- 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
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
- 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
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
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
- 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
- Add XHIGH_MODELS constant and getAvailableThinkingLevels() to AgentSession
- Update ThinkingSelectorComponent to accept availableLevels parameter
- Both shift+tab cycling and /thinking command now show xhigh for supported models
- Update types.ts documentation to list supported models
When cwd is `~/.pi/agent/` or a subdirectory, the global AGENTS.md file
was included twice in the system prompt.
`loadProjectContextFiles()` loads context files in two steps:
1. Explicitly loads from `getAgentDir()` (`~/.pi/agent/`)
2. Walks from cwd up to root, collecting all AGENTS.md/CLAUDE.md files
There was no deduplication. When cwd is at or below `~/.pi/agent/`, the
ancestor walk includes that directory again.
Fix: track seen paths with a Set and skip duplicates.
- 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
Add isEscape() helper that handles both raw (\x1b) and Kitty protocol
(\x1b[27u) Escape sequences. Update all components that check for
Escape key to use the new helper.
- 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
- 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
- Auto-enable all models after /login via POST /models/{model}/policy
- Use openai-responses API for gpt-5/o3/o4 models (not accessible via completions)
- Normalize tool call IDs when switching between github-copilot models with different APIs
(fixes#198: openai-responses generates 450+ char IDs with special chars that break other models)
- Update README with streamlined GitHub Copilot docs
