apex-code 0.4.0 → 0.5.1

package/CHANGELOG.md

@@ -1,6 +1,38 @@
 # Apex Code changelog
 
-## [Unreleased]
+## [0.5.1] - 2026-09-27
+
+### Changed
+
+- **A session opens with everything collapsed.** Tool output shows a counted preview, edit diffs show their line counts, thinking shows one `Thinking... ctrl+o to expand` line, and a multi-line error shows its first line (or, for a Python traceback, the raised error) with the same hint. Press `ctrl+o` to step through overview, details, and all. The level you pick is saved as `chatDetail` in `~/.apex-code/settings.json`, so the next session opens at it; `/settings` also has a Conversation detail row. Turning thinking on with `ctrl+t` opens the transcript far enough to show it.
+
+### Fixed
+
+- **Starting Apex in a trusted project left untracked files behind.** Reading permission rules went through the write lock, which creates the file it locks, so the first run in any trusted repository created `.apex-code/permissions.json` and `.apex-code/permissions.local.json`, and `~/.apex-code/permissions.json`. Missing rules files are read as empty without creating anything; other filesystem errors are surfaced in the permission snapshot instead of being mistaken for missing files. Files are still created the first time you save a rule.
+
+## [0.5.0] - 2026-09-23
+
+### Changed
+
+- **An update shows one line at launch instead of the full release notes.** `collapseChangelog` now defaults to `true`. Run `/changelog` for the full notes, or set `collapseChangelog: false` to see them at launch again.
+- **Pickers, dialogs, and extension components in the composer area line up with the composer.** They start on the `›` column, two columns in. An extension component mounted there moves with them.
+- **An extension renderer that collapses its output now states what it hides.** The generic `ctrl+o to expand` hint the panel used to append is gone, because it also appeared under output that was shown in full. Built-in tools print a counted hint, `... (12 more lines, ctrl+o to expand)`; an extension should do the same.
+- **The interface speaks one grammar.** Key hints read `up/down move · enter select · escape/ctrl+c close` everywhere and name the key you bound. Text fields use the composer's `›` prompt. Picker titles are sentence case, and `/settings` has one.
+
+### Fixed
+
+- **Your message and the assistant's answer looked the same.** Both wore the same accent rail. Your message keeps the rail, now with a gap before the text; the assistant's has none.
+- **A failed retry run stacked one error per attempt.** It now ends in one line, `Error: … (gave up after 3 retries)` or `(retry cancelled)`.
+- **Tool panels contradicted themselves.** bash showed its duration twice with two different numbers, a panel offered `ctrl+o to expand` under output it already showed in full, and a preview could hide a single line behind a hint that took the same row. Each panel now has one blank row under its header.
+- **The footer said `CH95.0%`.** It now reads `cache 95%`, and usage below 0.1% reads `<0.1%` instead of `0.0%` beside a lit gauge cell.
+- **Palette rows carried an unexplained `[u]`, `[p]`, or `[t]`.** The scope letter is gone; a skill or command from a package still names it, `[npm:…]` or `[git:…]`.
+- **Running from source failed at startup with `hljs is not defined`.** Use `npx tsx --tsconfig tsconfig.runtime.json`, which `pi-test.sh` and the README now do.
+
+- **`--mode json` exited `0` when the run failed.** Both assignments of a non-zero exit code sat inside a `if (mode === "text")` branch, so a provider error, a cancelled run, and an exhausted `runBudget` all reported success to the caller. The JSON stream carried the failure the whole time; only the exit code disagreed, which is the worst shape for the mode the README recommends for automation, because a CI job reads the code and not the stream. The outcome is now resolved once for every mode, from `agent_end`'s structured stop reason where there is one and from the settled assistant message otherwise. `--mode text` keeps its behavior on every path a run actually takes. Two edge cases do move, both toward the stop reason the loop decided rather than a message that may predate it: an `agent_end` failure whose last message is not an assistant message now exits 1 instead of 0, and a `completed` run whose last message still carries a stale error now exits 0 instead of 1. This is a deliberate break for anyone whose pipeline treated `0` from `--mode json` as "the process ran": those runs now exit `1`, which is what they always meant.
+
+### Added
+
+- **A `result` envelope ends a `--mode json` run.** The final line is `{"type":"result","status":"..."}`, where `status` is `completed`, `error`, `aborted`, or `budget-exhausted` — the agent loop's own `AgentStopReason` vocabulary rather than a second one that could drift from it. It lets a caller branch on why a run ended instead of inferring it from an integer, which is why the exit codes stay at `0` and `1` rather than growing a numeric taxonomy that would freeze today's guesses. It is written by print mode, not emitted by the session, so it is not an `AgentSessionEvent` and never appears in `--mode text`.
 
 ## [0.4.0] - 2026-09-21
 
@@ -468,6 +500,244 @@ The entries below are retained as historical attribution for the forked code.
