What changed in pi, release by release
The lines under each release are pi's own release-note bullets with pull request numbers, names and links removed, grouped by its own headings. Wording is theirs. Not affiliated with pi.
v1.5.2
- NewFork sessions whose folder is gone: when a session's original folder was moved or deleted, you can now fork it into the current folder instead of…
- FixedFixed /import of a session whose working directory no longer exists leaving a copy in the session directory, and continuing it leaving a second copy…
- FixedFixed Anthropic OAuth requests reporting an outdated Claude Code version
- ChangedWhen a session's working directory no longer exists, for example after the project folder was renamed, interactive mode now offers Continue, Fork, or…
v1.5.1
- BreakingCustom GrepOperations.readFile callbacks are no longer called for context lines. The field remains accepted as optional and deprecated so existing…
- BreakingOpenAI-compatible models no longer send "tools": when all tools are disabled in a session that has used tools; the field is omitted. This fixes 400…
- NewShell login and logout: use pi auth login provider and pi auth logout provider without starting a session, with API-key and no-browser sign-in…
- NewIdle prompt cache warming: eligible caches now stay warm for up to 30 minutes between runs when a refresh is expected to pay for itself. See…
v1.5.0
- BreakingTool argument validation runs on /pi-schema. TypeBox features outside JSON Schema (Type.Refine, Type.BigInt, Type.Undefined, codecs, Format.Set…
- NewExtension update changelogs: see what changed in installed extension packages on the next fresh launch after an update. Package authors can choose…
- NewFaster streaming: large tool calls are parsed incrementally, and code-heavy answers and tool rows reuse highlighting and rendered Markdown instead of…
- ChangedExtensions keep importing Type, Static and TSchema from /pi-ai: Pi maps that import to pi-ai's compat entry plus the TypeBox it bundles, now that…
v1.4.0
- NewImage input for classifiers: codemode models.classify accepts images for TypeSafe's Jev and Cloudflare's Clef models on typesafe,…
- NewModels Configuration reference: every provider, model, model override, and compatibility field of models.json, generated from its schema. See Models…
- FixedFixed compaction and branch summaries failing with "generation hit the token cap" when reasoning used most of the fixed summary output limit.…
- FixedFixed models.schema.json missing descriptions for provider and model fields, so editors showed no hints for them
- ChangedProvider attribution headers now come from pi-ai's client identity. Extensions'
before_provider_headershandlers no longer see the OpenRouter, NVIDIA…
v1.3.0
- NewChoose where /share uploads: sessionShareDestination selects auto, gist, or radius. See Sessions and context and Export or share a session.
- NewCache-preserving thinking level changes on OpenAI GPT-6: changing the thinking level mid-session with an API key keeps the prompt cache.
- FixedPinned internal Pi dependencies to exact release versions to prevent fresh installs from mixing incompatible packages
- FixedFixed resumed sessions dropping tools activated during the session. Resume now restores the session's active tools, with --tools +name/-name entries…
- ChangedChanged the kimi-coding provider to use OpenAI Chat Completions at the protocol used by the official Kimi Code client. K3, K3-256K, and Kimi For…
v1.2.0
- BreakingPublished generated configuration schemas for models, settings, keybindings, and themes at The theme schema moved to themes loaded during startup now…
- BreakingChanged
before_agent_startto also fire for runs started by pi.sendMessage(..., { triggerTurn: true }) while idle. BeforeAgentStartEvent is now a… - BreakingChanged the session to count as busy while a run starts, including during
before_agent_starthandlers: ctx.isIdle is false, pi.sendMessage queues… - NewPer-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…
- NewPublished configuration schemas: add $schema to settings.json, models.json, keybindings, and themes for editor validation and completion. See…
v1.1.0
- NewProgram status reporting: terminals and agent dashboards that support OSC 7501 see whether Pi is working, blocked on a dialog or login, done, or…
- NewClaude Haiku 5.5: anthropic/claude-haiku-5-5, with adaptive thinking up to xhigh/max effort.
- FixedFixed bash and PowerShell results losing Took after reloading a session, and the live Took including wall-clock steps; both now show the recorded…
- FixedFixed managed installs keeping every old release; pi update now keeps only the new release and the one it updated
- ChangedChanged outputPad to also apply to ! command output, tool output, and summary blocks
v1.0.4
- NewTool patterns and --no-mcp: --tools and --exclude-tools accept * patterns, for example --tools read,codemode,'mcpradius*' keeps only one MCP server's…
- NewCodemode persists images: tools.read on an image file now gives back an image block that image can show. See Call tools.
- FixedFixed syntax highlighting losing colors after the first line of multiline strings and comments in fenced code blocks
- FixedFixed codemode scripts not receiving images from read: tools.read now resolves to an image block for image files, which image shows
v1.0.3
- BreakingRenamed the Azure provider from azure-openai-responses to azure. Rename the provider key in auth.json (or run /login again), in models.json, and in…
- NewAzure Foundry Chat Completions — The azure provider (renamed from azure-openai-responses) now also serves Foundry Chat Completions deployments,…
- NewCodemode 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…
- FixedFixed subscription logins such as Sign in with ChatGPT failing with
refresh_token_invalidatedafter a request was cancelled during an OAuth token… - FixedFixed codemode failing for the rest of a session after a pnpm global update removed the running install, and added a restart hint when errors occur…
v1.0.2
- NewSampling by thinking level — samplingParamsByThinkingLevel in models.json sets sampling parameters such as temperature and
top_pfor each thinking… - NewAdded samplingParamsByThinkingLevel to models.json for per-thinking-level sampling parameter overrides on OpenAI-compatible APIs. See Configure…
How we calculate
- Days between releases: The median of the gaps, in days, between the release dates listed above.
Data: earendil-works/pi's GitHub releases page, read November 18, 2026. Every other figure on this page is copied from the record, not calculated by us.
Get this for your repo, every release
pi publishes release notes that people can read. FoxPlug writes yours from what you ship: a changelog entry and posts for the places your users are, each approved by you.
Get this for your repo, every releaseTry it on your repo nowYour changelog, written for you
FoxPlug writes your changelog from your releases and commits in plain English and publishes it as a page and a feed your users can follow. The page above shows what that looks like for a product people really use.
Write my changelog See the changelog FoxPlug wrote from its own commits
Free to start. Pro is a month.
FoxPlug Pro
- A public changelog page and feed for each project
- Written from your releases and commits, in plain English your users read
- Connect GitHub and new releases become new entries