Pi v1.6.0 is a Mario Zechner release published 2026-11-20 with 62 listed changes, flagged for breaking changes, security fixes. Summary and full notes below, extracted from the official notes.
One free email: every breaking change, retirement and price change across 23 coding agents. No spam, unsubscribe anytime.
Subscribe free← All Pi releases and breaking changes
### New Features
- **GPT-6.2 Astra and GPT-6.2 Sol**: both models are available on the `openai`, `azure`, and `openai-codex` providers, and GPT-6.2 Sol is now the default model for all three. See [Providers](https://github.com/earendil-works/pi/blob/v1.6.0/packages/coding-agent/docs/providers.md).
### Breaking Changes
- Extension components: `render()` now returns `readonly string[]`, and `Container` returns the same cached array while its children are unchanged. Extensions that modify render output in place, including `super.render()` in a `Container` subclass or an embedded component's output, must copy it first ([#9549](https://github.com/earendil-works/pi/issues/9549))
### Added
- Added GPT-6.2 Astra and GPT-6.2 Sol to the `openai`, `azure`, and `openai-codex` providers. Both reject reasoning effort `none` and `minimal`, so thinking level `off` is unavailable. Azure serves them with a 1.05M context window; Codex serves GPT-6.2 Sol with 500K and GPT-6.2 Astra with 272K
- Added `qwen4-max-preview` to the Qwen Token Plan Individual providers ([#12259](https://github.com/earendil-works/pi/issues/12259))
- Added `deepseek-v4.1-flash` and `deepseek-v4.1-flash-1017` to the Qwen Token Plan Individual providers, and per-plan key variables `QWEN_TOKEN_PLAN_TEAM_API_KEY`, `QWEN_TOKEN_PLAN_TEAM_CN_API_KEY`, `QWEN_TOKEN_PLAN_INDIVIDUAL_API_KEY`, and `QWEN_TOKEN_PLAN_INDIVIDUAL_CN_API_KEY`; the shared `QWEN_TOKEN_PLAN_API_KEY` and `QWEN_TOKEN_PLAN_CN_API_KEY` still work ([#11773](https://github.com/earendil-works/pi/issues/11773))
- Added a transcript notice when OpenAI drops reasoning items from a request, such as `OpenAI dropped 2 reasoning items: prefix_mismatch (details in session)` after compaction on GPT-6.2. Like the Anthropic thinking notice, it is shown when `showCacheMissNotices` is on and only when more items are dropped than in the previous response. Both notices now name the reasons
### Changed
- Qwen Token Plan providers now use the current gateways (`token-plan.maas.qwencloudapi.com` international, `token-plan.maas.qianwenaiapi.com` China), and `qwen-token-plan` and `qwen-token-plan-cn` are named "Qwen Token Plan Team" and "Qwen Token Plan Team CN". Provider IDs are unchanged, and the old `aliyuncs.com` hosts still work ([#11773](https://github.com/earendil-works/pi/issues/11773))
- Updated `undici` to 8.12.4 for security advisories GHSA-mqg3-3v4r-cm32, GHSA-7xg3-fphp-28hg, GHSA-5rm8-gv32-r954, GHSA-9v6h-8rgp-m69f, GHSA-3g9m-rv3r-w5w2, and GHSA-r4pc-4jcp-7pqc ([#12200](https://github.com/earendil-works/pi/issues/12200))
- The default model for the `openai`, `azure`, and `openai-codex` providers is now GPT-6.2 Sol (`gpt-6.2-sol`) instead of GPT-6.1 Sol, at the same price
- The find tool's path patterns are now relative to the search directory, like grep's `glob`: `src/*.ts` finds `src/a.ts` but no longer `pkg/src/a.ts`; use `**/src/*.ts` to match at any depth. Patterns without `/` still match file names at any depth ([#12066](https://github.com/earendil-works/pi/issues/12066))
- The llama.cpp extension now connects to `http://127.0.0.1:9931` by default, the current llama-server default port, instead of port 8080 ([#12001](https://github.com/earendil-works/pi/pull/12001) by [@julien-c](https://github.com/julien-c))
- Anthropic message threads are now on by default for any provider whose baseUrl is on api.anthropic.com, not only the `anthropic` provider ([#11987](https://github.com/earendil-works/pi/issues/11987))
- The resume command printed on exit is now on its own line after `To resume this session:`, so it can be selected with a triple-click ([#12237](https://github.com/earendil-works/pi/issues/12237))
### Fixed
- Fixed `read` storing a note that the current model does not support images, which was replayed to the model as stale text after switching to a vision model. The image is still replaced with a placeholder per request for models without image input, and the read result now shows the warning in the TUI only, also when collapsed ([#12131](https://github.com/earendil-works/pi/issues/12131))