 
 # Changelog
 
+## [0.87.1] - 2026-09-22
+
+### 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](docs/models.md#select-a-model).
+- **Grok 4.7 by default for xAI** — New xAI sessions now default to Grok 4.7. See [Provider Authentication](docs/providers.md#use-an-api-key-from-the-environment).
+
+### Added
+
+- Added inherited Claude Opus 5.5, GPT-6 Sol, and GPT-6 Luna support for GitHub Copilot.
+- Added inherited GPT-6 Sol and GPT-6 Luna support for OpenAI API keys and OpenAI Codex subscriptions.
+- Added inherited Claude Opus 5.5 support for Anthropic with adaptive thinking and a 1M context window.
+
+### Changed
+
+- Changed the default xAI model to Grok 4.7.
+
+### Fixed
+
+- Fixed split-turn compaction summaries being refused by Claude Fable 5.1 by clearly separating the conversation and using continuation-oriented instructions ([#9908](https://github.com/earendil-works/pi/pull/9908) by [@davidbrai](https://github.com/davidbrai)).
+- Fixed missing or invalid `--mode` values being silently ignored instead of reporting an error and exiting with a nonzero status ([#9045](https://github.com/earendil-works/pi/issues/9045)).
+- Fixed inherited image-only user messages being rejected by some OpenAI-compatible providers because they included an empty text part ([#9797](https://github.com/earendil-works/pi/issues/9797)).
+- Fixed inherited Anthropic OAuth requests reporting an outdated Claude Code version.
+
+## [0.87.0] - 2026-09-21
+
+### New Features
+
+- **Canonical session context and extension boundaries** — Edit model context without rewriting history and add actionable lifecycle hooks. See [ContextEditEntry](docs/session-format.md#contexteditentry) and [extension events](docs/extensions.md#extension-events).
+- **Full-transcript context extensions** — Use `context_with_system` for per-request system-message transformations. See [`context_with_system`](docs/extensions.md#context_with_system).
+- **Per-model image input limits** — Configure cache-safe image resizing per model for attachments, `read`, and tool-result images. See [Image Input Limits](docs/models.md#image-input-limits).
+
+### Breaking Changes
+
+- Removed the inherited `shouldStopAfterTurn` agent option. Use `finishTurn` and return `{ action: "end" }` instead. `finishTurn` runs before `turn_end` but applies the decision afterward, and it also receives error and aborted responses; migrate normal-response predicates by returning `undefined` for those hard exits. See the `@earendil-works/pi-agent-core` changelog for a complete before-and-after example.
+- Added `ContextEditEntry` to the exported `SessionEntry` union. TypeScript consumers with exhaustive entry switches must handle `context_edit`; use `replacement: null` for omission and a content replacement otherwise.
+- Made `SessionManager` canonical for `AgentSession` provider context. Assigning `session.agent.state.messages` no longer replaces future request history; restore with `SessionManager.inMemory(cwd, { id }, entries)`, navigate with `session.navigateTree()`, or append through `session.sessionManager` and call `session.refreshContext()`.
+- Expanded `TurnEndEvent` with required boundary fields and added `AgentBeforeSettleEvent` to the exported `ExtensionEvent` union. Consumers constructing events or exhaustively switching on `ExtensionEvent` must handle the new shapes. `ExtensionRunner.emit()` no longer accepts `turn_end`; host integrations dispatch actionable boundaries with `emitBoundary(baseEvent, buildContext)`.
+- Deferred runs requested from `agent_settled` handlers until all settled handlers finish. Handlers still observe `ctx.isIdle() === true`, but no longer see a reentrant `agent_start` during the same notification dispatch.
+
+### Added
+
+- Added append-only model-context edits. For example, `sessionManager.appendContextEdit(entryId, null)` omits one message from future provider context without changing raw history, usage, or UI history.
+- Added actionable `turn_end` and `agent_before_settle` extension boundaries. Return `{ entries: [...event.entries, draft], continue: true }` to persist structural entries in order and ensure one next provider request without changing steering or follow-up scheduling.
+- Added retain-none compaction input: `sessionManager.appendCompaction(summary, null, tokensBefore)` stores the compaction's own ID as its kept boundary.
+- Added the `context_with_system` extension event, which runs after `context` handlers on the full transcript including system messages and sends its result verbatim. See [`context_with_system`](docs/extensions.md#context_with_system).
+- Added per-model image resize profiles through `inputLimits.images.resize` in `models.json`, applied to file attachments, image reads, and tool-result images ([#9631](https://github.com/earendil-works/pi/issues/9631)).
+
+### Fixed
+
+- Fixed string context-edit replacements producing invalid assistant and tool-result message content instead of text blocks.
+- Fixed context-invisible boundary metadata and replacement edits causing newly appended or replaced input to be summarized before its first provider request.
+- Fixed edited-context accounting both discarding valid assistant usage captured after the latest context edit and reusing that usage after a later compaction made it stale.
