Pi by Mario Zechner
Source: https://github.com/badlogic/pi-mono/releases
Weekly digest: every breaking change, retirement and price change across 20+ coding agents, one email.
Form not loading? Subscribe here.
2026-10-15 · 32 changes · release
- New Features
- Choose where /share uploads: sessionShareDestination selects auto, gist, or radius. See Sessions and context and Export or share a session.
- Cache-preserving thinking level changes on OpenAI GPT-6: changing the thinking level mid-session with an API key keeps the prompt cache.
2026-10-12 · 43 changes · release
- New Features
- Per-key OpenRouter model lists: with an OpenRouter key, Pi lists only the models that key may use, with the key's context size, max output, and prices, including regional endpoints set in models.json.
- Published configuration schemas: add $schema to settings.json, models.json, keybindings, and themes for editor validation and completion. See Settings, Models, Keybindings, and Themes.
2026-10-07 · 38 changes · release
- New Features
- Program status reporting: terminals and agent dashboards that support OSC 7501 see whether Pi is working, blocked on a dialog or login, done, or failed. See Program status.
- Claude Haiku 5.5: anthropic/claude-haiku-5-5, with adaptive thinking up to xhigh/max effort.
2026-10-05 · 12 changes · release
- New Features
- Tool patterns and --no-mcp: --tools and --exclude-tools accept patterns, for example --tools read,codemode,'mcpradius' keeps only one MCP server's tools. --tools now keeps MCP tools unless an entry s
- Codemode persists images: tools.read() on an image file now gives back an image block that image() can show. See Call tools.
2026-10-05 · 10 changes · release
- New Features
- Azure Foundry Chat Completions — The azure provider (renamed from azure-openai-responses) now also serves Foundry Chat Completions deployments, starting with azure/deepseek-v4-pro. See Azure OpenAI.
- Codemode images saved to files — image() also writes each image to a temp file and names the path in the result, so later turns can copy or move generated images. See Generate images.
2026-10-04 · 2 changes · release
- New Features
- Sampling by thinking level — samplingParamsByThinkingLevel in models.json sets sampling parameters such as temperature and topp for each thinking level on OpenAI-compatible APIs. See Configure samplin
- Added samplingParamsByThinkingLevel to models.json for per-thinking-level sampling parameter overrides on OpenAI-compatible APIs. See Configure sampling by thinking level (#9776 by @mrexodia)
2026-10-03 · 27 changes · release
- New Features
- Nix flake — nix run github:earendil-works/pi/stable runs the latest release, and nix profile add github:earendil-works/pi/stable installs it. See Install pi.
- Project overrides for MCP servers — .pi/mcp.json and /mcp can enable, disable, or change the exposure of a user-level server for one project. See Configure servers.
2026-10-01 · 32 changes · release
- New Features
- Fullscreen by default — The TUI now runs fullscreen. Set tuiMode to "regular" to keep the terminal's normal scrollback. See Terminal and display.
- Leaner codemode — About 40% fewer prompt tokens, and errors that tell the model how to recover. See Codemode.
2026-09-30 · 26 changes · release
- New Features
- MCP servers stay out of the way: servers with the default codemode exposure are no longer listed in the codemode description and no longer block the first prompt. They appear in a short system prompt
- More MCP authentication options: oauth.clientName for servers that only accept known OAuth clients, and "auth": { "provider": "<provider>" } to authenticate HTTP servers with a provider's /login token
2026-09-29 · 4 changes · release
- New Features
- GPT-6.1 Sol — Available on OpenAI, Azure OpenAI, and OpenAI Codex, and now the default OpenAI Codex model. See Select a model.
- Added GPT-6.1 Sol (gpt-6.1-sol) to the OpenAI, Azure OpenAI Responses, and OpenAI Codex providers.
2026-09-29 · 65 changes · release
- New Features
- Codemode and MCP — Connect MCP servers and let models run JavaScript that calls tools in parallel. See MCP Servers and Enable codemode.
- System theme — Pi's colors now come from your terminal's own palette by default. See Use your terminal's colors.
2026-09-22 · 10 changes · release
- New Features
- Latest frontier models — Use Claude Opus 5.5, GPT-6 Sol, and GPT-6 Luna through supported providers, including GitHub Copilot. See Choose a Model.
- Grok 4.7 by default for xAI — New xAI sessions now default to Grok 4.7. See Provider Authentication.
2026-09-21 · 24 changes · release
- New Features
- Canonical session context and extension boundaries — Edit model context without rewriting history and add actionable lifecycle hooks. See ContextEditEntry and extension events.
- Full-transcript context extensions — Use contextwithsystem for per-request system-message transformations. See contextwithsystem.
2026-09-20 · 8 changes · release
- New Features
- Meta Muse provider — Sign in with Meta using /login meta or use METAAPIKEY to access Muse Spark models. See Meta (Muse subscription).
- Added Meta (Muse subscription) login via /login meta with automatic Model API key refresh, plus METAAPIKEY support (#9096 by @xl0).
2026-09-19 · 66 changes · release
- New Features
- Prompt cache warming — Keep valuable prompt caches alive during long tool runs and optionally while idle using cost-aware refreshes. See Cache Warming.
