@oh-my-pi/pi-tui 15.12.3 → 15.13.0

package/CHANGELOG.md

@@ -2,32 +2,24 @@
 
 ## [Unreleased]
 
-## [15.11.8] - 2026-06-12
-
-### Changed
-
-- Markdown rendering during streaming re-lexes only the grown tail instead of the whole buffer on every reveal tick. marked has no resumable lexer, but block tokenization is local across a blank-line boundary with balanced fences, so the largest blank-line-bounded prefix's block tokens are frozen and reused (`lex(prefix) ++ lex(tail)`), with a full-lex fallback for non-append edits, reference-link definitions, and CRLF input. The output is byte-identical to a full lex (covered by a contract test), turning the O(N²) cost of revealing a long single-block message into O(N): a 6,000-grapheme reveal dropped from ~575 ms to ~89 ms of CPU in benchmarks.
+### Breaking Changes
 
-## [15.11.5] - 2026-06-12
+- Removed Kitty temp-file image transmission, its startup support probe, the `PI_KITTY_IMAGE_TRANSMISSION` override, and the temp-file helper exports. Kitty/Ghostty image payloads now stay on in-band base64 before placeholder/direct placement, avoiding blank first renders from temp-file load races.
+- Renamed `RenderRequestOptions.allowUnknownViewportMutation` → `allowUnknownViewportTransientRepaint`. The option only permits a transient live-viewport repaint (autocomplete/IME/focused-editor chrome) on hosts that cannot report viewport position; it never authorizes a settled transcript commit. The old name implied any offscreen mutation was safe to push into native scrollback, which led callers to emit duplicate transcript copies.
 
 ### Added
 
+- Added volatile speech-to-text preview support to `Editor` with `setVolatileText(text)`, `clearVolatileText()`, and `commitVolatileText(text)` so hosts can replace, discard, or commit live dictated text at the cursor without appending
+- Added an always-on `LoopWatchdog` armed in `TUI.start()`/`TUI.stop()` that logs `ui.loop-blocked` (rising-edge deduped, with `blockedMs` and the phase active during the elapsed interval) when a self-scheduled probe tick runs late, plus a `ui.select-filter` breadcrumb around the `SelectList` fuzzy filter. The phase is read via `takeRecentLoopPhase`, so a synchronous block whose breadcrumb was pushed and popped before the delayed tick runs is still attributed to its phase instead of "unknown". `stop()` cancels the armed timer (via `clearTimeout` on the default handle) so repeated start/stop cycles leave no pending probe, with the generation guard as a fallback ([#2485](https://github.com/can1357/oh-my-pi/issues/2485))
+- Added `ctrl+j` as a second default binding for the `tui.input.newLine` action alongside `shift+enter`, so terminals that cannot emit `shift+enter` still have a newline key. On terminals with Kitty-protocol / `modifyOtherKeys` disambiguation `ctrl+j` inserts a newline while `Enter` still submits; on legacy terminals where `ctrl+j` and `Enter` are both byte-identical `LF` it submits (documented limitation). User keybinding overrides still take precedence ([#2473](https://github.com/can1357/oh-my-pi/issues/2473))
+- Added an `Editor.onLargePaste(text, lineCount)` hook, fired for a "marker-sized" paste (the point where the editor would otherwise collapse it into a `[Paste #N]` token). Returning `true` lets the host intercept the paste — e.g. to offer wrap-in-code-block / wrap-in-XML / attach-as-file choices — and suppresses the default marker (no undo state is recorded). Added `Editor.insertPaste(content)` so the host can re-insert a (possibly transformed) collapsed paste marker without re-triggering the hook.
+- Added `Editor.deleteBeforeCursor(count)`, which removes up to `count` characters immediately before the cursor on the current line (capped at the cursor column, single line, records one undo state). Hosts use it to "track back" optimistically-inserted characters — e.g. the coding-agent hold-`Space` push-to-talk gesture deleting the space-bar auto-repeat burst.
+- Added an optional `getNativeScrollbackSnapshotSafeEnd()` to the `NativeScrollbackLiveRegion` contract: a *durable* commit boundary (D ≥ the byte-stable `commitSafeEnd`) for live rows whose current snapshot is permanent content but may still drift bytes later (a streaming markdown table re-aligning its columns). The engine commits these rows when they scroll above the window — never dropping them — but **audit-exempt** (tracked via a new byte-stable `auditRows` prefix), so a later layout change of an already-committed row freezes a stale row in history (duplication never loss) instead of re-anchoring the committed-prefix audit and spraying duplicate snapshots. Components that omit it are unchanged: `durableBoundary === byteStableBoundary` and `auditRows === committedRows`, so the ledger math is byte-identical.
+- Added `ViewportTailProvider` to let child components provide their visible tail rows during fast-path non-multiplexer resize rendering
+- Added `TUI.resizeViewportPaints` and `TUI.resizeViewportActive` getters to expose deferred resize viewport repaint diagnostics
+- `PI_FORCE_HYPERLINKS=1` / `PI_NO_HYPERLINKS=1` env overrides for the OSC 8 hyperlink capability, mirroring the `PI_FORCE_SYNC_OUTPUT`/`PI_NO_SYNC_OUTPUT` shape (opt-out beats force-on).
 - Added `fuzzyRank` to return sorted matches together with a fuzzy score
 - Added a configurable `Input.prompt` field (defaults to `"> "`; set to `""` for chrome-less embedding inside custom banners)
-
-### Changed
-
-- Changed fuzzy matching to normalize queries and text into words, including camelCase and punctuation separators, before scoring
-- Changed `Input.setValue` to place the cursor at the end of the new value instead of clamping it to its previous position, so typing after seeding a prefilled value appends rather than prepends
-
-### Fixed
-
-- Fixed multi-word searches so `fuzzyMatch` no longer matches when query letters are only scattered across unrelated words
-
-## [15.11.4] - 2026-06-12
-
-### Added
-
 - Added `partialHoldTimeout` to `StdinBufferOptions` to control the maximum extra delay held for unambiguous incomplete escape sequences before they are flushed
 - Added `SettingsList.sidebarWidth` option for a fixed split-layout sidebar width
 - Added mouse pointer support APIs to `SettingsList` with `setHoverItem`, `hitTest`, `hoverTest`, and `routeSubmenuMouse` for row targeting and submenu routing
@@ -39,68 +31,59 @@
 - Added a host-integration surface to `SettingsList`: a `SettingsListOptions` constructor arg (`layout` to force the flat layout, `typeToSearch: false` to hand the query to a parent, `emptyText`, `hint`), `selectItem(id)`, `getSelectedItem()`, `onSelectionChange`, `hasOpenSubmenu()`, and the exported `getSettingItemFilterText` helper.
 - Added keyboard section focus to `SettingsList`: `toggleSectionFocus()` / `sectionFocused` / `hasSectionFocusTargets()` flip Up/Down between row navigation and whole-section jumps — the cursor glyph parks on the active sidebar entry (or the active heading row in the flat layout) while the row cursor hides, Enter/Esc drop focus back to the rows, and any explicit row selection (`selectItem`, wheel, filtering) exits it.
 - Added muted tabs to `TabBar` (`Tab.muted` + `TabBarTheme.mutedTab`, skipped by keyboard navigation), `setTabs(tabs, activeId?)`/`setActiveById(id)` for re-rendering the strip without firing `onTabChange`, an optional empty label (drops the `Label:` prefix), and a `showHint` switch for the trailing "(tab to cycle)" hint.
+- Added `TUI.requestComponentRender(component)` to schedule component-scoped renders for self-contained updates
+- Added support for asynchronous `onSubmit` handlers by allowing the callback to return a `Promise<void>`
+- `SettingsList` now supports type-to-search filtering with Escape clearing an active query before canceling.
+- Added a `wrapDescription` option to `SelectListLayoutOptions`. When enabled, long descriptions wrap onto continuation rows indented under the description column instead of being silently truncated. The slash-command/skill autocomplete picker now opts in so descriptions like the bundled skills' remain fully readable at normal terminal widths. `maxVisible` becomes the picker's visual row budget so the popup height stays bounded even when items wrap (a single 5-row description with `maxVisible=3` clips with the scrollbar carrying the offscreen tail). Navigation stays item-to-item, the narrow-width fallback (`width <= 40`) is unchanged, and the `ScrollView` scrollbar tracks visual rows so the thumb stays correct when items wrap unevenly. ([#2169](https://github.com/can1357/oh-my-pi/issues/2169))
+- Added `TUI.getFocused()` accessor and `Input.pasteText(text)` method so callers consuming non-bracketed paste transports (e.g. kitty's OSC 5522 enhanced clipboard) can route a paste payload to the currently focused modal Input rather than always to the primary editor. Mirrors the existing `Editor.pasteText` semantics: newlines stripped, tabs normalized, NFC normalization applied. ([#2127](https://github.com/can1357/oh-my-pi/issues/2127))
+- Added `atomicTokenPattern` to `Editor`: when set to a global regex matching placeholder tokens such as `[Image #1, 800x600]` or `[Paste #2, +30 lines]`, a single backspace or forward-delete landing anywhere on a token removes the whole token instead of corrupting it into stray text.
