segmenter to operate
on grapheme clusters instead of individual UTF-16 code units. This
fixes deletion of emojis and other multi-codepoint characters.
fixes#240
Fixes keyboard input in Ghostty on Linux when Num Lock is enabled.
The Kitty protocol includes Caps Lock (64) and Num Lock (128) bits
in modifier values. Now masks out lock bits when matching shortcuts.
Added helper functions: isArrowUp/Down/Left/Right, isEnter, isTab,
isBackspace, isShiftEnter, isAltEnter, isAltLeft/Right, isCtrlLeft/Right
fixes#243
- Add supportsXhigh() function to ai package for checking xhigh support
- Clamp xhigh to high for OpenAI models that don't support it
- Update coding-agent to use centralized supportsXhigh()
- gpt-5.2, gpt-5.2-codex now show xhigh in thinking selector
Closes#236
- Export getMarkdownTheme() from coding-agent for custom tools
- Chain/parallel modes now use Markdown component in expanded view
- Chain streaming updates include all previous steps (not just current)
- Strip {previous} placeholder from task preview in renderCall
Breaking changes:
- Custom tools now require index.ts entry point in subdirectory
(e.g., tools/mytool/index.ts instead of tools/mytool.ts)
Subagent tool improvements:
- Refactored to use Message[] from ai package instead of custom types
- Extracted agent discovery to separate agents.ts module
- Added parallel mode streaming (shows progress from all tasks)
- Added turn count to usage stats footer
- Removed redundant Query section from scout output
Fixes:
- JSON mode stdout flush: Fixed race condition where pi --mode json
could exit before all output was written, causing consumers to
miss final events
Also:
- Added signal/timeout support to pi.exec() for custom tools and hooks
- Renamed pi-pods bin to avoid conflict with pi
Mario Zechner