- Fixed MCP tools loaded by `tool_search` being dropped on resume and `/reload` when an extension deactivates only its own tool at `session_start`, as pi-web-access and pi-subagents do in `toolActivation: "auto"` mode ([#11996](https://github.com/earendil-works/pi/issues/11996))
- Fixed the standalone binary failing to resolve extension npm dependencies whose entry point is declared in `package.json` `main` or `exports` (for example `shiki`, `yaml`, `graceful-fs`), including imports made from inside other dependencies ([#12012](https://github.com/earendil-works/pi/issues/12012))
- Fixed the find tool returning no results for patterns starting with `./`, such as `./src/*.ts` ([#12020](https://github.com/earendil-works/pi/issues/12020))
- Fixed pi exiting with an uncaught `AbortError` when a `read` tool call is cancelled while the file is being opened ([#11956](https://github.com/earendil-works/pi/issues/11956))
- Fixed pi exiting with an uncaught `AbortError` when the session picker cancels loading after skipping a `.jsonl` file that is not a session, and fixed such files staying open ([#11956](https://github.com/earendil-works/pi/issues/11956))
- Fixed `/share` crashing pi when the GitHub CLI fails to start
- Fixed `pi update` on Windows managed installs failing with "Could not verify managed Pi" when an older system Node.js comes before the installer's standalone Node.js on PATH ([#12048](https://github.com/earendil-works/pi/issues/12048))
- Fixed `/export` HTML showing raw terminal hyperlink escape codes around links in custom tool output; links are now clickable ([#12003](https://github.com/earendil-works/pi/issues/12003))
- Fixed the bash tool returning no output, with a footer like `[Showing lines 3-2 of 2]`, when the output ends in one line longer than about 100KB, such as a `grep` match in a minified file; it now shows the end of that line ([#12062](https://github.com/earendil-works/pi/issues/12062))
- Fixed provider errors reading "Connection closed." not triggering automatic retries ([#12064](https://github.com/earendil-works/pi/issues/12064))
- Fixed `/resume` sometimes selecting an unrelated session while the list reloads after deleting or renaming a session ([#12106](https://github.com/earendil-works/pi/issues/12106))
- Fixed Groq Qwen models failing with `400 Unexpected message role`; OpenAI-compatible providers other than OpenAI now receive system messages (the system prompt and mid-conversation system messages) with the `system` role ([#10741](https://github.com/earendil-works/pi/issues/10741))
- Fixed `enabledModels`/`--models` warnings such as `No models match pattern "github-copilot/nope"` being written over the interactive TUI on every `/new`, `/resume` and `/fork`, which left stale lines in fullscreen mode. The warnings are now shown once at startup, in the chat in interactive mode and on stderr in other modes; RPC mode no longer repeats them on stderr for each `new_session`, `switch_session` or `fork` ([#11264](https://github.com/earendil-works/pi/issues/11264))
- Fixed the find tool matching path patterns through folders above the search path: with the project in `~/src/app`, `src/**/*.ts` returned every `.ts` file in the project ([#12066](https://github.com/earendil-works/pi/issues/12066))
- Fixed pi crashing with `RangeError: Maximum call stack size exceeded` when rendering a very large edit diff, for example after editing a file with a multi-megabyte line, and again on every resume of that session ([#8036](https://github.com/earendil-works/pi/issues/8036))
- Fixed pressing Esc during a batch of tool calls leaving the calls that had not started yet without a result in the session; they now get an "Operation aborted" result ([#9986](https://github.com/earendil-works/pi/issues/9986))
- Fixed an unreadable `CHANGELOG.md` (pi's own or an extension package's) printing `Warning: Could not parse changelog` over the interactive TUI; it now shows no changelog notes ([#11264](https://github.com/earendil-works/pi/issues/11264))