+- Added exported `canonicalKeyId` and `addKeyAliases` keybinding helpers so consumers can share the same canonical shortcut matching semantics as `KeybindingsManager`.
+- Added `super` modifier support to native key parsing/matching and bound `super+alt+backspace` / `super+alt+delete` (and `super+alt+d`) into the word-delete defaults so Ghostty's default macOS Option+Backspace wire (`ESC [127;11u` — kitty modifier 11 = super|alt) deletes a word instead of falling through to single-char delete ([#2064](https://github.com/can1357/oh-my-pi/issues/2064)).
+- Added `TUI.addStartListener()` so feature hooks can re-enable terminal modes after temporary stop/start cycles such as external-editor handoffs.
+- Added `Editor.pasteText()` to apply terminal-style paste handling for text inserted from non-bracketed paste transports
+- Added an optional `dispose()` lifecycle method to `Component` so components can release timers and subscriptions during permanent teardown
+- Added `Container.dispose()` to propagate teardown to child components when a component tree is permanently discarded
+- Added `Loader.dispose()` to stop the loader animation timer when the component is disposed
+- Added a `ScrollView` `ellipsis` option (defaults to `Ellipsis.Unicode`) so callers that pre-wrap content to width can pass `Ellipsis.Omit` and suppress the stray per-line `…` that lands on trailing padding.
+- Added `ScrollView.handleScrollKey()` plus a `fastScrollLines` option so every scroll view gets shared navigation keys, including Shift+Arrow to scroll faster.
+- Added `OverlayOptions.fullscreen`: while the topmost visible overlay sets it, the engine borrows the terminal's alternate screen buffer for the overlay's lifetime and paints only the modal there — no ED3, no transcript re-commit — so the transcript stays untouched on the normal screen and is not scrollable behind the modal. Mouse tracking (`?1000h`/`?1006h`) is enabled for the modal's lifetime and disabled on exit, so the rest of the app keeps the terminal's native text selection.
+- Added the `submitPinsViewportToTail` terminal capability and `detectSubmitPinsViewportToTail()`: genuine local terminals where a submit keystroke scrolls the host to its tail reconcile deferred native scrollback at the prompt-submit checkpoint even when the viewport position is unprobeable (Ghostty/kitty/iTerm/WezTerm/Alacritty). Restores the pre-regression submit reconciliation without re-enabling it for Windows Terminal/ConPTY, SSH, or multiplexers, where a submit is not proof the host is at the tail.
+- Added `TUI.resetDisplay()` to force an immediate full-frame replay, including native scrollback when the host can safely clear it.
+- Added `setPaddingY` to `Box` so vertical padding can be updated programmatically after creation.
+- Added `setPaddingX` to `Box` so horizontal padding can be updated programmatically after creation
+- Added `ScrollView`, a fixed-height viewport component for pre-rendered lines with optional right-edge scrollbars and imperative scroll/page controls.
+- Added optional `Terminal.hasEagerEraseScrollbackRisk()` so custom/test terminal implementations can override the global ED3-risk profile without mutating the shared `TERMINAL` object.
+- Added `PI_TUI_SYNC_OUTPUT=0` and `PI_TUI_SYNC_OUTPUT=1` to explicitly disable or force-enable DEC 2026 synchronized-output mode, alongside `PI_FORCE_SYNC_OUTPUT=1` as a force-on alias
+- Added `PI_TUI_ED3_SAFE=1` environment override to treat a terminal as non-ED3-risk for eager native scrollback rebuilds on unknown POSIX hosts
+- Added Kitty `CSI 22 J` screen-to-scrollback clears for non-destructive full paints, while keeping ED3 for destructive history/session rebuilds.
+- Added Kitty OSC 99 rich notification formatting and startup capability probing.
+- Added Kitty OSC 66 text-sized Markdown H1 headings (2x scale) plus native text-width support for OSC 66 spans. Off by default and gated to Kitty (the only terminal implementing OSC 66) via the `TERMINAL.textSizing` capability; hosts enable it through `setTextSizing`.
+- Added Kitty Unicode placeholder image rendering (`U=1` + U+10EEEE with explicit row/column diacritics): inline images are drawn as real text cells that carry the image id in their foreground color, so they survive horizontal slicing, reflow, and overlapping draws instead of relying on cursor-positioned `a=p` placements. Enabled by default on Kitty-family terminals; opt out with `PI_NO_KITTY_PLACEHOLDERS=1`, and falls back to direct placement when a grid exceeds the diacritic table's addressable range.
+- Added Kitty temp-file image transmission (`t=t`): on local sessions, decoded PNG bytes are written to a `tty-graphics-protocol` temp file and the path is sent instead of in-band base64, gated behind a startup `a=q,t=t` support probe. Controlled by `PI_KITTY_IMAGE_TRANSMISSION=direct|temp-file|auto`; disabled over SSH unless explicitly forced.
+- Added DECRQM capability detection for DEC private modes 2026 (synchronized output) and 2048 (in-band resize). Synchronized-output paint wrappers are dropped when the terminal reports 2026 unsupported (preserving the `PI_NO_SYNC_OUTPUT` override), and DEC 2048 in-band resize is enabled when supported — reported geometry and cell pixel size are updated from `CSI 48 ; rows ; cols ; yPx ; xPx t` reports, with SIGWINCH and `CSI 16 t` kept as fallbacks.
+- Added an injectable render scheduler for TUI tests, allowing deterministic render drains without patching global clocks or event-loop timing.
+- Added `ImageBudget`, an inline-image cap that keeps only the most recent N images as live terminal graphics and demotes older ones to their text fallback. Once a new image pushes the count past the cap, the renderer hides the oldest via a full redraw plus an explicit Kitty graphics purge (`a=d,d=I`) — text-clear escapes (`CSI 2 J`/`CSI 3 J`) do not remove Kitty images. Configure the cap via `TUI#setMaxInlineImages` (`0` disables it).
+- Changed Kitty inline images to a transmit-once + placement scheme: the base64 data is sent a single time (`a=t`) keyed by a stable image id, then every repaint emits only the tiny placement (`a=p,i=…,p=…`). Repaints — including full redraws — no longer re-send image data or stack duplicate placements, and the diff/line buffers and render caches hold short placement strings instead of multi-KB base64. The `ImageBudget` doubles as the transmit store (it tracks which ids are loaded and re-transmits after a purge frees the data). iTerm2/Sixel, which have no addressable image store, keep sending inline data as before.
+- Added a renderer-level DECCARA rectangular-SGR optimizer that paints solid background panels/rows (Box/Text/Markdown fills, status bars, any full-width `theme.bg` row) as a single coalesced rectangle escape (`CSI 2*x` / `CSI Pt;Pl;Pb;Pr;<sgr>$r` / `CSI *x`) instead of emitting a full-width run of background-styled spaces on every visible row. It operates at emit time on the final ANSI strings — components are unchanged — and strips only trailing padding it can prove sits under a single non-default background span, coalescing vertically adjacent identical fills into one rectangle and falling back to the original bytes whenever the rectangle would not save bytes. Enabled only on Kitty, which implements the SGR-background extension (`docs/deccara.rst`); **Ghostty is intentionally excluded** because its `CSI $r` is unimplemented (ghostty-org/ghostty#632) and would drop the background entirely. Scrollback-bound rows and the append/scroll paths always keep the padded representation so native history preserves colored cells, and the `PI_NO_DECCARA` kill switch (plus tmux/screen/zellij detection) forces the fallback.
+- Added `CMUX_SURFACE_ID` environment variable support to `getTerminalId()`, so cmux terminal surfaces get a stable identifier alongside kitty, tmux, macOS Terminal.app, and Windows Terminal — enabling per-surface session breadcrumbs for `omp -c` in cmux.
+- Added `PI_NO_SYNC_OUTPUT=1` to disable DEC 2026 synchronized-output wrappers for terminals whose implementation is buggy or visually worse, while keeping the renderer's autowrap guards active during paints ([#1765](https://github.com/can1357/oh-my-pi/issues/1765)).
+- Added `overflowSearch` to `SelectListLayoutOptions` to let consumers enable or disable type-to-filter search and search-status rendering per SelectList instance
+- Added fuzzy type-to-filter search to overflowing `SelectList` pickers, with search status and result counts.
+- Added `TUI.setEagerNativeScrollbackRebuild(enabled)` — while enabled, live render frames rebuild native scrollback on offscreen/structural changes even when the viewport position is unobservable (POSIX), instead of deferring to a non-destructive repaint. Trades the anti-yank guarantee for clean, duplicate-free history; intended for windows where output above the fold is actively re-laying out (e.g. a tool whose result is still streaming). A terminal that reports a known-scrolled viewport still defers.
+- Added autocomplete triggering for internal URL scheme tokens such as `local://` and `skill://` while typing in the editor
 
