merge v1.11-compaction

- compaction.ts: usable/isOverflow/estimate/turns/select/buildPrompt/process
- compaction-prompt.ts: SUMMARY_TEMPLATE verbatim from opencode
- schema: messages.{compacted_at,summary,tail_start_id} + chats.needs_compaction
- inference: auto-trigger on overflow, pre-fetch compaction before next turn
- /compact slash command rewired to new path
- WS: chat_status working/idle around compaction + compacted frame
- frontend: SummaryCard + sonner toast on compacted
- 24 unit tests for pure functions

CLAUDE.md

@@ -6,6 +6,8 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 Self-hosted single-user developer chat app. AI assistant with read-only file tools (view_file, list_dir, grep, find_files) running against a local llama-swap inference server. Sessions organized by project, with a multi-pane workspace (chat + file browser side by side).
 
+Plus `apps/booterm` (second container, port 9501, bookworm-slim+glibc): Fastify + node-pty + tmux. Browser terminal panes WS to `/ws/term/sessions/:sid/panes/:pid`; per-session tmux session `bc-<sid>`, per-pane window `term-<pid>`. Shells drop privs to samkintop via `gosu` in `tmux.conf` default-command.
+
 ## Commands
 
 ```bash
@@ -35,7 +37,7 @@ Tests: `pnpm -C apps/server test` runs 23 vitest tests. No test harness on `apps
 
 ## Architecture
 
-**Monorepo**: pnpm workspaces with `apps/server` (Fastify + postgres) and `apps/web` (React + Vite).
+**Monorepo**: pnpm workspaces with `apps/server` (Fastify + postgres), `apps/web` (React + Vite), and `apps/booterm` (Fastify + node-pty + tmux).
 
 ### Server (`apps/server/src/`)
 
@@ -66,6 +68,13 @@ Key patterns:
 - **`hooks/useSidebar.ts`** — Module-singleton with Set<setState> subscriber pattern; one bus subscription guarded by `globalThis.__boocode_sidebar_subscribed` for HMR safety. Every new `SessionEvent` type needs a `case` in the `applyEvent` switch (no-op `return prev` is fine).
 - **`api/client.ts`** — Centralized typed fetch wrapper. All endpoints under `api.*` namespace.
 
+Font / CSS pipeline (apps/web):
+- Tailwind v4's `@import "tailwindcss"` directive strips font URLs from subsequent CSS `@import`s — `@fontsource*` packages must be imported as JS side-effect modules in `apps/web/src/main.tsx`, not via `@import` in `globals.css`. Otherwise the woff2 files never make it to `dist/`.
+- Lightning CSS (inside `@tailwindcss/postcss` v4) collapses contiguous unicode-ranges to wildcard shorthand (`U+0000-FFFF` → `U+????`), which iOS Safari/Vivaldi mishandles (silently drops the font from those codepoints). Use explicit non-wildcard-collapsible subranges (e.g. `U+2500-259F` not `U+2500-25FF`). The `apps/web` build script greps `dist/assets/*.css` for `U+2500-259F` and fails the build if missing — preserve that guard.
+- `@font-face` blocks must live AFTER all `@import` statements (CSS spec). Earlier placement silently breaks every subsequent `@import` (this broke the 18 theme palette imports in globals.css for one session).
+- JetBrainsMono Nerd Font self-hosted in `apps/web/src/fonts/` (TTF from ryanoasis/nerd-fonts release) — needed because `@fontsource-variable/jetbrains-mono` ships subsetted woff2s that don't cover `U+2500-259F` (box drawing + block elements, used by opencode's banner). "NL" = No Ligatures (matches `font-feature-settings: "liga" 0`); "Mono" = single-cell icon width so TUI layouts don't desync.
+- xterm-addon-webgl rasterizes glyphs via Canvas2D into a GPU texture atlas. Canvas2D does NOT honor `font-display: block` — it uses whatever font is currently registered. Gate xterm initialization on `document.fonts.load(<font-name>)` resolving before calling `term.open()` (see `fontsReady` useState in `TerminalPane.tsx`). iOS Safari/Vivaldi also reclaims WebGL contexts from backgrounded tabs: keep `webgl.onContextLoss(() => webgl.dispose())` + recreate via visibilitychange. Do NOT manually dispose+recreate the addon after font load — iOS silently fails the second GL context creation and the terminal drops to DOM renderer with stale metrics.
+
 ### Data flow for chat
 
 1. User sends message → POST `/api/sessions/:id/messages` creates user + assistant (status=streaming) rows
@@ -99,6 +108,12 @@ Required: `DATABASE_URL`, `LLAMA_SWAP_URL`. Optional: `PORT` (3000), `HOST` (0.0
 - Don't accumulate `.bak-*` files. Clean them up in the same batch or immediately after merge.
 - Fastify global JSON parser tolerates empty bodies (overridden in `index.ts`); bodyless POSTs (archive, unarchive, stop) work without setting `Content-Type` tricks on the client.
 - Event dedup discipline: for any mutation the server publishes via `broker.publishUser`, do NOT add a local `sessionEvents.emit(...)` after the API call — `useUserEvents` forwards the WS frame onto the bus. Frontend mutation handlers must be idempotent (dedup by id, no-op on already-present).
+- `node:20-*` base images ship a `node` user at uid/gid 1000 — delete it (`userdel`/`groupdel` on debian, `deluser`/`delgroup` on alpine) before adding samkintop at 1000.
+- node-pty's compiled `.node` is libc-specific: proddeps and runtime Dockerfile stages must share libc (alpine↔musl or bookworm-slim↔glibc); the TS-only builder stage can stay alpine for speed.
+- pnpm 10 `--frozen-lockfile` skips node-pty's postinstall — the Docker proddeps stage runs `cd node_modules/node-pty && npm run install` to force the native compile.
+- A local PreToolUse hook (`security_reminder_hook.py`) regex-flags Node's older `child_process` spawn helpers as unsafe (false positive even on the File-suffixed variant). Use `spawn` — it's accepted.
+- `/opt/boolab` hosts a working sibling BooCode terminal at `boocode.indifferentketchup.com`. Useful for visual side-by-side comparison on the same iPhone when debugging booterm rendering. Boolab uses Tailwind v3 (`@tailwind base`); boocode uses v4 — many subtle build differences. Don't assume parity.
+- booterm SSHs to the host as `samkintop@100.114.205.53` (the Tailscale IP). The hostname `ubuntu-homelab` (shown in the bash prompt after login) does NOT resolve from inside the container — only the host's `/etc/hosts` knows it. Override via `BOOTERM_SSH_HOST` / `BOOTERM_SSH_USER` env vars in docker-compose if you ever move the shell to a different machine.
 
 ## Conventions
 
@@ -109,3 +124,7 @@ Required: `DATABASE_URL`, `LLAMA_SWAP_URL`. Optional: `PORT` (3000), `HOST` (0.0
 - Discriminated unions for type narrowing: `Pane` (by `kind`), `SessionEvent` (by `type`), `InferenceFrame` (by `type`).
 - shadcn primitives live in `components/ui/`. Don't modify them unless adding a new primitive.
 - `inferLanguage()` from `lib/attachments.ts` is the canonical file-extension-to-language map. `CodeBlock.tsx` keeps its own `LANG_MAP` because it also resolves markdown fence names.
+- Two UI event buses: `hooks/sessionEvents.ts` for DB-state events (chat_created, session_updated); `lib/events.ts` for ephemeral UI (`sendToTerminal`, `terminalsRegistry`). Don't merge — different subscriber lifecycles.
+- `vite.config.ts` proxy entries are order-sensitive: more-specific prefixes (`/api/term`, `/ws/term`) must come BEFORE `/api`.
+- Mobile pane URL sync (`Session.tsx`): the `?pane=<id>` effect resets `activePaneIdx` whenever `panes` changes. New-pane creation on mobile must push `?pane=` atomically — `addPaneAndSwitch` is the wrapper that does this. `addSplitPane` returns the new pane id for callers.
+- xterm.js v5 uses canvas rendering — browser doesn't see xterm's selection; the native right-click menu has no working Copy for terminal text. App keybindings (`Cmd/Ctrl-C`, `Cmd/Ctrl-Shift-C`) are the path.

apps/booterm/Dockerfile

@@ -15,28 +15,48 @@ COPY apps/booterm ./apps/booterm
 RUN pnpm --filter=@boocode/booterm build
 
 # ---- Prod-deps stage: hoisted, native built via npm rebuild ----
-FROM node:20-alpine AS proddeps
+# v1.10.2: switched to bookworm-slim (glibc) so node-pty's native .node is
+# compiled against the same libc as the runtime stage. A musl-built .node
+# won't dlopen in a glibc node binary, so both stages must match.
+FROM node:20-bookworm-slim AS proddeps
 ENV COREPACK_DEFAULT_TO_LATEST=0
 RUN corepack enable && corepack prepare pnpm@10.15.1 --activate
-RUN apk add --no-cache python3 make g++
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3 make g++ ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
 WORKDIR /prod
 COPY apps/booterm/package.json ./package.json
 RUN pnpm install --prod --config.node-linker=hoisted --config.strict-peer-dependencies=false
 # pnpm 10 ignores build scripts; force compile with npm directly.
-# node-gyp is bundled with npm in the node:20-alpine image.
+# node-gyp is bundled with npm in the node:20-bookworm-slim image.
 RUN cd node_modules/node-pty && npm run install
 # Sanity check — fail the build if the artifact still isn't there
 RUN test -f node_modules/node-pty/build/Release/pty.node && echo "pty.node OK" || (echo "pty.node MISSING" && exit 1)
 
 # ---- Runtime ----
-FROM node:20-alpine AS runtime
-RUN apk add --no-cache tmux libstdc++ bash su-exec shadow
-# v1.10.1: terminal shells inside tmux drop privs to samkintop via su-exec.
+# v1.10.2: switched from node:20-alpine (musl) to node:20-bookworm-slim (glibc)
+# so glibc-linked binaries from /home/samkintop (Claude Code, opencode, the
+# host's nvm node) run inside the container when invoked from the terminal
+# pane. Side-effect: su-exec is alpine-only — Debian replacement is gosu.
+FROM node:20-bookworm-slim AS runtime
+# v1.10.8d: openssh-client added so the terminal can ssh -t samkintop@host
+# (matching boolab's pattern) — that's how the in-pane shell gets access to
+# host tools (docker, claude, opencode) that don't exist inside the container.
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    tmux bash gosu ca-certificates procps openssh-client \
+    && rm -rf /var/lib/apt/lists/*
 # Mirror uid/gid 1000:1000 from the host so the bind-mounted /home/samkintop
 # (added in docker-compose) is owned by the user from the container's view.
-RUN deluser --remove-home node 2>/dev/null; delgroup node 2>/dev/null; \
-    addgroup -g 1000 samkintop && \
-    adduser -D -u 1000 -G samkintop -s /bin/bash samkintop
+# bookworm-slim ships a `node` user at 1000 — wipe whatever sits on uid/gid
+# 1000 first, then create samkintop fresh.
+RUN if id -u 1000 >/dev/null 2>&1; then \
+        userdel -r "$(id -un 1000)" 2>/dev/null || true; \
+    fi; \
+    if getent group 1000 >/dev/null 2>&1; then \
+        groupdel "$(getent group 1000 | cut -d: -f1)" 2>/dev/null || true; \
+    fi; \
+    groupadd -g 1000 samkintop && \
+    useradd -m -u 1000 -g 1000 -s /bin/bash samkintop
 WORKDIR /app
 COPY --from=builder /build/apps/booterm/dist ./dist
 COPY --from=proddeps /prod/package.json ./package.json

apps/booterm/src/pty/manager.ts

@@ -1,7 +1,6 @@
 import { spawn } from 'node:child_process';
 import type { FastifyBaseLogger } from 'fastify';
 
-// UUIDs already match [0-9a-f-]; allow uppercase and longer just in case.
 const ID_RE = /^[a-zA-Z0-9_-]{1,64}$/;
 
 export function sanitizeId(raw: string): string | null {
@@ -9,12 +8,15 @@ export function sanitizeId(raw: string): string | null {
   return raw.toLowerCase();
 }
 
-export function tmuxSessionName(sessionId: string): string {
-  return `bc-${sessionId}`;
-}
-
-export function tmuxWindowName(paneId: string): string {
-  return `term-${paneId}`;
+// v1.10.8c: per-pane tmux sessions (boolab pattern). Previously booterm used
+// one tmux session per chat-session with one window per pane; that meant the
+// session-level window-size policy was shared across panes, and
+// `attach-session -d` (used to take over from a stale browser) would detach
+// every other pane attached to the same session — the "[detached]" bug.
+// Now each pane gets its own tmux session named `bc-<paneId>`. The bc- prefix
+// namespaces booterm sessions on the shared tmux server.
+export function tmuxSessionName(paneId: string): string {
+  return `bc-${paneId}`;
 }
 
 interface CmdResult {
@@ -23,15 +25,17 @@ interface CmdResult {
   code: number;
 }
 
-// Wrap child_process.spawn with shell:false so each argv element is passed
-// as a separate argument — no shell interpolation, no injection surface.
 function runTmux(tmuxConfPath: string, args: string[]): Promise<CmdResult> {
   return new Promise((resolve) => {
     const child = spawn('tmux', ['-f', tmuxConfPath, ...args], { shell: false });
     let stdout = '';
     let stderr = '';
-    child.stdout.on('data', (chunk: Buffer) => { stdout += chunk.toString('utf8'); });
-    child.stderr.on('data', (chunk: Buffer) => { stderr += chunk.toString('utf8'); });
+    child.stdout.on('data', (chunk: Buffer) => {
+      stdout += chunk.toString('utf8');
+    });
+    child.stderr.on('data', (chunk: Buffer) => {
+      stderr += chunk.toString('utf8');
+    });
     child.on('error', (err) => {
       resolve({ stdout, stderr: stderr + String(err), code: 1 });
     });
@@ -46,57 +50,115 @@ export async function hasSession(tmuxConfPath: string, sessionName: string): Pro
   return res.code === 0;
 }
 
-export async function listWindows(tmuxConfPath: string, sessionName: string): Promise<string[]> {
-  const res = await runTmux(tmuxConfPath, ['list-windows', '-t', sessionName, '-F', '#{window_name}']);
-  if (res.code !== 0) return [];
-  return res.stdout.trim().split('\n').filter(Boolean);
+// Default fallback size — wider than any real terminal would care about; the
+// real client size lands via the WS resize frame within a few ms of attach.
+const DEFAULT_COLS = 200;
+const DEFAULT_ROWS = 50;
+
+// v1.10.8d: per-pane shell is `ssh -t samkintop@SSH_HOST` (matches boolab's
+// pattern). The container has no docker / claude / opencode binaries; SSH'ing
+// to the host gives the user their full normal shell environment. Default is
+// the host's Tailscale IP (100.114.205.53) — the hostname `ubuntu-homelab`
+// only resolves on the host's local /etc/hosts, not from inside containers,
+// so SSH'ing to the hostname fails with `Could not resolve hostname` even
+// though the host machine is reachable. Boolab uses the same IP.
+const SSH_HOST = process.env['BOOTERM_SSH_HOST']?.trim() || '100.114.205.53';
+const SSH_USER = process.env['BOOTERM_SSH_USER']?.trim() || 'samkintop';
+
+// POSIX shell single-quote escape: wrap in '…', escape embedded singles by
+// closing-the-quote, inserting an escaped quote, and re-opening.
+function shellEscape(s: string): string {
+  return `'${s.replace(/'/g, `'\\''`)}'`;
 }
 
-export async function killWindow(
+// Idempotent. Creates the tmux session if it doesn't exist, sized via -x/-y
+// from the client's measured xterm dimensions. With `window-size = largest`
+// + `aggressive-resize on` in tmux.conf, the attached client's actual size
+// wins once it reports in — but seeding at the right size avoids the brief
+// window where bash/TUI inherits the default 80x24 from a stale fallback.
+export async function ensureSession(
   tmuxConfPath: string,
   sessionName: string,
-  windowName: string,
-): Promise<boolean> {
-  const res = await runTmux(tmuxConfPath, ['kill-window', '-t', `${sessionName}:${windowName}`]);
-  return res.code === 0;
-}
-
-// Idempotent. Creates the tmux session if it doesn't exist, then ensures the
-// named window is present. The session's initial window is created with the
-// target name (via `-n`) so we don't need a separate rename step.
-export async function ensureWindow(
-  tmuxConfPath: string,
-  sessionName: string,
-  windowName: string,
   projectRoot: string,
   log: FastifyBaseLogger,
+  cols?: number,
+  rows?: number,
 ): Promise<void> {
-  if (!(await hasSession(tmuxConfPath, sessionName))) {
-    log.info({ sessionName, windowName, projectRoot }, 'creating tmux session');
-    const res = await runTmux(tmuxConfPath, [
+  if (await hasSession(tmuxConfPath, sessionName)) return;
+  const sizeCols = cols && cols > 0 ? Math.floor(cols) : DEFAULT_COLS;
+  const sizeRows = rows && rows > 0 ? Math.floor(rows) : DEFAULT_ROWS;
+  // Bypass tmux.conf's default-command — build the per-pane argv explicitly
+  // so we can wrap ssh in the gosu privilege drop. The remote shell sequence
+  // (per boolab's invariants in services/tmux_session.py target_cmd_for):
+  //   1. ssh's argv must flatten into a single quoted bash -lc <script>
+  //   2. -l on the outer bash sources ~/.profile on the remote (PATH etc.)
+  //   3. cd to projectRoot, then exec bash -l so the user lands in the repo
+  // /opt is bind-mounted host↔container, so projectRoot resolves to the
+  // same files on both sides.
+  const remoteScript = `cd ${shellEscape(projectRoot)} && exec bash -l`;
+  const remoteCmd = `bash -lc ${shellEscape(remoteScript)}`;
+  const argv = [
     'new-session', '-d',
     '-s', sessionName,
-      '-n', windowName,
     '-c', projectRoot,
-    ]);
+    '-x', String(sizeCols),
+    '-y', String(sizeRows),
+    '--',
+    // gosu drops privs from the container's root (tmux server runs as root)
+    // to samkintop:samkintop. env restores HOME/USER/SHELL so ssh finds the
+    // right ~/.ssh/id_ed25519 (key is mode 0600 and ssh refuses keys whose
+    // UID doesn't match the running user — both are 1000 here).
