Implements #645:
- ResourceLoader/PackageManager system replacing legacy discovery
- CLI commands: pi install, pi remove, pi update, pi list
- /reload command for hot reload in interactive mode
- session.reload() and session.bindExtensions() APIs
- CLI flags: --skill, --theme, --prompt-template, --no-themes, --no-prompt-templates
- Extension conflict detection with filtering
- Support for npm:, git:, local paths, and raw git URLs
- Auto npm install for git repos with package.json
closes#645
- Add progress callbacks to PackageManager for TUI status during install/remove/update
- Add extension conflict detection (tools, commands, flags with same names)
- Accept raw GitHub/GitLab URLs without git: prefix
- Add tests for package-manager.ts and resource-loader.ts
- Add empty fixture directories for skills tests
- 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
The TUI only re-renders changed lines. During agent streaming, the
conversation lines above DOSBox change but DOSBox lines stay the same.
This caused the image to stay at its old position while text scrolled.
Fix: Add invisible timestamp to image line to force TUI to see it as
changed every render, ensuring the image is always re-rendered at the
correct position.
bundle.extract() uses XMLHttpRequest which doesn't exist in Node.js.
Reverted to writing files directly to Emscripten FS after DOSBox init.
jsdos mounts C: to /home/web_user by default.
The previous approach of writing files to Emscripten FS after DOSBox
started didn't work because the C: drive mount was pointing elsewhere.
Now we create a proper zip archive of QBasic files and include it in
the jsdos bundle using the extract() API with a data URL. The bundle
extracts to the C: drive root on startup.
- DOSBox now starts at session_start and persists in background
- /dosbox command attaches UI to running instance (Ctrl+Q detaches)
- Added dosbox tool with actions: send_keys, screenshot, read_text
- Bundled QuickBASIC 4.5 files, mounted at C:\QB on startup
- Agent can interact with DOSBox programmatically via tool
Use: pi -e ./examples/extensions/pi-dosbox
Then: /dosbox to view, or let agent use the dosbox tool
- allocateImageId() now returns random IDs instead of sequential
- Static images no longer auto-allocate IDs (transient display)
- Only explicit imageId usage (like DOSBox) gets tracked IDs
- Suppress emulators exit logging in DOSBox dispose
Fixes image replacement bug when extension and main app both
allocated sequential IDs starting at 1.
- Add allocateImageId() to generate unique image IDs
- Add deleteKittyImage() and deleteAllKittyImages() functions
- Image component now tracks its ID and has dispose() method
- renderImage() returns imageId for tracking
- DOSBox: reuse single image ID for all frames, delete on dispose
Fixes image accumulation hitting terminal quota and lingering
images after component close.
- Render DOSBox framebuffer as images in terminal via emulators package
- Support keyboard input with js-dos key codes
- Push Kitty enhanced mode for proper key press/release events
- Standalone app (npm start) and pi extension entry point
- Exit with Ctrl+Q
- Classic gameplay with 5x11 alien formation
- 3 alien types, destructible shields, level progression
- Uses Kitty keyboard protocol for smooth movement
- Saves game state on pause, tracks high score
When switching between OpenAI models (e.g., gpt-5-mini to gpt-5.2-codex),
function_call IDs with fc_ prefix trigger pairing validation errors because
OpenAI tracks which fc_xxx IDs were paired with rs_xxx reasoning items.
The fix omits the id field for function_calls from different models, which
avoids the pairing validation while keeping call_id for matching with
function_call_output.
Fixes#886
- Add maxLinesRendered to track terminal's working area (grows with content, only resets on full clear)
- Fix viewport calculation: use maxLinesRendered instead of cursorRow for correct viewport bounds
- Separate cursorRow (end of content for viewport calc) from hardwareCursorRow (actual cursor position)
- Refactor full render into fullRender(clear) helper to reduce duplication
- Fix shrink-clearing: properly clear extra lines when content shrinks
- Add PI_TUI_DEBUG=1 env var for render debugging (writes to /tmp/tui/)
The core issue was that after partial renders (e.g., overlay show/hide), the viewport
calculation used cursorRow which reflected where rendering stopped, not where content
ended. This caused incorrect viewport bounds, leading to cursor movement into scrollback
(unreachable) or rendering at wrong positions.
Additionally, when content shrank (e.g., selector dismissed), the terminal still had
the old lines as blank space. maxLinesRendered tracks this so viewport calculations
account for the terminal's actual working area.