 ### Changed
 
+- Changed non-multiplexer terminal resize handling so each SIGWINCH paints only the visible viewport and defers the full rewrap and native scrollback replay until the resize settles
+- Auto-enable OSC 8 hyperlinks inside tmux when tmux self-reports >= 3.4 via `TERM_PROGRAM_VERSION`; tmux 3.4 stores OSC 8 as a cell attribute and forwards it to outer terminals whose `terminal-features` include `hyperlinks`. Older tmux, GNU screen, and tmux without a reported version still default off. Resolution is factored into `hyperlinksUserOverride()` and `shouldEnableHyperlinksByDefault()` mirroring the sync-output helpers ([#2403](https://github.com/can1357/oh-my-pi/issues/2403)).
+- Markdown rendering during streaming re-lexes only the grown tail instead of the whole buffer on every reveal tick. marked has no resumable lexer, but block tokenization is local across a blank-line boundary with balanced fences, so the largest blank-line-bounded prefix's block tokens are frozen and reused (`lex(prefix) ++ lex(tail)`), with a full-lex fallback for non-append edits, reference-link definitions, and CRLF input. The output is byte-identical to a full lex (covered by a contract test), turning the O(N²) cost of revealing a long single-block message into O(N): a 6,000-grapheme reveal dropped from ~575 ms to ~89 ms of CPU in benchmarks.
+- Changed fuzzy matching to normalize queries and text into words, including camelCase and punctuation separators, before scoring
+- Changed `Input.setValue` to place the cursor at the end of the new value instead of clamping it to its previous position, so typing after seeding a prefilled value appends rather than prepends
 - Changed `SettingsList` section-focused keyboard handling so `Up`/`Down` now jump between sections and `Enter`/`Escape` exit section focus before confirming or cancelling a setting
 - Changed `SettingsList` split layout at wide widths to render the full list in the right pane and dim items outside the active section instead of showing only the active-section rows
 - Changed `SettingsList` to omit the default hint row (and preceding blank line) when `options.hint` is set to an empty string
 - Changed tab-bar overflow handling to collapse tabs to their `short` forms before wrapping to multiple lines
-
-### Fixed
-
-- Fixed `StdinBuffer` handling of split SGR mouse reports so fragmented sequences are reassembled instead of leaking their tail bytes as literal input
-- Fixed Esc being unreliable (or seconds-slow) inside fullscreen overlays such as `/settings` on kitty-protocol terminals (Ghostty/kitty): the kitty keyboard mode stack is per-screen, so entering the alternate screen silently reverted keys to legacy encoding while the app still parsed them as kitty input. The TUI now re-pushes the active kitty flags right after `\x1b[?1049h` and pops them before `\x1b[?1049l`.
-- Fixed `StdinBuffer` tearing a buffered bare `ESC` followed by another escape sequence: the `\x1b\x1b` candidate was consumed as alt+esc before the CSI/SS3 continuation byte was ever inspected, swallowing the Esc keypress and leaking the follower's tail (`[B`, `[<35;22;17M`) as typed text into focused components. Meta-CSI chords (`\x1b\x1b[A`) now stay whole, and `ESC` + SGR mouse report is split into a real Esc keypress plus a parseable report.
-- Lowered `PARTIAL_HOLD_MAX_MS` from 500ms to 150ms so a dangling escape partial that never completes (e.g. a bare `ESC` arriving while the kitty-active flag is stale) is delivered after at most ~200ms instead of half a second.
-- Fixed deferred partial-flush behavior so pending incomplete escapes are not split across timer boundaries and can still complete when the next chunk arrives
-- Fixed kitty keyboard-mode handling of a dangling `ESC` so it can be joined with subsequent CSI mouse/kitty input instead of being emitted as a standalone sequence
-- Fixed `SettingsList` to clear section-focus state when filtering items, changing data, scrolling with the mouse wheel, or selecting by ID so stale heading focus does not persist across interactions
-- `SettingsList` now renders every state — list, open submenu, filtered results, empty — at one stable height, so interacting with a bottom-anchored settings panel no longer resizes the live terminal region on each keystroke (which forced re-anchoring and could strand stale scrollback rows).
-
-## [15.11.3] - 2026-06-11
-
-### Fixed
-
-- Fixed the root compose letting a lower child's native-scrollback live seam overwrite a higher one: the topmost seam (and its commit-safe extension) now defines the commit boundary, so a status loader below a streaming transcript can no longer cause still-mutable transcript rows to be committed as stale history ([#2328](https://github.com/can1357/oh-my-pi/pull/2328)).
-
-## [15.11.2] - 2026-06-11
-
-### Fixed
-
-- Fixed Ctrl+C/exit corrupting the parent shell on Windows: `emergencyTerminalRestore()` wrote `\x1b[?1049l` (leave alternate screen) unconditionally on every exit path, and conhost/Windows Terminal execute an unconditional cursor restore for it even when the alt buffer was never entered — with no prior save the cursor jumped to the viewport home, so the shell prompt landed on top of the dead frame. The leave sequence is now gated on tracked alt-screen state (set/cleared by the TUI's fullscreen-overlay enter/leave and stop paths).
-- Skipped native syntax highlighting for transient markdown streaming renders, including nested list code blocks, leaving code blocks plain until their content stabilizes to avoid main-thread highlighter spikes.
-
-## [15.11.1] - 2026-06-11
-
-### Added
-
-- Added `TUI.requestComponentRender(component)` to schedule component-scoped renders for self-contained updates
-
-### Changed
-
 - Changed the render pipeline to reuse only affected root subtrees for component-scoped updates, avoiding full-tree compose when animations or other isolated component changes occur
-
-### Fixed
-
-- Fixed component-scoped renders to preserve prior live scrollback seam data for skipped root children, preventing duplicate or missing rows during spinner-only updates
-- Reported committed native scrollback row counts to interested child components so immutable history can be skipped without breaking live-region commit bookkeeping.
-- Fixed `ProcessTerminal` treating asynchronous stdout `EIO` errors as uncaught exceptions: stdout `error` events now mark the terminal dead, disable future renders, and keep the active session process alive ([#2284](https://github.com/can1357/oh-my-pi/issues/2284)).
-
-## [15.11.0] - 2026-06-10
-
-### Added
-
-- Added support for asynchronous `onSubmit` handlers by allowing the callback to return a `Promise<void>`
-
-## [15.10.11] - 2026-06-10
-
-### Added
-
-- `SettingsList` now supports type-to-search filtering with Escape clearing an active query before canceling.
-
-### Changed
-
 - Preserved list selection by item ID when replacing settings so focus stays on the same setting
 - Displayed a no matching settings message and search-editing hint when filtering returns no matches
 - Expanded settings search matching to include IDs, current values, descriptions, and option values as well as labels
@@ -114,9 +97,45 @@
 - Overlays now composite into the visible window slice only and freeze commits while visible, so overlay pixels can never enter native scrollback and closing an overlay no longer triggers a destructive history rebuild.
 - Inline-image budget demotion now deletes the demoted image's graphics by id and lets the window diff repaint the text fallback — no more mid-session destructive full replay when the image cap is exceeded.
 - The render-stress harness now validates the contract with a shadow commit ledger (an independent reimplementation of the ledger math fed only by observed frames and bytes), asserting scrollback equals the committed prefix row-for-row and that tape growth matches physical scroll exactly, across randomized op sequences, resizes, overlays, and multiplexer scenarios. The ghostty-web virtual terminal additionally survives libghostty-vt 0.4's WASM allocator traps via an event-log replay/compaction recovery, and strips non-spacing combining marks on input (a margin-aligned combining cluster deterministically corrupts that engine; mark placement through it was already unverifiable).
+- Changed the large-paste placeholder label from `[paste #N +X lines]`/`[paste #N Y chars]` to `[Paste #N, +X lines]`/`[Paste #N, Y chars]`.
+- Changed static `Loader` messages to repaint only at the spinner's 80 ms cadence; time-dependent message colorizers can opt into 16 ms redraws with `animated: true`.
+- Changed keybinding matching to precompute canonical key sets so each input sequence is parsed once per binding check instead of once per candidate key.
+- Made `Component.invalidate()` optional so leaf components without render caches no longer need no-op invalidation hooks.
+- `TERMINAL` is now a `RuntimeTerminal` whose post-construction capabilities (image protocol and the probe-driven flags) are writable, replacing the `as unknown as MutableTerminalInfo` cast pattern and the positional `withTerminalOverrides` rebuild with a prototype-preserving `clone()`.
+- Reworked the DEC 2026 synchronized-output default policy: a positive DECRQM mode-2026 report now **enables** sync (previously a report could only disable it), so conservatively defaulted-off hosts that actually support it — current Zellij, tmux master, foot, contour, mintty — are upgraded at runtime. The static allowlist also covers Alacritty and the VS Code terminal, honors a `TERM_FEATURES` `Sy` advertisement and `WT_SESSION` (Windows Terminal / WSL), and no longer blanket-disables SSH (DEC 2026 passes through to the outer terminal). Risky multiplexers still start off and rely on the probe. Added `synchronizedOutputUserOverride()` as the shared opt-out/force resolver.
+- Changed `SelectList` to render its visible window through `ScrollView`, replacing the `(N/M)` text scroll indicator with a uniform right-edge scrollbar (the type-to-search hint line is preserved).
+- Changed terminal resize handling so any width or height change always performs a clean reset + redraw: the renderer now unconditionally clears the viewport and native scrollback (`CSI 2 J` / `CSI 3 J`) and replays the full transcript at the new geometry, replacing the previous matrix of conditional viewport-repaint / history-rebuild / deferred-mutation branches. Multiplexer panes still repaint the visible window in place (pane scrollback cannot be erased), but a resize during active ED3-risk foreground streaming now performs the same clean rebuild rather than downgrading to a non-destructive viewport repaint: the terminal already re-wrapped its saved lines at the old width, so the rebuild must erase them (ED 3) instead of leaving the mis-wrapped history on screen. As a deliberate tradeoff this drops the prior no-overflow and confirmed-scrolled guards on resize: a reader scrolled into history snaps back to the bottom and preexisting shell scrollback above the UI is cleared.
+- Changed native-scrollback safety defaults to treat unknown POSIX, SSH, and multiplexer-shaped terminals as ED3-risk for passive rendering; checkpoint replay now requires a positive at-tail viewport proof instead of assuming prompt submit makes host scrollback safe.
+- Changed synchronized-output defaults to a conservative opt-in profile: DEC 2026 paint wrappers stay disabled for remote/multiplexer/VTE/unknown terminals unless explicitly forced, while the autowrap guards remain active.
+- Changed foreground-stream rendering on ED3-risk terminals (Ghostty/kitty/Alacritty/VTE/iTerm2 on POSIX) to defer native-scrollback commits for unpinned transient frames: while a turn streams, generic frames repaint only the viewport and suppress `\r\n` scroll growth, so transient output (spinner ticks, partial lines, status rows) never pollutes terminal history. Components that report a `NativeScrollbackLiveRegion` still commit newly sealed prefix rows while keeping the active suffix dirty for checkpoint replay. Native scrollback is reconciled in a single ED3 (`CSI 3 J`) + re-emit at the next checkpoint (prompt submit) or on an explicit user-input/IME opt-in; an erase is never emitted mid-stream under a possibly-scrolled reader. Non-ED3-risk terminals keep their eager live rebuild. ([#1895](https://github.com/can1357/oh-my-pi/pull/1895))
+- Changed TUI tests to use Ghostty's VT engine (`ghostty-web`) instead of `@xterm/headless`.
+- Changed the default inline-image live graphics budget from 3 to 8 images.
+- Disabled interactive search filtering for editor autocomplete and slash-command `SelectList`s by passing `overflowSearch: false` in their layout options
 