+    'gosu', 'samkintop:samkintop',
+    'env', 'HOME=/home/samkintop', 'USER=samkintop', 'SHELL=/bin/bash',
+    'ssh', '-t',
+    '-o', 'StrictHostKeyChecking=yes',
+    '-o', 'ServerAliveInterval=30',
+    '-o', 'ServerAliveCountMax=3',
+    `${SSH_USER}@${SSH_HOST}`,
+    remoteCmd,
+  ];
+  log.info(
+    { sessionName, projectRoot, cols: sizeCols, rows: sizeRows, sshTarget: `${SSH_USER}@${SSH_HOST}` },
+    'creating tmux session (ssh to host)',
+  );
+  const res = await runTmux(tmuxConfPath, argv);
   if (res.code !== 0) {
     log.error({ res }, 'tmux new-session failed');
     throw new Error(`tmux new-session failed: ${res.stderr}`);
   }
-    return;
-  }
-
-  const windows = await listWindows(tmuxConfPath, sessionName);
-  if (windows.includes(windowName)) return;
-
-  const res = await runTmux(tmuxConfPath, [
-    'new-window',
-    '-t', sessionName,
-    '-n', windowName,
-    '-c', projectRoot,
-  ]);
-  if (res.code !== 0) {
-    log.error({ res }, 'tmux new-window failed');
-    throw new Error(`tmux new-window failed: ${res.stderr}`);
-  }
+}
+
+export async function killSession(
+  tmuxConfPath: string,
+  sessionName: string,
+): Promise<boolean> {
+  const res = await runTmux(tmuxConfPath, ['kill-session', '-t', sessionName]);
+  return res.code === 0;
+}
+
+// v1.10.8c: capture-pane on WS attach to replay the buffer state to the fresh
+// xterm (boolab pattern). `-e` preserves ANSI escape sequences so colours and
+// cursor position survive the replay. Returns empty string on failure — the
+// client falls back to whatever tmux itself decides to repaint, which is
+// non-fatal but visually noisier.
+//
+// v1.10.8d: strip trailing blank rows. tmux capture-pane emits one `\n` per
+// pane row (including all the empty rows below the actual content), so on a
+// fresh 35-row pane with just the bash prompt at row 0, the output is
+// `<prompt>` followed by 35 `\n` bytes. When xterm.write()s those naively,
+// the cursor advances row-by-row until it hits the bottom of the canvas and
+// scrolls — pushing the prompt into the scrollback buffer where the user
+// can't see it. Stripping the trailing newlines leaves xterm's cursor at the
+// natural end of the rendered content (matching tmux's actual cursor
+// position for the common single-line-prompt case).
+export async function capturePane(
+  tmuxConfPath: string,
+  sessionName: string,
+  lines: number = 2000,
+): Promise<string> {
+  const res = await runTmux(tmuxConfPath, [
+    'capture-pane', '-t', sessionName, '-p', '-e', '-S', `-${lines}`,
+  ]);
+  if (res.code !== 0) return '';
+  return res.stdout.replace(/(?:\r?\n)+$/, '');
 }

apps/booterm/src/pty/pty.ts

@@ -3,7 +3,6 @@ import type { IPty } from 'node-pty';
 
 export interface AttachPtyOptions {
   sessionName: string;
-  windowName: string;
   projectRoot: string;
   cols: number;
   rows: number;
@@ -19,16 +18,24 @@ function cleanEnv(): { [key: string]: string } {
   return out;
 }
 
-// Spawns a tmux client attached to the given session+window. `-d` detaches any
-// other client so a browser refresh takes over the same window without
-// duplicate input. tmux server (and the window) persists across PTY exits.
+// v1.10.8c: no `-d` (multi-attach friendly — boolab pattern). With per-pane
+// tmux sessions, dropping `-d` means multiple browser tabs viewing the same
+// pane share one tmux session as N clients; tmux fans I/O at the session
+// layer just like boolab's backend. The earlier `-d` flag detached EVERY
+// other client of the session — across windows — which caused the
+// "[detached] from session" bug whenever a new pane attached to a chat
+// session that already had another pane open.
+//
+// Tmux server + session persist across PTY exits, so a refresh resumes with
+// full scrollback. Explicit destroy happens via the /kill route (called from
+// the frontend when the user closes a pane).
 export function attachPty(opts: AttachPtyOptions): IPty {
   return pty.spawn(
     'tmux',
     [
       '-f', opts.tmuxConfPath,
-      'attach-session', '-d',
-      '-t', `${opts.sessionName}:${opts.windowName}`,
+      'attach-session',
+      '-t', opts.sessionName,
     ],
     {
       name: 'xterm-256color',

apps/booterm/src/routes/terminals.ts

@@ -4,22 +4,33 @@ import { getSessionInfo } from '../db.js';
 import {
   sanitizeId,
   tmuxSessionName,
-  tmuxWindowName,
-  ensureWindow,
-  killWindow,
+  ensureSession,
+  killSession,
   hasSession,
-  listWindows,
 } from '../pty/manager.js';
-import { resizePane } from '../ws/attach.js';
 
 const ParamsSchema = z.object({ sid: z.string(), pid: z.string() });
-const ResizeBodySchema = z.object({
-  cols: z.coerce.number().int().min(1).max(2000),
-  rows: z.coerce.number().int().min(1).max(2000),
-});
+// v1.10.8c: optional cols/rows on /start so the per-pane tmux session is
+// born at the right dimensions. Bodyless POSTs remain valid (Fastify's
+// tolerant parser).
+const StartBodySchema = z
+  .object({
+    cols: z.coerce.number().int().min(1).max(2000).optional(),
+    rows: z.coerce.number().int().min(1).max(2000).optional(),
+  })
+  .partial()
+  .optional();
 
 export function registerTerminalRoutes(app: FastifyInstance, tmuxConfPath: string): void {
-  app.post<{ Params: { sid: string; pid: string } }>(
+  // v1.10.8c: /start creates the per-pane tmux session. Idempotent — a second
+  // /start on the same paneId is a no-op (hasSession returns true). The WS
+  // attach handler also calls ensureSession as belt-and-suspenders, so /start
+  // is technically optional, but having it as a separate step surfaces tmux
+  // errors as HTTP responses (vs WS 1011 close codes).
+  app.post<{
+    Params: { sid: string; pid: string };
+    Body: { cols?: number; rows?: number } | undefined;
+  }>(
     '/api/term/sessions/:sid/panes/:pid/start',
     async (req, reply) => {
       const p = ParamsSchema.safeParse(req.params);
@@ -28,39 +39,35 @@ export function registerTerminalRoutes(app: FastifyInstance, tmuxConfPath: strin
       const pid = sanitizeId(p.data.pid);
       if (!sid || !pid) return reply.code(400).send({ error: 'bad_id_format' });
 
+      const b = StartBodySchema.safeParse(req.body ?? {});
+      const cols = b.success ? b.data?.cols : undefined;
+      const rows = b.success ? b.data?.rows : undefined;
+
       const session = await getSessionInfo(sid);
       if (!session) return reply.code(404).send({ error: 'unknown_session' });
 
-      const sessionName = tmuxSessionName(sid);
-      const windowName = tmuxWindowName(pid);
+      const sessionName = tmuxSessionName(pid);
 
       try {
-        await ensureWindow(tmuxConfPath, sessionName, windowName, session.project_path, req.log);
+        await ensureSession(
+          tmuxConfPath,
+          sessionName,
+          session.project_path,
+          req.log,
+          cols,
+          rows,
+        );
       } catch (err) {
-        req.log.error({ err }, 'ensureWindow failed');
+        req.log.error({ err }, 'ensureSession failed');
         return reply.code(500).send({ error: 'tmux_failed' });
       }
-      return reply.code(200).send({ tmux_window: windowName });
-    },
-  );
-
-  app.post<{ Params: { sid: string; pid: string }; Body: { cols: number; rows: number } }>(
-    '/api/term/sessions/:sid/panes/:pid/resize',
-    async (req, reply) => {
-      const p = ParamsSchema.safeParse(req.params);
-      if (!p.success) return reply.code(400).send({ error: 'bad_params' });
-      const b = ResizeBodySchema.safeParse(req.body);
-      if (!b.success) return reply.code(400).send({ error: 'bad_body' });
-      const sid = sanitizeId(p.data.sid);
-      const pid = sanitizeId(p.data.pid);
-      if (!sid || !pid) return reply.code(400).send({ error: 'bad_id_format' });
-
-      const ok = resizePane(pid, b.data.cols, b.data.rows);
-      if (!ok) return reply.code(404).send({ error: 'no_active_pty' });
-      return reply.code(200).send({ ok: true });
+      return reply.code(200).send({ tmux_session: sessionName });
     },
   );
 
+  // v1.10.8c: explicit pane teardown. Frontend calls this when the user
+  // intentionally closes a terminal pane (vs an implicit WS disconnect, which
+  // leaves the tmux session intact for refresh-driven resume).
   app.post<{ Params: { sid: string; pid: string } }>(
     '/api/term/sessions/:sid/panes/:pid/kill',
     async (req, reply) => {
@@ -70,19 +77,17 @@ export function registerTerminalRoutes(app: FastifyInstance, tmuxConfPath: strin
       const pid = sanitizeId(p.data.pid);
       if (!sid || !pid) return reply.code(400).send({ error: 'bad_id_format' });
 
-      const sessionName = tmuxSessionName(sid);
-      const windowName = tmuxWindowName(pid);
-
+      const sessionName = tmuxSessionName(pid);
       if (!(await hasSession(tmuxConfPath, sessionName))) {
-        return reply.code(404).send({ error: 'unknown_session' });
-      }
-      const windows = await listWindows(tmuxConfPath, sessionName);
-      if (!windows.includes(windowName)) {
         return reply.code(404).send({ error: 'unknown_pane' });
       }
-      const killed = await killWindow(tmuxConfPath, sessionName, windowName);
+      const killed = await killSession(tmuxConfPath, sessionName);
       if (!killed) return reply.code(500).send({ error: 'tmux_kill_failed' });
       return reply.code(200).send({ ok: true });
     },
   );
+
+  // Resize endpoint removed in v1.10.8c. Resize now flows in-band via the
+  // WebSocket as a `{type:"resize",cols,rows}` text frame — no more race
+  // between active-PTY-map registration and HTTP POST lookup. See ws/attach.ts.
 }

apps/booterm/src/ws/attach.ts

@@ -1,25 +1,15 @@
 import type { FastifyInstance } from 'fastify';
 import type { IPty } from 'node-pty';
 import { getSessionInfo } from '../db.js';
-import { sanitizeId, tmuxSessionName, tmuxWindowName, ensureWindow } from '../pty/manager.js';
+import {
+  sanitizeId,
+  tmuxSessionName,
+  ensureSession,
+  capturePane,
+} from '../pty/manager.js';
 import { attachPty } from '../pty/pty.js';
 import { getUser } from '../auth.js';
 
-// Registry of currently-attached PTYs keyed by paneId. Used by the resize REST
-// route to find the active node-pty handle so it can call pty.resize(cols, rows).
-const active = new Map<string, IPty>();
-
-export function resizePane(paneId: string, cols: number, rows: number): boolean {
-  const handle = active.get(paneId);
-  if (!handle) return false;
-  try {
-    handle.resize(cols, rows);
-    return true;
-  } catch {
-    return false;
-  }
-}
-
 export function registerWsAttachRoute(app: FastifyInstance, tmuxConfPath: string): void {
   app.get<{
     Params: { sid: string; pid: string };
@@ -44,24 +34,33 @@ export function registerWsAttachRoute(app: FastifyInstance, tmuxConfPath: string
         return;
       }
 
-      const sessionName = tmuxSessionName(sid);
-      const windowName = tmuxWindowName(pid);
+      const sessionName = tmuxSessionName(pid);
+      const cols = parseInt(req.query.cols ?? '', 10) || 80;
+      const rows = parseInt(req.query.rows ?? '', 10) || 24;
+
+      // Idempotent — /start typically created the session already, but cover
+      // the race where the client opens the WS before /start's response lands
+      // (or skips /start entirely). With per-pane tmux sessions there's no
+      // cross-pane interference, so creating-on-attach is safe.
       try {
-        await ensureWindow(tmuxConfPath, sessionName, windowName, session.project_path, req.log);
+        await ensureSession(
+          tmuxConfPath,
+          sessionName,
+          session.project_path,
+          req.log,
+          cols,
+          rows,
+        );
       } catch (err) {
-        req.log.error({ err }, 'ensureWindow failed in WS handler');
+        req.log.error({ err }, 'ensureSession failed in WS handler');
         socket.close(1011, 'tmux_failed');
         return;
       }
 
-      const cols = parseInt(req.query.cols ?? '', 10) || 80;
-      const rows = parseInt(req.query.rows ?? '', 10) || 24;
-
       let handle: IPty;
       try {
         handle = attachPty({
           sessionName,
-          windowName,
           projectRoot: session.project_path,
           cols,
           rows,
@@ -73,9 +72,31 @@ export function registerWsAttachRoute(app: FastifyInstance, tmuxConfPath: string
         return;
       }
 
-      active.set(pid, handle);
+      // Frame contract (boolab pattern):
+      //   server → client text:    JSON control — `init` on connect, `exit` on PTY death
+      //   server → client binary:  raw PTY bytes (first frame after init = capture-pane replay)
+      //   client → server binary:  user keystrokes
+      //   client → server text:    JSON control — `{type:"resize", cols, rows}`
+      //
+      // The init frame lets the client term.clear() before paint so a remount
+      // doesn't show stale buffer content. The capture-pane replay then
+      // paints the current tmux pane state into the fresh xterm.
+      try {
+        socket.send(JSON.stringify({ type: 'init', cols, rows, tmux_session: sessionName }));
+      } catch (err) {
+        req.log.warn({ err }, 'init frame send failed');
+      }
 
-      const onData = (data: string) => {
+      try {
+        const capture = await capturePane(tmuxConfPath, sessionName);
+        if (capture.length > 0) {
+          socket.send(Buffer.from(capture, 'utf8'), { binary: true });
+        }
+      } catch (err) {
+        req.log.warn({ err }, 'capture-pane failed');
+      }
+
+      const onData = (data: string): void => {
         if (socket.readyState !== socket.OPEN) return;
         try {
           socket.send(Buffer.from(data, 'utf8'), { binary: true });
@@ -85,13 +106,32 @@ export function registerWsAttachRoute(app: FastifyInstance, tmuxConfPath: string
       };
       handle.onData(onData);
 
-      socket.on('message', (data: Buffer | string) => {
+      socket.on('message', (rawData: Buffer | string, isBinary?: boolean) => {
+        // ws v8 emits Buffer + isBinary boolean; older versions emit string
+        // for text frames. Either way: text path tries JSON parse for the
+        // resize control; binary path writes to the PTY.
+        const isTextFrame = typeof rawData === 'string' || isBinary === false;
+        if (isTextFrame) {
+          const text = typeof rawData === 'string' ? rawData : rawData.toString('utf8');
           try {
-          if (typeof data === 'string') {
-            handle.write(data);
-          } else {
-            handle.write(data.toString('utf8'));
+            const parsed = JSON.parse(text) as { type?: string; cols?: number; rows?: number };
+            if (parsed.type === 'resize') {
+              const newCols = Math.max(1, Math.min(2000, Math.floor(Number(parsed.cols) || 80)));
+              const newRows = Math.max(1, Math.min(2000, Math.floor(Number(parsed.rows) || 24)));
+              req.log.info({ pid, cols: newCols, rows: newRows }, 'resize');
+              try {
+                handle.resize(newCols, newRows);
+              } catch {
+                /* ignore — invalid winsize bubble */
               }
+            }
+          } catch {
+            /* malformed text frame — drop silently */
+          }
+          return;
+        }
+        try {
+          handle.write((rawData as Buffer).toString('utf8'));
         } catch (err) {
           req.log.warn({ err }, 'pty write failed');
         }
@@ -110,13 +150,13 @@ export function registerWsAttachRoute(app: FastifyInstance, tmuxConfPath: string
         } catch {
           /* ignore */
         }
-        if (active.get(pid) === handle) active.delete(pid);
       });
 
-      // WS close kills the local PTY (the tmux client). The tmux server and
-      // window persist so a refresh resumes with full scrollback.
+      // WS close kills the tmux client (the local PTY) but the tmux server +
+      // session persist — so a refresh resumes with full scrollback. Permanent
+      // teardown happens via the /kill route called from the frontend when the
+      // user closes the pane.
       socket.on('close', () => {
-        if (active.get(pid) === handle) active.delete(pid);
         try {
           handle.kill();
         } catch {

apps/booterm/tmux.conf

@@ -1,13 +1,30 @@
 set -g default-terminal "screen-256color"
 set -g history-limit 50000
-set -g mouse on
+
+# v1.10.8c: per-pane tmux sessions (boolab pattern). With one session per
+# pane, the session size adapts to the attached client; `window-size = largest`
+# + `aggressive-resize on` make tmux pick up the client's actual cols/rows
+# instead of falling back to 80x24. Critical for opencode/claude TUIs that
+# read TIOCGWINSZ once at fork time.
+set -g window-size largest
+set -g aggressive-resize on
+
+# v1.10.3: `set -g mouse on` removed. tmux's mouse mode captured wheel/touch
+# events at the protocol level, so xterm.js never saw them and the viewport
+# couldn't scroll on mobile. With mouse off, xterm.js handles scrollback
+# natively (wheel on desktop, finger-drag on mobile via touch-action: pan-y).
+# Tradeoff: lose tmux mouse pane-resize and scroll-inside-vim; acceptable for
+# the homelab single-user setup.
+set -g mouse off
 setw -g mode-keys vi
 set -g status off
 set -g destroy-unattached off
 
 # v1.10.1: shells drop privs to samkintop (uid 1000) so the terminal runs in
 # the user's environment, not root. `env HOME=… USER=…` is required because
-# su-exec only changes uid/gid — it leaves env intact, and tmux server runs
-# as root so HOME would otherwise be /root. bash -l then sources samkintop's
-# ~/.profile / ~/.bashrc to pick up PATH (nvm, ~/.local/bin, ~/.opencode/bin).
-set -g default-command "su-exec samkintop:samkintop env HOME=/home/samkintop USER=samkintop SHELL=/bin/bash bash -l"
+# gosu only changes uid/gid — env (including HOME) survives, and the tmux
+# server runs as root so HOME would otherwise be /root. bash -l then sources
+# samkintop's ~/.profile / ~/.bashrc to pick up PATH (nvm, ~/.local/bin,
+# ~/.opencode/bin).
+# v1.10.2: su-exec → gosu (alpine → debian; functionally identical).
