- Export isBashToolResult, isReadToolResult, etc. type guards
- Update hooks.md with type guard usage examples
- Document custom tool handling in hooks.md
Breaking change: ToolResultEvent now exposes content and typed details
instead of just a result string. Hook handlers returning { result: ... }
must change to { content: [...] }.
- ToolResultEvent is now a discriminated union based on toolName
- Each built-in tool has typed details (BashToolDetails, etc.)
- Export tool details types and TruncationResult
- Update hooks.md documentation
Closes#233
Implement Agent Skills standard (https://agentskills.io/specification):
- Validate name (must match parent dir, lowercase, max 64 chars)
- Validate description (required, max 1024 chars)
- Warn on unknown frontmatter fields
- Warn on name collisions (keep first)
- Change prompt format to XML structure
- Remove {baseDir} placeholder (use relative paths)
- Add tests and update documentation
fixes#231
- Add isCtrlD helper to keys.ts
- CustomEditor intercepts Ctrl+D and only triggers callback when editor is empty
- Single Ctrl+D with empty input exits immediately
- Update CHANGELOG to frame as feature (Kitty protocol support) not fix
- Add isCtrlA/C/E/K/O/P/T/U/W helper functions that check both raw and Kitty formats
- Add isAltBackspace helper function
- Refactor editor.ts, input.ts, select-list.ts to use helper functions
- Refactor custom-editor.ts, session-selector.ts, user-message-selector.ts
- Add CHANGELOG entry for the Shift+Enter fix
Enable the Kitty keyboard protocol on terminal start to receive enhanced
key sequences that include modifier information. This fixes Shift+Enter
not working in Ghostty, Kitty, WezTerm, and other modern terminals.
Changes:
- Enable Kitty protocol on start (\x1b[>1u), disable on stop (\x1b[<u)
- Add centralized key definitions in packages/tui/src/keys.ts
- Support both legacy and Kitty sequences for all modifier+key combos:
- Shift+Enter, Alt+Enter for newlines
- Shift+Tab for thinking level cycling
- Ctrl+C, Ctrl+A, Ctrl+E, Ctrl+K, Ctrl+U, Ctrl+W, Ctrl+O, Ctrl+P, Ctrl+T
- Alt+Backspace for word deletion
- Export Keys constants and helper functions from @mariozechner/pi-tui
- Extract diff rendering to dedicated diff.ts component
- Show word-level changes with inverse highlighting when a single line is modified
- Use diffWords for cleaner token grouping (includes adjacent whitespace)
- Only apply intra-line diff when exactly 1 removed and 1 added line (true modification)
- Multi-line changes show all removed then all added without incorrect pairing
- Add theme.inverse() method for inverse text styling
- Fix external dependency name (pi-agent-core -> pi-agent)
- Add missing files: hooks/, custom-tools/, skills.ts, github-copilot.ts
- Update components list with all 18 current components
- Add Key Abstractions sections for hooks, custom tools, skills
- Add 'Adding a New Hook Event' to development guide
- Move config.ts to correct location in directory tree
- Custom tools: TypeScript modules that extend pi with new tools
- Custom TUI rendering via renderCall/renderResult
- User interaction via pi.ui (select, confirm, input, notify)
- Session lifecycle via onSession callback for state reconstruction
- Examples: todo.ts, question.ts, hello.ts
- Hook examples: permission-gate, git-checkpoint, protected-paths
- Session lifecycle centralized in AgentSession
- Works across all modes (interactive, print, RPC)
- Unified session event for hooks (replaces session_start/session_switch)
- Box component added to pi-tui
- Examples bundled in npm and binary releases
Fixes#190
Previous test used compressed 8k images (0.01MB) which was meaningless.
Now tests with actual large noise images that don't compress.
Realistic payload limits discovered:
- Anthropic: 6 x 3MB = ~18MB total (not 32MB as documented)
- OpenAI: 2 x 15MB = ~30MB total
- Gemini: 10 x 20MB = ~200MB total (very permissive)
- Mistral: 4 x 10MB = ~40MB total
- xAI: 1 x 20MB (strict request size limit)
- Groq: 5 x 5760px images (5 image + pixel limit)
- zAI: 2 x 15MB = ~30MB (50MB request limit)
- OpenRouter: 2 x 5MB = ~10MB total
Also fixed GEMINI_API_KEY env var (was GOOGLE_API_KEY).
Related to #120
- Add AgentToolUpdateCallback type and optional onUpdate callback to AgentTool.execute()
- Add tool_execution_update event with toolCallId, toolName, args, partialResult
- Normalize tool_execution_end to always use AgentToolResult (no more string fallback)
- Bash tool streams truncated rolling buffer output during execution
- ToolExecutionComponent shows last N lines when collapsed (not first N)
- Interactive mode handles tool_execution_update events
- Update RPC docs and ai/agent READMEs
fixes#44
Previously, when reasoning was not specified, some providers like Gemini
with 'dynamic thinking' enabled by default would still use thinking.
Now explicitly sets thinkingEnabled: false (Anthropic) and
thinking: { enabled: false } (Google) when reasoning is undefined.
Closes#180