 ### Fixed
 
+- Fixed overlays without an explicit `maxHeight` dropping their bottom rows off-screen when taller than the terminal: `#resolveOverlayLayout` now defaults the height cap to the available rows, so a tall overlay is sliced to fit (and re-clamps on resize) instead of overflowing the visible region.
+- Fixed `Editor.#decorate` rejecting keyword matches glued to the cursor: `CURSOR_MARKER` begins with ESC (non-whitespace), so decorators with a right-boundary lookahead (e.g. `/(?<!\S)ultrathink(?!\S)/`) failed at the seam and dropped highlighting until a trailing character was typed. The decorate hook now splits around the marker and decorates each user-text segment in isolation so word-boundary lookarounds resolve correctly on both sides ([#2475](https://github.com/can1357/oh-my-pi/issues/2475)).
+- Fixed non-multiplexer resize drags with width changes briefly showing terminal-reflowed wrapped fragments: transient resize frames now borrow the alternate screen and return to the normal screen for the settled authoritative replay.
+- Fixed `isMultiplexerSession()` only checking the `TMUX`/`STY`/`ZELLIJ` env vars and missing the `TERM=tmux-*`/`screen-*` fallback every sibling detector uses. When the multiplexer env was stripped but `TERM` survived (`sudo` without `-E`, `su`, env-sanitizing launchers/ssh), the renderer misclassified the pane as a direct terminal and emitted ED3 (`CSI 3 J`) on resize/replace/`resetDisplay`, which wipes tmux pane history — scrollback only reappeared after a full rerender (Ctrl+L). The check now aligns with `shouldEnableSynchronizedOutputByDefault`, `detectRectangularSgrSupport`, and `getFallbackImageProtocol` in `terminal-capabilities.ts` ([#2544](https://github.com/can1357/oh-my-pi/issues/2544)).
+- Fixed live transcript rows duplicating into native scrollback during a non-multiplexer resize drag: the viewport fast-path repaint now parks the hardware cursor at the real content bottom (mirroring the authoritative paint) instead of the padded viewport bottom, so a subsequent height shrink no longer scrolls live rows into history before the settle replay
+- Fixed inline images flipping to their text fallback during a non-multiplexer resize drag: the viewport fast path now drives the image budget as a stable partial pass that replays the committed per-image live/text split by id, instead of deriving it from the reversed, tail-only walk order
+- Fixed issue #2088 viewport flash and repeated full rewrites during rapid terminal drags outside multiplexers by replaying the full transcript only after the resize settle window
+- Fixed multi-word searches so `fuzzyMatch` no longer matches when query letters are only scattered across unrelated words
+- Fixed `StdinBuffer` handling of split SGR mouse reports so fragmented sequences are reassembled instead of leaking their tail bytes as literal input
+- Fixed Esc being unreliable (or seconds-slow) inside fullscreen overlays such as `/settings` on kitty-protocol terminals (Ghostty/kitty): the kitty keyboard mode stack is per-screen, so entering the alternate screen silently reverted keys to legacy encoding while the app still parsed them as kitty input. The TUI now re-pushes the active kitty flags right after `\x1b[?1049h` and pops them before `\x1b[?1049l`.
+- Fixed `StdinBuffer` tearing a buffered bare `ESC` followed by another escape sequence: the `\x1b\x1b` candidate was consumed as alt+esc before the CSI/SS3 continuation byte was ever inspected, swallowing the Esc keypress and leaking the follower's tail (`[B`, `[<35;22;17M`) as typed text into focused components. Meta-CSI chords (`\x1b\x1b[A`) now stay whole, and `ESC` + SGR mouse report is split into a real Esc keypress plus a parseable report.
+- Lowered `PARTIAL_HOLD_MAX_MS` from 500ms to 150ms so a dangling escape partial that never completes (e.g. a bare `ESC` arriving while the kitty-active flag is stale) is delivered after at most ~200ms instead of half a second.
+- Fixed deferred partial-flush behavior so pending incomplete escapes are not split across timer boundaries and can still complete when the next chunk arrives
+- Fixed kitty keyboard-mode handling of a dangling `ESC` so it can be joined with subsequent CSI mouse/kitty input instead of being emitted as a standalone sequence
+- Fixed `SettingsList` to clear section-focus state when filtering items, changing data, scrolling with the mouse wheel, or selecting by ID so stale heading focus does not persist across interactions
+- `SettingsList` now renders every state — list, open submenu, filtered results, empty — at one stable height, so interacting with a bottom-anchored settings panel no longer resizes the live terminal region on each keystroke (which forced re-anchoring and could strand stale scrollback rows).
+- Fixed the root compose letting a lower child's native-scrollback live seam overwrite a higher one: the topmost seam (and its commit-safe extension) now defines the commit boundary, so a status loader below a streaming transcript can no longer cause still-mutable transcript rows to be committed as stale history ([#2328](https://github.com/can1357/oh-my-pi/pull/2328)).
+- Fixed Ctrl+C/exit corrupting the parent shell on Windows: `emergencyTerminalRestore()` wrote `\x1b[?1049l` (leave alternate screen) unconditionally on every exit path, and conhost/Windows Terminal execute an unconditional cursor restore for it even when the alt buffer was never entered — with no prior save the cursor jumped to the viewport home, so the shell prompt landed on top of the dead frame. The leave sequence is now gated on tracked alt-screen state (set/cleared by the TUI's fullscreen-overlay enter/leave and stop paths).
+- Skipped native syntax highlighting for transient markdown streaming renders, including nested list code blocks, leaving code blocks plain until their content stabilizes to avoid main-thread highlighter spikes.
+- Fixed component-scoped renders to preserve prior live scrollback seam data for skipped root children, preventing duplicate or missing rows during spinner-only updates
+- Reported committed native scrollback row counts to interested child components so immutable history can be skipped without breaking live-region commit bookkeeping.
+- Fixed `ProcessTerminal` treating asynchronous stdout `EIO` errors as uncaught exceptions: stdout `error` events now mark the terminal dead, disable future renders, and keep the active session process alive ([#2284](https://github.com/can1357/oh-my-pi/issues/2284)).
 - Fixed Windows rendering degrading into CP437 mojibake (`Γöé`/`ΓöÇ` instead of box-drawing borders and Nerd Font glyphs) after a console-sharing child process changed the console codepage (e.g. PHP CLI's implicit `chcp`, php.net request #73716): the breakage stayed latent until the next full repaint such as ctrl+o expand. The terminal now re-asserts the UTF-8 codepage (output and input) before each stdout write
 - Fixed crash recovery leaving the shell unusable: `emergencyTerminalRestore` (and `terminal.stop()`) never left the alt screen nor disabled mouse tracking, so a crash during a fullscreen overlay stranded the user on the alternate buffer with any-motion mouse reporting spewing escape garbage until a manual `reset`
 - Fixed bracketed paste with a lost `ESC[201~` end marker (ssh/tmux truncation) silently eating all subsequent input forever while growing memory unboundedly — paste mode now has an inactivity watchdog (1s) and a byte cap (64 MiB) that exit paste mode and deliver the accumulated bytes through the paste event
@@ -131,74 +150,13 @@
 - Fixed committed transcript rows silently vanishing when a component re-laid-out content the engine had already scrolled into native history — a TTSR stream rewind truncating a streamed block, or the image budget demoting a committed inline image to its one-line fallback, shifted every row below by the height delta and the engine kept committing from the stale index, skipping that many rows of everything after (missing interruption banners, half-cut images in scrollback). The engine now audits its committed prefix every ordinary frame: an in-place edit or restyle keeps its alignment (stale styling in history remains the accepted artifact), while any shift re-anchors the commit index at the first moved row and recommits from there — history keeps the stale copy and gains a fresh one. Duplication, never loss. The detector (`findCommittedPrefixResync`, exported for the stress harness's shadow ledger) samples the prefix tail SGR-stripped so theme restyles and single-row edits never trigger spurious recommits.
 - Fixed budget-demoted inline images shrinking their transcript block: the text fallback is now height-preserving once a graphic has rendered (reserved rows plus the fallback line), so demotion never shifts content below a committed image.
 - Fixed stale trailing cells bleeding into committed history on combining-heavy rows: the native width model can over-count Arabic/combining clusters, classifying a short-rendering row as full-width and skipping the trailing erase — the previous occupant's cells then scrolled into scrollback baked into the committed row. Non-ASCII row rewrites now erase the line before writing.
-
-### Removed
-
-- Removed the probe/defer API surface: `TUI.setEagerNativeScrollbackRebuild()`, `TUI.refreshNativeScrollbackIfDirty()`, `TUI.setClearOnShrink()`/`getClearOnShrink()`, `RenderRequestOptions.allowUnknownViewportMutation`, `NativeScrollbackRefreshOptions`, `Terminal.isNativeViewportAtBottom()`, `Terminal.hasEagerEraseScrollbackRisk()`, and the `eagerEraseScrollbackRisk`/`submitPinsViewportToTail` capability fields with their detectors.
-- Removed the `PI_TUI_ED3_SAFE`, `PI_CLEAR_ON_SHRINK`, and `PI_TUI_DEBUG` environment variables (the levers they tuned no longer exist; `PI_DEBUG_REDRAW` now logs the commit-ledger state per frame).
-
-## [15.10.9] - 2026-06-09
-
-### Added
-
-- Added a `wrapDescription` option to `SelectListLayoutOptions`. When enabled, long descriptions wrap onto continuation rows indented under the description column instead of being silently truncated. The slash-command/skill autocomplete picker now opts in so descriptions like the bundled skills' remain fully readable at normal terminal widths. `maxVisible` becomes the picker's visual row budget so the popup height stays bounded even when items wrap (a single 5-row description with `maxVisible=3` clips with the scrollbar carrying the offscreen tail). Navigation stays item-to-item, the narrow-width fallback (`width <= 40`) is unchanged, and the `ScrollView` scrollbar tracks visual rows so the thumb stays correct when items wrap unevenly. ([#2169](https://github.com/can1357/oh-my-pi/issues/2169))
-
-### Fixed
-
 - Fixed Ghostty's first inline image in a fresh TUI session sometimes rendering as an empty placeholder block by holding the initial Kitty graphics paint until the terminal startup settle window has passed. Direct Kitty placements also keep their zero-width reservation rows non-plain so image-only transcript blocks do not collapse when blank-edge trimming runs.
-
-## [15.10.8] - 2026-06-09
-
-### Fixed
-
 - Fixed TUI renders repeatedly clearing terminal scrollback after content filled the viewport. Unknown viewport probes no longer let foreground-streaming offscreen growth take the destructive `historyRebuild` path on every frame; newly appended tail rows stay reachable while stale history waits for a safe checkpoint. ([#2154](https://github.com/can1357/oh-my-pi/issues/2154))
-
-## [15.10.6] - 2026-06-08
-
-### Added
-
-- Added `TUI.getFocused()` accessor and `Input.pasteText(text)` method so callers consuming non-bracketed paste transports (e.g. kitty's OSC 5522 enhanced clipboard) can route a paste payload to the currently focused modal Input rather than always to the primary editor. Mirrors the existing `Editor.pasteText` semantics: newlines stripped, tabs normalized, NFC normalization applied. ([#2127](https://github.com/can1357/oh-my-pi/issues/2127))
-
-### Fixed
-
 - Fixed tmux/screen/zellij rewind/branch (`requestRender(true, { clearScrollback: true })`) permanently anchoring the input box to the pane top and overlaying scrollback after a streamed reply had grown past the viewport. `#emitFullPaint` only reset `#scrollbackHighWater` inside the `clearScrollback` branch and otherwise raised it monotonically, so inside multiplexers (where `\x1b[3J` is a no-op and `clearScrollback` is forced off) the streaming peak survived the rewind; on the next frame `#planLiveRegionPinnedRender` saw the stale high-water and anchored `renderViewportTop` past the actual content, repainting every visible row blank and parking the cursor at screen row 0 for the rest of the session. A full repaint with `clearViewport: true` re-emits the entire transcript from row 0, so `#scrollbackHighWater` is now assigned (not max-clamped) to the natural push count regardless of whether ED 3 was issued ([#2130](https://github.com/can1357/oh-my-pi/issues/2130)).
-
-## [15.10.5] - 2026-06-08
-
-### Added
-
-- Added `atomicTokenPattern` to `Editor`: when set to a global regex matching placeholder tokens such as `[Image #1, 800x600]` or `[Paste #2, +30 lines]`, a single backspace or forward-delete landing anywhere on a token removes the whole token instead of corrupting it into stray text.
-
-### Changed
-
-- Changed the large-paste placeholder label from `[paste #N +X lines]`/`[paste #N Y chars]` to `[Paste #N, +X lines]`/`[Paste #N, Y chars]`.
-
-### Fixed
-
