- Sync all packages to version 0.7.7
- Rewrite sync-versions.js to handle ALL inter-package dependencies automatically
- Fix web-ui dependency on pi-ai (was 0.6.0, now 0.7.7)
- Move agent fix changelog entry to coding-agent CHANGELOG
- Remove redundant agent CHANGELOG.md
- Improve README.md with clearer lockstep versioning docs
- Add /changelog command to display full changelog in TUI (newest last)
- Fix changelog description (not a scrollable viewer, just displays in chat)
- Update CHANGELOG for 0.7.7 release
- BREAKING: Renamed AGENT.md to AGENTS.md for project context files
- Added automatic changelog viewer on startup for new sessions
- Added settings manager to track last shown changelog version
- BREAKING: Store provider and modelId separately in session files (fixes#4)
- Fixed markdown list rendering when items contain inline code with cyan formatting
- Added dynamic border component for TUI
- Updated changelog with entries for #4 and #5
- Replace backslashes in addition to forward slashes
- Remove colons from Windows drive letters (C:, D:, etc)
- Fixes ENOENT error on Windows when creating session directories
- Move lit from dependencies to peerDependencies in web-ui to prevent multiple Lit instances being loaded
- Update mini-lit from 0.1.8/0.1.10 to 0.2.0 in root package.json and web-ui/package.json
- Install @tailwindcss/vite in web-ui/example
- Run biome formatting fixes across codebase
This resolves HMR custom element re-registration errors caused by duplicate Lit registries.
- Add NO_IMAGE to error finish reasons in Google provider
- Fix non-null assertion after optional chaining in Anthropic provider
- Migrate biome config to 2.3.5
- Ignore Tailwind CSS file from biome checks
- Bump all packages to version 0.6.0
Tool results now use content blocks and can include both text and images.
All providers (Anthropic, Google, OpenAI Completions, OpenAI Responses)
correctly pass images from tool results to LLMs.
- Update ToolResultMessage type to use content blocks
- Add placeholder text for image-only tool results in Google/Anthropic
- OpenAI providers send tool result + follow-up user message with images
- Fix Anthropic JSON parsing for empty tool arguments
- Add comprehensive tests for image-only and text+image tool results
- Update README with tool result content blocks API
- Add /thinking slash command with autocomplete for setting reasoning levels (off, minimal, low, medium, high)
- Fix Ctrl+C behavior: remove hardcoded exit in TUI, let focused component handle it
- Add empty lines before and after tool execution components for better visual separation
- Fix stats rendering: display stats AFTER tool executions complete (matches web-ui behavior)
- Remove "Press Ctrl+C again to exit" message, show "(esc to interrupt)" in loader instead
- Add bash tool abort signal support with immediate SIGKILL on interrupt
- Make Text and Markdown components return empty arrays when no actual text content
- Add setCustomBgRgb() method to Markdown for dynamic background colors
- Remove old TUI implementation and components (LoadingAnimation, MarkdownComponent, TextComponent, TextEditor, WhitespaceComponent)
- Rename components-new to components with new API (Loader, Markdown, Text, Editor, Spacer)
- Move Text and Input components to separate files in src/components/
- Add render caching to Text component (similar to Markdown)
- Add proper ANSI code handling in Text component using stripVTControlCharacters
- Update coding-agent to use new TUI API (requires ProcessTerminal, uses custom Editor subclass for key handling)
- Remove old test files, keep only chat-simple.ts and virtual-terminal.ts
- Update README.md with new minimal API documentation
- Switch from tsc to tsgo for type checking
- Update package dependencies across monorepo
- Add handling for message_start event to capture initial token usage
- Fix message_delta to use assignment (=) instead of addition (+=)
since Anthropic sends cumulative token counts, not incremental
- Add comprehensive tests for all providers (Google, OpenAI Completions,
OpenAI Responses, Anthropic)
- Document OpenAI limitation: token stats only available at stream end
Fixes issue where aborted streams had zero token counts despite
Anthropic sending input tokens in the initial message_start event.
Fixes issue where unpaired Unicode surrogates in tool results cause JSON serialization errors in API providers, particularly Anthropic.