+- Fixed selected error retries and final length/overflow recovery retaining abandoned model attempts in future provider context; post-run recovery omissions are now persisted without hiding raw transcript history or changing queue scheduling.
+- Fixed `context` handlers that filter or slice messages dropping the prompt and tool declarations, which after extension-driven compaction left requests without built-in tools or made Codex emit raw tool-call text. Handlers no longer see system messages; Pi restores the prompt and tool state after they run. See [`context`](docs/extensions.md#context) ([#9789](https://github.com/earendil-works/pi/issues/9789), [#9822](https://github.com/earendil-works/pi/issues/9822)).
+- Preserved Apex Code's local ZIP-only `/bug` report flow while adopting upstream's offline guard; bug reports are not uploaded.
+- Fixed idle prompt-cache warming rebuilding expired caches when its timer or an extension decision is delayed.
+- Improved crash diagnostics with hints identifying loaded extensions that appear in the stack trace.
+- Fixed text files beginning with `GIF` being misclassified as images and omitted from `read` and CLI `@file` input ([#9755](https://github.com/earendil-works/pi/issues/9755)).
+- Fixed malformed prompt template frontmatter being silently ignored instead of reported as a resource warning ([#9830](https://github.com/earendil-works/pi/pull/9830) by [@christianklotz](https://github.com/christianklotz)).
+- Fixed inherited unknown OpenAI-compatible Chat Completions endpoints receiving strict tool schemas unless they explicitly advertise support ([#9816](https://github.com/earendil-works/pi/issues/9816)).
+
+## [0.86.1] - 2026-09-20
+
+### New Features
+
+- **Meta Muse provider** — Sign in with Meta using `/login meta` or use `META_API_KEY` to access Muse Spark models. See [Meta (Muse subscription)](docs/providers.md#meta-muse-subscription).
+
+### Added
+
+- Added Meta (Muse subscription) login via `/login meta` with automatic Model API key refresh, plus `META_API_KEY` support ([#9096](https://github.com/earendil-works/pi/pull/9096) by [@xl0](https://github.com/xl0)).
+
+### Changed
+
+- Enabled Node's persistent compile cache before loading the bundled CLI runtime, reducing repeat launch time.
+
+### Fixed
+
+- Fixed `/bug` descriptions dropping line breaks from pasted diagnostics.
+- Fixed `/bug` hints appearing for user cancellations and retryable provider failures such as service unavailability.
+- Fixed clipboard copy failing in containers and WSL without WSLg by restoring the OSC 52 fallback when no display is available, and added a verified Windows clipboard backend for WSL ([#9688](https://github.com/earendil-works/pi/issues/9688)).
+- Fixed inherited z.ai `Prompt too long` errors not being recognized as context overflow ([#9805](https://github.com/earendil-works/pi/issues/9805)).
+- Fixed inherited Cerebras models advertising unsupported strict tool schemas, which caused HTTP 400 errors when strict and non-strict tools were mixed ([#9804](https://github.com/earendil-works/pi/pull/9804) by [@EdenGottlieb](https://github.com/EdenGottlieb)).
+
+## [0.86.0] - 2026-09-19
+
+### 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](docs/settings.md#cache-warming).
+- **Bug reporting** — Report problems with `/bug` using redacted diagnostics, optional transcripts, or exported ZIP archives. See [Reporting Bugs](docs/sessions.md#reporting-bugs).
+- **Transcript-aware prompt and tool updates** — Preserve instruction and tool changes across resume and branch navigation while retaining cached prefixes. See [`before_agent_start`](docs/extensions.md#before_agent_start).
+- **Offline Radius model catalog** — Select Radius models immediately, with cached and live catalogs overlaid when available. See [Radius](docs/providers.md#radius).
+- **Per-model compaction budgets** — Configure reserved and recent-token budgets by model. See [Per-model overrides](docs/compaction.md#per-model-overrides).
+
+### Breaking Changes
+
+- Changed inherited pi-ai provider stream inputs from `Context` to normalized `TranscriptContext` values. Custom providers must read system prompts and tool declarations from `context.messages` with `getCurrentSystemPrompt()` and `getCurrentTools()`. See [Custom Streaming API](docs/custom-provider.md#custom-streaming-api).
+- Restricted inherited `ToolCall.arguments` and `ToolResultMessage.details` to JSON-compatible values, changed `ToolResultMessage` into a conditional type, and made `JsonValue` arrays readonly.
+- `user_bash` now fails closed: errors or invalid defined results abort the command without invoking later handlers or executing locally. Return `undefined` to continue propagation; otherwise return `{ operations }` or `{ result }` ([#9068](https://github.com/earendil-works/pi/issues/9068)).