 - Fixed pasting large text lagging the prompt for hundreds of milliseconds before the `[paste #N …]` placeholder appeared. `StdinBuffer` assembled bracketed pastes by re-concatenating and re-scanning the entire accumulated buffer on every incoming stdin chunk (`#pasteBuffer += chunk; indexOf(END)`), which is O(n²) in the paste size and dominates when the terminal/PTY delivers the paste in many small reads (SSH, tmux, slow hosts) — a 1 MB paste at 1 KB chunks cost ~33 ms and 5 MB ~740 ms. Chunks are now collected in an array and joined once when the end marker arrives, with a short overlap tail carried across chunk boundaries so a marker split between two reads is still detected without rescanning, making assembly O(n) (~1 ms for 5 MB). The `Editor` paste cleaner also dropped its `split("").filter().join("")` per-code-unit array allocation in favor of a single control-character regex pass (~20× faster on large pastes).
-
-## [15.10.4] - 2026-06-08
-
-### Fixed
-
 - Fixed Windows ConPTY session-resume painting the transcript with the last several rows truncated below the viewport until Alt+Tab forced a host repaint. After `sessionReplace`/`historyRebuild`/`overlayRebuild` paints that scroll-push content into native scrollback, the renderer now arms a 150 ms ConPTY settle window that coalesces spinner/blink-driven `requestRender(false)` calls into a single trailing render — Windows Terminal's viewport-follow logic no longer falls further behind the cursor on every tick of the post-paint storm. The arm also reclaims any render request queued *during* the in-flight composition (notably `ImageBudget.endPass()` calling `requestRender()` synchronously when a frame trips the live-graphics cap): without that, the queued request sat on the standard 30 Hz throttle and fired at ~33 ms — well inside the 150 ms quiet window — defeating the coalescing. Bumped the ConPTY per-`WriteFile` chunk cap from 8 KiB to 16 KiB so a multi-megabyte resume paint emits half as many writes (still well under the ~32 KiB threshold from #2034 that the original cap defends against), and made the cap measure encoded UTF-8 bytes instead of JS code units so a CJK-heavy transcript can't silently inflate a 16-KiB-of-code-units chunk into ~48 KiB of `WriteFile` traffic and reintroduce the #2034 viewport bug ([#2095](https://github.com/can1357/oh-my-pi/issues/2095)).
-
-## [15.10.3] - 2026-06-08
-
-### Fixed
-
 - Fixed DEC 2048 in-band resize reports (`CSI 48;rows;cols;hpx;wpx t`) leaking into the focused editor as literal text during a rapid resize. When the window is resized quickly the event loop stays busy long enough for the `StdinBuffer` flush timeout to fire mid-report; the `\x1b[48;…` prefix was emitted as one event and the tail (e.g. `8;125;1156;1125t`) arrived as bare printable characters that the editor inserted. `ProcessTerminal` now reassembles a split in-band report (including a split at the bare `\x1b[4` type field) until its terminator and then drives the resize. A reassembled sequence that turns out not to be a resize report — such as a split kitty key like `\x1b[48;5u` (codepoint 48 = `0`) — is forwarded to the input handler as a single escape sequence rather than dropped or leaked.
 - Coalesced terminal-multiplexer SIGWINCH events into a single forced render once the pane stops resizing so closing/dragging a tmux/screen/zellij split no longer flashes the viewport blank before the new geometry repaints ([#2088](https://github.com/can1357/oh-my-pi/issues/2088)).
-
-## [15.10.2] - 2026-06-08
-
-### Added
-
-- Added exported `canonicalKeyId` and `addKeyAliases` keybinding helpers so consumers can share the same canonical shortcut matching semantics as `KeybindingsManager`.
-- Added `super` modifier support to native key parsing/matching and bound `super+alt+backspace` / `super+alt+delete` (and `super+alt+d`) into the word-delete defaults so Ghostty's default macOS Option+Backspace wire (`ESC [127;11u` — kitty modifier 11 = super|alt) deletes a word instead of falling through to single-char delete ([#2064](https://github.com/can1357/oh-my-pi/issues/2064)).
-
-### Fixed
-
 - Fixed focus-changing in-place menus leaving stale Working/menu rows and parking the hardware cursor in the old menu viewport on terminals without a scroll-position oracle.
 - Fixed redundant terminal cursor updates so repeated renders that do not change the cursor row, column, or visibility no longer emit ANSI move/hide sequences
 - Fixed repeated cursor updates during no-op re-renders by reusing the last known cursor state, preventing unnecessary cursor position changes and hide/show sequences
@@ -206,37 +164,7 @@
 - Bounded TUI line fitting for oversized raw rows so ANSI-heavy subagent output and zero-width-heavy text cannot grow render buffers independently of the viewport or hide visible suffix text ([#2045](https://github.com/can1357/oh-my-pi/issues/2045)).
 - Fixed tmux offscreen-shrink frames to skip repainting when the visible tail is unchanged, avoiding intermittent blank/refresh flashes in pane terminals ([#2046](https://github.com/can1357/oh-my-pi/issues/2046)).
 - Fixed Windows ConPTY hosts (Windows Terminal, Tabby, Hyper, VS Code) parking the viewport at the top of a full paint after a `/resume` or any long-session repaint. `ProcessTerminal#safeWrite` now splits oversized writes into ≤ 8 KiB pieces at line boundaries on `win32` and inside WSL (where stdout still crosses ConPTY at the `wslhost` boundary) so each underlying `WriteFile` stays below the ~32 KiB threshold where ConPTY stops tracking the cursor; the data was always delivered, but the host UI's scroll position would not follow until any focus event forced a re-query. ([#2034](https://github.com/can1357/oh-my-pi/issues/2034))
-
-## [15.10.1] - 2026-06-07
-
-### Breaking Changes
-
-- Removed Kitty temp-file image transmission, its startup support probe, the `PI_KITTY_IMAGE_TRANSMISSION` override, and the temp-file helper exports. Kitty/Ghostty image payloads now stay on in-band base64 before placeholder/direct placement, avoiding blank first renders from temp-file load races.
-- Renamed `RenderRequestOptions.allowUnknownViewportMutation` → `allowUnknownViewportTransientRepaint`. The option only permits a transient live-viewport repaint (autocomplete/IME/focused-editor chrome) on hosts that cannot report viewport position; it never authorizes a settled transcript commit. The old name implied any offscreen mutation was safe to push into native scrollback, which led callers to emit duplicate transcript copies.
-
-### Added
-
-- Added `TUI.addStartListener()` so feature hooks can re-enable terminal modes after temporary stop/start cycles such as external-editor handoffs.
-- Added `Editor.pasteText()` to apply terminal-style paste handling for text inserted from non-bracketed paste transports
-- Added an optional `dispose()` lifecycle method to `Component` so components can release timers and subscriptions during permanent teardown
-- Added `Container.dispose()` to propagate teardown to child components when a component tree is permanently discarded
-- Added `Loader.dispose()` to stop the loader animation timer when the component is disposed
-- Added a `ScrollView` `ellipsis` option (defaults to `Ellipsis.Unicode`) so callers that pre-wrap content to width can pass `Ellipsis.Omit` and suppress the stray per-line `…` that lands on trailing padding.
-- Added `ScrollView.handleScrollKey()` plus a `fastScrollLines` option so every scroll view gets shared navigation keys, including Shift+Arrow to scroll faster.
-- Added `OverlayOptions.fullscreen`: while the topmost visible overlay sets it, the engine borrows the terminal's alternate screen buffer for the overlay's lifetime and paints only the modal there — no ED3, no transcript re-commit — so the transcript stays untouched on the normal screen and is not scrollable behind the modal. Mouse tracking (`?1000h`/`?1006h`) is enabled for the modal's lifetime and disabled on exit, so the rest of the app keeps the terminal's native text selection.
-- Added the `submitPinsViewportToTail` terminal capability and `detectSubmitPinsViewportToTail()`: genuine local terminals where a submit keystroke scrolls the host to its tail reconcile deferred native scrollback at the prompt-submit checkpoint even when the viewport position is unprobeable (Ghostty/kitty/iTerm/WezTerm/Alacritty). Restores the pre-regression submit reconciliation without re-enabling it for Windows Terminal/ConPTY, SSH, or multiplexers, where a submit is not proof the host is at the tail.
-
-### Changed
-
-- Changed static `Loader` messages to repaint only at the spinner's 80 ms cadence; time-dependent message colorizers can opt into 16 ms redraws with `animated: true`.
-- Changed keybinding matching to precompute canonical key sets so each input sequence is parsed once per binding check instead of once per candidate key.
-- Made `Component.invalidate()` optional so leaf components without render caches no longer need no-op invalidation hooks.
-- `TERMINAL` is now a `RuntimeTerminal` whose post-construction capabilities (image protocol and the probe-driven flags) are writable, replacing the `as unknown as MutableTerminalInfo` cast pattern and the positional `withTerminalOverrides` rebuild with a prototype-preserving `clone()`.
-
-### Fixed
-
 - Fixed `Loader` text updates to skip identical messages and preserve the rendered `Text` cache instead of invalidating it every timer tick.
-
 - Fixed fullscreen overlay alt-frame rendering to reuse the current line-preparation path instead of calling removed fitting helpers.
 - Reduced TUI render-path line fitting by deferring overlay base-frame fitting until an overlay rebuild and by reusing already-fitted lines in emitters.
 - Reduced live-region pinned repaint output by diffing unchanged viewport rows when no sealed rows are being committed to native scrollback.
@@ -251,145 +179,34 @@
 - Fixed `visibleWidth()` so terminal column measurements for ANSI and OSC text now match the native truncation/wrapping helpers, including OSC 66 text-sizing spans being counted at their scaled payload width
 - Fixed cursor, padding, and line-fit behavior when strings contain tabs or OSC escapes by aligning `visibleWidth()` with the native text-width model
 - Fixed the transcript — or a re-appearing prior view such as the welcome screen — duplicating itself on terminals without a scroll-position oracle (Ghostty/kitty/iTerm/WezTerm) when a foreground tool completes by rewriting a partly-committed block, or when the transcript is reset. A non-destructive viewport repaint no longer re-paints rows that are byte-identical to what is already committed to native scrollback into the active grid; the repaint anchor is clamped to the committed-and-unchanged prefix (`min(firstChanged, scrollbackHighWater)`).
-
-## [15.10.0] - 2026-06-06
-
-### Changed
-
-- Reworked the DEC 2026 synchronized-output default policy: a positive DECRQM mode-2026 report now **enables** sync (previously a report could only disable it), so conservatively defaulted-off hosts that actually support it — current Zellij, tmux master, foot, contour, mintty — are upgraded at runtime. The static allowlist also covers Alacritty and the VS Code terminal, honors a `TERM_FEATURES` `Sy` advertisement and `WT_SESSION` (Windows Terminal / WSL), and no longer blanket-disables SSH (DEC 2026 passes through to the outer terminal). Risky multiplexers still start off and rely on the probe. Added `synchronizedOutputUserOverride()` as the shared opt-out/force resolver.
-
-### Fixed
-
 - Fixed WSL/Windows Terminal row flicker while typing by repainting changed text rows before clearing only their stale suffix ([#2011](https://github.com/can1357/oh-my-pi/issues/2011)).
 - Fixed terminals that support DEC 2026 still tearing/flickering because the renderer ignored a positive DECRQM capability report and kept synchronized output off — most visibly WSL + Windows Terminal, Alacritty (≥0.13), and the VS Code terminal (≥1.108), which were detected yet refused sync.
-
-## [15.9.69] - 2026-06-06
-
-### Added
-
-- Added `TUI.resetDisplay()` to force an immediate full-frame replay, including native scrollback when the host can safely clear it.
-- Added `setPaddingY` to `Box` so vertical padding can be updated programmatically after creation.
-
-### Fixed
-
 - Fixed DECCARA background-fill optimization running when synchronized output is disabled, which could expose default-background gaps during rapidly updating tool-use panels ([#2000](https://github.com/can1357/oh-my-pi/issues/2000)).
-
-## [15.9.67] - 2026-06-06
-
-### Added
-
-- Added `setPaddingX` to `Box` so horizontal padding can be updated programmatically after creation
-- Added `ScrollView`, a fixed-height viewport component for pre-rendered lines with optional right-edge scrollbars and imperative scroll/page controls.
-- Added optional `Terminal.hasEagerEraseScrollbackRisk()` so custom/test terminal implementations can override the global ED3-risk profile without mutating the shared `TERMINAL` object.
-
-### Changed
-
-- Changed `SelectList` to render its visible window through `ScrollView`, replacing the `(N/M)` text scroll indicator with a uniform right-edge scrollbar (the type-to-search hint line is preserved).
-
-### Fixed
-
 - Fixed unknown-viewport deferred renders freezing bottom-anchored live chrome; deferred history mutations can now repaint only the active-grid bottom row with relative cursor movement, so spinner/status tails keep advancing without rewriting rows a scrolled reader can still see.
 - Fixed autocomplete popups freezing live repaint on ED3-risk macOS/POSIX terminals with unknown native viewport position; direct autocomplete shrink frames now repaint the live viewport without zero-byte deferral and preserve the old bottom anchor when padding can clear stale popup rows without duplicating committed scrollback.
 - Fixed focused Up/Down navigation on ED3-risk macOS/POSIX terminals replaying the whole transcript after dirty foreground-stream renders; selector/editor frames now repaint non-destructively instead of emitting `CSI 3 J` on every arrow-key move ([#1962](https://github.com/can1357/oh-my-pi/issues/1962)).