+set -g default-command "gosu samkintop:samkintop env HOME=/home/samkintop USER=samkintop SHELL=/bin/bash bash -l"

apps/server/src/index.ts

@@ -19,6 +19,7 @@ import { registerSkillsRoutes } from './routes/skills.js';
 import { createInferenceRunner } from './services/inference.js';
 import { createBroker } from './services/broker.js';
 import { listSkills } from './services/skills.js';
+import * as compaction from './services/compaction.js';
 
 async function main() {
   const config = loadConfig();
@@ -81,6 +82,11 @@ async function main() {
       publish: (sessionId, frame) => {
         broker.publish(sessionId, frame as unknown as Record<string, unknown> & { type: string });
       },
+      // v1.11: broker handle for compaction.process to publish 'compacted'
+      // frames on the per-session channel. Inference's regular publish path
+      // is bound to (sessionId, InferenceFrame); compaction publishes a
+      // different frame shape, so it goes through the raw broker.
+      broker,
     },
     (user, frame) => {
       broker.publishUser(user, frame as unknown as Record<string, unknown> & { type: string });
@@ -90,9 +96,13 @@ async function main() {
     enqueueInference: (sessionId, chatId, assistantId, user) => {
       inference.enqueue(sessionId, chatId, assistantId, user);
     },
-    enqueueCompact: (sessionId, chatId, compactId, user) => {
-      inference.enqueueCompact(sessionId, chatId, compactId, user);
-    },
+    // v1.11: synchronous compaction. Awaits the LLM call inside the route's
+    // request lifecycle; the new summary row arrives via the WS 'compacted'
+    // frame published from inside compaction.process. We let the error
+    // bubble up so the route can reply 500 — manual /compact failures
+    // should be loud (the user just clicked a button).
+    runCompaction: (chatId) =>
+      compaction.process({ sql, config, log: app.log, broker, chatId }),
     cancelInference: async (sessionId, chatId) => {
       return inference.cancel(sessionId, chatId);
     },

apps/server/src/routes/chats.ts

@@ -316,7 +316,8 @@ export function registerChatRoutes(
       }
       const rows = await sql<Message[]>`
         SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
-               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata
+               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata,
+               summary, tail_start_id, compacted_at
         FROM messages
         WHERE chat_id = ${req.params.id}
         ORDER BY created_at ASC, id ASC

apps/server/src/routes/messages.ts

@@ -49,7 +49,12 @@ const AskUserInputArgs = z.object({
 
 interface MessageHandlers {
   enqueueInference: (sessionId: string, chatId: string, assistantMessageId: string, user: string) => void;
-  enqueueCompact: (sessionId: string, chatId: string, compactMessageId: string, user: string) => void;
+  // v1.11: returns a promise that resolves after compaction.process finishes
+  // (await the LLM call). Throws on failure — the route surfaces a 500.
+  // Replaces the v1.10 enqueueCompact (which fired-and-forgot a kind='compact'
+  // streaming row). The new anchored-rolling strategy inserts a single
+  // summary=true assistant row only after the LLM responds.
+  runCompaction: (chatId: string) => Promise<void>;
   publishUserMessage: (
     sessionId: string,
     chatId: string,
@@ -81,9 +86,15 @@ export function registerMessageRoutes(
         reply.code(404);
         return { error: 'session not found' };
       }
+      // v1.11: returns ALL messages including compacted ones. The UI
+      // distinguishes via the new `summary` flag (renders an accordion
+      // SummaryCard) and shows compacted_at-stamped rows inline for context.
+      // Internal inference assembly filters compacted_at IS NULL separately —
+      // see services/inference.ts loadContext + services/compaction.ts.
       const rows = await sql<Message[]>`
         SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
-               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata
+               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata,
+               summary, tail_start_id, compacted_at
         FROM messages
         WHERE session_id = ${req.params.id}
         ORDER BY created_at ASC, id ASC
@@ -251,29 +262,30 @@ export function registerMessageRoutes(
     }
   );
 
+  // v1.11: manual /compact. Was a streaming kind='compact' row inserted by
+  // this handler; now delegates to the anchored-rolling compaction service.
+  // Synchronous (we await the LLM call) — callers either await or rely on
+  // the 'compacted' WS frame to refresh their view. The response carries
+  // no body of interest; the new summary row arrives via the WS frame.
   app.post<{ Params: { id: string } }>(
     '/api/chats/:id/compact',
     async (req, reply) => {
-      const chatRows = await sql<Chat[]>`
-        SELECT id, session_id FROM chats WHERE id = ${req.params.id} AND status = 'open'
+      const chatRows = await sql<{ id: string }[]>`
+        SELECT id FROM chats WHERE id = ${req.params.id} AND status = 'open'
       `;
       if (chatRows.length === 0) {
         reply.code(404);
         return { error: 'chat not found' };
       }
-      const chat = chatRows[0]!;
-      const sessionId = chat.session_id;
-
-      const [compactMsg] = await sql<{ id: string }[]>`
-        INSERT INTO messages (session_id, chat_id, role, content, kind, status, created_at)
-        VALUES (${sessionId}, ${chat.id}, 'system', '', 'compact', 'streaming', clock_timestamp())
-        RETURNING id
-      `;
-
-      handlers.enqueueCompact(sessionId, chat.id, compactMsg!.id, 'default');
-
-      reply.code(202);
-      return { compact_message_id: compactMsg!.id };
+      try {
+        await handlers.runCompaction(chatRows[0]!.id);
+      } catch (err) {
+        req.log.error({ err, chatId: chatRows[0]!.id }, 'manual compaction failed');
+        reply.code(500);
+        return { error: err instanceof Error ? err.message : 'compaction failed' };
+      }
+      reply.code(200);
+      return { ok: true };
     }
   );
 

apps/server/src/routes/ws.ts

@@ -21,9 +21,12 @@ export function registerWebSocket(
         return;
       }
 
+      // v1.11: snapshot includes compaction fields so MessageBubble can
+      // render the SummaryCard for summary=true rows on first connect.
       const messages = await sql<Message[]>`
         SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
-               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata
+               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata,
+               summary, tail_start_id, compacted_at
         FROM messages
         WHERE session_id = ${sessionId}
         ORDER BY created_at ASC, id ASC

apps/server/src/schema.sql

@@ -179,3 +179,25 @@ INSERT INTO settings (key, value) VALUES ('theme_mode', '"dark"') ON CONFLICT (k
 ALTER TABLE projects ADD COLUMN IF NOT EXISTS default_system_prompt TEXT NOT NULL DEFAULT '';
 ALTER TABLE projects ADD COLUMN IF NOT EXISTS default_web_search_enabled BOOLEAN NOT NULL DEFAULT false;
 ALTER TABLE sessions ADD COLUMN IF NOT EXISTS web_search_enabled BOOLEAN;
+
+-- v1.11: anchored rolling compaction.
+--   compacted_at  — marks rows that are "behind the curtain" of the latest
+--                   summary. Inference assembly filters compacted_at IS NULL;
+--                   the API GET still returns all rows so the UI can show
+--                   history with the summary card inline.
+--   summary       — true on the assistant row that IS the anchored summary.
+--                   Exactly one row per chat is the "current" summary
+--                   (every prior summary row is itself compacted_at-stamped
+--                   when superseded, leaving one live anchor).
+--   tail_start_id — points at the first preserved message that the summary
+--                   covers up to (exclusive). Lets the UI/debug reason about
+--                   the boundary without re-deriving from compacted_at.
+--   needs_compaction — flag on chats (not sessions) because chat history is
+--                   per-chat; sessions have 1:N chats. Set true post-overflow,
+--                   cleared by compaction.process at the start of the next
+--                   inference turn.
+ALTER TABLE messages ADD COLUMN IF NOT EXISTS compacted_at TIMESTAMPTZ;
+ALTER TABLE messages ADD COLUMN IF NOT EXISTS summary BOOLEAN NOT NULL DEFAULT FALSE;
+ALTER TABLE messages ADD COLUMN IF NOT EXISTS tail_start_id UUID REFERENCES messages(id) ON DELETE SET NULL;
+ALTER TABLE chats ADD COLUMN IF NOT EXISTS needs_compaction BOOLEAN NOT NULL DEFAULT FALSE;
+CREATE INDEX IF NOT EXISTS idx_messages_chat_compacted ON messages (chat_id, compacted_at);

apps/server/src/services/__tests__/compaction.test.ts

@@ -0,0 +1,258 @@
+import { describe, it, expect } from 'vitest';
+import {
+  usable,
+  isOverflow,
+  estimate,
+  turns,
+  select,
+  buildPrompt,
+  type CompactionMessage,
+} from '../compaction.js';
+import { SUMMARY_TEMPLATE } from '../compaction-prompt.js';
+
+// ---- fixture ----------------------------------------------------------------
+// Tiny constructor for the message shape `compaction.ts` consumes. Default
+// values match the post-CP1 schema (summary=false, kind='message', complete).
+// Tests that need a summary row pass `summary: true`.
+
+let counter = 0;
+function mkMsg(
+  role: CompactionMessage['role'],
+  content: string,
+  overrides: Partial<CompactionMessage> = {},
+): CompactionMessage {
+  counter += 1;
+  return {
+    id: `m${counter}`,
+    role,
+    content,
+    kind: 'message',
+    summary: false,
+    status: 'complete',
+    tool_calls: null,
+    tool_results: null,
+    metadata: null,
+    created_at: new Date(counter * 1000).toISOString(),
+    ...overrides,
+  };
+}
+
+// ---- usable -----------------------------------------------------------------
+
+describe('usable', () => {
+  it('returns 0 when contextLimit is 0', () => {
+    expect(usable(0)).toBe(0);
+  });
+
+  it('returns 0 when contextLimit is below the 20k buffer', () => {
+    // Math.max(0, x - 20000) clamps the subtraction so we never report
+    // negative headroom. A 10k-context model reports 0 usable, which makes
+    // isOverflow short-circuit to false (correct — we can't size the
+    // compaction with no headroom).
+    expect(usable(10_000)).toBe(0);
+    expect(usable(19_999)).toBe(0);
+    expect(usable(20_000)).toBe(0);
+  });
+
+  it('subtracts the 20k buffer from a normal-sized context window', () => {
+    expect(usable(100_000)).toBe(80_000);
+    expect(usable(32_768)).toBe(12_768);
+  });
+});
+
+// ---- isOverflow -------------------------------------------------------------
+
+describe('isOverflow', () => {
+  it('returns false when usable is 0 (unknown / sub-buffer context)', () => {
+    expect(isOverflow({ prompt_tokens: 999_999, completion_tokens: 0 }, 0)).toBe(false);
+    expect(isOverflow({ prompt_tokens: 0, completion_tokens: 999_999 }, 10_000)).toBe(false);
+  });
+
+  it('returns false at 50% of usable', () => {
+    // usable(100k) = 80k → 50% = 40k.
+    expect(isOverflow({ prompt_tokens: 30_000, completion_tokens: 10_000 }, 100_000)).toBe(false);
+  });
+
+  it('returns false just under usable', () => {
+    expect(isOverflow({ prompt_tokens: 79_000, completion_tokens: 999 }, 100_000)).toBe(false);
+  });
+
+  it('returns true exactly at usable (>=, not strict >)', () => {
+    expect(isOverflow({ prompt_tokens: 80_000, completion_tokens: 0 }, 100_000)).toBe(true);
+  });
+
+  it('returns true above usable', () => {
+    expect(isOverflow({ prompt_tokens: 50_000, completion_tokens: 40_000 }, 100_000)).toBe(true);
+  });
+});
+
+// ---- estimate ---------------------------------------------------------------
+
+describe('estimate', () => {
+  it('returns a tiny value for an empty array (JSON.stringify([]) is "[]")', () => {
+    // Math.ceil('[]'.length / 4) = 1. Documented here so the next reader
+    // doesn't think "0" is the expected baseline — char-count/4 will never
+    // be exactly 0 for any JSON-serializable input.
+    expect(estimate([])).toBe(1);
+  });
+
+  it('scales roughly with content length', () => {
+    const tiny = estimate([mkMsg('user', 'hi')]);
+    const big = estimate([mkMsg('user', 'x'.repeat(4000))]);
+    expect(big).toBeGreaterThan(tiny);
+    expect(big).toBeGreaterThanOrEqual(1000); // 4000 chars / 4 = 1000 floor
+  });
+
+  it('is deterministic across repeated calls', () => {
+    const msgs = [mkMsg('user', 'one'), mkMsg('assistant', 'two')];
+    expect(estimate(msgs)).toBe(estimate(msgs));
+  });
+});
+
+// ---- turns ------------------------------------------------------------------
+
+describe('turns', () => {
+  it('returns [] for an empty message list', () => {
+    expect(turns([])).toEqual([]);
+  });
+
+  it('returns one turn for a single user message', () => {
+    const u = mkMsg('user', 'hi');
+    const result = turns([u]);
+    expect(result).toHaveLength(1);
+    expect(result[0]).toEqual({ start: 0, end: 1, id: u.id });
+  });
+
+  it('returns two turns for user/assistant/user/assistant', () => {
+    const u1 = mkMsg('user', 'q1');
+    const a1 = mkMsg('assistant', 'a1');
+    const u2 = mkMsg('user', 'q2');
+    const a2 = mkMsg('assistant', 'a2');
+    const result = turns([u1, a1, u2, a2]);
+    expect(result).toEqual([
+      { start: 0, end: 2, id: u1.id },
+      { start: 2, end: 4, id: u2.id },
+    ]);
+  });
+
+  it('extends the final turn end to include trailing non-user messages', () => {
+    // Spec wording: "user/assistant + trailing system → trailing included
+    // in last turn's range". Single-turn variant: [user, assistant, system]
+    // should produce one turn with end=3 (covers all three indices).
+    const u = mkMsg('user', 'q');
+    const a = mkMsg('assistant', 'a');
+    const s = mkMsg('system', 'note');
+    const result = turns([u, a, s]);
+    expect(result).toEqual([{ start: 0, end: 3, id: u.id }]);
+  });
+
+  it('skips user rows flagged as summary (anchored-rolling rows)', () => {
+    // Defense-in-depth — process() pre-filters summary rows, but turns()
+    // also skips them so a misuse from another caller doesn't create a
+    // bogus turn boundary on the summary row itself.
+    const u1 = mkMsg('user', 'q1');
+    const a1 = mkMsg('assistant', 'a1');
+    const sum = mkMsg('user', 'rolled-up', { summary: true });
+    const u2 = mkMsg('user', 'q2');
+    const result = turns([u1, a1, sum, u2]);
+    expect(result.map((t) => t.id)).toEqual([u1.id, u2.id]);
+  });
+});
+
+// ---- select -----------------------------------------------------------------
+
+describe('select', () => {
+  it('returns empty head + undefined tail for an empty message list', () => {
+    const result = select([], 100_000);
+    expect(result.head).toEqual([]);
+    expect(result.tail_start_id).toBeUndefined();
+  });
+
+  it('full-preserves when there are fewer turns than tail_turns', () => {
+    // 1 turn but tail_turns=2: keep === turn0 → keep.start === 0 →
+    // sentinel-return path that signals "no compaction this round".
+    const u = mkMsg('user', 'only');
+    const a = mkMsg('assistant', 'a');
+    const result = select([u, a], 100_000, 2);
+    expect(result.head).toEqual([u, a]);
+    expect(result.tail_start_id).toBeUndefined();
+  });
+
+  it('keeps the last tail_turns turns when they all fit the budget', () => {
+    // 3 turns, all small. tail_turns=2 means keep the last 2; head =
+    // messages[0..turn2.start] = just turn1's content.
+    const u1 = mkMsg('user', 'q1');
+    const a1 = mkMsg('assistant', 'a1');
+    const u2 = mkMsg('user', 'q2');
+    const a2 = mkMsg('assistant', 'a2');
+    const u3 = mkMsg('user', 'q3');
+    const a3 = mkMsg('assistant', 'a3');
+    const msgs = [u1, a1, u2, a2, u3, a3];
+    const result = select(msgs, 100_000, 2);
+    // Turn boundaries: [0,2), [2,4), [4,6). slice(-2) = turns at 2 and 4.
+    // Walking backward: u3 fits, then u2 fits → keep={start:2, id:u2.id}.
+    expect(result.tail_start_id).toBe(u2.id);
+    expect(result.head).toEqual([u1, a1]);
+  });
+
+  it('splits a turn mid-stream when the whole turn would overflow the budget', () => {
+    // tail_turns=1 so we look only at the most recent turn. Stuff it past
+    // 8k of content (max preserve budget) and the splitter walks forward
+    // looking for the largest suffix that fits.
+    const u1 = mkMsg('user', 'q1');
+    const a1 = mkMsg('assistant', 'a1');
+    const u2 = mkMsg('user', 'q2 with a giant payload');
+    const huge = mkMsg('assistant', 'X'.repeat(40_000)); // ~10k tokens
+    const smallTail = mkMsg('assistant', 'short answer');
+    const msgs = [u1, a1, u2, huge, smallTail];
+    const result = select(msgs, 100_000, 1);
+    // The split walks from turn.start+1 forward; the first index whose
+    // [i, end) slice fits the budget becomes the new keep. We don't assert
+    // a specific id (depends on character math), only that compaction was
+    // triggered (tail_start_id set, head non-empty) and that the head
+    // doesn't include the final small message.
+    expect(result.tail_start_id).toBeDefined();
+    expect(result.head.length).toBeGreaterThan(0);
+    expect(result.head).not.toContain(smallTail);
+  });
+
+  it('full-preserves when no split point fits', () => {
+    // Single oversized turn; splitTurn walks but each suffix is still too
+    // big. After the loop, keep is undefined → full-preserve sentinel.
+    // Force this with a sub-buffer context so budget is the floor (2k),
+    // and a single 40k-char message.
+    const u = mkMsg('user', 'oversized');
+    const a = mkMsg('assistant', 'Y'.repeat(40_000));
+    const result = select([u, a], 30_000, 1);
+    // usable(30k) = 10k → budget = min(8k, max(2k, floor(10k*0.25))) =
+    // min(8k, max(2k, 2500)) = 2500. 40k chars ≈ 10k tokens. Can't fit.