+
+### Added
+
+- Added transcript-backed mid-conversation system prompt and tool changes so instruction and tool updates survive resume and branch navigation while preserving cached prefixes on supported models. See [`before_agent_start`](docs/extensions.md#before_agent_start) and [Entry Types](docs/session-format.md#entry-types) ([#9548](https://github.com/earendil-works/pi/pull/9548)).
+- Added inherited native deferred tool loading for Fireworks Messages models. Use `ToolSearch` or `tool_search` as the loader name for prompt-prefix deferral ([#9323](https://github.com/earendil-works/pi/issues/9323)).
+- Added click toggling for branch summaries, compaction summaries, and skill invocation entries.
+- Added the public Radius model catalog for immediate and offline model selection, with cached and live gateway catalogs overlaid when available.
+- Added `ctx.modelRegistry.stream()` and `streamSimple()` for extension model calls through configured providers with resolved authentication ([#8964](https://github.com/earendil-works/pi/issues/8964)).
+- Added per-model `reserveTokens` and `keepRecentTokens` settings through `compaction.modelOverrides`, with ordinary compaction settings as fallback ([#8133](https://github.com/earendil-works/pi-mono/issues/8133)).
+- Added `compat.allowedFallbackModels` configuration for overriding or disabling Anthropic server-side fallback models ([#9294](https://github.com/earendil-works/pi/issues/9294)).
+- Added an unsubscribe function from `pi.on()` so extensions can drop event handlers. Handlers added or removed during a dispatch apply to later dispatches, not the current one ([#8967](https://github.com/earendil-works/pi/issues/8967)).
+- Exported extension hook event and result types that were previously omitted from the package entry points ([#9642](https://github.com/earendil-works/pi/pull/9642)).
+- Added `/bug [description]` to report a bug to the Pi developers. The report bundles environment, model, provider, extension, and settings metadata (secrets redacted), assistant message diagnostics from the session, optionally the session transcript, or a model-written summary of what went wrong instead. It is uploaded to Radius (no login required; attributed when logged in) or exported as a zip archive, and the report id is recorded in the session as a `pi.bug-report` entry. Crashes are recorded in `~/.pi/agent/crashes.json`, announced once on the next start, and attached to the next report; unexplained errors and exhausted retries point at `/bug` once per session.
+- Added cost-aware prompt-cache warming during long tool runs and optionally while idle, with configurable modes, model cache-lifetime metadata, `/session` diagnostics, transcript notices, and the `cache_warming_decision` extension event. See [Cache Warming](docs/settings.md#cache-warming) ([#9668](https://github.com/earendil-works/pi/pull/9668)).
+
+### Changed
+
+- Enabled Node's persistent compile cache before loading the bundled CLI runtime, reducing repeat launch time.
+- Made `--resume` session results appear progressively, using file modification times to prioritize all-folder loading and cancelling outstanding transcript reads after selection.
+- Reduced `--continue` startup time by checking candidate session headers in modification-time order and stopping after the newest matching session.
+- Replaced the external native clipboard dependency with bundled asynchronous macOS, Windows, and X11 helpers while preserving platform command and OSC 52 fallbacks ([#9163](https://github.com/earendil-works/pi/pull/9163)).
+- Reduced inherited fuzzy search latency for long texts by using native substring search instead of scanning each character in JavaScript ([#9267](https://github.com/earendil-works/pi/issues/9267)).
+- Moved compaction, branch summarization, and retry spinners into the editor border alongside the working indicator. Custom editors use the same embedding opt-in for all status spinners.
+- Enabled strict-prefer JSON-schema sampling by default for built-in `read`, `bash`, `powershell`, `edit`, and `write` tools, without requiring `PI_EXPERIMENTAL`. Extensions can re-register tool definitions with `constrainedSampling: false`.
+- Formatted Bash and PowerShell tool durations of at least one minute as minutes and seconds, with hours when needed ([#9628](https://github.com/earendil-works/pi/issues/9628)).
+- Deferred the extension compiler and bundled virtual modules until a filesystem extension is loaded, reducing the baseline SDK import cost ([#9540](https://github.com/earendil-works/pi/issues/9540)).
+
+### Fixed
+
+- Fixed GitHub Copilot GPT models, including GPT-6 Astra, using the Chat Completions adapter instead of the required Responses adapter ([#9253](https://github.com/earendil-works/pi/pull/9253) by [@petrroll](https://github.com/petrroll)).
+- Fixed inherited DeepSeek V4.1 thinking levels on OpenRouter and OpenCode Go preserving provider effort metadata ([#9485](https://github.com/earendil-works/pi/issues/9485)).
+- Fixed inherited bodyless HTTP 400/413 errors from non-Cerebras providers being misclassified as context overflow ([#9482](https://github.com/earendil-works/pi/issues/9482)).
+- Fixed inherited Vercel AI Gateway replaying unsigned thinking as assistant text ([#9676](https://github.com/earendil-works/pi/issues/9676)).