 - Fixed tmux (and screen/zellij) pane scrollback losing the head of a long streamed assistant reply once it grew past the visible pane, and stranding the chrome/footer in pane history after a later collapse — producing the "repeating chunks and missing sections" reporters saw when scrolling back through tmux pane history ([#1974](https://github.com/can1357/oh-my-pi/issues/1974)). The renderer's foreground-streaming cap-to-viewport branch (introduced in 15.9.2 for ED3-risk hosts that can checkpoint-rebuild later) also activated inside multiplexers, where checkpoint reconcile is a no-op (`refreshNativeScrollbackIfDirty` short-circuits because `\x1b[3J` cannot erase pane history). Every streaming frame clipped `lines` to the visible tail and reset `#scrollbackHighWater` to 0, so any row that scrolled above the viewport top was committed nowhere — pane history stayed empty until streaming ended. Meanwhile `#planLiveRegionPinnedRender` was explicitly disabled for multiplexers, but its `#emitLiveRegionPinnedRepaint` is built from the exact primitives tmux accepts (relative cursor moves, per-line `\x1b[2K`, `\r\n` to scroll the sealed prefix past the viewport bottom) and never emits `\x1b[2J`/`\x1b[3J`. The pinned planner now runs in multiplexers too, the cap branch skips them, and the diff/append path commits incrementally into pane history; the actively-mutating live tail stays in the visible viewport only.
-
-## [15.9.5] - 2026-06-05
-
-### Changed
-
-- Changed terminal resize handling so any width or height change always performs a clean reset + redraw: the renderer now unconditionally clears the viewport and native scrollback (`CSI 2 J` / `CSI 3 J`) and replays the full transcript at the new geometry, replacing the previous matrix of conditional viewport-repaint / history-rebuild / deferred-mutation branches. Multiplexer panes still repaint the visible window in place (pane scrollback cannot be erased), but a resize during active ED3-risk foreground streaming now performs the same clean rebuild rather than downgrading to a non-destructive viewport repaint: the terminal already re-wrapped its saved lines at the old width, so the rebuild must erase them (ED 3) instead of leaving the mis-wrapped history on screen. As a deliberate tradeoff this drops the prior no-overflow and confirmed-scrolled guards on resize: a reader scrolled into history snaps back to the bottom and preexisting shell scrollback above the UI is cleared.
-
-### Fixed
-
 - Fixed ED3-risk foreground streaming dropping the scrolled-off head of an append-only live block that alone overflows the viewport (a long streamed assistant reply). The live-region pin again committed native scrollback only up to the live-region start, so once the live block grew past the viewport its earlier rows scrolled above the viewport top but were committed nowhere and repainted nowhere — they vanished, leaving the reply looking like a ~viewport-tall circular buffer. The `NativeScrollbackLiveRegion` seam now also reports an optional append-only `getNativeScrollbackCommitSafeEnd`, and the pinned commit boundary is the deeper of the sealed start and that append-only end: rows in `[liveRegionStart, commitSafeEnd)` above the viewport top commit to scrollback, while volatile live blocks (tool previews that collapse) omit the boundary and keep their mutable rows deferred — preserving the pending-box-above-running-box fix.
-
-## [15.9.4] - 2026-06-05
-
-### Added
-
-- Added `PI_TUI_SYNC_OUTPUT=0` and `PI_TUI_SYNC_OUTPUT=1` to explicitly disable or force-enable DEC 2026 synchronized-output mode, alongside `PI_FORCE_SYNC_OUTPUT=1` as a force-on alias
-- Added `PI_TUI_ED3_SAFE=1` environment override to treat a terminal as non-ED3-risk for eager native scrollback rebuilds on unknown POSIX hosts
-
-### Changed
-
-- Changed native-scrollback safety defaults to treat unknown POSIX, SSH, and multiplexer-shaped terminals as ED3-risk for passive rendering; checkpoint replay now requires a positive at-tail viewport proof instead of assuming prompt submit makes host scrollback safe.
-- Changed synchronized-output defaults to a conservative opt-in profile: DEC 2026 paint wrappers stay disabled for remote/multiplexer/VTE/unknown terminals unless explicitly forced, while the autowrap guards remain active.
-
-### Fixed
-
 - Fixed ED3-risk unknown-viewport renders repainting offscreen structural edits over stale native scrollback, which could duplicate or shift rows when async blocks collapsed or middle rows were deleted.
 - Fixed ED3-risk foreground streams committing mutable live-region rows into native scrollback, which could leave a stale `pending` tool box above the `running` box after the preview re-rendered.
 - Fixed TUI shutdown leaving paint-time terminal state and Kitty image data behind by restoring synchronized-output/autowrap modes and purging all transmitted Kitty image ids on stop.
 - Fixed stdin buffering splitting surrogate-pair text into UTF-16 halves and reduced timing sensitivity for incomplete escape sequences.
 - Fixed terminal content not reflowing after a resize on terminals using DEC 2048 in-band resize (kitty/Ghostty/iTerm2/WezTerm). `ProcessTerminal.columns`/`rows` returned the last cached in-band report even after the OS already knew the new size, so a SIGWINCH whose in-band report was dropped or malformed (split past the stdin flush window, `:`-subparameter fields) re-rendered the whole transcript at the stale width. OS resize events now reconcile cached in-band geometry against the live `process.stdout` dimensions, dropping a stale cached value so the next render uses the true size; a valid in-band report still re-seeds pixel sizing.
-
-## [15.9.3] - 2026-06-05
-
-### Fixed
-
 - Fixed ED3-risk foreground streaming erasing the head of any block that alone overflows the viewport (a tall tool result drawn in one frame, or a multi-line assistant reply growing past the viewport as it streams). The live-region pin committed native scrollback only up to the sealed-prefix boundary (`liveRegionStart`), so rows of the live block that had physically scrolled above the viewport top were neither pushed into scrollback nor kept in the repainted viewport — they vanished. The commit boundary is now the viewport top: every row above the viewport enters scrollback (only the tail still visible in the viewport stays transient and deferred to the checkpoint).
 - Fixed the same ED3-risk live-region pin duplicating already-committed scrollback rows when a foreground stream's live region collapsed mid-turn (a tool preview shrinking to its compact result, an assistant block re-wrapping shorter, a late tool completion). Because growth commits every row above the viewport top to native scrollback, a subsequent shrink moved the bottom-anchored viewport back across those committed rows and the repaint re-drew them into the viewport — so they appeared twice on scroll-up, and with no prompt-submit checkpoint to reconcile (autonomous multi-turn runs, or the session ending into the welcome screen) the duplicate was baked permanently into terminal history. The pinned repaint now separates commit geometry from repaint geometry: a collapse clamps the repaint to the committed sealed boundary (`min(#scrollbackHighWater, liveRegionStart)`) instead of re-exposing those rows, leaving native scrollback un-duplicated without emitting ED3 under a possibly-scrolled reader; stale mutable live-region saved lines still reconcile at the next checkpoint.
 - Fixed hiding overlays during ED3-risk foreground streaming on unknown-viewport terminals leaving the overlay's transient rows in native scrollback. Overlay visibility reductions now bypass the streaming deferral path and rebuild once, so hidden dialog/notification sentinels are scrubbed immediately.
 - Fixed ED3-risk / unknown-viewport terminals (including WSL fronted by Windows Terminal) keeping the foreground-stream eager-rebuild mode active after the stream had already settled. A later scrolled content shrink or resize-with-append could then bypass the anti-yank deferral and repaint from stale geometry, jumping the viewport or replaying the wrong rows. The eager opt-in now drops immediately when no teardown render is pending, and the one-frame post-checkpoint suffix-suppression path no longer overrides geometry reflow handling.
-
-## [15.9.2] - 2026-06-05
-
-### Changed
-
-- Changed foreground-stream rendering on ED3-risk terminals (Ghostty/kitty/Alacritty/VTE/iTerm2 on POSIX) to defer native-scrollback commits for unpinned transient frames: while a turn streams, generic frames repaint only the viewport and suppress `\r\n` scroll growth, so transient output (spinner ticks, partial lines, status rows) never pollutes terminal history. Components that report a `NativeScrollbackLiveRegion` still commit newly sealed prefix rows while keeping the active suffix dirty for checkpoint replay. Native scrollback is reconciled in a single ED3 (`CSI 3 J`) + re-emit at the next checkpoint (prompt submit) or on an explicit user-input/IME opt-in; an erase is never emitted mid-stream under a possibly-scrolled reader. Non-ED3-risk terminals keep their eager live rebuild. ([#1895](https://github.com/can1357/oh-my-pi/pull/1895))
-
-### Fixed
-
 - Fixed ED3-risk foreground streaming dropping sealed transcript rows above the live block until the next prompt-submit checkpoint, which made scrollback beyond the viewport appear duplicated or out of order. The renderer restores native-scrollback live-region pinning so newly sealed rows are appended once while active live rows remain deferred.
 - Fixed inline images (added in 15.9) rendering as a wall of empty PUA box glyphs and producing laggy scrolling on Kitty-protocol terminals that do not implement Unicode placeholders — most notably WezTerm (per upstream wezterm/wezterm#986, placeholder support is still unchecked) and the tmux/screen `getFallbackImageProtocol` path that forces Kitty mode even on non-supporting outer terminals (Terminal.app, etc.). `unicodePlaceholders` now defaults on only for `kitty` and `ghostty`; everything else falls back to direct `a=p,i=…,p=…` placement, which those paths already render correctly. `PI_NO_KITTY_PLACEHOLDERS=1` is still honored as a hard opt-out, and a new `PI_KITTY_PLACEHOLDERS=1` opts in on otherwise-unsupported terminals (e.g. a wezterm nightly that has merged placeholder support) ([#1877](https://github.com/can1357/oh-my-pi/issues/1877)).
-
-## [15.9.1] - 2026-06-04
-
-### Fixed
-
 - Fixed the OSC 11 appearance poll re-querying every 2s forever on terminals that support Mode 2031 but never change theme, whose repeated OSC 11/DA1 writes cleared the user's active text selection (breaking copy every 2 seconds). The poll now stops as soon as DECRQM confirms Mode 2031 support, since push notifications make polling redundant.
-
-## [15.9.0] - 2026-06-04
-
-### Added
-
-- Added Kitty `CSI 22 J` screen-to-scrollback clears for non-destructive full paints, while keeping ED3 for destructive history/session rebuilds.
-- Added Kitty OSC 99 rich notification formatting and startup capability probing.
-- Added Kitty OSC 66 text-sized Markdown H1 headings (2x scale) plus native text-width support for OSC 66 spans. Off by default and gated to Kitty (the only terminal implementing OSC 66) via the `TERMINAL.textSizing` capability; hosts enable it through `setTextSizing`.
-- Added Kitty Unicode placeholder image rendering (`U=1` + U+10EEEE with explicit row/column diacritics): inline images are drawn as real text cells that carry the image id in their foreground color, so they survive horizontal slicing, reflow, and overlapping draws instead of relying on cursor-positioned `a=p` placements. Enabled by default on Kitty-family terminals; opt out with `PI_NO_KITTY_PLACEHOLDERS=1`, and falls back to direct placement when a grid exceeds the diacritic table's addressable range.
-- Added Kitty temp-file image transmission (`t=t`): on local sessions, decoded PNG bytes are written to a `tty-graphics-protocol` temp file and the path is sent instead of in-band base64, gated behind a startup `a=q,t=t` support probe. Controlled by `PI_KITTY_IMAGE_TRANSMISSION=direct|temp-file|auto`; disabled over SSH unless explicitly forced.
-- Added DECRQM capability detection for DEC private modes 2026 (synchronized output) and 2048 (in-band resize). Synchronized-output paint wrappers are dropped when the terminal reports 2026 unsupported (preserving the `PI_NO_SYNC_OUTPUT` override), and DEC 2048 in-band resize is enabled when supported — reported geometry and cell pixel size are updated from `CSI 48 ; rows ; cols ; yPx ; xPx t` reports, with SIGWINCH and `CSI 16 t` kept as fallbacks.
-- Added an injectable render scheduler for TUI tests, allowing deterministic render drains without patching global clocks or event-loop timing.
-- Added `ImageBudget`, an inline-image cap that keeps only the most recent N images as live terminal graphics and demotes older ones to their text fallback. Once a new image pushes the count past the cap, the renderer hides the oldest via a full redraw plus an explicit Kitty graphics purge (`a=d,d=I`) — text-clear escapes (`CSI 2 J`/`CSI 3 J`) do not remove Kitty images. Configure the cap via `TUI#setMaxInlineImages` (`0` disables it).
-- Changed Kitty inline images to a transmit-once + placement scheme: the base64 data is sent a single time (`a=t`) keyed by a stable image id, then every repaint emits only the tiny placement (`a=p,i=…,p=…`). Repaints — including full redraws — no longer re-send image data or stack duplicate placements, and the diff/line buffers and render caches hold short placement strings instead of multi-KB base64. The `ImageBudget` doubles as the transmit store (it tracks which ids are loaded and re-transmits after a purge frees the data). iTerm2/Sixel, which have no addressable image store, keep sending inline data as before.