+    expect(result.tail_start_id).toBeUndefined();
+    expect(result.head).toEqual([u, a]);
+  });
+});
+
+// ---- buildPrompt ------------------------------------------------------------
+
+describe('buildPrompt', () => {
+  it('opens with the "create new" anchor when previousSummary is undefined', () => {
+    const out = buildPrompt(undefined, []);
+    expect(out.startsWith('Create a new anchored summary')).toBe(true);
+    expect(out).toContain(SUMMARY_TEMPLATE);
+    expect(out).not.toContain('<previous-summary>');
+  });
+
+  it('opens with the "update" anchor and embeds previousSummary verbatim', () => {
+    const prev = '## Goal\n- finish v1.11 compaction';
+    const out = buildPrompt(prev, []);
+    expect(out.startsWith('Update the anchored summary')).toBe(true);
+    expect(out).toContain('<previous-summary>');
+    expect(out).toContain(prev);
+    expect(out).toContain('</previous-summary>');
+    expect(out).toContain(SUMMARY_TEMPLATE);
+  });
+
+  it('appends extra context strings after the template (reserved for plugin injection)', () => {
+    const out = buildPrompt(undefined, ['extra-context-line']);
+    expect(out.endsWith('extra-context-line')).toBe(true);
+  });
+});

apps/server/src/services/compaction-prompt.ts

@@ -0,0 +1,40 @@
+// v1.11: anchored rolling summary template. Verbatim port from opencode
+// (packages/opencode/src/session/compaction.ts SUMMARY_TEMPLATE). Kept in a
+// separate module so the long template literal doesn't bloat compaction.ts.
+
+export const SUMMARY_TEMPLATE = `Output exactly the Markdown structure shown inside <template> and keep the section order unchanged. Do not include the <template> tags in your response.
+<template>
+## Goal
+- [single-sentence task summary]
+
+## Constraints & Preferences
+- [user constraints, preferences, specs, or "(none)"]
+
+## Progress
+### Done
+- [completed work or "(none)"]
+
+### In Progress
+- [current work or "(none)"]
+
+### Blocked
+- [blockers or "(none)"]
+
+## Key Decisions
+- [decision and why, or "(none)"]
+
+## Next Steps
+- [ordered next actions or "(none)"]
+
+## Critical Context
+- [important technical facts, errors, open questions, or "(none)"]
+
+## Relevant Files
+- [file or directory path: why it matters, or "(none)"]
+</template>
+
+Rules:
+- Keep every section, even when empty.
+- Use terse bullets, not prose paragraphs.
+- Preserve exact file paths, commands, error strings, and identifiers when known.
+- Do not mention the summary process or that context was compacted.`;

apps/server/src/services/compaction.ts

@@ -0,0 +1,503 @@
+// v1.11: anchored rolling compaction. Ported algorithms (not Effect-TS code)
+// from opencode (packages/opencode/src/session/{compaction,overflow}.ts).
+//
+// What's different from BooCode's legacy /compact:
+//   - Operates per-chat (chats have N:1 to sessions; history is per-chat).
+//   - Detects overflow automatically after each inference completion using
+//     llama-swap's reported n_ctx; flags chats.needs_compaction=true.
+//   - On the next turn (or manual /compact) we summarize the *head* (messages
+//     prior to a preserved tail of N user-turns) into a single
+//     summary=true assistant row. Older messages get compacted_at-stamped so
+//     inference assembly filters them out; the GET endpoint still returns
+//     them so the UI can show history with the summary card inline.
+//   - The summary is *anchored rolling* — exactly one live summary=true row
+//     per chat. Subsequent compactions read the prior summary as
+//     previousSummary, ask the LLM to update-merge it, then mark the prior
+//     summary row compacted_at too (it stays in the UI but isn't sent to the
+//     LLM again).
+
+import type { FastifyBaseLogger } from 'fastify';
+import type { Sql } from '../db.js';
+import type { Config } from '../config.js';
+import type { Broker } from './broker.js';
+import { SUMMARY_TEMPLATE } from './compaction-prompt.js';
+
+const COMPACTION_BUFFER = 20_000;
+const MIN_PRESERVE_RECENT_TOKENS = 2_000;
+const MAX_PRESERVE_RECENT_TOKENS = 8_000;
+const DEFAULT_TAIL_TURNS = 2;
+
+// Subset of Message fields compaction touches. Selecting only what's needed
+// keeps process() independent of api.ts mutations and reduces DB egress.
+export interface CompactionMessage {
+  id: string;
+  role: 'user' | 'assistant' | 'system' | 'tool';
+  content: string;
+  kind: 'message' | 'compact';
+  summary: boolean;
+  status: 'streaming' | 'complete' | 'failed' | 'cancelled';
+  tool_calls: Array<{ id: string; name: string; args: Record<string, unknown> }> | null;
+  tool_results: { tool_call_id: string; output: unknown; truncated: boolean; error?: string } | null;
+  metadata: { kind?: string } | null;
+  created_at: string;
+}
+
+// === overflow ===
+
+// Tokens we hold in reserve for the model's response so a near-full context
+// can still produce a useful turn. Mirrors opencode's COMPACTION_BUFFER.
+// Returns 0 when the context limit is unknown (caller treats 0 as "do not
+// trigger overflow"); avoids dividing-by-zero downstream.
+export function usable(contextLimit: number): number {
+  if (!contextLimit || contextLimit <= 0) return 0;
+  return Math.max(0, contextLimit - COMPACTION_BUFFER);
+}
+
+export interface Usage {
+  prompt_tokens: number;
+  completion_tokens: number;
+}
+
+// True when the assistant just used >= usable() tokens. Unknown limit → false
+// (we never auto-trigger compaction without a budget — better to keep
+// inference flowing than to fall into a compaction we can't size properly).
+export function isOverflow(usage: Usage, contextLimit: number): boolean {
+  const budget = usable(contextLimit);
+  if (budget <= 0) return false;
+  return (usage.prompt_tokens + usage.completion_tokens) >= budget;
+}
+
+// === selection ===
+
+interface Turn {
+  start: number;
+  end: number;
+  id: string;
+}
+
+// Char-count / 4 token estimate. Matches opencode's Token.estimate (which
+// also goes through JSON.stringify). Adequate for tail-fitting math; we
+// don't need a real tokenizer here — the 20k buffer absorbs the slop.
+export function estimate(messages: CompactionMessage[]): number {
+  return Math.ceil(JSON.stringify(messages).length / 4);
+}
+
+// Walk messages, return one Turn per user message that is NOT a summary row.
+// end = next-user-start; final turn ends at messages.length.
+export function turns(messages: CompactionMessage[]): Turn[] {
+  const result: Turn[] = [];
+  for (let i = 0; i < messages.length; i++) {
+    const m = messages[i]!;
+    if (m.role !== 'user') continue;
+    if (m.summary) continue;
+    result.push({ start: i, end: messages.length, id: m.id });
+  }
+  for (let i = 0; i < result.length - 1; i++) {
+    result[i]!.end = result[i + 1]!.start;
+  }
+  return result;
+}
+
+// Inside a turn that doesn't fit whole, walk forward from start+1 looking for
+// the largest suffix that fits the remaining budget. Returns the keep-start
+// index (the first preserved message) or undefined if no suffix fits.
+function splitTurn(
+  messages: CompactionMessage[],
+  turn: Turn,
+  budget: number,
+): { start: number; id: string } | undefined {
+  if (budget <= 0) return undefined;
+  if (turn.end - turn.start <= 1) return undefined;
+  for (let start = turn.start + 1; start < turn.end; start++) {
+    const size = estimate(messages.slice(start, turn.end));
+    if (size > budget) continue;
+    return { start, id: messages[start]!.id };
+  }
+  return undefined;
+}
+
+export interface SelectResult {
+  head: CompactionMessage[];
+  tail_start_id: string | undefined;
+}
+
+// Choose the boundary between the "head" (to be summarized) and the "tail"
+// (preserved verbatim). Strategy:
+//   1. Reserve a budget for the recent tail. Default ranges [2k, 8k] tokens
+//      with 25% of usable() as the target.
+//   2. Take the last `tail_turns` user-turns; greedily fit from newest back.
+//   3. If the next-older turn doesn't fit whole, split it mid-turn.
+//   4. If we couldn't keep anything OR everything fit (keep.start === 0),
+//      return full-preserve (no compaction this round).
+export function select(
+  messages: CompactionMessage[],
+  contextLimit: number,
+  tailTurns: number = DEFAULT_TAIL_TURNS,
+): SelectResult {
+  if (tailTurns <= 0) return { head: messages, tail_start_id: undefined };
+  const budget = Math.min(
+    MAX_PRESERVE_RECENT_TOKENS,
+    Math.max(MIN_PRESERVE_RECENT_TOKENS, Math.floor(usable(contextLimit) * 0.25)),
+  );
+
+  const all = turns(messages);
+  if (all.length === 0) return { head: messages, tail_start_id: undefined };
+  const recent = all.slice(-tailTurns);
+
+  let total = 0;
+  let keep: { start: number; id: string } | undefined;
+  for (let i = recent.length - 1; i >= 0; i--) {
+    const turn = recent[i]!;
+    const size = estimate(messages.slice(turn.start, turn.end));
+    if (total + size <= budget) {
+      total += size;
+      keep = { start: turn.start, id: turn.id };
+      continue;
+    }
+    const remaining = budget - total;
+    const split = splitTurn(messages, turn, remaining);
+    if (split) keep = split;
+    break;
+  }
+
+  if (!keep || keep.start === 0) {
+    return { head: messages, tail_start_id: undefined };
+  }
+  return {
+    head: messages.slice(0, keep.start),
+    tail_start_id: keep.id,
+  };
+}
+
+// === prompt assembly ===
+
+// Build the final user message that asks the model to (re)produce the
+// anchored summary. `context` is reserved for future plugin injection;
+// callers pass [] today.
+export function buildPrompt(
+  previousSummary: string | undefined,
+  context: string[],
+): string {
+  const anchor = previousSummary
+    ? [
+        'Update the anchored summary below using the conversation history above.',
+        'Preserve still-true details, remove stale details, and merge in the new facts.',
+        '<previous-summary>',
+        previousSummary,
+        '</previous-summary>',
+      ].join('\n')
+    : 'Create a new anchored summary from the conversation history above.';
+  return [anchor, SUMMARY_TEMPLATE, ...context].join('\n\n');
+}
+
+// === OpenAI conversion (compaction-local; intentionally does NOT call
+// inference.ts buildMessagesPayload because that uses the legacy "find latest
+// kind='compact' marker and skip everything before it" shortcircuit, which
+// would silently drop pre-legacy-compact history before the LLM sees it.
+// Compaction wants to send the entire head, full stop.) ===
+
+interface OpenAiMessage {
+  role: 'system' | 'user' | 'assistant' | 'tool';
+  content: string | null;
+  tool_calls?: Array<{
+    id: string;
+    type: 'function';
+    function: { name: string; arguments: string };
+  }>;
+  tool_call_id?: string;
+}
+
+function isCapHitSentinel(m: CompactionMessage): boolean {
+  return m.role === 'system' && m.metadata != null && m.metadata.kind === 'cap_hit';
+}
+
+function buildHeadPayload(head: CompactionMessage[]): OpenAiMessage[] {
+  const out: OpenAiMessage[] = [];
+  for (const m of head) {
+    if (isCapHitSentinel(m)) continue;
+    if (m.role === 'assistant' && (m.status === 'streaming' || m.status === 'cancelled')) continue;
+    if (m.kind === 'compact') {
+      // Legacy compact row — pass through as system context. The new
+      // anchored summary will subsume it, but the LLM should see it during
+      // the bridging round so it can carry forward the still-true bits.
+      out.push({ role: 'system', content: m.content });
+      continue;
+    }
+    if (m.summary) {
+      // Defense in depth: process() filters these out of the select-input
+      // already. If one slips through, render it as assistant content so we
+      // never crash here.
+      out.push({ role: 'assistant', content: m.content });
+      continue;
+    }
+    if (m.role === 'tool') {
+      const tr = m.tool_results;
+      if (!tr) continue;
+      const outputText = tr.error
+        ? `error: ${tr.error}`
+        : typeof tr.output === 'string'
+          ? tr.output
+          : JSON.stringify(tr.output);
+      out.push({ role: 'tool', content: outputText, tool_call_id: tr.tool_call_id });
+      continue;
+    }
+    if (m.role === 'assistant') {
+      const msg: OpenAiMessage = {
+        role: 'assistant',
+        content: m.content && m.content.length > 0 ? m.content : null,
+      };
+      if (m.tool_calls && m.tool_calls.length > 0) {
+        msg.tool_calls = m.tool_calls.map((tc) => ({
+          id: tc.id,
+          type: 'function' as const,
+          function: { name: tc.name, arguments: JSON.stringify(tc.args) },
+        }));
+      }
+      out.push(msg);
+      continue;
+    }
+    out.push({ role: 'user', content: m.content });
+  }
+  return out;
+}
+
+// === llama-swap call ===
+
+// Non-streaming completion. Opencode streams; for a one-shot summary call a
+// single POST is less code and the latency hit is acceptable (the user
+// doesn't see this directly — useSessionStream emits the toast + refetches
+// on the 'compacted' frame).
+interface CompletionResult {
+  content: string;
+  promptTokens: number;
+  completionTokens: number;
+  nCtx: number | null;
+}
+
+async function callLlamaSwap(
+  config: Config,
+  model: string,
+  messages: OpenAiMessage[],
+  log: FastifyBaseLogger,
+): Promise<CompletionResult> {
+  const res = await fetch(`${config.LLAMA_SWAP_URL}/v1/chat/completions`, {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ model, messages, stream: false }),
+  });
+  if (!res.ok) {
+    const text = await res.text().catch(() => '');
+    throw new Error(`llama-swap returned ${res.status}: ${text.slice(0, 200)}`);
+  }
+  const json = (await res.json()) as {
+    choices?: Array<{ message?: { content?: string } }>;
+    usage?: { prompt_tokens?: number; completion_tokens?: number };
+    timings?: { n_ctx?: number };
+  };
+  const content = json.choices?.[0]?.message?.content ?? '';
+  const promptTokens = json.usage?.prompt_tokens ?? 0;
+  const completionTokens = json.usage?.completion_tokens ?? 0;
+  const nCtx = typeof json.timings?.n_ctx === 'number' ? json.timings.n_ctx : null;
+  log.debug({ promptTokens, completionTokens, nCtx, chars: content.length }, 'compaction llm complete');
+  return { content, promptTokens, completionTokens, nCtx };
+}
+
+// === entry point ===
+
+export interface ProcessInput {
+  sql: Sql;
+  config: Config;
+  log: FastifyBaseLogger;
+  broker: Broker;
+  chatId: string;
+}
+
+// Runs one round of anchored rolling compaction on `chatId`. No-ops cleanly
+// (clearing needs_compaction) when there's nothing reasonable to compact.
+// Throws on LLM failure — callers decide whether to log+swallow or surface.
+export async function process(input: ProcessInput): Promise<void> {
+  const { sql, config, log, broker, chatId } = input;
+
+  // 1. Resolve chat → session for model + WS publish channel.
+  const chatRows = await sql<{ id: string; session_id: string }[]>`
+    SELECT id, session_id FROM chats WHERE id = ${chatId}
+  `;
+  if (chatRows.length === 0) {
+    log.warn({ chatId }, 'compaction: chat not found');
+    return;
+  }
+  const chat = chatRows[0]!;
+  const sessionId = chat.session_id;
+
+  const sessRows = await sql<{ id: string; model: string }[]>`
+    SELECT id, model FROM sessions WHERE id = ${sessionId}
+  `;
+  if (sessRows.length === 0) {
+    log.warn({ chatId, sessionId }, 'compaction: session not found');
+    return;
+  }
+  const session = sessRows[0]!;
+
+  // 2. All currently-active messages in this chat (compacted_at IS NULL).
+  // ORDER BY (created_at, id) matches loadContext in inference.ts so the
+  // turns() boundary logic sees the same sequence the LLM will.
+  const messages = await sql<CompactionMessage[]>`
+    SELECT id, role, content, kind, summary, status, tool_calls, tool_results, metadata, created_at
+    FROM messages
+    WHERE chat_id = ${chatId} AND compacted_at IS NULL
+    ORDER BY created_at ASC, id ASC
+  `;
+  if (messages.length === 0) {
+    await sql`UPDATE chats SET needs_compaction = false WHERE id = ${chatId}`;
+    return;
+  }
+
+  // 3. Find the prior anchored summary (newest summary=true row). Its content
+  // becomes previousSummary — the anchor in the prompt. Filter it out of the
+  // select-input so we don't double-encode (it's already in the anchor text).
+  const previousSummary = messages.filter((m) => m.summary).at(-1)?.content;
+  const forSelect = messages.filter((m) => !m.summary);
+
+  // 4. Resolve a recent context limit. llama-swap reports timings.n_ctx per
+  // completion; we cache it on messages.ctx_max. Use the most recent value
+  // from any message in this chat (oldest assumption is the same model is
+  // still running). When unknown, fall back to model.context_limit-less
+  // defaults via the buffer-only path (see usable()).
+  const ctxRows = await sql<{ ctx_max: number | null }[]>`
+    SELECT ctx_max FROM messages
+    WHERE chat_id = ${chatId} AND ctx_max IS NOT NULL
+    ORDER BY created_at DESC LIMIT 1
+  `;
+  const contextLimit = ctxRows[0]?.ctx_max ?? 0;
+
+  // 5. Decide head / tail.
+  const sel = select(forSelect, contextLimit);
+  if (!sel.tail_start_id || sel.head.length === 0) {
+    // Full preserve — nothing to compact this round. Clear the flag so we
+    // don't loop. (Could happen when the chat is short or the budget swung
+    // wider after a model context bump.)
+    await sql`UPDATE chats SET needs_compaction = false WHERE id = ${chatId}`;
+    log.info({ chatId, contextLimit, msgCount: messages.length }, 'compaction: nothing to compact');
+    return;
+  }
+
+  // 6. Build the OpenAI request: head as user/assistant/tool turns + a final
+  // user message carrying buildPrompt(previousSummary, []). No system prompt
+  // — matches opencode (`system: []`); the template + anchor are sufficient.
+  const headPayload = buildHeadPayload(sel.head);
+  const finalUser: OpenAiMessage = { role: 'user', content: buildPrompt(previousSummary, []) };
+  const payload = [...headPayload, finalUser];
+
+  log.info(
+    {
+      chatId,
+      contextLimit,
+      headLen: sel.head.length,
+      tailStartId: sel.tail_start_id,
+      hadPrevSummary: previousSummary !== undefined,
+    },
+    'compaction: invoking model',
+  );
+
+  // 6a. Flip the chat dot amber for the duration of the LLM call + DB writes.
+  // Same { type: 'chat_status', status: 'working', at } shape inference.ts
+  // emits at runner enqueue. publishUser → broadcasts on the per-user channel
+  // (all devices / tabs see it) since chat_status is a user-channel frame in
+  // BooCode (see useChatStatus.ts, which is the consumer).