- Fixed problems found when replacing the session with `/new`, `/resume`, `/fork` or RPC `new_session`, `switch_session` and `fork` never being shown, for example a project extension that fails to load after `/resume` into another project, or an `enabledModels` pattern that matches nothing after a settings change. Interactive mode now shows them in the chat and print, JSON and RPC modes write them to stderr; a problem already reported is not repeated. SDK hosts can call the new `AgentSessionRuntime.takeUnreportedDiagnostics()` at startup and after each replacement to get each diagnostic once
- Fixed RPC `new_session`, `switch_session`, `fork` and `clone` running extension `session_start` and `resources_discover` handlers twice for the new session. RPC clients now also receive events emitted by `session_start` handlers, such as `entry_appended` for entries they append ([#10470](https://github.com/earendil-works/pi/issues/10470))
- Fixed an exception thrown by an extension's `pi.events` handler being printed with `console.error` over the interactive TUI. It is now reported like other extension errors: in the chat in interactive mode, as `extension_error` in RPC mode and as `Extension error (...)` in print mode. Errors from a handler that fails after its session was replaced are dropped ([#11264](https://github.com/earendil-works/pi/issues/11264))
- Fixed `AgentSession.reload()` not emitting `session_start` to extensions when the SDK host bound them with `bindExtensions({})`, after it had already emitted `session_shutdown`. Extensions that start work in `session_start`, such as the MCP extension connecting its servers, stayed stopped after a reload
- Fixed `--mode json` dropping events emitted by extension `session_start` handlers, such as `entry_appended` for entries they append, at startup and after an extension replaces the session
- Fixed `Could not restore model <provider>/<model>. Using <fallback>` being shown only at interactive startup. Resuming or forking into a session whose model no longer exists or has no login switched to another model without notice, and print, JSON and RPC modes never showed it. It is now reported in every mode, at startup and after `/resume`, `/fork` and RPC `switch_session` or `fork`
- Fixed git and npm output, such as `Cloning into ...` or `added 12 packages`, being drawn over the interactive TUI when pi installed or refreshed packages during `/reload`, `/new`, `/resume` and `/fork`, including temporary `-e git:` and `-e npm:` packages. In interactive mode their output is now captured, and a failed install reports the end of it. Until the TUI starts, each install is announced as `Installing <source>...` on stderr instead of showing git and npm output. git and ssh can no longer prompt in interactive mode: a package that needs a typed password or passphrase fails with a hint to set up a credential helper or ssh agent, or to run `pi install <source>` once from the shell. `pi install` and `pi update` keep live output ([#11264](https://github.com/earendil-works/pi/issues/11264))
- Fixed fullscreen scrolling in long sessions saturating a CPU core by re-rendering the whole transcript on every wheel event ([#9549](https://github.com/earendil-works/pi/issues/9549))
- Fixed search in `/login`, `/logout`, `/scoped-models` and `/resume` keeping the highlight on the row scrolled to before typing, so Enter picked whichever entry landed there instead of the best match; a query now highlights the top match, as `/model` does ([#12245](https://github.com/earendil-works/pi/issues/12245), [#12246](https://github.com/earendil-works/pi/pull/12246) by [@acmerfight](https://github.com/acmerfight))
- Fixed exiting pi, `pi config` and the `--resume` and other startup pickers dropping terminal output still queued in stdout, such as the resets that turn off mouse tracking and Kitty keyboard reporting; the shell could then print mouse and key reports as text. pi now waits up to one second for queued output before exiting or continuing ([#12133](https://github.com/earendil-works/pi/issues/12133))
- Fixed moving the cursor in a search field with Left, Right, Home or End moving the highlight back to the first entry in `/login`, `/logout`, `/model`, `/scoped-models`, `/resume`, `/settings`, the per-model settings model picker and `pi config` ([#12245](https://github.com/earendil-works/pi/issues/12245))
- Fixed llama.cpp decision classifiers ignoring the image input that llama.cpp reports, such as Clef with its `mmproj`; `models.classify()` now sends their images to `/v1/systemone` ([#12282](https://github.com/earendil-works/pi/issues/12282))
