When a provider (e.g., Google Gemini CLI) requests a retry delay longer
than maxDelayMs (default: 60s), the request fails immediately with an
informative error instead of waiting silently for hours.
The error is then handled by agent-level auto-retry, which shows the
delay to the user and allows aborting with Escape.
- Add maxRetryDelayMs to StreamOptions (packages/ai)
- Add maxRetryDelayMs to AgentOptions (packages/agent)
- Add retry.maxDelayMs to settings (packages/coding-agent)
- Update _isRetryableError to match 'retry delay' errors
fixes#1123
- Add ResourceLoader interface and DefaultResourceLoader implementation
- Add PackageManager for npm/git extension sources with install/remove/update
- Add session.reload() and session.bindExtensions() APIs
- Add /reload command in interactive mode
- Add CLI flags: --skill, --theme, --prompt-template, --no-themes, --no-prompt-templates
- Add pi install/remove/update commands for extension management
- Refactor settings.json to use arrays for skills, prompts, themes
- Remove legacy SkillsSettings source flags and filters
- Update SDK examples and documentation for ResourceLoader pattern
- Add theme registration and loadThemeFromPath for dynamic themes
- Add getShellEnv to include bin dir in PATH for bash commands
Error messages for missing credentials and shell config now use
getAuthPath() and getSettingsPath() instead of hardcoded ~/.pi/agent/
paths, so they correctly reflect PI_CODING_AGENT_DIR when set.
Detect OAuth authentication failures (expired credentials, offline) and provide helpful error message instead of crashing with generic 'No API key found' error.
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
When 429/500 errors occur during tool execution, empty assistant messages
with stopReason='error' get persisted. These break the tool_use -> tool_result
chain for Claude/Gemini APIs.
Added centralized filtering in transformMessages to skip assistant messages
with empty content and no tool calls. Provider-level filters remain for
defense-in-depth.
The --no-skills flag set options.skills = [] in main.ts, but the
interactive mode UI would rediscover skills anyway because it called
loadSkills() directly instead of using the already-loaded skills.
Changes:
- Add AgentSession.skills and AgentSession.skillWarnings properties
- discoverSkills() now returns { skills, warnings } instead of Skill[]
- Interactive mode uses session.skills instead of calling loadSkills()
- Update SDK docs and examples for new return type
Fixes#577
The --no-skills flag set options.skills = [] in main.ts, but the interactive mode UI would rediscover skills anyway because it called loadSkills() directly.
Changes:
- Add AgentSession.skills and AgentSession.skillWarnings properties
- discoverSkills() now returns { skills, warnings } instead of Skill[]
- Interactive mode uses session.skills instead of calling loadSkills()
Co-authored-by: Carlos Villela <cv@lixo.org>
When passing a string systemPrompt to createAgentSession(), it is now
used as-is without appending context files and skills. This matches the
documented behavior: 'String replaces default, function receives default
and returns final.'
Previously, string systemPrompt would have context files and skills
appended, causing duplication if they were already in the string.
fixes#543
- Add setActiveTools() to ExtensionAPI for dynamic tool management
- Extensions can now override, wrap, or disable built-in tools
- Add tool-override.ts example demonstrating the pattern
- Update documentation for tool override capabilities
Tools now use ExtensionRunner.createContext() instead of a separate
inline context factory. This ensures tools and event handlers share
the same context, fixing ctx.shutdown() and other context methods.
- Made ExtensionRunner.createContext() public
- Changed wrapRegisteredTools to accept ExtensionRunner instead of getContext callback
- Create ExtensionRunner when SDK custom tools are present (not just extensions)
- Removed redundant inline context factory from sdk.ts
The tool execution context was created with a no-op shutdown handler.
Now it delegates to ExtensionRunner.shutdown() which uses the handler
set by the mode via initialize().
- Replace per-extension closures with shared ExtensionRuntime
- Split context actions: ExtensionContextActions (required) + ExtensionCommandContextActions (optional)
- Rename LoadedExtension to Extension, remove setter methods
- Change runner.initialize() from options object to positional params
- Derive hasUI from uiContext presence (no separate param)
- Add warning when extensions override built-in tools
- RPC and print modes now provide full command context actions
BREAKING CHANGE: Extension system types and initialization API changed.
See CHANGELOG.md for migration details.
Extensions can now use async initialization, enabling:
- Dynamic imports (e.g., loading tools from external packages)
- Async setup (config fetching, service connections)
- Lazy-loaded dependencies
Changes:
- ExtensionFactory type now returns void | Promise<void>
- loadExtensionFromFactory is now async, returns Promise<LoadedExtension>
- All factory(api) calls are now awaited
Backwards compatible: sync extensions continue to work unchanged.