+- Fixed inherited Google Generative AI and Vertex AI using unsupported thinking levels when reasoning is omitted or when model capabilities differ within a Gemini family ([#9455](https://github.com/earendil-works/pi/issues/9455)).
+- Fixed inherited Anthropic-compatible relays breaking signed thinking replay when they report a different response model, while preserving fallback pricing ([#9188](https://github.com/earendil-works/pi/issues/9188)).
+- Fixed inherited Amazon Bedrock one-hour cache writes being priced at the five-minute rate ([#9457](https://github.com/earendil-works/pi/issues/9457)).
+- Fixed inherited quadratic CPU usage when draining buffered `EventStream` events ([#9055](https://github.com/earendil-works/pi/issues/9055)).
+- Fixed inherited Mistral Medium reasoning requests to use `reasoning_effort` for all reasoning-capable `mistral-medium-*` model IDs instead of the unsupported `prompt_mode` ([#8700](https://github.com/earendil-works/pi/issues/8700)).
+- Fixed inherited OpenCode and OpenCode Go requests to send `x-opencode-session` from `sessionId` across all supported API adapters ([#9326](https://github.com/earendil-works/pi/issues/9326)).
+- Fixed inherited OpenAI Codex requests to send the model's Off reasoning effort instead of omitting it, while respecting unsupported Off mappings ([#9191](https://github.com/earendil-works/pi/issues/9191)).
+- Fixed inherited Fireworks unsigned thinking replay and reasoning effort selection using catalog metadata, with verified DeepSeek V4 and Qwen3.8 fallbacks and removal of redundant GLM 5.2 and Kimi K3 effort aliases ([#9323](https://github.com/earendil-works/pi/issues/9323)).
+- Fixed inherited OpenRouter requests to send `x-session-id` from `sessionId` for Chat Completions and Anthropic Messages models when prompt caching is enabled ([#9102](https://github.com/earendil-works/pi/issues/9102)).
+- Fixed the inherited DeepSeek catalog to advertise `deepseek-flash` for DeepSeek V4.1 Flash instead of retired Flash aliases, and refreshed DeepSeek pricing metadata ([#9423](https://github.com/earendil-works/pi/issues/9423)).
+- Fixed inherited Mistral-hosted GLM-5.2 reasoning requests to use `reasoning_effort` instead of the ignored `prompt_mode` ([#9375](https://github.com/earendil-works/pi/issues/9375)).
+- Fixed inherited OpenAI-compatible Responses errors to identify the actual provider instead of always labeling them as OpenAI errors ([#9298](https://github.com/earendil-works/pi/issues/9298)).
+- Fixed inherited Baseten requests to send session-affinity headers from `sessionId` for automatic prompt-cache routing ([#9629](https://github.com/earendil-works/pi/issues/9629)).
+- Fixed inherited retry classification for Cloudflare 520 responses ([#9627](https://github.com/earendil-works/pi/issues/9627)).
+- Fixed inherited retry classification for transient Azure peak-load capacity errors ([#9669](https://github.com/earendil-works/pi/issues/9669)).
+- Fixed session tree navigation racing with active compaction and replacing its progress UI ([#9179](https://github.com/earendil-works/pi/pull/9179) by [@acmerfight](https://github.com/acmerfight)).
+- Fixed exact session ID lookup scanning complete transcript bodies instead of reading session headers ([#9601](https://github.com/earendil-works/pi/pull/9601) by [@metaist](https://github.com/metaist)).
+- Fixed repeated Anthropic thinking-drop notices being shown for the same dropped blocks, and shortened notices while retaining details in the session ([#9391](https://github.com/earendil-works/pi/issues/9391)).
+- Fixed mid-run threshold compaction silently skipping oversized trailing tool results ([#9740](https://github.com/earendil-works/pi/issues/9740)).
+- Fixed signal-terminated local shell commands being reported as successful with partial output ([#9577](https://github.com/earendil-works/pi/issues/9577) by [@BrendanJMurphy](https://github.com/BrendanJMurphy)).
+- Fixed local clipboard failures reporting success when the terminal ignored the fallback OSC 52 write, and added platform-specific setup guidance when no clipboard backend works ([#9618](https://github.com/earendil-works/pi/issues/9618)).
+- Capped agent-level retry backoff at `retry.maxAgentDelayMs` (60s by default) so long retry runs stay responsive during prolonged transient outages ([#8826](https://github.com/earendil-works/pi/issues/8826)).
+- Fixed direct RPC `steer` and `follow_up` commands bypassing extension `input` handlers ([#8718](https://github.com/earendil-works/pi/issues/8718)).
+- Fixed premature missing-model errors after login by waiting for catalog discovery. Radius now defaults to `balanced`, falling back to the first available Radius model when needed.
+- Fixed fullscreen mode reserving a blank row for custom footers that render zero rows ([#8919](https://github.com/earendil-works/pi/issues/8919)).