+  broker.publishUser('default', {
+    type: 'chat_status',
+    chat_id: chatId,
+    status: 'working',
+    at: new Date().toISOString(),
+  });
+
+  // try/finally so the dot ALWAYS drops back to idle, even if the LLM call
+  // throws or a downstream DB write fails. The succeeded flag gates the
+  // 'compacted' frame + final log: we only signal completion to the UI when
+  // the new summary row actually landed.
+  let succeeded = false;
+  let newId = '';
+  let result: CompletionResult | undefined;
+  try {
+    // 7. Single completion (no tools). Throws on llama-swap failure.
+    result = await callLlamaSwap(config, session.model, payload, log);
+
+    // 8. Insert the new anchored summary row. role='assistant' per spec; the
+    // UI distinguishes via summary=true. tail_start_id points at the first
+    // preserved tail message so debug surfaces / future tools can reason
+    // about the boundary without re-deriving from compacted_at.
+    const insertRows = await sql<{ id: string }[]>`
+      INSERT INTO messages (
+        session_id, chat_id, role, content, kind, status,
+        summary, tail_start_id,
+        tokens_used, ctx_used, ctx_max,
+        created_at, finished_at
+      )
+      VALUES (
+        ${sessionId}, ${chatId}, 'assistant', ${result.content}, 'message', 'complete',
+        true, ${sel.tail_start_id},
+        ${result.completionTokens}, ${result.promptTokens}, ${result.nCtx},
+        clock_timestamp(), clock_timestamp()
+      )
+      RETURNING id
+    `;
+    newId = insertRows[0]!.id;
+
+    // 9. Mark every prior live message (head + prior summary) as compacted.
+    // Bound by "created_at strictly less than tail_start_id's created_at" so
+    // the preserved tail stays compacted_at=NULL. Exclude the new summary
+    // row we just inserted (it's "now", which is >= tail_start_id's
+    // created_at anyway, but defensive).
+    await sql`
+      UPDATE messages
+      SET compacted_at = clock_timestamp()
+      WHERE chat_id = ${chatId}
+        AND compacted_at IS NULL
+        AND id != ${newId}
+        AND created_at < (SELECT created_at FROM messages WHERE id = ${sel.tail_start_id})
+    `;
+
+    // 10. Clear the flag and bump the chat's updated_at so the sidebar
+    // reflects recent activity.
+    await sql`
+      UPDATE chats
+      SET needs_compaction = false, updated_at = clock_timestamp()
+      WHERE id = ${chatId}
+    `;
+
+    succeeded = true;
+  } finally {
+    // Always restore the dot. Status='idle' (not 'error') even on failure —
+    // the caller logs/re-surfaces the error separately; the dot doesn't
+    // need to stay red across reloads for a transient compaction blip.
+    broker.publishUser('default', {
+      type: 'chat_status',
+      chat_id: chatId,
+      status: 'idle',
+      at: new Date().toISOString(),
+    });
+  }
+
+  // 11. Tell the client. useSessionStream subscribes to the per-session WS
+  // channel; the handler refetches messages (so the new summary row + the
+  // compacted_at-stamped older rows render correctly) and fires a sonner
+  // toast. Order matters: idle must precede 'compacted' so the dot is
+  // already green by the time the refetch toast appears.
+  if (succeeded) {
+    broker.publish(sessionId, {
+      type: 'compacted',
+      session_id: sessionId,
+      chat_id: chatId,
+      summary_message_id: newId,
+    });
+    log.info(
+      {
+        chatId,
+        newId,
+        completionTokens: result?.completionTokens,
+        promptTokens: result?.promptTokens,
+      },
+      'compaction: complete',
+    );
+  }
+}

apps/server/src/services/inference.ts

@@ -21,6 +21,8 @@ import {
 import { PathScopeError, resolveProjectRoot } from './path_guard.js';
 import { maybeAutoNameChat } from './auto_name.js';
 import { getAgentById } from './agents.js';
+import * as compaction from './compaction.js';
+import type { Broker } from './broker.js';
 
 const BASE_SYSTEM_PROMPT = (projectPath: string) =>
   `You are BooCode Chat, a code investigation assistant. The user is working on a project located at ${projectPath}. Use the file-read tools (view_file, list_dir, grep, find_files) to investigate code when needed. Be concise. Cite file paths and line numbers when discussing code. Do not hallucinate file contents — read the file first. Tool results may be truncated; if so, narrow your query rather than guessing.`;
@@ -147,6 +149,12 @@ export interface InferenceContext {
   log: FastifyBaseLogger;
   publish: FramePublisher;
   publishUser: (frame: UserStreamFrame) => void;
+  // v1.11: passed through so compaction.process can publish 'compacted'
+  // frames on the same session WS channel useSessionStream subscribes to.
+  // Compaction is the only path that needs the raw broker handle (regular
+  // inference goes through `publish`); keeping a separate field avoids
+  // tempting other code paths into bypassing the session-id binding.
+  broker: Broker;
 }
 
 // Resolution order: base prompt < agent.system_prompt < user prompt, where
@@ -260,17 +268,48 @@ async function loadContext(
   if (projectRows.length === 0) return null;
   const project = projectRows[0]!;
 
+  // v1.11: filter compacted messages out of the inference assembly. The GET
+  // /api/sessions/:id/messages endpoint still returns everything (so the UI
+  // can show history with the summary card inline); only LLM payloads skip
+  // compacted rows. compacted_at IS NULL keeps the active summary + tail.
   const history = await sql<Message[]>`
     SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
            tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata
     FROM messages
-    WHERE chat_id = ${chatId}
+    WHERE chat_id = ${chatId} AND compacted_at IS NULL
     ORDER BY created_at ASC, id ASC
   `;
 
   return { session, project, history };
 }
 
+// v1.11: shared helper used after both finalizeCompletion and executeToolPhase
+// persist their token counts. Reads tokens off the just-UPDATEd row (which
+// the caller returns from RETURNING), runs compaction.isOverflow, and flips
+// chats.needs_compaction. The next runAssistantTurn invocation acts on it.
+// Silent on missing tokens — llama-swap occasionally omits usage on truncated
+// streams, and we'd rather miss one overflow than crash the inference path.
+async function maybeFlagForCompaction(
+  ctx: InferenceContext,
+  chatId: string,
+  updated: { tokens_used: number | null; ctx_used: number | null; ctx_max: number | null } | undefined,
+): Promise<void> {
+  if (!updated) return;
+  const promptTokens = updated.ctx_used;
+  const completionTokens = updated.tokens_used;
+  const contextLimit = updated.ctx_max;
+  if (typeof promptTokens !== 'number') return;
+  if (typeof completionTokens !== 'number') return;
+  if (typeof contextLimit !== 'number') return;
+  const overflow = compaction.isOverflow(
+    { prompt_tokens: promptTokens, completion_tokens: completionTokens },
+    contextLimit,
+  );
+  if (!overflow) return;
+  await ctx.sql`UPDATE chats SET needs_compaction = true WHERE id = ${chatId}`;
+  ctx.log.info({ chatId, promptTokens, completionTokens, contextLimit }, 'inference: flagged for compaction');
+}
+
 async function* sseLines(stream: ReadableStream<Uint8Array>): AsyncGenerator<string> {
   const reader = stream.getReader();
   const decoder = new TextDecoder('utf-8');
@@ -310,6 +349,70 @@ interface StreamOptions {
   temperature?: number;
 }
 
+// v1.10.5 Qwen-coder XML fallback. Some local models (notably qwen3-coder via
+// llama-swap) emit tool calls as inline XML inside delta.content rather than
+// the structured delta.tool_calls field. The XML shape is:
+//   <tool_call>
+//   <function=NAME>
+//   <parameter=KEY>
+//   VALUE
+//   </parameter>
+//   ...more parameters...
+//   </function>
+//   </tool_call>
+// Multiple <tool_call> blocks may appear back-to-back; they never nest.
+// streamCompletion buffers delta.content, extracts complete blocks, parses
+// them via parseXmlToolCall, and pushes synthetic entries into the existing
+// toolCallsBuffer alongside any native JSON-format tool calls.
+const XML_TOOL_OPEN = '<tool_call>';
+const XML_TOOL_CLOSE = '</tool_call>';
+
+function parseXmlToolCall(
+  block: string,
+): { name: string; args: Record<string, unknown> } | null {
+  const nameMatch = block.match(/<function=([^>]+)>/);
+  if (!nameMatch || !nameMatch[1]) return null;
+  const name = nameMatch[1].trim();
+  if (!name) return null;
+  const args: Record<string, unknown> = {};
+  // Non-greedy body so each <parameter=…>…</parameter> pair is matched
+  // independently even when multiple appear in the same block.
+  const paramRe = /<parameter=([^>]+)>([\s\S]*?)<\/parameter>/g;
+  for (const m of block.matchAll(paramRe)) {
+    const key = (m[1] ?? '').trim();
+    if (!key) continue;
+    const raw = (m[2] ?? '').trim();
+    try {
+      args[key] = JSON.parse(raw);
+    } catch {
+      args[key] = raw;
+    }
+  }
+  return { name, args };
+}
+
+// Locate the first character that begins (or completely contains) an
+// unfinished <tool_call> opener in `s`. Returns -1 when `s` can be flushed
+// to the client in full without risking a partial tag leak.
+//   Case 1: a full `<tool_call>` opener with no matching closer — caller
+//           must keep everything from that index forward until the next
+//           chunk arrives with the closer.
+//   Case 2: `s` ends with a strict prefix of `<tool_call>` (e.g. `<tool_c`).
+//           Caller must keep just that suffix in the buffer.
+// Note: case 1 assumes the calling loop already extracted every complete
+// <tool_call>…</tool_call> pair before reaching this check.
+function partialXmlOpenerStart(s: string): number {
+  const fullOpener = s.indexOf(XML_TOOL_OPEN);
+  if (fullOpener !== -1) return fullOpener;
+  const lastLt = s.lastIndexOf('<');
+  if (lastLt === -1) return -1;
+  const suffix = s.slice(lastLt);
+  if (XML_TOOL_OPEN.startsWith(suffix) && suffix.length < XML_TOOL_OPEN.length) {
+    return lastLt;
+  }
+  return -1;
+}
+
 async function streamCompletion(
   ctx: InferenceContext,
   model: string,
@@ -344,6 +447,10 @@ async function streamCompletion(
   }
 
   let content = '';
+  // v1.10.5: holds delta.content bytes that may contain a partial XML tool
+  // call. Anything not part of a (possibly forming) <tool_call>…</tool_call>
+  // pair is flushed to content + onDelta as soon as we know it's safe.
+  let pendingBuffer = '';
   let finishReason: string | null = null;
   let promptTokens: number | null = null;
   let completionTokens: number | null = null;
@@ -377,8 +484,50 @@ async function streamCompletion(
     if (!choice) continue;
     const delta = choice.delta ?? {};
     if (typeof delta.content === 'string' && delta.content.length > 0) {
-      content += delta.content;
-      onDelta(delta.content);
+      // v1.10.5 XML fallback. Append, then extract any complete tool_call
+      // blocks before deciding what's safe to flush as visible content.
+      pendingBuffer += delta.content;
+      while (true) {
+        const startIdx = pendingBuffer.indexOf(XML_TOOL_OPEN);
+        if (startIdx === -1) break;
+        const closeIdx = pendingBuffer.indexOf(XML_TOOL_CLOSE, startIdx);
+        if (closeIdx === -1) break;
+        const blockEnd = closeIdx + XML_TOOL_CLOSE.length;
+        const block = pendingBuffer.slice(startIdx, blockEnd);
+        // Any text before the opener is plain content — flush it now.
+        if (startIdx > 0) {
+          const before = pendingBuffer.slice(0, startIdx);
+          content += before;
+          onDelta(before);
+        }
+        const parsedCall = parseXmlToolCall(block);
+        if (parsedCall) {
+          const synthIdx = toolCallsBuffer.size;
+          toolCallsBuffer.set(synthIdx, {
+            id: `xml_call_${synthIdx}`,
+            name: parsedCall.name,
+            argsText: JSON.stringify(parsedCall.args),
+          });
+        }
+        // If parsing failed we still drop the block — emitting unparseable
+        // XML to the chat would look worse than silently swallowing it.
+        pendingBuffer = pendingBuffer.slice(blockEnd);
+      }
+      // After all complete blocks are out, hold back any (partial or full)
+      // unclosed opener; flush the rest.
+      const partialIdx = partialXmlOpenerStart(pendingBuffer);
+      if (partialIdx >= 0) {
+        if (partialIdx > 0) {
+          const flush = pendingBuffer.slice(0, partialIdx);
+          content += flush;
+          onDelta(flush);
+        }
+        pendingBuffer = pendingBuffer.slice(partialIdx);
+      } else if (pendingBuffer.length > 0) {
+        content += pendingBuffer;
+        onDelta(pendingBuffer);
+        pendingBuffer = '';
+      }
     }
     if (Array.isArray(delta.tool_calls)) {
       for (const tc of delta.tool_calls) {
@@ -393,6 +542,15 @@ async function streamCompletion(
     if (choice.finish_reason) finishReason = choice.finish_reason;
   }
 
+  // v1.10.5: if the stream ended mid-XML (e.g. model truncated, no closer
+  // ever arrived), flush whatever was buffered as plain content so it isn't
+  // silently dropped. Better to show a stray `<tool_call>` than vanish text.
+  if (pendingBuffer.length > 0) {
+    content += pendingBuffer;
+    onDelta(pendingBuffer);
+    pendingBuffer = '';
+  }
+
   const toolCalls: ToolCall[] = [];
   for (const [, t] of [...toolCallsBuffer.entries()].sort(([a], [b]) => a - b)) {
     let args: Record<string, unknown> = {};
@@ -639,6 +797,10 @@ async function executeToolPhase(
     WHERE id = ${assistantMessageId}
     RETURNING tokens_used, ctx_used, ctx_max, finished_at
   `;
+  // v1.11: flag for compaction if this turn pushed us over the usable budget.
+  // We never compact mid-loop (the recursive runAssistantTurn keeps tools
+  // flowing); the flag fires on the NEXT turn's pre-fetch hook above.
+  await maybeFlagForCompaction(ctx, chatId, updated);
   const [toolSessRow] = await ctx.sql<{ project_id: string; name: string; updated_at: string }[]>`
     UPDATE sessions SET updated_at = clock_timestamp()
     WHERE id = ${sessionId}
@@ -770,6 +932,9 @@ async function finalizeCompletion(
     WHERE id = ${assistantMessageId}
     RETURNING tokens_used, ctx_used, ctx_max, finished_at
   `;
+  // v1.11: flag for compaction on the terminal turn too. Catches the common
+  // case of a turn that hit the limit without invoking tools.
+  await maybeFlagForCompaction(ctx, chatId, updated);
   const [completeSessRow] = await ctx.sql<{ project_id: string; name: string; updated_at: string }[]>`
     UPDATE sessions SET updated_at = clock_timestamp()
     WHERE id = ${sessionId}
@@ -808,6 +973,29 @@ async function runAssistantTurn(
 ): Promise<void> {
   const { sessionId, chatId } = args;
 
+  // v1.11: if the prior turn flagged this chat for compaction, run it first
+  // so loadContext below reads the post-compaction history. We swallow
+  // compaction failures (clearing the flag so we don't loop) and proceed
+  // with the un-compacted history — a slow turn that hits the model's
+  // hard limit is recoverable; a dead session is not.
+  const chatFlag = await ctx.sql<{ needs_compaction: boolean }[]>`
+    SELECT needs_compaction FROM chats WHERE id = ${chatId}
+  `;
+  if (chatFlag[0]?.needs_compaction) {
+    try {
+      await compaction.process({
+        sql: ctx.sql,
+        config: ctx.config,
+        log: ctx.log,
+        broker: ctx.broker,
+        chatId,
+      });
+    } catch (err) {
+      ctx.log.warn({ err, chatId }, 'auto-compaction failed; clearing flag and proceeding');
+      await ctx.sql`UPDATE chats SET needs_compaction = false WHERE id = ${chatId}`;
+    }
+  }
+
   const loaded = await loadContext(ctx.sql, sessionId, chatId);
   if (!loaded) {
     ctx.log.warn({ sessionId }, 'inference: session or project missing');
@@ -1118,81 +1306,6 @@ async function insertCapHitSentinel(
   });
 }
 
-const COMPACT_SYSTEM_PROMPT =
-  'Summarize the preceding conversation into a dense but complete context paragraph. Preserve all key facts, decisions, file paths, code patterns, and action items. Do not add any new information. Output only the summary paragraph.';
-
-async function runCompact(
-  ctx: InferenceContext,
-  sessionId: string,
-  chatId: string,
-  compactMessageId: string
-): Promise<void> {
-  const loaded = await loadContext(ctx.sql, sessionId, chatId);
-  if (!loaded) return;
-  const { session, project, history } = loaded;
-
-  const messagesForSummary = buildMessagesPayload(session, project,
-    history.filter((m) => m.id !== compactMessageId)
-  );
-  messagesForSummary.push({
-    role: 'system',
-    content: COMPACT_SYSTEM_PROMPT,
-  });
-
-  ctx.publish(sessionId, {
-    type: 'message_started',
-    message_id: compactMessageId,
-    chat_id: chatId,
-    role: 'assistant',
-  });
-
-  let content = '';
-  try {
-    const result = await streamCompletion(
-      ctx,
-      session.model,
-      messagesForSummary,
-      { tools: null },
-      (delta) => {
-        content += delta;
-        ctx.publish(sessionId, {
-          type: 'delta',
-          message_id: compactMessageId,
-          chat_id: chatId,
-          content: delta,
-        });
-      }
-    );
-    content = result.content;
-  } catch (err) {
-    const errMsg = err instanceof Error ? err.message : String(err);
-    await ctx.sql`
-      UPDATE messages SET status = 'failed', content = ${content}, finished_at = clock_timestamp()
-      WHERE id = ${compactMessageId}
-    `;
-    ctx.publish(sessionId, {
-      type: 'error',
-      message_id: compactMessageId,
-      chat_id: chatId,
-      error: errMsg,
-    });
-    return;
-  }
-
-  const preCompactCount = history.filter((m) => m.id !== compactMessageId && m.kind !== 'compact').length;
-  const summary = `[Context compacted — ${preCompactCount} messages summarized]\n\n${content}`;
-
-  await ctx.sql`
-    UPDATE messages SET content = ${summary}, status = 'complete', finished_at = clock_timestamp()
-    WHERE id = ${compactMessageId}
-  `;
-  ctx.publish(sessionId, {
-    type: 'message_complete',
-    message_id: compactMessageId,
-    chat_id: chatId,
-  });
-}
-
 interface InferenceRegistration {
   controller: AbortController;
   completed: Promise<void>;
@@ -1209,6 +1322,10 @@ export function createInferenceRunner(
       const callCtx: InferenceContext = {
         ...ctx,
         publishUser: (frame) => publishUserFn(user, frame),
+        // v1.11: broker comes in via ctx (set at registration time). Repeated
+        // here so the destructure carries it onto the per-call ctx without
+        // having to add it to every enqueue/cancel signature individually.