-- Added a renderer-level DECCARA rectangular-SGR optimizer that paints solid background panels/rows (Box/Text/Markdown fills, status bars, any full-width `theme.bg` row) as a single coalesced rectangle escape (`CSI 2*x` / `CSI Pt;Pl;Pb;Pr;<sgr>$r` / `CSI *x`) instead of emitting a full-width run of background-styled spaces on every visible row. It operates at emit time on the final ANSI strings — components are unchanged — and strips only trailing padding it can prove sits under a single non-default background span, coalescing vertically adjacent identical fills into one rectangle and falling back to the original bytes whenever the rectangle would not save bytes. Enabled only on Kitty, which implements the SGR-background extension (`docs/deccara.rst`); **Ghostty is intentionally excluded** because its `CSI $r` is unimplemented (ghostty-org/ghostty#632) and would drop the background entirely. Scrollback-bound rows and the append/scroll paths always keep the padded representation so native history preserves colored cells, and the `PI_NO_DECCARA` kill switch (plus tmux/screen/zellij detection) forces the fallback.
-- Added `CMUX_SURFACE_ID` environment variable support to `getTerminalId()`, so cmux terminal surfaces get a stable identifier alongside kitty, tmux, macOS Terminal.app, and Windows Terminal — enabling per-surface session breadcrumbs for `omp -c` in cmux.
-
-### Changed
-
-- Changed TUI tests to use Ghostty's VT engine (`ghostty-web`) instead of `@xterm/headless`.
-- Changed the default inline-image live graphics budget from 3 to 8 images.
-
-### Fixed
-
 - Fixed the DECCARA background-fill optimizer rejecting or repainting the wrong cells when a trailing fill crossed from default-background spaces into colored spaces.
 - Fixed DEC private-mode reports with DECRPM status 3/4 being treated as unsupported, so permanent 2026/2048 reports stay recognized.
 - Fixed OSC 66 text-sizing width and slicing edge cases, including ZWJ emoji payloads and partial slices through scaled spans.
-
 - Fixed focused `Input` components following `TUI#setShowHardwareCursor`, so single-line prompts render either the terminal cursor or software cursor consistently with the editor.
 - Fixed the DECCARA background-fill optimizer painting fills on the wrong rows ("split into unaligned halves") in the differential repaint path. When a diff grew the transcript past the viewport, writing the rewritten rows scrolled the terminal, but the absolute DECCARA rectangle coordinates were derived from the pre-scroll viewport top, so every fill landed `scrollAmount` rows too low while the relatively-positioned text settled correctly; rows scrolled into history were also shortened, dropping their background padding from native scrollback. Rectangles now target the post-scroll rows and only rows remaining in the final viewport are optimized.
 - Fixed native scrollback desynchronization after terminal width or height changes reflowed overflowing content while the viewport was not at the bottom
 - Fixed a notification chip (or any injected block) rendering on top of an actively streaming tool render on ED3-risk terminals (Ghostty/kitty/Alacritty/iTerm2). While a foreground tool streams, its header's elapsed-time counter ticks every frame; once output scrolls the header above the viewport top, each tick is an offscreen edit that — because the eager scrollback-rebuild opt-in is gated off on these terminals — repaints the viewport in place and advances the rendered line count without committing the new overflow to native history. `#scrollbackHighWater` then lagged the logical viewport top, so a later content shrink whose changes landed in the visible region slipped past the shrink-across-boundary guard and reached the differential emitter, which is anchored to `#maxLinesRendered - height`: it rewrote only the suffix, dropped the newly exposed top row, and left a blank at the bottom, drifting every row below the edit one line up so it painted over the rows above. Such shrinks now re-anchor the bottom of the viewport with a non-destructive repaint, and the foreground-streaming shrink-across-boundary case repaints the live tail instead of padding and pinning the pre-shrink viewport.
 - Fixed a terminal resize during foreground-tool streaming on an unknown-viewport / ED3-risk host (Ghostty/kitty/Alacritty/iTerm2/WSL) leaving native scrollback permanently out of sync, so scrolling back after the turn showed missing rows. A pure geometry resize (no content change) takes the in-place viewport-repaint path, which — unlike a content-bearing resize that rebuilds via the geometry branch — never flagged native history. Because the prompt-submit checkpoint (`refreshNativeScrollbackIfDirty`) only rebuilds when scrollback is marked dirty on these hosts, the discrepancy was never reconciled. Overflowing geometry repaints whose viewport is not known to be at the bottom now mark scrollback dirty so the next checkpoint rebuilds an exact copy of the transcript.
-
-## [15.8.2] - 2026-06-03
-
-### Added
-
-- Added `PI_NO_SYNC_OUTPUT=1` to disable DEC 2026 synchronized-output wrappers for terminals whose implementation is buggy or visually worse, while keeping the renderer's autowrap guards active during paints ([#1765](https://github.com/can1357/oh-my-pi/issues/1765)).
-
-### Fixed
-
 - Fixed terminal resizes that land in the same render frame as streamed output splicing a phantom blank row into native scrollback and offsetting every later row by one. A height shrink (or width change carrying an append) with content overflowing the viewport fell through to the differential emitter, whose scroll math is anchored to the pre-resize viewport top and hardware-cursor row — both invalidated by the terminal's own resize reflow. Geometry-changed frames now rebuild native history when the viewport is at (or possibly at) the bottom, and defer non-destructively for a reader confirmed scrolled into history.
 - Fixed Ghostty/kitty/Alacritty-style ED3-risk terminals freezing the prompt after a deferred shrink; focused keyboard input now uses the same explicit user-input viewport opt-in as autocomplete and can repaint immediately instead of waiting for a resize.
 - Deferred eager live scrollback rebuilds under WSL fronted by Windows Terminal (`WT_SESSION` present in a Linux environment) so foreground streaming no longer emits ED3 (`CSI 3 J`) and yanks a reader scrolled into Windows Terminal's host scrollback; deferred rewrites still reconcile at the next prompt-submit checkpoint ([#1610](https://github.com/can1357/oh-my-pi/issues/1610)).
@@ -403,78 +220,105 @@
 - Deferred eager live scrollback rebuilds on macOS Terminal.app and iTerm2 so assistant/tool streaming no longer emits ED3 (`CSI 3 J`) while their native viewport position is unobservable, preserving readers scrolled into terminal history ([#1300](https://github.com/can1357/oh-my-pi/issues/1300)).
 - Fixed width-shrink reflow leaving old-width rows in native history so later appends no longer undercount scrollback growth or duplicate wrapped content.
 - Fixed hiding overlays after terminal reflow so stale dialog rows are scrubbed from native scrollback on non-multiplexer terminals.
+- Deferred eager live scrollback rebuilds on VTE terminals so GNOME-style Linux terminals do not flash or erase readable scrollback during streaming ([#1719](https://github.com/can1357/oh-my-pi/issues/1719)).
+- Deferred eager live scrollback rebuilds on POSIX terminals where xterm ED3 (`CSI 3 J`, erase saved lines) can disturb scrolled-up readers during streaming, while keeping direct user-input and checkpoint rebuilds explicit ([#1682](https://github.com/can1357/oh-my-pi/issues/1682)).
+- Fixed TUI shutdown placing the parent shell prompt one row below short rendered content instead of directly on the next line ([#1620](https://github.com/can1357/oh-my-pi/issues/1620)).
+- Stopped painting inline color swatches for 4-digit hex runs in Markdown rendering. The `#RGBA` CSS form collides with hashline `#TAG` snapshot tags (4 hex digits, e.g. `#6C5E`), which were sprouting spurious RGB swatches in prose and codespans. Only `#RGB`, `#RRGGBB`, and `#RRGGBBAA` qualify now.
+- Fixed native Windows + Windows Terminal freezing the editor on the wrap keystroke, on `/plan`/`/resume`/model-switch/status-line toggles, and on any other offscreen structural mutation until the next prompt submit. The `15.7.5` `#1635` fix routed every viewport-saturating pure-append and structural mutation through `deferredMutation` (a literal no-op) whenever `isNativeViewportAtBottom()` returned `undefined` — which it always does under `WT_SESSION` because the kernel32 probe can't see WT host scrollback. The deferral was only ever meant for the *confirmed-scrolled* case; an unknown viewport now falls back to a non-destructive `viewportRepaint` instead, so the live UI keeps updating without emitting `\x1b[3J` and without yanking a possibly-scrolled reader. Confirmed-scrolled frames (probe returns `false`) still defer.
+- Removed the hard-coded 20-result cap on `@`-prefixed fuzzy file completion in `CombinedAutocompleteProvider.#getFuzzyFileSuggestions`. The dropdown now honors the existing `maxResults: 100` ceiling already configured for `fuzzyFind`, so projects with many files sharing a common stem (e.g. `@controller`, `@test`) surface all relevant matches instead of being silently truncated. ([#1652](https://github.com/can1357/oh-my-pi/issues/1652))
+- Fixed native Windows + Windows Terminal scrollback being yanked to the top when a streaming response triggered a TUI full redraw. Under ConPTY the `kernel32` `GetConsoleScreenBufferInfo` probe answers about the pseudo-console (always at the buffer tail) and not about WT's host scrollback, so `isNativeViewportAtBottom()` falsely returned `true` while the user was scrolled up and the shrink-across-viewport branch issued a destructive `historyRebuild` (`\x1b[2J\x1b[H\x1b[3J`). The probe now short-circuits to `undefined` whenever `WT_SESSION` is set, letting the existing deferred-rebuild path keep streaming-time mutations non-destructive and reconcile native history at the next prompt-submit checkpoint. ([#1635](https://github.com/can1357/oh-my-pi/issues/1635))
+- Preserved hidden tmux overlays in the live viewport by removing overlay content from view when an overlay was hidden while keeping pane history intact
+- Preserved native scrollback when forced TUI renders coalesce with content growth, and deferred pure tail appends while readers are scrolled into history.
+- Preserved existing terminal scrollback during forced and structural TUI renders so preexisting shell lines remained visible after component mutations
+- Rebuilt native scrollback for safe bottom-anchored offscreen edits and high-water preview collapses instead of repainting only the viewport, preventing stale or duplicated rows above the live viewport.
+- Stripped internal cursor marker sentinels from all rendered lines so offscreen focus markers no longer leak into terminal output
+- Truncated all painted lines to terminal width during viewport repaints and append-tail updates so long content no longer overflows or wraps unexpectedly
+- Fixed `tui.select.cancel` handling in `SelectList` so pressing Escape or Ctrl+C closes the list even when no matches are currently shown
+- Fixed native scrollback corruption when an offscreen row edit and repeated-tail append land in one render frame; ambiguous appended tails now rebuild history instead of splicing stale rows into the buffer.
+- Fixed scrolled-up readers being yanked back to the tail whenever streaming content arrived on POSIX terminals (macOS/Linux). Native viewport position is unobservable there (`isNativeViewportAtBottom()` returns `undefined`), and the planner optimistically treated "unknown" as "at bottom", so every offscreen streaming edit ran a destructive `historyRebuild` that cleared scrollback and snapped the view to the bottom. Live render frames now treat an unknown viewport as unsafe for a destructive rebuild — they defer to a non-destructive viewport repaint and reconcile native scrollback at the next explicit checkpoint (prompt submit). Resize and checkpoint replays keep the prior behavior.
+- Fixed native scrollback not rewrapping when the terminal widens on POSIX. A width increase reflows the transcript to fewer lines, which the shrink-across-boundary branch intercepted and (after the unknown-viewport deferral) repainted only the viewport — leaving committed history wrapped at the old width and duplicated above the live viewport. Width changes now rebuild native scrollback at the new geometry even when the viewport position is unknown (a yank is acceptable on an explicit resize); a terminal that can report a scrolled viewport still defers.
+- Fixed slash-command autocomplete repainting when a Windows Terminal session cannot report native scrollback position; live input renders can now bypass the unknown-viewport deferral without weakening background scrollback protection. ([#1550](https://github.com/can1357/oh-my-pi/issues/1550))
+- Fixed streaming output staying invisible in Windows Terminal + WSL2 until the window was minimized + restored. The 15.5.14 WSL branch of `requiresNativeViewportProofForReplay` treated an unknown native viewport state as "scrolled into history" — but `ProcessTerminal.isNativeViewportAtBottom` can only return a real answer through `kernel32.dll` FFI, which a Linux user-space process inside WSL cannot load, so the probe was permanently `undefined`. Every row-inserting structural mutation (each new streaming token row above the bottom-anchored prompt) was therefore classified as `deferredMutation` and emitted zero bytes. Any geometry change (resize/minimize/restore) bypassed the gate via a different render intent, which is why the output became visible only on window resize. The WSL clause is removed; on platforms where the probe cannot answer, unknown is treated as at-bottom (the pre-15.5.14 behaviour) so the live render path runs again. Native Win32 keeps the conservative "assume scrolled when unknown" heuristic since `kernel32` FFI does succeed there and unknown means the probe transiently failed. ([#1534](https://github.com/can1357/oh-my-pi/issues/1534))
 