+- Fixed extension tools without parameter schemas to be rejected during registration instead of breaking provider requests ([#9300](https://github.com/earendil-works/pi/issues/9300)).
+- Fixed `before_agent_start` handlers returning `systemPrompt` (and `forceSystemPrompt`) on models with mid-conversation system messages: the forced prompt is now sent as the provider's leading system prompt instead of being appended as a section patch after the original prompt.
+- Fixed loaded llama.cpp models with `enable_thinking` chat templates ignoring Pi's thinking level ([#9528](https://github.com/earendil-works/pi/issues/9528)).
+- Fixed cancellation races that could start automatic compaction, leave stale retry state, or miss cancellation while waiting for summarization authentication ([#9340](https://github.com/earendil-works/pi/issues/9340), [#9777](https://github.com/earendil-works/pi/issues/9777)).
+- Fixed asynchronous Kitty image conversion replacing newer partial tool output images ([#8743](https://github.com/earendil-works/pi/pull/8743) by [@wutongyuonce](https://github.com/wutongyuonce)).
+- Fixed inherited skill slash-command autocomplete ranking the `skill:` prefix instead of the bare skill name ([#9120](https://github.com/earendil-works/pi/pull/9120) by [@yearth](https://github.com/yearth)).
+- Fixed inherited file autocomplete boundaries and path quoting around CJK punctuation ([#9746](https://github.com/earendil-works/pi/pull/9746) by [@haoqixu](https://github.com/haoqixu)).
+- Fixed inherited LaTeX legacy font switches falling back to raw source, centered `cases` layouts around surrounding equations, and vertically laid out unsupported and nested display scripts ([#8827](https://github.com/earendil-works/pi/issues/8827), [#9564](https://github.com/earendil-works/pi/issues/9564), [#7929](https://github.com/earendil-works/pi/issues/7929)).
+- Fixed inherited fullscreen Kitty images being erased by later row clears in WezTerm ([#9169](https://github.com/earendil-works/pi/issues/9169)).
+
+### Removed
+
+- Removed unavailable inherited GPT-5.4 and GPT-5.4 mini models from OpenAI Codex selection ([#9394](https://github.com/earendil-works/pi/issues/9394)).
+
+## [0.85.1] - 2026-09-05
+
+### New Features
+
+- **GPT-6 Astra** — Available through OpenAI API keys and OpenAI Codex subscriptions. See [API Keys](docs/providers.md#api-keys) and [OpenAI Codex](docs/providers.md#openai-codex).
+
+### Added
+
+- Added GPT-6 Astra for OpenAI API keys and OpenAI Codex subscriptions.
+- Added five-times-faster mouse wheel scrolling while holding Alt in fullscreen mode ([#9166](https://github.com/earendil-works/pi/pull/9166) by [@xl0](https://github.com/xl0)).
+
+### Fixed
+
+- Fixed configurable save keybindings in the model and thinking selectors ([#9149](https://github.com/earendil-works/pi/pull/9149) by [@rwachtler](https://github.com/rwachtler)).
+- Fixed SDK import failures caused by unintentionally publishing internal experimental code and dependencies in 0.85.0. The experimental `client` and `experimental/plugin` subpaths and server/client commands are now source-only through `pi-test.sh`; the supported local SDK and stdio RPC API are unchanged ([#9132](https://github.com/earendil-works/pi/issues/9132)).
+- Fixed mouse hover changing selection and recentering autocomplete and settings lists, causing clicks to target a different item.
+- Fixed long prompt-cache requests for GPT-5.6+ Responses models to use `prompt_cache_options.ttl: "30m"` instead of `prompt_cache_retention: "24h"`.
+
+## [0.85.0] - 2026-09-04
+
+### New Features
+
+- **Persistent Claude thinking effort** — Supported Anthropic transports preserve per-turn effort and recover safely from signed-thinking mismatches. See [Model Configuration](docs/models.md#model-configuration).
+- **Fullscreen transcript controls** — Jump to the latest message from a scrolled transcript and use the embedded working indicator. See [TUI Fullscreen Viewport](docs/keybindings.md#tui-fullscreen-viewport).
+- **Restorable in-memory sessions** — Resume externally stored session entries through the SDK. See [Session Management](docs/sdk.md#session-management).
+
+### Added
+
+- Added `SessionManager.inMemory()` support for restoring externally managed session entries ([#8980](https://github.com/earendil-works/pi/pull/8980) by [@y-nk](https://github.com/y-nk)).
+- Added inherited OpenAI-compatible `vllmPriority` and `supportsMaxOutputTokens` model settings for vLLM scheduler priority and OpenAI Responses output-token limits ([#9004](https://github.com/earendil-works/pi/pull/9004) by [@AppleDannyClegg](https://github.com/AppleDannyClegg), [#8941](https://github.com/earendil-works/pi/pull/8941) by [@scturtle](https://github.com/scturtle)).