+        broker: ctx.broker,
       };
       // v1.8 mobile-tabs: announce working before the async loop starts so
       // every device subscribed to the user channel sees the amber dot.
@@ -1238,20 +1355,6 @@ export function createInferenceRunner(
       })();
     },
 
-    enqueueCompact(sessionId: string, chatId: string, compactMessageId: string, user: string) {
-      const callCtx: InferenceContext = {
-        ...ctx,
-        publishUser: (frame) => publishUserFn(user, frame),
-      };
-      void (async () => {
-        try {
-          await runCompact(callCtx, sessionId, chatId, compactMessageId);
-        } catch (err) {
-          callCtx.log.error({ err }, 'unhandled compact error');
-        }
-      })();
-    },
-
     async cancel(_sessionId: string, chatId: string): Promise<boolean> {
       const reg = registry.get(chatId);
       if (!reg) return false;

apps/server/src/types/api.ts

@@ -159,6 +159,12 @@ export interface Message {
   // v1.8.2: per-message metadata. See MessageMetadata for the discriminated
   // shapes currently in use.
   metadata: MessageMetadata | null;
+  // v1.11: anchored rolling compaction. Optional so consumers that SELECT
+  // the pre-v1.11 column set still type-check. See compaction.ts +
+  // schema.sql for semantics.
+  summary?: boolean;
+  tail_start_id?: string | null;
+  compacted_at?: string | null;
 }
 
 export interface ModelInfo {

apps/web/package.json

@@ -12,6 +12,11 @@
   "dependencies": {
     "@fontsource-variable/inter": "^5.2.8",
     "@fontsource-variable/jetbrains-mono": "^5.2.8",
+    "@xterm/addon-fit": "0.10.0",
+    "@xterm/addon-search": "^0.15.0",
+    "@xterm/addon-web-links": "0.11.0",
+    "@xterm/addon-webgl": "^0.19.0",
+    "@xterm/xterm": "5.5.0",
     "class-variance-authority": "^0.7.1",
     "clsx": "^2.1.1",
     "lucide-react": "^1.16.0",
@@ -26,10 +31,7 @@
     "shiki": "^1.29.2",
     "sonner": "^2.0.7",
     "tailwind-merge": "^3.6.0",
-    "tw-animate-css": "^1.4.0",
-    "xterm": "^5.3.0",
-    "xterm-addon-fit": "^0.8.0",
-    "xterm-addon-web-links": "^0.9.0"
+    "tw-animate-css": "^1.4.0"
   },
   "devDependencies": {
     "@tailwindcss/postcss": "^4.3.0",

apps/web/src/App.tsx

@@ -68,8 +68,13 @@ function AppShell() {
   // theme class on <html> is correct before any child renders.
   useTheme();
   useUserEvents();
+  // v1.10.8c: h-dvh (dynamic viewport) instead of h-screen (100vh) so the
+  // root height excludes the iOS URL-bar overlay area. Without this, every
+  // descendant — including the terminal pane — measures itself against a
+  // height that extends behind the URL bar, and xterm allocates extra rows
+  // that scroll out of reach on iPhone.
   return (
-    <div className="h-screen flex bg-background text-foreground">
+    <div className="h-dvh flex bg-background text-foreground">
       <ProjectSidebar />
       <MobileBackdrop />
       <main className="flex-1 flex flex-col min-w-0">

apps/web/src/api/client.ts

@@ -168,8 +168,11 @@ export const api = {
       request<void>(`/api/chats/${chatId}`, { method: 'DELETE' }),
     messages: (chatId: string) =>
       request<Message[]>(`/api/chats/${chatId}/messages`),
+    // v1.11: anchored-rolling compaction. POST awaits the LLM call inside
+    // the route's lifecycle; the new summary row arrives via the 'compacted'
+    // WS frame (useSessionStream refetches + toasts).
     compact: (chatId: string) =>
-      request<{ compact_message_id: string }>(`/api/chats/${chatId}/compact`, { method: 'POST' }),
+      request<{ ok: true }>(`/api/chats/${chatId}/compact`, { method: 'POST' }),
     stop: (chatId: string) =>
       request<{ stopped: boolean }>(`/api/chats/${chatId}/stop`, { method: 'POST' }),
     forceSend: (chatId: string, content: string) =>
@@ -264,18 +267,23 @@ export const api = {
 
   // v1.10 booterm: REST control plane for terminal panes. WebSocket attach
   // lives at /ws/term/sessions/:sid/panes/:pid (handled directly by
-  // TerminalPane). All three endpoints are tolerant of empty bodies on the
-  // POSTs that don't take parameters.
+  // TerminalPane). v1.10.8c: resize moved in-band onto the WebSocket as a
+  // `{type:"resize",cols,rows}` text frame — the old /resize HTTP endpoint is
+  // gone, eliminating the race between WS attach and PTY-map registration.
   terminals: {
-    start: (sessionId: string, paneId: string) =>
-      request<{ tmux_window: string }>(
+    // cols/rows are optional. When passed, booterm sizes the per-pane tmux
+    // session at creation time so the inner bash (and any TUI it spawns) is
+    // born with the correct PTY dimensions instead of tmux's 80x24 default.
+    start: (sessionId: string, paneId: string, cols?: number, rows?: number) =>
+      request<{ tmux_session: string }>(
         `/api/term/sessions/${sessionId}/panes/${paneId}/start`,
-        { method: 'POST' },
-      ),
-    resize: (sessionId: string, paneId: string, cols: number, rows: number) =>
-      request<{ ok: true }>(
-        `/api/term/sessions/${sessionId}/panes/${paneId}/resize`,
-        { method: 'POST', body: JSON.stringify({ cols, rows }) },
+        {
+          method: 'POST',
+          body:
+            cols !== undefined && rows !== undefined
+              ? JSON.stringify({ cols, rows })
+              : undefined,
+        },
       ),
     kill: (sessionId: string, paneId: string) =>
       request<{ ok: true }>(

apps/web/src/api/types.ts

@@ -145,6 +145,19 @@ export interface Message {
   // v1.8.2: per-message metadata; see MessageMetadata. null for the vast
   // majority of messages.
   metadata: MessageMetadata | null;
+  // v1.11: anchored rolling compaction fields. Optional on the wire so that
+  // older API responses (or test fixtures) parse without explicit nulls.
+  //   summary       — true on the assistant row that holds the active
+  //                   anchored summary. Render via SummaryCard.
+  //   tail_start_id — first preserved tail message the summary covers up to
+  //                   (exclusive). Diagnostic only on the client.
+  //   compacted_at  — set on rows that are "behind the curtain" of the
+  //                   current summary. Returned by the GET endpoint so the
+  //                   UI can show history, but the server-side inference
+  //                   assembly filters these out.
+  summary?: boolean;
+  tail_start_id?: string | null;
+  compacted_at?: string | null;
 }
 
 export interface ModelInfo {
@@ -305,6 +318,11 @@ export type WsFrame =
     }
   | { type: 'messages_deleted'; message_ids: string[]; chat_id?: string }
   | { type: 'chat_renamed'; chat_id: string; name: string }
+  // v1.11: published by services/compaction.ts after the new anchored
+  // summary row lands. Carries the new summary row id for diagnostics; the
+  // session-stream handler ignores the id and re-fetches the full message
+  // list (the cohort of compacted_at-stamped rows changed too).
+  | { type: 'compacted'; session_id: string; chat_id: string; summary_message_id: string }
   // v1.8.2: `reason` discriminates structured failures (the UI prefers it
   // over `error` text when present).
   | { type: 'error'; message_id?: string; chat_id?: string; error: string; reason?: ErrorReason };

apps/web/src/components/ChatInput.tsx

@@ -25,6 +25,7 @@ import { AgentPicker } from '@/components/AgentPicker';
 import { SkillSlashCommand } from '@/components/SkillSlashCommand';
 import { api } from '@/api/client';
 import { sessionEvents } from '@/hooks/sessionEvents';
+import { chatInputsRegistry, sendToChat } from '@/lib/events';
 import { useSkills } from '@/hooks/useSkills';
 import { useViewport } from '@/hooks/useViewport';
 
@@ -51,9 +52,16 @@ interface Props {
   // empty). Callers wire this to api.chats.skillInvoke. Omitting the prop
   // disables slash-command dispatch (input is sent as literal text).
   onSlashCommand?: (skillName: string, userMessage: string) => void | Promise<void>;
+  // v1.10.4: send-to-chat reverse path. When chatId is provided, this input
+  // registers in chatInputsRegistry so the terminal floating menu can list
+  // it, and subscribes to sendToChat events scoped to this chatId. Receiving
+  // an event appends the text to the current draft (with a newline separator
+  // when non-empty) and focuses — no auto-send.
+  chatId?: string;
+  chatLabel?: string;
 }
 
-export function ChatInput({ disabled, projectId, agentId, onAgentChange, sessionId, webSearchEnabled, onSend, onForceSend, onSlashCommand }: Props) {
+export function ChatInput({ disabled, projectId, agentId, onAgentChange, sessionId, webSearchEnabled, onSend, onForceSend, onSlashCommand, chatId, chatLabel }: Props) {
   const { isMobile } = useViewport();
   const [value, setValue] = useState('');
   const [busy, setBusy] = useState(false);
@@ -107,6 +115,35 @@ export function ChatInput({ disabled, projectId, agentId, onAgentChange, session
     });
   }, []);
 
+  // v1.10.4: register this input in the chat-input registry so the terminal
+  // pane's "Send to chat" menu can list it. Re-registers when chatLabel
+  // changes (e.g. rename) so the menu reflects the current name.
+  useEffect(() => {
+    if (!chatId) return;
+    return chatInputsRegistry.register(chatId, chatLabel ?? 'Chat', () => {
+      textareaRef.current?.focus();
+    });
+  }, [chatId, chatLabel]);
+
+  // v1.10.4: subscribe to send_to_chat events scoped by chatId. Appends the
+  // payload text to the current draft (with a newline separator if the
+  // draft is non-empty) and focuses the textarea. Does NOT auto-submit.
+  useEffect(() => {
+    if (!chatId) return;
+    return sendToChat.subscribe(({ chat_id, text }) => {
+      if (chat_id !== chatId) return;
+      setValue((prev) => (prev.length === 0 ? text : `${prev}\n${text}`));
+      requestAnimationFrame(() => {
+        const ta = textareaRef.current;
+        if (!ta) return;
+        ta.focus();
+        // Put caret at end so the user can keep typing immediately.
+        const end = ta.value.length;
+        ta.selectionStart = ta.selectionEnd = end;
+      });
+    });
+  }, [chatId]);
+
   function removeAttachment(id: string) {
     setAttachments(prev => prev.filter(a => a.id !== id));
   }

apps/web/src/components/ChatTabBar.tsx

@@ -1,5 +1,5 @@
 import { useState } from 'react';
-import { History, MessageSquare, Plus, X } from 'lucide-react';
+import { Bot, History, MessageSquare, Plus, Terminal, X } from 'lucide-react';
 import type { Chat, WorkspacePane } from '@/api/types';
 import { StatusDot } from '@/components/StatusDot';
 import {
@@ -9,6 +9,12 @@ import {
   ContextMenuSeparator,
   ContextMenuTrigger,
 } from '@/components/ui/context-menu';
+import {
+  DropdownMenu,
+  DropdownMenuContent,
+  DropdownMenuItem,
+  DropdownMenuTrigger,
+} from '@/components/ui/dropdown-menu';
 import { useLongPress } from '@/hooks/useLongPress';
 import { cn } from '@/lib/utils';
 
@@ -20,7 +26,7 @@ interface Props {
   onCloseOthers: (chatId: string) => void;
   onCloseToRight: (chatId: string) => void;
   onCloseAll: () => void;
-  onNewChat: () => void;
+  onAddPane: (kind: 'chat' | 'terminal' | 'agent') => void;
   onShowHistory: () => void;
   onRename: (chatId: string, name: string) => Promise<void>;
   onRemovePane?: () => void;
@@ -34,7 +40,7 @@ export function ChatTabBar({
   onCloseOthers,
   onCloseToRight,
   onCloseAll,
-  onNewChat,
+  onAddPane,
   onShowHistory,
   onRename,
   onRemovePane,
@@ -125,7 +131,7 @@ export function ChatTabBar({
               </div>
             </ContextMenuTrigger>
             <ContextMenuContent>
-              <ContextMenuItem onSelect={() => onNewChat()}>
+              <ContextMenuItem onSelect={() => onAddPane('chat')}>
                 New chat
               </ContextMenuItem>
               <ContextMenuSeparator />
@@ -164,15 +170,29 @@ export function ChatTabBar({
       )}
 
       <div className="flex items-center ml-auto gap-0.5 px-1 shrink-0">
+        <DropdownMenu>
+          <DropdownMenuTrigger asChild>
             <button
               type="button"
-          onClick={onNewChat}
               className="inline-flex items-center justify-center p-1 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:min-h-[44px] max-md:min-w-[44px]"
-          aria-label="New chat"
-          title="New chat"
+              aria-label="New pane"
+              title="New pane"
             >
               <Plus size={12} />
             </button>
+          </DropdownMenuTrigger>
+          <DropdownMenuContent align="end" className="min-w-40">
+            <DropdownMenuItem onSelect={() => onAddPane('chat')}>
+              <MessageSquare size={14} /> New chat
+            </DropdownMenuItem>
+            <DropdownMenuItem onSelect={() => onAddPane('terminal')}>
+              <Terminal size={14} /> New terminal
+            </DropdownMenuItem>
+            <DropdownMenuItem onSelect={() => onAddPane('agent')}>
+              <Bot size={14} /> New agent
+            </DropdownMenuItem>
+          </DropdownMenuContent>
+        </DropdownMenu>
         <button
           type="button"
           onClick={onShowHistory}

apps/web/src/components/MessageBubble.tsx

@@ -537,7 +537,70 @@ function CompactCard({ message, sessionChats }: { message: Message; sessionChats
   );
 }
 
+// v1.11 anchored rolling summary. Inserted by services/compaction.ts as a
+// role='assistant', summary=true row. Distinct from legacy CompactCard
+// (which renders the kind='compact' system rows produced by v1.10 /compact).
+// Collapsed by default; header shows the timestamp; body renders the
+// summary markdown when expanded. Copy button matches CompactCard's affordance.
+function SummaryCard({ message }: { message: Message }) {
+  const [expanded, setExpanded] = useState(false);
+  const [copied, setCopied] = useState(false);
+
+  // Use finished_at when available (that's when the summary actually landed);
+  // fall back to created_at for any row missing it. Both are ISO strings.
+  const ts = message.finished_at ?? message.created_at;
+  const headerTs = ts ? new Date(ts).toLocaleString() : '';
+
+  async function handleCopy() {
+    try {
+      await navigator.clipboard.writeText(message.content);
+      setCopied(true);
+      setTimeout(() => setCopied(false), 1200);
+      toast.success('Summary copied to clipboard');
+    } catch {
+      toast.error('Copy failed');
+    }
+  }
+
+  return (
+    <div className="rounded-lg border border-primary/30 bg-primary/5 text-sm">
+      <div className="flex items-center gap-2 px-3 py-2">
+        <button
+          type="button"
+          onClick={() => setExpanded(!expanded)}
+          className="flex items-center gap-1.5 flex-1 min-w-0 text-left text-muted-foreground hover:text-foreground"
+        >
+          {expanded ? <ChevronDown size={14} /> : <ChevronRight size={14} />}
+          <span className="text-xs font-medium truncate">
+            Compacted summary — {headerTs}
+          </span>
+        </button>
+        <button
+          type="button"
+          onClick={() => void handleCopy()}
+          className="p-1 rounded hover:bg-muted text-muted-foreground"
+          aria-label="Copy summary"
+          title="Copy summary"
+        >
+          {copied ? <Check size={12} /> : <Copy size={12} />}
+        </button>
+      </div>
+      {expanded && (
+        <div className="px-3 pb-3 text-xs leading-relaxed border-t pt-2">
+          <MarkdownBody content={message.content} />
+        </div>
+      )}
+    </div>
+  );
+}
+
 export function MessageBubble({ message, sessionChats, capHitInfo }: Props) {
+  // v1.11: anchored rolling summary row. Checked BEFORE the kind==='compact'
+  // branch because summary=true never coexists with kind='compact' (new
+  // compactions emit role='assistant' rows with kind='message'+summary=true).
+  if (message.summary) {
+    return <SummaryCard message={message} />;
+  }
   if (message.kind === 'compact') {
     return <CompactCard message={message} sessionChats={sessionChats} />;
   }

apps/web/src/components/MobileTabSwitcher.tsx

@@ -1,4 +1,4 @@
-import { useState } from 'react';
+import { useRef, useState } from 'react';
 import {
   Bot,
   ChevronDown,
@@ -31,6 +31,15 @@ interface Props {
   onRenameChat: (chatId: string, name: string) => Promise<void>;
 }
 
+// v1.10.4: swipe-left-to-close on the pane pill. Threshold matches the spec
+// (80px). Vertical bail-out at 30px because the pill sits inside a vertical
+// scrollable header — diagonal-ish swipes shouldn't accidentally close panes.
+const SWIPE_CLOSE_PX = 80;
+const SWIPE_VERTICAL_BAIL_PX = 30;
+// Visual cap: pill translates left up to this much. Past this, dragX stays
+// pinned so the user has a clear "release to close" indicator.
+const SWIPE_VISUAL_CAP = 120;
+
 function paneIcon(kind: WorkspacePane['kind']) {
   if (kind === 'terminal') return <Terminal size={14} />;
   if (kind === 'agent') return <Bot size={14} />;
@@ -70,11 +79,66 @@ export function MobileTabSwitcher({
   const [open, setOpen] = useState(false);
   const [renamingChatId, setRenamingChatId] = useState<string | null>(null);
   const [renameValue, setRenameValue] = useState('');
+  // v1.10.4: swipe-left state. dragX is the (clamped, negative) drag offset
+  // in px. suppressClick latches when a swipe completes so the trailing click
+  // doesn't pop open the BottomSheet on the just-closed pane.