Extensions can now replace the built-in footer with a custom component:
- setFooter(factory) replaces with custom component
- setFooter(undefined) restores built-in footer
Includes example extension demonstrating context usage display.
Closes#481
- Setting controls filtering at convertToLlm layer
- Images are always stored in session, filtered dynamically based on current setting
- Toggle mid-session works: LLM sees/doesn't see images already in session
- Fixed SettingsManager.save() to handle inMemory mode for all setters
Closes#492
- Setting controls filtering at convertToLlm layer (defense-in-depth)
- Images are always stored in session, filtered dynamically based on current setting
- Toggle mid-session works: LLM sees/doesn't see images already in session
- Fixed SettingsManager.save() to handle inMemory mode for all setters
Closes#492
- Add sessionId to StreamOptions for providers that support session-based caching
- OpenAI Codex provider uses sessionId for prompt_cache_key and routing headers
- Agent class now accepts and forwards sessionId to stream functions
- coding-agent passes session ID from SessionManager and updates on session changes
- Update ai package README with table of contents, OpenAI Codex OAuth docs, and env vars table
- Increase Codex instructions cache TTL from 15 minutes to 24 hours
- Add tests for sessionId forwarding in ai and agent packages
- Accept ExtensionFactory[] for inline extensions (merged with discovery)
- Mark preloadedExtensions as @internal (CLI implementation detail)
- Update sdk.md with inline extension example
- Update CHANGELOG
Breaking changes:
- Settings: 'hooks' and 'customTools' arrays replaced with 'extensions'
- CLI: '--hook' and '--tool' flags replaced with '--extension' / '-e'
- API: HookMessage renamed to CustomMessage, role 'hookMessage' to 'custom'
- API: FileSlashCommand renamed to PromptTemplate
- API: discoverSlashCommands() renamed to discoverPromptTemplates()
- Directories: commands/ renamed to prompts/ for prompt templates
Migration:
- Session version bumped to 3 (auto-migrates v2 sessions)
- Old 'hookMessage' role entries converted to 'custom'
Structural changes:
- src/core/hooks/ and src/core/custom-tools/ merged into src/core/extensions/
- src/core/slash-commands.ts renamed to src/core/prompt-templates.ts
- examples/hooks/ and examples/custom-tools/ merged into examples/extensions/
- docs/hooks.md and docs/custom-tools.md merged into docs/extensions.md
New test coverage:
- test/extensions-runner.test.ts (10 tests)
- test/extensions-discovery.test.ts (26 tests)
- test/prompt-templates.test.ts
- event-bus.ts: await async handlers to catch errors properly
- agent-session.ts: clear _pendingNextTurnMessages on newSession/switchSession/branch
- sdk.ts: make eventBus first (required) param for discoverHooks/discoverCustomTools
- docs/sdk.md: document eventBus sharing pattern for hook/tool communication
* feat(coding-agent): add event bus for tool/hook communication
Adds pi.events API enabling custom tools and hooks to communicate via
pub/sub. Tools can emit events, hooks can listen. Shared EventBus instance
created per session in createAgentSession().
- EventBus interface with emit() and on() methods
- on() returns unsubscribe function
- Threaded through hook and tool loaders
- Documented in hooks.md and custom-tools.md
* fix(coding-agent): wrap event handlers to catch errors
* docs: note async handler error handling for event bus
* feat(coding-agent): add sendMessage to tools, nextTurn delivery mode
- Custom tools now have pi.sendMessage() for direct agent notifications
- New deliverAs: 'nextTurn' queues messages for next user prompt
- Fix: hooks and tools now share the same eventBus (was isolated before)
* fix(coding-agent): nextTurn delivery should always queue, even when streaming
- createAllTools() populates registry with all 7 built-in tools
- --tools flag only sets initially active tools (default: read/bash/edit/write)
- Hooks can enable any tool from registry via setActiveTools()
- System prompt rebuilds with correct tool guidelines when tools change
- Document tsx module resolution workaround in README
1. Merge setWidget and setWidgetComponent into single overloaded method
- Accepts either string[] or component factory function
- Uses single Map<string, Component> internally
- String arrays wrapped in Container with Text components
2. Use KeyId type for registerShortcut instead of plain string
- Import Key from @mariozechner/pi-tui
- Update plan-mode example to use Key.shift('p')
- Type-safe shortcut registration
3. Fix tool API docs
- Both built-in and custom tools can be enabled/disabled
- Removed incorrect 'custom tools always active' statement
4. Use matchesKey instead of matchShortcut (already done in rebase)
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