+- Added inherited LaTeX rendering for relational algebra join symbols ([#9050](https://github.com/earendil-works/pi/pull/9050) by [@haoqixu](https://github.com/haoqixu)).
+- Added a clickable "Jump to latest message" label with the `tui.altScreen.bottom` shortcut to the fullscreen transcript while it is scrolled up ([#9080](https://github.com/earendil-works/pi/pull/9080) by [@rwachtler](https://github.com/rwachtler)).
+- Added Meta (Muse subscription) login via `/login meta` with automatic Model API key refresh, plus `META_API_KEY` support.
+
+### Changed
+
+- Moved the streaming working indicator into the default editor border and matched its default spinner and label to the thinking-level border color. Custom editors retain the standalone indicator unless they opt in to embedding it ([#8799](https://github.com/earendil-works/pi/pull/8799) by [@cristinaponcela](https://github.com/cristinaponcela)).
+- Reduced inherited fullscreen transcript search latency on large transcripts by caching unchanged search results, indexing ASCII runs, and limiting highlight work to visible matches ([#8800](https://github.com/earendil-works/pi/pull/8800) by [@cristinaponcela](https://github.com/cristinaponcela)).
+
+### Fixed
+
+- Fixed managed `fd` and ripgrep downloads on Linux musl systems ([#9070](https://github.com/earendil-works/pi/pull/9070) by [@Charlie0113-T](https://github.com/Charlie0113-T)).
+- Removed the unavailable inherited Grok Build 0.1 model from `/model` ([#9093](https://github.com/earendil-works/pi/pull/9093) by [@Jaaneek](https://github.com/Jaaneek)).
+- Fixed inherited provider streams emitting incompatible event sequences and custom tool-call deltas.
+- Restored the `@earendil-works/pi-coding-agent/client` compatibility entry point.
+- Fixed the inherited Qwen Token Plan Individual catalog to include Qwen3.8 Flash ([#9021](https://github.com/earendil-works/pi/issues/9021)).
+- Fixed inherited OpenAI Codex SSE parsing to process terminal events that are not followed by a blank line ([#9047](https://github.com/earendil-works/pi/issues/9047)).
+- Fixed inherited GitHub Copilot Claude Fable 5 requests so selected reasoning levels are sent ([#8961](https://github.com/earendil-works/pi/issues/8961)).
+- Fixed inherited Baseten GLM-5.2 models incorrectly advertising image input support ([#8293](https://github.com/earendil-works/pi/pull/8293) by [@Panoplos](https://github.com/Panoplos)).
+- Fixed skills being unavailable when Bash is the only enabled tool ([#8552](https://github.com/earendil-works/pi/pull/8552) by [@xl0](https://github.com/xl0)).
+- Fixed concurrent session shares overwriting one another ([#8613](https://github.com/earendil-works/pi/pull/8613) by [@wutongyuonce](https://github.com/wutongyuonce)).
+- Fixed image orientation detection skipping EXIF data after non-EXIF APP1 segments ([#8616](https://github.com/earendil-works/pi/pull/8616) by [@wutongyuonce](https://github.com/wutongyuonce)).
+- Fixed imported sessions overwriting an existing session with the same filename ([#8985](https://github.com/earendil-works/pi/pull/8985) by [@wutongyuonce](https://github.com/wutongyuonce)).
+- Fixed session forks losing their compaction boundary ([#8990](https://github.com/earendil-works/pi/pull/8990) by [@acmerfight](https://github.com/acmerfight)).
+- Fixed in-memory session forks before an active turn settled ([#8937](https://github.com/earendil-works/pi/pull/8937) by [@acmerfight](https://github.com/acmerfight)).
+- Fixed inherited Fireworks GLM models using the wrong API adapter.
+- Fixed inherited `NO_PROXY` matching for root domains and subdomains ([#8737](https://github.com/earendil-works/pi/pull/8737) by [@MeiSiristhebest](https://github.com/MeiSiristhebest)).
+- Fixed `bash`, `edit`, `find`, `grep`, `ls`, `read`, and `write` tools ignoring `ctx.cwd` ([#8627](https://github.com/earendil-works/pi/pull/8627) by [@vmizg](https://github.com/vmizg)).
+- Fixed inherited terminal startup under restricted seccomp policies that reject the `SIGWINCH` self-signal ([#8898](https://github.com/earendil-works/pi/pull/8898) by [@bartlomiejkida](https://github.com/bartlomiejkida)).
+- Fixed inherited Zed terminal image capability detection ([#8828](https://github.com/earendil-works/pi/pull/8828) by [@Perlence](https://github.com/Perlence)).
+- Fixed drag selection continuing over the fullscreen editor.
+- Fixed managed `fd` and ripgrep downloads requiring the GitHub Releases API ([#8708](https://github.com/earendil-works/pi/pull/8708) by [@Terminator666666](https://github.com/Terminator666666)).