+  const [dragX, setDragX] = useState(0);
+  const swipeStart = useRef<{ x: number; y: number } | null>(null);
+  const swipeBailed = useRef(false);
+  const suppressClick = useRef(false);
 
   const active = panes[activePaneIdx];
   const activeLabel = active ? paneLabel(active, chats) : 'Empty';
   const activeChatId = paneActiveChatId(active);
 
+  function onPillTouchStart(e: React.TouchEvent<HTMLDivElement>): void {
+    if (e.touches.length !== 1) return;
+    const t = e.touches[0]!;
+    swipeStart.current = { x: t.clientX, y: t.clientY };
+    swipeBailed.current = false;
+    setDragX(0);
+  }
+  function onPillTouchMove(e: React.TouchEvent<HTMLDivElement>): void {
+    if (!swipeStart.current || swipeBailed.current) return;
+    if (e.touches.length !== 1) return;
+    const t = e.touches[0]!;
+    const dx = t.clientX - swipeStart.current.x;
+    const dy = t.clientY - swipeStart.current.y;
+    // Bail to scroll if vertical motion dominates before horizontal.
+    if (Math.abs(dy) > SWIPE_VERTICAL_BAIL_PX && Math.abs(dy) > Math.abs(dx)) {
+      swipeBailed.current = true;
+      setDragX(0);
+      return;
+    }
+    // Only allow leftward drag (negative). Cap visual displacement.
+    const clamped = Math.max(-SWIPE_VISUAL_CAP, Math.min(0, dx));
+    setDragX(clamped);
+  }
+  function onPillTouchEnd(): void {
+    const finalDx = dragX;
+    swipeStart.current = null;
+    if (swipeBailed.current) {
+      setDragX(0);
+      return;
+    }
+    if (finalDx <= -SWIPE_CLOSE_PX && panes.length > 1) {
+      suppressClick.current = true;
+      // Reset dragX after the close so subsequent re-renders look right.
+      setDragX(0);
+      onRemovePane(activePaneIdx);
+      return;
+    }
+    setDragX(0);
+  }
+  function onPillClick(): void {
+    if (suppressClick.current) {
+      suppressClick.current = false;
+      return;
+    }
+    setOpen(true);
+  }
+  const swipeProgress = Math.min(1, Math.abs(dragX) / SWIPE_CLOSE_PX);
+
   // Long-press mirrors ChatTabBar: synthesize a contextmenu event on the row
   // so the trailing kebab's Radix DropdownMenu opens at the touch point.
   const longPress = useLongPress(({ clientX, clientY, target }) => {
@@ -113,17 +177,39 @@ export function MobileTabSwitcher({
 
   return (
     <>
+      <div
+        className="flex-1 relative min-w-0"
+        onTouchStart={onPillTouchStart}
+        onTouchMove={onPillTouchMove}
+        onTouchEnd={onPillTouchEnd}
+        onTouchCancel={onPillTouchEnd}
+      >
+        {/* v1.10.4: red "Close" hint behind the pill. Opacity tracks the
+            swipe progress (0 at rest, 1 at the close threshold). aria-hidden
+            because the actionable affordance is the swipe, not this label. */}
+        <div
+          aria-hidden="true"
+          className="absolute inset-0 flex items-center justify-end pr-4 rounded-full bg-destructive/80 text-destructive-foreground text-xs font-medium"
+          style={{ opacity: swipeProgress, pointerEvents: 'none' }}
+        >
+          Close
+        </div>
         <button
           type="button"
-        onClick={() => setOpen(true)}
-        className="flex-1 inline-flex items-center gap-1.5 min-h-[44px] px-3 text-sm rounded-full bg-muted/40 hover:bg-muted/70 text-foreground min-w-0"
+          onClick={onPillClick}
+          className="flex-1 w-full inline-flex items-center gap-1.5 min-h-[44px] px-3 text-sm rounded-full bg-muted/40 hover:bg-muted/70 text-foreground min-w-0 relative"
           aria-label="Switch pane"
+          style={{
+            transform: `translateX(${dragX}px)`,
+            transition: dragX === 0 ? 'transform 180ms ease-out' : 'none',
+          }}
         >
           <span className="shrink-0 text-muted-foreground">{paneIcon(active?.kind ?? 'chat')}</span>
           <StatusDot chatId={activeChatId} />
           <span className="truncate flex-1 text-left">{activeLabel}</span>
           <ChevronDown size={14} className="opacity-60 shrink-0" />
         </button>
+      </div>
 
       <BottomSheet open={open} onClose={() => setOpen(false)} title="Panes">
         <ul className="px-2 py-2 space-y-1">

apps/web/src/components/Workspace.tsx

@@ -1,9 +1,10 @@
 import { useEffect, useMemo, useState } from 'react';
-import { PanelRight, MessageSquare, Terminal, Bot, X } from 'lucide-react';
+import { PanelRight, MessageSquare, Terminal, Bot, Clipboard, Plus, X } from 'lucide-react';
 import type { Chat, Project, Session, WorkspacePane } from '@/api/types';
 import { MAX_PANES, type UseWorkspacePanesResult } from '@/hooks/useWorkspacePanes';
 import type { UseSessionChatsResult } from '@/hooks/useSessionChats';
 import { useViewport } from '@/hooks/useViewport';
+import { terminalsRegistry } from '@/lib/events';
 import { ChatPane } from '@/components/panes/ChatPane';
 import { SettingsPane } from '@/components/panes/SettingsPane';
 import { TerminalPane } from '@/components/panes/TerminalPane';
@@ -226,7 +227,10 @@ export function Workspace({
                   onCloseOthers={(chatId) => closeOtherTabs(idx, chatId)}
                   onCloseToRight={(chatId) => closeTabsToRight(idx, chatId)}
                   onCloseAll={() => closeAllTabs(idx)}
-                  onNewChat={() => void createChat(idx)}
+                  onAddPane={(kind) => {
+                    if (kind === 'chat') void createChat(idx);
+                    else addSplitPane(kind);
+                  }}
                   onShowHistory={() => showLandingPage(idx)}
                   onRename={renameChat}
                   onRemovePane={panes.length > 1 ? () => removePane(idx) : undefined}
@@ -238,6 +242,47 @@ export function Workspace({
                   <span className="text-xs text-muted-foreground">
                     {terminalLabels.get(pane.id) ?? 'Terminal'}
                   </span>
+                  <DropdownMenu>
+                    <DropdownMenuTrigger asChild>
+                      <button
+                        type="button"
+                        onClick={(e) => e.stopPropagation()}
+                        className="ml-auto inline-flex items-center justify-center size-5 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:size-7"
+                        aria-label="New pane"
+                        title="New pane"
+                      >
+                        <Plus size={12} />
+                      </button>
+                    </DropdownMenuTrigger>
+                    <DropdownMenuContent align="end" className="min-w-40">
+                      <DropdownMenuItem onSelect={() => addSplitPane('chat')}>
+                        <MessageSquare size={14} /> New chat
+                      </DropdownMenuItem>
+                      <DropdownMenuItem onSelect={() => addSplitPane('terminal')}>
+                        <Terminal size={14} /> New terminal
+                      </DropdownMenuItem>
+                      <DropdownMenuItem onSelect={() => addSplitPane('agent')}>
+                        <Bot size={14} /> New agent
+                      </DropdownMenuItem>
+                    </DropdownMenuContent>
+                  </DropdownMenu>
+                  {/* v1.10.4: iOS Safari restricts navigator.clipboard.readText
+                      outside direct user gestures. A real button click IS a
+                      gesture, so this works where keystroke-driven paste may
+                      not on iOS. The action lives in TerminalPane behind the
+                      registry's paste() callback. */}
+                  <button
+                    type="button"
+                    onClick={(e) => {
+                      e.stopPropagation();
+                      terminalsRegistry.get(pane.id)?.paste();
+                    }}
+                    className="inline-flex items-center justify-center size-5 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:size-7"
+                    aria-label="Paste from clipboard"
+                    title="Paste from clipboard"
+                  >
+                    <Clipboard size={12} />
+                  </button>
                   {panes.length > 1 && (
                     <button
                       type="button"
@@ -245,7 +290,7 @@ export function Workspace({
                         e.stopPropagation();
                         removePane(idx);
                       }}
-                      className="ml-auto inline-flex items-center justify-center size-5 rounded text-muted-foreground hover:bg-muted hover:text-foreground"
+                      className="inline-flex items-center justify-center size-5 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:size-7"
                       aria-label="Close terminal pane"
                       title="Close terminal pane"
                     >
@@ -271,6 +316,7 @@ export function Workspace({
                   sessionId={sessionId}
                   paneId={pane.id}
                   label={terminalLabels.get(pane.id) ?? 'Terminal'}
+                  active={idx === activePaneIdx}
                 />
               ) : pane.kind === 'chat' && pane.chatId ? (
                 <ChatPane

apps/web/src/components/panes/ChatPane.tsx

@@ -196,6 +196,8 @@ export function ChatPane({ sessionId, chatId, projectId, agentId, onAgentChange,
           onSend={handleSend}
           onForceSend={streaming ? handleForceSend : undefined}
           onSlashCommand={handleSlashCommand}
+          chatId={chatId}
+          chatLabel={sessionChats?.find((c) => c.id === chatId)?.name ?? 'Chat'}
         />
       </div>
     </div>

apps/web/src/hooks/useSessionStream.ts

@@ -1,5 +1,7 @@
 import { useEffect, useRef, useState } from 'react';
+import { toast } from 'sonner';
 import type { Message, WsFrame } from '@/api/types';
+import { api } from '@/api/client';
 import { sessionEvents } from './sessionEvents';
 
 // session_renamed frame removed from WsFrame — it was declared but never
@@ -161,6 +163,12 @@ function applyFrame(state: State, frame: WsFrame): State {
         : state.messages;
       return { ...state, messages: next, error: frame.error };
     }
+    case 'compacted': {
+      // v1.11: side effects (refetch + toast) live in ws.onmessage; the
+      // reducer just no-ops so TS exhaustiveness is satisfied without
+      // duplicating async work inside a synchronous reducer.
+      return state;
+    }
   }
 }
 
@@ -196,6 +204,25 @@ export function useSessionStream(sessionId: string | undefined) {
       ws.onmessage = (ev) => {
         try {
           const frame = JSON.parse(typeof ev.data === 'string' ? ev.data : '') as WsFrame;
+          // v1.11: on a compaction completion, re-fetch the message list so
+          // the new summary row + the cohort of compacted_at-stamped older
+          // rows render correctly. We dispatch the fresh list as a synthetic
+          // 'snapshot' frame so the reducer's existing path handles state
+          // replacement (no need for a parallel "refetched" path).
+          // The toast is purely UX feedback; missing it would still leave
+          // the chat in a valid state.
+          if (frame.type === 'compacted') {
+            toast.success('Context compacted to free space');
+            void api.messages
+              .list(frame.session_id)
+              .then((messages) => {
+                setState((s) => applyFrame(s, { type: 'snapshot', messages }));
+              })
+              .catch((err: unknown) => {
+                console.warn('compacted refetch failed', err);
+              });
+            return;
+          }
           setState((s) => applyFrame(s, frame));
         } catch (err) {
           console.warn('bad ws frame', err);

apps/web/src/hooks/useWorkspacePanes.ts

@@ -1,6 +1,7 @@
 import { useCallback, useEffect, useRef, useState } from 'react';
 import type { DragEvent } from 'react';
 import { toast } from 'sonner';
+import { api } from '@/api/client';
 import type { WorkspacePane } from '@/api/types';
 import { setActivePaneInfo, clearActivePane } from '@/hooks/useActivePane';
 
@@ -11,8 +12,11 @@ function generateId(): string {
   return crypto.randomUUID();
 }
 
-function emptyPane(): WorkspacePane {
-  return { id: generateId(), kind: 'empty', chatIds: [], activeChatIdx: -1 };
+// v1.10.3: optional id arg lets addSplitPane lift id generation out of the
+// setPanes updater so the new pane's id can be returned synchronously to the
+// caller (needed for mobile URL state).
+function emptyPane(id: string = generateId()): WorkspacePane {
+  return { id, kind: 'empty', chatIds: [], activeChatIdx: -1 };
 }
 
 function chatPane(chatId: string): WorkspacePane {
@@ -23,8 +27,8 @@ function chatPane(chatId: string): WorkspacePane {
 // tmux window key on booterm — see apps/booterm/src/pty/manager.ts. They
 // persist in localStorage along with chat panes so a refresh resumes the
 // same tmux window via the idempotent start endpoint.
-function terminalPane(): WorkspacePane {
-  return { id: generateId(), kind: 'terminal', chatIds: [], activeChatIdx: -1 };
+function terminalPane(id: string = generateId()): WorkspacePane {
+  return { id, kind: 'terminal', chatIds: [], activeChatIdx: -1 };
 }
 
 // v1.9: settings pane factory. No chats, no state beyond identity — the
@@ -80,7 +84,11 @@ export interface UseWorkspacePanesResult {
   closeTabsToRight: (paneIdx: number, pivotChatId: string) => void;
   closeAllTabs: (paneIdx: number) => void;
   showLandingPage: (paneIdx: number) => void;
-  addSplitPane: (kind: 'chat' | 'terminal' | 'agent') => void;
+  // v1.10.3: returns the new pane's id (or null if the operation was a no-op:
+  // 'agent' kind is a toast stub, or max panes reached). Callers can use the
+  // id to update mobile URL state so the URL-sync effect doesn't fight the
+  // freshly-set activePaneIdx.
+  addSplitPane: (kind: 'chat' | 'terminal' | 'agent') => string | null;
   // Open-on-first-click, close-on-second-click. Singleton — settings panes
   // don't count toward MAX_PANES. Closing the only remaining pane (edge case)
   // falls back to an empty pane to preserve the "always one pane" invariant.
@@ -241,22 +249,29 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
     });
   }, []);
 
-  const addSplitPane = useCallback((kind: 'chat' | 'terminal' | 'agent') => {
+  const addSplitPane = useCallback((kind: 'chat' | 'terminal' | 'agent'): string | null => {
     if (kind === 'agent') {
       toast('Agent panes coming in BooCoder');
-      return;
+      return null;
     }
+    // Generate the id outside the updater so we can return it deterministically.
+    // setPanes's updater can be invoked twice in strict mode; using a fixed id
+    // ensures both invocations agree and the returned id matches what landed.
+    const newPaneId = generateId();
+    let success = false;
     setPanes((prev) => {
       // v1.9: settings panes are excluded from the MAX cap (decision c).
       if (nonSettingsCount(prev) >= MAX_PANES) {
         toast.error(`Maximum ${MAX_PANES} panes`);
         return prev;
       }
-      const newPane = kind === 'terminal' ? terminalPane() : emptyPane();
+      const newPane = kind === 'terminal' ? terminalPane(newPaneId) : emptyPane(newPaneId);
       const next = [...prev, newPane];
       setActivePaneIdx(next.length - 1);
+      success = true;
       return next;
     });
+    return success ? newPaneId : null;
   }, []);
 
   const toggleSettingsPane = useCallback(() => {
@@ -288,11 +303,19 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
         }
         return prev;
       }
+      // v1.10.8c: with per-pane tmux sessions, an unkilled session leaks until
+      // the next `tmux kill-server`. Fire-and-forget /kill on terminal removal.
+      // The endpoint is idempotent (404 on missing session) so a strict-mode
+      // double-invoke of the updater is safe.
+      const removed = prev[idx];
+      if (removed?.kind === 'terminal') {
+        api.terminals.kill(sessionId, removed.id).catch(() => { /* non-fatal */ });
+      }
       const next = prev.filter((_, i) => i !== idx);
       setActivePaneIdx((ai) => Math.min(ai, next.length - 1));
       return next;
     });
-  }, []);
+  }, [sessionId]);
 
   // Replaces a single empty default pane with a chat pane. Used by the initial
   // chat fetch to land on the most-recent open chat if no saved pane state.

apps/web/src/lib/events.ts

@@ -4,7 +4,8 @@
 //
 // Also exposes a tiny registry of currently-mounted terminal panes so the
 // MessageBubble context menu can list them. TerminalPane registers on mount,
-// unregisters on unmount.
+// unregisters on unmount. v1.10.4 adds a parallel ChatInput registry used by
+// the terminal floating menu's "Send to chat" submenu.
 
 type Listener<T> = (payload: T) => void;
 
@@ -41,9 +42,25 @@ export interface SendToTerminalPayload {
 
 export const sendToTerminal = createEvent<SendToTerminalPayload>();
 
+// v1.10.4: reverse direction. Terminal floating menu "Send to chat" emits this
+// with the target chat's chat_id; ChatInput subscribes and appends to its draft.
+export interface SendToChatPayload {
+  chat_id: string;
+  text: string;
+}
+
+export const sendToChat = createEvent<SendToChatPayload>();
+
 export interface TerminalRegistration {
   paneId: string;
   label: string;
+  // v1.10.3 kbd-shortcuts: Cmd+` needs to focus the active terminal's xterm
+  // input layer. TerminalPane binds this to term.focus().
+  focus: () => void;
+  // v1.10.4: Cmd+F opens the search bar over the active terminal. Workspace
+  // also binds a "Paste" button in the terminal pane header to paste().
+  openSearch: () => void;
+  paste: () => void;
 }
 
 const terminalRegistry = new Map<string, TerminalRegistration>();
@@ -60,8 +77,14 @@ function notifyRegistry(): void {
 }
 
 export const terminalsRegistry = {
-  register(paneId: string, label: string): () => void {
-    terminalRegistry.set(paneId, { paneId, label });
+  register(
+    paneId: string,
+    label: string,
+    focus: () => void,
+    openSearch: () => void,
+    paste: () => void,
+  ): () => void {
+    terminalRegistry.set(paneId, { paneId, label, focus, openSearch, paste });
     notifyRegistry();
     return () => {
       terminalRegistry.delete(paneId);
@@ -71,6 +94,9 @@ export const terminalsRegistry = {
   list(): TerminalRegistration[] {
     return Array.from(terminalRegistry.values());
   },
+  get(paneId: string): TerminalRegistration | undefined {
+    return terminalRegistry.get(paneId);
+  },
   subscribe(listener: Listener<void>): () => void {
     registryListeners.add(listener);
     return () => {
@@ -78,3 +104,48 @@ export const terminalsRegistry = {
     };
   },
 };
+
+// v1.10.4: parallel registry of mounted ChatInput components so the terminal
+// floating menu's "Send to chat" submenu can list open chats. Mirrors
+// terminalsRegistry exactly; same subscriber pattern.