- Fixed `kill -TSTP` from outside pi stopping it without restoring the terminal, which left mouse tracking and the Kitty keyboard protocol on at the shell prompt and turned mouse movement into garbage input. pi now suspends as with Ctrl+Z and redraws on `fg` ([#12283](https://github.com/earendil-works/pi/pull/12283) by [@haoqixu](https://github.com/haoqixu))
- Fixed changing the thinking level on the `openai-codex` provider invalidating the prompt cache on GPT-6 models ([#12269](https://github.com/earendil-works/pi/issues/12269))
- Fixed unscoped syntax-highlighted text inheriting the terminal foreground and becoming unreadable on contrasting tool cards ([#11092](https://github.com/earendil-works/pi/issues/11092))
- Fixed `/copy` saying "No agent messages to copy yet." after Esc during a tool call or after a provider error; it now copies the previous answer. RPC `get_last_assistant_text` skips the same messages ([#12119](https://github.com/earendil-works/pi/issues/12119), [#12121](https://github.com/earendil-works/pi/pull/12121) by [@acmerfight](https://github.com/acmerfight))
- Fixed `pi.exec` reporting exit code 0 for commands ended by a signal, such as a timeout, an abort or a crash; it now reports 128 + the signal number, like a shell (143 for SIGTERM, 137 for SIGKILL) ([#12088](https://github.com/earendil-works/pi/issues/12088), [#12089](https://github.com/earendil-works/pi/pull/12089) by [@acmerfight](https://github.com/acmerfight))
- Fixed GitHub Copilot Gemini and Kimi models (`gemini-4-argon`, `gemini-4-carbon`, `gemini-3.8-flash`, `kimi-k3`) ignoring the thinking level, and Copilot usage always reporting 0 reasoning tokens ([#12110](https://github.com/earendil-works/pi/pull/12110) by [@DenielC1](https://github.com/DenielC1))
- Fixed provider errors that report only a Node socket error code, such as `read ECONNRESET`, `write EPIPE`, or `connect ETIMEDOUT`, not triggering automatic retries ([#12128](https://github.com/earendil-works/pi/issues/12128))
- Fixed OpenAI rejecting requests with a 400 error when a tool's schema contains a node without a `type` (such as `items: {}` or `Type.Unknown()`); such tools are now sent in non-strict mode ([#12049](https://github.com/earendil-works/pi/issues/12049))
- Fixed Mistral Large 4 tool calls stalling for minutes; Mistral models no longer receive strict tools unless `compat.supportsStrictMode` is set ([#12148](https://github.com/earendil-works/pi/issues/12148))
- Fixed non-strict Anthropic tool schemas not telling the model that extra arguments are forbidden ([#12067](https://github.com/earendil-works/pi/issues/12067))
- Fixed GitHub Copilot models on the Responses API (GPT, Grok, MAI-Code) filling omitted optional tool arguments with empty strings or invented values ([#12286](https://github.com/earendil-works/pi/issues/12286))
- Fixed the OpenAI Codex WebSocket 60-minute connection limit failing the turn when it hit mid-stream, for example during long thinking; the request is now retried on a fresh connection ([#12124](https://github.com/earendil-works/pi/issues/12124))
- Fixed the `openai-codex` provider getting almost no prompt cache hits for the system prompt on GPT-6.2 models ([#12273](https://github.com/earendil-works/pi/issues/12273))
- Fixed the `openai-codex` provider ignoring a model's `maxTokens`
- Fixed fullscreen Kitty images disappearing after a full redraw such as a window resize ([#12010](https://github.com/earendil-works/pi/issues/12010))
- Fixed text after a multi-row inline image in Markdown drawing over the image ([#12017](https://github.com/earendil-works/pi/issues/12017))
- Fixed Kitty and iTerm2 images covering overlays drawn over them ([#11584](https://github.com/earendil-works/pi/issues/11584))
- Fixed Enter on a Tab path menu for an absolute path (`look at /tmp/fi`) or a slash command argument menu (`/open /tm`) submitting the prompt instead of accepting the completion ([#12309](https://github.com/earendil-works/pi/issues/12309), [#12312](https://github.com/earendil-works/pi/pull/12312) by [@acmerfight](https://github.com/acmerfight))
### Removed
- Removed the retired `deepseek-v3.2` and `deepseek-v4-flash` from the Qwen Token Plan Team providers; use `deepseek-v4-flash-0731` or `deepseek-v4.1-flash` ([#11773](https://github.com/earendil-works/pi/issues/11773))