- Add sanitizeSurrogates() utility function to remove unpaired surrogates
- Apply sanitization in all provider convertMessages() functions:
- User message text content (string and text blocks)
- Assistant message text and thinking blocks
- Tool result output
- System prompts
- Valid emoji (properly paired surrogates) are preserved
- Add comprehensive test suite covering all 8 providers
Previously only Google and Groq handled unpaired surrogates correctly.
Now all providers (Anthropic, OpenAI Completions/Responses, Google, xAI, Groq, Cerebras, zAI) sanitize text before API submission.
- Export UserMessageWithAttachments type from web-ui index
- Remove unused i18n import from extract-document tool
- Update models.generated.ts (model order changes from API)
This fixes type errors when sitegeist uses custom user message renderer
When downloading HTML artifacts, the generated HTML now works standalone
without requiring the extension runtime.
Changes:
- Add PrepareHtmlOptions config object to SandboxedIframe.prepareHtmlDocument()
- Add isStandalone flag to skip runtime bridge and navigation interceptor
- When isStandalone=true:
- window.sendRuntimeMessage is NOT defined
- Navigation interceptor is NOT injected
- Artifact runtime providers fall back to embedded data
- HtmlArtifact download button now uses isStandalone: true
This fixes the issue where downloaded HTML artifacts would:
- Try to call window.sendRuntimeMessage (which would fail silently)
- Try to postMessage to non-existent parent window
- Not work when opened via file:// protocol
Now downloaded artifacts work completely standalone with embedded data.
The negated approach broke browser_script which runs in page context.
browser_script injects into web pages (http://, https://) where
chrome.runtime.sendMessage doesn't work. The original whitelist
approach correctly identifies extension contexts only.
The real issue with artifacts in sandbox iframes needs a different fix.
- Changed ToolRenderer return type from TemplateResult to ToolRenderResult
- ToolRenderResult = { content: TemplateResult, isCustom: boolean }
- isCustom: true = no card wrapper, false = wrap in card
- Updated all existing tool renderers to return new format
- Updated Messages.ts to handle custom rendering
This enables tools to render without default card chrome when needed.
- Update renderHeader and renderCollapsibleHeader in renderer-registry.ts to accept `text: string | TemplateResult`
- Remove duplicated renderCollapsibleHeaderWithPill helper in artifacts-tool-renderer.ts
- Update all artifact renderer calls to use renderHeaderWithPill() inline
- Remove all separate pill rendering below headers
This allows artifact pills to be rendered inline with header text without code duplication.
- Move mini-lit from dependencies to peerDependencies
- Keep in devDependencies for development
- Prevents bundlers from including mini-lit when consuming pi-web-ui
- Consumer (sitegeist) provides mini-lit, esbuild bundles it once
- Fixes duplicate mini-lit bundling issue permanently
Storage Architecture:
- New pluggable storage system with backends (LocalStorage, ChromeStorage, IndexedDB)
- SettingsRepository for app settings (proxy config, etc.)
- ProviderKeysRepository for API key management
- AppStorage with global accessors (getAppStorage, setAppStorage, initAppStorage)
Transport Refactoring:
- Renamed DirectTransport → ProviderTransport (calls LLM providers with optional CORS proxy)
- Renamed ProxyTransport → AppTransport (uses app server with user auth)
- Updated TransportMode: "direct" → "provider", "proxy" → "app"
CORS Proxy Integration:
- ProviderTransport checks proxy.enabled/proxy.url from storage
- When enabled, modifies model baseUrl to route through proxy: {proxyUrl}/?url={originalBaseUrl}
- ProviderKeyInput test function also honors proxy settings
- Settings dialog with Proxy tab (Switch toggle, URL input, explanatory description)
Anthropic Prompt Caching:
- System prompt cached with cache_control markers (both OAuth and regular API keys)
- Last user message cached to cache conversation history
- Saves 90% on input tokens for cached content (10x cost reduction)
Settings Dialog Improvements:
- Configurable tab system with SettingsTab base class
- ApiKeysTab and ProxyTab as custom elements
- Switch toggle for proxy enable (instead of Checkbox)
- Explanatory paragraphs for each tab
- ApiKeyPromptDialog reuses ProviderKeyInput component
Removed:
- Deprecated ApiKeysDialog (replaced by ProviderKeyInput in SettingsDialog)
- Old storage-adapter and key-store (replaced by new storage architecture)