- Added headers field to base StreamOptions interface
- Updated all providers to merge options.headers with defaults
- Forward headers and onPayload through streamSimple/completeSimple
- Bedrock not supported (uses AWS SDK auth)
Tests were throwing errors instead of skipping on CI where no API keys
are configured. Now uses describe.skipIf() and it.skipIf() patterns
consistent with other tests in the package.
Fixes OpenAI Responses 400 error 'reasoning without following item' by
skipping errored/aborted assistant messages entirely rather than filtering
at the provider level. This covers openai-responses, openai-codex-responses,
and future providers.
Removes strictResponsesPairing compat option (no longer needed).
Closes#838
Split OpenAICompat into OpenAICompletionsCompat and OpenAIResponsesCompat
for type-safe API-specific compat settings. Added strictResponsesPairing
option to suppress orphaned reasoning/tool calls on incomplete turns,
fixing 400 errors on Azure's Responses API which requires strict pairing.
Closes#768
Container components with embedded Input/Editor children must implement
Focusable and propagate focus state to enable correct IME candidate
window positioning.
Related to #827
Components with search inputs now implement Focusable interface and
propagate focus state to their child Input components. This allows
the hardware cursor to be positioned correctly for IME candidate
window placement.
Affected components:
- ModelSelectorComponent
- ScopedModelsSelectorComponent
- SessionSelectorComponent (and SessionList)
- ExtensionInputComponent
- LoginDialogComponent
- TreeSelectorComponent (and LabelInput)
fixes#827
- Add APPROVED_CONTRIBUTORS file with existing contributors
- Add pr-gate.yml workflow to close PRs from unapproved contributors
- Add approve-contributor.yml workflow to approve via lgtm on issues
- Add CONTRIBUTING.md with guidelines
- Update README.md to point to CONTRIBUTING.md
- Replace hardcoded pi->CC tool mappings with single CC tool name list
- Case-insensitive lookup: if tool name matches CC tool, use CC casing
- Remove broken find->Glob mapping (round-trip failed)
- Add test coverage for tool name normalization
When an assistant message has stopReason 'error', its tool calls are now
excluded from pending tool tracking. This prevents synthetic tool results
from being generated for calls that will be dropped by provider-specific
converters (e.g., Codex drops tool calls from errored messages).
Previously, this mismatch caused OpenAI to reject requests with 'No tool
call found for function call output with call_id ...' errors.
fixes#812
Instead of skipping unsigned tool calls entirely (which lobotomizes context),
convert them to text with an explicit note telling the model this is historical
context from a different model and not a format to mimic.
This preserves tool call/result context when switching from providers without
thought signatures (e.g. Claude via Antigravity) to Gemini 3.
When auto-compaction fails (e.g., quota exceeded), emit the error via
the auto_compaction_end event instead of throwing. The UI now displays
the error message, allowing users to take action (switch models, wait
for quota reset, etc.) instead of crashing.
fixes#792
Multiple agents may work on different files in the same worktree.
Added rules to prevent agents from accidentally committing or
destroying each other's work.
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.
When --no-extensions was used, extensionsResult.extensions was an empty
array. The condition in buildSessionOptions() checked .length > 0,
so preloadedExtensions was not set. This caused createAgentSession()
to fall through to extension discovery.
Remove the .length > 0 condition so the empty result is passed through,
signaling that extension loading was already handled.
Fixes#776
- Update ExtensionCommandContext.navigateTree type signature
- Pass new options through in print-mode and rpc-mode handlers
- Update docs/extensions.md, docs/sdk.md, docs/tree.md
- Add changelog entry
Previous commit broke Node.js/tsx by using the ESM entry point which
doesn't work with Node. This creates a wrapper module that:
- Uses require() for lazy loading (works in both Node and Bun)
- Gracefully handles load failures (returns original image)
- Works in Node.js, tsx, and Bun compiled binaries
- Import photon-node from ESM entry point (photon_rs_bg.js) instead of CJS
entry, allowing Bun to embed WASM in compiled binaries
- Add photon.d.ts for TypeScript support of ESM entry
- Add scripts/build-binaries.sh for local binary builds
- Simplify GitHub workflow to use the build script
- Add binaries/ to gitignore
Fixes cursor visibility issues in JetBrains IDE terminals (IntelliJ, PyCharm) where
the hardware cursor either blinks or becomes invisible depending on settings.
Fixes#771
Previously, OpenAI-compatible provider settings (like developer role support)
were detected only from the baseUrl. When using custom URLs (e.g., proxies),
detection failed. Now checks model.provider first, then falls back to URL.
Fixes#774
Mario Zechner