 ### Removed
 
+- Removed the probe/defer API surface: `TUI.setEagerNativeScrollbackRebuild()`, `TUI.refreshNativeScrollbackIfDirty()`, `TUI.setClearOnShrink()`/`getClearOnShrink()`, `RenderRequestOptions.allowUnknownViewportMutation`, `NativeScrollbackRefreshOptions`, `Terminal.isNativeViewportAtBottom()`, `Terminal.hasEagerEraseScrollbackRisk()`, and the `eagerEraseScrollbackRisk`/`submitPinsViewportToTail` capability fields with their detectors.
+- Removed the `PI_TUI_ED3_SAFE`, `PI_CLEAR_ON_SHRINK`, and `PI_TUI_DEBUG` environment variables (the levers they tuned no longer exist; `PI_DEBUG_REDRAW` now logs the commit-ledger state per frame).
 - Removed `shouldTrustNativeViewportProbe` and `ProcessTerminal`'s kernel32 `GetConsoleScreenBufferInfo` viewport probe. No Windows environment can answer "is the user's viewport at the bottom" truthfully — under ConPTY (every modern host) the pseudo-console buffer is pinned to the visible grid so the probe always read "at bottom", and under legacy conhost the window tracks the output cursor rather than the buffer tail so it always read "scrolled up" — so the probe and its trust gate are gone; `ProcessTerminal` no longer implements the optional `Terminal.isNativeViewportAtBottom`.
 
-## [15.8.1] - 2026-06-02
+## [15.13.0] - 2026-06-14
 
-### Fixed
+## [15.12.6] - 2026-06-14
 
-- Deferred eager live scrollback rebuilds on VTE terminals so GNOME-style Linux terminals do not flash or erase readable scrollback during streaming ([#1719](https://github.com/can1357/oh-my-pi/issues/1719)).
+## [15.12.5] - 2026-06-13
 
-## [15.8.0] - 2026-06-02
+## [15.12.4] - 2026-06-13
 
-### Fixed
+## [15.11.8] - 2026-06-12
 
-- Deferred eager live scrollback rebuilds on POSIX terminals where xterm ED3 (`CSI 3 J`, erase saved lines) can disturb scrolled-up readers during streaming, while keeping direct user-input and checkpoint rebuilds explicit ([#1682](https://github.com/can1357/oh-my-pi/issues/1682)).
-- Fixed TUI shutdown placing the parent shell prompt one row below short rendered content instead of directly on the next line ([#1620](https://github.com/can1357/oh-my-pi/issues/1620)).
-- Stopped painting inline color swatches for 4-digit hex runs in Markdown rendering. The `#RGBA` CSS form collides with hashline `#TAG` snapshot tags (4 hex digits, e.g. `#6C5E`), which were sprouting spurious RGB swatches in prose and codespans. Only `#RGB`, `#RRGGBB`, and `#RRGGBBAA` qualify now.
+## [15.11.5] - 2026-06-12
 
-## [15.7.6] - 2026-06-01
+## [15.11.4] - 2026-06-12
 
-### Fixed
+## [15.11.3] - 2026-06-11
 
-- Fixed native Windows + Windows Terminal freezing the editor on the wrap keystroke, on `/plan`/`/resume`/model-switch/status-line toggles, and on any other offscreen structural mutation until the next prompt submit. The `15.7.5` `#1635` fix routed every viewport-saturating pure-append and structural mutation through `deferredMutation` (a literal no-op) whenever `isNativeViewportAtBottom()` returned `undefined` — which it always does under `WT_SESSION` because the kernel32 probe can't see WT host scrollback. The deferral was only ever meant for the *confirmed-scrolled* case; an unknown viewport now falls back to a non-destructive `viewportRepaint` instead, so the live UI keeps updating without emitting `\x1b[3J` and without yanking a possibly-scrolled reader. Confirmed-scrolled frames (probe returns `false`) still defer.
-- Removed the hard-coded 20-result cap on `@`-prefixed fuzzy file completion in `CombinedAutocompleteProvider.#getFuzzyFileSuggestions`. The dropdown now honors the existing `maxResults: 100` ceiling already configured for `fuzzyFind`, so projects with many files sharing a common stem (e.g. `@controller`, `@test`) surface all relevant matches instead of being silently truncated. ([#1652](https://github.com/can1357/oh-my-pi/issues/1652))
+## [15.11.2] - 2026-06-11
 
-## [15.7.5] - 2026-06-01
+## [15.11.1] - 2026-06-11
 
-### Fixed
+## [15.11.0] - 2026-06-10
 
-- Fixed native Windows + Windows Terminal scrollback being yanked to the top when a streaming response triggered a TUI full redraw. Under ConPTY the `kernel32` `GetConsoleScreenBufferInfo` probe answers about the pseudo-console (always at the buffer tail) and not about WT's host scrollback, so `isNativeViewportAtBottom()` falsely returned `true` while the user was scrolled up and the shrink-across-viewport branch issued a destructive `historyRebuild` (`\x1b[2J\x1b[H\x1b[3J`). The probe now short-circuits to `undefined` whenever `WT_SESSION` is set, letting the existing deferred-rebuild path keep streaming-time mutations non-destructive and reconcile native history at the next prompt-submit checkpoint. ([#1635](https://github.com/can1357/oh-my-pi/issues/1635))
+## [15.10.11] - 2026-06-10
 
-## [15.7.3] - 2026-05-31
+## [15.10.9] - 2026-06-09
 
-### Added
+## [15.10.8] - 2026-06-09
 
-- Added `overflowSearch` to `SelectListLayoutOptions` to let consumers enable or disable type-to-filter search and search-status rendering per SelectList instance
-- Added fuzzy type-to-filter search to overflowing `SelectList` pickers, with search status and result counts.
-- Added `TUI.setEagerNativeScrollbackRebuild(enabled)` — while enabled, live render frames rebuild native scrollback on offscreen/structural changes even when the viewport position is unobservable (POSIX), instead of deferring to a non-destructive repaint. Trades the anti-yank guarantee for clean, duplicate-free history; intended for windows where output above the fold is actively re-laying out (e.g. a tool whose result is still streaming). A terminal that reports a known-scrolled viewport still defers.
+## [15.10.6] - 2026-06-08
 
-### Changed
+## [15.10.5] - 2026-06-08
 
-- Disabled interactive search filtering for editor autocomplete and slash-command `SelectList`s by passing `overflowSearch: false` in their layout options
+## [15.10.4] - 2026-06-08
 
-### Fixed
+## [15.10.3] - 2026-06-08
 
-- Preserved hidden tmux overlays in the live viewport by removing overlay content from view when an overlay was hidden while keeping pane history intact
-- Preserved native scrollback when forced TUI renders coalesce with content growth, and deferred pure tail appends while readers are scrolled into history.
-- Preserved existing terminal scrollback during forced and structural TUI renders so preexisting shell lines remained visible after component mutations
-- Rebuilt native scrollback for safe bottom-anchored offscreen edits and high-water preview collapses instead of repainting only the viewport, preventing stale or duplicated rows above the live viewport.
-- Stripped internal cursor marker sentinels from all rendered lines so offscreen focus markers no longer leak into terminal output
-- Truncated all painted lines to terminal width during viewport repaints and append-tail updates so long content no longer overflows or wraps unexpectedly
-- Fixed `tui.select.cancel` handling in `SelectList` so pressing Escape or Ctrl+C closes the list even when no matches are currently shown
-- Fixed native scrollback corruption when an offscreen row edit and repeated-tail append land in one render frame; ambiguous appended tails now rebuild history instead of splicing stale rows into the buffer.
-- Fixed scrolled-up readers being yanked back to the tail whenever streaming content arrived on POSIX terminals (macOS/Linux). Native viewport position is unobservable there (`isNativeViewportAtBottom()` returns `undefined`), and the planner optimistically treated "unknown" as "at bottom", so every offscreen streaming edit ran a destructive `historyRebuild` that cleared scrollback and snapped the view to the bottom. Live render frames now treat an unknown viewport as unsafe for a destructive rebuild — they defer to a non-destructive viewport repaint and reconcile native scrollback at the next explicit checkpoint (prompt submit). Resize and checkpoint replays keep the prior behavior.
-- Fixed native scrollback not rewrapping when the terminal widens on POSIX. A width increase reflows the transcript to fewer lines, which the shrink-across-boundary branch intercepted and (after the unknown-viewport deferral) repainted only the viewport — leaving committed history wrapped at the old width and duplicated above the live viewport. Width changes now rebuild native scrollback at the new geometry even when the viewport position is unknown (a yank is acceptable on an explicit resize); a terminal that can report a scrolled viewport still defers.
+## [15.10.2] - 2026-06-08
 
-## [15.7.0] - 2026-05-31
+## [15.10.1] - 2026-06-07
 
-### Fixed
+## [15.10.0] - 2026-06-06
 
-- Fixed slash-command autocomplete repainting when a Windows Terminal session cannot report native scrollback position; live input renders can now bypass the unknown-viewport deferral without weakening background scrollback protection. ([#1550](https://github.com/can1357/oh-my-pi/issues/1550))
+## [15.9.69] - 2026-06-06
 
-## [15.6.0] - 2026-05-30
+## [15.9.67] - 2026-06-06
 
-### Added
+## [15.9.5] - 2026-06-05
 
-- Added autocomplete triggering for internal URL scheme tokens such as `local://` and `skill://` while typing in the editor
+## [15.9.4] - 2026-06-05
 
-### Fixed
+## [15.9.3] - 2026-06-05
 
-- Fixed streaming output staying invisible in Windows Terminal + WSL2 until the window was minimized + restored. The 15.5.14 WSL branch of `requiresNativeViewportProofForReplay` treated an unknown native viewport state as "scrolled into history" — but `ProcessTerminal.isNativeViewportAtBottom` can only return a real answer through `kernel32.dll` FFI, which a Linux user-space process inside WSL cannot load, so the probe was permanently `undefined`. Every row-inserting structural mutation (each new streaming token row above the bottom-anchored prompt) was therefore classified as `deferredMutation` and emitted zero bytes. Any geometry change (resize/minimize/restore) bypassed the gate via a different render intent, which is why the output became visible only on window resize. The WSL clause is removed; on platforms where the probe cannot answer, unknown is treated as at-bottom (the pre-15.5.14 behaviour) so the live render path runs again. Native Win32 keeps the conservative "assume scrolled when unknown" heuristic since `kernel32` FFI does succeed there and unknown means the probe transiently failed. ([#1534](https://github.com/can1357/oh-my-pi/issues/1534))
+## [15.9.2] - 2026-06-05
+
+## [15.9.1] - 2026-06-04
+
+## [15.9.0] - 2026-06-04
+
+## [15.8.2] - 2026-06-03
+
+## [15.8.1] - 2026-06-02
+
+## [15.8.0] - 2026-06-02
+
+## [15.7.6] - 2026-06-01
+
+## [15.7.5] - 2026-06-01
+
+## [15.7.3] - 2026-05-31
+
+## [15.7.0] - 2026-05-31
+
+## [15.6.0] - 2026-05-30
 
 ## [15.5.14] - 2026-05-29