- Bug reporting — Report problems with /bug using redacted diagnostics, optional transcripts, or exported ZIP archives. See Reporting Bugs.
2026-09-05 · 7 changes · release
- New Features
- GPT-6 Astra — Available through OpenAI API keys and OpenAI Codex subscriptions. See API Keys and OpenAI Codex.
- Added GPT-6 Astra for OpenAI API keys and OpenAI Codex subscriptions.
2026-09-04 · 34 changes · release
- New Features
- Persistent Claude thinking effort — Supported Anthropic transports preserve per-turn effort and recover safely from signed-thinking mismatches. See Model Configuration.
- Fullscreen transcript controls — Jump to the latest message from a scrolled transcript and use the embedded working indicator. See TUI Fullscreen Viewport.
2026-08-28 · 29 changes · release
- New Features
- Terminal capability overrides — Override detected terminal hyperlink, image, and truecolor support. See Capability Overrides.
- Extension UI prompt events — Integrations can distinguish active agent work from time spent waiting for ctx.ui prompts. See Extension UI prompt events.
2026-08-24 · 62 changes · release
- New Features
- PowerShell tool — Use optional native PowerShell command execution on Windows. See PowerShell Tool.
- Safer managed updates — Stage, verify, and atomically activate updates for installer-managed installations. See Install and Manage.
2026-08-14 · 42 changes · release
- New Features
- Fullscreen transcript search — Search and navigate matches in fullscreen mode. See TUI Fullscreen Viewport.
- Configurable default tools — Choose startup built-in tools globally or per project. See Tools.
2026-08-07 · 17 changes · release
- New Features
- Qwen Token Plan Individual — Use the built-in provider for models documented for Individual subscriptions. See API Keys.
- Authentication readiness checks — Use pi auth check to verify provider or model credentials, optionally emitting the resolved credential.
2026-08-06 · 119 changes · release
- New Features
- Fullscreen TUI mode — Switch between regular and fullscreen modes at runtime, with a sticky editor and footer, independently scrollable transcript, and draggable scrollbars. See UI & Display.
- Mermaid and LaTeX rendering — Render Mermaid diagrams and terminal-friendly Unicode math in interactive transcripts. See Markdown settings and TUI Markdown.
v0.83.0breakingdeprecatedmodelpricing
2026-07-29 · 28 changes · release
- New Features
- Credential export for external clients — pi auth print-api-key and pi auth print-bearer-token export configured credentials with automatic OAuth refresh and minimum-validity enforcement.
- Headless OpenRouter sign-in — Complete /login over SSH by pasting the redirect URL or authorization code when the loopback callback is unavailable. See OpenRouter.
2026-07-25 · 13 changes · release
- New Features
- Claude Opus 5 — Available on Anthropic and Amazon Bedrock with adaptive thinking (including xhigh), inference profiles, and prompt caching. See Providers.
- Anthropic gateway bearer auth — ANTHROPICAUTHTOKEN authenticates against Anthropic-compatible gateways that require Authorization: Bearer, including compaction and branch summaries. See Environment Va
2026-07-24 · 27 changes · release
- New Features
- Constrained tool sampling — Tools can prefer or require strict JSON Schema sampling or use OpenAI Lark/regex grammars, with model capability metadata preventing unsupported requests. See Constrained S
- OpenRouter and Kimi Code sign-in — Use /login to authorize OpenRouter or a Kimi Code subscription without manually configuring API keys. See OpenRouter.
2026-07-21 · 7 changes · release
- New Features
- Verifiable release source archives — GitHub releases now include deterministic, checksummed source archives with instructions for rebuilding standalone binaries. See Building standalone binaries from
- Resilient compaction and branch summaries — Transient provider failures now follow the configured retry policy, with retry lifecycle events available to interactive, JSON, RPC, and SDK consumers. See
2026-07-21 · 31 changes · release
- New Features
- Local llama.cpp model management — Connect to a llama.cpp router, search and download Hugging Face models, and explicitly load or unload models with live progress. See llama.cpp.
- Full provider extensions — Extensions can register complete pi-ai providers with authentication, model refresh, filtering, and custom streaming. See Register New Provider.
2026-07-16 · 5 changes · release
- New Features
- Kimi Coding thinking compatibility — Kimi Coding models now use adaptive thinking correctly; K3 exposes its supported max level and supports replaying empty-signature thinking blocks. See Kimi For Cod
- Fixed inherited Kimi Coding requests to use Anthropic adaptive thinking effort without token budgets, and enabled empty thinking signatures for K3 and kimi-for-coding.
2026-07-16 · 7 changes · release
- New Features
- Kimi K3 and deferred tool loading — Use Kimi K3 across built-in providers, including progressive extension tool activation through Kimi’s native protocol. See Dynamic Tool Loading, OpenAI Compatibilit
- Added inherited Kimi K3 support for Kimi Coding, Moonshot AI, Moonshot AI China, OpenRouter, and Vercel AI Gateway.
2026-07-16 · 23 changes · release
- New Features
- Unified model runtime and provider authentication — ModelRuntime centralizes model configuration, provider-owned /login, and dynamic provider catalogs. See Providers.
- Live model catalog refresh — /model refreshes configured providers in the background, and pi update --models forces an immediate refresh. See Install and Manage.