mise auto-detects single-directory archives and extracts with strip_components=1.
Using a 'pi/' wrapper directory ensures the internal structure is preserved.
Reverts the code workaround (theme dir fallback) in favor of fixing the tarball.
- Remove loader exports from index.ts to break circular dependency
- Static import of index.js in loader.ts for virtualModules
- Add @mariozechner/pi-agent-core to virtualModules
- Update @mariozechner/jiti to 2.6.5 (bundles babel for Bun binary)
- Update SDK docs to use correct extension terminology
Fixes#696
- Replaced sharp dependency with wasm-vips (WebAssembly build of libvips)
- Eliminates native build requirements that caused installation failures
- Added vips.ts singleton wrapper for async initialization
- Updated image-resize.ts and image-convert.ts to use wasm-vips API
- Added unit tests for image processing functionality
Z.ai uses thinking: { type: "enabled" | "disabled" } instead of
OpenAI's reasoning_effort. Added thinkingFormat compat flag to handle
this. Thinking is now explicitly enabled/disabled based on user setting.
Changes from the original:
- Full custom UI with options list instead of simple ctx.ui.select()
- Option descriptions: support { label, description? } in addition to strings
- Built-in 'Other...' option with inline editor for free-text input
- Better UX: Escape in editor returns to options, Escape in options cancels
- Numbered options display (1. Option, 2. Option, etc.)
- Enhanced result rendering showing selection index
Changes from the original:
- Explicit [DONE:n] tag tracking (more accurate than auto-marking on tool_result)
- Plan: header requirement - only extracts todos from 'Plan:' sections
- Utils extracted to separate file for testability
- Better session resume - only scans messages after plan-mode-execute marker
- Context filtering - properly filters plan-mode-context custom type messages
- Refactored to directory structure (index.ts + utils.ts + README.md)
The original auto-completed steps on every tool_result, which was inaccurate
for multi-tool steps. This version uses explicit [DONE:n] markers that the
agent outputs after completing each step.
- Fix ai/CHANGELOG.md: add PR link and author attribution
- Add coding-agent/CHANGELOG.md entry for vercel-ai-gateway provider
- Fix model-resolver.test.ts: use anthropic-messages API type to match generated models
- Add vercel-ai-gateway to test suites: tokens, abort, empty, context-overflow, unicode-surrogate, tool-call-without-result, image-tool-result, total-tokens, image-limits
Adjust base colors (teal, blue, green, red, yellow, dimGray) to meet
4.5:1 contrast ratio against white backgrounds. Update thinking level
colors to reference theme vars for consistency.
Refactor test-theme-colors.ts into a CLI with contrast, test, and theme
commands for easier color validation.
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
* feat: add summarize extension example
Demonstrates custom UI with markdown rendering and external model
integration for conversation summarization.
* chore: update examples/extensions/README.md with summarize.ts
- Switch from jiti to @mariozechner/jiti fork
- Use virtualModules option for bundled packages in compiled binary
- Disable tryNative so jiti handles all nested imports
- Lazy-load pi-coding-agent to avoid circular dependency
- Add minimax to KnownProvider and Api types
- Add MINIMAX_API_KEY to getEnvApiKey()
- Generate MiniMax-M2 and MiniMax-M2.1 models
- Add context overflow detection pattern
- Add tests to all required test files
- Update README and CHANGELOG with attribution
Also fixes:
- Bedrock duplicate toolResult ID when content has multiple blocks
- Sandbox extension unused parameter lint warning
- Add move() pure function for swapping adjacent items
- Handle Alt+Up/Down in handleInput to reorder enabled models
- Selection follows the moved item
- Update footer hint with new shortcut
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace mutable items[].enabled with EnabledIds type (null | string[])
- Extract state operations as pure functions (toggle, enableAll, clearAll, move, getSortedIds)
- Simplify component to UI wiring only
- Prepare for Alt+Up/Down model reordering feature
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Improve Cloud Code Assist error messages
- Extract just the message from verbose JSON error responses
- Extract cause from generic 'fetch failed' errors for better diagnostics
* Make 'other side closed' network error retryable
* Make 'other side closed' network error retryable
Adds support for Amazon Bedrock with Claude models including:
- Full streaming support via Converse API
- Reasoning/thinking support for Claude models
- Cross-region inference model ID handling
- Multiple AWS credential sources (profile, IAM keys, API keys)
- Image support in messages and tool results
- Unicode surrogate sanitization
Also adds 'Adding a New Provider' documentation to AGENTS.md and README.
Co-authored-by: nickchan2 <nickchan2@users.noreply.github.com>
Uses @anthropic-ai/sandbox-runtime to enforce filesystem and network
restrictions on bash commands (sandbox-exec on macOS, bubblewrap on Linux).
Features:
- Per-project config via .pi/sandbox.json
- Global config via ~/.pi/agent/sandbox.json
- Enabled by default with sensible defaults
- --no-sandbox flag to disable
- /sandbox command to view current config
When running with tsx in dev mode, jiti loads extensions in a separate
module cache. This caused the theme to be undefined in jiti's copy of
theme.ts since initTheme() was only called on tsx's copy.
Using globalThis with Symbol.for() ensures all module instances share
the same theme, regardless of which loader created them.