+export interface ChatInputRegistration {
+  chatId: string;
+  label: string;
+  focus: () => void;
+}
+
+const chatInputRegistry = new Map<string, ChatInputRegistration>();
+const chatInputListeners = new Set<Listener<void>>();
+
+function notifyChatInputs(): void {
+  for (const l of chatInputListeners) {
+    try {
+      l();
+    } catch {
+      /* ignore */
+    }
+  }
+}
+
+export const chatInputsRegistry = {
+  register(chatId: string, label: string, focus: () => void): () => void {
+    chatInputRegistry.set(chatId, { chatId, label, focus });
+    notifyChatInputs();
+    return () => {
+      chatInputRegistry.delete(chatId);
+      notifyChatInputs();
+    };
+  },
+  list(): ChatInputRegistration[] {
+    return Array.from(chatInputRegistry.values());
+  },
+  get(chatId: string): ChatInputRegistration | undefined {
+    return chatInputRegistry.get(chatId);
+  },
+  subscribe(listener: Listener<void>): () => void {
+    chatInputListeners.add(listener);
+    return () => {
+      chatInputListeners.delete(listener);
+    };
+  },
+};

apps/web/src/main.tsx

@@ -1,3 +1,8 @@
+// Fonts imported as JS side-effect modules (boolab pattern, adapted for
+// Tailwind v4 + Vite asset-pipeline URL rewriting). Must precede the React
+// imports so the @font-face CSS lands before any component-tree render.
+import '@fontsource-variable/inter';
+import '@fontsource-variable/jetbrains-mono';
 import React from 'react';
 import ReactDOM from 'react-dom/client';
 import App from './App';

apps/web/src/pages/Session.tsx

@@ -10,6 +10,7 @@ import { ChevronRight, FolderTree, Menu } from 'lucide-react';
 import { api } from '@/api/client';
 import type { Project, Session as SessionType } from '@/api/types';
 import { sessionEvents } from '@/hooks/sessionEvents';
+import { terminalsRegistry } from '@/lib/events';
 import { useActivePane } from '@/hooks/useActivePane';
 import { useSidebarDrawer } from '@/hooks/useSidebarDrawer';
 import { useRightRailDrawer } from '@/hooks/useRightRailDrawer';
@@ -170,6 +171,122 @@ function SessionInner({ sessionId }: { sessionId: string }) {
     [setActivePaneIdx, isMobile, panes, navigate, location.pathname, location.search],
   );
 
+  // v1.10.3 fix: addSplitPane sets activePaneIdx, but on mobile the URL-sync
+  // effect below sees a stale ?pane= and immediately resets the index. Push
+  // the new pane's id to the URL atomically so the effect's next pass sees a
+  // matching id and is a no-op. Desktop has no URL pane state — fall through.
+  const addPaneAndSwitch = useCallback(
+    (kind: 'chat' | 'terminal' | 'agent') => {
+      const newPaneId = addSplitPane(kind);
+      if (newPaneId === null) return;
+      if (isMobile) {
+        const params = new URLSearchParams(location.search);
+        params.set('pane', newPaneId);
+        navigate(`${location.pathname}?${params.toString()}`);
+      }
+    },
+    [addSplitPane, isMobile, navigate, location.pathname, location.search],
+  );
+
+  // v1.10.3 keyboard shortcuts. Window-level keydown so they fire from
+  // anywhere in the session view. Only Cmd/Ctrl-Shift-C defers to the xterm
+  // (which has its own copy binding for that combo); everything else fires
+  // regardless of focus. Cmd-W and Cmd-T are typically reserved by the
+  // browser — preventDefault() works in most browsers but not all.
+  useEffect(() => {
+    function onKey(e: KeyboardEvent): void {
+      const mod = e.ctrlKey || e.metaKey;
+      if (!mod) return;
+      const key = e.key.toLowerCase();
+      const target = e.target;
+      const inXterm = target instanceof Element && target.closest('.xterm') !== null;
+
+      // Cmd/Ctrl + ` — focus the active terminal or jump to the most recent
+      // terminal pane and focus it. No-op if there are no terminal panes.
+      if (key === '`') {
+        e.preventDefault();
+        const activePane = panes[activePaneIdx];
+        if (activePane?.kind === 'terminal') {
+          terminalsRegistry.get(activePane.id)?.focus();
+          return;
+        }
+        let lastTermIdx = -1;
+        for (let i = panes.length - 1; i >= 0; i--) {
+          if (panes[i]?.kind === 'terminal') {
+            lastTermIdx = i;
+            break;
+          }
+        }
+        if (lastTermIdx < 0) return;
+        const target = panes[lastTermIdx];
+        switchActivePane(lastTermIdx);
+        if (target) {
+          // The terminal may have just mounted on mobile (it was return-null
+          // before the switch). Defer focus until the new render commits.
+          setTimeout(() => terminalsRegistry.get(target.id)?.focus(), 80);
+        }
+        return;
+      }
+
+      // Cmd/Ctrl + Shift + T — new terminal pane and switch to it.
+      if (key === 't' && e.shiftKey) {
+        e.preventDefault();
+        addPaneAndSwitch('terminal');
+        return;
+      }
+
+      // Cmd/Ctrl + Shift + C — new chat pane and switch to it. The xterm's
+      // own Shift-C binding is "copy selection" — defer to it when in xterm.
+      if (key === 'c' && e.shiftKey) {
+        if (inXterm) return;
+        e.preventDefault();
+        addPaneAndSwitch('chat');
+        return;
+      }
+
+      // Cmd/Ctrl + W — close the active pane.
+      if (key === 'w' && !e.shiftKey) {
+        e.preventDefault();
+        removePane(activePaneIdx);
+        return;
+      }
+
+      // v1.10.4: Cmd/Ctrl + F — when the active pane is a terminal, open the
+      // scrollback search bar. When it isn't, fall through to the browser's
+      // native find (no preventDefault, no early return).
+      if (key === 'f' && !e.shiftKey) {
+        const activePane = panes[activePaneIdx];
+        if (activePane?.kind === 'terminal') {
+          e.preventDefault();
+          terminalsRegistry.get(activePane.id)?.openSearch();
+        }
+        return;
+      }
+
+      // Cmd/Ctrl + Tab / Shift+Tab — cycle through panes.
+      if (key === 'tab') {
+        if (panes.length <= 1) return;
+        e.preventDefault();
+        const dir = e.shiftKey ? -1 : 1;
+        const next = (activePaneIdx + dir + panes.length) % panes.length;
+        switchActivePane(next);
+        return;
+      }
+
+      // Cmd/Ctrl + 1..9 — direct jump to pane N.
+      if (/^[1-9]$/.test(key)) {
+        const idx = parseInt(key, 10) - 1;
+        if (idx < panes.length) {
+          e.preventDefault();
+          switchActivePane(idx);
+        }
+        return;
+      }
+    }
+    window.addEventListener('keydown', onKey);
+    return () => window.removeEventListener('keydown', onKey);
+  }, [panes, activePaneIdx, switchActivePane, addPaneAndSwitch, removePane]);
+
   async function saveName() {
     if (!session) return;
     const trimmed = name.trim();
@@ -264,7 +381,7 @@ function SessionInner({ sessionId }: { sessionId: string }) {
                 onRenameChat={renameChat}
               />
               <NewPaneMenu
-                onAddPane={addSplitPane}
+                onAddPane={addPaneAndSwitch}
                 disabled={panes.length >= MAX_PANES}
               />
             </div>

apps/web/src/styles/globals.css

@@ -1,8 +1,7 @@
 @import "tailwindcss";
 @import "tw-animate-css";
 @import "shadcn/tailwind.css";
-@import "@fontsource-variable/inter";
-@import "@fontsource-variable/jetbrains-mono";
+/* @fontsource-variable JBM + Inter imported from main.tsx as JS modules. */
 
 /* themes-v1: 18 preset palettes. Order matches docs/themes_v1.md §1 with
    obsidian first (default). Each file declares .theme-<id> for the light
@@ -152,3 +151,96 @@
     @apply font-sans;
   }
 }
+
+/*
+ * iOS Safari auto-enlarges text in narrow viewports (anti-zoom). On its own
+ * that's fine for HTML chrome, but xterm.js measures its cell width from a
+ * hidden text-measure element — so when iOS up-sizes that element, xterm
+ * computes wider cells and the terminal ends up at fewer cols than it should.
+ * In opencode this surfaces as the small fragmented banner instead of the
+ * big chunky one (opencode picks the banner glyph set based on terminal
+ * width). 100% disables the auto-adjust and keeps boocode at the same
+ * effective cols as boolab on the same iPhone.
+ */
+html, body {
+  -webkit-text-size-adjust: 100% !important;
+  -ms-text-size-adjust: 100% !important;
+  text-size-adjust: 100% !important;
+}
+
+/* iOS Safari auto-zooms when a user taps an input/textarea whose font-size
+ * is under 16px. Pin every input/textarea/select to 16px (boolab pattern)
+ * to suppress the zoom — applies globally; specific components can override
+ * with `text-base` or inline if a smaller visual is intentional. */
+input, textarea, select {
+  font-size: 16px !important;
+}
+
+/*
+ * xterm.js overrides (boolab pattern — see /opt/boolab/frontend/src/styles/globals.css).
+ *
+ * Why these live in a global stylesheet, not in an inline <style> inside the
+ * component: an inline <style> inserted at component-mount time races the
+ * upstream @xterm/xterm/css/xterm.css that ships with the addon. We saw the
+ * right-edge stripe persist on iOS even though the override was identical to
+ * boolab's — moving the rules here so they're parsed alongside index.css
+ * eliminates that race.
+ */
+
+.xterm,
+.xterm *,
+.xterm .xterm-rows,
+.xterm .xterm-rows * {
+  font-family: 'JetBrains Mono Variable', 'JetBrains Mono', 'Fira Code', Menlo, monospace !important;
+}
+
+/* Fill the host node — xterm's only non-absolute sizing comes from the canvas,
+ * and fractional rounding would otherwise leave a phantom right-edge stripe.
+ */
+.xterm {
+  width: 100% !important;
+  height: 100% !important;
+}
+
+/* Lock cell metrics so block-element glyphs (U+2580..U+259F) tile without
+ * subpixel gaps. Any non-zero letter-spacing or line-height ≠ 1 leaves
+ * fractional space between cells that paints as a horizontal/vertical
+ * stripe through the opencode banner on iOS. Disabling ligatures
+ * (font-feature-settings + font-variant-ligatures) prevents the renderer
+ * from collapsing adjacent block chars into shaped glyphs at unpredictable
+ * widths.
+ */
+.xterm,
+.xterm .xterm-rows {
+  letter-spacing: 0 !important;
+  line-height: 1 !important;
+  font-feature-settings: "liga" 0, "calt" 0 !important;
+  font-variant-ligatures: none !important;
+}
+
+.xterm .xterm-viewport {
+  overflow-y: hidden !important;
+  scrollbar-width: none !important;
+  -ms-overflow-style: none !important;
+  /*
+   * xterm.css ships `background-color: #000` on the viewport (kept for OS X
+   * scrollbar opacity in the upstream default). FitAddon rounds cols down
+   * to integer cells, so .xterm-screen is up to `cellWidth - 1` pixels
+   * narrower than .xterm-viewport — the strip between the canvas right
+   * edge and the viewport right edge then paints viewport's #000, which
+   * differs from the theme background (#0b0f14, set on the host wrapper in
+   * TerminalPane.tsx + via Terminal options.theme.background) and shows up
+   * as a visible right-edge gap.
+   *
+   * Setting viewport's background transparent lets the host wrapper's
+   * #0b0f14 show through, hiding the sub-cell remainder. Single source of
+   * truth for the bg color: the host.
+   */
+  background-color: transparent !important;
+}
+
+.xterm .xterm-viewport::-webkit-scrollbar {
+  width: 0 !important;
+  height: 0 !important;
+  display: none !important;
+}

pnpm-lock.yaml

@@ -91,6 +91,21 @@ importers:
       '@fontsource-variable/jetbrains-mono':
         specifier: ^5.2.8
         version: 5.2.8
+      '@xterm/addon-fit':
+        specifier: 0.10.0
+        version: 0.10.0(@xterm/xterm@5.5.0)
+      '@xterm/addon-search':
+        specifier: ^0.15.0
+        version: 0.15.0(@xterm/xterm@5.5.0)
+      '@xterm/addon-web-links':
+        specifier: 0.11.0
+        version: 0.11.0(@xterm/xterm@5.5.0)
+      '@xterm/addon-webgl':
+        specifier: ^0.19.0
+        version: 0.19.0
+      '@xterm/xterm':
+        specifier: 5.5.0
+        version: 5.5.0
       class-variance-authority:
         specifier: ^0.7.1
         version: 0.7.1
@@ -136,15 +151,6 @@ importers:
       tw-animate-css:
         specifier: ^1.4.0
         version: 1.4.0
-      xterm:
-        specifier: ^5.3.0
-        version: 5.3.0
-      xterm-addon-fit:
-        specifier: ^0.8.0
-        version: 0.8.0(xterm@5.3.0)
-      xterm-addon-web-links:
-        specifier: ^0.9.0
-        version: 0.9.0(xterm@5.3.0)
     devDependencies:
       '@tailwindcss/postcss':
         specifier: ^4.3.0
@@ -1840,6 +1846,27 @@ packages:
   '@vitest/utils@3.2.4':
     resolution: {integrity: sha512-fB2V0JFrQSMsCo9HiSq3Ezpdv4iYaXRG1Sx8edX3MwxfyNn83mKiGzOcH+Fkxt4MHxr3y42fQi1oeAInqgX2QA==}
 
+  '@xterm/addon-fit@0.10.0':
+    resolution: {integrity: sha512-UFYkDm4HUahf2lnEyHvio51TNGiLK66mqP2JoATy7hRZeXaGMRDr00JiSF7m63vR5WKATF605yEggJKsw0JpMQ==}
+    peerDependencies:
+      '@xterm/xterm': ^5.0.0
+
+  '@xterm/addon-search@0.15.0':
+    resolution: {integrity: sha512-ZBZKLQ+EuKE83CqCmSSz5y1tx+aNOCUaA7dm6emgOX+8J9H1FWXZyrKfzjwzV+V14TV3xToz1goIeRhXBS5qjg==}
+    peerDependencies:
+      '@xterm/xterm': ^5.0.0
+
+  '@xterm/addon-web-links@0.11.0':
+    resolution: {integrity: sha512-nIHQ38pQI+a5kXnRaTgwqSHnX7KE6+4SVoceompgHL26unAxdfP6IPqUTSYPQgSwM56hsElfoNrrW5V7BUED/Q==}
+    peerDependencies:
+      '@xterm/xterm': ^5.0.0
+
+  '@xterm/addon-webgl@0.19.0':
+    resolution: {integrity: sha512-b3fMOsyLVuCeNJWxolACEUED0vm7qC0cy4wRvf3oURSzDTYVQiGPhTnhWZwIHdvC48Y+oLhvYXnY4XDXPoJo6A==}
+
+  '@xterm/xterm@5.5.0':
+    resolution: {integrity: sha512-hqJHYaQb5OptNunnyAnkHyM8aCjZ1MEIDTQu1iIbbTD/xops91NB5yq1ZK/dC2JDbVWtF23zUtl9JE2NqwT87A==}
+
   abstract-logging@2.0.1:
     resolution: {integrity: sha512-2BjRTZxTPvheOvGbBslFSYOUkr+SjPtOnrLP33f+VIWLzezQpZcqVg7ja3L4dBXmzzgwT+a029jRx5PCi3JuiA==}
 
@@ -3903,22 +3930,6 @@ packages:
     resolution: {integrity: sha512-LKYU1iAXJXUgAXn9URjiu+MWhyUXHsvfp7mcuYm9dSUKK0/CjtrUwFAxD82/mCWbtLsGjFIad0wIsod4zrTAEQ==}
     engines: {node: '>=0.4'}
 
-  xterm-addon-fit@0.8.0:
-    resolution: {integrity: sha512-yj3Np7XlvxxhYF/EJ7p3KHaMt6OdwQ+HDu573Vx1lRXsVxOcnVJs51RgjZOouIZOczTsskaS+CpXspK81/DLqw==}
-    deprecated: This package is now deprecated. Move to @xterm/addon-fit instead.
-    peerDependencies:
-      xterm: ^5.0.0
-
-  xterm-addon-web-links@0.9.0:
-    resolution: {integrity: sha512-LIzi4jBbPlrKMZF3ihoyqayWyTXAwGfu4yprz1aK2p71e9UKXN6RRzVONR0L+Zd+Ik5tPVI9bwp9e8fDTQh49Q==}
-    deprecated: This package is now deprecated. Move to @xterm/addon-web-links instead.
-    peerDependencies:
-      xterm: ^5.0.0
-
-  xterm@5.3.0:
-    resolution: {integrity: sha512-8QqjlekLUFTrU6x7xck1MsPzPA571K5zNqWm0M0oroYEWVOptZ0+ubQSkQ3uxIEhcIHRujJy6emDWX4A7qyFzg==}
-    deprecated: This package is now deprecated. Move to @xterm/xterm instead.
-
   y18n@5.0.8:
     resolution: {integrity: sha512-0pfFzegeDWJHJIAmTLRP2DwHjdF5s7jo9tuztdQxAhINCdvS+3nGINqPd00AphqJR/0LhANUS6/+7SCb98YOfA==}
     engines: {node: '>=10'}
@@ -5592,6 +5603,22 @@ snapshots:
       loupe: 3.2.1
       tinyrainbow: 2.0.0
 
+  '@xterm/addon-fit@0.10.0(@xterm/xterm@5.5.0)':
+    dependencies:
+      '@xterm/xterm': 5.5.0
+
+  '@xterm/addon-search@0.15.0(@xterm/xterm@5.5.0)':
+    dependencies:
+      '@xterm/xterm': 5.5.0
+
+  '@xterm/addon-web-links@0.11.0(@xterm/xterm@5.5.0)':
+    dependencies:
+      '@xterm/xterm': 5.5.0
+
+  '@xterm/addon-webgl@0.19.0': {}
+
+  '@xterm/xterm@5.5.0': {}
+
   abstract-logging@2.0.1: {}
 
   accepts@2.0.0:
@@ -7963,16 +7990,6 @@ snapshots:
 
   xtend@4.0.2: {}
 
-  xterm-addon-fit@0.8.0(xterm@5.3.0):
-    dependencies:
-      xterm: 5.3.0
-
-  xterm-addon-web-links@0.9.0(xterm@5.3.0):
-    dependencies:
-      xterm: 5.3.0
-
-  xterm@5.3.0: {}
-
   y18n@5.0.8: {}
 
   yallist@3.1.1: {}