+- Fixed branch summaries failing when reasoning consumes the previous 2048-token output cap ([#8845](https://github.com/earendil-works/pi/issues/8845)).
+- Fixed the write tool reporting UTF-16 code-unit counts as byte counts by removing the misleading count ([#8979](https://github.com/earendil-works/pi/issues/8979)).
+- Fixed proxied plain-HTTP provider requests hanging after a tool call by tunneling them with CONNECT ([#8134](https://github.com/earendil-works/pi/issues/8134)).
+- Fixed RPC `abort` reporting success without cancelling an in-progress manual compaction ([#8920](https://github.com/earendil-works/pi/issues/8920)).
+
 ## [0.84.4] - 2026-08-28
 
 ### New Features
@@ -480,6 +750,8 @@ The entries below are retained as historical attribution for the forked code.
 
 ### Added
 
+- Added `supportsMidConvoEffort` to custom Anthropic Messages model compatibility settings.
+- Added transcript notices for Anthropic thinking blocks dropped during provider recovery when cache miss notices are enabled.
 - Added `ui_prompt_start` and `ui_prompt_end` extension events so host integrations can distinguish active agent work from waiting on user-facing `ctx.ui` prompts ([#8355](https://github.com/earendil-works/pi/pull/8355) by [@cristinaponcela](https://github.com/cristinaponcela)).
 - Added `detectSupportedImageMimeTypeFromFile()` to the public library exports ([#8600](https://github.com/earendil-works/pi/pull/8600) by [@xl0](https://github.com/xl0)).
 - Added inherited experimental vision-capable `deepseek-v4-flash-vision-exp` model support.
@@ -488,6 +760,11 @@ The entries below are retained as historical attribution for the forked code.
 - Added environment variables and advanced settings for overriding auto-detected terminal hyperlink, image, and truecolor capabilities ([#8665](https://github.com/earendil-works/pi/issues/8665)).
 - Added `fullscreenCopyOnSelect` to disable automatic fullscreen selection copy; when disabled, `Ctrl+X` copies the active text selection before falling back to the last assistant message, while `/tree` still copies the selected message ([#7720](https://github.com/earendil-works/pi/issues/7720)).
 
+### Changed
+- Changed fullscreen scrollbars to reveal on pointer entry, support optional `scrollbarTrack` and `scrollbarThumb` theme colors with muted and text fallbacks, keep one thumb color across normal and expanded states, and support track-click jumping.
+- Changed fullscreen transcript search arrows to underline on hover and capitalized the search placeholder.
+- Changed selectors in `/thinking`, `/model`, `/scoped-models`, `/trust`, per-model thinking settings, and theme settings to keep active options marked while browsing. `/scoped-models` now uses consistent per-item toggles and strikes through unavailable models ([#8900](https://github.com/earendil-works/pi/pull/8900)).
+
 ### Fixed
 
 - Fixed toggling thinking visibility clearing partial output from running Bash tools ([#8611](https://github.com/earendil-works/pi/issues/8611)).
@@ -525,11 +802,7 @@ The entries below are retained as historical attribution for the forked code.
 - Added an optional `powershell` tool for Windows, configurable through `defaultTools` and the SDK. See [PowerShell Tool](docs/windows.md#powershell-tool).
 - Added a `/thinking` selector and searchable default choices to the model and thinking selectors; Ctrl+S saves the selected model as the global default. See [Models and Thinking](docs/keybindings.md#models-and-thinking).
 - Added optional routing session IDs to exported compaction summary helpers so callers can preserve provider routing without enabling prompt cache writes.
-- Added 
-
-
-
-usage notices for compaction and branch summaries when cache miss notices are enabled.
+- Added transcript usage notices for compaction and branch summaries when cache miss notices are enabled.
 - Added `session_compact_failed` extension events so compaction failures and aborts expose their reason, retry state, source, and error message to handlers ([#8175](https://github.com/earendil-works/pi/issues/8175)).
 - Added inherited provider-neutral `toolChoice` support to simple stream requests.
 - Added inherited automatic Anthropic server-side refusal fallback for supported first-party models, including returned-model usage pricing ([#8017](https://github.com/earendil-works/pi/issues/8017)).
@@ -603,6 +876,7 @@ usage notices for compaction and branch summaries when cache miss notices are en
 
 ### Added
 
+- Added per-block fullscreen mouse expansion for thinking sections and tool results, while preserving drag selection and link activation.
 - Added fullscreen transcript search with `Ctrl+Shift+F`, incremental match highlighting, configurable search match theme colors, and next/previous navigation with `Enter`/`Ctrl+G` and `Shift+Enter`/`Ctrl+Shift+G`.
 - Added experimental strict JSON-schema constrained sampling for the default `read`, `bash`, `edit`, and `write` tools under `PI_EXPERIMENTAL=1`.
 - Added a fullscreen exit output setting to choose between printing the final transcript and only a session resume hint.